diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,8 +1,8 @@ { - "best_metric": 0.567031216286806, - "best_model_checkpoint": "../checkpoints/pretrain_clean/sandy-star-569_exp7_custom_rassp_neims/checkpoint-224000", - "epoch": 0.9999553591357528, - "global_step": 224000, + "best_metric": 0.5744133702663434, + "best_model_checkpoint": "../checkpoints/pretrain_clean/fresh-universe-588_exp8_448/checkpoint-448000", + "epoch": 0.9999776790696636, + "global_step": 448000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, @@ -10,135415 +10,271047 @@ { "epoch": 0.0, "learning_rate": 5.000000000000001e-07, - "loss": 5.6312, + "loss": 5.6888, "step": 10 }, { "epoch": 0.0, "learning_rate": 1.0000000000000002e-06, - "loss": 4.6821, + "loss": 4.7651, "step": 20 }, { "epoch": 0.0, "learning_rate": 1.5e-06, - "loss": 3.6321, + "loss": 3.6771, "step": 30 }, { "epoch": 0.0, "learning_rate": 2.0000000000000003e-06, - "loss": 3.023, + "loss": 3.0273, "step": 40 }, { "epoch": 0.0, "learning_rate": 2.5e-06, - "loss": 2.6799, + "loss": 2.6997, "step": 50 }, { "epoch": 0.0, "learning_rate": 3e-06, - "loss": 2.4379, + "loss": 2.4346, "step": 60 }, { "epoch": 0.0, "learning_rate": 3.5000000000000004e-06, - "loss": 2.1893, + "loss": 2.1813, "step": 70 }, { "epoch": 0.0, "learning_rate": 4.000000000000001e-06, - "loss": 1.9779, + "loss": 1.9853, "step": 80 }, { "epoch": 0.0, "learning_rate": 4.5e-06, - "loss": 1.8255, + "loss": 1.861, "step": 90 }, { "epoch": 0.0, "learning_rate": 5e-06, - "loss": 1.748, + "loss": 1.7491, "step": 100 }, { "epoch": 0.0, "learning_rate": 5.500000000000001e-06, - "loss": 1.6764, + "loss": 1.694, "step": 110 }, { "epoch": 0.0, "learning_rate": 6e-06, - "loss": 1.6328, + "loss": 1.6375, "step": 120 }, { "epoch": 0.0, "learning_rate": 6.5000000000000004e-06, - "loss": 1.598, + "loss": 1.6102, "step": 130 }, { "epoch": 0.0, "learning_rate": 7.000000000000001e-06, - "loss": 1.5572, + "loss": 1.5793, "step": 140 }, { "epoch": 0.0, "learning_rate": 7.5e-06, - "loss": 1.5327, + "loss": 1.5581, "step": 150 }, { "epoch": 0.0, "learning_rate": 8.000000000000001e-06, - "loss": 1.5113, + "loss": 1.5311, "step": 160 }, { "epoch": 0.0, "learning_rate": 8.500000000000002e-06, - "loss": 1.4871, + "loss": 1.5008, "step": 170 }, { "epoch": 0.0, "learning_rate": 9e-06, - "loss": 1.4737, + "loss": 1.4804, "step": 180 }, { "epoch": 0.0, "learning_rate": 9.5e-06, - "loss": 1.4602, + "loss": 1.4589, "step": 190 }, { "epoch": 0.0, "learning_rate": 1e-05, - "loss": 1.4283, + "loss": 1.4319, "step": 200 }, { "epoch": 0.0, "learning_rate": 1.05e-05, - "loss": 1.4138, + "loss": 1.4409, "step": 210 }, { "epoch": 0.0, "learning_rate": 1.1000000000000001e-05, - "loss": 1.398, + "loss": 1.4245, "step": 220 }, { "epoch": 0.0, "learning_rate": 1.1500000000000002e-05, - "loss": 1.3849, + "loss": 1.3989, "step": 230 }, { "epoch": 0.0, "learning_rate": 1.2e-05, - "loss": 1.3664, + "loss": 1.3817, "step": 240 }, { "epoch": 0.0, "learning_rate": 1.25e-05, - "loss": 1.3479, + "loss": 1.3737, "step": 250 }, { "epoch": 0.0, "learning_rate": 1.3000000000000001e-05, - "loss": 1.3367, + "loss": 1.3517, "step": 260 }, { "epoch": 0.0, "learning_rate": 1.3500000000000001e-05, - "loss": 1.3338, + "loss": 1.3366, "step": 270 }, { "epoch": 0.0, "learning_rate": 1.4000000000000001e-05, - "loss": 1.3033, + "loss": 1.3128, "step": 280 }, { "epoch": 0.0, "learning_rate": 1.45e-05, - "loss": 1.2978, + "loss": 1.2951, "step": 290 }, { "epoch": 0.0, "learning_rate": 1.5e-05, - "loss": 1.2837, + "loss": 1.2744, "step": 300 }, { "epoch": 0.0, "learning_rate": 1.55e-05, - "loss": 1.2658, + "loss": 1.2643, "step": 310 }, { "epoch": 0.0, "learning_rate": 1.6000000000000003e-05, - "loss": 1.259, + "loss": 1.2537, "step": 320 }, { "epoch": 0.0, "learning_rate": 1.65e-05, - "loss": 1.2587, + "loss": 1.2378, "step": 330 }, { "epoch": 0.0, "learning_rate": 1.7000000000000003e-05, - "loss": 1.2363, + "loss": 1.2414, "step": 340 }, { "epoch": 0.0, "learning_rate": 1.75e-05, - "loss": 1.2299, + "loss": 1.2218, "step": 350 }, { "epoch": 0.0, "learning_rate": 1.8e-05, - "loss": 1.2127, + "loss": 1.2122, "step": 360 }, { "epoch": 0.0, "learning_rate": 1.85e-05, - "loss": 1.1884, + "loss": 1.197, "step": 370 }, { "epoch": 0.0, "learning_rate": 1.9e-05, - "loss": 1.2035, + "loss": 1.1759, "step": 380 }, { "epoch": 0.0, "learning_rate": 1.9500000000000003e-05, - "loss": 1.1833, + "loss": 1.1813, "step": 390 }, { "epoch": 0.0, "learning_rate": 2e-05, - "loss": 1.1625, + "loss": 1.1697, "step": 400 }, { "epoch": 0.0, "learning_rate": 2.05e-05, - "loss": 1.1529, + "loss": 1.1567, "step": 410 }, { "epoch": 0.0, "learning_rate": 2.1e-05, - "loss": 1.152, + "loss": 1.1488, "step": 420 }, { "epoch": 0.0, "learning_rate": 2.15e-05, - "loss": 1.1415, + "loss": 1.1366, "step": 430 }, { "epoch": 0.0, "learning_rate": 2.2000000000000003e-05, - "loss": 1.1204, + "loss": 1.1232, "step": 440 }, { "epoch": 0.0, "learning_rate": 2.25e-05, - "loss": 1.1233, + "loss": 1.1139, "step": 450 }, { "epoch": 0.0, "learning_rate": 2.3000000000000003e-05, - "loss": 1.1146, + "loss": 1.1179, "step": 460 }, { "epoch": 0.0, "learning_rate": 2.35e-05, - "loss": 1.1, + "loss": 1.1031, "step": 470 }, { "epoch": 0.0, "learning_rate": 2.4e-05, - "loss": 1.0915, + "loss": 1.0881, "step": 480 }, { "epoch": 0.0, "learning_rate": 2.45e-05, - "loss": 1.0861, + "loss": 1.0907, "step": 490 }, { "epoch": 0.0, "learning_rate": 2.5e-05, - "loss": 1.0895, + "loss": 1.0787, "step": 500 }, { "epoch": 0.0, "learning_rate": 2.5500000000000003e-05, - "loss": 1.0562, + "loss": 1.0736, "step": 510 }, { "epoch": 0.0, "learning_rate": 2.6000000000000002e-05, - "loss": 1.0528, + "loss": 1.0532, "step": 520 }, { "epoch": 0.0, "learning_rate": 2.6500000000000004e-05, - "loss": 1.0552, + "loss": 1.0548, "step": 530 }, { "epoch": 0.0, "learning_rate": 2.7000000000000002e-05, - "loss": 1.0509, + "loss": 1.0459, "step": 540 }, { "epoch": 0.0, "learning_rate": 2.7500000000000004e-05, - "loss": 1.0406, + "loss": 1.0324, "step": 550 }, { "epoch": 0.0, "learning_rate": 2.8000000000000003e-05, - "loss": 1.0405, + "loss": 1.041, "step": 560 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 2.8499999999999998e-05, - "loss": 1.0507, + "loss": 1.022, "step": 570 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 2.9e-05, - "loss": 1.0223, + "loss": 1.0183, "step": 580 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 2.95e-05, - "loss": 1.0203, + "loss": 1.0076, "step": 590 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3e-05, - "loss": 1.022, + "loss": 1.0017, "step": 600 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.05e-05, - "loss": 1.0133, + "loss": 0.9882, "step": 610 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.1e-05, - "loss": 1.011, + "loss": 0.9848, "step": 620 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.15e-05, - "loss": 0.997, + "loss": 0.9847, "step": 630 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.2000000000000005e-05, - "loss": 0.9955, + "loss": 0.9827, "step": 640 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.2500000000000004e-05, - "loss": 1.0008, + "loss": 0.9786, "step": 650 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.3e-05, - "loss": 0.9762, + "loss": 0.9701, "step": 660 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.35e-05, - "loss": 0.9747, + "loss": 0.9617, "step": 670 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.4000000000000007e-05, - "loss": 0.9655, + "loss": 0.9694, "step": 680 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.45e-05, - "loss": 0.951, + "loss": 0.9546, "step": 690 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.5e-05, - "loss": 0.9574, + "loss": 0.9528, "step": 700 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.55e-05, - "loss": 0.958, + "loss": 0.9488, "step": 710 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.6e-05, - "loss": 0.9536, + "loss": 0.9352, "step": 720 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.65e-05, - "loss": 0.9435, + "loss": 0.9258, "step": 730 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.7e-05, - "loss": 0.9277, + "loss": 0.9229, "step": 740 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.7500000000000003e-05, - "loss": 0.9369, + "loss": 0.9223, "step": 750 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.8e-05, - "loss": 0.9304, + "loss": 0.9223, "step": 760 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.85e-05, - "loss": 0.929, + "loss": 0.9165, "step": 770 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.9000000000000006e-05, - "loss": 0.9181, + "loss": 0.9234, "step": 780 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 3.9500000000000005e-05, - "loss": 0.9128, + "loss": 0.9296, "step": 790 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4e-05, - "loss": 0.9203, + "loss": 0.9076, "step": 800 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.05e-05, - "loss": 0.9045, + "loss": 0.8889, "step": 810 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.1e-05, - "loss": 0.9146, + "loss": 0.8946, "step": 820 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.15e-05, - "loss": 0.8995, + "loss": 0.897, "step": 830 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.2e-05, - "loss": 0.8941, + "loss": 0.8937, "step": 840 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.25e-05, - "loss": 0.882, + "loss": 0.8846, "step": 850 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.3e-05, - "loss": 0.8762, + "loss": 0.89, "step": 860 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.35e-05, - "loss": 0.873, + "loss": 0.8755, "step": 870 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.4000000000000006e-05, - "loss": 0.8696, + "loss": 0.8721, "step": 880 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.4500000000000004e-05, - "loss": 0.8757, + "loss": 0.8567, "step": 890 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.5e-05, - "loss": 0.8679, + "loss": 0.8606, "step": 900 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.55e-05, - "loss": 0.8856, + "loss": 0.8776, "step": 910 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.600000000000001e-05, - "loss": 0.8639, + "loss": 0.8653, "step": 920 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.6500000000000005e-05, - "loss": 0.8649, + "loss": 0.8509, "step": 930 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.7e-05, - "loss": 0.854, + "loss": 0.8564, "step": 940 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.75e-05, - "loss": 0.85, + "loss": 0.8495, "step": 950 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.8e-05, - "loss": 0.8576, + "loss": 0.8411, "step": 960 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.85e-05, - "loss": 0.851, + "loss": 0.8621, "step": 970 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.9e-05, - "loss": 0.8442, + "loss": 0.8514, "step": 980 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 4.9500000000000004e-05, - "loss": 0.8519, + "loss": 0.8504, "step": 990 }, { - "epoch": 0.01, + "epoch": 0.0, "learning_rate": 5e-05, - "loss": 0.823, + "loss": 0.8382, "step": 1000 }, { - "epoch": 0.01, - "learning_rate": 4.999549590127015e-05, - "loss": 0.8245, + "epoch": 0.0, + "learning_rate": 4.999888145679068e-05, + "loss": 0.8305, "step": 1010 }, { - "epoch": 0.01, - "learning_rate": 4.999099180254032e-05, - "loss": 0.8233, + "epoch": 0.0, + "learning_rate": 4.999776291358135e-05, + "loss": 0.8268, "step": 1020 }, { - "epoch": 0.01, - "learning_rate": 4.998648770381047e-05, - "loss": 0.8105, + "epoch": 0.0, + "learning_rate": 4.999664437037203e-05, + "loss": 0.8273, "step": 1030 }, { - "epoch": 0.01, - "learning_rate": 4.9981983605080626e-05, - "loss": 0.8243, + "epoch": 0.0, + "learning_rate": 4.99955258271627e-05, + "loss": 0.8198, "step": 1040 }, { - "epoch": 0.01, - "learning_rate": 4.997747950635078e-05, - "loss": 0.8143, + "epoch": 0.0, + "learning_rate": 4.999440728395338e-05, + "loss": 0.8178, "step": 1050 }, { - "epoch": 0.01, - "learning_rate": 4.9972975407620934e-05, - "loss": 0.8189, + "epoch": 0.0, + "learning_rate": 4.9993288740744056e-05, + "loss": 0.8122, "step": 1060 }, { - "epoch": 0.01, - "learning_rate": 4.996847130889109e-05, - "loss": 0.8096, + "epoch": 0.0, + "learning_rate": 4.9992170197534734e-05, + "loss": 0.8044, "step": 1070 }, { - "epoch": 0.01, - "learning_rate": 4.996396721016125e-05, - "loss": 0.8259, + "epoch": 0.0, + "learning_rate": 4.999105165432541e-05, + "loss": 0.8064, "step": 1080 }, { - "epoch": 0.01, - "learning_rate": 4.9959463111431406e-05, - "loss": 0.8043, + "epoch": 0.0, + "learning_rate": 4.9989933111116083e-05, + "loss": 0.7956, "step": 1090 }, { - "epoch": 0.01, - "learning_rate": 4.9954959012701564e-05, - "loss": 0.8135, + "epoch": 0.0, + "learning_rate": 4.998881456790676e-05, + "loss": 0.8042, "step": 1100 }, { - "epoch": 0.01, - "learning_rate": 4.9950454913971714e-05, - "loss": 0.8117, + "epoch": 0.0, + "learning_rate": 4.998769602469744e-05, + "loss": 0.8026, "step": 1110 }, { - "epoch": 0.01, - "learning_rate": 4.994595081524187e-05, - "loss": 0.8017, + "epoch": 0.0, + "learning_rate": 4.998657748148811e-05, + "loss": 0.8154, "step": 1120 }, { - "epoch": 0.01, - "learning_rate": 4.994144671651203e-05, - "loss": 0.7817, + "epoch": 0.0, + "learning_rate": 4.998545893827879e-05, + "loss": 0.7893, "step": 1130 }, { - "epoch": 0.01, - "learning_rate": 4.993694261778219e-05, - "loss": 0.7965, + "epoch": 0.0, + "learning_rate": 4.998434039506946e-05, + "loss": 0.7923, "step": 1140 }, { - "epoch": 0.01, - "learning_rate": 4.993243851905234e-05, - "loss": 0.799, + "epoch": 0.0, + "learning_rate": 4.998322185186014e-05, + "loss": 0.8017, "step": 1150 }, { - "epoch": 0.01, - "learning_rate": 4.9927934420322495e-05, - "loss": 0.7889, + "epoch": 0.0, + "learning_rate": 4.9982103308650815e-05, + "loss": 0.7914, "step": 1160 }, { - "epoch": 0.01, - "learning_rate": 4.992343032159265e-05, - "loss": 0.7837, + "epoch": 0.0, + "learning_rate": 4.998098476544149e-05, + "loss": 0.7769, "step": 1170 }, { - "epoch": 0.01, - "learning_rate": 4.99189262228628e-05, - "loss": 0.7745, + "epoch": 0.0, + "learning_rate": 4.997986622223217e-05, + "loss": 0.7866, "step": 1180 }, { - "epoch": 0.01, - "learning_rate": 4.991442212413297e-05, - "loss": 0.7818, + "epoch": 0.0, + "learning_rate": 4.997874767902284e-05, + "loss": 0.7825, "step": 1190 }, { - "epoch": 0.01, - "learning_rate": 4.990991802540312e-05, - "loss": 0.777, + "epoch": 0.0, + "learning_rate": 4.997762913581352e-05, + "loss": 0.7789, "step": 1200 }, { - "epoch": 0.01, - "learning_rate": 4.990541392667327e-05, - "loss": 0.7802, + "epoch": 0.0, + "learning_rate": 4.997651059260419e-05, + "loss": 0.7861, "step": 1210 }, { - "epoch": 0.01, - "learning_rate": 4.990090982794343e-05, - "loss": 0.7723, + "epoch": 0.0, + "learning_rate": 4.997539204939487e-05, + "loss": 0.7765, "step": 1220 }, { - "epoch": 0.01, - "learning_rate": 4.9896405729213584e-05, - "loss": 0.7667, + "epoch": 0.0, + "learning_rate": 4.997427350618555e-05, + "loss": 0.7806, "step": 1230 }, { - "epoch": 0.01, - "learning_rate": 4.989190163048375e-05, - "loss": 0.7629, + "epoch": 0.0, + "learning_rate": 4.997315496297622e-05, + "loss": 0.7596, "step": 1240 }, { - "epoch": 0.01, - "learning_rate": 4.98873975317539e-05, - "loss": 0.7658, + "epoch": 0.0, + "learning_rate": 4.9972036419766896e-05, + "loss": 0.7705, "step": 1250 }, { - "epoch": 0.01, - "learning_rate": 4.988289343302405e-05, - "loss": 0.7675, + "epoch": 0.0, + "learning_rate": 4.9970917876557574e-05, + "loss": 0.7708, "step": 1260 }, { - "epoch": 0.01, - "learning_rate": 4.9878389334294214e-05, - "loss": 0.7783, + "epoch": 0.0, + "learning_rate": 4.996979933334825e-05, + "loss": 0.7653, "step": 1270 }, { - "epoch": 0.01, - "learning_rate": 4.9873885235564365e-05, - "loss": 0.7725, + "epoch": 0.0, + "learning_rate": 4.996868079013893e-05, + "loss": 0.7641, "step": 1280 }, { - "epoch": 0.01, - "learning_rate": 4.986938113683452e-05, - "loss": 0.7466, + "epoch": 0.0, + "learning_rate": 4.99675622469296e-05, + "loss": 0.7543, "step": 1290 }, { - "epoch": 0.01, - "learning_rate": 4.986487703810468e-05, - "loss": 0.7584, + "epoch": 0.0, + "learning_rate": 4.996644370372028e-05, + "loss": 0.7587, "step": 1300 }, { - "epoch": 0.01, - "learning_rate": 4.986037293937483e-05, - "loss": 0.7501, + "epoch": 0.0, + "learning_rate": 4.996532516051095e-05, + "loss": 0.7625, "step": 1310 }, { - "epoch": 0.01, - "learning_rate": 4.985586884064499e-05, - "loss": 0.7441, + "epoch": 0.0, + "learning_rate": 4.996420661730163e-05, + "loss": 0.7539, "step": 1320 }, { - "epoch": 0.01, - "learning_rate": 4.9851364741915145e-05, - "loss": 0.7623, + "epoch": 0.0, + "learning_rate": 4.9963088074092306e-05, + "loss": 0.7532, "step": 1330 }, { - "epoch": 0.01, - "learning_rate": 4.98468606431853e-05, - "loss": 0.7599, + "epoch": 0.0, + "learning_rate": 4.996196953088298e-05, + "loss": 0.7535, "step": 1340 }, { - "epoch": 0.01, - "learning_rate": 4.9842356544455454e-05, - "loss": 0.7447, + "epoch": 0.0, + "learning_rate": 4.9960850987673655e-05, + "loss": 0.7416, "step": 1350 }, { - "epoch": 0.01, - "learning_rate": 4.983785244572561e-05, - "loss": 0.7466, + "epoch": 0.0, + "learning_rate": 4.995973244446433e-05, + "loss": 0.7501, "step": 1360 }, { - "epoch": 0.01, - "learning_rate": 4.983334834699577e-05, - "loss": 0.7459, + "epoch": 0.0, + "learning_rate": 4.995861390125501e-05, + "loss": 0.7513, "step": 1370 }, { - "epoch": 0.01, - "learning_rate": 4.9828844248265926e-05, - "loss": 0.7451, + "epoch": 0.0, + "learning_rate": 4.995749535804569e-05, + "loss": 0.7402, "step": 1380 }, { - "epoch": 0.01, - "learning_rate": 4.9824340149536084e-05, - "loss": 0.7386, + "epoch": 0.0, + "learning_rate": 4.995637681483636e-05, + "loss": 0.7434, "step": 1390 }, { - "epoch": 0.01, - "learning_rate": 4.9819836050806234e-05, - "loss": 0.7357, + "epoch": 0.0, + "learning_rate": 4.995525827162704e-05, + "loss": 0.7385, "step": 1400 }, { - "epoch": 0.01, - "learning_rate": 4.981533195207639e-05, - "loss": 0.7353, + "epoch": 0.0, + "learning_rate": 4.995413972841771e-05, + "loss": 0.7291, "step": 1410 }, { - "epoch": 0.01, - "learning_rate": 4.981082785334655e-05, - "loss": 0.7355, + "epoch": 0.0, + "learning_rate": 4.995302118520839e-05, + "loss": 0.7367, "step": 1420 }, { - "epoch": 0.01, - "learning_rate": 4.98063237546167e-05, - "loss": 0.7362, + "epoch": 0.0, + "learning_rate": 4.9951902641999065e-05, + "loss": 0.7483, "step": 1430 }, { - "epoch": 0.01, - "learning_rate": 4.9801819655886864e-05, - "loss": 0.7297, + "epoch": 0.0, + "learning_rate": 4.9950784098789736e-05, + "loss": 0.7208, "step": 1440 }, { - "epoch": 0.01, - "learning_rate": 4.9797315557157015e-05, - "loss": 0.7255, + "epoch": 0.0, + "learning_rate": 4.9949665555580414e-05, + "loss": 0.7322, "step": 1450 }, { - "epoch": 0.01, - "learning_rate": 4.9792811458427166e-05, - "loss": 0.7226, + "epoch": 0.0, + "learning_rate": 4.9948547012371085e-05, + "loss": 0.7256, "step": 1460 }, { - "epoch": 0.01, - "learning_rate": 4.978830735969733e-05, - "loss": 0.7212, + "epoch": 0.0, + "learning_rate": 4.994742846916176e-05, + "loss": 0.7363, "step": 1470 }, { - "epoch": 0.01, - "learning_rate": 4.978380326096748e-05, - "loss": 0.7315, + "epoch": 0.0, + "learning_rate": 4.994630992595244e-05, + "loss": 0.7417, "step": 1480 }, { - "epoch": 0.01, - "learning_rate": 4.977929916223764e-05, - "loss": 0.7288, + "epoch": 0.0, + "learning_rate": 4.994519138274312e-05, + "loss": 0.7225, "step": 1490 }, { - "epoch": 0.01, - "learning_rate": 4.9774795063507796e-05, - "loss": 0.7242, + "epoch": 0.0, + "learning_rate": 4.99440728395338e-05, + "loss": 0.7311, "step": 1500 }, { - "epoch": 0.01, - "learning_rate": 4.9770290964777946e-05, - "loss": 0.7262, + "epoch": 0.0, + "learning_rate": 4.994295429632447e-05, + "loss": 0.7173, "step": 1510 }, { - "epoch": 0.01, - "learning_rate": 4.976578686604811e-05, - "loss": 0.7144, + "epoch": 0.0, + "learning_rate": 4.9941835753115146e-05, + "loss": 0.7196, "step": 1520 }, { - "epoch": 0.01, - "learning_rate": 4.976128276731826e-05, - "loss": 0.7137, + "epoch": 0.0, + "learning_rate": 4.994071720990582e-05, + "loss": 0.7104, "step": 1530 }, { - "epoch": 0.01, - "learning_rate": 4.975677866858842e-05, - "loss": 0.7135, + "epoch": 0.0, + "learning_rate": 4.9939598666696495e-05, + "loss": 0.717, "step": 1540 }, { - "epoch": 0.01, - "learning_rate": 4.9752274569858576e-05, - "loss": 0.7088, + "epoch": 0.0, + "learning_rate": 4.993848012348717e-05, + "loss": 0.7036, "step": 1550 }, { - "epoch": 0.01, - "learning_rate": 4.974777047112873e-05, - "loss": 0.7179, + "epoch": 0.0, + "learning_rate": 4.9937361580277844e-05, + "loss": 0.7181, "step": 1560 }, { - "epoch": 0.01, - "learning_rate": 4.9743266372398885e-05, - "loss": 0.7158, + "epoch": 0.0, + "learning_rate": 4.993624303706852e-05, + "loss": 0.7119, "step": 1570 }, { - "epoch": 0.01, - "learning_rate": 4.973876227366904e-05, - "loss": 0.7069, + "epoch": 0.0, + "learning_rate": 4.99351244938592e-05, + "loss": 0.7155, "step": 1580 }, { - "epoch": 0.01, - "learning_rate": 4.97342581749392e-05, - "loss": 0.7045, + "epoch": 0.0, + "learning_rate": 4.993400595064988e-05, + "loss": 0.7184, "step": 1590 }, { - "epoch": 0.01, - "learning_rate": 4.972975407620935e-05, - "loss": 0.7086, + "epoch": 0.0, + "learning_rate": 4.9932887407440556e-05, + "loss": 0.716, "step": 1600 }, { - "epoch": 0.01, - "learning_rate": 4.972524997747951e-05, - "loss": 0.7045, + "epoch": 0.0, + "learning_rate": 4.993176886423123e-05, + "loss": 0.6994, "step": 1610 }, { - "epoch": 0.01, - "learning_rate": 4.9720745878749665e-05, - "loss": 0.6964, + "epoch": 0.0, + "learning_rate": 4.9930650321021905e-05, + "loss": 0.7175, "step": 1620 }, { - "epoch": 0.01, - "learning_rate": 4.9716241780019816e-05, - "loss": 0.6968, + "epoch": 0.0, + "learning_rate": 4.9929531777812576e-05, + "loss": 0.7219, "step": 1630 }, { - "epoch": 0.01, - "learning_rate": 4.971173768128998e-05, - "loss": 0.7022, + "epoch": 0.0, + "learning_rate": 4.9928413234603254e-05, + "loss": 0.6999, "step": 1640 }, { - "epoch": 0.01, - "learning_rate": 4.970723358256013e-05, - "loss": 0.7158, + "epoch": 0.0, + "learning_rate": 4.992729469139393e-05, + "loss": 0.7104, "step": 1650 }, { - "epoch": 0.01, - "learning_rate": 4.970272948383029e-05, - "loss": 0.7046, + "epoch": 0.0, + "learning_rate": 4.99261761481846e-05, + "loss": 0.6954, "step": 1660 }, { - "epoch": 0.01, - "learning_rate": 4.9698225385100446e-05, - "loss": 0.7001, + "epoch": 0.0, + "learning_rate": 4.992505760497528e-05, + "loss": 0.6909, "step": 1670 }, { - "epoch": 0.01, - "learning_rate": 4.96937212863706e-05, - "loss": 0.6951, + "epoch": 0.0, + "learning_rate": 4.992393906176596e-05, + "loss": 0.7053, "step": 1680 }, { - "epoch": 0.02, - "learning_rate": 4.9689217187640754e-05, - "loss": 0.687, + "epoch": 0.0, + "learning_rate": 4.992282051855664e-05, + "loss": 0.6992, "step": 1690 }, { - "epoch": 0.02, - "learning_rate": 4.968471308891091e-05, - "loss": 0.692, + "epoch": 0.0, + "learning_rate": 4.9921701975347315e-05, + "loss": 0.6928, "step": 1700 }, { - "epoch": 0.02, - "learning_rate": 4.968020899018106e-05, - "loss": 0.7096, + "epoch": 0.0, + "learning_rate": 4.9920583432137986e-05, + "loss": 0.6927, "step": 1710 }, { - "epoch": 0.02, - "learning_rate": 4.967570489145123e-05, - "loss": 0.6935, + "epoch": 0.0, + "learning_rate": 4.9919464888928664e-05, + "loss": 0.69, "step": 1720 }, { - "epoch": 0.02, - "learning_rate": 4.967120079272138e-05, - "loss": 0.6947, + "epoch": 0.0, + "learning_rate": 4.9918346345719335e-05, + "loss": 0.6922, "step": 1730 }, { - "epoch": 0.02, - "learning_rate": 4.9666696693991535e-05, - "loss": 0.6895, + "epoch": 0.0, + "learning_rate": 4.991722780251001e-05, + "loss": 0.6906, "step": 1740 }, { - "epoch": 0.02, - "learning_rate": 4.966219259526169e-05, - "loss": 0.6882, + "epoch": 0.0, + "learning_rate": 4.991610925930069e-05, + "loss": 0.6911, "step": 1750 }, { - "epoch": 0.02, - "learning_rate": 4.965768849653184e-05, - "loss": 0.6756, + "epoch": 0.0, + "learning_rate": 4.991499071609136e-05, + "loss": 0.6872, "step": 1760 }, { - "epoch": 0.02, - "learning_rate": 4.9653184397802e-05, - "loss": 0.6963, + "epoch": 0.0, + "learning_rate": 4.991387217288204e-05, + "loss": 0.688, "step": 1770 }, { - "epoch": 0.02, - "learning_rate": 4.964868029907216e-05, - "loss": 0.6819, + "epoch": 0.0, + "learning_rate": 4.991275362967272e-05, + "loss": 0.6892, "step": 1780 }, { - "epoch": 0.02, - "learning_rate": 4.9644176200342316e-05, - "loss": 0.6813, + "epoch": 0.0, + "learning_rate": 4.9911635086463396e-05, + "loss": 0.6933, "step": 1790 }, { - "epoch": 0.02, - "learning_rate": 4.963967210161247e-05, - "loss": 0.6769, + "epoch": 0.0, + "learning_rate": 4.991051654325407e-05, + "loss": 0.6898, "step": 1800 }, { - "epoch": 0.02, - "learning_rate": 4.9635168002882624e-05, - "loss": 0.6751, + "epoch": 0.0, + "learning_rate": 4.9909398000044745e-05, + "loss": 0.6807, "step": 1810 }, { - "epoch": 0.02, - "learning_rate": 4.963066390415278e-05, - "loss": 0.6791, + "epoch": 0.0, + "learning_rate": 4.990827945683542e-05, + "loss": 0.6811, "step": 1820 }, { - "epoch": 0.02, - "learning_rate": 4.962615980542294e-05, - "loss": 0.6782, + "epoch": 0.0, + "learning_rate": 4.9907160913626094e-05, + "loss": 0.6745, "step": 1830 }, { - "epoch": 0.02, - "learning_rate": 4.9621655706693096e-05, - "loss": 0.6866, + "epoch": 0.0, + "learning_rate": 4.990604237041677e-05, + "loss": 0.6792, "step": 1840 }, { - "epoch": 0.02, - "learning_rate": 4.961715160796325e-05, - "loss": 0.6788, + "epoch": 0.0, + "learning_rate": 4.990492382720744e-05, + "loss": 0.6846, "step": 1850 }, { - "epoch": 0.02, - "learning_rate": 4.9612647509233404e-05, - "loss": 0.6751, + "epoch": 0.0, + "learning_rate": 4.990380528399812e-05, + "loss": 0.6791, "step": 1860 }, { - "epoch": 0.02, - "learning_rate": 4.960814341050356e-05, - "loss": 0.6736, + "epoch": 0.0, + "learning_rate": 4.99026867407888e-05, + "loss": 0.679, "step": 1870 }, { - "epoch": 0.02, - "learning_rate": 4.960363931177371e-05, - "loss": 0.6721, + "epoch": 0.0, + "learning_rate": 4.990156819757947e-05, + "loss": 0.6759, "step": 1880 }, { - "epoch": 0.02, - "learning_rate": 4.959913521304388e-05, - "loss": 0.6709, + "epoch": 0.0, + "learning_rate": 4.9900449654370155e-05, + "loss": 0.6682, "step": 1890 }, { - "epoch": 0.02, - "learning_rate": 4.959463111431403e-05, - "loss": 0.6756, + "epoch": 0.0, + "learning_rate": 4.9899331111160826e-05, + "loss": 0.6784, "step": 1900 }, { - "epoch": 0.02, - "learning_rate": 4.959012701558418e-05, - "loss": 0.6746, + "epoch": 0.0, + "learning_rate": 4.9898212567951504e-05, + "loss": 0.6828, "step": 1910 }, { - "epoch": 0.02, - "learning_rate": 4.958562291685434e-05, - "loss": 0.6728, + "epoch": 0.0, + "learning_rate": 4.989709402474218e-05, + "loss": 0.6887, "step": 1920 }, { - "epoch": 0.02, - "learning_rate": 4.958111881812449e-05, - "loss": 0.6707, + "epoch": 0.0, + "learning_rate": 4.989597548153285e-05, + "loss": 0.6762, "step": 1930 }, { - "epoch": 0.02, - "learning_rate": 4.957661471939465e-05, - "loss": 0.671, + "epoch": 0.0, + "learning_rate": 4.989485693832353e-05, + "loss": 0.6702, "step": 1940 }, { - "epoch": 0.02, - "learning_rate": 4.957211062066481e-05, - "loss": 0.666, + "epoch": 0.0, + "learning_rate": 4.98937383951142e-05, + "loss": 0.6733, "step": 1950 }, { - "epoch": 0.02, - "learning_rate": 4.956760652193496e-05, - "loss": 0.6593, + "epoch": 0.0, + "learning_rate": 4.989261985190488e-05, + "loss": 0.6778, "step": 1960 }, { - "epoch": 0.02, - "learning_rate": 4.956310242320512e-05, - "loss": 0.6597, + "epoch": 0.0, + "learning_rate": 4.989150130869556e-05, + "loss": 0.6702, "step": 1970 }, { - "epoch": 0.02, - "learning_rate": 4.9558598324475274e-05, - "loss": 0.661, + "epoch": 0.0, + "learning_rate": 4.989038276548623e-05, + "loss": 0.6782, "step": 1980 }, { - "epoch": 0.02, - "learning_rate": 4.955409422574543e-05, - "loss": 0.6622, + "epoch": 0.0, + "learning_rate": 4.988926422227691e-05, + "loss": 0.655, "step": 1990 }, { - "epoch": 0.02, - "learning_rate": 4.954959012701559e-05, - "loss": 0.6585, + "epoch": 0.0, + "learning_rate": 4.9888145679067585e-05, + "loss": 0.6633, "step": 2000 }, { - "epoch": 0.02, - "learning_rate": 4.954508602828574e-05, - "loss": 0.657, + "epoch": 0.0, + "learning_rate": 4.988702713585826e-05, + "loss": 0.6632, "step": 2010 }, { - "epoch": 0.02, - "learning_rate": 4.95405819295559e-05, - "loss": 0.6502, + "epoch": 0.0, + "learning_rate": 4.988590859264894e-05, + "loss": 0.6717, "step": 2020 }, { - "epoch": 0.02, - "learning_rate": 4.9536077830826055e-05, - "loss": 0.6568, + "epoch": 0.0, + "learning_rate": 4.988479004943961e-05, + "loss": 0.6664, "step": 2030 }, { - "epoch": 0.02, - "learning_rate": 4.953157373209621e-05, - "loss": 0.6657, + "epoch": 0.0, + "learning_rate": 4.988367150623029e-05, + "loss": 0.6597, "step": 2040 }, { - "epoch": 0.02, - "learning_rate": 4.952706963336636e-05, - "loss": 0.6577, + "epoch": 0.0, + "learning_rate": 4.988255296302096e-05, + "loss": 0.6505, "step": 2050 }, { - "epoch": 0.02, - "learning_rate": 4.952256553463652e-05, - "loss": 0.6433, + "epoch": 0.0, + "learning_rate": 4.988143441981164e-05, + "loss": 0.6567, "step": 2060 }, { - "epoch": 0.02, - "learning_rate": 4.951806143590668e-05, - "loss": 0.6408, + "epoch": 0.0, + "learning_rate": 4.988031587660232e-05, + "loss": 0.6642, "step": 2070 }, { - "epoch": 0.02, - "learning_rate": 4.9513557337176835e-05, - "loss": 0.645, + "epoch": 0.0, + "learning_rate": 4.987919733339299e-05, + "loss": 0.6505, "step": 2080 }, { - "epoch": 0.02, - "learning_rate": 4.950905323844699e-05, - "loss": 0.6593, + "epoch": 0.0, + "learning_rate": 4.9878078790183666e-05, + "loss": 0.6622, "step": 2090 }, { - "epoch": 0.02, - "learning_rate": 4.9504549139717144e-05, - "loss": 0.6411, + "epoch": 0.0, + "learning_rate": 4.9876960246974344e-05, + "loss": 0.6669, "step": 2100 }, { - "epoch": 0.02, - "learning_rate": 4.95000450409873e-05, - "loss": 0.6464, + "epoch": 0.0, + "learning_rate": 4.987584170376502e-05, + "loss": 0.655, "step": 2110 }, { - "epoch": 0.02, - "learning_rate": 4.949554094225746e-05, - "loss": 0.6513, + "epoch": 0.0, + "learning_rate": 4.987472316055569e-05, + "loss": 0.6638, "step": 2120 }, { - "epoch": 0.02, - "learning_rate": 4.949103684352761e-05, - "loss": 0.6556, + "epoch": 0.0, + "learning_rate": 4.987360461734637e-05, + "loss": 0.6475, "step": 2130 }, { - "epoch": 0.02, - "learning_rate": 4.948653274479777e-05, - "loss": 0.6494, + "epoch": 0.0, + "learning_rate": 4.987248607413705e-05, + "loss": 0.6668, "step": 2140 }, { - "epoch": 0.02, - "learning_rate": 4.9482028646067924e-05, - "loss": 0.6472, + "epoch": 0.0, + "learning_rate": 4.987136753092772e-05, + "loss": 0.6541, "step": 2150 }, { - "epoch": 0.02, - "learning_rate": 4.9477524547338075e-05, - "loss": 0.6541, + "epoch": 0.0, + "learning_rate": 4.98702489877184e-05, + "loss": 0.6484, "step": 2160 }, { - "epoch": 0.02, - "learning_rate": 4.947302044860824e-05, - "loss": 0.6434, + "epoch": 0.0, + "learning_rate": 4.986913044450907e-05, + "loss": 0.6447, "step": 2170 }, { - "epoch": 0.02, - "learning_rate": 4.946851634987839e-05, - "loss": 0.6395, + "epoch": 0.0, + "learning_rate": 4.986801190129975e-05, + "loss": 0.6499, "step": 2180 }, { - "epoch": 0.02, - "learning_rate": 4.946401225114855e-05, - "loss": 0.6425, + "epoch": 0.0, + "learning_rate": 4.9866893358090425e-05, + "loss": 0.6442, "step": 2190 }, { - "epoch": 0.02, - "learning_rate": 4.9459508152418705e-05, - "loss": 0.6401, + "epoch": 0.0, + "learning_rate": 4.98657748148811e-05, + "loss": 0.6443, "step": 2200 }, { - "epoch": 0.02, - "learning_rate": 4.9455004053688856e-05, - "loss": 0.6413, + "epoch": 0.0, + "learning_rate": 4.986465627167178e-05, + "loss": 0.6505, "step": 2210 }, { - "epoch": 0.02, - "learning_rate": 4.945049995495902e-05, - "loss": 0.6343, + "epoch": 0.0, + "learning_rate": 4.986353772846245e-05, + "loss": 0.6482, "step": 2220 }, { - "epoch": 0.02, - "learning_rate": 4.944599585622917e-05, - "loss": 0.6376, + "epoch": 0.0, + "learning_rate": 4.986241918525313e-05, + "loss": 0.6324, "step": 2230 }, { - "epoch": 0.02, - "learning_rate": 4.944149175749933e-05, - "loss": 0.6449, + "epoch": 0.0, + "learning_rate": 4.986130064204381e-05, + "loss": 0.6464, "step": 2240 }, { - "epoch": 0.02, - "learning_rate": 4.9436987658769486e-05, - "loss": 0.6488, + "epoch": 0.01, + "learning_rate": 4.986018209883448e-05, + "loss": 0.6398, "step": 2250 }, { - "epoch": 0.02, - "learning_rate": 4.9432483560039636e-05, - "loss": 0.6449, + "epoch": 0.01, + "learning_rate": 4.985906355562516e-05, + "loss": 0.6488, "step": 2260 }, { - "epoch": 0.02, - "learning_rate": 4.9427979461309794e-05, - "loss": 0.6362, + "epoch": 0.01, + "learning_rate": 4.985794501241583e-05, + "loss": 0.6463, "step": 2270 }, { - "epoch": 0.02, - "learning_rate": 4.942347536257995e-05, - "loss": 0.6282, + "epoch": 0.01, + "learning_rate": 4.9856826469206506e-05, + "loss": 0.6363, "step": 2280 }, { - "epoch": 0.02, - "learning_rate": 4.941897126385011e-05, - "loss": 0.6325, + "epoch": 0.01, + "learning_rate": 4.9855707925997184e-05, + "loss": 0.6403, "step": 2290 }, { - "epoch": 0.02, - "learning_rate": 4.941446716512026e-05, - "loss": 0.6248, + "epoch": 0.01, + "learning_rate": 4.9854589382787855e-05, + "loss": 0.6369, "step": 2300 }, { - "epoch": 0.02, - "learning_rate": 4.940996306639042e-05, - "loss": 0.6321, + "epoch": 0.01, + "learning_rate": 4.985347083957854e-05, + "loss": 0.6385, "step": 2310 }, { - "epoch": 0.02, - "learning_rate": 4.9405458967660575e-05, - "loss": 0.6337, + "epoch": 0.01, + "learning_rate": 4.985235229636921e-05, + "loss": 0.6361, "step": 2320 }, { - "epoch": 0.02, - "learning_rate": 4.9400954868930725e-05, - "loss": 0.6247, + "epoch": 0.01, + "learning_rate": 4.985123375315989e-05, + "loss": 0.634, "step": 2330 }, { - "epoch": 0.02, - "learning_rate": 4.939645077020088e-05, - "loss": 0.6413, + "epoch": 0.01, + "learning_rate": 4.985011520995057e-05, + "loss": 0.6391, "step": 2340 }, { - "epoch": 0.02, - "learning_rate": 4.939194667147104e-05, - "loss": 0.6293, + "epoch": 0.01, + "learning_rate": 4.984899666674124e-05, + "loss": 0.6315, "step": 2350 }, { - "epoch": 0.02, - "learning_rate": 4.93874425727412e-05, - "loss": 0.6231, + "epoch": 0.01, + "learning_rate": 4.9847878123531916e-05, + "loss": 0.6299, "step": 2360 }, { - "epoch": 0.02, - "learning_rate": 4.9382938474011355e-05, - "loss": 0.6164, + "epoch": 0.01, + "learning_rate": 4.984675958032259e-05, + "loss": 0.6319, "step": 2370 }, { - "epoch": 0.02, - "learning_rate": 4.9378434375281506e-05, - "loss": 0.624, + "epoch": 0.01, + "learning_rate": 4.9845641037113265e-05, + "loss": 0.6267, "step": 2380 }, { - "epoch": 0.02, - "learning_rate": 4.9373930276551663e-05, - "loss": 0.6209, + "epoch": 0.01, + "learning_rate": 4.984452249390394e-05, + "loss": 0.6261, "step": 2390 }, { - "epoch": 0.02, - "learning_rate": 4.936942617782182e-05, - "loss": 0.6242, + "epoch": 0.01, + "learning_rate": 4.9843403950694614e-05, + "loss": 0.6264, "step": 2400 }, { - "epoch": 0.02, - "learning_rate": 4.936492207909197e-05, - "loss": 0.6156, + "epoch": 0.01, + "learning_rate": 4.984228540748529e-05, + "loss": 0.6383, "step": 2410 }, { - "epoch": 0.02, - "learning_rate": 4.9360417980362136e-05, - "loss": 0.6301, + "epoch": 0.01, + "learning_rate": 4.984116686427597e-05, + "loss": 0.6349, "step": 2420 }, { - "epoch": 0.02, - "learning_rate": 4.9355913881632287e-05, - "loss": 0.6267, + "epoch": 0.01, + "learning_rate": 4.984004832106665e-05, + "loss": 0.6239, "step": 2430 }, { - "epoch": 0.02, - "learning_rate": 4.9351409782902444e-05, - "loss": 0.6251, + "epoch": 0.01, + "learning_rate": 4.983892977785732e-05, + "loss": 0.6335, "step": 2440 }, { - "epoch": 0.02, - "learning_rate": 4.93469056841726e-05, - "loss": 0.6307, + "epoch": 0.01, + "learning_rate": 4.9837811234648e-05, + "loss": 0.6181, "step": 2450 }, { - "epoch": 0.02, - "learning_rate": 4.934240158544275e-05, - "loss": 0.6141, + "epoch": 0.01, + "learning_rate": 4.9836692691438675e-05, + "loss": 0.6176, "step": 2460 }, { - "epoch": 0.02, - "learning_rate": 4.933789748671291e-05, - "loss": 0.6151, + "epoch": 0.01, + "learning_rate": 4.9835574148229346e-05, + "loss": 0.6294, "step": 2470 }, { - "epoch": 0.02, - "learning_rate": 4.933339338798307e-05, - "loss": 0.6142, + "epoch": 0.01, + "learning_rate": 4.9834455605020024e-05, + "loss": 0.6297, "step": 2480 }, { - "epoch": 0.02, - "learning_rate": 4.9328889289253225e-05, - "loss": 0.6157, + "epoch": 0.01, + "learning_rate": 4.9833337061810695e-05, + "loss": 0.6307, "step": 2490 }, { - "epoch": 0.02, - "learning_rate": 4.932438519052338e-05, - "loss": 0.6208, + "epoch": 0.01, + "learning_rate": 4.983221851860137e-05, + "loss": 0.635, "step": 2500 }, { - "epoch": 0.02, - "learning_rate": 4.931988109179353e-05, - "loss": 0.6123, + "epoch": 0.01, + "learning_rate": 4.983109997539205e-05, + "loss": 0.6292, "step": 2510 }, { - "epoch": 0.02, - "learning_rate": 4.931537699306369e-05, - "loss": 0.6286, + "epoch": 0.01, + "learning_rate": 4.982998143218273e-05, + "loss": 0.624, "step": 2520 }, { - "epoch": 0.02, - "learning_rate": 4.931087289433385e-05, - "loss": 0.6165, + "epoch": 0.01, + "learning_rate": 4.982886288897341e-05, + "loss": 0.6219, "step": 2530 }, { - "epoch": 0.02, - "learning_rate": 4.9306368795604005e-05, - "loss": 0.6264, + "epoch": 0.01, + "learning_rate": 4.982774434576408e-05, + "loss": 0.621, "step": 2540 }, { - "epoch": 0.02, - "learning_rate": 4.9301864696874156e-05, - "loss": 0.6146, + "epoch": 0.01, + "learning_rate": 4.9826625802554756e-05, + "loss": 0.6173, "step": 2550 }, { - "epoch": 0.02, - "learning_rate": 4.9297360598144314e-05, - "loss": 0.6107, + "epoch": 0.01, + "learning_rate": 4.9825507259345434e-05, + "loss": 0.6313, "step": 2560 }, { - "epoch": 0.02, - "learning_rate": 4.929285649941447e-05, - "loss": 0.6246, + "epoch": 0.01, + "learning_rate": 4.9824388716136105e-05, + "loss": 0.6215, "step": 2570 }, { - "epoch": 0.02, - "learning_rate": 4.928835240068462e-05, - "loss": 0.6186, + "epoch": 0.01, + "learning_rate": 4.982327017292678e-05, + "loss": 0.6139, "step": 2580 }, { - "epoch": 0.02, - "learning_rate": 4.928384830195478e-05, - "loss": 0.6052, + "epoch": 0.01, + "learning_rate": 4.9822151629717454e-05, + "loss": 0.6176, "step": 2590 }, { - "epoch": 0.02, - "learning_rate": 4.927934420322494e-05, - "loss": 0.6133, + "epoch": 0.01, + "learning_rate": 4.982103308650813e-05, + "loss": 0.6154, "step": 2600 }, { - "epoch": 0.02, - "learning_rate": 4.927484010449509e-05, - "loss": 0.6051, + "epoch": 0.01, + "learning_rate": 4.981991454329881e-05, + "loss": 0.6142, "step": 2610 }, { - "epoch": 0.02, - "learning_rate": 4.927033600576525e-05, - "loss": 0.6103, + "epoch": 0.01, + "learning_rate": 4.981879600008949e-05, + "loss": 0.6194, "step": 2620 }, { - "epoch": 0.02, - "learning_rate": 4.92658319070354e-05, - "loss": 0.6126, + "epoch": 0.01, + "learning_rate": 4.9817677456880166e-05, + "loss": 0.615, "step": 2630 }, { - "epoch": 0.02, - "learning_rate": 4.926132780830556e-05, - "loss": 0.6001, + "epoch": 0.01, + "learning_rate": 4.981655891367084e-05, + "loss": 0.6151, "step": 2640 }, { - "epoch": 0.02, - "learning_rate": 4.925682370957572e-05, - "loss": 0.6016, + "epoch": 0.01, + "learning_rate": 4.9815440370461515e-05, + "loss": 0.6113, "step": 2650 }, { - "epoch": 0.02, - "learning_rate": 4.925231961084587e-05, - "loss": 0.5969, + "epoch": 0.01, + "learning_rate": 4.981432182725219e-05, + "loss": 0.6127, "step": 2660 }, { - "epoch": 0.02, - "learning_rate": 4.924781551211603e-05, - "loss": 0.6054, + "epoch": 0.01, + "learning_rate": 4.9813203284042864e-05, + "loss": 0.6136, "step": 2670 }, { - "epoch": 0.02, - "learning_rate": 4.924331141338618e-05, - "loss": 0.607, + "epoch": 0.01, + "learning_rate": 4.981208474083354e-05, + "loss": 0.6204, "step": 2680 }, { - "epoch": 0.02, - "learning_rate": 4.923880731465634e-05, - "loss": 0.6077, + "epoch": 0.01, + "learning_rate": 4.981096619762421e-05, + "loss": 0.6218, "step": 2690 }, { - "epoch": 0.02, - "learning_rate": 4.92343032159265e-05, - "loss": 0.6062, + "epoch": 0.01, + "learning_rate": 4.980984765441489e-05, + "loss": 0.6096, "step": 2700 }, { - "epoch": 0.02, - "learning_rate": 4.922979911719665e-05, - "loss": 0.614, + "epoch": 0.01, + "learning_rate": 4.980872911120557e-05, + "loss": 0.6057, "step": 2710 }, { - "epoch": 0.02, - "learning_rate": 4.9225295018466806e-05, - "loss": 0.6075, + "epoch": 0.01, + "learning_rate": 4.980761056799625e-05, + "loss": 0.6004, "step": 2720 }, { - "epoch": 0.02, - "learning_rate": 4.9220790919736964e-05, - "loss": 0.5958, + "epoch": 0.01, + "learning_rate": 4.9806492024786925e-05, + "loss": 0.6092, "step": 2730 }, { - "epoch": 0.02, - "learning_rate": 4.921628682100712e-05, - "loss": 0.6007, + "epoch": 0.01, + "learning_rate": 4.9805373481577596e-05, + "loss": 0.6133, "step": 2740 }, { - "epoch": 0.02, - "learning_rate": 4.921178272227727e-05, - "loss": 0.6013, + "epoch": 0.01, + "learning_rate": 4.9804254938368274e-05, + "loss": 0.602, "step": 2750 }, { - "epoch": 0.02, - "learning_rate": 4.920727862354743e-05, - "loss": 0.6001, + "epoch": 0.01, + "learning_rate": 4.9803136395158945e-05, + "loss": 0.6142, "step": 2760 }, { - "epoch": 0.02, - "learning_rate": 4.920277452481759e-05, - "loss": 0.596, + "epoch": 0.01, + "learning_rate": 4.980201785194962e-05, + "loss": 0.6113, "step": 2770 }, { - "epoch": 0.02, - "learning_rate": 4.9198270426087745e-05, - "loss": 0.5937, + "epoch": 0.01, + "learning_rate": 4.98008993087403e-05, + "loss": 0.5999, "step": 2780 }, { - "epoch": 0.02, - "learning_rate": 4.9193766327357895e-05, - "loss": 0.5946, + "epoch": 0.01, + "learning_rate": 4.979978076553097e-05, + "loss": 0.6043, "step": 2790 }, { - "epoch": 0.02, - "learning_rate": 4.918926222862805e-05, - "loss": 0.5972, + "epoch": 0.01, + "learning_rate": 4.979866222232165e-05, + "loss": 0.605, "step": 2800 }, { - "epoch": 0.03, - "learning_rate": 4.918475812989821e-05, - "loss": 0.5965, + "epoch": 0.01, + "learning_rate": 4.979754367911232e-05, + "loss": 0.6095, "step": 2810 }, { - "epoch": 0.03, - "learning_rate": 4.918025403116837e-05, - "loss": 0.5984, + "epoch": 0.01, + "learning_rate": 4.9796425135903e-05, + "loss": 0.6107, "step": 2820 }, { - "epoch": 0.03, - "learning_rate": 4.917574993243852e-05, - "loss": 0.6022, + "epoch": 0.01, + "learning_rate": 4.979530659269368e-05, + "loss": 0.6, "step": 2830 }, { - "epoch": 0.03, - "learning_rate": 4.9171245833708676e-05, - "loss": 0.598, + "epoch": 0.01, + "learning_rate": 4.9794188049484355e-05, + "loss": 0.5943, "step": 2840 }, { - "epoch": 0.03, - "learning_rate": 4.9166741734978834e-05, - "loss": 0.5907, + "epoch": 0.01, + "learning_rate": 4.979306950627503e-05, + "loss": 0.5995, "step": 2850 }, { - "epoch": 0.03, - "learning_rate": 4.9162237636248984e-05, - "loss": 0.587, + "epoch": 0.01, + "learning_rate": 4.9791950963065704e-05, + "loss": 0.6054, "step": 2860 }, { - "epoch": 0.03, - "learning_rate": 4.915773353751915e-05, - "loss": 0.593, + "epoch": 0.01, + "learning_rate": 4.979083241985638e-05, + "loss": 0.6061, "step": 2870 }, { - "epoch": 0.03, - "learning_rate": 4.91532294387893e-05, - "loss": 0.5956, + "epoch": 0.01, + "learning_rate": 4.978971387664706e-05, + "loss": 0.6042, "step": 2880 }, { - "epoch": 0.03, - "learning_rate": 4.914872534005946e-05, - "loss": 0.5963, + "epoch": 0.01, + "learning_rate": 4.978859533343773e-05, + "loss": 0.6029, "step": 2890 }, { - "epoch": 0.03, - "learning_rate": 4.9144221241329614e-05, - "loss": 0.5877, + "epoch": 0.01, + "learning_rate": 4.978747679022841e-05, + "loss": 0.5979, "step": 2900 }, { - "epoch": 0.03, - "learning_rate": 4.9139717142599765e-05, - "loss": 0.59, + "epoch": 0.01, + "learning_rate": 4.978635824701908e-05, + "loss": 0.5999, "step": 2910 }, { - "epoch": 0.03, - "learning_rate": 4.913521304386993e-05, + "epoch": 0.01, + "learning_rate": 4.978523970380976e-05, "loss": 0.5918, "step": 2920 }, { - "epoch": 0.03, - "learning_rate": 4.913070894514008e-05, - "loss": 0.5927, + "epoch": 0.01, + "learning_rate": 4.9784121160600436e-05, + "loss": 0.597, "step": 2930 }, { - "epoch": 0.03, - "learning_rate": 4.912620484641024e-05, - "loss": 0.5965, + "epoch": 0.01, + "learning_rate": 4.9783002617391114e-05, + "loss": 0.5871, "step": 2940 }, { - "epoch": 0.03, - "learning_rate": 4.9121700747680395e-05, - "loss": 0.587, + "epoch": 0.01, + "learning_rate": 4.978188407418179e-05, + "loss": 0.5981, "step": 2950 }, { - "epoch": 0.03, - "learning_rate": 4.9117196648950546e-05, - "loss": 0.5781, + "epoch": 0.01, + "learning_rate": 4.978076553097246e-05, + "loss": 0.6106, "step": 2960 }, { - "epoch": 0.03, - "learning_rate": 4.91126925502207e-05, - "loss": 0.5836, + "epoch": 0.01, + "learning_rate": 4.977964698776314e-05, + "loss": 0.5926, "step": 2970 }, { - "epoch": 0.03, - "learning_rate": 4.910818845149086e-05, - "loss": 0.5858, + "epoch": 0.01, + "learning_rate": 4.977852844455382e-05, + "loss": 0.5912, "step": 2980 }, { - "epoch": 0.03, - "learning_rate": 4.910368435276101e-05, - "loss": 0.589, + "epoch": 0.01, + "learning_rate": 4.977740990134449e-05, + "loss": 0.594, "step": 2990 }, { - "epoch": 0.03, - "learning_rate": 4.909918025403117e-05, - "loss": 0.591, + "epoch": 0.01, + "learning_rate": 4.977629135813517e-05, + "loss": 0.5871, "step": 3000 }, { - "epoch": 0.03, - "learning_rate": 4.9094676155301326e-05, - "loss": 0.5819, + "epoch": 0.01, + "learning_rate": 4.977517281492584e-05, + "loss": 0.5946, "step": 3010 }, { - "epoch": 0.03, - "learning_rate": 4.9090172056571484e-05, - "loss": 0.5861, + "epoch": 0.01, + "learning_rate": 4.977405427171652e-05, + "loss": 0.6057, "step": 3020 }, { - "epoch": 0.03, - "learning_rate": 4.9085667957841634e-05, - "loss": 0.5859, + "epoch": 0.01, + "learning_rate": 4.9772935728507195e-05, + "loss": 0.5917, "step": 3030 }, { - "epoch": 0.03, - "learning_rate": 4.908116385911179e-05, - "loss": 0.5843, + "epoch": 0.01, + "learning_rate": 4.977181718529787e-05, + "loss": 0.5847, "step": 3040 }, { - "epoch": 0.03, - "learning_rate": 4.907665976038195e-05, - "loss": 0.5909, + "epoch": 0.01, + "learning_rate": 4.977069864208855e-05, + "loss": 0.5813, "step": 3050 }, { - "epoch": 0.03, - "learning_rate": 4.907215566165211e-05, - "loss": 0.5877, + "epoch": 0.01, + "learning_rate": 4.976958009887922e-05, + "loss": 0.5934, "step": 3060 }, { - "epoch": 0.03, - "learning_rate": 4.9067651562922264e-05, - "loss": 0.5849, + "epoch": 0.01, + "learning_rate": 4.97684615556699e-05, + "loss": 0.5928, "step": 3070 }, { - "epoch": 0.03, - "learning_rate": 4.9063147464192415e-05, - "loss": 0.5802, + "epoch": 0.01, + "learning_rate": 4.976734301246057e-05, + "loss": 0.5871, "step": 3080 }, { - "epoch": 0.03, - "learning_rate": 4.905864336546257e-05, - "loss": 0.5763, + "epoch": 0.01, + "learning_rate": 4.976622446925125e-05, + "loss": 0.5885, "step": 3090 }, { - "epoch": 0.03, - "learning_rate": 4.905413926673273e-05, - "loss": 0.5846, + "epoch": 0.01, + "learning_rate": 4.976510592604193e-05, + "loss": 0.5852, "step": 3100 }, { - "epoch": 0.03, - "learning_rate": 4.904963516800288e-05, - "loss": 0.573, + "epoch": 0.01, + "learning_rate": 4.97639873828326e-05, + "loss": 0.5924, "step": 3110 }, { - "epoch": 0.03, - "learning_rate": 4.9045131069273045e-05, - "loss": 0.575, + "epoch": 0.01, + "learning_rate": 4.9762868839623276e-05, + "loss": 0.5914, "step": 3120 }, { - "epoch": 0.03, - "learning_rate": 4.9040626970543196e-05, - "loss": 0.5837, + "epoch": 0.01, + "learning_rate": 4.976175029641395e-05, + "loss": 0.5933, "step": 3130 }, { - "epoch": 0.03, - "learning_rate": 4.903612287181335e-05, - "loss": 0.5814, + "epoch": 0.01, + "learning_rate": 4.976063175320463e-05, + "loss": 0.5851, "step": 3140 }, { - "epoch": 0.03, - "learning_rate": 4.903161877308351e-05, - "loss": 0.5766, + "epoch": 0.01, + "learning_rate": 4.975951320999531e-05, + "loss": 0.5872, "step": 3150 }, { - "epoch": 0.03, - "learning_rate": 4.902711467435366e-05, - "loss": 0.5823, + "epoch": 0.01, + "learning_rate": 4.975839466678598e-05, + "loss": 0.5844, "step": 3160 }, { - "epoch": 0.03, - "learning_rate": 4.902261057562382e-05, - "loss": 0.5753, + "epoch": 0.01, + "learning_rate": 4.975727612357666e-05, + "loss": 0.5803, "step": 3170 }, { - "epoch": 0.03, - "learning_rate": 4.9018106476893977e-05, - "loss": 0.5861, + "epoch": 0.01, + "learning_rate": 4.975615758036733e-05, + "loss": 0.5887, "step": 3180 }, { - "epoch": 0.03, - "learning_rate": 4.9013602378164134e-05, - "loss": 0.578, + "epoch": 0.01, + "learning_rate": 4.975503903715801e-05, + "loss": 0.5814, "step": 3190 }, { - "epoch": 0.03, - "learning_rate": 4.900909827943429e-05, - "loss": 0.5695, + "epoch": 0.01, + "learning_rate": 4.9753920493948686e-05, + "loss": 0.5762, "step": 3200 }, { - "epoch": 0.03, - "learning_rate": 4.900459418070444e-05, - "loss": 0.5804, + "epoch": 0.01, + "learning_rate": 4.975280195073936e-05, + "loss": 0.5829, "step": 3210 }, { - "epoch": 0.03, - "learning_rate": 4.90000900819746e-05, + "epoch": 0.01, + "learning_rate": 4.9751683407530035e-05, "loss": 0.5748, "step": 3220 }, { - "epoch": 0.03, - "learning_rate": 4.899558598324476e-05, - "loss": 0.5747, + "epoch": 0.01, + "learning_rate": 4.9750564864320706e-05, + "loss": 0.5753, "step": 3230 }, { - "epoch": 0.03, - "learning_rate": 4.899108188451491e-05, - "loss": 0.5843, + "epoch": 0.01, + "learning_rate": 4.9749446321111384e-05, + "loss": 0.5734, "step": 3240 }, { - "epoch": 0.03, - "learning_rate": 4.8986577785785065e-05, - "loss": 0.5747, + "epoch": 0.01, + "learning_rate": 4.974832777790206e-05, + "loss": 0.5722, "step": 3250 }, { - "epoch": 0.03, - "learning_rate": 4.898207368705522e-05, - "loss": 0.5733, + "epoch": 0.01, + "learning_rate": 4.974720923469274e-05, + "loss": 0.5871, "step": 3260 }, { - "epoch": 0.03, - "learning_rate": 4.897756958832538e-05, - "loss": 0.567, + "epoch": 0.01, + "learning_rate": 4.974609069148342e-05, + "loss": 0.5868, "step": 3270 }, { - "epoch": 0.03, - "learning_rate": 4.897306548959553e-05, - "loss": 0.5765, + "epoch": 0.01, + "learning_rate": 4.974497214827409e-05, + "loss": 0.5816, "step": 3280 }, { - "epoch": 0.03, - "learning_rate": 4.896856139086569e-05, - "loss": 0.5722, + "epoch": 0.01, + "learning_rate": 4.974385360506477e-05, + "loss": 0.5778, "step": 3290 }, { - "epoch": 0.03, - "learning_rate": 4.8964057292135846e-05, - "loss": 0.5716, + "epoch": 0.01, + "learning_rate": 4.9742735061855445e-05, + "loss": 0.5744, "step": 3300 }, { - "epoch": 0.03, - "learning_rate": 4.8959553193406e-05, - "loss": 0.572, + "epoch": 0.01, + "learning_rate": 4.9741616518646116e-05, + "loss": 0.5821, "step": 3310 }, { - "epoch": 0.03, - "learning_rate": 4.895504909467616e-05, - "loss": 0.5678, + "epoch": 0.01, + "learning_rate": 4.9740497975436794e-05, + "loss": 0.5822, "step": 3320 }, { - "epoch": 0.03, - "learning_rate": 4.895054499594631e-05, - "loss": 0.5619, + "epoch": 0.01, + "learning_rate": 4.9739379432227465e-05, + "loss": 0.5775, "step": 3330 }, { - "epoch": 0.03, - "learning_rate": 4.894604089721647e-05, - "loss": 0.5623, + "epoch": 0.01, + "learning_rate": 4.973826088901814e-05, + "loss": 0.5749, "step": 3340 }, { - "epoch": 0.03, - "learning_rate": 4.894153679848663e-05, - "loss": 0.565, + "epoch": 0.01, + "learning_rate": 4.973714234580882e-05, + "loss": 0.5807, "step": 3350 }, { - "epoch": 0.03, - "learning_rate": 4.893703269975678e-05, - "loss": 0.5696, + "epoch": 0.01, + "learning_rate": 4.97360238025995e-05, + "loss": 0.5707, "step": 3360 }, { - "epoch": 0.03, - "learning_rate": 4.893252860102694e-05, - "loss": 0.5626, + "epoch": 0.01, + "learning_rate": 4.9734905259390177e-05, + "loss": 0.5693, "step": 3370 }, { - "epoch": 0.03, - "learning_rate": 4.892802450229709e-05, - "loss": 0.5641, + "epoch": 0.01, + "learning_rate": 4.973378671618085e-05, + "loss": 0.5674, "step": 3380 }, { - "epoch": 0.03, - "learning_rate": 4.892352040356725e-05, - "loss": 0.5678, + "epoch": 0.01, + "learning_rate": 4.9732668172971526e-05, + "loss": 0.5643, "step": 3390 }, { - "epoch": 0.03, - "learning_rate": 4.891901630483741e-05, - "loss": 0.5631, + "epoch": 0.01, + "learning_rate": 4.97315496297622e-05, + "loss": 0.5711, "step": 3400 }, { - "epoch": 0.03, - "learning_rate": 4.891451220610756e-05, - "loss": 0.5699, + "epoch": 0.01, + "learning_rate": 4.9730431086552875e-05, + "loss": 0.5764, "step": 3410 }, { - "epoch": 0.03, - "learning_rate": 4.8910008107377716e-05, - "loss": 0.5677, + "epoch": 0.01, + "learning_rate": 4.972931254334355e-05, + "loss": 0.5757, "step": 3420 }, { - "epoch": 0.03, - "learning_rate": 4.890550400864787e-05, - "loss": 0.5635, + "epoch": 0.01, + "learning_rate": 4.9728194000134224e-05, + "loss": 0.5697, "step": 3430 }, { - "epoch": 0.03, - "learning_rate": 4.8900999909918024e-05, - "loss": 0.5675, + "epoch": 0.01, + "learning_rate": 4.97270754569249e-05, + "loss": 0.5704, "step": 3440 }, { - "epoch": 0.03, - "learning_rate": 4.889649581118818e-05, - "loss": 0.5553, + "epoch": 0.01, + "learning_rate": 4.972595691371558e-05, + "loss": 0.5749, "step": 3450 }, { - "epoch": 0.03, - "learning_rate": 4.889199171245834e-05, - "loss": 0.5655, + "epoch": 0.01, + "learning_rate": 4.972483837050626e-05, + "loss": 0.5751, "step": 3460 }, { - "epoch": 0.03, - "learning_rate": 4.8887487613728496e-05, - "loss": 0.5568, + "epoch": 0.01, + "learning_rate": 4.9723719827296936e-05, + "loss": 0.5771, "step": 3470 }, { - "epoch": 0.03, - "learning_rate": 4.8882983514998654e-05, - "loss": 0.5627, + "epoch": 0.01, + "learning_rate": 4.972260128408761e-05, + "loss": 0.573, "step": 3480 }, { - "epoch": 0.03, - "learning_rate": 4.8878479416268805e-05, - "loss": 0.5623, + "epoch": 0.01, + "learning_rate": 4.9721482740878285e-05, + "loss": 0.5602, "step": 3490 }, { - "epoch": 0.03, - "learning_rate": 4.887397531753896e-05, - "loss": 0.5674, + "epoch": 0.01, + "learning_rate": 4.9720364197668956e-05, + "loss": 0.568, "step": 3500 }, { - "epoch": 0.03, - "learning_rate": 4.886947121880912e-05, - "loss": 0.558, + "epoch": 0.01, + "learning_rate": 4.9719245654459634e-05, + "loss": 0.5706, "step": 3510 }, { - "epoch": 0.03, - "learning_rate": 4.886496712007928e-05, - "loss": 0.5593, + "epoch": 0.01, + "learning_rate": 4.971812711125031e-05, + "loss": 0.5584, "step": 3520 }, { - "epoch": 0.03, - "learning_rate": 4.886046302134943e-05, - "loss": 0.5604, + "epoch": 0.01, + "learning_rate": 4.971700856804098e-05, + "loss": 0.5667, "step": 3530 }, { - "epoch": 0.03, - "learning_rate": 4.8855958922619585e-05, - "loss": 0.5658, + "epoch": 0.01, + "learning_rate": 4.971589002483166e-05, + "loss": 0.565, "step": 3540 }, { - "epoch": 0.03, - "learning_rate": 4.885145482388974e-05, - "loss": 0.5564, + "epoch": 0.01, + "learning_rate": 4.971477148162234e-05, + "loss": 0.5723, "step": 3550 }, { - "epoch": 0.03, - "learning_rate": 4.8846950725159893e-05, - "loss": 0.5589, + "epoch": 0.01, + "learning_rate": 4.9713652938413017e-05, + "loss": 0.5546, "step": 3560 }, { - "epoch": 0.03, - "learning_rate": 4.884244662643006e-05, - "loss": 0.555, + "epoch": 0.01, + "learning_rate": 4.9712534395203694e-05, + "loss": 0.5597, "step": 3570 }, { - "epoch": 0.03, - "learning_rate": 4.883794252770021e-05, - "loss": 0.5544, + "epoch": 0.01, + "learning_rate": 4.9711415851994366e-05, + "loss": 0.5682, "step": 3580 }, { - "epoch": 0.03, - "learning_rate": 4.8833438428970366e-05, - "loss": 0.5582, + "epoch": 0.01, + "learning_rate": 4.9710297308785044e-05, + "loss": 0.5626, "step": 3590 }, { - "epoch": 0.03, - "learning_rate": 4.8828934330240523e-05, - "loss": 0.5516, + "epoch": 0.01, + "learning_rate": 4.9709178765575715e-05, + "loss": 0.5601, "step": 3600 }, { - "epoch": 0.03, - "learning_rate": 4.8824430231510674e-05, - "loss": 0.5566, + "epoch": 0.01, + "learning_rate": 4.970806022236639e-05, + "loss": 0.5546, "step": 3610 }, { - "epoch": 0.03, - "learning_rate": 4.881992613278084e-05, - "loss": 0.5517, + "epoch": 0.01, + "learning_rate": 4.970694167915707e-05, + "loss": 0.5572, "step": 3620 }, { - "epoch": 0.03, - "learning_rate": 4.881542203405099e-05, - "loss": 0.5518, + "epoch": 0.01, + "learning_rate": 4.970582313594774e-05, + "loss": 0.557, "step": 3630 }, { - "epoch": 0.03, - "learning_rate": 4.881091793532114e-05, - "loss": 0.5511, + "epoch": 0.01, + "learning_rate": 4.970470459273842e-05, + "loss": 0.5655, "step": 3640 }, { - "epoch": 0.03, - "learning_rate": 4.8806413836591304e-05, - "loss": 0.5618, + "epoch": 0.01, + "learning_rate": 4.970358604952909e-05, + "loss": 0.5636, "step": 3650 }, { - "epoch": 0.03, - "learning_rate": 4.8801909737861455e-05, - "loss": 0.5454, + "epoch": 0.01, + "learning_rate": 4.970246750631977e-05, + "loss": 0.5584, "step": 3660 }, { - "epoch": 0.03, - "learning_rate": 4.879740563913161e-05, - "loss": 0.5564, + "epoch": 0.01, + "learning_rate": 4.9701348963110453e-05, + "loss": 0.5595, "step": 3670 }, { - "epoch": 0.03, - "learning_rate": 4.879290154040177e-05, - "loss": 0.558, + "epoch": 0.01, + "learning_rate": 4.9700230419901125e-05, + "loss": 0.5593, "step": 3680 }, { - "epoch": 0.03, - "learning_rate": 4.878839744167192e-05, - "loss": 0.5519, + "epoch": 0.01, + "learning_rate": 4.96991118766918e-05, + "loss": 0.5613, "step": 3690 }, { - "epoch": 0.03, - "learning_rate": 4.878389334294208e-05, - "loss": 0.5461, + "epoch": 0.01, + "learning_rate": 4.9697993333482474e-05, + "loss": 0.5526, "step": 3700 }, { - "epoch": 0.03, - "learning_rate": 4.8779389244212236e-05, - "loss": 0.5558, + "epoch": 0.01, + "learning_rate": 4.969687479027315e-05, + "loss": 0.5532, "step": 3710 }, { - "epoch": 0.03, - "learning_rate": 4.877488514548239e-05, - "loss": 0.5593, + "epoch": 0.01, + "learning_rate": 4.969575624706382e-05, + "loss": 0.5614, "step": 3720 }, { - "epoch": 0.03, - "learning_rate": 4.8770381046752544e-05, - "loss": 0.5586, + "epoch": 0.01, + "learning_rate": 4.96946377038545e-05, + "loss": 0.5584, "step": 3730 }, { - "epoch": 0.03, - "learning_rate": 4.87658769480227e-05, - "loss": 0.5455, + "epoch": 0.01, + "learning_rate": 4.969351916064518e-05, + "loss": 0.5566, "step": 3740 }, { - "epoch": 0.03, - "learning_rate": 4.876137284929286e-05, - "loss": 0.5522, + "epoch": 0.01, + "learning_rate": 4.969240061743585e-05, + "loss": 0.5628, "step": 3750 }, { - "epoch": 0.03, - "learning_rate": 4.8756868750563016e-05, - "loss": 0.553, + "epoch": 0.01, + "learning_rate": 4.969128207422653e-05, + "loss": 0.5575, "step": 3760 }, { - "epoch": 0.03, - "learning_rate": 4.8752364651833174e-05, - "loss": 0.5501, + "epoch": 0.01, + "learning_rate": 4.9690163531017206e-05, + "loss": 0.5415, "step": 3770 }, { - "epoch": 0.03, - "learning_rate": 4.8747860553103324e-05, - "loss": 0.5448, + "epoch": 0.01, + "learning_rate": 4.9689044987807884e-05, + "loss": 0.5584, "step": 3780 }, { - "epoch": 0.03, - "learning_rate": 4.874335645437348e-05, - "loss": 0.5454, + "epoch": 0.01, + "learning_rate": 4.968792644459856e-05, + "loss": 0.5547, "step": 3790 }, { - "epoch": 0.03, - "learning_rate": 4.873885235564364e-05, - "loss": 0.5429, + "epoch": 0.01, + "learning_rate": 4.968680790138923e-05, + "loss": 0.5539, "step": 3800 }, { - "epoch": 0.03, - "learning_rate": 4.873434825691379e-05, - "loss": 0.5503, + "epoch": 0.01, + "learning_rate": 4.968568935817991e-05, + "loss": 0.5536, "step": 3810 }, { - "epoch": 0.03, - "learning_rate": 4.8729844158183954e-05, - "loss": 0.555, + "epoch": 0.01, + "learning_rate": 4.968457081497058e-05, + "loss": 0.5557, "step": 3820 }, { - "epoch": 0.03, - "learning_rate": 4.8725340059454105e-05, - "loss": 0.5426, + "epoch": 0.01, + "learning_rate": 4.968345227176126e-05, + "loss": 0.5549, "step": 3830 }, { - "epoch": 0.03, - "learning_rate": 4.872083596072426e-05, - "loss": 0.5435, + "epoch": 0.01, + "learning_rate": 4.968233372855194e-05, + "loss": 0.5589, "step": 3840 }, { - "epoch": 0.03, - "learning_rate": 4.871633186199442e-05, - "loss": 0.5513, + "epoch": 0.01, + "learning_rate": 4.968121518534261e-05, + "loss": 0.5545, "step": 3850 }, { - "epoch": 0.03, - "learning_rate": 4.871182776326457e-05, - "loss": 0.5425, + "epoch": 0.01, + "learning_rate": 4.968009664213329e-05, + "loss": 0.5525, "step": 3860 }, { - "epoch": 0.03, - "learning_rate": 4.870732366453473e-05, - "loss": 0.5486, + "epoch": 0.01, + "learning_rate": 4.9678978098923965e-05, + "loss": 0.5487, "step": 3870 }, { - "epoch": 0.03, - "learning_rate": 4.8702819565804886e-05, - "loss": 0.5487, + "epoch": 0.01, + "learning_rate": 4.967785955571464e-05, + "loss": 0.5557, "step": 3880 }, { - "epoch": 0.03, - "learning_rate": 4.8698315467075037e-05, - "loss": 0.5357, + "epoch": 0.01, + "learning_rate": 4.967674101250532e-05, + "loss": 0.5481, "step": 3890 }, { - "epoch": 0.03, - "learning_rate": 4.86938113683452e-05, - "loss": 0.551, + "epoch": 0.01, + "learning_rate": 4.967562246929599e-05, + "loss": 0.5522, "step": 3900 }, { - "epoch": 0.03, - "learning_rate": 4.868930726961535e-05, - "loss": 0.5425, + "epoch": 0.01, + "learning_rate": 4.967450392608667e-05, + "loss": 0.5424, "step": 3910 }, { - "epoch": 0.03, - "learning_rate": 4.868480317088551e-05, - "loss": 0.5472, + "epoch": 0.01, + "learning_rate": 4.967338538287734e-05, + "loss": 0.5566, "step": 3920 }, { - "epoch": 0.04, - "learning_rate": 4.8680299072155666e-05, - "loss": 0.5333, + "epoch": 0.01, + "learning_rate": 4.967226683966802e-05, + "loss": 0.5577, "step": 3930 }, { - "epoch": 0.04, - "learning_rate": 4.867579497342582e-05, - "loss": 0.543, + "epoch": 0.01, + "learning_rate": 4.9671148296458696e-05, + "loss": 0.5517, "step": 3940 }, { - "epoch": 0.04, - "learning_rate": 4.8671290874695975e-05, - "loss": 0.5498, + "epoch": 0.01, + "learning_rate": 4.967002975324937e-05, + "loss": 0.5484, "step": 3950 }, { - "epoch": 0.04, - "learning_rate": 4.866678677596613e-05, - "loss": 0.5499, + "epoch": 0.01, + "learning_rate": 4.9668911210040046e-05, + "loss": 0.5511, "step": 3960 }, { - "epoch": 0.04, - "learning_rate": 4.866228267723629e-05, - "loss": 0.5519, + "epoch": 0.01, + "learning_rate": 4.9667792666830724e-05, + "loss": 0.5466, "step": 3970 }, { - "epoch": 0.04, - "learning_rate": 4.865777857850644e-05, - "loss": 0.5457, + "epoch": 0.01, + "learning_rate": 4.96666741236214e-05, + "loss": 0.5482, "step": 3980 }, { - "epoch": 0.04, - "learning_rate": 4.86532744797766e-05, - "loss": 0.546, + "epoch": 0.01, + "learning_rate": 4.966555558041208e-05, + "loss": 0.5486, "step": 3990 }, { - "epoch": 0.04, - "learning_rate": 4.8648770381046755e-05, - "loss": 0.5387, + "epoch": 0.01, + "learning_rate": 4.966443703720275e-05, + "loss": 0.5374, "step": 4000 }, { - "epoch": 0.04, - "learning_rate": 4.8644266282316906e-05, - "loss": 0.5373, + "epoch": 0.01, + "learning_rate": 4.966331849399343e-05, + "loss": 0.5384, "step": 4010 }, { - "epoch": 0.04, - "learning_rate": 4.863976218358707e-05, - "loss": 0.5405, + "epoch": 0.01, + "learning_rate": 4.96621999507841e-05, + "loss": 0.5448, "step": 4020 }, { - "epoch": 0.04, - "learning_rate": 4.863525808485722e-05, - "loss": 0.5395, + "epoch": 0.01, + "learning_rate": 4.966108140757478e-05, + "loss": 0.5407, "step": 4030 }, { - "epoch": 0.04, - "learning_rate": 4.863075398612738e-05, - "loss": 0.5483, + "epoch": 0.01, + "learning_rate": 4.965996286436545e-05, + "loss": 0.5378, "step": 4040 }, { - "epoch": 0.04, - "learning_rate": 4.8626249887397536e-05, - "loss": 0.5434, + "epoch": 0.01, + "learning_rate": 4.9658844321156127e-05, + "loss": 0.5472, "step": 4050 }, { - "epoch": 0.04, - "learning_rate": 4.862174578866769e-05, - "loss": 0.5366, + "epoch": 0.01, + "learning_rate": 4.9657725777946805e-05, + "loss": 0.5446, "step": 4060 }, { - "epoch": 0.04, - "learning_rate": 4.861724168993785e-05, - "loss": 0.5329, + "epoch": 0.01, + "learning_rate": 4.9656607234737476e-05, + "loss": 0.5386, "step": 4070 }, { - "epoch": 0.04, - "learning_rate": 4.8612737591208e-05, - "loss": 0.5478, + "epoch": 0.01, + "learning_rate": 4.9655488691528154e-05, + "loss": 0.5431, "step": 4080 }, { - "epoch": 0.04, - "learning_rate": 4.860823349247815e-05, - "loss": 0.5339, + "epoch": 0.01, + "learning_rate": 4.965437014831883e-05, + "loss": 0.5481, "step": 4090 }, { - "epoch": 0.04, - "learning_rate": 4.860372939374832e-05, - "loss": 0.5342, + "epoch": 0.01, + "learning_rate": 4.965325160510951e-05, + "loss": 0.5466, "step": 4100 }, { - "epoch": 0.04, - "learning_rate": 4.859922529501847e-05, - "loss": 0.5387, + "epoch": 0.01, + "learning_rate": 4.965213306190019e-05, + "loss": 0.5432, "step": 4110 }, { - "epoch": 0.04, - "learning_rate": 4.8594721196288625e-05, + "epoch": 0.01, + "learning_rate": 4.965101451869086e-05, "loss": 0.5368, "step": 4120 }, { - "epoch": 0.04, - "learning_rate": 4.859021709755878e-05, - "loss": 0.5337, + "epoch": 0.01, + "learning_rate": 4.9649895975481536e-05, + "loss": 0.5338, "step": 4130 }, { - "epoch": 0.04, - "learning_rate": 4.858571299882893e-05, - "loss": 0.5409, + "epoch": 0.01, + "learning_rate": 4.964877743227221e-05, + "loss": 0.5326, "step": 4140 }, { - "epoch": 0.04, - "learning_rate": 4.858120890009909e-05, - "loss": 0.5447, + "epoch": 0.01, + "learning_rate": 4.9647658889062886e-05, + "loss": 0.5416, "step": 4150 }, { - "epoch": 0.04, - "learning_rate": 4.857670480136925e-05, - "loss": 0.5323, + "epoch": 0.01, + "learning_rate": 4.9646540345853563e-05, + "loss": 0.541, "step": 4160 }, { - "epoch": 0.04, - "learning_rate": 4.8572200702639406e-05, - "loss": 0.5305, + "epoch": 0.01, + "learning_rate": 4.9645421802644235e-05, + "loss": 0.5324, "step": 4170 }, { - "epoch": 0.04, - "learning_rate": 4.856769660390956e-05, - "loss": 0.5379, + "epoch": 0.01, + "learning_rate": 4.964430325943491e-05, + "loss": 0.544, "step": 4180 }, { - "epoch": 0.04, - "learning_rate": 4.8563192505179714e-05, - "loss": 0.5368, + "epoch": 0.01, + "learning_rate": 4.964318471622559e-05, + "loss": 0.5456, "step": 4190 }, { - "epoch": 0.04, - "learning_rate": 4.855868840644987e-05, - "loss": 0.5368, + "epoch": 0.01, + "learning_rate": 4.964206617301627e-05, + "loss": 0.5338, "step": 4200 }, { - "epoch": 0.04, - "learning_rate": 4.855418430772003e-05, - "loss": 0.531, + "epoch": 0.01, + "learning_rate": 4.9640947629806946e-05, + "loss": 0.5519, "step": 4210 }, { - "epoch": 0.04, - "learning_rate": 4.8549680208990186e-05, - "loss": 0.5291, + "epoch": 0.01, + "learning_rate": 4.963982908659762e-05, + "loss": 0.5442, "step": 4220 }, { - "epoch": 0.04, - "learning_rate": 4.854517611026034e-05, - "loss": 0.5398, + "epoch": 0.01, + "learning_rate": 4.9638710543388295e-05, + "loss": 0.5411, "step": 4230 }, { - "epoch": 0.04, - "learning_rate": 4.8540672011530495e-05, - "loss": 0.5346, + "epoch": 0.01, + "learning_rate": 4.9637592000178967e-05, + "loss": 0.5395, "step": 4240 }, { - "epoch": 0.04, - "learning_rate": 4.853616791280065e-05, - "loss": 0.529, + "epoch": 0.01, + "learning_rate": 4.9636473456969644e-05, + "loss": 0.5379, "step": 4250 }, { - "epoch": 0.04, - "learning_rate": 4.85316638140708e-05, - "loss": 0.5343, + "epoch": 0.01, + "learning_rate": 4.963535491376032e-05, + "loss": 0.5342, "step": 4260 }, { - "epoch": 0.04, - "learning_rate": 4.852715971534097e-05, - "loss": 0.5276, + "epoch": 0.01, + "learning_rate": 4.9634236370550994e-05, + "loss": 0.5308, "step": 4270 }, { - "epoch": 0.04, - "learning_rate": 4.852265561661112e-05, - "loss": 0.5326, + "epoch": 0.01, + "learning_rate": 4.963311782734167e-05, + "loss": 0.5393, "step": 4280 }, { - "epoch": 0.04, - "learning_rate": 4.851815151788127e-05, - "loss": 0.5272, + "epoch": 0.01, + "learning_rate": 4.963199928413235e-05, + "loss": 0.5349, "step": 4290 }, { - "epoch": 0.04, - "learning_rate": 4.851364741915143e-05, - "loss": 0.5221, + "epoch": 0.01, + "learning_rate": 4.963088074092303e-05, + "loss": 0.5357, "step": 4300 }, { - "epoch": 0.04, - "learning_rate": 4.8509143320421583e-05, - "loss": 0.5332, + "epoch": 0.01, + "learning_rate": 4.9629762197713705e-05, + "loss": 0.5337, "step": 4310 }, { - "epoch": 0.04, - "learning_rate": 4.850463922169175e-05, - "loss": 0.5353, + "epoch": 0.01, + "learning_rate": 4.9628643654504376e-05, + "loss": 0.5412, "step": 4320 }, { - "epoch": 0.04, - "learning_rate": 4.85001351229619e-05, - "loss": 0.5251, + "epoch": 0.01, + "learning_rate": 4.9627525111295054e-05, + "loss": 0.5324, "step": 4330 }, { - "epoch": 0.04, - "learning_rate": 4.849563102423205e-05, - "loss": 0.525, + "epoch": 0.01, + "learning_rate": 4.9626406568085726e-05, + "loss": 0.532, "step": 4340 }, { - "epoch": 0.04, - "learning_rate": 4.8491126925502213e-05, - "loss": 0.5233, + "epoch": 0.01, + "learning_rate": 4.9625288024876403e-05, + "loss": 0.5298, "step": 4350 }, { - "epoch": 0.04, - "learning_rate": 4.8486622826772364e-05, - "loss": 0.5301, + "epoch": 0.01, + "learning_rate": 4.9624169481667075e-05, + "loss": 0.5274, "step": 4360 }, { - "epoch": 0.04, - "learning_rate": 4.848211872804252e-05, - "loss": 0.5247, + "epoch": 0.01, + "learning_rate": 4.962305093845775e-05, + "loss": 0.5267, "step": 4370 }, { - "epoch": 0.04, - "learning_rate": 4.847761462931268e-05, - "loss": 0.5301, + "epoch": 0.01, + "learning_rate": 4.962193239524843e-05, + "loss": 0.5265, "step": 4380 }, { - "epoch": 0.04, - "learning_rate": 4.847311053058283e-05, - "loss": 0.5239, + "epoch": 0.01, + "learning_rate": 4.962081385203911e-05, + "loss": 0.5364, "step": 4390 }, { - "epoch": 0.04, - "learning_rate": 4.846860643185299e-05, - "loss": 0.5225, + "epoch": 0.01, + "learning_rate": 4.9619695308829786e-05, + "loss": 0.5268, "step": 4400 }, { - "epoch": 0.04, - "learning_rate": 4.8464102333123145e-05, - "loss": 0.5249, + "epoch": 0.01, + "learning_rate": 4.961857676562046e-05, + "loss": 0.5392, "step": 4410 }, { - "epoch": 0.04, - "learning_rate": 4.84595982343933e-05, - "loss": 0.5241, + "epoch": 0.01, + "learning_rate": 4.9617458222411135e-05, + "loss": 0.5345, "step": 4420 }, { - "epoch": 0.04, - "learning_rate": 4.845509413566345e-05, - "loss": 0.5242, + "epoch": 0.01, + "learning_rate": 4.961633967920181e-05, + "loss": 0.5273, "step": 4430 }, { - "epoch": 0.04, - "learning_rate": 4.845059003693361e-05, - "loss": 0.519, + "epoch": 0.01, + "learning_rate": 4.9615221135992484e-05, + "loss": 0.5271, "step": 4440 }, { - "epoch": 0.04, - "learning_rate": 4.844608593820377e-05, - "loss": 0.5223, + "epoch": 0.01, + "learning_rate": 4.961410259278316e-05, + "loss": 0.5403, "step": 4450 }, { - "epoch": 0.04, - "learning_rate": 4.8441581839473925e-05, - "loss": 0.5246, + "epoch": 0.01, + "learning_rate": 4.9612984049573834e-05, + "loss": 0.5349, "step": 4460 }, { - "epoch": 0.04, - "learning_rate": 4.843707774074408e-05, - "loss": 0.5242, + "epoch": 0.01, + "learning_rate": 4.961186550636451e-05, + "loss": 0.5325, "step": 4470 }, { - "epoch": 0.04, - "learning_rate": 4.8432573642014234e-05, - "loss": 0.5208, + "epoch": 0.01, + "learning_rate": 4.961074696315519e-05, + "loss": 0.5387, "step": 4480 }, { - "epoch": 0.04, - "learning_rate": 4.842806954328439e-05, - "loss": 0.5207, + "epoch": 0.01, + "learning_rate": 4.960962841994586e-05, + "loss": 0.5335, "step": 4490 }, { - "epoch": 0.04, - "learning_rate": 4.842356544455455e-05, - "loss": 0.5179, + "epoch": 0.01, + "learning_rate": 4.9608509876736545e-05, + "loss": 0.5222, "step": 4500 }, { - "epoch": 0.04, - "learning_rate": 4.84190613458247e-05, - "loss": 0.5216, + "epoch": 0.01, + "learning_rate": 4.9607391333527216e-05, + "loss": 0.5245, "step": 4510 }, { - "epoch": 0.04, - "learning_rate": 4.8414557247094864e-05, - "loss": 0.5266, + "epoch": 0.01, + "learning_rate": 4.9606272790317894e-05, + "loss": 0.5333, "step": 4520 }, { - "epoch": 0.04, - "learning_rate": 4.8410053148365014e-05, - "loss": 0.5256, + "epoch": 0.01, + "learning_rate": 4.960515424710857e-05, + "loss": 0.5265, "step": 4530 }, { - "epoch": 0.04, - "learning_rate": 4.8405549049635165e-05, - "loss": 0.5296, + "epoch": 0.01, + "learning_rate": 4.9604035703899243e-05, + "loss": 0.5184, "step": 4540 }, { - "epoch": 0.04, - "learning_rate": 4.840104495090533e-05, - "loss": 0.5135, + "epoch": 0.01, + "learning_rate": 4.960291716068992e-05, + "loss": 0.5248, "step": 4550 }, { - "epoch": 0.04, - "learning_rate": 4.839654085217548e-05, - "loss": 0.5172, + "epoch": 0.01, + "learning_rate": 4.960179861748059e-05, + "loss": 0.526, "step": 4560 }, { - "epoch": 0.04, - "learning_rate": 4.839203675344564e-05, - "loss": 0.5212, + "epoch": 0.01, + "learning_rate": 4.960068007427127e-05, + "loss": 0.5257, "step": 4570 }, { - "epoch": 0.04, - "learning_rate": 4.8387532654715795e-05, - "loss": 0.5257, + "epoch": 0.01, + "learning_rate": 4.959956153106195e-05, + "loss": 0.529, "step": 4580 }, { - "epoch": 0.04, - "learning_rate": 4.8383028555985946e-05, - "loss": 0.5268, + "epoch": 0.01, + "learning_rate": 4.959844298785262e-05, + "loss": 0.5305, "step": 4590 }, { - "epoch": 0.04, - "learning_rate": 4.837852445725611e-05, - "loss": 0.5204, + "epoch": 0.01, + "learning_rate": 4.95973244446433e-05, + "loss": 0.5254, "step": 4600 }, { - "epoch": 0.04, - "learning_rate": 4.837402035852626e-05, - "loss": 0.5172, + "epoch": 0.01, + "learning_rate": 4.9596205901433975e-05, + "loss": 0.5184, "step": 4610 }, { - "epoch": 0.04, - "learning_rate": 4.836951625979642e-05, - "loss": 0.509, + "epoch": 0.01, + "learning_rate": 4.959508735822465e-05, + "loss": 0.5213, "step": 4620 }, { - "epoch": 0.04, - "learning_rate": 4.8365012161066576e-05, - "loss": 0.5138, + "epoch": 0.01, + "learning_rate": 4.9593968815015324e-05, + "loss": 0.5263, "step": 4630 }, { - "epoch": 0.04, - "learning_rate": 4.8360508062336726e-05, - "loss": 0.5104, + "epoch": 0.01, + "learning_rate": 4.9592850271806e-05, + "loss": 0.5222, "step": 4640 }, { - "epoch": 0.04, - "learning_rate": 4.8356003963606884e-05, - "loss": 0.5066, + "epoch": 0.01, + "learning_rate": 4.959173172859668e-05, + "loss": 0.5269, "step": 4650 }, { - "epoch": 0.04, - "learning_rate": 4.835149986487704e-05, - "loss": 0.5159, + "epoch": 0.01, + "learning_rate": 4.959061318538735e-05, + "loss": 0.5241, "step": 4660 }, { - "epoch": 0.04, - "learning_rate": 4.83469957661472e-05, - "loss": 0.515, + "epoch": 0.01, + "learning_rate": 4.958949464217803e-05, + "loss": 0.53, "step": 4670 }, { - "epoch": 0.04, - "learning_rate": 4.834249166741735e-05, - "loss": 0.524, + "epoch": 0.01, + "learning_rate": 4.95883760989687e-05, + "loss": 0.5252, "step": 4680 }, { - "epoch": 0.04, - "learning_rate": 4.833798756868751e-05, - "loss": 0.5194, + "epoch": 0.01, + "learning_rate": 4.958725755575938e-05, + "loss": 0.5228, "step": 4690 }, { - "epoch": 0.04, - "learning_rate": 4.8333483469957665e-05, - "loss": 0.5196, + "epoch": 0.01, + "learning_rate": 4.9586139012550056e-05, + "loss": 0.5241, "step": 4700 }, { - "epoch": 0.04, - "learning_rate": 4.8328979371227815e-05, - "loss": 0.5163, + "epoch": 0.01, + "learning_rate": 4.9585020469340734e-05, + "loss": 0.517, "step": 4710 }, { - "epoch": 0.04, - "learning_rate": 4.832447527249798e-05, - "loss": 0.509, + "epoch": 0.01, + "learning_rate": 4.958390192613141e-05, + "loss": 0.5204, "step": 4720 }, { - "epoch": 0.04, - "learning_rate": 4.831997117376813e-05, - "loss": 0.5138, + "epoch": 0.01, + "learning_rate": 4.958278338292208e-05, + "loss": 0.5231, "step": 4730 }, { - "epoch": 0.04, - "learning_rate": 4.831546707503829e-05, - "loss": 0.5125, + "epoch": 0.01, + "learning_rate": 4.958166483971276e-05, + "loss": 0.5249, "step": 4740 }, { - "epoch": 0.04, - "learning_rate": 4.8310962976308445e-05, - "loss": 0.5086, + "epoch": 0.01, + "learning_rate": 4.958054629650344e-05, + "loss": 0.5214, "step": 4750 }, { - "epoch": 0.04, - "learning_rate": 4.8306458877578596e-05, - "loss": 0.5187, + "epoch": 0.01, + "learning_rate": 4.957942775329411e-05, + "loss": 0.5204, "step": 4760 }, { - "epoch": 0.04, - "learning_rate": 4.830195477884876e-05, - "loss": 0.5172, + "epoch": 0.01, + "learning_rate": 4.957830921008479e-05, + "loss": 0.5177, "step": 4770 }, { - "epoch": 0.04, - "learning_rate": 4.829745068011891e-05, - "loss": 0.5107, + "epoch": 0.01, + "learning_rate": 4.957719066687546e-05, + "loss": 0.5155, "step": 4780 }, { - "epoch": 0.04, - "learning_rate": 4.829294658138906e-05, - "loss": 0.5124, + "epoch": 0.01, + "learning_rate": 4.957607212366614e-05, + "loss": 0.5225, "step": 4790 }, { - "epoch": 0.04, - "learning_rate": 4.8288442482659226e-05, - "loss": 0.5193, + "epoch": 0.01, + "learning_rate": 4.9574953580456815e-05, + "loss": 0.5131, "step": 4800 }, { - "epoch": 0.04, - "learning_rate": 4.828393838392938e-05, - "loss": 0.5234, + "epoch": 0.01, + "learning_rate": 4.957383503724749e-05, + "loss": 0.5195, "step": 4810 }, { - "epoch": 0.04, - "learning_rate": 4.8279434285199534e-05, - "loss": 0.5183, + "epoch": 0.01, + "learning_rate": 4.957271649403817e-05, + "loss": 0.5165, "step": 4820 }, { - "epoch": 0.04, - "learning_rate": 4.827493018646969e-05, - "loss": 0.5062, + "epoch": 0.01, + "learning_rate": 4.957159795082884e-05, + "loss": 0.5223, "step": 4830 }, { - "epoch": 0.04, - "learning_rate": 4.827042608773984e-05, - "loss": 0.5161, + "epoch": 0.01, + "learning_rate": 4.957047940761952e-05, + "loss": 0.5203, "step": 4840 }, { - "epoch": 0.04, - "learning_rate": 4.826592198901e-05, - "loss": 0.5056, + "epoch": 0.01, + "learning_rate": 4.95693608644102e-05, + "loss": 0.5222, "step": 4850 }, { - "epoch": 0.04, - "learning_rate": 4.826141789028016e-05, - "loss": 0.5121, + "epoch": 0.01, + "learning_rate": 4.956824232120087e-05, + "loss": 0.5182, "step": 4860 }, { - "epoch": 0.04, - "learning_rate": 4.8256913791550315e-05, - "loss": 0.505, + "epoch": 0.01, + "learning_rate": 4.956712377799155e-05, + "loss": 0.5154, "step": 4870 }, { - "epoch": 0.04, - "learning_rate": 4.825240969282047e-05, - "loss": 0.5041, + "epoch": 0.01, + "learning_rate": 4.956600523478222e-05, + "loss": 0.5186, "step": 4880 }, { - "epoch": 0.04, - "learning_rate": 4.824790559409062e-05, - "loss": 0.5174, + "epoch": 0.01, + "learning_rate": 4.9564886691572896e-05, + "loss": 0.5193, "step": 4890 }, { - "epoch": 0.04, - "learning_rate": 4.824340149536078e-05, - "loss": 0.5112, + "epoch": 0.01, + "learning_rate": 4.9563768148363574e-05, + "loss": 0.5192, "step": 4900 }, { - "epoch": 0.04, - "learning_rate": 4.823889739663094e-05, - "loss": 0.5041, + "epoch": 0.01, + "learning_rate": 4.956264960515425e-05, + "loss": 0.5107, "step": 4910 }, { - "epoch": 0.04, - "learning_rate": 4.8234393297901096e-05, - "loss": 0.5107, + "epoch": 0.01, + "learning_rate": 4.956153106194493e-05, + "loss": 0.5131, "step": 4920 }, { - "epoch": 0.04, - "learning_rate": 4.8229889199171246e-05, - "loss": 0.5069, + "epoch": 0.01, + "learning_rate": 4.95604125187356e-05, + "loss": 0.516, "step": 4930 }, { - "epoch": 0.04, - "learning_rate": 4.8225385100441404e-05, - "loss": 0.5033, + "epoch": 0.01, + "learning_rate": 4.955929397552628e-05, + "loss": 0.5099, "step": 4940 }, { - "epoch": 0.04, - "learning_rate": 4.822088100171156e-05, - "loss": 0.5079, + "epoch": 0.01, + "learning_rate": 4.955817543231695e-05, + "loss": 0.5172, "step": 4950 }, { - "epoch": 0.04, - "learning_rate": 4.821637690298171e-05, - "loss": 0.5112, + "epoch": 0.01, + "learning_rate": 4.955705688910763e-05, + "loss": 0.5148, "step": 4960 }, { - "epoch": 0.04, - "learning_rate": 4.8211872804251876e-05, - "loss": 0.5072, + "epoch": 0.01, + "learning_rate": 4.9555938345898306e-05, + "loss": 0.5076, "step": 4970 }, { - "epoch": 0.04, - "learning_rate": 4.820736870552203e-05, - "loss": 0.5161, + "epoch": 0.01, + "learning_rate": 4.955481980268898e-05, + "loss": 0.5084, "step": 4980 }, { - "epoch": 0.04, - "learning_rate": 4.820286460679218e-05, - "loss": 0.5092, + "epoch": 0.01, + "learning_rate": 4.9553701259479655e-05, + "loss": 0.5105, "step": 4990 }, { - "epoch": 0.04, - "learning_rate": 4.819836050806234e-05, - "loss": 0.5129, + "epoch": 0.01, + "learning_rate": 4.9552582716270326e-05, + "loss": 0.5161, "step": 5000 }, { - "epoch": 0.04, - "learning_rate": 4.819385640933249e-05, - "loss": 0.503, + "epoch": 0.01, + "learning_rate": 4.9551464173061004e-05, + "loss": 0.5154, "step": 5010 }, { - "epoch": 0.04, - "learning_rate": 4.818935231060265e-05, - "loss": 0.5073, + "epoch": 0.01, + "learning_rate": 4.955034562985168e-05, + "loss": 0.5221, "step": 5020 }, { - "epoch": 0.04, - "learning_rate": 4.818484821187281e-05, - "loss": 0.509, + "epoch": 0.01, + "learning_rate": 4.954922708664236e-05, + "loss": 0.5224, "step": 5030 }, { - "epoch": 0.04, - "learning_rate": 4.818034411314296e-05, - "loss": 0.5086, + "epoch": 0.01, + "learning_rate": 4.954810854343304e-05, + "loss": 0.5102, "step": 5040 }, { - "epoch": 0.05, - "learning_rate": 4.817584001441312e-05, - "loss": 0.5002, + "epoch": 0.01, + "learning_rate": 4.954699000022371e-05, + "loss": 0.5164, "step": 5050 }, { - "epoch": 0.05, - "learning_rate": 4.817133591568327e-05, - "loss": 0.5097, + "epoch": 0.01, + "learning_rate": 4.954587145701439e-05, + "loss": 0.5118, "step": 5060 }, { - "epoch": 0.05, - "learning_rate": 4.816683181695343e-05, - "loss": 0.5133, + "epoch": 0.01, + "learning_rate": 4.9544752913805065e-05, + "loss": 0.5141, "step": 5070 }, { - "epoch": 0.05, - "learning_rate": 4.816232771822359e-05, - "loss": 0.5051, + "epoch": 0.01, + "learning_rate": 4.9543634370595736e-05, + "loss": 0.5136, "step": 5080 }, { - "epoch": 0.05, - "learning_rate": 4.815782361949374e-05, - "loss": 0.4998, + "epoch": 0.01, + "learning_rate": 4.9542515827386414e-05, + "loss": 0.5115, "step": 5090 }, { - "epoch": 0.05, - "learning_rate": 4.8153319520763897e-05, - "loss": 0.5067, + "epoch": 0.01, + "learning_rate": 4.9541397284177085e-05, + "loss": 0.5164, "step": 5100 }, { - "epoch": 0.05, - "learning_rate": 4.8148815422034054e-05, - "loss": 0.5022, + "epoch": 0.01, + "learning_rate": 4.954027874096776e-05, + "loss": 0.51, "step": 5110 }, { - "epoch": 0.05, - "learning_rate": 4.814431132330421e-05, - "loss": 0.4996, + "epoch": 0.01, + "learning_rate": 4.953916019775844e-05, + "loss": 0.5207, "step": 5120 }, { - "epoch": 0.05, - "learning_rate": 4.813980722457436e-05, - "loss": 0.5028, + "epoch": 0.01, + "learning_rate": 4.953804165454912e-05, + "loss": 0.517, "step": 5130 }, { - "epoch": 0.05, - "learning_rate": 4.813530312584452e-05, - "loss": 0.5042, + "epoch": 0.01, + "learning_rate": 4.95369231113398e-05, + "loss": 0.5185, "step": 5140 }, { - "epoch": 0.05, - "learning_rate": 4.813079902711468e-05, - "loss": 0.503, + "epoch": 0.01, + "learning_rate": 4.953580456813047e-05, + "loss": 0.5119, "step": 5150 }, { - "epoch": 0.05, - "learning_rate": 4.8126294928384835e-05, - "loss": 0.5028, + "epoch": 0.01, + "learning_rate": 4.9534686024921146e-05, + "loss": 0.509, "step": 5160 }, { - "epoch": 0.05, - "learning_rate": 4.812179082965499e-05, - "loss": 0.5074, + "epoch": 0.01, + "learning_rate": 4.9533567481711824e-05, + "loss": 0.5103, "step": 5170 }, { - "epoch": 0.05, - "learning_rate": 4.811728673092514e-05, - "loss": 0.4989, + "epoch": 0.01, + "learning_rate": 4.9532448938502495e-05, + "loss": 0.5046, "step": 5180 }, { - "epoch": 0.05, - "learning_rate": 4.81127826321953e-05, - "loss": 0.4971, + "epoch": 0.01, + "learning_rate": 4.953133039529317e-05, + "loss": 0.5035, "step": 5190 }, { - "epoch": 0.05, - "learning_rate": 4.810827853346546e-05, - "loss": 0.4975, + "epoch": 0.01, + "learning_rate": 4.9530211852083844e-05, + "loss": 0.5049, "step": 5200 }, { - "epoch": 0.05, - "learning_rate": 4.810377443473561e-05, - "loss": 0.5005, + "epoch": 0.01, + "learning_rate": 4.952909330887452e-05, + "loss": 0.5038, "step": 5210 }, { - "epoch": 0.05, - "learning_rate": 4.8099270336005766e-05, - "loss": 0.4984, + "epoch": 0.01, + "learning_rate": 4.95279747656652e-05, + "loss": 0.5111, "step": 5220 }, { - "epoch": 0.05, - "learning_rate": 4.8094766237275924e-05, - "loss": 0.5091, + "epoch": 0.01, + "learning_rate": 4.952685622245588e-05, + "loss": 0.5084, "step": 5230 }, { - "epoch": 0.05, - "learning_rate": 4.8090262138546074e-05, - "loss": 0.5023, + "epoch": 0.01, + "learning_rate": 4.9525737679246556e-05, + "loss": 0.5061, "step": 5240 }, { - "epoch": 0.05, - "learning_rate": 4.808575803981624e-05, - "loss": 0.5034, + "epoch": 0.01, + "learning_rate": 4.952461913603723e-05, + "loss": 0.4996, "step": 5250 }, { - "epoch": 0.05, - "learning_rate": 4.808125394108639e-05, - "loss": 0.5039, + "epoch": 0.01, + "learning_rate": 4.9523500592827905e-05, + "loss": 0.4982, "step": 5260 }, { - "epoch": 0.05, - "learning_rate": 4.807674984235655e-05, - "loss": 0.4982, + "epoch": 0.01, + "learning_rate": 4.9522382049618576e-05, + "loss": 0.4991, "step": 5270 }, { - "epoch": 0.05, - "learning_rate": 4.8072245743626704e-05, - "loss": 0.4987, + "epoch": 0.01, + "learning_rate": 4.9521263506409254e-05, + "loss": 0.5012, "step": 5280 }, { - "epoch": 0.05, - "learning_rate": 4.8067741644896855e-05, - "loss": 0.5001, + "epoch": 0.01, + "learning_rate": 4.952014496319993e-05, + "loss": 0.4943, "step": 5290 }, { - "epoch": 0.05, - "learning_rate": 4.806323754616702e-05, - "loss": 0.4977, + "epoch": 0.01, + "learning_rate": 4.95190264199906e-05, + "loss": 0.5043, "step": 5300 }, { - "epoch": 0.05, - "learning_rate": 4.805873344743717e-05, - "loss": 0.4986, + "epoch": 0.01, + "learning_rate": 4.951790787678128e-05, + "loss": 0.5021, "step": 5310 }, { - "epoch": 0.05, - "learning_rate": 4.805422934870733e-05, - "loss": 0.5021, + "epoch": 0.01, + "learning_rate": 4.951678933357195e-05, + "loss": 0.5051, "step": 5320 }, { - "epoch": 0.05, - "learning_rate": 4.8049725249977485e-05, - "loss": 0.4976, + "epoch": 0.01, + "learning_rate": 4.951567079036264e-05, + "loss": 0.5019, "step": 5330 }, { - "epoch": 0.05, - "learning_rate": 4.8045221151247636e-05, - "loss": 0.4944, + "epoch": 0.01, + "learning_rate": 4.9514552247153315e-05, + "loss": 0.5049, "step": 5340 }, { - "epoch": 0.05, - "learning_rate": 4.804071705251779e-05, - "loss": 0.4973, + "epoch": 0.01, + "learning_rate": 4.9513433703943986e-05, + "loss": 0.503, "step": 5350 }, { - "epoch": 0.05, - "learning_rate": 4.803621295378795e-05, - "loss": 0.4967, + "epoch": 0.01, + "learning_rate": 4.9512315160734664e-05, + "loss": 0.5033, "step": 5360 }, { - "epoch": 0.05, - "learning_rate": 4.803170885505811e-05, - "loss": 0.4922, + "epoch": 0.01, + "learning_rate": 4.9511196617525335e-05, + "loss": 0.4969, "step": 5370 }, { - "epoch": 0.05, - "learning_rate": 4.802720475632826e-05, - "loss": 0.4996, + "epoch": 0.01, + "learning_rate": 4.951007807431601e-05, + "loss": 0.5077, "step": 5380 }, { - "epoch": 0.05, - "learning_rate": 4.8022700657598416e-05, - "loss": 0.4939, + "epoch": 0.01, + "learning_rate": 4.950895953110669e-05, + "loss": 0.5078, "step": 5390 }, { - "epoch": 0.05, - "learning_rate": 4.8018196558868574e-05, - "loss": 0.4895, + "epoch": 0.01, + "learning_rate": 4.950784098789736e-05, + "loss": 0.5017, "step": 5400 }, { - "epoch": 0.05, - "learning_rate": 4.8013692460138725e-05, - "loss": 0.4889, + "epoch": 0.01, + "learning_rate": 4.950672244468804e-05, + "loss": 0.4969, "step": 5410 }, { - "epoch": 0.05, - "learning_rate": 4.800918836140889e-05, - "loss": 0.5032, + "epoch": 0.01, + "learning_rate": 4.950560390147871e-05, + "loss": 0.5017, "step": 5420 }, { - "epoch": 0.05, - "learning_rate": 4.800468426267904e-05, - "loss": 0.4973, + "epoch": 0.01, + "learning_rate": 4.950448535826939e-05, + "loss": 0.5032, "step": 5430 }, { - "epoch": 0.05, - "learning_rate": 4.80001801639492e-05, - "loss": 0.5013, + "epoch": 0.01, + "learning_rate": 4.950336681506007e-05, + "loss": 0.5047, "step": 5440 }, { - "epoch": 0.05, - "learning_rate": 4.7995676065219355e-05, - "loss": 0.4948, + "epoch": 0.01, + "learning_rate": 4.9502248271850745e-05, + "loss": 0.501, "step": 5450 }, { - "epoch": 0.05, - "learning_rate": 4.7991171966489505e-05, - "loss": 0.4958, + "epoch": 0.01, + "learning_rate": 4.950112972864142e-05, + "loss": 0.5084, "step": 5460 }, { - "epoch": 0.05, - "learning_rate": 4.798666786775966e-05, - "loss": 0.4929, + "epoch": 0.01, + "learning_rate": 4.9500011185432094e-05, + "loss": 0.5063, "step": 5470 }, { - "epoch": 0.05, - "learning_rate": 4.798216376902982e-05, - "loss": 0.4822, + "epoch": 0.01, + "learning_rate": 4.949889264222277e-05, + "loss": 0.5046, "step": 5480 }, { - "epoch": 0.05, - "learning_rate": 4.797765967029997e-05, - "loss": 0.4921, + "epoch": 0.01, + "learning_rate": 4.949777409901345e-05, + "loss": 0.5002, "step": 5490 }, { - "epoch": 0.05, - "learning_rate": 4.7973155571570135e-05, - "loss": 0.4982, + "epoch": 0.01, + "learning_rate": 4.949665555580412e-05, + "loss": 0.4976, "step": 5500 }, { - "epoch": 0.05, - "learning_rate": 4.7968651472840286e-05, - "loss": 0.4989, + "epoch": 0.01, + "learning_rate": 4.94955370125948e-05, + "loss": 0.4977, "step": 5510 }, { - "epoch": 0.05, - "learning_rate": 4.7964147374110443e-05, - "loss": 0.487, + "epoch": 0.01, + "learning_rate": 4.949441846938547e-05, + "loss": 0.5022, "step": 5520 }, { - "epoch": 0.05, - "learning_rate": 4.79596432753806e-05, - "loss": 0.4991, + "epoch": 0.01, + "learning_rate": 4.949329992617615e-05, + "loss": 0.4964, "step": 5530 }, { - "epoch": 0.05, - "learning_rate": 4.795513917665075e-05, - "loss": 0.4882, + "epoch": 0.01, + "learning_rate": 4.9492181382966826e-05, + "loss": 0.4973, "step": 5540 }, { - "epoch": 0.05, - "learning_rate": 4.795063507792091e-05, - "loss": 0.4846, + "epoch": 0.01, + "learning_rate": 4.9491062839757504e-05, + "loss": 0.5024, "step": 5550 }, { - "epoch": 0.05, - "learning_rate": 4.794613097919107e-05, - "loss": 0.4884, + "epoch": 0.01, + "learning_rate": 4.948994429654818e-05, + "loss": 0.4898, "step": 5560 }, { - "epoch": 0.05, - "learning_rate": 4.7941626880461224e-05, - "loss": 0.4951, + "epoch": 0.01, + "learning_rate": 4.948882575333885e-05, + "loss": 0.499, "step": 5570 }, { - "epoch": 0.05, - "learning_rate": 4.793712278173138e-05, - "loss": 0.4937, + "epoch": 0.01, + "learning_rate": 4.948770721012953e-05, + "loss": 0.4948, "step": 5580 }, { - "epoch": 0.05, - "learning_rate": 4.793261868300153e-05, - "loss": 0.4953, + "epoch": 0.01, + "learning_rate": 4.94865886669202e-05, + "loss": 0.4968, "step": 5590 }, { - "epoch": 0.05, - "learning_rate": 4.792811458427169e-05, - "loss": 0.4963, + "epoch": 0.01, + "learning_rate": 4.948547012371088e-05, + "loss": 0.4975, "step": 5600 }, { - "epoch": 0.05, - "learning_rate": 4.792361048554185e-05, - "loss": 0.4959, + "epoch": 0.01, + "learning_rate": 4.948435158050156e-05, + "loss": 0.5025, "step": 5610 }, { - "epoch": 0.05, - "learning_rate": 4.7919106386812005e-05, - "loss": 0.4988, + "epoch": 0.01, + "learning_rate": 4.948323303729223e-05, + "loss": 0.496, "step": 5620 }, { - "epoch": 0.05, - "learning_rate": 4.7914602288082156e-05, - "loss": 0.4915, + "epoch": 0.01, + "learning_rate": 4.948211449408291e-05, + "loss": 0.5001, "step": 5630 }, { - "epoch": 0.05, - "learning_rate": 4.791009818935231e-05, - "loss": 0.4896, + "epoch": 0.01, + "learning_rate": 4.9480995950873585e-05, + "loss": 0.4992, "step": 5640 }, { - "epoch": 0.05, - "learning_rate": 4.790559409062247e-05, - "loss": 0.4882, + "epoch": 0.01, + "learning_rate": 4.947987740766426e-05, + "loss": 0.4972, "step": 5650 }, { - "epoch": 0.05, - "learning_rate": 4.790108999189262e-05, - "loss": 0.4927, + "epoch": 0.01, + "learning_rate": 4.947875886445494e-05, + "loss": 0.4938, "step": 5660 }, { - "epoch": 0.05, - "learning_rate": 4.789658589316278e-05, - "loss": 0.4839, + "epoch": 0.01, + "learning_rate": 4.947764032124561e-05, + "loss": 0.5016, "step": 5670 }, { - "epoch": 0.05, - "learning_rate": 4.7892081794432936e-05, - "loss": 0.486, + "epoch": 0.01, + "learning_rate": 4.947652177803629e-05, + "loss": 0.4983, "step": 5680 }, { - "epoch": 0.05, - "learning_rate": 4.788757769570309e-05, - "loss": 0.487, + "epoch": 0.01, + "learning_rate": 4.947540323482696e-05, + "loss": 0.4942, "step": 5690 }, { - "epoch": 0.05, - "learning_rate": 4.788307359697325e-05, - "loss": 0.4852, + "epoch": 0.01, + "learning_rate": 4.947428469161764e-05, + "loss": 0.4969, "step": 5700 }, { - "epoch": 0.05, - "learning_rate": 4.78785694982434e-05, - "loss": 0.4874, + "epoch": 0.01, + "learning_rate": 4.947316614840832e-05, + "loss": 0.4947, "step": 5710 }, { - "epoch": 0.05, - "learning_rate": 4.787406539951356e-05, - "loss": 0.4999, + "epoch": 0.01, + "learning_rate": 4.947204760519899e-05, + "loss": 0.4942, "step": 5720 }, { - "epoch": 0.05, - "learning_rate": 4.786956130078372e-05, - "loss": 0.4855, + "epoch": 0.01, + "learning_rate": 4.9470929061989666e-05, + "loss": 0.4922, "step": 5730 }, { - "epoch": 0.05, - "learning_rate": 4.786505720205387e-05, - "loss": 0.4927, + "epoch": 0.01, + "learning_rate": 4.9469810518780344e-05, + "loss": 0.483, "step": 5740 }, { - "epoch": 0.05, - "learning_rate": 4.786055310332403e-05, - "loss": 0.4927, + "epoch": 0.01, + "learning_rate": 4.946869197557102e-05, + "loss": 0.4924, "step": 5750 }, { - "epoch": 0.05, - "learning_rate": 4.785604900459418e-05, - "loss": 0.4917, + "epoch": 0.01, + "learning_rate": 4.94675734323617e-05, + "loss": 0.4888, "step": 5760 }, { - "epoch": 0.05, - "learning_rate": 4.785154490586434e-05, - "loss": 0.4843, + "epoch": 0.01, + "learning_rate": 4.946645488915237e-05, + "loss": 0.4922, "step": 5770 }, { - "epoch": 0.05, - "learning_rate": 4.78470408071345e-05, - "loss": 0.4861, + "epoch": 0.01, + "learning_rate": 4.946533634594305e-05, + "loss": 0.497, "step": 5780 }, { - "epoch": 0.05, - "learning_rate": 4.784253670840465e-05, - "loss": 0.4865, + "epoch": 0.01, + "learning_rate": 4.946421780273372e-05, + "loss": 0.4878, "step": 5790 }, { - "epoch": 0.05, - "learning_rate": 4.7838032609674806e-05, - "loss": 0.4785, + "epoch": 0.01, + "learning_rate": 4.94630992595244e-05, + "loss": 0.4921, "step": 5800 }, { - "epoch": 0.05, - "learning_rate": 4.783352851094496e-05, - "loss": 0.486, + "epoch": 0.01, + "learning_rate": 4.9461980716315076e-05, + "loss": 0.4895, "step": 5810 }, { - "epoch": 0.05, - "learning_rate": 4.782902441221512e-05, - "loss": 0.4827, + "epoch": 0.01, + "learning_rate": 4.946086217310575e-05, + "loss": 0.493, "step": 5820 }, { - "epoch": 0.05, - "learning_rate": 4.782452031348527e-05, - "loss": 0.4852, + "epoch": 0.01, + "learning_rate": 4.9459743629896425e-05, + "loss": 0.489, "step": 5830 }, { - "epoch": 0.05, - "learning_rate": 4.782001621475543e-05, - "loss": 0.4819, + "epoch": 0.01, + "learning_rate": 4.9458625086687096e-05, + "loss": 0.4845, "step": 5840 }, { - "epoch": 0.05, - "learning_rate": 4.7815512116025587e-05, - "loss": 0.4837, + "epoch": 0.01, + "learning_rate": 4.9457506543477774e-05, + "loss": 0.4901, "step": 5850 }, { - "epoch": 0.05, - "learning_rate": 4.781100801729574e-05, - "loss": 0.488, + "epoch": 0.01, + "learning_rate": 4.945638800026846e-05, + "loss": 0.486, "step": 5860 }, { - "epoch": 0.05, - "learning_rate": 4.7806503918565895e-05, - "loss": 0.4852, + "epoch": 0.01, + "learning_rate": 4.945526945705913e-05, + "loss": 0.4906, "step": 5870 }, { - "epoch": 0.05, - "learning_rate": 4.780199981983605e-05, - "loss": 0.4879, + "epoch": 0.01, + "learning_rate": 4.945415091384981e-05, + "loss": 0.4961, "step": 5880 }, { - "epoch": 0.05, - "learning_rate": 4.779749572110621e-05, - "loss": 0.489, + "epoch": 0.01, + "learning_rate": 4.945303237064048e-05, + "loss": 0.4902, "step": 5890 }, { - "epoch": 0.05, - "learning_rate": 4.779299162237637e-05, - "loss": 0.4785, + "epoch": 0.01, + "learning_rate": 4.945191382743116e-05, + "loss": 0.4959, "step": 5900 }, { - "epoch": 0.05, - "learning_rate": 4.778848752364652e-05, - "loss": 0.4834, + "epoch": 0.01, + "learning_rate": 4.945079528422183e-05, + "loss": 0.4887, "step": 5910 }, { - "epoch": 0.05, - "learning_rate": 4.7783983424916675e-05, - "loss": 0.4749, + "epoch": 0.01, + "learning_rate": 4.9449676741012506e-05, + "loss": 0.4808, "step": 5920 }, { - "epoch": 0.05, - "learning_rate": 4.777947932618683e-05, - "loss": 0.4841, + "epoch": 0.01, + "learning_rate": 4.9448558197803184e-05, + "loss": 0.49, "step": 5930 }, { - "epoch": 0.05, - "learning_rate": 4.7774975227456984e-05, - "loss": 0.4821, + "epoch": 0.01, + "learning_rate": 4.9447439654593855e-05, + "loss": 0.4874, "step": 5940 }, { - "epoch": 0.05, - "learning_rate": 4.777047112872715e-05, - "loss": 0.4818, + "epoch": 0.01, + "learning_rate": 4.944632111138453e-05, + "loss": 0.4939, "step": 5950 }, { - "epoch": 0.05, - "learning_rate": 4.77659670299973e-05, - "loss": 0.4799, + "epoch": 0.01, + "learning_rate": 4.944520256817521e-05, + "loss": 0.4931, "step": 5960 }, { - "epoch": 0.05, - "learning_rate": 4.7761462931267456e-05, - "loss": 0.4845, + "epoch": 0.01, + "learning_rate": 4.944408402496589e-05, + "loss": 0.496, "step": 5970 }, { - "epoch": 0.05, - "learning_rate": 4.7756958832537614e-05, - "loss": 0.4808, + "epoch": 0.01, + "learning_rate": 4.944296548175657e-05, + "loss": 0.4918, "step": 5980 }, { - "epoch": 0.05, - "learning_rate": 4.7752454733807764e-05, - "loss": 0.4817, + "epoch": 0.01, + "learning_rate": 4.944184693854724e-05, + "loss": 0.4914, "step": 5990 }, { - "epoch": 0.05, - "learning_rate": 4.774795063507792e-05, - "loss": 0.4811, + "epoch": 0.01, + "learning_rate": 4.9440728395337916e-05, + "loss": 0.4809, "step": 6000 }, { - "epoch": 0.05, - "learning_rate": 4.774344653634808e-05, - "loss": 0.4869, + "epoch": 0.01, + "learning_rate": 4.943960985212859e-05, + "loss": 0.4828, "step": 6010 }, { - "epoch": 0.05, - "learning_rate": 4.773894243761824e-05, - "loss": 0.4907, + "epoch": 0.01, + "learning_rate": 4.9438491308919265e-05, + "loss": 0.4865, "step": 6020 }, { - "epoch": 0.05, - "learning_rate": 4.7734438338888394e-05, - "loss": 0.4819, + "epoch": 0.01, + "learning_rate": 4.943737276570994e-05, + "loss": 0.4817, "step": 6030 }, { - "epoch": 0.05, - "learning_rate": 4.7729934240158545e-05, - "loss": 0.4809, + "epoch": 0.01, + "learning_rate": 4.9436254222500614e-05, + "loss": 0.4921, "step": 6040 }, { - "epoch": 0.05, - "learning_rate": 4.77254301414287e-05, - "loss": 0.4842, + "epoch": 0.01, + "learning_rate": 4.943513567929129e-05, + "loss": 0.4963, "step": 6050 }, { - "epoch": 0.05, - "learning_rate": 4.772092604269886e-05, - "loss": 0.481, + "epoch": 0.01, + "learning_rate": 4.943401713608197e-05, + "loss": 0.4823, "step": 6060 }, { - "epoch": 0.05, - "learning_rate": 4.771642194396902e-05, - "loss": 0.4821, + "epoch": 0.01, + "learning_rate": 4.943289859287265e-05, + "loss": 0.4848, "step": 6070 }, { - "epoch": 0.05, - "learning_rate": 4.771191784523917e-05, - "loss": 0.4771, + "epoch": 0.01, + "learning_rate": 4.9431780049663326e-05, + "loss": 0.4916, "step": 6080 }, { - "epoch": 0.05, - "learning_rate": 4.7707413746509326e-05, - "loss": 0.4883, + "epoch": 0.01, + "learning_rate": 4.9430661506454e-05, + "loss": 0.4826, "step": 6090 }, { - "epoch": 0.05, - "learning_rate": 4.770290964777948e-05, - "loss": 0.4789, + "epoch": 0.01, + "learning_rate": 4.9429542963244675e-05, + "loss": 0.488, "step": 6100 }, { - "epoch": 0.05, - "learning_rate": 4.7698405549049634e-05, - "loss": 0.4801, + "epoch": 0.01, + "learning_rate": 4.9428424420035346e-05, + "loss": 0.48, "step": 6110 }, { - "epoch": 0.05, - "learning_rate": 4.769390145031979e-05, - "loss": 0.4812, + "epoch": 0.01, + "learning_rate": 4.9427305876826024e-05, + "loss": 0.4866, "step": 6120 }, { - "epoch": 0.05, - "learning_rate": 4.768939735158995e-05, + "epoch": 0.01, + "learning_rate": 4.94261873336167e-05, "loss": 0.4795, "step": 6130 }, { - "epoch": 0.05, - "learning_rate": 4.76848932528601e-05, - "loss": 0.4765, + "epoch": 0.01, + "learning_rate": 4.942506879040737e-05, + "loss": 0.4769, "step": 6140 }, { - "epoch": 0.05, - "learning_rate": 4.7680389154130264e-05, - "loss": 0.4835, + "epoch": 0.01, + "learning_rate": 4.942395024719805e-05, + "loss": 0.4789, "step": 6150 }, { - "epoch": 0.05, - "learning_rate": 4.7675885055400415e-05, - "loss": 0.4804, + "epoch": 0.01, + "learning_rate": 4.942283170398873e-05, + "loss": 0.4768, "step": 6160 }, { - "epoch": 0.06, - "learning_rate": 4.767138095667057e-05, - "loss": 0.4768, + "epoch": 0.01, + "learning_rate": 4.942171316077941e-05, + "loss": 0.4885, "step": 6170 }, { - "epoch": 0.06, - "learning_rate": 4.766687685794073e-05, - "loss": 0.4778, + "epoch": 0.01, + "learning_rate": 4.9420594617570085e-05, + "loss": 0.4829, "step": 6180 }, { - "epoch": 0.06, - "learning_rate": 4.766237275921088e-05, - "loss": 0.4706, + "epoch": 0.01, + "learning_rate": 4.9419476074360756e-05, + "loss": 0.4771, "step": 6190 }, { - "epoch": 0.06, - "learning_rate": 4.7657868660481045e-05, - "loss": 0.4827, + "epoch": 0.01, + "learning_rate": 4.9418357531151434e-05, + "loss": 0.4867, "step": 6200 }, { - "epoch": 0.06, - "learning_rate": 4.7653364561751195e-05, - "loss": 0.4738, + "epoch": 0.01, + "learning_rate": 4.9417238987942105e-05, + "loss": 0.4809, "step": 6210 }, { - "epoch": 0.06, - "learning_rate": 4.764886046302135e-05, - "loss": 0.4757, + "epoch": 0.01, + "learning_rate": 4.941612044473278e-05, + "loss": 0.4839, "step": 6220 }, { - "epoch": 0.06, - "learning_rate": 4.764435636429151e-05, - "loss": 0.4799, + "epoch": 0.01, + "learning_rate": 4.9415001901523454e-05, + "loss": 0.4828, "step": 6230 }, { - "epoch": 0.06, - "learning_rate": 4.763985226556166e-05, - "loss": 0.4713, + "epoch": 0.01, + "learning_rate": 4.941388335831413e-05, + "loss": 0.4869, "step": 6240 }, { - "epoch": 0.06, - "learning_rate": 4.763534816683182e-05, - "loss": 0.4699, + "epoch": 0.01, + "learning_rate": 4.941276481510481e-05, + "loss": 0.4909, "step": 6250 }, { - "epoch": 0.06, - "learning_rate": 4.7630844068101976e-05, - "loss": 0.4725, + "epoch": 0.01, + "learning_rate": 4.941164627189548e-05, + "loss": 0.4825, "step": 6260 }, { - "epoch": 0.06, - "learning_rate": 4.7626339969372133e-05, - "loss": 0.4737, + "epoch": 0.01, + "learning_rate": 4.941052772868616e-05, + "loss": 0.4828, "step": 6270 }, { - "epoch": 0.06, - "learning_rate": 4.7621835870642284e-05, - "loss": 0.4824, + "epoch": 0.01, + "learning_rate": 4.940940918547684e-05, + "loss": 0.4834, "step": 6280 }, { - "epoch": 0.06, - "learning_rate": 4.761733177191244e-05, - "loss": 0.4754, + "epoch": 0.01, + "learning_rate": 4.9408290642267515e-05, + "loss": 0.4798, "step": 6290 }, { - "epoch": 0.06, - "learning_rate": 4.76128276731826e-05, - "loss": 0.4784, + "epoch": 0.01, + "learning_rate": 4.940717209905819e-05, + "loss": 0.4775, "step": 6300 }, { - "epoch": 0.06, - "learning_rate": 4.7608323574452757e-05, - "loss": 0.4798, + "epoch": 0.01, + "learning_rate": 4.9406053555848864e-05, + "loss": 0.5057, "step": 6310 }, { - "epoch": 0.06, - "learning_rate": 4.760381947572291e-05, - "loss": 0.4668, + "epoch": 0.01, + "learning_rate": 4.940493501263954e-05, + "loss": 0.4889, "step": 6320 }, { - "epoch": 0.06, - "learning_rate": 4.7599315376993065e-05, - "loss": 0.4731, + "epoch": 0.01, + "learning_rate": 4.940381646943021e-05, + "loss": 0.4881, "step": 6330 }, { - "epoch": 0.06, - "learning_rate": 4.759481127826322e-05, - "loss": 0.4688, + "epoch": 0.01, + "learning_rate": 4.940269792622089e-05, + "loss": 0.4773, "step": 6340 }, { - "epoch": 0.06, - "learning_rate": 4.759030717953338e-05, - "loss": 0.4738, + "epoch": 0.01, + "learning_rate": 4.940157938301157e-05, + "loss": 0.4786, "step": 6350 }, { - "epoch": 0.06, - "learning_rate": 4.758580308080353e-05, - "loss": 0.4716, + "epoch": 0.01, + "learning_rate": 4.940046083980224e-05, + "loss": 0.4829, "step": 6360 }, { - "epoch": 0.06, - "learning_rate": 4.758129898207369e-05, - "loss": 0.4722, + "epoch": 0.01, + "learning_rate": 4.939934229659292e-05, + "loss": 0.4682, "step": 6370 }, { - "epoch": 0.06, - "learning_rate": 4.7576794883343845e-05, - "loss": 0.4708, + "epoch": 0.01, + "learning_rate": 4.9398223753383596e-05, + "loss": 0.4783, "step": 6380 }, { - "epoch": 0.06, - "learning_rate": 4.7572290784613996e-05, - "loss": 0.4769, + "epoch": 0.01, + "learning_rate": 4.9397105210174274e-05, + "loss": 0.4826, "step": 6390 }, { - "epoch": 0.06, - "learning_rate": 4.756778668588416e-05, - "loss": 0.4841, + "epoch": 0.01, + "learning_rate": 4.939598666696495e-05, + "loss": 0.4823, "step": 6400 }, { - "epoch": 0.06, - "learning_rate": 4.756328258715431e-05, - "loss": 0.4659, + "epoch": 0.01, + "learning_rate": 4.939486812375562e-05, + "loss": 0.4839, "step": 6410 }, { - "epoch": 0.06, - "learning_rate": 4.755877848842447e-05, - "loss": 0.4707, + "epoch": 0.01, + "learning_rate": 4.93937495805463e-05, + "loss": 0.4785, "step": 6420 }, { - "epoch": 0.06, - "learning_rate": 4.7554274389694626e-05, - "loss": 0.4651, + "epoch": 0.01, + "learning_rate": 4.939263103733697e-05, + "loss": 0.4754, "step": 6430 }, { - "epoch": 0.06, - "learning_rate": 4.754977029096478e-05, - "loss": 0.47, + "epoch": 0.01, + "learning_rate": 4.939151249412765e-05, + "loss": 0.4798, "step": 6440 }, { - "epoch": 0.06, - "learning_rate": 4.754526619223494e-05, - "loss": 0.4697, + "epoch": 0.01, + "learning_rate": 4.939039395091833e-05, + "loss": 0.4779, "step": 6450 }, { - "epoch": 0.06, - "learning_rate": 4.754076209350509e-05, - "loss": 0.4685, + "epoch": 0.01, + "learning_rate": 4.9389275407709e-05, + "loss": 0.4725, "step": 6460 }, { - "epoch": 0.06, - "learning_rate": 4.753625799477525e-05, - "loss": 0.4718, + "epoch": 0.01, + "learning_rate": 4.938815686449968e-05, + "loss": 0.4778, "step": 6470 }, { - "epoch": 0.06, - "learning_rate": 4.753175389604541e-05, - "loss": 0.4688, + "epoch": 0.01, + "learning_rate": 4.9387038321290355e-05, + "loss": 0.4838, "step": 6480 }, { - "epoch": 0.06, - "learning_rate": 4.752724979731556e-05, - "loss": 0.4705, + "epoch": 0.01, + "learning_rate": 4.938591977808103e-05, + "loss": 0.4724, "step": 6490 }, { - "epoch": 0.06, - "learning_rate": 4.7522745698585715e-05, + "epoch": 0.01, + "learning_rate": 4.938480123487171e-05, "loss": 0.4787, "step": 6500 }, { - "epoch": 0.06, - "learning_rate": 4.751824159985587e-05, - "loss": 0.4714, + "epoch": 0.01, + "learning_rate": 4.938368269166238e-05, + "loss": 0.4782, "step": 6510 }, { - "epoch": 0.06, - "learning_rate": 4.751373750112602e-05, - "loss": 0.4659, + "epoch": 0.01, + "learning_rate": 4.938256414845306e-05, + "loss": 0.4747, "step": 6520 }, { - "epoch": 0.06, - "learning_rate": 4.750923340239618e-05, - "loss": 0.4721, + "epoch": 0.01, + "learning_rate": 4.938144560524373e-05, + "loss": 0.4794, "step": 6530 }, { - "epoch": 0.06, - "learning_rate": 4.750472930366634e-05, - "loss": 0.4701, + "epoch": 0.01, + "learning_rate": 4.938032706203441e-05, + "loss": 0.4721, "step": 6540 }, { - "epoch": 0.06, - "learning_rate": 4.7500225204936496e-05, - "loss": 0.4704, + "epoch": 0.01, + "learning_rate": 4.937920851882508e-05, + "loss": 0.4765, "step": 6550 }, { - "epoch": 0.06, - "learning_rate": 4.7495721106206646e-05, - "loss": 0.4699, + "epoch": 0.01, + "learning_rate": 4.937808997561576e-05, + "loss": 0.4735, "step": 6560 }, { - "epoch": 0.06, - "learning_rate": 4.7491217007476804e-05, - "loss": 0.4692, + "epoch": 0.01, + "learning_rate": 4.9376971432406436e-05, + "loss": 0.472, "step": 6570 }, { - "epoch": 0.06, - "learning_rate": 4.748671290874696e-05, - "loss": 0.4699, + "epoch": 0.01, + "learning_rate": 4.9375852889197114e-05, + "loss": 0.4778, "step": 6580 }, { - "epoch": 0.06, - "learning_rate": 4.748220881001712e-05, - "loss": 0.4725, + "epoch": 0.01, + "learning_rate": 4.937473434598779e-05, + "loss": 0.4695, "step": 6590 }, { - "epoch": 0.06, - "learning_rate": 4.7477704711287276e-05, - "loss": 0.4656, + "epoch": 0.01, + "learning_rate": 4.937361580277846e-05, + "loss": 0.473, "step": 6600 }, { - "epoch": 0.06, - "learning_rate": 4.747320061255743e-05, - "loss": 0.4645, + "epoch": 0.01, + "learning_rate": 4.937249725956914e-05, + "loss": 0.469, "step": 6610 }, { - "epoch": 0.06, - "learning_rate": 4.7468696513827585e-05, - "loss": 0.4674, + "epoch": 0.01, + "learning_rate": 4.937137871635982e-05, + "loss": 0.4673, "step": 6620 }, { - "epoch": 0.06, - "learning_rate": 4.746419241509774e-05, - "loss": 0.475, + "epoch": 0.01, + "learning_rate": 4.937026017315049e-05, + "loss": 0.4737, "step": 6630 }, { - "epoch": 0.06, - "learning_rate": 4.745968831636789e-05, - "loss": 0.4701, + "epoch": 0.01, + "learning_rate": 4.936914162994117e-05, + "loss": 0.4738, "step": 6640 }, { - "epoch": 0.06, - "learning_rate": 4.745518421763806e-05, - "loss": 0.471, + "epoch": 0.01, + "learning_rate": 4.936802308673184e-05, + "loss": 0.469, "step": 6650 }, { - "epoch": 0.06, - "learning_rate": 4.745068011890821e-05, - "loss": 0.4634, + "epoch": 0.01, + "learning_rate": 4.936690454352252e-05, + "loss": 0.4738, "step": 6660 }, { - "epoch": 0.06, - "learning_rate": 4.7446176020178365e-05, - "loss": 0.4669, + "epoch": 0.01, + "learning_rate": 4.9365786000313195e-05, + "loss": 0.473, "step": 6670 }, { - "epoch": 0.06, - "learning_rate": 4.744167192144852e-05, - "loss": 0.477, + "epoch": 0.01, + "learning_rate": 4.9364667457103866e-05, + "loss": 0.4769, "step": 6680 }, { - "epoch": 0.06, - "learning_rate": 4.7437167822718674e-05, - "loss": 0.4706, + "epoch": 0.01, + "learning_rate": 4.936354891389455e-05, + "loss": 0.466, "step": 6690 }, { - "epoch": 0.06, - "learning_rate": 4.743266372398883e-05, - "loss": 0.4631, + "epoch": 0.01, + "learning_rate": 4.936243037068522e-05, + "loss": 0.4748, "step": 6700 }, { - "epoch": 0.06, - "learning_rate": 4.742815962525899e-05, - "loss": 0.4605, + "epoch": 0.01, + "learning_rate": 4.93613118274759e-05, + "loss": 0.4709, "step": 6710 }, { - "epoch": 0.06, - "learning_rate": 4.7423655526529146e-05, - "loss": 0.4624, + "epoch": 0.01, + "learning_rate": 4.936019328426658e-05, + "loss": 0.4692, "step": 6720 }, { - "epoch": 0.06, - "learning_rate": 4.7419151427799304e-05, - "loss": 0.4602, + "epoch": 0.02, + "learning_rate": 4.935907474105725e-05, + "loss": 0.4701, "step": 6730 }, { - "epoch": 0.06, - "learning_rate": 4.7414647329069454e-05, - "loss": 0.4651, + "epoch": 0.02, + "learning_rate": 4.935795619784793e-05, + "loss": 0.4667, "step": 6740 }, { - "epoch": 0.06, - "learning_rate": 4.741014323033961e-05, - "loss": 0.4632, + "epoch": 0.02, + "learning_rate": 4.93568376546386e-05, + "loss": 0.4735, "step": 6750 }, { - "epoch": 0.06, - "learning_rate": 4.740563913160977e-05, - "loss": 0.4608, + "epoch": 0.02, + "learning_rate": 4.9355719111429276e-05, + "loss": 0.4717, "step": 6760 }, { - "epoch": 0.06, - "learning_rate": 4.740113503287992e-05, - "loss": 0.4642, + "epoch": 0.02, + "learning_rate": 4.9354600568219954e-05, + "loss": 0.4793, "step": 6770 }, { - "epoch": 0.06, - "learning_rate": 4.739663093415008e-05, - "loss": 0.4609, + "epoch": 0.02, + "learning_rate": 4.9353482025010625e-05, + "loss": 0.4721, "step": 6780 }, { - "epoch": 0.06, - "learning_rate": 4.7392126835420235e-05, - "loss": 0.4711, + "epoch": 0.02, + "learning_rate": 4.93523634818013e-05, + "loss": 0.4762, "step": 6790 }, { - "epoch": 0.06, - "learning_rate": 4.738762273669039e-05, - "loss": 0.4691, + "epoch": 0.02, + "learning_rate": 4.935124493859198e-05, + "loss": 0.4704, "step": 6800 }, { - "epoch": 0.06, - "learning_rate": 4.738311863796054e-05, - "loss": 0.4581, + "epoch": 0.02, + "learning_rate": 4.935012639538266e-05, + "loss": 0.4678, "step": 6810 }, { - "epoch": 0.06, - "learning_rate": 4.73786145392307e-05, - "loss": 0.4652, + "epoch": 0.02, + "learning_rate": 4.9349007852173337e-05, + "loss": 0.4729, "step": 6820 }, { - "epoch": 0.06, - "learning_rate": 4.737411044050086e-05, - "loss": 0.4605, + "epoch": 0.02, + "learning_rate": 4.934788930896401e-05, + "loss": 0.4751, "step": 6830 }, { - "epoch": 0.06, - "learning_rate": 4.736960634177101e-05, - "loss": 0.4673, + "epoch": 0.02, + "learning_rate": 4.9346770765754686e-05, + "loss": 0.4699, "step": 6840 }, { - "epoch": 0.06, - "learning_rate": 4.736510224304117e-05, - "loss": 0.4621, + "epoch": 0.02, + "learning_rate": 4.934565222254536e-05, + "loss": 0.4693, "step": 6850 }, { - "epoch": 0.06, - "learning_rate": 4.7360598144311324e-05, - "loss": 0.4601, + "epoch": 0.02, + "learning_rate": 4.9344533679336035e-05, + "loss": 0.4615, "step": 6860 }, { - "epoch": 0.06, - "learning_rate": 4.735609404558148e-05, - "loss": 0.4636, + "epoch": 0.02, + "learning_rate": 4.9343415136126706e-05, + "loss": 0.4729, "step": 6870 }, { - "epoch": 0.06, - "learning_rate": 4.735158994685164e-05, - "loss": 0.464, + "epoch": 0.02, + "learning_rate": 4.9342296592917384e-05, + "loss": 0.4649, "step": 6880 }, { - "epoch": 0.06, - "learning_rate": 4.734708584812179e-05, - "loss": 0.4613, + "epoch": 0.02, + "learning_rate": 4.934117804970806e-05, + "loss": 0.4661, "step": 6890 }, { - "epoch": 0.06, - "learning_rate": 4.7342581749391954e-05, - "loss": 0.4593, + "epoch": 0.02, + "learning_rate": 4.934005950649874e-05, + "loss": 0.4664, "step": 6900 }, { - "epoch": 0.06, - "learning_rate": 4.7338077650662104e-05, - "loss": 0.4559, + "epoch": 0.02, + "learning_rate": 4.933894096328942e-05, + "loss": 0.4652, "step": 6910 }, { - "epoch": 0.06, - "learning_rate": 4.733357355193226e-05, - "loss": 0.4626, + "epoch": 0.02, + "learning_rate": 4.933782242008009e-05, + "loss": 0.463, "step": 6920 }, { - "epoch": 0.06, - "learning_rate": 4.732906945320242e-05, + "epoch": 0.02, + "learning_rate": 4.933670387687077e-05, "loss": 0.4659, "step": 6930 }, { - "epoch": 0.06, - "learning_rate": 4.732456535447257e-05, - "loss": 0.4651, + "epoch": 0.02, + "learning_rate": 4.9335585333661445e-05, + "loss": 0.4692, "step": 6940 }, { - "epoch": 0.06, - "learning_rate": 4.732006125574273e-05, - "loss": 0.4608, + "epoch": 0.02, + "learning_rate": 4.9334466790452116e-05, + "loss": 0.4661, "step": 6950 }, { - "epoch": 0.06, - "learning_rate": 4.7315557157012885e-05, - "loss": 0.4626, + "epoch": 0.02, + "learning_rate": 4.9333348247242794e-05, + "loss": 0.4629, "step": 6960 }, { - "epoch": 0.06, - "learning_rate": 4.7311053058283036e-05, - "loss": 0.4504, + "epoch": 0.02, + "learning_rate": 4.9332229704033465e-05, + "loss": 0.4692, "step": 6970 }, { - "epoch": 0.06, - "learning_rate": 4.730654895955319e-05, - "loss": 0.4611, + "epoch": 0.02, + "learning_rate": 4.933111116082414e-05, + "loss": 0.4657, "step": 6980 }, { - "epoch": 0.06, - "learning_rate": 4.730204486082335e-05, - "loss": 0.4561, + "epoch": 0.02, + "learning_rate": 4.932999261761482e-05, + "loss": 0.4611, "step": 6990 }, { - "epoch": 0.06, - "learning_rate": 4.729754076209351e-05, - "loss": 0.4556, + "epoch": 0.02, + "learning_rate": 4.93288740744055e-05, + "loss": 0.4687, "step": 7000 }, { - "epoch": 0.06, - "learning_rate": 4.7293036663363666e-05, - "loss": 0.459, + "epoch": 0.02, + "learning_rate": 4.9327755531196177e-05, + "loss": 0.4634, "step": 7010 }, { - "epoch": 0.06, - "learning_rate": 4.7288532564633817e-05, - "loss": 0.4649, + "epoch": 0.02, + "learning_rate": 4.932663698798685e-05, + "loss": 0.4771, "step": 7020 }, { - "epoch": 0.06, - "learning_rate": 4.7284028465903974e-05, - "loss": 0.4576, + "epoch": 0.02, + "learning_rate": 4.9325518444777526e-05, + "loss": 0.4646, "step": 7030 }, { - "epoch": 0.06, - "learning_rate": 4.727952436717413e-05, - "loss": 0.4645, + "epoch": 0.02, + "learning_rate": 4.9324399901568204e-05, + "loss": 0.4709, "step": 7040 }, { - "epoch": 0.06, - "learning_rate": 4.727502026844429e-05, - "loss": 0.4677, + "epoch": 0.02, + "learning_rate": 4.9323281358358875e-05, + "loss": 0.4733, "step": 7050 }, { - "epoch": 0.06, - "learning_rate": 4.727051616971444e-05, - "loss": 0.4592, + "epoch": 0.02, + "learning_rate": 4.932216281514955e-05, + "loss": 0.4696, "step": 7060 }, { - "epoch": 0.06, - "learning_rate": 4.72660120709846e-05, - "loss": 0.4596, + "epoch": 0.02, + "learning_rate": 4.9321044271940224e-05, + "loss": 0.4682, "step": 7070 }, { - "epoch": 0.06, - "learning_rate": 4.7261507972254755e-05, - "loss": 0.4563, + "epoch": 0.02, + "learning_rate": 4.93199257287309e-05, + "loss": 0.4648, "step": 7080 }, { - "epoch": 0.06, - "learning_rate": 4.7257003873524905e-05, - "loss": 0.4632, + "epoch": 0.02, + "learning_rate": 4.931880718552158e-05, + "loss": 0.4603, "step": 7090 }, { - "epoch": 0.06, - "learning_rate": 4.725249977479507e-05, - "loss": 0.4574, + "epoch": 0.02, + "learning_rate": 4.931768864231225e-05, + "loss": 0.4663, "step": 7100 }, { - "epoch": 0.06, - "learning_rate": 4.724799567606522e-05, - "loss": 0.4519, + "epoch": 0.02, + "learning_rate": 4.9316570099102935e-05, + "loss": 0.4642, "step": 7110 }, { - "epoch": 0.06, - "learning_rate": 4.724349157733538e-05, - "loss": 0.4637, + "epoch": 0.02, + "learning_rate": 4.931545155589361e-05, + "loss": 0.4679, "step": 7120 }, { - "epoch": 0.06, - "learning_rate": 4.7238987478605535e-05, - "loss": 0.4606, + "epoch": 0.02, + "learning_rate": 4.9314333012684285e-05, + "loss": 0.4662, "step": 7130 }, { - "epoch": 0.06, - "learning_rate": 4.7234483379875686e-05, - "loss": 0.4589, + "epoch": 0.02, + "learning_rate": 4.931321446947496e-05, + "loss": 0.4704, "step": 7140 }, { - "epoch": 0.06, - "learning_rate": 4.722997928114585e-05, - "loss": 0.4564, + "epoch": 0.02, + "learning_rate": 4.9312095926265634e-05, + "loss": 0.4621, "step": 7150 }, { - "epoch": 0.06, - "learning_rate": 4.7225475182416e-05, - "loss": 0.458, + "epoch": 0.02, + "learning_rate": 4.931097738305631e-05, + "loss": 0.4619, "step": 7160 }, { - "epoch": 0.06, - "learning_rate": 4.722097108368615e-05, - "loss": 0.4643, + "epoch": 0.02, + "learning_rate": 4.930985883984698e-05, + "loss": 0.4619, "step": 7170 }, { - "epoch": 0.06, - "learning_rate": 4.7216466984956316e-05, - "loss": 0.4613, + "epoch": 0.02, + "learning_rate": 4.930874029663766e-05, + "loss": 0.458, "step": 7180 }, { - "epoch": 0.06, - "learning_rate": 4.721196288622647e-05, - "loss": 0.4594, + "epoch": 0.02, + "learning_rate": 4.930762175342833e-05, + "loss": 0.463, "step": 7190 }, { - "epoch": 0.06, - "learning_rate": 4.7207458787496624e-05, - "loss": 0.4554, + "epoch": 0.02, + "learning_rate": 4.930650321021901e-05, + "loss": 0.4615, "step": 7200 }, { - "epoch": 0.06, - "learning_rate": 4.720295468876678e-05, - "loss": 0.4582, + "epoch": 0.02, + "learning_rate": 4.930538466700969e-05, + "loss": 0.4647, "step": 7210 }, { - "epoch": 0.06, - "learning_rate": 4.719845059003693e-05, - "loss": 0.4581, + "epoch": 0.02, + "learning_rate": 4.9304266123800366e-05, + "loss": 0.4614, "step": 7220 }, { - "epoch": 0.06, - "learning_rate": 4.719394649130709e-05, - "loss": 0.4556, + "epoch": 0.02, + "learning_rate": 4.9303147580591044e-05, + "loss": 0.4654, "step": 7230 }, { - "epoch": 0.06, - "learning_rate": 4.718944239257725e-05, - "loss": 0.4555, + "epoch": 0.02, + "learning_rate": 4.9302029037381715e-05, + "loss": 0.4642, "step": 7240 }, { - "epoch": 0.06, - "learning_rate": 4.7184938293847405e-05, - "loss": 0.4587, + "epoch": 0.02, + "learning_rate": 4.930091049417239e-05, + "loss": 0.4622, "step": 7250 }, { - "epoch": 0.06, - "learning_rate": 4.7180434195117556e-05, - "loss": 0.4608, + "epoch": 0.02, + "learning_rate": 4.929979195096307e-05, + "loss": 0.4676, "step": 7260 }, { - "epoch": 0.06, - "learning_rate": 4.717593009638771e-05, - "loss": 0.444, + "epoch": 0.02, + "learning_rate": 4.929867340775374e-05, + "loss": 0.4723, "step": 7270 }, { - "epoch": 0.06, - "learning_rate": 4.717142599765787e-05, - "loss": 0.4546, + "epoch": 0.02, + "learning_rate": 4.929755486454442e-05, + "loss": 0.4603, "step": 7280 }, { - "epoch": 0.07, - "learning_rate": 4.716692189892803e-05, - "loss": 0.4577, + "epoch": 0.02, + "learning_rate": 4.929643632133509e-05, + "loss": 0.4684, "step": 7290 }, { - "epoch": 0.07, - "learning_rate": 4.7162417800198186e-05, - "loss": 0.4527, + "epoch": 0.02, + "learning_rate": 4.929531777812577e-05, + "loss": 0.4643, "step": 7300 }, { - "epoch": 0.07, - "learning_rate": 4.7157913701468336e-05, - "loss": 0.4608, + "epoch": 0.02, + "learning_rate": 4.929419923491645e-05, + "loss": 0.4622, "step": 7310 }, { - "epoch": 0.07, - "learning_rate": 4.7153409602738494e-05, - "loss": 0.4599, + "epoch": 0.02, + "learning_rate": 4.9293080691707125e-05, + "loss": 0.4606, "step": 7320 }, { - "epoch": 0.07, - "learning_rate": 4.714890550400865e-05, - "loss": 0.4579, + "epoch": 0.02, + "learning_rate": 4.92919621484978e-05, + "loss": 0.4633, "step": 7330 }, { - "epoch": 0.07, - "learning_rate": 4.71444014052788e-05, - "loss": 0.4503, + "epoch": 0.02, + "learning_rate": 4.9290843605288474e-05, + "loss": 0.4584, "step": 7340 }, { - "epoch": 0.07, - "learning_rate": 4.7139897306548966e-05, - "loss": 0.4478, + "epoch": 0.02, + "learning_rate": 4.928972506207915e-05, + "loss": 0.4635, "step": 7350 }, { - "epoch": 0.07, - "learning_rate": 4.713539320781912e-05, - "loss": 0.4559, + "epoch": 0.02, + "learning_rate": 4.928860651886983e-05, + "loss": 0.4681, "step": 7360 }, { - "epoch": 0.07, - "learning_rate": 4.7130889109089275e-05, - "loss": 0.4539, + "epoch": 0.02, + "learning_rate": 4.92874879756605e-05, + "loss": 0.4578, "step": 7370 }, { - "epoch": 0.07, - "learning_rate": 4.712638501035943e-05, - "loss": 0.4545, + "epoch": 0.02, + "learning_rate": 4.928636943245118e-05, + "loss": 0.4588, "step": 7380 }, { - "epoch": 0.07, - "learning_rate": 4.712188091162958e-05, - "loss": 0.452, + "epoch": 0.02, + "learning_rate": 4.928525088924185e-05, + "loss": 0.4566, "step": 7390 }, { - "epoch": 0.07, - "learning_rate": 4.711737681289974e-05, - "loss": 0.4511, + "epoch": 0.02, + "learning_rate": 4.928413234603253e-05, + "loss": 0.456, "step": 7400 }, { - "epoch": 0.07, - "learning_rate": 4.71128727141699e-05, - "loss": 0.454, + "epoch": 0.02, + "learning_rate": 4.9283013802823206e-05, + "loss": 0.4593, "step": 7410 }, { - "epoch": 0.07, - "learning_rate": 4.710836861544005e-05, - "loss": 0.4555, + "epoch": 0.02, + "learning_rate": 4.9281895259613883e-05, + "loss": 0.4622, "step": 7420 }, { - "epoch": 0.07, - "learning_rate": 4.710386451671021e-05, - "loss": 0.4583, + "epoch": 0.02, + "learning_rate": 4.928077671640456e-05, + "loss": 0.4619, "step": 7430 }, { - "epoch": 0.07, - "learning_rate": 4.7099360417980363e-05, - "loss": 0.4585, + "epoch": 0.02, + "learning_rate": 4.927965817319523e-05, + "loss": 0.4595, "step": 7440 }, { - "epoch": 0.07, - "learning_rate": 4.709485631925052e-05, - "loss": 0.4575, + "epoch": 0.02, + "learning_rate": 4.927853962998591e-05, + "loss": 0.4662, "step": 7450 }, { - "epoch": 0.07, - "learning_rate": 4.709035222052068e-05, - "loss": 0.4586, + "epoch": 0.02, + "learning_rate": 4.927742108677659e-05, + "loss": 0.4635, "step": 7460 }, { - "epoch": 0.07, - "learning_rate": 4.708584812179083e-05, - "loss": 0.4548, + "epoch": 0.02, + "learning_rate": 4.927630254356726e-05, + "loss": 0.4605, "step": 7470 }, { - "epoch": 0.07, - "learning_rate": 4.708134402306099e-05, - "loss": 0.4567, + "epoch": 0.02, + "learning_rate": 4.927518400035794e-05, + "loss": 0.4563, "step": 7480 }, { - "epoch": 0.07, - "learning_rate": 4.7076839924331144e-05, - "loss": 0.4568, + "epoch": 0.02, + "learning_rate": 4.927406545714861e-05, + "loss": 0.4629, "step": 7490 }, { - "epoch": 0.07, - "learning_rate": 4.70723358256013e-05, - "loss": 0.4638, + "epoch": 0.02, + "learning_rate": 4.9272946913939287e-05, + "loss": 0.4536, "step": 7500 }, { - "epoch": 0.07, - "learning_rate": 4.706783172687145e-05, - "loss": 0.4506, + "epoch": 0.02, + "learning_rate": 4.927182837072996e-05, + "loss": 0.4537, "step": 7510 }, { - "epoch": 0.07, - "learning_rate": 4.706332762814161e-05, - "loss": 0.4497, + "epoch": 0.02, + "learning_rate": 4.927070982752064e-05, + "loss": 0.4528, "step": 7520 }, { - "epoch": 0.07, - "learning_rate": 4.705882352941177e-05, - "loss": 0.4505, + "epoch": 0.02, + "learning_rate": 4.926959128431132e-05, + "loss": 0.4498, "step": 7530 }, { - "epoch": 0.07, - "learning_rate": 4.705431943068192e-05, - "loss": 0.4499, + "epoch": 0.02, + "learning_rate": 4.926847274110199e-05, + "loss": 0.4515, "step": 7540 }, { - "epoch": 0.07, - "learning_rate": 4.704981533195208e-05, - "loss": 0.4446, + "epoch": 0.02, + "learning_rate": 4.926735419789267e-05, + "loss": 0.4545, "step": 7550 }, { - "epoch": 0.07, - "learning_rate": 4.704531123322223e-05, - "loss": 0.4461, + "epoch": 0.02, + "learning_rate": 4.926623565468334e-05, + "loss": 0.4574, "step": 7560 }, { - "epoch": 0.07, - "learning_rate": 4.704080713449239e-05, - "loss": 0.448, + "epoch": 0.02, + "learning_rate": 4.926511711147402e-05, + "loss": 0.4536, "step": 7570 }, { - "epoch": 0.07, - "learning_rate": 4.703630303576255e-05, - "loss": 0.4527, + "epoch": 0.02, + "learning_rate": 4.9263998568264696e-05, + "loss": 0.4622, "step": 7580 }, { - "epoch": 0.07, - "learning_rate": 4.70317989370327e-05, - "loss": 0.4523, + "epoch": 0.02, + "learning_rate": 4.926288002505537e-05, + "loss": 0.4575, "step": 7590 }, { - "epoch": 0.07, - "learning_rate": 4.702729483830286e-05, - "loss": 0.4528, + "epoch": 0.02, + "learning_rate": 4.9261761481846046e-05, + "loss": 0.4599, "step": 7600 }, { - "epoch": 0.07, - "learning_rate": 4.7022790739573014e-05, - "loss": 0.4479, + "epoch": 0.02, + "learning_rate": 4.926064293863672e-05, + "loss": 0.4595, "step": 7610 }, { - "epoch": 0.07, - "learning_rate": 4.7018286640843164e-05, - "loss": 0.4542, + "epoch": 0.02, + "learning_rate": 4.9259524395427395e-05, + "loss": 0.4559, "step": 7620 }, { - "epoch": 0.07, - "learning_rate": 4.701378254211333e-05, - "loss": 0.4498, + "epoch": 0.02, + "learning_rate": 4.925840585221807e-05, + "loss": 0.4491, "step": 7630 }, { - "epoch": 0.07, - "learning_rate": 4.700927844338348e-05, - "loss": 0.4534, + "epoch": 0.02, + "learning_rate": 4.925728730900875e-05, + "loss": 0.4511, "step": 7640 }, { - "epoch": 0.07, - "learning_rate": 4.700477434465364e-05, - "loss": 0.4505, + "epoch": 0.02, + "learning_rate": 4.925616876579943e-05, + "loss": 0.4525, "step": 7650 }, { - "epoch": 0.07, - "learning_rate": 4.7000270245923794e-05, - "loss": 0.445, + "epoch": 0.02, + "learning_rate": 4.92550502225901e-05, + "loss": 0.4543, "step": 7660 }, { - "epoch": 0.07, - "learning_rate": 4.6995766147193945e-05, - "loss": 0.4439, + "epoch": 0.02, + "learning_rate": 4.925393167938078e-05, + "loss": 0.4571, "step": 7670 }, { - "epoch": 0.07, - "learning_rate": 4.69912620484641e-05, - "loss": 0.4478, + "epoch": 0.02, + "learning_rate": 4.9252813136171455e-05, + "loss": 0.4512, "step": 7680 }, { - "epoch": 0.07, - "learning_rate": 4.698675794973426e-05, - "loss": 0.4442, + "epoch": 0.02, + "learning_rate": 4.9251694592962127e-05, + "loss": 0.4511, "step": 7690 }, { - "epoch": 0.07, - "learning_rate": 4.698225385100442e-05, - "loss": 0.4467, + "epoch": 0.02, + "learning_rate": 4.9250576049752804e-05, + "loss": 0.4539, "step": 7700 }, { - "epoch": 0.07, - "learning_rate": 4.6977749752274575e-05, - "loss": 0.4457, + "epoch": 0.02, + "learning_rate": 4.9249457506543476e-05, + "loss": 0.453, "step": 7710 }, { - "epoch": 0.07, - "learning_rate": 4.6973245653544726e-05, - "loss": 0.4461, + "epoch": 0.02, + "learning_rate": 4.9248338963334154e-05, + "loss": 0.4518, "step": 7720 }, { - "epoch": 0.07, - "learning_rate": 4.696874155481488e-05, - "loss": 0.4501, + "epoch": 0.02, + "learning_rate": 4.924722042012483e-05, + "loss": 0.4536, "step": 7730 }, { - "epoch": 0.07, - "learning_rate": 4.696423745608504e-05, - "loss": 0.4508, + "epoch": 0.02, + "learning_rate": 4.924610187691551e-05, + "loss": 0.4535, "step": 7740 }, { - "epoch": 0.07, - "learning_rate": 4.69597333573552e-05, - "loss": 0.4473, + "epoch": 0.02, + "learning_rate": 4.924498333370619e-05, + "loss": 0.4588, "step": 7750 }, { - "epoch": 0.07, - "learning_rate": 4.695522925862535e-05, - "loss": 0.4528, + "epoch": 0.02, + "learning_rate": 4.924386479049686e-05, + "loss": 0.4537, "step": 7760 }, { - "epoch": 0.07, - "learning_rate": 4.6950725159895507e-05, - "loss": 0.4446, + "epoch": 0.02, + "learning_rate": 4.9242746247287536e-05, + "loss": 0.4553, "step": 7770 }, { - "epoch": 0.07, - "learning_rate": 4.6946221061165664e-05, - "loss": 0.4406, + "epoch": 0.02, + "learning_rate": 4.924162770407821e-05, + "loss": 0.4489, "step": 7780 }, { - "epoch": 0.07, - "learning_rate": 4.6941716962435815e-05, - "loss": 0.4438, + "epoch": 0.02, + "learning_rate": 4.9240509160868886e-05, + "loss": 0.4557, "step": 7790 }, { - "epoch": 0.07, - "learning_rate": 4.693721286370598e-05, - "loss": 0.446, + "epoch": 0.02, + "learning_rate": 4.9239390617659563e-05, + "loss": 0.4555, "step": 7800 }, { - "epoch": 0.07, - "learning_rate": 4.693270876497613e-05, - "loss": 0.4494, + "epoch": 0.02, + "learning_rate": 4.9238272074450235e-05, + "loss": 0.4498, "step": 7810 }, { - "epoch": 0.07, - "learning_rate": 4.692820466624628e-05, - "loss": 0.4474, + "epoch": 0.02, + "learning_rate": 4.923715353124091e-05, + "loss": 0.4517, "step": 7820 }, { - "epoch": 0.07, - "learning_rate": 4.6923700567516445e-05, - "loss": 0.4492, + "epoch": 0.02, + "learning_rate": 4.923603498803159e-05, + "loss": 0.4527, "step": 7830 }, { - "epoch": 0.07, - "learning_rate": 4.6919196468786595e-05, - "loss": 0.4432, + "epoch": 0.02, + "learning_rate": 4.923491644482227e-05, + "loss": 0.4548, "step": 7840 }, { - "epoch": 0.07, - "learning_rate": 4.691469237005676e-05, - "loss": 0.449, + "epoch": 0.02, + "learning_rate": 4.9233797901612946e-05, + "loss": 0.4509, "step": 7850 }, { - "epoch": 0.07, - "learning_rate": 4.691018827132691e-05, - "loss": 0.4399, + "epoch": 0.02, + "learning_rate": 4.923267935840362e-05, + "loss": 0.4537, "step": 7860 }, { - "epoch": 0.07, - "learning_rate": 4.690568417259706e-05, - "loss": 0.4467, + "epoch": 0.02, + "learning_rate": 4.9231560815194295e-05, + "loss": 0.4528, "step": 7870 }, { - "epoch": 0.07, - "learning_rate": 4.6901180073867225e-05, - "loss": 0.4426, + "epoch": 0.02, + "learning_rate": 4.9230442271984967e-05, + "loss": 0.4536, "step": 7880 }, { - "epoch": 0.07, - "learning_rate": 4.6896675975137376e-05, - "loss": 0.447, + "epoch": 0.02, + "learning_rate": 4.9229323728775644e-05, + "loss": 0.4469, "step": 7890 }, { - "epoch": 0.07, - "learning_rate": 4.6892171876407534e-05, - "loss": 0.4474, + "epoch": 0.02, + "learning_rate": 4.922820518556632e-05, + "loss": 0.4482, "step": 7900 }, { - "epoch": 0.07, - "learning_rate": 4.688766777767769e-05, - "loss": 0.44, + "epoch": 0.02, + "learning_rate": 4.9227086642356994e-05, + "loss": 0.4488, "step": 7910 }, { - "epoch": 0.07, - "learning_rate": 4.688316367894784e-05, - "loss": 0.4416, + "epoch": 0.02, + "learning_rate": 4.922596809914767e-05, + "loss": 0.4528, "step": 7920 }, { - "epoch": 0.07, - "learning_rate": 4.6878659580218e-05, - "loss": 0.4417, + "epoch": 0.02, + "learning_rate": 4.922484955593835e-05, + "loss": 0.4502, "step": 7930 }, { - "epoch": 0.07, - "learning_rate": 4.687415548148816e-05, - "loss": 0.4425, + "epoch": 0.02, + "learning_rate": 4.922373101272903e-05, + "loss": 0.4496, "step": 7940 }, { - "epoch": 0.07, - "learning_rate": 4.6869651382758314e-05, - "loss": 0.4444, + "epoch": 0.02, + "learning_rate": 4.9222612469519705e-05, + "loss": 0.4506, "step": 7950 }, { - "epoch": 0.07, - "learning_rate": 4.6865147284028465e-05, - "loss": 0.4454, + "epoch": 0.02, + "learning_rate": 4.9221493926310376e-05, + "loss": 0.4476, "step": 7960 }, { - "epoch": 0.07, - "learning_rate": 4.686064318529862e-05, - "loss": 0.4463, + "epoch": 0.02, + "learning_rate": 4.9220375383101054e-05, + "loss": 0.4484, "step": 7970 }, { - "epoch": 0.07, - "learning_rate": 4.685613908656878e-05, - "loss": 0.4432, + "epoch": 0.02, + "learning_rate": 4.9219256839891725e-05, + "loss": 0.453, "step": 7980 }, { - "epoch": 0.07, - "learning_rate": 4.685163498783894e-05, - "loss": 0.4375, + "epoch": 0.02, + "learning_rate": 4.9218138296682403e-05, + "loss": 0.4552, "step": 7990 }, { - "epoch": 0.07, - "learning_rate": 4.6847130889109095e-05, - "loss": 0.4416, - "step": 8000 - }, - { - "epoch": 0.07, - "eval_NEIMS_canon_smiles": 0.9101666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.0007, - "eval_NEIMS_daylight_tanimoto_simil": 0.3176162209335286, - "eval_NEIMS_exact_mols": 0.0006833333333333333, - "eval_NEIMS_exact_smiles": 0.0006, - "eval_NEIMS_loss": 0.4383198618888855, - "eval_NEIMS_matched_formulas": 0.1968, - "eval_NEIMS_morgan_tanimoto_simil": 0.21320042323766042, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0006833333333333333, - "eval_NEIMS_runtime": 742.0808, - "eval_NEIMS_samples_per_second": 80.854, - "eval_NEIMS_steps_per_second": 1.264, - "step": 8000 - }, - { - "epoch": 0.07, - "eval_RASSP_canon_smiles": 0.9061842588573146, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.001402477710622099, - "eval_RASSP_daylight_tanimoto_simil": 0.3428026749410063, - "eval_RASSP_exact_mols": 0.001402477710622099, - "eval_RASSP_exact_smiles": 0.0012856045680702574, - "eval_RASSP_loss": 0.41522035002708435, - "eval_RASSP_matched_formulas": 0.23663472134103583, - "eval_RASSP_morgan_tanimoto_simil": 0.2166757279880561, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.0014191738738437906, - "eval_RASSP_runtime": 810.9619, - "eval_RASSP_samples_per_second": 73.856, - "eval_RASSP_steps_per_second": 1.154, - "step": 8000 - }, - { - "epoch": 0.07, - "eval_NIST_canon_smiles": 0.861340809880399, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.0008517585264577492, - "eval_NIST_daylight_tanimoto_simil": 0.20700074836664745, - "eval_NIST_exact_mols": 0.0008162685878553431, - "eval_NIST_exact_smiles": 0.0007807786492529368, - "eval_NIST_loss": 1.4345619678497314, - "eval_NIST_matched_formulas": 0.02083259395961245, - "eval_NIST_morgan_tanimoto_simil": 0.16496379689687352, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.0008162685878553431, - "eval_NIST_runtime": 531.7761, - "eval_NIST_samples_per_second": 52.987, - "eval_NIST_steps_per_second": 0.829, + "epoch": 0.02, + "learning_rate": 4.921701975347308e-05, + "loss": 0.4577, "step": 8000 }, { - "epoch": 0.07, - "learning_rate": 4.6842626790379246e-05, - "loss": 0.4428, + "epoch": 0.02, + "learning_rate": 4.921590121026375e-05, + "loss": 0.4505, "step": 8010 }, { - "epoch": 0.07, - "learning_rate": 4.68381226916494e-05, - "loss": 0.4477, + "epoch": 0.02, + "learning_rate": 4.921478266705443e-05, + "loss": 0.448, "step": 8020 }, { - "epoch": 0.07, - "learning_rate": 4.683361859291956e-05, - "loss": 0.4491, + "epoch": 0.02, + "learning_rate": 4.92136641238451e-05, + "loss": 0.4487, "step": 8030 }, { - "epoch": 0.07, - "learning_rate": 4.682911449418971e-05, - "loss": 0.4455, + "epoch": 0.02, + "learning_rate": 4.921254558063578e-05, + "loss": 0.4524, "step": 8040 }, { - "epoch": 0.07, - "learning_rate": 4.6824610395459876e-05, - "loss": 0.437, + "epoch": 0.02, + "learning_rate": 4.921142703742646e-05, + "loss": 0.4483, "step": 8050 }, { - "epoch": 0.07, - "learning_rate": 4.6820106296730026e-05, - "loss": 0.4461, + "epoch": 0.02, + "learning_rate": 4.9210308494217135e-05, + "loss": 0.4488, "step": 8060 }, { - "epoch": 0.07, - "learning_rate": 4.681560219800018e-05, - "loss": 0.4465, + "epoch": 0.02, + "learning_rate": 4.920918995100781e-05, + "loss": 0.4457, "step": 8070 }, { - "epoch": 0.07, - "learning_rate": 4.681109809927034e-05, - "loss": 0.4435, + "epoch": 0.02, + "learning_rate": 4.9208071407798484e-05, + "loss": 0.4448, "step": 8080 }, { - "epoch": 0.07, - "learning_rate": 4.680659400054049e-05, - "loss": 0.4386, + "epoch": 0.02, + "learning_rate": 4.920695286458916e-05, + "loss": 0.45, "step": 8090 }, { - "epoch": 0.07, - "learning_rate": 4.680208990181065e-05, - "loss": 0.4474, + "epoch": 0.02, + "learning_rate": 4.9205834321379833e-05, + "loss": 0.4465, "step": 8100 }, { - "epoch": 0.07, - "learning_rate": 4.679758580308081e-05, - "loss": 0.449, + "epoch": 0.02, + "learning_rate": 4.920471577817051e-05, + "loss": 0.4484, "step": 8110 }, { - "epoch": 0.07, - "learning_rate": 4.679308170435096e-05, - "loss": 0.4357, + "epoch": 0.02, + "learning_rate": 4.920359723496119e-05, + "loss": 0.4476, "step": 8120 }, { - "epoch": 0.07, - "learning_rate": 4.678857760562112e-05, - "loss": 0.4312, + "epoch": 0.02, + "learning_rate": 4.920247869175186e-05, + "loss": 0.4487, "step": 8130 }, { - "epoch": 0.07, - "learning_rate": 4.678407350689127e-05, - "loss": 0.4414, + "epoch": 0.02, + "learning_rate": 4.920136014854254e-05, + "loss": 0.4484, "step": 8140 }, { - "epoch": 0.07, - "learning_rate": 4.677956940816143e-05, - "loss": 0.4379, + "epoch": 0.02, + "learning_rate": 4.9200241605333216e-05, + "loss": 0.4467, "step": 8150 }, { - "epoch": 0.07, - "learning_rate": 4.677506530943159e-05, - "loss": 0.4408, + "epoch": 0.02, + "learning_rate": 4.9199123062123894e-05, + "loss": 0.4447, "step": 8160 }, { - "epoch": 0.07, - "learning_rate": 4.677056121070174e-05, - "loss": 0.4408, + "epoch": 0.02, + "learning_rate": 4.919800451891457e-05, + "loss": 0.447, "step": 8170 }, { - "epoch": 0.07, - "learning_rate": 4.6766057111971896e-05, - "loss": 0.4368, + "epoch": 0.02, + "learning_rate": 4.919688597570524e-05, + "loss": 0.4435, "step": 8180 }, { - "epoch": 0.07, - "learning_rate": 4.6761553013242053e-05, - "loss": 0.4357, + "epoch": 0.02, + "learning_rate": 4.919576743249592e-05, + "loss": 0.4412, "step": 8190 }, { - "epoch": 0.07, - "learning_rate": 4.675704891451221e-05, - "loss": 0.4416, + "epoch": 0.02, + "learning_rate": 4.919464888928659e-05, + "loss": 0.4467, "step": 8200 }, { - "epoch": 0.07, - "learning_rate": 4.675254481578236e-05, - "loss": 0.4376, + "epoch": 0.02, + "learning_rate": 4.919353034607727e-05, + "loss": 0.4458, "step": 8210 }, { - "epoch": 0.07, - "learning_rate": 4.674804071705252e-05, - "loss": 0.4423, + "epoch": 0.02, + "learning_rate": 4.919241180286795e-05, + "loss": 0.4528, "step": 8220 }, { - "epoch": 0.07, - "learning_rate": 4.674353661832268e-05, - "loss": 0.4399, + "epoch": 0.02, + "learning_rate": 4.919129325965862e-05, + "loss": 0.451, "step": 8230 }, { - "epoch": 0.07, - "learning_rate": 4.673903251959283e-05, - "loss": 0.4386, + "epoch": 0.02, + "learning_rate": 4.91901747164493e-05, + "loss": 0.4505, "step": 8240 }, { - "epoch": 0.07, - "learning_rate": 4.673452842086299e-05, - "loss": 0.4469, + "epoch": 0.02, + "learning_rate": 4.9189056173239975e-05, + "loss": 0.4459, "step": 8250 }, { - "epoch": 0.07, - "learning_rate": 4.673002432213314e-05, - "loss": 0.4382, + "epoch": 0.02, + "learning_rate": 4.918793763003065e-05, + "loss": 0.4518, "step": 8260 }, { - "epoch": 0.07, - "learning_rate": 4.67255202234033e-05, - "loss": 0.441, + "epoch": 0.02, + "learning_rate": 4.918681908682133e-05, + "loss": 0.4502, "step": 8270 }, { - "epoch": 0.07, - "learning_rate": 4.672101612467346e-05, - "loss": 0.4388, + "epoch": 0.02, + "learning_rate": 4.9185700543612e-05, + "loss": 0.4582, "step": 8280 }, { - "epoch": 0.07, - "learning_rate": 4.671651202594361e-05, - "loss": 0.4379, + "epoch": 0.02, + "learning_rate": 4.918458200040268e-05, + "loss": 0.4404, "step": 8290 }, { - "epoch": 0.07, - "learning_rate": 4.671200792721377e-05, - "loss": 0.4457, + "epoch": 0.02, + "learning_rate": 4.918346345719335e-05, + "loss": 0.4359, "step": 8300 }, { - "epoch": 0.07, - "learning_rate": 4.670750382848392e-05, - "loss": 0.4402, + "epoch": 0.02, + "learning_rate": 4.918234491398403e-05, + "loss": 0.4454, "step": 8310 }, { - "epoch": 0.07, - "learning_rate": 4.6702999729754074e-05, - "loss": 0.4349, + "epoch": 0.02, + "learning_rate": 4.918122637077471e-05, + "loss": 0.4438, "step": 8320 }, { - "epoch": 0.07, - "learning_rate": 4.669849563102424e-05, - "loss": 0.4348, + "epoch": 0.02, + "learning_rate": 4.918010782756538e-05, + "loss": 0.4513, "step": 8330 }, { - "epoch": 0.07, - "learning_rate": 4.669399153229439e-05, - "loss": 0.444, + "epoch": 0.02, + "learning_rate": 4.9178989284356056e-05, + "loss": 0.4423, "step": 8340 }, { - "epoch": 0.07, - "learning_rate": 4.6689487433564546e-05, - "loss": 0.4368, + "epoch": 0.02, + "learning_rate": 4.9177870741146734e-05, + "loss": 0.4486, "step": 8350 }, { - "epoch": 0.07, - "learning_rate": 4.6684983334834704e-05, - "loss": 0.4306, + "epoch": 0.02, + "learning_rate": 4.917675219793741e-05, + "loss": 0.4398, "step": 8360 }, { - "epoch": 0.07, - "learning_rate": 4.6680479236104854e-05, - "loss": 0.4403, + "epoch": 0.02, + "learning_rate": 4.917563365472809e-05, + "loss": 0.4363, "step": 8370 }, { - "epoch": 0.07, - "learning_rate": 4.667597513737501e-05, - "loss": 0.4349, + "epoch": 0.02, + "learning_rate": 4.917451511151876e-05, + "loss": 0.4428, "step": 8380 }, { - "epoch": 0.07, - "learning_rate": 4.667147103864517e-05, - "loss": 0.44, + "epoch": 0.02, + "learning_rate": 4.917339656830944e-05, + "loss": 0.4426, "step": 8390 }, { - "epoch": 0.07, - "learning_rate": 4.666696693991533e-05, - "loss": 0.4341, + "epoch": 0.02, + "learning_rate": 4.917227802510011e-05, + "loss": 0.445, "step": 8400 }, { - "epoch": 0.08, - "learning_rate": 4.6662462841185484e-05, - "loss": 0.4396, + "epoch": 0.02, + "learning_rate": 4.917115948189079e-05, + "loss": 0.4359, "step": 8410 }, { - "epoch": 0.08, - "learning_rate": 4.6657958742455635e-05, - "loss": 0.4365, + "epoch": 0.02, + "learning_rate": 4.917004093868146e-05, + "loss": 0.4451, "step": 8420 }, { - "epoch": 0.08, - "learning_rate": 4.665345464372579e-05, - "loss": 0.4437, + "epoch": 0.02, + "learning_rate": 4.916892239547214e-05, + "loss": 0.4431, "step": 8430 }, { - "epoch": 0.08, - "learning_rate": 4.664895054499595e-05, - "loss": 0.4389, + "epoch": 0.02, + "learning_rate": 4.9167803852262815e-05, + "loss": 0.4381, "step": 8440 }, { - "epoch": 0.08, - "learning_rate": 4.664444644626611e-05, - "loss": 0.4344, + "epoch": 0.02, + "learning_rate": 4.9166685309053486e-05, + "loss": 0.4451, "step": 8450 }, { - "epoch": 0.08, - "learning_rate": 4.663994234753626e-05, - "loss": 0.436, + "epoch": 0.02, + "learning_rate": 4.9165566765844164e-05, + "loss": 0.4489, "step": 8460 }, { - "epoch": 0.08, - "learning_rate": 4.6635438248806416e-05, - "loss": 0.4299, + "epoch": 0.02, + "learning_rate": 4.916444822263484e-05, + "loss": 0.4439, "step": 8470 }, { - "epoch": 0.08, - "learning_rate": 4.663093415007657e-05, - "loss": 0.4394, + "epoch": 0.02, + "learning_rate": 4.916332967942552e-05, + "loss": 0.439, "step": 8480 }, { - "epoch": 0.08, - "learning_rate": 4.6626430051346724e-05, - "loss": 0.4458, + "epoch": 0.02, + "learning_rate": 4.91622111362162e-05, + "loss": 0.4436, "step": 8490 }, { - "epoch": 0.08, - "learning_rate": 4.662192595261689e-05, - "loss": 0.4399, + "epoch": 0.02, + "learning_rate": 4.916109259300687e-05, + "loss": 0.4402, "step": 8500 }, { - "epoch": 0.08, - "learning_rate": 4.661742185388704e-05, - "loss": 0.4387, + "epoch": 0.02, + "learning_rate": 4.915997404979755e-05, + "loss": 0.4367, "step": 8510 }, { - "epoch": 0.08, - "learning_rate": 4.661291775515719e-05, - "loss": 0.4362, + "epoch": 0.02, + "learning_rate": 4.915885550658822e-05, + "loss": 0.4352, "step": 8520 }, { - "epoch": 0.08, - "learning_rate": 4.6608413656427354e-05, - "loss": 0.4389, + "epoch": 0.02, + "learning_rate": 4.9157736963378896e-05, + "loss": 0.4463, "step": 8530 }, { - "epoch": 0.08, - "learning_rate": 4.6603909557697505e-05, - "loss": 0.4324, + "epoch": 0.02, + "learning_rate": 4.9156618420169574e-05, + "loss": 0.4328, "step": 8540 }, { - "epoch": 0.08, - "learning_rate": 4.659940545896766e-05, - "loss": 0.4322, + "epoch": 0.02, + "learning_rate": 4.9155499876960245e-05, + "loss": 0.4399, "step": 8550 }, { - "epoch": 0.08, - "learning_rate": 4.659490136023782e-05, - "loss": 0.434, + "epoch": 0.02, + "learning_rate": 4.915438133375092e-05, + "loss": 0.445, "step": 8560 }, { - "epoch": 0.08, - "learning_rate": 4.659039726150797e-05, - "loss": 0.4264, + "epoch": 0.02, + "learning_rate": 4.91532627905416e-05, + "loss": 0.4381, "step": 8570 }, { - "epoch": 0.08, - "learning_rate": 4.6585893162778135e-05, - "loss": 0.4354, + "epoch": 0.02, + "learning_rate": 4.915214424733228e-05, + "loss": 0.4425, "step": 8580 }, { - "epoch": 0.08, - "learning_rate": 4.6581389064048285e-05, - "loss": 0.4372, + "epoch": 0.02, + "learning_rate": 4.915102570412296e-05, + "loss": 0.4472, "step": 8590 }, { - "epoch": 0.08, - "learning_rate": 4.657688496531844e-05, - "loss": 0.4346, + "epoch": 0.02, + "learning_rate": 4.914990716091363e-05, + "loss": 0.4502, "step": 8600 }, { - "epoch": 0.08, - "learning_rate": 4.65723808665886e-05, - "loss": 0.4328, + "epoch": 0.02, + "learning_rate": 4.9148788617704306e-05, + "loss": 0.4449, "step": 8610 }, { - "epoch": 0.08, - "learning_rate": 4.656787676785875e-05, - "loss": 0.4304, + "epoch": 0.02, + "learning_rate": 4.914767007449498e-05, + "loss": 0.437, "step": 8620 }, { - "epoch": 0.08, - "learning_rate": 4.656337266912891e-05, - "loss": 0.426, + "epoch": 0.02, + "learning_rate": 4.9146551531285655e-05, + "loss": 0.4461, "step": 8630 }, { - "epoch": 0.08, - "learning_rate": 4.6558868570399066e-05, - "loss": 0.4298, + "epoch": 0.02, + "learning_rate": 4.914543298807633e-05, + "loss": 0.4367, "step": 8640 }, { - "epoch": 0.08, - "learning_rate": 4.6554364471669224e-05, - "loss": 0.4302, + "epoch": 0.02, + "learning_rate": 4.9144314444867004e-05, + "loss": 0.4423, "step": 8650 }, { - "epoch": 0.08, - "learning_rate": 4.6549860372939374e-05, - "loss": 0.437, + "epoch": 0.02, + "learning_rate": 4.914319590165768e-05, + "loss": 0.4461, "step": 8660 }, { - "epoch": 0.08, - "learning_rate": 4.654535627420953e-05, - "loss": 0.4311, + "epoch": 0.02, + "learning_rate": 4.914207735844836e-05, + "loss": 0.4375, "step": 8670 }, { - "epoch": 0.08, - "learning_rate": 4.654085217547969e-05, - "loss": 0.4265, + "epoch": 0.02, + "learning_rate": 4.914095881523904e-05, + "loss": 0.4371, "step": 8680 }, { - "epoch": 0.08, - "learning_rate": 4.653634807674985e-05, - "loss": 0.4339, + "epoch": 0.02, + "learning_rate": 4.9139840272029716e-05, + "loss": 0.4367, "step": 8690 }, { - "epoch": 0.08, - "learning_rate": 4.6531843978020004e-05, - "loss": 0.427, + "epoch": 0.02, + "learning_rate": 4.913872172882039e-05, + "loss": 0.4341, "step": 8700 }, { - "epoch": 0.08, - "learning_rate": 4.6527339879290155e-05, - "loss": 0.4301, + "epoch": 0.02, + "learning_rate": 4.9137603185611065e-05, + "loss": 0.437, "step": 8710 }, { - "epoch": 0.08, - "learning_rate": 4.652283578056031e-05, - "loss": 0.4358, + "epoch": 0.02, + "learning_rate": 4.9136484642401736e-05, + "loss": 0.4295, "step": 8720 }, { - "epoch": 0.08, - "learning_rate": 4.651833168183047e-05, - "loss": 0.4322, + "epoch": 0.02, + "learning_rate": 4.9135366099192414e-05, + "loss": 0.4402, "step": 8730 }, { - "epoch": 0.08, - "learning_rate": 4.651382758310062e-05, - "loss": 0.4275, + "epoch": 0.02, + "learning_rate": 4.9134247555983085e-05, + "loss": 0.4364, "step": 8740 }, { - "epoch": 0.08, - "learning_rate": 4.650932348437078e-05, - "loss": 0.4339, + "epoch": 0.02, + "learning_rate": 4.913312901277376e-05, + "loss": 0.44, "step": 8750 }, { - "epoch": 0.08, - "learning_rate": 4.6504819385640936e-05, - "loss": 0.4276, + "epoch": 0.02, + "learning_rate": 4.913201046956444e-05, + "loss": 0.4417, "step": 8760 }, { - "epoch": 0.08, - "learning_rate": 4.6500315286911086e-05, - "loss": 0.4348, + "epoch": 0.02, + "learning_rate": 4.913089192635512e-05, + "loss": 0.4349, "step": 8770 }, { - "epoch": 0.08, - "learning_rate": 4.649581118818125e-05, - "loss": 0.4317, + "epoch": 0.02, + "learning_rate": 4.91297733831458e-05, + "loss": 0.4398, "step": 8780 }, { - "epoch": 0.08, - "learning_rate": 4.64913070894514e-05, - "loss": 0.429, + "epoch": 0.02, + "learning_rate": 4.912865483993647e-05, + "loss": 0.4389, "step": 8790 }, { - "epoch": 0.08, - "learning_rate": 4.648680299072156e-05, - "loss": 0.43, + "epoch": 0.02, + "learning_rate": 4.9127536296727146e-05, + "loss": 0.4336, "step": 8800 }, { - "epoch": 0.08, - "learning_rate": 4.6482298891991716e-05, - "loss": 0.4343, + "epoch": 0.02, + "learning_rate": 4.9126417753517824e-05, + "loss": 0.4371, "step": 8810 }, { - "epoch": 0.08, - "learning_rate": 4.647779479326187e-05, - "loss": 0.4364, + "epoch": 0.02, + "learning_rate": 4.9125299210308495e-05, + "loss": 0.435, "step": 8820 }, { - "epoch": 0.08, - "learning_rate": 4.647329069453203e-05, - "loss": 0.4291, + "epoch": 0.02, + "learning_rate": 4.912418066709917e-05, + "loss": 0.4417, "step": 8830 }, { - "epoch": 0.08, - "learning_rate": 4.646878659580218e-05, - "loss": 0.4254, + "epoch": 0.02, + "learning_rate": 4.9123062123889844e-05, + "loss": 0.439, "step": 8840 }, { - "epoch": 0.08, - "learning_rate": 4.646428249707234e-05, - "loss": 0.4275, + "epoch": 0.02, + "learning_rate": 4.912194358068052e-05, + "loss": 0.4419, "step": 8850 }, { - "epoch": 0.08, - "learning_rate": 4.64597783983425e-05, - "loss": 0.4303, + "epoch": 0.02, + "learning_rate": 4.91208250374712e-05, + "loss": 0.4357, "step": 8860 }, { - "epoch": 0.08, - "learning_rate": 4.645527429961265e-05, - "loss": 0.4389, + "epoch": 0.02, + "learning_rate": 4.911970649426187e-05, + "loss": 0.4324, "step": 8870 }, { - "epoch": 0.08, - "learning_rate": 4.6450770200882805e-05, - "loss": 0.4288, + "epoch": 0.02, + "learning_rate": 4.9118587951052556e-05, + "loss": 0.4314, "step": 8880 }, { - "epoch": 0.08, - "learning_rate": 4.644626610215296e-05, - "loss": 0.4287, + "epoch": 0.02, + "learning_rate": 4.911746940784323e-05, + "loss": 0.4345, "step": 8890 }, { - "epoch": 0.08, - "learning_rate": 4.644176200342312e-05, - "loss": 0.4321, + "epoch": 0.02, + "learning_rate": 4.9116350864633905e-05, + "loss": 0.4326, "step": 8900 }, { - "epoch": 0.08, - "learning_rate": 4.643725790469327e-05, - "loss": 0.4184, + "epoch": 0.02, + "learning_rate": 4.911523232142458e-05, + "loss": 0.4328, "step": 8910 }, { - "epoch": 0.08, - "learning_rate": 4.643275380596343e-05, - "loss": 0.4287, + "epoch": 0.02, + "learning_rate": 4.9114113778215254e-05, + "loss": 0.4371, "step": 8920 }, { - "epoch": 0.08, - "learning_rate": 4.6428249707233586e-05, - "loss": 0.4309, + "epoch": 0.02, + "learning_rate": 4.911299523500593e-05, + "loss": 0.4343, "step": 8930 }, { - "epoch": 0.08, - "learning_rate": 4.6423745608503737e-05, - "loss": 0.4304, + "epoch": 0.02, + "learning_rate": 4.91118766917966e-05, + "loss": 0.437, "step": 8940 }, { - "epoch": 0.08, - "learning_rate": 4.64192415097739e-05, - "loss": 0.4299, + "epoch": 0.02, + "learning_rate": 4.911075814858728e-05, + "loss": 0.4306, "step": 8950 }, { - "epoch": 0.08, - "learning_rate": 4.641473741104405e-05, - "loss": 0.4312, + "epoch": 0.02, + "learning_rate": 4.910963960537796e-05, + "loss": 0.4346, "step": 8960 }, { - "epoch": 0.08, - "learning_rate": 4.641023331231421e-05, - "loss": 0.4333, + "epoch": 0.02, + "learning_rate": 4.910852106216863e-05, + "loss": 0.436, "step": 8970 }, { - "epoch": 0.08, - "learning_rate": 4.6405729213584367e-05, - "loss": 0.4306, + "epoch": 0.02, + "learning_rate": 4.910740251895931e-05, + "loss": 0.4364, "step": 8980 }, { - "epoch": 0.08, - "learning_rate": 4.640122511485452e-05, - "loss": 0.4217, + "epoch": 0.02, + "learning_rate": 4.9106283975749986e-05, + "loss": 0.4388, "step": 8990 }, { - "epoch": 0.08, - "learning_rate": 4.6396721016124675e-05, - "loss": 0.4264, + "epoch": 0.02, + "learning_rate": 4.9105165432540664e-05, + "loss": 0.4315, "step": 9000 }, { - "epoch": 0.08, - "learning_rate": 4.639221691739483e-05, - "loss": 0.4296, + "epoch": 0.02, + "learning_rate": 4.910404688933134e-05, + "loss": 0.4358, "step": 9010 }, { - "epoch": 0.08, - "learning_rate": 4.638771281866498e-05, - "loss": 0.4258, + "epoch": 0.02, + "learning_rate": 4.910292834612201e-05, + "loss": 0.4355, "step": 9020 }, { - "epoch": 0.08, - "learning_rate": 4.638320871993515e-05, - "loss": 0.4363, + "epoch": 0.02, + "learning_rate": 4.910180980291269e-05, + "loss": 0.4378, "step": 9030 }, { - "epoch": 0.08, - "learning_rate": 4.63787046212053e-05, - "loss": 0.4255, + "epoch": 0.02, + "learning_rate": 4.910069125970336e-05, + "loss": 0.4386, "step": 9040 }, { - "epoch": 0.08, - "learning_rate": 4.6374200522475455e-05, - "loss": 0.422, + "epoch": 0.02, + "learning_rate": 4.909957271649404e-05, + "loss": 0.4349, "step": 9050 }, { - "epoch": 0.08, - "learning_rate": 4.636969642374561e-05, - "loss": 0.4235, + "epoch": 0.02, + "learning_rate": 4.909845417328471e-05, + "loss": 0.4352, "step": 9060 }, { - "epoch": 0.08, - "learning_rate": 4.6365192325015764e-05, - "loss": 0.4239, + "epoch": 0.02, + "learning_rate": 4.909733563007539e-05, + "loss": 0.4259, "step": 9070 }, { - "epoch": 0.08, - "learning_rate": 4.636068822628592e-05, - "loss": 0.435, + "epoch": 0.02, + "learning_rate": 4.909621708686607e-05, + "loss": 0.4369, "step": 9080 }, { - "epoch": 0.08, - "learning_rate": 4.635618412755608e-05, - "loss": 0.4327, + "epoch": 0.02, + "learning_rate": 4.9095098543656745e-05, + "loss": 0.4307, "step": 9090 }, { - "epoch": 0.08, - "learning_rate": 4.6351680028826236e-05, - "loss": 0.4259, + "epoch": 0.02, + "learning_rate": 4.909398000044742e-05, + "loss": 0.4314, "step": 9100 }, { - "epoch": 0.08, - "learning_rate": 4.6347175930096394e-05, - "loss": 0.43, + "epoch": 0.02, + "learning_rate": 4.9092861457238094e-05, + "loss": 0.4353, "step": 9110 }, { - "epoch": 0.08, - "learning_rate": 4.6342671831366544e-05, - "loss": 0.4256, + "epoch": 0.02, + "learning_rate": 4.909174291402877e-05, + "loss": 0.4312, "step": 9120 }, { - "epoch": 0.08, - "learning_rate": 4.63381677326367e-05, - "loss": 0.4322, + "epoch": 0.02, + "learning_rate": 4.909062437081945e-05, + "loss": 0.4329, "step": 9130 }, { - "epoch": 0.08, - "learning_rate": 4.633366363390686e-05, - "loss": 0.4324, + "epoch": 0.02, + "learning_rate": 4.908950582761012e-05, + "loss": 0.431, "step": 9140 }, { - "epoch": 0.08, - "learning_rate": 4.632915953517702e-05, - "loss": 0.4259, + "epoch": 0.02, + "learning_rate": 4.90883872844008e-05, + "loss": 0.4332, "step": 9150 }, { - "epoch": 0.08, - "learning_rate": 4.632465543644717e-05, - "loss": 0.4284, + "epoch": 0.02, + "learning_rate": 4.908726874119147e-05, + "loss": 0.4316, "step": 9160 }, { - "epoch": 0.08, - "learning_rate": 4.6320151337717325e-05, - "loss": 0.4245, + "epoch": 0.02, + "learning_rate": 4.908615019798215e-05, + "loss": 0.4361, "step": 9170 }, { - "epoch": 0.08, - "learning_rate": 4.631564723898748e-05, - "loss": 0.4294, + "epoch": 0.02, + "learning_rate": 4.9085031654772826e-05, + "loss": 0.4315, "step": 9180 }, { - "epoch": 0.08, - "learning_rate": 4.631114314025763e-05, - "loss": 0.4311, + "epoch": 0.02, + "learning_rate": 4.9083913111563504e-05, + "loss": 0.4281, "step": 9190 }, { - "epoch": 0.08, - "learning_rate": 4.630663904152779e-05, - "loss": 0.4211, + "epoch": 0.02, + "learning_rate": 4.908279456835418e-05, + "loss": 0.4239, "step": 9200 }, { - "epoch": 0.08, - "learning_rate": 4.630213494279795e-05, - "loss": 0.4243, + "epoch": 0.02, + "learning_rate": 4.908167602514485e-05, + "loss": 0.4363, "step": 9210 }, { - "epoch": 0.08, - "learning_rate": 4.62976308440681e-05, - "loss": 0.4251, + "epoch": 0.02, + "learning_rate": 4.908055748193553e-05, + "loss": 0.4315, "step": 9220 }, { - "epoch": 0.08, - "learning_rate": 4.629312674533826e-05, - "loss": 0.4349, + "epoch": 0.02, + "learning_rate": 4.907943893872621e-05, + "loss": 0.4315, "step": 9230 }, { - "epoch": 0.08, - "learning_rate": 4.6288622646608414e-05, - "loss": 0.4237, + "epoch": 0.02, + "learning_rate": 4.907832039551688e-05, + "loss": 0.4394, "step": 9240 }, { - "epoch": 0.08, - "learning_rate": 4.628411854787857e-05, - "loss": 0.4172, + "epoch": 0.02, + "learning_rate": 4.907720185230756e-05, + "loss": 0.4291, "step": 9250 }, { - "epoch": 0.08, - "learning_rate": 4.627961444914873e-05, - "loss": 0.424, + "epoch": 0.02, + "learning_rate": 4.907608330909823e-05, + "loss": 0.432, "step": 9260 }, { - "epoch": 0.08, - "learning_rate": 4.627511035041888e-05, - "loss": 0.4256, + "epoch": 0.02, + "learning_rate": 4.907496476588891e-05, + "loss": 0.4308, "step": 9270 }, { - "epoch": 0.08, - "learning_rate": 4.6270606251689044e-05, - "loss": 0.4252, + "epoch": 0.02, + "learning_rate": 4.9073846222679585e-05, + "loss": 0.4375, "step": 9280 }, { - "epoch": 0.08, - "learning_rate": 4.6266102152959195e-05, - "loss": 0.4235, + "epoch": 0.02, + "learning_rate": 4.9072727679470256e-05, + "loss": 0.4341, "step": 9290 }, { - "epoch": 0.08, - "learning_rate": 4.626159805422935e-05, - "loss": 0.4206, + "epoch": 0.02, + "learning_rate": 4.907160913626094e-05, + "loss": 0.4288, "step": 9300 }, { - "epoch": 0.08, - "learning_rate": 4.625709395549951e-05, - "loss": 0.4221, + "epoch": 0.02, + "learning_rate": 4.907049059305161e-05, + "loss": 0.4303, "step": 9310 }, { - "epoch": 0.08, - "learning_rate": 4.625258985676966e-05, - "loss": 0.4207, + "epoch": 0.02, + "learning_rate": 4.906937204984229e-05, + "loss": 0.4276, "step": 9320 }, { - "epoch": 0.08, - "learning_rate": 4.624808575803982e-05, - "loss": 0.4245, + "epoch": 0.02, + "learning_rate": 4.906825350663297e-05, + "loss": 0.4285, "step": 9330 }, { - "epoch": 0.08, - "learning_rate": 4.6243581659309975e-05, - "loss": 0.4178, + "epoch": 0.02, + "learning_rate": 4.906713496342364e-05, + "loss": 0.4257, "step": 9340 }, { - "epoch": 0.08, - "learning_rate": 4.623907756058013e-05, - "loss": 0.4159, + "epoch": 0.02, + "learning_rate": 4.906601642021432e-05, + "loss": 0.4295, "step": 9350 }, { - "epoch": 0.08, - "learning_rate": 4.6234573461850283e-05, - "loss": 0.4194, + "epoch": 0.02, + "learning_rate": 4.906489787700499e-05, + "loss": 0.4264, "step": 9360 }, { - "epoch": 0.08, - "learning_rate": 4.623006936312044e-05, - "loss": 0.4239, + "epoch": 0.02, + "learning_rate": 4.9063779333795666e-05, + "loss": 0.4361, "step": 9370 }, { - "epoch": 0.08, - "learning_rate": 4.62255652643906e-05, - "loss": 0.4261, + "epoch": 0.02, + "learning_rate": 4.906266079058634e-05, + "loss": 0.4398, "step": 9380 }, { - "epoch": 0.08, - "learning_rate": 4.6221061165660756e-05, - "loss": 0.4186, + "epoch": 0.02, + "learning_rate": 4.9061542247377015e-05, + "loss": 0.4251, "step": 9390 }, { - "epoch": 0.08, - "learning_rate": 4.621655706693091e-05, - "loss": 0.4261, + "epoch": 0.02, + "learning_rate": 4.906042370416769e-05, + "loss": 0.4299, "step": 9400 }, { - "epoch": 0.08, - "learning_rate": 4.6212052968201064e-05, - "loss": 0.4197, + "epoch": 0.02, + "learning_rate": 4.905930516095837e-05, + "loss": 0.4298, "step": 9410 }, { - "epoch": 0.08, - "learning_rate": 4.620754886947122e-05, - "loss": 0.4327, + "epoch": 0.02, + "learning_rate": 4.905818661774905e-05, + "loss": 0.4306, "step": 9420 }, { - "epoch": 0.08, - "learning_rate": 4.620304477074138e-05, + "epoch": 0.02, + "learning_rate": 4.905706807453972e-05, "loss": 0.4267, "step": 9430 }, { - "epoch": 0.08, - "learning_rate": 4.619854067201153e-05, - "loss": 0.4204, + "epoch": 0.02, + "learning_rate": 4.90559495313304e-05, + "loss": 0.434, "step": 9440 }, { - "epoch": 0.08, - "learning_rate": 4.619403657328169e-05, - "loss": 0.424, + "epoch": 0.02, + "learning_rate": 4.9054830988121076e-05, + "loss": 0.4298, "step": 9450 }, { - "epoch": 0.08, - "learning_rate": 4.6189532474551845e-05, - "loss": 0.4207, + "epoch": 0.02, + "learning_rate": 4.905371244491175e-05, + "loss": 0.4298, "step": 9460 }, { - "epoch": 0.08, - "learning_rate": 4.6185028375821996e-05, - "loss": 0.4277, + "epoch": 0.02, + "learning_rate": 4.9052593901702425e-05, + "loss": 0.4255, "step": 9470 }, { - "epoch": 0.08, - "learning_rate": 4.618052427709216e-05, - "loss": 0.4201, + "epoch": 0.02, + "learning_rate": 4.9051475358493096e-05, + "loss": 0.4243, "step": 9480 }, { - "epoch": 0.08, - "learning_rate": 4.617602017836231e-05, - "loss": 0.4256, + "epoch": 0.02, + "learning_rate": 4.9050356815283774e-05, + "loss": 0.424, "step": 9490 }, { - "epoch": 0.08, - "learning_rate": 4.617151607963247e-05, - "loss": 0.423, + "epoch": 0.02, + "learning_rate": 4.904923827207445e-05, + "loss": 0.4232, "step": 9500 }, { - "epoch": 0.08, - "learning_rate": 4.6167011980902626e-05, - "loss": 0.4301, + "epoch": 0.02, + "learning_rate": 4.904811972886513e-05, + "loss": 0.4254, "step": 9510 }, { - "epoch": 0.08, - "learning_rate": 4.6162507882172776e-05, - "loss": 0.4175, + "epoch": 0.02, + "learning_rate": 4.904700118565581e-05, + "loss": 0.4349, "step": 9520 }, { - "epoch": 0.09, - "learning_rate": 4.615800378344294e-05, - "loss": 0.4238, + "epoch": 0.02, + "learning_rate": 4.904588264244648e-05, + "loss": 0.4292, "step": 9530 }, { - "epoch": 0.09, - "learning_rate": 4.615349968471309e-05, - "loss": 0.4174, + "epoch": 0.02, + "learning_rate": 4.904476409923716e-05, + "loss": 0.4283, "step": 9540 }, { - "epoch": 0.09, - "learning_rate": 4.614899558598325e-05, - "loss": 0.4243, + "epoch": 0.02, + "learning_rate": 4.9043645556027835e-05, + "loss": 0.4268, "step": 9550 }, { - "epoch": 0.09, - "learning_rate": 4.6144491487253406e-05, - "loss": 0.4269, + "epoch": 0.02, + "learning_rate": 4.9042527012818506e-05, + "loss": 0.4292, "step": 9560 }, { - "epoch": 0.09, - "learning_rate": 4.613998738852356e-05, - "loss": 0.4243, + "epoch": 0.02, + "learning_rate": 4.9041408469609184e-05, + "loss": 0.4276, "step": 9570 }, { - "epoch": 0.09, - "learning_rate": 4.6135483289793714e-05, - "loss": 0.4174, + "epoch": 0.02, + "learning_rate": 4.9040289926399855e-05, + "loss": 0.425, "step": 9580 }, { - "epoch": 0.09, - "learning_rate": 4.613097919106387e-05, - "loss": 0.4191, + "epoch": 0.02, + "learning_rate": 4.903917138319053e-05, + "loss": 0.4228, "step": 9590 }, { - "epoch": 0.09, - "learning_rate": 4.612647509233403e-05, - "loss": 0.4187, + "epoch": 0.02, + "learning_rate": 4.903805283998121e-05, + "loss": 0.4239, "step": 9600 }, { - "epoch": 0.09, - "learning_rate": 4.612197099360418e-05, - "loss": 0.4266, + "epoch": 0.02, + "learning_rate": 4.903693429677189e-05, + "loss": 0.4292, "step": 9610 }, { - "epoch": 0.09, - "learning_rate": 4.611746689487434e-05, - "loss": 0.4163, + "epoch": 0.02, + "learning_rate": 4.903581575356257e-05, + "loss": 0.4242, "step": 9620 }, { - "epoch": 0.09, - "learning_rate": 4.6112962796144495e-05, - "loss": 0.4208, + "epoch": 0.02, + "learning_rate": 4.903469721035324e-05, + "loss": 0.4264, "step": 9630 }, { - "epoch": 0.09, - "learning_rate": 4.6108458697414646e-05, - "loss": 0.421, + "epoch": 0.02, + "learning_rate": 4.9033578667143916e-05, + "loss": 0.4243, "step": 9640 }, { - "epoch": 0.09, - "learning_rate": 4.61039545986848e-05, - "loss": 0.4181, + "epoch": 0.02, + "learning_rate": 4.9032460123934594e-05, + "loss": 0.424, "step": 9650 }, { - "epoch": 0.09, - "learning_rate": 4.609945049995496e-05, - "loss": 0.421, + "epoch": 0.02, + "learning_rate": 4.9031341580725265e-05, + "loss": 0.4285, "step": 9660 }, { - "epoch": 0.09, - "learning_rate": 4.609494640122512e-05, - "loss": 0.4275, + "epoch": 0.02, + "learning_rate": 4.903022303751594e-05, + "loss": 0.4234, "step": 9670 }, { - "epoch": 0.09, - "learning_rate": 4.6090442302495276e-05, - "loss": 0.4141, + "epoch": 0.02, + "learning_rate": 4.9029104494306614e-05, + "loss": 0.4236, "step": 9680 }, { - "epoch": 0.09, - "learning_rate": 4.6085938203765427e-05, - "loss": 0.425, + "epoch": 0.02, + "learning_rate": 4.902798595109729e-05, + "loss": 0.4252, "step": 9690 }, { - "epoch": 0.09, - "learning_rate": 4.6081434105035584e-05, - "loss": 0.4203, + "epoch": 0.02, + "learning_rate": 4.902686740788796e-05, + "loss": 0.4237, "step": 9700 }, { - "epoch": 0.09, - "learning_rate": 4.607693000630574e-05, - "loss": 0.418, + "epoch": 0.02, + "learning_rate": 4.902574886467865e-05, + "loss": 0.4229, "step": 9710 }, { - "epoch": 0.09, - "learning_rate": 4.607242590757589e-05, - "loss": 0.4144, + "epoch": 0.02, + "learning_rate": 4.9024630321469326e-05, + "loss": 0.4264, "step": 9720 }, { - "epoch": 0.09, - "learning_rate": 4.6067921808846056e-05, - "loss": 0.4161, + "epoch": 0.02, + "learning_rate": 4.902351177826e-05, + "loss": 0.4226, "step": 9730 }, { - "epoch": 0.09, - "learning_rate": 4.606341771011621e-05, - "loss": 0.4209, + "epoch": 0.02, + "learning_rate": 4.9022393235050675e-05, + "loss": 0.4217, "step": 9740 }, { - "epoch": 0.09, - "learning_rate": 4.6058913611386365e-05, - "loss": 0.4216, + "epoch": 0.02, + "learning_rate": 4.9021274691841346e-05, + "loss": 0.4275, "step": 9750 }, { - "epoch": 0.09, - "learning_rate": 4.605440951265652e-05, - "loss": 0.4177, + "epoch": 0.02, + "learning_rate": 4.9020156148632024e-05, + "loss": 0.4258, "step": 9760 }, { - "epoch": 0.09, - "learning_rate": 4.604990541392667e-05, - "loss": 0.4215, + "epoch": 0.02, + "learning_rate": 4.90190376054227e-05, + "loss": 0.4239, "step": 9770 }, { - "epoch": 0.09, - "learning_rate": 4.604540131519683e-05, - "loss": 0.413, + "epoch": 0.02, + "learning_rate": 4.901791906221337e-05, + "loss": 0.4218, "step": 9780 }, { - "epoch": 0.09, - "learning_rate": 4.604089721646699e-05, - "loss": 0.4112, + "epoch": 0.02, + "learning_rate": 4.901680051900405e-05, + "loss": 0.4247, "step": 9790 }, { - "epoch": 0.09, - "learning_rate": 4.6036393117737145e-05, - "loss": 0.4181, + "epoch": 0.02, + "learning_rate": 4.901568197579472e-05, + "loss": 0.4308, "step": 9800 }, { - "epoch": 0.09, - "learning_rate": 4.60318890190073e-05, - "loss": 0.4139, + "epoch": 0.02, + "learning_rate": 4.90145634325854e-05, + "loss": 0.4251, "step": 9810 }, { - "epoch": 0.09, - "learning_rate": 4.6027384920277454e-05, - "loss": 0.4213, + "epoch": 0.02, + "learning_rate": 4.901344488937608e-05, + "loss": 0.4282, "step": 9820 }, { - "epoch": 0.09, - "learning_rate": 4.602288082154761e-05, - "loss": 0.4175, + "epoch": 0.02, + "learning_rate": 4.9012326346166756e-05, + "loss": 0.4234, "step": 9830 }, { - "epoch": 0.09, - "learning_rate": 4.601837672281777e-05, - "loss": 0.4179, + "epoch": 0.02, + "learning_rate": 4.9011207802957434e-05, + "loss": 0.4255, "step": 9840 }, { - "epoch": 0.09, - "learning_rate": 4.601387262408792e-05, - "loss": 0.4186, + "epoch": 0.02, + "learning_rate": 4.9010089259748105e-05, + "loss": 0.4264, "step": 9850 }, { - "epoch": 0.09, - "learning_rate": 4.600936852535808e-05, - "loss": 0.4142, + "epoch": 0.02, + "learning_rate": 4.900897071653878e-05, + "loss": 0.4191, "step": 9860 }, { - "epoch": 0.09, - "learning_rate": 4.6004864426628234e-05, - "loss": 0.4213, + "epoch": 0.02, + "learning_rate": 4.900785217332946e-05, + "loss": 0.4152, "step": 9870 }, { - "epoch": 0.09, - "learning_rate": 4.600036032789839e-05, - "loss": 0.4221, + "epoch": 0.02, + "learning_rate": 4.900673363012013e-05, + "loss": 0.4202, "step": 9880 }, { - "epoch": 0.09, - "learning_rate": 4.599585622916854e-05, - "loss": 0.4134, + "epoch": 0.02, + "learning_rate": 4.900561508691081e-05, + "loss": 0.4227, "step": 9890 }, { - "epoch": 0.09, - "learning_rate": 4.59913521304387e-05, - "loss": 0.4151, + "epoch": 0.02, + "learning_rate": 4.900449654370148e-05, + "loss": 0.4204, "step": 9900 }, { - "epoch": 0.09, - "learning_rate": 4.598684803170886e-05, - "loss": 0.4173, + "epoch": 0.02, + "learning_rate": 4.900337800049216e-05, + "loss": 0.4242, "step": 9910 }, { - "epoch": 0.09, - "learning_rate": 4.598234393297901e-05, - "loss": 0.4174, + "epoch": 0.02, + "learning_rate": 4.900225945728284e-05, + "loss": 0.4239, "step": 9920 }, { - "epoch": 0.09, - "learning_rate": 4.597783983424917e-05, - "loss": 0.4229, + "epoch": 0.02, + "learning_rate": 4.9001140914073515e-05, + "loss": 0.4203, "step": 9930 }, { - "epoch": 0.09, - "learning_rate": 4.597333573551932e-05, - "loss": 0.412, + "epoch": 0.02, + "learning_rate": 4.900002237086419e-05, + "loss": 0.4219, "step": 9940 }, { - "epoch": 0.09, - "learning_rate": 4.596883163678948e-05, - "loss": 0.4179, + "epoch": 0.02, + "learning_rate": 4.8998903827654864e-05, + "loss": 0.4264, "step": 9950 }, { - "epoch": 0.09, - "learning_rate": 4.596432753805964e-05, - "loss": 0.4109, + "epoch": 0.02, + "learning_rate": 4.899778528444554e-05, + "loss": 0.429, "step": 9960 }, { - "epoch": 0.09, - "learning_rate": 4.595982343932979e-05, - "loss": 0.4129, + "epoch": 0.02, + "learning_rate": 4.899666674123622e-05, + "loss": 0.4181, "step": 9970 }, { - "epoch": 0.09, - "learning_rate": 4.595531934059995e-05, - "loss": 0.4156, + "epoch": 0.02, + "learning_rate": 4.899554819802689e-05, + "loss": 0.4173, "step": 9980 }, { - "epoch": 0.09, - "learning_rate": 4.5950815241870104e-05, - "loss": 0.4174, + "epoch": 0.02, + "learning_rate": 4.899442965481757e-05, + "loss": 0.4248, "step": 9990 }, { - "epoch": 0.09, - "learning_rate": 4.594631114314026e-05, - "loss": 0.4106, + "epoch": 0.02, + "learning_rate": 4.899331111160824e-05, + "loss": 0.4209, "step": 10000 }, { - "epoch": 0.09, - "learning_rate": 4.594180704441042e-05, - "loss": 0.4197, + "epoch": 0.02, + "learning_rate": 4.899219256839892e-05, + "loss": 0.4228, "step": 10010 }, { - "epoch": 0.09, - "learning_rate": 4.593730294568057e-05, - "loss": 0.4133, + "epoch": 0.02, + "learning_rate": 4.8991074025189596e-05, + "loss": 0.4161, "step": 10020 }, { - "epoch": 0.09, - "learning_rate": 4.593279884695073e-05, - "loss": 0.4083, + "epoch": 0.02, + "learning_rate": 4.8990067336301205e-05, + "loss": 0.4167, "step": 10030 }, { - "epoch": 0.09, - "learning_rate": 4.5928294748220885e-05, - "loss": 0.4184, + "epoch": 0.02, + "learning_rate": 4.898894879309188e-05, + "loss": 0.4242, "step": 10040 }, { - "epoch": 0.09, - "learning_rate": 4.5923790649491035e-05, - "loss": 0.4168, + "epoch": 0.02, + "learning_rate": 4.8987830249882554e-05, + "loss": 0.4171, "step": 10050 }, { - "epoch": 0.09, - "learning_rate": 4.591973696063418e-05, - "loss": 0.4122, + "epoch": 0.02, + "learning_rate": 4.898671170667323e-05, + "loss": 0.4203, "step": 10060 }, { - "epoch": 0.09, - "learning_rate": 4.5915232861904337e-05, - "loss": 0.4192, + "epoch": 0.02, + "learning_rate": 4.89855931634639e-05, + "loss": 0.4178, "step": 10070 }, { - "epoch": 0.09, - "learning_rate": 4.5910728763174494e-05, - "loss": 0.4138, + "epoch": 0.02, + "learning_rate": 4.898447462025458e-05, + "loss": 0.4139, "step": 10080 }, { - "epoch": 0.09, - "learning_rate": 4.5906224664444645e-05, - "loss": 0.4146, + "epoch": 0.02, + "learning_rate": 4.898335607704526e-05, + "loss": 0.4221, "step": 10090 }, { - "epoch": 0.09, - "learning_rate": 4.59017205657148e-05, - "loss": 0.4114, + "epoch": 0.02, + "learning_rate": 4.8982237533835937e-05, + "loss": 0.4175, "step": 10100 }, { - "epoch": 0.09, - "learning_rate": 4.589721646698496e-05, - "loss": 0.4186, + "epoch": 0.02, + "learning_rate": 4.8981118990626614e-05, + "loss": 0.4247, "step": 10110 }, { - "epoch": 0.09, - "learning_rate": 4.589271236825512e-05, - "loss": 0.4192, + "epoch": 0.02, + "learning_rate": 4.8980000447417286e-05, + "loss": 0.4167, "step": 10120 }, { - "epoch": 0.09, - "learning_rate": 4.588820826952527e-05, - "loss": 0.4254, + "epoch": 0.02, + "learning_rate": 4.8978881904207964e-05, + "loss": 0.4241, "step": 10130 }, { - "epoch": 0.09, - "learning_rate": 4.5883704170795425e-05, - "loss": 0.4187, + "epoch": 0.02, + "learning_rate": 4.8977763360998635e-05, + "loss": 0.4185, "step": 10140 }, { - "epoch": 0.09, - "learning_rate": 4.587920007206558e-05, - "loss": 0.4155, + "epoch": 0.02, + "learning_rate": 4.897664481778931e-05, + "loss": 0.4224, "step": 10150 }, { - "epoch": 0.09, - "learning_rate": 4.5874695973335734e-05, - "loss": 0.4127, + "epoch": 0.02, + "learning_rate": 4.897552627457999e-05, + "loss": 0.4233, "step": 10160 }, { - "epoch": 0.09, - "learning_rate": 4.58701918746059e-05, - "loss": 0.4118, + "epoch": 0.02, + "learning_rate": 4.897440773137066e-05, + "loss": 0.4244, "step": 10170 }, { - "epoch": 0.09, - "learning_rate": 4.586568777587605e-05, - "loss": 0.4147, + "epoch": 0.02, + "learning_rate": 4.897328918816134e-05, + "loss": 0.421, "step": 10180 }, { - "epoch": 0.09, - "learning_rate": 4.5861183677146206e-05, - "loss": 0.4157, + "epoch": 0.02, + "learning_rate": 4.897217064495202e-05, + "loss": 0.4217, "step": 10190 }, { - "epoch": 0.09, - "learning_rate": 4.5856679578416364e-05, - "loss": 0.4113, + "epoch": 0.02, + "learning_rate": 4.8971052101742695e-05, + "loss": 0.4137, "step": 10200 }, { - "epoch": 0.09, - "learning_rate": 4.5852175479686514e-05, - "loss": 0.4162, + "epoch": 0.02, + "learning_rate": 4.8969933558533373e-05, + "loss": 0.422, "step": 10210 }, { - "epoch": 0.09, - "learning_rate": 4.584767138095667e-05, - "loss": 0.4091, + "epoch": 0.02, + "learning_rate": 4.8968815015324045e-05, + "loss": 0.4149, "step": 10220 }, { - "epoch": 0.09, - "learning_rate": 4.584316728222683e-05, - "loss": 0.4215, + "epoch": 0.02, + "learning_rate": 4.896769647211472e-05, + "loss": 0.4184, "step": 10230 }, { - "epoch": 0.09, - "learning_rate": 4.583866318349698e-05, - "loss": 0.4153, + "epoch": 0.02, + "learning_rate": 4.8966577928905394e-05, + "loss": 0.4158, "step": 10240 }, { - "epoch": 0.09, - "learning_rate": 4.5834159084767144e-05, - "loss": 0.4196, + "epoch": 0.02, + "learning_rate": 4.896545938569607e-05, + "loss": 0.4188, "step": 10250 }, { - "epoch": 0.09, - "learning_rate": 4.5829654986037295e-05, - "loss": 0.4186, + "epoch": 0.02, + "learning_rate": 4.896434084248675e-05, + "loss": 0.4182, "step": 10260 }, { - "epoch": 0.09, - "learning_rate": 4.582515088730745e-05, - "loss": 0.4124, + "epoch": 0.02, + "learning_rate": 4.896322229927742e-05, + "loss": 0.4119, "step": 10270 }, { - "epoch": 0.09, - "learning_rate": 4.582064678857761e-05, - "loss": 0.4131, + "epoch": 0.02, + "learning_rate": 4.89621037560681e-05, + "loss": 0.4126, "step": 10280 }, { - "epoch": 0.09, - "learning_rate": 4.581614268984776e-05, - "loss": 0.4109, + "epoch": 0.02, + "learning_rate": 4.8960985212858777e-05, + "loss": 0.4161, "step": 10290 }, { - "epoch": 0.09, - "learning_rate": 4.581163859111792e-05, - "loss": 0.4065, + "epoch": 0.02, + "learning_rate": 4.8959866669649454e-05, + "loss": 0.4152, "step": 10300 }, { - "epoch": 0.09, - "learning_rate": 4.5807134492388076e-05, - "loss": 0.411, + "epoch": 0.02, + "learning_rate": 4.895874812644013e-05, + "loss": 0.4178, "step": 10310 }, { - "epoch": 0.09, - "learning_rate": 4.580263039365823e-05, - "loss": 0.412, + "epoch": 0.02, + "learning_rate": 4.8957629583230804e-05, + "loss": 0.4199, "step": 10320 }, { - "epoch": 0.09, - "learning_rate": 4.579812629492839e-05, - "loss": 0.4125, + "epoch": 0.02, + "learning_rate": 4.895651104002148e-05, + "loss": 0.4248, "step": 10330 }, { - "epoch": 0.09, - "learning_rate": 4.579362219619854e-05, - "loss": 0.4103, + "epoch": 0.02, + "learning_rate": 4.895539249681215e-05, + "loss": 0.4201, "step": 10340 }, { - "epoch": 0.09, - "learning_rate": 4.57891180974687e-05, - "loss": 0.414, + "epoch": 0.02, + "learning_rate": 4.895427395360283e-05, + "loss": 0.4229, "step": 10350 }, { - "epoch": 0.09, - "learning_rate": 4.5784613998738856e-05, - "loss": 0.41, + "epoch": 0.02, + "learning_rate": 4.895315541039351e-05, + "loss": 0.4166, "step": 10360 }, { - "epoch": 0.09, - "learning_rate": 4.5780109900009014e-05, - "loss": 0.4108, + "epoch": 0.02, + "learning_rate": 4.895203686718418e-05, + "loss": 0.4174, "step": 10370 }, { - "epoch": 0.09, - "learning_rate": 4.5775605801279165e-05, - "loss": 0.4198, + "epoch": 0.02, + "learning_rate": 4.895091832397486e-05, + "loss": 0.4194, "step": 10380 }, { - "epoch": 0.09, - "learning_rate": 4.577110170254932e-05, - "loss": 0.4196, + "epoch": 0.02, + "learning_rate": 4.894979978076553e-05, + "loss": 0.4124, "step": 10390 }, { - "epoch": 0.09, - "learning_rate": 4.576659760381948e-05, - "loss": 0.4072, + "epoch": 0.02, + "learning_rate": 4.8948681237556207e-05, + "loss": 0.4135, "step": 10400 }, { - "epoch": 0.09, - "learning_rate": 4.576209350508963e-05, - "loss": 0.4127, + "epoch": 0.02, + "learning_rate": 4.8947562694346885e-05, + "loss": 0.4161, "step": 10410 }, { - "epoch": 0.09, - "learning_rate": 4.575758940635979e-05, - "loss": 0.4103, + "epoch": 0.02, + "learning_rate": 4.894644415113756e-05, + "loss": 0.4143, "step": 10420 }, { - "epoch": 0.09, - "learning_rate": 4.5753085307629945e-05, - "loss": 0.4104, + "epoch": 0.02, + "learning_rate": 4.894532560792824e-05, + "loss": 0.4163, "step": 10430 }, { - "epoch": 0.09, - "learning_rate": 4.5748581208900096e-05, - "loss": 0.4116, + "epoch": 0.02, + "learning_rate": 4.894420706471891e-05, + "loss": 0.4132, "step": 10440 }, { - "epoch": 0.09, - "learning_rate": 4.574407711017026e-05, - "loss": 0.4097, + "epoch": 0.02, + "learning_rate": 4.894308852150959e-05, + "loss": 0.4186, "step": 10450 }, { - "epoch": 0.09, - "learning_rate": 4.573957301144041e-05, - "loss": 0.4162, + "epoch": 0.02, + "learning_rate": 4.894196997830026e-05, + "loss": 0.4283, "step": 10460 }, { - "epoch": 0.09, - "learning_rate": 4.573506891271057e-05, - "loss": 0.4091, + "epoch": 0.02, + "learning_rate": 4.894085143509094e-05, + "loss": 0.4173, "step": 10470 }, { - "epoch": 0.09, - "learning_rate": 4.5730564813980726e-05, - "loss": 0.4086, + "epoch": 0.02, + "learning_rate": 4.8939732891881616e-05, + "loss": 0.4147, "step": 10480 }, { - "epoch": 0.09, - "learning_rate": 4.572606071525088e-05, - "loss": 0.4175, + "epoch": 0.02, + "learning_rate": 4.893861434867229e-05, + "loss": 0.4136, "step": 10490 }, { - "epoch": 0.09, - "learning_rate": 4.572155661652104e-05, - "loss": 0.416, + "epoch": 0.02, + "learning_rate": 4.8937495805462966e-05, + "loss": 0.4152, "step": 10500 }, { - "epoch": 0.09, - "learning_rate": 4.571705251779119e-05, - "loss": 0.4084, + "epoch": 0.02, + "learning_rate": 4.8936377262253643e-05, + "loss": 0.4188, "step": 10510 }, { - "epoch": 0.09, - "learning_rate": 4.571254841906135e-05, - "loss": 0.4102, + "epoch": 0.02, + "learning_rate": 4.893525871904432e-05, + "loss": 0.422, "step": 10520 }, { - "epoch": 0.09, - "learning_rate": 4.570804432033151e-05, - "loss": 0.4111, + "epoch": 0.02, + "learning_rate": 4.8934140175835e-05, + "loss": 0.414, "step": 10530 }, { - "epoch": 0.09, - "learning_rate": 4.570354022160166e-05, - "loss": 0.41, + "epoch": 0.02, + "learning_rate": 4.893302163262567e-05, + "loss": 0.4155, "step": 10540 }, { - "epoch": 0.09, - "learning_rate": 4.5699036122871815e-05, - "loss": 0.4059, + "epoch": 0.02, + "learning_rate": 4.893190308941635e-05, + "loss": 0.4154, "step": 10550 }, { - "epoch": 0.09, - "learning_rate": 4.569453202414197e-05, - "loss": 0.4127, + "epoch": 0.02, + "learning_rate": 4.893078454620702e-05, + "loss": 0.4165, "step": 10560 }, { - "epoch": 0.09, - "learning_rate": 4.569002792541213e-05, - "loss": 0.4124, + "epoch": 0.02, + "learning_rate": 4.89296660029977e-05, + "loss": 0.4196, "step": 10570 }, { - "epoch": 0.09, - "learning_rate": 4.568552382668228e-05, - "loss": 0.4074, + "epoch": 0.02, + "learning_rate": 4.8928547459788375e-05, + "loss": 0.4175, "step": 10580 }, { - "epoch": 0.09, - "learning_rate": 4.568101972795244e-05, - "loss": 0.4051, + "epoch": 0.02, + "learning_rate": 4.8927428916579047e-05, + "loss": 0.4105, "step": 10590 }, { - "epoch": 0.09, - "learning_rate": 4.5676515629222596e-05, - "loss": 0.4012, + "epoch": 0.02, + "learning_rate": 4.8926310373369724e-05, + "loss": 0.414, "step": 10600 }, { - "epoch": 0.09, - "learning_rate": 4.567201153049275e-05, - "loss": 0.3994, + "epoch": 0.02, + "learning_rate": 4.89251918301604e-05, + "loss": 0.4153, "step": 10610 }, { - "epoch": 0.09, - "learning_rate": 4.5667507431762904e-05, - "loss": 0.4108, + "epoch": 0.02, + "learning_rate": 4.892407328695108e-05, + "loss": 0.416, "step": 10620 }, { - "epoch": 0.09, - "learning_rate": 4.566300333303306e-05, - "loss": 0.4074, + "epoch": 0.02, + "learning_rate": 4.892295474374176e-05, + "loss": 0.4091, "step": 10630 }, { - "epoch": 0.09, - "learning_rate": 4.565849923430322e-05, - "loss": 0.403, + "epoch": 0.02, + "learning_rate": 4.892183620053243e-05, + "loss": 0.4144, "step": 10640 }, { - "epoch": 0.1, - "learning_rate": 4.5653995135573376e-05, - "loss": 0.4043, + "epoch": 0.02, + "learning_rate": 4.892071765732311e-05, + "loss": 0.4146, "step": 10650 }, { - "epoch": 0.1, - "learning_rate": 4.564949103684353e-05, - "loss": 0.4067, + "epoch": 0.02, + "learning_rate": 4.891959911411378e-05, + "loss": 0.4143, "step": 10660 }, { - "epoch": 0.1, - "learning_rate": 4.5644986938113684e-05, - "loss": 0.4113, + "epoch": 0.02, + "learning_rate": 4.8918480570904456e-05, + "loss": 0.4173, "step": 10670 }, { - "epoch": 0.1, - "learning_rate": 4.564048283938384e-05, - "loss": 0.4099, + "epoch": 0.02, + "learning_rate": 4.891736202769513e-05, + "loss": 0.4119, "step": 10680 }, { - "epoch": 0.1, - "learning_rate": 4.563597874065399e-05, - "loss": 0.4096, + "epoch": 0.02, + "learning_rate": 4.8916243484485806e-05, + "loss": 0.4153, "step": 10690 }, { - "epoch": 0.1, - "learning_rate": 4.563147464192416e-05, - "loss": 0.4099, + "epoch": 0.02, + "learning_rate": 4.8915124941276483e-05, + "loss": 0.4141, "step": 10700 }, { - "epoch": 0.1, - "learning_rate": 4.562697054319431e-05, - "loss": 0.4147, + "epoch": 0.02, + "learning_rate": 4.891400639806716e-05, + "loss": 0.4107, "step": 10710 }, { - "epoch": 0.1, - "learning_rate": 4.5622466444464465e-05, - "loss": 0.4083, + "epoch": 0.02, + "learning_rate": 4.891288785485784e-05, + "loss": 0.4143, "step": 10720 }, { - "epoch": 0.1, - "learning_rate": 4.561796234573462e-05, - "loss": 0.4085, + "epoch": 0.02, + "learning_rate": 4.891176931164851e-05, + "loss": 0.4051, "step": 10730 }, { - "epoch": 0.1, - "learning_rate": 4.561345824700477e-05, - "loss": 0.4028, + "epoch": 0.02, + "learning_rate": 4.891065076843919e-05, + "loss": 0.4127, "step": 10740 }, { - "epoch": 0.1, - "learning_rate": 4.560895414827494e-05, - "loss": 0.4065, + "epoch": 0.02, + "learning_rate": 4.8909532225229866e-05, + "loss": 0.4095, "step": 10750 }, { - "epoch": 0.1, - "learning_rate": 4.560445004954509e-05, - "loss": 0.4139, + "epoch": 0.02, + "learning_rate": 4.890841368202054e-05, + "loss": 0.4149, "step": 10760 }, { - "epoch": 0.1, - "learning_rate": 4.5599945950815246e-05, - "loss": 0.409, + "epoch": 0.02, + "learning_rate": 4.8907295138811215e-05, + "loss": 0.4232, "step": 10770 }, { - "epoch": 0.1, - "learning_rate": 4.55954418520854e-05, - "loss": 0.4004, + "epoch": 0.02, + "learning_rate": 4.8906176595601887e-05, + "loss": 0.4097, "step": 10780 }, { - "epoch": 0.1, - "learning_rate": 4.5590937753355554e-05, - "loss": 0.3992, + "epoch": 0.02, + "learning_rate": 4.8905058052392564e-05, + "loss": 0.4149, "step": 10790 }, { - "epoch": 0.1, - "learning_rate": 4.558643365462571e-05, - "loss": 0.4009, + "epoch": 0.02, + "learning_rate": 4.890393950918324e-05, + "loss": 0.4145, "step": 10800 }, { - "epoch": 0.1, - "learning_rate": 4.558192955589587e-05, - "loss": 0.4141, + "epoch": 0.02, + "learning_rate": 4.8902820965973914e-05, + "loss": 0.4114, "step": 10810 }, { - "epoch": 0.1, - "learning_rate": 4.557742545716602e-05, - "loss": 0.4048, + "epoch": 0.02, + "learning_rate": 4.890170242276459e-05, + "loss": 0.4114, "step": 10820 }, { - "epoch": 0.1, - "learning_rate": 4.557292135843618e-05, - "loss": 0.4016, + "epoch": 0.02, + "learning_rate": 4.890058387955527e-05, + "loss": 0.4141, "step": 10830 }, { - "epoch": 0.1, - "learning_rate": 4.5568417259706335e-05, - "loss": 0.4098, + "epoch": 0.02, + "learning_rate": 4.889946533634595e-05, + "loss": 0.4205, "step": 10840 }, { - "epoch": 0.1, - "learning_rate": 4.556391316097649e-05, - "loss": 0.4073, + "epoch": 0.02, + "learning_rate": 4.8898346793136625e-05, + "loss": 0.4125, "step": 10850 }, { - "epoch": 0.1, - "learning_rate": 4.555940906224664e-05, - "loss": 0.4088, + "epoch": 0.02, + "learning_rate": 4.8897228249927296e-05, + "loss": 0.4102, "step": 10860 }, { - "epoch": 0.1, - "learning_rate": 4.55549049635168e-05, - "loss": 0.413, + "epoch": 0.02, + "learning_rate": 4.8896109706717974e-05, + "loss": 0.4159, "step": 10870 }, { - "epoch": 0.1, - "learning_rate": 4.555040086478696e-05, - "loss": 0.4073, + "epoch": 0.02, + "learning_rate": 4.8894991163508645e-05, + "loss": 0.4142, "step": 10880 }, { - "epoch": 0.1, - "learning_rate": 4.5545896766057115e-05, - "loss": 0.4025, + "epoch": 0.02, + "learning_rate": 4.8893872620299323e-05, + "loss": 0.4169, "step": 10890 }, { - "epoch": 0.1, - "learning_rate": 4.554139266732727e-05, - "loss": 0.4116, + "epoch": 0.02, + "learning_rate": 4.889275407709e-05, + "loss": 0.4098, "step": 10900 }, { - "epoch": 0.1, - "learning_rate": 4.5536888568597424e-05, - "loss": 0.3997, + "epoch": 0.02, + "learning_rate": 4.889163553388067e-05, + "loss": 0.4138, "step": 10910 }, { - "epoch": 0.1, - "learning_rate": 4.553238446986758e-05, - "loss": 0.4063, + "epoch": 0.02, + "learning_rate": 4.889051699067135e-05, + "loss": 0.4142, "step": 10920 }, { - "epoch": 0.1, - "learning_rate": 4.552788037113774e-05, - "loss": 0.4013, + "epoch": 0.02, + "learning_rate": 4.888939844746203e-05, + "loss": 0.4123, "step": 10930 }, { - "epoch": 0.1, - "learning_rate": 4.552337627240789e-05, - "loss": 0.4054, + "epoch": 0.02, + "learning_rate": 4.8888279904252706e-05, + "loss": 0.4155, "step": 10940 }, { - "epoch": 0.1, - "learning_rate": 4.5518872173678054e-05, - "loss": 0.4122, + "epoch": 0.02, + "learning_rate": 4.8887161361043384e-05, + "loss": 0.4086, "step": 10950 }, { - "epoch": 0.1, - "learning_rate": 4.5514368074948204e-05, - "loss": 0.3989, + "epoch": 0.02, + "learning_rate": 4.8886042817834055e-05, + "loss": 0.4048, "step": 10960 }, { - "epoch": 0.1, - "learning_rate": 4.550986397621836e-05, - "loss": 0.4, + "epoch": 0.02, + "learning_rate": 4.888492427462473e-05, + "loss": 0.4109, "step": 10970 }, { - "epoch": 0.1, - "learning_rate": 4.550535987748852e-05, - "loss": 0.4072, + "epoch": 0.02, + "learning_rate": 4.8883805731415404e-05, + "loss": 0.411, "step": 10980 }, { - "epoch": 0.1, - "learning_rate": 4.550085577875867e-05, - "loss": 0.4066, + "epoch": 0.02, + "learning_rate": 4.888268718820608e-05, + "loss": 0.4116, "step": 10990 }, { - "epoch": 0.1, - "learning_rate": 4.549635168002883e-05, - "loss": 0.407, + "epoch": 0.02, + "learning_rate": 4.8881568644996754e-05, + "loss": 0.4135, "step": 11000 }, { - "epoch": 0.1, - "learning_rate": 4.5491847581298985e-05, - "loss": 0.4013, + "epoch": 0.02, + "learning_rate": 4.888045010178743e-05, + "loss": 0.416, "step": 11010 }, { - "epoch": 0.1, - "learning_rate": 4.548734348256914e-05, - "loss": 0.4019, + "epoch": 0.02, + "learning_rate": 4.887933155857811e-05, + "loss": 0.4073, "step": 11020 }, { - "epoch": 0.1, - "learning_rate": 4.54828393838393e-05, - "loss": 0.4017, + "epoch": 0.02, + "learning_rate": 4.887821301536879e-05, + "loss": 0.407, "step": 11030 }, { - "epoch": 0.1, - "learning_rate": 4.547833528510945e-05, - "loss": 0.4031, + "epoch": 0.02, + "learning_rate": 4.8877094472159465e-05, + "loss": 0.4034, "step": 11040 }, { - "epoch": 0.1, - "learning_rate": 4.547383118637961e-05, - "loss": 0.4032, + "epoch": 0.02, + "learning_rate": 4.8875975928950136e-05, + "loss": 0.41, "step": 11050 }, { - "epoch": 0.1, - "learning_rate": 4.5469327087649766e-05, - "loss": 0.4068, + "epoch": 0.02, + "learning_rate": 4.8874857385740814e-05, + "loss": 0.4061, "step": 11060 }, { - "epoch": 0.1, - "learning_rate": 4.5464822988919916e-05, - "loss": 0.4055, + "epoch": 0.02, + "learning_rate": 4.887373884253149e-05, + "loss": 0.4074, "step": 11070 }, { - "epoch": 0.1, - "learning_rate": 4.5460318890190074e-05, - "loss": 0.4014, + "epoch": 0.02, + "learning_rate": 4.887262029932216e-05, + "loss": 0.4106, "step": 11080 }, { - "epoch": 0.1, - "learning_rate": 4.545581479146023e-05, - "loss": 0.4062, + "epoch": 0.02, + "learning_rate": 4.887150175611284e-05, + "loss": 0.408, "step": 11090 }, { - "epoch": 0.1, - "learning_rate": 4.545131069273039e-05, - "loss": 0.3928, + "epoch": 0.02, + "learning_rate": 4.887038321290351e-05, + "loss": 0.4086, "step": 11100 }, { - "epoch": 0.1, - "learning_rate": 4.544680659400054e-05, - "loss": 0.4021, + "epoch": 0.02, + "learning_rate": 4.886926466969419e-05, + "loss": 0.4087, "step": 11110 }, { - "epoch": 0.1, - "learning_rate": 4.54423024952707e-05, - "loss": 0.3974, + "epoch": 0.02, + "learning_rate": 4.886814612648487e-05, + "loss": 0.4075, "step": 11120 }, { - "epoch": 0.1, - "learning_rate": 4.5437798396540855e-05, - "loss": 0.3969, + "epoch": 0.02, + "learning_rate": 4.8867027583275546e-05, + "loss": 0.4105, "step": 11130 }, { - "epoch": 0.1, - "learning_rate": 4.5433294297811005e-05, - "loss": 0.4056, + "epoch": 0.02, + "learning_rate": 4.8865909040066224e-05, + "loss": 0.4037, "step": 11140 }, { - "epoch": 0.1, - "learning_rate": 4.542879019908117e-05, - "loss": 0.4166, + "epoch": 0.02, + "learning_rate": 4.8864790496856895e-05, + "loss": 0.4058, "step": 11150 }, { - "epoch": 0.1, - "learning_rate": 4.542428610035132e-05, - "loss": 0.4086, + "epoch": 0.02, + "learning_rate": 4.886367195364757e-05, + "loss": 0.4092, "step": 11160 }, { - "epoch": 0.1, - "learning_rate": 4.541978200162148e-05, - "loss": 0.4073, + "epoch": 0.02, + "learning_rate": 4.886255341043825e-05, + "loss": 0.4063, "step": 11170 }, { - "epoch": 0.1, - "learning_rate": 4.5415277902891635e-05, - "loss": 0.406, + "epoch": 0.02, + "learning_rate": 4.886143486722892e-05, + "loss": 0.41, "step": 11180 }, { - "epoch": 0.1, - "learning_rate": 4.5410773804161786e-05, - "loss": 0.404, + "epoch": 0.02, + "learning_rate": 4.88603163240196e-05, + "loss": 0.4096, "step": 11190 }, { - "epoch": 0.1, - "learning_rate": 4.540626970543195e-05, - "loss": 0.4084, + "epoch": 0.02, + "learning_rate": 4.885919778081027e-05, + "loss": 0.4096, "step": 11200 }, { - "epoch": 0.1, - "learning_rate": 4.54017656067021e-05, - "loss": 0.3998, + "epoch": 0.03, + "learning_rate": 4.885807923760095e-05, + "loss": 0.4114, "step": 11210 }, { - "epoch": 0.1, - "learning_rate": 4.539726150797226e-05, - "loss": 0.4024, + "epoch": 0.03, + "learning_rate": 4.885696069439163e-05, + "loss": 0.4067, "step": 11220 }, { - "epoch": 0.1, - "learning_rate": 4.5392757409242416e-05, - "loss": 0.401, + "epoch": 0.03, + "learning_rate": 4.88558421511823e-05, + "loss": 0.4099, "step": 11230 }, { - "epoch": 0.1, - "learning_rate": 4.5388253310512567e-05, - "loss": 0.3996, + "epoch": 0.03, + "learning_rate": 4.885472360797298e-05, + "loss": 0.4059, "step": 11240 }, { - "epoch": 0.1, - "learning_rate": 4.5383749211782724e-05, - "loss": 0.3962, + "epoch": 0.03, + "learning_rate": 4.8853605064763654e-05, + "loss": 0.4076, "step": 11250 }, { - "epoch": 0.1, - "learning_rate": 4.537924511305288e-05, - "loss": 0.3998, + "epoch": 0.03, + "learning_rate": 4.885248652155433e-05, + "loss": 0.4092, "step": 11260 }, { - "epoch": 0.1, - "learning_rate": 4.537474101432303e-05, - "loss": 0.3991, + "epoch": 0.03, + "learning_rate": 4.885136797834501e-05, + "loss": 0.4059, "step": 11270 }, { - "epoch": 0.1, - "learning_rate": 4.537023691559319e-05, - "loss": 0.4011, + "epoch": 0.03, + "learning_rate": 4.885024943513568e-05, + "loss": 0.4075, "step": 11280 }, { - "epoch": 0.1, - "learning_rate": 4.536573281686335e-05, - "loss": 0.4039, + "epoch": 0.03, + "learning_rate": 4.884913089192636e-05, + "loss": 0.4071, "step": 11290 }, { - "epoch": 0.1, - "learning_rate": 4.5361228718133505e-05, - "loss": 0.3988, + "epoch": 0.03, + "learning_rate": 4.884801234871703e-05, + "loss": 0.4056, "step": 11300 }, { - "epoch": 0.1, - "learning_rate": 4.535672461940366e-05, - "loss": 0.406, + "epoch": 0.03, + "learning_rate": 4.884689380550771e-05, + "loss": 0.4056, "step": 11310 }, { - "epoch": 0.1, - "learning_rate": 4.535222052067381e-05, - "loss": 0.3949, + "epoch": 0.03, + "learning_rate": 4.884577526229838e-05, + "loss": 0.4034, "step": 11320 }, { - "epoch": 0.1, - "learning_rate": 4.534771642194397e-05, - "loss": 0.3954, + "epoch": 0.03, + "learning_rate": 4.884465671908906e-05, + "loss": 0.4056, "step": 11330 }, { - "epoch": 0.1, - "learning_rate": 4.534321232321413e-05, - "loss": 0.3944, + "epoch": 0.03, + "learning_rate": 4.8843538175879735e-05, + "loss": 0.3998, "step": 11340 }, { - "epoch": 0.1, - "learning_rate": 4.5338708224484285e-05, - "loss": 0.4005, + "epoch": 0.03, + "learning_rate": 4.884241963267041e-05, + "loss": 0.4069, "step": 11350 }, { - "epoch": 0.1, - "learning_rate": 4.5334204125754436e-05, - "loss": 0.3951, + "epoch": 0.03, + "learning_rate": 4.884130108946109e-05, + "loss": 0.4078, "step": 11360 }, { - "epoch": 0.1, - "learning_rate": 4.5329700027024594e-05, - "loss": 0.3957, + "epoch": 0.03, + "learning_rate": 4.884018254625176e-05, + "loss": 0.401, "step": 11370 }, { - "epoch": 0.1, - "learning_rate": 4.532519592829475e-05, - "loss": 0.3995, + "epoch": 0.03, + "learning_rate": 4.883906400304244e-05, + "loss": 0.4051, "step": 11380 }, { - "epoch": 0.1, - "learning_rate": 4.53206918295649e-05, - "loss": 0.4007, + "epoch": 0.03, + "learning_rate": 4.883794545983312e-05, + "loss": 0.408, "step": 11390 }, { - "epoch": 0.1, - "learning_rate": 4.5316187730835066e-05, - "loss": 0.3968, + "epoch": 0.03, + "learning_rate": 4.883682691662379e-05, + "loss": 0.4032, "step": 11400 }, { - "epoch": 0.1, - "learning_rate": 4.531168363210522e-05, - "loss": 0.4015, + "epoch": 0.03, + "learning_rate": 4.883570837341447e-05, + "loss": 0.4039, "step": 11410 }, { - "epoch": 0.1, - "learning_rate": 4.5307179533375374e-05, - "loss": 0.4037, + "epoch": 0.03, + "learning_rate": 4.883458983020514e-05, + "loss": 0.4048, "step": 11420 }, { - "epoch": 0.1, - "learning_rate": 4.530267543464553e-05, - "loss": 0.3992, + "epoch": 0.03, + "learning_rate": 4.8833471286995816e-05, + "loss": 0.4096, "step": 11430 }, { - "epoch": 0.1, - "learning_rate": 4.529817133591568e-05, - "loss": 0.3987, + "epoch": 0.03, + "learning_rate": 4.8832352743786494e-05, + "loss": 0.4092, "step": 11440 }, { - "epoch": 0.1, - "learning_rate": 4.529366723718585e-05, - "loss": 0.3972, + "epoch": 0.03, + "learning_rate": 4.883123420057717e-05, + "loss": 0.4077, "step": 11450 }, { - "epoch": 0.1, - "learning_rate": 4.5289163138456e-05, - "loss": 0.4025, + "epoch": 0.03, + "learning_rate": 4.883011565736785e-05, + "loss": 0.4104, "step": 11460 }, { - "epoch": 0.1, - "learning_rate": 4.528465903972615e-05, - "loss": 0.3964, + "epoch": 0.03, + "learning_rate": 4.882899711415852e-05, + "loss": 0.4157, "step": 11470 }, { - "epoch": 0.1, - "learning_rate": 4.528015494099631e-05, - "loss": 0.4009, + "epoch": 0.03, + "learning_rate": 4.88278785709492e-05, + "loss": 0.4063, "step": 11480 }, { - "epoch": 0.1, - "learning_rate": 4.527565084226646e-05, - "loss": 0.3963, + "epoch": 0.03, + "learning_rate": 4.882676002773988e-05, + "loss": 0.4079, "step": 11490 }, { - "epoch": 0.1, - "learning_rate": 4.527114674353662e-05, - "loss": 0.3987, + "epoch": 0.03, + "learning_rate": 4.882564148453055e-05, + "loss": 0.407, "step": 11500 }, { - "epoch": 0.1, - "learning_rate": 4.526664264480678e-05, - "loss": 0.3989, + "epoch": 0.03, + "learning_rate": 4.8824522941321226e-05, + "loss": 0.4102, "step": 11510 }, { - "epoch": 0.1, - "learning_rate": 4.526213854607693e-05, - "loss": 0.397, + "epoch": 0.03, + "learning_rate": 4.88234043981119e-05, + "loss": 0.4098, "step": 11520 }, { - "epoch": 0.1, - "learning_rate": 4.5257634447347086e-05, - "loss": 0.3993, + "epoch": 0.03, + "learning_rate": 4.8822285854902575e-05, + "loss": 0.4142, "step": 11530 }, { - "epoch": 0.1, - "learning_rate": 4.5253130348617244e-05, - "loss": 0.4045, + "epoch": 0.03, + "learning_rate": 4.882116731169325e-05, + "loss": 0.4048, "step": 11540 }, { - "epoch": 0.1, - "learning_rate": 4.52486262498874e-05, - "loss": 0.4007, + "epoch": 0.03, + "learning_rate": 4.882004876848393e-05, + "loss": 0.4101, "step": 11550 }, { - "epoch": 0.1, - "learning_rate": 4.524412215115755e-05, - "loss": 0.4013, + "epoch": 0.03, + "learning_rate": 4.881893022527461e-05, + "loss": 0.4075, "step": 11560 }, { - "epoch": 0.1, - "learning_rate": 4.523961805242771e-05, - "loss": 0.3975, + "epoch": 0.03, + "learning_rate": 4.881781168206528e-05, + "loss": 0.4031, "step": 11570 }, { - "epoch": 0.1, - "learning_rate": 4.523511395369787e-05, - "loss": 0.3981, + "epoch": 0.03, + "learning_rate": 4.881669313885596e-05, + "loss": 0.3999, "step": 11580 }, { - "epoch": 0.1, - "learning_rate": 4.5230609854968025e-05, - "loss": 0.3975, + "epoch": 0.03, + "learning_rate": 4.8815574595646636e-05, + "loss": 0.3997, "step": 11590 }, { - "epoch": 0.1, - "learning_rate": 4.522610575623818e-05, - "loss": 0.4031, + "epoch": 0.03, + "learning_rate": 4.881445605243731e-05, + "loss": 0.4089, "step": 11600 }, { - "epoch": 0.1, - "learning_rate": 4.522160165750833e-05, - "loss": 0.3976, + "epoch": 0.03, + "learning_rate": 4.8813337509227985e-05, + "loss": 0.3994, "step": 11610 }, { - "epoch": 0.1, - "learning_rate": 4.521709755877849e-05, - "loss": 0.4013, + "epoch": 0.03, + "learning_rate": 4.8812218966018656e-05, + "loss": 0.4082, "step": 11620 }, { - "epoch": 0.1, - "learning_rate": 4.521259346004865e-05, - "loss": 0.3989, + "epoch": 0.03, + "learning_rate": 4.8811100422809334e-05, + "loss": 0.3993, "step": 11630 }, { - "epoch": 0.1, - "learning_rate": 4.52080893613188e-05, - "loss": 0.3949, + "epoch": 0.03, + "learning_rate": 4.8809981879600005e-05, + "loss": 0.4032, "step": 11640 }, { - "epoch": 0.1, - "learning_rate": 4.520358526258896e-05, - "loss": 0.4069, + "epoch": 0.03, + "learning_rate": 4.880886333639068e-05, + "loss": 0.4, "step": 11650 }, { - "epoch": 0.1, - "learning_rate": 4.5199081163859114e-05, - "loss": 0.389, + "epoch": 0.03, + "learning_rate": 4.880774479318137e-05, + "loss": 0.3984, "step": 11660 }, { - "epoch": 0.1, - "learning_rate": 4.519457706512927e-05, - "loss": 0.3993, + "epoch": 0.03, + "learning_rate": 4.880662624997204e-05, + "loss": 0.4036, "step": 11670 }, { - "epoch": 0.1, - "learning_rate": 4.519007296639943e-05, - "loss": 0.3866, + "epoch": 0.03, + "learning_rate": 4.880550770676272e-05, + "loss": 0.4051, "step": 11680 }, { - "epoch": 0.1, - "learning_rate": 4.518556886766958e-05, - "loss": 0.4033, + "epoch": 0.03, + "learning_rate": 4.880438916355339e-05, + "loss": 0.401, "step": 11690 }, { - "epoch": 0.1, - "learning_rate": 4.518106476893974e-05, - "loss": 0.399, + "epoch": 0.03, + "learning_rate": 4.8803270620344066e-05, + "loss": 0.3985, "step": 11700 }, { - "epoch": 0.1, - "learning_rate": 4.5176560670209894e-05, - "loss": 0.393, + "epoch": 0.03, + "learning_rate": 4.8802152077134744e-05, + "loss": 0.4027, "step": 11710 }, { - "epoch": 0.1, - "learning_rate": 4.5172056571480045e-05, - "loss": 0.3923, + "epoch": 0.03, + "learning_rate": 4.8801033533925415e-05, + "loss": 0.4051, "step": 11720 }, { - "epoch": 0.1, - "learning_rate": 4.516755247275021e-05, - "loss": 0.3892, + "epoch": 0.03, + "learning_rate": 4.879991499071609e-05, + "loss": 0.4066, "step": 11730 }, { - "epoch": 0.1, - "learning_rate": 4.516304837402036e-05, - "loss": 0.396, + "epoch": 0.03, + "learning_rate": 4.8798796447506764e-05, + "loss": 0.3964, "step": 11740 }, { - "epoch": 0.1, - "learning_rate": 4.515854427529052e-05, - "loss": 0.4043, + "epoch": 0.03, + "learning_rate": 4.879767790429744e-05, + "loss": 0.4036, "step": 11750 }, { - "epoch": 0.1, - "learning_rate": 4.5154040176560675e-05, - "loss": 0.3955, + "epoch": 0.03, + "learning_rate": 4.879655936108812e-05, + "loss": 0.4019, "step": 11760 }, { - "epoch": 0.11, - "learning_rate": 4.5149536077830826e-05, - "loss": 0.4022, + "epoch": 0.03, + "learning_rate": 4.87954408178788e-05, + "loss": 0.4029, "step": 11770 }, { - "epoch": 0.11, - "learning_rate": 4.514503197910098e-05, - "loss": 0.4031, + "epoch": 0.03, + "learning_rate": 4.8794322274669476e-05, + "loss": 0.4035, "step": 11780 }, { - "epoch": 0.11, - "learning_rate": 4.514052788037114e-05, - "loss": 0.3997, + "epoch": 0.03, + "learning_rate": 4.879320373146015e-05, + "loss": 0.406, "step": 11790 }, { - "epoch": 0.11, - "learning_rate": 4.51360237816413e-05, - "loss": 0.3949, + "epoch": 0.03, + "learning_rate": 4.8792085188250825e-05, + "loss": 0.3981, "step": 11800 }, { - "epoch": 0.11, - "learning_rate": 4.513151968291145e-05, - "loss": 0.3939, + "epoch": 0.03, + "learning_rate": 4.87909666450415e-05, + "loss": 0.4018, "step": 11810 }, { - "epoch": 0.11, - "learning_rate": 4.5127015584181606e-05, - "loss": 0.3911, + "epoch": 0.03, + "learning_rate": 4.8789848101832174e-05, + "loss": 0.4072, "step": 11820 }, { - "epoch": 0.11, - "learning_rate": 4.5122511485451764e-05, - "loss": 0.3927, + "epoch": 0.03, + "learning_rate": 4.878872955862285e-05, + "loss": 0.3943, "step": 11830 }, { - "epoch": 0.11, - "learning_rate": 4.5118007386721914e-05, - "loss": 0.3907, + "epoch": 0.03, + "learning_rate": 4.878761101541352e-05, + "loss": 0.4024, "step": 11840 }, { - "epoch": 0.11, - "learning_rate": 4.511350328799208e-05, - "loss": 0.3871, + "epoch": 0.03, + "learning_rate": 4.87864924722042e-05, + "loss": 0.3969, "step": 11850 }, { - "epoch": 0.11, - "learning_rate": 4.510899918926223e-05, - "loss": 0.3999, + "epoch": 0.03, + "learning_rate": 4.878537392899488e-05, + "loss": 0.3993, "step": 11860 }, { - "epoch": 0.11, - "learning_rate": 4.510449509053239e-05, - "loss": 0.3958, + "epoch": 0.03, + "learning_rate": 4.878425538578556e-05, + "loss": 0.4009, "step": 11870 }, { - "epoch": 0.11, - "learning_rate": 4.5099990991802544e-05, - "loss": 0.3957, + "epoch": 0.03, + "learning_rate": 4.8783136842576235e-05, + "loss": 0.4017, "step": 11880 }, { - "epoch": 0.11, - "learning_rate": 4.5095486893072695e-05, - "loss": 0.3987, + "epoch": 0.03, + "learning_rate": 4.8782018299366906e-05, + "loss": 0.3964, "step": 11890 }, { - "epoch": 0.11, - "learning_rate": 4.509098279434286e-05, - "loss": 0.3993, + "epoch": 0.03, + "learning_rate": 4.8780899756157584e-05, + "loss": 0.4051, "step": 11900 }, { - "epoch": 0.11, - "learning_rate": 4.508647869561301e-05, - "loss": 0.3859, + "epoch": 0.03, + "learning_rate": 4.877978121294826e-05, + "loss": 0.4061, "step": 11910 }, { - "epoch": 0.11, - "learning_rate": 4.508197459688316e-05, - "loss": 0.3927, + "epoch": 0.03, + "learning_rate": 4.877866266973893e-05, + "loss": 0.4083, "step": 11920 }, { - "epoch": 0.11, - "learning_rate": 4.5077470498153325e-05, - "loss": 0.3943, + "epoch": 0.03, + "learning_rate": 4.877754412652961e-05, + "loss": 0.3968, "step": 11930 }, { - "epoch": 0.11, - "learning_rate": 4.5072966399423476e-05, - "loss": 0.3943, + "epoch": 0.03, + "learning_rate": 4.877642558332028e-05, + "loss": 0.4022, "step": 11940 }, { - "epoch": 0.11, - "learning_rate": 4.506846230069363e-05, - "loss": 0.3894, + "epoch": 0.03, + "learning_rate": 4.877530704011096e-05, + "loss": 0.4031, "step": 11950 }, { - "epoch": 0.11, - "learning_rate": 4.506395820196379e-05, - "loss": 0.3881, + "epoch": 0.03, + "learning_rate": 4.877418849690164e-05, + "loss": 0.407, "step": 11960 }, { - "epoch": 0.11, - "learning_rate": 4.505945410323394e-05, - "loss": 0.3908, + "epoch": 0.03, + "learning_rate": 4.8773069953692316e-05, + "loss": 0.4039, "step": 11970 }, { - "epoch": 0.11, - "learning_rate": 4.50549500045041e-05, - "loss": 0.3999, + "epoch": 0.03, + "learning_rate": 4.8771951410482994e-05, + "loss": 0.4005, "step": 11980 }, { - "epoch": 0.11, - "learning_rate": 4.5050445905774257e-05, - "loss": 0.3927, + "epoch": 0.03, + "learning_rate": 4.8770832867273665e-05, + "loss": 0.3948, "step": 11990 }, { - "epoch": 0.11, - "learning_rate": 4.5045941807044414e-05, - "loss": 0.3952, + "epoch": 0.03, + "learning_rate": 4.876971432406434e-05, + "loss": 0.3958, "step": 12000 }, { - "epoch": 0.11, - "learning_rate": 4.504143770831457e-05, - "loss": 0.3894, + "epoch": 0.03, + "learning_rate": 4.8768595780855014e-05, + "loss": 0.4054, "step": 12010 }, { - "epoch": 0.11, - "learning_rate": 4.503693360958472e-05, - "loss": 0.3979, + "epoch": 0.03, + "learning_rate": 4.876747723764569e-05, + "loss": 0.3989, "step": 12020 }, { - "epoch": 0.11, - "learning_rate": 4.503242951085488e-05, - "loss": 0.3965, + "epoch": 0.03, + "learning_rate": 4.876635869443637e-05, + "loss": 0.3933, "step": 12030 }, { - "epoch": 0.11, - "learning_rate": 4.502792541212504e-05, - "loss": 0.3978, + "epoch": 0.03, + "learning_rate": 4.876524015122704e-05, + "loss": 0.3976, "step": 12040 }, { - "epoch": 0.11, - "learning_rate": 4.5023421313395195e-05, - "loss": 0.3971, + "epoch": 0.03, + "learning_rate": 4.876423346233866e-05, + "loss": 0.3964, "step": 12050 }, { - "epoch": 0.11, - "learning_rate": 4.501936762453833e-05, - "loss": 0.3899, + "epoch": 0.03, + "learning_rate": 4.876311491912933e-05, + "loss": 0.4082, "step": 12060 }, { - "epoch": 0.11, - "learning_rate": 4.501486352580849e-05, - "loss": 0.3998, + "epoch": 0.03, + "learning_rate": 4.8761996375920006e-05, + "loss": 0.3971, "step": 12070 }, { - "epoch": 0.11, - "learning_rate": 4.501035942707864e-05, - "loss": 0.3976, + "epoch": 0.03, + "learning_rate": 4.876087783271068e-05, + "loss": 0.395, "step": 12080 }, { - "epoch": 0.11, - "learning_rate": 4.50058553283488e-05, - "loss": 0.393, + "epoch": 0.03, + "learning_rate": 4.8759759289501355e-05, + "loss": 0.3972, "step": 12090 }, { - "epoch": 0.11, - "learning_rate": 4.5001351229618955e-05, - "loss": 0.3926, + "epoch": 0.03, + "learning_rate": 4.875864074629203e-05, + "loss": 0.3938, "step": 12100 }, { - "epoch": 0.11, - "learning_rate": 4.499684713088911e-05, - "loss": 0.3937, + "epoch": 0.03, + "learning_rate": 4.8757522203082704e-05, + "loss": 0.3981, "step": 12110 }, { - "epoch": 0.11, - "learning_rate": 4.499234303215927e-05, - "loss": 0.3834, + "epoch": 0.03, + "learning_rate": 4.875640365987338e-05, + "loss": 0.4005, "step": 12120 }, { - "epoch": 0.11, - "learning_rate": 4.498783893342942e-05, - "loss": 0.3944, + "epoch": 0.03, + "learning_rate": 4.875528511666406e-05, + "loss": 0.3964, "step": 12130 }, { - "epoch": 0.11, - "learning_rate": 4.498333483469958e-05, - "loss": 0.3928, + "epoch": 0.03, + "learning_rate": 4.875416657345474e-05, + "loss": 0.3981, "step": 12140 }, { - "epoch": 0.11, - "learning_rate": 4.4978830735969736e-05, - "loss": 0.4, + "epoch": 0.03, + "learning_rate": 4.8753048030245416e-05, + "loss": 0.4012, "step": 12150 }, { - "epoch": 0.11, - "learning_rate": 4.4974326637239886e-05, - "loss": 0.3895, + "epoch": 0.03, + "learning_rate": 4.875192948703609e-05, + "loss": 0.4036, "step": 12160 }, { - "epoch": 0.11, - "learning_rate": 4.496982253851005e-05, - "loss": 0.4059, + "epoch": 0.03, + "learning_rate": 4.8750810943826765e-05, + "loss": 0.3969, "step": 12170 }, { - "epoch": 0.11, - "learning_rate": 4.49653184397802e-05, - "loss": 0.3932, + "epoch": 0.03, + "learning_rate": 4.8749692400617436e-05, + "loss": 0.3979, "step": 12180 }, { - "epoch": 0.11, - "learning_rate": 4.496081434105036e-05, - "loss": 0.3923, + "epoch": 0.03, + "learning_rate": 4.8748573857408114e-05, + "loss": 0.4004, "step": 12190 }, { - "epoch": 0.11, - "learning_rate": 4.4956310242320516e-05, - "loss": 0.3869, + "epoch": 0.03, + "learning_rate": 4.874745531419879e-05, + "loss": 0.3943, "step": 12200 }, { - "epoch": 0.11, - "learning_rate": 4.495180614359067e-05, - "loss": 0.398, + "epoch": 0.03, + "learning_rate": 4.874633677098946e-05, + "loss": 0.4027, "step": 12210 }, { - "epoch": 0.11, - "learning_rate": 4.4947302044860824e-05, - "loss": 0.3987, + "epoch": 0.03, + "learning_rate": 4.874521822778014e-05, + "loss": 0.393, "step": 12220 }, { - "epoch": 0.11, - "learning_rate": 4.494279794613098e-05, - "loss": 0.3932, + "epoch": 0.03, + "learning_rate": 4.874409968457081e-05, + "loss": 0.3967, "step": 12230 }, { - "epoch": 0.11, - "learning_rate": 4.493829384740114e-05, - "loss": 0.3971, + "epoch": 0.03, + "learning_rate": 4.87429811413615e-05, + "loss": 0.3934, "step": 12240 }, { - "epoch": 0.11, - "learning_rate": 4.49337897486713e-05, - "loss": 0.3907, + "epoch": 0.03, + "learning_rate": 4.8741862598152175e-05, + "loss": 0.3934, "step": 12250 }, { - "epoch": 0.11, - "learning_rate": 4.492928564994145e-05, - "loss": 0.391, + "epoch": 0.03, + "learning_rate": 4.8740744054942846e-05, + "loss": 0.3972, "step": 12260 }, { - "epoch": 0.11, - "learning_rate": 4.4924781551211605e-05, - "loss": 0.3926, + "epoch": 0.03, + "learning_rate": 4.8739625511733524e-05, + "loss": 0.3985, "step": 12270 }, { - "epoch": 0.11, - "learning_rate": 4.492027745248176e-05, - "loss": 0.3855, + "epoch": 0.03, + "learning_rate": 4.8738506968524195e-05, + "loss": 0.405, "step": 12280 }, { - "epoch": 0.11, - "learning_rate": 4.491577335375191e-05, - "loss": 0.3925, + "epoch": 0.03, + "learning_rate": 4.873738842531487e-05, + "loss": 0.3905, "step": 12290 }, { - "epoch": 0.11, - "learning_rate": 4.491126925502207e-05, - "loss": 0.3927, + "epoch": 0.03, + "learning_rate": 4.873626988210555e-05, + "loss": 0.3954, "step": 12300 }, { - "epoch": 0.11, - "learning_rate": 4.490676515629223e-05, - "loss": 0.3919, + "epoch": 0.03, + "learning_rate": 4.873515133889622e-05, + "loss": 0.4024, "step": 12310 }, { - "epoch": 0.11, - "learning_rate": 4.4902261057562386e-05, - "loss": 0.392, + "epoch": 0.03, + "learning_rate": 4.87340327956869e-05, + "loss": 0.3966, "step": 12320 }, { - "epoch": 0.11, - "learning_rate": 4.4897756958832537e-05, - "loss": 0.3901, + "epoch": 0.03, + "learning_rate": 4.873291425247757e-05, + "loss": 0.3887, "step": 12330 }, { - "epoch": 0.11, - "learning_rate": 4.4893252860102694e-05, - "loss": 0.3853, + "epoch": 0.03, + "learning_rate": 4.873179570926825e-05, + "loss": 0.3972, "step": 12340 }, { - "epoch": 0.11, - "learning_rate": 4.488874876137285e-05, - "loss": 0.3845, + "epoch": 0.03, + "learning_rate": 4.873067716605893e-05, + "loss": 0.3912, "step": 12350 }, { - "epoch": 0.11, - "learning_rate": 4.4884244662643e-05, - "loss": 0.3849, + "epoch": 0.03, + "learning_rate": 4.8729558622849605e-05, + "loss": 0.3947, "step": 12360 }, { - "epoch": 0.11, - "learning_rate": 4.4879740563913167e-05, - "loss": 0.3845, + "epoch": 0.03, + "learning_rate": 4.872844007964028e-05, + "loss": 0.3923, "step": 12370 }, { - "epoch": 0.11, - "learning_rate": 4.487523646518332e-05, - "loss": 0.3931, + "epoch": 0.03, + "learning_rate": 4.8727321536430954e-05, + "loss": 0.3907, "step": 12380 }, { - "epoch": 0.11, - "learning_rate": 4.4870732366453475e-05, - "loss": 0.3952, + "epoch": 0.03, + "learning_rate": 4.872620299322163e-05, + "loss": 0.3968, "step": 12390 }, { - "epoch": 0.11, - "learning_rate": 4.486622826772363e-05, - "loss": 0.3905, + "epoch": 0.03, + "learning_rate": 4.87250844500123e-05, + "loss": 0.4005, "step": 12400 }, { - "epoch": 0.11, - "learning_rate": 4.486172416899378e-05, - "loss": 0.3874, + "epoch": 0.03, + "learning_rate": 4.872396590680298e-05, + "loss": 0.4019, "step": 12410 }, { - "epoch": 0.11, - "learning_rate": 4.485722007026395e-05, - "loss": 0.3888, + "epoch": 0.03, + "learning_rate": 4.872284736359366e-05, + "loss": 0.3957, "step": 12420 }, { - "epoch": 0.11, - "learning_rate": 4.48527159715341e-05, - "loss": 0.3862, + "epoch": 0.03, + "learning_rate": 4.872172882038433e-05, + "loss": 0.3954, "step": 12430 }, { - "epoch": 0.11, - "learning_rate": 4.4848211872804255e-05, - "loss": 0.3905, + "epoch": 0.03, + "learning_rate": 4.872061027717501e-05, + "loss": 0.3958, "step": 12440 }, { - "epoch": 0.11, - "learning_rate": 4.484370777407441e-05, - "loss": 0.3858, + "epoch": 0.03, + "learning_rate": 4.8719491733965686e-05, + "loss": 0.4008, "step": 12450 }, { - "epoch": 0.11, - "learning_rate": 4.4839203675344564e-05, - "loss": 0.3892, + "epoch": 0.03, + "learning_rate": 4.8718373190756364e-05, + "loss": 0.3885, "step": 12460 }, { - "epoch": 0.11, - "learning_rate": 4.483469957661472e-05, - "loss": 0.3862, + "epoch": 0.03, + "learning_rate": 4.871725464754704e-05, + "loss": 0.3943, "step": 12470 }, { - "epoch": 0.11, - "learning_rate": 4.483019547788488e-05, - "loss": 0.3913, + "epoch": 0.03, + "learning_rate": 4.871613610433771e-05, + "loss": 0.405, "step": 12480 }, { - "epoch": 0.11, - "learning_rate": 4.482569137915503e-05, - "loss": 0.3881, + "epoch": 0.03, + "learning_rate": 4.871501756112839e-05, + "loss": 0.4009, "step": 12490 }, { - "epoch": 0.11, - "learning_rate": 4.482118728042519e-05, - "loss": 0.3887, + "epoch": 0.03, + "learning_rate": 4.871389901791906e-05, + "loss": 0.393, "step": 12500 }, { - "epoch": 0.11, - "learning_rate": 4.4816683181695344e-05, - "loss": 0.3998, + "epoch": 0.03, + "learning_rate": 4.871278047470974e-05, + "loss": 0.3962, "step": 12510 }, { - "epoch": 0.11, - "learning_rate": 4.48121790829655e-05, - "loss": 0.3872, + "epoch": 0.03, + "learning_rate": 4.871166193150042e-05, + "loss": 0.3979, "step": 12520 }, { - "epoch": 0.11, - "learning_rate": 4.480767498423566e-05, - "loss": 0.3832, + "epoch": 0.03, + "learning_rate": 4.871054338829109e-05, + "loss": 0.3987, "step": 12530 }, { - "epoch": 0.11, - "learning_rate": 4.480317088550581e-05, - "loss": 0.3909, + "epoch": 0.03, + "learning_rate": 4.870942484508177e-05, + "loss": 0.3882, "step": 12540 }, { - "epoch": 0.11, - "learning_rate": 4.479866678677597e-05, - "loss": 0.3839, + "epoch": 0.03, + "learning_rate": 4.8708306301872445e-05, + "loss": 0.3987, "step": 12550 }, { - "epoch": 0.11, - "learning_rate": 4.4794162688046125e-05, - "loss": 0.3841, + "epoch": 0.03, + "learning_rate": 4.870718775866312e-05, + "loss": 0.4016, "step": 12560 }, { - "epoch": 0.11, - "learning_rate": 4.478965858931628e-05, - "loss": 0.3856, + "epoch": 0.03, + "learning_rate": 4.87060692154538e-05, + "loss": 0.4, "step": 12570 }, { - "epoch": 0.11, - "learning_rate": 4.478515449058643e-05, - "loss": 0.3882, + "epoch": 0.03, + "learning_rate": 4.870495067224447e-05, + "loss": 0.3947, "step": 12580 }, { - "epoch": 0.11, - "learning_rate": 4.478065039185659e-05, - "loss": 0.3814, + "epoch": 0.03, + "learning_rate": 4.870383212903515e-05, + "loss": 0.3988, "step": 12590 }, { - "epoch": 0.11, - "learning_rate": 4.477614629312675e-05, - "loss": 0.3879, + "epoch": 0.03, + "learning_rate": 4.870271358582582e-05, + "loss": 0.3913, "step": 12600 }, { - "epoch": 0.11, - "learning_rate": 4.47716421943969e-05, - "loss": 0.3856, + "epoch": 0.03, + "learning_rate": 4.87015950426165e-05, + "loss": 0.3965, "step": 12610 }, { - "epoch": 0.11, - "learning_rate": 4.476713809566706e-05, - "loss": 0.3889, + "epoch": 0.03, + "learning_rate": 4.870047649940718e-05, + "loss": 0.3933, "step": 12620 }, { - "epoch": 0.11, - "learning_rate": 4.4762633996937214e-05, - "loss": 0.394, + "epoch": 0.03, + "learning_rate": 4.869935795619785e-05, + "loss": 0.3986, "step": 12630 }, { - "epoch": 0.11, - "learning_rate": 4.475812989820737e-05, - "loss": 0.3823, + "epoch": 0.03, + "learning_rate": 4.8698239412988526e-05, + "loss": 0.395, "step": 12640 }, { - "epoch": 0.11, - "learning_rate": 4.475362579947753e-05, - "loss": 0.3898, + "epoch": 0.03, + "learning_rate": 4.8697120869779204e-05, + "loss": 0.3999, "step": 12650 }, { - "epoch": 0.11, - "learning_rate": 4.474912170074768e-05, - "loss": 0.3932, + "epoch": 0.03, + "learning_rate": 4.869600232656988e-05, + "loss": 0.3956, "step": 12660 }, { - "epoch": 0.11, - "learning_rate": 4.4744617602017844e-05, - "loss": 0.3882, + "epoch": 0.03, + "learning_rate": 4.869488378336055e-05, + "loss": 0.3961, "step": 12670 }, { - "epoch": 0.11, - "learning_rate": 4.4740113503287995e-05, - "loss": 0.3881, + "epoch": 0.03, + "learning_rate": 4.869376524015123e-05, + "loss": 0.3967, "step": 12680 }, { - "epoch": 0.11, - "learning_rate": 4.4735609404558145e-05, - "loss": 0.3901, + "epoch": 0.03, + "learning_rate": 4.869264669694191e-05, + "loss": 0.3978, "step": 12690 }, { - "epoch": 0.11, - "learning_rate": 4.473110530582831e-05, - "loss": 0.3834, + "epoch": 0.03, + "learning_rate": 4.869152815373258e-05, + "loss": 0.3995, "step": 12700 }, { - "epoch": 0.11, - "learning_rate": 4.472660120709846e-05, - "loss": 0.3892, + "epoch": 0.03, + "learning_rate": 4.869040961052326e-05, + "loss": 0.3932, "step": 12710 }, { - "epoch": 0.11, - "learning_rate": 4.472209710836862e-05, - "loss": 0.3877, + "epoch": 0.03, + "learning_rate": 4.868929106731393e-05, + "loss": 0.3943, "step": 12720 }, { - "epoch": 0.11, - "learning_rate": 4.4717593009638775e-05, - "loss": 0.3842, + "epoch": 0.03, + "learning_rate": 4.868817252410461e-05, + "loss": 0.3958, "step": 12730 }, { - "epoch": 0.11, - "learning_rate": 4.4713088910908926e-05, - "loss": 0.3932, + "epoch": 0.03, + "learning_rate": 4.8687053980895285e-05, + "loss": 0.3926, "step": 12740 }, { - "epoch": 0.11, - "learning_rate": 4.4708584812179083e-05, - "loss": 0.3888, + "epoch": 0.03, + "learning_rate": 4.8685935437685956e-05, + "loss": 0.398, "step": 12750 }, { - "epoch": 0.11, - "learning_rate": 4.470408071344924e-05, - "loss": 0.3854, + "epoch": 0.03, + "learning_rate": 4.8684816894476634e-05, + "loss": 0.399, "step": 12760 }, { - "epoch": 0.11, - "learning_rate": 4.46995766147194e-05, - "loss": 0.3887, + "epoch": 0.03, + "learning_rate": 4.868369835126731e-05, + "loss": 0.3855, "step": 12770 }, { - "epoch": 0.11, - "learning_rate": 4.469507251598955e-05, - "loss": 0.3969, + "epoch": 0.03, + "learning_rate": 4.868257980805799e-05, + "loss": 0.3946, "step": 12780 }, { - "epoch": 0.11, - "learning_rate": 4.469056841725971e-05, - "loss": 0.3828, + "epoch": 0.03, + "learning_rate": 4.868146126484867e-05, + "loss": 0.3941, "step": 12790 }, { - "epoch": 0.11, - "learning_rate": 4.4686064318529864e-05, - "loss": 0.3808, + "epoch": 0.03, + "learning_rate": 4.868034272163934e-05, + "loss": 0.3984, "step": 12800 }, { - "epoch": 0.11, - "learning_rate": 4.468156021980002e-05, - "loss": 0.3869, + "epoch": 0.03, + "learning_rate": 4.8679224178430017e-05, + "loss": 0.3962, "step": 12810 }, { - "epoch": 0.11, - "learning_rate": 4.467705612107018e-05, - "loss": 0.386, + "epoch": 0.03, + "learning_rate": 4.867810563522069e-05, + "loss": 0.3959, "step": 12820 }, { - "epoch": 0.11, - "learning_rate": 4.467255202234033e-05, - "loss": 0.3838, + "epoch": 0.03, + "learning_rate": 4.8676987092011366e-05, + "loss": 0.3909, "step": 12830 }, { - "epoch": 0.11, - "learning_rate": 4.466804792361049e-05, - "loss": 0.3827, + "epoch": 0.03, + "learning_rate": 4.8675868548802044e-05, + "loss": 0.3884, "step": 12840 }, { - "epoch": 0.11, - "learning_rate": 4.4663543824880645e-05, - "loss": 0.3814, + "epoch": 0.03, + "learning_rate": 4.8674750005592715e-05, + "loss": 0.386, "step": 12850 }, { - "epoch": 0.11, - "learning_rate": 4.4659039726150796e-05, - "loss": 0.3863, + "epoch": 0.03, + "learning_rate": 4.867363146238339e-05, + "loss": 0.3899, "step": 12860 }, { - "epoch": 0.11, - "learning_rate": 4.465453562742096e-05, - "loss": 0.3784, + "epoch": 0.03, + "learning_rate": 4.867251291917407e-05, + "loss": 0.3908, "step": 12870 }, { - "epoch": 0.11, - "learning_rate": 4.465003152869111e-05, - "loss": 0.3854, + "epoch": 0.03, + "learning_rate": 4.867139437596475e-05, + "loss": 0.391, "step": 12880 }, { - "epoch": 0.12, - "learning_rate": 4.464552742996127e-05, - "loss": 0.3889, + "epoch": 0.03, + "learning_rate": 4.8670275832755426e-05, + "loss": 0.3819, "step": 12890 }, { - "epoch": 0.12, - "learning_rate": 4.4641023331231426e-05, - "loss": 0.3876, + "epoch": 0.03, + "learning_rate": 4.86691572895461e-05, + "loss": 0.3856, "step": 12900 }, { - "epoch": 0.12, - "learning_rate": 4.4636519232501576e-05, - "loss": 0.3912, + "epoch": 0.03, + "learning_rate": 4.8668038746336776e-05, + "loss": 0.3901, "step": 12910 }, { - "epoch": 0.12, - "learning_rate": 4.4632015133771734e-05, - "loss": 0.3842, + "epoch": 0.03, + "learning_rate": 4.866692020312745e-05, + "loss": 0.393, "step": 12920 }, { - "epoch": 0.12, - "learning_rate": 4.462751103504189e-05, - "loss": 0.3836, + "epoch": 0.03, + "learning_rate": 4.8665801659918125e-05, + "loss": 0.3916, "step": 12930 }, { - "epoch": 0.12, - "learning_rate": 4.462300693631204e-05, - "loss": 0.3818, + "epoch": 0.03, + "learning_rate": 4.86646831167088e-05, + "loss": 0.3926, "step": 12940 }, { - "epoch": 0.12, - "learning_rate": 4.4618502837582206e-05, - "loss": 0.3838, + "epoch": 0.03, + "learning_rate": 4.8663564573499474e-05, + "loss": 0.3954, "step": 12950 }, { - "epoch": 0.12, - "learning_rate": 4.461399873885236e-05, - "loss": 0.3818, + "epoch": 0.03, + "learning_rate": 4.866244603029015e-05, + "loss": 0.3969, "step": 12960 }, { - "epoch": 0.12, - "learning_rate": 4.4609494640122514e-05, - "loss": 0.3852, + "epoch": 0.03, + "learning_rate": 4.866132748708083e-05, + "loss": 0.3937, "step": 12970 }, { - "epoch": 0.12, - "learning_rate": 4.460499054139267e-05, - "loss": 0.3878, + "epoch": 0.03, + "learning_rate": 4.866020894387151e-05, + "loss": 0.3933, "step": 12980 }, { - "epoch": 0.12, - "learning_rate": 4.460048644266282e-05, - "loss": 0.3834, + "epoch": 0.03, + "learning_rate": 4.865909040066218e-05, + "loss": 0.3952, "step": 12990 }, { - "epoch": 0.12, - "learning_rate": 4.459598234393298e-05, - "loss": 0.3879, + "epoch": 0.03, + "learning_rate": 4.8657971857452857e-05, + "loss": 0.3969, "step": 13000 }, { - "epoch": 0.12, - "learning_rate": 4.459147824520314e-05, - "loss": 0.3806, + "epoch": 0.03, + "learning_rate": 4.8656853314243534e-05, + "loss": 0.3934, "step": 13010 }, { - "epoch": 0.12, - "learning_rate": 4.4586974146473295e-05, - "loss": 0.3859, + "epoch": 0.03, + "learning_rate": 4.8655734771034206e-05, + "loss": 0.3902, "step": 13020 }, { - "epoch": 0.12, - "learning_rate": 4.4582470047743446e-05, - "loss": 0.3859, + "epoch": 0.03, + "learning_rate": 4.8654616227824884e-05, + "loss": 0.3906, "step": 13030 }, { - "epoch": 0.12, - "learning_rate": 4.45779659490136e-05, - "loss": 0.3763, + "epoch": 0.03, + "learning_rate": 4.8653497684615555e-05, + "loss": 0.3882, "step": 13040 }, { - "epoch": 0.12, - "learning_rate": 4.457346185028376e-05, - "loss": 0.3828, + "epoch": 0.03, + "learning_rate": 4.865237914140623e-05, + "loss": 0.3921, "step": 13050 }, { - "epoch": 0.12, - "learning_rate": 4.456895775155391e-05, - "loss": 0.3845, + "epoch": 0.03, + "learning_rate": 4.865126059819691e-05, + "loss": 0.3956, "step": 13060 }, { - "epoch": 0.12, - "learning_rate": 4.4564453652824076e-05, - "loss": 0.388, + "epoch": 0.03, + "learning_rate": 4.865014205498759e-05, + "loss": 0.3868, "step": 13070 }, { - "epoch": 0.12, - "learning_rate": 4.4559949554094227e-05, - "loss": 0.3858, + "epoch": 0.03, + "learning_rate": 4.8649023511778266e-05, + "loss": 0.3865, "step": 13080 }, { - "epoch": 0.12, - "learning_rate": 4.4555445455364384e-05, - "loss": 0.3922, + "epoch": 0.03, + "learning_rate": 4.864790496856894e-05, + "loss": 0.3925, "step": 13090 }, { - "epoch": 0.12, - "learning_rate": 4.455094135663454e-05, - "loss": 0.3793, + "epoch": 0.03, + "learning_rate": 4.8646786425359615e-05, + "loss": 0.3884, "step": 13100 }, { - "epoch": 0.12, - "learning_rate": 4.454643725790469e-05, - "loss": 0.3843, + "epoch": 0.03, + "learning_rate": 4.8645667882150293e-05, + "loss": 0.3984, "step": 13110 }, { - "epoch": 0.12, - "learning_rate": 4.4541933159174856e-05, - "loss": 0.3881, + "epoch": 0.03, + "learning_rate": 4.8644549338940965e-05, + "loss": 0.3882, "step": 13120 }, { - "epoch": 0.12, - "learning_rate": 4.453742906044501e-05, - "loss": 0.387, + "epoch": 0.03, + "learning_rate": 4.864343079573164e-05, + "loss": 0.396, "step": 13130 }, { - "epoch": 0.12, - "learning_rate": 4.453292496171516e-05, - "loss": 0.39, + "epoch": 0.03, + "learning_rate": 4.8642312252522314e-05, + "loss": 0.3926, "step": 13140 }, { - "epoch": 0.12, - "learning_rate": 4.452842086298532e-05, - "loss": 0.3851, + "epoch": 0.03, + "learning_rate": 4.864119370931299e-05, + "loss": 0.3844, "step": 13150 }, { - "epoch": 0.12, - "learning_rate": 4.452391676425547e-05, - "loss": 0.3856, + "epoch": 0.03, + "learning_rate": 4.864007516610367e-05, + "loss": 0.3875, "step": 13160 }, { - "epoch": 0.12, - "learning_rate": 4.451941266552563e-05, - "loss": 0.3808, + "epoch": 0.03, + "learning_rate": 4.863895662289434e-05, + "loss": 0.3908, "step": 13170 }, { - "epoch": 0.12, - "learning_rate": 4.451490856679579e-05, - "loss": 0.3771, + "epoch": 0.03, + "learning_rate": 4.863783807968502e-05, + "loss": 0.3891, "step": 13180 }, { - "epoch": 0.12, - "learning_rate": 4.451040446806594e-05, - "loss": 0.3809, + "epoch": 0.03, + "learning_rate": 4.8636719536475697e-05, + "loss": 0.3944, "step": 13190 }, { - "epoch": 0.12, - "learning_rate": 4.4505900369336096e-05, - "loss": 0.3885, + "epoch": 0.03, + "learning_rate": 4.8635600993266374e-05, + "loss": 0.3903, "step": 13200 }, { - "epoch": 0.12, - "learning_rate": 4.4501396270606254e-05, - "loss": 0.3761, + "epoch": 0.03, + "learning_rate": 4.863448245005705e-05, + "loss": 0.3872, "step": 13210 }, { - "epoch": 0.12, - "learning_rate": 4.449689217187641e-05, - "loss": 0.3877, + "epoch": 0.03, + "learning_rate": 4.8633363906847724e-05, + "loss": 0.3926, "step": 13220 }, { - "epoch": 0.12, - "learning_rate": 4.449238807314657e-05, - "loss": 0.3866, + "epoch": 0.03, + "learning_rate": 4.86322453636384e-05, + "loss": 0.3883, "step": 13230 }, { - "epoch": 0.12, - "learning_rate": 4.448788397441672e-05, - "loss": 0.3873, + "epoch": 0.03, + "learning_rate": 4.863112682042907e-05, + "loss": 0.3809, "step": 13240 }, { - "epoch": 0.12, - "learning_rate": 4.448337987568688e-05, - "loss": 0.3809, + "epoch": 0.03, + "learning_rate": 4.863000827721975e-05, + "loss": 0.3896, "step": 13250 }, { - "epoch": 0.12, - "learning_rate": 4.4478875776957034e-05, - "loss": 0.3812, + "epoch": 0.03, + "learning_rate": 4.862888973401043e-05, + "loss": 0.3932, "step": 13260 }, { - "epoch": 0.12, - "learning_rate": 4.447437167822719e-05, - "loss": 0.3844, + "epoch": 0.03, + "learning_rate": 4.86277711908011e-05, + "loss": 0.3879, "step": 13270 }, { - "epoch": 0.12, - "learning_rate": 4.446986757949734e-05, - "loss": 0.3798, + "epoch": 0.03, + "learning_rate": 4.862665264759178e-05, + "loss": 0.3902, "step": 13280 }, { - "epoch": 0.12, - "learning_rate": 4.44653634807675e-05, - "loss": 0.3814, + "epoch": 0.03, + "learning_rate": 4.8625534104382455e-05, + "loss": 0.3876, "step": 13290 }, { - "epoch": 0.12, - "learning_rate": 4.446085938203766e-05, - "loss": 0.3808, + "epoch": 0.03, + "learning_rate": 4.8624415561173133e-05, + "loss": 0.3904, "step": 13300 }, { - "epoch": 0.12, - "learning_rate": 4.445635528330781e-05, - "loss": 0.3736, + "epoch": 0.03, + "learning_rate": 4.8623297017963805e-05, + "loss": 0.3879, "step": 13310 }, { - "epoch": 0.12, - "learning_rate": 4.445185118457797e-05, - "loss": 0.3772, + "epoch": 0.03, + "learning_rate": 4.862217847475448e-05, + "loss": 0.3889, "step": 13320 }, { - "epoch": 0.12, - "learning_rate": 4.444734708584812e-05, - "loss": 0.3839, + "epoch": 0.03, + "learning_rate": 4.862105993154516e-05, + "loss": 0.3879, "step": 13330 }, { - "epoch": 0.12, - "learning_rate": 4.4442842987118274e-05, - "loss": 0.3743, + "epoch": 0.03, + "learning_rate": 4.861994138833583e-05, + "loss": 0.391, "step": 13340 }, { - "epoch": 0.12, - "learning_rate": 4.443833888838844e-05, - "loss": 0.3845, + "epoch": 0.03, + "learning_rate": 4.861882284512651e-05, + "loss": 0.3866, "step": 13350 }, { - "epoch": 0.12, - "learning_rate": 4.443383478965859e-05, - "loss": 0.3827, + "epoch": 0.03, + "learning_rate": 4.861770430191718e-05, + "loss": 0.3874, "step": 13360 }, { - "epoch": 0.12, - "learning_rate": 4.442933069092875e-05, - "loss": 0.3754, + "epoch": 0.03, + "learning_rate": 4.861658575870786e-05, + "loss": 0.3863, "step": 13370 }, { - "epoch": 0.12, - "learning_rate": 4.4424826592198904e-05, - "loss": 0.3807, + "epoch": 0.03, + "learning_rate": 4.8615467215498536e-05, + "loss": 0.394, "step": 13380 }, { - "epoch": 0.12, - "learning_rate": 4.4420322493469055e-05, - "loss": 0.3783, + "epoch": 0.03, + "learning_rate": 4.8614348672289214e-05, + "loss": 0.3903, "step": 13390 }, { - "epoch": 0.12, - "learning_rate": 4.441581839473922e-05, - "loss": 0.3812, + "epoch": 0.03, + "learning_rate": 4.861323012907989e-05, + "loss": 0.3917, "step": 13400 }, { - "epoch": 0.12, - "learning_rate": 4.441131429600937e-05, - "loss": 0.3814, + "epoch": 0.03, + "learning_rate": 4.8612111585870563e-05, + "loss": 0.3908, "step": 13410 }, { - "epoch": 0.12, - "learning_rate": 4.440681019727953e-05, - "loss": 0.378, + "epoch": 0.03, + "learning_rate": 4.861099304266124e-05, + "loss": 0.3912, "step": 13420 }, { - "epoch": 0.12, - "learning_rate": 4.4402306098549685e-05, - "loss": 0.3785, + "epoch": 0.03, + "learning_rate": 4.860987449945192e-05, + "loss": 0.3806, "step": 13430 }, { - "epoch": 0.12, - "learning_rate": 4.4397801999819835e-05, - "loss": 0.3827, + "epoch": 0.03, + "learning_rate": 4.860875595624259e-05, + "loss": 0.3924, "step": 13440 }, { - "epoch": 0.12, - "learning_rate": 4.439329790108999e-05, - "loss": 0.3787, + "epoch": 0.03, + "learning_rate": 4.860763741303327e-05, + "loss": 0.3919, "step": 13450 }, { - "epoch": 0.12, - "learning_rate": 4.438879380236015e-05, - "loss": 0.3871, + "epoch": 0.03, + "learning_rate": 4.860651886982394e-05, + "loss": 0.3841, "step": 13460 }, { - "epoch": 0.12, - "learning_rate": 4.438428970363031e-05, - "loss": 0.3857, + "epoch": 0.03, + "learning_rate": 4.860540032661462e-05, + "loss": 0.3841, "step": 13470 }, { - "epoch": 0.12, - "learning_rate": 4.437978560490046e-05, - "loss": 0.3758, + "epoch": 0.03, + "learning_rate": 4.8604281783405295e-05, + "loss": 0.3925, "step": 13480 }, { - "epoch": 0.12, - "learning_rate": 4.4375281506170616e-05, - "loss": 0.3859, + "epoch": 0.03, + "learning_rate": 4.860316324019597e-05, + "loss": 0.384, "step": 13490 }, { - "epoch": 0.12, - "learning_rate": 4.4370777407440773e-05, - "loss": 0.382, + "epoch": 0.03, + "learning_rate": 4.860204469698665e-05, + "loss": 0.3854, "step": 13500 }, { - "epoch": 0.12, - "learning_rate": 4.436627330871093e-05, - "loss": 0.3843, + "epoch": 0.03, + "learning_rate": 4.860092615377732e-05, + "loss": 0.38, "step": 13510 }, { - "epoch": 0.12, - "learning_rate": 4.436176920998109e-05, - "loss": 0.3798, + "epoch": 0.03, + "learning_rate": 4.8599807610568e-05, + "loss": 0.3913, "step": 13520 }, { - "epoch": 0.12, - "learning_rate": 4.435726511125124e-05, - "loss": 0.3803, + "epoch": 0.03, + "learning_rate": 4.859868906735868e-05, + "loss": 0.3918, "step": 13530 }, { - "epoch": 0.12, - "learning_rate": 4.43527610125214e-05, - "loss": 0.379, + "epoch": 0.03, + "learning_rate": 4.859757052414935e-05, + "loss": 0.392, "step": 13540 }, { - "epoch": 0.12, - "learning_rate": 4.4348256913791554e-05, - "loss": 0.3794, + "epoch": 0.03, + "learning_rate": 4.859645198094003e-05, + "loss": 0.3903, "step": 13550 }, { - "epoch": 0.12, - "learning_rate": 4.4343752815061705e-05, - "loss": 0.3771, + "epoch": 0.03, + "learning_rate": 4.85953334377307e-05, + "loss": 0.3829, "step": 13560 }, { - "epoch": 0.12, - "learning_rate": 4.433924871633187e-05, - "loss": 0.3787, + "epoch": 0.03, + "learning_rate": 4.8594214894521376e-05, + "loss": 0.384, "step": 13570 }, { - "epoch": 0.12, - "learning_rate": 4.433474461760202e-05, - "loss": 0.3849, + "epoch": 0.03, + "learning_rate": 4.8593096351312054e-05, + "loss": 0.3811, "step": 13580 }, { - "epoch": 0.12, - "learning_rate": 4.433024051887217e-05, - "loss": 0.3856, + "epoch": 0.03, + "learning_rate": 4.8591977808102726e-05, + "loss": 0.3936, "step": 13590 }, { - "epoch": 0.12, - "learning_rate": 4.4325736420142335e-05, - "loss": 0.3799, + "epoch": 0.03, + "learning_rate": 4.859085926489341e-05, + "loss": 0.3819, "step": 13600 }, { - "epoch": 0.12, - "learning_rate": 4.4321232321412486e-05, - "loss": 0.3757, + "epoch": 0.03, + "learning_rate": 4.858974072168408e-05, + "loss": 0.3838, "step": 13610 }, { - "epoch": 0.12, - "learning_rate": 4.431672822268264e-05, - "loss": 0.3806, + "epoch": 0.03, + "learning_rate": 4.858862217847476e-05, + "loss": 0.3908, "step": 13620 }, { - "epoch": 0.12, - "learning_rate": 4.43122241239528e-05, - "loss": 0.3808, + "epoch": 0.03, + "learning_rate": 4.858750363526543e-05, + "loss": 0.3865, "step": 13630 }, { - "epoch": 0.12, - "learning_rate": 4.430772002522295e-05, - "loss": 0.3831, + "epoch": 0.03, + "learning_rate": 4.858638509205611e-05, + "loss": 0.3868, "step": 13640 }, { - "epoch": 0.12, - "learning_rate": 4.4303215926493115e-05, - "loss": 0.3807, + "epoch": 0.03, + "learning_rate": 4.8585266548846786e-05, + "loss": 0.3882, "step": 13650 }, { - "epoch": 0.12, - "learning_rate": 4.4298711827763266e-05, - "loss": 0.3856, + "epoch": 0.03, + "learning_rate": 4.858414800563746e-05, + "loss": 0.3798, "step": 13660 }, { - "epoch": 0.12, - "learning_rate": 4.4294207729033424e-05, - "loss": 0.3799, + "epoch": 0.03, + "learning_rate": 4.8583029462428135e-05, + "loss": 0.3763, "step": 13670 }, { - "epoch": 0.12, - "learning_rate": 4.428970363030358e-05, - "loss": 0.376, + "epoch": 0.03, + "learning_rate": 4.8581910919218807e-05, + "loss": 0.3844, "step": 13680 }, { - "epoch": 0.12, - "learning_rate": 4.428519953157373e-05, - "loss": 0.3802, + "epoch": 0.03, + "learning_rate": 4.8580792376009484e-05, + "loss": 0.3827, "step": 13690 }, { - "epoch": 0.12, - "learning_rate": 4.428069543284389e-05, - "loss": 0.3736, + "epoch": 0.03, + "learning_rate": 4.857967383280016e-05, + "loss": 0.3838, "step": 13700 }, { - "epoch": 0.12, - "learning_rate": 4.427619133411405e-05, - "loss": 0.3733, + "epoch": 0.03, + "learning_rate": 4.857855528959084e-05, + "loss": 0.3884, "step": 13710 }, { - "epoch": 0.12, - "learning_rate": 4.4271687235384204e-05, - "loss": 0.384, + "epoch": 0.03, + "learning_rate": 4.857743674638152e-05, + "loss": 0.3836, "step": 13720 }, { - "epoch": 0.12, - "learning_rate": 4.4267183136654355e-05, - "loss": 0.3802, + "epoch": 0.03, + "learning_rate": 4.857631820317219e-05, + "loss": 0.3858, "step": 13730 }, { - "epoch": 0.12, - "learning_rate": 4.426267903792451e-05, - "loss": 0.3796, + "epoch": 0.03, + "learning_rate": 4.857519965996287e-05, + "loss": 0.3883, "step": 13740 }, { - "epoch": 0.12, - "learning_rate": 4.425817493919467e-05, - "loss": 0.3759, + "epoch": 0.03, + "learning_rate": 4.8574081116753545e-05, + "loss": 0.3777, "step": 13750 }, { - "epoch": 0.12, - "learning_rate": 4.425367084046482e-05, - "loss": 0.3734, + "epoch": 0.03, + "learning_rate": 4.8572962573544216e-05, + "loss": 0.386, "step": 13760 }, { - "epoch": 0.12, - "learning_rate": 4.4249166741734985e-05, - "loss": 0.3796, + "epoch": 0.03, + "learning_rate": 4.8571844030334894e-05, + "loss": 0.3808, "step": 13770 }, { - "epoch": 0.12, - "learning_rate": 4.4244662643005136e-05, - "loss": 0.3843, + "epoch": 0.03, + "learning_rate": 4.8570725487125566e-05, + "loss": 0.3896, "step": 13780 }, { - "epoch": 0.12, - "learning_rate": 4.424015854427529e-05, - "loss": 0.3821, + "epoch": 0.03, + "learning_rate": 4.8569606943916243e-05, + "loss": 0.384, "step": 13790 }, { - "epoch": 0.12, - "learning_rate": 4.423565444554545e-05, - "loss": 0.3774, + "epoch": 0.03, + "learning_rate": 4.856848840070692e-05, + "loss": 0.3856, "step": 13800 }, { - "epoch": 0.12, - "learning_rate": 4.42311503468156e-05, - "loss": 0.3688, + "epoch": 0.03, + "learning_rate": 4.85673698574976e-05, + "loss": 0.3862, "step": 13810 }, { - "epoch": 0.12, - "learning_rate": 4.4226646248085766e-05, - "loss": 0.3778, + "epoch": 0.03, + "learning_rate": 4.856625131428828e-05, + "loss": 0.3878, "step": 13820 }, { - "epoch": 0.12, - "learning_rate": 4.4222142149355916e-05, - "loss": 0.3673, + "epoch": 0.03, + "learning_rate": 4.856513277107895e-05, + "loss": 0.3906, "step": 13830 }, { - "epoch": 0.12, - "learning_rate": 4.421763805062607e-05, - "loss": 0.3784, + "epoch": 0.03, + "learning_rate": 4.8564014227869626e-05, + "loss": 0.3865, "step": 13840 }, { - "epoch": 0.12, - "learning_rate": 4.421313395189623e-05, - "loss": 0.3785, + "epoch": 0.03, + "learning_rate": 4.8562895684660304e-05, + "loss": 0.384, "step": 13850 }, { - "epoch": 0.12, - "learning_rate": 4.420862985316638e-05, - "loss": 0.3729, + "epoch": 0.03, + "learning_rate": 4.8561777141450975e-05, + "loss": 0.3828, "step": 13860 }, { - "epoch": 0.12, - "learning_rate": 4.420412575443654e-05, - "loss": 0.3801, + "epoch": 0.03, + "learning_rate": 4.856065859824165e-05, + "loss": 0.3864, "step": 13870 }, { - "epoch": 0.12, - "learning_rate": 4.41996216557067e-05, - "loss": 0.3755, + "epoch": 0.03, + "learning_rate": 4.8559540055032324e-05, + "loss": 0.3862, "step": 13880 }, { - "epoch": 0.12, - "learning_rate": 4.419511755697685e-05, - "loss": 0.3764, + "epoch": 0.03, + "learning_rate": 4.8558421511823e-05, + "loss": 0.3863, "step": 13890 }, { - "epoch": 0.12, - "learning_rate": 4.4190613458247005e-05, - "loss": 0.3748, + "epoch": 0.03, + "learning_rate": 4.855730296861368e-05, + "loss": 0.3863, "step": 13900 }, { - "epoch": 0.12, - "learning_rate": 4.418610935951716e-05, - "loss": 0.3778, + "epoch": 0.03, + "learning_rate": 4.855618442540436e-05, + "loss": 0.3842, "step": 13910 }, { - "epoch": 0.12, - "learning_rate": 4.418160526078732e-05, - "loss": 0.378, + "epoch": 0.03, + "learning_rate": 4.8555065882195036e-05, + "loss": 0.3872, "step": 13920 }, { - "epoch": 0.12, - "learning_rate": 4.417710116205748e-05, - "loss": 0.376, + "epoch": 0.03, + "learning_rate": 4.855394733898571e-05, + "loss": 0.3818, "step": 13930 }, { - "epoch": 0.12, - "learning_rate": 4.417259706332763e-05, - "loss": 0.3844, + "epoch": 0.03, + "learning_rate": 4.8552828795776385e-05, + "loss": 0.3894, "step": 13940 }, { - "epoch": 0.12, - "learning_rate": 4.4168092964597786e-05, - "loss": 0.3763, + "epoch": 0.03, + "learning_rate": 4.8551710252567056e-05, + "loss": 0.3829, "step": 13950 }, { - "epoch": 0.12, - "learning_rate": 4.4163588865867944e-05, - "loss": 0.3754, + "epoch": 0.03, + "learning_rate": 4.8550591709357734e-05, + "loss": 0.3844, "step": 13960 }, { - "epoch": 0.12, - "learning_rate": 4.41590847671381e-05, - "loss": 0.3782, + "epoch": 0.03, + "learning_rate": 4.854947316614841e-05, + "loss": 0.3837, "step": 13970 }, { - "epoch": 0.12, - "learning_rate": 4.415458066840825e-05, - "loss": 0.3762, + "epoch": 0.03, + "learning_rate": 4.8548354622939083e-05, + "loss": 0.3763, "step": 13980 }, { - "epoch": 0.12, - "learning_rate": 4.415007656967841e-05, - "loss": 0.3765, + "epoch": 0.03, + "learning_rate": 4.854723607972976e-05, + "loss": 0.3774, "step": 13990 }, { - "epoch": 0.12, - "learning_rate": 4.414557247094857e-05, - "loss": 0.3691, + "epoch": 0.03, + "learning_rate": 4.854611753652043e-05, + "loss": 0.3803, "step": 14000 }, { - "epoch": 0.13, - "learning_rate": 4.414106837221872e-05, - "loss": 0.375, + "epoch": 0.03, + "learning_rate": 4.854499899331111e-05, + "loss": 0.3795, "step": 14010 }, { - "epoch": 0.13, - "learning_rate": 4.413656427348888e-05, - "loss": 0.377, + "epoch": 0.03, + "learning_rate": 4.8543880450101795e-05, + "loss": 0.3809, "step": 14020 }, { - "epoch": 0.13, - "learning_rate": 4.413206017475903e-05, - "loss": 0.3734, + "epoch": 0.03, + "learning_rate": 4.8542761906892466e-05, + "loss": 0.3795, "step": 14030 }, { - "epoch": 0.13, - "learning_rate": 4.412755607602918e-05, - "loss": 0.3807, + "epoch": 0.03, + "learning_rate": 4.8541643363683144e-05, + "loss": 0.3883, "step": 14040 }, { - "epoch": 0.13, - "learning_rate": 4.412305197729935e-05, - "loss": 0.3767, + "epoch": 0.03, + "learning_rate": 4.8540524820473815e-05, + "loss": 0.3805, "step": 14050 }, { - "epoch": 0.13, - "learning_rate": 4.41185478785695e-05, - "loss": 0.3696, + "epoch": 0.03, + "learning_rate": 4.853940627726449e-05, + "loss": 0.3865, "step": 14060 }, { - "epoch": 0.13, - "learning_rate": 4.411449418971264e-05, - "loss": 0.3744, + "epoch": 0.03, + "learning_rate": 4.853828773405517e-05, + "loss": 0.3854, "step": 14070 }, { - "epoch": 0.13, - "learning_rate": 4.410999009098279e-05, - "loss": 0.3749, + "epoch": 0.03, + "learning_rate": 4.853716919084584e-05, + "loss": 0.3776, "step": 14080 }, { - "epoch": 0.13, - "learning_rate": 4.410548599225296e-05, - "loss": 0.3762, + "epoch": 0.03, + "learning_rate": 4.853605064763652e-05, + "loss": 0.385, "step": 14090 }, { - "epoch": 0.13, - "learning_rate": 4.410098189352311e-05, - "loss": 0.3763, + "epoch": 0.03, + "learning_rate": 4.853493210442719e-05, + "loss": 0.3857, "step": 14100 }, { - "epoch": 0.13, - "learning_rate": 4.409647779479326e-05, - "loss": 0.3748, + "epoch": 0.03, + "learning_rate": 4.853381356121787e-05, + "loss": 0.3797, "step": 14110 }, { - "epoch": 0.13, - "learning_rate": 4.409197369606342e-05, - "loss": 0.378, + "epoch": 0.03, + "learning_rate": 4.853269501800855e-05, + "loss": 0.3877, "step": 14120 }, { - "epoch": 0.13, - "learning_rate": 4.408746959733357e-05, - "loss": 0.3776, + "epoch": 0.03, + "learning_rate": 4.8531576474799225e-05, + "loss": 0.3807, "step": 14130 }, { - "epoch": 0.13, - "learning_rate": 4.408296549860373e-05, - "loss": 0.376, + "epoch": 0.03, + "learning_rate": 4.8530569785910834e-05, + "loss": 0.3815, "step": 14140 }, { - "epoch": 0.13, - "learning_rate": 4.407846139987389e-05, - "loss": 0.3743, + "epoch": 0.03, + "learning_rate": 4.8529451242701505e-05, + "loss": 0.3822, "step": 14150 }, { - "epoch": 0.13, - "learning_rate": 4.407395730114404e-05, - "loss": 0.3679, + "epoch": 0.03, + "learning_rate": 4.852833269949218e-05, + "loss": 0.3812, "step": 14160 }, { - "epoch": 0.13, - "learning_rate": 4.40694532024142e-05, - "loss": 0.3715, + "epoch": 0.03, + "learning_rate": 4.8527214156282854e-05, + "loss": 0.381, "step": 14170 }, { - "epoch": 0.13, - "learning_rate": 4.4064949103684354e-05, - "loss": 0.3763, + "epoch": 0.03, + "learning_rate": 4.852609561307354e-05, + "loss": 0.3792, "step": 14180 }, { - "epoch": 0.13, - "learning_rate": 4.406044500495451e-05, - "loss": 0.3745, + "epoch": 0.03, + "learning_rate": 4.852497706986422e-05, + "loss": 0.3849, "step": 14190 }, { - "epoch": 0.13, - "learning_rate": 4.405594090622467e-05, - "loss": 0.3732, + "epoch": 0.03, + "learning_rate": 4.852385852665489e-05, + "loss": 0.3863, "step": 14200 }, { - "epoch": 0.13, - "learning_rate": 4.405143680749482e-05, - "loss": 0.3737, + "epoch": 0.03, + "learning_rate": 4.8522739983445566e-05, + "loss": 0.3832, "step": 14210 }, { - "epoch": 0.13, - "learning_rate": 4.404693270876498e-05, - "loss": 0.3672, + "epoch": 0.03, + "learning_rate": 4.852162144023624e-05, + "loss": 0.3801, "step": 14220 }, { - "epoch": 0.13, - "learning_rate": 4.4042428610035135e-05, - "loss": 0.3753, + "epoch": 0.03, + "learning_rate": 4.8520502897026915e-05, + "loss": 0.3774, "step": 14230 }, { - "epoch": 0.13, - "learning_rate": 4.403792451130529e-05, - "loss": 0.3712, + "epoch": 0.03, + "learning_rate": 4.851938435381759e-05, + "loss": 0.3738, "step": 14240 }, { - "epoch": 0.13, - "learning_rate": 4.403342041257544e-05, - "loss": 0.3709, + "epoch": 0.03, + "learning_rate": 4.8518265810608264e-05, + "loss": 0.3854, "step": 14250 }, { - "epoch": 0.13, - "learning_rate": 4.40289163138456e-05, - "loss": 0.3674, + "epoch": 0.03, + "learning_rate": 4.851714726739894e-05, + "loss": 0.3868, "step": 14260 }, { - "epoch": 0.13, - "learning_rate": 4.402441221511576e-05, - "loss": 0.3614, + "epoch": 0.03, + "learning_rate": 4.851602872418961e-05, + "loss": 0.3817, "step": 14270 }, { - "epoch": 0.13, - "learning_rate": 4.401990811638591e-05, - "loss": 0.3746, + "epoch": 0.03, + "learning_rate": 4.851491018098029e-05, + "loss": 0.3781, "step": 14280 }, { - "epoch": 0.13, - "learning_rate": 4.401540401765607e-05, - "loss": 0.374, + "epoch": 0.03, + "learning_rate": 4.851379163777097e-05, + "loss": 0.3818, "step": 14290 }, { - "epoch": 0.13, - "learning_rate": 4.4010899918926224e-05, - "loss": 0.3769, + "epoch": 0.03, + "learning_rate": 4.851267309456165e-05, + "loss": 0.3823, "step": 14300 }, { - "epoch": 0.13, - "learning_rate": 4.400639582019638e-05, - "loss": 0.3751, + "epoch": 0.03, + "learning_rate": 4.8511554551352325e-05, + "loss": 0.3835, "step": 14310 }, { - "epoch": 0.13, - "learning_rate": 4.400189172146654e-05, - "loss": 0.3735, + "epoch": 0.03, + "learning_rate": 4.8510436008142996e-05, + "loss": 0.3811, "step": 14320 }, { - "epoch": 0.13, - "learning_rate": 4.399738762273669e-05, - "loss": 0.378, + "epoch": 0.03, + "learning_rate": 4.8509317464933674e-05, + "loss": 0.379, "step": 14330 }, { - "epoch": 0.13, - "learning_rate": 4.3992883524006854e-05, - "loss": 0.3709, + "epoch": 0.03, + "learning_rate": 4.8508198921724345e-05, + "loss": 0.3777, "step": 14340 }, { - "epoch": 0.13, - "learning_rate": 4.3988379425277004e-05, - "loss": 0.3685, + "epoch": 0.03, + "learning_rate": 4.850708037851502e-05, + "loss": 0.3804, "step": 14350 }, { - "epoch": 0.13, - "learning_rate": 4.3983875326547155e-05, - "loss": 0.3718, + "epoch": 0.03, + "learning_rate": 4.85059618353057e-05, + "loss": 0.3855, "step": 14360 }, { - "epoch": 0.13, - "learning_rate": 4.397937122781732e-05, - "loss": 0.3767, + "epoch": 0.03, + "learning_rate": 4.850484329209637e-05, + "loss": 0.379, "step": 14370 }, { - "epoch": 0.13, - "learning_rate": 4.397486712908747e-05, - "loss": 0.368, + "epoch": 0.03, + "learning_rate": 4.850372474888705e-05, + "loss": 0.3795, "step": 14380 }, { - "epoch": 0.13, - "learning_rate": 4.397036303035763e-05, - "loss": 0.3698, + "epoch": 0.03, + "learning_rate": 4.850260620567773e-05, + "loss": 0.3834, "step": 14390 }, { - "epoch": 0.13, - "learning_rate": 4.3965858931627785e-05, - "loss": 0.3747, + "epoch": 0.03, + "learning_rate": 4.8501487662468406e-05, + "loss": 0.3759, "step": 14400 }, { - "epoch": 0.13, - "learning_rate": 4.3961354832897936e-05, - "loss": 0.377, + "epoch": 0.03, + "learning_rate": 4.8500369119259084e-05, + "loss": 0.3829, "step": 14410 }, { - "epoch": 0.13, - "learning_rate": 4.395685073416809e-05, - "loss": 0.3758, + "epoch": 0.03, + "learning_rate": 4.8499250576049755e-05, + "loss": 0.3743, "step": 14420 }, { - "epoch": 0.13, - "learning_rate": 4.395234663543825e-05, - "loss": 0.3711, + "epoch": 0.03, + "learning_rate": 4.849813203284043e-05, + "loss": 0.3809, "step": 14430 }, { - "epoch": 0.13, - "learning_rate": 4.394784253670841e-05, - "loss": 0.3786, + "epoch": 0.03, + "learning_rate": 4.8497013489631104e-05, + "loss": 0.3802, "step": 14440 }, { - "epoch": 0.13, - "learning_rate": 4.3943338437978566e-05, - "loss": 0.3774, + "epoch": 0.03, + "learning_rate": 4.849589494642178e-05, + "loss": 0.3781, "step": 14450 }, { - "epoch": 0.13, - "learning_rate": 4.3938834339248716e-05, - "loss": 0.3718, + "epoch": 0.03, + "learning_rate": 4.849477640321246e-05, + "loss": 0.3868, "step": 14460 }, { - "epoch": 0.13, - "learning_rate": 4.3934330240518874e-05, - "loss": 0.3706, + "epoch": 0.03, + "learning_rate": 4.849365786000313e-05, + "loss": 0.3797, "step": 14470 }, { - "epoch": 0.13, - "learning_rate": 4.392982614178903e-05, - "loss": 0.3746, + "epoch": 0.03, + "learning_rate": 4.849253931679381e-05, + "loss": 0.3822, "step": 14480 }, { - "epoch": 0.13, - "learning_rate": 4.392532204305919e-05, - "loss": 0.3657, + "epoch": 0.03, + "learning_rate": 4.849142077358449e-05, + "loss": 0.3778, "step": 14490 }, { - "epoch": 0.13, - "learning_rate": 4.392081794432934e-05, - "loss": 0.3743, + "epoch": 0.03, + "learning_rate": 4.8490302230375165e-05, + "loss": 0.3754, "step": 14500 }, { - "epoch": 0.13, - "learning_rate": 4.39163138455995e-05, - "loss": 0.3704, + "epoch": 0.03, + "learning_rate": 4.848918368716584e-05, + "loss": 0.3784, "step": 14510 }, { - "epoch": 0.13, - "learning_rate": 4.3911809746869654e-05, - "loss": 0.3764, + "epoch": 0.03, + "learning_rate": 4.8488065143956514e-05, + "loss": 0.3784, "step": 14520 }, { - "epoch": 0.13, - "learning_rate": 4.3907305648139805e-05, - "loss": 0.3634, + "epoch": 0.03, + "learning_rate": 4.848694660074719e-05, + "loss": 0.3765, "step": 14530 }, { - "epoch": 0.13, - "learning_rate": 4.390280154940997e-05, - "loss": 0.3709, + "epoch": 0.03, + "learning_rate": 4.848582805753786e-05, + "loss": 0.377, "step": 14540 }, { - "epoch": 0.13, - "learning_rate": 4.389829745068012e-05, - "loss": 0.3657, + "epoch": 0.03, + "learning_rate": 4.848470951432854e-05, + "loss": 0.3769, "step": 14550 }, { - "epoch": 0.13, - "learning_rate": 4.389379335195027e-05, - "loss": 0.3773, + "epoch": 0.03, + "learning_rate": 4.848359097111922e-05, + "loss": 0.3786, "step": 14560 }, { - "epoch": 0.13, - "learning_rate": 4.3889289253220435e-05, - "loss": 0.3764, + "epoch": 0.03, + "learning_rate": 4.848247242790989e-05, + "loss": 0.3785, "step": 14570 }, { - "epoch": 0.13, - "learning_rate": 4.3884785154490586e-05, - "loss": 0.3739, + "epoch": 0.03, + "learning_rate": 4.848135388470057e-05, + "loss": 0.3782, "step": 14580 }, { - "epoch": 0.13, - "learning_rate": 4.388028105576075e-05, - "loss": 0.3757, + "epoch": 0.03, + "learning_rate": 4.848023534149124e-05, + "loss": 0.3809, "step": 14590 }, { - "epoch": 0.13, - "learning_rate": 4.38757769570309e-05, - "loss": 0.3727, + "epoch": 0.03, + "learning_rate": 4.8479116798281924e-05, + "loss": 0.3817, "step": 14600 }, { - "epoch": 0.13, - "learning_rate": 4.387127285830105e-05, - "loss": 0.3738, + "epoch": 0.03, + "learning_rate": 4.8477998255072595e-05, + "loss": 0.3777, "step": 14610 }, { - "epoch": 0.13, - "learning_rate": 4.3866768759571216e-05, - "loss": 0.3728, + "epoch": 0.03, + "learning_rate": 4.847687971186327e-05, + "loss": 0.3716, "step": 14620 }, { - "epoch": 0.13, - "learning_rate": 4.3862264660841367e-05, - "loss": 0.3678, + "epoch": 0.03, + "learning_rate": 4.847576116865395e-05, + "loss": 0.371, "step": 14630 }, { - "epoch": 0.13, - "learning_rate": 4.3857760562111524e-05, - "loss": 0.3772, + "epoch": 0.03, + "learning_rate": 4.847464262544462e-05, + "loss": 0.3812, "step": 14640 }, { - "epoch": 0.13, - "learning_rate": 4.385325646338168e-05, - "loss": 0.3719, + "epoch": 0.03, + "learning_rate": 4.84735240822353e-05, + "loss": 0.3807, "step": 14650 }, { - "epoch": 0.13, - "learning_rate": 4.384875236465183e-05, - "loss": 0.3743, + "epoch": 0.03, + "learning_rate": 4.847240553902597e-05, + "loss": 0.3798, "step": 14660 }, { - "epoch": 0.13, - "learning_rate": 4.384424826592199e-05, - "loss": 0.3693, + "epoch": 0.03, + "learning_rate": 4.847128699581665e-05, + "loss": 0.3768, "step": 14670 }, { - "epoch": 0.13, - "learning_rate": 4.383974416719215e-05, - "loss": 0.3745, + "epoch": 0.03, + "learning_rate": 4.847016845260733e-05, + "loss": 0.3748, "step": 14680 }, { - "epoch": 0.13, - "learning_rate": 4.3835240068462305e-05, - "loss": 0.3723, + "epoch": 0.03, + "learning_rate": 4.8469049909398e-05, + "loss": 0.3761, "step": 14690 }, { - "epoch": 0.13, - "learning_rate": 4.3830735969732455e-05, - "loss": 0.3731, + "epoch": 0.03, + "learning_rate": 4.8467931366188676e-05, + "loss": 0.3814, "step": 14700 }, { - "epoch": 0.13, - "learning_rate": 4.382623187100261e-05, - "loss": 0.3704, + "epoch": 0.03, + "learning_rate": 4.8466812822979354e-05, + "loss": 0.3763, "step": 14710 }, { - "epoch": 0.13, - "learning_rate": 4.382172777227277e-05, - "loss": 0.3669, + "epoch": 0.03, + "learning_rate": 4.846569427977003e-05, + "loss": 0.3853, "step": 14720 }, { - "epoch": 0.13, - "learning_rate": 4.381722367354293e-05, - "loss": 0.3679, + "epoch": 0.03, + "learning_rate": 4.846457573656071e-05, + "loss": 0.3836, "step": 14730 }, { - "epoch": 0.13, - "learning_rate": 4.3812719574813085e-05, - "loss": 0.3693, + "epoch": 0.03, + "learning_rate": 4.846345719335138e-05, + "loss": 0.376, "step": 14740 }, { - "epoch": 0.13, - "learning_rate": 4.3808215476083236e-05, - "loss": 0.3677, + "epoch": 0.03, + "learning_rate": 4.846233865014206e-05, + "loss": 0.3758, "step": 14750 }, { - "epoch": 0.13, - "learning_rate": 4.3803711377353394e-05, - "loss": 0.3719, + "epoch": 0.03, + "learning_rate": 4.846122010693273e-05, + "loss": 0.3775, "step": 14760 }, { - "epoch": 0.13, - "learning_rate": 4.379920727862355e-05, - "loss": 0.3744, + "epoch": 0.03, + "learning_rate": 4.846010156372341e-05, + "loss": 0.3763, "step": 14770 }, { - "epoch": 0.13, - "learning_rate": 4.37947031798937e-05, - "loss": 0.3742, + "epoch": 0.03, + "learning_rate": 4.8458983020514086e-05, + "loss": 0.3784, "step": 14780 }, { - "epoch": 0.13, - "learning_rate": 4.3790199081163866e-05, - "loss": 0.3727, + "epoch": 0.03, + "learning_rate": 4.845786447730476e-05, + "loss": 0.3761, "step": 14790 }, { - "epoch": 0.13, - "learning_rate": 4.378569498243402e-05, - "loss": 0.3681, + "epoch": 0.03, + "learning_rate": 4.8456745934095435e-05, + "loss": 0.3819, "step": 14800 }, { - "epoch": 0.13, - "learning_rate": 4.378119088370417e-05, - "loss": 0.3668, + "epoch": 0.03, + "learning_rate": 4.845562739088611e-05, + "loss": 0.3726, "step": 14810 }, { - "epoch": 0.13, - "learning_rate": 4.377668678497433e-05, - "loss": 0.3693, + "epoch": 0.03, + "learning_rate": 4.845450884767679e-05, + "loss": 0.3784, "step": 14820 }, { - "epoch": 0.13, - "learning_rate": 4.377218268624448e-05, - "loss": 0.372, + "epoch": 0.03, + "learning_rate": 4.845339030446747e-05, + "loss": 0.3796, "step": 14830 }, { - "epoch": 0.13, - "learning_rate": 4.376767858751464e-05, - "loss": 0.371, + "epoch": 0.03, + "learning_rate": 4.845227176125814e-05, + "loss": 0.3763, "step": 14840 }, { - "epoch": 0.13, - "learning_rate": 4.37631744887848e-05, - "loss": 0.3661, + "epoch": 0.03, + "learning_rate": 4.845115321804882e-05, + "loss": 0.3783, "step": 14850 }, { - "epoch": 0.13, - "learning_rate": 4.375867039005495e-05, - "loss": 0.374, + "epoch": 0.03, + "learning_rate": 4.845003467483949e-05, + "loss": 0.3752, "step": 14860 }, { - "epoch": 0.13, - "learning_rate": 4.375416629132511e-05, - "loss": 0.3716, + "epoch": 0.03, + "learning_rate": 4.844891613163017e-05, + "loss": 0.3778, "step": 14870 }, { - "epoch": 0.13, - "learning_rate": 4.374966219259526e-05, - "loss": 0.371, + "epoch": 0.03, + "learning_rate": 4.8447797588420845e-05, + "loss": 0.3755, "step": 14880 }, { - "epoch": 0.13, - "learning_rate": 4.374515809386542e-05, - "loss": 0.3707, + "epoch": 0.03, + "learning_rate": 4.8446679045211516e-05, + "loss": 0.3804, "step": 14890 }, { - "epoch": 0.13, - "learning_rate": 4.374065399513558e-05, - "loss": 0.3665, + "epoch": 0.03, + "learning_rate": 4.8445560502002194e-05, + "loss": 0.3747, "step": 14900 }, { - "epoch": 0.13, - "learning_rate": 4.373614989640573e-05, - "loss": 0.3642, + "epoch": 0.03, + "learning_rate": 4.844444195879287e-05, + "loss": 0.3808, "step": 14910 }, { - "epoch": 0.13, - "learning_rate": 4.3731645797675886e-05, - "loss": 0.3679, + "epoch": 0.03, + "learning_rate": 4.844332341558355e-05, + "loss": 0.3737, "step": 14920 }, { - "epoch": 0.13, - "learning_rate": 4.3727141698946044e-05, - "loss": 0.3696, + "epoch": 0.03, + "learning_rate": 4.844220487237422e-05, + "loss": 0.377, "step": 14930 }, { - "epoch": 0.13, - "learning_rate": 4.37226376002162e-05, - "loss": 0.3655, + "epoch": 0.03, + "learning_rate": 4.84410863291649e-05, + "loss": 0.3773, "step": 14940 }, { - "epoch": 0.13, - "learning_rate": 4.371813350148635e-05, - "loss": 0.3685, + "epoch": 0.03, + "learning_rate": 4.843996778595558e-05, + "loss": 0.3837, "step": 14950 }, { - "epoch": 0.13, - "learning_rate": 4.371362940275651e-05, - "loss": 0.376, + "epoch": 0.03, + "learning_rate": 4.843884924274625e-05, + "loss": 0.3746, "step": 14960 }, { - "epoch": 0.13, - "learning_rate": 4.370912530402667e-05, - "loss": 0.366, + "epoch": 0.03, + "learning_rate": 4.8437730699536926e-05, + "loss": 0.3771, "step": 14970 }, { - "epoch": 0.13, - "learning_rate": 4.370462120529682e-05, - "loss": 0.3678, + "epoch": 0.03, + "learning_rate": 4.84366121563276e-05, + "loss": 0.3747, "step": 14980 }, { - "epoch": 0.13, - "learning_rate": 4.370011710656698e-05, - "loss": 0.3696, + "epoch": 0.03, + "learning_rate": 4.8435493613118275e-05, + "loss": 0.3803, "step": 14990 }, { - "epoch": 0.13, - "learning_rate": 4.369561300783713e-05, - "loss": 0.3632, + "epoch": 0.03, + "learning_rate": 4.843437506990895e-05, + "loss": 0.3825, "step": 15000 }, { - "epoch": 0.13, - "learning_rate": 4.369110890910729e-05, - "loss": 0.3721, + "epoch": 0.03, + "learning_rate": 4.843325652669963e-05, + "loss": 0.3779, "step": 15010 }, { - "epoch": 0.13, - "learning_rate": 4.368660481037745e-05, - "loss": 0.3652, + "epoch": 0.03, + "learning_rate": 4.843213798349031e-05, + "loss": 0.3816, "step": 15020 }, { - "epoch": 0.13, - "learning_rate": 4.36821007116476e-05, - "loss": 0.3654, + "epoch": 0.03, + "learning_rate": 4.843101944028098e-05, + "loss": 0.3732, "step": 15030 }, { - "epoch": 0.13, - "learning_rate": 4.367759661291776e-05, - "loss": 0.3676, + "epoch": 0.03, + "learning_rate": 4.842990089707166e-05, + "loss": 0.3775, "step": 15040 }, { - "epoch": 0.13, - "learning_rate": 4.3673092514187913e-05, - "loss": 0.3676, + "epoch": 0.03, + "learning_rate": 4.8428782353862336e-05, + "loss": 0.3742, "step": 15050 }, { - "epoch": 0.13, - "learning_rate": 4.3668588415458064e-05, - "loss": 0.3736, + "epoch": 0.03, + "learning_rate": 4.842766381065301e-05, + "loss": 0.3823, "step": 15060 }, { - "epoch": 0.13, - "learning_rate": 4.366408431672823e-05, - "loss": 0.3684, + "epoch": 0.03, + "learning_rate": 4.8426545267443685e-05, + "loss": 0.3801, "step": 15070 }, { - "epoch": 0.13, - "learning_rate": 4.365958021799838e-05, - "loss": 0.3724, + "epoch": 0.03, + "learning_rate": 4.8425426724234356e-05, + "loss": 0.3797, "step": 15080 }, { - "epoch": 0.13, - "learning_rate": 4.365507611926854e-05, - "loss": 0.3657, + "epoch": 0.03, + "learning_rate": 4.8424308181025034e-05, + "loss": 0.371, "step": 15090 }, { - "epoch": 0.13, - "learning_rate": 4.3650572020538694e-05, - "loss": 0.3694, + "epoch": 0.03, + "learning_rate": 4.842318963781571e-05, + "loss": 0.3749, "step": 15100 }, { - "epoch": 0.13, - "learning_rate": 4.3646067921808845e-05, - "loss": 0.3665, + "epoch": 0.03, + "learning_rate": 4.842207109460638e-05, + "loss": 0.3757, "step": 15110 }, { - "epoch": 0.13, - "learning_rate": 4.3641563823079e-05, - "loss": 0.3739, + "epoch": 0.03, + "learning_rate": 4.842095255139706e-05, + "loss": 0.3688, "step": 15120 }, { - "epoch": 0.14, - "learning_rate": 4.363705972434916e-05, - "loss": 0.3717, + "epoch": 0.03, + "learning_rate": 4.841983400818774e-05, + "loss": 0.3736, "step": 15130 }, { - "epoch": 0.14, - "learning_rate": 4.363255562561932e-05, - "loss": 0.3765, + "epoch": 0.03, + "learning_rate": 4.841871546497842e-05, + "loss": 0.3744, "step": 15140 }, { - "epoch": 0.14, - "learning_rate": 4.3628051526889475e-05, - "loss": 0.3655, + "epoch": 0.03, + "learning_rate": 4.8417596921769095e-05, + "loss": 0.3747, "step": 15150 }, { - "epoch": 0.14, - "learning_rate": 4.3623547428159626e-05, - "loss": 0.3705, + "epoch": 0.03, + "learning_rate": 4.8416478378559766e-05, + "loss": 0.3718, "step": 15160 }, { - "epoch": 0.14, - "learning_rate": 4.361904332942978e-05, - "loss": 0.3707, + "epoch": 0.03, + "learning_rate": 4.8415359835350444e-05, + "loss": 0.3756, "step": 15170 }, { - "epoch": 0.14, - "learning_rate": 4.361453923069994e-05, - "loss": 0.3655, + "epoch": 0.03, + "learning_rate": 4.8414241292141115e-05, + "loss": 0.3746, "step": 15180 }, { - "epoch": 0.14, - "learning_rate": 4.36100351319701e-05, - "loss": 0.3667, + "epoch": 0.03, + "learning_rate": 4.841312274893179e-05, + "loss": 0.3772, "step": 15190 }, { - "epoch": 0.14, - "learning_rate": 4.360553103324025e-05, - "loss": 0.3657, + "epoch": 0.03, + "learning_rate": 4.841200420572247e-05, + "loss": 0.3729, "step": 15200 }, { - "epoch": 0.14, - "learning_rate": 4.3601026934510406e-05, - "loss": 0.3656, + "epoch": 0.03, + "learning_rate": 4.841088566251314e-05, + "loss": 0.3719, "step": 15210 }, { - "epoch": 0.14, - "learning_rate": 4.3596522835780564e-05, - "loss": 0.3607, + "epoch": 0.03, + "learning_rate": 4.840976711930382e-05, + "loss": 0.371, "step": 15220 }, { - "epoch": 0.14, - "learning_rate": 4.3592018737050714e-05, - "loss": 0.3678, + "epoch": 0.03, + "learning_rate": 4.84086485760945e-05, + "loss": 0.37, "step": 15230 }, { - "epoch": 0.14, - "learning_rate": 4.358751463832088e-05, - "loss": 0.3698, + "epoch": 0.03, + "learning_rate": 4.8407530032885176e-05, + "loss": 0.3755, "step": 15240 }, { - "epoch": 0.14, - "learning_rate": 4.358301053959103e-05, - "loss": 0.3654, + "epoch": 0.03, + "learning_rate": 4.840641148967585e-05, + "loss": 0.3687, "step": 15250 }, { - "epoch": 0.14, - "learning_rate": 4.357850644086118e-05, - "loss": 0.3688, + "epoch": 0.03, + "learning_rate": 4.8405292946466525e-05, + "loss": 0.374, "step": 15260 }, { - "epoch": 0.14, - "learning_rate": 4.3574002342131344e-05, - "loss": 0.368, + "epoch": 0.03, + "learning_rate": 4.84041744032572e-05, + "loss": 0.3749, "step": 15270 }, { - "epoch": 0.14, - "learning_rate": 4.3569498243401495e-05, - "loss": 0.3703, + "epoch": 0.03, + "learning_rate": 4.8403055860047874e-05, + "loss": 0.3692, "step": 15280 }, { - "epoch": 0.14, - "learning_rate": 4.356499414467165e-05, - "loss": 0.3677, + "epoch": 0.03, + "learning_rate": 4.840193731683855e-05, + "loss": 0.3734, "step": 15290 }, { - "epoch": 0.14, - "learning_rate": 4.356049004594181e-05, - "loss": 0.3656, + "epoch": 0.03, + "learning_rate": 4.840081877362922e-05, + "loss": 0.3701, "step": 15300 }, { - "epoch": 0.14, - "learning_rate": 4.355598594721196e-05, - "loss": 0.3666, + "epoch": 0.03, + "learning_rate": 4.83997002304199e-05, + "loss": 0.3733, "step": 15310 }, { - "epoch": 0.14, - "learning_rate": 4.3551481848482125e-05, - "loss": 0.3701, + "epoch": 0.03, + "learning_rate": 4.839858168721058e-05, + "loss": 0.3704, "step": 15320 }, { - "epoch": 0.14, - "learning_rate": 4.3546977749752276e-05, - "loss": 0.3717, + "epoch": 0.03, + "learning_rate": 4.839746314400126e-05, + "loss": 0.3769, "step": 15330 }, { - "epoch": 0.14, - "learning_rate": 4.354247365102243e-05, - "loss": 0.3707, + "epoch": 0.03, + "learning_rate": 4.8396344600791935e-05, + "loss": 0.3721, "step": 15340 }, { - "epoch": 0.14, - "learning_rate": 4.353796955229259e-05, - "loss": 0.3654, + "epoch": 0.03, + "learning_rate": 4.8395226057582606e-05, + "loss": 0.3639, "step": 15350 }, { - "epoch": 0.14, - "learning_rate": 4.353346545356274e-05, - "loss": 0.372, + "epoch": 0.03, + "learning_rate": 4.8394107514373284e-05, + "loss": 0.3753, "step": 15360 }, { - "epoch": 0.14, - "learning_rate": 4.35289613548329e-05, - "loss": 0.3656, + "epoch": 0.03, + "learning_rate": 4.839298897116396e-05, + "loss": 0.3731, "step": 15370 }, { - "epoch": 0.14, - "learning_rate": 4.3524457256103057e-05, - "loss": 0.3654, + "epoch": 0.03, + "learning_rate": 4.839187042795463e-05, + "loss": 0.3763, "step": 15380 }, { - "epoch": 0.14, - "learning_rate": 4.3519953157373214e-05, - "loss": 0.373, + "epoch": 0.03, + "learning_rate": 4.839075188474531e-05, + "loss": 0.3745, "step": 15390 }, { - "epoch": 0.14, - "learning_rate": 4.3515449058643365e-05, - "loss": 0.3712, + "epoch": 0.03, + "learning_rate": 4.838963334153598e-05, + "loss": 0.3742, "step": 15400 }, { - "epoch": 0.14, - "learning_rate": 4.351094495991352e-05, - "loss": 0.3634, + "epoch": 0.03, + "learning_rate": 4.838851479832666e-05, + "loss": 0.3662, "step": 15410 }, { - "epoch": 0.14, - "learning_rate": 4.350644086118368e-05, - "loss": 0.3684, + "epoch": 0.03, + "learning_rate": 4.838739625511734e-05, + "loss": 0.375, "step": 15420 }, { - "epoch": 0.14, - "learning_rate": 4.350193676245384e-05, - "loss": 0.3648, + "epoch": 0.03, + "learning_rate": 4.8386277711908016e-05, + "loss": 0.3718, "step": 15430 }, { - "epoch": 0.14, - "learning_rate": 4.3497432663723995e-05, - "loss": 0.3659, + "epoch": 0.03, + "learning_rate": 4.8385159168698694e-05, + "loss": 0.3709, "step": 15440 }, { - "epoch": 0.14, - "learning_rate": 4.3492928564994145e-05, - "loss": 0.3631, + "epoch": 0.03, + "learning_rate": 4.8384040625489365e-05, + "loss": 0.3647, "step": 15450 }, { - "epoch": 0.14, - "learning_rate": 4.34884244662643e-05, - "loss": 0.3682, + "epoch": 0.03, + "learning_rate": 4.838292208228004e-05, + "loss": 0.3716, "step": 15460 }, { - "epoch": 0.14, - "learning_rate": 4.348392036753446e-05, - "loss": 0.3658, + "epoch": 0.03, + "learning_rate": 4.838180353907072e-05, + "loss": 0.3726, "step": 15470 }, { - "epoch": 0.14, - "learning_rate": 4.347941626880461e-05, - "loss": 0.368, + "epoch": 0.03, + "learning_rate": 4.838068499586139e-05, + "loss": 0.3703, "step": 15480 }, { - "epoch": 0.14, - "learning_rate": 4.347491217007477e-05, - "loss": 0.363, + "epoch": 0.03, + "learning_rate": 4.837956645265207e-05, + "loss": 0.3703, "step": 15490 }, { - "epoch": 0.14, - "learning_rate": 4.3470408071344926e-05, - "loss": 0.3585, + "epoch": 0.03, + "learning_rate": 4.837844790944274e-05, + "loss": 0.3698, "step": 15500 }, { - "epoch": 0.14, - "learning_rate": 4.346590397261508e-05, - "loss": 0.3592, + "epoch": 0.03, + "learning_rate": 4.837732936623342e-05, + "loss": 0.3753, "step": 15510 }, { - "epoch": 0.14, - "learning_rate": 4.346139987388524e-05, - "loss": 0.3607, + "epoch": 0.03, + "learning_rate": 4.83762108230241e-05, + "loss": 0.3704, "step": 15520 }, { - "epoch": 0.14, - "learning_rate": 4.345689577515539e-05, - "loss": 0.3598, + "epoch": 0.03, + "learning_rate": 4.837509227981477e-05, + "loss": 0.3721, "step": 15530 }, { - "epoch": 0.14, - "learning_rate": 4.345239167642555e-05, - "loss": 0.3657, + "epoch": 0.03, + "learning_rate": 4.8373973736605446e-05, + "loss": 0.3769, "step": 15540 }, { - "epoch": 0.14, - "learning_rate": 4.344788757769571e-05, - "loss": 0.3659, + "epoch": 0.03, + "learning_rate": 4.8372855193396124e-05, + "loss": 0.3619, "step": 15550 }, { - "epoch": 0.14, - "learning_rate": 4.344338347896586e-05, - "loss": 0.3633, + "epoch": 0.03, + "learning_rate": 4.83717366501868e-05, + "loss": 0.3679, "step": 15560 }, { - "epoch": 0.14, - "learning_rate": 4.343887938023602e-05, - "loss": 0.3667, + "epoch": 0.03, + "learning_rate": 4.837061810697747e-05, + "loss": 0.3744, "step": 15570 }, { - "epoch": 0.14, - "learning_rate": 4.343437528150617e-05, - "loss": 0.3681, + "epoch": 0.03, + "learning_rate": 4.836949956376815e-05, + "loss": 0.3754, "step": 15580 }, { - "epoch": 0.14, - "learning_rate": 4.342987118277633e-05, - "loss": 0.3605, + "epoch": 0.03, + "learning_rate": 4.836838102055883e-05, + "loss": 0.3703, "step": 15590 }, { - "epoch": 0.14, - "learning_rate": 4.342536708404649e-05, - "loss": 0.3753, + "epoch": 0.03, + "learning_rate": 4.83672624773495e-05, + "loss": 0.3729, "step": 15600 }, { - "epoch": 0.14, - "learning_rate": 4.342086298531664e-05, - "loss": 0.3653, + "epoch": 0.03, + "learning_rate": 4.836614393414018e-05, + "loss": 0.3684, "step": 15610 }, { - "epoch": 0.14, - "learning_rate": 4.3416358886586796e-05, - "loss": 0.3636, + "epoch": 0.03, + "learning_rate": 4.836502539093085e-05, + "loss": 0.3723, "step": 15620 }, { - "epoch": 0.14, - "learning_rate": 4.341185478785695e-05, - "loss": 0.3582, + "epoch": 0.03, + "learning_rate": 4.836390684772153e-05, + "loss": 0.3703, "step": 15630 }, { - "epoch": 0.14, - "learning_rate": 4.340735068912711e-05, - "loss": 0.3688, + "epoch": 0.03, + "learning_rate": 4.8362788304512205e-05, + "loss": 0.3699, "step": 15640 }, { - "epoch": 0.14, - "learning_rate": 4.340284659039726e-05, - "loss": 0.3642, + "epoch": 0.03, + "learning_rate": 4.836166976130288e-05, + "loss": 0.3686, "step": 15650 }, { - "epoch": 0.14, - "learning_rate": 4.339834249166742e-05, - "loss": 0.358, + "epoch": 0.03, + "learning_rate": 4.836055121809356e-05, + "loss": 0.3708, "step": 15660 }, { - "epoch": 0.14, - "learning_rate": 4.3393838392937576e-05, - "loss": 0.3671, + "epoch": 0.03, + "learning_rate": 4.835943267488423e-05, + "loss": 0.3699, "step": 15670 }, { - "epoch": 0.14, - "learning_rate": 4.338933429420773e-05, - "loss": 0.3653, + "epoch": 0.03, + "learning_rate": 4.835831413167491e-05, + "loss": 0.3721, "step": 15680 }, { - "epoch": 0.14, - "learning_rate": 4.338483019547789e-05, - "loss": 0.3646, + "epoch": 0.04, + "learning_rate": 4.835719558846559e-05, + "loss": 0.3687, "step": 15690 }, { - "epoch": 0.14, - "learning_rate": 4.338032609674804e-05, - "loss": 0.3643, + "epoch": 0.04, + "learning_rate": 4.835607704525626e-05, + "loss": 0.3673, "step": 15700 }, { - "epoch": 0.14, - "learning_rate": 4.33758219980182e-05, - "loss": 0.3583, + "epoch": 0.04, + "learning_rate": 4.8354958502046937e-05, + "loss": 0.3709, "step": 15710 }, { - "epoch": 0.14, - "learning_rate": 4.337131789928836e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.835383995883761e-05, + "loss": 0.3662, "step": 15720 }, { - "epoch": 0.14, - "learning_rate": 4.336681380055851e-05, - "loss": 0.3677, + "epoch": 0.04, + "learning_rate": 4.8352721415628286e-05, + "loss": 0.3665, "step": 15730 }, { - "epoch": 0.14, - "learning_rate": 4.3362309701828665e-05, - "loss": 0.3614, + "epoch": 0.04, + "learning_rate": 4.8351602872418964e-05, + "loss": 0.3713, "step": 15740 }, { - "epoch": 0.14, - "learning_rate": 4.335780560309882e-05, - "loss": 0.3623, + "epoch": 0.04, + "learning_rate": 4.835048432920964e-05, + "loss": 0.3738, "step": 15750 }, { - "epoch": 0.14, - "learning_rate": 4.3353301504368973e-05, - "loss": 0.3551, + "epoch": 0.04, + "learning_rate": 4.834936578600032e-05, + "loss": 0.3759, "step": 15760 }, { - "epoch": 0.14, - "learning_rate": 4.334879740563914e-05, - "loss": 0.3628, + "epoch": 0.04, + "learning_rate": 4.834824724279099e-05, + "loss": 0.3675, "step": 15770 }, { - "epoch": 0.14, - "learning_rate": 4.334429330690929e-05, - "loss": 0.3689, + "epoch": 0.04, + "learning_rate": 4.834712869958167e-05, + "loss": 0.3682, "step": 15780 }, { - "epoch": 0.14, - "learning_rate": 4.3339789208179446e-05, - "loss": 0.3594, + "epoch": 0.04, + "learning_rate": 4.8346010156372346e-05, + "loss": 0.3728, "step": 15790 }, { - "epoch": 0.14, - "learning_rate": 4.3335285109449603e-05, - "loss": 0.3628, + "epoch": 0.04, + "learning_rate": 4.834489161316302e-05, + "loss": 0.3726, "step": 15800 }, { - "epoch": 0.14, - "learning_rate": 4.3330781010719754e-05, - "loss": 0.3657, + "epoch": 0.04, + "learning_rate": 4.8343773069953696e-05, + "loss": 0.372, "step": 15810 }, { - "epoch": 0.14, - "learning_rate": 4.332627691198991e-05, - "loss": 0.3619, + "epoch": 0.04, + "learning_rate": 4.834265452674437e-05, + "loss": 0.3657, "step": 15820 }, { - "epoch": 0.14, - "learning_rate": 4.332177281326007e-05, - "loss": 0.3698, + "epoch": 0.04, + "learning_rate": 4.8341535983535045e-05, + "loss": 0.3736, "step": 15830 }, { - "epoch": 0.14, - "learning_rate": 4.331726871453023e-05, - "loss": 0.3647, + "epoch": 0.04, + "learning_rate": 4.834041744032572e-05, + "loss": 0.3673, "step": 15840 }, { - "epoch": 0.14, - "learning_rate": 4.3312764615800384e-05, - "loss": 0.3661, + "epoch": 0.04, + "learning_rate": 4.83392988971164e-05, + "loss": 0.3654, "step": 15850 }, { - "epoch": 0.14, - "learning_rate": 4.3308260517070535e-05, - "loss": 0.3647, + "epoch": 0.04, + "learning_rate": 4.833818035390708e-05, + "loss": 0.3737, "step": 15860 }, { - "epoch": 0.14, - "learning_rate": 4.330375641834069e-05, - "loss": 0.3623, + "epoch": 0.04, + "learning_rate": 4.833706181069775e-05, + "loss": 0.3711, "step": 15870 }, { - "epoch": 0.14, - "learning_rate": 4.329925231961085e-05, - "loss": 0.3679, + "epoch": 0.04, + "learning_rate": 4.833594326748843e-05, + "loss": 0.3713, "step": 15880 }, { - "epoch": 0.14, - "learning_rate": 4.329474822088101e-05, - "loss": 0.3595, + "epoch": 0.04, + "learning_rate": 4.83348247242791e-05, + "loss": 0.3722, "step": 15890 }, { - "epoch": 0.14, - "learning_rate": 4.329024412215116e-05, - "loss": 0.361, + "epoch": 0.04, + "learning_rate": 4.8333706181069777e-05, + "loss": 0.3745, "step": 15900 }, { - "epoch": 0.14, - "learning_rate": 4.3285740023421316e-05, - "loss": 0.3593, + "epoch": 0.04, + "learning_rate": 4.8332587637860454e-05, + "loss": 0.3777, "step": 15910 }, { - "epoch": 0.14, - "learning_rate": 4.328123592469147e-05, - "loss": 0.3678, + "epoch": 0.04, + "learning_rate": 4.8331469094651126e-05, + "loss": 0.3688, "step": 15920 }, { - "epoch": 0.14, - "learning_rate": 4.3276731825961624e-05, - "loss": 0.3646, + "epoch": 0.04, + "learning_rate": 4.8330350551441804e-05, + "loss": 0.3731, "step": 15930 }, { - "epoch": 0.14, - "learning_rate": 4.327222772723178e-05, - "loss": 0.3672, + "epoch": 0.04, + "learning_rate": 4.8329232008232475e-05, + "loss": 0.3722, "step": 15940 }, { - "epoch": 0.14, - "learning_rate": 4.326772362850194e-05, - "loss": 0.3612, + "epoch": 0.04, + "learning_rate": 4.832811346502315e-05, + "loss": 0.3697, "step": 15950 }, { - "epoch": 0.14, - "learning_rate": 4.326321952977209e-05, - "loss": 0.3609, + "epoch": 0.04, + "learning_rate": 4.832699492181384e-05, + "loss": 0.3622, "step": 15960 }, { - "epoch": 0.14, - "learning_rate": 4.3258715431042254e-05, - "loss": 0.3561, + "epoch": 0.04, + "learning_rate": 4.832587637860451e-05, + "loss": 0.3659, "step": 15970 }, { - "epoch": 0.14, - "learning_rate": 4.3254211332312404e-05, - "loss": 0.3553, + "epoch": 0.04, + "learning_rate": 4.8324757835395186e-05, + "loss": 0.3685, "step": 15980 }, { - "epoch": 0.14, - "learning_rate": 4.324970723358256e-05, - "loss": 0.3646, + "epoch": 0.04, + "learning_rate": 4.832363929218586e-05, + "loss": 0.3771, "step": 15990 }, { - "epoch": 0.14, - "learning_rate": 4.324520313485272e-05, - "loss": 0.3612, + "epoch": 0.04, + "learning_rate": 4.8322520748976536e-05, + "loss": 0.3748, "step": 16000 }, { - "epoch": 0.14, - "eval_NEIMS_canon_smiles": 0.91085, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.0039, - "eval_NEIMS_daylight_tanimoto_simil": 0.3440219888393381, - "eval_NEIMS_exact_mols": 0.0038833333333333333, - "eval_NEIMS_exact_smiles": 0.0037166666666666667, - "eval_NEIMS_loss": 0.36472371220588684, - "eval_NEIMS_matched_formulas": 0.3067, - "eval_NEIMS_morgan_tanimoto_simil": 0.24112814002003777, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.003933333333333333, - "eval_NEIMS_runtime": 723.6863, - "eval_NEIMS_samples_per_second": 82.909, - "eval_NEIMS_steps_per_second": 1.296, + "epoch": 0.04, + "eval_NEIMS_canon_smiles": 0.9322833333333334, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.002683333333333333, + "eval_NEIMS_daylight_tanimoto_simil": 0.34392575241200163, + "eval_NEIMS_exact_mols": 0.00265, + "eval_NEIMS_exact_smiles": 0.00255, + "eval_NEIMS_loss": 0.37214910984039307, + "eval_NEIMS_matched_formulas": 0.24103333333333332, + "eval_NEIMS_morgan_tanimoto_simil": 0.2411642503576946, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0026666666666666666, + "eval_NEIMS_runtime": 750.0856, + "eval_NEIMS_samples_per_second": 79.991, + "eval_NEIMS_steps_per_second": 1.251, "step": 16000 }, { - "epoch": 0.14, - "eval_RASSP_canon_smiles": 0.9057501586135506, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.006995692389888804, - "eval_RASSP_daylight_tanimoto_simil": 0.3861519831986421, - "eval_RASSP_exact_mols": 0.006945603900223729, - "eval_RASSP_exact_smiles": 0.006578288309346512, - "eval_RASSP_loss": 0.3267086148262024, - "eval_RASSP_matched_formulas": 0.39488095635622933, - "eval_RASSP_morgan_tanimoto_simil": 0.25511754811398485, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.006978996226667112, - "eval_RASSP_runtime": 828.7523, - "eval_RASSP_samples_per_second": 72.27, - "eval_RASSP_steps_per_second": 1.129, + "epoch": 0.04, + "eval_RASSP_canon_smiles": 0.9278558787190704, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.0040905599893144556, + "eval_RASSP_daylight_tanimoto_simil": 0.37401171321214854, + "eval_RASSP_exact_mols": 0.004057167662871072, + "eval_RASSP_exact_smiles": 0.003923598357097539, + "eval_RASSP_loss": 0.3527809977531433, + "eval_RASSP_matched_formulas": 0.3061909373226033, + "eval_RASSP_morgan_tanimoto_simil": 0.24349179726404968, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.004073863826092764, + "eval_RASSP_runtime": 828.5972, + "eval_RASSP_samples_per_second": 72.284, + "eval_RASSP_steps_per_second": 1.13, "step": 16000 }, { - "epoch": 0.14, - "eval_NIST_canon_smiles": 0.8548461511161586, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.002555275579373248, - "eval_NIST_daylight_tanimoto_simil": 0.21976448765447698, - "eval_NIST_exact_mols": 0.002271356070553998, - "eval_NIST_exact_smiles": 0.002093906377541967, - "eval_NIST_loss": 1.5112570524215698, - "eval_NIST_matched_formulas": 0.03275721333002094, - "eval_NIST_morgan_tanimoto_simil": 0.1761940699405261, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.002448805763566029, - "eval_NIST_runtime": 455.2328, - "eval_NIST_samples_per_second": 61.896, - "eval_NIST_steps_per_second": 0.969, + "epoch": 0.04, + "eval_NEIMS_old_canon_smiles": 0.9314333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.0025666666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.342187401082499, + "eval_NEIMS_old_exact_mols": 0.0025666666666666667, + "eval_NEIMS_old_exact_smiles": 0.0024, + "eval_NEIMS_old_loss": 0.3725118935108185, + "eval_NEIMS_old_matched_formulas": 0.23713333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.24129186809186173, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.0025666666666666667, + "eval_NEIMS_old_runtime": 367.4027, + "eval_NEIMS_old_samples_per_second": 81.654, + "eval_NEIMS_old_steps_per_second": 1.277, "step": 16000 }, { - "epoch": 0.14, - "learning_rate": 4.324069903612287e-05, - "loss": 0.3649, + "epoch": 0.04, + "eval_RASSP_old_canon_smiles": 0.9263189508459305, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.004304735208729603, + "eval_RASSP_old_daylight_tanimoto_simil": 0.37772694911068816, + "eval_RASSP_old_exact_mols": 0.004204625087596356, + "eval_RASSP_old_exact_smiles": 0.004104514966463109, + "eval_RASSP_old_loss": 0.34419357776641846, + "eval_RASSP_old_matched_formulas": 0.32228784996829846, + "eval_RASSP_old_morgan_tanimoto_simil": 0.2464420297950009, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.004204625087596356, + "eval_RASSP_old_runtime": 414.4404, + "eval_RASSP_old_samples_per_second": 72.307, + "eval_RASSP_old_steps_per_second": 1.132, + "step": 16000 + }, + { + "epoch": 0.04, + "eval_NIST_canon_smiles": 0.8825637931646378, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.002271356070553998, + "eval_NIST_daylight_tanimoto_simil": 0.227922124107278, + "eval_NIST_exact_mols": 0.001987436561734748, + "eval_NIST_exact_smiles": 0.001951946623132342, + "eval_NIST_loss": 1.8087286949157715, + "eval_NIST_matched_formulas": 0.028782340206551443, + "eval_NIST_morgan_tanimoto_simil": 0.18515316983431618, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.0020584164389395605, + "eval_NIST_runtime": 464.5459, + "eval_NIST_samples_per_second": 60.655, + "eval_NIST_steps_per_second": 0.949, + "step": 16000 + }, + { + "epoch": 0.04, + "learning_rate": 4.8321402205767213e-05, + "loss": 0.3715, "step": 16010 }, { - "epoch": 0.14, - "learning_rate": 4.3236194937393034e-05, - "loss": 0.3641, + "epoch": 0.04, + "learning_rate": 4.8320283662557885e-05, + "loss": 0.3652, "step": 16020 }, { - "epoch": 0.14, - "learning_rate": 4.3231690838663185e-05, - "loss": 0.358, + "epoch": 0.04, + "learning_rate": 4.831916511934856e-05, + "loss": 0.3673, "step": 16030 }, { - "epoch": 0.14, - "learning_rate": 4.322718673993334e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.8318046576139234e-05, + "loss": 0.3697, "step": 16040 }, { - "epoch": 0.14, - "learning_rate": 4.32226826412035e-05, - "loss": 0.3644, + "epoch": 0.04, + "learning_rate": 4.831692803292991e-05, + "loss": 0.3714, "step": 16050 }, { - "epoch": 0.14, - "learning_rate": 4.321817854247365e-05, - "loss": 0.3683, + "epoch": 0.04, + "learning_rate": 4.831580948972059e-05, + "loss": 0.3692, "step": 16060 }, { - "epoch": 0.14, - "learning_rate": 4.321367444374381e-05, - "loss": 0.3613, + "epoch": 0.04, + "learning_rate": 4.831469094651127e-05, + "loss": 0.3722, "step": 16070 }, { - "epoch": 0.14, - "learning_rate": 4.3209620754886945e-05, - "loss": 0.3691, + "epoch": 0.04, + "learning_rate": 4.8313572403301945e-05, + "loss": 0.3685, "step": 16080 }, { - "epoch": 0.14, - "learning_rate": 4.320511665615711e-05, - "loss": 0.3645, + "epoch": 0.04, + "learning_rate": 4.8312453860092617e-05, + "loss": 0.3637, "step": 16090 }, { - "epoch": 0.14, - "learning_rate": 4.320061255742726e-05, - "loss": 0.3535, + "epoch": 0.04, + "learning_rate": 4.8311335316883294e-05, + "loss": 0.3643, "step": 16100 }, { - "epoch": 0.14, - "learning_rate": 4.319610845869742e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.831021677367397e-05, + "loss": 0.3674, "step": 16110 }, { - "epoch": 0.14, - "learning_rate": 4.3191604359967575e-05, - "loss": 0.3661, + "epoch": 0.04, + "learning_rate": 4.8309098230464644e-05, + "loss": 0.3682, "step": 16120 }, { - "epoch": 0.14, - "learning_rate": 4.3187100261237726e-05, - "loss": 0.3574, + "epoch": 0.04, + "learning_rate": 4.830797968725532e-05, + "loss": 0.3705, "step": 16130 }, { - "epoch": 0.14, - "learning_rate": 4.3182596162507883e-05, - "loss": 0.3624, + "epoch": 0.04, + "learning_rate": 4.830686114404599e-05, + "loss": 0.3694, "step": 16140 }, { - "epoch": 0.14, - "learning_rate": 4.317809206377804e-05, - "loss": 0.3632, + "epoch": 0.04, + "learning_rate": 4.830574260083667e-05, + "loss": 0.363, "step": 16150 }, { - "epoch": 0.14, - "learning_rate": 4.31735879650482e-05, - "loss": 0.3618, + "epoch": 0.04, + "learning_rate": 4.830462405762735e-05, + "loss": 0.3694, "step": 16160 }, { - "epoch": 0.14, - "learning_rate": 4.316908386631835e-05, - "loss": 0.3676, + "epoch": 0.04, + "learning_rate": 4.8303505514418026e-05, + "loss": 0.3643, "step": 16170 }, { - "epoch": 0.14, - "learning_rate": 4.316457976758851e-05, - "loss": 0.362, + "epoch": 0.04, + "learning_rate": 4.8302498825529635e-05, + "loss": 0.3683, "step": 16180 }, { - "epoch": 0.14, - "learning_rate": 4.3160075668858664e-05, - "loss": 0.3617, + "epoch": 0.04, + "learning_rate": 4.8301380282320306e-05, + "loss": 0.3712, "step": 16190 }, { - "epoch": 0.14, - "learning_rate": 4.3155571570128815e-05, - "loss": 0.3557, + "epoch": 0.04, + "learning_rate": 4.8300261739110984e-05, + "loss": 0.3632, "step": 16200 }, { - "epoch": 0.14, - "learning_rate": 4.315106747139898e-05, - "loss": 0.3608, + "epoch": 0.04, + "learning_rate": 4.8299143195901655e-05, + "loss": 0.3712, "step": 16210 }, { - "epoch": 0.14, - "learning_rate": 4.314656337266913e-05, - "loss": 0.3637, + "epoch": 0.04, + "learning_rate": 4.829802465269233e-05, + "loss": 0.369, "step": 16220 }, { - "epoch": 0.14, - "learning_rate": 4.314205927393929e-05, - "loss": 0.3556, + "epoch": 0.04, + "learning_rate": 4.829690610948301e-05, + "loss": 0.371, "step": 16230 }, { - "epoch": 0.14, - "learning_rate": 4.3137555175209445e-05, - "loss": 0.3638, + "epoch": 0.04, + "learning_rate": 4.829578756627369e-05, + "loss": 0.3651, "step": 16240 }, { - "epoch": 0.15, - "learning_rate": 4.3133051076479596e-05, - "loss": 0.3564, + "epoch": 0.04, + "learning_rate": 4.829466902306437e-05, + "loss": 0.3663, "step": 16250 }, { - "epoch": 0.15, - "learning_rate": 4.312854697774975e-05, - "loss": 0.3611, + "epoch": 0.04, + "learning_rate": 4.829355047985504e-05, + "loss": 0.3728, "step": 16260 }, { - "epoch": 0.15, - "learning_rate": 4.312404287901991e-05, - "loss": 0.3588, + "epoch": 0.04, + "learning_rate": 4.8292431936645716e-05, + "loss": 0.3697, "step": 16270 }, { - "epoch": 0.15, - "learning_rate": 4.311953878029006e-05, - "loss": 0.3539, + "epoch": 0.04, + "learning_rate": 4.829131339343639e-05, + "loss": 0.368, "step": 16280 }, { - "epoch": 0.15, - "learning_rate": 4.3115034681560226e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.8290194850227065e-05, + "loss": 0.3699, "step": 16290 }, { - "epoch": 0.15, - "learning_rate": 4.3110530582830376e-05, - "loss": 0.3583, + "epoch": 0.04, + "learning_rate": 4.828907630701774e-05, + "loss": 0.3725, "step": 16300 }, { - "epoch": 0.15, - "learning_rate": 4.3106026484100534e-05, - "loss": 0.3643, + "epoch": 0.04, + "learning_rate": 4.8287957763808414e-05, + "loss": 0.3662, "step": 16310 }, { - "epoch": 0.15, - "learning_rate": 4.310152238537069e-05, - "loss": 0.3579, + "epoch": 0.04, + "learning_rate": 4.828683922059909e-05, + "loss": 0.3682, "step": 16320 }, { - "epoch": 0.15, - "learning_rate": 4.309701828664084e-05, - "loss": 0.3635, + "epoch": 0.04, + "learning_rate": 4.828572067738977e-05, + "loss": 0.3713, "step": 16330 }, { - "epoch": 0.15, - "learning_rate": 4.3092514187911e-05, - "loss": 0.3603, + "epoch": 0.04, + "learning_rate": 4.828460213418045e-05, + "loss": 0.3677, "step": 16340 }, { - "epoch": 0.15, - "learning_rate": 4.308801008918116e-05, - "loss": 0.3601, + "epoch": 0.04, + "learning_rate": 4.8283483590971126e-05, + "loss": 0.3686, "step": 16350 }, { - "epoch": 0.15, - "learning_rate": 4.3083505990451314e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.82823650477618e-05, + "loss": 0.3678, "step": 16360 }, { - "epoch": 0.15, - "learning_rate": 4.307900189172147e-05, - "loss": 0.359, + "epoch": 0.04, + "learning_rate": 4.8281246504552475e-05, + "loss": 0.3658, "step": 16370 }, { - "epoch": 0.15, - "learning_rate": 4.307449779299162e-05, - "loss": 0.3657, + "epoch": 0.04, + "learning_rate": 4.8280127961343146e-05, + "loss": 0.3639, "step": 16380 }, { - "epoch": 0.15, - "learning_rate": 4.306999369426178e-05, - "loss": 0.3587, + "epoch": 0.04, + "learning_rate": 4.8279009418133824e-05, + "loss": 0.3632, "step": 16390 }, { - "epoch": 0.15, - "learning_rate": 4.306548959553194e-05, - "loss": 0.3602, + "epoch": 0.04, + "learning_rate": 4.82778908749245e-05, + "loss": 0.3666, "step": 16400 }, { - "epoch": 0.15, - "learning_rate": 4.3060985496802095e-05, - "loss": 0.361, + "epoch": 0.04, + "learning_rate": 4.827677233171517e-05, + "loss": 0.3674, "step": 16410 }, { - "epoch": 0.15, - "learning_rate": 4.3056481398072246e-05, - "loss": 0.3638, + "epoch": 0.04, + "learning_rate": 4.827565378850585e-05, + "loss": 0.3635, "step": 16420 }, { - "epoch": 0.15, - "learning_rate": 4.30519772993424e-05, - "loss": 0.3648, + "epoch": 0.04, + "learning_rate": 4.827453524529653e-05, + "loss": 0.3708, "step": 16430 }, { - "epoch": 0.15, - "learning_rate": 4.304747320061256e-05, - "loss": 0.3533, + "epoch": 0.04, + "learning_rate": 4.827341670208721e-05, + "loss": 0.3672, "step": 16440 }, { - "epoch": 0.15, - "learning_rate": 4.304296910188271e-05, - "loss": 0.3564, + "epoch": 0.04, + "learning_rate": 4.8272298158877885e-05, + "loss": 0.3619, "step": 16450 }, { - "epoch": 0.15, - "learning_rate": 4.3038465003152876e-05, - "loss": 0.3616, + "epoch": 0.04, + "learning_rate": 4.8271179615668556e-05, + "loss": 0.3634, "step": 16460 }, { - "epoch": 0.15, - "learning_rate": 4.3033960904423026e-05, - "loss": 0.3596, + "epoch": 0.04, + "learning_rate": 4.8270061072459234e-05, + "loss": 0.3681, "step": 16470 }, { - "epoch": 0.15, - "learning_rate": 4.302945680569318e-05, - "loss": 0.3579, + "epoch": 0.04, + "learning_rate": 4.8268942529249905e-05, + "loss": 0.3704, "step": 16480 }, { - "epoch": 0.15, - "learning_rate": 4.302495270696334e-05, - "loss": 0.3562, + "epoch": 0.04, + "learning_rate": 4.826782398604058e-05, + "loss": 0.3681, "step": 16490 }, { - "epoch": 0.15, - "learning_rate": 4.302044860823349e-05, - "loss": 0.3583, + "epoch": 0.04, + "learning_rate": 4.826670544283126e-05, + "loss": 0.3659, "step": 16500 }, { - "epoch": 0.15, - "learning_rate": 4.301594450950365e-05, - "loss": 0.3562, + "epoch": 0.04, + "learning_rate": 4.826558689962193e-05, + "loss": 0.3626, "step": 16510 }, { - "epoch": 0.15, - "learning_rate": 4.301144041077381e-05, - "loss": 0.3561, + "epoch": 0.04, + "learning_rate": 4.826446835641261e-05, + "loss": 0.368, "step": 16520 }, { - "epoch": 0.15, - "learning_rate": 4.300693631204396e-05, - "loss": 0.3529, + "epoch": 0.04, + "learning_rate": 4.826334981320328e-05, + "loss": 0.3723, "step": 16530 }, { - "epoch": 0.15, - "learning_rate": 4.300243221331412e-05, - "loss": 0.3531, + "epoch": 0.04, + "learning_rate": 4.8262231269993966e-05, + "loss": 0.365, "step": 16540 }, { - "epoch": 0.15, - "learning_rate": 4.299792811458427e-05, - "loss": 0.3581, + "epoch": 0.04, + "learning_rate": 4.826111272678464e-05, + "loss": 0.3695, "step": 16550 }, { - "epoch": 0.15, - "learning_rate": 4.299342401585443e-05, - "loss": 0.3566, + "epoch": 0.04, + "learning_rate": 4.8259994183575315e-05, + "loss": 0.3694, "step": 16560 }, { - "epoch": 0.15, - "learning_rate": 4.298891991712459e-05, - "loss": 0.3619, + "epoch": 0.04, + "learning_rate": 4.825887564036599e-05, + "loss": 0.3688, "step": 16570 }, { - "epoch": 0.15, - "learning_rate": 4.298441581839474e-05, - "loss": 0.3625, + "epoch": 0.04, + "learning_rate": 4.8257757097156664e-05, + "loss": 0.3685, "step": 16580 }, { - "epoch": 0.15, - "learning_rate": 4.2979911719664896e-05, - "loss": 0.3538, + "epoch": 0.04, + "learning_rate": 4.825663855394734e-05, + "loss": 0.3628, "step": 16590 }, { - "epoch": 0.15, - "learning_rate": 4.2975407620935054e-05, - "loss": 0.3573, + "epoch": 0.04, + "learning_rate": 4.825552001073801e-05, + "loss": 0.366, "step": 16600 }, { - "epoch": 0.15, - "learning_rate": 4.297090352220521e-05, - "loss": 0.3588, + "epoch": 0.04, + "learning_rate": 4.825440146752869e-05, + "loss": 0.3663, "step": 16610 }, { - "epoch": 0.15, - "learning_rate": 4.296639942347536e-05, - "loss": 0.3622, + "epoch": 0.04, + "learning_rate": 4.825328292431937e-05, + "loss": 0.3654, "step": 16620 }, { - "epoch": 0.15, - "learning_rate": 4.296189532474552e-05, - "loss": 0.3578, + "epoch": 0.04, + "learning_rate": 4.825216438111004e-05, + "loss": 0.3698, "step": 16630 }, { - "epoch": 0.15, - "learning_rate": 4.295739122601568e-05, - "loss": 0.3637, + "epoch": 0.04, + "learning_rate": 4.825104583790072e-05, + "loss": 0.3601, "step": 16640 }, { - "epoch": 0.15, - "learning_rate": 4.2952887127285834e-05, - "loss": 0.3577, + "epoch": 0.04, + "learning_rate": 4.8249927294691396e-05, + "loss": 0.3692, "step": 16650 }, { - "epoch": 0.15, - "learning_rate": 4.294838302855599e-05, - "loss": 0.3579, + "epoch": 0.04, + "learning_rate": 4.8248808751482074e-05, + "loss": 0.3648, "step": 16660 }, { - "epoch": 0.15, - "learning_rate": 4.294387892982614e-05, - "loss": 0.3601, + "epoch": 0.04, + "learning_rate": 4.824769020827275e-05, + "loss": 0.3672, "step": 16670 }, { - "epoch": 0.15, - "learning_rate": 4.29393748310963e-05, - "loss": 0.3551, + "epoch": 0.04, + "learning_rate": 4.824657166506342e-05, + "loss": 0.3689, "step": 16680 }, { - "epoch": 0.15, - "learning_rate": 4.293487073236646e-05, - "loss": 0.3608, + "epoch": 0.04, + "learning_rate": 4.82454531218541e-05, + "loss": 0.3631, "step": 16690 }, { - "epoch": 0.15, - "learning_rate": 4.293036663363661e-05, - "loss": 0.3514, + "epoch": 0.04, + "learning_rate": 4.824433457864477e-05, + "loss": 0.3675, "step": 16700 }, { - "epoch": 0.15, - "learning_rate": 4.2925862534906766e-05, - "loss": 0.3493, + "epoch": 0.04, + "learning_rate": 4.824321603543545e-05, + "loss": 0.3624, "step": 16710 }, { - "epoch": 0.15, - "learning_rate": 4.292135843617692e-05, - "loss": 0.3605, + "epoch": 0.04, + "learning_rate": 4.824209749222613e-05, + "loss": 0.3666, "step": 16720 }, { - "epoch": 0.15, - "learning_rate": 4.2916854337447074e-05, - "loss": 0.3541, + "epoch": 0.04, + "learning_rate": 4.82409789490168e-05, + "loss": 0.3636, "step": 16730 }, { - "epoch": 0.15, - "learning_rate": 4.291235023871724e-05, - "loss": 0.3551, + "epoch": 0.04, + "learning_rate": 4.823986040580748e-05, + "loss": 0.3568, "step": 16740 }, { - "epoch": 0.15, - "learning_rate": 4.290784613998739e-05, - "loss": 0.3555, + "epoch": 0.04, + "learning_rate": 4.8238741862598155e-05, + "loss": 0.3589, "step": 16750 }, { - "epoch": 0.15, - "learning_rate": 4.2903342041257546e-05, - "loss": 0.3547, + "epoch": 0.04, + "learning_rate": 4.823762331938883e-05, + "loss": 0.3676, "step": 16760 }, { - "epoch": 0.15, - "learning_rate": 4.2898837942527704e-05, - "loss": 0.3633, + "epoch": 0.04, + "learning_rate": 4.823650477617951e-05, + "loss": 0.3589, "step": 16770 }, { - "epoch": 0.15, - "learning_rate": 4.2894333843797855e-05, - "loss": 0.356, + "epoch": 0.04, + "learning_rate": 4.823538623297018e-05, + "loss": 0.363, "step": 16780 }, { - "epoch": 0.15, - "learning_rate": 4.288982974506802e-05, - "loss": 0.3537, + "epoch": 0.04, + "learning_rate": 4.823426768976086e-05, + "loss": 0.3606, "step": 16790 }, { - "epoch": 0.15, - "learning_rate": 4.288532564633817e-05, - "loss": 0.3549, + "epoch": 0.04, + "learning_rate": 4.823314914655153e-05, + "loss": 0.3619, "step": 16800 }, { - "epoch": 0.15, - "learning_rate": 4.288082154760833e-05, - "loss": 0.3536, + "epoch": 0.04, + "learning_rate": 4.823203060334221e-05, + "loss": 0.3745, "step": 16810 }, { - "epoch": 0.15, - "learning_rate": 4.2876317448878485e-05, - "loss": 0.3616, + "epoch": 0.04, + "learning_rate": 4.823091206013289e-05, + "loss": 0.3657, "step": 16820 }, { - "epoch": 0.15, - "learning_rate": 4.2871813350148635e-05, - "loss": 0.3591, + "epoch": 0.04, + "learning_rate": 4.822979351692356e-05, + "loss": 0.3673, "step": 16830 }, { - "epoch": 0.15, - "learning_rate": 4.286730925141879e-05, - "loss": 0.3602, + "epoch": 0.04, + "learning_rate": 4.8228674973714236e-05, + "loss": 0.3694, "step": 16840 }, { - "epoch": 0.15, - "learning_rate": 4.286280515268895e-05, - "loss": 0.3541, + "epoch": 0.04, + "learning_rate": 4.8227556430504914e-05, + "loss": 0.3649, "step": 16850 }, { - "epoch": 0.15, - "learning_rate": 4.285830105395911e-05, - "loss": 0.3476, + "epoch": 0.04, + "learning_rate": 4.822643788729559e-05, + "loss": 0.3653, "step": 16860 }, { - "epoch": 0.15, - "learning_rate": 4.285379695522926e-05, - "loss": 0.3537, + "epoch": 0.04, + "learning_rate": 4.822531934408626e-05, + "loss": 0.366, "step": 16870 }, { - "epoch": 0.15, - "learning_rate": 4.2849292856499416e-05, - "loss": 0.3562, + "epoch": 0.04, + "learning_rate": 4.822420080087694e-05, + "loss": 0.3611, "step": 16880 }, { - "epoch": 0.15, - "learning_rate": 4.2844788757769573e-05, - "loss": 0.3559, + "epoch": 0.04, + "learning_rate": 4.822308225766762e-05, + "loss": 0.3657, "step": 16890 }, { - "epoch": 0.15, - "learning_rate": 4.2840284659039724e-05, - "loss": 0.3565, + "epoch": 0.04, + "learning_rate": 4.822196371445829e-05, + "loss": 0.3627, "step": 16900 }, { - "epoch": 0.15, - "learning_rate": 4.283578056030988e-05, - "loss": 0.3485, + "epoch": 0.04, + "learning_rate": 4.822084517124897e-05, + "loss": 0.3679, "step": 16910 }, { - "epoch": 0.15, - "learning_rate": 4.283127646158004e-05, - "loss": 0.3528, + "epoch": 0.04, + "learning_rate": 4.821972662803964e-05, + "loss": 0.3593, "step": 16920 }, { - "epoch": 0.15, - "learning_rate": 4.2826772362850197e-05, - "loss": 0.3576, + "epoch": 0.04, + "learning_rate": 4.821860808483032e-05, + "loss": 0.3645, "step": 16930 }, { - "epoch": 0.15, - "learning_rate": 4.2822268264120354e-05, - "loss": 0.3571, + "epoch": 0.04, + "learning_rate": 4.8217489541620995e-05, + "loss": 0.3692, "step": 16940 }, { - "epoch": 0.15, - "learning_rate": 4.2817764165390505e-05, - "loss": 0.3599, + "epoch": 0.04, + "learning_rate": 4.821637099841167e-05, + "loss": 0.3614, "step": 16950 }, { - "epoch": 0.15, - "learning_rate": 4.281326006666066e-05, - "loss": 0.3554, + "epoch": 0.04, + "learning_rate": 4.821525245520235e-05, + "loss": 0.3698, "step": 16960 }, { - "epoch": 0.15, - "learning_rate": 4.280875596793082e-05, - "loss": 0.3571, + "epoch": 0.04, + "learning_rate": 4.821413391199302e-05, + "loss": 0.3618, "step": 16970 }, { - "epoch": 0.15, - "learning_rate": 4.280425186920097e-05, - "loss": 0.3595, + "epoch": 0.04, + "learning_rate": 4.82130153687837e-05, + "loss": 0.3598, "step": 16980 }, { - "epoch": 0.15, - "learning_rate": 4.2799747770471135e-05, - "loss": 0.3558, + "epoch": 0.04, + "learning_rate": 4.821189682557438e-05, + "loss": 0.3606, "step": 16990 }, { - "epoch": 0.15, - "learning_rate": 4.2795243671741285e-05, - "loss": 0.358, + "epoch": 0.04, + "learning_rate": 4.821077828236505e-05, + "loss": 0.3582, "step": 17000 }, { - "epoch": 0.15, - "learning_rate": 4.279073957301144e-05, - "loss": 0.3592, + "epoch": 0.04, + "learning_rate": 4.820965973915573e-05, + "loss": 0.3599, "step": 17010 }, { - "epoch": 0.15, - "learning_rate": 4.27862354742816e-05, - "loss": 0.3611, + "epoch": 0.04, + "learning_rate": 4.82085411959464e-05, + "loss": 0.3623, "step": 17020 }, { - "epoch": 0.15, - "learning_rate": 4.278173137555175e-05, - "loss": 0.3566, + "epoch": 0.04, + "learning_rate": 4.8207422652737076e-05, + "loss": 0.3549, "step": 17030 }, { - "epoch": 0.15, - "learning_rate": 4.277722727682191e-05, - "loss": 0.3543, + "epoch": 0.04, + "learning_rate": 4.8206304109527754e-05, + "loss": 0.3617, "step": 17040 }, { - "epoch": 0.15, - "learning_rate": 4.2772723178092066e-05, - "loss": 0.3492, + "epoch": 0.04, + "learning_rate": 4.8205185566318425e-05, + "loss": 0.361, "step": 17050 }, { - "epoch": 0.15, - "learning_rate": 4.2768219079362224e-05, - "loss": 0.35, + "epoch": 0.04, + "learning_rate": 4.82040670231091e-05, + "loss": 0.3626, "step": 17060 }, { - "epoch": 0.15, - "learning_rate": 4.276371498063238e-05, - "loss": 0.352, + "epoch": 0.04, + "learning_rate": 4.820294847989978e-05, + "loss": 0.3636, "step": 17070 }, { - "epoch": 0.15, - "learning_rate": 4.275921088190253e-05, - "loss": 0.3558, + "epoch": 0.04, + "learning_rate": 4.820182993669046e-05, + "loss": 0.367, "step": 17080 }, { - "epoch": 0.15, - "learning_rate": 4.275470678317269e-05, - "loss": 0.3529, + "epoch": 0.04, + "learning_rate": 4.820071139348114e-05, + "loss": 0.3629, "step": 17090 }, { - "epoch": 0.15, - "learning_rate": 4.275020268444285e-05, - "loss": 0.3526, + "epoch": 0.04, + "learning_rate": 4.819959285027181e-05, + "loss": 0.3604, "step": 17100 }, { - "epoch": 0.15, - "learning_rate": 4.2745698585713004e-05, - "loss": 0.3574, + "epoch": 0.04, + "learning_rate": 4.8198474307062486e-05, + "loss": 0.3596, "step": 17110 }, { - "epoch": 0.15, - "learning_rate": 4.2741194486983155e-05, - "loss": 0.3556, + "epoch": 0.04, + "learning_rate": 4.819735576385316e-05, + "loss": 0.3617, "step": 17120 }, { - "epoch": 0.15, - "learning_rate": 4.273669038825331e-05, - "loss": 0.3532, + "epoch": 0.04, + "learning_rate": 4.8196237220643835e-05, + "loss": 0.3633, "step": 17130 }, { - "epoch": 0.15, - "learning_rate": 4.273218628952347e-05, - "loss": 0.3551, + "epoch": 0.04, + "learning_rate": 4.819511867743451e-05, + "loss": 0.3613, "step": 17140 }, { - "epoch": 0.15, - "learning_rate": 4.272768219079362e-05, - "loss": 0.3486, + "epoch": 0.04, + "learning_rate": 4.8194000134225184e-05, + "loss": 0.3575, "step": 17150 }, { - "epoch": 0.15, - "learning_rate": 4.272317809206378e-05, - "loss": 0.351, + "epoch": 0.04, + "learning_rate": 4.819288159101586e-05, + "loss": 0.3611, "step": 17160 }, { - "epoch": 0.15, - "learning_rate": 4.2718673993333936e-05, - "loss": 0.3512, + "epoch": 0.04, + "learning_rate": 4.819176304780654e-05, + "loss": 0.358, "step": 17170 }, { - "epoch": 0.15, - "learning_rate": 4.2714169894604086e-05, - "loss": 0.3546, + "epoch": 0.04, + "learning_rate": 4.819064450459722e-05, + "loss": 0.3591, "step": 17180 }, { - "epoch": 0.15, - "learning_rate": 4.270966579587425e-05, - "loss": 0.3574, + "epoch": 0.04, + "learning_rate": 4.818952596138789e-05, + "loss": 0.3597, "step": 17190 }, { - "epoch": 0.15, - "learning_rate": 4.27051616971444e-05, - "loss": 0.3508, + "epoch": 0.04, + "learning_rate": 4.818840741817857e-05, + "loss": 0.3555, "step": 17200 }, { - "epoch": 0.15, - "learning_rate": 4.270065759841456e-05, - "loss": 0.356, + "epoch": 0.04, + "learning_rate": 4.8187288874969245e-05, + "loss": 0.3563, "step": 17210 }, { - "epoch": 0.15, - "learning_rate": 4.2696153499684716e-05, - "loss": 0.3444, + "epoch": 0.04, + "learning_rate": 4.8186170331759916e-05, + "loss": 0.3615, "step": 17220 }, { - "epoch": 0.15, - "learning_rate": 4.269164940095487e-05, - "loss": 0.3564, + "epoch": 0.04, + "learning_rate": 4.8185051788550594e-05, + "loss": 0.3579, "step": 17230 }, { - "epoch": 0.15, - "learning_rate": 4.268714530222503e-05, - "loss": 0.3607, + "epoch": 0.04, + "learning_rate": 4.8183933245341265e-05, + "loss": 0.3582, "step": 17240 }, { - "epoch": 0.15, - "learning_rate": 4.268264120349518e-05, - "loss": 0.3625, + "epoch": 0.04, + "learning_rate": 4.818281470213194e-05, + "loss": 0.3628, "step": 17250 }, { - "epoch": 0.15, - "learning_rate": 4.267813710476534e-05, - "loss": 0.3566, + "epoch": 0.04, + "learning_rate": 4.818169615892262e-05, + "loss": 0.3637, "step": 17260 }, { - "epoch": 0.15, - "learning_rate": 4.26736330060355e-05, - "loss": 0.3533, + "epoch": 0.04, + "learning_rate": 4.81805776157133e-05, + "loss": 0.3695, "step": 17270 }, { - "epoch": 0.15, - "learning_rate": 4.266912890730565e-05, - "loss": 0.3546, + "epoch": 0.04, + "learning_rate": 4.817945907250398e-05, + "loss": 0.3597, "step": 17280 }, { - "epoch": 0.15, - "learning_rate": 4.2664624808575805e-05, - "loss": 0.3535, + "epoch": 0.04, + "learning_rate": 4.817834052929465e-05, + "loss": 0.3592, "step": 17290 }, { - "epoch": 0.15, - "learning_rate": 4.266012070984596e-05, - "loss": 0.3532, + "epoch": 0.04, + "learning_rate": 4.8177221986085326e-05, + "loss": 0.3542, "step": 17300 }, { - "epoch": 0.15, - "learning_rate": 4.265561661111612e-05, - "loss": 0.349, + "epoch": 0.04, + "learning_rate": 4.8176103442876004e-05, + "loss": 0.3595, "step": 17310 }, { - "epoch": 0.15, - "learning_rate": 4.265111251238627e-05, - "loss": 0.352, + "epoch": 0.04, + "learning_rate": 4.8174984899666675e-05, + "loss": 0.3536, "step": 17320 }, { - "epoch": 0.15, - "learning_rate": 4.264660841365643e-05, - "loss": 0.3522, + "epoch": 0.04, + "learning_rate": 4.817386635645735e-05, + "loss": 0.3564, "step": 17330 }, { - "epoch": 0.15, - "learning_rate": 4.2642104314926586e-05, - "loss": 0.3479, + "epoch": 0.04, + "learning_rate": 4.8172747813248024e-05, + "loss": 0.3629, "step": 17340 }, { - "epoch": 0.15, - "learning_rate": 4.2637600216196744e-05, - "loss": 0.353, + "epoch": 0.04, + "learning_rate": 4.81716292700387e-05, + "loss": 0.36, "step": 17350 }, { - "epoch": 0.15, - "learning_rate": 4.2633096117466894e-05, - "loss": 0.3529, + "epoch": 0.04, + "learning_rate": 4.817051072682938e-05, + "loss": 0.3615, "step": 17360 }, { - "epoch": 0.16, - "learning_rate": 4.262859201873705e-05, - "loss": 0.3499, + "epoch": 0.04, + "learning_rate": 4.816939218362006e-05, + "loss": 0.3563, "step": 17370 }, { - "epoch": 0.16, - "learning_rate": 4.262408792000721e-05, - "loss": 0.3464, + "epoch": 0.04, + "learning_rate": 4.8168273640410736e-05, + "loss": 0.3555, "step": 17380 }, { - "epoch": 0.16, - "learning_rate": 4.261958382127737e-05, - "loss": 0.3499, + "epoch": 0.04, + "learning_rate": 4.816715509720141e-05, + "loss": 0.3586, "step": 17390 }, { - "epoch": 0.16, - "learning_rate": 4.261507972254752e-05, - "loss": 0.3528, + "epoch": 0.04, + "learning_rate": 4.8166036553992085e-05, + "loss": 0.3656, "step": 17400 }, { - "epoch": 0.16, - "learning_rate": 4.2610575623817675e-05, - "loss": 0.3546, + "epoch": 0.04, + "learning_rate": 4.816491801078276e-05, + "loss": 0.3565, "step": 17410 }, { - "epoch": 0.16, - "learning_rate": 4.260607152508783e-05, - "loss": 0.3502, + "epoch": 0.04, + "learning_rate": 4.8163799467573434e-05, + "loss": 0.3581, "step": 17420 }, { - "epoch": 0.16, - "learning_rate": 4.260156742635798e-05, - "loss": 0.3458, + "epoch": 0.04, + "learning_rate": 4.816268092436411e-05, + "loss": 0.3605, "step": 17430 }, { - "epoch": 0.16, - "learning_rate": 4.259706332762815e-05, - "loss": 0.3537, + "epoch": 0.04, + "learning_rate": 4.816156238115478e-05, + "loss": 0.3629, "step": 17440 }, { - "epoch": 0.16, - "learning_rate": 4.25925592288983e-05, - "loss": 0.355, + "epoch": 0.04, + "learning_rate": 4.816044383794546e-05, + "loss": 0.3564, "step": 17450 }, { - "epoch": 0.16, - "learning_rate": 4.2588055130168456e-05, - "loss": 0.3547, + "epoch": 0.04, + "learning_rate": 4.815932529473614e-05, + "loss": 0.361, "step": 17460 }, { - "epoch": 0.16, - "learning_rate": 4.258355103143861e-05, - "loss": 0.3454, + "epoch": 0.04, + "learning_rate": 4.815820675152681e-05, + "loss": 0.3583, "step": 17470 }, { - "epoch": 0.16, - "learning_rate": 4.2579046932708764e-05, - "loss": 0.3506, + "epoch": 0.04, + "learning_rate": 4.815708820831749e-05, + "loss": 0.3547, "step": 17480 }, { - "epoch": 0.16, - "learning_rate": 4.257454283397893e-05, + "epoch": 0.04, + "learning_rate": 4.8155969665108166e-05, "loss": 0.3536, "step": 17490 }, { - "epoch": 0.16, - "learning_rate": 4.257003873524908e-05, - "loss": 0.3516, + "epoch": 0.04, + "learning_rate": 4.8154851121898844e-05, + "loss": 0.3548, "step": 17500 }, { - "epoch": 0.16, - "learning_rate": 4.2565534636519236e-05, - "loss": 0.3497, + "epoch": 0.04, + "learning_rate": 4.8153732578689515e-05, + "loss": 0.3592, "step": 17510 }, { - "epoch": 0.16, - "learning_rate": 4.2561030537789394e-05, - "loss": 0.3481, + "epoch": 0.04, + "learning_rate": 4.815261403548019e-05, + "loss": 0.36, "step": 17520 }, { - "epoch": 0.16, - "learning_rate": 4.2556526439059544e-05, - "loss": 0.3528, + "epoch": 0.04, + "learning_rate": 4.815149549227087e-05, + "loss": 0.36, "step": 17530 }, { - "epoch": 0.16, - "learning_rate": 4.25520223403297e-05, - "loss": 0.346, + "epoch": 0.04, + "learning_rate": 4.815037694906154e-05, + "loss": 0.357, "step": 17540 }, { - "epoch": 0.16, - "learning_rate": 4.254751824159986e-05, - "loss": 0.3546, + "epoch": 0.04, + "learning_rate": 4.814925840585222e-05, + "loss": 0.3554, "step": 17550 }, { - "epoch": 0.16, - "learning_rate": 4.254301414287001e-05, - "loss": 0.3465, + "epoch": 0.04, + "learning_rate": 4.814813986264289e-05, + "loss": 0.3545, "step": 17560 }, { - "epoch": 0.16, - "learning_rate": 4.253851004414017e-05, - "loss": 0.3476, + "epoch": 0.04, + "learning_rate": 4.814702131943357e-05, + "loss": 0.3602, "step": 17570 }, { - "epoch": 0.16, - "learning_rate": 4.2534005945410325e-05, - "loss": 0.3551, + "epoch": 0.04, + "learning_rate": 4.814590277622425e-05, + "loss": 0.3599, "step": 17580 }, { - "epoch": 0.16, - "learning_rate": 4.252950184668048e-05, - "loss": 0.3521, + "epoch": 0.04, + "learning_rate": 4.8144784233014925e-05, + "loss": 0.361, "step": 17590 }, { - "epoch": 0.16, - "learning_rate": 4.252499774795063e-05, - "loss": 0.3497, + "epoch": 0.04, + "learning_rate": 4.81436656898056e-05, + "loss": 0.3645, "step": 17600 }, { - "epoch": 0.16, - "learning_rate": 4.252049364922079e-05, - "loss": 0.3491, + "epoch": 0.04, + "learning_rate": 4.8142547146596274e-05, + "loss": 0.3624, "step": 17610 }, { - "epoch": 0.16, - "learning_rate": 4.251598955049095e-05, - "loss": 0.3463, + "epoch": 0.04, + "learning_rate": 4.814142860338695e-05, + "loss": 0.3656, "step": 17620 }, { - "epoch": 0.16, - "learning_rate": 4.2511485451761106e-05, - "loss": 0.3498, + "epoch": 0.04, + "learning_rate": 4.814031006017763e-05, + "loss": 0.3579, "step": 17630 }, { - "epoch": 0.16, - "learning_rate": 4.250698135303126e-05, - "loss": 0.3523, + "epoch": 0.04, + "learning_rate": 4.81391915169683e-05, + "loss": 0.3548, "step": 17640 }, { - "epoch": 0.16, - "learning_rate": 4.2502477254301414e-05, - "loss": 0.3508, + "epoch": 0.04, + "learning_rate": 4.813807297375898e-05, + "loss": 0.3621, "step": 17650 }, { - "epoch": 0.16, - "learning_rate": 4.249797315557157e-05, - "loss": 0.3499, + "epoch": 0.04, + "learning_rate": 4.813695443054965e-05, + "loss": 0.3608, "step": 17660 }, { - "epoch": 0.16, - "learning_rate": 4.249346905684173e-05, - "loss": 0.3488, + "epoch": 0.04, + "learning_rate": 4.813583588734033e-05, + "loss": 0.3638, "step": 17670 }, { - "epoch": 0.16, - "learning_rate": 4.248896495811188e-05, - "loss": 0.3502, + "epoch": 0.04, + "learning_rate": 4.8134717344131006e-05, + "loss": 0.3624, "step": 17680 }, { - "epoch": 0.16, - "learning_rate": 4.2484460859382044e-05, - "loss": 0.3427, + "epoch": 0.04, + "learning_rate": 4.8133598800921684e-05, + "loss": 0.3571, "step": 17690 }, { - "epoch": 0.16, - "learning_rate": 4.2479956760652195e-05, - "loss": 0.352, + "epoch": 0.04, + "learning_rate": 4.813248025771236e-05, + "loss": 0.3585, "step": 17700 }, { - "epoch": 0.16, - "learning_rate": 4.247545266192235e-05, - "loss": 0.3532, + "epoch": 0.04, + "learning_rate": 4.813136171450303e-05, + "loss": 0.3599, "step": 17710 }, { - "epoch": 0.16, - "learning_rate": 4.247094856319251e-05, - "loss": 0.3536, + "epoch": 0.04, + "learning_rate": 4.813024317129371e-05, + "loss": 0.3521, "step": 17720 }, { - "epoch": 0.16, - "learning_rate": 4.246644446446266e-05, - "loss": 0.3445, + "epoch": 0.04, + "learning_rate": 4.812912462808439e-05, + "loss": 0.3619, "step": 17730 }, { - "epoch": 0.16, - "learning_rate": 4.246194036573282e-05, - "loss": 0.3509, + "epoch": 0.04, + "learning_rate": 4.812800608487506e-05, + "loss": 0.3572, "step": 17740 }, { - "epoch": 0.16, - "learning_rate": 4.2457436267002975e-05, - "loss": 0.3493, + "epoch": 0.04, + "learning_rate": 4.812688754166574e-05, + "loss": 0.3572, "step": 17750 }, { - "epoch": 0.16, - "learning_rate": 4.245293216827313e-05, - "loss": 0.3479, + "epoch": 0.04, + "learning_rate": 4.812576899845641e-05, + "loss": 0.3583, "step": 17760 }, { - "epoch": 0.16, - "learning_rate": 4.244842806954329e-05, - "loss": 0.3554, + "epoch": 0.04, + "learning_rate": 4.812465045524709e-05, + "loss": 0.3589, "step": 17770 }, { - "epoch": 0.16, - "learning_rate": 4.244392397081344e-05, - "loss": 0.3456, + "epoch": 0.04, + "learning_rate": 4.8123531912037765e-05, + "loss": 0.3582, "step": 17780 }, { - "epoch": 0.16, - "learning_rate": 4.24394198720836e-05, - "loss": 0.3501, + "epoch": 0.04, + "learning_rate": 4.812241336882844e-05, + "loss": 0.3571, "step": 17790 }, { - "epoch": 0.16, - "learning_rate": 4.2434915773353756e-05, - "loss": 0.3466, + "epoch": 0.04, + "learning_rate": 4.812129482561912e-05, + "loss": 0.3501, "step": 17800 }, { - "epoch": 0.16, - "learning_rate": 4.243041167462391e-05, - "loss": 0.3477, + "epoch": 0.04, + "learning_rate": 4.812017628240979e-05, + "loss": 0.3592, "step": 17810 }, { - "epoch": 0.16, - "learning_rate": 4.2425907575894064e-05, - "loss": 0.3534, + "epoch": 0.04, + "learning_rate": 4.811905773920047e-05, + "loss": 0.3554, "step": 17820 }, { - "epoch": 0.16, - "learning_rate": 4.242140347716422e-05, - "loss": 0.3512, + "epoch": 0.04, + "learning_rate": 4.811793919599114e-05, + "loss": 0.3502, "step": 17830 }, { - "epoch": 0.16, - "learning_rate": 4.241689937843438e-05, - "loss": 0.3498, + "epoch": 0.04, + "learning_rate": 4.811682065278182e-05, + "loss": 0.3565, "step": 17840 }, { - "epoch": 0.16, - "learning_rate": 4.241239527970453e-05, - "loss": 0.3527, + "epoch": 0.04, + "learning_rate": 4.81157021095725e-05, + "loss": 0.3526, "step": 17850 }, { - "epoch": 0.16, - "learning_rate": 4.240789118097469e-05, - "loss": 0.3481, + "epoch": 0.04, + "learning_rate": 4.811458356636317e-05, + "loss": 0.3589, "step": 17860 }, { - "epoch": 0.16, - "learning_rate": 4.2403387082244845e-05, - "loss": 0.343, + "epoch": 0.04, + "learning_rate": 4.8113465023153846e-05, + "loss": 0.3592, "step": 17870 }, { - "epoch": 0.16, - "learning_rate": 4.2398882983514996e-05, - "loss": 0.3509, + "epoch": 0.04, + "learning_rate": 4.811234647994452e-05, + "loss": 0.357, "step": 17880 }, { - "epoch": 0.16, - "learning_rate": 4.239437888478516e-05, - "loss": 0.3467, + "epoch": 0.04, + "learning_rate": 4.8111227936735195e-05, + "loss": 0.3608, "step": 17890 }, { - "epoch": 0.16, - "learning_rate": 4.238987478605531e-05, - "loss": 0.3457, + "epoch": 0.04, + "learning_rate": 4.811010939352587e-05, + "loss": 0.3581, "step": 17900 }, { - "epoch": 0.16, - "learning_rate": 4.238537068732547e-05, - "loss": 0.3491, + "epoch": 0.04, + "learning_rate": 4.810899085031655e-05, + "loss": 0.3625, "step": 17910 }, { - "epoch": 0.16, - "learning_rate": 4.2380866588595626e-05, - "loss": 0.3453, + "epoch": 0.04, + "learning_rate": 4.810787230710723e-05, + "loss": 0.3594, "step": 17920 }, { - "epoch": 0.16, - "learning_rate": 4.2376362489865776e-05, - "loss": 0.3426, + "epoch": 0.04, + "learning_rate": 4.81067537638979e-05, + "loss": 0.3592, "step": 17930 }, { - "epoch": 0.16, - "learning_rate": 4.237185839113594e-05, - "loss": 0.3409, + "epoch": 0.04, + "learning_rate": 4.810563522068858e-05, + "loss": 0.3622, "step": 17940 }, { - "epoch": 0.16, - "learning_rate": 4.236735429240609e-05, - "loss": 0.3478, + "epoch": 0.04, + "learning_rate": 4.8104516677479256e-05, + "loss": 0.3579, "step": 17950 }, { - "epoch": 0.16, - "learning_rate": 4.236285019367625e-05, - "loss": 0.3462, + "epoch": 0.04, + "learning_rate": 4.810339813426993e-05, + "loss": 0.3559, "step": 17960 }, { - "epoch": 0.16, - "learning_rate": 4.2358346094946406e-05, - "loss": 0.3543, + "epoch": 0.04, + "learning_rate": 4.8102279591060605e-05, + "loss": 0.356, "step": 17970 }, { - "epoch": 0.16, - "learning_rate": 4.235384199621656e-05, - "loss": 0.3456, + "epoch": 0.04, + "learning_rate": 4.8101161047851276e-05, + "loss": 0.3557, "step": 17980 }, { - "epoch": 0.16, - "learning_rate": 4.2349337897486715e-05, - "loss": 0.3535, + "epoch": 0.04, + "learning_rate": 4.8100042504641954e-05, + "loss": 0.3519, "step": 17990 }, { - "epoch": 0.16, - "learning_rate": 4.234483379875687e-05, - "loss": 0.3459, + "epoch": 0.04, + "learning_rate": 4.809892396143263e-05, + "loss": 0.3568, "step": 18000 }, { - "epoch": 0.16, - "learning_rate": 4.234032970002702e-05, - "loss": 0.3531, + "epoch": 0.04, + "learning_rate": 4.809780541822331e-05, + "loss": 0.3623, "step": 18010 }, { - "epoch": 0.16, - "learning_rate": 4.233582560129718e-05, - "loss": 0.3519, + "epoch": 0.04, + "learning_rate": 4.809668687501399e-05, + "loss": 0.3581, "step": 18020 }, { - "epoch": 0.16, - "learning_rate": 4.233132150256734e-05, - "loss": 0.3497, + "epoch": 0.04, + "learning_rate": 4.809556833180466e-05, + "loss": 0.3545, "step": 18030 }, { - "epoch": 0.16, - "learning_rate": 4.2326817403837495e-05, - "loss": 0.3478, + "epoch": 0.04, + "learning_rate": 4.809444978859534e-05, + "loss": 0.351, "step": 18040 }, { - "epoch": 0.16, - "learning_rate": 4.232231330510765e-05, - "loss": 0.3473, + "epoch": 0.04, + "learning_rate": 4.8093331245386015e-05, + "loss": 0.3569, "step": 18050 }, { - "epoch": 0.16, - "learning_rate": 4.2317809206377803e-05, - "loss": 0.3449, + "epoch": 0.04, + "learning_rate": 4.8092212702176686e-05, + "loss": 0.3588, "step": 18060 }, { - "epoch": 0.16, - "learning_rate": 4.231330510764796e-05, - "loss": 0.3544, + "epoch": 0.04, + "learning_rate": 4.8091094158967364e-05, + "loss": 0.3563, "step": 18070 }, { - "epoch": 0.16, - "learning_rate": 4.230880100891812e-05, - "loss": 0.346, + "epoch": 0.04, + "learning_rate": 4.8089975615758035e-05, + "loss": 0.3556, "step": 18080 }, { - "epoch": 0.16, - "learning_rate": 4.2304296910188276e-05, - "loss": 0.3526, + "epoch": 0.04, + "learning_rate": 4.808885707254871e-05, + "loss": 0.3521, "step": 18090 }, { - "epoch": 0.16, - "learning_rate": 4.229979281145843e-05, - "loss": 0.3572, + "epoch": 0.04, + "learning_rate": 4.808773852933939e-05, + "loss": 0.3594, "step": 18100 }, { - "epoch": 0.16, - "learning_rate": 4.2295288712728584e-05, - "loss": 0.3499, + "epoch": 0.04, + "learning_rate": 4.808661998613007e-05, + "loss": 0.3515, "step": 18110 }, { - "epoch": 0.16, - "learning_rate": 4.229078461399874e-05, - "loss": 0.3527, + "epoch": 0.04, + "learning_rate": 4.8085501442920747e-05, + "loss": 0.3574, "step": 18120 }, { - "epoch": 0.16, - "learning_rate": 4.228628051526889e-05, - "loss": 0.353, + "epoch": 0.04, + "learning_rate": 4.808438289971142e-05, + "loss": 0.358, "step": 18130 }, { - "epoch": 0.16, - "learning_rate": 4.228177641653906e-05, - "loss": 0.3465, + "epoch": 0.04, + "learning_rate": 4.8083264356502096e-05, + "loss": 0.3577, "step": 18140 }, { - "epoch": 0.16, - "learning_rate": 4.227727231780921e-05, - "loss": 0.3451, + "epoch": 0.04, + "learning_rate": 4.808214581329277e-05, + "loss": 0.3545, "step": 18150 }, { - "epoch": 0.16, - "learning_rate": 4.2272768219079365e-05, - "loss": 0.3461, + "epoch": 0.04, + "learning_rate": 4.8081027270083445e-05, + "loss": 0.3558, "step": 18160 }, { - "epoch": 0.16, - "learning_rate": 4.226826412034952e-05, - "loss": 0.3461, + "epoch": 0.04, + "learning_rate": 4.807990872687412e-05, + "loss": 0.3608, "step": 18170 }, { - "epoch": 0.16, - "learning_rate": 4.226376002161967e-05, - "loss": 0.3388, + "epoch": 0.04, + "learning_rate": 4.8078790183664794e-05, + "loss": 0.3584, "step": 18180 }, { - "epoch": 0.16, - "learning_rate": 4.225970633276282e-05, - "loss": 0.3459, + "epoch": 0.04, + "learning_rate": 4.807767164045547e-05, + "loss": 0.3555, "step": 18190 }, { - "epoch": 0.16, - "learning_rate": 4.225520223403297e-05, - "loss": 0.3471, + "epoch": 0.04, + "learning_rate": 4.807655309724615e-05, + "loss": 0.3492, "step": 18200 }, { - "epoch": 0.16, - "learning_rate": 4.225069813530313e-05, - "loss": 0.3539, + "epoch": 0.04, + "learning_rate": 4.807543455403683e-05, + "loss": 0.3518, "step": 18210 }, { - "epoch": 0.16, - "learning_rate": 4.224619403657328e-05, - "loss": 0.3486, + "epoch": 0.04, + "learning_rate": 4.8074316010827506e-05, + "loss": 0.3583, "step": 18220 }, { - "epoch": 0.16, - "learning_rate": 4.224168993784344e-05, - "loss": 0.3535, + "epoch": 0.04, + "learning_rate": 4.807319746761818e-05, + "loss": 0.3553, "step": 18230 }, { - "epoch": 0.16, - "learning_rate": 4.22371858391136e-05, - "loss": 0.3473, + "epoch": 0.04, + "learning_rate": 4.8072078924408855e-05, + "loss": 0.3555, "step": 18240 }, { - "epoch": 0.16, - "learning_rate": 4.223268174038375e-05, - "loss": 0.3449, + "epoch": 0.04, + "learning_rate": 4.8070960381199526e-05, + "loss": 0.3501, "step": 18250 }, { - "epoch": 0.16, - "learning_rate": 4.2228177641653906e-05, - "loss": 0.3474, + "epoch": 0.04, + "learning_rate": 4.8069841837990204e-05, + "loss": 0.3581, "step": 18260 }, { - "epoch": 0.16, - "learning_rate": 4.222367354292406e-05, - "loss": 0.3438, + "epoch": 0.04, + "learning_rate": 4.806883514910181e-05, + "loss": 0.3514, "step": 18270 }, { - "epoch": 0.16, - "learning_rate": 4.221916944419422e-05, - "loss": 0.3456, + "epoch": 0.04, + "learning_rate": 4.806771660589249e-05, + "loss": 0.3507, "step": 18280 }, { - "epoch": 0.16, - "learning_rate": 4.221466534546438e-05, - "loss": 0.3511, + "epoch": 0.04, + "learning_rate": 4.806659806268317e-05, + "loss": 0.3499, "step": 18290 }, { - "epoch": 0.16, - "learning_rate": 4.221016124673453e-05, - "loss": 0.3421, + "epoch": 0.04, + "learning_rate": 4.806547951947384e-05, + "loss": 0.3605, "step": 18300 }, { - "epoch": 0.16, - "learning_rate": 4.2205657148004686e-05, - "loss": 0.3423, + "epoch": 0.04, + "learning_rate": 4.806436097626452e-05, + "loss": 0.3522, "step": 18310 }, { - "epoch": 0.16, - "learning_rate": 4.2201153049274844e-05, - "loss": 0.3488, + "epoch": 0.04, + "learning_rate": 4.806324243305519e-05, + "loss": 0.3541, "step": 18320 }, { - "epoch": 0.16, - "learning_rate": 4.2196648950545e-05, - "loss": 0.3443, + "epoch": 0.04, + "learning_rate": 4.8062123889845866e-05, + "loss": 0.3529, "step": 18330 }, { - "epoch": 0.16, - "learning_rate": 4.219214485181515e-05, - "loss": 0.3533, + "epoch": 0.04, + "learning_rate": 4.8061005346636544e-05, + "loss": 0.3568, "step": 18340 }, { - "epoch": 0.16, - "learning_rate": 4.218764075308531e-05, - "loss": 0.3534, + "epoch": 0.04, + "learning_rate": 4.8059886803427216e-05, + "loss": 0.3571, "step": 18350 }, { - "epoch": 0.16, - "learning_rate": 4.218313665435547e-05, - "loss": 0.3464, + "epoch": 0.04, + "learning_rate": 4.8058768260217893e-05, + "loss": 0.3547, "step": 18360 }, { - "epoch": 0.16, - "learning_rate": 4.217863255562562e-05, - "loss": 0.3519, + "epoch": 0.04, + "learning_rate": 4.805764971700857e-05, + "loss": 0.3486, "step": 18370 }, { - "epoch": 0.16, - "learning_rate": 4.2174128456895775e-05, - "loss": 0.3433, + "epoch": 0.04, + "learning_rate": 4.805653117379925e-05, + "loss": 0.3484, "step": 18380 }, { - "epoch": 0.16, - "learning_rate": 4.216962435816593e-05, - "loss": 0.3522, + "epoch": 0.04, + "learning_rate": 4.805541263058993e-05, + "loss": 0.3597, "step": 18390 }, { - "epoch": 0.16, - "learning_rate": 4.2165120259436084e-05, - "loss": 0.3488, + "epoch": 0.04, + "learning_rate": 4.80542940873806e-05, + "loss": 0.3495, "step": 18400 }, { - "epoch": 0.16, - "learning_rate": 4.216061616070625e-05, - "loss": 0.3439, + "epoch": 0.04, + "learning_rate": 4.8053175544171276e-05, + "loss": 0.356, "step": 18410 }, { - "epoch": 0.16, - "learning_rate": 4.21561120619764e-05, - "loss": 0.3445, + "epoch": 0.04, + "learning_rate": 4.805205700096195e-05, + "loss": 0.3578, "step": 18420 }, { - "epoch": 0.16, - "learning_rate": 4.2151607963246556e-05, - "loss": 0.3459, + "epoch": 0.04, + "learning_rate": 4.8050938457752625e-05, + "loss": 0.3529, "step": 18430 }, { - "epoch": 0.16, - "learning_rate": 4.2147103864516713e-05, - "loss": 0.3392, + "epoch": 0.04, + "learning_rate": 4.80498199145433e-05, + "loss": 0.3568, "step": 18440 }, { - "epoch": 0.16, - "learning_rate": 4.2142599765786864e-05, - "loss": 0.3451, + "epoch": 0.04, + "learning_rate": 4.8048701371333975e-05, + "loss": 0.3524, "step": 18450 }, { - "epoch": 0.16, - "learning_rate": 4.213809566705703e-05, - "loss": 0.3451, + "epoch": 0.04, + "learning_rate": 4.804758282812465e-05, + "loss": 0.3493, "step": 18460 }, { - "epoch": 0.16, - "learning_rate": 4.213359156832718e-05, - "loss": 0.3495, + "epoch": 0.04, + "learning_rate": 4.8046464284915324e-05, + "loss": 0.3542, "step": 18470 }, { - "epoch": 0.16, - "learning_rate": 4.212908746959734e-05, - "loss": 0.3505, + "epoch": 0.04, + "learning_rate": 4.8045345741706e-05, + "loss": 0.3583, "step": 18480 }, { - "epoch": 0.17, - "learning_rate": 4.2124583370867494e-05, - "loss": 0.3428, + "epoch": 0.04, + "learning_rate": 4.8044227198496686e-05, + "loss": 0.3507, "step": 18490 }, { - "epoch": 0.17, - "learning_rate": 4.2120079272137645e-05, - "loss": 0.3421, + "epoch": 0.04, + "learning_rate": 4.804310865528736e-05, + "loss": 0.3535, "step": 18500 }, { - "epoch": 0.17, - "learning_rate": 4.21155751734078e-05, - "loss": 0.3459, + "epoch": 0.04, + "learning_rate": 4.8041990112078035e-05, + "loss": 0.35, "step": 18510 }, { - "epoch": 0.17, - "learning_rate": 4.211107107467796e-05, - "loss": 0.3419, + "epoch": 0.04, + "learning_rate": 4.8040871568868706e-05, + "loss": 0.3526, "step": 18520 }, { - "epoch": 0.17, - "learning_rate": 4.210656697594812e-05, - "loss": 0.3473, + "epoch": 0.04, + "learning_rate": 4.8039753025659384e-05, + "loss": 0.3542, "step": 18530 }, { - "epoch": 0.17, - "learning_rate": 4.210206287721827e-05, - "loss": 0.3486, + "epoch": 0.04, + "learning_rate": 4.8038634482450056e-05, + "loss": 0.357, "step": 18540 }, { - "epoch": 0.17, - "learning_rate": 4.2097558778488426e-05, - "loss": 0.3456, + "epoch": 0.04, + "learning_rate": 4.8037515939240733e-05, + "loss": 0.3508, "step": 18550 }, { - "epoch": 0.17, - "learning_rate": 4.209305467975858e-05, + "epoch": 0.04, + "learning_rate": 4.803639739603141e-05, "loss": 0.3498, "step": 18560 }, { - "epoch": 0.17, - "learning_rate": 4.208855058102874e-05, - "loss": 0.3464, + "epoch": 0.04, + "learning_rate": 4.803527885282208e-05, + "loss": 0.3534, "step": 18570 }, { - "epoch": 0.17, - "learning_rate": 4.208404648229889e-05, - "loss": 0.3515, + "epoch": 0.04, + "learning_rate": 4.803416030961276e-05, + "loss": 0.3539, "step": 18580 }, { - "epoch": 0.17, - "learning_rate": 4.207954238356905e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.803304176640344e-05, + "loss": 0.3595, "step": 18590 }, { - "epoch": 0.17, - "learning_rate": 4.2075038284839206e-05, - "loss": 0.3448, + "epoch": 0.04, + "learning_rate": 4.8031923223194116e-05, + "loss": 0.3504, "step": 18600 }, { - "epoch": 0.17, - "learning_rate": 4.2070534186109364e-05, - "loss": 0.3483, + "epoch": 0.04, + "learning_rate": 4.8030804679984794e-05, + "loss": 0.3492, "step": 18610 }, { - "epoch": 0.17, - "learning_rate": 4.2066030087379514e-05, - "loss": 0.345, + "epoch": 0.04, + "learning_rate": 4.8029686136775465e-05, + "loss": 0.3482, "step": 18620 }, { - "epoch": 0.17, - "learning_rate": 4.206152598864967e-05, - "loss": 0.3406, + "epoch": 0.04, + "learning_rate": 4.802856759356614e-05, + "loss": 0.3485, "step": 18630 }, { - "epoch": 0.17, - "learning_rate": 4.205702188991983e-05, - "loss": 0.3412, + "epoch": 0.04, + "learning_rate": 4.8027449050356814e-05, + "loss": 0.3558, "step": 18640 }, { - "epoch": 0.17, - "learning_rate": 4.205251779118998e-05, - "loss": 0.3438, + "epoch": 0.04, + "learning_rate": 4.802633050714749e-05, + "loss": 0.3486, "step": 18650 }, { - "epoch": 0.17, - "learning_rate": 4.2048013692460144e-05, - "loss": 0.3501, + "epoch": 0.04, + "learning_rate": 4.802521196393817e-05, + "loss": 0.3524, "step": 18660 }, { - "epoch": 0.17, - "learning_rate": 4.2043509593730295e-05, - "loss": 0.3467, + "epoch": 0.04, + "learning_rate": 4.802409342072884e-05, + "loss": 0.3498, "step": 18670 }, { - "epoch": 0.17, - "learning_rate": 4.203900549500045e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.802297487751952e-05, + "loss": 0.349, "step": 18680 }, { - "epoch": 0.17, - "learning_rate": 4.203450139627061e-05, - "loss": 0.347, + "epoch": 0.04, + "learning_rate": 4.80218563343102e-05, + "loss": 0.3447, "step": 18690 }, { - "epoch": 0.17, - "learning_rate": 4.202999729754076e-05, - "loss": 0.3384, + "epoch": 0.04, + "learning_rate": 4.8020737791100875e-05, + "loss": 0.3475, "step": 18700 }, { - "epoch": 0.17, - "learning_rate": 4.2025493198810925e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.801961924789155e-05, + "loss": 0.3503, "step": 18710 }, { - "epoch": 0.17, - "learning_rate": 4.2020989100081076e-05, - "loss": 0.3451, + "epoch": 0.04, + "learning_rate": 4.8018500704682224e-05, + "loss": 0.3475, "step": 18720 }, { - "epoch": 0.17, - "learning_rate": 4.201648500135123e-05, + "epoch": 0.04, + "learning_rate": 4.80173821614729e-05, "loss": 0.3497, "step": 18730 }, { - "epoch": 0.17, - "learning_rate": 4.201198090262139e-05, - "loss": 0.345, + "epoch": 0.04, + "learning_rate": 4.8016263618263573e-05, + "loss": 0.352, "step": 18740 }, { - "epoch": 0.17, - "learning_rate": 4.200747680389154e-05, - "loss": 0.3435, + "epoch": 0.04, + "learning_rate": 4.801514507505425e-05, + "loss": 0.3453, "step": 18750 }, { - "epoch": 0.17, - "learning_rate": 4.20029727051617e-05, - "loss": 0.3491, + "epoch": 0.04, + "learning_rate": 4.801402653184493e-05, + "loss": 0.3506, "step": 18760 }, { - "epoch": 0.17, - "learning_rate": 4.1998468606431857e-05, - "loss": 0.3386, + "epoch": 0.04, + "learning_rate": 4.80129079886356e-05, + "loss": 0.3499, "step": 18770 }, { - "epoch": 0.17, - "learning_rate": 4.199396450770201e-05, - "loss": 0.3443, + "epoch": 0.04, + "learning_rate": 4.801178944542628e-05, + "loss": 0.3533, "step": 18780 }, { - "epoch": 0.17, - "learning_rate": 4.1989460408972165e-05, - "loss": 0.3468, + "epoch": 0.04, + "learning_rate": 4.8010670902216956e-05, + "loss": 0.3527, "step": 18790 }, { - "epoch": 0.17, - "learning_rate": 4.198495631024232e-05, - "loss": 0.3455, + "epoch": 0.04, + "learning_rate": 4.8009552359007634e-05, + "loss": 0.3523, "step": 18800 }, { - "epoch": 0.17, - "learning_rate": 4.198045221151248e-05, - "loss": 0.3462, + "epoch": 0.04, + "learning_rate": 4.800843381579831e-05, + "loss": 0.344, "step": 18810 }, { - "epoch": 0.17, - "learning_rate": 4.197594811278263e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.800731527258898e-05, + "loss": 0.351, "step": 18820 }, { - "epoch": 0.17, - "learning_rate": 4.197144401405279e-05, - "loss": 0.3493, + "epoch": 0.04, + "learning_rate": 4.800619672937966e-05, + "loss": 0.3531, "step": 18830 }, { - "epoch": 0.17, - "learning_rate": 4.1966939915322945e-05, - "loss": 0.3464, + "epoch": 0.04, + "learning_rate": 4.800507818617033e-05, + "loss": 0.3539, "step": 18840 }, { - "epoch": 0.17, - "learning_rate": 4.19624358165931e-05, - "loss": 0.3433, + "epoch": 0.04, + "learning_rate": 4.800395964296101e-05, + "loss": 0.3534, "step": 18850 }, { - "epoch": 0.17, - "learning_rate": 4.195793171786326e-05, - "loss": 0.3377, + "epoch": 0.04, + "learning_rate": 4.800284109975168e-05, + "loss": 0.3475, "step": 18860 }, { - "epoch": 0.17, - "learning_rate": 4.195342761913341e-05, - "loss": 0.3458, + "epoch": 0.04, + "learning_rate": 4.800172255654236e-05, + "loss": 0.3542, "step": 18870 }, { - "epoch": 0.17, - "learning_rate": 4.194892352040357e-05, - "loss": 0.3449, + "epoch": 0.04, + "learning_rate": 4.800060401333304e-05, + "loss": 0.353, "step": 18880 }, { - "epoch": 0.17, - "learning_rate": 4.1944419421673726e-05, - "loss": 0.3462, + "epoch": 0.04, + "learning_rate": 4.799948547012371e-05, + "loss": 0.3492, "step": 18890 }, { - "epoch": 0.17, - "learning_rate": 4.193991532294388e-05, - "loss": 0.3382, + "epoch": 0.04, + "learning_rate": 4.799836692691439e-05, + "loss": 0.3494, "step": 18900 }, { - "epoch": 0.17, - "learning_rate": 4.193541122421404e-05, - "loss": 0.3397, + "epoch": 0.04, + "learning_rate": 4.7997248383705064e-05, + "loss": 0.3504, "step": 18910 }, { - "epoch": 0.17, - "learning_rate": 4.193090712548419e-05, - "loss": 0.3355, + "epoch": 0.04, + "learning_rate": 4.799612984049574e-05, + "loss": 0.3518, "step": 18920 }, { - "epoch": 0.17, - "learning_rate": 4.192640302675435e-05, - "loss": 0.3346, + "epoch": 0.04, + "learning_rate": 4.799501129728642e-05, + "loss": 0.3537, "step": 18930 }, { - "epoch": 0.17, - "learning_rate": 4.192189892802451e-05, - "loss": 0.3478, + "epoch": 0.04, + "learning_rate": 4.799389275407709e-05, + "loss": 0.3483, "step": 18940 }, { - "epoch": 0.17, - "learning_rate": 4.191739482929466e-05, - "loss": 0.3475, + "epoch": 0.04, + "learning_rate": 4.799277421086777e-05, + "loss": 0.3555, "step": 18950 }, { - "epoch": 0.17, - "learning_rate": 4.1912890730564815e-05, - "loss": 0.347, + "epoch": 0.04, + "learning_rate": 4.799165566765844e-05, + "loss": 0.3587, "step": 18960 }, { - "epoch": 0.17, - "learning_rate": 4.190838663183497e-05, - "loss": 0.3373, + "epoch": 0.04, + "learning_rate": 4.799053712444912e-05, + "loss": 0.3431, "step": 18970 }, { - "epoch": 0.17, - "learning_rate": 4.190388253310512e-05, - "loss": 0.3435, + "epoch": 0.04, + "learning_rate": 4.7989418581239796e-05, + "loss": 0.3501, "step": 18980 }, { - "epoch": 0.17, - "learning_rate": 4.189937843437529e-05, - "loss": 0.3369, + "epoch": 0.04, + "learning_rate": 4.798830003803047e-05, + "loss": 0.3563, "step": 18990 }, { - "epoch": 0.17, - "learning_rate": 4.189487433564544e-05, - "loss": 0.3411, + "epoch": 0.04, + "learning_rate": 4.7987181494821145e-05, + "loss": 0.3537, "step": 19000 }, { - "epoch": 0.17, - "learning_rate": 4.1890370236915596e-05, - "loss": 0.3469, + "epoch": 0.04, + "learning_rate": 4.798606295161182e-05, + "loss": 0.3505, "step": 19010 }, { - "epoch": 0.17, - "learning_rate": 4.188586613818575e-05, - "loss": 0.3417, + "epoch": 0.04, + "learning_rate": 4.79849444084025e-05, + "loss": 0.3531, "step": 19020 }, { - "epoch": 0.17, - "learning_rate": 4.1881362039455904e-05, - "loss": 0.3467, + "epoch": 0.04, + "learning_rate": 4.798382586519318e-05, + "loss": 0.3484, "step": 19030 }, { - "epoch": 0.17, - "learning_rate": 4.187685794072606e-05, - "loss": 0.3469, + "epoch": 0.04, + "learning_rate": 4.798270732198385e-05, + "loss": 0.3526, "step": 19040 }, { - "epoch": 0.17, - "learning_rate": 4.187235384199622e-05, - "loss": 0.3398, + "epoch": 0.04, + "learning_rate": 4.798158877877453e-05, + "loss": 0.3486, "step": 19050 }, { - "epoch": 0.17, - "learning_rate": 4.1867849743266376e-05, - "loss": 0.3401, + "epoch": 0.04, + "learning_rate": 4.79804702355652e-05, + "loss": 0.3569, "step": 19060 }, { - "epoch": 0.17, - "learning_rate": 4.186334564453653e-05, - "loss": 0.344, + "epoch": 0.04, + "learning_rate": 4.797935169235588e-05, + "loss": 0.3512, "step": 19070 }, { - "epoch": 0.17, - "learning_rate": 4.1858841545806685e-05, - "loss": 0.3411, + "epoch": 0.04, + "learning_rate": 4.7978233149146555e-05, + "loss": 0.3481, "step": 19080 }, { - "epoch": 0.17, - "learning_rate": 4.185433744707684e-05, - "loss": 0.345, + "epoch": 0.04, + "learning_rate": 4.7977114605937226e-05, + "loss": 0.3524, "step": 19090 }, { - "epoch": 0.17, - "learning_rate": 4.184983334834699e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.7975996062727904e-05, + "loss": 0.3493, "step": 19100 }, { - "epoch": 0.17, - "learning_rate": 4.184532924961716e-05, - "loss": 0.3407, + "epoch": 0.04, + "learning_rate": 4.797487751951858e-05, + "loss": 0.3508, "step": 19110 }, { - "epoch": 0.17, - "learning_rate": 4.184082515088731e-05, - "loss": 0.3441, + "epoch": 0.04, + "learning_rate": 4.797375897630926e-05, + "loss": 0.3508, "step": 19120 }, { - "epoch": 0.17, - "learning_rate": 4.1836321052157465e-05, - "loss": 0.3392, + "epoch": 0.04, + "learning_rate": 4.797264043309994e-05, + "loss": 0.3517, "step": 19130 }, { - "epoch": 0.17, - "learning_rate": 4.183181695342762e-05, - "loss": 0.3422, + "epoch": 0.04, + "learning_rate": 4.797152188989061e-05, + "loss": 0.3512, "step": 19140 }, { - "epoch": 0.17, - "learning_rate": 4.1827312854697773e-05, - "loss": 0.3522, + "epoch": 0.04, + "learning_rate": 4.797040334668129e-05, + "loss": 0.3552, "step": 19150 }, { - "epoch": 0.17, - "learning_rate": 4.182280875596794e-05, - "loss": 0.3417, + "epoch": 0.04, + "learning_rate": 4.796928480347196e-05, + "loss": 0.351, "step": 19160 }, { - "epoch": 0.17, - "learning_rate": 4.181830465723809e-05, - "loss": 0.3505, + "epoch": 0.04, + "learning_rate": 4.7968166260262636e-05, + "loss": 0.356, "step": 19170 }, { - "epoch": 0.17, - "learning_rate": 4.1813800558508246e-05, - "loss": 0.341, + "epoch": 0.04, + "learning_rate": 4.796704771705331e-05, + "loss": 0.3514, "step": 19180 }, { - "epoch": 0.17, - "learning_rate": 4.1809296459778403e-05, - "loss": 0.3373, + "epoch": 0.04, + "learning_rate": 4.7965929173843985e-05, + "loss": 0.3529, "step": 19190 }, { - "epoch": 0.17, - "learning_rate": 4.1804792361048554e-05, - "loss": 0.3381, + "epoch": 0.04, + "learning_rate": 4.796481063063466e-05, + "loss": 0.3486, "step": 19200 }, { - "epoch": 0.17, - "learning_rate": 4.180028826231871e-05, - "loss": 0.3337, + "epoch": 0.04, + "learning_rate": 4.796369208742534e-05, + "loss": 0.3465, "step": 19210 }, { - "epoch": 0.17, - "learning_rate": 4.179578416358887e-05, - "loss": 0.3393, + "epoch": 0.04, + "learning_rate": 4.796257354421602e-05, + "loss": 0.3531, "step": 19220 }, { - "epoch": 0.17, - "learning_rate": 4.179128006485902e-05, - "loss": 0.3395, + "epoch": 0.04, + "learning_rate": 4.796145500100669e-05, + "loss": 0.352, "step": 19230 }, { - "epoch": 0.17, - "learning_rate": 4.178677596612918e-05, - "loss": 0.3418, + "epoch": 0.04, + "learning_rate": 4.796033645779737e-05, + "loss": 0.3471, "step": 19240 }, { - "epoch": 0.17, - "learning_rate": 4.1782271867399335e-05, - "loss": 0.343, + "epoch": 0.04, + "learning_rate": 4.7959217914588046e-05, + "loss": 0.3533, "step": 19250 }, { - "epoch": 0.17, - "learning_rate": 4.177776776866949e-05, - "loss": 0.3453, + "epoch": 0.04, + "learning_rate": 4.795809937137872e-05, + "loss": 0.3511, "step": 19260 }, { - "epoch": 0.17, - "learning_rate": 4.177326366993965e-05, - "loss": 0.3394, + "epoch": 0.04, + "learning_rate": 4.7956980828169395e-05, + "loss": 0.3518, "step": 19270 }, { - "epoch": 0.17, - "learning_rate": 4.17687595712098e-05, - "loss": 0.3354, + "epoch": 0.04, + "learning_rate": 4.7955862284960066e-05, + "loss": 0.35, "step": 19280 }, { - "epoch": 0.17, - "learning_rate": 4.176425547247996e-05, - "loss": 0.3425, + "epoch": 0.04, + "learning_rate": 4.7954743741750744e-05, + "loss": 0.348, "step": 19290 }, { - "epoch": 0.17, - "learning_rate": 4.1759751373750116e-05, - "loss": 0.348, + "epoch": 0.04, + "learning_rate": 4.795362519854142e-05, + "loss": 0.3546, "step": 19300 }, { - "epoch": 0.17, - "learning_rate": 4.175524727502027e-05, - "loss": 0.3341, + "epoch": 0.04, + "learning_rate": 4.79525066553321e-05, + "loss": 0.3446, "step": 19310 }, { - "epoch": 0.17, - "learning_rate": 4.1750743176290424e-05, - "loss": 0.3415, + "epoch": 0.04, + "learning_rate": 4.795138811212278e-05, + "loss": 0.3526, "step": 19320 }, { - "epoch": 0.17, - "learning_rate": 4.174623907756058e-05, - "loss": 0.3448, + "epoch": 0.04, + "learning_rate": 4.795026956891345e-05, + "loss": 0.3523, "step": 19330 }, { - "epoch": 0.17, - "learning_rate": 4.174173497883074e-05, - "loss": 0.3501, + "epoch": 0.04, + "learning_rate": 4.794915102570413e-05, + "loss": 0.3503, "step": 19340 }, { - "epoch": 0.17, - "learning_rate": 4.173723088010089e-05, - "loss": 0.3401, + "epoch": 0.04, + "learning_rate": 4.7948032482494805e-05, + "loss": 0.3502, "step": 19350 }, { - "epoch": 0.17, - "learning_rate": 4.1732726781371054e-05, - "loss": 0.3403, + "epoch": 0.04, + "learning_rate": 4.7946913939285476e-05, + "loss": 0.3499, "step": 19360 }, { - "epoch": 0.17, - "learning_rate": 4.1728222682641204e-05, - "loss": 0.3443, + "epoch": 0.04, + "learning_rate": 4.7945795396076154e-05, + "loss": 0.35, "step": 19370 }, { - "epoch": 0.17, - "learning_rate": 4.172371858391136e-05, - "loss": 0.3462, + "epoch": 0.04, + "learning_rate": 4.7944676852866825e-05, + "loss": 0.3474, "step": 19380 }, { - "epoch": 0.17, - "learning_rate": 4.171921448518152e-05, - "loss": 0.3381, + "epoch": 0.04, + "learning_rate": 4.79435583096575e-05, + "loss": 0.3439, "step": 19390 }, { - "epoch": 0.17, - "learning_rate": 4.171471038645167e-05, - "loss": 0.3439, + "epoch": 0.04, + "learning_rate": 4.794243976644818e-05, + "loss": 0.3393, "step": 19400 }, { - "epoch": 0.17, - "learning_rate": 4.1710206287721834e-05, - "loss": 0.3393, + "epoch": 0.04, + "learning_rate": 4.794132122323885e-05, + "loss": 0.3517, "step": 19410 }, { - "epoch": 0.17, - "learning_rate": 4.1705702188991985e-05, - "loss": 0.3398, + "epoch": 0.04, + "learning_rate": 4.794020268002953e-05, + "loss": 0.357, "step": 19420 }, { - "epoch": 0.17, - "learning_rate": 4.1701198090262136e-05, - "loss": 0.3362, + "epoch": 0.04, + "learning_rate": 4.793908413682021e-05, + "loss": 0.3607, "step": 19430 }, { - "epoch": 0.17, - "learning_rate": 4.16966939915323e-05, - "loss": 0.3359, + "epoch": 0.04, + "learning_rate": 4.7937965593610886e-05, + "loss": 0.3504, "step": 19440 }, { - "epoch": 0.17, - "learning_rate": 4.169218989280245e-05, - "loss": 0.3372, + "epoch": 0.04, + "learning_rate": 4.793684705040156e-05, + "loss": 0.3498, "step": 19450 }, { - "epoch": 0.17, - "learning_rate": 4.168768579407261e-05, - "loss": 0.3334, + "epoch": 0.04, + "learning_rate": 4.7935728507192235e-05, + "loss": 0.357, "step": 19460 }, { - "epoch": 0.17, - "learning_rate": 4.1683181695342766e-05, - "loss": 0.3383, + "epoch": 0.04, + "learning_rate": 4.793460996398291e-05, + "loss": 0.35, "step": 19470 }, { - "epoch": 0.17, - "learning_rate": 4.1678677596612916e-05, - "loss": 0.3442, + "epoch": 0.04, + "learning_rate": 4.7933491420773584e-05, + "loss": 0.3554, "step": 19480 }, { - "epoch": 0.17, - "learning_rate": 4.1674173497883074e-05, - "loss": 0.3448, + "epoch": 0.04, + "learning_rate": 4.793237287756426e-05, + "loss": 0.3459, "step": 19490 }, { - "epoch": 0.17, - "learning_rate": 4.166966939915323e-05, - "loss": 0.3337, + "epoch": 0.04, + "learning_rate": 4.793125433435493e-05, + "loss": 0.3473, "step": 19500 }, { - "epoch": 0.17, - "learning_rate": 4.166516530042339e-05, - "loss": 0.3366, + "epoch": 0.04, + "learning_rate": 4.793013579114561e-05, + "loss": 0.3437, "step": 19510 }, { - "epoch": 0.17, - "learning_rate": 4.166066120169354e-05, - "loss": 0.3402, + "epoch": 0.04, + "learning_rate": 4.792901724793629e-05, + "loss": 0.3478, "step": 19520 }, { - "epoch": 0.17, - "learning_rate": 4.16561571029637e-05, - "loss": 0.3349, + "epoch": 0.04, + "learning_rate": 4.792789870472697e-05, + "loss": 0.3477, "step": 19530 }, { - "epoch": 0.17, - "learning_rate": 4.1651653004233855e-05, - "loss": 0.3357, + "epoch": 0.04, + "learning_rate": 4.7926780161517645e-05, + "loss": 0.3475, "step": 19540 }, { - "epoch": 0.17, - "learning_rate": 4.164714890550401e-05, - "loss": 0.3397, + "epoch": 0.04, + "learning_rate": 4.7925661618308316e-05, + "loss": 0.3502, "step": 19550 }, { - "epoch": 0.17, - "learning_rate": 4.164264480677417e-05, - "loss": 0.3419, + "epoch": 0.04, + "learning_rate": 4.7924543075098994e-05, + "loss": 0.3455, "step": 19560 }, { - "epoch": 0.17, - "learning_rate": 4.163814070804432e-05, - "loss": 0.3438, + "epoch": 0.04, + "learning_rate": 4.792342453188967e-05, + "loss": 0.3495, "step": 19570 }, { - "epoch": 0.17, - "learning_rate": 4.163363660931448e-05, - "loss": 0.3433, + "epoch": 0.04, + "learning_rate": 4.792230598868034e-05, + "loss": 0.3493, "step": 19580 }, { - "epoch": 0.17, - "learning_rate": 4.1629132510584635e-05, - "loss": 0.3399, + "epoch": 0.04, + "learning_rate": 4.792118744547102e-05, + "loss": 0.3455, "step": 19590 }, { - "epoch": 0.17, - "learning_rate": 4.1624628411854786e-05, - "loss": 0.3427, + "epoch": 0.04, + "learning_rate": 4.792006890226169e-05, + "loss": 0.3487, "step": 19600 }, { - "epoch": 0.18, - "learning_rate": 4.162012431312495e-05, - "loss": 0.3392, + "epoch": 0.04, + "learning_rate": 4.791895035905237e-05, + "loss": 0.3552, "step": 19610 }, { - "epoch": 0.18, - "learning_rate": 4.16156202143951e-05, - "loss": 0.3397, + "epoch": 0.04, + "learning_rate": 4.791783181584305e-05, + "loss": 0.3448, "step": 19620 }, { - "epoch": 0.18, - "learning_rate": 4.161111611566525e-05, - "loss": 0.3364, + "epoch": 0.04, + "learning_rate": 4.7916713272633726e-05, + "loss": 0.3437, "step": 19630 }, { - "epoch": 0.18, - "learning_rate": 4.1606612016935416e-05, - "loss": 0.3429, + "epoch": 0.04, + "learning_rate": 4.7915594729424404e-05, + "loss": 0.3469, "step": 19640 }, { - "epoch": 0.18, - "learning_rate": 4.160210791820557e-05, - "loss": 0.3411, + "epoch": 0.04, + "learning_rate": 4.7914476186215075e-05, + "loss": 0.3461, "step": 19650 }, { - "epoch": 0.18, - "learning_rate": 4.1597603819475724e-05, - "loss": 0.3406, + "epoch": 0.04, + "learning_rate": 4.791335764300575e-05, + "loss": 0.3512, "step": 19660 }, { - "epoch": 0.18, - "learning_rate": 4.159309972074588e-05, - "loss": 0.3349, + "epoch": 0.04, + "learning_rate": 4.791223909979643e-05, + "loss": 0.3441, "step": 19670 }, { - "epoch": 0.18, - "learning_rate": 4.158859562201603e-05, - "loss": 0.3444, + "epoch": 0.04, + "learning_rate": 4.79111205565871e-05, + "loss": 0.351, "step": 19680 }, { - "epoch": 0.18, - "learning_rate": 4.15840915232862e-05, - "loss": 0.3412, + "epoch": 0.04, + "learning_rate": 4.791000201337778e-05, + "loss": 0.3481, "step": 19690 }, { - "epoch": 0.18, - "learning_rate": 4.157958742455635e-05, - "loss": 0.3374, + "epoch": 0.04, + "learning_rate": 4.790888347016845e-05, + "loss": 0.3452, "step": 19700 }, { - "epoch": 0.18, - "learning_rate": 4.1575083325826505e-05, - "loss": 0.3392, + "epoch": 0.04, + "learning_rate": 4.790776492695913e-05, + "loss": 0.3432, "step": 19710 }, { - "epoch": 0.18, - "learning_rate": 4.157057922709666e-05, - "loss": 0.34, + "epoch": 0.04, + "learning_rate": 4.790664638374981e-05, + "loss": 0.3495, "step": 19720 }, { - "epoch": 0.18, - "learning_rate": 4.156607512836681e-05, - "loss": 0.3364, + "epoch": 0.04, + "learning_rate": 4.7905527840540485e-05, + "loss": 0.3462, "step": 19730 }, { - "epoch": 0.18, - "learning_rate": 4.156157102963697e-05, - "loss": 0.3397, + "epoch": 0.04, + "learning_rate": 4.790440929733116e-05, + "loss": 0.3481, "step": 19740 }, { - "epoch": 0.18, - "learning_rate": 4.155706693090713e-05, - "loss": 0.3408, + "epoch": 0.04, + "learning_rate": 4.7903290754121834e-05, + "loss": 0.3439, "step": 19750 }, { - "epoch": 0.18, - "learning_rate": 4.1552562832177286e-05, - "loss": 0.3405, + "epoch": 0.04, + "learning_rate": 4.790217221091251e-05, + "loss": 0.3468, "step": 19760 }, { - "epoch": 0.18, - "learning_rate": 4.1548058733447436e-05, - "loss": 0.3363, + "epoch": 0.04, + "learning_rate": 4.790105366770318e-05, + "loss": 0.3505, "step": 19770 }, { - "epoch": 0.18, - "learning_rate": 4.1543554634717594e-05, - "loss": 0.3384, + "epoch": 0.04, + "learning_rate": 4.789993512449386e-05, + "loss": 0.351, "step": 19780 }, { - "epoch": 0.18, - "learning_rate": 4.153905053598775e-05, - "loss": 0.3324, + "epoch": 0.04, + "learning_rate": 4.789881658128454e-05, + "loss": 0.3466, "step": 19790 }, { - "epoch": 0.18, - "learning_rate": 4.15345464372579e-05, - "loss": 0.3366, + "epoch": 0.04, + "learning_rate": 4.789769803807521e-05, + "loss": 0.3415, "step": 19800 }, { - "epoch": 0.18, - "learning_rate": 4.1530042338528066e-05, - "loss": 0.3342, + "epoch": 0.04, + "learning_rate": 4.789657949486589e-05, + "loss": 0.3465, "step": 19810 }, { - "epoch": 0.18, - "learning_rate": 4.152553823979822e-05, - "loss": 0.3398, + "epoch": 0.04, + "learning_rate": 4.789546095165656e-05, + "loss": 0.3483, "step": 19820 }, { - "epoch": 0.18, - "learning_rate": 4.1521034141068374e-05, - "loss": 0.3394, + "epoch": 0.04, + "learning_rate": 4.789434240844724e-05, + "loss": 0.3469, "step": 19830 }, { - "epoch": 0.18, - "learning_rate": 4.151653004233853e-05, - "loss": 0.3384, + "epoch": 0.04, + "learning_rate": 4.7893223865237915e-05, + "loss": 0.3502, "step": 19840 }, { - "epoch": 0.18, - "learning_rate": 4.151202594360868e-05, - "loss": 0.3428, + "epoch": 0.04, + "learning_rate": 4.789210532202859e-05, + "loss": 0.3531, "step": 19850 }, { - "epoch": 0.18, - "learning_rate": 4.150752184487885e-05, - "loss": 0.3329, + "epoch": 0.04, + "learning_rate": 4.789098677881927e-05, + "loss": 0.3506, "step": 19860 }, { - "epoch": 0.18, - "learning_rate": 4.1503017746149e-05, - "loss": 0.333, + "epoch": 0.04, + "learning_rate": 4.788986823560994e-05, + "loss": 0.346, "step": 19870 }, { - "epoch": 0.18, - "learning_rate": 4.149851364741915e-05, - "loss": 0.3353, + "epoch": 0.04, + "learning_rate": 4.788874969240062e-05, + "loss": 0.3412, "step": 19880 }, { - "epoch": 0.18, - "learning_rate": 4.149400954868931e-05, - "loss": 0.3391, + "epoch": 0.04, + "learning_rate": 4.78876311491913e-05, + "loss": 0.347, "step": 19890 }, { - "epoch": 0.18, - "learning_rate": 4.1489505449959463e-05, - "loss": 0.3406, + "epoch": 0.04, + "learning_rate": 4.788651260598197e-05, + "loss": 0.349, "step": 19900 }, { - "epoch": 0.18, - "learning_rate": 4.148500135122962e-05, - "loss": 0.3365, + "epoch": 0.04, + "learning_rate": 4.788539406277265e-05, + "loss": 0.3459, "step": 19910 }, { - "epoch": 0.18, - "learning_rate": 4.148049725249978e-05, - "loss": 0.3371, + "epoch": 0.04, + "learning_rate": 4.788427551956332e-05, + "loss": 0.3428, "step": 19920 }, { - "epoch": 0.18, - "learning_rate": 4.147599315376993e-05, - "loss": 0.3346, + "epoch": 0.04, + "learning_rate": 4.7883156976353996e-05, + "loss": 0.3465, "step": 19930 }, { - "epoch": 0.18, - "learning_rate": 4.1471489055040087e-05, - "loss": 0.3373, + "epoch": 0.04, + "learning_rate": 4.7882038433144674e-05, + "loss": 0.3455, "step": 19940 }, { - "epoch": 0.18, - "learning_rate": 4.1466984956310244e-05, - "loss": 0.339, + "epoch": 0.04, + "learning_rate": 4.788091988993535e-05, + "loss": 0.3434, "step": 19950 }, { - "epoch": 0.18, - "learning_rate": 4.14624808575804e-05, - "loss": 0.3465, + "epoch": 0.04, + "learning_rate": 4.787980134672603e-05, + "loss": 0.3417, "step": 19960 }, { - "epoch": 0.18, - "learning_rate": 4.145797675885056e-05, - "loss": 0.3341, + "epoch": 0.04, + "learning_rate": 4.78786828035167e-05, + "loss": 0.3437, "step": 19970 }, { - "epoch": 0.18, - "learning_rate": 4.145347266012071e-05, - "loss": 0.3412, + "epoch": 0.04, + "learning_rate": 4.787756426030738e-05, + "loss": 0.346, "step": 19980 }, { - "epoch": 0.18, - "learning_rate": 4.144896856139087e-05, - "loss": 0.3432, + "epoch": 0.04, + "learning_rate": 4.787644571709806e-05, + "loss": 0.3472, "step": 19990 }, { - "epoch": 0.18, - "learning_rate": 4.1444464462661025e-05, - "loss": 0.3411, + "epoch": 0.04, + "learning_rate": 4.787532717388873e-05, + "loss": 0.344, "step": 20000 }, { - "epoch": 0.18, - "learning_rate": 4.143996036393118e-05, - "loss": 0.3474, + "epoch": 0.04, + "learning_rate": 4.7874208630679406e-05, + "loss": 0.3482, "step": 20010 }, { - "epoch": 0.18, - "learning_rate": 4.143545626520133e-05, - "loss": 0.3394, + "epoch": 0.04, + "learning_rate": 4.787309008747008e-05, + "loss": 0.3496, "step": 20020 }, { - "epoch": 0.18, - "learning_rate": 4.143095216647149e-05, - "loss": 0.3452, + "epoch": 0.04, + "learning_rate": 4.7871971544260755e-05, + "loss": 0.354, "step": 20030 }, { - "epoch": 0.18, - "learning_rate": 4.142644806774165e-05, - "loss": 0.3327, + "epoch": 0.04, + "learning_rate": 4.787085300105143e-05, + "loss": 0.3454, "step": 20040 }, { - "epoch": 0.18, - "learning_rate": 4.14219439690118e-05, - "loss": 0.3392, + "epoch": 0.04, + "learning_rate": 4.786973445784211e-05, + "loss": 0.3486, "step": 20050 }, { - "epoch": 0.18, - "learning_rate": 4.141743987028196e-05, - "loss": 0.3358, + "epoch": 0.04, + "learning_rate": 4.786861591463279e-05, + "loss": 0.3423, "step": 20060 }, { - "epoch": 0.18, - "learning_rate": 4.1412935771552114e-05, - "loss": 0.336, + "epoch": 0.04, + "learning_rate": 4.786749737142346e-05, + "loss": 0.3521, "step": 20070 }, { - "epoch": 0.18, - "learning_rate": 4.1408431672822264e-05, - "loss": 0.335, + "epoch": 0.04, + "learning_rate": 4.786637882821414e-05, + "loss": 0.3455, "step": 20080 }, { - "epoch": 0.18, - "learning_rate": 4.140392757409243e-05, - "loss": 0.342, + "epoch": 0.04, + "learning_rate": 4.786526028500481e-05, + "loss": 0.3456, "step": 20090 }, { - "epoch": 0.18, - "learning_rate": 4.139942347536258e-05, - "loss": 0.338, + "epoch": 0.04, + "learning_rate": 4.786414174179549e-05, + "loss": 0.3488, "step": 20100 }, { - "epoch": 0.18, - "learning_rate": 4.1394919376632744e-05, - "loss": 0.3317, + "epoch": 0.04, + "learning_rate": 4.7863023198586165e-05, + "loss": 0.3425, "step": 20110 }, { - "epoch": 0.18, - "learning_rate": 4.1390415277902894e-05, - "loss": 0.3402, + "epoch": 0.04, + "learning_rate": 4.7861904655376836e-05, + "loss": 0.3399, "step": 20120 }, { - "epoch": 0.18, - "learning_rate": 4.1385911179173045e-05, - "loss": 0.3419, + "epoch": 0.04, + "learning_rate": 4.7860786112167514e-05, + "loss": 0.3411, "step": 20130 }, { - "epoch": 0.18, - "learning_rate": 4.138140708044321e-05, - "loss": 0.3359, + "epoch": 0.04, + "learning_rate": 4.785966756895819e-05, + "loss": 0.3409, "step": 20140 }, { - "epoch": 0.18, - "learning_rate": 4.137690298171336e-05, - "loss": 0.3329, + "epoch": 0.04, + "learning_rate": 4.785854902574887e-05, + "loss": 0.3363, "step": 20150 }, { - "epoch": 0.18, - "learning_rate": 4.137239888298352e-05, - "loss": 0.3337, + "epoch": 0.04, + "learning_rate": 4.785743048253955e-05, + "loss": 0.3442, "step": 20160 }, { - "epoch": 0.18, - "learning_rate": 4.1367894784253675e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.785631193933022e-05, + "loss": 0.3425, "step": 20170 }, { - "epoch": 0.18, - "learning_rate": 4.1363390685523826e-05, - "loss": 0.3343, + "epoch": 0.05, + "learning_rate": 4.78551933961209e-05, + "loss": 0.343, "step": 20180 }, { - "epoch": 0.18, - "learning_rate": 4.135888658679398e-05, - "loss": 0.3347, + "epoch": 0.05, + "learning_rate": 4.785407485291157e-05, + "loss": 0.3473, "step": 20190 }, { - "epoch": 0.18, - "learning_rate": 4.135483289793712e-05, - "loss": 0.3349, + "epoch": 0.05, + "learning_rate": 4.7852956309702246e-05, + "loss": 0.3502, "step": 20200 }, { - "epoch": 0.18, - "learning_rate": 4.1350328799207284e-05, - "loss": 0.3325, + "epoch": 0.05, + "learning_rate": 4.7851837766492924e-05, + "loss": 0.3463, "step": 20210 }, { - "epoch": 0.18, - "learning_rate": 4.1345824700477435e-05, - "loss": 0.3339, + "epoch": 0.05, + "learning_rate": 4.7850719223283595e-05, + "loss": 0.3447, "step": 20220 }, { - "epoch": 0.18, - "learning_rate": 4.134132060174759e-05, - "loss": 0.3342, + "epoch": 0.05, + "learning_rate": 4.784960068007427e-05, + "loss": 0.3427, "step": 20230 }, { - "epoch": 0.18, - "learning_rate": 4.133681650301775e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.7848482136864944e-05, + "loss": 0.3434, "step": 20240 }, { - "epoch": 0.18, - "learning_rate": 4.13323124042879e-05, - "loss": 0.3314, + "epoch": 0.05, + "learning_rate": 4.784736359365562e-05, + "loss": 0.3428, "step": 20250 }, { - "epoch": 0.18, - "learning_rate": 4.132780830555806e-05, - "loss": 0.3375, + "epoch": 0.05, + "learning_rate": 4.784624505044631e-05, + "loss": 0.3461, "step": 20260 }, { - "epoch": 0.18, - "learning_rate": 4.1323304206828216e-05, - "loss": 0.33, + "epoch": 0.05, + "learning_rate": 4.784512650723698e-05, + "loss": 0.3442, "step": 20270 }, { - "epoch": 0.18, - "learning_rate": 4.1318800108098373e-05, - "loss": 0.3387, + "epoch": 0.05, + "learning_rate": 4.7844007964027656e-05, + "loss": 0.3457, "step": 20280 }, { - "epoch": 0.18, - "learning_rate": 4.1314296009368524e-05, - "loss": 0.3341, + "epoch": 0.05, + "learning_rate": 4.784288942081833e-05, + "loss": 0.3491, "step": 20290 }, { - "epoch": 0.18, - "learning_rate": 4.130979191063868e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.7841770877609005e-05, + "loss": 0.3521, "step": 20300 }, { - "epoch": 0.18, - "learning_rate": 4.130528781190884e-05, - "loss": 0.3311, + "epoch": 0.05, + "learning_rate": 4.784065233439968e-05, + "loss": 0.3398, "step": 20310 }, { - "epoch": 0.18, - "learning_rate": 4.130078371317899e-05, - "loss": 0.3425, + "epoch": 0.05, + "learning_rate": 4.7839533791190354e-05, + "loss": 0.3441, "step": 20320 }, { - "epoch": 0.18, - "learning_rate": 4.1296279614449154e-05, - "loss": 0.3391, + "epoch": 0.05, + "learning_rate": 4.783841524798103e-05, + "loss": 0.3397, "step": 20330 }, { - "epoch": 0.18, - "learning_rate": 4.1291775515719305e-05, - "loss": 0.3381, + "epoch": 0.05, + "learning_rate": 4.78372967047717e-05, + "loss": 0.3453, "step": 20340 }, { - "epoch": 0.18, - "learning_rate": 4.128727141698946e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.783617816156238e-05, + "loss": 0.3405, "step": 20350 }, { - "epoch": 0.18, - "learning_rate": 4.128276731825962e-05, - "loss": 0.3356, + "epoch": 0.05, + "learning_rate": 4.783505961835306e-05, + "loss": 0.3504, "step": 20360 }, { - "epoch": 0.18, - "learning_rate": 4.127826321952977e-05, - "loss": 0.3335, + "epoch": 0.05, + "learning_rate": 4.783394107514374e-05, + "loss": 0.3444, "step": 20370 }, { - "epoch": 0.18, - "learning_rate": 4.1273759120799935e-05, - "loss": 0.3394, + "epoch": 0.05, + "learning_rate": 4.7832822531934415e-05, + "loss": 0.343, "step": 20380 }, { - "epoch": 0.18, - "learning_rate": 4.1269255022070085e-05, - "loss": 0.3367, + "epoch": 0.05, + "learning_rate": 4.7831703988725086e-05, + "loss": 0.3383, "step": 20390 }, { - "epoch": 0.18, - "learning_rate": 4.126475092334024e-05, - "loss": 0.3345, + "epoch": 0.05, + "learning_rate": 4.7830585445515764e-05, + "loss": 0.3399, "step": 20400 }, { - "epoch": 0.18, - "learning_rate": 4.12602468246104e-05, - "loss": 0.3312, + "epoch": 0.05, + "learning_rate": 4.7829466902306435e-05, + "loss": 0.3431, "step": 20410 }, { - "epoch": 0.18, - "learning_rate": 4.125574272588055e-05, - "loss": 0.3371, + "epoch": 0.05, + "learning_rate": 4.782834835909711e-05, + "loss": 0.339, "step": 20420 }, { - "epoch": 0.18, - "learning_rate": 4.125123862715071e-05, - "loss": 0.3389, + "epoch": 0.05, + "learning_rate": 4.782722981588779e-05, + "loss": 0.3416, "step": 20430 }, { - "epoch": 0.18, - "learning_rate": 4.1246734528420866e-05, - "loss": 0.3319, + "epoch": 0.05, + "learning_rate": 4.782611127267846e-05, + "loss": 0.341, "step": 20440 }, { - "epoch": 0.18, - "learning_rate": 4.124223042969102e-05, - "loss": 0.3469, + "epoch": 0.05, + "learning_rate": 4.782510458379008e-05, + "loss": 0.3405, "step": 20450 }, { - "epoch": 0.18, - "learning_rate": 4.1237726330961174e-05, - "loss": 0.3356, + "epoch": 0.05, + "learning_rate": 4.782398604058075e-05, + "loss": 0.3427, "step": 20460 }, { - "epoch": 0.18, - "learning_rate": 4.123322223223133e-05, - "loss": 0.3391, + "epoch": 0.05, + "learning_rate": 4.782286749737143e-05, + "loss": 0.3416, "step": 20470 }, { - "epoch": 0.18, - "learning_rate": 4.122871813350149e-05, - "loss": 0.334, + "epoch": 0.05, + "learning_rate": 4.78217489541621e-05, + "loss": 0.3494, "step": 20480 }, { - "epoch": 0.18, - "learning_rate": 4.122421403477165e-05, - "loss": 0.3292, + "epoch": 0.05, + "learning_rate": 4.7820630410952776e-05, + "loss": 0.3463, "step": 20490 }, { - "epoch": 0.18, - "learning_rate": 4.12197099360418e-05, - "loss": 0.3373, + "epoch": 0.05, + "learning_rate": 4.7819511867743454e-05, + "loss": 0.341, "step": 20500 }, { - "epoch": 0.18, - "learning_rate": 4.1215205837311955e-05, - "loss": 0.3405, + "epoch": 0.05, + "learning_rate": 4.7818393324534125e-05, + "loss": 0.3442, "step": 20510 }, { - "epoch": 0.18, - "learning_rate": 4.121070173858211e-05, - "loss": 0.3374, + "epoch": 0.05, + "learning_rate": 4.78172747813248e-05, + "loss": 0.3472, "step": 20520 }, { - "epoch": 0.18, - "learning_rate": 4.120619763985227e-05, - "loss": 0.3315, + "epoch": 0.05, + "learning_rate": 4.781615623811548e-05, + "loss": 0.3423, "step": 20530 }, { - "epoch": 0.18, - "learning_rate": 4.120169354112242e-05, - "loss": 0.336, + "epoch": 0.05, + "learning_rate": 4.781503769490616e-05, + "loss": 0.3442, "step": 20540 }, { - "epoch": 0.18, - "learning_rate": 4.119718944239258e-05, - "loss": 0.3368, + "epoch": 0.05, + "learning_rate": 4.7813919151696836e-05, + "loss": 0.3437, "step": 20550 }, { - "epoch": 0.18, - "learning_rate": 4.1192685343662736e-05, - "loss": 0.3298, + "epoch": 0.05, + "learning_rate": 4.781280060848751e-05, + "loss": 0.3384, "step": 20560 }, { - "epoch": 0.18, - "learning_rate": 4.1188181244932886e-05, - "loss": 0.3328, + "epoch": 0.05, + "learning_rate": 4.7811682065278186e-05, + "loss": 0.342, "step": 20570 }, { - "epoch": 0.18, - "learning_rate": 4.118367714620305e-05, - "loss": 0.3318, + "epoch": 0.05, + "learning_rate": 4.781056352206886e-05, + "loss": 0.3489, "step": 20580 }, { - "epoch": 0.18, - "learning_rate": 4.11791730474732e-05, - "loss": 0.3331, + "epoch": 0.05, + "learning_rate": 4.7809444978859535e-05, + "loss": 0.3404, "step": 20590 }, { - "epoch": 0.18, - "learning_rate": 4.117466894874336e-05, - "loss": 0.3307, + "epoch": 0.05, + "learning_rate": 4.780832643565021e-05, + "loss": 0.3428, "step": 20600 }, { - "epoch": 0.18, - "learning_rate": 4.1170164850013516e-05, - "loss": 0.3398, + "epoch": 0.05, + "learning_rate": 4.7807207892440884e-05, + "loss": 0.3478, "step": 20610 }, { - "epoch": 0.18, - "learning_rate": 4.116566075128367e-05, - "loss": 0.3381, + "epoch": 0.05, + "learning_rate": 4.780608934923156e-05, + "loss": 0.3439, "step": 20620 }, { - "epoch": 0.18, - "learning_rate": 4.116115665255383e-05, - "loss": 0.3316, + "epoch": 0.05, + "learning_rate": 4.780497080602224e-05, + "loss": 0.3441, "step": 20630 }, { - "epoch": 0.18, - "learning_rate": 4.115665255382398e-05, - "loss": 0.3366, + "epoch": 0.05, + "learning_rate": 4.780385226281292e-05, + "loss": 0.3411, "step": 20640 }, { - "epoch": 0.18, - "learning_rate": 4.115214845509413e-05, - "loss": 0.3357, + "epoch": 0.05, + "learning_rate": 4.7802733719603595e-05, + "loss": 0.3449, "step": 20650 }, { - "epoch": 0.18, - "learning_rate": 4.11476443563643e-05, - "loss": 0.3376, + "epoch": 0.05, + "learning_rate": 4.7801615176394267e-05, + "loss": 0.347, "step": 20660 }, { - "epoch": 0.18, - "learning_rate": 4.114314025763445e-05, - "loss": 0.3354, + "epoch": 0.05, + "learning_rate": 4.7800496633184945e-05, + "loss": 0.3425, "step": 20670 }, { - "epoch": 0.18, - "learning_rate": 4.1138636158904605e-05, - "loss": 0.3334, + "epoch": 0.05, + "learning_rate": 4.7799378089975616e-05, + "loss": 0.3437, "step": 20680 }, { - "epoch": 0.18, - "learning_rate": 4.113413206017476e-05, - "loss": 0.3374, + "epoch": 0.05, + "learning_rate": 4.7798259546766294e-05, + "loss": 0.3377, "step": 20690 }, { - "epoch": 0.18, - "learning_rate": 4.1129627961444914e-05, - "loss": 0.3329, + "epoch": 0.05, + "learning_rate": 4.779714100355697e-05, + "loss": 0.3461, "step": 20700 }, { - "epoch": 0.18, - "learning_rate": 4.112512386271507e-05, - "loss": 0.3349, + "epoch": 0.05, + "learning_rate": 4.779602246034764e-05, + "loss": 0.3448, "step": 20710 }, { - "epoch": 0.18, - "learning_rate": 4.112061976398523e-05, - "loss": 0.3265, + "epoch": 0.05, + "learning_rate": 4.779490391713832e-05, + "loss": 0.3467, "step": 20720 }, { - "epoch": 0.19, - "learning_rate": 4.1116115665255386e-05, - "loss": 0.3322, + "epoch": 0.05, + "learning_rate": 4.7793785373929e-05, + "loss": 0.3438, "step": 20730 }, { - "epoch": 0.19, - "learning_rate": 4.111161156652554e-05, - "loss": 0.333, + "epoch": 0.05, + "learning_rate": 4.7792666830719676e-05, + "loss": 0.3473, "step": 20740 }, { - "epoch": 0.19, - "learning_rate": 4.1107107467795694e-05, - "loss": 0.3322, + "epoch": 0.05, + "learning_rate": 4.7791548287510354e-05, + "loss": 0.3536, "step": 20750 }, { - "epoch": 0.19, - "learning_rate": 4.110260336906585e-05, - "loss": 0.3298, + "epoch": 0.05, + "learning_rate": 4.7790429744301026e-05, + "loss": 0.3396, "step": 20760 }, { - "epoch": 0.19, - "learning_rate": 4.109809927033601e-05, - "loss": 0.3301, + "epoch": 0.05, + "learning_rate": 4.7789311201091703e-05, + "loss": 0.3445, "step": 20770 }, { - "epoch": 0.19, - "learning_rate": 4.109359517160617e-05, - "loss": 0.3334, + "epoch": 0.05, + "learning_rate": 4.7788192657882375e-05, + "loss": 0.3457, "step": 20780 }, { - "epoch": 0.19, - "learning_rate": 4.108909107287632e-05, - "loss": 0.3305, + "epoch": 0.05, + "learning_rate": 4.778707411467305e-05, + "loss": 0.3463, "step": 20790 }, { - "epoch": 0.19, - "learning_rate": 4.1084586974146475e-05, - "loss": 0.3309, + "epoch": 0.05, + "learning_rate": 4.7785955571463724e-05, + "loss": 0.3404, "step": 20800 }, { - "epoch": 0.19, - "learning_rate": 4.108008287541663e-05, - "loss": 0.3269, + "epoch": 0.05, + "learning_rate": 4.77848370282544e-05, + "loss": 0.3403, "step": 20810 }, { - "epoch": 0.19, - "learning_rate": 4.107557877668678e-05, - "loss": 0.3296, + "epoch": 0.05, + "learning_rate": 4.778371848504508e-05, + "loss": 0.34, "step": 20820 }, { - "epoch": 0.19, - "learning_rate": 4.107107467795695e-05, - "loss": 0.3337, + "epoch": 0.05, + "learning_rate": 4.778259994183575e-05, + "loss": 0.3461, "step": 20830 }, { - "epoch": 0.19, - "learning_rate": 4.10665705792271e-05, - "loss": 0.3282, + "epoch": 0.05, + "learning_rate": 4.7781481398626435e-05, + "loss": 0.3419, "step": 20840 }, { - "epoch": 0.19, - "learning_rate": 4.106206648049725e-05, - "loss": 0.33, + "epoch": 0.05, + "learning_rate": 4.7780362855417107e-05, + "loss": 0.343, "step": 20850 }, { - "epoch": 0.19, - "learning_rate": 4.105756238176741e-05, - "loss": 0.3382, + "epoch": 0.05, + "learning_rate": 4.7779244312207784e-05, + "loss": 0.3429, "step": 20860 }, { - "epoch": 0.19, - "learning_rate": 4.1053058283037564e-05, - "loss": 0.333, + "epoch": 0.05, + "learning_rate": 4.777812576899846e-05, + "loss": 0.3346, "step": 20870 }, { - "epoch": 0.19, - "learning_rate": 4.104855418430772e-05, - "loss": 0.3343, + "epoch": 0.05, + "learning_rate": 4.7777007225789134e-05, + "loss": 0.3435, "step": 20880 }, { - "epoch": 0.19, - "learning_rate": 4.104405008557788e-05, - "loss": 0.3348, + "epoch": 0.05, + "learning_rate": 4.777588868257981e-05, + "loss": 0.3469, "step": 20890 }, { - "epoch": 0.19, - "learning_rate": 4.103954598684803e-05, - "loss": 0.337, + "epoch": 0.05, + "learning_rate": 4.777477013937048e-05, + "loss": 0.338, "step": 20900 }, { - "epoch": 0.19, - "learning_rate": 4.1035041888118194e-05, - "loss": 0.3347, + "epoch": 0.05, + "learning_rate": 4.777365159616116e-05, + "loss": 0.3435, "step": 20910 }, { - "epoch": 0.19, - "learning_rate": 4.1030537789388344e-05, - "loss": 0.3388, + "epoch": 0.05, + "learning_rate": 4.777253305295184e-05, + "loss": 0.3416, "step": 20920 }, { - "epoch": 0.19, - "learning_rate": 4.10260336906585e-05, - "loss": 0.3309, + "epoch": 0.05, + "learning_rate": 4.777141450974251e-05, + "loss": 0.3403, "step": 20930 }, { - "epoch": 0.19, - "learning_rate": 4.102152959192866e-05, - "loss": 0.3343, + "epoch": 0.05, + "learning_rate": 4.777029596653319e-05, + "loss": 0.3431, "step": 20940 }, { - "epoch": 0.19, - "learning_rate": 4.101702549319881e-05, - "loss": 0.3313, + "epoch": 0.05, + "learning_rate": 4.7769177423323866e-05, + "loss": 0.345, "step": 20950 }, { - "epoch": 0.19, - "learning_rate": 4.101252139446897e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.7768058880114543e-05, + "loss": 0.3417, "step": 20960 }, { - "epoch": 0.19, - "learning_rate": 4.1008017295739125e-05, - "loss": 0.3335, + "epoch": 0.05, + "learning_rate": 4.776694033690522e-05, + "loss": 0.3427, "step": 20970 }, { - "epoch": 0.19, - "learning_rate": 4.100351319700928e-05, - "loss": 0.3333, + "epoch": 0.05, + "learning_rate": 4.776582179369589e-05, + "loss": 0.3426, "step": 20980 }, { - "epoch": 0.19, - "learning_rate": 4.099900909827943e-05, - "loss": 0.3254, + "epoch": 0.05, + "learning_rate": 4.776470325048657e-05, + "loss": 0.3465, "step": 20990 }, { - "epoch": 0.19, - "learning_rate": 4.099450499954959e-05, - "loss": 0.3358, + "epoch": 0.05, + "learning_rate": 4.776358470727724e-05, + "loss": 0.3484, "step": 21000 }, { - "epoch": 0.19, - "learning_rate": 4.099000090081975e-05, - "loss": 0.3255, + "epoch": 0.05, + "learning_rate": 4.776246616406792e-05, + "loss": 0.3453, "step": 21010 }, { - "epoch": 0.19, - "learning_rate": 4.09854968020899e-05, - "loss": 0.3249, + "epoch": 0.05, + "learning_rate": 4.77613476208586e-05, + "loss": 0.3335, "step": 21020 }, { - "epoch": 0.19, - "learning_rate": 4.098099270336006e-05, - "loss": 0.3354, + "epoch": 0.05, + "learning_rate": 4.776022907764927e-05, + "loss": 0.3386, "step": 21030 }, { - "epoch": 0.19, - "learning_rate": 4.0976488604630214e-05, - "loss": 0.3305, + "epoch": 0.05, + "learning_rate": 4.7759110534439947e-05, + "loss": 0.3372, "step": 21040 }, { - "epoch": 0.19, - "learning_rate": 4.097198450590037e-05, - "loss": 0.3289, + "epoch": 0.05, + "learning_rate": 4.7757991991230624e-05, + "loss": 0.3475, "step": 21050 }, { - "epoch": 0.19, - "learning_rate": 4.096748040717053e-05, - "loss": 0.329, + "epoch": 0.05, + "learning_rate": 4.77568734480213e-05, + "loss": 0.3453, "step": 21060 }, { - "epoch": 0.19, - "learning_rate": 4.096297630844068e-05, - "loss": 0.3291, + "epoch": 0.05, + "learning_rate": 4.775575490481198e-05, + "loss": 0.3368, "step": 21070 }, { - "epoch": 0.19, - "learning_rate": 4.0958472209710844e-05, - "loss": 0.33, + "epoch": 0.05, + "learning_rate": 4.775463636160265e-05, + "loss": 0.3425, "step": 21080 }, { - "epoch": 0.19, - "learning_rate": 4.0953968110980995e-05, - "loss": 0.3335, + "epoch": 0.05, + "learning_rate": 4.775351781839333e-05, + "loss": 0.3361, "step": 21090 }, { - "epoch": 0.19, - "learning_rate": 4.0949464012251145e-05, - "loss": 0.3314, + "epoch": 0.05, + "learning_rate": 4.7752399275184e-05, + "loss": 0.3376, "step": 21100 }, { - "epoch": 0.19, - "learning_rate": 4.094495991352131e-05, - "loss": 0.3327, + "epoch": 0.05, + "learning_rate": 4.775128073197468e-05, + "loss": 0.3356, "step": 21110 }, { - "epoch": 0.19, - "learning_rate": 4.094045581479146e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.775016218876535e-05, + "loss": 0.3388, "step": 21120 }, { - "epoch": 0.19, - "learning_rate": 4.093595171606162e-05, - "loss": 0.3355, + "epoch": 0.05, + "learning_rate": 4.774904364555603e-05, + "loss": 0.3392, "step": 21130 }, { - "epoch": 0.19, - "learning_rate": 4.0931447617331775e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.7747925102346705e-05, + "loss": 0.3419, "step": 21140 }, { - "epoch": 0.19, - "learning_rate": 4.0926943518601926e-05, - "loss": 0.3351, + "epoch": 0.05, + "learning_rate": 4.7746806559137383e-05, + "loss": 0.3407, "step": 21150 }, { - "epoch": 0.19, - "learning_rate": 4.0922439419872084e-05, - "loss": 0.3299, + "epoch": 0.05, + "learning_rate": 4.774568801592806e-05, + "loss": 0.3387, "step": 21160 }, { - "epoch": 0.19, - "learning_rate": 4.091793532114224e-05, - "loss": 0.3281, + "epoch": 0.05, + "learning_rate": 4.774456947271873e-05, + "loss": 0.3362, "step": 21170 }, { - "epoch": 0.19, - "learning_rate": 4.09134312224124e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.774345092950941e-05, + "loss": 0.3376, "step": 21180 }, { - "epoch": 0.19, - "learning_rate": 4.0908927123682556e-05, - "loss": 0.3398, + "epoch": 0.05, + "learning_rate": 4.774233238630009e-05, + "loss": 0.3461, "step": 21190 }, { - "epoch": 0.19, - "learning_rate": 4.090442302495271e-05, - "loss": 0.3311, + "epoch": 0.05, + "learning_rate": 4.774121384309076e-05, + "loss": 0.3396, "step": 21200 }, { - "epoch": 0.19, - "learning_rate": 4.0899918926222864e-05, - "loss": 0.3279, + "epoch": 0.05, + "learning_rate": 4.774009529988144e-05, + "loss": 0.3406, "step": 21210 }, { - "epoch": 0.19, - "learning_rate": 4.089541482749302e-05, - "loss": 0.3308, + "epoch": 0.05, + "learning_rate": 4.773897675667211e-05, + "loss": 0.3392, "step": 21220 }, { - "epoch": 0.19, - "learning_rate": 4.089091072876318e-05, - "loss": 0.3236, + "epoch": 0.05, + "learning_rate": 4.7737858213462786e-05, + "loss": 0.3446, "step": 21230 }, { - "epoch": 0.19, - "learning_rate": 4.088640663003333e-05, - "loss": 0.3353, + "epoch": 0.05, + "learning_rate": 4.7736739670253464e-05, + "loss": 0.3395, "step": 21240 }, { - "epoch": 0.19, - "learning_rate": 4.088190253130349e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.7735621127044136e-05, + "loss": 0.3347, "step": 21250 }, { - "epoch": 0.19, - "learning_rate": 4.0877398432573645e-05, - "loss": 0.3267, + "epoch": 0.05, + "learning_rate": 4.773450258383482e-05, + "loss": 0.3426, "step": 21260 }, { - "epoch": 0.19, - "learning_rate": 4.0872894333843796e-05, - "loss": 0.3282, + "epoch": 0.05, + "learning_rate": 4.773338404062549e-05, + "loss": 0.3364, "step": 21270 }, { - "epoch": 0.19, - "learning_rate": 4.086839023511396e-05, - "loss": 0.3275, + "epoch": 0.05, + "learning_rate": 4.773226549741617e-05, + "loss": 0.334, "step": 21280 }, { - "epoch": 0.19, - "learning_rate": 4.086388613638411e-05, - "loss": 0.3282, + "epoch": 0.05, + "learning_rate": 4.773114695420685e-05, + "loss": 0.338, "step": 21290 }, { - "epoch": 0.19, - "learning_rate": 4.085938203765426e-05, - "loss": 0.3346, + "epoch": 0.05, + "learning_rate": 4.773002841099752e-05, + "loss": 0.3394, "step": 21300 }, { - "epoch": 0.19, - "learning_rate": 4.0854877938924426e-05, - "loss": 0.3345, + "epoch": 0.05, + "learning_rate": 4.7728909867788196e-05, + "loss": 0.3418, "step": 21310 }, { - "epoch": 0.19, - "learning_rate": 4.0850373840194576e-05, - "loss": 0.3285, + "epoch": 0.05, + "learning_rate": 4.772779132457887e-05, + "loss": 0.3413, "step": 21320 }, { - "epoch": 0.19, - "learning_rate": 4.084586974146474e-05, - "loss": 0.3358, + "epoch": 0.05, + "learning_rate": 4.7726672781369545e-05, + "loss": 0.3381, "step": 21330 }, { - "epoch": 0.19, - "learning_rate": 4.084136564273489e-05, - "loss": 0.3315, + "epoch": 0.05, + "learning_rate": 4.772555423816022e-05, + "loss": 0.3411, "step": 21340 }, { - "epoch": 0.19, - "learning_rate": 4.083686154400504e-05, - "loss": 0.3299, + "epoch": 0.05, + "learning_rate": 4.7724435694950895e-05, + "loss": 0.3369, "step": 21350 }, { - "epoch": 0.19, - "learning_rate": 4.0832357445275206e-05, - "loss": 0.3239, + "epoch": 0.05, + "learning_rate": 4.772331715174157e-05, + "loss": 0.3367, "step": 21360 }, { - "epoch": 0.19, - "learning_rate": 4.082785334654536e-05, - "loss": 0.3294, + "epoch": 0.05, + "learning_rate": 4.772219860853225e-05, + "loss": 0.3402, "step": 21370 }, { - "epoch": 0.19, - "learning_rate": 4.0823349247815515e-05, - "loss": 0.3318, + "epoch": 0.05, + "learning_rate": 4.772108006532293e-05, + "loss": 0.3355, "step": 21380 }, { - "epoch": 0.19, - "learning_rate": 4.081884514908567e-05, - "loss": 0.3263, + "epoch": 0.05, + "learning_rate": 4.7719961522113606e-05, + "loss": 0.3424, "step": 21390 }, { - "epoch": 0.19, - "learning_rate": 4.081434105035582e-05, - "loss": 0.3332, + "epoch": 0.05, + "learning_rate": 4.771884297890428e-05, + "loss": 0.337, "step": 21400 }, { - "epoch": 0.19, - "learning_rate": 4.080983695162598e-05, - "loss": 0.3352, + "epoch": 0.05, + "learning_rate": 4.7717724435694955e-05, + "loss": 0.3385, "step": 21410 }, { - "epoch": 0.19, - "learning_rate": 4.080533285289614e-05, - "loss": 0.3323, + "epoch": 0.05, + "learning_rate": 4.7716605892485626e-05, + "loss": 0.3372, "step": 21420 }, { - "epoch": 0.19, - "learning_rate": 4.0800828754166295e-05, - "loss": 0.3281, + "epoch": 0.05, + "learning_rate": 4.7715487349276304e-05, + "loss": 0.344, "step": 21430 }, { - "epoch": 0.19, - "learning_rate": 4.0796324655436446e-05, - "loss": 0.3353, + "epoch": 0.05, + "learning_rate": 4.7714368806066976e-05, + "loss": 0.3406, "step": 21440 }, { - "epoch": 0.19, - "learning_rate": 4.0791820556706603e-05, - "loss": 0.3335, + "epoch": 0.05, + "learning_rate": 4.7713250262857653e-05, + "loss": 0.3317, "step": 21450 }, { - "epoch": 0.19, - "learning_rate": 4.078731645797676e-05, - "loss": 0.3312, + "epoch": 0.05, + "learning_rate": 4.771213171964833e-05, + "loss": 0.3394, "step": 21460 }, { - "epoch": 0.19, - "learning_rate": 4.078281235924692e-05, - "loss": 0.3226, + "epoch": 0.05, + "learning_rate": 4.771101317643901e-05, + "loss": 0.337, "step": 21470 }, { - "epoch": 0.19, - "learning_rate": 4.0778308260517076e-05, - "loss": 0.332, + "epoch": 0.05, + "learning_rate": 4.770989463322969e-05, + "loss": 0.3424, "step": 21480 }, { - "epoch": 0.19, - "learning_rate": 4.077380416178723e-05, - "loss": 0.3284, + "epoch": 0.05, + "learning_rate": 4.770877609002036e-05, + "loss": 0.3433, "step": 21490 }, { - "epoch": 0.19, - "learning_rate": 4.0769300063057384e-05, - "loss": 0.3249, + "epoch": 0.05, + "learning_rate": 4.7707657546811036e-05, + "loss": 0.341, "step": 21500 }, { - "epoch": 0.19, - "learning_rate": 4.076479596432754e-05, - "loss": 0.3286, + "epoch": 0.05, + "learning_rate": 4.7706539003601714e-05, + "loss": 0.3331, "step": 21510 }, { - "epoch": 0.19, - "learning_rate": 4.076029186559769e-05, - "loss": 0.3251, + "epoch": 0.05, + "learning_rate": 4.7705420460392385e-05, + "loss": 0.3314, "step": 21520 }, { - "epoch": 0.19, - "learning_rate": 4.075578776686786e-05, - "loss": 0.3265, + "epoch": 0.05, + "learning_rate": 4.770430191718306e-05, + "loss": 0.3408, "step": 21530 }, { - "epoch": 0.19, - "learning_rate": 4.075128366813801e-05, - "loss": 0.3316, + "epoch": 0.05, + "learning_rate": 4.7703183373973734e-05, + "loss": 0.3387, "step": 21540 }, { - "epoch": 0.19, - "learning_rate": 4.074677956940816e-05, - "loss": 0.3282, + "epoch": 0.05, + "learning_rate": 4.770206483076441e-05, + "loss": 0.3367, "step": 21550 }, { - "epoch": 0.19, - "learning_rate": 4.074227547067832e-05, - "loss": 0.3281, + "epoch": 0.05, + "learning_rate": 4.770094628755509e-05, + "loss": 0.3449, "step": 21560 }, { - "epoch": 0.19, - "learning_rate": 4.073777137194847e-05, - "loss": 0.331, + "epoch": 0.05, + "learning_rate": 4.769982774434577e-05, + "loss": 0.3361, "step": 21570 }, { - "epoch": 0.19, - "learning_rate": 4.073326727321863e-05, - "loss": 0.3293, + "epoch": 0.05, + "learning_rate": 4.7698709201136446e-05, + "loss": 0.3372, "step": 21580 }, { - "epoch": 0.19, - "learning_rate": 4.072876317448879e-05, - "loss": 0.3263, + "epoch": 0.05, + "learning_rate": 4.769759065792712e-05, + "loss": 0.341, "step": 21590 }, { - "epoch": 0.19, - "learning_rate": 4.072425907575894e-05, - "loss": 0.3311, + "epoch": 0.05, + "learning_rate": 4.7696472114717795e-05, + "loss": 0.3392, "step": 21600 }, { - "epoch": 0.19, - "learning_rate": 4.07197549770291e-05, - "loss": 0.3242, + "epoch": 0.05, + "learning_rate": 4.769535357150847e-05, + "loss": 0.3377, "step": 21610 }, { - "epoch": 0.19, - "learning_rate": 4.0715250878299254e-05, - "loss": 0.3263, + "epoch": 0.05, + "learning_rate": 4.7694235028299144e-05, + "loss": 0.3434, "step": 21620 }, { - "epoch": 0.19, - "learning_rate": 4.071074677956941e-05, - "loss": 0.334, + "epoch": 0.05, + "learning_rate": 4.769311648508982e-05, + "loss": 0.3349, "step": 21630 }, { - "epoch": 0.19, - "learning_rate": 4.070624268083957e-05, - "loss": 0.3334, + "epoch": 0.05, + "learning_rate": 4.7691997941880493e-05, + "loss": 0.3351, "step": 21640 }, { - "epoch": 0.19, - "learning_rate": 4.070173858210972e-05, - "loss": 0.331, + "epoch": 0.05, + "learning_rate": 4.769087939867117e-05, + "loss": 0.3363, "step": 21650 }, { - "epoch": 0.19, - "learning_rate": 4.069723448337988e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.768976085546185e-05, + "loss": 0.3375, "step": 21660 }, { - "epoch": 0.19, - "learning_rate": 4.0692730384650034e-05, - "loss": 0.3329, + "epoch": 0.05, + "learning_rate": 4.768864231225253e-05, + "loss": 0.3375, "step": 21670 }, { - "epoch": 0.19, - "learning_rate": 4.068822628592019e-05, - "loss": 0.329, + "epoch": 0.05, + "learning_rate": 4.7687523769043205e-05, + "loss": 0.3424, "step": 21680 }, { - "epoch": 0.19, - "learning_rate": 4.068372218719034e-05, - "loss": 0.3315, + "epoch": 0.05, + "learning_rate": 4.7686405225833876e-05, + "loss": 0.3325, "step": 21690 }, { - "epoch": 0.19, - "learning_rate": 4.06792180884605e-05, - "loss": 0.3225, + "epoch": 0.05, + "learning_rate": 4.7685286682624554e-05, + "loss": 0.339, "step": 21700 }, { - "epoch": 0.19, - "learning_rate": 4.067471398973066e-05, - "loss": 0.3292, + "epoch": 0.05, + "learning_rate": 4.768416813941523e-05, + "loss": 0.3446, "step": 21710 }, { - "epoch": 0.19, - "learning_rate": 4.067020989100081e-05, - "loss": 0.332, + "epoch": 0.05, + "learning_rate": 4.76830495962059e-05, + "loss": 0.3351, "step": 21720 }, { - "epoch": 0.19, - "learning_rate": 4.066570579227097e-05, - "loss": 0.3335, + "epoch": 0.05, + "learning_rate": 4.768193105299658e-05, + "loss": 0.3388, "step": 21730 }, { - "epoch": 0.19, - "learning_rate": 4.066120169354112e-05, - "loss": 0.3238, + "epoch": 0.05, + "learning_rate": 4.768081250978725e-05, + "loss": 0.3422, "step": 21740 }, { - "epoch": 0.19, - "learning_rate": 4.065669759481128e-05, - "loss": 0.3307, + "epoch": 0.05, + "learning_rate": 4.767969396657793e-05, + "loss": 0.3379, "step": 21750 }, { - "epoch": 0.19, - "learning_rate": 4.065219349608144e-05, - "loss": 0.3233, + "epoch": 0.05, + "learning_rate": 4.76785754233686e-05, + "loss": 0.3389, "step": 21760 }, { - "epoch": 0.19, - "learning_rate": 4.064768939735159e-05, - "loss": 0.328, + "epoch": 0.05, + "learning_rate": 4.767745688015928e-05, + "loss": 0.3422, "step": 21770 }, { - "epoch": 0.19, - "learning_rate": 4.0643185298621746e-05, - "loss": 0.3307, + "epoch": 0.05, + "learning_rate": 4.767633833694996e-05, + "loss": 0.3442, "step": 21780 }, { - "epoch": 0.19, - "learning_rate": 4.0638681199891904e-05, - "loss": 0.3299, + "epoch": 0.05, + "learning_rate": 4.7675219793740635e-05, + "loss": 0.3446, "step": 21790 }, { - "epoch": 0.19, - "learning_rate": 4.0634177101162055e-05, - "loss": 0.3338, + "epoch": 0.05, + "learning_rate": 4.767410125053131e-05, + "loss": 0.3388, "step": 21800 }, { - "epoch": 0.19, - "learning_rate": 4.062967300243222e-05, - "loss": 0.3227, + "epoch": 0.05, + "learning_rate": 4.7672982707321984e-05, + "loss": 0.3362, "step": 21810 }, { - "epoch": 0.19, - "learning_rate": 4.062516890370237e-05, - "loss": 0.3267, + "epoch": 0.05, + "learning_rate": 4.767186416411266e-05, + "loss": 0.3415, "step": 21820 }, { - "epoch": 0.19, - "learning_rate": 4.062066480497253e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.767074562090334e-05, + "loss": 0.3366, "step": 21830 }, { - "epoch": 0.19, - "learning_rate": 4.0616160706242685e-05, - "loss": 0.3272, + "epoch": 0.05, + "learning_rate": 4.766962707769401e-05, + "loss": 0.3386, "step": 21840 }, { - "epoch": 0.2, - "learning_rate": 4.0611656607512835e-05, - "loss": 0.3301, + "epoch": 0.05, + "learning_rate": 4.766850853448469e-05, + "loss": 0.3362, "step": 21850 }, { - "epoch": 0.2, - "learning_rate": 4.060715250878299e-05, - "loss": 0.3314, + "epoch": 0.05, + "learning_rate": 4.766738999127536e-05, + "loss": 0.3384, "step": 21860 }, { - "epoch": 0.2, - "learning_rate": 4.060264841005315e-05, - "loss": 0.3268, + "epoch": 0.05, + "learning_rate": 4.766627144806604e-05, + "loss": 0.3392, "step": 21870 }, { - "epoch": 0.2, - "learning_rate": 4.059814431132331e-05, - "loss": 0.3316, + "epoch": 0.05, + "learning_rate": 4.7665152904856716e-05, + "loss": 0.3389, "step": 21880 }, { - "epoch": 0.2, - "learning_rate": 4.0593640212593465e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.7664034361647394e-05, + "loss": 0.3384, "step": 21890 }, { - "epoch": 0.2, - "learning_rate": 4.0589136113863616e-05, - "loss": 0.3289, + "epoch": 0.05, + "learning_rate": 4.766291581843807e-05, + "loss": 0.3334, "step": 21900 }, { - "epoch": 0.2, - "learning_rate": 4.0584632015133774e-05, - "loss": 0.3308, + "epoch": 0.05, + "learning_rate": 4.766179727522874e-05, + "loss": 0.3362, "step": 21910 }, { - "epoch": 0.2, - "learning_rate": 4.058012791640393e-05, - "loss": 0.3298, + "epoch": 0.05, + "learning_rate": 4.766067873201942e-05, + "loss": 0.3384, "step": 21920 }, { - "epoch": 0.2, - "learning_rate": 4.057562381767409e-05, - "loss": 0.3251, + "epoch": 0.05, + "learning_rate": 4.76595601888101e-05, + "loss": 0.3341, "step": 21930 }, { - "epoch": 0.2, - "learning_rate": 4.057111971894424e-05, - "loss": 0.3257, + "epoch": 0.05, + "learning_rate": 4.765844164560077e-05, + "loss": 0.3358, "step": 21940 }, { - "epoch": 0.2, - "learning_rate": 4.05666156202144e-05, - "loss": 0.3273, + "epoch": 0.05, + "learning_rate": 4.765732310239145e-05, + "loss": 0.3352, "step": 21950 }, { - "epoch": 0.2, - "learning_rate": 4.0562111521484554e-05, - "loss": 0.3267, + "epoch": 0.05, + "learning_rate": 4.765620455918212e-05, + "loss": 0.3439, "step": 21960 }, { - "epoch": 0.2, - "learning_rate": 4.0557607422754705e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.76550860159728e-05, + "loss": 0.3444, "step": 21970 }, { - "epoch": 0.2, - "learning_rate": 4.055310332402487e-05, - "loss": 0.3237, + "epoch": 0.05, + "learning_rate": 4.7653967472763475e-05, + "loss": 0.3394, "step": 21980 }, { - "epoch": 0.2, - "learning_rate": 4.054859922529502e-05, - "loss": 0.3269, + "epoch": 0.05, + "learning_rate": 4.765284892955415e-05, + "loss": 0.3339, "step": 21990 }, { - "epoch": 0.2, - "learning_rate": 4.054409512656517e-05, - "loss": 0.3223, + "epoch": 0.05, + "learning_rate": 4.765173038634483e-05, + "loss": 0.343, "step": 22000 }, { - "epoch": 0.2, - "learning_rate": 4.0539591027835335e-05, - "loss": 0.3288, + "epoch": 0.05, + "learning_rate": 4.76506118431355e-05, + "loss": 0.3391, "step": 22010 }, { - "epoch": 0.2, - "learning_rate": 4.0535086929105486e-05, - "loss": 0.3247, + "epoch": 0.05, + "learning_rate": 4.764949329992618e-05, + "loss": 0.3352, "step": 22020 }, { - "epoch": 0.2, - "learning_rate": 4.053058283037564e-05, - "loss": 0.3266, + "epoch": 0.05, + "learning_rate": 4.764837475671686e-05, + "loss": 0.3407, "step": 22030 }, { - "epoch": 0.2, - "learning_rate": 4.05260787316458e-05, - "loss": 0.3303, + "epoch": 0.05, + "learning_rate": 4.764725621350753e-05, + "loss": 0.3347, "step": 22040 }, { - "epoch": 0.2, - "learning_rate": 4.052157463291595e-05, - "loss": 0.3217, + "epoch": 0.05, + "learning_rate": 4.764613767029821e-05, + "loss": 0.3365, "step": 22050 }, { - "epoch": 0.2, - "learning_rate": 4.0517070534186116e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.764501912708888e-05, + "loss": 0.3334, "step": 22060 }, { - "epoch": 0.2, - "learning_rate": 4.0512566435456266e-05, - "loss": 0.3226, + "epoch": 0.05, + "learning_rate": 4.7643900583879556e-05, + "loss": 0.3308, "step": 22070 }, { - "epoch": 0.2, - "learning_rate": 4.0508062336726424e-05, - "loss": 0.327, + "epoch": 0.05, + "learning_rate": 4.764278204067023e-05, + "loss": 0.3364, "step": 22080 }, { - "epoch": 0.2, - "learning_rate": 4.050355823799658e-05, - "loss": 0.3259, + "epoch": 0.05, + "learning_rate": 4.764166349746091e-05, + "loss": 0.3388, "step": 22090 }, { - "epoch": 0.2, - "learning_rate": 4.049905413926673e-05, - "loss": 0.3271, + "epoch": 0.05, + "learning_rate": 4.764054495425159e-05, + "loss": 0.3378, "step": 22100 }, { - "epoch": 0.2, - "learning_rate": 4.049455004053689e-05, - "loss": 0.318, + "epoch": 0.05, + "learning_rate": 4.763942641104226e-05, + "loss": 0.3356, "step": 22110 }, { - "epoch": 0.2, - "learning_rate": 4.049004594180705e-05, - "loss": 0.3322, + "epoch": 0.05, + "learning_rate": 4.763830786783294e-05, + "loss": 0.3375, "step": 22120 }, { - "epoch": 0.2, - "learning_rate": 4.0485541843077205e-05, - "loss": 0.3242, + "epoch": 0.05, + "learning_rate": 4.763718932462361e-05, + "loss": 0.3347, "step": 22130 }, { - "epoch": 0.2, - "learning_rate": 4.0481037744347355e-05, - "loss": 0.3297, + "epoch": 0.05, + "learning_rate": 4.763607078141429e-05, + "loss": 0.3401, "step": 22140 }, { - "epoch": 0.2, - "learning_rate": 4.047653364561751e-05, - "loss": 0.3311, + "epoch": 0.05, + "learning_rate": 4.7634952238204966e-05, + "loss": 0.3423, "step": 22150 }, { - "epoch": 0.2, - "learning_rate": 4.047202954688767e-05, - "loss": 0.3224, + "epoch": 0.05, + "learning_rate": 4.763383369499564e-05, + "loss": 0.3355, "step": 22160 }, { - "epoch": 0.2, - "learning_rate": 4.046752544815783e-05, - "loss": 0.3266, + "epoch": 0.05, + "learning_rate": 4.7632715151786315e-05, + "loss": 0.3337, "step": 22170 }, { - "epoch": 0.2, - "learning_rate": 4.0463021349427985e-05, - "loss": 0.3144, + "epoch": 0.05, + "learning_rate": 4.7631596608576986e-05, + "loss": 0.3357, "step": 22180 }, { - "epoch": 0.2, - "learning_rate": 4.0458517250698136e-05, - "loss": 0.3331, + "epoch": 0.05, + "learning_rate": 4.7630478065367664e-05, + "loss": 0.3383, "step": 22190 }, { - "epoch": 0.2, - "learning_rate": 4.0454013151968293e-05, - "loss": 0.3235, + "epoch": 0.05, + "learning_rate": 4.762935952215834e-05, + "loss": 0.333, "step": 22200 }, { - "epoch": 0.2, - "learning_rate": 4.044950905323845e-05, - "loss": 0.3265, + "epoch": 0.05, + "learning_rate": 4.762824097894902e-05, + "loss": 0.337, "step": 22210 }, { - "epoch": 0.2, - "learning_rate": 4.044545536438159e-05, - "loss": 0.3343, + "epoch": 0.05, + "learning_rate": 4.76271224357397e-05, + "loss": 0.3325, "step": 22220 }, { - "epoch": 0.2, - "learning_rate": 4.0440951265651745e-05, - "loss": 0.332, + "epoch": 0.05, + "learning_rate": 4.762600389253037e-05, + "loss": 0.3378, "step": 22230 }, { - "epoch": 0.2, - "learning_rate": 4.04364471669219e-05, - "loss": 0.322, + "epoch": 0.05, + "learning_rate": 4.762488534932105e-05, + "loss": 0.3381, "step": 22240 }, { - "epoch": 0.2, - "learning_rate": 4.043194306819206e-05, - "loss": 0.3236, + "epoch": 0.05, + "learning_rate": 4.7623766806111725e-05, + "loss": 0.3363, "step": 22250 }, { - "epoch": 0.2, - "learning_rate": 4.042743896946221e-05, - "loss": 0.3323, + "epoch": 0.05, + "learning_rate": 4.7622648262902396e-05, + "loss": 0.3324, "step": 22260 }, { - "epoch": 0.2, - "learning_rate": 4.042293487073237e-05, - "loss": 0.3214, + "epoch": 0.05, + "learning_rate": 4.7621529719693074e-05, + "loss": 0.3428, "step": 22270 }, { - "epoch": 0.2, - "learning_rate": 4.0418430772002526e-05, - "loss": 0.3247, + "epoch": 0.05, + "learning_rate": 4.7620411176483745e-05, + "loss": 0.3406, "step": 22280 }, { - "epoch": 0.2, - "learning_rate": 4.041392667327268e-05, - "loss": 0.3228, + "epoch": 0.05, + "learning_rate": 4.761929263327442e-05, + "loss": 0.3328, "step": 22290 }, { - "epoch": 0.2, - "learning_rate": 4.040942257454284e-05, - "loss": 0.3202, + "epoch": 0.05, + "learning_rate": 4.76181740900651e-05, + "loss": 0.3342, "step": 22300 }, { - "epoch": 0.2, - "learning_rate": 4.040491847581299e-05, - "loss": 0.3258, + "epoch": 0.05, + "learning_rate": 4.761705554685578e-05, + "loss": 0.3357, "step": 22310 }, { - "epoch": 0.2, - "learning_rate": 4.040041437708314e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.761593700364646e-05, + "loss": 0.3308, "step": 22320 }, { - "epoch": 0.2, - "learning_rate": 4.039591027835331e-05, - "loss": 0.3249, + "epoch": 0.05, + "learning_rate": 4.761481846043713e-05, + "loss": 0.3313, "step": 22330 }, { - "epoch": 0.2, - "learning_rate": 4.039140617962346e-05, - "loss": 0.3299, + "epoch": 0.05, + "learning_rate": 4.7613699917227806e-05, + "loss": 0.3293, "step": 22340 }, { - "epoch": 0.2, - "learning_rate": 4.0386902080893615e-05, - "loss": 0.331, + "epoch": 0.05, + "learning_rate": 4.761258137401848e-05, + "loss": 0.3348, "step": 22350 }, { - "epoch": 0.2, - "learning_rate": 4.038239798216377e-05, - "loss": 0.3334, + "epoch": 0.05, + "learning_rate": 4.7611462830809155e-05, + "loss": 0.337, "step": 22360 }, { - "epoch": 0.2, - "learning_rate": 4.037789388343392e-05, - "loss": 0.3193, + "epoch": 0.05, + "learning_rate": 4.761034428759983e-05, + "loss": 0.3352, "step": 22370 }, { - "epoch": 0.2, - "learning_rate": 4.037338978470409e-05, - "loss": 0.3308, + "epoch": 0.05, + "learning_rate": 4.7609225744390504e-05, + "loss": 0.3341, "step": 22380 }, { - "epoch": 0.2, - "learning_rate": 4.036888568597424e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.760810720118118e-05, + "loss": 0.3378, "step": 22390 }, { - "epoch": 0.2, - "learning_rate": 4.0364381587244396e-05, - "loss": 0.3233, + "epoch": 0.05, + "learning_rate": 4.760698865797186e-05, + "loss": 0.3346, "step": 22400 }, { - "epoch": 0.2, - "learning_rate": 4.035987748851455e-05, - "loss": 0.3292, + "epoch": 0.05, + "learning_rate": 4.760587011476254e-05, + "loss": 0.3418, "step": 22410 }, { - "epoch": 0.2, - "learning_rate": 4.0355373389784704e-05, - "loss": 0.3215, + "epoch": 0.05, + "learning_rate": 4.7604751571553216e-05, + "loss": 0.3344, "step": 22420 }, { - "epoch": 0.2, - "learning_rate": 4.035086929105486e-05, - "loss": 0.3234, + "epoch": 0.05, + "learning_rate": 4.760363302834389e-05, + "loss": 0.3364, "step": 22430 }, { - "epoch": 0.2, - "learning_rate": 4.034636519232502e-05, - "loss": 0.3274, + "epoch": 0.05, + "learning_rate": 4.7602514485134565e-05, + "loss": 0.3366, "step": 22440 }, { - "epoch": 0.2, - "learning_rate": 4.0341861093595176e-05, - "loss": 0.3207, + "epoch": 0.05, + "learning_rate": 4.7601395941925236e-05, + "loss": 0.3335, "step": 22450 }, { - "epoch": 0.2, - "learning_rate": 4.033735699486533e-05, - "loss": 0.3342, + "epoch": 0.05, + "learning_rate": 4.7600277398715914e-05, + "loss": 0.3308, "step": 22460 }, { - "epoch": 0.2, - "learning_rate": 4.0332852896135485e-05, - "loss": 0.3247, + "epoch": 0.05, + "learning_rate": 4.759915885550659e-05, + "loss": 0.331, "step": 22470 }, { - "epoch": 0.2, - "learning_rate": 4.032834879740564e-05, - "loss": 0.3293, + "epoch": 0.05, + "learning_rate": 4.759804031229726e-05, + "loss": 0.3372, "step": 22480 }, { - "epoch": 0.2, - "learning_rate": 4.032384469867579e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.759692176908794e-05, + "loss": 0.3333, "step": 22490 }, { - "epoch": 0.2, - "learning_rate": 4.031934059994596e-05, - "loss": 0.3196, + "epoch": 0.05, + "learning_rate": 4.759580322587862e-05, + "loss": 0.333, "step": 22500 }, { - "epoch": 0.2, - "learning_rate": 4.031483650121611e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.75946846826693e-05, + "loss": 0.3304, "step": 22510 }, { - "epoch": 0.2, - "learning_rate": 4.0310332402486265e-05, - "loss": 0.3225, + "epoch": 0.05, + "learning_rate": 4.7593566139459975e-05, + "loss": 0.3345, "step": 22520 }, { - "epoch": 0.2, - "learning_rate": 4.030582830375642e-05, - "loss": 0.3291, + "epoch": 0.05, + "learning_rate": 4.7592447596250646e-05, + "loss": 0.3309, "step": 22530 }, { - "epoch": 0.2, - "learning_rate": 4.0301324205026573e-05, - "loss": 0.3239, + "epoch": 0.05, + "learning_rate": 4.7591329053041324e-05, + "loss": 0.3363, "step": 22540 }, { - "epoch": 0.2, - "learning_rate": 4.029682010629674e-05, - "loss": 0.3267, + "epoch": 0.05, + "learning_rate": 4.7590210509831995e-05, + "loss": 0.341, "step": 22550 }, { - "epoch": 0.2, - "learning_rate": 4.029231600756689e-05, - "loss": 0.3242, + "epoch": 0.05, + "learning_rate": 4.758909196662267e-05, + "loss": 0.3309, "step": 22560 }, { - "epoch": 0.2, - "learning_rate": 4.028781190883704e-05, - "loss": 0.3183, + "epoch": 0.05, + "learning_rate": 4.758797342341335e-05, + "loss": 0.3341, "step": 22570 }, { - "epoch": 0.2, - "learning_rate": 4.0283307810107203e-05, - "loss": 0.3207, + "epoch": 0.05, + "learning_rate": 4.758696673452496e-05, + "loss": 0.335, "step": 22580 }, { - "epoch": 0.2, - "learning_rate": 4.0278803711377354e-05, - "loss": 0.3222, + "epoch": 0.05, + "learning_rate": 4.758584819131564e-05, + "loss": 0.3372, "step": 22590 }, { - "epoch": 0.2, - "learning_rate": 4.027429961264751e-05, - "loss": 0.3251, + "epoch": 0.05, + "learning_rate": 4.758472964810631e-05, + "loss": 0.3256, "step": 22600 }, { - "epoch": 0.2, - "learning_rate": 4.026979551391767e-05, - "loss": 0.3291, + "epoch": 0.05, + "learning_rate": 4.758361110489699e-05, + "loss": 0.335, "step": 22610 }, { - "epoch": 0.2, - "learning_rate": 4.026529141518782e-05, - "loss": 0.3279, + "epoch": 0.05, + "learning_rate": 4.758249256168766e-05, + "loss": 0.3283, "step": 22620 }, { - "epoch": 0.2, - "learning_rate": 4.026078731645798e-05, - "loss": 0.325, + "epoch": 0.05, + "learning_rate": 4.7581374018478336e-05, + "loss": 0.3407, "step": 22630 }, { - "epoch": 0.2, - "learning_rate": 4.0256283217728135e-05, - "loss": 0.3203, + "epoch": 0.05, + "learning_rate": 4.7580255475269014e-05, + "loss": 0.3358, "step": 22640 }, { - "epoch": 0.2, - "learning_rate": 4.025177911899829e-05, - "loss": 0.3268, + "epoch": 0.05, + "learning_rate": 4.7579136932059685e-05, + "loss": 0.3405, "step": 22650 }, { - "epoch": 0.2, - "learning_rate": 4.024727502026845e-05, - "loss": 0.3249, + "epoch": 0.05, + "learning_rate": 4.757801838885036e-05, + "loss": 0.3309, "step": 22660 }, { - "epoch": 0.2, - "learning_rate": 4.02427709215386e-05, - "loss": 0.3309, + "epoch": 0.05, + "learning_rate": 4.757689984564104e-05, + "loss": 0.3386, "step": 22670 }, { - "epoch": 0.2, - "learning_rate": 4.023826682280876e-05, - "loss": 0.3212, + "epoch": 0.05, + "learning_rate": 4.757578130243172e-05, + "loss": 0.3332, "step": 22680 }, { - "epoch": 0.2, - "learning_rate": 4.0233762724078915e-05, - "loss": 0.3226, + "epoch": 0.05, + "learning_rate": 4.75746627592224e-05, + "loss": 0.3329, "step": 22690 }, { - "epoch": 0.2, - "learning_rate": 4.022925862534907e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.757354421601307e-05, + "loss": 0.3291, "step": 22700 }, { - "epoch": 0.2, - "learning_rate": 4.0224754526619224e-05, - "loss": 0.335, + "epoch": 0.05, + "learning_rate": 4.7572425672803746e-05, + "loss": 0.3316, "step": 22710 }, { - "epoch": 0.2, - "learning_rate": 4.022025042788938e-05, - "loss": 0.3205, + "epoch": 0.05, + "learning_rate": 4.757130712959442e-05, + "loss": 0.3307, "step": 22720 }, { - "epoch": 0.2, - "learning_rate": 4.021574632915954e-05, - "loss": 0.3239, + "epoch": 0.05, + "learning_rate": 4.7570188586385095e-05, + "loss": 0.3286, "step": 22730 }, { - "epoch": 0.2, - "learning_rate": 4.021124223042969e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.7569070043175766e-05, + "loss": 0.3321, "step": 22740 }, { - "epoch": 0.2, - "learning_rate": 4.0206738131699854e-05, - "loss": 0.3204, + "epoch": 0.05, + "learning_rate": 4.7567951499966444e-05, + "loss": 0.3331, "step": 22750 }, { - "epoch": 0.2, - "learning_rate": 4.0202234032970004e-05, - "loss": 0.3269, + "epoch": 0.05, + "learning_rate": 4.756683295675712e-05, + "loss": 0.341, "step": 22760 }, { - "epoch": 0.2, - "learning_rate": 4.0197729934240155e-05, - "loss": 0.3226, + "epoch": 0.05, + "learning_rate": 4.756571441354779e-05, + "loss": 0.3353, "step": 22770 }, { - "epoch": 0.2, - "learning_rate": 4.019322583551032e-05, - "loss": 0.3194, + "epoch": 0.05, + "learning_rate": 4.756459587033847e-05, + "loss": 0.333, "step": 22780 }, { - "epoch": 0.2, - "learning_rate": 4.018872173678047e-05, - "loss": 0.3319, + "epoch": 0.05, + "learning_rate": 4.756347732712915e-05, + "loss": 0.3231, "step": 22790 }, { - "epoch": 0.2, - "learning_rate": 4.018421763805063e-05, - "loss": 0.323, + "epoch": 0.05, + "learning_rate": 4.756235878391983e-05, + "loss": 0.3357, "step": 22800 }, { - "epoch": 0.2, - "learning_rate": 4.0179713539320785e-05, - "loss": 0.3278, + "epoch": 0.05, + "learning_rate": 4.7561240240710505e-05, + "loss": 0.3378, "step": 22810 }, { - "epoch": 0.2, - "learning_rate": 4.0175209440590936e-05, - "loss": 0.3213, + "epoch": 0.05, + "learning_rate": 4.7560121697501176e-05, + "loss": 0.3312, "step": 22820 }, { - "epoch": 0.2, - "learning_rate": 4.01707053418611e-05, - "loss": 0.3211, + "epoch": 0.05, + "learning_rate": 4.7559003154291854e-05, + "loss": 0.3377, "step": 22830 }, { - "epoch": 0.2, - "learning_rate": 4.016620124313125e-05, - "loss": 0.32, + "epoch": 0.05, + "learning_rate": 4.7557884611082525e-05, + "loss": 0.334, "step": 22840 }, { - "epoch": 0.2, - "learning_rate": 4.016169714440141e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.75567660678732e-05, + "loss": 0.3335, "step": 22850 }, { - "epoch": 0.2, - "learning_rate": 4.0157193045671566e-05, - "loss": 0.3282, + "epoch": 0.05, + "learning_rate": 4.755564752466388e-05, + "loss": 0.3342, "step": 22860 }, { - "epoch": 0.2, - "learning_rate": 4.0152688946941716e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.755452898145455e-05, + "loss": 0.3296, "step": 22870 }, { - "epoch": 0.2, - "learning_rate": 4.0148184848211874e-05, - "loss": 0.3207, + "epoch": 0.05, + "learning_rate": 4.755341043824523e-05, + "loss": 0.3369, "step": 22880 }, { - "epoch": 0.2, - "learning_rate": 4.014368074948203e-05, - "loss": 0.3221, + "epoch": 0.05, + "learning_rate": 4.755229189503591e-05, + "loss": 0.3324, "step": 22890 }, { - "epoch": 0.2, - "learning_rate": 4.013917665075219e-05, - "loss": 0.3235, + "epoch": 0.05, + "learning_rate": 4.7551173351826586e-05, + "loss": 0.3342, "step": 22900 }, { - "epoch": 0.2, - "learning_rate": 4.013467255202234e-05, - "loss": 0.3242, + "epoch": 0.05, + "learning_rate": 4.7550054808617264e-05, + "loss": 0.3287, "step": 22910 }, { - "epoch": 0.2, - "learning_rate": 4.01301684532925e-05, - "loss": 0.3273, + "epoch": 0.05, + "learning_rate": 4.7548936265407935e-05, + "loss": 0.3279, "step": 22920 }, { - "epoch": 0.2, - "learning_rate": 4.0125664354562655e-05, - "loss": 0.3245, + "epoch": 0.05, + "learning_rate": 4.754781772219861e-05, + "loss": 0.3342, "step": 22930 }, { - "epoch": 0.2, - "learning_rate": 4.0121160255832805e-05, - "loss": 0.3207, + "epoch": 0.05, + "learning_rate": 4.7546699178989284e-05, + "loss": 0.3336, "step": 22940 }, { - "epoch": 0.2, - "learning_rate": 4.011665615710297e-05, - "loss": 0.3178, + "epoch": 0.05, + "learning_rate": 4.754558063577996e-05, + "loss": 0.3347, "step": 22950 }, { - "epoch": 0.2, - "learning_rate": 4.011215205837312e-05, - "loss": 0.3209, + "epoch": 0.05, + "learning_rate": 4.754446209257064e-05, + "loss": 0.3305, "step": 22960 }, { - "epoch": 0.21, - "learning_rate": 4.010764795964328e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.754334354936131e-05, + "loss": 0.3362, "step": 22970 }, { - "epoch": 0.21, - "learning_rate": 4.0103143860913435e-05, - "loss": 0.3171, + "epoch": 0.05, + "learning_rate": 4.754222500615199e-05, + "loss": 0.3299, "step": 22980 }, { - "epoch": 0.21, - "learning_rate": 4.0098639762183586e-05, - "loss": 0.3194, + "epoch": 0.05, + "learning_rate": 4.754110646294267e-05, + "loss": 0.3364, "step": 22990 }, { - "epoch": 0.21, - "learning_rate": 4.0094135663453744e-05, - "loss": 0.32, + "epoch": 0.05, + "learning_rate": 4.7539987919733345e-05, + "loss": 0.3283, "step": 23000 }, { - "epoch": 0.21, - "learning_rate": 4.00896315647239e-05, - "loss": 0.3213, + "epoch": 0.05, + "learning_rate": 4.753886937652402e-05, + "loss": 0.33, "step": 23010 }, { - "epoch": 0.21, - "learning_rate": 4.008512746599405e-05, - "loss": 0.322, + "epoch": 0.05, + "learning_rate": 4.7537750833314694e-05, + "loss": 0.3354, "step": 23020 }, { - "epoch": 0.21, - "learning_rate": 4.0080623367264216e-05, - "loss": 0.3218, + "epoch": 0.05, + "learning_rate": 4.753663229010537e-05, + "loss": 0.3369, "step": 23030 }, { - "epoch": 0.21, - "learning_rate": 4.007611926853437e-05, - "loss": 0.3196, + "epoch": 0.05, + "learning_rate": 4.753551374689604e-05, + "loss": 0.3298, "step": 23040 }, { - "epoch": 0.21, - "learning_rate": 4.0071615169804524e-05, - "loss": 0.3249, + "epoch": 0.05, + "learning_rate": 4.753439520368672e-05, + "loss": 0.3306, "step": 23050 }, { - "epoch": 0.21, - "learning_rate": 4.006711107107468e-05, - "loss": 0.3237, + "epoch": 0.05, + "learning_rate": 4.753327666047739e-05, + "loss": 0.3323, "step": 23060 }, { - "epoch": 0.21, - "learning_rate": 4.006260697234483e-05, - "loss": 0.318, + "epoch": 0.05, + "learning_rate": 4.753215811726807e-05, + "loss": 0.3341, "step": 23070 }, { - "epoch": 0.21, - "learning_rate": 4.005810287361499e-05, - "loss": 0.3252, + "epoch": 0.05, + "learning_rate": 4.753103957405875e-05, + "loss": 0.3281, "step": 23080 }, { - "epoch": 0.21, - "learning_rate": 4.005359877488515e-05, - "loss": 0.3189, + "epoch": 0.05, + "learning_rate": 4.7529921030849426e-05, + "loss": 0.328, "step": 23090 }, { - "epoch": 0.21, - "learning_rate": 4.0049094676155305e-05, - "loss": 0.3199, + "epoch": 0.05, + "learning_rate": 4.7528802487640104e-05, + "loss": 0.3331, "step": 23100 }, { - "epoch": 0.21, - "learning_rate": 4.004459057742546e-05, - "loss": 0.3179, + "epoch": 0.05, + "learning_rate": 4.7527683944430775e-05, + "loss": 0.3279, "step": 23110 }, { - "epoch": 0.21, - "learning_rate": 4.004008647869561e-05, - "loss": 0.3216, + "epoch": 0.05, + "learning_rate": 4.752656540122145e-05, + "loss": 0.3271, "step": 23120 }, { - "epoch": 0.21, - "learning_rate": 4.003558237996577e-05, - "loss": 0.3203, + "epoch": 0.05, + "learning_rate": 4.752544685801213e-05, + "loss": 0.3315, "step": 23130 }, { - "epoch": 0.21, - "learning_rate": 4.003107828123593e-05, - "loss": 0.3196, + "epoch": 0.05, + "learning_rate": 4.75243283148028e-05, + "loss": 0.3221, "step": 23140 }, { - "epoch": 0.21, - "learning_rate": 4.0026574182506086e-05, - "loss": 0.3151, + "epoch": 0.05, + "learning_rate": 4.752320977159348e-05, + "loss": 0.3324, "step": 23150 }, { - "epoch": 0.21, - "learning_rate": 4.0022070083776236e-05, - "loss": 0.3217, + "epoch": 0.05, + "learning_rate": 4.752209122838415e-05, + "loss": 0.3279, "step": 23160 }, { - "epoch": 0.21, - "learning_rate": 4.0017565985046394e-05, - "loss": 0.322, + "epoch": 0.05, + "learning_rate": 4.752097268517483e-05, + "loss": 0.3334, "step": 23170 }, { - "epoch": 0.21, - "learning_rate": 4.001306188631655e-05, - "loss": 0.3177, + "epoch": 0.05, + "learning_rate": 4.751985414196551e-05, + "loss": 0.3326, "step": 23180 }, { - "epoch": 0.21, - "learning_rate": 4.00085577875867e-05, - "loss": 0.323, + "epoch": 0.05, + "learning_rate": 4.751873559875618e-05, + "loss": 0.3314, "step": 23190 }, { - "epoch": 0.21, - "learning_rate": 4.0004053688856866e-05, - "loss": 0.3198, + "epoch": 0.05, + "learning_rate": 4.751761705554686e-05, + "loss": 0.3267, "step": 23200 }, { - "epoch": 0.21, - "learning_rate": 3.999954959012702e-05, - "loss": 0.3226, + "epoch": 0.05, + "learning_rate": 4.7516498512337534e-05, + "loss": 0.3314, "step": 23210 }, { - "epoch": 0.21, - "learning_rate": 3.999504549139717e-05, - "loss": 0.3186, + "epoch": 0.05, + "learning_rate": 4.751537996912821e-05, + "loss": 0.3285, "step": 23220 }, { - "epoch": 0.21, - "learning_rate": 3.999054139266733e-05, - "loss": 0.3177, + "epoch": 0.05, + "learning_rate": 4.751426142591889e-05, + "loss": 0.3349, "step": 23230 }, { - "epoch": 0.21, - "learning_rate": 3.998603729393748e-05, - "loss": 0.3241, + "epoch": 0.05, + "learning_rate": 4.751314288270956e-05, + "loss": 0.3335, "step": 23240 }, { - "epoch": 0.21, - "learning_rate": 3.998153319520764e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.751202433950024e-05, + "loss": 0.3335, "step": 23250 }, { - "epoch": 0.21, - "learning_rate": 3.99770290964778e-05, - "loss": 0.3224, + "epoch": 0.05, + "learning_rate": 4.751090579629091e-05, + "loss": 0.3265, "step": 23260 }, { - "epoch": 0.21, - "learning_rate": 3.997252499774795e-05, - "loss": 0.3214, + "epoch": 0.05, + "learning_rate": 4.750978725308159e-05, + "loss": 0.3297, "step": 23270 }, { - "epoch": 0.21, - "learning_rate": 3.996802089901811e-05, - "loss": 0.3302, + "epoch": 0.05, + "learning_rate": 4.7508668709872266e-05, + "loss": 0.3289, "step": 23280 }, { - "epoch": 0.21, - "learning_rate": 3.996351680028826e-05, - "loss": 0.3181, + "epoch": 0.05, + "learning_rate": 4.750755016666294e-05, + "loss": 0.327, "step": 23290 }, { - "epoch": 0.21, - "learning_rate": 3.995901270155842e-05, - "loss": 0.315, + "epoch": 0.05, + "learning_rate": 4.7506431623453615e-05, + "loss": 0.3274, "step": 23300 }, { - "epoch": 0.21, - "learning_rate": 3.995450860282858e-05, - "loss": 0.3283, + "epoch": 0.05, + "learning_rate": 4.750531308024429e-05, + "loss": 0.3324, "step": 23310 }, { - "epoch": 0.21, - "learning_rate": 3.995000450409873e-05, - "loss": 0.3227, + "epoch": 0.05, + "learning_rate": 4.750419453703497e-05, + "loss": 0.3312, "step": 23320 }, { - "epoch": 0.21, - "learning_rate": 3.9945500405368887e-05, - "loss": 0.3239, + "epoch": 0.05, + "learning_rate": 4.750307599382565e-05, + "loss": 0.3315, "step": 23330 }, { - "epoch": 0.21, - "learning_rate": 3.9940996306639044e-05, - "loss": 0.3177, + "epoch": 0.05, + "learning_rate": 4.750195745061632e-05, + "loss": 0.3352, "step": 23340 }, { - "epoch": 0.21, - "learning_rate": 3.99364922079092e-05, - "loss": 0.322, + "epoch": 0.05, + "learning_rate": 4.7500838907407e-05, + "loss": 0.3292, "step": 23350 }, { - "epoch": 0.21, - "learning_rate": 3.993198810917935e-05, - "loss": 0.3237, + "epoch": 0.05, + "learning_rate": 4.749972036419767e-05, + "loss": 0.3298, "step": 23360 }, { - "epoch": 0.21, - "learning_rate": 3.992748401044951e-05, - "loss": 0.3199, + "epoch": 0.05, + "learning_rate": 4.749860182098835e-05, + "loss": 0.3335, "step": 23370 }, { - "epoch": 0.21, - "learning_rate": 3.992297991171967e-05, - "loss": 0.3228, + "epoch": 0.05, + "learning_rate": 4.749748327777902e-05, + "loss": 0.3221, "step": 23380 }, { - "epoch": 0.21, - "learning_rate": 3.9918475812989825e-05, - "loss": 0.3209, + "epoch": 0.05, + "learning_rate": 4.7496364734569696e-05, + "loss": 0.3386, "step": 23390 }, { - "epoch": 0.21, - "learning_rate": 3.991397171425998e-05, - "loss": 0.324, + "epoch": 0.05, + "learning_rate": 4.7495246191360374e-05, + "loss": 0.3261, "step": 23400 }, { - "epoch": 0.21, - "learning_rate": 3.990946761553013e-05, - "loss": 0.3147, + "epoch": 0.05, + "learning_rate": 4.749412764815105e-05, + "loss": 0.3294, "step": 23410 }, { - "epoch": 0.21, - "learning_rate": 3.990496351680029e-05, - "loss": 0.3206, + "epoch": 0.05, + "learning_rate": 4.749300910494173e-05, + "loss": 0.331, "step": 23420 }, { - "epoch": 0.21, - "learning_rate": 3.990045941807045e-05, - "loss": 0.3182, + "epoch": 0.05, + "learning_rate": 4.74918905617324e-05, + "loss": 0.3272, "step": 23430 }, { - "epoch": 0.21, - "learning_rate": 3.98959553193406e-05, - "loss": 0.3221, + "epoch": 0.05, + "learning_rate": 4.749077201852308e-05, + "loss": 0.328, "step": 23440 }, { - "epoch": 0.21, - "learning_rate": 3.9891451220610756e-05, - "loss": 0.3219, + "epoch": 0.05, + "learning_rate": 4.7489653475313757e-05, + "loss": 0.3326, "step": 23450 }, { - "epoch": 0.21, - "learning_rate": 3.9886947121880914e-05, - "loss": 0.3221, + "epoch": 0.05, + "learning_rate": 4.748853493210443e-05, + "loss": 0.3281, "step": 23460 }, { - "epoch": 0.21, - "learning_rate": 3.9882443023151064e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.7487416388895106e-05, + "loss": 0.3319, "step": 23470 }, { - "epoch": 0.21, - "learning_rate": 3.987793892442123e-05, - "loss": 0.3204, + "epoch": 0.05, + "learning_rate": 4.748629784568578e-05, + "loss": 0.335, "step": 23480 }, { - "epoch": 0.21, - "learning_rate": 3.987343482569138e-05, - "loss": 0.3179, + "epoch": 0.05, + "learning_rate": 4.7485179302476455e-05, + "loss": 0.3309, "step": 23490 }, { - "epoch": 0.21, - "learning_rate": 3.986893072696154e-05, - "loss": 0.3212, + "epoch": 0.05, + "learning_rate": 4.748406075926713e-05, + "loss": 0.3285, "step": 23500 }, { - "epoch": 0.21, - "learning_rate": 3.9864426628231694e-05, - "loss": 0.3177, + "epoch": 0.05, + "learning_rate": 4.748294221605781e-05, + "loss": 0.332, "step": 23510 }, { - "epoch": 0.21, - "learning_rate": 3.9859922529501845e-05, - "loss": 0.3218, + "epoch": 0.05, + "learning_rate": 4.748182367284849e-05, + "loss": 0.3365, "step": 23520 }, { - "epoch": 0.21, - "learning_rate": 3.985541843077201e-05, - "loss": 0.3161, + "epoch": 0.05, + "learning_rate": 4.748070512963916e-05, + "loss": 0.3319, "step": 23530 }, { - "epoch": 0.21, - "learning_rate": 3.985091433204216e-05, - "loss": 0.3164, + "epoch": 0.05, + "learning_rate": 4.747958658642984e-05, + "loss": 0.3342, "step": 23540 }, { - "epoch": 0.21, - "learning_rate": 3.984641023331232e-05, - "loss": 0.3243, + "epoch": 0.05, + "learning_rate": 4.7478468043220515e-05, + "loss": 0.3309, "step": 23550 }, { - "epoch": 0.21, - "learning_rate": 3.9841906134582475e-05, - "loss": 0.321, + "epoch": 0.05, + "learning_rate": 4.7477349500011187e-05, + "loss": 0.329, "step": 23560 }, { - "epoch": 0.21, - "learning_rate": 3.9837402035852626e-05, - "loss": 0.3203, + "epoch": 0.05, + "learning_rate": 4.7476230956801865e-05, + "loss": 0.3359, "step": 23570 }, { - "epoch": 0.21, - "learning_rate": 3.983289793712278e-05, - "loss": 0.3165, + "epoch": 0.05, + "learning_rate": 4.7475112413592536e-05, + "loss": 0.3297, "step": 23580 }, { - "epoch": 0.21, - "learning_rate": 3.982839383839294e-05, - "loss": 0.3108, + "epoch": 0.05, + "learning_rate": 4.7473993870383214e-05, + "loss": 0.3326, "step": 23590 }, { - "epoch": 0.21, - "learning_rate": 3.98238897396631e-05, - "loss": 0.3153, + "epoch": 0.05, + "learning_rate": 4.747287532717389e-05, + "loss": 0.3316, "step": 23600 }, { - "epoch": 0.21, - "learning_rate": 3.981938564093325e-05, - "loss": 0.3238, + "epoch": 0.05, + "learning_rate": 4.747175678396456e-05, + "loss": 0.3317, "step": 23610 }, { - "epoch": 0.21, - "learning_rate": 3.9814881542203406e-05, - "loss": 0.3163, + "epoch": 0.05, + "learning_rate": 4.747063824075525e-05, + "loss": 0.3186, "step": 23620 }, { - "epoch": 0.21, - "learning_rate": 3.9810377443473564e-05, - "loss": 0.3164, + "epoch": 0.05, + "learning_rate": 4.746951969754592e-05, + "loss": 0.3316, "step": 23630 }, { - "epoch": 0.21, - "learning_rate": 3.9805873344743715e-05, - "loss": 0.3169, + "epoch": 0.05, + "learning_rate": 4.7468401154336596e-05, + "loss": 0.3331, "step": 23640 }, { - "epoch": 0.21, - "learning_rate": 3.980136924601387e-05, - "loss": 0.3191, + "epoch": 0.05, + "learning_rate": 4.7467282611127274e-05, + "loss": 0.3295, "step": 23650 }, { - "epoch": 0.21, - "learning_rate": 3.979686514728403e-05, - "loss": 0.3203, + "epoch": 0.05, + "learning_rate": 4.7466164067917946e-05, + "loss": 0.334, "step": 23660 }, { - "epoch": 0.21, - "learning_rate": 3.979236104855419e-05, - "loss": 0.3167, + "epoch": 0.05, + "learning_rate": 4.7465045524708623e-05, + "loss": 0.3301, "step": 23670 }, { - "epoch": 0.21, - "learning_rate": 3.9787856949824345e-05, - "loss": 0.3174, + "epoch": 0.05, + "learning_rate": 4.7463926981499295e-05, + "loss": 0.3335, "step": 23680 }, { - "epoch": 0.21, - "learning_rate": 3.9783352851094495e-05, - "loss": 0.3174, + "epoch": 0.05, + "learning_rate": 4.746280843828997e-05, + "loss": 0.3297, "step": 23690 }, { - "epoch": 0.21, - "learning_rate": 3.977884875236465e-05, - "loss": 0.3175, + "epoch": 0.05, + "learning_rate": 4.7461689895080644e-05, + "loss": 0.3281, "step": 23700 }, { - "epoch": 0.21, - "learning_rate": 3.977434465363481e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.746057135187132e-05, + "loss": 0.3285, "step": 23710 }, { - "epoch": 0.21, - "learning_rate": 3.976984055490496e-05, - "loss": 0.3225, + "epoch": 0.05, + "learning_rate": 4.7459452808662e-05, + "loss": 0.3357, "step": 23720 }, { - "epoch": 0.21, - "learning_rate": 3.9765336456175125e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.745833426545268e-05, + "loss": 0.3261, "step": 23730 }, { - "epoch": 0.21, - "learning_rate": 3.9760832357445276e-05, - "loss": 0.3256, + "epoch": 0.05, + "learning_rate": 4.7457215722243355e-05, + "loss": 0.3275, "step": 23740 }, { - "epoch": 0.21, - "learning_rate": 3.9756328258715433e-05, - "loss": 0.3223, + "epoch": 0.05, + "learning_rate": 4.7456097179034027e-05, + "loss": 0.323, "step": 23750 }, { - "epoch": 0.21, - "learning_rate": 3.975182415998559e-05, - "loss": 0.3194, + "epoch": 0.05, + "learning_rate": 4.7454978635824705e-05, + "loss": 0.3257, "step": 23760 }, { - "epoch": 0.21, - "learning_rate": 3.974732006125574e-05, - "loss": 0.3192, + "epoch": 0.05, + "learning_rate": 4.745386009261538e-05, + "loss": 0.3245, "step": 23770 }, { - "epoch": 0.21, - "learning_rate": 3.97428159625259e-05, - "loss": 0.3152, + "epoch": 0.05, + "learning_rate": 4.7452741549406054e-05, + "loss": 0.3288, "step": 23780 }, { - "epoch": 0.21, - "learning_rate": 3.973831186379606e-05, - "loss": 0.3165, + "epoch": 0.05, + "learning_rate": 4.745162300619673e-05, + "loss": 0.3227, "step": 23790 }, { - "epoch": 0.21, - "learning_rate": 3.9733807765066214e-05, - "loss": 0.3174, + "epoch": 0.05, + "learning_rate": 4.74505044629874e-05, + "loss": 0.3302, "step": 23800 }, { - "epoch": 0.21, - "learning_rate": 3.972930366633637e-05, - "loss": 0.3163, + "epoch": 0.05, + "learning_rate": 4.744938591977808e-05, + "loss": 0.3238, "step": 23810 }, { - "epoch": 0.21, - "learning_rate": 3.972479956760652e-05, - "loss": 0.3199, + "epoch": 0.05, + "learning_rate": 4.744826737656876e-05, + "loss": 0.3283, "step": 23820 }, { - "epoch": 0.21, - "learning_rate": 3.972029546887668e-05, - "loss": 0.3178, + "epoch": 0.05, + "learning_rate": 4.7447148833359436e-05, + "loss": 0.3271, "step": 23830 }, { - "epoch": 0.21, - "learning_rate": 3.971579137014684e-05, - "loss": 0.3179, + "epoch": 0.05, + "learning_rate": 4.7446030290150114e-05, + "loss": 0.3268, "step": 23840 }, { - "epoch": 0.21, - "learning_rate": 3.9711287271416995e-05, - "loss": 0.3149, + "epoch": 0.05, + "learning_rate": 4.7444911746940786e-05, + "loss": 0.3283, "step": 23850 }, { - "epoch": 0.21, - "learning_rate": 3.9706783172687146e-05, - "loss": 0.3227, + "epoch": 0.05, + "learning_rate": 4.7443793203731463e-05, + "loss": 0.323, "step": 23860 }, { - "epoch": 0.21, - "learning_rate": 3.97022790739573e-05, - "loss": 0.3264, + "epoch": 0.05, + "learning_rate": 4.744267466052214e-05, + "loss": 0.329, "step": 23870 }, { - "epoch": 0.21, - "learning_rate": 3.969777497522746e-05, - "loss": 0.3189, + "epoch": 0.05, + "learning_rate": 4.744155611731281e-05, + "loss": 0.3278, "step": 23880 }, { - "epoch": 0.21, - "learning_rate": 3.969327087649761e-05, - "loss": 0.318, + "epoch": 0.05, + "learning_rate": 4.744043757410349e-05, + "loss": 0.3255, "step": 23890 }, { - "epoch": 0.21, - "learning_rate": 3.968876677776777e-05, - "loss": 0.3143, + "epoch": 0.05, + "learning_rate": 4.743931903089416e-05, + "loss": 0.3302, "step": 23900 }, { - "epoch": 0.21, - "learning_rate": 3.9684262679037926e-05, - "loss": 0.3224, + "epoch": 0.05, + "learning_rate": 4.743820048768484e-05, + "loss": 0.3257, "step": 23910 }, { - "epoch": 0.21, - "learning_rate": 3.967975858030808e-05, - "loss": 0.323, + "epoch": 0.05, + "learning_rate": 4.743708194447552e-05, + "loss": 0.331, "step": 23920 }, { - "epoch": 0.21, - "learning_rate": 3.967525448157824e-05, - "loss": 0.3143, + "epoch": 0.05, + "learning_rate": 4.7435963401266195e-05, + "loss": 0.3275, "step": 23930 }, { - "epoch": 0.21, - "learning_rate": 3.967075038284839e-05, - "loss": 0.3161, + "epoch": 0.05, + "learning_rate": 4.743484485805687e-05, + "loss": 0.3306, "step": 23940 }, { - "epoch": 0.21, - "learning_rate": 3.966624628411855e-05, - "loss": 0.3206, + "epoch": 0.05, + "learning_rate": 4.7433726314847544e-05, + "loss": 0.3293, "step": 23950 }, { - "epoch": 0.21, - "learning_rate": 3.966174218538871e-05, - "loss": 0.3204, + "epoch": 0.05, + "learning_rate": 4.743260777163822e-05, + "loss": 0.3275, "step": 23960 }, { - "epoch": 0.21, - "learning_rate": 3.965723808665886e-05, - "loss": 0.3105, + "epoch": 0.05, + "learning_rate": 4.74314892284289e-05, + "loss": 0.3313, "step": 23970 }, { - "epoch": 0.21, - "learning_rate": 3.965273398792902e-05, - "loss": 0.315, + "epoch": 0.05, + "learning_rate": 4.743037068521957e-05, + "loss": 0.332, "step": 23980 }, { - "epoch": 0.21, - "learning_rate": 3.964822988919917e-05, - "loss": 0.3221, + "epoch": 0.05, + "learning_rate": 4.742925214201025e-05, + "loss": 0.3262, "step": 23990 }, { - "epoch": 0.21, - "learning_rate": 3.964372579046933e-05, - "loss": 0.3177, - "step": 24000 - }, - { - "epoch": 0.21, - "eval_NEIMS_canon_smiles": 0.9376666666666666, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.007333333333333333, - "eval_NEIMS_daylight_tanimoto_simil": 0.3685876987924181, - "eval_NEIMS_exact_mols": 0.007316666666666667, - "eval_NEIMS_exact_smiles": 0.007, - "eval_NEIMS_loss": 0.32910066843032837, - "eval_NEIMS_matched_formulas": 0.34065, - "eval_NEIMS_morgan_tanimoto_simil": 0.26411947676764336, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.007366666666666666, - "eval_NEIMS_runtime": 718.8898, - "eval_NEIMS_samples_per_second": 83.462, - "eval_NEIMS_steps_per_second": 1.305, - "step": 24000 - }, - { - "epoch": 0.21, - "eval_RASSP_canon_smiles": 0.9262029585601229, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.016562593915918123, - "eval_RASSP_daylight_tanimoto_simil": 0.4282559377231019, - "eval_RASSP_exact_mols": 0.01652920158947474, - "eval_RASSP_exact_smiles": 0.01564430493872508, - "eval_RASSP_loss": 0.2825922966003418, - "eval_RASSP_matched_formulas": 0.4687781747754366, - "eval_RASSP_morgan_tanimoto_simil": 0.2914407359801654, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.016562593915918123, - "eval_RASSP_runtime": 825.2247, - "eval_RASSP_samples_per_second": 72.579, - "eval_RASSP_steps_per_second": 1.134, - "step": 24000 - }, - { - "epoch": 0.21, - "eval_NIST_canon_smiles": 0.9001313127728289, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.002768215210987685, - "eval_NIST_daylight_tanimoto_simil": 0.23418501426051763, - "eval_NIST_exact_mols": 0.0026972353337828725, - "eval_NIST_exact_smiles": 0.0025907655179756538, - "eval_NIST_loss": 1.490809440612793, - "eval_NIST_matched_formulas": 0.03726443553252653, - "eval_NIST_morgan_tanimoto_simil": 0.1899051613413322, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.002768215210987685, - "eval_NIST_runtime": 446.8802, - "eval_NIST_samples_per_second": 63.053, - "eval_NIST_steps_per_second": 0.987, + "epoch": 0.05, + "learning_rate": 4.742813359880092e-05, + "loss": 0.3275, "step": 24000 }, { - "epoch": 0.21, - "learning_rate": 3.963922169173949e-05, - "loss": 0.316, + "epoch": 0.05, + "learning_rate": 4.74270150555916e-05, + "loss": 0.3277, "step": 24010 }, { - "epoch": 0.21, - "learning_rate": 3.963471759300964e-05, - "loss": 0.319, + "epoch": 0.05, + "learning_rate": 4.742589651238227e-05, + "loss": 0.3251, "step": 24020 }, { - "epoch": 0.21, - "learning_rate": 3.9630213494279796e-05, - "loss": 0.3164, + "epoch": 0.05, + "learning_rate": 4.7424777969172954e-05, + "loss": 0.3271, "step": 24030 }, { - "epoch": 0.21, - "learning_rate": 3.962570939554995e-05, - "loss": 0.3254, + "epoch": 0.05, + "learning_rate": 4.742365942596363e-05, + "loss": 0.3344, "step": 24040 }, { - "epoch": 0.21, - "learning_rate": 3.962120529682011e-05, - "loss": 0.3206, + "epoch": 0.05, + "learning_rate": 4.7422540882754303e-05, + "loss": 0.3293, "step": 24050 }, { - "epoch": 0.21, - "learning_rate": 3.961670119809026e-05, - "loss": 0.3253, + "epoch": 0.05, + "learning_rate": 4.742142233954498e-05, + "loss": 0.3287, "step": 24060 }, { - "epoch": 0.21, - "learning_rate": 3.961219709936042e-05, - "loss": 0.3162, + "epoch": 0.05, + "learning_rate": 4.742030379633565e-05, + "loss": 0.3276, "step": 24070 }, { - "epoch": 0.21, - "learning_rate": 3.9607693000630577e-05, - "loss": 0.3183, + "epoch": 0.05, + "learning_rate": 4.741918525312633e-05, + "loss": 0.3275, "step": 24080 }, { - "epoch": 0.22, - "learning_rate": 3.9603188901900734e-05, - "loss": 0.3215, + "epoch": 0.05, + "learning_rate": 4.741806670991701e-05, + "loss": 0.334, "step": 24090 }, { - "epoch": 0.22, - "learning_rate": 3.9598684803170885e-05, - "loss": 0.3141, + "epoch": 0.05, + "learning_rate": 4.741694816670768e-05, + "loss": 0.3267, "step": 24100 }, { - "epoch": 0.22, - "learning_rate": 3.959418070444104e-05, - "loss": 0.3205, + "epoch": 0.05, + "learning_rate": 4.741582962349836e-05, + "loss": 0.3324, "step": 24110 }, { - "epoch": 0.22, - "learning_rate": 3.95896766057112e-05, - "loss": 0.3134, + "epoch": 0.05, + "learning_rate": 4.741471108028903e-05, + "loss": 0.3279, "step": 24120 }, { - "epoch": 0.22, - "learning_rate": 3.958517250698136e-05, - "loss": 0.3169, + "epoch": 0.05, + "learning_rate": 4.7413592537079707e-05, + "loss": 0.325, "step": 24130 }, { - "epoch": 0.22, - "learning_rate": 3.958066840825151e-05, - "loss": 0.3232, + "epoch": 0.05, + "learning_rate": 4.7412473993870384e-05, + "loss": 0.3296, "step": 24140 }, { - "epoch": 0.22, - "learning_rate": 3.9576164309521665e-05, - "loss": 0.3156, + "epoch": 0.05, + "learning_rate": 4.741135545066106e-05, + "loss": 0.3237, "step": 24150 }, { - "epoch": 0.22, - "learning_rate": 3.957166021079182e-05, - "loss": 0.3207, + "epoch": 0.05, + "learning_rate": 4.741023690745174e-05, + "loss": 0.3277, "step": 24160 }, { - "epoch": 0.22, - "learning_rate": 3.9567156112061974e-05, - "loss": 0.3196, + "epoch": 0.05, + "learning_rate": 4.740911836424241e-05, + "loss": 0.3264, "step": 24170 }, { - "epoch": 0.22, - "learning_rate": 3.956265201333214e-05, - "loss": 0.3154, + "epoch": 0.05, + "learning_rate": 4.740799982103309e-05, + "loss": 0.3266, "step": 24180 }, { - "epoch": 0.22, - "learning_rate": 3.955814791460229e-05, - "loss": 0.318, + "epoch": 0.05, + "learning_rate": 4.740688127782377e-05, + "loss": 0.328, "step": 24190 }, { - "epoch": 0.22, - "learning_rate": 3.9553643815872446e-05, - "loss": 0.315, + "epoch": 0.05, + "learning_rate": 4.740576273461444e-05, + "loss": 0.3299, "step": 24200 }, { - "epoch": 0.22, - "learning_rate": 3.9549139717142604e-05, - "loss": 0.3078, + "epoch": 0.05, + "learning_rate": 4.7404644191405116e-05, + "loss": 0.321, "step": 24210 }, { - "epoch": 0.22, - "learning_rate": 3.9544635618412754e-05, - "loss": 0.3179, + "epoch": 0.05, + "learning_rate": 4.740352564819579e-05, + "loss": 0.3248, "step": 24220 }, { - "epoch": 0.22, - "learning_rate": 3.954013151968292e-05, - "loss": 0.316, + "epoch": 0.05, + "learning_rate": 4.7402407104986465e-05, + "loss": 0.3305, "step": 24230 }, { - "epoch": 0.22, - "learning_rate": 3.953562742095307e-05, - "loss": 0.3144, + "epoch": 0.05, + "learning_rate": 4.740128856177714e-05, + "loss": 0.3315, "step": 24240 }, { - "epoch": 0.22, - "learning_rate": 3.953112332222323e-05, - "loss": 0.3149, + "epoch": 0.05, + "learning_rate": 4.740017001856782e-05, + "loss": 0.3247, "step": 24250 }, { - "epoch": 0.22, - "learning_rate": 3.9526619223493384e-05, - "loss": 0.3248, + "epoch": 0.05, + "learning_rate": 4.73990514753585e-05, + "loss": 0.3324, "step": 24260 }, { - "epoch": 0.22, - "learning_rate": 3.9522115124763535e-05, - "loss": 0.3198, + "epoch": 0.05, + "learning_rate": 4.739793293214917e-05, + "loss": 0.3294, "step": 24270 }, { - "epoch": 0.22, - "learning_rate": 3.951761102603369e-05, - "loss": 0.313, + "epoch": 0.05, + "learning_rate": 4.739681438893985e-05, + "loss": 0.3246, "step": 24280 }, { - "epoch": 0.22, - "learning_rate": 3.951355733717683e-05, - "loss": 0.3137, + "epoch": 0.05, + "learning_rate": 4.7395695845730526e-05, + "loss": 0.3252, "step": 24290 }, { - "epoch": 0.22, - "learning_rate": 3.9509053238446994e-05, - "loss": 0.3215, + "epoch": 0.05, + "learning_rate": 4.73945773025212e-05, + "loss": 0.331, "step": 24300 }, { - "epoch": 0.22, - "learning_rate": 3.9504549139717144e-05, - "loss": 0.3178, + "epoch": 0.05, + "learning_rate": 4.7393458759311875e-05, + "loss": 0.3224, "step": 24310 }, { - "epoch": 0.22, - "learning_rate": 3.95000450409873e-05, - "loss": 0.3239, + "epoch": 0.05, + "learning_rate": 4.7392340216102546e-05, + "loss": 0.3308, "step": 24320 }, { - "epoch": 0.22, - "learning_rate": 3.949554094225746e-05, - "loss": 0.3224, + "epoch": 0.05, + "learning_rate": 4.7391221672893224e-05, + "loss": 0.3261, "step": 24330 }, { - "epoch": 0.22, - "learning_rate": 3.949103684352761e-05, - "loss": 0.314, + "epoch": 0.05, + "learning_rate": 4.73901031296839e-05, + "loss": 0.328, "step": 24340 }, { - "epoch": 0.22, - "learning_rate": 3.948653274479777e-05, - "loss": 0.3155, + "epoch": 0.05, + "learning_rate": 4.738898458647458e-05, + "loss": 0.3206, "step": 24350 }, { - "epoch": 0.22, - "learning_rate": 3.9482028646067925e-05, - "loss": 0.3202, + "epoch": 0.05, + "learning_rate": 4.738786604326526e-05, + "loss": 0.3223, "step": 24360 }, { - "epoch": 0.22, - "learning_rate": 3.947752454733808e-05, - "loss": 0.3158, + "epoch": 0.05, + "learning_rate": 4.738674750005593e-05, + "loss": 0.3278, "step": 24370 }, { - "epoch": 0.22, - "learning_rate": 3.947302044860823e-05, - "loss": 0.3103, + "epoch": 0.05, + "learning_rate": 4.738562895684661e-05, + "loss": 0.3263, "step": 24380 }, { - "epoch": 0.22, - "learning_rate": 3.946851634987839e-05, - "loss": 0.3179, + "epoch": 0.05, + "learning_rate": 4.738451041363728e-05, + "loss": 0.3251, "step": 24390 }, { - "epoch": 0.22, - "learning_rate": 3.946401225114855e-05, - "loss": 0.3134, + "epoch": 0.05, + "learning_rate": 4.7383391870427956e-05, + "loss": 0.3248, "step": 24400 }, { - "epoch": 0.22, - "learning_rate": 3.94595081524187e-05, - "loss": 0.3134, + "epoch": 0.05, + "learning_rate": 4.7382273327218634e-05, + "loss": 0.3241, "step": 24410 }, { - "epoch": 0.22, - "learning_rate": 3.9455004053688857e-05, - "loss": 0.3138, + "epoch": 0.05, + "learning_rate": 4.7381154784009305e-05, + "loss": 0.3302, "step": 24420 }, { - "epoch": 0.22, - "learning_rate": 3.9450499954959014e-05, - "loss": 0.3162, + "epoch": 0.05, + "learning_rate": 4.738003624079998e-05, + "loss": 0.3305, "step": 24430 }, { - "epoch": 0.22, - "learning_rate": 3.944599585622917e-05, - "loss": 0.321, + "epoch": 0.05, + "learning_rate": 4.737891769759066e-05, + "loss": 0.3228, "step": 24440 }, { - "epoch": 0.22, - "learning_rate": 3.944149175749933e-05, - "loss": 0.3236, + "epoch": 0.05, + "learning_rate": 4.737779915438134e-05, + "loss": 0.3286, "step": 24450 }, { - "epoch": 0.22, - "learning_rate": 3.943698765876948e-05, - "loss": 0.3186, + "epoch": 0.05, + "learning_rate": 4.737668061117202e-05, + "loss": 0.3271, "step": 24460 }, { - "epoch": 0.22, - "learning_rate": 3.943248356003964e-05, - "loss": 0.3133, + "epoch": 0.05, + "learning_rate": 4.737556206796269e-05, + "loss": 0.3219, "step": 24470 }, { - "epoch": 0.22, - "learning_rate": 3.9427979461309795e-05, - "loss": 0.3145, + "epoch": 0.05, + "learning_rate": 4.7374443524753366e-05, + "loss": 0.3258, "step": 24480 }, { - "epoch": 0.22, - "learning_rate": 3.9423475362579945e-05, - "loss": 0.3145, + "epoch": 0.05, + "learning_rate": 4.737332498154404e-05, + "loss": 0.3293, "step": 24490 }, { - "epoch": 0.22, - "learning_rate": 3.941897126385011e-05, - "loss": 0.3196, + "epoch": 0.05, + "learning_rate": 4.7372206438334715e-05, + "loss": 0.3233, "step": 24500 }, { - "epoch": 0.22, - "learning_rate": 3.941446716512026e-05, - "loss": 0.3101, + "epoch": 0.05, + "learning_rate": 4.737108789512539e-05, + "loss": 0.327, "step": 24510 }, { - "epoch": 0.22, - "learning_rate": 3.940996306639042e-05, - "loss": 0.3182, + "epoch": 0.05, + "learning_rate": 4.7369969351916064e-05, + "loss": 0.324, "step": 24520 }, { - "epoch": 0.22, - "learning_rate": 3.9405458967660575e-05, - "loss": 0.3143, + "epoch": 0.05, + "learning_rate": 4.736885080870674e-05, + "loss": 0.3253, "step": 24530 }, { - "epoch": 0.22, - "learning_rate": 3.9400954868930726e-05, - "loss": 0.312, + "epoch": 0.05, + "learning_rate": 4.7367732265497413e-05, + "loss": 0.3198, "step": 24540 }, { - "epoch": 0.22, - "learning_rate": 3.9396450770200884e-05, - "loss": 0.3163, + "epoch": 0.05, + "learning_rate": 4.736661372228809e-05, + "loss": 0.3276, "step": 24550 }, { - "epoch": 0.22, - "learning_rate": 3.939194667147104e-05, - "loss": 0.3113, + "epoch": 0.05, + "learning_rate": 4.736549517907877e-05, + "loss": 0.3226, "step": 24560 }, { - "epoch": 0.22, - "learning_rate": 3.93874425727412e-05, - "loss": 0.3151, + "epoch": 0.05, + "learning_rate": 4.736437663586945e-05, + "loss": 0.3287, "step": 24570 }, { - "epoch": 0.22, - "learning_rate": 3.9382938474011356e-05, - "loss": 0.3056, + "epoch": 0.05, + "learning_rate": 4.7363258092660125e-05, + "loss": 0.3242, "step": 24580 }, { - "epoch": 0.22, - "learning_rate": 3.937843437528151e-05, - "loss": 0.3195, + "epoch": 0.05, + "learning_rate": 4.7362139549450796e-05, + "loss": 0.3294, "step": 24590 }, { - "epoch": 0.22, - "learning_rate": 3.9373930276551664e-05, - "loss": 0.3125, + "epoch": 0.05, + "learning_rate": 4.7361021006241474e-05, + "loss": 0.327, "step": 24600 }, { - "epoch": 0.22, - "learning_rate": 3.936942617782182e-05, - "loss": 0.3172, + "epoch": 0.05, + "learning_rate": 4.735990246303215e-05, + "loss": 0.3281, "step": 24610 }, { - "epoch": 0.22, - "learning_rate": 3.936492207909198e-05, - "loss": 0.3199, + "epoch": 0.05, + "learning_rate": 4.735878391982282e-05, + "loss": 0.3201, "step": 24620 }, { - "epoch": 0.22, - "learning_rate": 3.936041798036213e-05, - "loss": 0.3148, + "epoch": 0.05, + "learning_rate": 4.735777723093444e-05, + "loss": 0.3248, "step": 24630 }, { - "epoch": 0.22, - "learning_rate": 3.935591388163229e-05, - "loss": 0.3155, + "epoch": 0.05, + "learning_rate": 4.735665868772511e-05, + "loss": 0.3269, "step": 24640 }, { - "epoch": 0.22, - "learning_rate": 3.9351409782902445e-05, - "loss": 0.3131, + "epoch": 0.06, + "learning_rate": 4.735554014451579e-05, + "loss": 0.3208, "step": 24650 }, { - "epoch": 0.22, - "learning_rate": 3.9346905684172596e-05, - "loss": 0.3094, + "epoch": 0.06, + "learning_rate": 4.735442160130646e-05, + "loss": 0.3252, "step": 24660 }, { - "epoch": 0.22, - "learning_rate": 3.934240158544275e-05, - "loss": 0.3178, + "epoch": 0.06, + "learning_rate": 4.735330305809714e-05, + "loss": 0.3237, "step": 24670 }, { - "epoch": 0.22, - "learning_rate": 3.933789748671291e-05, - "loss": 0.3211, + "epoch": 0.06, + "learning_rate": 4.7352184514887815e-05, + "loss": 0.3278, "step": 24680 }, { - "epoch": 0.22, - "learning_rate": 3.933339338798306e-05, - "loss": 0.3188, + "epoch": 0.06, + "learning_rate": 4.7351065971678486e-05, + "loss": 0.3215, "step": 24690 }, { - "epoch": 0.22, - "learning_rate": 3.9328889289253226e-05, - "loss": 0.3162, + "epoch": 0.06, + "learning_rate": 4.7349947428469164e-05, + "loss": 0.3284, "step": 24700 }, { - "epoch": 0.22, - "learning_rate": 3.9324385190523376e-05, - "loss": 0.3115, + "epoch": 0.06, + "learning_rate": 4.7348828885259835e-05, + "loss": 0.323, "step": 24710 }, { - "epoch": 0.22, - "learning_rate": 3.9319881091793534e-05, - "loss": 0.3129, + "epoch": 0.06, + "learning_rate": 4.734771034205051e-05, + "loss": 0.3223, "step": 24720 }, { - "epoch": 0.22, - "learning_rate": 3.931537699306369e-05, - "loss": 0.3114, + "epoch": 0.06, + "learning_rate": 4.734659179884119e-05, + "loss": 0.3263, "step": 24730 }, { - "epoch": 0.22, - "learning_rate": 3.931087289433384e-05, - "loss": 0.3133, + "epoch": 0.06, + "learning_rate": 4.734547325563187e-05, + "loss": 0.3296, "step": 24740 }, { - "epoch": 0.22, - "learning_rate": 3.9306368795604006e-05, - "loss": 0.3105, + "epoch": 0.06, + "learning_rate": 4.734435471242255e-05, + "loss": 0.3212, "step": 24750 }, { - "epoch": 0.22, - "learning_rate": 3.930186469687416e-05, - "loss": 0.3108, + "epoch": 0.06, + "learning_rate": 4.734323616921322e-05, + "loss": 0.3187, "step": 24760 }, { - "epoch": 0.22, - "learning_rate": 3.9297360598144315e-05, - "loss": 0.3145, + "epoch": 0.06, + "learning_rate": 4.7342117626003896e-05, + "loss": 0.3251, "step": 24770 }, { - "epoch": 0.22, - "learning_rate": 3.929285649941447e-05, - "loss": 0.3121, + "epoch": 0.06, + "learning_rate": 4.734099908279457e-05, + "loss": 0.3257, "step": 24780 }, { - "epoch": 0.22, - "learning_rate": 3.928835240068462e-05, - "loss": 0.3154, + "epoch": 0.06, + "learning_rate": 4.7339880539585245e-05, + "loss": 0.3206, "step": 24790 }, { - "epoch": 0.22, - "learning_rate": 3.928384830195478e-05, - "loss": 0.3132, + "epoch": 0.06, + "learning_rate": 4.733876199637592e-05, + "loss": 0.321, "step": 24800 }, { - "epoch": 0.22, - "learning_rate": 3.927934420322494e-05, - "loss": 0.3159, + "epoch": 0.06, + "learning_rate": 4.7337643453166594e-05, + "loss": 0.3136, "step": 24810 }, { - "epoch": 0.22, - "learning_rate": 3.9274840104495095e-05, - "loss": 0.3214, + "epoch": 0.06, + "learning_rate": 4.733652490995727e-05, + "loss": 0.3279, "step": 24820 }, { - "epoch": 0.22, - "learning_rate": 3.9270336005765246e-05, - "loss": 0.3137, + "epoch": 0.06, + "learning_rate": 4.733540636674795e-05, + "loss": 0.3207, "step": 24830 }, { - "epoch": 0.22, - "learning_rate": 3.9265831907035403e-05, - "loss": 0.309, + "epoch": 0.06, + "learning_rate": 4.733428782353863e-05, + "loss": 0.3242, "step": 24840 }, { - "epoch": 0.22, - "learning_rate": 3.926132780830556e-05, - "loss": 0.3141, + "epoch": 0.06, + "learning_rate": 4.7333169280329306e-05, + "loss": 0.3247, "step": 24850 }, { - "epoch": 0.22, - "learning_rate": 3.925682370957572e-05, - "loss": 0.3146, + "epoch": 0.06, + "learning_rate": 4.733205073711998e-05, + "loss": 0.3316, "step": 24860 }, { - "epoch": 0.22, - "learning_rate": 3.925231961084587e-05, - "loss": 0.3129, + "epoch": 0.06, + "learning_rate": 4.7330932193910655e-05, + "loss": 0.3266, "step": 24870 }, { - "epoch": 0.22, - "learning_rate": 3.924781551211603e-05, - "loss": 0.3145, + "epoch": 0.06, + "learning_rate": 4.7329813650701326e-05, + "loss": 0.3241, "step": 24880 }, { - "epoch": 0.22, - "learning_rate": 3.9243311413386184e-05, - "loss": 0.3125, + "epoch": 0.06, + "learning_rate": 4.7328695107492004e-05, + "loss": 0.328, "step": 24890 }, { - "epoch": 0.22, - "learning_rate": 3.923880731465634e-05, - "loss": 0.3172, + "epoch": 0.06, + "learning_rate": 4.732757656428268e-05, + "loss": 0.3223, "step": 24900 }, { - "epoch": 0.22, - "learning_rate": 3.923430321592649e-05, - "loss": 0.3169, + "epoch": 0.06, + "learning_rate": 4.732645802107335e-05, + "loss": 0.3236, "step": 24910 }, { - "epoch": 0.22, - "learning_rate": 3.922979911719665e-05, - "loss": 0.3151, + "epoch": 0.06, + "learning_rate": 4.732533947786403e-05, + "loss": 0.3256, "step": 24920 }, { - "epoch": 0.22, - "learning_rate": 3.922529501846681e-05, - "loss": 0.311, + "epoch": 0.06, + "learning_rate": 4.732422093465471e-05, + "loss": 0.3243, "step": 24930 }, { - "epoch": 0.22, - "learning_rate": 3.922079091973696e-05, - "loss": 0.312, + "epoch": 0.06, + "learning_rate": 4.732310239144539e-05, + "loss": 0.3192, "step": 24940 }, { - "epoch": 0.22, - "learning_rate": 3.921628682100712e-05, - "loss": 0.3155, + "epoch": 0.06, + "learning_rate": 4.7321983848236065e-05, + "loss": 0.3195, "step": 24950 }, { - "epoch": 0.22, - "learning_rate": 3.921178272227727e-05, - "loss": 0.3092, + "epoch": 0.06, + "learning_rate": 4.7320865305026736e-05, + "loss": 0.3244, "step": 24960 }, { - "epoch": 0.22, - "learning_rate": 3.920727862354743e-05, - "loss": 0.3161, + "epoch": 0.06, + "learning_rate": 4.7319746761817414e-05, + "loss": 0.3192, "step": 24970 }, { - "epoch": 0.22, - "learning_rate": 3.920277452481759e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.7318628218608085e-05, + "loss": 0.3258, "step": 24980 }, { - "epoch": 0.22, - "learning_rate": 3.919827042608774e-05, - "loss": 0.3134, + "epoch": 0.06, + "learning_rate": 4.731750967539876e-05, + "loss": 0.3268, "step": 24990 }, { - "epoch": 0.22, - "learning_rate": 3.91937663273579e-05, - "loss": 0.3161, + "epoch": 0.06, + "learning_rate": 4.7316391132189434e-05, + "loss": 0.3245, "step": 25000 }, { - "epoch": 0.22, - "learning_rate": 3.9189262228628054e-05, - "loss": 0.3102, + "epoch": 0.06, + "learning_rate": 4.731527258898011e-05, + "loss": 0.3219, "step": 25010 }, { - "epoch": 0.22, - "learning_rate": 3.918475812989821e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.731415404577079e-05, + "loss": 0.3227, "step": 25020 }, { - "epoch": 0.22, - "learning_rate": 3.918025403116837e-05, - "loss": 0.3113, + "epoch": 0.06, + "learning_rate": 4.731303550256147e-05, + "loss": 0.3219, "step": 25030 }, { - "epoch": 0.22, - "learning_rate": 3.917574993243852e-05, - "loss": 0.3104, + "epoch": 0.06, + "learning_rate": 4.7311916959352146e-05, + "loss": 0.3251, "step": 25040 }, { - "epoch": 0.22, - "learning_rate": 3.917124583370868e-05, - "loss": 0.3073, + "epoch": 0.06, + "learning_rate": 4.731079841614282e-05, + "loss": 0.3247, "step": 25050 }, { - "epoch": 0.22, - "learning_rate": 3.9166741734978834e-05, - "loss": 0.3092, + "epoch": 0.06, + "learning_rate": 4.7309679872933495e-05, + "loss": 0.3212, "step": 25060 }, { - "epoch": 0.22, - "learning_rate": 3.9162237636248985e-05, - "loss": 0.3188, + "epoch": 0.06, + "learning_rate": 4.730856132972417e-05, + "loss": 0.3201, "step": 25070 }, { - "epoch": 0.22, - "learning_rate": 3.915773353751914e-05, - "loss": 0.3166, + "epoch": 0.06, + "learning_rate": 4.7307442786514844e-05, + "loss": 0.3191, "step": 25080 }, { - "epoch": 0.22, - "learning_rate": 3.91532294387893e-05, - "loss": 0.3134, + "epoch": 0.06, + "learning_rate": 4.730632424330552e-05, + "loss": 0.3252, "step": 25090 }, { - "epoch": 0.22, - "learning_rate": 3.914872534005946e-05, - "loss": 0.3108, + "epoch": 0.06, + "learning_rate": 4.730520570009619e-05, + "loss": 0.3263, "step": 25100 }, { - "epoch": 0.22, - "learning_rate": 3.914422124132961e-05, - "loss": 0.3153, + "epoch": 0.06, + "learning_rate": 4.730408715688687e-05, + "loss": 0.3232, "step": 25110 }, { - "epoch": 0.22, - "learning_rate": 3.9139717142599766e-05, - "loss": 0.3111, + "epoch": 0.06, + "learning_rate": 4.730296861367755e-05, + "loss": 0.3189, "step": 25120 }, { - "epoch": 0.22, - "learning_rate": 3.913521304386992e-05, - "loss": 0.3162, + "epoch": 0.06, + "learning_rate": 4.730185007046822e-05, + "loss": 0.3204, "step": 25130 }, { - "epoch": 0.22, - "learning_rate": 3.913070894514008e-05, - "loss": 0.3134, + "epoch": 0.06, + "learning_rate": 4.73007315272589e-05, + "loss": 0.3286, "step": 25140 }, { - "epoch": 0.22, - "learning_rate": 3.912620484641024e-05, - "loss": 0.3127, + "epoch": 0.06, + "learning_rate": 4.7299612984049576e-05, + "loss": 0.3229, "step": 25150 }, { - "epoch": 0.22, - "learning_rate": 3.912170074768039e-05, - "loss": 0.3114, + "epoch": 0.06, + "learning_rate": 4.7298494440840254e-05, + "loss": 0.3245, "step": 25160 }, { - "epoch": 0.22, - "learning_rate": 3.9117196648950546e-05, - "loss": 0.3103, + "epoch": 0.06, + "learning_rate": 4.729737589763093e-05, + "loss": 0.3225, "step": 25170 }, { - "epoch": 0.22, - "learning_rate": 3.9112692550220704e-05, - "loss": 0.3133, + "epoch": 0.06, + "learning_rate": 4.72962573544216e-05, + "loss": 0.3243, "step": 25180 }, { - "epoch": 0.22, - "learning_rate": 3.9108188451490855e-05, - "loss": 0.3172, + "epoch": 0.06, + "learning_rate": 4.729513881121228e-05, + "loss": 0.321, "step": 25190 }, { - "epoch": 0.22, - "learning_rate": 3.910368435276102e-05, - "loss": 0.3117, + "epoch": 0.06, + "learning_rate": 4.729402026800295e-05, + "loss": 0.3291, "step": 25200 }, { - "epoch": 0.23, - "learning_rate": 3.909918025403117e-05, - "loss": 0.3221, + "epoch": 0.06, + "learning_rate": 4.729290172479363e-05, + "loss": 0.3202, "step": 25210 }, { - "epoch": 0.23, - "learning_rate": 3.909467615530133e-05, - "loss": 0.3146, + "epoch": 0.06, + "learning_rate": 4.729178318158431e-05, + "loss": 0.3213, "step": 25220 }, { - "epoch": 0.23, - "learning_rate": 3.9090172056571485e-05, - "loss": 0.3124, + "epoch": 0.06, + "learning_rate": 4.729066463837498e-05, + "loss": 0.3282, "step": 25230 }, { - "epoch": 0.23, - "learning_rate": 3.9085667957841635e-05, - "loss": 0.3141, + "epoch": 0.06, + "learning_rate": 4.728954609516566e-05, + "loss": 0.3272, "step": 25240 }, { - "epoch": 0.23, - "learning_rate": 3.908116385911179e-05, - "loss": 0.3078, + "epoch": 0.06, + "learning_rate": 4.7288427551956335e-05, + "loss": 0.3234, "step": 25250 }, { - "epoch": 0.23, - "learning_rate": 3.907665976038195e-05, - "loss": 0.3115, + "epoch": 0.06, + "learning_rate": 4.728730900874701e-05, + "loss": 0.319, "step": 25260 }, { - "epoch": 0.23, - "learning_rate": 3.907215566165211e-05, - "loss": 0.3131, + "epoch": 0.06, + "learning_rate": 4.728619046553769e-05, + "loss": 0.3249, "step": 25270 }, { - "epoch": 0.23, - "learning_rate": 3.906765156292226e-05, - "loss": 0.3094, + "epoch": 0.06, + "learning_rate": 4.728507192232836e-05, + "loss": 0.3244, "step": 25280 }, { - "epoch": 0.23, - "learning_rate": 3.9063147464192416e-05, - "loss": 0.3101, + "epoch": 0.06, + "learning_rate": 4.728395337911904e-05, + "loss": 0.3246, "step": 25290 }, { - "epoch": 0.23, - "learning_rate": 3.9058643365462574e-05, - "loss": 0.315, + "epoch": 0.06, + "learning_rate": 4.728283483590971e-05, + "loss": 0.3203, "step": 25300 }, { - "epoch": 0.23, - "learning_rate": 3.905413926673273e-05, - "loss": 0.3082, + "epoch": 0.06, + "learning_rate": 4.728171629270039e-05, + "loss": 0.3255, "step": 25310 }, { - "epoch": 0.23, - "learning_rate": 3.904963516800288e-05, - "loss": 0.3115, + "epoch": 0.06, + "learning_rate": 4.728059774949106e-05, + "loss": 0.3275, "step": 25320 }, { - "epoch": 0.23, - "learning_rate": 3.904513106927304e-05, - "loss": 0.3115, + "epoch": 0.06, + "learning_rate": 4.727947920628174e-05, + "loss": 0.3184, "step": 25330 }, { - "epoch": 0.23, - "learning_rate": 3.90406269705432e-05, - "loss": 0.3106, + "epoch": 0.06, + "learning_rate": 4.7278360663072416e-05, + "loss": 0.3251, "step": 25340 }, { - "epoch": 0.23, - "learning_rate": 3.9036122871813354e-05, - "loss": 0.3141, + "epoch": 0.06, + "learning_rate": 4.7277242119863094e-05, + "loss": 0.3279, "step": 25350 }, { - "epoch": 0.23, - "learning_rate": 3.9031618773083505e-05, - "loss": 0.3097, + "epoch": 0.06, + "learning_rate": 4.727612357665377e-05, + "loss": 0.3213, "step": 25360 }, { - "epoch": 0.23, - "learning_rate": 3.902711467435366e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.727500503344444e-05, + "loss": 0.3204, "step": 25370 }, { - "epoch": 0.23, - "learning_rate": 3.902261057562382e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.727388649023512e-05, + "loss": 0.3219, "step": 25380 }, { - "epoch": 0.23, - "learning_rate": 3.901810647689397e-05, - "loss": 0.3189, + "epoch": 0.06, + "learning_rate": 4.72727679470258e-05, + "loss": 0.3246, "step": 25390 }, { - "epoch": 0.23, - "learning_rate": 3.9013602378164135e-05, - "loss": 0.3078, + "epoch": 0.06, + "learning_rate": 4.727164940381647e-05, + "loss": 0.3231, "step": 25400 }, { - "epoch": 0.23, - "learning_rate": 3.9009098279434286e-05, - "loss": 0.3092, + "epoch": 0.06, + "learning_rate": 4.727053086060715e-05, + "loss": 0.3245, "step": 25410 }, { - "epoch": 0.23, - "learning_rate": 3.900459418070444e-05, - "loss": 0.315, + "epoch": 0.06, + "learning_rate": 4.726941231739782e-05, + "loss": 0.3215, "step": 25420 }, { - "epoch": 0.23, - "learning_rate": 3.90000900819746e-05, - "loss": 0.3127, + "epoch": 0.06, + "learning_rate": 4.72682937741885e-05, + "loss": 0.3202, "step": 25430 }, { - "epoch": 0.23, - "learning_rate": 3.899558598324475e-05, - "loss": 0.3092, + "epoch": 0.06, + "learning_rate": 4.7267175230979175e-05, + "loss": 0.3184, "step": 25440 }, { - "epoch": 0.23, - "learning_rate": 3.8991081884514916e-05, - "loss": 0.3105, + "epoch": 0.06, + "learning_rate": 4.726605668776985e-05, + "loss": 0.3337, "step": 25450 }, { - "epoch": 0.23, - "learning_rate": 3.8986577785785066e-05, - "loss": 0.3093, + "epoch": 0.06, + "learning_rate": 4.726493814456053e-05, + "loss": 0.3265, "step": 25460 }, { - "epoch": 0.23, - "learning_rate": 3.8982073687055224e-05, - "loss": 0.3113, + "epoch": 0.06, + "learning_rate": 4.72638196013512e-05, + "loss": 0.3223, "step": 25470 }, { - "epoch": 0.23, - "learning_rate": 3.897756958832538e-05, - "loss": 0.3123, + "epoch": 0.06, + "learning_rate": 4.726270105814188e-05, + "loss": 0.3189, "step": 25480 }, { - "epoch": 0.23, - "learning_rate": 3.897306548959553e-05, - "loss": 0.3169, + "epoch": 0.06, + "learning_rate": 4.726158251493256e-05, + "loss": 0.3176, "step": 25490 }, { - "epoch": 0.23, - "learning_rate": 3.896856139086569e-05, - "loss": 0.3172, + "epoch": 0.06, + "learning_rate": 4.726046397172323e-05, + "loss": 0.3184, "step": 25500 }, { - "epoch": 0.23, - "learning_rate": 3.896405729213585e-05, - "loss": 0.309, + "epoch": 0.06, + "learning_rate": 4.725934542851391e-05, + "loss": 0.3225, "step": 25510 }, { - "epoch": 0.23, - "learning_rate": 3.8959553193406e-05, - "loss": 0.3057, + "epoch": 0.06, + "learning_rate": 4.725822688530458e-05, + "loss": 0.3268, "step": 25520 }, { - "epoch": 0.23, - "learning_rate": 3.8955049094676155e-05, - "loss": 0.3108, + "epoch": 0.06, + "learning_rate": 4.7257108342095256e-05, + "loss": 0.3251, "step": 25530 }, { - "epoch": 0.23, - "learning_rate": 3.895054499594631e-05, - "loss": 0.315, + "epoch": 0.06, + "learning_rate": 4.7255989798885934e-05, + "loss": 0.3201, "step": 25540 }, { - "epoch": 0.23, - "learning_rate": 3.894604089721647e-05, - "loss": 0.3135, + "epoch": 0.06, + "learning_rate": 4.7254871255676605e-05, + "loss": 0.3221, "step": 25550 }, { - "epoch": 0.23, - "learning_rate": 3.894153679848662e-05, - "loss": 0.3102, + "epoch": 0.06, + "learning_rate": 4.725375271246729e-05, + "loss": 0.327, "step": 25560 }, { - "epoch": 0.23, - "learning_rate": 3.893703269975678e-05, - "loss": 0.3095, + "epoch": 0.06, + "learning_rate": 4.725263416925796e-05, + "loss": 0.3195, "step": 25570 }, { - "epoch": 0.23, - "learning_rate": 3.8932528601026936e-05, - "loss": 0.3139, + "epoch": 0.06, + "learning_rate": 4.725151562604864e-05, + "loss": 0.3206, "step": 25580 }, { - "epoch": 0.23, - "learning_rate": 3.892802450229709e-05, - "loss": 0.3063, + "epoch": 0.06, + "learning_rate": 4.725039708283932e-05, + "loss": 0.3234, "step": 25590 }, { - "epoch": 0.23, - "learning_rate": 3.892352040356725e-05, - "loss": 0.3091, + "epoch": 0.06, + "learning_rate": 4.724927853962999e-05, + "loss": 0.3195, "step": 25600 }, { - "epoch": 0.23, - "learning_rate": 3.89190163048374e-05, - "loss": 0.3127, + "epoch": 0.06, + "learning_rate": 4.7248159996420666e-05, + "loss": 0.3284, "step": 25610 }, { - "epoch": 0.23, - "learning_rate": 3.891451220610756e-05, - "loss": 0.3073, + "epoch": 0.06, + "learning_rate": 4.724704145321134e-05, + "loss": 0.3192, "step": 25620 }, { - "epoch": 0.23, - "learning_rate": 3.8910008107377717e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.7245922910002015e-05, + "loss": 0.3293, "step": 25630 }, { - "epoch": 0.23, - "learning_rate": 3.890550400864787e-05, - "loss": 0.3154, + "epoch": 0.06, + "learning_rate": 4.7244804366792686e-05, + "loss": 0.3212, "step": 25640 }, { - "epoch": 0.23, - "learning_rate": 3.890099990991803e-05, - "loss": 0.3124, + "epoch": 0.06, + "learning_rate": 4.7243685823583364e-05, + "loss": 0.3158, "step": 25650 }, { - "epoch": 0.23, - "learning_rate": 3.889649581118818e-05, - "loss": 0.3184, + "epoch": 0.06, + "learning_rate": 4.724256728037404e-05, + "loss": 0.321, "step": 25660 }, { - "epoch": 0.23, - "learning_rate": 3.889199171245834e-05, - "loss": 0.3109, + "epoch": 0.06, + "learning_rate": 4.724144873716472e-05, + "loss": 0.3213, "step": 25670 }, { - "epoch": 0.23, - "learning_rate": 3.88874876137285e-05, - "loss": 0.3122, + "epoch": 0.06, + "learning_rate": 4.72403301939554e-05, + "loss": 0.3183, "step": 25680 }, { - "epoch": 0.23, - "learning_rate": 3.888298351499865e-05, - "loss": 0.3136, + "epoch": 0.06, + "learning_rate": 4.723921165074607e-05, + "loss": 0.3176, "step": 25690 }, { - "epoch": 0.23, - "learning_rate": 3.8878479416268805e-05, - "loss": 0.3128, + "epoch": 0.06, + "learning_rate": 4.723809310753675e-05, + "loss": 0.3154, "step": 25700 }, { - "epoch": 0.23, - "learning_rate": 3.887397531753896e-05, - "loss": 0.3196, + "epoch": 0.06, + "learning_rate": 4.7236974564327425e-05, + "loss": 0.321, "step": 25710 }, { - "epoch": 0.23, - "learning_rate": 3.8869471218809114e-05, - "loss": 0.3121, + "epoch": 0.06, + "learning_rate": 4.7235856021118096e-05, + "loss": 0.3245, "step": 25720 }, { - "epoch": 0.23, - "learning_rate": 3.886496712007928e-05, - "loss": 0.3063, + "epoch": 0.06, + "learning_rate": 4.7234737477908774e-05, + "loss": 0.3179, "step": 25730 }, { - "epoch": 0.23, - "learning_rate": 3.886046302134943e-05, - "loss": 0.3109, + "epoch": 0.06, + "learning_rate": 4.7233618934699445e-05, + "loss": 0.3149, "step": 25740 }, { - "epoch": 0.23, - "learning_rate": 3.8855958922619586e-05, - "loss": 0.3075, + "epoch": 0.06, + "learning_rate": 4.723250039149012e-05, + "loss": 0.3171, "step": 25750 }, { - "epoch": 0.23, - "learning_rate": 3.8851454823889744e-05, - "loss": 0.3034, + "epoch": 0.06, + "learning_rate": 4.72313818482808e-05, + "loss": 0.3235, "step": 25760 }, { - "epoch": 0.23, - "learning_rate": 3.8846950725159894e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.723026330507148e-05, + "loss": 0.3211, "step": 25770 }, { - "epoch": 0.23, - "learning_rate": 3.884244662643005e-05, - "loss": 0.3093, + "epoch": 0.06, + "learning_rate": 4.722914476186216e-05, + "loss": 0.3216, "step": 25780 }, { - "epoch": 0.23, - "learning_rate": 3.883794252770021e-05, - "loss": 0.3067, + "epoch": 0.06, + "learning_rate": 4.722802621865283e-05, + "loss": 0.3278, "step": 25790 }, { - "epoch": 0.23, - "learning_rate": 3.883343842897037e-05, - "loss": 0.2994, + "epoch": 0.06, + "learning_rate": 4.7226907675443506e-05, + "loss": 0.3213, "step": 25800 }, { - "epoch": 0.23, - "learning_rate": 3.882893433024052e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.7225789132234184e-05, + "loss": 0.3178, "step": 25810 }, { - "epoch": 0.23, - "learning_rate": 3.8824430231510675e-05, - "loss": 0.3072, + "epoch": 0.06, + "learning_rate": 4.7224670589024855e-05, + "loss": 0.3229, "step": 25820 }, { - "epoch": 0.23, - "learning_rate": 3.881992613278083e-05, - "loss": 0.3123, + "epoch": 0.06, + "learning_rate": 4.722355204581553e-05, + "loss": 0.3212, "step": 25830 }, { - "epoch": 0.23, - "learning_rate": 3.881542203405098e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.7222433502606204e-05, + "loss": 0.3211, "step": 25840 }, { - "epoch": 0.23, - "learning_rate": 3.881091793532115e-05, - "loss": 0.308, + "epoch": 0.06, + "learning_rate": 4.722131495939688e-05, + "loss": 0.3244, "step": 25850 }, { - "epoch": 0.23, - "learning_rate": 3.88064138365913e-05, - "loss": 0.3071, + "epoch": 0.06, + "learning_rate": 4.722019641618756e-05, + "loss": 0.3248, "step": 25860 }, { - "epoch": 0.23, - "learning_rate": 3.8801909737861456e-05, - "loss": 0.3164, + "epoch": 0.06, + "learning_rate": 4.721907787297824e-05, + "loss": 0.3195, "step": 25870 }, { - "epoch": 0.23, - "learning_rate": 3.879740563913161e-05, - "loss": 0.3041, + "epoch": 0.06, + "learning_rate": 4.7217959329768916e-05, + "loss": 0.3179, "step": 25880 }, { - "epoch": 0.23, - "learning_rate": 3.8792901540401764e-05, - "loss": 0.313, + "epoch": 0.06, + "learning_rate": 4.721684078655959e-05, + "loss": 0.3205, "step": 25890 }, { - "epoch": 0.23, - "learning_rate": 3.878839744167193e-05, - "loss": 0.3088, + "epoch": 0.06, + "learning_rate": 4.7215722243350265e-05, + "loss": 0.3229, "step": 25900 }, { - "epoch": 0.23, - "learning_rate": 3.878389334294208e-05, - "loss": 0.3098, + "epoch": 0.06, + "learning_rate": 4.721460370014094e-05, + "loss": 0.3196, "step": 25910 }, { - "epoch": 0.23, - "learning_rate": 3.8779389244212236e-05, - "loss": 0.3083, + "epoch": 0.06, + "learning_rate": 4.7213485156931614e-05, + "loss": 0.3235, "step": 25920 }, { - "epoch": 0.23, - "learning_rate": 3.8774885145482394e-05, - "loss": 0.3033, + "epoch": 0.06, + "learning_rate": 4.721236661372229e-05, + "loss": 0.3216, "step": 25930 }, { - "epoch": 0.23, - "learning_rate": 3.8770381046752545e-05, - "loss": 0.3109, + "epoch": 0.06, + "learning_rate": 4.721124807051296e-05, + "loss": 0.3202, "step": 25940 }, { - "epoch": 0.23, - "learning_rate": 3.87658769480227e-05, - "loss": 0.3105, + "epoch": 0.06, + "learning_rate": 4.721012952730364e-05, + "loss": 0.3229, "step": 25950 }, { - "epoch": 0.23, - "learning_rate": 3.876137284929286e-05, - "loss": 0.3096, + "epoch": 0.06, + "learning_rate": 4.720901098409431e-05, + "loss": 0.3181, "step": 25960 }, { - "epoch": 0.23, - "learning_rate": 3.875686875056301e-05, - "loss": 0.3016, - "step": 25970 + "epoch": 0.06, + "learning_rate": 4.720789244088499e-05, + "loss": 0.3222, + "step": 25970 }, { - "epoch": 0.23, - "learning_rate": 3.875236465183317e-05, - "loss": 0.3023, + "epoch": 0.06, + "learning_rate": 4.7206773897675675e-05, + "loss": 0.3229, "step": 25980 }, { - "epoch": 0.23, - "learning_rate": 3.8747860553103325e-05, - "loss": 0.3146, + "epoch": 0.06, + "learning_rate": 4.7205655354466346e-05, + "loss": 0.31, "step": 25990 }, { - "epoch": 0.23, - "learning_rate": 3.874335645437348e-05, - "loss": 0.3102, + "epoch": 0.06, + "learning_rate": 4.7204536811257024e-05, + "loss": 0.3172, "step": 26000 }, { - "epoch": 0.23, - "learning_rate": 3.873885235564364e-05, - "loss": 0.3155, + "epoch": 0.06, + "learning_rate": 4.7203418268047695e-05, + "loss": 0.3234, "step": 26010 }, { - "epoch": 0.23, - "learning_rate": 3.873434825691379e-05, - "loss": 0.3086, + "epoch": 0.06, + "learning_rate": 4.720229972483837e-05, + "loss": 0.3232, "step": 26020 }, { - "epoch": 0.23, - "learning_rate": 3.872984415818395e-05, - "loss": 0.3138, + "epoch": 0.06, + "learning_rate": 4.720118118162905e-05, + "loss": 0.3215, "step": 26030 }, { - "epoch": 0.23, - "learning_rate": 3.8725340059454106e-05, - "loss": 0.3133, + "epoch": 0.06, + "learning_rate": 4.720006263841972e-05, + "loss": 0.3145, "step": 26040 }, { - "epoch": 0.23, - "learning_rate": 3.8720835960724263e-05, - "loss": 0.3084, + "epoch": 0.06, + "learning_rate": 4.71989440952104e-05, + "loss": 0.3189, "step": 26050 }, { - "epoch": 0.23, - "learning_rate": 3.8716331861994414e-05, - "loss": 0.3169, + "epoch": 0.06, + "learning_rate": 4.719782555200107e-05, + "loss": 0.3196, "step": 26060 }, { - "epoch": 0.23, - "learning_rate": 3.871182776326457e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.719670700879175e-05, + "loss": 0.3187, "step": 26070 }, { - "epoch": 0.23, - "learning_rate": 3.870732366453473e-05, - "loss": 0.3094, + "epoch": 0.06, + "learning_rate": 4.719558846558243e-05, + "loss": 0.3239, "step": 26080 }, { - "epoch": 0.23, - "learning_rate": 3.870281956580488e-05, - "loss": 0.3052, + "epoch": 0.06, + "learning_rate": 4.7194469922373105e-05, + "loss": 0.3183, "step": 26090 }, { - "epoch": 0.23, - "learning_rate": 3.8698315467075044e-05, - "loss": 0.3107, + "epoch": 0.06, + "learning_rate": 4.719335137916378e-05, + "loss": 0.3147, "step": 26100 }, { - "epoch": 0.23, - "learning_rate": 3.8693811368345195e-05, - "loss": 0.3095, + "epoch": 0.06, + "learning_rate": 4.7192232835954454e-05, + "loss": 0.3131, "step": 26110 }, { - "epoch": 0.23, - "learning_rate": 3.868930726961535e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.719111429274513e-05, + "loss": 0.3178, "step": 26120 }, { - "epoch": 0.23, - "learning_rate": 3.868480317088551e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.718999574953581e-05, + "loss": 0.3179, "step": 26130 }, { - "epoch": 0.23, - "learning_rate": 3.868029907215566e-05, - "loss": 0.3091, + "epoch": 0.06, + "learning_rate": 4.718887720632648e-05, + "loss": 0.3216, "step": 26140 }, { - "epoch": 0.23, - "learning_rate": 3.8675794973425825e-05, - "loss": 0.3082, + "epoch": 0.06, + "learning_rate": 4.718775866311716e-05, + "loss": 0.319, "step": 26150 }, { - "epoch": 0.23, - "learning_rate": 3.8671290874695976e-05, - "loss": 0.309, + "epoch": 0.06, + "learning_rate": 4.718664011990783e-05, + "loss": 0.3093, "step": 26160 }, { - "epoch": 0.23, - "learning_rate": 3.8666786775966126e-05, - "loss": 0.3068, + "epoch": 0.06, + "learning_rate": 4.718552157669851e-05, + "loss": 0.3143, "step": 26170 }, { - "epoch": 0.23, - "learning_rate": 3.866228267723629e-05, - "loss": 0.3072, + "epoch": 0.06, + "learning_rate": 4.7184403033489186e-05, + "loss": 0.3177, "step": 26180 }, { - "epoch": 0.23, - "learning_rate": 3.865777857850644e-05, - "loss": 0.3077, + "epoch": 0.06, + "learning_rate": 4.7183284490279864e-05, + "loss": 0.3196, "step": 26190 }, { - "epoch": 0.23, - "learning_rate": 3.86532744797766e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.718216594707054e-05, + "loss": 0.32, "step": 26200 }, { - "epoch": 0.23, - "learning_rate": 3.8648770381046756e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.718104740386121e-05, + "loss": 0.3115, "step": 26210 }, { - "epoch": 0.23, - "learning_rate": 3.864426628231691e-05, - "loss": 0.3079, + "epoch": 0.06, + "learning_rate": 4.717992886065189e-05, + "loss": 0.3209, "step": 26220 }, { - "epoch": 0.23, - "learning_rate": 3.8639762183587064e-05, - "loss": 0.3095, + "epoch": 0.06, + "learning_rate": 4.717881031744257e-05, + "loss": 0.3199, "step": 26230 }, { - "epoch": 0.23, - "learning_rate": 3.863525808485722e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.717769177423324e-05, + "loss": 0.3216, "step": 26240 }, { - "epoch": 0.23, - "learning_rate": 3.863075398612738e-05, - "loss": 0.3079, + "epoch": 0.06, + "learning_rate": 4.717657323102392e-05, + "loss": 0.3178, "step": 26250 }, { - "epoch": 0.23, - "learning_rate": 3.862624988739753e-05, - "loss": 0.3115, + "epoch": 0.06, + "learning_rate": 4.717545468781459e-05, + "loss": 0.3193, "step": 26260 }, { - "epoch": 0.23, - "learning_rate": 3.862174578866769e-05, - "loss": 0.3133, + "epoch": 0.06, + "learning_rate": 4.717433614460527e-05, + "loss": 0.3198, "step": 26270 }, { - "epoch": 0.23, - "learning_rate": 3.8617241689937845e-05, - "loss": 0.3111, + "epoch": 0.06, + "learning_rate": 4.7173217601395945e-05, + "loss": 0.3198, "step": 26280 }, { - "epoch": 0.23, - "learning_rate": 3.8612737591208e-05, - "loss": 0.3107, + "epoch": 0.06, + "learning_rate": 4.717209905818662e-05, + "loss": 0.3213, "step": 26290 }, { - "epoch": 0.23, - "learning_rate": 3.860823349247816e-05, - "loss": 0.3084, + "epoch": 0.06, + "learning_rate": 4.71709805149773e-05, + "loss": 0.3233, "step": 26300 }, { - "epoch": 0.23, - "learning_rate": 3.860372939374831e-05, - "loss": 0.3124, + "epoch": 0.06, + "learning_rate": 4.716986197176797e-05, + "loss": 0.3168, "step": 26310 }, { - "epoch": 0.23, - "learning_rate": 3.859922529501847e-05, - "loss": 0.3085, + "epoch": 0.06, + "learning_rate": 4.716874342855865e-05, + "loss": 0.3232, "step": 26320 }, { - "epoch": 0.24, - "learning_rate": 3.8594721196288626e-05, - "loss": 0.3092, + "epoch": 0.06, + "learning_rate": 4.716762488534932e-05, + "loss": 0.3215, "step": 26330 }, { - "epoch": 0.24, - "learning_rate": 3.8590217097558777e-05, - "loss": 0.306, + "epoch": 0.06, + "learning_rate": 4.716650634214e-05, + "loss": 0.3235, "step": 26340 }, { - "epoch": 0.24, - "learning_rate": 3.858571299882894e-05, - "loss": 0.311, + "epoch": 0.06, + "learning_rate": 4.7165387798930677e-05, + "loss": 0.3183, "step": 26350 }, { - "epoch": 0.24, - "learning_rate": 3.858120890009909e-05, - "loss": 0.3113, + "epoch": 0.06, + "learning_rate": 4.716426925572135e-05, + "loss": 0.323, "step": 26360 }, { - "epoch": 0.24, - "learning_rate": 3.857670480136924e-05, - "loss": 0.3109, + "epoch": 0.06, + "learning_rate": 4.7163150712512026e-05, + "loss": 0.318, "step": 26370 }, { - "epoch": 0.24, - "learning_rate": 3.8572200702639407e-05, - "loss": 0.3101, + "epoch": 0.06, + "learning_rate": 4.71620321693027e-05, + "loss": 0.322, "step": 26380 }, { - "epoch": 0.24, - "learning_rate": 3.856769660390956e-05, - "loss": 0.3131, + "epoch": 0.06, + "learning_rate": 4.716091362609338e-05, + "loss": 0.3242, "step": 26390 }, { - "epoch": 0.24, - "learning_rate": 3.8563192505179715e-05, - "loss": 0.3084, + "epoch": 0.06, + "learning_rate": 4.715979508288406e-05, + "loss": 0.3219, "step": 26400 }, { - "epoch": 0.24, - "learning_rate": 3.855868840644987e-05, - "loss": 0.3035, + "epoch": 0.06, + "learning_rate": 4.715867653967473e-05, + "loss": 0.32, "step": 26410 }, { - "epoch": 0.24, - "learning_rate": 3.855418430772002e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.715755799646541e-05, + "loss": 0.3197, "step": 26420 }, { - "epoch": 0.24, - "learning_rate": 3.854968020899019e-05, - "loss": 0.3102, + "epoch": 0.06, + "learning_rate": 4.715643945325608e-05, + "loss": 0.3214, "step": 26430 }, { - "epoch": 0.24, - "learning_rate": 3.854517611026034e-05, - "loss": 0.3084, + "epoch": 0.06, + "learning_rate": 4.715532091004676e-05, + "loss": 0.3225, "step": 26440 }, { - "epoch": 0.24, - "learning_rate": 3.8540672011530495e-05, - "loss": 0.3219, + "epoch": 0.06, + "learning_rate": 4.7154202366837435e-05, + "loss": 0.319, "step": 26450 }, { - "epoch": 0.24, - "learning_rate": 3.853616791280065e-05, - "loss": 0.3117, + "epoch": 0.06, + "learning_rate": 4.715308382362811e-05, + "loss": 0.3176, "step": 26460 }, { - "epoch": 0.24, - "learning_rate": 3.8531663814070804e-05, - "loss": 0.3022, + "epoch": 0.06, + "learning_rate": 4.7151965280418785e-05, + "loss": 0.3232, "step": 26470 }, { - "epoch": 0.24, - "learning_rate": 3.852761012521395e-05, - "loss": 0.3083, + "epoch": 0.06, + "learning_rate": 4.7150846737209456e-05, + "loss": 0.3163, "step": 26480 }, { - "epoch": 0.24, - "learning_rate": 3.85231060264841e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.7149728194000134e-05, + "loss": 0.3189, "step": 26490 }, { - "epoch": 0.24, - "learning_rate": 3.851860192775426e-05, - "loss": 0.3057, + "epoch": 0.06, + "learning_rate": 4.714860965079081e-05, + "loss": 0.3138, "step": 26500 }, { - "epoch": 0.24, - "learning_rate": 3.851409782902441e-05, - "loss": 0.307, + "epoch": 0.06, + "learning_rate": 4.714749110758149e-05, + "loss": 0.3158, "step": 26510 }, { - "epoch": 0.24, - "learning_rate": 3.850959373029457e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.714637256437217e-05, + "loss": 0.3184, "step": 26520 }, { - "epoch": 0.24, - "learning_rate": 3.850508963156473e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.714525402116284e-05, + "loss": 0.315, "step": 26530 }, { - "epoch": 0.24, - "learning_rate": 3.850058553283488e-05, - "loss": 0.3101, + "epoch": 0.06, + "learning_rate": 4.7144135477953516e-05, + "loss": 0.3234, "step": 26540 }, { - "epoch": 0.24, - "learning_rate": 3.8496081434105036e-05, - "loss": 0.3131, + "epoch": 0.06, + "learning_rate": 4.7143016934744194e-05, + "loss": 0.3201, "step": 26550 }, { - "epoch": 0.24, - "learning_rate": 3.8491577335375194e-05, - "loss": 0.3098, + "epoch": 0.06, + "learning_rate": 4.7141898391534866e-05, + "loss": 0.3167, "step": 26560 }, { - "epoch": 0.24, - "learning_rate": 3.848707323664535e-05, - "loss": 0.3093, + "epoch": 0.06, + "learning_rate": 4.7140779848325543e-05, + "loss": 0.3148, "step": 26570 }, { - "epoch": 0.24, - "learning_rate": 3.84825691379155e-05, - "loss": 0.3122, + "epoch": 0.06, + "learning_rate": 4.7139661305116215e-05, + "loss": 0.3146, "step": 26580 }, { - "epoch": 0.24, - "learning_rate": 3.847806503918566e-05, - "loss": 0.3041, + "epoch": 0.06, + "learning_rate": 4.713854276190689e-05, + "loss": 0.3162, "step": 26590 }, { - "epoch": 0.24, - "learning_rate": 3.847356094045582e-05, - "loss": 0.3022, + "epoch": 0.06, + "learning_rate": 4.713742421869757e-05, + "loss": 0.3217, "step": 26600 }, { - "epoch": 0.24, - "learning_rate": 3.846905684172597e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.713630567548825e-05, + "loss": 0.3138, "step": 26610 }, { - "epoch": 0.24, - "learning_rate": 3.846455274299613e-05, - "loss": 0.3117, + "epoch": 0.06, + "learning_rate": 4.7135187132278926e-05, + "loss": 0.3222, "step": 26620 }, { - "epoch": 0.24, - "learning_rate": 3.846004864426628e-05, - "loss": 0.3013, + "epoch": 0.06, + "learning_rate": 4.71340685890696e-05, + "loss": 0.3115, "step": 26630 }, { - "epoch": 0.24, - "learning_rate": 3.845554454553644e-05, - "loss": 0.307, + "epoch": 0.06, + "learning_rate": 4.7132950045860275e-05, + "loss": 0.315, "step": 26640 }, { - "epoch": 0.24, - "learning_rate": 3.84510404468066e-05, - "loss": 0.3117, + "epoch": 0.06, + "learning_rate": 4.7131831502650947e-05, + "loss": 0.316, "step": 26650 }, { - "epoch": 0.24, - "learning_rate": 3.844653634807675e-05, - "loss": 0.3129, + "epoch": 0.06, + "learning_rate": 4.7130824813762555e-05, + "loss": 0.3166, "step": 26660 }, { - "epoch": 0.24, - "learning_rate": 3.844203224934691e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.712970627055323e-05, + "loss": 0.3148, "step": 26670 }, { - "epoch": 0.24, - "learning_rate": 3.843752815061706e-05, - "loss": 0.3027, + "epoch": 0.06, + "learning_rate": 4.712858772734391e-05, + "loss": 0.3228, "step": 26680 }, { - "epoch": 0.24, - "learning_rate": 3.843302405188722e-05, - "loss": 0.3004, + "epoch": 0.06, + "learning_rate": 4.712746918413459e-05, + "loss": 0.3159, "step": 26690 }, { - "epoch": 0.24, - "learning_rate": 3.842851995315738e-05, - "loss": 0.3088, + "epoch": 0.06, + "learning_rate": 4.712635064092526e-05, + "loss": 0.3165, "step": 26700 }, { - "epoch": 0.24, - "learning_rate": 3.842401585442753e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.712523209771594e-05, + "loss": 0.3147, "step": 26710 }, { - "epoch": 0.24, - "learning_rate": 3.8419511755697687e-05, - "loss": 0.3101, + "epoch": 0.06, + "learning_rate": 4.712411355450661e-05, + "loss": 0.317, "step": 26720 }, { - "epoch": 0.24, - "learning_rate": 3.8415007656967844e-05, - "loss": 0.3071, + "epoch": 0.06, + "learning_rate": 4.712299501129729e-05, + "loss": 0.3109, "step": 26730 }, { - "epoch": 0.24, - "learning_rate": 3.8410503558237995e-05, - "loss": 0.306, + "epoch": 0.06, + "learning_rate": 4.7121876468087965e-05, + "loss": 0.3146, "step": 26740 }, { - "epoch": 0.24, - "learning_rate": 3.840599945950815e-05, - "loss": 0.3052, + "epoch": 0.06, + "learning_rate": 4.7120757924878636e-05, + "loss": 0.3105, "step": 26750 }, { - "epoch": 0.24, - "learning_rate": 3.840149536077831e-05, - "loss": 0.31, + "epoch": 0.06, + "learning_rate": 4.7119639381669314e-05, + "loss": 0.3195, "step": 26760 }, { - "epoch": 0.24, - "learning_rate": 3.839699126204847e-05, - "loss": 0.3043, + "epoch": 0.06, + "learning_rate": 4.711852083845999e-05, + "loss": 0.3154, "step": 26770 }, { - "epoch": 0.24, - "learning_rate": 3.8392487163318625e-05, - "loss": 0.3106, + "epoch": 0.06, + "learning_rate": 4.711740229525067e-05, + "loss": 0.3233, "step": 26780 }, { - "epoch": 0.24, - "learning_rate": 3.8387983064588775e-05, - "loss": 0.3052, + "epoch": 0.06, + "learning_rate": 4.711628375204135e-05, + "loss": 0.3178, "step": 26790 }, { - "epoch": 0.24, - "learning_rate": 3.838347896585893e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.711516520883202e-05, + "loss": 0.3183, "step": 26800 }, { - "epoch": 0.24, - "learning_rate": 3.837897486712909e-05, - "loss": 0.3132, + "epoch": 0.06, + "learning_rate": 4.71140466656227e-05, + "loss": 0.3158, "step": 26810 }, { - "epoch": 0.24, - "learning_rate": 3.837447076839925e-05, - "loss": 0.3027, + "epoch": 0.06, + "learning_rate": 4.711292812241337e-05, + "loss": 0.3172, "step": 26820 }, { - "epoch": 0.24, - "learning_rate": 3.83699666696694e-05, - "loss": 0.3015, + "epoch": 0.06, + "learning_rate": 4.7111809579204046e-05, + "loss": 0.3158, "step": 26830 }, { - "epoch": 0.24, - "learning_rate": 3.8365462570939556e-05, - "loss": 0.3066, + "epoch": 0.06, + "learning_rate": 4.7110691035994724e-05, + "loss": 0.3143, "step": 26840 }, { - "epoch": 0.24, - "learning_rate": 3.8360958472209714e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.7109572492785395e-05, + "loss": 0.3191, "step": 26850 }, { - "epoch": 0.24, - "learning_rate": 3.8356454373479864e-05, - "loss": 0.3109, + "epoch": 0.06, + "learning_rate": 4.710845394957607e-05, + "loss": 0.3191, "step": 26860 }, { - "epoch": 0.24, - "learning_rate": 3.835195027475003e-05, - "loss": 0.3013, + "epoch": 0.06, + "learning_rate": 4.710733540636675e-05, + "loss": 0.3168, "step": 26870 }, { - "epoch": 0.24, - "learning_rate": 3.834744617602018e-05, - "loss": 0.3091, + "epoch": 0.06, + "learning_rate": 4.710621686315743e-05, + "loss": 0.3196, "step": 26880 }, { - "epoch": 0.24, - "learning_rate": 3.834294207729034e-05, - "loss": 0.3025, + "epoch": 0.06, + "learning_rate": 4.710509831994811e-05, + "loss": 0.3211, "step": 26890 }, { - "epoch": 0.24, - "learning_rate": 3.8338437978560494e-05, - "loss": 0.3101, + "epoch": 0.06, + "learning_rate": 4.710397977673878e-05, + "loss": 0.3171, "step": 26900 }, { - "epoch": 0.24, - "learning_rate": 3.8333933879830645e-05, - "loss": 0.3027, + "epoch": 0.06, + "learning_rate": 4.7102861233529456e-05, + "loss": 0.3184, "step": 26910 }, { - "epoch": 0.24, - "learning_rate": 3.832942978110081e-05, - "loss": 0.3069, + "epoch": 0.06, + "learning_rate": 4.710174269032013e-05, + "loss": 0.3146, "step": 26920 }, { - "epoch": 0.24, - "learning_rate": 3.832492568237096e-05, - "loss": 0.3054, + "epoch": 0.06, + "learning_rate": 4.7100624147110805e-05, + "loss": 0.3196, "step": 26930 }, { - "epoch": 0.24, - "learning_rate": 3.832042158364111e-05, - "loss": 0.3134, + "epoch": 0.06, + "learning_rate": 4.709950560390148e-05, + "loss": 0.3203, "step": 26940 }, { - "epoch": 0.24, - "learning_rate": 3.8315917484911275e-05, - "loss": 0.3082, + "epoch": 0.06, + "learning_rate": 4.7098387060692154e-05, + "loss": 0.3216, "step": 26950 }, { - "epoch": 0.24, - "learning_rate": 3.8311413386181426e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.709726851748283e-05, + "loss": 0.3214, "step": 26960 }, { - "epoch": 0.24, - "learning_rate": 3.830690928745158e-05, - "loss": 0.3031, + "epoch": 0.06, + "learning_rate": 4.709614997427351e-05, + "loss": 0.3189, "step": 26970 }, { - "epoch": 0.24, - "learning_rate": 3.830240518872174e-05, - "loss": 0.3091, + "epoch": 0.06, + "learning_rate": 4.709503143106419e-05, + "loss": 0.3173, "step": 26980 }, { - "epoch": 0.24, - "learning_rate": 3.829790108999189e-05, - "loss": 0.3073, + "epoch": 0.06, + "learning_rate": 4.709391288785486e-05, + "loss": 0.3176, "step": 26990 }, { - "epoch": 0.24, - "learning_rate": 3.829339699126205e-05, - "loss": 0.3036, + "epoch": 0.06, + "learning_rate": 4.709279434464554e-05, + "loss": 0.3188, "step": 27000 }, { - "epoch": 0.24, - "learning_rate": 3.8288892892532206e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.7091675801436215e-05, + "loss": 0.3159, "step": 27010 }, { - "epoch": 0.24, - "learning_rate": 3.8284388793802364e-05, - "loss": 0.3068, + "epoch": 0.06, + "learning_rate": 4.7090557258226886e-05, + "loss": 0.3165, "step": 27020 }, { - "epoch": 0.24, - "learning_rate": 3.8279884695072515e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.7089438715017564e-05, + "loss": 0.3149, "step": 27030 }, { - "epoch": 0.24, - "learning_rate": 3.827538059634267e-05, - "loss": 0.3071, + "epoch": 0.06, + "learning_rate": 4.7088320171808235e-05, + "loss": 0.3118, "step": 27040 }, { - "epoch": 0.24, - "learning_rate": 3.827087649761283e-05, - "loss": 0.3066, + "epoch": 0.06, + "learning_rate": 4.708720162859891e-05, + "loss": 0.3088, "step": 27050 }, { - "epoch": 0.24, - "learning_rate": 3.826637239888299e-05, - "loss": 0.307, + "epoch": 0.06, + "learning_rate": 4.708608308538959e-05, + "loss": 0.3215, "step": 27060 }, { - "epoch": 0.24, - "learning_rate": 3.8261868300153145e-05, - "loss": 0.3037, + "epoch": 0.06, + "learning_rate": 4.708496454218026e-05, + "loss": 0.3164, "step": 27070 }, { - "epoch": 0.24, - "learning_rate": 3.8257364201423295e-05, - "loss": 0.3058, + "epoch": 0.06, + "learning_rate": 4.708384599897094e-05, + "loss": 0.3146, "step": 27080 }, { - "epoch": 0.24, - "learning_rate": 3.825286010269345e-05, - "loss": 0.3124, + "epoch": 0.06, + "learning_rate": 4.708272745576162e-05, + "loss": 0.3161, "step": 27090 }, { - "epoch": 0.24, - "learning_rate": 3.824835600396361e-05, - "loss": 0.3119, + "epoch": 0.06, + "learning_rate": 4.7081608912552296e-05, + "loss": 0.3195, "step": 27100 }, { - "epoch": 0.24, - "learning_rate": 3.824385190523376e-05, - "loss": 0.3111, + "epoch": 0.06, + "learning_rate": 4.7080490369342974e-05, + "loss": 0.3179, "step": 27110 }, { - "epoch": 0.24, - "learning_rate": 3.8239347806503925e-05, - "loss": 0.306, + "epoch": 0.06, + "learning_rate": 4.7079371826133645e-05, + "loss": 0.3171, "step": 27120 }, { - "epoch": 0.24, - "learning_rate": 3.8234843707774076e-05, - "loss": 0.3035, + "epoch": 0.06, + "learning_rate": 4.707825328292432e-05, + "loss": 0.3116, "step": 27130 }, { - "epoch": 0.24, - "learning_rate": 3.823033960904423e-05, - "loss": 0.305, + "epoch": 0.06, + "learning_rate": 4.7077134739714994e-05, + "loss": 0.3204, "step": 27140 }, { - "epoch": 0.24, - "learning_rate": 3.822583551031439e-05, - "loss": 0.3047, + "epoch": 0.06, + "learning_rate": 4.707601619650567e-05, + "loss": 0.3122, "step": 27150 }, { - "epoch": 0.24, - "learning_rate": 3.822133141158454e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.707489765329635e-05, + "loss": 0.3227, "step": 27160 }, { - "epoch": 0.24, - "learning_rate": 3.82168273128547e-05, - "loss": 0.3003, + "epoch": 0.06, + "learning_rate": 4.707377911008702e-05, + "loss": 0.3179, "step": 27170 }, { - "epoch": 0.24, - "learning_rate": 3.821232321412486e-05, - "loss": 0.306, + "epoch": 0.06, + "learning_rate": 4.70726605668777e-05, + "loss": 0.3159, "step": 27180 }, { - "epoch": 0.24, - "learning_rate": 3.820781911539501e-05, - "loss": 0.2992, + "epoch": 0.06, + "learning_rate": 4.707154202366838e-05, + "loss": 0.3238, "step": 27190 }, { - "epoch": 0.24, - "learning_rate": 3.820331501666517e-05, - "loss": 0.2994, + "epoch": 0.06, + "learning_rate": 4.7070423480459055e-05, + "loss": 0.3154, "step": 27200 }, { - "epoch": 0.24, - "learning_rate": 3.819881091793532e-05, - "loss": 0.2994, + "epoch": 0.06, + "learning_rate": 4.706930493724973e-05, + "loss": 0.313, "step": 27210 }, { - "epoch": 0.24, - "learning_rate": 3.819430681920548e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.7068186394040404e-05, + "loss": 0.3167, "step": 27220 }, { - "epoch": 0.24, - "learning_rate": 3.818980272047564e-05, - "loss": 0.3006, + "epoch": 0.06, + "learning_rate": 4.706706785083108e-05, + "loss": 0.3156, "step": 27230 }, { - "epoch": 0.24, - "learning_rate": 3.818529862174579e-05, - "loss": 0.301, + "epoch": 0.06, + "learning_rate": 4.706594930762175e-05, + "loss": 0.3141, "step": 27240 }, { - "epoch": 0.24, - "learning_rate": 3.8180794523015946e-05, - "loss": 0.3035, + "epoch": 0.06, + "learning_rate": 4.706483076441243e-05, + "loss": 0.3113, "step": 27250 }, { - "epoch": 0.24, - "learning_rate": 3.81762904242861e-05, - "loss": 0.3076, + "epoch": 0.06, + "learning_rate": 4.706371222120311e-05, + "loss": 0.3124, "step": 27260 }, { - "epoch": 0.24, - "learning_rate": 3.817178632555626e-05, - "loss": 0.3085, + "epoch": 0.06, + "learning_rate": 4.706259367799378e-05, + "loss": 0.3168, "step": 27270 }, { - "epoch": 0.24, - "learning_rate": 3.816728222682641e-05, - "loss": 0.3026, + "epoch": 0.06, + "learning_rate": 4.706147513478446e-05, + "loss": 0.3162, "step": 27280 }, { - "epoch": 0.24, - "learning_rate": 3.816277812809657e-05, - "loss": 0.3156, + "epoch": 0.06, + "learning_rate": 4.7060356591575136e-05, + "loss": 0.3193, "step": 27290 }, { - "epoch": 0.24, - "learning_rate": 3.8158274029366726e-05, - "loss": 0.3162, + "epoch": 0.06, + "learning_rate": 4.7059238048365814e-05, + "loss": 0.3192, "step": 27300 }, { - "epoch": 0.24, - "learning_rate": 3.815376993063688e-05, - "loss": 0.3032, + "epoch": 0.06, + "learning_rate": 4.7058119505156485e-05, + "loss": 0.315, "step": 27310 }, { - "epoch": 0.24, - "learning_rate": 3.814926583190704e-05, - "loss": 0.301, + "epoch": 0.06, + "learning_rate": 4.705700096194716e-05, + "loss": 0.3179, "step": 27320 }, { - "epoch": 0.24, - "learning_rate": 3.814476173317719e-05, - "loss": 0.3062, + "epoch": 0.06, + "learning_rate": 4.705588241873784e-05, + "loss": 0.3161, "step": 27330 }, { - "epoch": 0.24, - "learning_rate": 3.814025763444735e-05, - "loss": 0.3056, + "epoch": 0.06, + "learning_rate": 4.705476387552851e-05, + "loss": 0.3153, "step": 27340 }, { - "epoch": 0.24, - "learning_rate": 3.813575353571751e-05, - "loss": 0.3089, + "epoch": 0.06, + "learning_rate": 4.705364533231919e-05, + "loss": 0.3139, "step": 27350 }, { - "epoch": 0.24, - "learning_rate": 3.813124943698766e-05, - "loss": 0.3042, + "epoch": 0.06, + "learning_rate": 4.705252678910986e-05, + "loss": 0.3208, "step": 27360 }, { - "epoch": 0.24, - "learning_rate": 3.812674533825782e-05, - "loss": 0.3117, + "epoch": 0.06, + "learning_rate": 4.705140824590054e-05, + "loss": 0.3193, "step": 27370 }, { - "epoch": 0.24, - "learning_rate": 3.812224123952797e-05, - "loss": 0.3164, + "epoch": 0.06, + "learning_rate": 4.705028970269122e-05, + "loss": 0.3154, "step": 27380 }, { - "epoch": 0.24, - "learning_rate": 3.811773714079812e-05, - "loss": 0.308, + "epoch": 0.06, + "learning_rate": 4.7049171159481895e-05, + "loss": 0.3201, "step": 27390 }, { - "epoch": 0.24, - "learning_rate": 3.811323304206829e-05, - "loss": 0.3097, + "epoch": 0.06, + "learning_rate": 4.704805261627257e-05, + "loss": 0.3143, "step": 27400 }, { - "epoch": 0.24, - "learning_rate": 3.810872894333844e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.7046934073063244e-05, + "loss": 0.3145, "step": 27410 }, { - "epoch": 0.24, - "learning_rate": 3.8104224844608596e-05, - "loss": 0.3082, + "epoch": 0.06, + "learning_rate": 4.704581552985392e-05, + "loss": 0.3117, "step": 27420 }, { - "epoch": 0.24, - "learning_rate": 3.809972074587875e-05, - "loss": 0.3054, + "epoch": 0.06, + "learning_rate": 4.70446969866446e-05, + "loss": 0.3165, "step": 27430 }, { - "epoch": 0.24, - "learning_rate": 3.8095216647148904e-05, - "loss": 0.3041, + "epoch": 0.06, + "learning_rate": 4.704357844343527e-05, + "loss": 0.3073, "step": 27440 }, { - "epoch": 0.25, - "learning_rate": 3.809071254841906e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.704245990022595e-05, + "loss": 0.3185, "step": 27450 }, { - "epoch": 0.25, - "learning_rate": 3.808620844968922e-05, - "loss": 0.3093, + "epoch": 0.06, + "learning_rate": 4.704134135701662e-05, + "loss": 0.3153, "step": 27460 }, { - "epoch": 0.25, - "learning_rate": 3.8081704350959376e-05, - "loss": 0.3053, + "epoch": 0.06, + "learning_rate": 4.70402228138073e-05, + "loss": 0.314, "step": 27470 }, { - "epoch": 0.25, - "learning_rate": 3.8077200252229534e-05, - "loss": 0.3015, + "epoch": 0.06, + "learning_rate": 4.7039104270597976e-05, + "loss": 0.3103, "step": 27480 }, { - "epoch": 0.25, - "learning_rate": 3.8072696153499685e-05, - "loss": 0.3031, + "epoch": 0.06, + "learning_rate": 4.703798572738865e-05, + "loss": 0.3127, "step": 27490 }, { - "epoch": 0.25, - "learning_rate": 3.806819205476984e-05, - "loss": 0.3068, + "epoch": 0.06, + "learning_rate": 4.7036867184179325e-05, + "loss": 0.314, "step": 27500 }, { - "epoch": 0.25, - "learning_rate": 3.806368795604e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.703574864097e-05, + "loss": 0.3097, "step": 27510 }, { - "epoch": 0.25, - "learning_rate": 3.805918385731016e-05, - "loss": 0.3024, + "epoch": 0.06, + "learning_rate": 4.703463009776068e-05, + "loss": 0.3211, "step": 27520 }, { - "epoch": 0.25, - "learning_rate": 3.805467975858031e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.703351155455136e-05, + "loss": 0.314, "step": 27530 }, { - "epoch": 0.25, - "learning_rate": 3.8050175659850465e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.703239301134203e-05, + "loss": 0.3164, "step": 27540 }, { - "epoch": 0.25, - "learning_rate": 3.804567156112062e-05, - "loss": 0.2969, + "epoch": 0.06, + "learning_rate": 4.703127446813271e-05, + "loss": 0.3131, "step": 27550 }, { - "epoch": 0.25, - "learning_rate": 3.8041167462390774e-05, - "loss": 0.3, + "epoch": 0.06, + "learning_rate": 4.703015592492338e-05, + "loss": 0.3119, "step": 27560 }, { - "epoch": 0.25, - "learning_rate": 3.803666336366094e-05, - "loss": 0.3044, + "epoch": 0.06, + "learning_rate": 4.702903738171406e-05, + "loss": 0.3164, "step": 27570 }, { - "epoch": 0.25, - "learning_rate": 3.803215926493109e-05, - "loss": 0.3019, + "epoch": 0.06, + "learning_rate": 4.7027918838504735e-05, + "loss": 0.3188, "step": 27580 }, { - "epoch": 0.25, - "learning_rate": 3.802765516620124e-05, - "loss": 0.2947, + "epoch": 0.06, + "learning_rate": 4.7026800295295406e-05, + "loss": 0.3177, "step": 27590 }, { - "epoch": 0.25, - "learning_rate": 3.8023151067471404e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.7025681752086084e-05, + "loss": 0.3107, "step": 27600 }, { - "epoch": 0.25, - "learning_rate": 3.8018646968741554e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.702456320887676e-05, + "loss": 0.3127, "step": 27610 }, { - "epoch": 0.25, - "learning_rate": 3.801414287001171e-05, - "loss": 0.3012, + "epoch": 0.06, + "learning_rate": 4.702344466566744e-05, + "loss": 0.3126, "step": 27620 }, { - "epoch": 0.25, - "learning_rate": 3.800963877128187e-05, - "loss": 0.3039, + "epoch": 0.06, + "learning_rate": 4.702232612245811e-05, + "loss": 0.3192, "step": 27630 }, { - "epoch": 0.25, - "learning_rate": 3.800513467255202e-05, - "loss": 0.2997, + "epoch": 0.06, + "learning_rate": 4.702120757924879e-05, + "loss": 0.3138, "step": 27640 }, { - "epoch": 0.25, - "learning_rate": 3.8000630573822184e-05, - "loss": 0.3026, + "epoch": 0.06, + "learning_rate": 4.702008903603947e-05, + "loss": 0.3171, "step": 27650 }, { - "epoch": 0.25, - "learning_rate": 3.7996126475092335e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.701897049283014e-05, + "loss": 0.3164, "step": 27660 }, { - "epoch": 0.25, - "learning_rate": 3.799162237636249e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.7017851949620816e-05, + "loss": 0.3112, "step": 27670 }, { - "epoch": 0.25, - "learning_rate": 3.798711827763265e-05, - "loss": 0.3042, + "epoch": 0.06, + "learning_rate": 4.701673340641149e-05, + "loss": 0.3097, "step": 27680 }, { - "epoch": 0.25, - "learning_rate": 3.79826141789028e-05, - "loss": 0.3026, + "epoch": 0.06, + "learning_rate": 4.7015614863202165e-05, + "loss": 0.3123, "step": 27690 }, { - "epoch": 0.25, - "learning_rate": 3.797811008017296e-05, - "loss": 0.3016, + "epoch": 0.06, + "learning_rate": 4.701449631999284e-05, + "loss": 0.3104, "step": 27700 }, { - "epoch": 0.25, - "learning_rate": 3.7973605981443116e-05, - "loss": 0.3067, + "epoch": 0.06, + "learning_rate": 4.701337777678352e-05, + "loss": 0.3116, "step": 27710 }, { - "epoch": 0.25, - "learning_rate": 3.796910188271327e-05, - "loss": 0.299, + "epoch": 0.06, + "learning_rate": 4.70122592335742e-05, + "loss": 0.3087, "step": 27720 }, { - "epoch": 0.25, - "learning_rate": 3.7964597783983424e-05, - "loss": 0.2985, + "epoch": 0.06, + "learning_rate": 4.701114069036487e-05, + "loss": 0.3082, "step": 27730 }, { - "epoch": 0.25, - "learning_rate": 3.796009368525358e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.701002214715555e-05, + "loss": 0.3181, "step": 27740 }, { - "epoch": 0.25, - "learning_rate": 3.795558958652374e-05, - "loss": 0.3078, + "epoch": 0.06, + "learning_rate": 4.7008903603946226e-05, + "loss": 0.3121, "step": 27750 }, { - "epoch": 0.25, - "learning_rate": 3.795108548779389e-05, - "loss": 0.3028, + "epoch": 0.06, + "learning_rate": 4.70077850607369e-05, + "loss": 0.3131, "step": 27760 }, { - "epoch": 0.25, - "learning_rate": 3.7946581389064054e-05, - "loss": 0.3047, + "epoch": 0.06, + "learning_rate": 4.7006666517527575e-05, + "loss": 0.317, "step": 27770 }, { - "epoch": 0.25, - "learning_rate": 3.7942077290334205e-05, - "loss": 0.3051, + "epoch": 0.06, + "learning_rate": 4.7005547974318246e-05, + "loss": 0.3135, "step": 27780 }, { - "epoch": 0.25, - "learning_rate": 3.793757319160436e-05, - "loss": 0.3047, + "epoch": 0.06, + "learning_rate": 4.7004429431108924e-05, + "loss": 0.3173, "step": 27790 }, { - "epoch": 0.25, - "learning_rate": 3.793306909287452e-05, - "loss": 0.3057, + "epoch": 0.06, + "learning_rate": 4.70033108878996e-05, + "loss": 0.313, "step": 27800 }, { - "epoch": 0.25, - "learning_rate": 3.792856499414467e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.700219234469028e-05, + "loss": 0.3178, "step": 27810 }, { - "epoch": 0.25, - "learning_rate": 3.7924060895414835e-05, - "loss": 0.3033, + "epoch": 0.06, + "learning_rate": 4.700107380148096e-05, + "loss": 0.3146, "step": 27820 }, { - "epoch": 0.25, - "learning_rate": 3.7919556796684985e-05, - "loss": 0.2986, + "epoch": 0.06, + "learning_rate": 4.699995525827163e-05, + "loss": 0.3127, "step": 27830 }, { - "epoch": 0.25, - "learning_rate": 3.7915052697955136e-05, - "loss": 0.305, + "epoch": 0.06, + "learning_rate": 4.699883671506231e-05, + "loss": 0.3136, "step": 27840 }, { - "epoch": 0.25, - "learning_rate": 3.79105485992253e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.6997718171852985e-05, + "loss": 0.3086, "step": 27850 }, { - "epoch": 0.25, - "learning_rate": 3.790604450049545e-05, - "loss": 0.3072, + "epoch": 0.06, + "learning_rate": 4.6996599628643656e-05, + "loss": 0.3116, "step": 27860 }, { - "epoch": 0.25, - "learning_rate": 3.790154040176561e-05, - "loss": 0.3019, + "epoch": 0.06, + "learning_rate": 4.6995481085434334e-05, + "loss": 0.3091, "step": 27870 }, { - "epoch": 0.25, - "learning_rate": 3.7897036303035766e-05, - "loss": 0.3012, + "epoch": 0.06, + "learning_rate": 4.6994362542225005e-05, + "loss": 0.3123, "step": 27880 }, { - "epoch": 0.25, - "learning_rate": 3.789253220430592e-05, - "loss": 0.308, + "epoch": 0.06, + "learning_rate": 4.699324399901568e-05, + "loss": 0.3192, "step": 27890 }, { - "epoch": 0.25, - "learning_rate": 3.7888028105576074e-05, - "loss": 0.2982, + "epoch": 0.06, + "learning_rate": 4.6992125455806354e-05, + "loss": 0.318, "step": 27900 }, { - "epoch": 0.25, - "learning_rate": 3.788352400684623e-05, - "loss": 0.3063, + "epoch": 0.06, + "learning_rate": 4.699100691259703e-05, + "loss": 0.3146, "step": 27910 }, { - "epoch": 0.25, - "learning_rate": 3.787901990811639e-05, - "loss": 0.306, + "epoch": 0.06, + "learning_rate": 4.698988836938772e-05, + "loss": 0.3082, "step": 27920 }, { - "epoch": 0.25, - "learning_rate": 3.7874515809386547e-05, - "loss": 0.2977, + "epoch": 0.06, + "learning_rate": 4.698876982617839e-05, + "loss": 0.3103, "step": 27930 }, { - "epoch": 0.25, - "learning_rate": 3.78700117106567e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.6987651282969066e-05, + "loss": 0.3154, "step": 27940 }, { - "epoch": 0.25, - "learning_rate": 3.7865507611926855e-05, - "loss": 0.3005, + "epoch": 0.06, + "learning_rate": 4.698653273975974e-05, + "loss": 0.3079, "step": 27950 }, { - "epoch": 0.25, - "learning_rate": 3.786100351319701e-05, - "loss": 0.2951, + "epoch": 0.06, + "learning_rate": 4.6985414196550415e-05, + "loss": 0.3144, "step": 27960 }, { - "epoch": 0.25, - "learning_rate": 3.785649941446717e-05, - "loss": 0.3032, + "epoch": 0.06, + "learning_rate": 4.698429565334109e-05, + "loss": 0.3119, "step": 27970 }, { - "epoch": 0.25, - "learning_rate": 3.785199531573732e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.6983177110131764e-05, + "loss": 0.3112, "step": 27980 }, { - "epoch": 0.25, - "learning_rate": 3.784749121700748e-05, - "loss": 0.3032, + "epoch": 0.06, + "learning_rate": 4.698205856692244e-05, + "loss": 0.3104, "step": 27990 }, { - "epoch": 0.25, - "learning_rate": 3.7842987118277635e-05, - "loss": 0.3019, + "epoch": 0.06, + "learning_rate": 4.698094002371311e-05, + "loss": 0.3113, "step": 28000 }, { - "epoch": 0.25, - "learning_rate": 3.7838483019547786e-05, - "loss": 0.2992, + "epoch": 0.06, + "learning_rate": 4.697982148050379e-05, + "loss": 0.3198, "step": 28010 }, { - "epoch": 0.25, - "learning_rate": 3.783397892081795e-05, - "loss": 0.3086, + "epoch": 0.06, + "learning_rate": 4.697870293729447e-05, + "loss": 0.3148, "step": 28020 }, { - "epoch": 0.25, - "learning_rate": 3.78294748220881e-05, - "loss": 0.3027, + "epoch": 0.06, + "learning_rate": 4.697758439408515e-05, + "loss": 0.3105, "step": 28030 }, { - "epoch": 0.25, - "learning_rate": 3.782497072335825e-05, - "loss": 0.2993, + "epoch": 0.06, + "learning_rate": 4.6976465850875825e-05, + "loss": 0.3161, "step": 28040 }, { - "epoch": 0.25, - "learning_rate": 3.7820466624628416e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.6975347307666496e-05, + "loss": 0.3147, "step": 28050 }, { - "epoch": 0.25, - "learning_rate": 3.781596252589857e-05, - "loss": 0.3064, + "epoch": 0.06, + "learning_rate": 4.6974228764457174e-05, + "loss": 0.3078, "step": 28060 }, { - "epoch": 0.25, - "learning_rate": 3.781145842716873e-05, - "loss": 0.2979, + "epoch": 0.06, + "learning_rate": 4.697311022124785e-05, + "loss": 0.3104, "step": 28070 }, { - "epoch": 0.25, - "learning_rate": 3.780695432843888e-05, - "loss": 0.3044, + "epoch": 0.06, + "learning_rate": 4.697199167803852e-05, + "loss": 0.3158, "step": 28080 }, { - "epoch": 0.25, - "learning_rate": 3.780245022970903e-05, - "loss": 0.2986, + "epoch": 0.06, + "learning_rate": 4.69708731348292e-05, + "loss": 0.3113, "step": 28090 }, { - "epoch": 0.25, - "learning_rate": 3.77979461309792e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.696975459161987e-05, + "loss": 0.3081, "step": 28100 }, { - "epoch": 0.25, - "learning_rate": 3.779344203224935e-05, - "loss": 0.2977, + "epoch": 0.06, + "learning_rate": 4.696863604841055e-05, + "loss": 0.306, "step": 28110 }, { - "epoch": 0.25, - "learning_rate": 3.7788937933519505e-05, - "loss": 0.3007, + "epoch": 0.06, + "learning_rate": 4.696751750520123e-05, + "loss": 0.3118, "step": 28120 }, { - "epoch": 0.25, - "learning_rate": 3.778443383478966e-05, - "loss": 0.2982, + "epoch": 0.06, + "learning_rate": 4.6966398961991906e-05, + "loss": 0.3116, "step": 28130 }, { - "epoch": 0.25, - "learning_rate": 3.777992973605981e-05, - "loss": 0.3004, + "epoch": 0.06, + "learning_rate": 4.6965280418782584e-05, + "loss": 0.311, "step": 28140 }, { - "epoch": 0.25, - "learning_rate": 3.777542563732997e-05, - "loss": 0.3065, + "epoch": 0.06, + "learning_rate": 4.6964161875573255e-05, + "loss": 0.3135, "step": 28150 }, { - "epoch": 0.25, - "learning_rate": 3.777092153860013e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.696304333236393e-05, + "loss": 0.3163, "step": 28160 }, { - "epoch": 0.25, - "learning_rate": 3.7766417439870286e-05, - "loss": 0.3072, + "epoch": 0.06, + "learning_rate": 4.696192478915461e-05, + "loss": 0.3131, "step": 28170 }, { - "epoch": 0.25, - "learning_rate": 3.7761913341140436e-05, - "loss": 0.2927, + "epoch": 0.06, + "learning_rate": 4.696080624594528e-05, + "loss": 0.3187, "step": 28180 }, { - "epoch": 0.25, - "learning_rate": 3.7757409242410594e-05, - "loss": 0.2973, + "epoch": 0.06, + "learning_rate": 4.695968770273596e-05, + "loss": 0.3075, "step": 28190 }, { - "epoch": 0.25, - "learning_rate": 3.775290514368075e-05, - "loss": 0.309, + "epoch": 0.06, + "learning_rate": 4.695856915952663e-05, + "loss": 0.3064, "step": 28200 }, { - "epoch": 0.25, - "learning_rate": 3.774840104495091e-05, - "loss": 0.3007, + "epoch": 0.06, + "learning_rate": 4.695745061631731e-05, + "loss": 0.3091, "step": 28210 }, { - "epoch": 0.25, - "learning_rate": 3.7743896946221066e-05, - "loss": 0.2991, + "epoch": 0.06, + "learning_rate": 4.695633207310799e-05, + "loss": 0.3133, "step": 28220 }, { - "epoch": 0.25, - "learning_rate": 3.773939284749122e-05, - "loss": 0.3015, + "epoch": 0.06, + "learning_rate": 4.6955213529898665e-05, + "loss": 0.3167, "step": 28230 }, { - "epoch": 0.25, - "learning_rate": 3.7734888748761375e-05, - "loss": 0.3016, + "epoch": 0.06, + "learning_rate": 4.695409498668934e-05, + "loss": 0.3092, "step": 28240 }, { - "epoch": 0.25, - "learning_rate": 3.773038465003153e-05, - "loss": 0.2989, + "epoch": 0.06, + "learning_rate": 4.6952976443480014e-05, + "loss": 0.3122, "step": 28250 }, { - "epoch": 0.25, - "learning_rate": 3.772588055130168e-05, - "loss": 0.3005, + "epoch": 0.06, + "learning_rate": 4.695185790027069e-05, + "loss": 0.3091, "step": 28260 }, { - "epoch": 0.25, - "learning_rate": 3.772137645257185e-05, - "loss": 0.3074, + "epoch": 0.06, + "learning_rate": 4.695073935706136e-05, + "loss": 0.3167, "step": 28270 }, { - "epoch": 0.25, - "learning_rate": 3.7716872353842e-05, - "loss": 0.3059, + "epoch": 0.06, + "learning_rate": 4.694962081385204e-05, + "loss": 0.3107, "step": 28280 }, { - "epoch": 0.25, - "learning_rate": 3.771236825511215e-05, - "loss": 0.2996, + "epoch": 0.06, + "learning_rate": 4.694850227064272e-05, + "loss": 0.3076, "step": 28290 }, { - "epoch": 0.25, - "learning_rate": 3.770786415638231e-05, - "loss": 0.2966, + "epoch": 0.06, + "learning_rate": 4.694738372743339e-05, + "loss": 0.3133, "step": 28300 }, { - "epoch": 0.25, - "learning_rate": 3.7703360057652464e-05, - "loss": 0.2949, + "epoch": 0.06, + "learning_rate": 4.694626518422407e-05, + "loss": 0.3112, "step": 28310 }, { - "epoch": 0.25, - "learning_rate": 3.769885595892262e-05, - "loss": 0.3018, + "epoch": 0.06, + "learning_rate": 4.694514664101474e-05, + "loss": 0.3144, "step": 28320 }, { - "epoch": 0.25, - "learning_rate": 3.769435186019278e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.6944028097805424e-05, + "loss": 0.3061, "step": 28330 }, { - "epoch": 0.25, - "learning_rate": 3.768984776146293e-05, - "loss": 0.2961, + "epoch": 0.06, + "learning_rate": 4.69429095545961e-05, + "loss": 0.314, "step": 28340 }, { - "epoch": 0.25, - "learning_rate": 3.7685343662733094e-05, - "loss": 0.3022, + "epoch": 0.06, + "learning_rate": 4.694179101138677e-05, + "loss": 0.3162, "step": 28350 }, { - "epoch": 0.25, - "learning_rate": 3.7680839564003244e-05, - "loss": 0.2991, + "epoch": 0.06, + "learning_rate": 4.694067246817745e-05, + "loss": 0.3096, "step": 28360 }, { - "epoch": 0.25, - "learning_rate": 3.76763354652734e-05, - "loss": 0.3025, + "epoch": 0.06, + "learning_rate": 4.693955392496812e-05, + "loss": 0.3122, "step": 28370 }, { - "epoch": 0.25, - "learning_rate": 3.767183136654356e-05, - "loss": 0.2986, + "epoch": 0.06, + "learning_rate": 4.69384353817588e-05, + "loss": 0.3128, "step": 28380 }, { - "epoch": 0.25, - "learning_rate": 3.766732726781371e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.693731683854948e-05, + "loss": 0.3079, "step": 28390 }, { - "epoch": 0.25, - "learning_rate": 3.766282316908387e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.693619829534015e-05, + "loss": 0.3079, "step": 28400 }, { - "epoch": 0.25, - "learning_rate": 3.7658319070354025e-05, - "loss": 0.3019, + "epoch": 0.06, + "learning_rate": 4.693507975213083e-05, + "loss": 0.3068, "step": 28410 }, { - "epoch": 0.25, - "learning_rate": 3.765381497162418e-05, - "loss": 0.3003, + "epoch": 0.06, + "learning_rate": 4.69339612089215e-05, + "loss": 0.3075, "step": 28420 }, { - "epoch": 0.25, - "learning_rate": 3.764931087289433e-05, - "loss": 0.3024, + "epoch": 0.06, + "learning_rate": 4.6932842665712176e-05, + "loss": 0.3111, "step": 28430 }, { - "epoch": 0.25, - "learning_rate": 3.764480677416449e-05, - "loss": 0.3004, + "epoch": 0.06, + "learning_rate": 4.6931724122502854e-05, + "loss": 0.3055, "step": 28440 }, { - "epoch": 0.25, - "learning_rate": 3.764030267543465e-05, - "loss": 0.298, + "epoch": 0.06, + "learning_rate": 4.693060557929353e-05, + "loss": 0.3097, "step": 28450 }, { - "epoch": 0.25, - "learning_rate": 3.76357985767048e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.692948703608421e-05, + "loss": 0.311, "step": 28460 }, { - "epoch": 0.25, - "learning_rate": 3.763129447797496e-05, - "loss": 0.3083, + "epoch": 0.06, + "learning_rate": 4.692836849287488e-05, + "loss": 0.3128, "step": 28470 }, { - "epoch": 0.25, - "learning_rate": 3.7626790379245114e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.692724994966556e-05, + "loss": 0.3063, "step": 28480 }, { - "epoch": 0.25, - "learning_rate": 3.762273669038826e-05, - "loss": 0.301, + "epoch": 0.06, + "learning_rate": 4.692613140645624e-05, + "loss": 0.3095, "step": 28490 }, { - "epoch": 0.25, - "learning_rate": 3.761823259165841e-05, - "loss": 0.304, + "epoch": 0.06, + "learning_rate": 4.692501286324691e-05, + "loss": 0.3111, "step": 28500 }, { - "epoch": 0.25, - "learning_rate": 3.7613728492928566e-05, - "loss": 0.2993, + "epoch": 0.06, + "learning_rate": 4.6923894320037586e-05, + "loss": 0.3067, "step": 28510 }, { - "epoch": 0.25, - "learning_rate": 3.760922439419872e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.692277577682826e-05, + "loss": 0.3073, "step": 28520 }, { - "epoch": 0.25, - "learning_rate": 3.7604720295468874e-05, - "loss": 0.3005, + "epoch": 0.06, + "learning_rate": 4.6921657233618935e-05, + "loss": 0.3096, "step": 28530 }, { - "epoch": 0.25, - "learning_rate": 3.760021619673904e-05, - "loss": 0.3062, + "epoch": 0.06, + "learning_rate": 4.692053869040961e-05, + "loss": 0.317, "step": 28540 }, { - "epoch": 0.25, - "learning_rate": 3.759571209800919e-05, - "loss": 0.298, + "epoch": 0.06, + "learning_rate": 4.691942014720029e-05, + "loss": 0.3083, "step": 28550 }, { - "epoch": 0.25, - "learning_rate": 3.7591207999279346e-05, - "loss": 0.2957, + "epoch": 0.06, + "learning_rate": 4.691830160399097e-05, + "loss": 0.3121, "step": 28560 }, { - "epoch": 0.26, - "learning_rate": 3.7586703900549504e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.691718306078164e-05, + "loss": 0.3143, "step": 28570 }, { - "epoch": 0.26, - "learning_rate": 3.7582199801819655e-05, - "loss": 0.2983, + "epoch": 0.06, + "learning_rate": 4.691606451757232e-05, + "loss": 0.3094, "step": 28580 }, { - "epoch": 0.26, - "learning_rate": 3.757769570308982e-05, - "loss": 0.2955, + "epoch": 0.06, + "learning_rate": 4.691494597436299e-05, + "loss": 0.3077, "step": 28590 }, { - "epoch": 0.26, - "learning_rate": 3.757319160435997e-05, - "loss": 0.3003, + "epoch": 0.06, + "learning_rate": 4.691382743115367e-05, + "loss": 0.3107, "step": 28600 }, { - "epoch": 0.26, - "learning_rate": 3.756868750563012e-05, - "loss": 0.2939, + "epoch": 0.06, + "learning_rate": 4.6912708887944345e-05, + "loss": 0.3105, "step": 28610 }, { - "epoch": 0.26, - "learning_rate": 3.7564183406900285e-05, - "loss": 0.2977, - "step": 28620 + "epoch": 0.06, + "learning_rate": 4.6911590344735016e-05, + "loss": 0.3156, + "step": 28620 }, { - "epoch": 0.26, - "learning_rate": 3.7559679308170435e-05, - "loss": 0.2964, + "epoch": 0.06, + "learning_rate": 4.6910471801525694e-05, + "loss": 0.3083, "step": 28630 }, { - "epoch": 0.26, - "learning_rate": 3.755517520944059e-05, - "loss": 0.2995, + "epoch": 0.06, + "learning_rate": 4.690935325831637e-05, + "loss": 0.312, "step": 28640 }, { - "epoch": 0.26, - "learning_rate": 3.755067111071075e-05, - "loss": 0.2977, + "epoch": 0.06, + "learning_rate": 4.690823471510705e-05, + "loss": 0.3098, "step": 28650 }, { - "epoch": 0.26, - "learning_rate": 3.75461670119809e-05, - "loss": 0.2973, + "epoch": 0.06, + "learning_rate": 4.690711617189773e-05, + "loss": 0.3096, "step": 28660 }, { - "epoch": 0.26, - "learning_rate": 3.754166291325106e-05, - "loss": 0.2948, + "epoch": 0.06, + "learning_rate": 4.69059976286884e-05, + "loss": 0.3105, "step": 28670 }, { - "epoch": 0.26, - "learning_rate": 3.7537158814521216e-05, - "loss": 0.2978, + "epoch": 0.06, + "learning_rate": 4.690487908547908e-05, + "loss": 0.3098, "step": 28680 }, { - "epoch": 0.26, - "learning_rate": 3.7532654715791374e-05, - "loss": 0.3037, + "epoch": 0.06, + "learning_rate": 4.690376054226975e-05, + "loss": 0.309, "step": 28690 }, { - "epoch": 0.26, - "learning_rate": 3.752815061706153e-05, - "loss": 0.3042, + "epoch": 0.06, + "learning_rate": 4.6902641999060426e-05, + "loss": 0.3068, "step": 28700 }, { - "epoch": 0.26, - "learning_rate": 3.752364651833168e-05, - "loss": 0.3008, + "epoch": 0.06, + "learning_rate": 4.6901635310172034e-05, + "loss": 0.3176, "step": 28710 }, { - "epoch": 0.26, - "learning_rate": 3.751914241960184e-05, - "loss": 0.2954, + "epoch": 0.06, + "learning_rate": 4.690051676696271e-05, + "loss": 0.3116, "step": 28720 }, { - "epoch": 0.26, - "learning_rate": 3.7514638320872e-05, - "loss": 0.3005, + "epoch": 0.06, + "learning_rate": 4.689939822375339e-05, + "loss": 0.3119, "step": 28730 }, { - "epoch": 0.26, - "learning_rate": 3.7510134222142154e-05, - "loss": 0.2979, + "epoch": 0.06, + "learning_rate": 4.689827968054406e-05, + "loss": 0.3091, "step": 28740 }, { - "epoch": 0.26, - "learning_rate": 3.7505630123412305e-05, - "loss": 0.2992, + "epoch": 0.06, + "learning_rate": 4.689716113733474e-05, + "loss": 0.3131, "step": 28750 }, { - "epoch": 0.26, - "learning_rate": 3.750112602468246e-05, - "loss": 0.3048, + "epoch": 0.06, + "learning_rate": 4.689604259412541e-05, + "loss": 0.3144, "step": 28760 }, { - "epoch": 0.26, - "learning_rate": 3.749662192595262e-05, - "loss": 0.3022, + "epoch": 0.06, + "learning_rate": 4.689492405091609e-05, + "loss": 0.3105, "step": 28770 }, { - "epoch": 0.26, - "learning_rate": 3.749211782722277e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.6893805507706766e-05, + "loss": 0.3109, "step": 28780 }, { - "epoch": 0.26, - "learning_rate": 3.7487613728492935e-05, - "loss": 0.2938, + "epoch": 0.06, + "learning_rate": 4.689268696449744e-05, + "loss": 0.3133, "step": 28790 }, { - "epoch": 0.26, - "learning_rate": 3.7483109629763086e-05, - "loss": 0.3022, + "epoch": 0.06, + "learning_rate": 4.6891568421288116e-05, + "loss": 0.3102, "step": 28800 }, { - "epoch": 0.26, - "learning_rate": 3.7478605531033236e-05, - "loss": 0.2986, + "epoch": 0.06, + "learning_rate": 4.6890449878078793e-05, + "loss": 0.305, "step": 28810 }, { - "epoch": 0.26, - "learning_rate": 3.74741014323034e-05, - "loss": 0.3007, + "epoch": 0.06, + "learning_rate": 4.688933133486947e-05, + "loss": 0.3106, "step": 28820 }, { - "epoch": 0.26, - "learning_rate": 3.746959733357355e-05, - "loss": 0.3019, + "epoch": 0.06, + "learning_rate": 4.688821279166015e-05, + "loss": 0.3132, "step": 28830 }, { - "epoch": 0.26, - "learning_rate": 3.7465093234843716e-05, - "loss": 0.2875, + "epoch": 0.06, + "learning_rate": 4.688709424845082e-05, + "loss": 0.3159, "step": 28840 }, { - "epoch": 0.26, - "learning_rate": 3.7460589136113866e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.68859757052415e-05, + "loss": 0.3121, "step": 28850 }, { - "epoch": 0.26, - "learning_rate": 3.745608503738402e-05, - "loss": 0.2969, + "epoch": 0.06, + "learning_rate": 4.688485716203217e-05, + "loss": 0.3126, "step": 28860 }, { - "epoch": 0.26, - "learning_rate": 3.745158093865418e-05, - "loss": 0.297, + "epoch": 0.06, + "learning_rate": 4.688373861882285e-05, + "loss": 0.3056, "step": 28870 }, { - "epoch": 0.26, - "learning_rate": 3.744707683992433e-05, - "loss": 0.3046, + "epoch": 0.06, + "learning_rate": 4.6882620075613525e-05, + "loss": 0.3088, "step": 28880 }, { - "epoch": 0.26, - "learning_rate": 3.744257274119449e-05, - "loss": 0.301, + "epoch": 0.06, + "learning_rate": 4.6881501532404197e-05, + "loss": 0.3168, "step": 28890 }, { - "epoch": 0.26, - "learning_rate": 3.743806864246465e-05, - "loss": 0.2969, + "epoch": 0.06, + "learning_rate": 4.6880382989194874e-05, + "loss": 0.3129, "step": 28900 }, { - "epoch": 0.26, - "learning_rate": 3.74335645437348e-05, - "loss": 0.3009, + "epoch": 0.06, + "learning_rate": 4.687926444598555e-05, + "loss": 0.316, "step": 28910 }, { - "epoch": 0.26, - "learning_rate": 3.7429060445004955e-05, - "loss": 0.301, + "epoch": 0.06, + "learning_rate": 4.687814590277623e-05, + "loss": 0.3139, "step": 28920 }, { - "epoch": 0.26, - "learning_rate": 3.742455634627511e-05, - "loss": 0.3037, + "epoch": 0.06, + "learning_rate": 4.68770273595669e-05, + "loss": 0.3092, "step": 28930 }, { - "epoch": 0.26, - "learning_rate": 3.742005224754527e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.687590881635758e-05, + "loss": 0.3107, "step": 28940 }, { - "epoch": 0.26, - "learning_rate": 3.741554814881542e-05, - "loss": 0.3053, + "epoch": 0.06, + "learning_rate": 4.687479027314826e-05, + "loss": 0.3115, "step": 28950 }, { - "epoch": 0.26, - "learning_rate": 3.741104405008558e-05, - "loss": 0.3004, + "epoch": 0.06, + "learning_rate": 4.687367172993893e-05, + "loss": 0.306, "step": 28960 }, { - "epoch": 0.26, - "learning_rate": 3.7406539951355736e-05, - "loss": 0.3031, + "epoch": 0.06, + "learning_rate": 4.6872553186729606e-05, + "loss": 0.3043, "step": 28970 }, { - "epoch": 0.26, - "learning_rate": 3.740203585262589e-05, - "loss": 0.2959, + "epoch": 0.06, + "learning_rate": 4.687143464352028e-05, + "loss": 0.3068, "step": 28980 }, { - "epoch": 0.26, - "learning_rate": 3.739753175389605e-05, - "loss": 0.2991, + "epoch": 0.06, + "learning_rate": 4.6870316100310955e-05, + "loss": 0.3052, "step": 28990 }, { - "epoch": 0.26, - "learning_rate": 3.73930276551662e-05, - "loss": 0.3042, + "epoch": 0.06, + "learning_rate": 4.6869197557101633e-05, + "loss": 0.3031, "step": 29000 }, { - "epoch": 0.26, - "learning_rate": 3.738852355643636e-05, - "loss": 0.3054, + "epoch": 0.06, + "learning_rate": 4.6868079013892305e-05, + "loss": 0.3136, "step": 29010 }, { - "epoch": 0.26, - "learning_rate": 3.7384019457706517e-05, - "loss": 0.2965, + "epoch": 0.06, + "learning_rate": 4.686696047068298e-05, + "loss": 0.3099, "step": 29020 }, { - "epoch": 0.26, - "learning_rate": 3.737951535897667e-05, - "loss": 0.2966, + "epoch": 0.06, + "learning_rate": 4.686584192747366e-05, + "loss": 0.3102, "step": 29030 }, { - "epoch": 0.26, - "learning_rate": 3.737501126024683e-05, - "loss": 0.302, + "epoch": 0.06, + "learning_rate": 4.686472338426434e-05, + "loss": 0.3067, "step": 29040 }, { - "epoch": 0.26, - "learning_rate": 3.737050716151698e-05, - "loss": 0.2984, + "epoch": 0.06, + "learning_rate": 4.6863604841055016e-05, + "loss": 0.3127, "step": 29050 }, { - "epoch": 0.26, - "learning_rate": 3.736600306278713e-05, - "loss": 0.2974, + "epoch": 0.06, + "learning_rate": 4.686248629784569e-05, + "loss": 0.3076, "step": 29060 }, { - "epoch": 0.26, - "learning_rate": 3.73614989640573e-05, - "loss": 0.3003, + "epoch": 0.06, + "learning_rate": 4.6861367754636365e-05, + "loss": 0.3111, "step": 29070 }, { - "epoch": 0.26, - "learning_rate": 3.735699486532745e-05, - "loss": 0.2981, + "epoch": 0.06, + "learning_rate": 4.6860249211427037e-05, + "loss": 0.305, "step": 29080 }, { - "epoch": 0.26, - "learning_rate": 3.7352490766597605e-05, - "loss": 0.2944, + "epoch": 0.06, + "learning_rate": 4.6859130668217714e-05, + "loss": 0.3113, "step": 29090 }, { - "epoch": 0.26, - "learning_rate": 3.734798666786776e-05, - "loss": 0.3002, + "epoch": 0.06, + "learning_rate": 4.685801212500839e-05, + "loss": 0.3167, "step": 29100 }, { - "epoch": 0.26, - "learning_rate": 3.7343482569137914e-05, - "loss": 0.3017, + "epoch": 0.06, + "learning_rate": 4.6856893581799064e-05, + "loss": 0.3108, "step": 29110 }, { - "epoch": 0.26, - "learning_rate": 3.733897847040808e-05, - "loss": 0.3055, + "epoch": 0.06, + "learning_rate": 4.685577503858974e-05, + "loss": 0.3093, "step": 29120 }, { - "epoch": 0.26, - "learning_rate": 3.733447437167823e-05, - "loss": 0.2986, + "epoch": 0.07, + "learning_rate": 4.685465649538042e-05, + "loss": 0.3069, "step": 29130 }, { - "epoch": 0.26, - "learning_rate": 3.7329970272948386e-05, - "loss": 0.299, + "epoch": 0.07, + "learning_rate": 4.68535379521711e-05, + "loss": 0.31, "step": 29140 }, { - "epoch": 0.26, - "learning_rate": 3.7325466174218544e-05, - "loss": 0.2984, + "epoch": 0.07, + "learning_rate": 4.6852419408961775e-05, + "loss": 0.3086, "step": 29150 }, { - "epoch": 0.26, - "learning_rate": 3.7320962075488694e-05, - "loss": 0.2983, + "epoch": 0.07, + "learning_rate": 4.6851300865752446e-05, + "loss": 0.3057, "step": 29160 }, { - "epoch": 0.26, - "learning_rate": 3.731645797675885e-05, - "loss": 0.2975, + "epoch": 0.07, + "learning_rate": 4.6850182322543124e-05, + "loss": 0.3099, "step": 29170 }, { - "epoch": 0.26, - "learning_rate": 3.731195387802901e-05, - "loss": 0.3002, + "epoch": 0.07, + "learning_rate": 4.6849063779333795e-05, + "loss": 0.308, "step": 29180 }, { - "epoch": 0.26, - "learning_rate": 3.730744977929917e-05, - "loss": 0.3029, + "epoch": 0.07, + "learning_rate": 4.684794523612447e-05, + "loss": 0.3078, "step": 29190 }, { - "epoch": 0.26, - "learning_rate": 3.730294568056932e-05, - "loss": 0.3, + "epoch": 0.07, + "learning_rate": 4.684682669291515e-05, + "loss": 0.3042, "step": 29200 }, { - "epoch": 0.26, - "learning_rate": 3.7298441581839475e-05, - "loss": 0.2993, + "epoch": 0.07, + "learning_rate": 4.684570814970582e-05, + "loss": 0.3029, "step": 29210 }, { - "epoch": 0.26, - "learning_rate": 3.729393748310963e-05, - "loss": 0.2968, + "epoch": 0.07, + "learning_rate": 4.68445896064965e-05, + "loss": 0.3096, "step": 29220 }, { - "epoch": 0.26, - "learning_rate": 3.728943338437978e-05, - "loss": 0.301, + "epoch": 0.07, + "learning_rate": 4.684347106328718e-05, + "loss": 0.3122, "step": 29230 }, { - "epoch": 0.26, - "learning_rate": 3.728492928564995e-05, - "loss": 0.2964, + "epoch": 0.07, + "learning_rate": 4.6842352520077856e-05, + "loss": 0.3061, "step": 29240 }, { - "epoch": 0.26, - "learning_rate": 3.72804251869201e-05, - "loss": 0.2982, + "epoch": 0.07, + "learning_rate": 4.684123397686853e-05, + "loss": 0.3032, "step": 29250 }, { - "epoch": 0.26, - "learning_rate": 3.7275921088190256e-05, - "loss": 0.299, + "epoch": 0.07, + "learning_rate": 4.6840115433659205e-05, + "loss": 0.3113, "step": 29260 }, { - "epoch": 0.26, - "learning_rate": 3.727141698946041e-05, - "loss": 0.2979, + "epoch": 0.07, + "learning_rate": 4.683899689044988e-05, + "loss": 0.3126, "step": 29270 }, { - "epoch": 0.26, - "learning_rate": 3.7266912890730564e-05, - "loss": 0.2995, + "epoch": 0.07, + "learning_rate": 4.6837878347240554e-05, + "loss": 0.3085, "step": 29280 }, { - "epoch": 0.26, - "learning_rate": 3.726240879200072e-05, - "loss": 0.3018, + "epoch": 0.07, + "learning_rate": 4.683675980403123e-05, + "loss": 0.3105, "step": 29290 }, { - "epoch": 0.26, - "learning_rate": 3.725790469327088e-05, - "loss": 0.2987, + "epoch": 0.07, + "learning_rate": 4.6835641260821903e-05, + "loss": 0.3094, "step": 29300 }, { - "epoch": 0.26, - "learning_rate": 3.725340059454103e-05, - "loss": 0.3027, + "epoch": 0.07, + "learning_rate": 4.683452271761258e-05, + "loss": 0.3131, "step": 29310 }, { - "epoch": 0.26, - "learning_rate": 3.7248896495811194e-05, - "loss": 0.2963, + "epoch": 0.07, + "learning_rate": 4.683340417440326e-05, + "loss": 0.3128, "step": 29320 }, { - "epoch": 0.26, - "learning_rate": 3.7244392397081345e-05, - "loss": 0.2952, + "epoch": 0.07, + "learning_rate": 4.683228563119394e-05, + "loss": 0.308, "step": 29330 }, { - "epoch": 0.26, - "learning_rate": 3.72398882983515e-05, - "loss": 0.301, + "epoch": 0.07, + "learning_rate": 4.6831167087984615e-05, + "loss": 0.305, "step": 29340 }, { - "epoch": 0.26, - "learning_rate": 3.723538419962166e-05, - "loss": 0.2942, + "epoch": 0.07, + "learning_rate": 4.6830048544775286e-05, + "loss": 0.3127, "step": 29350 }, { - "epoch": 0.26, - "learning_rate": 3.723088010089181e-05, - "loss": 0.2967, + "epoch": 0.07, + "learning_rate": 4.6828930001565964e-05, + "loss": 0.3102, "step": 29360 }, { - "epoch": 0.26, - "learning_rate": 3.722637600216197e-05, - "loss": 0.3007, + "epoch": 0.07, + "learning_rate": 4.682781145835664e-05, + "loss": 0.3104, "step": 29370 }, { - "epoch": 0.26, - "learning_rate": 3.7221871903432125e-05, - "loss": 0.2967, + "epoch": 0.07, + "learning_rate": 4.682669291514731e-05, + "loss": 0.308, "step": 29380 }, { - "epoch": 0.26, - "learning_rate": 3.721736780470228e-05, - "loss": 0.3014, + "epoch": 0.07, + "learning_rate": 4.682557437193799e-05, + "loss": 0.3102, "step": 29390 }, { - "epoch": 0.26, - "learning_rate": 3.721286370597244e-05, - "loss": 0.2965, + "epoch": 0.07, + "learning_rate": 4.682445582872866e-05, + "loss": 0.3072, "step": 29400 }, { - "epoch": 0.26, - "learning_rate": 3.720835960724259e-05, - "loss": 0.2985, + "epoch": 0.07, + "learning_rate": 4.682333728551934e-05, + "loss": 0.3053, "step": 29410 }, { - "epoch": 0.26, - "learning_rate": 3.720385550851275e-05, - "loss": 0.2991, + "epoch": 0.07, + "learning_rate": 4.682221874231002e-05, + "loss": 0.3037, "step": 29420 }, { - "epoch": 0.26, - "learning_rate": 3.7199351409782906e-05, - "loss": 0.3002, + "epoch": 0.07, + "learning_rate": 4.682110019910069e-05, + "loss": 0.3069, "step": 29430 }, { - "epoch": 0.26, - "learning_rate": 3.7194847311053063e-05, - "loss": 0.295, + "epoch": 0.07, + "learning_rate": 4.681998165589137e-05, + "loss": 0.3102, "step": 29440 }, { - "epoch": 0.26, - "learning_rate": 3.7190343212323214e-05, - "loss": 0.2948, + "epoch": 0.07, + "learning_rate": 4.6818863112682045e-05, + "loss": 0.3099, "step": 29450 }, { - "epoch": 0.26, - "learning_rate": 3.718583911359337e-05, - "loss": 0.2941, + "epoch": 0.07, + "learning_rate": 4.681774456947272e-05, + "loss": 0.312, "step": 29460 }, { - "epoch": 0.26, - "learning_rate": 3.718133501486353e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.68166260262634e-05, + "loss": 0.3056, "step": 29470 }, { - "epoch": 0.26, - "learning_rate": 3.717683091613368e-05, - "loss": 0.298, + "epoch": 0.07, + "learning_rate": 4.681550748305407e-05, + "loss": 0.3113, "step": 29480 }, { - "epoch": 0.26, - "learning_rate": 3.7172326817403844e-05, - "loss": 0.3002, + "epoch": 0.07, + "learning_rate": 4.681438893984475e-05, + "loss": 0.3128, "step": 29490 }, { - "epoch": 0.26, - "learning_rate": 3.7167822718673995e-05, - "loss": 0.301, + "epoch": 0.07, + "learning_rate": 4.681327039663542e-05, + "loss": 0.3067, "step": 29500 }, { - "epoch": 0.26, - "learning_rate": 3.7163318619944146e-05, - "loss": 0.2965, + "epoch": 0.07, + "learning_rate": 4.68121518534261e-05, + "loss": 0.3125, "step": 29510 }, { - "epoch": 0.26, - "learning_rate": 3.715881452121431e-05, - "loss": 0.2918, + "epoch": 0.07, + "learning_rate": 4.681103331021678e-05, + "loss": 0.3113, "step": 29520 }, { - "epoch": 0.26, - "learning_rate": 3.715431042248446e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.680991476700745e-05, + "loss": 0.3086, "step": 29530 }, { - "epoch": 0.26, - "learning_rate": 3.714980632375462e-05, - "loss": 0.2971, + "epoch": 0.07, + "learning_rate": 4.6808796223798126e-05, + "loss": 0.3097, "step": 29540 }, { - "epoch": 0.26, - "learning_rate": 3.7145302225024776e-05, - "loss": 0.3026, + "epoch": 0.07, + "learning_rate": 4.6807677680588804e-05, + "loss": 0.3045, "step": 29550 }, { - "epoch": 0.26, - "learning_rate": 3.7140798126294926e-05, - "loss": 0.2967, + "epoch": 0.07, + "learning_rate": 4.680655913737948e-05, + "loss": 0.3069, "step": 29560 }, { - "epoch": 0.26, - "learning_rate": 3.713629402756509e-05, - "loss": 0.2961, + "epoch": 0.07, + "learning_rate": 4.680544059417015e-05, + "loss": 0.3129, "step": 29570 }, { - "epoch": 0.26, - "learning_rate": 3.713178992883524e-05, - "loss": 0.2931, + "epoch": 0.07, + "learning_rate": 4.680432205096083e-05, + "loss": 0.3095, "step": 29580 }, { - "epoch": 0.26, - "learning_rate": 3.71272858301054e-05, - "loss": 0.2893, + "epoch": 0.07, + "learning_rate": 4.680320350775151e-05, + "loss": 0.3072, "step": 29590 }, { - "epoch": 0.26, - "learning_rate": 3.7122781731375556e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.680208496454218e-05, + "loss": 0.3058, "step": 29600 }, { - "epoch": 0.26, - "learning_rate": 3.711827763264571e-05, - "loss": 0.2948, + "epoch": 0.07, + "learning_rate": 4.680096642133286e-05, + "loss": 0.3163, "step": 29610 }, { - "epoch": 0.26, - "learning_rate": 3.7113773533915864e-05, - "loss": 0.2977, + "epoch": 0.07, + "learning_rate": 4.679984787812353e-05, + "loss": 0.3054, "step": 29620 }, { - "epoch": 0.26, - "learning_rate": 3.710926943518602e-05, - "loss": 0.2969, + "epoch": 0.07, + "learning_rate": 4.679872933491421e-05, + "loss": 0.3077, "step": 29630 }, { - "epoch": 0.26, - "learning_rate": 3.710476533645618e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.6797610791704885e-05, + "loss": 0.3064, "step": 29640 }, { - "epoch": 0.26, - "learning_rate": 3.710026123772633e-05, - "loss": 0.2971, + "epoch": 0.07, + "learning_rate": 4.679649224849556e-05, + "loss": 0.3082, "step": 29650 }, { - "epoch": 0.26, - "learning_rate": 3.709575713899649e-05, - "loss": 0.2965, + "epoch": 0.07, + "learning_rate": 4.679537370528624e-05, + "loss": 0.31, "step": 29660 }, { - "epoch": 0.26, - "learning_rate": 3.7091253040266645e-05, - "loss": 0.2974, + "epoch": 0.07, + "learning_rate": 4.679425516207691e-05, + "loss": 0.2984, "step": 29670 }, { - "epoch": 0.26, - "learning_rate": 3.70867489415368e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.679313661886759e-05, + "loss": 0.3067, "step": 29680 }, { - "epoch": 0.27, - "learning_rate": 3.708224484280696e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.679201807565827e-05, + "loss": 0.3085, "step": 29690 }, { - "epoch": 0.27, - "learning_rate": 3.707774074407711e-05, - "loss": 0.2889, + "epoch": 0.07, + "learning_rate": 4.679089953244894e-05, + "loss": 0.3032, "step": 29700 }, { - "epoch": 0.27, - "learning_rate": 3.707323664534727e-05, - "loss": 0.2993, + "epoch": 0.07, + "learning_rate": 4.678978098923962e-05, + "loss": 0.3034, "step": 29710 }, { - "epoch": 0.27, - "learning_rate": 3.7068732546617426e-05, - "loss": 0.2978, + "epoch": 0.07, + "learning_rate": 4.678866244603029e-05, + "loss": 0.3059, "step": 29720 }, { - "epoch": 0.27, - "learning_rate": 3.7064228447887577e-05, - "loss": 0.2974, + "epoch": 0.07, + "learning_rate": 4.6787543902820966e-05, + "loss": 0.3015, "step": 29730 }, { - "epoch": 0.27, - "learning_rate": 3.7059724349157734e-05, - "loss": 0.2934, + "epoch": 0.07, + "learning_rate": 4.6786425359611644e-05, + "loss": 0.3112, "step": 29740 }, { - "epoch": 0.27, - "learning_rate": 3.705522025042789e-05, - "loss": 0.298, + "epoch": 0.07, + "learning_rate": 4.678530681640232e-05, + "loss": 0.3074, "step": 29750 }, { - "epoch": 0.27, - "learning_rate": 3.705071615169804e-05, - "loss": 0.2998, + "epoch": 0.07, + "learning_rate": 4.6784188273193e-05, + "loss": 0.31, "step": 29760 }, { - "epoch": 0.27, - "learning_rate": 3.7046212052968207e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.678306972998367e-05, + "loss": 0.3097, "step": 29770 }, { - "epoch": 0.27, - "learning_rate": 3.704170795423836e-05, - "loss": 0.2964, + "epoch": 0.07, + "learning_rate": 4.678195118677435e-05, + "loss": 0.3031, "step": 29780 }, { - "epoch": 0.27, - "learning_rate": 3.7037203855508515e-05, - "loss": 0.2987, + "epoch": 0.07, + "learning_rate": 4.678083264356503e-05, + "loss": 0.3055, "step": 29790 }, { - "epoch": 0.27, - "learning_rate": 3.703269975677867e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.67797141003557e-05, + "loss": 0.308, "step": 29800 }, { - "epoch": 0.27, - "learning_rate": 3.702819565804882e-05, - "loss": 0.2934, + "epoch": 0.07, + "learning_rate": 4.6778595557146376e-05, + "loss": 0.3017, "step": 29810 }, { - "epoch": 0.27, - "learning_rate": 3.702369155931899e-05, - "loss": 0.2939, + "epoch": 0.07, + "learning_rate": 4.677747701393705e-05, + "loss": 0.3026, "step": 29820 }, { - "epoch": 0.27, - "learning_rate": 3.701918746058914e-05, - "loss": 0.2989, + "epoch": 0.07, + "learning_rate": 4.6776358470727725e-05, + "loss": 0.305, "step": 29830 }, { - "epoch": 0.27, - "learning_rate": 3.7014683361859295e-05, - "loss": 0.2954, + "epoch": 0.07, + "learning_rate": 4.67752399275184e-05, + "loss": 0.3128, "step": 29840 }, { - "epoch": 0.27, - "learning_rate": 3.701017926312945e-05, - "loss": 0.3008, + "epoch": 0.07, + "learning_rate": 4.6774121384309074e-05, + "loss": 0.3121, "step": 29850 }, { - "epoch": 0.27, - "learning_rate": 3.7005675164399604e-05, - "loss": 0.2944, + "epoch": 0.07, + "learning_rate": 4.677300284109975e-05, + "loss": 0.302, "step": 29860 }, { - "epoch": 0.27, - "learning_rate": 3.700117106566976e-05, - "loss": 0.2966, + "epoch": 0.07, + "learning_rate": 4.677188429789043e-05, + "loss": 0.3045, "step": 29870 }, { - "epoch": 0.27, - "learning_rate": 3.699666696693992e-05, - "loss": 0.3034, + "epoch": 0.07, + "learning_rate": 4.677076575468111e-05, + "loss": 0.3099, "step": 29880 }, { - "epoch": 0.27, - "learning_rate": 3.6992162868210076e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.676964721147178e-05, + "loss": 0.3019, "step": 29890 }, { - "epoch": 0.27, - "learning_rate": 3.698765876948023e-05, - "loss": 0.2986, + "epoch": 0.07, + "learning_rate": 4.676852866826246e-05, + "loss": 0.3072, "step": 29900 }, { - "epoch": 0.27, - "learning_rate": 3.6983154670750384e-05, - "loss": 0.2954, + "epoch": 0.07, + "learning_rate": 4.6767410125053135e-05, + "loss": 0.3101, "step": 29910 }, { - "epoch": 0.27, - "learning_rate": 3.697865057202054e-05, - "loss": 0.3012, + "epoch": 0.07, + "learning_rate": 4.6766291581843806e-05, + "loss": 0.3038, "step": 29920 }, { - "epoch": 0.27, - "learning_rate": 3.697414647329069e-05, - "loss": 0.298, + "epoch": 0.07, + "learning_rate": 4.6765173038634484e-05, + "loss": 0.3092, "step": 29930 }, { - "epoch": 0.27, - "learning_rate": 3.696964237456085e-05, - "loss": 0.2923, + "epoch": 0.07, + "learning_rate": 4.6764054495425155e-05, + "loss": 0.3078, "step": 29940 }, { - "epoch": 0.27, - "learning_rate": 3.696513827583101e-05, - "loss": 0.2914, + "epoch": 0.07, + "learning_rate": 4.676293595221583e-05, + "loss": 0.3053, "step": 29950 }, { - "epoch": 0.27, - "learning_rate": 3.6960634177101165e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.676181740900651e-05, + "loss": 0.3079, "step": 29960 }, { - "epoch": 0.27, - "learning_rate": 3.695613007837132e-05, - "loss": 0.293, + "epoch": 0.07, + "learning_rate": 4.676069886579719e-05, + "loss": 0.3096, "step": 29970 }, { - "epoch": 0.27, - "learning_rate": 3.695162597964147e-05, - "loss": 0.296, + "epoch": 0.07, + "learning_rate": 4.675958032258787e-05, + "loss": 0.3084, "step": 29980 }, { - "epoch": 0.27, - "learning_rate": 3.694712188091163e-05, - "loss": 0.2911, + "epoch": 0.07, + "learning_rate": 4.675846177937854e-05, + "loss": 0.3085, "step": 29990 }, { - "epoch": 0.27, - "learning_rate": 3.694261778218179e-05, - "loss": 0.293, + "epoch": 0.07, + "learning_rate": 4.6757343236169216e-05, + "loss": 0.2992, "step": 30000 }, { - "epoch": 0.27, - "learning_rate": 3.693811368345194e-05, - "loss": 0.2924, + "epoch": 0.07, + "learning_rate": 4.6756224692959894e-05, + "loss": 0.3073, "step": 30010 }, { - "epoch": 0.27, - "learning_rate": 3.69336095847221e-05, - "loss": 0.2981, + "epoch": 0.07, + "learning_rate": 4.6755106149750565e-05, + "loss": 0.3048, "step": 30020 }, { - "epoch": 0.27, - "learning_rate": 3.6929105485992254e-05, - "loss": 0.2941, + "epoch": 0.07, + "learning_rate": 4.675398760654124e-05, + "loss": 0.3035, "step": 30030 }, { - "epoch": 0.27, - "learning_rate": 3.692460138726241e-05, - "loss": 0.2966, + "epoch": 0.07, + "learning_rate": 4.6752869063331914e-05, + "loss": 0.3039, "step": 30040 }, { - "epoch": 0.27, - "learning_rate": 3.692009728853257e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.675175052012259e-05, + "loss": 0.3056, "step": 30050 }, { - "epoch": 0.27, - "learning_rate": 3.691559318980272e-05, - "loss": 0.2976, + "epoch": 0.07, + "learning_rate": 4.675063197691327e-05, + "loss": 0.3046, "step": 30060 }, { - "epoch": 0.27, - "learning_rate": 3.691108909107288e-05, - "loss": 0.2909, + "epoch": 0.07, + "learning_rate": 4.674951343370395e-05, + "loss": 0.3108, "step": 30070 }, { - "epoch": 0.27, - "learning_rate": 3.6906584992343035e-05, - "loss": 0.2923, + "epoch": 0.07, + "learning_rate": 4.6748394890494626e-05, + "loss": 0.3093, "step": 30080 }, { - "epoch": 0.27, - "learning_rate": 3.690208089361319e-05, - "loss": 0.3011, + "epoch": 0.07, + "learning_rate": 4.67472763472853e-05, + "loss": 0.3062, "step": 30090 }, { - "epoch": 0.27, - "learning_rate": 3.689757679488334e-05, - "loss": 0.2997, + "epoch": 0.07, + "learning_rate": 4.6746157804075975e-05, + "loss": 0.3063, "step": 30100 }, { - "epoch": 0.27, - "learning_rate": 3.68930726961535e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.674503926086665e-05, + "loss": 0.3072, "step": 30110 }, { - "epoch": 0.27, - "learning_rate": 3.688856859742366e-05, - "loss": 0.2996, + "epoch": 0.07, + "learning_rate": 4.6743920717657324e-05, + "loss": 0.3144, "step": 30120 }, { - "epoch": 0.27, - "learning_rate": 3.6884064498693815e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.6742802174448e-05, + "loss": 0.3107, "step": 30130 }, { - "epoch": 0.27, - "learning_rate": 3.687956039996397e-05, - "loss": 0.2948, + "epoch": 0.07, + "learning_rate": 4.674168363123867e-05, + "loss": 0.3004, "step": 30140 }, { - "epoch": 0.27, - "learning_rate": 3.6875056301234123e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.674056508802935e-05, + "loss": 0.3013, "step": 30150 }, { - "epoch": 0.27, - "learning_rate": 3.687055220250428e-05, - "loss": 0.2919, + "epoch": 0.07, + "learning_rate": 4.673944654482003e-05, + "loss": 0.3097, "step": 30160 }, { - "epoch": 0.27, - "learning_rate": 3.686604810377444e-05, - "loss": 0.2947, + "epoch": 0.07, + "learning_rate": 4.673832800161071e-05, + "loss": 0.307, "step": 30170 }, { - "epoch": 0.27, - "learning_rate": 3.686154400504459e-05, - "loss": 0.2941, + "epoch": 0.07, + "learning_rate": 4.6737209458401385e-05, + "loss": 0.3032, "step": 30180 }, { - "epoch": 0.27, - "learning_rate": 3.685703990631475e-05, - "loss": 0.2917, + "epoch": 0.07, + "learning_rate": 4.6736090915192056e-05, + "loss": 0.3042, "step": 30190 }, { - "epoch": 0.27, - "learning_rate": 3.6852535807584904e-05, - "loss": 0.3018, + "epoch": 0.07, + "learning_rate": 4.6734972371982734e-05, + "loss": 0.302, "step": 30200 }, { - "epoch": 0.27, - "learning_rate": 3.6848031708855055e-05, - "loss": 0.2991, + "epoch": 0.07, + "learning_rate": 4.6733853828773405e-05, + "loss": 0.3037, "step": 30210 }, { - "epoch": 0.27, - "learning_rate": 3.684352761012522e-05, - "loss": 0.3017, + "epoch": 0.07, + "learning_rate": 4.673273528556408e-05, + "loss": 0.3101, "step": 30220 }, { - "epoch": 0.27, - "learning_rate": 3.683902351139537e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.673161674235476e-05, + "loss": 0.3119, "step": 30230 }, { - "epoch": 0.27, - "learning_rate": 3.683451941266553e-05, - "loss": 0.2959, + "epoch": 0.07, + "learning_rate": 4.673049819914543e-05, + "loss": 0.3097, "step": 30240 }, { - "epoch": 0.27, - "learning_rate": 3.6830015313935685e-05, - "loss": 0.299, + "epoch": 0.07, + "learning_rate": 4.672937965593611e-05, + "loss": 0.3116, "step": 30250 }, { - "epoch": 0.27, - "learning_rate": 3.6825511215205836e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.672826111272678e-05, + "loss": 0.3034, "step": 30260 }, { - "epoch": 0.27, - "learning_rate": 3.6821007116476e-05, - "loss": 0.2964, + "epoch": 0.07, + "learning_rate": 4.672714256951746e-05, + "loss": 0.3077, "step": 30270 }, { - "epoch": 0.27, - "learning_rate": 3.681650301774615e-05, - "loss": 0.2933, + "epoch": 0.07, + "learning_rate": 4.6726024026308144e-05, + "loss": 0.3008, "step": 30280 }, { - "epoch": 0.27, - "learning_rate": 3.681199891901631e-05, - "loss": 0.2932, + "epoch": 0.07, + "learning_rate": 4.6724905483098815e-05, + "loss": 0.3063, "step": 30290 }, { - "epoch": 0.27, - "learning_rate": 3.6807494820286465e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.672378693988949e-05, + "loss": 0.3068, "step": 30300 }, { - "epoch": 0.27, - "learning_rate": 3.6802990721556616e-05, - "loss": 0.2892, + "epoch": 0.07, + "learning_rate": 4.6722668396680164e-05, + "loss": 0.307, "step": 30310 }, { - "epoch": 0.27, - "learning_rate": 3.6798486622826774e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.672154985347084e-05, + "loss": 0.3098, "step": 30320 }, { - "epoch": 0.27, - "learning_rate": 3.679398252409693e-05, - "loss": 0.293, + "epoch": 0.07, + "learning_rate": 4.672043131026152e-05, + "loss": 0.3017, "step": 30330 }, { - "epoch": 0.27, - "learning_rate": 3.678947842536709e-05, - "loss": 0.2949, + "epoch": 0.07, + "learning_rate": 4.671931276705219e-05, + "loss": 0.3081, "step": 30340 }, { - "epoch": 0.27, - "learning_rate": 3.678497432663724e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.671819422384287e-05, + "loss": 0.2997, "step": 30350 }, { - "epoch": 0.27, - "learning_rate": 3.67804702279074e-05, - "loss": 0.2949, + "epoch": 0.07, + "learning_rate": 4.671707568063354e-05, + "loss": 0.3104, "step": 30360 }, { - "epoch": 0.27, - "learning_rate": 3.6775966129177554e-05, - "loss": 0.2944, + "epoch": 0.07, + "learning_rate": 4.671595713742422e-05, + "loss": 0.3008, "step": 30370 }, { - "epoch": 0.27, - "learning_rate": 3.6771462030447705e-05, - "loss": 0.2923, + "epoch": 0.07, + "learning_rate": 4.6714838594214896e-05, + "loss": 0.3077, "step": 30380 }, { - "epoch": 0.27, - "learning_rate": 3.676695793171786e-05, - "loss": 0.2942, + "epoch": 0.07, + "learning_rate": 4.6713720051005574e-05, + "loss": 0.3033, "step": 30390 }, { - "epoch": 0.27, - "learning_rate": 3.676245383298802e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.671260150779625e-05, + "loss": 0.3051, "step": 30400 }, { - "epoch": 0.27, - "learning_rate": 3.675794973425818e-05, - "loss": 0.2969, + "epoch": 0.07, + "learning_rate": 4.671148296458692e-05, + "loss": 0.3037, "step": 30410 }, { - "epoch": 0.27, - "learning_rate": 3.6753445635528335e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.67103644213776e-05, + "loss": 0.3044, "step": 30420 }, { - "epoch": 0.27, - "learning_rate": 3.6748941536798486e-05, - "loss": 0.2883, + "epoch": 0.07, + "learning_rate": 4.670924587816828e-05, + "loss": 0.3108, "step": 30430 }, { - "epoch": 0.27, - "learning_rate": 3.674443743806864e-05, - "loss": 0.3013, + "epoch": 0.07, + "learning_rate": 4.670812733495895e-05, + "loss": 0.2998, "step": 30440 }, { - "epoch": 0.27, - "learning_rate": 3.67399333393388e-05, - "loss": 0.2976, + "epoch": 0.07, + "learning_rate": 4.670700879174963e-05, + "loss": 0.3073, "step": 30450 }, { - "epoch": 0.27, - "learning_rate": 3.673542924060895e-05, - "loss": 0.2963, + "epoch": 0.07, + "learning_rate": 4.67058902485403e-05, + "loss": 0.3141, "step": 30460 }, { - "epoch": 0.27, - "learning_rate": 3.6730925141879116e-05, - "loss": 0.2938, + "epoch": 0.07, + "learning_rate": 4.670477170533098e-05, + "loss": 0.304, "step": 30470 }, { - "epoch": 0.27, - "learning_rate": 3.6726421043149266e-05, - "loss": 0.2953, + "epoch": 0.07, + "learning_rate": 4.6703653162121655e-05, + "loss": 0.2987, "step": 30480 }, { - "epoch": 0.27, - "learning_rate": 3.6721916944419424e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.670253461891233e-05, + "loss": 0.3043, "step": 30490 }, { - "epoch": 0.27, - "learning_rate": 3.671741284568958e-05, - "loss": 0.2942, + "epoch": 0.07, + "learning_rate": 4.670141607570301e-05, + "loss": 0.3039, "step": 30500 }, { - "epoch": 0.27, - "learning_rate": 3.671290874695973e-05, - "loss": 0.2949, + "epoch": 0.07, + "learning_rate": 4.670029753249368e-05, + "loss": 0.3038, "step": 30510 }, { - "epoch": 0.27, - "learning_rate": 3.670840464822989e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.669917898928436e-05, + "loss": 0.3063, "step": 30520 }, { - "epoch": 0.27, - "learning_rate": 3.670390054950005e-05, - "loss": 0.2946, + "epoch": 0.07, + "learning_rate": 4.669806044607503e-05, + "loss": 0.3024, "step": 30530 }, { - "epoch": 0.27, - "learning_rate": 3.6699396450770205e-05, - "loss": 0.2855, + "epoch": 0.07, + "learning_rate": 4.669694190286571e-05, + "loss": 0.3072, "step": 30540 }, { - "epoch": 0.27, - "learning_rate": 3.669489235204036e-05, - "loss": 0.2949, + "epoch": 0.07, + "learning_rate": 4.669582335965639e-05, + "loss": 0.3018, "step": 30550 }, { - "epoch": 0.27, - "learning_rate": 3.669038825331051e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.669470481644706e-05, + "loss": 0.3062, "step": 30560 }, { - "epoch": 0.27, - "learning_rate": 3.668588415458067e-05, - "loss": 0.2893, + "epoch": 0.07, + "learning_rate": 4.6693586273237736e-05, + "loss": 0.3052, "step": 30570 }, { - "epoch": 0.27, - "learning_rate": 3.668138005585083e-05, - "loss": 0.291, + "epoch": 0.07, + "learning_rate": 4.6692467730028414e-05, + "loss": 0.3017, "step": 30580 }, { - "epoch": 0.27, - "learning_rate": 3.667687595712098e-05, - "loss": 0.2941, + "epoch": 0.07, + "learning_rate": 4.669134918681909e-05, + "loss": 0.3019, "step": 30590 }, { - "epoch": 0.27, - "learning_rate": 3.6672371858391136e-05, - "loss": 0.2945, + "epoch": 0.07, + "learning_rate": 4.669023064360977e-05, + "loss": 0.3028, "step": 30600 }, { - "epoch": 0.27, - "learning_rate": 3.6667867759661294e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.668911210040044e-05, + "loss": 0.3082, "step": 30610 }, { - "epoch": 0.27, - "learning_rate": 3.666381407080444e-05, - "loss": 0.2943, + "epoch": 0.07, + "learning_rate": 4.668799355719112e-05, + "loss": 0.3099, "step": 30620 }, { - "epoch": 0.27, - "learning_rate": 3.665930997207459e-05, - "loss": 0.2903, + "epoch": 0.07, + "learning_rate": 4.668687501398179e-05, + "loss": 0.3044, "step": 30630 }, { - "epoch": 0.27, - "learning_rate": 3.6654805873344746e-05, - "loss": 0.2898, + "epoch": 0.07, + "learning_rate": 4.668575647077247e-05, + "loss": 0.304, "step": 30640 }, { - "epoch": 0.27, - "learning_rate": 3.66503017746149e-05, - "loss": 0.2909, + "epoch": 0.07, + "learning_rate": 4.6684637927563146e-05, + "loss": 0.3104, "step": 30650 }, { - "epoch": 0.27, - "learning_rate": 3.664579767588506e-05, - "loss": 0.2886, + "epoch": 0.07, + "learning_rate": 4.668351938435382e-05, + "loss": 0.3064, "step": 30660 }, { - "epoch": 0.27, - "learning_rate": 3.664129357715521e-05, - "loss": 0.2982, + "epoch": 0.07, + "learning_rate": 4.6682400841144495e-05, + "loss": 0.3032, "step": 30670 }, { - "epoch": 0.27, - "learning_rate": 3.663678947842537e-05, - "loss": 0.2881, + "epoch": 0.07, + "learning_rate": 4.6681282297935166e-05, + "loss": 0.3042, "step": 30680 }, { - "epoch": 0.27, - "learning_rate": 3.6632285379695526e-05, - "loss": 0.2962, + "epoch": 0.07, + "learning_rate": 4.668016375472585e-05, + "loss": 0.3018, "step": 30690 }, { - "epoch": 0.27, - "learning_rate": 3.662778128096568e-05, - "loss": 0.3, + "epoch": 0.07, + "learning_rate": 4.667904521151653e-05, + "loss": 0.3075, "step": 30700 }, { - "epoch": 0.27, - "learning_rate": 3.662327718223584e-05, - "loss": 0.297, + "epoch": 0.07, + "learning_rate": 4.66779266683072e-05, + "loss": 0.3096, "step": 30710 }, { - "epoch": 0.27, - "learning_rate": 3.661877308350599e-05, - "loss": 0.2901, + "epoch": 0.07, + "learning_rate": 4.667680812509788e-05, + "loss": 0.3034, "step": 30720 }, { - "epoch": 0.27, - "learning_rate": 3.661426898477614e-05, - "loss": 0.2934, + "epoch": 0.07, + "learning_rate": 4.667568958188855e-05, + "loss": 0.3063, "step": 30730 }, { - "epoch": 0.27, - "learning_rate": 3.660976488604631e-05, - "loss": 0.2908, + "epoch": 0.07, + "learning_rate": 4.667468289300016e-05, + "loss": 0.3085, "step": 30740 }, { - "epoch": 0.27, - "learning_rate": 3.660526078731646e-05, - "loss": 0.2942, + "epoch": 0.07, + "learning_rate": 4.6673564349790836e-05, + "loss": 0.3021, "step": 30750 }, { - "epoch": 0.27, - "learning_rate": 3.6600756688586615e-05, - "loss": 0.2953, + "epoch": 0.07, + "learning_rate": 4.6672445806581514e-05, + "loss": 0.3034, "step": 30760 }, { - "epoch": 0.27, - "learning_rate": 3.659625258985677e-05, - "loss": 0.2934, + "epoch": 0.07, + "learning_rate": 4.667132726337219e-05, + "loss": 0.308, "step": 30770 }, { - "epoch": 0.27, - "learning_rate": 3.659174849112692e-05, - "loss": 0.2983, + "epoch": 0.07, + "learning_rate": 4.667020872016286e-05, + "loss": 0.3065, "step": 30780 }, { - "epoch": 0.27, - "learning_rate": 3.658724439239709e-05, - "loss": 0.2921, + "epoch": 0.07, + "learning_rate": 4.666909017695354e-05, + "loss": 0.2999, "step": 30790 }, { - "epoch": 0.27, - "learning_rate": 3.658274029366724e-05, - "loss": 0.2957, + "epoch": 0.07, + "learning_rate": 4.666797163374421e-05, + "loss": 0.3056, "step": 30800 }, { - "epoch": 0.28, - "learning_rate": 3.6578236194937396e-05, - "loss": 0.2949, + "epoch": 0.07, + "learning_rate": 4.666685309053489e-05, + "loss": 0.2983, "step": 30810 }, { - "epoch": 0.28, - "learning_rate": 3.657373209620755e-05, - "loss": 0.2985, + "epoch": 0.07, + "learning_rate": 4.666573454732557e-05, + "loss": 0.2993, "step": 30820 }, { - "epoch": 0.28, - "learning_rate": 3.6569227997477704e-05, - "loss": 0.2879, + "epoch": 0.07, + "learning_rate": 4.666461600411624e-05, + "loss": 0.3028, "step": 30830 }, { - "epoch": 0.28, - "learning_rate": 3.656472389874786e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.666349746090692e-05, + "loss": 0.3033, "step": 30840 }, { - "epoch": 0.28, - "learning_rate": 3.656021980001802e-05, - "loss": 0.2872, + "epoch": 0.07, + "learning_rate": 4.666237891769759e-05, + "loss": 0.2979, "step": 30850 }, { - "epoch": 0.28, - "learning_rate": 3.6555715701288176e-05, - "loss": 0.2912, + "epoch": 0.07, + "learning_rate": 4.666126037448827e-05, + "loss": 0.2999, "step": 30860 }, { - "epoch": 0.28, - "learning_rate": 3.655121160255833e-05, - "loss": 0.2935, + "epoch": 0.07, + "learning_rate": 4.6660141831278944e-05, + "loss": 0.3043, "step": 30870 }, { - "epoch": 0.28, - "learning_rate": 3.6546707503828485e-05, - "loss": 0.2927, + "epoch": 0.07, + "learning_rate": 4.665902328806962e-05, + "loss": 0.3068, "step": 30880 }, { - "epoch": 0.28, - "learning_rate": 3.654220340509864e-05, - "loss": 0.2874, + "epoch": 0.07, + "learning_rate": 4.66579047448603e-05, + "loss": 0.3054, "step": 30890 }, { - "epoch": 0.28, - "learning_rate": 3.65376993063688e-05, - "loss": 0.2957, + "epoch": 0.07, + "learning_rate": 4.665678620165097e-05, + "loss": 0.3049, "step": 30900 }, { - "epoch": 0.28, - "learning_rate": 3.653319520763896e-05, - "loss": 0.293, + "epoch": 0.07, + "learning_rate": 4.665566765844165e-05, + "loss": 0.3002, "step": 30910 }, { - "epoch": 0.28, - "learning_rate": 3.652869110890911e-05, - "loss": 0.291, + "epoch": 0.07, + "learning_rate": 4.665454911523232e-05, + "loss": 0.3065, "step": 30920 }, { - "epoch": 0.28, - "learning_rate": 3.6524187010179265e-05, - "loss": 0.2901, + "epoch": 0.07, + "learning_rate": 4.6653430572023e-05, + "loss": 0.3047, "step": 30930 }, { - "epoch": 0.28, - "learning_rate": 3.651968291144942e-05, - "loss": 0.2944, + "epoch": 0.07, + "learning_rate": 4.6652312028813676e-05, + "loss": 0.3063, "step": 30940 }, { - "epoch": 0.28, - "learning_rate": 3.6515178812719574e-05, - "loss": 0.2892, + "epoch": 0.07, + "learning_rate": 4.665119348560435e-05, + "loss": 0.3013, "step": 30950 }, { - "epoch": 0.28, - "learning_rate": 3.651067471398973e-05, - "loss": 0.2932, + "epoch": 0.07, + "learning_rate": 4.6650074942395025e-05, + "loss": 0.3078, "step": 30960 }, { - "epoch": 0.28, - "learning_rate": 3.650617061525989e-05, - "loss": 0.2929, + "epoch": 0.07, + "learning_rate": 4.66489563991857e-05, + "loss": 0.3058, "step": 30970 }, { - "epoch": 0.28, - "learning_rate": 3.650166651653004e-05, - "loss": 0.295, + "epoch": 0.07, + "learning_rate": 4.664783785597638e-05, + "loss": 0.3138, "step": 30980 }, { - "epoch": 0.28, - "learning_rate": 3.6497162417800204e-05, - "loss": 0.2918, + "epoch": 0.07, + "learning_rate": 4.664671931276706e-05, + "loss": 0.2993, "step": 30990 }, { - "epoch": 0.28, - "learning_rate": 3.6492658319070354e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.664560076955773e-05, + "loss": 0.298, "step": 31000 }, { - "epoch": 0.28, - "learning_rate": 3.648815422034051e-05, - "loss": 0.3002, + "epoch": 0.07, + "learning_rate": 4.664448222634841e-05, + "loss": 0.3016, "step": 31010 }, { - "epoch": 0.28, - "learning_rate": 3.648365012161067e-05, - "loss": 0.2921, + "epoch": 0.07, + "learning_rate": 4.664336368313908e-05, + "loss": 0.2976, "step": 31020 }, { - "epoch": 0.28, - "learning_rate": 3.647914602288082e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.664224513992976e-05, + "loss": 0.3046, "step": 31030 }, { - "epoch": 0.28, - "learning_rate": 3.6474641924150984e-05, - "loss": 0.2926, + "epoch": 0.07, + "learning_rate": 4.6641126596720435e-05, + "loss": 0.305, "step": 31040 }, { - "epoch": 0.28, - "learning_rate": 3.6470137825421135e-05, - "loss": 0.2951, + "epoch": 0.07, + "learning_rate": 4.6640008053511106e-05, + "loss": 0.3039, "step": 31050 }, { - "epoch": 0.28, - "learning_rate": 3.646563372669129e-05, - "loss": 0.2945, + "epoch": 0.07, + "learning_rate": 4.6638889510301784e-05, + "loss": 0.3059, "step": 31060 }, { - "epoch": 0.28, - "learning_rate": 3.646112962796145e-05, - "loss": 0.29, + "epoch": 0.07, + "learning_rate": 4.663777096709246e-05, + "loss": 0.301, "step": 31070 }, { - "epoch": 0.28, - "learning_rate": 3.64566255292316e-05, - "loss": 0.2904, + "epoch": 0.07, + "learning_rate": 4.663665242388314e-05, + "loss": 0.3062, "step": 31080 }, { - "epoch": 0.28, - "learning_rate": 3.645212143050176e-05, - "loss": 0.2939, + "epoch": 0.07, + "learning_rate": 4.663553388067382e-05, + "loss": 0.3017, "step": 31090 }, { - "epoch": 0.28, - "learning_rate": 3.6447617331771916e-05, - "loss": 0.2898, + "epoch": 0.07, + "learning_rate": 4.663441533746449e-05, + "loss": 0.3073, "step": 31100 }, { - "epoch": 0.28, - "learning_rate": 3.644311323304207e-05, - "loss": 0.2861, + "epoch": 0.07, + "learning_rate": 4.6633296794255167e-05, + "loss": 0.3004, "step": 31110 }, { - "epoch": 0.28, - "learning_rate": 3.6438609134312224e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.663217825104584e-05, + "loss": 0.2987, "step": 31120 }, { - "epoch": 0.28, - "learning_rate": 3.643410503558238e-05, - "loss": 0.2976, + "epoch": 0.07, + "learning_rate": 4.6631059707836516e-05, + "loss": 0.3062, "step": 31130 }, { - "epoch": 0.28, - "learning_rate": 3.642960093685254e-05, - "loss": 0.2924, + "epoch": 0.07, + "learning_rate": 4.6629941164627194e-05, + "loss": 0.3017, "step": 31140 }, { - "epoch": 0.28, - "learning_rate": 3.642509683812269e-05, - "loss": 0.2887, + "epoch": 0.07, + "learning_rate": 4.6628822621417865e-05, + "loss": 0.2968, "step": 31150 }, { - "epoch": 0.28, - "learning_rate": 3.642059273939285e-05, - "loss": 0.2937, + "epoch": 0.07, + "learning_rate": 4.662770407820854e-05, + "loss": 0.2987, "step": 31160 }, { - "epoch": 0.28, - "learning_rate": 3.6416088640663005e-05, - "loss": 0.2904, + "epoch": 0.07, + "learning_rate": 4.662658553499922e-05, + "loss": 0.2972, "step": 31170 }, { - "epoch": 0.28, - "learning_rate": 3.641158454193316e-05, - "loss": 0.2886, + "epoch": 0.07, + "learning_rate": 4.66254669917899e-05, + "loss": 0.305, "step": 31180 }, { - "epoch": 0.28, - "learning_rate": 3.640708044320332e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.662434844858057e-05, + "loss": 0.301, "step": 31190 }, { - "epoch": 0.28, - "learning_rate": 3.640257634447347e-05, - "loss": 0.2857, + "epoch": 0.07, + "learning_rate": 4.662322990537125e-05, + "loss": 0.3005, "step": 31200 }, { - "epoch": 0.28, - "learning_rate": 3.639807224574363e-05, - "loss": 0.2909, + "epoch": 0.07, + "learning_rate": 4.6622111362161925e-05, + "loss": 0.3076, "step": 31210 }, { - "epoch": 0.28, - "learning_rate": 3.6393568147013785e-05, - "loss": 0.2946, + "epoch": 0.07, + "learning_rate": 4.66209928189526e-05, + "loss": 0.2984, "step": 31220 }, { - "epoch": 0.28, - "learning_rate": 3.6389064048283936e-05, - "loss": 0.2931, + "epoch": 0.07, + "learning_rate": 4.6619874275743275e-05, + "loss": 0.3018, "step": 31230 }, { - "epoch": 0.28, - "learning_rate": 3.63845599495541e-05, - "loss": 0.292, + "epoch": 0.07, + "learning_rate": 4.6618755732533946e-05, + "loss": 0.3012, "step": 31240 }, { - "epoch": 0.28, - "learning_rate": 3.638005585082425e-05, - "loss": 0.2962, + "epoch": 0.07, + "learning_rate": 4.6617637189324624e-05, + "loss": 0.3028, "step": 31250 }, { - "epoch": 0.28, - "learning_rate": 3.637555175209441e-05, - "loss": 0.2841, + "epoch": 0.07, + "learning_rate": 4.66165186461153e-05, + "loss": 0.302, "step": 31260 }, { - "epoch": 0.28, - "learning_rate": 3.6371047653364566e-05, - "loss": 0.288, - "step": 31270 + "epoch": 0.07, + "learning_rate": 4.661540010290598e-05, + "loss": 0.3013, + "step": 31270 }, { - "epoch": 0.28, - "learning_rate": 3.6366543554634717e-05, - "loss": 0.2933, + "epoch": 0.07, + "learning_rate": 4.661428155969666e-05, + "loss": 0.2956, "step": 31280 }, { - "epoch": 0.28, - "learning_rate": 3.6362039455904874e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.661316301648733e-05, + "loss": 0.3034, "step": 31290 }, { - "epoch": 0.28, - "learning_rate": 3.635753535717503e-05, - "loss": 0.2961, + "epoch": 0.07, + "learning_rate": 4.6612044473278007e-05, + "loss": 0.2996, "step": 31300 }, { - "epoch": 0.28, - "learning_rate": 3.635303125844519e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.6610925930068684e-05, + "loss": 0.305, "step": 31310 }, { - "epoch": 0.28, - "learning_rate": 3.6348527159715347e-05, - "loss": 0.2873, + "epoch": 0.07, + "learning_rate": 4.6609807386859356e-05, + "loss": 0.3024, "step": 31320 }, { - "epoch": 0.28, - "learning_rate": 3.63440230609855e-05, - "loss": 0.2844, + "epoch": 0.07, + "learning_rate": 4.6608688843650034e-05, + "loss": 0.3032, "step": 31330 }, { - "epoch": 0.28, - "learning_rate": 3.6339518962255655e-05, - "loss": 0.2921, + "epoch": 0.07, + "learning_rate": 4.6607570300440705e-05, + "loss": 0.3021, "step": 31340 }, { - "epoch": 0.28, - "learning_rate": 3.633501486352581e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.660645175723138e-05, + "loss": 0.3003, "step": 31350 }, { - "epoch": 0.28, - "learning_rate": 3.633051076479597e-05, - "loss": 0.2854, + "epoch": 0.07, + "learning_rate": 4.660533321402206e-05, + "loss": 0.3036, "step": 31360 }, { - "epoch": 0.28, - "learning_rate": 3.632600666606612e-05, - "loss": 0.2901, + "epoch": 0.07, + "learning_rate": 4.660421467081273e-05, + "loss": 0.3066, "step": 31370 }, { - "epoch": 0.28, - "learning_rate": 3.632150256733628e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.660309612760341e-05, + "loss": 0.3049, "step": 31380 }, { - "epoch": 0.28, - "learning_rate": 3.6316998468606435e-05, - "loss": 0.2957, + "epoch": 0.07, + "learning_rate": 4.660197758439409e-05, + "loss": 0.3021, "step": 31390 }, { - "epoch": 0.28, - "learning_rate": 3.6312494369876586e-05, - "loss": 0.2887, + "epoch": 0.07, + "learning_rate": 4.6600859041184765e-05, + "loss": 0.3041, "step": 31400 }, { - "epoch": 0.28, - "learning_rate": 3.6307990271146744e-05, - "loss": 0.2966, + "epoch": 0.07, + "learning_rate": 4.6599740497975443e-05, + "loss": 0.2989, "step": 31410 }, { - "epoch": 0.28, - "learning_rate": 3.63034861724169e-05, - "loss": 0.2929, + "epoch": 0.07, + "learning_rate": 4.6598621954766115e-05, + "loss": 0.305, "step": 31420 }, { - "epoch": 0.28, - "learning_rate": 3.629898207368705e-05, - "loss": 0.2962, + "epoch": 0.07, + "learning_rate": 4.659750341155679e-05, + "loss": 0.3033, "step": 31430 }, { - "epoch": 0.28, - "learning_rate": 3.6294477974957216e-05, - "loss": 0.2917, + "epoch": 0.07, + "learning_rate": 4.6596384868347464e-05, + "loss": 0.2948, "step": 31440 }, { - "epoch": 0.28, - "learning_rate": 3.628997387622737e-05, - "loss": 0.297, + "epoch": 0.07, + "learning_rate": 4.659526632513814e-05, + "loss": 0.3052, "step": 31450 }, { - "epoch": 0.28, - "learning_rate": 3.6285469777497524e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.659414778192882e-05, + "loss": 0.3068, "step": 31460 }, { - "epoch": 0.28, - "learning_rate": 3.628096567876768e-05, - "loss": 0.2918, + "epoch": 0.07, + "learning_rate": 4.659302923871949e-05, + "loss": 0.3062, "step": 31470 }, { - "epoch": 0.28, - "learning_rate": 3.627646158003783e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.659191069551017e-05, + "loss": 0.3027, "step": 31480 }, { - "epoch": 0.28, - "learning_rate": 3.6271957481308e-05, - "loss": 0.2916, + "epoch": 0.07, + "learning_rate": 4.6590792152300846e-05, + "loss": 0.3058, "step": 31490 }, { - "epoch": 0.28, - "learning_rate": 3.626745338257815e-05, - "loss": 0.2889, + "epoch": 0.07, + "learning_rate": 4.6589673609091524e-05, + "loss": 0.3005, "step": 31500 }, { - "epoch": 0.28, - "learning_rate": 3.6262949283848305e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.6588555065882196e-05, + "loss": 0.3055, "step": 31510 }, { - "epoch": 0.28, - "learning_rate": 3.625844518511846e-05, - "loss": 0.2914, + "epoch": 0.07, + "learning_rate": 4.6587436522672873e-05, + "loss": 0.2987, "step": 31520 }, { - "epoch": 0.28, - "learning_rate": 3.625394108638861e-05, - "loss": 0.2859, + "epoch": 0.07, + "learning_rate": 4.658631797946355e-05, + "loss": 0.2984, "step": 31530 }, { - "epoch": 0.28, - "learning_rate": 3.624943698765877e-05, - "loss": 0.2899, + "epoch": 0.07, + "learning_rate": 4.658519943625422e-05, + "loss": 0.2976, "step": 31540 }, { - "epoch": 0.28, - "learning_rate": 3.624493288892893e-05, - "loss": 0.2966, + "epoch": 0.07, + "learning_rate": 4.65840808930449e-05, + "loss": 0.3041, "step": 31550 }, { - "epoch": 0.28, - "learning_rate": 3.6240428790199086e-05, - "loss": 0.2929, + "epoch": 0.07, + "learning_rate": 4.658296234983557e-05, + "loss": 0.3069, "step": 31560 }, { - "epoch": 0.28, - "learning_rate": 3.6235924691469236e-05, - "loss": 0.2945, + "epoch": 0.07, + "learning_rate": 4.658184380662625e-05, + "loss": 0.3, "step": 31570 }, { - "epoch": 0.28, - "learning_rate": 3.6231420592739394e-05, - "loss": 0.2948, + "epoch": 0.07, + "learning_rate": 4.658072526341693e-05, + "loss": 0.2983, "step": 31580 }, { - "epoch": 0.28, - "learning_rate": 3.622691649400955e-05, - "loss": 0.2896, + "epoch": 0.07, + "learning_rate": 4.6579606720207605e-05, + "loss": 0.3096, "step": 31590 }, { - "epoch": 0.28, - "learning_rate": 3.622241239527971e-05, - "loss": 0.2864, + "epoch": 0.07, + "learning_rate": 4.657848817699828e-05, + "loss": 0.3031, "step": 31600 }, { - "epoch": 0.28, - "learning_rate": 3.621790829654986e-05, - "loss": 0.2946, + "epoch": 0.07, + "learning_rate": 4.6577369633788955e-05, + "loss": 0.3034, "step": 31610 }, { - "epoch": 0.28, - "learning_rate": 3.621340419782002e-05, - "loss": 0.2874, + "epoch": 0.07, + "learning_rate": 4.657625109057963e-05, + "loss": 0.3052, "step": 31620 }, { - "epoch": 0.28, - "learning_rate": 3.6208900099090175e-05, - "loss": 0.2925, + "epoch": 0.07, + "learning_rate": 4.657513254737031e-05, + "loss": 0.3049, "step": 31630 }, { - "epoch": 0.28, - "learning_rate": 3.620439600036033e-05, - "loss": 0.2897, + "epoch": 0.07, + "learning_rate": 4.657401400416098e-05, + "loss": 0.2982, "step": 31640 }, { - "epoch": 0.28, - "learning_rate": 3.619989190163048e-05, - "loss": 0.2892, + "epoch": 0.07, + "learning_rate": 4.657289546095166e-05, + "loss": 0.2992, "step": 31650 }, { - "epoch": 0.28, - "learning_rate": 3.619538780290064e-05, - "loss": 0.2853, + "epoch": 0.07, + "learning_rate": 4.657177691774233e-05, + "loss": 0.3043, "step": 31660 }, { - "epoch": 0.28, - "learning_rate": 3.61908837041708e-05, - "loss": 0.2839, + "epoch": 0.07, + "learning_rate": 4.657065837453301e-05, + "loss": 0.3013, "step": 31670 }, { - "epoch": 0.28, - "learning_rate": 3.618637960544095e-05, - "loss": 0.2929, + "epoch": 0.07, + "learning_rate": 4.6569539831323686e-05, + "loss": 0.3026, "step": 31680 }, { - "epoch": 0.28, - "learning_rate": 3.618187550671111e-05, - "loss": 0.2882, + "epoch": 0.07, + "learning_rate": 4.6568421288114364e-05, + "loss": 0.3034, "step": 31690 }, { - "epoch": 0.28, - "learning_rate": 3.6177371407981264e-05, - "loss": 0.2884, + "epoch": 0.07, + "learning_rate": 4.656730274490504e-05, + "loss": 0.2986, "step": 31700 }, { - "epoch": 0.28, - "learning_rate": 3.617286730925142e-05, - "loss": 0.2843, + "epoch": 0.07, + "learning_rate": 4.6566184201695713e-05, + "loss": 0.3013, "step": 31710 }, { - "epoch": 0.28, - "learning_rate": 3.616836321052158e-05, - "loss": 0.2918, + "epoch": 0.07, + "learning_rate": 4.656506565848639e-05, + "loss": 0.3073, "step": 31720 }, { - "epoch": 0.28, - "learning_rate": 3.616385911179173e-05, - "loss": 0.2898, + "epoch": 0.07, + "learning_rate": 4.656394711527707e-05, + "loss": 0.2984, "step": 31730 }, { - "epoch": 0.28, - "learning_rate": 3.6159355013061893e-05, - "loss": 0.2911, + "epoch": 0.07, + "learning_rate": 4.656282857206774e-05, + "loss": 0.2957, "step": 31740 }, { - "epoch": 0.28, - "learning_rate": 3.6154850914332044e-05, - "loss": 0.2954, + "epoch": 0.07, + "learning_rate": 4.656171002885842e-05, + "loss": 0.3006, "step": 31750 }, { - "epoch": 0.28, - "learning_rate": 3.61503468156022e-05, - "loss": 0.2897, + "epoch": 0.07, + "learning_rate": 4.656059148564909e-05, + "loss": 0.3035, "step": 31760 }, { - "epoch": 0.28, - "learning_rate": 3.614584271687236e-05, - "loss": 0.2873, + "epoch": 0.07, + "learning_rate": 4.655947294243977e-05, + "loss": 0.3043, "step": 31770 }, { - "epoch": 0.28, - "learning_rate": 3.614133861814251e-05, - "loss": 0.2896, + "epoch": 0.07, + "learning_rate": 4.6558354399230445e-05, + "loss": 0.2976, "step": 31780 }, { - "epoch": 0.28, - "learning_rate": 3.613683451941267e-05, - "loss": 0.295, + "epoch": 0.07, + "learning_rate": 4.6557235856021117e-05, + "loss": 0.2987, "step": 31790 }, { - "epoch": 0.28, - "learning_rate": 3.6132330420682825e-05, - "loss": 0.2931, + "epoch": 0.07, + "learning_rate": 4.6556117312811794e-05, + "loss": 0.307, "step": 31800 }, { - "epoch": 0.28, - "learning_rate": 3.6127826321952976e-05, - "loss": 0.287, + "epoch": 0.07, + "learning_rate": 4.655499876960247e-05, + "loss": 0.3007, "step": 31810 }, { - "epoch": 0.28, - "learning_rate": 3.612332222322313e-05, - "loss": 0.2945, + "epoch": 0.07, + "learning_rate": 4.655388022639315e-05, + "loss": 0.301, "step": 31820 }, { - "epoch": 0.28, - "learning_rate": 3.611881812449329e-05, - "loss": 0.2906, + "epoch": 0.07, + "learning_rate": 4.655276168318382e-05, + "loss": 0.3025, "step": 31830 }, { - "epoch": 0.28, - "learning_rate": 3.611431402576345e-05, - "loss": 0.2914, + "epoch": 0.07, + "learning_rate": 4.65516431399745e-05, + "loss": 0.3039, "step": 31840 }, { - "epoch": 0.28, - "learning_rate": 3.61098099270336e-05, - "loss": 0.292, + "epoch": 0.07, + "learning_rate": 4.655052459676518e-05, + "loss": 0.3035, "step": 31850 }, { - "epoch": 0.28, - "learning_rate": 3.6105305828303756e-05, - "loss": 0.2822, + "epoch": 0.07, + "learning_rate": 4.654940605355585e-05, + "loss": 0.297, "step": 31860 }, { - "epoch": 0.28, - "learning_rate": 3.6100801729573914e-05, - "loss": 0.2907, + "epoch": 0.07, + "learning_rate": 4.6548287510346526e-05, + "loss": 0.3027, "step": 31870 }, { - "epoch": 0.28, - "learning_rate": 3.609629763084407e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.65471689671372e-05, + "loss": 0.3045, "step": 31880 }, { - "epoch": 0.28, - "learning_rate": 3.609179353211423e-05, - "loss": 0.2847, + "epoch": 0.07, + "learning_rate": 4.6546050423927875e-05, + "loss": 0.3002, "step": 31890 }, { - "epoch": 0.28, - "learning_rate": 3.608728943338438e-05, - "loss": 0.294, + "epoch": 0.07, + "learning_rate": 4.6544931880718553e-05, + "loss": 0.3072, "step": 31900 }, { - "epoch": 0.28, - "learning_rate": 3.608278533465454e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.654381333750923e-05, + "loss": 0.2971, "step": 31910 }, { - "epoch": 0.28, - "learning_rate": 3.6078281235924694e-05, - "loss": 0.2894, + "epoch": 0.07, + "learning_rate": 4.654269479429991e-05, + "loss": 0.3025, "step": 31920 }, { - "epoch": 0.29, - "learning_rate": 3.6073777137194845e-05, - "loss": 0.292, + "epoch": 0.07, + "learning_rate": 4.654157625109058e-05, + "loss": 0.3008, "step": 31930 }, { - "epoch": 0.29, - "learning_rate": 3.606927303846501e-05, - "loss": 0.2872, + "epoch": 0.07, + "learning_rate": 4.654045770788126e-05, + "loss": 0.2988, "step": 31940 }, { - "epoch": 0.29, - "learning_rate": 3.606476893973516e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.6539339164671936e-05, + "loss": 0.3028, "step": 31950 }, { - "epoch": 0.29, - "learning_rate": 3.606026484100532e-05, - "loss": 0.2866, + "epoch": 0.07, + "learning_rate": 4.653822062146261e-05, + "loss": 0.3006, "step": 31960 }, { - "epoch": 0.29, - "learning_rate": 3.6055760742275475e-05, - "loss": 0.2839, + "epoch": 0.07, + "learning_rate": 4.6537102078253285e-05, + "loss": 0.3027, "step": 31970 }, { - "epoch": 0.29, - "learning_rate": 3.6051256643545626e-05, - "loss": 0.2876, + "epoch": 0.07, + "learning_rate": 4.6535983535043957e-05, + "loss": 0.3048, "step": 31980 }, { - "epoch": 0.29, - "learning_rate": 3.604675254481578e-05, - "loss": 0.3028, + "epoch": 0.07, + "learning_rate": 4.6534864991834634e-05, + "loss": 0.3061, "step": 31990 }, { - "epoch": 0.29, - "learning_rate": 3.604224844608594e-05, - "loss": 0.2826, + "epoch": 0.07, + "learning_rate": 4.653374644862531e-05, + "loss": 0.3057, "step": 32000 }, { - "epoch": 0.29, - "eval_NEIMS_canon_smiles": 0.9411666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.012166666666666666, - "eval_NEIMS_daylight_tanimoto_simil": 0.38288233226711305, - "eval_NEIMS_exact_mols": 0.012083333333333333, - "eval_NEIMS_exact_smiles": 0.011716666666666667, - "eval_NEIMS_loss": 0.3008743226528168, - "eval_NEIMS_matched_formulas": 0.40558333333333335, - "eval_NEIMS_morgan_tanimoto_simil": 0.2822131343249727, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0122, - "eval_NEIMS_runtime": 704.6298, - "eval_NEIMS_samples_per_second": 85.151, - "eval_NEIMS_steps_per_second": 1.331, + "epoch": 0.07, + "eval_NEIMS_canon_smiles": 0.9321, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.0123, + "eval_NEIMS_daylight_tanimoto_simil": 0.38021381717417124, + "eval_NEIMS_exact_mols": 0.012166666666666666, + "eval_NEIMS_exact_smiles": 0.011683333333333334, + "eval_NEIMS_loss": 0.30227604508399963, + "eval_NEIMS_matched_formulas": 0.3999, + "eval_NEIMS_morgan_tanimoto_simil": 0.2785114888105248, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0123, + "eval_NEIMS_runtime": 728.0544, + "eval_NEIMS_samples_per_second": 82.411, + "eval_NEIMS_steps_per_second": 1.288, "step": 32000 }, { - "epoch": 0.29, - "eval_RASSP_canon_smiles": 0.9329315123384646, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.030520586369252346, - "eval_RASSP_daylight_tanimoto_simil": 0.4583983323036867, - "eval_RASSP_exact_mols": 0.030286840084148663, - "eval_RASSP_exact_smiles": 0.029318462617290545, - "eval_RASSP_loss": 0.2483576387166977, - "eval_RASSP_matched_formulas": 0.5404881958126022, - "eval_RASSP_morgan_tanimoto_simil": 0.3222687479375559, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.03033692857381374, - "eval_RASSP_runtime": 812.2405, - "eval_RASSP_samples_per_second": 73.739, - "eval_RASSP_steps_per_second": 1.152, + "epoch": 0.07, + "eval_RASSP_canon_smiles": 0.9311116305473003, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.01726383277122917, + "eval_RASSP_daylight_tanimoto_simil": 0.42488652840088303, + "eval_RASSP_exact_mols": 0.017113567302233946, + "eval_RASSP_exact_smiles": 0.016512505426253047, + "eval_RASSP_loss": 0.27535945177078247, + "eval_RASSP_matched_formulas": 0.511804187397736, + "eval_RASSP_morgan_tanimoto_simil": 0.28880685014759616, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.01714695962867733, + "eval_RASSP_runtime": 824.4744, + "eval_RASSP_samples_per_second": 72.645, + "eval_RASSP_steps_per_second": 1.135, "step": 32000 }, { - "epoch": 0.29, - "eval_NIST_canon_smiles": 0.9088618376690208, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.0056783901763849945, - "eval_NIST_daylight_tanimoto_simil": 0.24459893187079448, - "eval_NIST_exact_mols": 0.005217020974553714, - "eval_NIST_exact_smiles": 0.0050040813429392764, - "eval_NIST_loss": 1.4709786176681519, - "eval_NIST_matched_formulas": 0.05358980728963339, - "eval_NIST_morgan_tanimoto_simil": 0.20517589302071992, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.005642900237782589, - "eval_NIST_runtime": 444.8617, - "eval_NIST_samples_per_second": 63.339, - "eval_NIST_steps_per_second": 0.991, + "epoch": 0.07, + "eval_NEIMS_old_canon_smiles": 0.9337333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.011266666666666666, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.3778744952774363, + "eval_NEIMS_old_exact_mols": 0.011266666666666666, + "eval_NEIMS_old_exact_smiles": 0.010833333333333334, + "eval_NEIMS_old_loss": 0.3033360540866852, + "eval_NEIMS_old_matched_formulas": 0.3965666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.27767864377322915, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.011366666666666667, + "eval_NEIMS_old_runtime": 364.0863, + "eval_NEIMS_old_samples_per_second": 82.398, + "eval_NEIMS_old_steps_per_second": 1.288, "step": 32000 }, { - "epoch": 0.29, - "learning_rate": 3.603774434735609e-05, - "loss": 0.2906, + "epoch": 0.07, + "eval_RASSP_old_canon_smiles": 0.9309240164180599, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.019955284145893818, + "eval_RASSP_old_daylight_tanimoto_simil": 0.43178247412888165, + "eval_RASSP_old_exact_mols": 0.019788433944005073, + "eval_RASSP_old_exact_smiles": 0.019054293055694598, + "eval_RASSP_old_loss": 0.266217976808548, + "eval_RASSP_old_matched_formulas": 0.5274468582106985, + "eval_RASSP_old_morgan_tanimoto_simil": 0.29609832777421075, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.01988854406513832, + "eval_RASSP_old_runtime": 412.7968, + "eval_RASSP_old_samples_per_second": 72.595, + "eval_RASSP_old_steps_per_second": 1.136, + "step": 32000 + }, + { + "epoch": 0.07, + "eval_NIST_canon_smiles": 0.8701068247151933, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.004365262448095965, + "eval_NIST_daylight_tanimoto_simil": 0.23400403690573507, + "eval_NIST_exact_mols": 0.004081342939276715, + "eval_NIST_exact_smiles": 0.00393938318486709, + "eval_NIST_loss": 1.8355991840362549, + "eval_NIST_matched_formulas": 0.048159846683465235, + "eval_NIST_morgan_tanimoto_simil": 0.19075523728731553, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.00422330269368634, + "eval_NIST_runtime": 439.4633, + "eval_NIST_samples_per_second": 64.117, + "eval_NIST_steps_per_second": 1.003, + "step": 32000 + }, + { + "epoch": 0.07, + "learning_rate": 4.653262790541599e-05, + "loss": 0.3007, "step": 32010 }, { - "epoch": 0.29, - "learning_rate": 3.6033240248626256e-05, - "loss": 0.2851, + "epoch": 0.07, + "learning_rate": 4.653150936220667e-05, + "loss": 0.2946, "step": 32020 }, { - "epoch": 0.29, - "learning_rate": 3.6028736149896407e-05, - "loss": 0.2971, + "epoch": 0.07, + "learning_rate": 4.653039081899734e-05, + "loss": 0.3078, "step": 32030 }, { - "epoch": 0.29, - "learning_rate": 3.6024232051166564e-05, - "loss": 0.2919, + "epoch": 0.07, + "learning_rate": 4.652927227578802e-05, + "loss": 0.3055, "step": 32040 }, { - "epoch": 0.29, - "learning_rate": 3.601972795243672e-05, - "loss": 0.2938, + "epoch": 0.07, + "learning_rate": 4.6528153732578695e-05, + "loss": 0.3035, "step": 32050 }, { - "epoch": 0.29, - "learning_rate": 3.601522385370687e-05, - "loss": 0.2904, + "epoch": 0.07, + "learning_rate": 4.6527035189369366e-05, + "loss": 0.2999, "step": 32060 }, { - "epoch": 0.29, - "learning_rate": 3.601071975497703e-05, - "loss": 0.2867, + "epoch": 0.07, + "learning_rate": 4.6525916646160044e-05, + "loss": 0.2975, "step": 32070 }, { - "epoch": 0.29, - "learning_rate": 3.600621565624719e-05, - "loss": 0.2932, + "epoch": 0.07, + "learning_rate": 4.6524798102950715e-05, + "loss": 0.3021, "step": 32080 }, { - "epoch": 0.29, - "learning_rate": 3.6001711557517345e-05, - "loss": 0.2901, + "epoch": 0.07, + "learning_rate": 4.6523679559741393e-05, + "loss": 0.3019, "step": 32090 }, { - "epoch": 0.29, - "learning_rate": 3.5997207458787495e-05, - "loss": 0.2906, + "epoch": 0.07, + "learning_rate": 4.652256101653207e-05, + "loss": 0.2988, "step": 32100 }, { - "epoch": 0.29, - "learning_rate": 3.599270336005765e-05, - "loss": 0.2919, + "epoch": 0.07, + "learning_rate": 4.652144247332275e-05, + "loss": 0.3014, "step": 32110 }, { - "epoch": 0.29, - "learning_rate": 3.598819926132781e-05, - "loss": 0.2897, + "epoch": 0.07, + "learning_rate": 4.652032393011343e-05, + "loss": 0.2942, "step": 32120 }, { - "epoch": 0.29, - "learning_rate": 3.598369516259796e-05, - "loss": 0.2912, + "epoch": 0.07, + "learning_rate": 4.65192053869041e-05, + "loss": 0.3037, "step": 32130 }, { - "epoch": 0.29, - "learning_rate": 3.5979191063868125e-05, - "loss": 0.286, + "epoch": 0.07, + "learning_rate": 4.6518086843694776e-05, + "loss": 0.3013, "step": 32140 }, { - "epoch": 0.29, - "learning_rate": 3.5974686965138276e-05, - "loss": 0.2879, + "epoch": 0.07, + "learning_rate": 4.651696830048545e-05, + "loss": 0.2964, "step": 32150 }, { - "epoch": 0.29, - "learning_rate": 3.5970182866408434e-05, - "loss": 0.2889, + "epoch": 0.07, + "learning_rate": 4.6515849757276125e-05, + "loss": 0.3059, "step": 32160 }, { - "epoch": 0.29, - "learning_rate": 3.596567876767859e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.65147312140668e-05, + "loss": 0.3021, "step": 32170 }, { - "epoch": 0.29, - "learning_rate": 3.596117466894874e-05, - "loss": 0.2906, + "epoch": 0.07, + "learning_rate": 4.6513612670857474e-05, + "loss": 0.2998, "step": 32180 }, { - "epoch": 0.29, - "learning_rate": 3.5956670570218906e-05, - "loss": 0.2903, + "epoch": 0.07, + "learning_rate": 4.651249412764815e-05, + "loss": 0.3006, "step": 32190 }, { - "epoch": 0.29, - "learning_rate": 3.595216647148906e-05, - "loss": 0.291, + "epoch": 0.07, + "learning_rate": 4.6511375584438823e-05, + "loss": 0.3025, "step": 32200 }, { - "epoch": 0.29, - "learning_rate": 3.5947662372759214e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.65102570412295e-05, + "loss": 0.2967, "step": 32210 }, { - "epoch": 0.29, - "learning_rate": 3.594315827402937e-05, - "loss": 0.2858, + "epoch": 0.07, + "learning_rate": 4.6509138498020186e-05, + "loss": 0.3027, "step": 32220 }, { - "epoch": 0.29, - "learning_rate": 3.593865417529952e-05, - "loss": 0.2933, + "epoch": 0.07, + "learning_rate": 4.650801995481086e-05, + "loss": 0.3018, "step": 32230 }, { - "epoch": 0.29, - "learning_rate": 3.593415007656968e-05, - "loss": 0.2993, + "epoch": 0.07, + "learning_rate": 4.6506901411601535e-05, + "loss": 0.3016, "step": 32240 }, { - "epoch": 0.29, - "learning_rate": 3.592964597783984e-05, - "loss": 0.2897, + "epoch": 0.07, + "learning_rate": 4.6505782868392206e-05, + "loss": 0.2962, "step": 32250 }, { - "epoch": 0.29, - "learning_rate": 3.592514187910999e-05, - "loss": 0.2859, + "epoch": 0.07, + "learning_rate": 4.6504664325182884e-05, + "loss": 0.3026, "step": 32260 }, { - "epoch": 0.29, - "learning_rate": 3.5920637780380146e-05, - "loss": 0.2867, + "epoch": 0.07, + "learning_rate": 4.650354578197356e-05, + "loss": 0.2987, "step": 32270 }, { - "epoch": 0.29, - "learning_rate": 3.59161336816503e-05, - "loss": 0.286, + "epoch": 0.07, + "learning_rate": 4.650242723876423e-05, + "loss": 0.3026, "step": 32280 }, { - "epoch": 0.29, - "learning_rate": 3.591162958292046e-05, - "loss": 0.2904, + "epoch": 0.07, + "learning_rate": 4.650130869555491e-05, + "loss": 0.3025, "step": 32290 }, { - "epoch": 0.29, - "learning_rate": 3.590712548419062e-05, - "loss": 0.2969, + "epoch": 0.07, + "learning_rate": 4.650019015234558e-05, + "loss": 0.302, "step": 32300 }, { - "epoch": 0.29, - "learning_rate": 3.590262138546077e-05, - "loss": 0.2862, + "epoch": 0.07, + "learning_rate": 4.649907160913626e-05, + "loss": 0.3019, "step": 32310 }, { - "epoch": 0.29, - "learning_rate": 3.5898117286730926e-05, - "loss": 0.2867, + "epoch": 0.07, + "learning_rate": 4.649795306592694e-05, + "loss": 0.3023, "step": 32320 }, { - "epoch": 0.29, - "learning_rate": 3.5893613188001084e-05, - "loss": 0.287, + "epoch": 0.07, + "learning_rate": 4.6496834522717616e-05, + "loss": 0.3044, "step": 32330 }, { - "epoch": 0.29, - "learning_rate": 3.588910908927124e-05, - "loss": 0.2889, + "epoch": 0.07, + "learning_rate": 4.6495715979508294e-05, + "loss": 0.3017, "step": 32340 }, { - "epoch": 0.29, - "learning_rate": 3.588460499054139e-05, - "loss": 0.2811, + "epoch": 0.07, + "learning_rate": 4.6494597436298965e-05, + "loss": 0.3031, "step": 32350 }, { - "epoch": 0.29, - "learning_rate": 3.588010089181155e-05, - "loss": 0.2884, + "epoch": 0.07, + "learning_rate": 4.649347889308964e-05, + "loss": 0.3037, "step": 32360 }, { - "epoch": 0.29, - "learning_rate": 3.587559679308171e-05, - "loss": 0.2812, + "epoch": 0.07, + "learning_rate": 4.649236034988032e-05, + "loss": 0.2979, "step": 32370 }, { - "epoch": 0.29, - "learning_rate": 3.587109269435186e-05, - "loss": 0.2902, + "epoch": 0.07, + "learning_rate": 4.649124180667099e-05, + "loss": 0.3007, "step": 32380 }, { - "epoch": 0.29, - "learning_rate": 3.586658859562202e-05, - "loss": 0.2843, + "epoch": 0.07, + "learning_rate": 4.649012326346167e-05, + "loss": 0.2999, "step": 32390 }, { - "epoch": 0.29, - "learning_rate": 3.586208449689217e-05, - "loss": 0.2866, + "epoch": 0.07, + "learning_rate": 4.648900472025234e-05, + "loss": 0.2944, "step": 32400 }, { - "epoch": 0.29, - "learning_rate": 3.585758039816233e-05, - "loss": 0.2995, + "epoch": 0.07, + "learning_rate": 4.648788617704302e-05, + "loss": 0.3004, "step": 32410 }, { - "epoch": 0.29, - "learning_rate": 3.585307629943249e-05, - "loss": 0.2898, + "epoch": 0.07, + "learning_rate": 4.64867676338337e-05, + "loss": 0.3079, "step": 32420 }, { - "epoch": 0.29, - "learning_rate": 3.584857220070264e-05, - "loss": 0.2919, + "epoch": 0.07, + "learning_rate": 4.6485649090624375e-05, + "loss": 0.2995, "step": 32430 }, { - "epoch": 0.29, - "learning_rate": 3.5844068101972796e-05, - "loss": 0.28, + "epoch": 0.07, + "learning_rate": 4.648453054741505e-05, + "loss": 0.2991, "step": 32440 }, { - "epoch": 0.29, - "learning_rate": 3.5839564003242953e-05, - "loss": 0.2842, + "epoch": 0.07, + "learning_rate": 4.6483412004205724e-05, + "loss": 0.2977, "step": 32450 }, { - "epoch": 0.29, - "learning_rate": 3.5835059904513104e-05, - "loss": 0.2846, + "epoch": 0.07, + "learning_rate": 4.64822934609964e-05, + "loss": 0.2996, "step": 32460 }, { - "epoch": 0.29, - "learning_rate": 3.583055580578327e-05, - "loss": 0.2839, + "epoch": 0.07, + "learning_rate": 4.648117491778707e-05, + "loss": 0.2945, "step": 32470 }, { - "epoch": 0.29, - "learning_rate": 3.582605170705342e-05, - "loss": 0.2851, + "epoch": 0.07, + "learning_rate": 4.648005637457775e-05, + "loss": 0.3008, "step": 32480 }, { - "epoch": 0.29, - "learning_rate": 3.582154760832358e-05, - "loss": 0.2871, + "epoch": 0.07, + "learning_rate": 4.647893783136843e-05, + "loss": 0.3006, "step": 32490 }, { - "epoch": 0.29, - "learning_rate": 3.5817043509593734e-05, - "loss": 0.2894, + "epoch": 0.07, + "learning_rate": 4.64778192881591e-05, + "loss": 0.2996, "step": 32500 }, { - "epoch": 0.29, - "learning_rate": 3.5812539410863885e-05, + "epoch": 0.07, + "learning_rate": 4.647670074494978e-05, "loss": 0.29, "step": 32510 }, { - "epoch": 0.29, - "learning_rate": 3.580803531213404e-05, - "loss": 0.2848, + "epoch": 0.07, + "learning_rate": 4.6475582201740456e-05, + "loss": 0.2932, "step": 32520 }, { - "epoch": 0.29, - "learning_rate": 3.58035312134042e-05, - "loss": 0.2892, + "epoch": 0.07, + "learning_rate": 4.6474463658531134e-05, + "loss": 0.2992, "step": 32530 }, { - "epoch": 0.29, - "learning_rate": 3.579902711467436e-05, - "loss": 0.2847, + "epoch": 0.07, + "learning_rate": 4.647334511532181e-05, + "loss": 0.2959, "step": 32540 }, { - "epoch": 0.29, - "learning_rate": 3.579452301594451e-05, - "loss": 0.2855, + "epoch": 0.07, + "learning_rate": 4.647222657211248e-05, + "loss": 0.2928, "step": 32550 }, { - "epoch": 0.29, - "learning_rate": 3.5790018917214666e-05, - "loss": 0.2871, + "epoch": 0.07, + "learning_rate": 4.647110802890316e-05, + "loss": 0.3025, "step": 32560 }, { - "epoch": 0.29, - "learning_rate": 3.578551481848482e-05, - "loss": 0.2843, + "epoch": 0.07, + "learning_rate": 4.646998948569383e-05, + "loss": 0.3025, "step": 32570 }, { - "epoch": 0.29, - "learning_rate": 3.5781010719754974e-05, - "loss": 0.2928, + "epoch": 0.07, + "learning_rate": 4.646887094248451e-05, + "loss": 0.3002, "step": 32580 }, { - "epoch": 0.29, - "learning_rate": 3.577650662102514e-05, - "loss": 0.2858, + "epoch": 0.07, + "learning_rate": 4.646775239927519e-05, + "loss": 0.3001, "step": 32590 }, { - "epoch": 0.29, - "learning_rate": 3.577200252229529e-05, - "loss": 0.2815, + "epoch": 0.07, + "learning_rate": 4.646663385606586e-05, + "loss": 0.298, "step": 32600 }, { - "epoch": 0.29, - "learning_rate": 3.5767498423565446e-05, - "loss": 0.2849, + "epoch": 0.07, + "learning_rate": 4.646551531285654e-05, + "loss": 0.3045, "step": 32610 }, { - "epoch": 0.29, - "learning_rate": 3.5762994324835604e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.646439676964721e-05, + "loss": 0.3007, "step": 32620 }, { - "epoch": 0.29, - "learning_rate": 3.5758490226105754e-05, - "loss": 0.297, + "epoch": 0.07, + "learning_rate": 4.6463278226437886e-05, + "loss": 0.2946, "step": 32630 }, { - "epoch": 0.29, - "learning_rate": 3.575398612737592e-05, - "loss": 0.2834, + "epoch": 0.07, + "learning_rate": 4.646215968322857e-05, + "loss": 0.2998, "step": 32640 }, { - "epoch": 0.29, - "learning_rate": 3.574948202864607e-05, - "loss": 0.2869, + "epoch": 0.07, + "learning_rate": 4.646104114001924e-05, + "loss": 0.2987, "step": 32650 }, { - "epoch": 0.29, - "learning_rate": 3.574497792991622e-05, - "loss": 0.284, + "epoch": 0.07, + "learning_rate": 4.645992259680992e-05, + "loss": 0.2986, "step": 32660 }, { - "epoch": 0.29, - "learning_rate": 3.5740473831186384e-05, - "loss": 0.2849, + "epoch": 0.07, + "learning_rate": 4.645880405360059e-05, + "loss": 0.2981, "step": 32670 }, { - "epoch": 0.29, - "learning_rate": 3.5735969732456535e-05, - "loss": 0.2882, + "epoch": 0.07, + "learning_rate": 4.645768551039127e-05, + "loss": 0.2976, "step": 32680 }, { - "epoch": 0.29, - "learning_rate": 3.573146563372669e-05, - "loss": 0.2853, + "epoch": 0.07, + "learning_rate": 4.645656696718195e-05, + "loss": 0.2975, "step": 32690 }, { - "epoch": 0.29, - "learning_rate": 3.572696153499685e-05, - "loss": 0.2881, + "epoch": 0.07, + "learning_rate": 4.645544842397262e-05, + "loss": 0.3018, "step": 32700 }, { - "epoch": 0.29, - "learning_rate": 3.5722457436267e-05, - "loss": 0.2873, + "epoch": 0.07, + "learning_rate": 4.6454329880763296e-05, + "loss": 0.2998, "step": 32710 }, { - "epoch": 0.29, - "learning_rate": 3.571795333753716e-05, - "loss": 0.2824, + "epoch": 0.07, + "learning_rate": 4.645321133755397e-05, + "loss": 0.301, "step": 32720 }, { - "epoch": 0.29, - "learning_rate": 3.5713449238807316e-05, - "loss": 0.2881, + "epoch": 0.07, + "learning_rate": 4.6452092794344645e-05, + "loss": 0.2984, "step": 32730 }, { - "epoch": 0.29, - "learning_rate": 3.570894514007747e-05, - "loss": 0.2848, + "epoch": 0.07, + "learning_rate": 4.645097425113532e-05, + "loss": 0.2916, "step": 32740 }, { - "epoch": 0.29, - "learning_rate": 3.570444104134763e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.6449855707926e-05, + "loss": 0.3008, "step": 32750 }, { - "epoch": 0.29, - "learning_rate": 3.569993694261778e-05, - "loss": 0.2955, + "epoch": 0.07, + "learning_rate": 4.644873716471668e-05, + "loss": 0.3, "step": 32760 }, { - "epoch": 0.29, - "learning_rate": 3.569543284388794e-05, - "loss": 0.2858, + "epoch": 0.07, + "learning_rate": 4.644761862150735e-05, + "loss": 0.2971, "step": 32770 }, { - "epoch": 0.29, - "learning_rate": 3.569137915503108e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.644650007829803e-05, + "loss": 0.2927, "step": 32780 }, { - "epoch": 0.29, - "learning_rate": 3.5686875056301233e-05, - "loss": 0.2857, + "epoch": 0.07, + "learning_rate": 4.64453815350887e-05, + "loss": 0.2959, "step": 32790 }, { - "epoch": 0.29, - "learning_rate": 3.568237095757139e-05, - "loss": 0.2917, + "epoch": 0.07, + "learning_rate": 4.644426299187938e-05, + "loss": 0.2947, "step": 32800 }, { - "epoch": 0.29, - "learning_rate": 3.567786685884155e-05, - "loss": 0.2838, + "epoch": 0.07, + "learning_rate": 4.644325630299099e-05, + "loss": 0.2988, "step": 32810 }, { - "epoch": 0.29, - "learning_rate": 3.5673362760111706e-05, - "loss": 0.286, + "epoch": 0.07, + "learning_rate": 4.6442137759781664e-05, + "loss": 0.3068, "step": 32820 }, { - "epoch": 0.29, - "learning_rate": 3.566885866138186e-05, - "loss": 0.2888, + "epoch": 0.07, + "learning_rate": 4.644101921657234e-05, + "loss": 0.2992, "step": 32830 }, { - "epoch": 0.29, - "learning_rate": 3.5664354562652014e-05, - "loss": 0.2912, + "epoch": 0.07, + "learning_rate": 4.643990067336301e-05, + "loss": 0.2994, "step": 32840 }, { - "epoch": 0.29, - "learning_rate": 3.565985046392217e-05, - "loss": 0.2881, + "epoch": 0.07, + "learning_rate": 4.643878213015369e-05, + "loss": 0.2961, "step": 32850 }, { - "epoch": 0.29, - "learning_rate": 3.565534636519233e-05, - "loss": 0.2865, + "epoch": 0.07, + "learning_rate": 4.643766358694436e-05, + "loss": 0.3018, "step": 32860 }, { - "epoch": 0.29, - "learning_rate": 3.565084226646248e-05, - "loss": 0.2845, + "epoch": 0.07, + "learning_rate": 4.643654504373504e-05, + "loss": 0.3002, "step": 32870 }, { - "epoch": 0.29, - "learning_rate": 3.564633816773264e-05, - "loss": 0.2764, + "epoch": 0.07, + "learning_rate": 4.643542650052572e-05, + "loss": 0.2927, "step": 32880 }, { - "epoch": 0.29, - "learning_rate": 3.5641834069002795e-05, - "loss": 0.2899, + "epoch": 0.07, + "learning_rate": 4.643430795731639e-05, + "loss": 0.299, "step": 32890 }, { - "epoch": 0.29, - "learning_rate": 3.5637329970272946e-05, - "loss": 0.285, + "epoch": 0.07, + "learning_rate": 4.643318941410707e-05, + "loss": 0.2978, "step": 32900 }, { - "epoch": 0.29, - "learning_rate": 3.563282587154311e-05, - "loss": 0.2981, + "epoch": 0.07, + "learning_rate": 4.6432070870897745e-05, + "loss": 0.2925, "step": 32910 }, { - "epoch": 0.29, - "learning_rate": 3.562832177281326e-05, - "loss": 0.2895, + "epoch": 0.07, + "learning_rate": 4.643095232768842e-05, + "loss": 0.2943, "step": 32920 }, { - "epoch": 0.29, - "learning_rate": 3.562381767408342e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.64298337844791e-05, + "loss": 0.2979, "step": 32930 }, { - "epoch": 0.29, - "learning_rate": 3.5619313575353576e-05, - "loss": 0.2888, + "epoch": 0.07, + "learning_rate": 4.642871524126977e-05, + "loss": 0.2973, "step": 32940 }, { - "epoch": 0.29, - "learning_rate": 3.5614809476623726e-05, - "loss": 0.2845, + "epoch": 0.07, + "learning_rate": 4.642759669806045e-05, + "loss": 0.2975, "step": 32950 }, { - "epoch": 0.29, - "learning_rate": 3.561030537789389e-05, - "loss": 0.2864, + "epoch": 0.07, + "learning_rate": 4.642647815485112e-05, + "loss": 0.2951, "step": 32960 }, { - "epoch": 0.29, - "learning_rate": 3.560580127916404e-05, - "loss": 0.2822, + "epoch": 0.07, + "learning_rate": 4.64253596116418e-05, + "loss": 0.2953, "step": 32970 }, { - "epoch": 0.29, - "learning_rate": 3.56012971804342e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.642424106843248e-05, + "loss": 0.2947, "step": 32980 }, { - "epoch": 0.29, - "learning_rate": 3.5596793081704356e-05, - "loss": 0.2885, + "epoch": 0.07, + "learning_rate": 4.642312252522315e-05, + "loss": 0.3003, "step": 32990 }, { - "epoch": 0.29, - "learning_rate": 3.559228898297451e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.6422003982013826e-05, + "loss": 0.2943, "step": 33000 }, { - "epoch": 0.29, - "learning_rate": 3.5587784884244664e-05, - "loss": 0.2888, + "epoch": 0.07, + "learning_rate": 4.6420885438804504e-05, + "loss": 0.297, "step": 33010 }, { - "epoch": 0.29, - "learning_rate": 3.558328078551482e-05, - "loss": 0.2936, + "epoch": 0.07, + "learning_rate": 4.641976689559518e-05, + "loss": 0.2941, "step": 33020 }, { - "epoch": 0.29, - "learning_rate": 3.557877668678497e-05, - "loss": 0.2899, + "epoch": 0.07, + "learning_rate": 4.641864835238586e-05, + "loss": 0.2951, "step": 33030 }, { - "epoch": 0.29, - "learning_rate": 3.557427258805513e-05, - "loss": 0.2813, + "epoch": 0.07, + "learning_rate": 4.641752980917653e-05, + "loss": 0.2952, "step": 33040 }, { - "epoch": 0.3, - "learning_rate": 3.556976848932529e-05, - "loss": 0.2856, + "epoch": 0.07, + "learning_rate": 4.641641126596721e-05, + "loss": 0.2977, "step": 33050 }, { - "epoch": 0.3, - "learning_rate": 3.5565264390595445e-05, - "loss": 0.2833, + "epoch": 0.07, + "learning_rate": 4.641529272275788e-05, + "loss": 0.2997, "step": 33060 }, { - "epoch": 0.3, - "learning_rate": 3.5560760291865596e-05, - "loss": 0.2853, + "epoch": 0.07, + "learning_rate": 4.641417417954856e-05, + "loss": 0.2997, "step": 33070 }, { - "epoch": 0.3, - "learning_rate": 3.555625619313575e-05, - "loss": 0.2811, + "epoch": 0.07, + "learning_rate": 4.6413055636339236e-05, + "loss": 0.2939, "step": 33080 }, { - "epoch": 0.3, - "learning_rate": 3.555175209440591e-05, - "loss": 0.2805, + "epoch": 0.07, + "learning_rate": 4.641193709312991e-05, + "loss": 0.2974, "step": 33090 }, { - "epoch": 0.3, - "learning_rate": 3.554724799567607e-05, - "loss": 0.2813, + "epoch": 0.07, + "learning_rate": 4.6410818549920585e-05, + "loss": 0.2989, "step": 33100 }, { - "epoch": 0.3, - "learning_rate": 3.5542743896946226e-05, - "loss": 0.2842, + "epoch": 0.07, + "learning_rate": 4.640970000671126e-05, + "loss": 0.2909, "step": 33110 }, { - "epoch": 0.3, - "learning_rate": 3.5538239798216377e-05, - "loss": 0.2865, + "epoch": 0.07, + "learning_rate": 4.640858146350194e-05, + "loss": 0.2985, "step": 33120 }, { - "epoch": 0.3, - "learning_rate": 3.5533735699486534e-05, - "loss": 0.2855, + "epoch": 0.07, + "learning_rate": 4.640746292029262e-05, + "loss": 0.2989, "step": 33130 }, { - "epoch": 0.3, - "learning_rate": 3.552923160075669e-05, - "loss": 0.2828, + "epoch": 0.07, + "learning_rate": 4.640634437708329e-05, + "loss": 0.2977, "step": 33140 }, { - "epoch": 0.3, - "learning_rate": 3.552472750202684e-05, - "loss": 0.2878, + "epoch": 0.07, + "learning_rate": 4.640522583387397e-05, + "loss": 0.2973, "step": 33150 }, { - "epoch": 0.3, - "learning_rate": 3.5520223403297006e-05, - "loss": 0.2787, + "epoch": 0.07, + "learning_rate": 4.640410729066464e-05, + "loss": 0.2996, "step": 33160 }, { - "epoch": 0.3, - "learning_rate": 3.551571930456716e-05, - "loss": 0.2881, + "epoch": 0.07, + "learning_rate": 4.640298874745532e-05, + "loss": 0.2995, "step": 33170 }, { - "epoch": 0.3, - "learning_rate": 3.5511215205837315e-05, - "loss": 0.2871, + "epoch": 0.07, + "learning_rate": 4.640187020424599e-05, + "loss": 0.3007, "step": 33180 }, { - "epoch": 0.3, - "learning_rate": 3.550671110710747e-05, - "loss": 0.2844, + "epoch": 0.07, + "learning_rate": 4.6400751661036666e-05, + "loss": 0.3027, "step": 33190 }, { - "epoch": 0.3, - "learning_rate": 3.550220700837762e-05, - "loss": 0.2877, + "epoch": 0.07, + "learning_rate": 4.6399633117827344e-05, + "loss": 0.2965, "step": 33200 }, { - "epoch": 0.3, - "learning_rate": 3.549770290964778e-05, - "loss": 0.285, + "epoch": 0.07, + "learning_rate": 4.6398514574618015e-05, + "loss": 0.3048, "step": 33210 }, { - "epoch": 0.3, - "learning_rate": 3.549319881091794e-05, - "loss": 0.2815, + "epoch": 0.07, + "learning_rate": 4.63973960314087e-05, + "loss": 0.2991, "step": 33220 }, { - "epoch": 0.3, - "learning_rate": 3.548869471218809e-05, - "loss": 0.2851, + "epoch": 0.07, + "learning_rate": 4.639627748819937e-05, + "loss": 0.2965, "step": 33230 }, { - "epoch": 0.3, - "learning_rate": 3.548419061345825e-05, - "loss": 0.2889, + "epoch": 0.07, + "learning_rate": 4.639515894499005e-05, + "loss": 0.2953, "step": 33240 }, { - "epoch": 0.3, - "learning_rate": 3.5479686514728404e-05, - "loss": 0.2844, + "epoch": 0.07, + "learning_rate": 4.639404040178073e-05, + "loss": 0.2979, "step": 33250 }, { - "epoch": 0.3, - "learning_rate": 3.547518241599856e-05, - "loss": 0.2892, + "epoch": 0.07, + "learning_rate": 4.63929218585714e-05, + "loss": 0.2932, "step": 33260 }, { - "epoch": 0.3, - "learning_rate": 3.547067831726872e-05, - "loss": 0.2921, + "epoch": 0.07, + "learning_rate": 4.6391803315362076e-05, + "loss": 0.2984, "step": 33270 }, { - "epoch": 0.3, - "learning_rate": 3.546617421853887e-05, - "loss": 0.282, + "epoch": 0.07, + "learning_rate": 4.639068477215275e-05, + "loss": 0.297, "step": 33280 }, { - "epoch": 0.3, - "learning_rate": 3.546167011980903e-05, - "loss": 0.2814, + "epoch": 0.07, + "learning_rate": 4.6389566228943425e-05, + "loss": 0.2949, "step": 33290 }, { - "epoch": 0.3, - "learning_rate": 3.5457166021079184e-05, - "loss": 0.2869, + "epoch": 0.07, + "learning_rate": 4.63884476857341e-05, + "loss": 0.2999, "step": 33300 }, { - "epoch": 0.3, - "learning_rate": 3.545266192234934e-05, - "loss": 0.2854, + "epoch": 0.07, + "learning_rate": 4.6387329142524774e-05, + "loss": 0.2947, "step": 33310 }, { - "epoch": 0.3, - "learning_rate": 3.544815782361949e-05, - "loss": 0.2838, + "epoch": 0.07, + "learning_rate": 4.638621059931545e-05, + "loss": 0.2951, "step": 33320 }, { - "epoch": 0.3, - "learning_rate": 3.544365372488965e-05, - "loss": 0.2858, + "epoch": 0.07, + "learning_rate": 4.638509205610613e-05, + "loss": 0.2964, "step": 33330 }, { - "epoch": 0.3, - "learning_rate": 3.543914962615981e-05, - "loss": 0.2838, + "epoch": 0.07, + "learning_rate": 4.638397351289681e-05, + "loss": 0.2979, "step": 33340 }, { - "epoch": 0.3, - "learning_rate": 3.543464552742996e-05, - "loss": 0.2882, + "epoch": 0.07, + "learning_rate": 4.6382854969687486e-05, + "loss": 0.299, "step": 33350 }, { - "epoch": 0.3, - "learning_rate": 3.543014142870012e-05, - "loss": 0.288, + "epoch": 0.07, + "learning_rate": 4.638173642647816e-05, + "loss": 0.3018, "step": 33360 }, { - "epoch": 0.3, - "learning_rate": 3.542563732997027e-05, - "loss": 0.2827, + "epoch": 0.07, + "learning_rate": 4.6380617883268835e-05, + "loss": 0.2948, "step": 33370 }, { - "epoch": 0.3, - "learning_rate": 3.542113323124043e-05, - "loss": 0.286, + "epoch": 0.07, + "learning_rate": 4.6379499340059506e-05, + "loss": 0.297, "step": 33380 }, { - "epoch": 0.3, - "learning_rate": 3.541662913251059e-05, - "loss": 0.29, + "epoch": 0.07, + "learning_rate": 4.6378380796850184e-05, + "loss": 0.3023, "step": 33390 }, { - "epoch": 0.3, - "learning_rate": 3.541212503378074e-05, - "loss": 0.2862, + "epoch": 0.07, + "learning_rate": 4.637726225364086e-05, + "loss": 0.2967, "step": 33400 }, { - "epoch": 0.3, - "learning_rate": 3.54076209350509e-05, - "loss": 0.2893, + "epoch": 0.07, + "learning_rate": 4.637614371043153e-05, + "loss": 0.2979, "step": 33410 }, { - "epoch": 0.3, - "learning_rate": 3.5403116836321054e-05, - "loss": 0.2861, + "epoch": 0.07, + "learning_rate": 4.637502516722221e-05, + "loss": 0.2974, "step": 33420 }, { - "epoch": 0.3, - "learning_rate": 3.539861273759121e-05, - "loss": 0.2923, + "epoch": 0.07, + "learning_rate": 4.637390662401289e-05, + "loss": 0.2937, "step": 33430 }, { - "epoch": 0.3, - "learning_rate": 3.539410863886137e-05, - "loss": 0.285, + "epoch": 0.07, + "learning_rate": 4.637278808080357e-05, + "loss": 0.2961, "step": 33440 }, { - "epoch": 0.3, - "learning_rate": 3.538960454013152e-05, - "loss": 0.2808, + "epoch": 0.07, + "learning_rate": 4.6371669537594245e-05, + "loss": 0.2932, "step": 33450 }, { - "epoch": 0.3, - "learning_rate": 3.538510044140168e-05, - "loss": 0.28, + "epoch": 0.07, + "learning_rate": 4.6370550994384916e-05, + "loss": 0.301, "step": 33460 }, { - "epoch": 0.3, - "learning_rate": 3.5380596342671835e-05, - "loss": 0.2806, + "epoch": 0.07, + "learning_rate": 4.6369432451175594e-05, + "loss": 0.2962, "step": 33470 }, { - "epoch": 0.3, - "learning_rate": 3.5376092243941985e-05, - "loss": 0.284, + "epoch": 0.07, + "learning_rate": 4.6368313907966265e-05, + "loss": 0.2946, "step": 33480 }, { - "epoch": 0.3, - "learning_rate": 3.537158814521214e-05, - "loss": 0.2913, + "epoch": 0.07, + "learning_rate": 4.636719536475694e-05, + "loss": 0.2952, "step": 33490 }, { - "epoch": 0.3, - "learning_rate": 3.53670840464823e-05, - "loss": 0.2922, + "epoch": 0.07, + "learning_rate": 4.6366076821547614e-05, + "loss": 0.2992, "step": 33500 }, { - "epoch": 0.3, - "learning_rate": 3.536257994775246e-05, - "loss": 0.2915, + "epoch": 0.07, + "learning_rate": 4.636495827833829e-05, + "loss": 0.2966, "step": 33510 }, { - "epoch": 0.3, - "learning_rate": 3.5358075849022615e-05, - "loss": 0.2854, + "epoch": 0.07, + "learning_rate": 4.636383973512897e-05, + "loss": 0.297, "step": 33520 }, { - "epoch": 0.3, - "learning_rate": 3.5353571750292766e-05, - "loss": 0.2891, + "epoch": 0.07, + "learning_rate": 4.636272119191965e-05, + "loss": 0.2906, "step": 33530 }, { - "epoch": 0.3, - "learning_rate": 3.5349067651562923e-05, - "loss": 0.2834, + "epoch": 0.07, + "learning_rate": 4.6361602648710326e-05, + "loss": 0.3002, "step": 33540 }, { - "epoch": 0.3, - "learning_rate": 3.534456355283308e-05, - "loss": 0.2729, + "epoch": 0.07, + "learning_rate": 4.6360484105501e-05, + "loss": 0.2942, "step": 33550 }, { - "epoch": 0.3, - "learning_rate": 3.534005945410324e-05, - "loss": 0.2831, + "epoch": 0.07, + "learning_rate": 4.6359365562291675e-05, + "loss": 0.2994, "step": 33560 }, { - "epoch": 0.3, - "learning_rate": 3.533555535537339e-05, - "loss": 0.2817, + "epoch": 0.07, + "learning_rate": 4.635824701908235e-05, + "loss": 0.2986, "step": 33570 }, { - "epoch": 0.3, - "learning_rate": 3.533105125664355e-05, - "loss": 0.2866, + "epoch": 0.07, + "learning_rate": 4.6357128475873024e-05, + "loss": 0.3036, "step": 33580 }, { - "epoch": 0.3, - "learning_rate": 3.5326547157913704e-05, - "loss": 0.2811, + "epoch": 0.07, + "learning_rate": 4.63560099326637e-05, + "loss": 0.2934, "step": 33590 }, { - "epoch": 0.3, - "learning_rate": 3.5322043059183855e-05, - "loss": 0.2828, + "epoch": 0.07, + "learning_rate": 4.635489138945437e-05, + "loss": 0.2977, "step": 33600 }, { - "epoch": 0.3, - "learning_rate": 3.531753896045402e-05, - "loss": 0.2829, + "epoch": 0.08, + "learning_rate": 4.635377284624505e-05, + "loss": 0.2958, "step": 33610 }, { - "epoch": 0.3, - "learning_rate": 3.531303486172417e-05, - "loss": 0.2918, + "epoch": 0.08, + "learning_rate": 4.635265430303573e-05, + "loss": 0.2985, "step": 33620 }, { - "epoch": 0.3, - "learning_rate": 3.530853076299433e-05, - "loss": 0.2813, + "epoch": 0.08, + "learning_rate": 4.635153575982641e-05, + "loss": 0.2976, "step": 33630 }, { - "epoch": 0.3, - "learning_rate": 3.5304026664264485e-05, - "loss": 0.2855, + "epoch": 0.08, + "learning_rate": 4.6350417216617085e-05, + "loss": 0.2995, "step": 33640 }, { - "epoch": 0.3, - "learning_rate": 3.5299522565534636e-05, - "loss": 0.2851, + "epoch": 0.08, + "learning_rate": 4.6349298673407756e-05, + "loss": 0.3004, "step": 33650 }, { - "epoch": 0.3, - "learning_rate": 3.52950184668048e-05, - "loss": 0.2825, + "epoch": 0.08, + "learning_rate": 4.6348180130198434e-05, + "loss": 0.2962, "step": 33660 }, { - "epoch": 0.3, - "learning_rate": 3.529051436807495e-05, - "loss": 0.2864, + "epoch": 0.08, + "learning_rate": 4.634706158698911e-05, + "loss": 0.2919, "step": 33670 }, { - "epoch": 0.3, - "learning_rate": 3.52860102693451e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.634594304377978e-05, + "loss": 0.3022, "step": 33680 }, { - "epoch": 0.3, - "learning_rate": 3.5281506170615265e-05, - "loss": 0.2894, + "epoch": 0.08, + "learning_rate": 4.634482450057046e-05, + "loss": 0.3001, "step": 33690 }, { - "epoch": 0.3, - "learning_rate": 3.5277002071885416e-05, - "loss": 0.2876, + "epoch": 0.08, + "learning_rate": 4.634370595736113e-05, + "loss": 0.2909, "step": 33700 }, { - "epoch": 0.3, - "learning_rate": 3.5272497973155574e-05, - "loss": 0.2903, + "epoch": 0.08, + "learning_rate": 4.634258741415181e-05, + "loss": 0.2962, "step": 33710 }, { - "epoch": 0.3, - "learning_rate": 3.526799387442573e-05, - "loss": 0.2809, + "epoch": 0.08, + "learning_rate": 4.634146887094249e-05, + "loss": 0.2942, "step": 33720 }, { - "epoch": 0.3, - "learning_rate": 3.526348977569588e-05, - "loss": 0.288, + "epoch": 0.08, + "learning_rate": 4.634035032773316e-05, + "loss": 0.2962, "step": 33730 }, { - "epoch": 0.3, - "learning_rate": 3.525898567696604e-05, - "loss": 0.2861, + "epoch": 0.08, + "learning_rate": 4.633923178452384e-05, + "loss": 0.2919, "step": 33740 }, { - "epoch": 0.3, - "learning_rate": 3.52544815782362e-05, - "loss": 0.2756, + "epoch": 0.08, + "learning_rate": 4.6338113241314515e-05, + "loss": 0.2995, "step": 33750 }, { - "epoch": 0.3, - "learning_rate": 3.5249977479506354e-05, - "loss": 0.2884, + "epoch": 0.08, + "learning_rate": 4.633699469810519e-05, + "loss": 0.296, "step": 33760 }, { - "epoch": 0.3, - "learning_rate": 3.5245473380776505e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.6335876154895864e-05, + "loss": 0.293, "step": 33770 }, { - "epoch": 0.3, - "learning_rate": 3.524096928204666e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.633475761168654e-05, + "loss": 0.2982, "step": 33780 }, { - "epoch": 0.3, - "learning_rate": 3.523646518331682e-05, - "loss": 0.2804, + "epoch": 0.08, + "learning_rate": 4.633363906847722e-05, + "loss": 0.2919, "step": 33790 }, { - "epoch": 0.3, - "learning_rate": 3.523196108458698e-05, - "loss": 0.2873, + "epoch": 0.08, + "learning_rate": 4.633252052526789e-05, + "loss": 0.2973, "step": 33800 }, { - "epoch": 0.3, - "learning_rate": 3.5227456985857135e-05, - "loss": 0.2888, + "epoch": 0.08, + "learning_rate": 4.633140198205857e-05, + "loss": 0.2906, "step": 33810 }, { - "epoch": 0.3, - "learning_rate": 3.5222952887127286e-05, - "loss": 0.2883, + "epoch": 0.08, + "learning_rate": 4.633028343884924e-05, + "loss": 0.2954, "step": 33820 }, { - "epoch": 0.3, - "learning_rate": 3.521844878839744e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.632916489563992e-05, + "loss": 0.2995, "step": 33830 }, { - "epoch": 0.3, - "learning_rate": 3.52139446896676e-05, - "loss": 0.286, + "epoch": 0.08, + "learning_rate": 4.6328046352430596e-05, + "loss": 0.2966, "step": 33840 }, { - "epoch": 0.3, - "learning_rate": 3.520944059093775e-05, - "loss": 0.2767, + "epoch": 0.08, + "learning_rate": 4.6326927809221274e-05, + "loss": 0.2955, "step": 33850 }, { - "epoch": 0.3, - "learning_rate": 3.5204936492207916e-05, - "loss": 0.2799, + "epoch": 0.08, + "learning_rate": 4.632580926601195e-05, + "loss": 0.2933, "step": 33860 }, { - "epoch": 0.3, - "learning_rate": 3.5200432393478066e-05, - "loss": 0.2838, + "epoch": 0.08, + "learning_rate": 4.632469072280262e-05, + "loss": 0.3042, "step": 33870 }, { - "epoch": 0.3, - "learning_rate": 3.519592829474822e-05, - "loss": 0.2813, + "epoch": 0.08, + "learning_rate": 4.63235721795933e-05, + "loss": 0.2997, "step": 33880 }, { - "epoch": 0.3, - "learning_rate": 3.519142419601838e-05, - "loss": 0.2816, + "epoch": 0.08, + "learning_rate": 4.632245363638398e-05, + "loss": 0.2978, "step": 33890 }, { - "epoch": 0.3, - "learning_rate": 3.518692009728853e-05, - "loss": 0.2851, + "epoch": 0.08, + "learning_rate": 4.632133509317465e-05, + "loss": 0.2978, "step": 33900 }, { - "epoch": 0.3, - "learning_rate": 3.518241599855869e-05, - "loss": 0.2822, + "epoch": 0.08, + "learning_rate": 4.632021654996533e-05, + "loss": 0.2955, "step": 33910 }, { - "epoch": 0.3, - "learning_rate": 3.517791189982885e-05, - "loss": 0.2821, + "epoch": 0.08, + "learning_rate": 4.6319098006756e-05, + "loss": 0.2974, "step": 33920 }, { - "epoch": 0.3, - "learning_rate": 3.5173407801099e-05, - "loss": 0.2748, + "epoch": 0.08, + "learning_rate": 4.631797946354668e-05, + "loss": 0.29, "step": 33930 }, { - "epoch": 0.3, - "learning_rate": 3.516890370236916e-05, - "loss": 0.2796, + "epoch": 0.08, + "learning_rate": 4.6316860920337355e-05, + "loss": 0.3029, "step": 33940 }, { - "epoch": 0.3, - "learning_rate": 3.516439960363931e-05, - "loss": 0.2854, + "epoch": 0.08, + "learning_rate": 4.631574237712803e-05, + "loss": 0.303, "step": 33950 }, { - "epoch": 0.3, - "learning_rate": 3.515989550490947e-05, - "loss": 0.2827, + "epoch": 0.08, + "learning_rate": 4.631462383391871e-05, + "loss": 0.2976, "step": 33960 }, { - "epoch": 0.3, - "learning_rate": 3.515539140617963e-05, - "loss": 0.2811, + "epoch": 0.08, + "learning_rate": 4.631350529070938e-05, + "loss": 0.2943, "step": 33970 }, { - "epoch": 0.3, - "learning_rate": 3.515088730744978e-05, - "loss": 0.281, + "epoch": 0.08, + "learning_rate": 4.631238674750006e-05, + "loss": 0.2965, "step": 33980 }, { - "epoch": 0.3, - "learning_rate": 3.5146383208719936e-05, - "loss": 0.2787, + "epoch": 0.08, + "learning_rate": 4.631126820429074e-05, + "loss": 0.2973, "step": 33990 }, { - "epoch": 0.3, - "learning_rate": 3.5141879109990094e-05, - "loss": 0.2809, + "epoch": 0.08, + "learning_rate": 4.631014966108141e-05, + "loss": 0.2996, "step": 34000 }, { - "epoch": 0.3, - "learning_rate": 3.513737501126025e-05, - "loss": 0.2846, + "epoch": 0.08, + "learning_rate": 4.6309031117872087e-05, + "loss": 0.2972, "step": 34010 }, { - "epoch": 0.3, - "learning_rate": 3.51328709125304e-05, - "loss": 0.2836, + "epoch": 0.08, + "learning_rate": 4.630791257466276e-05, + "loss": 0.2964, "step": 34020 }, { - "epoch": 0.3, - "learning_rate": 3.512836681380056e-05, - "loss": 0.2829, + "epoch": 0.08, + "learning_rate": 4.6306794031453436e-05, + "loss": 0.296, "step": 34030 }, { - "epoch": 0.3, - "learning_rate": 3.512386271507072e-05, - "loss": 0.2848, + "epoch": 0.08, + "learning_rate": 4.6305675488244114e-05, + "loss": 0.2947, "step": 34040 }, { - "epoch": 0.3, - "learning_rate": 3.511935861634087e-05, - "loss": 0.2798, + "epoch": 0.08, + "learning_rate": 4.630455694503479e-05, + "loss": 0.2976, "step": 34050 }, { - "epoch": 0.3, - "learning_rate": 3.511485451761103e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.630343840182547e-05, + "loss": 0.2966, "step": 34060 }, { - "epoch": 0.3, - "learning_rate": 3.511035041888118e-05, - "loss": 0.2861, + "epoch": 0.08, + "learning_rate": 4.630231985861614e-05, + "loss": 0.2972, "step": 34070 }, { - "epoch": 0.3, - "learning_rate": 3.510584632015134e-05, - "loss": 0.2845, + "epoch": 0.08, + "learning_rate": 4.630120131540682e-05, + "loss": 0.3001, "step": 34080 }, { - "epoch": 0.3, - "learning_rate": 3.51013422214215e-05, - "loss": 0.2807, + "epoch": 0.08, + "learning_rate": 4.630008277219749e-05, + "loss": 0.2943, "step": 34090 }, { - "epoch": 0.3, - "learning_rate": 3.509683812269165e-05, - "loss": 0.283, + "epoch": 0.08, + "learning_rate": 4.629896422898817e-05, + "loss": 0.2924, "step": 34100 }, { - "epoch": 0.3, - "learning_rate": 3.509233402396181e-05, - "loss": 0.2881, + "epoch": 0.08, + "learning_rate": 4.6297845685778846e-05, + "loss": 0.2934, "step": 34110 }, { - "epoch": 0.3, - "learning_rate": 3.508782992523196e-05, - "loss": 0.2798, + "epoch": 0.08, + "learning_rate": 4.629672714256952e-05, + "loss": 0.2901, "step": 34120 }, { - "epoch": 0.3, - "learning_rate": 3.5083325826502114e-05, - "loss": 0.2852, + "epoch": 0.08, + "learning_rate": 4.6295608599360195e-05, + "loss": 0.2921, "step": 34130 }, { - "epoch": 0.3, - "learning_rate": 3.507882172777228e-05, - "loss": 0.2818, + "epoch": 0.08, + "learning_rate": 4.6294490056150866e-05, + "loss": 0.2957, "step": 34140 }, { - "epoch": 0.3, - "learning_rate": 3.507431762904243e-05, - "loss": 0.2877, + "epoch": 0.08, + "learning_rate": 4.6293371512941544e-05, + "loss": 0.2964, "step": 34150 }, { - "epoch": 0.3, - "learning_rate": 3.5069813530312586e-05, - "loss": 0.2882, + "epoch": 0.08, + "learning_rate": 4.629225296973222e-05, + "loss": 0.2987, "step": 34160 }, { - "epoch": 0.31, - "learning_rate": 3.5065309431582744e-05, - "loss": 0.2833, + "epoch": 0.08, + "learning_rate": 4.62911344265229e-05, + "loss": 0.2974, "step": 34170 }, { - "epoch": 0.31, - "learning_rate": 3.5060805332852895e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.629001588331358e-05, + "loss": 0.2977, "step": 34180 }, { - "epoch": 0.31, - "learning_rate": 3.505630123412305e-05, - "loss": 0.2797, + "epoch": 0.08, + "learning_rate": 4.628889734010425e-05, + "loss": 0.2887, "step": 34190 }, { - "epoch": 0.31, - "learning_rate": 3.505179713539321e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.6287778796894927e-05, + "loss": 0.2952, "step": 34200 }, { - "epoch": 0.31, - "learning_rate": 3.504729303666337e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.6286660253685604e-05, + "loss": 0.2914, "step": 34210 }, { - "epoch": 0.31, - "learning_rate": 3.5042788937933524e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.6285541710476276e-05, + "loss": 0.2953, "step": 34220 }, { - "epoch": 0.31, - "learning_rate": 3.5038284839203675e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.6284423167266954e-05, + "loss": 0.297, "step": 34230 }, { - "epoch": 0.31, - "learning_rate": 3.503378074047383e-05, - "loss": 0.2867, + "epoch": 0.08, + "learning_rate": 4.6283304624057625e-05, + "loss": 0.2928, "step": 34240 }, { - "epoch": 0.31, - "learning_rate": 3.502927664174399e-05, - "loss": 0.2824, + "epoch": 0.08, + "learning_rate": 4.62821860808483e-05, + "loss": 0.2973, "step": 34250 }, { - "epoch": 0.31, - "learning_rate": 3.502477254301415e-05, - "loss": 0.2864, + "epoch": 0.08, + "learning_rate": 4.628106753763898e-05, + "loss": 0.2904, "step": 34260 }, { - "epoch": 0.31, - "learning_rate": 3.50202684442843e-05, - "loss": 0.2802, + "epoch": 0.08, + "learning_rate": 4.627994899442966e-05, + "loss": 0.2933, "step": 34270 }, { - "epoch": 0.31, - "learning_rate": 3.5015764345554456e-05, - "loss": 0.2849, + "epoch": 0.08, + "learning_rate": 4.6278830451220336e-05, + "loss": 0.2896, "step": 34280 }, { - "epoch": 0.31, - "learning_rate": 3.501126024682461e-05, - "loss": 0.2757, + "epoch": 0.08, + "learning_rate": 4.627771190801101e-05, + "loss": 0.2946, "step": 34290 }, { - "epoch": 0.31, - "learning_rate": 3.5006756148094764e-05, - "loss": 0.2887, + "epoch": 0.08, + "learning_rate": 4.6276593364801685e-05, + "loss": 0.2985, "step": 34300 }, { - "epoch": 0.31, - "learning_rate": 3.500225204936493e-05, - "loss": 0.2787, + "epoch": 0.08, + "learning_rate": 4.6275474821592363e-05, + "loss": 0.2895, "step": 34310 }, { - "epoch": 0.31, - "learning_rate": 3.499774795063508e-05, - "loss": 0.2827, + "epoch": 0.08, + "learning_rate": 4.6274356278383035e-05, + "loss": 0.2899, "step": 34320 }, { - "epoch": 0.31, - "learning_rate": 3.499324385190523e-05, - "loss": 0.274, + "epoch": 0.08, + "learning_rate": 4.627323773517371e-05, + "loss": 0.2987, "step": 34330 }, { - "epoch": 0.31, - "learning_rate": 3.4988739753175394e-05, - "loss": 0.2813, + "epoch": 0.08, + "learning_rate": 4.6272119191964384e-05, + "loss": 0.2979, "step": 34340 }, { - "epoch": 0.31, - "learning_rate": 3.4984235654445545e-05, - "loss": 0.2819, + "epoch": 0.08, + "learning_rate": 4.627100064875506e-05, + "loss": 0.2904, "step": 34350 }, { - "epoch": 0.31, - "learning_rate": 3.497973155571571e-05, - "loss": 0.2845, + "epoch": 0.08, + "learning_rate": 4.626988210554574e-05, + "loss": 0.2935, "step": 34360 }, { - "epoch": 0.31, - "learning_rate": 3.497522745698586e-05, - "loss": 0.284, + "epoch": 0.08, + "learning_rate": 4.626876356233642e-05, + "loss": 0.2942, "step": 34370 }, { - "epoch": 0.31, - "learning_rate": 3.497072335825601e-05, - "loss": 0.2822, + "epoch": 0.08, + "learning_rate": 4.6267645019127095e-05, + "loss": 0.2846, "step": 34380 }, { - "epoch": 0.31, - "learning_rate": 3.4966219259526175e-05, - "loss": 0.272, + "epoch": 0.08, + "learning_rate": 4.6266526475917766e-05, + "loss": 0.2956, "step": 34390 }, { - "epoch": 0.31, - "learning_rate": 3.4961715160796325e-05, - "loss": 0.2826, + "epoch": 0.08, + "learning_rate": 4.6265407932708444e-05, + "loss": 0.2958, "step": 34400 }, { - "epoch": 0.31, - "learning_rate": 3.495721106206648e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.6264289389499116e-05, + "loss": 0.2905, "step": 34410 }, { - "epoch": 0.31, - "learning_rate": 3.495270696333664e-05, - "loss": 0.2816, + "epoch": 0.08, + "learning_rate": 4.6263170846289794e-05, + "loss": 0.2862, "step": 34420 }, { - "epoch": 0.31, - "learning_rate": 3.494820286460679e-05, - "loss": 0.2737, + "epoch": 0.08, + "learning_rate": 4.626205230308047e-05, + "loss": 0.2935, "step": 34430 }, { - "epoch": 0.31, - "learning_rate": 3.494369876587695e-05, - "loss": 0.2789, + "epoch": 0.08, + "learning_rate": 4.626093375987114e-05, + "loss": 0.2941, "step": 34440 }, { - "epoch": 0.31, - "learning_rate": 3.4939194667147106e-05, - "loss": 0.2819, + "epoch": 0.08, + "learning_rate": 4.625981521666182e-05, + "loss": 0.2925, "step": 34450 }, { - "epoch": 0.31, - "learning_rate": 3.4934690568417264e-05, - "loss": 0.2806, + "epoch": 0.08, + "learning_rate": 4.62586966734525e-05, + "loss": 0.2903, "step": 34460 }, { - "epoch": 0.31, - "learning_rate": 3.4930186469687414e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.6257578130243176e-05, + "loss": 0.2821, "step": 34470 }, { - "epoch": 0.31, - "learning_rate": 3.492568237095757e-05, - "loss": 0.2848, + "epoch": 0.08, + "learning_rate": 4.6256459587033854e-05, + "loss": 0.2894, "step": 34480 }, { - "epoch": 0.31, - "learning_rate": 3.492117827222773e-05, - "loss": 0.2777, + "epoch": 0.08, + "learning_rate": 4.6255341043824525e-05, + "loss": 0.293, "step": 34490 }, { - "epoch": 0.31, - "learning_rate": 3.491667417349789e-05, - "loss": 0.2794, + "epoch": 0.08, + "learning_rate": 4.62542225006152e-05, + "loss": 0.2952, "step": 34500 }, { - "epoch": 0.31, - "learning_rate": 3.4912170074768044e-05, - "loss": 0.2795, + "epoch": 0.08, + "learning_rate": 4.6253103957405875e-05, + "loss": 0.2925, "step": 34510 }, { - "epoch": 0.31, - "learning_rate": 3.4907665976038195e-05, - "loss": 0.2871, + "epoch": 0.08, + "learning_rate": 4.625198541419655e-05, + "loss": 0.2964, "step": 34520 }, { - "epoch": 0.31, - "learning_rate": 3.490316187730835e-05, - "loss": 0.2897, + "epoch": 0.08, + "learning_rate": 4.625086687098723e-05, + "loss": 0.2937, "step": 34530 }, { - "epoch": 0.31, - "learning_rate": 3.489865777857851e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.62497483277779e-05, + "loss": 0.291, "step": 34540 }, { - "epoch": 0.31, - "learning_rate": 3.489415367984866e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.624862978456858e-05, + "loss": 0.2946, "step": 34550 }, { - "epoch": 0.31, - "learning_rate": 3.4889649581118825e-05, - "loss": 0.2833, + "epoch": 0.08, + "learning_rate": 4.624751124135925e-05, + "loss": 0.2896, "step": 34560 }, { - "epoch": 0.31, - "learning_rate": 3.4885145482388976e-05, - "loss": 0.2789, + "epoch": 0.08, + "learning_rate": 4.624639269814993e-05, + "loss": 0.2883, "step": 34570 }, { - "epoch": 0.31, - "learning_rate": 3.4880641383659126e-05, - "loss": 0.2755, + "epoch": 0.08, + "learning_rate": 4.624527415494061e-05, + "loss": 0.2942, "step": 34580 }, { - "epoch": 0.31, - "learning_rate": 3.487613728492929e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.6244155611731284e-05, + "loss": 0.2925, "step": 34590 }, { - "epoch": 0.31, - "learning_rate": 3.487163318619944e-05, - "loss": 0.2857, + "epoch": 0.08, + "learning_rate": 4.624303706852196e-05, + "loss": 0.2958, "step": 34600 }, { - "epoch": 0.31, - "learning_rate": 3.48671290874696e-05, - "loss": 0.2799, + "epoch": 0.08, + "learning_rate": 4.6241918525312633e-05, + "loss": 0.2891, "step": 34610 }, { - "epoch": 0.31, - "learning_rate": 3.4862624988739756e-05, - "loss": 0.2788, + "epoch": 0.08, + "learning_rate": 4.624079998210331e-05, + "loss": 0.2913, "step": 34620 }, { - "epoch": 0.31, - "learning_rate": 3.485812089000991e-05, - "loss": 0.2752, + "epoch": 0.08, + "learning_rate": 4.623968143889399e-05, + "loss": 0.2934, "step": 34630 }, { - "epoch": 0.31, - "learning_rate": 3.485361679128007e-05, - "loss": 0.2792, + "epoch": 0.08, + "learning_rate": 4.623856289568466e-05, + "loss": 0.2924, "step": 34640 }, { - "epoch": 0.31, - "learning_rate": 3.484911269255022e-05, - "loss": 0.2807, + "epoch": 0.08, + "learning_rate": 4.623744435247534e-05, + "loss": 0.297, "step": 34650 }, { - "epoch": 0.31, - "learning_rate": 3.484460859382038e-05, - "loss": 0.2785, + "epoch": 0.08, + "learning_rate": 4.623632580926601e-05, + "loss": 0.2961, "step": 34660 }, { - "epoch": 0.31, - "learning_rate": 3.484010449509054e-05, - "loss": 0.2795, + "epoch": 0.08, + "learning_rate": 4.623520726605669e-05, + "loss": 0.2951, "step": 34670 }, { - "epoch": 0.31, - "learning_rate": 3.483560039636069e-05, - "loss": 0.2741, + "epoch": 0.08, + "learning_rate": 4.6234088722847365e-05, + "loss": 0.2924, "step": 34680 }, { - "epoch": 0.31, - "learning_rate": 3.4831096297630845e-05, - "loss": 0.2756, + "epoch": 0.08, + "learning_rate": 4.623297017963804e-05, + "loss": 0.2884, "step": 34690 }, { - "epoch": 0.31, - "learning_rate": 3.4826592198901e-05, - "loss": 0.2748, + "epoch": 0.08, + "learning_rate": 4.623185163642872e-05, + "loss": 0.2902, "step": 34700 }, { - "epoch": 0.31, - "learning_rate": 3.482208810017116e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.623073309321939e-05, + "loss": 0.2941, "step": 34710 }, { - "epoch": 0.31, - "learning_rate": 3.481758400144131e-05, - "loss": 0.2794, + "epoch": 0.08, + "learning_rate": 4.622961455001007e-05, + "loss": 0.2906, "step": 34720 }, { - "epoch": 0.31, - "learning_rate": 3.481307990271147e-05, - "loss": 0.2841, + "epoch": 0.08, + "learning_rate": 4.622849600680074e-05, + "loss": 0.2943, "step": 34730 }, { - "epoch": 0.31, - "learning_rate": 3.4808575803981626e-05, - "loss": 0.2796, + "epoch": 0.08, + "learning_rate": 4.622737746359142e-05, + "loss": 0.2903, "step": 34740 }, { - "epoch": 0.31, - "learning_rate": 3.480407170525178e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.62262589203821e-05, + "loss": 0.2961, "step": 34750 }, { - "epoch": 0.31, - "learning_rate": 3.479956760652194e-05, - "loss": 0.2836, + "epoch": 0.08, + "learning_rate": 4.622514037717277e-05, + "loss": 0.2893, "step": 34760 }, { - "epoch": 0.31, - "learning_rate": 3.479506350779209e-05, - "loss": 0.2786, + "epoch": 0.08, + "learning_rate": 4.6224021833963446e-05, + "loss": 0.2949, "step": 34770 }, { - "epoch": 0.31, - "learning_rate": 3.479055940906225e-05, - "loss": 0.2777, + "epoch": 0.08, + "learning_rate": 4.6222903290754124e-05, + "loss": 0.2866, "step": 34780 }, { - "epoch": 0.31, - "learning_rate": 3.478605531033241e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.62217847475448e-05, + "loss": 0.2913, "step": 34790 }, { - "epoch": 0.31, - "learning_rate": 3.478155121160256e-05, - "loss": 0.2855, + "epoch": 0.08, + "learning_rate": 4.622066620433548e-05, + "loss": 0.2927, "step": 34800 }, { - "epoch": 0.31, - "learning_rate": 3.4777047112872715e-05, - "loss": 0.2856, + "epoch": 0.08, + "learning_rate": 4.621954766112615e-05, + "loss": 0.2899, "step": 34810 }, { - "epoch": 0.31, - "learning_rate": 3.477254301414287e-05, - "loss": 0.2816, + "epoch": 0.08, + "learning_rate": 4.621842911791683e-05, + "loss": 0.288, "step": 34820 }, { - "epoch": 0.31, - "learning_rate": 3.476803891541302e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.62173105747075e-05, + "loss": 0.298, "step": 34830 }, { - "epoch": 0.31, - "learning_rate": 3.476353481668319e-05, - "loss": 0.2795, + "epoch": 0.08, + "learning_rate": 4.621619203149818e-05, + "loss": 0.2913, "step": 34840 }, { - "epoch": 0.31, - "learning_rate": 3.475903071795334e-05, - "loss": 0.2813, + "epoch": 0.08, + "learning_rate": 4.6215073488288856e-05, + "loss": 0.2914, "step": 34850 }, { - "epoch": 0.31, - "learning_rate": 3.4754526619223496e-05, - "loss": 0.2787, + "epoch": 0.08, + "learning_rate": 4.6214066799400465e-05, + "loss": 0.2917, "step": 34860 }, { - "epoch": 0.31, - "learning_rate": 3.475002252049365e-05, - "loss": 0.2863, + "epoch": 0.08, + "learning_rate": 4.621294825619114e-05, + "loss": 0.29, "step": 34870 }, { - "epoch": 0.31, - "learning_rate": 3.4745518421763804e-05, - "loss": 0.2768, + "epoch": 0.08, + "learning_rate": 4.6211829712981814e-05, + "loss": 0.2927, "step": 34880 }, { - "epoch": 0.31, - "learning_rate": 3.474101432303396e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.621071116977249e-05, + "loss": 0.2938, "step": 34890 }, { - "epoch": 0.31, - "learning_rate": 3.473651022430412e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.620959262656316e-05, + "loss": 0.2931, "step": 34900 }, { - "epoch": 0.31, - "learning_rate": 3.4732006125574276e-05, - "loss": 0.2739, + "epoch": 0.08, + "learning_rate": 4.620847408335384e-05, + "loss": 0.2955, "step": 34910 }, { - "epoch": 0.31, - "learning_rate": 3.472750202684443e-05, - "loss": 0.2827, + "epoch": 0.08, + "learning_rate": 4.620735554014452e-05, + "loss": 0.2927, "step": 34920 }, { - "epoch": 0.31, - "learning_rate": 3.4722997928114584e-05, - "loss": 0.2784, + "epoch": 0.08, + "learning_rate": 4.620623699693519e-05, + "loss": 0.291, "step": 34930 }, { - "epoch": 0.31, - "learning_rate": 3.471849382938474e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.620511845372587e-05, + "loss": 0.2947, "step": 34940 }, { - "epoch": 0.31, - "learning_rate": 3.47139897306549e-05, - "loss": 0.2819, + "epoch": 0.08, + "learning_rate": 4.6203999910516546e-05, + "loss": 0.297, "step": 34950 }, { - "epoch": 0.31, - "learning_rate": 3.470948563192506e-05, - "loss": 0.28, + "epoch": 0.08, + "learning_rate": 4.6202881367307224e-05, + "loss": 0.2913, "step": 34960 }, { - "epoch": 0.31, - "learning_rate": 3.470498153319521e-05, - "loss": 0.2792, + "epoch": 0.08, + "learning_rate": 4.62017628240979e-05, + "loss": 0.2914, "step": 34970 }, { - "epoch": 0.31, - "learning_rate": 3.4700477434465365e-05, - "loss": 0.2852, + "epoch": 0.08, + "learning_rate": 4.620064428088857e-05, + "loss": 0.2953, "step": 34980 }, { - "epoch": 0.31, - "learning_rate": 3.469597333573552e-05, - "loss": 0.2842, + "epoch": 0.08, + "learning_rate": 4.619952573767925e-05, + "loss": 0.2942, "step": 34990 }, { - "epoch": 0.31, - "learning_rate": 3.469146923700567e-05, - "loss": 0.2798, + "epoch": 0.08, + "learning_rate": 4.619840719446992e-05, + "loss": 0.2932, "step": 35000 }, { - "epoch": 0.31, - "learning_rate": 3.468696513827584e-05, - "loss": 0.2825, + "epoch": 0.08, + "learning_rate": 4.61972886512606e-05, + "loss": 0.2972, "step": 35010 }, { - "epoch": 0.31, - "learning_rate": 3.468246103954599e-05, - "loss": 0.2879, + "epoch": 0.08, + "learning_rate": 4.619617010805128e-05, + "loss": 0.2937, "step": 35020 }, { - "epoch": 0.31, - "learning_rate": 3.467795694081614e-05, - "loss": 0.2776, + "epoch": 0.08, + "learning_rate": 4.619505156484195e-05, + "loss": 0.2955, "step": 35030 }, { - "epoch": 0.31, - "learning_rate": 3.46734528420863e-05, - "loss": 0.2774, + "epoch": 0.08, + "learning_rate": 4.619393302163263e-05, + "loss": 0.2907, "step": 35040 }, { - "epoch": 0.31, - "learning_rate": 3.4668948743356454e-05, - "loss": 0.2794, + "epoch": 0.08, + "learning_rate": 4.6192814478423305e-05, + "loss": 0.2923, "step": 35050 }, { - "epoch": 0.31, - "learning_rate": 3.466444464462661e-05, - "loss": 0.2759, + "epoch": 0.08, + "learning_rate": 4.619169593521398e-05, + "loss": 0.2929, "step": 35060 }, { - "epoch": 0.31, - "learning_rate": 3.465994054589677e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.619057739200466e-05, + "loss": 0.2919, "step": 35070 }, { - "epoch": 0.31, - "learning_rate": 3.465543644716692e-05, - "loss": 0.2828, + "epoch": 0.08, + "learning_rate": 4.618945884879533e-05, + "loss": 0.2844, "step": 35080 }, { - "epoch": 0.31, - "learning_rate": 3.4650932348437084e-05, - "loss": 0.2756, + "epoch": 0.08, + "learning_rate": 4.618834030558601e-05, + "loss": 0.2911, "step": 35090 }, { - "epoch": 0.31, - "learning_rate": 3.4646428249707235e-05, - "loss": 0.2726, + "epoch": 0.08, + "learning_rate": 4.618722176237668e-05, + "loss": 0.2916, "step": 35100 }, { - "epoch": 0.31, - "learning_rate": 3.464192415097739e-05, - "loss": 0.2828, + "epoch": 0.08, + "learning_rate": 4.618610321916736e-05, + "loss": 0.2939, "step": 35110 }, { - "epoch": 0.31, - "learning_rate": 3.463742005224755e-05, - "loss": 0.2784, + "epoch": 0.08, + "learning_rate": 4.618498467595803e-05, + "loss": 0.2959, "step": 35120 }, { - "epoch": 0.31, - "learning_rate": 3.46329159535177e-05, - "loss": 0.2858, + "epoch": 0.08, + "learning_rate": 4.618386613274871e-05, + "loss": 0.2853, "step": 35130 }, { - "epoch": 0.31, - "learning_rate": 3.4628862264660844e-05, - "loss": 0.2844, + "epoch": 0.08, + "learning_rate": 4.6182747589539386e-05, + "loss": 0.2901, "step": 35140 }, { - "epoch": 0.31, - "learning_rate": 3.4624358165930995e-05, - "loss": 0.2861, + "epoch": 0.08, + "learning_rate": 4.618162904633006e-05, + "loss": 0.291, "step": 35150 }, { - "epoch": 0.31, - "learning_rate": 3.461985406720116e-05, - "loss": 0.2826, + "epoch": 0.08, + "learning_rate": 4.618051050312074e-05, + "loss": 0.2852, "step": 35160 }, { - "epoch": 0.31, - "learning_rate": 3.461534996847131e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.617939195991141e-05, + "loss": 0.2894, "step": 35170 }, { - "epoch": 0.31, - "learning_rate": 3.461084586974147e-05, - "loss": 0.2796, + "epoch": 0.08, + "learning_rate": 4.617827341670209e-05, + "loss": 0.2925, "step": 35180 }, { - "epoch": 0.31, - "learning_rate": 3.4606341771011625e-05, - "loss": 0.2879, + "epoch": 0.08, + "learning_rate": 4.617715487349277e-05, + "loss": 0.2942, "step": 35190 }, { - "epoch": 0.31, - "learning_rate": 3.4601837672281776e-05, - "loss": 0.2807, + "epoch": 0.08, + "learning_rate": 4.617603633028344e-05, + "loss": 0.2904, "step": 35200 }, { - "epoch": 0.31, - "learning_rate": 3.459733357355193e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.617491778707412e-05, + "loss": 0.2879, "step": 35210 }, { - "epoch": 0.31, - "learning_rate": 3.459282947482209e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.617379924386479e-05, + "loss": 0.2909, "step": 35220 }, { - "epoch": 0.31, - "learning_rate": 3.458832537609225e-05, - "loss": 0.277, + "epoch": 0.08, + "learning_rate": 4.617268070065547e-05, + "loss": 0.2908, "step": 35230 }, { - "epoch": 0.31, - "learning_rate": 3.45838212773624e-05, - "loss": 0.283, + "epoch": 0.08, + "learning_rate": 4.6171562157446145e-05, + "loss": 0.2953, "step": 35240 }, { - "epoch": 0.31, - "learning_rate": 3.4579317178632556e-05, - "loss": 0.2809, + "epoch": 0.08, + "learning_rate": 4.6170443614236816e-05, + "loss": 0.2873, "step": 35250 }, { - "epoch": 0.31, - "learning_rate": 3.4574813079902714e-05, - "loss": 0.2848, + "epoch": 0.08, + "learning_rate": 4.6169325071027494e-05, + "loss": 0.2922, "step": 35260 }, { - "epoch": 0.31, - "learning_rate": 3.4570308981172864e-05, - "loss": 0.272, + "epoch": 0.08, + "learning_rate": 4.616820652781817e-05, + "loss": 0.2895, "step": 35270 }, { - "epoch": 0.31, - "learning_rate": 3.456580488244303e-05, - "loss": 0.2791, + "epoch": 0.08, + "learning_rate": 4.616708798460885e-05, + "loss": 0.2922, "step": 35280 }, { - "epoch": 0.32, - "learning_rate": 3.456130078371318e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.616596944139953e-05, + "loss": 0.2895, "step": 35290 }, { - "epoch": 0.32, - "learning_rate": 3.455679668498334e-05, - "loss": 0.2871, + "epoch": 0.08, + "learning_rate": 4.61648508981902e-05, + "loss": 0.2909, "step": 35300 }, { - "epoch": 0.32, - "learning_rate": 3.4552292586253494e-05, - "loss": 0.2779, + "epoch": 0.08, + "learning_rate": 4.616373235498088e-05, + "loss": 0.2941, "step": 35310 }, { - "epoch": 0.32, - "learning_rate": 3.4547788487523645e-05, - "loss": 0.2822, + "epoch": 0.08, + "learning_rate": 4.616261381177155e-05, + "loss": 0.2875, "step": 35320 }, { - "epoch": 0.32, - "learning_rate": 3.454328438879381e-05, - "loss": 0.2824, + "epoch": 0.08, + "learning_rate": 4.6161495268562226e-05, + "loss": 0.2919, "step": 35330 }, { - "epoch": 0.32, - "learning_rate": 3.453878029006396e-05, - "loss": 0.2815, + "epoch": 0.08, + "learning_rate": 4.6160376725352904e-05, + "loss": 0.2946, "step": 35340 }, { - "epoch": 0.32, - "learning_rate": 3.453427619133411e-05, - "loss": 0.2781, + "epoch": 0.08, + "learning_rate": 4.6159258182143575e-05, + "loss": 0.2872, "step": 35350 }, { - "epoch": 0.32, - "learning_rate": 3.4529772092604275e-05, - "loss": 0.2874, + "epoch": 0.08, + "learning_rate": 4.615813963893425e-05, + "loss": 0.2889, "step": 35360 }, { - "epoch": 0.32, - "learning_rate": 3.4525267993874426e-05, - "loss": 0.2812, + "epoch": 0.08, + "learning_rate": 4.615702109572493e-05, + "loss": 0.2877, "step": 35370 }, { - "epoch": 0.32, - "learning_rate": 3.452076389514458e-05, - "loss": 0.2793, + "epoch": 0.08, + "learning_rate": 4.615590255251561e-05, + "loss": 0.2932, "step": 35380 }, { - "epoch": 0.32, - "learning_rate": 3.451625979641474e-05, - "loss": 0.285, + "epoch": 0.08, + "learning_rate": 4.615478400930629e-05, + "loss": 0.2916, "step": 35390 }, { - "epoch": 0.32, - "learning_rate": 3.451175569768489e-05, - "loss": 0.2782, + "epoch": 0.08, + "learning_rate": 4.615366546609696e-05, + "loss": 0.2939, "step": 35400 }, { - "epoch": 0.32, - "learning_rate": 3.450725159895505e-05, - "loss": 0.2789, + "epoch": 0.08, + "learning_rate": 4.6152546922887636e-05, + "loss": 0.2939, "step": 35410 }, { - "epoch": 0.32, - "learning_rate": 3.4502747500225207e-05, - "loss": 0.2798, + "epoch": 0.08, + "learning_rate": 4.615142837967831e-05, + "loss": 0.2834, "step": 35420 }, { - "epoch": 0.32, - "learning_rate": 3.4498243401495364e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.6150309836468985e-05, + "loss": 0.287, "step": 35430 }, { - "epoch": 0.32, - "learning_rate": 3.449373930276552e-05, - "loss": 0.2799, + "epoch": 0.08, + "learning_rate": 4.6149191293259656e-05, + "loss": 0.2885, "step": 35440 }, { - "epoch": 0.32, - "learning_rate": 3.448923520403567e-05, - "loss": 0.2832, + "epoch": 0.08, + "learning_rate": 4.6148072750050334e-05, + "loss": 0.2883, "step": 35450 }, { - "epoch": 0.32, - "learning_rate": 3.448473110530583e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.614695420684101e-05, + "loss": 0.2873, "step": 35460 }, { - "epoch": 0.32, - "learning_rate": 3.448022700657599e-05, - "loss": 0.2832, + "epoch": 0.08, + "learning_rate": 4.614583566363169e-05, + "loss": 0.2898, "step": 35470 }, { - "epoch": 0.32, - "learning_rate": 3.4475722907846145e-05, - "loss": 0.2773, + "epoch": 0.08, + "learning_rate": 4.614471712042237e-05, + "loss": 0.2942, "step": 35480 }, { - "epoch": 0.32, - "learning_rate": 3.4471218809116295e-05, - "loss": 0.2832, + "epoch": 0.08, + "learning_rate": 4.614359857721304e-05, + "loss": 0.2828, "step": 35490 }, { - "epoch": 0.32, - "learning_rate": 3.446671471038645e-05, - "loss": 0.2722, + "epoch": 0.08, + "learning_rate": 4.614248003400372e-05, + "loss": 0.2842, "step": 35500 }, { - "epoch": 0.32, - "learning_rate": 3.446221061165661e-05, - "loss": 0.278, + "epoch": 0.08, + "learning_rate": 4.6141361490794395e-05, + "loss": 0.2887, "step": 35510 }, { - "epoch": 0.32, - "learning_rate": 3.445770651292676e-05, - "loss": 0.2772, + "epoch": 0.08, + "learning_rate": 4.6140242947585066e-05, + "loss": 0.2866, "step": 35520 }, { - "epoch": 0.32, - "learning_rate": 3.4453202414196925e-05, - "loss": 0.278, + "epoch": 0.08, + "learning_rate": 4.6139124404375744e-05, + "loss": 0.2932, "step": 35530 }, { - "epoch": 0.32, - "learning_rate": 3.4448698315467076e-05, - "loss": 0.2745, + "epoch": 0.08, + "learning_rate": 4.6138005861166415e-05, + "loss": 0.2875, "step": 35540 }, { - "epoch": 0.32, - "learning_rate": 3.444419421673723e-05, - "loss": 0.2813, + "epoch": 0.08, + "learning_rate": 4.613688731795709e-05, + "loss": 0.2892, "step": 35550 }, { - "epoch": 0.32, - "learning_rate": 3.443969011800739e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.613576877474777e-05, + "loss": 0.29, "step": 35560 }, { - "epoch": 0.32, - "learning_rate": 3.443518601927754e-05, - "loss": 0.2811, + "epoch": 0.08, + "learning_rate": 4.613465023153844e-05, + "loss": 0.2897, "step": 35570 }, { - "epoch": 0.32, - "learning_rate": 3.4430681920547706e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.613353168832913e-05, + "loss": 0.2892, "step": 35580 }, { - "epoch": 0.32, - "learning_rate": 3.442617782181786e-05, - "loss": 0.2736, + "epoch": 0.08, + "learning_rate": 4.61324131451198e-05, + "loss": 0.294, "step": 35590 }, { - "epoch": 0.32, - "learning_rate": 3.442167372308801e-05, - "loss": 0.2805, + "epoch": 0.08, + "learning_rate": 4.6131294601910476e-05, + "loss": 0.2854, "step": 35600 }, { - "epoch": 0.32, - "learning_rate": 3.441716962435817e-05, - "loss": 0.2832, + "epoch": 0.08, + "learning_rate": 4.6130176058701154e-05, + "loss": 0.2899, "step": 35610 }, { - "epoch": 0.32, - "learning_rate": 3.441266552562832e-05, - "loss": 0.2765, + "epoch": 0.08, + "learning_rate": 4.6129057515491825e-05, + "loss": 0.2887, "step": 35620 }, { - "epoch": 0.32, - "learning_rate": 3.440816142689848e-05, - "loss": 0.2764, + "epoch": 0.08, + "learning_rate": 4.61279389722825e-05, + "loss": 0.2903, "step": 35630 }, { - "epoch": 0.32, - "learning_rate": 3.440365732816864e-05, - "loss": 0.2715, + "epoch": 0.08, + "learning_rate": 4.6126820429073174e-05, + "loss": 0.2869, "step": 35640 }, { - "epoch": 0.32, - "learning_rate": 3.439915322943879e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.612570188586385e-05, + "loss": 0.2889, "step": 35650 }, { - "epoch": 0.32, - "learning_rate": 3.4394649130708946e-05, - "loss": 0.2769, + "epoch": 0.08, + "learning_rate": 4.612458334265453e-05, + "loss": 0.2908, "step": 35660 }, { - "epoch": 0.32, - "learning_rate": 3.43901450319791e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.61234647994452e-05, + "loss": 0.2921, "step": 35670 }, { - "epoch": 0.32, - "learning_rate": 3.438564093324926e-05, - "loss": 0.2827, + "epoch": 0.08, + "learning_rate": 4.612234625623588e-05, + "loss": 0.2848, "step": 35680 }, { - "epoch": 0.32, - "learning_rate": 3.438113683451941e-05, - "loss": 0.2811, + "epoch": 0.08, + "learning_rate": 4.612122771302656e-05, + "loss": 0.2927, "step": 35690 }, { - "epoch": 0.32, - "learning_rate": 3.437663273578957e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.6120109169817235e-05, + "loss": 0.2911, "step": 35700 }, { - "epoch": 0.32, - "learning_rate": 3.4372128637059726e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.611899062660791e-05, + "loss": 0.2872, "step": 35710 }, { - "epoch": 0.32, - "learning_rate": 3.4367624538329884e-05, - "loss": 0.2791, + "epoch": 0.08, + "learning_rate": 4.6117872083398584e-05, + "loss": 0.2928, "step": 35720 }, { - "epoch": 0.32, - "learning_rate": 3.436312043960004e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.611675354018926e-05, + "loss": 0.2943, "step": 35730 }, { - "epoch": 0.32, - "learning_rate": 3.435861634087019e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.611563499697993e-05, + "loss": 0.2852, "step": 35740 }, { - "epoch": 0.32, - "learning_rate": 3.435411224214035e-05, - "loss": 0.2775, + "epoch": 0.08, + "learning_rate": 4.611451645377061e-05, + "loss": 0.2888, "step": 35750 }, { - "epoch": 0.32, - "learning_rate": 3.434960814341051e-05, - "loss": 0.2726, + "epoch": 0.08, + "learning_rate": 4.611339791056128e-05, + "loss": 0.2878, "step": 35760 }, { - "epoch": 0.32, - "learning_rate": 3.434510404468066e-05, - "loss": 0.2706, + "epoch": 0.08, + "learning_rate": 4.611227936735196e-05, + "loss": 0.2927, "step": 35770 }, { - "epoch": 0.32, - "learning_rate": 3.434059994595082e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.611116082414264e-05, + "loss": 0.2875, "step": 35780 }, { - "epoch": 0.32, - "learning_rate": 3.433609584722097e-05, - "loss": 0.2777, + "epoch": 0.08, + "learning_rate": 4.6110042280933316e-05, + "loss": 0.2904, "step": 35790 }, { - "epoch": 0.32, - "learning_rate": 3.4331591748491123e-05, - "loss": 0.282, + "epoch": 0.08, + "learning_rate": 4.6108923737723994e-05, + "loss": 0.2917, "step": 35800 }, { - "epoch": 0.32, - "learning_rate": 3.432708764976129e-05, - "loss": 0.2747, + "epoch": 0.08, + "learning_rate": 4.6107805194514665e-05, + "loss": 0.289, "step": 35810 }, { - "epoch": 0.32, - "learning_rate": 3.432258355103144e-05, - "loss": 0.2741, + "epoch": 0.08, + "learning_rate": 4.610668665130534e-05, + "loss": 0.2866, "step": 35820 }, { - "epoch": 0.32, - "learning_rate": 3.4318079452301596e-05, - "loss": 0.2727, + "epoch": 0.08, + "learning_rate": 4.610556810809602e-05, + "loss": 0.2867, "step": 35830 }, { - "epoch": 0.32, - "learning_rate": 3.4313575353571753e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.610444956488669e-05, + "loss": 0.2897, "step": 35840 }, { - "epoch": 0.32, - "learning_rate": 3.4309071254841904e-05, - "loss": 0.2742, + "epoch": 0.08, + "learning_rate": 4.610333102167737e-05, + "loss": 0.2864, "step": 35850 }, { - "epoch": 0.32, - "learning_rate": 3.430456715611207e-05, - "loss": 0.276, + "epoch": 0.08, + "learning_rate": 4.610221247846804e-05, + "loss": 0.2893, "step": 35860 }, { - "epoch": 0.32, - "learning_rate": 3.430006305738222e-05, - "loss": 0.2771, + "epoch": 0.08, + "learning_rate": 4.610109393525872e-05, + "loss": 0.2836, "step": 35870 }, { - "epoch": 0.32, - "learning_rate": 3.429555895865238e-05, - "loss": 0.269, + "epoch": 0.08, + "learning_rate": 4.60999753920494e-05, + "loss": 0.285, "step": 35880 }, { - "epoch": 0.32, - "learning_rate": 3.4291054859922534e-05, - "loss": 0.2727, + "epoch": 0.08, + "learning_rate": 4.6098856848840075e-05, + "loss": 0.2914, "step": 35890 }, { - "epoch": 0.32, - "learning_rate": 3.4286550761192685e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.609773830563075e-05, + "loss": 0.2892, "step": 35900 }, { - "epoch": 0.32, - "learning_rate": 3.428204666246284e-05, - "loss": 0.2805, + "epoch": 0.08, + "learning_rate": 4.6096619762421424e-05, + "loss": 0.2862, "step": 35910 }, { - "epoch": 0.32, - "learning_rate": 3.4277542563733e-05, - "loss": 0.278, + "epoch": 0.08, + "learning_rate": 4.60955012192121e-05, + "loss": 0.2932, "step": 35920 }, { - "epoch": 0.32, - "learning_rate": 3.427303846500316e-05, - "loss": 0.2841, + "epoch": 0.08, + "learning_rate": 4.609438267600278e-05, + "loss": 0.2881, "step": 35930 }, { - "epoch": 0.32, - "learning_rate": 3.426853436627331e-05, - "loss": 0.285, + "epoch": 0.08, + "learning_rate": 4.609326413279345e-05, + "loss": 0.2835, "step": 35940 }, { - "epoch": 0.32, - "learning_rate": 3.4264030267543466e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.609214558958413e-05, + "loss": 0.291, "step": 35950 }, { - "epoch": 0.32, - "learning_rate": 3.425952616881362e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.60910270463748e-05, + "loss": 0.2913, "step": 35960 }, { - "epoch": 0.32, - "learning_rate": 3.4255022070083774e-05, - "loss": 0.2755, + "epoch": 0.08, + "learning_rate": 4.608990850316548e-05, + "loss": 0.2918, "step": 35970 }, { - "epoch": 0.32, - "learning_rate": 3.425051797135394e-05, - "loss": 0.2799, + "epoch": 0.08, + "learning_rate": 4.6088789959956156e-05, + "loss": 0.2967, "step": 35980 }, { - "epoch": 0.32, - "learning_rate": 3.424601387262409e-05, - "loss": 0.2823, + "epoch": 0.08, + "learning_rate": 4.6087671416746834e-05, + "loss": 0.2868, "step": 35990 }, { - "epoch": 0.32, - "learning_rate": 3.4241509773894246e-05, - "loss": 0.2811, + "epoch": 0.08, + "learning_rate": 4.608655287353751e-05, + "loss": 0.2872, "step": 36000 }, { - "epoch": 0.32, - "learning_rate": 3.4237005675164404e-05, - "loss": 0.2767, + "epoch": 0.08, + "learning_rate": 4.608543433032818e-05, + "loss": 0.2881, "step": 36010 }, { - "epoch": 0.32, - "learning_rate": 3.4232501576434554e-05, - "loss": 0.2732, + "epoch": 0.08, + "learning_rate": 4.608431578711886e-05, + "loss": 0.2938, "step": 36020 }, { - "epoch": 0.32, - "learning_rate": 3.422799747770471e-05, - "loss": 0.2747, + "epoch": 0.08, + "learning_rate": 4.608319724390954e-05, + "loss": 0.2924, "step": 36030 }, { - "epoch": 0.32, - "learning_rate": 3.422349337897487e-05, - "loss": 0.2803, + "epoch": 0.08, + "learning_rate": 4.608207870070021e-05, + "loss": 0.2848, "step": 36040 }, { - "epoch": 0.32, - "learning_rate": 3.421898928024502e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.608096015749089e-05, + "loss": 0.2916, "step": 36050 }, { - "epoch": 0.32, - "learning_rate": 3.4214485181515184e-05, - "loss": 0.2726, + "epoch": 0.08, + "learning_rate": 4.607984161428156e-05, + "loss": 0.2903, "step": 36060 }, { - "epoch": 0.32, - "learning_rate": 3.4209981082785335e-05, - "loss": 0.2725, + "epoch": 0.08, + "learning_rate": 4.607872307107224e-05, + "loss": 0.2843, "step": 36070 }, { - "epoch": 0.32, - "learning_rate": 3.420547698405549e-05, - "loss": 0.2742, + "epoch": 0.08, + "learning_rate": 4.607760452786291e-05, + "loss": 0.2914, "step": 36080 }, { - "epoch": 0.32, - "learning_rate": 3.420097288532565e-05, - "loss": 0.2737, + "epoch": 0.08, + "learning_rate": 4.6076485984653586e-05, + "loss": 0.29, "step": 36090 }, { - "epoch": 0.32, - "learning_rate": 3.41964687865958e-05, - "loss": 0.2825, + "epoch": 0.08, + "learning_rate": 4.6075367441444264e-05, + "loss": 0.2852, "step": 36100 }, { - "epoch": 0.32, - "learning_rate": 3.419196468786596e-05, - "loss": 0.2801, + "epoch": 0.08, + "learning_rate": 4.607424889823494e-05, + "loss": 0.2907, "step": 36110 }, { - "epoch": 0.32, - "learning_rate": 3.4187460589136116e-05, - "loss": 0.2721, + "epoch": 0.08, + "learning_rate": 4.607313035502562e-05, + "loss": 0.2928, "step": 36120 }, { - "epoch": 0.32, - "learning_rate": 3.418295649040627e-05, - "loss": 0.2671, + "epoch": 0.08, + "learning_rate": 4.607201181181629e-05, + "loss": 0.2871, "step": 36130 }, { - "epoch": 0.32, - "learning_rate": 3.417845239167643e-05, - "loss": 0.2681, + "epoch": 0.08, + "learning_rate": 4.607089326860697e-05, + "loss": 0.2879, "step": 36140 }, { - "epoch": 0.32, - "learning_rate": 3.417394829294658e-05, - "loss": 0.2745, + "epoch": 0.08, + "learning_rate": 4.606977472539765e-05, + "loss": 0.2901, "step": 36150 }, { - "epoch": 0.32, - "learning_rate": 3.416944419421674e-05, - "loss": 0.2771, + "epoch": 0.08, + "learning_rate": 4.606865618218832e-05, + "loss": 0.285, "step": 36160 }, { - "epoch": 0.32, - "learning_rate": 3.4164940095486896e-05, - "loss": 0.2775, + "epoch": 0.08, + "learning_rate": 4.6067537638978996e-05, + "loss": 0.2841, "step": 36170 }, { - "epoch": 0.32, - "learning_rate": 3.4160435996757054e-05, - "loss": 0.2717, + "epoch": 0.08, + "learning_rate": 4.606641909576967e-05, + "loss": 0.2869, "step": 36180 }, { - "epoch": 0.32, - "learning_rate": 3.4155931898027205e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.6065300552560345e-05, + "loss": 0.2957, "step": 36190 }, { - "epoch": 0.32, - "learning_rate": 3.415142779929736e-05, - "loss": 0.2799, + "epoch": 0.08, + "learning_rate": 4.606418200935102e-05, + "loss": 0.2892, "step": 36200 }, { - "epoch": 0.32, - "learning_rate": 3.414692370056752e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.60630634661417e-05, + "loss": 0.2896, "step": 36210 }, { - "epoch": 0.32, - "learning_rate": 3.414241960183767e-05, - "loss": 0.2767, + "epoch": 0.08, + "learning_rate": 4.606194492293238e-05, + "loss": 0.2918, "step": 36220 }, { - "epoch": 0.32, - "learning_rate": 3.4137915503107835e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.606082637972305e-05, + "loss": 0.2931, "step": 36230 }, { - "epoch": 0.32, - "learning_rate": 3.4133411404377985e-05, - "loss": 0.2708, + "epoch": 0.08, + "learning_rate": 4.605970783651373e-05, + "loss": 0.2845, "step": 36240 }, { - "epoch": 0.32, - "learning_rate": 3.4128907305648136e-05, - "loss": 0.2771, + "epoch": 0.08, + "learning_rate": 4.6058589293304406e-05, + "loss": 0.2937, "step": 36250 }, { - "epoch": 0.32, - "learning_rate": 3.41244032069183e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.605747075009508e-05, + "loss": 0.2864, "step": 36260 }, { - "epoch": 0.32, - "learning_rate": 3.411989910818845e-05, - "loss": 0.2733, + "epoch": 0.08, + "learning_rate": 4.6056352206885755e-05, + "loss": 0.2873, "step": 36270 }, { - "epoch": 0.32, - "learning_rate": 3.411539500945861e-05, - "loss": 0.2769, + "epoch": 0.08, + "learning_rate": 4.6055233663676426e-05, + "loss": 0.2877, "step": 36280 }, { - "epoch": 0.32, - "learning_rate": 3.4110890910728766e-05, - "loss": 0.2762, + "epoch": 0.08, + "learning_rate": 4.6054115120467104e-05, + "loss": 0.294, "step": 36290 }, { - "epoch": 0.32, - "learning_rate": 3.410638681199892e-05, - "loss": 0.2779, + "epoch": 0.08, + "learning_rate": 4.605299657725778e-05, + "loss": 0.2961, "step": 36300 }, { - "epoch": 0.32, - "learning_rate": 3.410188271326908e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.605187803404846e-05, + "loss": 0.2963, "step": 36310 }, { - "epoch": 0.32, - "learning_rate": 3.409737861453923e-05, - "loss": 0.2738, + "epoch": 0.08, + "learning_rate": 4.605075949083914e-05, + "loss": 0.2955, "step": 36320 }, { - "epoch": 0.32, - "learning_rate": 3.409287451580939e-05, - "loss": 0.2812, + "epoch": 0.08, + "learning_rate": 4.604964094762981e-05, + "loss": 0.2882, "step": 36330 }, { - "epoch": 0.32, - "learning_rate": 3.408837041707955e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.604852240442049e-05, + "loss": 0.2848, "step": 36340 }, { - "epoch": 0.32, - "learning_rate": 3.40838663183497e-05, - "loss": 0.2767, + "epoch": 0.08, + "learning_rate": 4.6047403861211165e-05, + "loss": 0.2859, "step": 36350 }, { - "epoch": 0.32, - "learning_rate": 3.4079362219619855e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.6046285318001836e-05, + "loss": 0.2867, "step": 36360 }, { - "epoch": 0.32, - "learning_rate": 3.407485812089001e-05, - "loss": 0.2771, + "epoch": 0.08, + "learning_rate": 4.6045166774792514e-05, + "loss": 0.2851, "step": 36370 }, { - "epoch": 0.32, - "learning_rate": 3.407035402216017e-05, - "loss": 0.2817, + "epoch": 0.08, + "learning_rate": 4.6044048231583185e-05, + "loss": 0.2826, "step": 36380 }, { - "epoch": 0.32, - "learning_rate": 3.406584992343032e-05, - "loss": 0.282, + "epoch": 0.08, + "learning_rate": 4.604292968837386e-05, + "loss": 0.2907, "step": 36390 }, { - "epoch": 0.32, - "learning_rate": 3.406134582470048e-05, - "loss": 0.2774, + "epoch": 0.08, + "learning_rate": 4.604181114516454e-05, + "loss": 0.2842, "step": 36400 }, { - "epoch": 0.33, - "learning_rate": 3.4056841725970636e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.604069260195522e-05, + "loss": 0.2873, "step": 36410 }, { - "epoch": 0.33, - "learning_rate": 3.405233762724079e-05, - "loss": 0.2718, + "epoch": 0.08, + "learning_rate": 4.6039574058745897e-05, + "loss": 0.2857, "step": 36420 }, { - "epoch": 0.33, - "learning_rate": 3.404783352851095e-05, - "loss": 0.2769, + "epoch": 0.08, + "learning_rate": 4.603845551553657e-05, + "loss": 0.2915, "step": 36430 }, { - "epoch": 0.33, - "learning_rate": 3.40433294297811e-05, - "loss": 0.2838, + "epoch": 0.08, + "learning_rate": 4.6037336972327246e-05, + "loss": 0.282, "step": 36440 }, { - "epoch": 0.33, - "learning_rate": 3.403882533105126e-05, - "loss": 0.2814, + "epoch": 0.08, + "learning_rate": 4.603621842911792e-05, + "loss": 0.294, "step": 36450 }, { - "epoch": 0.33, - "learning_rate": 3.4034321232321416e-05, - "loss": 0.2765, + "epoch": 0.08, + "learning_rate": 4.6035099885908595e-05, + "loss": 0.2901, "step": 36460 }, { - "epoch": 0.33, - "learning_rate": 3.402981713359157e-05, - "loss": 0.2803, + "epoch": 0.08, + "learning_rate": 4.603398134269927e-05, + "loss": 0.288, "step": 36470 }, { - "epoch": 0.33, - "learning_rate": 3.4025313034861725e-05, - "loss": 0.272, + "epoch": 0.08, + "learning_rate": 4.6032862799489944e-05, + "loss": 0.2868, "step": 36480 }, { - "epoch": 0.33, - "learning_rate": 3.402080893613188e-05, - "loss": 0.2777, + "epoch": 0.08, + "learning_rate": 4.603174425628062e-05, + "loss": 0.2887, "step": 36490 }, { - "epoch": 0.33, - "learning_rate": 3.401630483740203e-05, - "loss": 0.2764, + "epoch": 0.08, + "learning_rate": 4.603062571307129e-05, + "loss": 0.2884, "step": 36500 }, { - "epoch": 0.33, - "learning_rate": 3.40118007386722e-05, - "loss": 0.2717, + "epoch": 0.08, + "learning_rate": 4.602950716986197e-05, + "loss": 0.2875, "step": 36510 }, { - "epoch": 0.33, - "learning_rate": 3.400729663994235e-05, - "loss": 0.2727, + "epoch": 0.08, + "learning_rate": 4.602838862665265e-05, + "loss": 0.2899, "step": 36520 }, { - "epoch": 0.33, - "learning_rate": 3.4002792541212505e-05, - "loss": 0.2808, + "epoch": 0.08, + "learning_rate": 4.602727008344333e-05, + "loss": 0.2859, "step": 36530 }, { - "epoch": 0.33, - "learning_rate": 3.399828844248266e-05, - "loss": 0.2771, + "epoch": 0.08, + "learning_rate": 4.6026151540234005e-05, + "loss": 0.2868, "step": 36540 }, { - "epoch": 0.33, - "learning_rate": 3.3993784343752813e-05, - "loss": 0.2756, + "epoch": 0.08, + "learning_rate": 4.6025032997024676e-05, + "loss": 0.2891, "step": 36550 }, { - "epoch": 0.33, - "learning_rate": 3.398928024502298e-05, - "loss": 0.269, + "epoch": 0.08, + "learning_rate": 4.6023914453815354e-05, + "loss": 0.2845, "step": 36560 }, { - "epoch": 0.33, - "learning_rate": 3.398477614629313e-05, - "loss": 0.2729, + "epoch": 0.08, + "learning_rate": 4.602279591060603e-05, + "loss": 0.2882, "step": 36570 }, { - "epoch": 0.33, - "learning_rate": 3.3980272047563286e-05, - "loss": 0.2727, + "epoch": 0.08, + "learning_rate": 4.60216773673967e-05, + "loss": 0.2861, "step": 36580 }, { - "epoch": 0.33, - "learning_rate": 3.397576794883344e-05, - "loss": 0.2722, + "epoch": 0.08, + "learning_rate": 4.602055882418738e-05, + "loss": 0.2895, "step": 36590 }, { - "epoch": 0.33, - "learning_rate": 3.3971263850103594e-05, - "loss": 0.273, + "epoch": 0.08, + "learning_rate": 4.601944028097805e-05, + "loss": 0.2888, "step": 36600 }, { - "epoch": 0.33, - "learning_rate": 3.396675975137375e-05, - "loss": 0.2772, + "epoch": 0.08, + "learning_rate": 4.601832173776873e-05, + "loss": 0.2894, "step": 36610 }, { - "epoch": 0.33, - "learning_rate": 3.396225565264391e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.601720319455941e-05, + "loss": 0.286, "step": 36620 }, { - "epoch": 0.33, - "learning_rate": 3.3957751553914067e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.6016084651350086e-05, + "loss": 0.2908, "step": 36630 }, { - "epoch": 0.33, - "learning_rate": 3.395324745518422e-05, - "loss": 0.2682, + "epoch": 0.08, + "learning_rate": 4.6014966108140764e-05, + "loss": 0.2848, "step": 36640 }, { - "epoch": 0.33, - "learning_rate": 3.3948743356454375e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.6013847564931435e-05, + "loss": 0.2858, "step": 36650 }, { - "epoch": 0.33, - "learning_rate": 3.394423925772453e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.601272902172211e-05, + "loss": 0.2835, "step": 36660 }, { - "epoch": 0.33, - "learning_rate": 3.393973515899468e-05, - "loss": 0.2749, + "epoch": 0.08, + "learning_rate": 4.6011610478512784e-05, + "loss": 0.288, "step": 36670 }, { - "epoch": 0.33, - "learning_rate": 3.393523106026484e-05, - "loss": 0.2708, + "epoch": 0.08, + "learning_rate": 4.601049193530346e-05, + "loss": 0.2959, "step": 36680 }, { - "epoch": 0.33, - "learning_rate": 3.3930726961535e-05, - "loss": 0.2728, + "epoch": 0.08, + "learning_rate": 4.600937339209414e-05, + "loss": 0.2878, "step": 36690 }, { - "epoch": 0.33, - "learning_rate": 3.3926222862805155e-05, - "loss": 0.2783, + "epoch": 0.08, + "learning_rate": 4.600825484888481e-05, + "loss": 0.2923, "step": 36700 }, { - "epoch": 0.33, - "learning_rate": 3.392171876407531e-05, - "loss": 0.2717, + "epoch": 0.08, + "learning_rate": 4.600713630567549e-05, + "loss": 0.2872, "step": 36710 }, { - "epoch": 0.33, - "learning_rate": 3.3917214665345464e-05, - "loss": 0.2721, + "epoch": 0.08, + "learning_rate": 4.6006017762466167e-05, + "loss": 0.288, "step": 36720 }, { - "epoch": 0.33, - "learning_rate": 3.391271056661562e-05, - "loss": 0.2732, + "epoch": 0.08, + "learning_rate": 4.6004899219256845e-05, + "loss": 0.2893, "step": 36730 }, { - "epoch": 0.33, - "learning_rate": 3.390820646788578e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.600378067604752e-05, + "loss": 0.2871, "step": 36740 }, { - "epoch": 0.33, - "learning_rate": 3.390370236915593e-05, - "loss": 0.2769, + "epoch": 0.08, + "learning_rate": 4.6002662132838194e-05, + "loss": 0.2943, "step": 36750 }, { - "epoch": 0.33, - "learning_rate": 3.3899198270426094e-05, - "loss": 0.277, + "epoch": 0.08, + "learning_rate": 4.600154358962887e-05, + "loss": 0.2849, "step": 36760 }, { - "epoch": 0.33, - "learning_rate": 3.3894694171696244e-05, - "loss": 0.2732, + "epoch": 0.08, + "learning_rate": 4.600042504641954e-05, + "loss": 0.2856, "step": 36770 }, { - "epoch": 0.33, - "learning_rate": 3.38901900729664e-05, - "loss": 0.2719, + "epoch": 0.08, + "learning_rate": 4.599930650321022e-05, + "loss": 0.2878, "step": 36780 }, { - "epoch": 0.33, - "learning_rate": 3.388568597423656e-05, - "loss": 0.2778, + "epoch": 0.08, + "learning_rate": 4.59981879600009e-05, + "loss": 0.287, "step": 36790 }, { - "epoch": 0.33, - "learning_rate": 3.388118187550671e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.599706941679157e-05, + "loss": 0.2916, "step": 36800 }, { - "epoch": 0.33, - "learning_rate": 3.387667777677687e-05, - "loss": 0.2758, + "epoch": 0.08, + "learning_rate": 4.599595087358225e-05, + "loss": 0.2878, "step": 36810 }, { - "epoch": 0.33, - "learning_rate": 3.3872173678047025e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.5994832330372926e-05, + "loss": 0.2851, "step": 36820 }, { - "epoch": 0.33, - "learning_rate": 3.386766957931718e-05, - "loss": 0.2696, + "epoch": 0.08, + "learning_rate": 4.5993713787163603e-05, + "loss": 0.2894, "step": 36830 }, { - "epoch": 0.33, - "learning_rate": 3.386316548058734e-05, - "loss": 0.2713, + "epoch": 0.08, + "learning_rate": 4.599259524395428e-05, + "loss": 0.2811, "step": 36840 }, { - "epoch": 0.33, - "learning_rate": 3.385866138185749e-05, - "loss": 0.2716, + "epoch": 0.08, + "learning_rate": 4.599147670074495e-05, + "loss": 0.287, "step": 36850 }, { - "epoch": 0.33, - "learning_rate": 3.385415728312765e-05, - "loss": 0.274, + "epoch": 0.08, + "learning_rate": 4.599035815753563e-05, + "loss": 0.2846, "step": 36860 }, { - "epoch": 0.33, - "learning_rate": 3.3849653184397806e-05, - "loss": 0.2737, + "epoch": 0.08, + "learning_rate": 4.598935146864723e-05, + "loss": 0.2852, "step": 36870 }, { - "epoch": 0.33, - "learning_rate": 3.384514908566796e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.598823292543791e-05, + "loss": 0.2828, "step": 36880 }, { - "epoch": 0.33, - "learning_rate": 3.3840644986938114e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.598711438222859e-05, + "loss": 0.2855, "step": 36890 }, { - "epoch": 0.33, - "learning_rate": 3.383614088820827e-05, - "loss": 0.2749, + "epoch": 0.08, + "learning_rate": 4.5985995839019266e-05, + "loss": 0.2883, "step": 36900 }, { - "epoch": 0.33, - "learning_rate": 3.383163678947843e-05, - "loss": 0.2711, + "epoch": 0.08, + "learning_rate": 4.5984877295809944e-05, + "loss": 0.2843, "step": 36910 }, { - "epoch": 0.33, - "learning_rate": 3.382713269074858e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.5983758752600615e-05, + "loss": 0.283, "step": 36920 }, { - "epoch": 0.33, - "learning_rate": 3.382262859201874e-05, - "loss": 0.2701, + "epoch": 0.08, + "learning_rate": 4.598264020939129e-05, + "loss": 0.2886, "step": 36930 }, { - "epoch": 0.33, - "learning_rate": 3.3818124493288895e-05, - "loss": 0.2788, + "epoch": 0.08, + "learning_rate": 4.5981521666181964e-05, + "loss": 0.2862, "step": 36940 }, { - "epoch": 0.33, - "learning_rate": 3.3813620394559045e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.598040312297264e-05, + "loss": 0.2895, "step": 36950 }, { - "epoch": 0.33, - "learning_rate": 3.380911629582921e-05, - "loss": 0.2674, + "epoch": 0.08, + "learning_rate": 4.597928457976332e-05, + "loss": 0.2883, "step": 36960 }, { - "epoch": 0.33, - "learning_rate": 3.380461219709936e-05, - "loss": 0.273, + "epoch": 0.08, + "learning_rate": 4.597816603655399e-05, + "loss": 0.2769, "step": 36970 }, { - "epoch": 0.33, - "learning_rate": 3.380010809836952e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.597704749334467e-05, + "loss": 0.2885, "step": 36980 }, { - "epoch": 0.33, - "learning_rate": 3.3795603999639675e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.597592895013535e-05, + "loss": 0.2878, "step": 36990 }, { - "epoch": 0.33, - "learning_rate": 3.3791099900909826e-05, - "loss": 0.2685, + "epoch": 0.08, + "learning_rate": 4.5974810406926025e-05, + "loss": 0.2814, "step": 37000 }, { - "epoch": 0.33, - "learning_rate": 3.378659580217999e-05, - "loss": 0.2723, + "epoch": 0.08, + "learning_rate": 4.59736918637167e-05, + "loss": 0.2833, "step": 37010 }, { - "epoch": 0.33, - "learning_rate": 3.378209170345014e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.5972573320507374e-05, + "loss": 0.2836, "step": 37020 }, { - "epoch": 0.33, - "learning_rate": 3.37775876047203e-05, - "loss": 0.2738, + "epoch": 0.08, + "learning_rate": 4.597145477729805e-05, + "loss": 0.2898, "step": 37030 }, { - "epoch": 0.33, - "learning_rate": 3.3773083505990456e-05, - "loss": 0.2683, + "epoch": 0.08, + "learning_rate": 4.597033623408872e-05, + "loss": 0.2881, "step": 37040 }, { - "epoch": 0.33, - "learning_rate": 3.376857940726061e-05, - "loss": 0.2773, + "epoch": 0.08, + "learning_rate": 4.59692176908794e-05, + "loss": 0.2889, "step": 37050 }, { - "epoch": 0.33, - "learning_rate": 3.3764075308530764e-05, - "loss": 0.2732, + "epoch": 0.08, + "learning_rate": 4.596809914767007e-05, + "loss": 0.2823, "step": 37060 }, { - "epoch": 0.33, - "learning_rate": 3.375957120980092e-05, - "loss": 0.2767, + "epoch": 0.08, + "learning_rate": 4.596698060446075e-05, + "loss": 0.2928, "step": 37070 }, { - "epoch": 0.33, - "learning_rate": 3.375506711107108e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.596586206125143e-05, + "loss": 0.2813, "step": 37080 }, { - "epoch": 0.33, - "learning_rate": 3.375056301234123e-05, - "loss": 0.2746, + "epoch": 0.08, + "learning_rate": 4.59647435180421e-05, + "loss": 0.2921, "step": 37090 }, { - "epoch": 0.33, - "learning_rate": 3.374605891361139e-05, - "loss": 0.2753, + "epoch": 0.08, + "learning_rate": 4.596362497483278e-05, + "loss": 0.2929, "step": 37100 }, { - "epoch": 0.33, - "learning_rate": 3.3741554814881545e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.5962506431623455e-05, + "loss": 0.2813, "step": 37110 }, { - "epoch": 0.33, - "learning_rate": 3.37370507161517e-05, - "loss": 0.277, + "epoch": 0.08, + "learning_rate": 4.596138788841413e-05, + "loss": 0.2818, "step": 37120 }, { - "epoch": 0.33, - "learning_rate": 3.373254661742185e-05, - "loss": 0.2759, + "epoch": 0.08, + "learning_rate": 4.596026934520481e-05, + "loss": 0.2911, "step": 37130 }, { - "epoch": 0.33, - "learning_rate": 3.372804251869201e-05, - "loss": 0.2779, + "epoch": 0.08, + "learning_rate": 4.595915080199548e-05, + "loss": 0.2889, "step": 37140 }, { - "epoch": 0.33, - "learning_rate": 3.372353841996217e-05, - "loss": 0.2726, + "epoch": 0.08, + "learning_rate": 4.595803225878616e-05, + "loss": 0.286, "step": 37150 }, { - "epoch": 0.33, - "learning_rate": 3.3719034321232326e-05, - "loss": 0.2747, + "epoch": 0.08, + "learning_rate": 4.595691371557683e-05, + "loss": 0.2935, "step": 37160 }, { - "epoch": 0.33, - "learning_rate": 3.3714530222502476e-05, - "loss": 0.272, + "epoch": 0.08, + "learning_rate": 4.595579517236751e-05, + "loss": 0.281, "step": 37170 }, { - "epoch": 0.33, - "learning_rate": 3.3710026123772634e-05, - "loss": 0.2729, + "epoch": 0.08, + "learning_rate": 4.595467662915819e-05, + "loss": 0.2859, "step": 37180 }, { - "epoch": 0.33, - "learning_rate": 3.370552202504279e-05, - "loss": 0.2722, + "epoch": 0.08, + "learning_rate": 4.595355808594886e-05, + "loss": 0.2886, "step": 37190 }, { - "epoch": 0.33, - "learning_rate": 3.370101792631294e-05, - "loss": 0.274, + "epoch": 0.08, + "learning_rate": 4.5952439542739536e-05, + "loss": 0.2791, "step": 37200 }, { - "epoch": 0.33, - "learning_rate": 3.3696513827583106e-05, - "loss": 0.2725, + "epoch": 0.08, + "learning_rate": 4.5951320999530214e-05, + "loss": 0.2836, "step": 37210 }, { - "epoch": 0.33, - "learning_rate": 3.369200972885326e-05, - "loss": 0.2759, + "epoch": 0.08, + "learning_rate": 4.595020245632089e-05, + "loss": 0.2818, "step": 37220 }, { - "epoch": 0.33, - "learning_rate": 3.3687505630123414e-05, - "loss": 0.2716, + "epoch": 0.08, + "learning_rate": 4.594908391311157e-05, + "loss": 0.2853, "step": 37230 }, { - "epoch": 0.33, - "learning_rate": 3.368300153139357e-05, - "loss": 0.2745, + "epoch": 0.08, + "learning_rate": 4.594796536990224e-05, + "loss": 0.2915, "step": 37240 }, { - "epoch": 0.33, - "learning_rate": 3.367849743266372e-05, - "loss": 0.2694, + "epoch": 0.08, + "learning_rate": 4.594684682669292e-05, + "loss": 0.2831, "step": 37250 }, { - "epoch": 0.33, - "learning_rate": 3.367399333393388e-05, - "loss": 0.2793, + "epoch": 0.08, + "learning_rate": 4.594572828348359e-05, + "loss": 0.2901, "step": 37260 }, { - "epoch": 0.33, - "learning_rate": 3.366948923520404e-05, - "loss": 0.279, + "epoch": 0.08, + "learning_rate": 4.594460974027427e-05, + "loss": 0.2951, "step": 37270 }, { - "epoch": 0.33, - "learning_rate": 3.366543554634718e-05, - "loss": 0.2721, + "epoch": 0.08, + "learning_rate": 4.5943491197064946e-05, + "loss": 0.2846, "step": 37280 }, { - "epoch": 0.33, - "learning_rate": 3.366093144761733e-05, - "loss": 0.2765, + "epoch": 0.08, + "learning_rate": 4.594237265385562e-05, + "loss": 0.2921, "step": 37290 }, { - "epoch": 0.33, - "learning_rate": 3.365642734888749e-05, - "loss": 0.2657, + "epoch": 0.08, + "learning_rate": 4.5941254110646295e-05, + "loss": 0.2832, "step": 37300 }, { - "epoch": 0.33, - "learning_rate": 3.365192325015765e-05, - "loss": 0.2728, + "epoch": 0.08, + "learning_rate": 4.594013556743697e-05, + "loss": 0.287, "step": 37310 }, { - "epoch": 0.33, - "learning_rate": 3.36474191514278e-05, - "loss": 0.2705, + "epoch": 0.08, + "learning_rate": 4.593901702422765e-05, + "loss": 0.2845, "step": 37320 }, { - "epoch": 0.33, - "learning_rate": 3.3642915052697955e-05, - "loss": 0.2723, + "epoch": 0.08, + "learning_rate": 4.593789848101833e-05, + "loss": 0.2858, "step": 37330 }, { - "epoch": 0.33, - "learning_rate": 3.363841095396811e-05, - "loss": 0.2743, + "epoch": 0.08, + "learning_rate": 4.5936779937809e-05, + "loss": 0.2867, "step": 37340 }, { - "epoch": 0.33, - "learning_rate": 3.363390685523827e-05, - "loss": 0.2668, + "epoch": 0.08, + "learning_rate": 4.593566139459968e-05, + "loss": 0.2858, "step": 37350 }, { - "epoch": 0.33, - "learning_rate": 3.362940275650843e-05, - "loss": 0.2755, + "epoch": 0.08, + "learning_rate": 4.593454285139035e-05, + "loss": 0.2875, "step": 37360 }, { - "epoch": 0.33, - "learning_rate": 3.362489865777858e-05, - "loss": 0.28, + "epoch": 0.08, + "learning_rate": 4.593342430818103e-05, + "loss": 0.2861, "step": 37370 }, { - "epoch": 0.33, - "learning_rate": 3.3620394559048736e-05, - "loss": 0.2691, + "epoch": 0.08, + "learning_rate": 4.59323057649717e-05, + "loss": 0.2837, "step": 37380 }, { - "epoch": 0.33, - "learning_rate": 3.3615890460318894e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.5931187221762376e-05, + "loss": 0.2856, "step": 37390 }, { - "epoch": 0.33, - "learning_rate": 3.361138636158905e-05, - "loss": 0.2654, + "epoch": 0.08, + "learning_rate": 4.5930068678553054e-05, + "loss": 0.2867, "step": 37400 }, { - "epoch": 0.33, - "learning_rate": 3.36068822628592e-05, - "loss": 0.2687, + "epoch": 0.08, + "learning_rate": 4.592895013534373e-05, + "loss": 0.2837, "step": 37410 }, { - "epoch": 0.33, - "learning_rate": 3.360237816412936e-05, - "loss": 0.2716, + "epoch": 0.08, + "learning_rate": 4.592783159213441e-05, + "loss": 0.2859, "step": 37420 }, { - "epoch": 0.33, - "learning_rate": 3.359787406539952e-05, - "loss": 0.2682, + "epoch": 0.08, + "learning_rate": 4.592671304892508e-05, + "loss": 0.2835, "step": 37430 }, { - "epoch": 0.33, - "learning_rate": 3.359336996666967e-05, - "loss": 0.2699, + "epoch": 0.08, + "learning_rate": 4.592559450571576e-05, + "loss": 0.2873, "step": 37440 }, { - "epoch": 0.33, - "learning_rate": 3.3588865867939825e-05, - "loss": 0.2704, + "epoch": 0.08, + "learning_rate": 4.592447596250644e-05, + "loss": 0.287, "step": 37450 }, { - "epoch": 0.33, - "learning_rate": 3.358436176920998e-05, - "loss": 0.2728, + "epoch": 0.08, + "learning_rate": 4.592335741929711e-05, + "loss": 0.2849, "step": 37460 }, { - "epoch": 0.33, - "learning_rate": 3.357985767048013e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.5922238876087786e-05, + "loss": 0.2855, "step": 37470 }, { - "epoch": 0.33, - "learning_rate": 3.35753535717503e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.592112033287846e-05, + "loss": 0.2924, "step": 37480 }, { - "epoch": 0.33, - "learning_rate": 3.357084947302045e-05, - "loss": 0.2757, + "epoch": 0.08, + "learning_rate": 4.5920001789669135e-05, + "loss": 0.2856, "step": 37490 }, { - "epoch": 0.33, - "learning_rate": 3.3566345374290606e-05, - "loss": 0.271, + "epoch": 0.08, + "learning_rate": 4.591888324645981e-05, + "loss": 0.2878, "step": 37500 }, { - "epoch": 0.33, - "learning_rate": 3.356184127556076e-05, - "loss": 0.2705, + "epoch": 0.08, + "learning_rate": 4.5917764703250484e-05, + "loss": 0.2839, "step": 37510 }, { - "epoch": 0.33, - "learning_rate": 3.3557337176830914e-05, - "loss": 0.2664, + "epoch": 0.08, + "learning_rate": 4.591664616004117e-05, + "loss": 0.2901, "step": 37520 }, { - "epoch": 0.34, - "learning_rate": 3.355283307810108e-05, - "loss": 0.272, + "epoch": 0.08, + "learning_rate": 4.591552761683184e-05, + "loss": 0.2929, "step": 37530 }, { - "epoch": 0.34, - "learning_rate": 3.354832897937123e-05, - "loss": 0.2759, + "epoch": 0.08, + "learning_rate": 4.591440907362252e-05, + "loss": 0.2835, "step": 37540 }, { - "epoch": 0.34, - "learning_rate": 3.3543824880641386e-05, - "loss": 0.2714, + "epoch": 0.08, + "learning_rate": 4.5913290530413196e-05, + "loss": 0.282, "step": 37550 }, { - "epoch": 0.34, - "learning_rate": 3.3539320781911544e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.591217198720387e-05, + "loss": 0.2903, "step": 37560 }, { - "epoch": 0.34, - "learning_rate": 3.3534816683181694e-05, - "loss": 0.2692, + "epoch": 0.08, + "learning_rate": 4.5911053443994545e-05, + "loss": 0.2844, "step": 37570 }, { - "epoch": 0.34, - "learning_rate": 3.353031258445185e-05, - "loss": 0.2674, + "epoch": 0.08, + "learning_rate": 4.5909934900785216e-05, + "loss": 0.2804, "step": 37580 }, { - "epoch": 0.34, - "learning_rate": 3.352580848572201e-05, - "loss": 0.27, + "epoch": 0.08, + "learning_rate": 4.5908816357575894e-05, + "loss": 0.2857, "step": 37590 }, { - "epoch": 0.34, - "learning_rate": 3.352130438699217e-05, - "loss": 0.2723, + "epoch": 0.08, + "learning_rate": 4.590769781436657e-05, + "loss": 0.2895, "step": 37600 }, { - "epoch": 0.34, - "learning_rate": 3.351680028826232e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.590657927115724e-05, + "loss": 0.2838, "step": 37610 }, { - "epoch": 0.34, - "learning_rate": 3.3512296189532475e-05, - "loss": 0.2736, + "epoch": 0.08, + "learning_rate": 4.590546072794792e-05, + "loss": 0.2822, "step": 37620 }, { - "epoch": 0.34, - "learning_rate": 3.350779209080263e-05, - "loss": 0.2713, + "epoch": 0.08, + "learning_rate": 4.59043421847386e-05, + "loss": 0.2875, "step": 37630 }, { - "epoch": 0.34, - "learning_rate": 3.350328799207279e-05, - "loss": 0.2704, + "epoch": 0.08, + "learning_rate": 4.590322364152928e-05, + "loss": 0.2841, "step": 37640 }, { - "epoch": 0.34, - "learning_rate": 3.349878389334295e-05, - "loss": 0.2721, + "epoch": 0.08, + "learning_rate": 4.5902105098319955e-05, + "loss": 0.2846, "step": 37650 }, { - "epoch": 0.34, - "learning_rate": 3.34942797946131e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.5900986555110626e-05, + "loss": 0.2799, "step": 37660 }, { - "epoch": 0.34, - "learning_rate": 3.3489775695883256e-05, - "loss": 0.2746, + "epoch": 0.08, + "learning_rate": 4.5899868011901304e-05, + "loss": 0.2849, "step": 37670 }, { - "epoch": 0.34, - "learning_rate": 3.348527159715341e-05, - "loss": 0.275, + "epoch": 0.08, + "learning_rate": 4.5898749468691975e-05, + "loss": 0.2835, "step": 37680 }, { - "epoch": 0.34, - "learning_rate": 3.3480767498423564e-05, - "loss": 0.2712, + "epoch": 0.08, + "learning_rate": 4.589763092548265e-05, + "loss": 0.2873, "step": 37690 }, { - "epoch": 0.34, - "learning_rate": 3.347626339969372e-05, - "loss": 0.2711, + "epoch": 0.08, + "learning_rate": 4.5896512382273324e-05, + "loss": 0.2896, "step": 37700 }, { - "epoch": 0.34, - "learning_rate": 3.347175930096388e-05, - "loss": 0.2695, + "epoch": 0.08, + "learning_rate": 4.5895393839064e-05, + "loss": 0.2889, "step": 37710 }, { - "epoch": 0.34, - "learning_rate": 3.346725520223403e-05, - "loss": 0.2699, + "epoch": 0.08, + "learning_rate": 4.589427529585468e-05, + "loss": 0.2861, "step": 37720 }, { - "epoch": 0.34, - "learning_rate": 3.3462751103504194e-05, - "loss": 0.2736, + "epoch": 0.08, + "learning_rate": 4.589315675264536e-05, + "loss": 0.2868, "step": 37730 }, { - "epoch": 0.34, - "learning_rate": 3.3458247004774345e-05, - "loss": 0.2673, + "epoch": 0.08, + "learning_rate": 4.5892038209436036e-05, + "loss": 0.2816, "step": 37740 }, { - "epoch": 0.34, - "learning_rate": 3.34537429060445e-05, - "loss": 0.2755, + "epoch": 0.08, + "learning_rate": 4.589091966622671e-05, + "loss": 0.2815, "step": 37750 }, { - "epoch": 0.34, - "learning_rate": 3.344923880731466e-05, - "loss": 0.2722, + "epoch": 0.08, + "learning_rate": 4.5889801123017385e-05, + "loss": 0.2883, "step": 37760 }, { - "epoch": 0.34, - "learning_rate": 3.344473470858481e-05, - "loss": 0.2715, + "epoch": 0.08, + "learning_rate": 4.588868257980806e-05, + "loss": 0.2842, "step": 37770 }, { - "epoch": 0.34, - "learning_rate": 3.3440230609854975e-05, - "loss": 0.2706, + "epoch": 0.08, + "learning_rate": 4.5887564036598734e-05, + "loss": 0.2821, "step": 37780 }, { - "epoch": 0.34, - "learning_rate": 3.3435726511125125e-05, - "loss": 0.2673, + "epoch": 0.08, + "learning_rate": 4.588644549338941e-05, + "loss": 0.2847, "step": 37790 }, { - "epoch": 0.34, - "learning_rate": 3.343122241239528e-05, - "loss": 0.2724, + "epoch": 0.08, + "learning_rate": 4.588532695018008e-05, + "loss": 0.2924, "step": 37800 }, { - "epoch": 0.34, - "learning_rate": 3.342671831366544e-05, - "loss": 0.2694, + "epoch": 0.08, + "learning_rate": 4.588420840697076e-05, + "loss": 0.2809, "step": 37810 }, { - "epoch": 0.34, - "learning_rate": 3.342221421493559e-05, - "loss": 0.2738, + "epoch": 0.08, + "learning_rate": 4.588308986376144e-05, + "loss": 0.2807, "step": 37820 }, { - "epoch": 0.34, - "learning_rate": 3.341771011620575e-05, - "loss": 0.2725, + "epoch": 0.08, + "learning_rate": 4.588197132055212e-05, + "loss": 0.2851, "step": 37830 }, { - "epoch": 0.34, - "learning_rate": 3.3413206017475906e-05, - "loss": 0.268, + "epoch": 0.08, + "learning_rate": 4.5880852777342795e-05, + "loss": 0.2786, "step": 37840 }, { - "epoch": 0.34, - "learning_rate": 3.3408701918746064e-05, - "loss": 0.2664, + "epoch": 0.08, + "learning_rate": 4.5879734234133466e-05, + "loss": 0.2786, "step": 37850 }, { - "epoch": 0.34, - "learning_rate": 3.3404197820016214e-05, - "loss": 0.2756, + "epoch": 0.08, + "learning_rate": 4.5878615690924144e-05, + "loss": 0.2864, "step": 37860 }, { - "epoch": 0.34, - "learning_rate": 3.339969372128637e-05, - "loss": 0.2723, + "epoch": 0.08, + "learning_rate": 4.587749714771482e-05, + "loss": 0.2785, "step": 37870 }, { - "epoch": 0.34, - "learning_rate": 3.339518962255653e-05, - "loss": 0.2693, + "epoch": 0.08, + "learning_rate": 4.587637860450549e-05, + "loss": 0.281, "step": 37880 }, { - "epoch": 0.34, - "learning_rate": 3.339068552382668e-05, - "loss": 0.2737, + "epoch": 0.08, + "learning_rate": 4.587526006129617e-05, + "loss": 0.2865, "step": 37890 }, { - "epoch": 0.34, - "learning_rate": 3.338618142509684e-05, - "loss": 0.2741, + "epoch": 0.08, + "learning_rate": 4.587414151808684e-05, + "loss": 0.287, "step": 37900 }, { - "epoch": 0.34, - "learning_rate": 3.3381677326366995e-05, - "loss": 0.2747, + "epoch": 0.08, + "learning_rate": 4.587302297487752e-05, + "loss": 0.2834, "step": 37910 }, { - "epoch": 0.34, - "learning_rate": 3.337717322763715e-05, - "loss": 0.2704, + "epoch": 0.08, + "learning_rate": 4.58719044316682e-05, + "loss": 0.2904, "step": 37920 }, { - "epoch": 0.34, - "learning_rate": 3.337266912890731e-05, - "loss": 0.2728, + "epoch": 0.08, + "learning_rate": 4.587078588845887e-05, + "loss": 0.2834, "step": 37930 }, { - "epoch": 0.34, - "learning_rate": 3.336816503017746e-05, - "loss": 0.264, + "epoch": 0.08, + "learning_rate": 4.5869667345249554e-05, + "loss": 0.2857, "step": 37940 }, { - "epoch": 0.34, - "learning_rate": 3.336366093144762e-05, - "loss": 0.2731, + "epoch": 0.08, + "learning_rate": 4.5868548802040225e-05, + "loss": 0.286, "step": 37950 }, { - "epoch": 0.34, - "learning_rate": 3.3359156832717776e-05, - "loss": 0.2757, + "epoch": 0.08, + "learning_rate": 4.58674302588309e-05, + "loss": 0.2817, "step": 37960 }, { - "epoch": 0.34, - "learning_rate": 3.3354652733987926e-05, - "loss": 0.2766, + "epoch": 0.08, + "learning_rate": 4.586631171562158e-05, + "loss": 0.2884, "step": 37970 }, { - "epoch": 0.34, - "learning_rate": 3.335014863525809e-05, - "loss": 0.2673, + "epoch": 0.08, + "learning_rate": 4.586519317241225e-05, + "loss": 0.2822, "step": 37980 }, { - "epoch": 0.34, - "learning_rate": 3.334564453652824e-05, - "loss": 0.2707, + "epoch": 0.08, + "learning_rate": 4.586407462920293e-05, + "loss": 0.286, "step": 37990 }, { - "epoch": 0.34, - "learning_rate": 3.33411404377984e-05, - "loss": 0.2728, + "epoch": 0.08, + "learning_rate": 4.58629560859936e-05, + "loss": 0.2802, "step": 38000 }, { - "epoch": 0.34, - "learning_rate": 3.3336636339068556e-05, - "loss": 0.2723, + "epoch": 0.08, + "learning_rate": 4.586183754278428e-05, + "loss": 0.2852, "step": 38010 }, { - "epoch": 0.34, - "learning_rate": 3.333213224033871e-05, - "loss": 0.2726, + "epoch": 0.08, + "learning_rate": 4.586071899957495e-05, + "loss": 0.2786, "step": 38020 }, { - "epoch": 0.34, - "learning_rate": 3.3327628141608865e-05, - "loss": 0.2751, + "epoch": 0.08, + "learning_rate": 4.585960045636563e-05, + "loss": 0.2837, "step": 38030 }, { - "epoch": 0.34, - "learning_rate": 3.332312404287902e-05, - "loss": 0.276, + "epoch": 0.08, + "learning_rate": 4.5858481913156306e-05, + "loss": 0.2794, "step": 38040 }, { - "epoch": 0.34, - "learning_rate": 3.331861994414918e-05, - "loss": 0.2698, + "epoch": 0.08, + "learning_rate": 4.5857363369946984e-05, + "loss": 0.2841, "step": 38050 }, { - "epoch": 0.34, - "learning_rate": 3.331411584541934e-05, - "loss": 0.2761, + "epoch": 0.08, + "learning_rate": 4.585624482673766e-05, + "loss": 0.2847, "step": 38060 }, { - "epoch": 0.34, - "learning_rate": 3.330961174668949e-05, - "loss": 0.268, + "epoch": 0.08, + "learning_rate": 4.585512628352833e-05, + "loss": 0.2846, "step": 38070 }, { - "epoch": 0.34, - "learning_rate": 3.3305107647959645e-05, - "loss": 0.2706, + "epoch": 0.08, + "learning_rate": 4.585400774031901e-05, + "loss": 0.2855, "step": 38080 }, { - "epoch": 0.34, - "learning_rate": 3.33006035492298e-05, - "loss": 0.2757, + "epoch": 0.09, + "learning_rate": 4.585288919710969e-05, + "loss": 0.2847, "step": 38090 }, { - "epoch": 0.34, - "learning_rate": 3.3296099450499953e-05, - "loss": 0.2726, + "epoch": 0.09, + "learning_rate": 4.585177065390036e-05, + "loss": 0.2826, "step": 38100 }, { - "epoch": 0.34, - "learning_rate": 3.329159535177011e-05, - "loss": 0.2782, + "epoch": 0.09, + "learning_rate": 4.585065211069104e-05, + "loss": 0.2856, "step": 38110 }, { - "epoch": 0.34, - "learning_rate": 3.328709125304027e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.584953356748171e-05, + "loss": 0.284, "step": 38120 }, { - "epoch": 0.34, - "learning_rate": 3.3282587154310426e-05, - "loss": 0.2767, + "epoch": 0.09, + "learning_rate": 4.584841502427239e-05, + "loss": 0.2828, "step": 38130 }, { - "epoch": 0.34, - "learning_rate": 3.327808305558058e-05, - "loss": 0.273, + "epoch": 0.09, + "learning_rate": 4.5847296481063065e-05, + "loss": 0.2785, "step": 38140 }, { - "epoch": 0.34, - "learning_rate": 3.3273578956850734e-05, - "loss": 0.2689, + "epoch": 0.09, + "learning_rate": 4.584617793785374e-05, + "loss": 0.2812, "step": 38150 }, { - "epoch": 0.34, - "learning_rate": 3.326907485812089e-05, - "loss": 0.2715, + "epoch": 0.09, + "learning_rate": 4.584505939464442e-05, + "loss": 0.2808, "step": 38160 }, { - "epoch": 0.34, - "learning_rate": 3.326457075939104e-05, - "loss": 0.2655, + "epoch": 0.09, + "learning_rate": 4.584394085143509e-05, + "loss": 0.2865, "step": 38170 }, { - "epoch": 0.34, - "learning_rate": 3.326006666066121e-05, - "loss": 0.2624, + "epoch": 0.09, + "learning_rate": 4.584282230822577e-05, + "loss": 0.2841, "step": 38180 }, { - "epoch": 0.34, - "learning_rate": 3.325556256193136e-05, - "loss": 0.272, + "epoch": 0.09, + "learning_rate": 4.584170376501645e-05, + "loss": 0.285, "step": 38190 }, { - "epoch": 0.34, - "learning_rate": 3.3251058463201515e-05, - "loss": 0.2696, + "epoch": 0.09, + "learning_rate": 4.584058522180712e-05, + "loss": 0.2838, "step": 38200 }, { - "epoch": 0.34, - "learning_rate": 3.324655436447167e-05, - "loss": 0.2729, + "epoch": 0.09, + "learning_rate": 4.58394666785978e-05, + "loss": 0.2847, "step": 38210 }, { - "epoch": 0.34, - "learning_rate": 3.324205026574182e-05, - "loss": 0.2747, + "epoch": 0.09, + "learning_rate": 4.583834813538847e-05, + "loss": 0.2847, "step": 38220 }, { - "epoch": 0.34, - "learning_rate": 3.323754616701199e-05, - "loss": 0.2733, + "epoch": 0.09, + "learning_rate": 4.5837229592179146e-05, + "loss": 0.2828, "step": 38230 }, { - "epoch": 0.34, - "learning_rate": 3.323304206828214e-05, - "loss": 0.2691, + "epoch": 0.09, + "learning_rate": 4.5836111048969824e-05, + "loss": 0.2835, "step": 38240 }, { - "epoch": 0.34, - "learning_rate": 3.3228537969552296e-05, - "loss": 0.2702, + "epoch": 0.09, + "learning_rate": 4.58349925057605e-05, + "loss": 0.2839, "step": 38250 }, { - "epoch": 0.34, - "learning_rate": 3.322403387082245e-05, - "loss": 0.2755, + "epoch": 0.09, + "learning_rate": 4.583387396255118e-05, + "loss": 0.2841, "step": 38260 }, { - "epoch": 0.34, - "learning_rate": 3.3219529772092604e-05, - "loss": 0.2695, + "epoch": 0.09, + "learning_rate": 4.583275541934185e-05, + "loss": 0.2843, "step": 38270 }, { - "epoch": 0.34, - "learning_rate": 3.321502567336276e-05, - "loss": 0.2651, + "epoch": 0.09, + "learning_rate": 4.583163687613253e-05, + "loss": 0.275, "step": 38280 }, { - "epoch": 0.34, - "learning_rate": 3.321052157463292e-05, - "loss": 0.2704, + "epoch": 0.09, + "learning_rate": 4.583051833292321e-05, + "loss": 0.2828, "step": 38290 }, { - "epoch": 0.34, - "learning_rate": 3.3206017475903076e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.582939978971388e-05, + "loss": 0.2822, "step": 38300 }, { - "epoch": 0.34, - "learning_rate": 3.320151337717323e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.5828281246504556e-05, + "loss": 0.2796, "step": 38310 }, { - "epoch": 0.34, - "learning_rate": 3.3197009278443384e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.582716270329523e-05, + "loss": 0.2863, "step": 38320 }, { - "epoch": 0.34, - "learning_rate": 3.319250517971354e-05, - "loss": 0.2705, + "epoch": 0.09, + "learning_rate": 4.5826044160085905e-05, + "loss": 0.2819, "step": 38330 }, { - "epoch": 0.34, - "learning_rate": 3.31880010809837e-05, - "loss": 0.2696, + "epoch": 0.09, + "learning_rate": 4.5824925616876576e-05, + "loss": 0.2817, "step": 38340 }, { - "epoch": 0.34, - "learning_rate": 3.318349698225385e-05, - "loss": 0.2752, + "epoch": 0.09, + "learning_rate": 4.582380707366726e-05, + "loss": 0.2846, "step": 38350 }, { - "epoch": 0.34, - "learning_rate": 3.317899288352401e-05, - "loss": 0.2721, + "epoch": 0.09, + "learning_rate": 4.582268853045794e-05, + "loss": 0.2851, "step": 38360 }, { - "epoch": 0.34, - "learning_rate": 3.3174488784794165e-05, - "loss": 0.2681, + "epoch": 0.09, + "learning_rate": 4.582156998724861e-05, + "loss": 0.2806, "step": 38370 }, { - "epoch": 0.34, - "learning_rate": 3.316998468606432e-05, - "loss": 0.2726, + "epoch": 0.09, + "learning_rate": 4.582045144403929e-05, + "loss": 0.284, "step": 38380 }, { - "epoch": 0.34, - "learning_rate": 3.316548058733447e-05, - "loss": 0.2728, + "epoch": 0.09, + "learning_rate": 4.581933290082996e-05, + "loss": 0.2806, "step": 38390 }, { - "epoch": 0.34, - "learning_rate": 3.316097648860463e-05, - "loss": 0.2718, + "epoch": 0.09, + "learning_rate": 4.581821435762064e-05, + "loss": 0.286, "step": 38400 }, { - "epoch": 0.34, - "learning_rate": 3.315647238987479e-05, - "loss": 0.2784, + "epoch": 0.09, + "learning_rate": 4.5817095814411315e-05, + "loss": 0.2818, "step": 38410 }, { - "epoch": 0.34, - "learning_rate": 3.315196829114494e-05, - "loss": 0.2692, + "epoch": 0.09, + "learning_rate": 4.5815977271201986e-05, + "loss": 0.2792, "step": 38420 }, { - "epoch": 0.34, - "learning_rate": 3.31474641924151e-05, - "loss": 0.2763, + "epoch": 0.09, + "learning_rate": 4.5814858727992664e-05, + "loss": 0.2794, "step": 38430 }, { - "epoch": 0.34, - "learning_rate": 3.3142960093685254e-05, - "loss": 0.2688, + "epoch": 0.09, + "learning_rate": 4.5813740184783335e-05, + "loss": 0.2835, "step": 38440 }, { - "epoch": 0.34, - "learning_rate": 3.313845599495541e-05, - "loss": 0.2726, + "epoch": 0.09, + "learning_rate": 4.581262164157401e-05, + "loss": 0.2789, "step": 38450 }, { - "epoch": 0.34, - "learning_rate": 3.313395189622557e-05, - "loss": 0.2703, + "epoch": 0.09, + "learning_rate": 4.581150309836469e-05, + "loss": 0.2795, "step": 38460 }, { - "epoch": 0.34, - "learning_rate": 3.312944779749572e-05, - "loss": 0.2716, + "epoch": 0.09, + "learning_rate": 4.581038455515537e-05, + "loss": 0.2846, "step": 38470 }, { - "epoch": 0.34, - "learning_rate": 3.3124943698765884e-05, - "loss": 0.2716, + "epoch": 0.09, + "learning_rate": 4.580926601194605e-05, + "loss": 0.2873, "step": 38480 }, { - "epoch": 0.34, - "learning_rate": 3.3120439600036035e-05, - "loss": 0.2667, + "epoch": 0.09, + "learning_rate": 4.580814746873672e-05, + "loss": 0.2841, "step": 38490 }, { - "epoch": 0.34, - "learning_rate": 3.311593550130619e-05, - "loss": 0.2722, + "epoch": 0.09, + "learning_rate": 4.5807028925527396e-05, + "loss": 0.2838, "step": 38500 }, { - "epoch": 0.34, - "learning_rate": 3.311143140257635e-05, - "loss": 0.274, + "epoch": 0.09, + "learning_rate": 4.5805910382318074e-05, + "loss": 0.2815, "step": 38510 }, { - "epoch": 0.34, - "learning_rate": 3.31069273038465e-05, - "loss": 0.2733, + "epoch": 0.09, + "learning_rate": 4.5804791839108745e-05, + "loss": 0.2811, "step": 38520 }, { - "epoch": 0.34, - "learning_rate": 3.310242320511666e-05, - "loss": 0.2709, + "epoch": 0.09, + "learning_rate": 4.580367329589942e-05, + "loss": 0.285, "step": 38530 }, { - "epoch": 0.34, - "learning_rate": 3.3097919106386815e-05, - "loss": 0.2674, + "epoch": 0.09, + "learning_rate": 4.5802554752690094e-05, + "loss": 0.2855, "step": 38540 }, { - "epoch": 0.34, - "learning_rate": 3.3093415007656966e-05, - "loss": 0.2689, + "epoch": 0.09, + "learning_rate": 4.580143620948077e-05, + "loss": 0.2824, "step": 38550 }, { - "epoch": 0.34, - "learning_rate": 3.3088910908927124e-05, - "loss": 0.2742, + "epoch": 0.09, + "learning_rate": 4.580031766627145e-05, + "loss": 0.2874, "step": 38560 }, { - "epoch": 0.34, - "learning_rate": 3.308440681019728e-05, - "loss": 0.2697, + "epoch": 0.09, + "learning_rate": 4.579919912306213e-05, + "loss": 0.283, "step": 38570 }, { - "epoch": 0.34, - "learning_rate": 3.307990271146744e-05, - "loss": 0.2743, + "epoch": 0.09, + "learning_rate": 4.5798080579852806e-05, + "loss": 0.282, "step": 38580 }, { - "epoch": 0.34, - "learning_rate": 3.307539861273759e-05, - "loss": 0.2667, + "epoch": 0.09, + "learning_rate": 4.579696203664348e-05, + "loss": 0.2823, "step": 38590 }, { - "epoch": 0.34, - "learning_rate": 3.307089451400775e-05, - "loss": 0.2682, + "epoch": 0.09, + "learning_rate": 4.5795843493434155e-05, + "loss": 0.2861, "step": 38600 }, { - "epoch": 0.34, - "learning_rate": 3.3066390415277904e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.579472495022483e-05, + "loss": 0.2822, "step": 38610 }, { - "epoch": 0.34, - "learning_rate": 3.306188631654806e-05, - "loss": 0.2738, + "epoch": 0.09, + "learning_rate": 4.5793606407015504e-05, + "loss": 0.287, "step": 38620 }, { - "epoch": 0.34, - "learning_rate": 3.305738221781822e-05, - "loss": 0.2726, + "epoch": 0.09, + "learning_rate": 4.579248786380618e-05, + "loss": 0.2802, "step": 38630 }, { - "epoch": 0.34, - "learning_rate": 3.305287811908837e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.579136932059685e-05, + "loss": 0.2768, "step": 38640 }, { - "epoch": 0.35, - "learning_rate": 3.304837402035853e-05, - "loss": 0.2718, + "epoch": 0.09, + "learning_rate": 4.579025077738753e-05, + "loss": 0.2841, "step": 38650 }, { - "epoch": 0.35, - "learning_rate": 3.3043869921628685e-05, - "loss": 0.2696, + "epoch": 0.09, + "learning_rate": 4.578913223417821e-05, + "loss": 0.2795, "step": 38660 }, { - "epoch": 0.35, - "learning_rate": 3.3039365822898836e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.578801369096889e-05, + "loss": 0.2832, "step": 38670 }, { - "epoch": 0.35, - "learning_rate": 3.3034861724169e-05, - "loss": 0.2786, + "epoch": 0.09, + "learning_rate": 4.5786895147759565e-05, + "loss": 0.2798, "step": 38680 }, { - "epoch": 0.35, - "learning_rate": 3.303035762543915e-05, - "loss": 0.2723, + "epoch": 0.09, + "learning_rate": 4.5785776604550236e-05, + "loss": 0.2875, "step": 38690 }, { - "epoch": 0.35, - "learning_rate": 3.302585352670931e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.5784658061340914e-05, + "loss": 0.2901, "step": 38700 }, { - "epoch": 0.35, - "learning_rate": 3.3021349427979466e-05, - "loss": 0.2711, + "epoch": 0.09, + "learning_rate": 4.5783539518131585e-05, + "loss": 0.284, "step": 38710 }, { - "epoch": 0.35, - "learning_rate": 3.3016845329249616e-05, - "loss": 0.2677, + "epoch": 0.09, + "learning_rate": 4.578242097492226e-05, + "loss": 0.2873, "step": 38720 }, { - "epoch": 0.35, - "learning_rate": 3.3012341230519774e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.578130243171294e-05, + "loss": 0.2812, "step": 38730 }, { - "epoch": 0.35, - "learning_rate": 3.300783713178993e-05, - "loss": 0.2639, + "epoch": 0.09, + "learning_rate": 4.578018388850361e-05, + "loss": 0.2819, "step": 38740 }, { - "epoch": 0.35, - "learning_rate": 3.300333303306008e-05, - "loss": 0.2771, + "epoch": 0.09, + "learning_rate": 4.577906534529429e-05, + "loss": 0.2823, "step": 38750 }, { - "epoch": 0.35, - "learning_rate": 3.2998828934330246e-05, - "loss": 0.272, + "epoch": 0.09, + "learning_rate": 4.577794680208497e-05, + "loss": 0.2829, "step": 38760 }, { - "epoch": 0.35, - "learning_rate": 3.29943248356004e-05, - "loss": 0.2674, + "epoch": 0.09, + "learning_rate": 4.5776828258875646e-05, + "loss": 0.2851, "step": 38770 }, { - "epoch": 0.35, - "learning_rate": 3.2989820736870555e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.5775709715666324e-05, + "loss": 0.2903, "step": 38780 }, { - "epoch": 0.35, - "learning_rate": 3.298531663814071e-05, - "loss": 0.2668, + "epoch": 0.09, + "learning_rate": 4.5774591172456995e-05, + "loss": 0.2786, "step": 38790 }, { - "epoch": 0.35, - "learning_rate": 3.298081253941086e-05, - "loss": 0.2651, + "epoch": 0.09, + "learning_rate": 4.577347262924767e-05, + "loss": 0.2831, "step": 38800 }, { - "epoch": 0.35, - "learning_rate": 3.297630844068102e-05, - "loss": 0.27, + "epoch": 0.09, + "learning_rate": 4.5772354086038344e-05, + "loss": 0.2861, "step": 38810 }, { - "epoch": 0.35, - "learning_rate": 3.297180434195118e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.577123554282902e-05, + "loss": 0.2882, "step": 38820 }, { - "epoch": 0.35, - "learning_rate": 3.2967300243221335e-05, - "loss": 0.2696, + "epoch": 0.09, + "learning_rate": 4.57701169996197e-05, + "loss": 0.2839, "step": 38830 }, { - "epoch": 0.35, - "learning_rate": 3.2962796144491486e-05, - "loss": 0.2735, + "epoch": 0.09, + "learning_rate": 4.576899845641037e-05, + "loss": 0.2875, "step": 38840 }, { - "epoch": 0.35, - "learning_rate": 3.2958292045761643e-05, - "loss": 0.2758, + "epoch": 0.09, + "learning_rate": 4.576787991320105e-05, + "loss": 0.2854, "step": 38850 }, { - "epoch": 0.35, - "learning_rate": 3.29537879470318e-05, - "loss": 0.2663, + "epoch": 0.09, + "learning_rate": 4.576676136999172e-05, + "loss": 0.2811, "step": 38860 }, { - "epoch": 0.35, - "learning_rate": 3.294928384830195e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.57656428267824e-05, + "loss": 0.2867, "step": 38870 }, { - "epoch": 0.35, - "learning_rate": 3.2944779749572116e-05, - "loss": 0.2725, + "epoch": 0.09, + "learning_rate": 4.5764524283573076e-05, + "loss": 0.2794, "step": 38880 }, { - "epoch": 0.35, - "learning_rate": 3.294027565084227e-05, - "loss": 0.2643, + "epoch": 0.09, + "learning_rate": 4.5763517594684685e-05, + "loss": 0.2803, "step": 38890 }, { - "epoch": 0.35, - "learning_rate": 3.2935771552112424e-05, - "loss": 0.2734, + "epoch": 0.09, + "learning_rate": 4.576239905147536e-05, + "loss": 0.2854, "step": 38900 }, { - "epoch": 0.35, - "learning_rate": 3.293126745338258e-05, - "loss": 0.2666, + "epoch": 0.09, + "learning_rate": 4.5761280508266034e-05, + "loss": 0.2793, "step": 38910 }, { - "epoch": 0.35, - "learning_rate": 3.292676335465273e-05, - "loss": 0.2683, + "epoch": 0.09, + "learning_rate": 4.576016196505671e-05, + "loss": 0.2814, "step": 38920 }, { - "epoch": 0.35, - "learning_rate": 3.2922259255922897e-05, - "loss": 0.2666, + "epoch": 0.09, + "learning_rate": 4.575904342184739e-05, + "loss": 0.2861, "step": 38930 }, { - "epoch": 0.35, - "learning_rate": 3.291775515719305e-05, - "loss": 0.263, + "epoch": 0.09, + "learning_rate": 4.575792487863807e-05, + "loss": 0.2823, "step": 38940 }, { - "epoch": 0.35, - "learning_rate": 3.2913251058463205e-05, - "loss": 0.2669, + "epoch": 0.09, + "learning_rate": 4.5756806335428745e-05, + "loss": 0.2838, "step": 38950 }, { - "epoch": 0.35, - "learning_rate": 3.290874695973336e-05, - "loss": 0.2764, + "epoch": 0.09, + "learning_rate": 4.5755687792219417e-05, + "loss": 0.2853, "step": 38960 }, { - "epoch": 0.35, - "learning_rate": 3.290424286100351e-05, - "loss": 0.2687, + "epoch": 0.09, + "learning_rate": 4.5754569249010094e-05, + "loss": 0.2788, "step": 38970 }, { - "epoch": 0.35, - "learning_rate": 3.289973876227367e-05, - "loss": 0.2682, + "epoch": 0.09, + "learning_rate": 4.5753450705800766e-05, + "loss": 0.2823, "step": 38980 }, { - "epoch": 0.35, - "learning_rate": 3.289523466354383e-05, - "loss": 0.268, + "epoch": 0.09, + "learning_rate": 4.5752332162591444e-05, + "loss": 0.2801, "step": 38990 }, { - "epoch": 0.35, - "learning_rate": 3.289073056481398e-05, - "loss": 0.2644, + "epoch": 0.09, + "learning_rate": 4.575121361938212e-05, + "loss": 0.2758, "step": 39000 }, { - "epoch": 0.35, - "learning_rate": 3.2886226466084136e-05, - "loss": 0.272, + "epoch": 0.09, + "learning_rate": 4.575009507617279e-05, + "loss": 0.2816, "step": 39010 }, { - "epoch": 0.35, - "learning_rate": 3.2881722367354294e-05, - "loss": 0.2716, + "epoch": 0.09, + "learning_rate": 4.574897653296347e-05, + "loss": 0.2823, "step": 39020 }, { - "epoch": 0.35, - "learning_rate": 3.287721826862445e-05, - "loss": 0.2678, + "epoch": 0.09, + "learning_rate": 4.574785798975414e-05, + "loss": 0.2764, "step": 39030 }, { - "epoch": 0.35, - "learning_rate": 3.287271416989461e-05, - "loss": 0.265, + "epoch": 0.09, + "learning_rate": 4.574673944654482e-05, + "loss": 0.279, "step": 39040 }, { - "epoch": 0.35, - "learning_rate": 3.286821007116476e-05, - "loss": 0.2734, + "epoch": 0.09, + "learning_rate": 4.57456209033355e-05, + "loss": 0.2802, "step": 39050 }, { - "epoch": 0.35, - "learning_rate": 3.286370597243492e-05, - "loss": 0.2722, + "epoch": 0.09, + "learning_rate": 4.5744502360126175e-05, + "loss": 0.2809, "step": 39060 }, { - "epoch": 0.35, - "learning_rate": 3.2859201873705074e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.5743383816916853e-05, + "loss": 0.2813, "step": 39070 }, { - "epoch": 0.35, - "learning_rate": 3.285469777497523e-05, - "loss": 0.2699, + "epoch": 0.09, + "learning_rate": 4.5742265273707525e-05, + "loss": 0.2805, "step": 39080 }, { - "epoch": 0.35, - "learning_rate": 3.285019367624538e-05, - "loss": 0.2709, + "epoch": 0.09, + "learning_rate": 4.57411467304982e-05, + "loss": 0.2804, "step": 39090 }, { - "epoch": 0.35, - "learning_rate": 3.284568957751554e-05, - "loss": 0.2651, + "epoch": 0.09, + "learning_rate": 4.5740028187288874e-05, + "loss": 0.2777, "step": 39100 }, { - "epoch": 0.35, - "learning_rate": 3.28411854787857e-05, - "loss": 0.2715, + "epoch": 0.09, + "learning_rate": 4.573890964407955e-05, + "loss": 0.2797, "step": 39110 }, { - "epoch": 0.35, - "learning_rate": 3.283668138005585e-05, - "loss": 0.2646, + "epoch": 0.09, + "learning_rate": 4.573779110087023e-05, + "loss": 0.2875, "step": 39120 }, { - "epoch": 0.35, - "learning_rate": 3.283217728132601e-05, - "loss": 0.2677, + "epoch": 0.09, + "learning_rate": 4.57366725576609e-05, + "loss": 0.2771, "step": 39130 }, { - "epoch": 0.35, - "learning_rate": 3.282767318259616e-05, - "loss": 0.2685, + "epoch": 0.09, + "learning_rate": 4.573555401445158e-05, + "loss": 0.2754, "step": 39140 }, { - "epoch": 0.35, - "learning_rate": 3.282316908386632e-05, - "loss": 0.2718, + "epoch": 0.09, + "learning_rate": 4.5734435471242257e-05, + "loss": 0.289, "step": 39150 }, { - "epoch": 0.35, - "learning_rate": 3.281866498513648e-05, - "loss": 0.2681, + "epoch": 0.09, + "learning_rate": 4.5733316928032934e-05, + "loss": 0.2828, "step": 39160 }, { - "epoch": 0.35, - "learning_rate": 3.281416088640663e-05, - "loss": 0.2705, + "epoch": 0.09, + "learning_rate": 4.573219838482361e-05, + "loss": 0.284, "step": 39170 }, { - "epoch": 0.35, - "learning_rate": 3.280965678767679e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.5731079841614284e-05, + "loss": 0.2814, "step": 39180 }, { - "epoch": 0.35, - "learning_rate": 3.2805152688946944e-05, - "loss": 0.2678, + "epoch": 0.09, + "learning_rate": 4.572996129840496e-05, + "loss": 0.285, "step": 39190 }, { - "epoch": 0.35, - "learning_rate": 3.2800648590217095e-05, - "loss": 0.2621, + "epoch": 0.09, + "learning_rate": 4.572884275519563e-05, + "loss": 0.2861, "step": 39200 }, { - "epoch": 0.35, - "learning_rate": 3.279614449148726e-05, - "loss": 0.268, + "epoch": 0.09, + "learning_rate": 4.572772421198631e-05, + "loss": 0.2801, "step": 39210 }, { - "epoch": 0.35, - "learning_rate": 3.279164039275741e-05, - "loss": 0.27, + "epoch": 0.09, + "learning_rate": 4.572660566877699e-05, + "loss": 0.2866, "step": 39220 }, { - "epoch": 0.35, - "learning_rate": 3.278713629402757e-05, - "loss": 0.2692, + "epoch": 0.09, + "learning_rate": 4.572548712556766e-05, + "loss": 0.2817, "step": 39230 }, { - "epoch": 0.35, - "learning_rate": 3.2782632195297725e-05, - "loss": 0.2671, + "epoch": 0.09, + "learning_rate": 4.572436858235834e-05, + "loss": 0.2792, "step": 39240 }, { - "epoch": 0.35, - "learning_rate": 3.2778128096567875e-05, - "loss": 0.2653, + "epoch": 0.09, + "learning_rate": 4.5723250039149015e-05, + "loss": 0.2873, "step": 39250 }, { - "epoch": 0.35, - "learning_rate": 3.277362399783803e-05, - "loss": 0.2701, + "epoch": 0.09, + "learning_rate": 4.5722131495939693e-05, + "loss": 0.2788, "step": 39260 }, { - "epoch": 0.35, - "learning_rate": 3.276911989910819e-05, - "loss": 0.2768, + "epoch": 0.09, + "learning_rate": 4.572101295273037e-05, + "loss": 0.2831, "step": 39270 }, { - "epoch": 0.35, - "learning_rate": 3.276461580037835e-05, - "loss": 0.2681, + "epoch": 0.09, + "learning_rate": 4.571989440952104e-05, + "loss": 0.2847, "step": 39280 }, { - "epoch": 0.35, - "learning_rate": 3.27601117016485e-05, - "loss": 0.2706, + "epoch": 0.09, + "learning_rate": 4.571877586631172e-05, + "loss": 0.2815, "step": 39290 }, { - "epoch": 0.35, - "learning_rate": 3.2755607602918656e-05, - "loss": 0.2738, + "epoch": 0.09, + "learning_rate": 4.571765732310239e-05, + "loss": 0.2782, "step": 39300 }, { - "epoch": 0.35, - "learning_rate": 3.2751103504188814e-05, - "loss": 0.2769, + "epoch": 0.09, + "learning_rate": 4.571653877989307e-05, + "loss": 0.2804, "step": 39310 }, { - "epoch": 0.35, - "learning_rate": 3.274659940545897e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.571542023668374e-05, + "loss": 0.2843, "step": 39320 }, { - "epoch": 0.35, - "learning_rate": 3.274209530672913e-05, - "loss": 0.271, + "epoch": 0.09, + "learning_rate": 4.571430169347442e-05, + "loss": 0.2824, "step": 39330 }, { - "epoch": 0.35, - "learning_rate": 3.2738041617872266e-05, - "loss": 0.2714, + "epoch": 0.09, + "learning_rate": 4.5713183150265096e-05, + "loss": 0.2825, "step": 39340 }, { - "epoch": 0.35, - "learning_rate": 3.273353751914242e-05, - "loss": 0.2716, + "epoch": 0.09, + "learning_rate": 4.5712064607055774e-05, + "loss": 0.2764, "step": 39350 }, { - "epoch": 0.35, - "learning_rate": 3.2729033420412574e-05, - "loss": 0.2691, + "epoch": 0.09, + "learning_rate": 4.571094606384645e-05, + "loss": 0.2768, "step": 39360 }, { - "epoch": 0.35, - "learning_rate": 3.272452932168273e-05, - "loss": 0.2631, + "epoch": 0.09, + "learning_rate": 4.5709827520637123e-05, + "loss": 0.2836, "step": 39370 }, { - "epoch": 0.35, - "learning_rate": 3.272002522295289e-05, - "loss": 0.2721, + "epoch": 0.09, + "learning_rate": 4.57087089774278e-05, + "loss": 0.2839, "step": 39380 }, { - "epoch": 0.35, - "learning_rate": 3.271552112422304e-05, - "loss": 0.27, + "epoch": 0.09, + "learning_rate": 4.570759043421848e-05, + "loss": 0.2899, "step": 39390 }, { - "epoch": 0.35, - "learning_rate": 3.2711017025493204e-05, - "loss": 0.2627, + "epoch": 0.09, + "learning_rate": 4.570647189100915e-05, + "loss": 0.2871, "step": 39400 }, { - "epoch": 0.35, - "learning_rate": 3.2706512926763354e-05, - "loss": 0.2655, + "epoch": 0.09, + "learning_rate": 4.570535334779983e-05, + "loss": 0.2797, "step": 39410 }, { - "epoch": 0.35, - "learning_rate": 3.270200882803351e-05, - "loss": 0.2717, + "epoch": 0.09, + "learning_rate": 4.57042348045905e-05, + "loss": 0.2815, "step": 39420 }, { - "epoch": 0.35, - "learning_rate": 3.269750472930367e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.570311626138118e-05, + "loss": 0.2827, "step": 39430 }, { - "epoch": 0.35, - "learning_rate": 3.269300063057382e-05, - "loss": 0.269, + "epoch": 0.09, + "learning_rate": 4.5701997718171855e-05, + "loss": 0.2846, "step": 39440 }, { - "epoch": 0.35, - "learning_rate": 3.2688496531843984e-05, - "loss": 0.2698, + "epoch": 0.09, + "learning_rate": 4.5700879174962527e-05, + "loss": 0.2811, "step": 39450 }, { - "epoch": 0.35, - "learning_rate": 3.2683992433114135e-05, - "loss": 0.2631, + "epoch": 0.09, + "learning_rate": 4.5699760631753205e-05, + "loss": 0.2834, "step": 39460 }, { - "epoch": 0.35, - "learning_rate": 3.267948833438429e-05, - "loss": 0.265, + "epoch": 0.09, + "learning_rate": 4.569864208854388e-05, + "loss": 0.2837, "step": 39470 }, { - "epoch": 0.35, - "learning_rate": 3.267498423565445e-05, - "loss": 0.2674, + "epoch": 0.09, + "learning_rate": 4.569752354533456e-05, + "loss": 0.2841, "step": 39480 }, { - "epoch": 0.35, - "learning_rate": 3.26704801369246e-05, - "loss": 0.271, + "epoch": 0.09, + "learning_rate": 4.569640500212524e-05, + "loss": 0.281, "step": 39490 }, { - "epoch": 0.35, - "learning_rate": 3.266597603819476e-05, - "loss": 0.2712, + "epoch": 0.09, + "learning_rate": 4.569528645891591e-05, + "loss": 0.2827, "step": 39500 }, { - "epoch": 0.35, - "learning_rate": 3.2661471939464916e-05, - "loss": 0.2683, + "epoch": 0.09, + "learning_rate": 4.569416791570659e-05, + "loss": 0.2818, "step": 39510 }, { - "epoch": 0.35, - "learning_rate": 3.2656967840735066e-05, - "loss": 0.2703, + "epoch": 0.09, + "learning_rate": 4.569304937249726e-05, + "loss": 0.2797, "step": 39520 }, { - "epoch": 0.35, - "learning_rate": 3.2652463742005224e-05, - "loss": 0.2708, + "epoch": 0.09, + "learning_rate": 4.5691930829287936e-05, + "loss": 0.2775, "step": 39530 }, { - "epoch": 0.35, - "learning_rate": 3.264795964327538e-05, - "loss": 0.2765, + "epoch": 0.09, + "learning_rate": 4.5690812286078614e-05, + "loss": 0.2838, "step": 39540 }, { - "epoch": 0.35, - "learning_rate": 3.264345554454554e-05, - "loss": 0.2657, + "epoch": 0.09, + "learning_rate": 4.5689693742869286e-05, + "loss": 0.2744, "step": 39550 }, { - "epoch": 0.35, - "learning_rate": 3.2638951445815696e-05, - "loss": 0.2668, + "epoch": 0.09, + "learning_rate": 4.5688575199659963e-05, + "loss": 0.284, "step": 39560 }, { - "epoch": 0.35, - "learning_rate": 3.263444734708585e-05, - "loss": 0.2691, + "epoch": 0.09, + "learning_rate": 4.568745665645064e-05, + "loss": 0.2748, "step": 39570 }, { - "epoch": 0.35, - "learning_rate": 3.2629943248356005e-05, - "loss": 0.2669, + "epoch": 0.09, + "learning_rate": 4.568633811324132e-05, + "loss": 0.2861, "step": 39580 }, { - "epoch": 0.35, - "learning_rate": 3.262543914962616e-05, - "loss": 0.265, + "epoch": 0.09, + "learning_rate": 4.5685219570032e-05, + "loss": 0.2845, "step": 39590 }, { - "epoch": 0.35, - "learning_rate": 3.262093505089632e-05, - "loss": 0.2697, + "epoch": 0.09, + "learning_rate": 4.568410102682267e-05, + "loss": 0.2784, "step": 39600 }, { - "epoch": 0.35, - "learning_rate": 3.261643095216647e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.5682982483613346e-05, + "loss": 0.2831, "step": 39610 }, { - "epoch": 0.35, - "learning_rate": 3.261192685343663e-05, - "loss": 0.2745, + "epoch": 0.09, + "learning_rate": 4.568186394040402e-05, + "loss": 0.2847, "step": 39620 }, { - "epoch": 0.35, - "learning_rate": 3.2607422754706785e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.5680745397194695e-05, + "loss": 0.2794, "step": 39630 }, { - "epoch": 0.35, - "learning_rate": 3.2602918655976936e-05, - "loss": 0.2679, + "epoch": 0.09, + "learning_rate": 4.5679626853985367e-05, + "loss": 0.2734, "step": 39640 }, { - "epoch": 0.35, - "learning_rate": 3.25984145572471e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.5678508310776044e-05, + "loss": 0.2802, "step": 39650 }, { - "epoch": 0.35, - "learning_rate": 3.259391045851725e-05, - "loss": 0.2621, + "epoch": 0.09, + "learning_rate": 4.567738976756672e-05, + "loss": 0.2786, "step": 39660 }, { - "epoch": 0.35, - "learning_rate": 3.258940635978741e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.56762712243574e-05, + "loss": 0.2806, "step": 39670 }, { - "epoch": 0.35, - "learning_rate": 3.2584902261057566e-05, - "loss": 0.2713, + "epoch": 0.09, + "learning_rate": 4.567515268114808e-05, + "loss": 0.2835, "step": 39680 }, { - "epoch": 0.35, - "learning_rate": 3.258039816232772e-05, - "loss": 0.2723, + "epoch": 0.09, + "learning_rate": 4.567403413793875e-05, + "loss": 0.2862, "step": 39690 }, { - "epoch": 0.35, - "learning_rate": 3.257589406359788e-05, - "loss": 0.2679, + "epoch": 0.09, + "learning_rate": 4.567291559472943e-05, + "loss": 0.2834, "step": 39700 }, { - "epoch": 0.35, - "learning_rate": 3.257138996486803e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.5671797051520105e-05, + "loss": 0.2768, "step": 39710 }, { - "epoch": 0.35, - "learning_rate": 3.256688586613819e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.5670678508310776e-05, + "loss": 0.2815, "step": 39720 }, { - "epoch": 0.35, - "learning_rate": 3.256238176740835e-05, - "loss": 0.2627, + "epoch": 0.09, + "learning_rate": 4.5669559965101454e-05, + "loss": 0.2801, "step": 39730 }, { - "epoch": 0.35, - "learning_rate": 3.25578776686785e-05, - "loss": 0.2652, + "epoch": 0.09, + "learning_rate": 4.5668441421892126e-05, + "loss": 0.278, "step": 39740 }, { - "epoch": 0.35, - "learning_rate": 3.2553373569948655e-05, - "loss": 0.2738, + "epoch": 0.09, + "learning_rate": 4.5667322878682803e-05, + "loss": 0.2742, "step": 39750 }, { - "epoch": 0.35, - "learning_rate": 3.254886947121881e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.566620433547348e-05, + "loss": 0.2732, "step": 39760 }, { - "epoch": 0.36, - "learning_rate": 3.254436537248896e-05, - "loss": 0.2702, + "epoch": 0.09, + "learning_rate": 4.566508579226416e-05, + "loss": 0.2824, "step": 39770 }, { - "epoch": 0.36, - "learning_rate": 3.253986127375912e-05, - "loss": 0.269, + "epoch": 0.09, + "learning_rate": 4.566396724905484e-05, + "loss": 0.2886, "step": 39780 }, { - "epoch": 0.36, - "learning_rate": 3.253535717502928e-05, - "loss": 0.2682, + "epoch": 0.09, + "learning_rate": 4.566284870584551e-05, + "loss": 0.2863, "step": 39790 }, { - "epoch": 0.36, - "learning_rate": 3.2530853076299436e-05, - "loss": 0.2695, + "epoch": 0.09, + "learning_rate": 4.5661730162636186e-05, + "loss": 0.2809, "step": 39800 }, { - "epoch": 0.36, - "learning_rate": 3.2526348977569586e-05, - "loss": 0.2625, + "epoch": 0.09, + "learning_rate": 4.5660611619426864e-05, + "loss": 0.2793, "step": 39810 }, { - "epoch": 0.36, - "learning_rate": 3.2521844878839744e-05, - "loss": 0.2629, + "epoch": 0.09, + "learning_rate": 4.5659493076217535e-05, + "loss": 0.2862, "step": 39820 }, { - "epoch": 0.36, - "learning_rate": 3.25173407801099e-05, - "loss": 0.2773, + "epoch": 0.09, + "learning_rate": 4.565837453300821e-05, + "loss": 0.2775, "step": 39830 }, { - "epoch": 0.36, - "learning_rate": 3.251283668138006e-05, - "loss": 0.2761, + "epoch": 0.09, + "learning_rate": 4.5657255989798884e-05, + "loss": 0.2795, "step": 39840 }, { - "epoch": 0.36, - "learning_rate": 3.2508332582650216e-05, - "loss": 0.2662, + "epoch": 0.09, + "learning_rate": 4.565613744658956e-05, + "loss": 0.2845, "step": 39850 }, { - "epoch": 0.36, - "learning_rate": 3.250382848392037e-05, - "loss": 0.2767, + "epoch": 0.09, + "learning_rate": 4.565501890338024e-05, + "loss": 0.287, "step": 39860 }, { - "epoch": 0.36, - "learning_rate": 3.2499324385190525e-05, - "loss": 0.2685, + "epoch": 0.09, + "learning_rate": 4.565390036017091e-05, + "loss": 0.2809, "step": 39870 }, { - "epoch": 0.36, - "learning_rate": 3.249482028646068e-05, - "loss": 0.2698, + "epoch": 0.09, + "learning_rate": 4.5652781816961596e-05, + "loss": 0.2774, "step": 39880 }, { - "epoch": 0.36, - "learning_rate": 3.249031618773083e-05, - "loss": 0.2655, + "epoch": 0.09, + "learning_rate": 4.565166327375227e-05, + "loss": 0.2797, "step": 39890 }, { - "epoch": 0.36, - "learning_rate": 3.2485812089001e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.5650544730542945e-05, + "loss": 0.2837, "step": 39900 }, { - "epoch": 0.36, - "learning_rate": 3.248130799027115e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.564942618733362e-05, + "loss": 0.2781, "step": 39910 }, { - "epoch": 0.36, - "learning_rate": 3.2476803891541305e-05, - "loss": 0.2649, + "epoch": 0.09, + "learning_rate": 4.5648307644124294e-05, + "loss": 0.2829, "step": 39920 }, { - "epoch": 0.36, - "learning_rate": 3.247229979281146e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.564718910091497e-05, + "loss": 0.2806, "step": 39930 }, { - "epoch": 0.36, - "learning_rate": 3.2467795694081613e-05, - "loss": 0.2604, + "epoch": 0.09, + "learning_rate": 4.5646070557705643e-05, + "loss": 0.2851, "step": 39940 }, { - "epoch": 0.36, - "learning_rate": 3.246329159535177e-05, - "loss": 0.273, + "epoch": 0.09, + "learning_rate": 4.564495201449632e-05, + "loss": 0.2839, "step": 39950 }, { - "epoch": 0.36, - "learning_rate": 3.245878749662193e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.564383347128699e-05, + "loss": 0.2826, "step": 39960 }, { - "epoch": 0.36, - "learning_rate": 3.245428339789208e-05, - "loss": 0.2728, + "epoch": 0.09, + "learning_rate": 4.564271492807767e-05, + "loss": 0.2794, "step": 39970 }, { - "epoch": 0.36, - "learning_rate": 3.244977929916224e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.564159638486835e-05, + "loss": 0.2796, "step": 39980 }, { - "epoch": 0.36, - "learning_rate": 3.2445275200432394e-05, - "loss": 0.2714, + "epoch": 0.09, + "learning_rate": 4.5640477841659026e-05, + "loss": 0.2767, "step": 39990 }, { - "epoch": 0.36, - "learning_rate": 3.244077110170255e-05, - "loss": 0.2708, - "step": 40000 - }, - { - "epoch": 0.36, - "eval_NEIMS_canon_smiles": 0.9353333333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.017566666666666668, - "eval_NEIMS_daylight_tanimoto_simil": 0.39882045391989296, - "eval_NEIMS_exact_mols": 0.017516666666666666, - "eval_NEIMS_exact_smiles": 0.01685, - "eval_NEIMS_loss": 0.28149697184562683, - "eval_NEIMS_matched_formulas": 0.4307, - "eval_NEIMS_morgan_tanimoto_simil": 0.2970297724918811, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.017616666666666666, - "eval_NEIMS_runtime": 716.5006, - "eval_NEIMS_samples_per_second": 83.74, - "eval_NEIMS_steps_per_second": 1.309, - "step": 40000 - }, - { - "epoch": 0.36, - "eval_RASSP_canon_smiles": 0.9259191237853541, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.04429492102714796, - "eval_RASSP_daylight_tanimoto_simil": 0.4832393482022256, - "eval_RASSP_exact_mols": 0.04409456706848766, - "eval_RASSP_exact_smiles": 0.042408254583096806, - "eval_RASSP_loss": 0.22775410115718842, - "eval_RASSP_matched_formulas": 0.573262764216783, - "eval_RASSP_morgan_tanimoto_simil": 0.34593379198899715, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.04417804788459612, - "eval_RASSP_runtime": 820.6658, - "eval_RASSP_samples_per_second": 72.982, - "eval_RASSP_steps_per_second": 1.141, - "step": 40000 - }, - { - "epoch": 0.36, - "eval_NIST_canon_smiles": 0.8790502892429997, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.007630336799517337, - "eval_NIST_daylight_tanimoto_simil": 0.25814331426059783, - "eval_NIST_exact_mols": 0.007239947474890869, - "eval_NIST_exact_smiles": 0.006956027966071619, - "eval_NIST_loss": 1.4002385139465332, - "eval_NIST_matched_formulas": 0.06413031905454804, - "eval_NIST_morgan_tanimoto_simil": 0.2147215198195743, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.007559356922312525, - "eval_NIST_runtime": 475.4693, - "eval_NIST_samples_per_second": 59.261, - "eval_NIST_steps_per_second": 0.928, + "epoch": 0.09, + "learning_rate": 4.5639359298449704e-05, + "loss": 0.2778, "step": 40000 }, { - "epoch": 0.36, - "learning_rate": 3.243626700297271e-05, - "loss": 0.2685, + "epoch": 0.09, + "learning_rate": 4.5638240755240375e-05, + "loss": 0.2869, "step": 40010 }, { - "epoch": 0.36, - "learning_rate": 3.243176290424286e-05, - "loss": 0.2671, + "epoch": 0.09, + "learning_rate": 4.563712221203105e-05, + "loss": 0.286, "step": 40020 }, { - "epoch": 0.36, - "learning_rate": 3.242725880551302e-05, - "loss": 0.2632, + "epoch": 0.09, + "learning_rate": 4.563600366882173e-05, + "loss": 0.2735, "step": 40030 }, { - "epoch": 0.36, - "learning_rate": 3.2422754706783175e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.56348851256124e-05, + "loss": 0.2779, "step": 40040 }, { - "epoch": 0.36, - "learning_rate": 3.241825060805333e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.563376658240308e-05, + "loss": 0.2846, "step": 40050 }, { - "epoch": 0.36, - "learning_rate": 3.241374650932348e-05, - "loss": 0.2689, + "epoch": 0.09, + "learning_rate": 4.563264803919375e-05, + "loss": 0.2859, "step": 40060 }, { - "epoch": 0.36, - "learning_rate": 3.240924241059364e-05, - "loss": 0.2738, + "epoch": 0.09, + "learning_rate": 4.563152949598443e-05, + "loss": 0.2799, "step": 40070 }, { - "epoch": 0.36, - "learning_rate": 3.24047383118638e-05, - "loss": 0.2683, + "epoch": 0.09, + "learning_rate": 4.563041095277511e-05, + "loss": 0.2826, "step": 40080 }, { - "epoch": 0.36, - "learning_rate": 3.240023421313395e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.5629292409565785e-05, + "loss": 0.2805, "step": 40090 }, { - "epoch": 0.36, - "learning_rate": 3.239573011440411e-05, - "loss": 0.2713, + "epoch": 0.09, + "learning_rate": 4.562817386635646e-05, + "loss": 0.2772, "step": 40100 }, { - "epoch": 0.36, - "learning_rate": 3.2391226015674264e-05, - "loss": 0.2611, + "epoch": 0.09, + "learning_rate": 4.5627055323147134e-05, + "loss": 0.2806, "step": 40110 }, { - "epoch": 0.36, - "learning_rate": 3.238672191694442e-05, - "loss": 0.2669, + "epoch": 0.09, + "learning_rate": 4.562593677993781e-05, + "loss": 0.2836, "step": 40120 }, { - "epoch": 0.36, - "learning_rate": 3.238221781821458e-05, - "loss": 0.2617, + "epoch": 0.09, + "learning_rate": 4.562481823672849e-05, + "loss": 0.282, "step": 40130 }, { - "epoch": 0.36, - "learning_rate": 3.237771371948473e-05, - "loss": 0.2653, + "epoch": 0.09, + "learning_rate": 4.562369969351916e-05, + "loss": 0.2806, "step": 40140 }, { - "epoch": 0.36, - "learning_rate": 3.2373209620754894e-05, - "loss": 0.2711, + "epoch": 0.09, + "learning_rate": 4.562258115030984e-05, + "loss": 0.2778, "step": 40150 }, { - "epoch": 0.36, - "learning_rate": 3.2368705522025044e-05, - "loss": 0.2699, + "epoch": 0.09, + "learning_rate": 4.562146260710051e-05, + "loss": 0.273, "step": 40160 }, { - "epoch": 0.36, - "learning_rate": 3.2364201423295195e-05, - "loss": 0.2662, + "epoch": 0.09, + "learning_rate": 4.562034406389119e-05, + "loss": 0.2831, "step": 40170 }, { - "epoch": 0.36, - "learning_rate": 3.235969732456536e-05, - "loss": 0.2711, + "epoch": 0.09, + "learning_rate": 4.5619225520681866e-05, + "loss": 0.2876, "step": 40180 }, { - "epoch": 0.36, - "learning_rate": 3.235519322583551e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.5618106977472544e-05, + "loss": 0.282, "step": 40190 }, { - "epoch": 0.36, - "learning_rate": 3.235068912710567e-05, - "loss": 0.2659, + "epoch": 0.09, + "learning_rate": 4.561698843426322e-05, + "loss": 0.2765, "step": 40200 }, { - "epoch": 0.36, - "learning_rate": 3.2346185028375825e-05, - "loss": 0.2731, + "epoch": 0.09, + "learning_rate": 4.561586989105389e-05, + "loss": 0.2838, "step": 40210 }, { - "epoch": 0.36, - "learning_rate": 3.2341680929645976e-05, - "loss": 0.2656, + "epoch": 0.09, + "learning_rate": 4.561475134784457e-05, + "loss": 0.2812, "step": 40220 }, { - "epoch": 0.36, - "learning_rate": 3.233717683091613e-05, - "loss": 0.2703, + "epoch": 0.09, + "learning_rate": 4.561363280463525e-05, + "loss": 0.2792, "step": 40230 }, { - "epoch": 0.36, - "learning_rate": 3.233267273218629e-05, - "loss": 0.2693, + "epoch": 0.09, + "learning_rate": 4.561251426142592e-05, + "loss": 0.2734, "step": 40240 }, { - "epoch": 0.36, - "learning_rate": 3.232816863345645e-05, - "loss": 0.2745, + "epoch": 0.09, + "learning_rate": 4.56113957182166e-05, + "loss": 0.2832, "step": 40250 }, { - "epoch": 0.36, - "learning_rate": 3.2323664534726606e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.561027717500727e-05, + "loss": 0.2827, "step": 40260 }, { - "epoch": 0.36, - "learning_rate": 3.2319160435996756e-05, - "loss": 0.268, + "epoch": 0.09, + "learning_rate": 4.560915863179795e-05, + "loss": 0.275, "step": 40270 }, { - "epoch": 0.36, - "learning_rate": 3.2314656337266914e-05, - "loss": 0.2693, + "epoch": 0.09, + "learning_rate": 4.560804008858862e-05, + "loss": 0.2787, "step": 40280 }, { - "epoch": 0.36, - "learning_rate": 3.231015223853707e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.56069215453793e-05, + "loss": 0.2817, "step": 40290 }, { - "epoch": 0.36, - "learning_rate": 3.230564813980723e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.560580300216998e-05, + "loss": 0.2783, "step": 40300 }, { - "epoch": 0.36, - "learning_rate": 3.230114404107738e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.560468445896065e-05, + "loss": 0.275, "step": 40310 }, { - "epoch": 0.36, - "learning_rate": 3.229663994234754e-05, - "loss": 0.2651, + "epoch": 0.09, + "learning_rate": 4.560356591575133e-05, + "loss": 0.2704, "step": 40320 }, { - "epoch": 0.36, - "learning_rate": 3.2292135843617695e-05, - "loss": 0.2663, + "epoch": 0.09, + "learning_rate": 4.5602447372542e-05, + "loss": 0.2804, "step": 40330 }, { - "epoch": 0.36, - "learning_rate": 3.2287631744887845e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.560132882933268e-05, + "loss": 0.2849, "step": 40340 }, { - "epoch": 0.36, - "learning_rate": 3.228312764615801e-05, - "loss": 0.2646, + "epoch": 0.09, + "learning_rate": 4.560021028612336e-05, + "loss": 0.2804, "step": 40350 }, { - "epoch": 0.36, - "learning_rate": 3.227862354742816e-05, - "loss": 0.2649, + "epoch": 0.09, + "learning_rate": 4.559909174291403e-05, + "loss": 0.283, "step": 40360 }, { - "epoch": 0.36, - "learning_rate": 3.227411944869832e-05, - "loss": 0.2682, + "epoch": 0.09, + "learning_rate": 4.5597973199704706e-05, + "loss": 0.2789, "step": 40370 }, { - "epoch": 0.36, - "learning_rate": 3.2269615349968475e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.559685465649538e-05, + "loss": 0.2812, "step": 40380 }, { - "epoch": 0.36, - "learning_rate": 3.2265111251238626e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.5595736113286055e-05, + "loss": 0.2813, "step": 40390 }, { - "epoch": 0.36, - "learning_rate": 3.226060715250879e-05, - "loss": 0.2747, + "epoch": 0.09, + "learning_rate": 4.559461757007673e-05, + "loss": 0.2776, "step": 40400 }, { - "epoch": 0.36, - "learning_rate": 3.225610305377894e-05, - "loss": 0.2677, + "epoch": 0.09, + "learning_rate": 4.559349902686741e-05, + "loss": 0.2769, "step": 40410 }, { - "epoch": 0.36, - "learning_rate": 3.225159895504909e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.559238048365809e-05, + "loss": 0.2746, "step": 40420 }, { - "epoch": 0.36, - "learning_rate": 3.2247094856319256e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.559126194044876e-05, + "loss": 0.2784, "step": 40430 }, { - "epoch": 0.36, - "learning_rate": 3.224259075758941e-05, - "loss": 0.2702, + "epoch": 0.09, + "learning_rate": 4.559014339723944e-05, + "loss": 0.2783, "step": 40440 }, { - "epoch": 0.36, - "learning_rate": 3.2238086658859564e-05, - "loss": 0.265, + "epoch": 0.09, + "learning_rate": 4.5589024854030116e-05, + "loss": 0.2816, "step": 40450 }, { - "epoch": 0.36, - "learning_rate": 3.223358256012972e-05, - "loss": 0.2685, + "epoch": 0.09, + "learning_rate": 4.558790631082079e-05, + "loss": 0.2813, "step": 40460 }, { - "epoch": 0.36, - "learning_rate": 3.222907846139987e-05, - "loss": 0.268, + "epoch": 0.09, + "learning_rate": 4.5586787767611465e-05, + "loss": 0.2777, "step": 40470 }, { - "epoch": 0.36, - "learning_rate": 3.222457436267003e-05, - "loss": 0.2627, + "epoch": 0.09, + "learning_rate": 4.5585669224402136e-05, + "loss": 0.2807, "step": 40480 }, { - "epoch": 0.36, - "learning_rate": 3.222007026394019e-05, - "loss": 0.2657, + "epoch": 0.09, + "learning_rate": 4.5584550681192814e-05, + "loss": 0.2737, "step": 40490 }, { - "epoch": 0.36, - "learning_rate": 3.2215566165210345e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.558343213798349e-05, + "loss": 0.2802, "step": 40500 }, { - "epoch": 0.36, - "learning_rate": 3.2211062066480496e-05, - "loss": 0.2662, + "epoch": 0.09, + "learning_rate": 4.558231359477417e-05, + "loss": 0.271, "step": 40510 }, { - "epoch": 0.36, - "learning_rate": 3.220655796775065e-05, - "loss": 0.2663, + "epoch": 0.09, + "learning_rate": 4.558119505156485e-05, + "loss": 0.2753, "step": 40520 }, { - "epoch": 0.36, - "learning_rate": 3.220205386902081e-05, - "loss": 0.2605, + "epoch": 0.09, + "learning_rate": 4.558007650835552e-05, + "loss": 0.2734, "step": 40530 }, { - "epoch": 0.36, - "learning_rate": 3.219754977029097e-05, - "loss": 0.2652, + "epoch": 0.09, + "learning_rate": 4.55789579651462e-05, + "loss": 0.277, "step": 40540 }, { - "epoch": 0.36, - "learning_rate": 3.2193045671561126e-05, - "loss": 0.2686, + "epoch": 0.09, + "learning_rate": 4.5577839421936875e-05, + "loss": 0.2778, "step": 40550 }, { - "epoch": 0.36, - "learning_rate": 3.2188541572831276e-05, - "loss": 0.2665, + "epoch": 0.09, + "learning_rate": 4.5576720878727546e-05, + "loss": 0.2822, "step": 40560 }, { - "epoch": 0.36, - "learning_rate": 3.2184037474101434e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.5575602335518224e-05, + "loss": 0.2828, "step": 40570 }, { - "epoch": 0.36, - "learning_rate": 3.217953337537159e-05, - "loss": 0.2659, + "epoch": 0.09, + "learning_rate": 4.5574483792308895e-05, + "loss": 0.2744, "step": 40580 }, { - "epoch": 0.36, - "learning_rate": 3.217502927664174e-05, - "loss": 0.2583, + "epoch": 0.09, + "learning_rate": 4.557336524909957e-05, + "loss": 0.2781, "step": 40590 }, { - "epoch": 0.36, - "learning_rate": 3.2170525177911906e-05, - "loss": 0.2675, + "epoch": 0.09, + "learning_rate": 4.557224670589025e-05, + "loss": 0.2759, "step": 40600 }, { - "epoch": 0.36, - "learning_rate": 3.216602107918206e-05, - "loss": 0.2613, + "epoch": 0.09, + "learning_rate": 4.557112816268093e-05, + "loss": 0.2796, "step": 40610 }, { - "epoch": 0.36, - "learning_rate": 3.216151698045221e-05, - "loss": 0.2596, + "epoch": 0.09, + "learning_rate": 4.557000961947161e-05, + "loss": 0.2811, "step": 40620 }, { - "epoch": 0.36, - "learning_rate": 3.215701288172237e-05, - "loss": 0.2678, + "epoch": 0.09, + "learning_rate": 4.556889107626228e-05, + "loss": 0.2736, "step": 40630 }, { - "epoch": 0.36, - "learning_rate": 3.215250878299252e-05, - "loss": 0.2656, + "epoch": 0.09, + "learning_rate": 4.5567772533052956e-05, + "loss": 0.2762, "step": 40640 }, { - "epoch": 0.36, - "learning_rate": 3.214800468426268e-05, - "loss": 0.2681, + "epoch": 0.09, + "learning_rate": 4.556665398984363e-05, + "loss": 0.2763, "step": 40650 }, { - "epoch": 0.36, - "learning_rate": 3.214350058553284e-05, - "loss": 0.2667, + "epoch": 0.09, + "learning_rate": 4.5565535446634305e-05, + "loss": 0.2842, "step": 40660 }, { - "epoch": 0.36, - "learning_rate": 3.213899648680299e-05, - "loss": 0.2585, + "epoch": 0.09, + "learning_rate": 4.556441690342498e-05, + "loss": 0.2802, "step": 40670 }, { - "epoch": 0.36, - "learning_rate": 3.213449238807315e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.5563298360215654e-05, + "loss": 0.2858, "step": 40680 }, { - "epoch": 0.36, - "learning_rate": 3.21299882893433e-05, - "loss": 0.2621, + "epoch": 0.09, + "learning_rate": 4.556217981700633e-05, + "loss": 0.2788, "step": 40690 }, { - "epoch": 0.36, - "learning_rate": 3.212548419061346e-05, - "loss": 0.2666, + "epoch": 0.09, + "learning_rate": 4.5561061273797e-05, + "loss": 0.279, "step": 40700 }, { - "epoch": 0.36, - "learning_rate": 3.212098009188362e-05, - "loss": 0.2602, + "epoch": 0.09, + "learning_rate": 4.555994273058769e-05, + "loss": 0.2749, "step": 40710 }, { - "epoch": 0.36, - "learning_rate": 3.211647599315377e-05, - "loss": 0.2652, + "epoch": 0.09, + "learning_rate": 4.5558824187378366e-05, + "loss": 0.2785, "step": 40720 }, { - "epoch": 0.36, - "learning_rate": 3.2111971894423927e-05, - "loss": 0.2665, + "epoch": 0.09, + "learning_rate": 4.555770564416904e-05, + "loss": 0.2827, "step": 40730 }, { - "epoch": 0.36, - "learning_rate": 3.2107467795694084e-05, - "loss": 0.2643, + "epoch": 0.09, + "learning_rate": 4.5556587100959715e-05, + "loss": 0.2746, "step": 40740 }, { - "epoch": 0.36, - "learning_rate": 3.210296369696424e-05, - "loss": 0.2622, + "epoch": 0.09, + "learning_rate": 4.5555468557750386e-05, + "loss": 0.2735, "step": 40750 }, { - "epoch": 0.36, - "learning_rate": 3.209845959823439e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.5554350014541064e-05, + "loss": 0.2822, "step": 40760 }, { - "epoch": 0.36, - "learning_rate": 3.209395549950455e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.555323147133174e-05, + "loss": 0.28, "step": 40770 }, { - "epoch": 0.36, - "learning_rate": 3.208945140077471e-05, - "loss": 0.2638, + "epoch": 0.09, + "learning_rate": 4.555211292812241e-05, + "loss": 0.2762, "step": 40780 }, { - "epoch": 0.36, - "learning_rate": 3.208494730204486e-05, - "loss": 0.2623, + "epoch": 0.09, + "learning_rate": 4.555099438491309e-05, + "loss": 0.2765, "step": 40790 }, { - "epoch": 0.36, - "learning_rate": 3.208044320331502e-05, - "loss": 0.2674, + "epoch": 0.09, + "learning_rate": 4.554987584170376e-05, + "loss": 0.274, "step": 40800 }, { - "epoch": 0.36, - "learning_rate": 3.207593910458517e-05, - "loss": 0.2717, + "epoch": 0.09, + "learning_rate": 4.554875729849444e-05, + "loss": 0.2787, "step": 40810 }, { - "epoch": 0.36, - "learning_rate": 3.207143500585533e-05, - "loss": 0.2671, + "epoch": 0.09, + "learning_rate": 4.554763875528512e-05, + "loss": 0.2817, "step": 40820 }, { - "epoch": 0.36, - "learning_rate": 3.206693090712549e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.5546520212075796e-05, + "loss": 0.277, "step": 40830 }, { - "epoch": 0.36, - "learning_rate": 3.206242680839564e-05, - "loss": 0.2624, + "epoch": 0.09, + "learning_rate": 4.5545401668866474e-05, + "loss": 0.2789, "step": 40840 }, { - "epoch": 0.36, - "learning_rate": 3.20579227096658e-05, - "loss": 0.2616, + "epoch": 0.09, + "learning_rate": 4.5544283125657145e-05, + "loss": 0.2813, "step": 40850 }, { - "epoch": 0.36, - "learning_rate": 3.2053418610935954e-05, - "loss": 0.2722, + "epoch": 0.09, + "learning_rate": 4.554316458244782e-05, + "loss": 0.2771, "step": 40860 }, { - "epoch": 0.36, - "learning_rate": 3.2048914512206104e-05, - "loss": 0.2619, + "epoch": 0.09, + "learning_rate": 4.55420460392385e-05, + "loss": 0.2823, "step": 40870 }, { - "epoch": 0.36, - "learning_rate": 3.204441041347627e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.554092749602917e-05, + "loss": 0.2742, "step": 40880 }, { - "epoch": 0.37, - "learning_rate": 3.203990631474642e-05, - "loss": 0.267, + "epoch": 0.09, + "learning_rate": 4.553980895281985e-05, + "loss": 0.2761, "step": 40890 }, { - "epoch": 0.37, - "learning_rate": 3.203540221601658e-05, - "loss": 0.2683, + "epoch": 0.09, + "learning_rate": 4.553869040961052e-05, + "loss": 0.2857, "step": 40900 }, { - "epoch": 0.37, - "learning_rate": 3.2030898117286734e-05, - "loss": 0.2646, + "epoch": 0.09, + "learning_rate": 4.55375718664012e-05, + "loss": 0.2817, "step": 40910 }, { - "epoch": 0.37, - "learning_rate": 3.2026394018556885e-05, - "loss": 0.2635, + "epoch": 0.09, + "learning_rate": 4.553656517751281e-05, + "loss": 0.2725, "step": 40920 }, { - "epoch": 0.37, - "learning_rate": 3.202188991982704e-05, - "loss": 0.2689, + "epoch": 0.09, + "learning_rate": 4.5535446634303486e-05, + "loss": 0.2792, "step": 40930 }, { - "epoch": 0.37, - "learning_rate": 3.20173858210972e-05, - "loss": 0.2656, + "epoch": 0.09, + "learning_rate": 4.5534328091094164e-05, + "loss": 0.271, "step": 40940 }, { - "epoch": 0.37, - "learning_rate": 3.201288172236736e-05, - "loss": 0.268, + "epoch": 0.09, + "learning_rate": 4.5533209547884835e-05, + "loss": 0.2748, "step": 40950 }, { - "epoch": 0.37, - "learning_rate": 3.2008377623637515e-05, - "loss": 0.2719, + "epoch": 0.09, + "learning_rate": 4.553209100467551e-05, + "loss": 0.2789, "step": 40960 }, { - "epoch": 0.37, - "learning_rate": 3.2003873524907666e-05, - "loss": 0.2611, + "epoch": 0.09, + "learning_rate": 4.5530972461466184e-05, + "loss": 0.2795, "step": 40970 }, { - "epoch": 0.37, - "learning_rate": 3.199936942617782e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.552985391825686e-05, + "loss": 0.2777, "step": 40980 }, { - "epoch": 0.37, - "learning_rate": 3.199486532744798e-05, - "loss": 0.2631, + "epoch": 0.09, + "learning_rate": 4.552873537504754e-05, + "loss": 0.275, "step": 40990 }, { - "epoch": 0.37, - "learning_rate": 3.199036122871814e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.552761683183822e-05, + "loss": 0.2769, "step": 41000 }, { - "epoch": 0.37, - "learning_rate": 3.198585712998829e-05, - "loss": 0.2657, + "epoch": 0.09, + "learning_rate": 4.5526498288628896e-05, + "loss": 0.2793, "step": 41010 }, { - "epoch": 0.37, - "learning_rate": 3.1981353031258446e-05, - "loss": 0.2631, + "epoch": 0.09, + "learning_rate": 4.552537974541957e-05, + "loss": 0.2778, "step": 41020 }, { - "epoch": 0.37, - "learning_rate": 3.1976848932528604e-05, - "loss": 0.263, + "epoch": 0.09, + "learning_rate": 4.5524261202210245e-05, + "loss": 0.2814, "step": 41030 }, { - "epoch": 0.37, - "learning_rate": 3.1972344833798755e-05, - "loss": 0.2643, + "epoch": 0.09, + "learning_rate": 4.5523142659000916e-05, + "loss": 0.2796, "step": 41040 }, { - "epoch": 0.37, - "learning_rate": 3.196784073506892e-05, - "loss": 0.266, + "epoch": 0.09, + "learning_rate": 4.5522024115791594e-05, + "loss": 0.279, "step": 41050 }, { - "epoch": 0.37, - "learning_rate": 3.196333663633907e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.552090557258227e-05, + "loss": 0.2785, "step": 41060 }, { - "epoch": 0.37, - "learning_rate": 3.195883253760922e-05, - "loss": 0.2692, + "epoch": 0.09, + "learning_rate": 4.551978702937294e-05, + "loss": 0.2767, "step": 41070 }, { - "epoch": 0.37, - "learning_rate": 3.1954328438879385e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.551866848616362e-05, + "loss": 0.2802, "step": 41080 }, { - "epoch": 0.37, - "learning_rate": 3.1949824340149535e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.55175499429543e-05, + "loss": 0.2724, "step": 41090 }, { - "epoch": 0.37, - "learning_rate": 3.19453202414197e-05, - "loss": 0.2608, + "epoch": 0.09, + "learning_rate": 4.551643139974498e-05, + "loss": 0.2849, "step": 41100 }, { - "epoch": 0.37, - "learning_rate": 3.194081614268985e-05, - "loss": 0.261, + "epoch": 0.09, + "learning_rate": 4.5515312856535655e-05, + "loss": 0.2819, "step": 41110 }, { - "epoch": 0.37, - "learning_rate": 3.193631204396e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.5514194313326326e-05, + "loss": 0.2787, "step": 41120 }, { - "epoch": 0.37, - "learning_rate": 3.1931807945230165e-05, - "loss": 0.2611, + "epoch": 0.09, + "learning_rate": 4.5513075770117004e-05, + "loss": 0.2767, "step": 41130 }, { - "epoch": 0.37, - "learning_rate": 3.1927303846500316e-05, - "loss": 0.263, + "epoch": 0.09, + "learning_rate": 4.5511957226907675e-05, + "loss": 0.2808, "step": 41140 }, { - "epoch": 0.37, - "learning_rate": 3.1922799747770473e-05, - "loss": 0.2615, + "epoch": 0.09, + "learning_rate": 4.551083868369835e-05, + "loss": 0.2816, "step": 41150 }, { - "epoch": 0.37, - "learning_rate": 3.191829564904063e-05, - "loss": 0.2655, + "epoch": 0.09, + "learning_rate": 4.550972014048903e-05, + "loss": 0.2774, "step": 41160 }, { - "epoch": 0.37, - "learning_rate": 3.191379155031078e-05, - "loss": 0.2692, + "epoch": 0.09, + "learning_rate": 4.55086015972797e-05, + "loss": 0.2746, "step": 41170 }, { - "epoch": 0.37, - "learning_rate": 3.190928745158094e-05, - "loss": 0.2632, + "epoch": 0.09, + "learning_rate": 4.550748305407038e-05, + "loss": 0.2771, "step": 41180 }, { - "epoch": 0.37, - "learning_rate": 3.19047833528511e-05, - "loss": 0.2671, + "epoch": 0.09, + "learning_rate": 4.550636451086106e-05, + "loss": 0.2741, "step": 41190 }, { - "epoch": 0.37, - "learning_rate": 3.1900279254121254e-05, - "loss": 0.2636, + "epoch": 0.09, + "learning_rate": 4.5505245967651736e-05, + "loss": 0.2712, "step": 41200 }, { - "epoch": 0.37, - "learning_rate": 3.1895775155391405e-05, - "loss": 0.2579, + "epoch": 0.09, + "learning_rate": 4.5504127424442414e-05, + "loss": 0.2794, "step": 41210 }, { - "epoch": 0.37, - "learning_rate": 3.189127105666156e-05, - "loss": 0.2599, + "epoch": 0.09, + "learning_rate": 4.5503008881233085e-05, + "loss": 0.281, "step": 41220 }, { - "epoch": 0.37, - "learning_rate": 3.188676695793172e-05, - "loss": 0.2624, + "epoch": 0.09, + "learning_rate": 4.550189033802376e-05, + "loss": 0.2757, "step": 41230 }, { - "epoch": 0.37, - "learning_rate": 3.188226285920188e-05, - "loss": 0.2624, + "epoch": 0.09, + "learning_rate": 4.5500771794814434e-05, + "loss": 0.283, "step": 41240 }, { - "epoch": 0.37, - "learning_rate": 3.1877758760472035e-05, - "loss": 0.27, + "epoch": 0.09, + "learning_rate": 4.549965325160511e-05, + "loss": 0.2752, "step": 41250 }, { - "epoch": 0.37, - "learning_rate": 3.1873254661742186e-05, - "loss": 0.2622, + "epoch": 0.09, + "learning_rate": 4.549853470839579e-05, + "loss": 0.278, "step": 41260 }, { - "epoch": 0.37, - "learning_rate": 3.186875056301234e-05, - "loss": 0.2584, + "epoch": 0.09, + "learning_rate": 4.549741616518646e-05, + "loss": 0.2757, "step": 41270 }, { - "epoch": 0.37, - "learning_rate": 3.18642464642825e-05, - "loss": 0.2595, + "epoch": 0.09, + "learning_rate": 4.549629762197714e-05, + "loss": 0.2786, "step": 41280 }, { - "epoch": 0.37, - "learning_rate": 3.185974236555265e-05, - "loss": 0.2687, + "epoch": 0.09, + "learning_rate": 4.549517907876782e-05, + "loss": 0.2846, "step": 41290 }, { - "epoch": 0.37, - "learning_rate": 3.1855238266822815e-05, - "loss": 0.2702, + "epoch": 0.09, + "learning_rate": 4.5494060535558495e-05, + "loss": 0.2754, "step": 41300 }, { - "epoch": 0.37, - "learning_rate": 3.1850734168092966e-05, - "loss": 0.2644, + "epoch": 0.09, + "learning_rate": 4.5492941992349166e-05, + "loss": 0.2741, "step": 41310 }, { - "epoch": 0.37, - "learning_rate": 3.184623006936312e-05, - "loss": 0.2612, + "epoch": 0.09, + "learning_rate": 4.5491823449139844e-05, + "loss": 0.2765, "step": 41320 }, { - "epoch": 0.37, - "learning_rate": 3.184172597063328e-05, - "loss": 0.2621, + "epoch": 0.09, + "learning_rate": 4.549070490593052e-05, + "loss": 0.2771, "step": 41330 }, { - "epoch": 0.37, - "learning_rate": 3.183722187190343e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.548958636272119e-05, + "loss": 0.2747, "step": 41340 }, { - "epoch": 0.37, - "learning_rate": 3.183271777317359e-05, - "loss": 0.2648, + "epoch": 0.09, + "learning_rate": 4.548846781951187e-05, + "loss": 0.2755, "step": 41350 }, { - "epoch": 0.37, - "learning_rate": 3.182821367444375e-05, - "loss": 0.2645, + "epoch": 0.09, + "learning_rate": 4.548734927630254e-05, + "loss": 0.2743, "step": 41360 }, { - "epoch": 0.37, - "learning_rate": 3.18237095757139e-05, - "loss": 0.2577, + "epoch": 0.09, + "learning_rate": 4.548623073309322e-05, + "loss": 0.2735, "step": 41370 }, { - "epoch": 0.37, - "learning_rate": 3.181920547698406e-05, - "loss": 0.2639, + "epoch": 0.09, + "learning_rate": 4.54851121898839e-05, + "loss": 0.2772, "step": 41380 }, { - "epoch": 0.37, - "learning_rate": 3.181470137825421e-05, - "loss": 0.2602, + "epoch": 0.09, + "learning_rate": 4.548399364667457e-05, + "loss": 0.2741, "step": 41390 }, { - "epoch": 0.37, - "learning_rate": 3.181019727952437e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.548287510346525e-05, + "loss": 0.2718, "step": 41400 }, { - "epoch": 0.37, - "learning_rate": 3.180569318079453e-05, - "loss": 0.2639, + "epoch": 0.09, + "learning_rate": 4.5481756560255925e-05, + "loss": 0.2731, "step": 41410 }, { - "epoch": 0.37, - "learning_rate": 3.180118908206468e-05, - "loss": 0.2644, + "epoch": 0.09, + "learning_rate": 4.54806380170466e-05, + "loss": 0.271, "step": 41420 }, { - "epoch": 0.37, - "learning_rate": 3.1796684983334836e-05, - "loss": 0.2613, + "epoch": 0.09, + "learning_rate": 4.547951947383728e-05, + "loss": 0.2713, "step": 41430 }, { - "epoch": 0.37, - "learning_rate": 3.179263129447797e-05, - "loss": 0.2675, + "epoch": 0.09, + "learning_rate": 4.547840093062795e-05, + "loss": 0.2726, "step": 41440 }, { - "epoch": 0.37, - "learning_rate": 3.178812719574813e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.547728238741863e-05, + "loss": 0.2746, "step": 41450 }, { - "epoch": 0.37, - "learning_rate": 3.178362309701829e-05, - "loss": 0.2612, + "epoch": 0.09, + "learning_rate": 4.54761638442093e-05, + "loss": 0.277, "step": 41460 }, { - "epoch": 0.37, - "learning_rate": 3.1779118998288445e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.547504530099998e-05, + "loss": 0.2746, "step": 41470 }, { - "epoch": 0.37, - "learning_rate": 3.17746148995586e-05, - "loss": 0.26, + "epoch": 0.09, + "learning_rate": 4.547392675779066e-05, + "loss": 0.2762, "step": 41480 }, { - "epoch": 0.37, - "learning_rate": 3.1770110800828753e-05, - "loss": 0.2614, + "epoch": 0.09, + "learning_rate": 4.547280821458133e-05, + "loss": 0.2749, "step": 41490 }, { - "epoch": 0.37, - "learning_rate": 3.176560670209891e-05, - "loss": 0.2657, + "epoch": 0.09, + "learning_rate": 4.5471689671372006e-05, + "loss": 0.2756, "step": 41500 }, { - "epoch": 0.37, - "learning_rate": 3.176110260336907e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.5470571128162684e-05, + "loss": 0.2796, "step": 41510 }, { - "epoch": 0.37, - "learning_rate": 3.1756598504639226e-05, - "loss": 0.2564, + "epoch": 0.09, + "learning_rate": 4.546945258495336e-05, + "loss": 0.2809, "step": 41520 }, { - "epoch": 0.37, - "learning_rate": 3.175209440590938e-05, - "loss": 0.2605, + "epoch": 0.09, + "learning_rate": 4.546833404174404e-05, + "loss": 0.2796, "step": 41530 }, { - "epoch": 0.37, - "learning_rate": 3.1747590307179534e-05, - "loss": 0.2548, + "epoch": 0.09, + "learning_rate": 4.546721549853471e-05, + "loss": 0.2773, "step": 41540 }, { - "epoch": 0.37, - "learning_rate": 3.174308620844969e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.546609695532539e-05, + "loss": 0.2736, "step": 41550 }, { - "epoch": 0.37, - "learning_rate": 3.173858210971984e-05, - "loss": 0.2616, + "epoch": 0.09, + "learning_rate": 4.546497841211606e-05, + "loss": 0.2768, "step": 41560 }, { - "epoch": 0.37, - "learning_rate": 3.173407801099001e-05, - "loss": 0.264, + "epoch": 0.09, + "learning_rate": 4.546385986890674e-05, + "loss": 0.2711, "step": 41570 }, { - "epoch": 0.37, - "learning_rate": 3.172957391226016e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.5462741325697416e-05, + "loss": 0.2774, "step": 41580 }, { - "epoch": 0.37, - "learning_rate": 3.1725069813530315e-05, - "loss": 0.27, + "epoch": 0.09, + "learning_rate": 4.546162278248809e-05, + "loss": 0.2747, "step": 41590 }, { - "epoch": 0.37, - "learning_rate": 3.172056571480047e-05, - "loss": 0.2617, + "epoch": 0.09, + "learning_rate": 4.5460504239278765e-05, + "loss": 0.2755, "step": 41600 }, { - "epoch": 0.37, - "learning_rate": 3.171606161607062e-05, - "loss": 0.2648, + "epoch": 0.09, + "learning_rate": 4.545938569606944e-05, + "loss": 0.2789, "step": 41610 }, { - "epoch": 0.37, - "learning_rate": 3.171155751734079e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.545826715286012e-05, + "loss": 0.2714, "step": 41620 }, { - "epoch": 0.37, - "learning_rate": 3.170705341861094e-05, - "loss": 0.2629, + "epoch": 0.09, + "learning_rate": 4.545714860965079e-05, + "loss": 0.274, "step": 41630 }, { - "epoch": 0.37, - "learning_rate": 3.170254931988109e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.545603006644147e-05, + "loss": 0.2766, "step": 41640 }, { - "epoch": 0.37, - "learning_rate": 3.169804522115125e-05, - "loss": 0.2621, + "epoch": 0.09, + "learning_rate": 4.545491152323215e-05, + "loss": 0.2776, "step": 41650 }, { - "epoch": 0.37, - "learning_rate": 3.1693541122421404e-05, - "loss": 0.2604, + "epoch": 0.09, + "learning_rate": 4.545379298002282e-05, + "loss": 0.2854, "step": 41660 }, { - "epoch": 0.37, - "learning_rate": 3.168903702369156e-05, - "loss": 0.2635, + "epoch": 0.09, + "learning_rate": 4.5452674436813497e-05, + "loss": 0.2776, "step": 41670 }, { - "epoch": 0.37, - "learning_rate": 3.168453292496172e-05, - "loss": 0.2625, + "epoch": 0.09, + "learning_rate": 4.545155589360417e-05, + "loss": 0.2687, "step": 41680 }, { - "epoch": 0.37, - "learning_rate": 3.168002882623187e-05, - "loss": 0.2606, + "epoch": 0.09, + "learning_rate": 4.5450437350394846e-05, + "loss": 0.2791, "step": 41690 }, { - "epoch": 0.37, - "learning_rate": 3.167552472750203e-05, - "loss": 0.2743, + "epoch": 0.09, + "learning_rate": 4.5449318807185524e-05, + "loss": 0.2757, "step": 41700 }, { - "epoch": 0.37, - "learning_rate": 3.1671020628772184e-05, - "loss": 0.2694, + "epoch": 0.09, + "learning_rate": 4.54482002639762e-05, + "loss": 0.2766, "step": 41710 }, { - "epoch": 0.37, - "learning_rate": 3.166651653004234e-05, - "loss": 0.2619, + "epoch": 0.09, + "learning_rate": 4.544708172076688e-05, + "loss": 0.2779, "step": 41720 }, { - "epoch": 0.37, - "learning_rate": 3.166201243131249e-05, - "loss": 0.2685, + "epoch": 0.09, + "learning_rate": 4.544596317755755e-05, + "loss": 0.2746, "step": 41730 }, { - "epoch": 0.37, - "learning_rate": 3.165750833258265e-05, - "loss": 0.2651, + "epoch": 0.09, + "learning_rate": 4.544484463434823e-05, + "loss": 0.2791, "step": 41740 }, { - "epoch": 0.37, - "learning_rate": 3.165300423385281e-05, - "loss": 0.2682, + "epoch": 0.09, + "learning_rate": 4.5443726091138906e-05, + "loss": 0.276, "step": 41750 }, { - "epoch": 0.37, - "learning_rate": 3.1648500135122965e-05, - "loss": 0.2676, + "epoch": 0.09, + "learning_rate": 4.544260754792958e-05, + "loss": 0.2794, "step": 41760 }, { - "epoch": 0.37, - "learning_rate": 3.164399603639312e-05, - "loss": 0.2594, + "epoch": 0.09, + "learning_rate": 4.5441489004720256e-05, + "loss": 0.2765, "step": 41770 }, { - "epoch": 0.37, - "learning_rate": 3.163949193766327e-05, - "loss": 0.264, + "epoch": 0.09, + "learning_rate": 4.544037046151093e-05, + "loss": 0.2747, "step": 41780 }, { - "epoch": 0.37, - "learning_rate": 3.163498783893343e-05, - "loss": 0.2587, + "epoch": 0.09, + "learning_rate": 4.5439251918301605e-05, + "loss": 0.277, "step": 41790 }, { - "epoch": 0.37, - "learning_rate": 3.163048374020359e-05, - "loss": 0.2622, + "epoch": 0.09, + "learning_rate": 4.543813337509228e-05, + "loss": 0.2767, "step": 41800 }, { - "epoch": 0.37, - "learning_rate": 3.162597964147374e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.5437014831882954e-05, + "loss": 0.2755, "step": 41810 }, { - "epoch": 0.37, - "learning_rate": 3.16214755427439e-05, - "loss": 0.2641, + "epoch": 0.09, + "learning_rate": 4.543589628867363e-05, + "loss": 0.2747, "step": 41820 }, { - "epoch": 0.37, - "learning_rate": 3.1616971444014054e-05, - "loss": 0.2595, + "epoch": 0.09, + "learning_rate": 4.543477774546431e-05, + "loss": 0.2725, "step": 41830 }, { - "epoch": 0.37, - "learning_rate": 3.1612467345284205e-05, - "loss": 0.2653, + "epoch": 0.09, + "learning_rate": 4.543365920225499e-05, + "loss": 0.2695, "step": 41840 }, { - "epoch": 0.37, - "learning_rate": 3.160796324655437e-05, - "loss": 0.2586, + "epoch": 0.09, + "learning_rate": 4.5432540659045665e-05, + "loss": 0.2792, "step": 41850 }, { - "epoch": 0.37, - "learning_rate": 3.160345914782452e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.5431422115836337e-05, + "loss": 0.2742, "step": 41860 }, { - "epoch": 0.37, - "learning_rate": 3.159895504909468e-05, - "loss": 0.2624, + "epoch": 0.09, + "learning_rate": 4.5430303572627014e-05, + "loss": 0.2723, "step": 41870 }, { - "epoch": 0.37, - "learning_rate": 3.1594450950364835e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.5429185029417686e-05, + "loss": 0.2771, "step": 41880 }, { - "epoch": 0.37, - "learning_rate": 3.1589946851634985e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.5428066486208364e-05, + "loss": 0.2741, "step": 41890 }, { - "epoch": 0.37, - "learning_rate": 3.158544275290515e-05, - "loss": 0.2633, + "epoch": 0.09, + "learning_rate": 4.542694794299904e-05, + "loss": 0.2772, "step": 41900 }, { - "epoch": 0.37, - "learning_rate": 3.15809386541753e-05, - "loss": 0.2643, + "epoch": 0.09, + "learning_rate": 4.542582939978971e-05, + "loss": 0.2672, "step": 41910 }, { - "epoch": 0.37, - "learning_rate": 3.157643455544546e-05, - "loss": 0.2573, + "epoch": 0.09, + "learning_rate": 4.542471085658039e-05, + "loss": 0.2736, "step": 41920 }, { - "epoch": 0.37, - "learning_rate": 3.1571930456715615e-05, - "loss": 0.2619, + "epoch": 0.09, + "learning_rate": 4.542359231337107e-05, + "loss": 0.2777, "step": 41930 }, { - "epoch": 0.37, - "learning_rate": 3.1567426357985766e-05, - "loss": 0.2663, + "epoch": 0.09, + "learning_rate": 4.5422473770161746e-05, + "loss": 0.2774, "step": 41940 }, { - "epoch": 0.37, - "learning_rate": 3.1562922259255924e-05, - "loss": 0.2607, + "epoch": 0.09, + "learning_rate": 4.542135522695242e-05, + "loss": 0.2743, "step": 41950 }, { - "epoch": 0.37, - "learning_rate": 3.155841816052608e-05, - "loss": 0.2649, + "epoch": 0.09, + "learning_rate": 4.5420236683743096e-05, + "loss": 0.2741, "step": 41960 }, { - "epoch": 0.37, - "learning_rate": 3.155391406179624e-05, - "loss": 0.261, + "epoch": 0.09, + "learning_rate": 4.5419118140533773e-05, + "loss": 0.2769, "step": 41970 }, { - "epoch": 0.37, - "learning_rate": 3.154940996306639e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.5417999597324445e-05, + "loss": 0.276, "step": 41980 }, { - "epoch": 0.37, - "learning_rate": 3.154490586433655e-05, - "loss": 0.2536, + "epoch": 0.09, + "learning_rate": 4.541688105411512e-05, + "loss": 0.2759, "step": 41990 }, { - "epoch": 0.37, - "learning_rate": 3.1540401765606704e-05, - "loss": 0.2601, + "epoch": 0.09, + "learning_rate": 4.5415762510905794e-05, + "loss": 0.2757, "step": 42000 }, { - "epoch": 0.38, - "learning_rate": 3.1535897666876855e-05, - "loss": 0.2599, + "epoch": 0.09, + "learning_rate": 4.541464396769647e-05, + "loss": 0.2708, "step": 42010 }, { - "epoch": 0.38, - "learning_rate": 3.153139356814702e-05, - "loss": 0.2597, + "epoch": 0.09, + "learning_rate": 4.541352542448715e-05, + "loss": 0.273, "step": 42020 }, { - "epoch": 0.38, - "learning_rate": 3.152688946941717e-05, - "loss": 0.2634, + "epoch": 0.09, + "learning_rate": 4.541240688127783e-05, + "loss": 0.2733, "step": 42030 }, { - "epoch": 0.38, - "learning_rate": 3.152238537068733e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.5411288338068505e-05, + "loss": 0.2734, "step": 42040 }, { - "epoch": 0.38, - "learning_rate": 3.1517881271957485e-05, - "loss": 0.2565, + "epoch": 0.09, + "learning_rate": 4.5410169794859177e-05, + "loss": 0.2731, "step": 42050 }, { - "epoch": 0.38, - "learning_rate": 3.1513377173227636e-05, - "loss": 0.2613, + "epoch": 0.09, + "learning_rate": 4.5409051251649854e-05, + "loss": 0.2754, "step": 42060 }, { - "epoch": 0.38, - "learning_rate": 3.15088730744978e-05, - "loss": 0.2639, + "epoch": 0.09, + "learning_rate": 4.540793270844053e-05, + "loss": 0.2699, "step": 42070 }, { - "epoch": 0.38, - "learning_rate": 3.150436897576795e-05, - "loss": 0.261, + "epoch": 0.09, + "learning_rate": 4.5406814165231204e-05, + "loss": 0.272, "step": 42080 }, { - "epoch": 0.38, - "learning_rate": 3.14998648770381e-05, - "loss": 0.2608, + "epoch": 0.09, + "learning_rate": 4.540569562202188e-05, + "loss": 0.2683, "step": 42090 }, { - "epoch": 0.38, - "learning_rate": 3.1495360778308266e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.540457707881255e-05, + "loss": 0.278, "step": 42100 }, { - "epoch": 0.38, - "learning_rate": 3.1490856679578416e-05, - "loss": 0.2672, + "epoch": 0.09, + "learning_rate": 4.540345853560323e-05, + "loss": 0.2726, "step": 42110 }, { - "epoch": 0.38, - "learning_rate": 3.1486352580848574e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.540233999239391e-05, + "loss": 0.2778, "step": 42120 }, { - "epoch": 0.38, - "learning_rate": 3.148184848211873e-05, - "loss": 0.2662, + "epoch": 0.09, + "learning_rate": 4.5401221449184586e-05, + "loss": 0.2755, "step": 42130 }, { - "epoch": 0.38, - "learning_rate": 3.147734438338888e-05, - "loss": 0.2614, + "epoch": 0.09, + "learning_rate": 4.5400102905975264e-05, + "loss": 0.27, "step": 42140 }, { - "epoch": 0.38, - "learning_rate": 3.147284028465904e-05, - "loss": 0.2646, + "epoch": 0.09, + "learning_rate": 4.5398984362765935e-05, + "loss": 0.2761, "step": 42150 }, { - "epoch": 0.38, - "learning_rate": 3.14683361859292e-05, - "loss": 0.2641, + "epoch": 0.09, + "learning_rate": 4.5397865819556613e-05, + "loss": 0.2734, "step": 42160 }, { - "epoch": 0.38, - "learning_rate": 3.1463832087199355e-05, - "loss": 0.263, + "epoch": 0.09, + "learning_rate": 4.539674727634729e-05, + "loss": 0.2811, "step": 42170 }, { - "epoch": 0.38, - "learning_rate": 3.145932798846951e-05, - "loss": 0.2633, + "epoch": 0.09, + "learning_rate": 4.539562873313796e-05, + "loss": 0.2714, "step": 42180 }, { - "epoch": 0.38, - "learning_rate": 3.145482388973966e-05, - "loss": 0.2688, + "epoch": 0.09, + "learning_rate": 4.539451018992864e-05, + "loss": 0.2717, "step": 42190 }, { - "epoch": 0.38, - "learning_rate": 3.145031979100982e-05, - "loss": 0.2616, + "epoch": 0.09, + "learning_rate": 4.539339164671931e-05, + "loss": 0.2767, "step": 42200 }, { - "epoch": 0.38, - "learning_rate": 3.144581569227998e-05, - "loss": 0.2652, + "epoch": 0.09, + "learning_rate": 4.539227310350999e-05, + "loss": 0.2709, "step": 42210 }, { - "epoch": 0.38, - "learning_rate": 3.1441311593550135e-05, - "loss": 0.2593, + "epoch": 0.09, + "learning_rate": 4.539115456030066e-05, + "loss": 0.2743, "step": 42220 }, { - "epoch": 0.38, - "learning_rate": 3.1436807494820286e-05, - "loss": 0.2574, + "epoch": 0.09, + "learning_rate": 4.539003601709134e-05, + "loss": 0.2693, "step": 42230 }, { - "epoch": 0.38, - "learning_rate": 3.1432303396090443e-05, - "loss": 0.2618, + "epoch": 0.09, + "learning_rate": 4.538891747388202e-05, + "loss": 0.2734, "step": 42240 }, { - "epoch": 0.38, - "learning_rate": 3.14277992973606e-05, - "loss": 0.2631, + "epoch": 0.09, + "learning_rate": 4.5387798930672694e-05, + "loss": 0.2751, "step": 42250 }, { - "epoch": 0.38, - "learning_rate": 3.142329519863075e-05, - "loss": 0.2557, + "epoch": 0.09, + "learning_rate": 4.538668038746337e-05, + "loss": 0.28, "step": 42260 }, { - "epoch": 0.38, - "learning_rate": 3.1418791099900916e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.5385561844254044e-05, + "loss": 0.2713, "step": 42270 }, { - "epoch": 0.38, - "learning_rate": 3.1414287001171067e-05, - "loss": 0.2625, + "epoch": 0.09, + "learning_rate": 4.538444330104472e-05, + "loss": 0.2789, "step": 42280 }, { - "epoch": 0.38, - "learning_rate": 3.140978290244122e-05, - "loss": 0.2629, + "epoch": 0.09, + "learning_rate": 4.53833247578354e-05, + "loss": 0.2774, "step": 42290 }, { - "epoch": 0.38, - "learning_rate": 3.140527880371138e-05, - "loss": 0.2673, + "epoch": 0.09, + "learning_rate": 4.538220621462607e-05, + "loss": 0.2766, "step": 42300 }, { - "epoch": 0.38, - "learning_rate": 3.140077470498153e-05, - "loss": 0.2611, + "epoch": 0.09, + "learning_rate": 4.538108767141675e-05, + "loss": 0.281, "step": 42310 }, { - "epoch": 0.38, - "learning_rate": 3.139627060625169e-05, - "loss": 0.2628, + "epoch": 0.09, + "learning_rate": 4.537996912820742e-05, + "loss": 0.2754, "step": 42320 }, { - "epoch": 0.38, - "learning_rate": 3.139176650752185e-05, - "loss": 0.2638, + "epoch": 0.09, + "learning_rate": 4.53788505849981e-05, + "loss": 0.274, "step": 42330 }, { - "epoch": 0.38, - "learning_rate": 3.1387262408792e-05, - "loss": 0.2642, + "epoch": 0.09, + "learning_rate": 4.5377732041788775e-05, + "loss": 0.2807, "step": 42340 }, { - "epoch": 0.38, - "learning_rate": 3.138275831006216e-05, - "loss": 0.2572, + "epoch": 0.09, + "learning_rate": 4.537661349857945e-05, + "loss": 0.2734, "step": 42350 }, { - "epoch": 0.38, - "learning_rate": 3.137825421133231e-05, - "loss": 0.2625, + "epoch": 0.09, + "learning_rate": 4.537549495537013e-05, + "loss": 0.2754, "step": 42360 }, { - "epoch": 0.38, - "learning_rate": 3.137375011260247e-05, - "loss": 0.2562, + "epoch": 0.09, + "learning_rate": 4.53743764121608e-05, + "loss": 0.2783, "step": 42370 }, { - "epoch": 0.38, - "learning_rate": 3.136924601387263e-05, - "loss": 0.2612, + "epoch": 0.09, + "learning_rate": 4.537325786895148e-05, + "loss": 0.2755, "step": 42380 }, { - "epoch": 0.38, - "learning_rate": 3.136474191514278e-05, - "loss": 0.2664, + "epoch": 0.09, + "learning_rate": 4.537213932574216e-05, + "loss": 0.271, "step": 42390 }, { - "epoch": 0.38, - "learning_rate": 3.1360237816412936e-05, - "loss": 0.2606, + "epoch": 0.09, + "learning_rate": 4.537102078253283e-05, + "loss": 0.2741, "step": 42400 }, { - "epoch": 0.38, - "learning_rate": 3.1355733717683094e-05, - "loss": 0.2613, + "epoch": 0.09, + "learning_rate": 4.536990223932351e-05, + "loss": 0.2779, "step": 42410 }, { - "epoch": 0.38, - "learning_rate": 3.135122961895325e-05, - "loss": 0.2579, + "epoch": 0.09, + "learning_rate": 4.536878369611418e-05, + "loss": 0.2758, "step": 42420 }, { - "epoch": 0.38, - "learning_rate": 3.13467255202234e-05, - "loss": 0.2552, + "epoch": 0.09, + "learning_rate": 4.5367665152904856e-05, + "loss": 0.2758, "step": 42430 }, { - "epoch": 0.38, - "learning_rate": 3.134222142149356e-05, - "loss": 0.2661, + "epoch": 0.09, + "learning_rate": 4.5366546609695534e-05, + "loss": 0.2701, "step": 42440 }, { - "epoch": 0.38, - "learning_rate": 3.133771732276372e-05, - "loss": 0.2603, + "epoch": 0.09, + "learning_rate": 4.536542806648621e-05, + "loss": 0.271, "step": 42450 }, { - "epoch": 0.38, - "learning_rate": 3.1333213224033874e-05, - "loss": 0.2597, + "epoch": 0.09, + "learning_rate": 4.536430952327689e-05, + "loss": 0.2742, "step": 42460 }, { - "epoch": 0.38, - "learning_rate": 3.132870912530403e-05, - "loss": 0.2593, + "epoch": 0.09, + "learning_rate": 4.536319098006756e-05, + "loss": 0.2728, "step": 42470 }, { - "epoch": 0.38, - "learning_rate": 3.132420502657418e-05, - "loss": 0.2611, + "epoch": 0.09, + "learning_rate": 4.536207243685824e-05, + "loss": 0.2762, "step": 42480 }, { - "epoch": 0.38, - "learning_rate": 3.131970092784434e-05, - "loss": 0.2612, + "epoch": 0.09, + "learning_rate": 4.536095389364892e-05, + "loss": 0.2762, "step": 42490 }, { - "epoch": 0.38, - "learning_rate": 3.13151968291145e-05, - "loss": 0.2696, + "epoch": 0.09, + "learning_rate": 4.535983535043959e-05, + "loss": 0.2756, "step": 42500 }, { - "epoch": 0.38, - "learning_rate": 3.131069273038465e-05, - "loss": 0.2579, + "epoch": 0.09, + "learning_rate": 4.5358716807230266e-05, + "loss": 0.2671, "step": 42510 }, { - "epoch": 0.38, - "learning_rate": 3.130618863165481e-05, - "loss": 0.2565, + "epoch": 0.09, + "learning_rate": 4.535759826402094e-05, + "loss": 0.2801, "step": 42520 }, { - "epoch": 0.38, - "learning_rate": 3.130168453292496e-05, - "loss": 0.2612, + "epoch": 0.09, + "learning_rate": 4.5356479720811615e-05, + "loss": 0.2734, "step": 42530 }, { - "epoch": 0.38, - "learning_rate": 3.1297180434195114e-05, - "loss": 0.2654, + "epoch": 0.09, + "learning_rate": 4.535536117760229e-05, + "loss": 0.2735, "step": 42540 }, { - "epoch": 0.38, - "learning_rate": 3.129267633546528e-05, - "loss": 0.2652, + "epoch": 0.09, + "learning_rate": 4.535424263439297e-05, + "loss": 0.2716, "step": 42550 }, { - "epoch": 0.38, - "learning_rate": 3.128817223673543e-05, - "loss": 0.258, + "epoch": 0.09, + "learning_rate": 4.535312409118365e-05, + "loss": 0.2755, "step": 42560 }, { - "epoch": 0.38, - "learning_rate": 3.1283668138005586e-05, - "loss": 0.2623, + "epoch": 0.1, + "learning_rate": 4.535200554797432e-05, + "loss": 0.2714, "step": 42570 }, { - "epoch": 0.38, - "learning_rate": 3.1279164039275744e-05, - "loss": 0.2582, + "epoch": 0.1, + "learning_rate": 4.5350887004765e-05, + "loss": 0.2754, "step": 42580 }, { - "epoch": 0.38, - "learning_rate": 3.1274659940545895e-05, - "loss": 0.2598, + "epoch": 0.1, + "learning_rate": 4.534976846155567e-05, + "loss": 0.2747, "step": 42590 }, { - "epoch": 0.38, - "learning_rate": 3.127015584181606e-05, - "loss": 0.2621, + "epoch": 0.1, + "learning_rate": 4.534864991834635e-05, + "loss": 0.2755, "step": 42600 }, { - "epoch": 0.38, - "learning_rate": 3.126565174308621e-05, - "loss": 0.2654, + "epoch": 0.1, + "learning_rate": 4.5347531375137025e-05, + "loss": 0.2739, "step": 42610 }, { - "epoch": 0.38, - "learning_rate": 3.126114764435637e-05, - "loss": 0.255, + "epoch": 0.1, + "learning_rate": 4.5346412831927696e-05, + "loss": 0.2721, "step": 42620 }, { - "epoch": 0.38, - "learning_rate": 3.1256643545626525e-05, - "loss": 0.2579, + "epoch": 0.1, + "learning_rate": 4.5345294288718374e-05, + "loss": 0.2713, "step": 42630 }, { - "epoch": 0.38, - "learning_rate": 3.1252139446896675e-05, - "loss": 0.2626, + "epoch": 0.1, + "learning_rate": 4.5344175745509046e-05, + "loss": 0.2744, "step": 42640 }, { - "epoch": 0.38, - "learning_rate": 3.124763534816683e-05, - "loss": 0.2591, + "epoch": 0.1, + "learning_rate": 4.534305720229973e-05, + "loss": 0.2772, "step": 42650 }, { - "epoch": 0.38, - "learning_rate": 3.124313124943699e-05, - "loss": 0.2551, + "epoch": 0.1, + "learning_rate": 4.534193865909041e-05, + "loss": 0.2741, "step": 42660 }, { - "epoch": 0.38, - "learning_rate": 3.123862715070715e-05, - "loss": 0.2633, + "epoch": 0.1, + "learning_rate": 4.534082011588108e-05, + "loss": 0.2699, "step": 42670 }, { - "epoch": 0.38, - "learning_rate": 3.12341230519773e-05, - "loss": 0.2603, + "epoch": 0.1, + "learning_rate": 4.533970157267176e-05, + "loss": 0.2728, "step": 42680 }, { - "epoch": 0.38, - "learning_rate": 3.1229618953247456e-05, - "loss": 0.2664, + "epoch": 0.1, + "learning_rate": 4.533858302946243e-05, + "loss": 0.2679, "step": 42690 }, { - "epoch": 0.38, - "learning_rate": 3.1225114854517614e-05, - "loss": 0.2625, + "epoch": 0.1, + "learning_rate": 4.5337464486253106e-05, + "loss": 0.2706, "step": 42700 }, { - "epoch": 0.38, - "learning_rate": 3.1220610755787764e-05, - "loss": 0.2626, + "epoch": 0.1, + "learning_rate": 4.5336345943043784e-05, + "loss": 0.2726, "step": 42710 }, { - "epoch": 0.38, - "learning_rate": 3.121610665705793e-05, - "loss": 0.2585, + "epoch": 0.1, + "learning_rate": 4.5335227399834455e-05, + "loss": 0.2698, "step": 42720 }, { - "epoch": 0.38, - "learning_rate": 3.121160255832808e-05, - "loss": 0.2577, + "epoch": 0.1, + "learning_rate": 4.533410885662513e-05, + "loss": 0.2792, "step": 42730 }, { - "epoch": 0.38, - "learning_rate": 3.120709845959824e-05, - "loss": 0.2604, + "epoch": 0.1, + "learning_rate": 4.5332990313415804e-05, + "loss": 0.2762, "step": 42740 }, { - "epoch": 0.38, - "learning_rate": 3.1202594360868394e-05, - "loss": 0.2636, + "epoch": 0.1, + "learning_rate": 4.533187177020648e-05, + "loss": 0.2736, "step": 42750 }, { - "epoch": 0.38, - "learning_rate": 3.1198090262138545e-05, - "loss": 0.2566, + "epoch": 0.1, + "learning_rate": 4.533075322699716e-05, + "loss": 0.2738, "step": 42760 }, { - "epoch": 0.38, - "learning_rate": 3.11935861634087e-05, - "loss": 0.2637, + "epoch": 0.1, + "learning_rate": 4.532963468378784e-05, + "loss": 0.2762, "step": 42770 }, { - "epoch": 0.38, - "learning_rate": 3.118908206467886e-05, - "loss": 0.264, + "epoch": 0.1, + "learning_rate": 4.5328516140578516e-05, + "loss": 0.2759, "step": 42780 }, { - "epoch": 0.38, - "learning_rate": 3.118457796594901e-05, - "loss": 0.2642, + "epoch": 0.1, + "learning_rate": 4.532739759736919e-05, + "loss": 0.2812, "step": 42790 }, { - "epoch": 0.38, - "learning_rate": 3.1180073867219175e-05, - "loss": 0.2587, + "epoch": 0.1, + "learning_rate": 4.5326279054159865e-05, + "loss": 0.2758, "step": 42800 }, { - "epoch": 0.38, - "learning_rate": 3.1175569768489326e-05, - "loss": 0.2544, + "epoch": 0.1, + "learning_rate": 4.532516051095054e-05, + "loss": 0.2799, "step": 42810 }, { - "epoch": 0.38, - "learning_rate": 3.117106566975948e-05, - "loss": 0.2666, + "epoch": 0.1, + "learning_rate": 4.5324041967741214e-05, + "loss": 0.28, "step": 42820 }, { - "epoch": 0.38, - "learning_rate": 3.116656157102964e-05, - "loss": 0.2616, + "epoch": 0.1, + "learning_rate": 4.532292342453189e-05, + "loss": 0.2731, "step": 42830 }, { - "epoch": 0.38, - "learning_rate": 3.116205747229979e-05, - "loss": 0.2641, + "epoch": 0.1, + "learning_rate": 4.5321804881322563e-05, + "loss": 0.2797, "step": 42840 }, { - "epoch": 0.38, - "learning_rate": 3.115755337356995e-05, - "loss": 0.259, + "epoch": 0.1, + "learning_rate": 4.532068633811324e-05, + "loss": 0.2728, "step": 42850 }, { - "epoch": 0.38, - "learning_rate": 3.1153049274840106e-05, - "loss": 0.256, + "epoch": 0.1, + "learning_rate": 4.531956779490392e-05, + "loss": 0.2808, "step": 42860 }, { - "epoch": 0.38, - "learning_rate": 3.1148545176110264e-05, - "loss": 0.2614, + "epoch": 0.1, + "learning_rate": 4.53184492516946e-05, + "loss": 0.2717, "step": 42870 }, { - "epoch": 0.38, - "learning_rate": 3.114404107738042e-05, - "loss": 0.2639, + "epoch": 0.1, + "learning_rate": 4.5317330708485275e-05, + "loss": 0.2805, "step": 42880 }, { - "epoch": 0.38, - "learning_rate": 3.113953697865057e-05, - "loss": 0.2599, + "epoch": 0.1, + "learning_rate": 4.5316212165275946e-05, + "loss": 0.27, "step": 42890 }, { - "epoch": 0.38, - "learning_rate": 3.113503287992073e-05, - "loss": 0.267, + "epoch": 0.1, + "learning_rate": 4.5315093622066624e-05, + "loss": 0.272, "step": 42900 }, { - "epoch": 0.38, - "learning_rate": 3.113052878119089e-05, - "loss": 0.2592, + "epoch": 0.1, + "learning_rate": 4.5313975078857295e-05, + "loss": 0.277, "step": 42910 }, { - "epoch": 0.38, - "learning_rate": 3.1126024682461044e-05, - "loss": 0.2574, + "epoch": 0.1, + "learning_rate": 4.5312968389968904e-05, + "loss": 0.2663, "step": 42920 }, { - "epoch": 0.38, - "learning_rate": 3.1121520583731195e-05, - "loss": 0.253, + "epoch": 0.1, + "learning_rate": 4.531184984675958e-05, + "loss": 0.2669, "step": 42930 }, { - "epoch": 0.38, - "learning_rate": 3.111701648500135e-05, - "loss": 0.2628, + "epoch": 0.1, + "learning_rate": 4.531073130355026e-05, + "loss": 0.2714, "step": 42940 }, { - "epoch": 0.38, - "learning_rate": 3.111251238627151e-05, - "loss": 0.258, + "epoch": 0.1, + "learning_rate": 4.530961276034094e-05, + "loss": 0.2797, "step": 42950 }, { - "epoch": 0.38, - "learning_rate": 3.110800828754166e-05, - "loss": 0.2625, + "epoch": 0.1, + "learning_rate": 4.530849421713161e-05, + "loss": 0.2754, "step": 42960 }, { - "epoch": 0.38, - "learning_rate": 3.110350418881182e-05, - "loss": 0.2502, + "epoch": 0.1, + "learning_rate": 4.530737567392229e-05, + "loss": 0.2729, "step": 42970 }, { - "epoch": 0.38, - "learning_rate": 3.1099000090081976e-05, - "loss": 0.271, + "epoch": 0.1, + "learning_rate": 4.530625713071296e-05, + "loss": 0.2704, "step": 42980 }, { - "epoch": 0.38, - "learning_rate": 3.1094495991352127e-05, - "loss": 0.2648, + "epoch": 0.1, + "learning_rate": 4.5305138587503636e-05, + "loss": 0.277, "step": 42990 }, { - "epoch": 0.38, - "learning_rate": 3.108999189262229e-05, - "loss": 0.2641, + "epoch": 0.1, + "learning_rate": 4.5304020044294314e-05, + "loss": 0.2708, "step": 43000 }, { - "epoch": 0.38, - "learning_rate": 3.108548779389244e-05, - "loss": 0.2568, + "epoch": 0.1, + "learning_rate": 4.5302901501084985e-05, + "loss": 0.2749, "step": 43010 }, { - "epoch": 0.38, - "learning_rate": 3.10809836951626e-05, - "loss": 0.2578, + "epoch": 0.1, + "learning_rate": 4.530178295787566e-05, + "loss": 0.2758, "step": 43020 }, { - "epoch": 0.38, - "learning_rate": 3.1076479596432757e-05, - "loss": 0.2588, + "epoch": 0.1, + "learning_rate": 4.530066441466634e-05, + "loss": 0.2726, "step": 43030 }, { - "epoch": 0.38, - "learning_rate": 3.107197549770291e-05, - "loss": 0.2573, + "epoch": 0.1, + "learning_rate": 4.529954587145702e-05, + "loss": 0.2763, "step": 43040 }, { - "epoch": 0.38, - "learning_rate": 3.106747139897307e-05, - "loss": 0.2591, + "epoch": 0.1, + "learning_rate": 4.52984273282477e-05, + "loss": 0.2731, "step": 43050 }, { - "epoch": 0.38, - "learning_rate": 3.106296730024322e-05, - "loss": 0.2595, + "epoch": 0.1, + "learning_rate": 4.529730878503837e-05, + "loss": 0.2643, "step": 43060 }, { - "epoch": 0.38, - "learning_rate": 3.105846320151338e-05, - "loss": 0.2586, + "epoch": 0.1, + "learning_rate": 4.5296190241829046e-05, + "loss": 0.2723, "step": 43070 }, { - "epoch": 0.38, - "learning_rate": 3.105395910278354e-05, - "loss": 0.2551, + "epoch": 0.1, + "learning_rate": 4.529507169861972e-05, + "loss": 0.2696, "step": 43080 }, { - "epoch": 0.38, - "learning_rate": 3.104945500405369e-05, - "loss": 0.256, + "epoch": 0.1, + "learning_rate": 4.5293953155410395e-05, + "loss": 0.2745, "step": 43090 }, { - "epoch": 0.38, - "learning_rate": 3.1044950905323845e-05, - "loss": 0.257, + "epoch": 0.1, + "learning_rate": 4.529283461220107e-05, + "loss": 0.2721, "step": 43100 }, { - "epoch": 0.38, - "learning_rate": 3.1040446806594e-05, - "loss": 0.2603, + "epoch": 0.1, + "learning_rate": 4.5291716068991744e-05, + "loss": 0.2705, "step": 43110 }, { - "epoch": 0.38, - "learning_rate": 3.103594270786416e-05, - "loss": 0.257, + "epoch": 0.1, + "learning_rate": 4.529059752578242e-05, + "loss": 0.2725, "step": 43120 }, { - "epoch": 0.39, - "learning_rate": 3.103143860913431e-05, - "loss": 0.2559, + "epoch": 0.1, + "learning_rate": 4.52894789825731e-05, + "loss": 0.2747, "step": 43130 }, { - "epoch": 0.39, - "learning_rate": 3.102693451040447e-05, - "loss": 0.2558, + "epoch": 0.1, + "learning_rate": 4.528836043936378e-05, + "loss": 0.269, "step": 43140 }, { - "epoch": 0.39, - "learning_rate": 3.1022430411674626e-05, - "loss": 0.2564, + "epoch": 0.1, + "learning_rate": 4.5287241896154456e-05, + "loss": 0.2774, "step": 43150 }, { - "epoch": 0.39, - "learning_rate": 3.1017926312944784e-05, - "loss": 0.2581, + "epoch": 0.1, + "learning_rate": 4.528612335294513e-05, + "loss": 0.273, "step": 43160 }, { - "epoch": 0.39, - "learning_rate": 3.101342221421494e-05, - "loss": 0.2599, + "epoch": 0.1, + "learning_rate": 4.5285004809735805e-05, + "loss": 0.2709, "step": 43170 }, { - "epoch": 0.39, - "learning_rate": 3.100891811548509e-05, - "loss": 0.2548, + "epoch": 0.1, + "learning_rate": 4.5283886266526476e-05, + "loss": 0.2708, "step": 43180 }, { - "epoch": 0.39, - "learning_rate": 3.100441401675525e-05, - "loss": 0.2552, + "epoch": 0.1, + "learning_rate": 4.5282767723317154e-05, + "loss": 0.2701, "step": 43190 }, { - "epoch": 0.39, - "learning_rate": 3.099990991802541e-05, - "loss": 0.2596, + "epoch": 0.1, + "learning_rate": 4.528164918010783e-05, + "loss": 0.2753, "step": 43200 }, { - "epoch": 0.39, - "learning_rate": 3.099540581929556e-05, - "loss": 0.2649, + "epoch": 0.1, + "learning_rate": 4.528064249121944e-05, + "loss": 0.2788, "step": 43210 }, { - "epoch": 0.39, - "learning_rate": 3.0990901720565715e-05, - "loss": 0.2539, + "epoch": 0.1, + "learning_rate": 4.527952394801012e-05, + "loss": 0.2679, "step": 43220 }, { - "epoch": 0.39, - "learning_rate": 3.098639762183587e-05, - "loss": 0.2609, + "epoch": 0.1, + "learning_rate": 4.527840540480079e-05, + "loss": 0.2692, "step": 43230 }, { - "epoch": 0.39, - "learning_rate": 3.098189352310602e-05, - "loss": 0.2575, + "epoch": 0.1, + "learning_rate": 4.527728686159147e-05, + "loss": 0.2651, "step": 43240 }, { - "epoch": 0.39, - "learning_rate": 3.097738942437619e-05, - "loss": 0.2597, + "epoch": 0.1, + "learning_rate": 4.527616831838214e-05, + "loss": 0.2742, "step": 43250 }, { - "epoch": 0.39, - "learning_rate": 3.097288532564634e-05, - "loss": 0.2651, + "epoch": 0.1, + "learning_rate": 4.527504977517282e-05, + "loss": 0.2689, "step": 43260 }, { - "epoch": 0.39, - "learning_rate": 3.0968381226916496e-05, - "loss": 0.2581, + "epoch": 0.1, + "learning_rate": 4.5273931231963495e-05, + "loss": 0.273, "step": 43270 }, { - "epoch": 0.39, - "learning_rate": 3.096387712818665e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.5272812688754166e-05, + "loss": 0.2708, "step": 43280 }, { - "epoch": 0.39, - "learning_rate": 3.0959373029456804e-05, - "loss": 0.2656, + "epoch": 0.1, + "learning_rate": 4.5271694145544844e-05, + "loss": 0.2797, "step": 43290 }, { - "epoch": 0.39, - "learning_rate": 3.095486893072697e-05, - "loss": 0.2566, + "epoch": 0.1, + "learning_rate": 4.527057560233552e-05, + "loss": 0.2706, "step": 43300 }, { - "epoch": 0.39, - "learning_rate": 3.095036483199712e-05, - "loss": 0.2594, + "epoch": 0.1, + "learning_rate": 4.52694570591262e-05, + "loss": 0.2713, "step": 43310 }, { - "epoch": 0.39, - "learning_rate": 3.0945860733267276e-05, - "loss": 0.2511, + "epoch": 0.1, + "learning_rate": 4.526833851591687e-05, + "loss": 0.2716, "step": 43320 }, { - "epoch": 0.39, - "learning_rate": 3.0941356634537434e-05, - "loss": 0.2602, + "epoch": 0.1, + "learning_rate": 4.526721997270755e-05, + "loss": 0.2729, "step": 43330 }, { - "epoch": 0.39, - "learning_rate": 3.0936852535807585e-05, - "loss": 0.2637, + "epoch": 0.1, + "learning_rate": 4.526610142949823e-05, + "loss": 0.276, "step": 43340 }, { - "epoch": 0.39, - "learning_rate": 3.093234843707774e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.52649828862889e-05, + "loss": 0.2748, "step": 43350 }, { - "epoch": 0.39, - "learning_rate": 3.09278443383479e-05, - "loss": 0.2604, + "epoch": 0.1, + "learning_rate": 4.5263864343079576e-05, + "loss": 0.2701, "step": 43360 }, { - "epoch": 0.39, - "learning_rate": 3.092334023961806e-05, - "loss": 0.2579, + "epoch": 0.1, + "learning_rate": 4.526274579987025e-05, + "loss": 0.2695, "step": 43370 }, { - "epoch": 0.39, - "learning_rate": 3.091883614088821e-05, - "loss": 0.2601, + "epoch": 0.1, + "learning_rate": 4.5261627256660925e-05, + "loss": 0.2655, "step": 43380 }, { - "epoch": 0.39, - "learning_rate": 3.0914332042158365e-05, - "loss": 0.2523, + "epoch": 0.1, + "learning_rate": 4.52605087134516e-05, + "loss": 0.2675, "step": 43390 }, { - "epoch": 0.39, - "learning_rate": 3.090982794342852e-05, - "loss": 0.2578, + "epoch": 0.1, + "learning_rate": 4.525939017024228e-05, + "loss": 0.2735, "step": 43400 }, { - "epoch": 0.39, - "learning_rate": 3.0905323844698673e-05, - "loss": 0.2561, + "epoch": 0.1, + "learning_rate": 4.525827162703296e-05, + "loss": 0.2653, "step": 43410 }, { - "epoch": 0.39, - "learning_rate": 3.090081974596883e-05, - "loss": 0.2614, + "epoch": 0.1, + "learning_rate": 4.525715308382363e-05, + "loss": 0.2726, "step": 43420 }, { - "epoch": 0.39, - "learning_rate": 3.089631564723899e-05, - "loss": 0.2576, + "epoch": 0.1, + "learning_rate": 4.525603454061431e-05, + "loss": 0.2736, "step": 43430 }, { - "epoch": 0.39, - "learning_rate": 3.0891811548509146e-05, - "loss": 0.2555, + "epoch": 0.1, + "learning_rate": 4.5254915997404986e-05, + "loss": 0.2718, "step": 43440 }, { - "epoch": 0.39, - "learning_rate": 3.0887307449779303e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.525379745419566e-05, + "loss": 0.2713, "step": 43450 }, { - "epoch": 0.39, - "learning_rate": 3.0882803351049454e-05, - "loss": 0.2557, + "epoch": 0.1, + "learning_rate": 4.5252678910986335e-05, + "loss": 0.2767, "step": 43460 }, { - "epoch": 0.39, - "learning_rate": 3.087829925231961e-05, - "loss": 0.263, + "epoch": 0.1, + "learning_rate": 4.5251560367777006e-05, + "loss": 0.2645, "step": 43470 }, { - "epoch": 0.39, - "learning_rate": 3.087379515358977e-05, - "loss": 0.2595, + "epoch": 0.1, + "learning_rate": 4.5250441824567684e-05, + "loss": 0.2711, "step": 43480 }, { - "epoch": 0.39, - "learning_rate": 3.086929105485992e-05, - "loss": 0.2602, + "epoch": 0.1, + "learning_rate": 4.524932328135836e-05, + "loss": 0.2695, "step": 43490 }, { - "epoch": 0.39, - "learning_rate": 3.0864786956130084e-05, - "loss": 0.2545, + "epoch": 0.1, + "learning_rate": 4.524820473814903e-05, + "loss": 0.2721, "step": 43500 }, { - "epoch": 0.39, - "learning_rate": 3.0860282857400235e-05, - "loss": 0.2566, + "epoch": 0.1, + "learning_rate": 4.524708619493971e-05, + "loss": 0.2668, "step": 43510 }, { - "epoch": 0.39, - "learning_rate": 3.085577875867039e-05, - "loss": 0.2547, + "epoch": 0.1, + "learning_rate": 4.524596765173039e-05, + "loss": 0.2659, "step": 43520 }, { - "epoch": 0.39, - "learning_rate": 3.085127465994055e-05, - "loss": 0.2606, + "epoch": 0.1, + "learning_rate": 4.5244849108521067e-05, + "loss": 0.267, "step": 43530 }, { - "epoch": 0.39, - "learning_rate": 3.08467705612107e-05, - "loss": 0.2561, + "epoch": 0.1, + "learning_rate": 4.5243730565311745e-05, + "loss": 0.2701, "step": 43540 }, { - "epoch": 0.39, - "learning_rate": 3.084226646248086e-05, - "loss": 0.2509, + "epoch": 0.1, + "learning_rate": 4.5242612022102416e-05, + "loss": 0.2757, "step": 43550 }, { - "epoch": 0.39, - "learning_rate": 3.0837762363751016e-05, - "loss": 0.2546, + "epoch": 0.1, + "learning_rate": 4.5241493478893094e-05, + "loss": 0.2779, "step": 43560 }, { - "epoch": 0.39, - "learning_rate": 3.083370867489416e-05, - "loss": 0.2597, + "epoch": 0.1, + "learning_rate": 4.5240374935683765e-05, + "loss": 0.272, "step": 43570 }, { - "epoch": 0.39, - "learning_rate": 3.082920457616431e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.523925639247444e-05, + "loss": 0.2732, "step": 43580 }, { - "epoch": 0.39, - "learning_rate": 3.082470047743447e-05, - "loss": 0.2631, + "epoch": 0.1, + "learning_rate": 4.523813784926512e-05, + "loss": 0.2699, "step": 43590 }, { - "epoch": 0.39, - "learning_rate": 3.0820196378704625e-05, - "loss": 0.2634, + "epoch": 0.1, + "learning_rate": 4.523701930605579e-05, + "loss": 0.2738, "step": 43600 }, { - "epoch": 0.39, - "learning_rate": 3.0815692279974776e-05, - "loss": 0.2649, + "epoch": 0.1, + "learning_rate": 4.523590076284647e-05, + "loss": 0.2786, "step": 43610 }, { - "epoch": 0.39, - "learning_rate": 3.081118818124493e-05, - "loss": 0.2584, + "epoch": 0.1, + "learning_rate": 4.523478221963715e-05, + "loss": 0.2691, "step": 43620 }, { - "epoch": 0.39, - "learning_rate": 3.080668408251509e-05, - "loss": 0.2629, + "epoch": 0.1, + "learning_rate": 4.5233663676427826e-05, + "loss": 0.2737, "step": 43630 }, { - "epoch": 0.39, - "learning_rate": 3.080217998378525e-05, - "loss": 0.2543, + "epoch": 0.1, + "learning_rate": 4.52325451332185e-05, + "loss": 0.2703, "step": 43640 }, { - "epoch": 0.39, - "learning_rate": 3.07976758850554e-05, - "loss": 0.2574, + "epoch": 0.1, + "learning_rate": 4.5231426590009175e-05, + "loss": 0.2736, "step": 43650 }, { - "epoch": 0.39, - "learning_rate": 3.0793171786325556e-05, - "loss": 0.2637, + "epoch": 0.1, + "learning_rate": 4.523030804679985e-05, + "loss": 0.2752, "step": 43660 }, { - "epoch": 0.39, - "learning_rate": 3.0788667687595714e-05, - "loss": 0.2619, + "epoch": 0.1, + "learning_rate": 4.5229189503590524e-05, + "loss": 0.2665, "step": 43670 }, { - "epoch": 0.39, - "learning_rate": 3.078416358886587e-05, - "loss": 0.2583, + "epoch": 0.1, + "learning_rate": 4.52280709603812e-05, + "loss": 0.272, "step": 43680 }, { - "epoch": 0.39, - "learning_rate": 3.077965949013603e-05, - "loss": 0.262, + "epoch": 0.1, + "learning_rate": 4.522695241717187e-05, + "loss": 0.274, "step": 43690 }, { - "epoch": 0.39, - "learning_rate": 3.077515539140618e-05, - "loss": 0.2643, + "epoch": 0.1, + "learning_rate": 4.522583387396255e-05, + "loss": 0.2658, "step": 43700 }, { - "epoch": 0.39, - "learning_rate": 3.077065129267634e-05, - "loss": 0.2676, + "epoch": 0.1, + "learning_rate": 4.522471533075323e-05, + "loss": 0.2769, "step": 43710 }, { - "epoch": 0.39, - "learning_rate": 3.0766147193946495e-05, - "loss": 0.2583, + "epoch": 0.1, + "learning_rate": 4.5223596787543907e-05, + "loss": 0.2763, "step": 43720 }, { - "epoch": 0.39, - "learning_rate": 3.0761643095216645e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.5222478244334585e-05, + "loss": 0.2737, "step": 43730 }, { - "epoch": 0.39, - "learning_rate": 3.075713899648681e-05, - "loss": 0.2585, + "epoch": 0.1, + "learning_rate": 4.5221359701125256e-05, + "loss": 0.2688, "step": 43740 }, { - "epoch": 0.39, - "learning_rate": 3.075263489775696e-05, - "loss": 0.2579, + "epoch": 0.1, + "learning_rate": 4.5220241157915934e-05, + "loss": 0.2674, "step": 43750 }, { - "epoch": 0.39, - "learning_rate": 3.074813079902711e-05, - "loss": 0.2608, + "epoch": 0.1, + "learning_rate": 4.521912261470661e-05, + "loss": 0.274, "step": 43760 }, { - "epoch": 0.39, - "learning_rate": 3.0743626700297275e-05, - "loss": 0.2571, + "epoch": 0.1, + "learning_rate": 4.521800407149728e-05, + "loss": 0.2697, "step": 43770 }, { - "epoch": 0.39, - "learning_rate": 3.0739122601567426e-05, - "loss": 0.2562, + "epoch": 0.1, + "learning_rate": 4.521688552828796e-05, + "loss": 0.2716, "step": 43780 }, { - "epoch": 0.39, - "learning_rate": 3.0734618502837583e-05, - "loss": 0.2602, + "epoch": 0.1, + "learning_rate": 4.521576698507863e-05, + "loss": 0.2705, "step": 43790 }, { - "epoch": 0.39, - "learning_rate": 3.073011440410774e-05, - "loss": 0.2574, + "epoch": 0.1, + "learning_rate": 4.521464844186931e-05, + "loss": 0.2736, "step": 43800 }, { - "epoch": 0.39, - "learning_rate": 3.072561030537789e-05, - "loss": 0.2554, + "epoch": 0.1, + "learning_rate": 4.521352989865999e-05, + "loss": 0.2716, "step": 43810 }, { - "epoch": 0.39, - "learning_rate": 3.0721106206648056e-05, - "loss": 0.2576, + "epoch": 0.1, + "learning_rate": 4.5212411355450666e-05, + "loss": 0.2699, "step": 43820 }, { - "epoch": 0.39, - "learning_rate": 3.071660210791821e-05, - "loss": 0.2591, + "epoch": 0.1, + "learning_rate": 4.5211292812241343e-05, + "loss": 0.2783, "step": 43830 }, { - "epoch": 0.39, - "learning_rate": 3.0712098009188364e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.5210174269032015e-05, + "loss": 0.2698, "step": 43840 }, { - "epoch": 0.39, - "learning_rate": 3.070759391045852e-05, - "loss": 0.253, + "epoch": 0.1, + "learning_rate": 4.520905572582269e-05, + "loss": 0.2685, "step": 43850 }, { - "epoch": 0.39, - "learning_rate": 3.070308981172867e-05, - "loss": 0.255, + "epoch": 0.1, + "learning_rate": 4.520793718261337e-05, + "loss": 0.2712, "step": 43860 }, { - "epoch": 0.39, - "learning_rate": 3.069858571299883e-05, - "loss": 0.2518, + "epoch": 0.1, + "learning_rate": 4.520681863940404e-05, + "loss": 0.2691, "step": 43870 }, { - "epoch": 0.39, - "learning_rate": 3.069408161426899e-05, - "loss": 0.2543, + "epoch": 0.1, + "learning_rate": 4.520570009619472e-05, + "loss": 0.2735, "step": 43880 }, { - "epoch": 0.39, - "learning_rate": 3.0689577515539145e-05, - "loss": 0.256, + "epoch": 0.1, + "learning_rate": 4.520458155298539e-05, + "loss": 0.2742, "step": 43890 }, { - "epoch": 0.39, - "learning_rate": 3.0685073416809296e-05, - "loss": 0.2621, + "epoch": 0.1, + "learning_rate": 4.520346300977607e-05, + "loss": 0.2711, "step": 43900 }, { - "epoch": 0.39, - "learning_rate": 3.068056931807945e-05, - "loss": 0.2582, + "epoch": 0.1, + "learning_rate": 4.5202344466566747e-05, + "loss": 0.269, "step": 43910 }, { - "epoch": 0.39, - "learning_rate": 3.067606521934961e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.520122592335742e-05, + "loss": 0.2697, "step": 43920 }, { - "epoch": 0.39, - "learning_rate": 3.067156112061976e-05, - "loss": 0.2591, + "epoch": 0.1, + "learning_rate": 4.5200107380148096e-05, + "loss": 0.2727, "step": 43930 }, { - "epoch": 0.39, - "learning_rate": 3.0667057021889926e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.5198988836938774e-05, + "loss": 0.2691, "step": 43940 }, { - "epoch": 0.39, - "learning_rate": 3.0662552923160076e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.519787029372945e-05, + "loss": 0.2686, "step": 43950 }, { - "epoch": 0.39, - "learning_rate": 3.0658048824430234e-05, - "loss": 0.2587, + "epoch": 0.1, + "learning_rate": 4.519675175052012e-05, + "loss": 0.2728, "step": 43960 }, { - "epoch": 0.39, - "learning_rate": 3.065354472570039e-05, - "loss": 0.2561, + "epoch": 0.1, + "learning_rate": 4.51956332073108e-05, + "loss": 0.2664, "step": 43970 }, { - "epoch": 0.39, - "learning_rate": 3.064904062697054e-05, - "loss": 0.2625, + "epoch": 0.1, + "learning_rate": 4.519451466410148e-05, + "loss": 0.2708, "step": 43980 }, { - "epoch": 0.39, - "learning_rate": 3.06445365282407e-05, - "loss": 0.2522, + "epoch": 0.1, + "learning_rate": 4.519339612089215e-05, + "loss": 0.2678, "step": 43990 }, { - "epoch": 0.39, - "learning_rate": 3.064003242951086e-05, - "loss": 0.26, + "epoch": 0.1, + "learning_rate": 4.519227757768283e-05, + "loss": 0.2701, "step": 44000 }, { - "epoch": 0.39, - "learning_rate": 3.063552833078101e-05, - "loss": 0.2627, + "epoch": 0.1, + "learning_rate": 4.51911590344735e-05, + "loss": 0.2726, "step": 44010 }, { - "epoch": 0.39, - "learning_rate": 3.063102423205117e-05, - "loss": 0.2606, + "epoch": 0.1, + "learning_rate": 4.519004049126418e-05, + "loss": 0.2718, "step": 44020 }, { - "epoch": 0.39, - "learning_rate": 3.062652013332132e-05, - "loss": 0.258, + "epoch": 0.1, + "learning_rate": 4.5188921948054855e-05, + "loss": 0.2748, "step": 44030 }, { - "epoch": 0.39, - "learning_rate": 3.062201603459148e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.518780340484553e-05, + "loss": 0.271, "step": 44040 }, { - "epoch": 0.39, - "learning_rate": 3.061751193586164e-05, - "loss": 0.2605, + "epoch": 0.1, + "learning_rate": 4.518668486163621e-05, + "loss": 0.2714, "step": 44050 }, { - "epoch": 0.39, - "learning_rate": 3.061300783713179e-05, - "loss": 0.2658, + "epoch": 0.1, + "learning_rate": 4.518556631842688e-05, + "loss": 0.2699, "step": 44060 }, { - "epoch": 0.39, - "learning_rate": 3.0608503738401946e-05, - "loss": 0.2584, + "epoch": 0.1, + "learning_rate": 4.518444777521756e-05, + "loss": 0.2711, "step": 44070 }, { - "epoch": 0.39, - "learning_rate": 3.06039996396721e-05, - "loss": 0.2598, + "epoch": 0.1, + "learning_rate": 4.518332923200824e-05, + "loss": 0.2709, "step": 44080 }, { - "epoch": 0.39, - "learning_rate": 3.059949554094226e-05, - "loss": 0.2625, + "epoch": 0.1, + "learning_rate": 4.518221068879891e-05, + "loss": 0.271, "step": 44090 }, { - "epoch": 0.39, - "learning_rate": 3.059499144221242e-05, - "loss": 0.2563, + "epoch": 0.1, + "learning_rate": 4.5181092145589587e-05, + "loss": 0.2692, "step": 44100 }, { - "epoch": 0.39, - "learning_rate": 3.059048734348257e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.517997360238026e-05, + "loss": 0.2662, "step": 44110 }, { - "epoch": 0.39, - "learning_rate": 3.0585983244752727e-05, - "loss": 0.2531, + "epoch": 0.1, + "learning_rate": 4.5178855059170936e-05, + "loss": 0.2691, "step": 44120 }, { - "epoch": 0.39, - "learning_rate": 3.0581479146022884e-05, - "loss": 0.2653, + "epoch": 0.1, + "learning_rate": 4.5177736515961614e-05, + "loss": 0.2702, "step": 44130 }, { - "epoch": 0.39, - "learning_rate": 3.057697504729304e-05, - "loss": 0.2587, + "epoch": 0.1, + "learning_rate": 4.517661797275229e-05, + "loss": 0.2727, "step": 44140 }, { - "epoch": 0.39, - "learning_rate": 3.057247094856319e-05, - "loss": 0.2617, + "epoch": 0.1, + "learning_rate": 4.517549942954297e-05, + "loss": 0.2672, "step": 44150 }, { - "epoch": 0.39, - "learning_rate": 3.056796684983335e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.517438088633364e-05, + "loss": 0.2693, "step": 44160 }, { - "epoch": 0.39, - "learning_rate": 3.056346275110351e-05, - "loss": 0.2614, + "epoch": 0.1, + "learning_rate": 4.517326234312432e-05, + "loss": 0.2681, "step": 44170 }, { - "epoch": 0.39, - "learning_rate": 3.055895865237366e-05, - "loss": 0.2562, + "epoch": 0.1, + "learning_rate": 4.5172143799914996e-05, + "loss": 0.2746, "step": 44180 }, { - "epoch": 0.39, - "learning_rate": 3.0554454553643815e-05, - "loss": 0.2544, + "epoch": 0.1, + "learning_rate": 4.517102525670567e-05, + "loss": 0.2725, "step": 44190 }, { - "epoch": 0.39, - "learning_rate": 3.054995045491397e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.5169906713496345e-05, + "loss": 0.2695, "step": 44200 }, { - "epoch": 0.39, - "learning_rate": 3.0545446356184124e-05, - "loss": 0.2656, + "epoch": 0.1, + "learning_rate": 4.5168788170287017e-05, + "loss": 0.2683, "step": 44210 }, { - "epoch": 0.39, - "learning_rate": 3.054094225745429e-05, - "loss": 0.2622, + "epoch": 0.1, + "learning_rate": 4.5167669627077695e-05, + "loss": 0.2677, "step": 44220 }, { - "epoch": 0.39, - "learning_rate": 3.053643815872444e-05, - "loss": 0.2594, + "epoch": 0.1, + "learning_rate": 4.516655108386837e-05, + "loss": 0.2712, "step": 44230 }, { - "epoch": 0.39, - "learning_rate": 3.0531934059994596e-05, - "loss": 0.2554, + "epoch": 0.1, + "learning_rate": 4.516543254065905e-05, + "loss": 0.2707, "step": 44240 }, { - "epoch": 0.4, - "learning_rate": 3.0527429961264754e-05, - "loss": 0.2581, + "epoch": 0.1, + "learning_rate": 4.516431399744973e-05, + "loss": 0.2677, "step": 44250 }, { - "epoch": 0.4, - "learning_rate": 3.0522925862534904e-05, - "loss": 0.2599, + "epoch": 0.1, + "learning_rate": 4.51631954542404e-05, + "loss": 0.2721, "step": 44260 }, { - "epoch": 0.4, - "learning_rate": 3.051842176380507e-05, - "loss": 0.2598, + "epoch": 0.1, + "learning_rate": 4.516207691103108e-05, + "loss": 0.2712, "step": 44270 }, { - "epoch": 0.4, - "learning_rate": 3.051391766507522e-05, - "loss": 0.2625, + "epoch": 0.1, + "learning_rate": 4.516095836782175e-05, + "loss": 0.2672, "step": 44280 }, { - "epoch": 0.4, - "learning_rate": 3.0509413566345373e-05, - "loss": 0.2549, + "epoch": 0.1, + "learning_rate": 4.5159839824612426e-05, + "loss": 0.2716, "step": 44290 }, { - "epoch": 0.4, - "learning_rate": 3.0504909467615534e-05, - "loss": 0.2505, + "epoch": 0.1, + "learning_rate": 4.5158721281403104e-05, + "loss": 0.274, "step": 44300 }, { - "epoch": 0.4, - "learning_rate": 3.050040536888569e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.5157602738193776e-05, + "loss": 0.2686, "step": 44310 }, { - "epoch": 0.4, - "learning_rate": 3.0495901270155842e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.5156484194984453e-05, + "loss": 0.2758, "step": 44320 }, { - "epoch": 0.4, - "learning_rate": 3.0491397171426e-05, - "loss": 0.2578, + "epoch": 0.1, + "learning_rate": 4.5155365651775125e-05, + "loss": 0.2684, "step": 44330 }, { - "epoch": 0.4, - "learning_rate": 3.0486893072696154e-05, - "loss": 0.2571, + "epoch": 0.1, + "learning_rate": 4.51542471085658e-05, + "loss": 0.2686, "step": 44340 }, { - "epoch": 0.4, - "learning_rate": 3.0482388973966308e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.515312856535649e-05, + "loss": 0.2763, "step": 44350 }, { - "epoch": 0.4, - "learning_rate": 3.047788487523647e-05, - "loss": 0.2522, + "epoch": 0.1, + "learning_rate": 4.515201002214716e-05, + "loss": 0.2717, "step": 44360 }, { - "epoch": 0.4, - "learning_rate": 3.0473380776506623e-05, - "loss": 0.2538, + "epoch": 0.1, + "learning_rate": 4.5150891478937836e-05, + "loss": 0.2729, "step": 44370 }, { - "epoch": 0.4, - "learning_rate": 3.046887667777678e-05, - "loss": 0.2551, + "epoch": 0.1, + "learning_rate": 4.514977293572851e-05, + "loss": 0.2695, "step": 44380 }, { - "epoch": 0.4, - "learning_rate": 3.0464372579046935e-05, - "loss": 0.2552, + "epoch": 0.1, + "learning_rate": 4.5148654392519185e-05, + "loss": 0.2716, "step": 44390 }, { - "epoch": 0.4, - "learning_rate": 3.045986848031709e-05, - "loss": 0.2596, + "epoch": 0.1, + "learning_rate": 4.514753584930986e-05, + "loss": 0.2776, "step": 44400 }, { - "epoch": 0.4, - "learning_rate": 3.0455364381587246e-05, - "loss": 0.2589, + "epoch": 0.1, + "learning_rate": 4.5146417306100535e-05, + "loss": 0.2697, "step": 44410 }, { - "epoch": 0.4, - "learning_rate": 3.04508602828574e-05, - "loss": 0.257, + "epoch": 0.1, + "learning_rate": 4.514529876289121e-05, + "loss": 0.2714, "step": 44420 }, { - "epoch": 0.4, - "learning_rate": 3.0446356184127555e-05, - "loss": 0.2592, + "epoch": 0.1, + "learning_rate": 4.5144180219681884e-05, + "loss": 0.2712, "step": 44430 }, { - "epoch": 0.4, - "learning_rate": 3.0441852085397715e-05, - "loss": 0.2623, + "epoch": 0.1, + "learning_rate": 4.514306167647256e-05, + "loss": 0.2713, "step": 44440 }, { - "epoch": 0.4, - "learning_rate": 3.043734798666787e-05, - "loss": 0.2566, + "epoch": 0.1, + "learning_rate": 4.514194313326324e-05, + "loss": 0.2708, "step": 44450 }, { - "epoch": 0.4, - "learning_rate": 3.0432843887938024e-05, - "loss": 0.2525, + "epoch": 0.1, + "learning_rate": 4.514082459005392e-05, + "loss": 0.2702, "step": 44460 }, { - "epoch": 0.4, - "learning_rate": 3.042833978920818e-05, - "loss": 0.2519, + "epoch": 0.1, + "learning_rate": 4.5139706046844595e-05, + "loss": 0.2728, "step": 44470 }, { - "epoch": 0.4, - "learning_rate": 3.0423835690478335e-05, - "loss": 0.2544, + "epoch": 0.1, + "learning_rate": 4.5138587503635266e-05, + "loss": 0.273, "step": 44480 }, { - "epoch": 0.4, - "learning_rate": 3.041933159174849e-05, - "loss": 0.2559, + "epoch": 0.1, + "learning_rate": 4.5137468960425944e-05, + "loss": 0.274, "step": 44490 }, { - "epoch": 0.4, - "learning_rate": 3.041482749301865e-05, - "loss": 0.2532, + "epoch": 0.1, + "learning_rate": 4.513635041721662e-05, + "loss": 0.2746, "step": 44500 }, { - "epoch": 0.4, - "learning_rate": 3.0410323394288804e-05, - "loss": 0.2507, + "epoch": 0.1, + "learning_rate": 4.5135231874007293e-05, + "loss": 0.2621, "step": 44510 }, { - "epoch": 0.4, - "learning_rate": 3.0405819295558962e-05, - "loss": 0.2573, + "epoch": 0.1, + "learning_rate": 4.513411333079797e-05, + "loss": 0.2679, "step": 44520 }, { - "epoch": 0.4, - "learning_rate": 3.0401315196829116e-05, - "loss": 0.259, + "epoch": 0.1, + "learning_rate": 4.513299478758864e-05, + "loss": 0.2623, "step": 44530 }, { - "epoch": 0.4, - "learning_rate": 3.039681109809927e-05, - "loss": 0.2537, + "epoch": 0.1, + "learning_rate": 4.513187624437932e-05, + "loss": 0.2692, "step": 44540 }, { - "epoch": 0.4, - "learning_rate": 3.039230699936943e-05, - "loss": 0.2567, + "epoch": 0.1, + "learning_rate": 4.513075770117e-05, + "loss": 0.2717, "step": 44550 }, { - "epoch": 0.4, - "learning_rate": 3.0387802900639585e-05, - "loss": 0.2591, + "epoch": 0.1, + "learning_rate": 4.5129639157960676e-05, + "loss": 0.2654, "step": 44560 }, { - "epoch": 0.4, - "learning_rate": 3.038329880190974e-05, - "loss": 0.2497, + "epoch": 0.1, + "learning_rate": 4.5128520614751354e-05, + "loss": 0.2729, "step": 44570 }, { - "epoch": 0.4, - "learning_rate": 3.0378794703179897e-05, - "loss": 0.2546, + "epoch": 0.1, + "learning_rate": 4.5127402071542025e-05, + "loss": 0.2738, "step": 44580 }, { - "epoch": 0.4, - "learning_rate": 3.037429060445005e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.51262835283327e-05, + "loss": 0.2678, "step": 44590 }, { - "epoch": 0.4, - "learning_rate": 3.0369786505720205e-05, - "loss": 0.2525, + "epoch": 0.1, + "learning_rate": 4.5125164985123374e-05, + "loss": 0.2681, "step": 44600 }, { - "epoch": 0.4, - "learning_rate": 3.0365282406990366e-05, - "loss": 0.2509, + "epoch": 0.1, + "learning_rate": 4.512404644191405e-05, + "loss": 0.2639, "step": 44610 }, { - "epoch": 0.4, - "learning_rate": 3.0360778308260516e-05, - "loss": 0.2584, + "epoch": 0.1, + "learning_rate": 4.512292789870473e-05, + "loss": 0.2674, "step": 44620 }, { - "epoch": 0.4, - "learning_rate": 3.035627420953067e-05, - "loss": 0.2555, + "epoch": 0.1, + "learning_rate": 4.51218093554954e-05, + "loss": 0.2797, "step": 44630 }, { - "epoch": 0.4, - "learning_rate": 3.035177011080083e-05, - "loss": 0.2611, + "epoch": 0.1, + "learning_rate": 4.512069081228608e-05, + "loss": 0.2732, "step": 44640 }, { - "epoch": 0.4, - "learning_rate": 3.0347266012070986e-05, - "loss": 0.2597, + "epoch": 0.1, + "learning_rate": 4.511957226907676e-05, + "loss": 0.2635, "step": 44650 }, { - "epoch": 0.4, - "learning_rate": 3.0342761913341143e-05, - "loss": 0.2606, + "epoch": 0.1, + "learning_rate": 4.5118453725867435e-05, + "loss": 0.2716, "step": 44660 }, { - "epoch": 0.4, - "learning_rate": 3.0338257814611297e-05, - "loss": 0.2568, + "epoch": 0.1, + "learning_rate": 4.511733518265811e-05, + "loss": 0.2719, "step": 44670 }, { - "epoch": 0.4, - "learning_rate": 3.033375371588145e-05, - "loss": 0.2538, + "epoch": 0.1, + "learning_rate": 4.5116216639448784e-05, + "loss": 0.263, "step": 44680 }, { - "epoch": 0.4, - "learning_rate": 3.0329249617151612e-05, - "loss": 0.2523, + "epoch": 0.1, + "learning_rate": 4.511509809623946e-05, + "loss": 0.2757, "step": 44690 }, { - "epoch": 0.4, - "learning_rate": 3.0324745518421766e-05, - "loss": 0.2632, + "epoch": 0.1, + "learning_rate": 4.5113979553030133e-05, + "loss": 0.268, "step": 44700 }, { - "epoch": 0.4, - "learning_rate": 3.032024141969192e-05, - "loss": 0.2506, + "epoch": 0.1, + "learning_rate": 4.511286100982081e-05, + "loss": 0.2689, "step": 44710 }, { - "epoch": 0.4, - "learning_rate": 3.0315737320962078e-05, - "loss": 0.2543, + "epoch": 0.1, + "learning_rate": 4.511174246661149e-05, + "loss": 0.2686, "step": 44720 }, { - "epoch": 0.4, - "learning_rate": 3.0311233222232232e-05, - "loss": 0.2617, + "epoch": 0.1, + "learning_rate": 4.511062392340216e-05, + "loss": 0.2705, "step": 44730 }, { - "epoch": 0.4, - "learning_rate": 3.0306729123502386e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.510950538019284e-05, + "loss": 0.2748, "step": 44740 }, { - "epoch": 0.4, - "learning_rate": 3.0302225024772547e-05, - "loss": 0.2573, + "epoch": 0.1, + "learning_rate": 4.510838683698351e-05, + "loss": 0.2672, "step": 44750 }, { - "epoch": 0.4, - "learning_rate": 3.02977209260427e-05, - "loss": 0.2592, + "epoch": 0.1, + "learning_rate": 4.5107268293774194e-05, + "loss": 0.2699, "step": 44760 }, { - "epoch": 0.4, - "learning_rate": 3.0293216827312855e-05, - "loss": 0.2573, + "epoch": 0.1, + "learning_rate": 4.510614975056487e-05, + "loss": 0.2717, "step": 44770 }, { - "epoch": 0.4, - "learning_rate": 3.0288712728583013e-05, - "loss": 0.2604, + "epoch": 0.1, + "learning_rate": 4.510503120735554e-05, + "loss": 0.2679, "step": 44780 }, { - "epoch": 0.4, - "learning_rate": 3.0284208629853167e-05, - "loss": 0.2627, + "epoch": 0.1, + "learning_rate": 4.510391266414622e-05, + "loss": 0.2653, "step": 44790 }, { - "epoch": 0.4, - "learning_rate": 3.0279704531123328e-05, - "loss": 0.2511, + "epoch": 0.1, + "learning_rate": 4.510279412093689e-05, + "loss": 0.2712, "step": 44800 }, { - "epoch": 0.4, - "learning_rate": 3.027520043239348e-05, - "loss": 0.2567, + "epoch": 0.1, + "learning_rate": 4.510167557772757e-05, + "loss": 0.2638, "step": 44810 }, { - "epoch": 0.4, - "learning_rate": 3.0270696333663632e-05, - "loss": 0.2532, + "epoch": 0.1, + "learning_rate": 4.510055703451825e-05, + "loss": 0.2691, "step": 44820 }, { - "epoch": 0.4, - "learning_rate": 3.0266192234933793e-05, - "loss": 0.2601, + "epoch": 0.1, + "learning_rate": 4.509943849130892e-05, + "loss": 0.2676, "step": 44830 }, { - "epoch": 0.4, - "learning_rate": 3.0261688136203947e-05, - "loss": 0.2556, + "epoch": 0.1, + "learning_rate": 4.50983199480996e-05, + "loss": 0.2742, "step": 44840 }, { - "epoch": 0.4, - "learning_rate": 3.02571840374741e-05, - "loss": 0.255, + "epoch": 0.1, + "learning_rate": 4.509720140489027e-05, + "loss": 0.267, "step": 44850 }, { - "epoch": 0.4, - "learning_rate": 3.025267993874426e-05, - "loss": 0.2606, + "epoch": 0.1, + "learning_rate": 4.5096082861680946e-05, + "loss": 0.2674, "step": 44860 }, { - "epoch": 0.4, - "learning_rate": 3.0248175840014413e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.5094964318471624e-05, + "loss": 0.2646, "step": 44870 }, { - "epoch": 0.4, - "learning_rate": 3.0243671741284567e-05, - "loss": 0.264, + "epoch": 0.1, + "learning_rate": 4.50938457752623e-05, + "loss": 0.2665, "step": 44880 }, { - "epoch": 0.4, - "learning_rate": 3.0239167642554728e-05, - "loss": 0.2501, + "epoch": 0.1, + "learning_rate": 4.509272723205298e-05, + "loss": 0.2756, "step": 44890 }, { - "epoch": 0.4, - "learning_rate": 3.0234663543824882e-05, - "loss": 0.2547, + "epoch": 0.1, + "learning_rate": 4.509160868884365e-05, + "loss": 0.2733, "step": 44900 }, { - "epoch": 0.4, - "learning_rate": 3.0230159445095036e-05, - "loss": 0.257, + "epoch": 0.1, + "learning_rate": 4.509049014563433e-05, + "loss": 0.267, "step": 44910 }, { - "epoch": 0.4, - "learning_rate": 3.0225655346365194e-05, - "loss": 0.2523, + "epoch": 0.1, + "learning_rate": 4.5089371602425e-05, + "loss": 0.2711, "step": 44920 }, { - "epoch": 0.4, - "learning_rate": 3.0221151247635348e-05, - "loss": 0.2581, + "epoch": 0.1, + "learning_rate": 4.508825305921568e-05, + "loss": 0.2697, "step": 44930 }, { - "epoch": 0.4, - "learning_rate": 3.021664714890551e-05, - "loss": 0.2573, + "epoch": 0.1, + "learning_rate": 4.5087134516006356e-05, + "loss": 0.2709, "step": 44940 }, { - "epoch": 0.4, - "learning_rate": 3.0212143050175663e-05, - "loss": 0.2548, + "epoch": 0.1, + "learning_rate": 4.508601597279703e-05, + "loss": 0.2689, "step": 44950 }, { - "epoch": 0.4, - "learning_rate": 3.0207638951445817e-05, - "loss": 0.2515, + "epoch": 0.1, + "learning_rate": 4.5084897429587705e-05, + "loss": 0.2689, "step": 44960 }, { - "epoch": 0.4, - "learning_rate": 3.0203134852715974e-05, - "loss": 0.2509, + "epoch": 0.1, + "learning_rate": 4.508377888637838e-05, + "loss": 0.2739, "step": 44970 }, { - "epoch": 0.4, - "learning_rate": 3.019863075398613e-05, - "loss": 0.2632, + "epoch": 0.1, + "learning_rate": 4.508266034316906e-05, + "loss": 0.267, "step": 44980 }, { - "epoch": 0.4, - "learning_rate": 3.0194126655256283e-05, - "loss": 0.2587, + "epoch": 0.1, + "learning_rate": 4.508154179995974e-05, + "loss": 0.2681, "step": 44990 }, { - "epoch": 0.4, - "learning_rate": 3.0189622556526444e-05, - "loss": 0.2616, + "epoch": 0.1, + "learning_rate": 4.508042325675041e-05, + "loss": 0.273, "step": 45000 }, { - "epoch": 0.4, - "learning_rate": 3.0185118457796598e-05, - "loss": 0.2576, + "epoch": 0.1, + "learning_rate": 4.507930471354109e-05, + "loss": 0.2701, "step": 45010 }, { - "epoch": 0.4, - "learning_rate": 3.0180614359066752e-05, - "loss": 0.2537, + "epoch": 0.1, + "learning_rate": 4.507818617033176e-05, + "loss": 0.2637, "step": 45020 }, { - "epoch": 0.4, - "learning_rate": 3.017611026033691e-05, - "loss": 0.2533, + "epoch": 0.1, + "learning_rate": 4.507706762712244e-05, + "loss": 0.2705, "step": 45030 }, { - "epoch": 0.4, - "learning_rate": 3.0171606161607063e-05, - "loss": 0.2632, + "epoch": 0.1, + "learning_rate": 4.5075949083913115e-05, + "loss": 0.2757, "step": 45040 }, { - "epoch": 0.4, - "learning_rate": 3.0167102062877217e-05, - "loss": 0.2595, + "epoch": 0.1, + "learning_rate": 4.5074830540703786e-05, + "loss": 0.2743, "step": 45050 }, { - "epoch": 0.4, - "learning_rate": 3.0162597964147375e-05, - "loss": 0.2484, + "epoch": 0.1, + "learning_rate": 4.5073711997494464e-05, + "loss": 0.2708, "step": 45060 }, { - "epoch": 0.4, - "learning_rate": 3.015809386541753e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.507259345428514e-05, + "loss": 0.2742, "step": 45070 }, { - "epoch": 0.4, - "learning_rate": 3.015358976668769e-05, - "loss": 0.2493, + "epoch": 0.1, + "learning_rate": 4.507147491107582e-05, + "loss": 0.2719, "step": 45080 }, { - "epoch": 0.4, - "learning_rate": 3.0149085667957844e-05, - "loss": 0.2552, + "epoch": 0.1, + "learning_rate": 4.50703563678665e-05, + "loss": 0.2637, "step": 45090 }, { - "epoch": 0.4, - "learning_rate": 3.0144581569227998e-05, - "loss": 0.2526, + "epoch": 0.1, + "learning_rate": 4.506923782465717e-05, + "loss": 0.2702, "step": 45100 }, { - "epoch": 0.4, - "learning_rate": 3.0140077470498156e-05, - "loss": 0.2511, + "epoch": 0.1, + "learning_rate": 4.506811928144785e-05, + "loss": 0.2698, "step": 45110 }, { - "epoch": 0.4, - "learning_rate": 3.013557337176831e-05, - "loss": 0.2514, + "epoch": 0.1, + "learning_rate": 4.506700073823852e-05, + "loss": 0.2708, "step": 45120 }, { - "epoch": 0.4, - "learning_rate": 3.0131069273038464e-05, - "loss": 0.2566, + "epoch": 0.1, + "learning_rate": 4.5065882195029196e-05, + "loss": 0.2715, "step": 45130 }, { - "epoch": 0.4, - "learning_rate": 3.0126565174308625e-05, - "loss": 0.2556, + "epoch": 0.1, + "learning_rate": 4.5064763651819874e-05, + "loss": 0.2697, "step": 45140 }, { - "epoch": 0.4, - "learning_rate": 3.012206107557878e-05, - "loss": 0.255, + "epoch": 0.1, + "learning_rate": 4.5063645108610545e-05, + "loss": 0.2626, "step": 45150 }, { - "epoch": 0.4, - "learning_rate": 3.0117556976848933e-05, - "loss": 0.2571, + "epoch": 0.1, + "learning_rate": 4.506252656540122e-05, + "loss": 0.2622, "step": 45160 }, { - "epoch": 0.4, - "learning_rate": 3.011305287811909e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.5061408022191894e-05, + "loss": 0.2646, "step": 45170 }, { - "epoch": 0.4, - "learning_rate": 3.0108548779389245e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.506028947898258e-05, + "loss": 0.2708, "step": 45180 }, { - "epoch": 0.4, - "learning_rate": 3.01040446806594e-05, - "loss": 0.2609, + "epoch": 0.1, + "learning_rate": 4.505917093577325e-05, + "loss": 0.2702, "step": 45190 }, { - "epoch": 0.4, - "learning_rate": 3.009954058192956e-05, - "loss": 0.2547, + "epoch": 0.1, + "learning_rate": 4.505805239256393e-05, + "loss": 0.2693, "step": 45200 }, { - "epoch": 0.4, - "learning_rate": 3.0095036483199714e-05, - "loss": 0.2496, + "epoch": 0.1, + "learning_rate": 4.5056933849354606e-05, + "loss": 0.2699, "step": 45210 }, { - "epoch": 0.4, - "learning_rate": 3.009053238446987e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.505581530614528e-05, + "loss": 0.2755, "step": 45220 }, { - "epoch": 0.4, - "learning_rate": 3.0086028285740025e-05, - "loss": 0.2575, + "epoch": 0.1, + "learning_rate": 4.5054696762935955e-05, + "loss": 0.274, "step": 45230 }, { - "epoch": 0.4, - "learning_rate": 3.008152418701018e-05, - "loss": 0.2534, + "epoch": 0.1, + "learning_rate": 4.5053578219726626e-05, + "loss": 0.2688, "step": 45240 }, { - "epoch": 0.4, - "learning_rate": 3.007702008828034e-05, - "loss": 0.2531, + "epoch": 0.1, + "learning_rate": 4.5052459676517304e-05, + "loss": 0.2738, "step": 45250 }, { - "epoch": 0.4, - "learning_rate": 3.0072515989550494e-05, - "loss": 0.2563, + "epoch": 0.1, + "learning_rate": 4.505134113330798e-05, + "loss": 0.2636, "step": 45260 }, { - "epoch": 0.4, - "learning_rate": 3.0068011890820645e-05, - "loss": 0.2531, + "epoch": 0.1, + "learning_rate": 4.505022259009865e-05, + "loss": 0.2697, "step": 45270 }, { - "epoch": 0.4, - "learning_rate": 3.0063507792090806e-05, - "loss": 0.2561, + "epoch": 0.1, + "learning_rate": 4.504910404688933e-05, + "loss": 0.2657, "step": 45280 }, { - "epoch": 0.4, - "learning_rate": 3.005900369336096e-05, - "loss": 0.2567, + "epoch": 0.1, + "learning_rate": 4.504798550368001e-05, + "loss": 0.2728, "step": 45290 }, { - "epoch": 0.4, - "learning_rate": 3.0054499594631114e-05, - "loss": 0.2661, + "epoch": 0.1, + "learning_rate": 4.504686696047069e-05, + "loss": 0.2717, "step": 45300 }, { - "epoch": 0.4, - "learning_rate": 3.004999549590127e-05, - "loss": 0.2506, + "epoch": 0.1, + "learning_rate": 4.5045748417261365e-05, + "loss": 0.2705, "step": 45310 }, { - "epoch": 0.4, - "learning_rate": 3.0045491397171426e-05, - "loss": 0.2552, + "epoch": 0.1, + "learning_rate": 4.5044629874052036e-05, + "loss": 0.2658, "step": 45320 }, { - "epoch": 0.4, - "learning_rate": 3.004098729844158e-05, - "loss": 0.2486, + "epoch": 0.1, + "learning_rate": 4.5043511330842714e-05, + "loss": 0.265, "step": 45330 }, { - "epoch": 0.4, - "learning_rate": 3.003648319971174e-05, - "loss": 0.2516, + "epoch": 0.1, + "learning_rate": 4.5042392787633385e-05, + "loss": 0.2714, "step": 45340 }, { - "epoch": 0.4, - "learning_rate": 3.0031979100981895e-05, - "loss": 0.2555, + "epoch": 0.1, + "learning_rate": 4.504127424442406e-05, + "loss": 0.2692, "step": 45350 }, { - "epoch": 0.4, - "learning_rate": 3.0027475002252052e-05, - "loss": 0.2571, + "epoch": 0.1, + "learning_rate": 4.504015570121474e-05, + "loss": 0.2731, "step": 45360 }, { - "epoch": 0.41, - "learning_rate": 3.0022970903522206e-05, - "loss": 0.2594, + "epoch": 0.1, + "learning_rate": 4.503903715800541e-05, + "loss": 0.2648, "step": 45370 }, { - "epoch": 0.41, - "learning_rate": 3.001846680479236e-05, - "loss": 0.2599, + "epoch": 0.1, + "learning_rate": 4.503791861479609e-05, + "loss": 0.2678, "step": 45380 }, { - "epoch": 0.41, - "learning_rate": 3.001396270606252e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.503680007158677e-05, + "loss": 0.267, "step": 45390 }, { - "epoch": 0.41, - "learning_rate": 3.0009458607332675e-05, - "loss": 0.2541, + "epoch": 0.1, + "learning_rate": 4.5035681528377446e-05, + "loss": 0.2686, "step": 45400 }, { - "epoch": 0.41, - "learning_rate": 3.000495450860283e-05, - "loss": 0.2511, + "epoch": 0.1, + "learning_rate": 4.5034562985168124e-05, + "loss": 0.2676, "step": 45410 }, { - "epoch": 0.41, - "learning_rate": 3.0000450409872987e-05, - "loss": 0.2586, + "epoch": 0.1, + "learning_rate": 4.5033444441958795e-05, + "loss": 0.2705, "step": 45420 }, { - "epoch": 0.41, - "learning_rate": 2.999594631114314e-05, - "loss": 0.2558, + "epoch": 0.1, + "learning_rate": 4.503232589874947e-05, + "loss": 0.2721, "step": 45430 }, { - "epoch": 0.41, - "learning_rate": 2.9991442212413295e-05, - "loss": 0.2526, + "epoch": 0.1, + "learning_rate": 4.5031207355540144e-05, + "loss": 0.272, "step": 45440 }, { - "epoch": 0.41, - "learning_rate": 2.9986938113683456e-05, - "loss": 0.2617, + "epoch": 0.1, + "learning_rate": 4.503008881233082e-05, + "loss": 0.266, "step": 45450 }, { - "epoch": 0.41, - "learning_rate": 2.998243401495361e-05, - "loss": 0.2539, + "epoch": 0.1, + "learning_rate": 4.50289702691215e-05, + "loss": 0.2704, "step": 45460 }, { - "epoch": 0.41, - "learning_rate": 2.997792991622376e-05, - "loss": 0.2532, + "epoch": 0.1, + "learning_rate": 4.502785172591217e-05, + "loss": 0.274, "step": 45470 }, { - "epoch": 0.41, - "learning_rate": 2.9973425817493922e-05, - "loss": 0.255, + "epoch": 0.1, + "learning_rate": 4.502673318270285e-05, + "loss": 0.2666, "step": 45480 }, { - "epoch": 0.41, - "learning_rate": 2.9968921718764076e-05, - "loss": 0.2582, + "epoch": 0.1, + "learning_rate": 4.502561463949353e-05, + "loss": 0.2679, "step": 45490 }, { - "epoch": 0.41, - "learning_rate": 2.9964417620034237e-05, - "loss": 0.2543, + "epoch": 0.1, + "learning_rate": 4.5024496096284205e-05, + "loss": 0.2667, "step": 45500 }, { - "epoch": 0.41, - "learning_rate": 2.9959913521304388e-05, - "loss": 0.2515, + "epoch": 0.1, + "learning_rate": 4.5023377553074876e-05, + "loss": 0.2683, "step": 45510 }, { - "epoch": 0.41, - "learning_rate": 2.995540942257454e-05, - "loss": 0.2508, + "epoch": 0.1, + "learning_rate": 4.5022259009865554e-05, + "loss": 0.2694, "step": 45520 }, { - "epoch": 0.41, - "learning_rate": 2.9950905323844703e-05, - "loss": 0.252, + "epoch": 0.1, + "learning_rate": 4.502114046665623e-05, + "loss": 0.2726, "step": 45530 }, { - "epoch": 0.41, - "learning_rate": 2.9946401225114857e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.50200219234469e-05, + "loss": 0.2674, "step": 45540 }, { - "epoch": 0.41, - "learning_rate": 2.994189712638501e-05, - "loss": 0.2521, + "epoch": 0.1, + "learning_rate": 4.501890338023758e-05, + "loss": 0.2692, "step": 45550 }, { - "epoch": 0.41, - "learning_rate": 2.9937393027655168e-05, - "loss": 0.2506, + "epoch": 0.1, + "learning_rate": 4.501778483702825e-05, + "loss": 0.2674, "step": 45560 }, { - "epoch": 0.41, - "learning_rate": 2.9932888928925322e-05, - "loss": 0.2484, + "epoch": 0.1, + "learning_rate": 4.501666629381893e-05, + "loss": 0.2732, "step": 45570 }, { - "epoch": 0.41, - "learning_rate": 2.9928384830195476e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.501554775060961e-05, + "loss": 0.2678, "step": 45580 }, { - "epoch": 0.41, - "learning_rate": 2.9923880731465637e-05, - "loss": 0.2548, + "epoch": 0.1, + "learning_rate": 4.5014429207400286e-05, + "loss": 0.2641, "step": 45590 }, { - "epoch": 0.41, - "learning_rate": 2.991937663273579e-05, - "loss": 0.2582, + "epoch": 0.1, + "learning_rate": 4.5013310664190964e-05, + "loss": 0.2693, "step": 45600 }, { - "epoch": 0.41, - "learning_rate": 2.9915322943878932e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.5012192120981635e-05, + "loss": 0.2725, "step": 45610 }, { - "epoch": 0.41, - "learning_rate": 2.9910818845149086e-05, - "loss": 0.2524, + "epoch": 0.1, + "learning_rate": 4.501107357777231e-05, + "loss": 0.2655, "step": 45620 }, { - "epoch": 0.41, - "learning_rate": 2.9906314746419243e-05, - "loss": 0.252, + "epoch": 0.1, + "learning_rate": 4.500995503456299e-05, + "loss": 0.2715, "step": 45630 }, { - "epoch": 0.41, - "learning_rate": 2.9901810647689397e-05, - "loss": 0.2519, + "epoch": 0.1, + "learning_rate": 4.500883649135366e-05, + "loss": 0.2651, "step": 45640 }, { - "epoch": 0.41, - "learning_rate": 2.989730654895955e-05, - "loss": 0.2556, + "epoch": 0.1, + "learning_rate": 4.500771794814434e-05, + "loss": 0.269, "step": 45650 }, { - "epoch": 0.41, - "learning_rate": 2.9892802450229712e-05, - "loss": 0.2489, + "epoch": 0.1, + "learning_rate": 4.500659940493501e-05, + "loss": 0.2632, "step": 45660 }, { - "epoch": 0.41, - "learning_rate": 2.9888298351499867e-05, - "loss": 0.2494, + "epoch": 0.1, + "learning_rate": 4.500548086172569e-05, + "loss": 0.2665, "step": 45670 }, { - "epoch": 0.41, - "learning_rate": 2.988379425277002e-05, - "loss": 0.2535, + "epoch": 0.1, + "learning_rate": 4.500436231851637e-05, + "loss": 0.267, "step": 45680 }, { - "epoch": 0.41, - "learning_rate": 2.9879290154040178e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.500324377530704e-05, + "loss": 0.2714, "step": 45690 }, { - "epoch": 0.41, - "learning_rate": 2.9874786055310332e-05, - "loss": 0.2571, + "epoch": 0.1, + "learning_rate": 4.5002125232097716e-05, + "loss": 0.2661, "step": 45700 }, { - "epoch": 0.41, - "learning_rate": 2.9870281956580486e-05, - "loss": 0.2575, + "epoch": 0.1, + "learning_rate": 4.5001006688888394e-05, + "loss": 0.2693, "step": 45710 }, { - "epoch": 0.41, - "learning_rate": 2.9865777857850647e-05, - "loss": 0.2502, + "epoch": 0.1, + "learning_rate": 4.499988814567907e-05, + "loss": 0.2648, "step": 45720 }, { - "epoch": 0.41, - "learning_rate": 2.98612737591208e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.499876960246975e-05, + "loss": 0.2666, "step": 45730 }, { - "epoch": 0.41, - "learning_rate": 2.985676966039096e-05, - "loss": 0.253, + "epoch": 0.1, + "learning_rate": 4.499765105926042e-05, + "loss": 0.2688, "step": 45740 }, { - "epoch": 0.41, - "learning_rate": 2.9852265561661113e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.49965325160511e-05, + "loss": 0.2738, "step": 45750 }, { - "epoch": 0.41, - "learning_rate": 2.9847761462931267e-05, - "loss": 0.2548, + "epoch": 0.1, + "learning_rate": 4.499541397284177e-05, + "loss": 0.2675, "step": 45760 }, { - "epoch": 0.41, - "learning_rate": 2.9843257364201428e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.499429542963245e-05, + "loss": 0.2687, "step": 45770 }, { - "epoch": 0.41, - "learning_rate": 2.9838753265471582e-05, - "loss": 0.2489, + "epoch": 0.1, + "learning_rate": 4.4993176886423126e-05, + "loss": 0.2662, "step": 45780 }, { - "epoch": 0.41, - "learning_rate": 2.9834249166741736e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.49920583432138e-05, + "loss": 0.2707, "step": 45790 }, { - "epoch": 0.41, - "learning_rate": 2.9829745068011894e-05, - "loss": 0.2492, + "epoch": 0.1, + "learning_rate": 4.4990939800004475e-05, + "loss": 0.2652, "step": 45800 }, { - "epoch": 0.41, - "learning_rate": 2.9825240969282048e-05, - "loss": 0.2592, + "epoch": 0.1, + "learning_rate": 4.498982125679515e-05, + "loss": 0.2661, "step": 45810 }, { - "epoch": 0.41, - "learning_rate": 2.9820736870552202e-05, - "loss": 0.2556, + "epoch": 0.1, + "learning_rate": 4.498870271358583e-05, + "loss": 0.2706, "step": 45820 }, { - "epoch": 0.41, - "learning_rate": 2.9816232771822363e-05, - "loss": 0.2505, + "epoch": 0.1, + "learning_rate": 4.49875841703765e-05, + "loss": 0.2675, "step": 45830 }, { - "epoch": 0.41, - "learning_rate": 2.9811728673092513e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.498646562716718e-05, + "loss": 0.2687, "step": 45840 }, { - "epoch": 0.41, - "learning_rate": 2.9807224574362668e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.498534708395786e-05, + "loss": 0.2671, "step": 45850 }, { - "epoch": 0.41, - "learning_rate": 2.980272047563283e-05, - "loss": 0.2498, + "epoch": 0.1, + "learning_rate": 4.498422854074853e-05, + "loss": 0.2642, "step": 45860 }, { - "epoch": 0.41, - "learning_rate": 2.9798216376902983e-05, - "loss": 0.2553, + "epoch": 0.1, + "learning_rate": 4.498310999753921e-05, + "loss": 0.2676, "step": 45870 }, { - "epoch": 0.41, - "learning_rate": 2.979371227817314e-05, - "loss": 0.2507, + "epoch": 0.1, + "learning_rate": 4.498199145432988e-05, + "loss": 0.2631, "step": 45880 }, { - "epoch": 0.41, - "learning_rate": 2.9789208179443294e-05, - "loss": 0.258, + "epoch": 0.1, + "learning_rate": 4.4980872911120556e-05, + "loss": 0.2647, "step": 45890 }, { - "epoch": 0.41, - "learning_rate": 2.9784704080713448e-05, - "loss": 0.2508, + "epoch": 0.1, + "learning_rate": 4.4979754367911234e-05, + "loss": 0.2651, "step": 45900 }, { - "epoch": 0.41, - "learning_rate": 2.978019998198361e-05, - "loss": 0.2564, + "epoch": 0.1, + "learning_rate": 4.497863582470191e-05, + "loss": 0.2652, "step": 45910 }, { - "epoch": 0.41, - "learning_rate": 2.9775695883253763e-05, - "loss": 0.2463, + "epoch": 0.1, + "learning_rate": 4.497751728149259e-05, + "loss": 0.2638, "step": 45920 }, { - "epoch": 0.41, - "learning_rate": 2.9771191784523917e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.497639873828326e-05, + "loss": 0.2667, "step": 45930 }, { - "epoch": 0.41, - "learning_rate": 2.9766687685794075e-05, - "loss": 0.2565, + "epoch": 0.1, + "learning_rate": 4.497528019507394e-05, + "loss": 0.2639, "step": 45940 }, { - "epoch": 0.41, - "learning_rate": 2.976218358706423e-05, - "loss": 0.2526, + "epoch": 0.1, + "learning_rate": 4.497416165186462e-05, + "loss": 0.2643, "step": 45950 }, { - "epoch": 0.41, - "learning_rate": 2.9757679488334383e-05, - "loss": 0.2531, + "epoch": 0.1, + "learning_rate": 4.497304310865529e-05, + "loss": 0.2722, "step": 45960 }, { - "epoch": 0.41, - "learning_rate": 2.9753175389604544e-05, - "loss": 0.2537, + "epoch": 0.1, + "learning_rate": 4.4971924565445966e-05, + "loss": 0.2581, "step": 45970 }, { - "epoch": 0.41, - "learning_rate": 2.9748671290874698e-05, - "loss": 0.2552, + "epoch": 0.1, + "learning_rate": 4.497080602223664e-05, + "loss": 0.2687, "step": 45980 }, { - "epoch": 0.41, - "learning_rate": 2.9744167192144852e-05, - "loss": 0.2521, + "epoch": 0.1, + "learning_rate": 4.4969687479027315e-05, + "loss": 0.2652, "step": 45990 }, { - "epoch": 0.41, - "learning_rate": 2.973966309341501e-05, - "loss": 0.2578, + "epoch": 0.1, + "learning_rate": 4.496856893581799e-05, + "loss": 0.2665, "step": 46000 }, { - "epoch": 0.41, - "learning_rate": 2.9735158994685164e-05, - "loss": 0.2612, + "epoch": 0.1, + "learning_rate": 4.496745039260867e-05, + "loss": 0.2687, "step": 46010 }, { - "epoch": 0.41, - "learning_rate": 2.9730654895955325e-05, - "loss": 0.2527, + "epoch": 0.1, + "learning_rate": 4.496633184939935e-05, + "loss": 0.265, "step": 46020 }, { - "epoch": 0.41, - "learning_rate": 2.972615079722548e-05, - "loss": 0.2494, + "epoch": 0.1, + "learning_rate": 4.496521330619002e-05, + "loss": 0.2663, "step": 46030 }, { - "epoch": 0.41, - "learning_rate": 2.972164669849563e-05, - "loss": 0.2568, + "epoch": 0.1, + "learning_rate": 4.49640947629807e-05, + "loss": 0.2674, "step": 46040 }, { - "epoch": 0.41, - "learning_rate": 2.971714259976579e-05, - "loss": 0.2589, + "epoch": 0.1, + "learning_rate": 4.4962976219771376e-05, + "loss": 0.2657, "step": 46050 }, { - "epoch": 0.41, - "learning_rate": 2.9712638501035944e-05, - "loss": 0.2602, + "epoch": 0.1, + "learning_rate": 4.496185767656205e-05, + "loss": 0.2683, "step": 46060 }, { - "epoch": 0.41, - "learning_rate": 2.97081344023061e-05, - "loss": 0.2554, + "epoch": 0.1, + "learning_rate": 4.4960739133352725e-05, + "loss": 0.2646, "step": 46070 }, { - "epoch": 0.41, - "learning_rate": 2.9703630303576256e-05, - "loss": 0.2575, + "epoch": 0.1, + "learning_rate": 4.4959620590143396e-05, + "loss": 0.2663, "step": 46080 }, { - "epoch": 0.41, - "learning_rate": 2.969912620484641e-05, - "loss": 0.2556, + "epoch": 0.1, + "learning_rate": 4.4958502046934074e-05, + "loss": 0.2647, "step": 46090 }, { - "epoch": 0.41, - "learning_rate": 2.9694622106116564e-05, - "loss": 0.2567, + "epoch": 0.1, + "learning_rate": 4.495738350372475e-05, + "loss": 0.2606, "step": 46100 }, { - "epoch": 0.41, - "learning_rate": 2.9690118007386725e-05, - "loss": 0.2507, + "epoch": 0.1, + "learning_rate": 4.495626496051542e-05, + "loss": 0.2602, "step": 46110 }, { - "epoch": 0.41, - "learning_rate": 2.968561390865688e-05, - "loss": 0.2607, + "epoch": 0.1, + "learning_rate": 4.49551464173061e-05, + "loss": 0.2729, "step": 46120 }, { - "epoch": 0.41, - "learning_rate": 2.9681109809927033e-05, - "loss": 0.2498, + "epoch": 0.1, + "learning_rate": 4.495402787409678e-05, + "loss": 0.2632, "step": 46130 }, { - "epoch": 0.41, - "learning_rate": 2.967660571119719e-05, - "loss": 0.2473, + "epoch": 0.1, + "learning_rate": 4.495290933088746e-05, + "loss": 0.2647, "step": 46140 }, { - "epoch": 0.41, - "learning_rate": 2.9672101612467345e-05, - "loss": 0.2465, + "epoch": 0.1, + "learning_rate": 4.495179078767813e-05, + "loss": 0.2668, "step": 46150 }, { - "epoch": 0.41, - "learning_rate": 2.9667597513737506e-05, - "loss": 0.2503, + "epoch": 0.1, + "learning_rate": 4.4950672244468806e-05, + "loss": 0.2668, "step": 46160 }, { - "epoch": 0.41, - "learning_rate": 2.966309341500766e-05, - "loss": 0.2539, + "epoch": 0.1, + "learning_rate": 4.4949553701259484e-05, + "loss": 0.2639, "step": 46170 }, { - "epoch": 0.41, - "learning_rate": 2.9658589316277814e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.4948435158050155e-05, + "loss": 0.2687, "step": 46180 }, { - "epoch": 0.41, - "learning_rate": 2.965408521754797e-05, - "loss": 0.2534, + "epoch": 0.1, + "learning_rate": 4.494731661484083e-05, + "loss": 0.2656, "step": 46190 }, { - "epoch": 0.41, - "learning_rate": 2.9649581118818126e-05, - "loss": 0.2585, + "epoch": 0.1, + "learning_rate": 4.4946198071631504e-05, + "loss": 0.2665, "step": 46200 }, { - "epoch": 0.41, - "learning_rate": 2.964507702008828e-05, - "loss": 0.2541, + "epoch": 0.1, + "learning_rate": 4.494507952842218e-05, + "loss": 0.2672, "step": 46210 }, { - "epoch": 0.41, - "learning_rate": 2.964057292135844e-05, - "loss": 0.2567, + "epoch": 0.1, + "learning_rate": 4.494396098521286e-05, + "loss": 0.2662, "step": 46220 }, { - "epoch": 0.41, - "learning_rate": 2.9636068822628595e-05, - "loss": 0.2486, + "epoch": 0.1, + "learning_rate": 4.494284244200354e-05, + "loss": 0.2641, "step": 46230 }, { - "epoch": 0.41, - "learning_rate": 2.9631564723898745e-05, - "loss": 0.2463, + "epoch": 0.1, + "learning_rate": 4.4941723898794216e-05, + "loss": 0.2667, "step": 46240 }, { - "epoch": 0.41, - "learning_rate": 2.9627060625168906e-05, - "loss": 0.2487, + "epoch": 0.1, + "learning_rate": 4.494060535558489e-05, + "loss": 0.2682, "step": 46250 }, { - "epoch": 0.41, - "learning_rate": 2.962255652643906e-05, - "loss": 0.2512, + "epoch": 0.1, + "learning_rate": 4.4939486812375565e-05, + "loss": 0.2623, "step": 46260 }, { - "epoch": 0.41, - "learning_rate": 2.9618052427709214e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.493836826916624e-05, + "loss": 0.2588, "step": 46270 }, { - "epoch": 0.41, - "learning_rate": 2.9613548328979372e-05, - "loss": 0.2546, + "epoch": 0.1, + "learning_rate": 4.4937249725956914e-05, + "loss": 0.27, "step": 46280 }, { - "epoch": 0.41, - "learning_rate": 2.9609044230249526e-05, - "loss": 0.2578, + "epoch": 0.1, + "learning_rate": 4.493613118274759e-05, + "loss": 0.2644, "step": 46290 }, { - "epoch": 0.41, - "learning_rate": 2.9604540131519687e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.493501263953826e-05, + "loss": 0.2686, "step": 46300 }, { - "epoch": 0.41, - "learning_rate": 2.960003603278984e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.493389409632894e-05, + "loss": 0.2637, "step": 46310 }, { - "epoch": 0.41, - "learning_rate": 2.9595531934059995e-05, - "loss": 0.2523, + "epoch": 0.1, + "learning_rate": 4.493277555311962e-05, + "loss": 0.2666, "step": 46320 }, { - "epoch": 0.41, - "learning_rate": 2.9591027835330153e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.49316570099103e-05, + "loss": 0.2664, "step": 46330 }, { - "epoch": 0.41, - "learning_rate": 2.9586523736600307e-05, - "loss": 0.2542, + "epoch": 0.1, + "learning_rate": 4.4930538466700975e-05, + "loss": 0.2647, "step": 46340 }, { - "epoch": 0.41, - "learning_rate": 2.958201963787046e-05, - "loss": 0.2537, + "epoch": 0.1, + "learning_rate": 4.4929419923491646e-05, + "loss": 0.2636, "step": 46350 }, { - "epoch": 0.41, - "learning_rate": 2.9577515539140622e-05, - "loss": 0.2513, + "epoch": 0.1, + "learning_rate": 4.4928301380282324e-05, + "loss": 0.2709, "step": 46360 }, { - "epoch": 0.41, - "learning_rate": 2.9573011440410776e-05, - "loss": 0.2478, + "epoch": 0.1, + "learning_rate": 4.4927182837073e-05, + "loss": 0.2694, "step": 46370 }, { - "epoch": 0.41, - "learning_rate": 2.956850734168093e-05, - "loss": 0.25, + "epoch": 0.1, + "learning_rate": 4.492606429386367e-05, + "loss": 0.2662, "step": 46380 }, { - "epoch": 0.41, - "learning_rate": 2.9564003242951087e-05, - "loss": 0.2489, + "epoch": 0.1, + "learning_rate": 4.492494575065435e-05, + "loss": 0.2615, "step": 46390 }, { - "epoch": 0.41, - "learning_rate": 2.955949914422124e-05, - "loss": 0.2513, + "epoch": 0.1, + "learning_rate": 4.492382720744502e-05, + "loss": 0.2661, "step": 46400 }, { - "epoch": 0.41, - "learning_rate": 2.9554995045491396e-05, - "loss": 0.2559, + "epoch": 0.1, + "learning_rate": 4.49227086642357e-05, + "loss": 0.2671, "step": 46410 }, { - "epoch": 0.41, - "learning_rate": 2.9550490946761557e-05, - "loss": 0.262, + "epoch": 0.1, + "learning_rate": 4.492159012102638e-05, + "loss": 0.2691, "step": 46420 }, { - "epoch": 0.41, - "learning_rate": 2.954598684803171e-05, - "loss": 0.2477, + "epoch": 0.1, + "learning_rate": 4.4920471577817056e-05, + "loss": 0.2655, "step": 46430 }, { - "epoch": 0.41, - "learning_rate": 2.9541482749301868e-05, - "loss": 0.2522, + "epoch": 0.1, + "learning_rate": 4.4919353034607734e-05, + "loss": 0.2598, "step": 46440 }, { - "epoch": 0.41, - "learning_rate": 2.9536978650572022e-05, - "loss": 0.2456, + "epoch": 0.1, + "learning_rate": 4.4918234491398405e-05, + "loss": 0.2698, "step": 46450 }, { - "epoch": 0.41, - "learning_rate": 2.9532474551842176e-05, - "loss": 0.2481, + "epoch": 0.1, + "learning_rate": 4.491711594818908e-05, + "loss": 0.2661, "step": 46460 }, { - "epoch": 0.41, - "learning_rate": 2.9527970453112337e-05, - "loss": 0.2543, + "epoch": 0.1, + "learning_rate": 4.4915997404979754e-05, + "loss": 0.2602, "step": 46470 }, { - "epoch": 0.41, - "learning_rate": 2.952346635438249e-05, - "loss": 0.2541, + "epoch": 0.1, + "learning_rate": 4.491487886177043e-05, + "loss": 0.2602, "step": 46480 }, { - "epoch": 0.42, - "learning_rate": 2.9518962255652642e-05, - "loss": 0.2558, + "epoch": 0.1, + "learning_rate": 4.491376031856111e-05, + "loss": 0.2625, "step": 46490 }, { - "epoch": 0.42, - "learning_rate": 2.9514458156922803e-05, - "loss": 0.2555, + "epoch": 0.1, + "learning_rate": 4.491264177535178e-05, + "loss": 0.265, "step": 46500 }, { - "epoch": 0.42, - "learning_rate": 2.9509954058192957e-05, - "loss": 0.253, + "epoch": 0.1, + "learning_rate": 4.491152323214246e-05, + "loss": 0.2649, "step": 46510 }, { - "epoch": 0.42, - "learning_rate": 2.950544995946311e-05, - "loss": 0.2526, + "epoch": 0.1, + "learning_rate": 4.491040468893313e-05, + "loss": 0.2678, "step": 46520 }, { - "epoch": 0.42, - "learning_rate": 2.950094586073327e-05, - "loss": 0.252, + "epoch": 0.1, + "learning_rate": 4.490928614572381e-05, + "loss": 0.2666, "step": 46530 }, { - "epoch": 0.42, - "learning_rate": 2.9496441762003423e-05, - "loss": 0.2506, + "epoch": 0.1, + "learning_rate": 4.490816760251449e-05, + "loss": 0.2711, "step": 46540 }, { - "epoch": 0.42, - "learning_rate": 2.9491937663273577e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.4907049059305164e-05, + "loss": 0.263, "step": 46550 }, { - "epoch": 0.42, - "learning_rate": 2.9487433564543738e-05, - "loss": 0.2519, + "epoch": 0.1, + "learning_rate": 4.490593051609584e-05, + "loss": 0.2628, "step": 46560 }, { - "epoch": 0.42, - "learning_rate": 2.9482929465813892e-05, - "loss": 0.2493, + "epoch": 0.1, + "learning_rate": 4.490481197288651e-05, + "loss": 0.272, "step": 46570 }, { - "epoch": 0.42, - "learning_rate": 2.947842536708405e-05, - "loss": 0.2468, + "epoch": 0.1, + "learning_rate": 4.490369342967719e-05, + "loss": 0.2701, "step": 46580 }, { - "epoch": 0.42, - "learning_rate": 2.9473921268354203e-05, - "loss": 0.2475, + "epoch": 0.1, + "learning_rate": 4.490257488646787e-05, + "loss": 0.2718, "step": 46590 }, { - "epoch": 0.42, - "learning_rate": 2.9469417169624358e-05, - "loss": 0.2454, + "epoch": 0.1, + "learning_rate": 4.490145634325854e-05, + "loss": 0.2611, "step": 46600 }, { - "epoch": 0.42, - "learning_rate": 2.946491307089452e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.490033780004922e-05, + "loss": 0.2637, "step": 46610 }, { - "epoch": 0.42, - "learning_rate": 2.9460408972164672e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.489921925683989e-05, + "loss": 0.2685, "step": 46620 }, { - "epoch": 0.42, - "learning_rate": 2.9455904873434827e-05, - "loss": 0.2481, + "epoch": 0.1, + "learning_rate": 4.489810071363057e-05, + "loss": 0.2665, "step": 46630 }, { - "epoch": 0.42, - "learning_rate": 2.9451400774704984e-05, - "loss": 0.2544, + "epoch": 0.1, + "learning_rate": 4.4896982170421245e-05, + "loss": 0.2686, "step": 46640 }, { - "epoch": 0.42, - "learning_rate": 2.9446896675975138e-05, - "loss": 0.2512, + "epoch": 0.1, + "learning_rate": 4.489586362721192e-05, + "loss": 0.2686, "step": 46650 }, { - "epoch": 0.42, - "learning_rate": 2.9442392577245292e-05, - "loss": 0.2525, + "epoch": 0.1, + "learning_rate": 4.48947450840026e-05, + "loss": 0.263, "step": 46660 }, { - "epoch": 0.42, - "learning_rate": 2.9437888478515453e-05, - "loss": 0.2492, + "epoch": 0.1, + "learning_rate": 4.489362654079327e-05, + "loss": 0.2652, "step": 46670 }, { - "epoch": 0.42, - "learning_rate": 2.9433384379785607e-05, - "loss": 0.2539, + "epoch": 0.1, + "learning_rate": 4.489250799758395e-05, + "loss": 0.265, "step": 46680 }, { - "epoch": 0.42, - "learning_rate": 2.9428880281055758e-05, - "loss": 0.2563, + "epoch": 0.1, + "learning_rate": 4.489138945437463e-05, + "loss": 0.2647, "step": 46690 }, { - "epoch": 0.42, - "learning_rate": 2.942437618232592e-05, - "loss": 0.2514, + "epoch": 0.1, + "learning_rate": 4.48902709111653e-05, + "loss": 0.2711, "step": 46700 }, { - "epoch": 0.42, - "learning_rate": 2.9419872083596073e-05, - "loss": 0.2513, + "epoch": 0.1, + "learning_rate": 4.488915236795598e-05, + "loss": 0.2682, "step": 46710 }, { - "epoch": 0.42, - "learning_rate": 2.9415367984866234e-05, - "loss": 0.2572, + "epoch": 0.1, + "learning_rate": 4.488803382474665e-05, + "loss": 0.2708, "step": 46720 }, { - "epoch": 0.42, - "learning_rate": 2.9410863886136385e-05, - "loss": 0.2525, + "epoch": 0.1, + "learning_rate": 4.4886915281537326e-05, + "loss": 0.2634, "step": 46730 }, { - "epoch": 0.42, - "learning_rate": 2.940635978740654e-05, - "loss": 0.2583, + "epoch": 0.1, + "learning_rate": 4.4885796738328004e-05, + "loss": 0.2625, "step": 46740 }, { - "epoch": 0.42, - "learning_rate": 2.94018556886767e-05, - "loss": 0.2579, + "epoch": 0.1, + "learning_rate": 4.488467819511868e-05, + "loss": 0.273, "step": 46750 }, { - "epoch": 0.42, - "learning_rate": 2.9397351589946854e-05, - "loss": 0.2487, + "epoch": 0.1, + "learning_rate": 4.488355965190936e-05, + "loss": 0.2635, "step": 46760 }, { - "epoch": 0.42, - "learning_rate": 2.9392847491217008e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.488244110870003e-05, + "loss": 0.2668, "step": 46770 }, { - "epoch": 0.42, - "learning_rate": 2.9388343392487165e-05, - "loss": 0.2504, + "epoch": 0.1, + "learning_rate": 4.488132256549071e-05, + "loss": 0.2649, "step": 46780 }, { - "epoch": 0.42, - "learning_rate": 2.938383929375732e-05, - "loss": 0.2533, + "epoch": 0.1, + "learning_rate": 4.488020402228138e-05, + "loss": 0.2617, "step": 46790 }, { - "epoch": 0.42, - "learning_rate": 2.9379335195027473e-05, - "loss": 0.2529, + "epoch": 0.1, + "learning_rate": 4.487908547907206e-05, + "loss": 0.261, "step": 46800 }, { - "epoch": 0.42, - "learning_rate": 2.9374831096297634e-05, - "loss": 0.2496, + "epoch": 0.1, + "learning_rate": 4.4877966935862736e-05, + "loss": 0.2657, "step": 46810 }, { - "epoch": 0.42, - "learning_rate": 2.937032699756779e-05, - "loss": 0.2509, + "epoch": 0.1, + "learning_rate": 4.487684839265341e-05, + "loss": 0.2695, "step": 46820 }, { - "epoch": 0.42, - "learning_rate": 2.9365822898837943e-05, - "loss": 0.2536, + "epoch": 0.1, + "learning_rate": 4.4875729849444085e-05, + "loss": 0.262, "step": 46830 }, { - "epoch": 0.42, - "learning_rate": 2.93613188001081e-05, - "loss": 0.251, + "epoch": 0.1, + "learning_rate": 4.487461130623476e-05, + "loss": 0.2649, "step": 46840 }, { - "epoch": 0.42, - "learning_rate": 2.9356814701378254e-05, - "loss": 0.2547, + "epoch": 0.1, + "learning_rate": 4.487349276302544e-05, + "loss": 0.2648, "step": 46850 }, { - "epoch": 0.42, - "learning_rate": 2.9352310602648415e-05, - "loss": 0.2521, + "epoch": 0.1, + "learning_rate": 4.487237421981612e-05, + "loss": 0.2737, "step": 46860 }, { - "epoch": 0.42, - "learning_rate": 2.934780650391857e-05, - "loss": 0.2502, + "epoch": 0.1, + "learning_rate": 4.487125567660679e-05, + "loss": 0.2594, "step": 46870 }, { - "epoch": 0.42, - "learning_rate": 2.9343302405188723e-05, - "loss": 0.257, + "epoch": 0.1, + "learning_rate": 4.487013713339747e-05, + "loss": 0.2707, "step": 46880 }, { - "epoch": 0.42, - "learning_rate": 2.933879830645888e-05, - "loss": 0.2548, + "epoch": 0.1, + "learning_rate": 4.486901859018814e-05, + "loss": 0.2632, "step": 46890 }, { - "epoch": 0.42, - "learning_rate": 2.9334294207729035e-05, - "loss": 0.2563, + "epoch": 0.1, + "learning_rate": 4.486790004697882e-05, + "loss": 0.2691, "step": 46900 }, { - "epoch": 0.42, - "learning_rate": 2.932979010899919e-05, - "loss": 0.2508, + "epoch": 0.1, + "learning_rate": 4.4866781503769495e-05, + "loss": 0.2743, "step": 46910 }, { - "epoch": 0.42, - "learning_rate": 2.932528601026935e-05, - "loss": 0.254, + "epoch": 0.1, + "learning_rate": 4.4865662960560166e-05, + "loss": 0.2661, "step": 46920 }, { - "epoch": 0.42, - "learning_rate": 2.93207819115395e-05, - "loss": 0.2491, + "epoch": 0.1, + "learning_rate": 4.4864544417350844e-05, + "loss": 0.261, "step": 46930 }, { - "epoch": 0.42, - "learning_rate": 2.9316277812809655e-05, - "loss": 0.2503, + "epoch": 0.1, + "learning_rate": 4.4863425874141515e-05, + "loss": 0.2697, "step": 46940 }, { - "epoch": 0.42, - "learning_rate": 2.9311773714079816e-05, - "loss": 0.2557, + "epoch": 0.1, + "learning_rate": 4.486230733093219e-05, + "loss": 0.2671, "step": 46950 }, { - "epoch": 0.42, - "learning_rate": 2.930726961534997e-05, - "loss": 0.2509, + "epoch": 0.1, + "learning_rate": 4.486118878772288e-05, + "loss": 0.2662, "step": 46960 }, { - "epoch": 0.42, - "learning_rate": 2.9302765516620124e-05, - "loss": 0.2493, + "epoch": 0.1, + "learning_rate": 4.486007024451355e-05, + "loss": 0.2695, "step": 46970 }, { - "epoch": 0.42, - "learning_rate": 2.929826141789028e-05, - "loss": 0.2531, + "epoch": 0.1, + "learning_rate": 4.4858951701304227e-05, + "loss": 0.2689, "step": 46980 }, { - "epoch": 0.42, - "learning_rate": 2.9293757319160435e-05, - "loss": 0.2554, + "epoch": 0.1, + "learning_rate": 4.48578331580949e-05, + "loss": 0.2727, "step": 46990 }, { - "epoch": 0.42, - "learning_rate": 2.9289253220430596e-05, - "loss": 0.2488, + "epoch": 0.1, + "learning_rate": 4.4856714614885576e-05, + "loss": 0.2638, "step": 47000 }, { - "epoch": 0.42, - "learning_rate": 2.928474912170075e-05, - "loss": 0.2502, + "epoch": 0.1, + "learning_rate": 4.4855596071676254e-05, + "loss": 0.2673, "step": 47010 }, { - "epoch": 0.42, - "learning_rate": 2.9280245022970904e-05, - "loss": 0.2508, + "epoch": 0.1, + "learning_rate": 4.4854477528466925e-05, + "loss": 0.2651, "step": 47020 }, { - "epoch": 0.42, - "learning_rate": 2.9275740924241062e-05, - "loss": 0.2499, + "epoch": 0.1, + "learning_rate": 4.48533589852576e-05, + "loss": 0.2658, "step": 47030 }, { - "epoch": 0.42, - "learning_rate": 2.9271236825511216e-05, - "loss": 0.2501, + "epoch": 0.1, + "learning_rate": 4.4852240442048274e-05, + "loss": 0.2674, "step": 47040 }, { - "epoch": 0.42, - "learning_rate": 2.926673272678137e-05, - "loss": 0.2553, + "epoch": 0.11, + "learning_rate": 4.485112189883895e-05, + "loss": 0.2571, "step": 47050 }, { - "epoch": 0.42, - "learning_rate": 2.926222862805153e-05, - "loss": 0.2494, + "epoch": 0.11, + "learning_rate": 4.485000335562963e-05, + "loss": 0.26, "step": 47060 }, { - "epoch": 0.42, - "learning_rate": 2.9257724529321685e-05, - "loss": 0.2568, + "epoch": 0.11, + "learning_rate": 4.484888481242031e-05, + "loss": 0.2633, "step": 47070 }, { - "epoch": 0.42, - "learning_rate": 2.925322043059184e-05, - "loss": 0.2468, + "epoch": 0.11, + "learning_rate": 4.4847766269210986e-05, + "loss": 0.2655, "step": 47080 }, { - "epoch": 0.42, - "learning_rate": 2.9248716331861997e-05, - "loss": 0.2499, + "epoch": 0.11, + "learning_rate": 4.484664772600166e-05, + "loss": 0.2689, "step": 47090 }, { - "epoch": 0.42, - "learning_rate": 2.924421223313215e-05, - "loss": 0.2491, + "epoch": 0.11, + "learning_rate": 4.4845529182792335e-05, + "loss": 0.2634, "step": 47100 }, { - "epoch": 0.42, - "learning_rate": 2.9239708134402305e-05, - "loss": 0.2491, + "epoch": 0.11, + "learning_rate": 4.4844410639583006e-05, + "loss": 0.2707, "step": 47110 }, { - "epoch": 0.42, - "learning_rate": 2.9235204035672466e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.4843292096373684e-05, + "loss": 0.2724, "step": 47120 }, { - "epoch": 0.42, - "learning_rate": 2.923069993694262e-05, - "loss": 0.2478, + "epoch": 0.11, + "learning_rate": 4.484217355316436e-05, + "loss": 0.2668, "step": 47130 }, { - "epoch": 0.42, - "learning_rate": 2.9226195838212777e-05, - "loss": 0.2502, + "epoch": 0.11, + "learning_rate": 4.484105500995503e-05, + "loss": 0.272, "step": 47140 }, { - "epoch": 0.42, - "learning_rate": 2.922169173948293e-05, - "loss": 0.2556, + "epoch": 0.11, + "learning_rate": 4.483993646674571e-05, + "loss": 0.2671, "step": 47150 }, { - "epoch": 0.42, - "learning_rate": 2.9217187640753086e-05, - "loss": 0.2476, + "epoch": 0.11, + "learning_rate": 4.483881792353639e-05, + "loss": 0.2698, "step": 47160 }, { - "epoch": 0.42, - "learning_rate": 2.9212683542023243e-05, - "loss": 0.2501, + "epoch": 0.11, + "learning_rate": 4.4837699380327067e-05, + "loss": 0.2659, "step": 47170 }, { - "epoch": 0.42, - "learning_rate": 2.9208179443293397e-05, - "loss": 0.2494, + "epoch": 0.11, + "learning_rate": 4.4836580837117744e-05, + "loss": 0.2593, "step": 47180 }, { - "epoch": 0.42, - "learning_rate": 2.920367534456355e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.4835462293908416e-05, + "loss": 0.2703, "step": 47190 }, { - "epoch": 0.42, - "learning_rate": 2.9199171245833712e-05, - "loss": 0.2525, + "epoch": 0.11, + "learning_rate": 4.4834343750699094e-05, + "loss": 0.267, "step": 47200 }, { - "epoch": 0.42, - "learning_rate": 2.9194667147103866e-05, - "loss": 0.2488, + "epoch": 0.11, + "learning_rate": 4.4833225207489765e-05, + "loss": 0.2617, "step": 47210 }, { - "epoch": 0.42, - "learning_rate": 2.919016304837402e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.483210666428044e-05, + "loss": 0.2637, "step": 47220 }, { - "epoch": 0.42, - "learning_rate": 2.9185658949644178e-05, - "loss": 0.2565, + "epoch": 0.11, + "learning_rate": 4.483109997539205e-05, + "loss": 0.2675, "step": 47230 }, { - "epoch": 0.42, - "learning_rate": 2.9181154850914332e-05, - "loss": 0.2542, + "epoch": 0.11, + "learning_rate": 4.482998143218273e-05, + "loss": 0.2642, "step": 47240 }, { - "epoch": 0.42, - "learning_rate": 2.9176650752184486e-05, - "loss": 0.2491, + "epoch": 0.11, + "learning_rate": 4.482886288897341e-05, + "loss": 0.2617, "step": 47250 }, { - "epoch": 0.42, - "learning_rate": 2.9172146653454647e-05, - "loss": 0.2515, + "epoch": 0.11, + "learning_rate": 4.482774434576408e-05, + "loss": 0.2657, "step": 47260 }, { - "epoch": 0.42, - "learning_rate": 2.91676425547248e-05, - "loss": 0.2523, + "epoch": 0.11, + "learning_rate": 4.4826625802554756e-05, + "loss": 0.2652, "step": 47270 }, { - "epoch": 0.42, - "learning_rate": 2.916313845599496e-05, - "loss": 0.2527, + "epoch": 0.11, + "learning_rate": 4.482550725934543e-05, + "loss": 0.2632, "step": 47280 }, { - "epoch": 0.42, - "learning_rate": 2.9158634357265113e-05, - "loss": 0.252, + "epoch": 0.11, + "learning_rate": 4.4824388716136105e-05, + "loss": 0.2606, "step": 47290 }, { - "epoch": 0.42, - "learning_rate": 2.9154130258535267e-05, - "loss": 0.252, + "epoch": 0.11, + "learning_rate": 4.482327017292678e-05, + "loss": 0.2621, "step": 47300 }, { - "epoch": 0.42, - "learning_rate": 2.9149626159805428e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.4822151629717455e-05, + "loss": 0.268, "step": 47310 }, { - "epoch": 0.42, - "learning_rate": 2.9145122061075582e-05, - "loss": 0.2607, + "epoch": 0.11, + "learning_rate": 4.482103308650813e-05, + "loss": 0.2649, "step": 47320 }, { - "epoch": 0.42, - "learning_rate": 2.9140617962345736e-05, - "loss": 0.2541, + "epoch": 0.11, + "learning_rate": 4.481991454329881e-05, + "loss": 0.2667, "step": 47330 }, { - "epoch": 0.42, - "learning_rate": 2.9136113863615893e-05, - "loss": 0.2559, + "epoch": 0.11, + "learning_rate": 4.481879600008949e-05, + "loss": 0.2622, "step": 47340 }, { - "epoch": 0.42, - "learning_rate": 2.9131609764886047e-05, - "loss": 0.2553, + "epoch": 0.11, + "learning_rate": 4.4817677456880166e-05, + "loss": 0.2684, "step": 47350 }, { - "epoch": 0.42, - "learning_rate": 2.91271056661562e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.481655891367084e-05, + "loss": 0.2642, "step": 47360 }, { - "epoch": 0.42, - "learning_rate": 2.9122601567426362e-05, - "loss": 0.2515, + "epoch": 0.11, + "learning_rate": 4.4815440370461515e-05, + "loss": 0.2653, "step": 47370 }, { - "epoch": 0.42, - "learning_rate": 2.9118097468696513e-05, - "loss": 0.2613, + "epoch": 0.11, + "learning_rate": 4.4814321827252186e-05, + "loss": 0.2615, "step": 47380 }, { - "epoch": 0.42, - "learning_rate": 2.9113593369966667e-05, - "loss": 0.2461, + "epoch": 0.11, + "learning_rate": 4.4813203284042864e-05, + "loss": 0.2624, "step": 47390 }, { - "epoch": 0.42, - "learning_rate": 2.9109089271236828e-05, - "loss": 0.2546, + "epoch": 0.11, + "learning_rate": 4.481208474083354e-05, + "loss": 0.2649, "step": 47400 }, { - "epoch": 0.42, - "learning_rate": 2.9104585172506982e-05, - "loss": 0.2547, + "epoch": 0.11, + "learning_rate": 4.4810966197624213e-05, + "loss": 0.2614, "step": 47410 }, { - "epoch": 0.42, - "learning_rate": 2.910008107377714e-05, - "loss": 0.2506, + "epoch": 0.11, + "learning_rate": 4.480984765441489e-05, + "loss": 0.2662, "step": 47420 }, { - "epoch": 0.42, - "learning_rate": 2.9095576975047294e-05, - "loss": 0.2543, + "epoch": 0.11, + "learning_rate": 4.480872911120557e-05, + "loss": 0.2603, "step": 47430 }, { - "epoch": 0.42, - "learning_rate": 2.9091072876317448e-05, - "loss": 0.2525, + "epoch": 0.11, + "learning_rate": 4.480761056799625e-05, + "loss": 0.2613, "step": 47440 }, { - "epoch": 0.42, - "learning_rate": 2.908656877758761e-05, - "loss": 0.254, + "epoch": 0.11, + "learning_rate": 4.4806492024786925e-05, + "loss": 0.2627, "step": 47450 }, { - "epoch": 0.42, - "learning_rate": 2.9082064678857763e-05, - "loss": 0.2473, + "epoch": 0.11, + "learning_rate": 4.4805373481577596e-05, + "loss": 0.2597, "step": 47460 }, { - "epoch": 0.42, - "learning_rate": 2.9077560580127917e-05, - "loss": 0.2532, + "epoch": 0.11, + "learning_rate": 4.4804254938368274e-05, + "loss": 0.2608, "step": 47470 }, { - "epoch": 0.42, - "learning_rate": 2.9073056481398075e-05, - "loss": 0.2443, + "epoch": 0.11, + "learning_rate": 4.4803136395158945e-05, + "loss": 0.262, "step": 47480 }, { - "epoch": 0.42, - "learning_rate": 2.906855238266823e-05, - "loss": 0.256, + "epoch": 0.11, + "learning_rate": 4.480201785194962e-05, + "loss": 0.2642, "step": 47490 }, { - "epoch": 0.42, - "learning_rate": 2.9064048283938383e-05, - "loss": 0.2521, + "epoch": 0.11, + "learning_rate": 4.4800899308740294e-05, + "loss": 0.2674, "step": 47500 }, { - "epoch": 0.42, - "learning_rate": 2.9059544185208544e-05, - "loss": 0.2485, + "epoch": 0.11, + "learning_rate": 4.479978076553097e-05, + "loss": 0.2664, "step": 47510 }, { - "epoch": 0.42, - "learning_rate": 2.9055040086478698e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.479866222232165e-05, + "loss": 0.2704, "step": 47520 }, { - "epoch": 0.42, - "learning_rate": 2.9050535987748852e-05, - "loss": 0.2547, + "epoch": 0.11, + "learning_rate": 4.479754367911232e-05, + "loss": 0.2631, "step": 47530 }, { - "epoch": 0.42, - "learning_rate": 2.904603188901901e-05, - "loss": 0.2477, + "epoch": 0.11, + "learning_rate": 4.4796425135903006e-05, + "loss": 0.2628, "step": 47540 }, { - "epoch": 0.42, - "learning_rate": 2.9041527790289163e-05, - "loss": 0.2506, + "epoch": 0.11, + "learning_rate": 4.479530659269368e-05, + "loss": 0.2664, "step": 47550 }, { - "epoch": 0.42, - "learning_rate": 2.9037023691559324e-05, - "loss": 0.2541, + "epoch": 0.11, + "learning_rate": 4.4794188049484355e-05, + "loss": 0.2615, "step": 47560 }, { - "epoch": 0.42, - "learning_rate": 2.903251959282948e-05, - "loss": 0.2458, + "epoch": 0.11, + "learning_rate": 4.479306950627503e-05, + "loss": 0.2624, "step": 47570 }, { - "epoch": 0.42, - "learning_rate": 2.902801549409963e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.4791950963065704e-05, + "loss": 0.2636, "step": 47580 }, { - "epoch": 0.42, - "learning_rate": 2.902351139536979e-05, - "loss": 0.25, + "epoch": 0.11, + "learning_rate": 4.479083241985638e-05, + "loss": 0.2605, "step": 47590 }, { - "epoch": 0.42, - "learning_rate": 2.9019007296639944e-05, - "loss": 0.2552, + "epoch": 0.11, + "learning_rate": 4.4789713876647053e-05, + "loss": 0.2677, "step": 47600 }, { - "epoch": 0.43, - "learning_rate": 2.9014503197910098e-05, - "loss": 0.256, + "epoch": 0.11, + "learning_rate": 4.478859533343773e-05, + "loss": 0.2672, "step": 47610 }, { - "epoch": 0.43, - "learning_rate": 2.9009999099180256e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.478747679022841e-05, + "loss": 0.2673, "step": 47620 }, { - "epoch": 0.43, - "learning_rate": 2.9005945410323393e-05, - "loss": 0.2575, + "epoch": 0.11, + "learning_rate": 4.478635824701908e-05, + "loss": 0.2643, "step": 47630 }, { - "epoch": 0.43, - "learning_rate": 2.9001441311593554e-05, - "loss": 0.2449, + "epoch": 0.11, + "learning_rate": 4.478523970380976e-05, + "loss": 0.2644, "step": 47640 }, { - "epoch": 0.43, - "learning_rate": 2.8996937212863708e-05, - "loss": 0.2518, + "epoch": 0.11, + "learning_rate": 4.4784121160600436e-05, + "loss": 0.2673, "step": 47650 }, { - "epoch": 0.43, - "learning_rate": 2.8992433114133865e-05, - "loss": 0.2512, + "epoch": 0.11, + "learning_rate": 4.4783002617391114e-05, + "loss": 0.2655, "step": 47660 }, { - "epoch": 0.43, - "learning_rate": 2.898792901540402e-05, - "loss": 0.2491, + "epoch": 0.11, + "learning_rate": 4.478188407418179e-05, + "loss": 0.2691, "step": 47670 }, { - "epoch": 0.43, - "learning_rate": 2.8983424916674173e-05, - "loss": 0.249, + "epoch": 0.11, + "learning_rate": 4.478076553097246e-05, + "loss": 0.264, "step": 47680 }, { - "epoch": 0.43, - "learning_rate": 2.8978920817944334e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.477964698776314e-05, + "loss": 0.2668, "step": 47690 }, { - "epoch": 0.43, - "learning_rate": 2.8974416719214485e-05, - "loss": 0.2513, + "epoch": 0.11, + "learning_rate": 4.477852844455381e-05, + "loss": 0.266, "step": 47700 }, { - "epoch": 0.43, - "learning_rate": 2.896991262048464e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.477740990134449e-05, + "loss": 0.2694, "step": 47710 }, { - "epoch": 0.43, - "learning_rate": 2.89654085217548e-05, - "loss": 0.2468, + "epoch": 0.11, + "learning_rate": 4.477629135813517e-05, + "loss": 0.2645, "step": 47720 }, { - "epoch": 0.43, - "learning_rate": 2.8960904423024954e-05, - "loss": 0.2453, + "epoch": 0.11, + "learning_rate": 4.477517281492584e-05, + "loss": 0.2671, "step": 47730 }, { - "epoch": 0.43, - "learning_rate": 2.8956400324295108e-05, - "loss": 0.2478, + "epoch": 0.11, + "learning_rate": 4.477405427171652e-05, + "loss": 0.2669, "step": 47740 }, { - "epoch": 0.43, - "learning_rate": 2.8951896225565266e-05, - "loss": 0.2472, + "epoch": 0.11, + "learning_rate": 4.4772935728507195e-05, + "loss": 0.265, "step": 47750 }, { - "epoch": 0.43, - "learning_rate": 2.894739212683542e-05, - "loss": 0.2451, + "epoch": 0.11, + "learning_rate": 4.477181718529787e-05, + "loss": 0.2594, "step": 47760 }, { - "epoch": 0.43, - "learning_rate": 2.8942888028105574e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.4770698642088544e-05, + "loss": 0.2607, "step": 47770 }, { - "epoch": 0.43, - "learning_rate": 2.8938383929375735e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.476958009887922e-05, + "loss": 0.2591, "step": 47780 }, { - "epoch": 0.43, - "learning_rate": 2.893387983064589e-05, - "loss": 0.25, + "epoch": 0.11, + "learning_rate": 4.47684615556699e-05, + "loss": 0.2621, "step": 47790 }, { - "epoch": 0.43, - "learning_rate": 2.8929375731916046e-05, - "loss": 0.2523, + "epoch": 0.11, + "learning_rate": 4.476734301246057e-05, + "loss": 0.2609, "step": 47800 }, { - "epoch": 0.43, - "learning_rate": 2.89248716331862e-05, - "loss": 0.2506, + "epoch": 0.11, + "learning_rate": 4.476622446925125e-05, + "loss": 0.2622, "step": 47810 }, { - "epoch": 0.43, - "learning_rate": 2.8920367534456355e-05, - "loss": 0.2461, + "epoch": 0.11, + "learning_rate": 4.476510592604192e-05, + "loss": 0.2649, "step": 47820 }, { - "epoch": 0.43, - "learning_rate": 2.8915863435726515e-05, - "loss": 0.2528, + "epoch": 0.11, + "learning_rate": 4.47639873828326e-05, + "loss": 0.267, "step": 47830 }, { - "epoch": 0.43, - "learning_rate": 2.891135933699667e-05, - "loss": 0.2516, + "epoch": 0.11, + "learning_rate": 4.4762868839623276e-05, + "loss": 0.2628, "step": 47840 }, { - "epoch": 0.43, - "learning_rate": 2.8906855238266824e-05, - "loss": 0.2473, + "epoch": 0.11, + "learning_rate": 4.4761750296413954e-05, + "loss": 0.2646, "step": 47850 }, { - "epoch": 0.43, - "learning_rate": 2.890235113953698e-05, - "loss": 0.2515, + "epoch": 0.11, + "learning_rate": 4.476063175320463e-05, + "loss": 0.261, "step": 47860 }, { - "epoch": 0.43, - "learning_rate": 2.8897847040807135e-05, - "loss": 0.2518, + "epoch": 0.11, + "learning_rate": 4.47595132099953e-05, + "loss": 0.2692, "step": 47870 }, { - "epoch": 0.43, - "learning_rate": 2.889334294207729e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.475839466678598e-05, + "loss": 0.2597, "step": 47880 }, { - "epoch": 0.43, - "learning_rate": 2.888883884334745e-05, - "loss": 0.2447, + "epoch": 0.11, + "learning_rate": 4.475727612357666e-05, + "loss": 0.2636, "step": 47890 }, { - "epoch": 0.43, - "learning_rate": 2.8884334744617604e-05, - "loss": 0.2456, + "epoch": 0.11, + "learning_rate": 4.475615758036733e-05, + "loss": 0.2628, "step": 47900 }, { - "epoch": 0.43, - "learning_rate": 2.8879830645887755e-05, - "loss": 0.2544, + "epoch": 0.11, + "learning_rate": 4.475503903715801e-05, + "loss": 0.2709, "step": 47910 }, { - "epoch": 0.43, - "learning_rate": 2.8875326547157916e-05, - "loss": 0.2526, + "epoch": 0.11, + "learning_rate": 4.475392049394868e-05, + "loss": 0.2638, "step": 47920 }, { - "epoch": 0.43, - "learning_rate": 2.887082244842807e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.475280195073936e-05, + "loss": 0.2626, "step": 47930 }, { - "epoch": 0.43, - "learning_rate": 2.886631834969823e-05, - "loss": 0.2486, + "epoch": 0.11, + "learning_rate": 4.4751683407530035e-05, + "loss": 0.2607, "step": 47940 }, { - "epoch": 0.43, - "learning_rate": 2.886181425096838e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.475056486432071e-05, + "loss": 0.2633, "step": 47950 }, { - "epoch": 0.43, - "learning_rate": 2.8857310152238536e-05, - "loss": 0.2448, + "epoch": 0.11, + "learning_rate": 4.474944632111139e-05, + "loss": 0.2604, "step": 47960 }, { - "epoch": 0.43, - "learning_rate": 2.8852806053508697e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.474832777790206e-05, + "loss": 0.2599, "step": 47970 }, { - "epoch": 0.43, - "learning_rate": 2.884830195477885e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.474720923469274e-05, + "loss": 0.2587, "step": 47980 }, { - "epoch": 0.43, - "learning_rate": 2.8843797856049005e-05, - "loss": 0.2458, + "epoch": 0.11, + "learning_rate": 4.474609069148342e-05, + "loss": 0.2558, "step": 47990 }, { - "epoch": 0.43, - "learning_rate": 2.8839293757319162e-05, - "loss": 0.2575, + "epoch": 0.11, + "learning_rate": 4.474497214827409e-05, + "loss": 0.2622, "step": 48000 }, { - "epoch": 0.43, - "eval_NEIMS_canon_smiles": 0.9293, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.024266666666666666, - "eval_NEIMS_daylight_tanimoto_simil": 0.40677611496886035, - "eval_NEIMS_exact_mols": 0.024116666666666668, - "eval_NEIMS_exact_smiles": 0.0234, - "eval_NEIMS_loss": 0.26602691411972046, - "eval_NEIMS_matched_formulas": 0.46668333333333334, - "eval_NEIMS_morgan_tanimoto_simil": 0.3061910596751587, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.024233333333333332, - "eval_NEIMS_runtime": 713.3854, - "eval_NEIMS_samples_per_second": 84.106, - "eval_NEIMS_steps_per_second": 1.315, + "epoch": 0.11, + "eval_NEIMS_canon_smiles": 0.9321333333333334, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.022166666666666668, + "eval_NEIMS_daylight_tanimoto_simil": 0.40743877433844605, + "eval_NEIMS_exact_mols": 0.022066666666666665, + "eval_NEIMS_exact_smiles": 0.021366666666666666, + "eval_NEIMS_loss": 0.2725822329521179, + "eval_NEIMS_matched_formulas": 0.45388333333333336, + "eval_NEIMS_morgan_tanimoto_simil": 0.3068103681966335, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.022233333333333334, + "eval_NEIMS_runtime": 732.0849, + "eval_NEIMS_samples_per_second": 81.958, + "eval_NEIMS_steps_per_second": 1.281, "step": 48000 }, { - "epoch": 0.43, - "eval_RASSP_canon_smiles": 0.9167362340134237, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.05900424082545831, - "eval_RASSP_daylight_tanimoto_simil": 0.5040080086306112, - "eval_RASSP_exact_mols": 0.05872040605068955, - "eval_RASSP_exact_smiles": 0.05633285470998765, - "eval_RASSP_loss": 0.20886576175689697, - "eval_RASSP_matched_formulas": 0.6356062376865796, - "eval_RASSP_morgan_tanimoto_simil": 0.36702623477912233, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.058870671519684774, - "eval_RASSP_runtime": 820.2508, - "eval_RASSP_samples_per_second": 73.019, - "eval_RASSP_steps_per_second": 1.141, + "epoch": 0.11, + "eval_RASSP_canon_smiles": 0.9303269108758807, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.030921294286572944, + "eval_RASSP_daylight_tanimoto_simil": 0.46107775038736043, + "eval_RASSP_exact_mols": 0.03075433265435603, + "eval_RASSP_exact_smiles": 0.02958560122883761, + "eval_RASSP_loss": 0.24379447102546692, + "eval_RASSP_matched_formulas": 0.5839483086786657, + "eval_RASSP_morgan_tanimoto_simil": 0.3230082185341353, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.03085450963368618, + "eval_RASSP_runtime": 837.4377, + "eval_RASSP_samples_per_second": 71.521, + "eval_RASSP_steps_per_second": 1.118, "step": 48000 }, { - "epoch": 0.43, - "eval_NIST_canon_smiles": 0.8894133513149022, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.00816268587855343, - "eval_NIST_daylight_tanimoto_simil": 0.25274513159009915, - "eval_NIST_exact_mols": 0.007772296553926961, - "eval_NIST_exact_smiles": 0.007097987720481243, - "eval_NIST_loss": 1.4815818071365356, - "eval_NIST_matched_formulas": 0.06746637328317422, - "eval_NIST_morgan_tanimoto_simil": 0.20769413146775717, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.008091706001348618, - "eval_NIST_runtime": 438.2907, - "eval_NIST_samples_per_second": 64.288, - "eval_NIST_steps_per_second": 1.006, + "epoch": 0.11, + "eval_NEIMS_old_canon_smiles": 0.9311333333333334, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.021966666666666666, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.4050060854823819, + "eval_NEIMS_old_exact_mols": 0.021866666666666666, + "eval_NEIMS_old_exact_smiles": 0.020833333333333332, + "eval_NEIMS_old_loss": 0.27354806661605835, + "eval_NEIMS_old_matched_formulas": 0.4479666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.30592744246161585, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.022, + "eval_NEIMS_old_runtime": 368.773, + "eval_NEIMS_old_samples_per_second": 81.351, + "eval_NEIMS_old_steps_per_second": 1.272, "step": 48000 }, { - "epoch": 0.43, - "learning_rate": 2.8834789658589316e-05, - "loss": 0.2475, + "epoch": 0.11, + "eval_RASSP_old_canon_smiles": 0.9287215937531285, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.037574665465345214, + "eval_RASSP_old_daylight_tanimoto_simil": 0.47090214808275194, + "eval_RASSP_old_exact_mols": 0.03737444522307872, + "eval_RASSP_old_exact_smiles": 0.036006273567591014, + "eval_RASSP_old_loss": 0.2359011471271515, + "eval_RASSP_old_matched_formulas": 0.5928521373510862, + "eval_RASSP_old_morgan_tanimoto_simil": 0.3331862928083495, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.037574665465345214, + "eval_RASSP_old_runtime": 416.2684, + "eval_RASSP_old_samples_per_second": 71.99, + "eval_RASSP_old_steps_per_second": 1.127, + "step": 48000 + }, + { + "epoch": 0.11, + "eval_NIST_canon_smiles": 0.8562657486602548, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.007630336799517337, + "eval_NIST_daylight_tanimoto_simil": 0.24491827018261106, + "eval_NIST_exact_mols": 0.007275437413493274, + "eval_NIST_exact_smiles": 0.006814068211661994, + "eval_NIST_loss": 1.8130793571472168, + "eval_NIST_matched_formulas": 0.05901976789580154, + "eval_NIST_morgan_tanimoto_simil": 0.20112500482050905, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.00759484686091493, + "eval_NIST_runtime": 488.7856, + "eval_NIST_samples_per_second": 57.647, + "eval_NIST_steps_per_second": 0.902, + "step": 48000 + }, + { + "epoch": 0.11, + "learning_rate": 4.474385360506477e-05, + "loss": 0.2675, "step": 48010 }, { - "epoch": 0.43, - "learning_rate": 2.883028555985947e-05, - "loss": 0.2552, + "epoch": 0.11, + "learning_rate": 4.474273506185544e-05, + "loss": 0.2659, "step": 48020 }, { - "epoch": 0.43, - "learning_rate": 2.882578146112963e-05, - "loss": 0.2526, + "epoch": 0.11, + "learning_rate": 4.4741616518646116e-05, + "loss": 0.2618, "step": 48030 }, { - "epoch": 0.43, - "learning_rate": 2.8821277362399785e-05, - "loss": 0.2513, + "epoch": 0.11, + "learning_rate": 4.4740497975436794e-05, + "loss": 0.2634, "step": 48040 }, { - "epoch": 0.43, - "learning_rate": 2.881677326366994e-05, - "loss": 0.2527, + "epoch": 0.11, + "learning_rate": 4.4739379432227465e-05, + "loss": 0.2605, "step": 48050 }, { - "epoch": 0.43, - "learning_rate": 2.8812269164940097e-05, - "loss": 0.2494, + "epoch": 0.11, + "learning_rate": 4.473826088901814e-05, + "loss": 0.2598, "step": 48060 }, { - "epoch": 0.43, - "learning_rate": 2.880776506621025e-05, - "loss": 0.2504, + "epoch": 0.11, + "learning_rate": 4.473714234580882e-05, + "loss": 0.2626, "step": 48070 }, { - "epoch": 0.43, - "learning_rate": 2.8803260967480412e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.47360238025995e-05, + "loss": 0.2657, "step": 48080 }, { - "epoch": 0.43, - "learning_rate": 2.8798756868750566e-05, - "loss": 0.2507, + "epoch": 0.11, + "learning_rate": 4.473490525939017e-05, + "loss": 0.2615, "step": 48090 }, { - "epoch": 0.43, - "learning_rate": 2.879425277002072e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.473378671618085e-05, + "loss": 0.261, "step": 48100 }, { - "epoch": 0.43, - "learning_rate": 2.8789748671290878e-05, - "loss": 0.2529, + "epoch": 0.11, + "learning_rate": 4.4732668172971526e-05, + "loss": 0.2631, "step": 48110 }, { - "epoch": 0.43, - "learning_rate": 2.8785244572561032e-05, - "loss": 0.2489, + "epoch": 0.11, + "learning_rate": 4.47315496297622e-05, + "loss": 0.2617, "step": 48120 }, { - "epoch": 0.43, - "learning_rate": 2.8780740473831186e-05, - "loss": 0.2521, + "epoch": 0.11, + "learning_rate": 4.4730431086552875e-05, + "loss": 0.2664, "step": 48130 }, { - "epoch": 0.43, - "learning_rate": 2.8776236375101347e-05, - "loss": 0.2539, + "epoch": 0.11, + "learning_rate": 4.4729312543343546e-05, + "loss": 0.2714, "step": 48140 }, { - "epoch": 0.43, - "learning_rate": 2.8771732276371498e-05, - "loss": 0.2568, + "epoch": 0.11, + "learning_rate": 4.4728194000134224e-05, + "loss": 0.2598, "step": 48150 }, { - "epoch": 0.43, - "learning_rate": 2.876722817764165e-05, - "loss": 0.2528, + "epoch": 0.11, + "learning_rate": 4.47270754569249e-05, + "loss": 0.2561, "step": 48160 }, { - "epoch": 0.43, - "learning_rate": 2.8762724078911813e-05, - "loss": 0.2439, + "epoch": 0.11, + "learning_rate": 4.472595691371558e-05, + "loss": 0.2647, "step": 48170 }, { - "epoch": 0.43, - "learning_rate": 2.8758219980181967e-05, - "loss": 0.256, + "epoch": 0.11, + "learning_rate": 4.472483837050626e-05, + "loss": 0.2673, "step": 48180 }, { - "epoch": 0.43, - "learning_rate": 2.875371588145212e-05, - "loss": 0.2497, + "epoch": 0.11, + "learning_rate": 4.472371982729693e-05, + "loss": 0.2585, "step": 48190 }, { - "epoch": 0.43, - "learning_rate": 2.8749211782722278e-05, - "loss": 0.2548, + "epoch": 0.11, + "learning_rate": 4.472260128408761e-05, + "loss": 0.2659, "step": 48200 }, { - "epoch": 0.43, - "learning_rate": 2.8744707683992432e-05, - "loss": 0.2486, + "epoch": 0.11, + "learning_rate": 4.4721482740878285e-05, + "loss": 0.2697, "step": 48210 }, { - "epoch": 0.43, - "learning_rate": 2.8740203585262593e-05, - "loss": 0.2548, + "epoch": 0.11, + "learning_rate": 4.4720364197668956e-05, + "loss": 0.2635, "step": 48220 }, { - "epoch": 0.43, - "learning_rate": 2.8735699486532747e-05, - "loss": 0.2475, + "epoch": 0.11, + "learning_rate": 4.4719245654459634e-05, + "loss": 0.2662, "step": 48230 }, { - "epoch": 0.43, - "learning_rate": 2.87311953878029e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.4718127111250305e-05, + "loss": 0.2616, "step": 48240 }, { - "epoch": 0.43, - "learning_rate": 2.872669128907306e-05, - "loss": 0.2508, + "epoch": 0.11, + "learning_rate": 4.471700856804098e-05, + "loss": 0.2642, "step": 48250 }, { - "epoch": 0.43, - "learning_rate": 2.8722187190343213e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.471589002483166e-05, + "loss": 0.2599, "step": 48260 }, { - "epoch": 0.43, - "learning_rate": 2.8717683091613367e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.471477148162234e-05, + "loss": 0.2664, "step": 48270 }, { - "epoch": 0.43, - "learning_rate": 2.8713178992883528e-05, - "loss": 0.2496, + "epoch": 0.11, + "learning_rate": 4.471365293841302e-05, + "loss": 0.2658, "step": 48280 }, { - "epoch": 0.43, - "learning_rate": 2.8708674894153682e-05, - "loss": 0.2534, + "epoch": 0.11, + "learning_rate": 4.471253439520369e-05, + "loss": 0.2657, "step": 48290 }, { - "epoch": 0.43, - "learning_rate": 2.8704170795423836e-05, - "loss": 0.2506, + "epoch": 0.11, + "learning_rate": 4.4711415851994366e-05, + "loss": 0.2661, "step": 48300 }, { - "epoch": 0.43, - "learning_rate": 2.8699666696693994e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.4710297308785044e-05, + "loss": 0.2645, "step": 48310 }, { - "epoch": 0.43, - "learning_rate": 2.8695162597964148e-05, - "loss": 0.2502, + "epoch": 0.11, + "learning_rate": 4.4709178765575715e-05, + "loss": 0.2668, "step": 48320 }, { - "epoch": 0.43, - "learning_rate": 2.8690658499234302e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.470806022236639e-05, + "loss": 0.2646, "step": 48330 }, { - "epoch": 0.43, - "learning_rate": 2.8686154400504463e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.4706941679157064e-05, + "loss": 0.2597, "step": 48340 }, { - "epoch": 0.43, - "learning_rate": 2.8681650301774614e-05, - "loss": 0.249, + "epoch": 0.11, + "learning_rate": 4.470582313594774e-05, + "loss": 0.2613, "step": 48350 }, { - "epoch": 0.43, - "learning_rate": 2.8677146203044774e-05, - "loss": 0.2538, + "epoch": 0.11, + "learning_rate": 4.470470459273842e-05, + "loss": 0.2597, "step": 48360 }, { - "epoch": 0.43, - "learning_rate": 2.867264210431493e-05, - "loss": 0.2475, + "epoch": 0.11, + "learning_rate": 4.47035860495291e-05, + "loss": 0.2663, "step": 48370 }, { - "epoch": 0.43, - "learning_rate": 2.8668138005585083e-05, - "loss": 0.2508, + "epoch": 0.11, + "learning_rate": 4.4702467506319776e-05, + "loss": 0.2671, "step": 48380 }, { - "epoch": 0.43, - "learning_rate": 2.866363390685524e-05, - "loss": 0.2493, + "epoch": 0.11, + "learning_rate": 4.470134896311045e-05, + "loss": 0.2638, "step": 48390 }, { - "epoch": 0.43, - "learning_rate": 2.8659129808125394e-05, - "loss": 0.2525, + "epoch": 0.11, + "learning_rate": 4.4700230419901125e-05, + "loss": 0.263, "step": 48400 }, { - "epoch": 0.43, - "learning_rate": 2.865462570939555e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.4699111876691796e-05, + "loss": 0.2633, "step": 48410 }, { - "epoch": 0.43, - "learning_rate": 2.865012161066571e-05, - "loss": 0.2452, + "epoch": 0.11, + "learning_rate": 4.4697993333482474e-05, + "loss": 0.2625, "step": 48420 }, { - "epoch": 0.43, - "learning_rate": 2.8645617511935863e-05, - "loss": 0.2461, + "epoch": 0.11, + "learning_rate": 4.469687479027315e-05, + "loss": 0.2652, "step": 48430 }, { - "epoch": 0.43, - "learning_rate": 2.8641113413206017e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.469575624706382e-05, + "loss": 0.2629, "step": 48440 }, { - "epoch": 0.43, - "learning_rate": 2.8636609314476175e-05, - "loss": 0.2502, + "epoch": 0.11, + "learning_rate": 4.46946377038545e-05, + "loss": 0.263, "step": 48450 }, { - "epoch": 0.43, - "learning_rate": 2.863210521574633e-05, - "loss": 0.2464, + "epoch": 0.11, + "learning_rate": 4.469351916064517e-05, + "loss": 0.2623, "step": 48460 }, { - "epoch": 0.43, - "learning_rate": 2.8627601117016483e-05, - "loss": 0.246, + "epoch": 0.11, + "learning_rate": 4.469240061743585e-05, + "loss": 0.2573, "step": 48470 }, { - "epoch": 0.43, - "learning_rate": 2.8623097018286644e-05, - "loss": 0.2472, + "epoch": 0.11, + "learning_rate": 4.469128207422653e-05, + "loss": 0.2638, "step": 48480 }, { - "epoch": 0.43, - "learning_rate": 2.8618592919556798e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.4690163531017206e-05, + "loss": 0.2597, "step": 48490 }, { - "epoch": 0.43, - "learning_rate": 2.8614088820826956e-05, - "loss": 0.2457, + "epoch": 0.11, + "learning_rate": 4.4689044987807884e-05, + "loss": 0.2611, "step": 48500 }, { - "epoch": 0.43, - "learning_rate": 2.860958472209711e-05, - "loss": 0.2485, + "epoch": 0.11, + "learning_rate": 4.4687926444598555e-05, + "loss": 0.2627, "step": 48510 }, { - "epoch": 0.43, - "learning_rate": 2.8605080623367264e-05, - "loss": 0.2418, + "epoch": 0.11, + "learning_rate": 4.468680790138923e-05, + "loss": 0.2614, "step": 48520 }, { - "epoch": 0.43, - "learning_rate": 2.8600576524637425e-05, - "loss": 0.2475, + "epoch": 0.11, + "learning_rate": 4.468568935817991e-05, + "loss": 0.2627, "step": 48530 }, { - "epoch": 0.43, - "learning_rate": 2.859607242590758e-05, - "loss": 0.249, + "epoch": 0.11, + "learning_rate": 4.468457081497058e-05, + "loss": 0.2603, "step": 48540 }, { - "epoch": 0.43, - "learning_rate": 2.8591568327177733e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.468345227176126e-05, + "loss": 0.2607, "step": 48550 }, { - "epoch": 0.43, - "learning_rate": 2.858706422844789e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.468233372855193e-05, + "loss": 0.2655, "step": 48560 }, { - "epoch": 0.43, - "learning_rate": 2.8582560129718044e-05, - "loss": 0.2494, + "epoch": 0.11, + "learning_rate": 4.468121518534261e-05, + "loss": 0.2598, "step": 48570 }, { - "epoch": 0.43, - "learning_rate": 2.85780560309882e-05, - "loss": 0.2411, + "epoch": 0.11, + "learning_rate": 4.468009664213329e-05, + "loss": 0.2606, "step": 48580 }, { - "epoch": 0.43, - "learning_rate": 2.857355193225836e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.4678978098923965e-05, + "loss": 0.254, "step": 48590 }, { - "epoch": 0.43, - "learning_rate": 2.856904783352851e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.467785955571464e-05, + "loss": 0.2579, "step": 48600 }, { - "epoch": 0.43, - "learning_rate": 2.8564543734798664e-05, - "loss": 0.2527, + "epoch": 0.11, + "learning_rate": 4.4676741012505314e-05, + "loss": 0.2604, "step": 48610 }, { - "epoch": 0.43, - "learning_rate": 2.8560039636068825e-05, - "loss": 0.2508, + "epoch": 0.11, + "learning_rate": 4.467562246929599e-05, + "loss": 0.2635, "step": 48620 }, { - "epoch": 0.43, - "learning_rate": 2.855553553733898e-05, - "loss": 0.2513, + "epoch": 0.11, + "learning_rate": 4.467450392608667e-05, + "loss": 0.2624, "step": 48630 }, { - "epoch": 0.43, - "learning_rate": 2.8551031438609137e-05, - "loss": 0.2424, + "epoch": 0.11, + "learning_rate": 4.467338538287734e-05, + "loss": 0.2528, "step": 48640 }, { - "epoch": 0.43, - "learning_rate": 2.854652733987929e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.467226683966802e-05, + "loss": 0.262, "step": 48650 }, { - "epoch": 0.43, - "learning_rate": 2.8542023241149445e-05, - "loss": 0.2478, + "epoch": 0.11, + "learning_rate": 4.467114829645869e-05, + "loss": 0.2598, "step": 48660 }, { - "epoch": 0.43, - "learning_rate": 2.8537519142419606e-05, - "loss": 0.2483, + "epoch": 0.11, + "learning_rate": 4.467002975324937e-05, + "loss": 0.2623, "step": 48670 }, { - "epoch": 0.43, - "learning_rate": 2.853301504368976e-05, - "loss": 0.2492, + "epoch": 0.11, + "learning_rate": 4.4668911210040046e-05, + "loss": 0.268, "step": 48680 }, { - "epoch": 0.43, - "learning_rate": 2.8528510944959914e-05, - "loss": 0.2424, + "epoch": 0.11, + "learning_rate": 4.4667792666830724e-05, + "loss": 0.2615, "step": 48690 }, { - "epoch": 0.43, - "learning_rate": 2.852400684623007e-05, - "loss": 0.2476, + "epoch": 0.11, + "learning_rate": 4.46666741236214e-05, + "loss": 0.2634, "step": 48700 }, { - "epoch": 0.43, - "learning_rate": 2.8519502747500226e-05, - "loss": 0.2444, + "epoch": 0.11, + "learning_rate": 4.466555558041207e-05, + "loss": 0.2593, "step": 48710 }, { - "epoch": 0.43, - "learning_rate": 2.851499864877038e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.466443703720275e-05, + "loss": 0.2577, "step": 48720 }, { - "epoch": 0.44, - "learning_rate": 2.851049455004054e-05, - "loss": 0.2446, + "epoch": 0.11, + "learning_rate": 4.466331849399342e-05, + "loss": 0.2642, "step": 48730 }, { - "epoch": 0.44, - "learning_rate": 2.8505990451310695e-05, - "loss": 0.2518, + "epoch": 0.11, + "learning_rate": 4.46621999507841e-05, + "loss": 0.2649, "step": 48740 }, { - "epoch": 0.44, - "learning_rate": 2.850148635258085e-05, - "loss": 0.2454, + "epoch": 0.11, + "learning_rate": 4.466108140757478e-05, + "loss": 0.2628, "step": 48750 }, { - "epoch": 0.44, - "learning_rate": 2.8496982253851006e-05, - "loss": 0.2485, + "epoch": 0.11, + "learning_rate": 4.465996286436545e-05, + "loss": 0.2575, "step": 48760 }, { - "epoch": 0.44, - "learning_rate": 2.849247815512116e-05, - "loss": 0.2465, + "epoch": 0.11, + "learning_rate": 4.465884432115613e-05, + "loss": 0.2575, "step": 48770 }, { - "epoch": 0.44, - "learning_rate": 2.848797405639132e-05, - "loss": 0.2497, + "epoch": 0.11, + "learning_rate": 4.4657725777946805e-05, + "loss": 0.2618, "step": 48780 }, { - "epoch": 0.44, - "learning_rate": 2.8483469957661475e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.465660723473748e-05, + "loss": 0.257, "step": 48790 }, { - "epoch": 0.44, - "learning_rate": 2.8478965858931626e-05, - "loss": 0.2449, + "epoch": 0.11, + "learning_rate": 4.465548869152816e-05, + "loss": 0.265, "step": 48800 }, { - "epoch": 0.44, - "learning_rate": 2.8474461760201787e-05, - "loss": 0.243, + "epoch": 0.11, + "learning_rate": 4.465437014831883e-05, + "loss": 0.2689, "step": 48810 }, { - "epoch": 0.44, - "learning_rate": 2.846995766147194e-05, - "loss": 0.2443, + "epoch": 0.11, + "learning_rate": 4.465325160510951e-05, + "loss": 0.2615, "step": 48820 }, { - "epoch": 0.44, - "learning_rate": 2.8465453562742095e-05, - "loss": 0.2382, + "epoch": 0.11, + "learning_rate": 4.465213306190018e-05, + "loss": 0.2581, "step": 48830 }, { - "epoch": 0.44, - "learning_rate": 2.8460949464012253e-05, - "loss": 0.2441, + "epoch": 0.11, + "learning_rate": 4.465101451869086e-05, + "loss": 0.2624, "step": 48840 }, { - "epoch": 0.44, - "learning_rate": 2.8456445365282407e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.464989597548154e-05, + "loss": 0.2618, "step": 48850 }, { - "epoch": 0.44, - "learning_rate": 2.845194126655256e-05, - "loss": 0.2521, + "epoch": 0.11, + "learning_rate": 4.464877743227221e-05, + "loss": 0.2644, "step": 48860 }, { - "epoch": 0.44, - "learning_rate": 2.8447437167822722e-05, - "loss": 0.2486, + "epoch": 0.11, + "learning_rate": 4.4647658889062886e-05, + "loss": 0.2593, "step": 48870 }, { - "epoch": 0.44, - "learning_rate": 2.8442933069092876e-05, - "loss": 0.2523, + "epoch": 0.11, + "learning_rate": 4.464654034585356e-05, + "loss": 0.2606, "step": 48880 }, { - "epoch": 0.44, - "learning_rate": 2.843842897036303e-05, - "loss": 0.2494, + "epoch": 0.11, + "learning_rate": 4.4645421802644235e-05, + "loss": 0.2659, "step": 48890 }, { - "epoch": 0.44, - "learning_rate": 2.8433924871633188e-05, - "loss": 0.2528, + "epoch": 0.11, + "learning_rate": 4.464430325943492e-05, + "loss": 0.2593, "step": 48900 }, { - "epoch": 0.44, - "learning_rate": 2.842942077290334e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.464318471622559e-05, + "loss": 0.2693, "step": 48910 }, { - "epoch": 0.44, - "learning_rate": 2.8424916674173503e-05, - "loss": 0.2463, + "epoch": 0.11, + "learning_rate": 4.464206617301627e-05, + "loss": 0.2732, "step": 48920 }, { - "epoch": 0.44, - "learning_rate": 2.8420412575443657e-05, - "loss": 0.2451, + "epoch": 0.11, + "learning_rate": 4.464094762980694e-05, + "loss": 0.2606, "step": 48930 }, { - "epoch": 0.44, - "learning_rate": 2.841590847671381e-05, - "loss": 0.253, + "epoch": 0.11, + "learning_rate": 4.463982908659762e-05, + "loss": 0.26, "step": 48940 }, { - "epoch": 0.44, - "learning_rate": 2.8411404377983968e-05, - "loss": 0.2516, + "epoch": 0.11, + "learning_rate": 4.4638710543388296e-05, + "loss": 0.2582, "step": 48950 }, { - "epoch": 0.44, - "learning_rate": 2.8406900279254122e-05, - "loss": 0.2512, + "epoch": 0.11, + "learning_rate": 4.463759200017897e-05, + "loss": 0.2562, "step": 48960 }, { - "epoch": 0.44, - "learning_rate": 2.8402396180524276e-05, - "loss": 0.2456, + "epoch": 0.11, + "learning_rate": 4.4636473456969645e-05, + "loss": 0.2572, "step": 48970 }, { - "epoch": 0.44, - "learning_rate": 2.8397892081794437e-05, - "loss": 0.2492, + "epoch": 0.11, + "learning_rate": 4.4635354913760316e-05, + "loss": 0.2622, "step": 48980 }, { - "epoch": 0.44, - "learning_rate": 2.839338798306459e-05, - "loss": 0.2497, + "epoch": 0.11, + "learning_rate": 4.4634236370550994e-05, + "loss": 0.2607, "step": 48990 }, { - "epoch": 0.44, - "learning_rate": 2.8388883884334742e-05, - "loss": 0.248, + "epoch": 0.11, + "learning_rate": 4.463311782734167e-05, + "loss": 0.2633, "step": 49000 }, { - "epoch": 0.44, - "learning_rate": 2.8384379785604903e-05, - "loss": 0.2518, + "epoch": 0.11, + "learning_rate": 4.463199928413235e-05, + "loss": 0.2601, "step": 49010 }, { - "epoch": 0.44, - "learning_rate": 2.8379875686875057e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.463088074092303e-05, + "loss": 0.2659, "step": 49020 }, { - "epoch": 0.44, - "learning_rate": 2.837537158814521e-05, - "loss": 0.2415, + "epoch": 0.11, + "learning_rate": 4.46297621977137e-05, + "loss": 0.2617, "step": 49030 }, { - "epoch": 0.44, - "learning_rate": 2.837086748941537e-05, - "loss": 0.2472, + "epoch": 0.11, + "learning_rate": 4.462864365450438e-05, + "loss": 0.2633, "step": 49040 }, { - "epoch": 0.44, - "learning_rate": 2.8366363390685523e-05, - "loss": 0.2428, + "epoch": 0.11, + "learning_rate": 4.462752511129505e-05, + "loss": 0.2645, "step": 49050 }, { - "epoch": 0.44, - "learning_rate": 2.8361859291955684e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.4626406568085726e-05, + "loss": 0.2605, "step": 49060 }, { - "epoch": 0.44, - "learning_rate": 2.8357355193225838e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.4625288024876404e-05, + "loss": 0.2644, "step": 49070 }, { - "epoch": 0.44, - "learning_rate": 2.8352851094495992e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.4624169481667075e-05, + "loss": 0.2611, "step": 49080 }, { - "epoch": 0.44, - "learning_rate": 2.834834699576615e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.462305093845775e-05, + "loss": 0.2676, "step": 49090 }, { - "epoch": 0.44, - "learning_rate": 2.8343842897036303e-05, - "loss": 0.2534, + "epoch": 0.11, + "learning_rate": 4.462193239524843e-05, + "loss": 0.2579, "step": 49100 }, { - "epoch": 0.44, - "learning_rate": 2.8339338798306458e-05, - "loss": 0.2493, + "epoch": 0.11, + "learning_rate": 4.462081385203911e-05, + "loss": 0.2567, "step": 49110 }, { - "epoch": 0.44, - "learning_rate": 2.833483469957662e-05, - "loss": 0.2452, + "epoch": 0.11, + "learning_rate": 4.461969530882979e-05, + "loss": 0.2589, "step": 49120 }, { - "epoch": 0.44, - "learning_rate": 2.8330330600846773e-05, - "loss": 0.2511, + "epoch": 0.11, + "learning_rate": 4.461857676562046e-05, + "loss": 0.2613, "step": 49130 }, { - "epoch": 0.44, - "learning_rate": 2.8325826502116927e-05, - "loss": 0.2466, + "epoch": 0.11, + "learning_rate": 4.4617458222411136e-05, + "loss": 0.2682, "step": 49140 }, { - "epoch": 0.44, - "learning_rate": 2.8321322403387084e-05, - "loss": 0.246, + "epoch": 0.11, + "learning_rate": 4.461645153352274e-05, + "loss": 0.258, "step": 49150 }, { - "epoch": 0.44, - "learning_rate": 2.8316818304657238e-05, - "loss": 0.2466, + "epoch": 0.11, + "learning_rate": 4.4615332990313416e-05, + "loss": 0.2676, "step": 49160 }, { - "epoch": 0.44, - "learning_rate": 2.8312314205927392e-05, - "loss": 0.241, + "epoch": 0.11, + "learning_rate": 4.4614214447104094e-05, + "loss": 0.2629, "step": 49170 }, { - "epoch": 0.44, - "learning_rate": 2.8307810107197553e-05, - "loss": 0.2489, + "epoch": 0.11, + "learning_rate": 4.461309590389477e-05, + "loss": 0.2591, "step": 49180 }, { - "epoch": 0.44, - "learning_rate": 2.8303306008467707e-05, - "loss": 0.2522, + "epoch": 0.11, + "learning_rate": 4.461197736068545e-05, + "loss": 0.2639, "step": 49190 }, { - "epoch": 0.44, - "learning_rate": 2.8298801909737865e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.461085881747612e-05, + "loss": 0.2615, "step": 49200 }, { - "epoch": 0.44, - "learning_rate": 2.829429781100802e-05, - "loss": 0.2511, + "epoch": 0.11, + "learning_rate": 4.46097402742668e-05, + "loss": 0.2609, "step": 49210 }, { - "epoch": 0.44, - "learning_rate": 2.8289793712278173e-05, - "loss": 0.2511, + "epoch": 0.11, + "learning_rate": 4.460862173105747e-05, + "loss": 0.2581, "step": 49220 }, { - "epoch": 0.44, - "learning_rate": 2.8285289613548334e-05, - "loss": 0.2482, + "epoch": 0.11, + "learning_rate": 4.460750318784815e-05, + "loss": 0.2672, "step": 49230 }, { - "epoch": 0.44, - "learning_rate": 2.8280785514818488e-05, - "loss": 0.2427, + "epoch": 0.11, + "learning_rate": 4.4606384644638826e-05, + "loss": 0.2594, "step": 49240 }, { - "epoch": 0.44, - "learning_rate": 2.827628141608864e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.46052661014295e-05, + "loss": 0.2605, "step": 49250 }, { - "epoch": 0.44, - "learning_rate": 2.82717773173588e-05, - "loss": 0.2551, + "epoch": 0.11, + "learning_rate": 4.4604147558220175e-05, + "loss": 0.2618, "step": 49260 }, { - "epoch": 0.44, - "learning_rate": 2.8267273218628954e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.460302901501085e-05, + "loss": 0.2642, "step": 49270 }, { - "epoch": 0.44, - "learning_rate": 2.8262769119899108e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.460191047180153e-05, + "loss": 0.2612, "step": 49280 }, { - "epoch": 0.44, - "learning_rate": 2.8258265021169265e-05, - "loss": 0.2482, + "epoch": 0.11, + "learning_rate": 4.460079192859221e-05, + "loss": 0.259, "step": 49290 }, { - "epoch": 0.44, - "learning_rate": 2.825376092243942e-05, - "loss": 0.2504, + "epoch": 0.11, + "learning_rate": 4.459967338538288e-05, + "loss": 0.2602, "step": 49300 }, { - "epoch": 0.44, - "learning_rate": 2.8249256823709574e-05, - "loss": 0.2442, + "epoch": 0.11, + "learning_rate": 4.459855484217356e-05, + "loss": 0.2622, "step": 49310 }, { - "epoch": 0.44, - "learning_rate": 2.8244752724979734e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.459743629896423e-05, + "loss": 0.2638, "step": 49320 }, { - "epoch": 0.44, - "learning_rate": 2.824024862624989e-05, - "loss": 0.2456, + "epoch": 0.11, + "learning_rate": 4.459631775575491e-05, + "loss": 0.2612, "step": 49330 }, { - "epoch": 0.44, - "learning_rate": 2.8235744527520046e-05, - "loss": 0.2465, + "epoch": 0.11, + "learning_rate": 4.4595199212545585e-05, + "loss": 0.2645, "step": 49340 }, { - "epoch": 0.44, - "learning_rate": 2.82312404287902e-05, - "loss": 0.2506, + "epoch": 0.11, + "learning_rate": 4.4594080669336256e-05, + "loss": 0.2614, "step": 49350 }, { - "epoch": 0.44, - "learning_rate": 2.8226736330060354e-05, - "loss": 0.2426, + "epoch": 0.11, + "learning_rate": 4.4592962126126934e-05, + "loss": 0.2604, "step": 49360 }, { - "epoch": 0.44, - "learning_rate": 2.8222232231330515e-05, - "loss": 0.2477, + "epoch": 0.11, + "learning_rate": 4.459184358291761e-05, + "loss": 0.2624, "step": 49370 }, { - "epoch": 0.44, - "learning_rate": 2.821772813260067e-05, - "loss": 0.2461, + "epoch": 0.11, + "learning_rate": 4.459072503970829e-05, + "loss": 0.2676, "step": 49380 }, { - "epoch": 0.44, - "learning_rate": 2.8213224033870823e-05, - "loss": 0.2457, + "epoch": 0.11, + "learning_rate": 4.458960649649897e-05, + "loss": 0.2638, "step": 49390 }, { - "epoch": 0.44, - "learning_rate": 2.820871993514098e-05, - "loss": 0.2501, + "epoch": 0.11, + "learning_rate": 4.458848795328964e-05, + "loss": 0.2647, "step": 49400 }, { - "epoch": 0.44, - "learning_rate": 2.8204215836411135e-05, - "loss": 0.2479, + "epoch": 0.11, + "learning_rate": 4.4587369410080317e-05, + "loss": 0.2596, "step": 49410 }, { - "epoch": 0.44, - "learning_rate": 2.819971173768129e-05, - "loss": 0.2487, + "epoch": 0.11, + "learning_rate": 4.458625086687099e-05, + "loss": 0.2652, "step": 49420 }, { - "epoch": 0.44, - "learning_rate": 2.819520763895145e-05, - "loss": 0.2491, + "epoch": 0.11, + "learning_rate": 4.4585132323661666e-05, + "loss": 0.2632, "step": 49430 }, { - "epoch": 0.44, - "learning_rate": 2.8190703540221604e-05, - "loss": 0.2465, + "epoch": 0.11, + "learning_rate": 4.458401378045234e-05, + "loss": 0.2638, "step": 49440 }, { - "epoch": 0.44, - "learning_rate": 2.8186199441491755e-05, - "loss": 0.2461, + "epoch": 0.11, + "learning_rate": 4.4582895237243015e-05, + "loss": 0.2547, "step": 49450 }, { - "epoch": 0.44, - "learning_rate": 2.8181695342761916e-05, - "loss": 0.2459, + "epoch": 0.11, + "learning_rate": 4.458177669403369e-05, + "loss": 0.2557, "step": 49460 }, { - "epoch": 0.44, - "learning_rate": 2.817719124403207e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.4580658150824364e-05, + "loss": 0.259, "step": 49470 }, { - "epoch": 0.44, - "learning_rate": 2.817268714530223e-05, - "loss": 0.2468, + "epoch": 0.11, + "learning_rate": 4.457953960761505e-05, + "loss": 0.2586, "step": 49480 }, { - "epoch": 0.44, - "learning_rate": 2.816818304657238e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.457842106440572e-05, + "loss": 0.2588, "step": 49490 }, { - "epoch": 0.44, - "learning_rate": 2.8163678947842535e-05, - "loss": 0.2514, + "epoch": 0.11, + "learning_rate": 4.45773025211964e-05, + "loss": 0.2585, "step": 49500 }, { - "epoch": 0.44, - "learning_rate": 2.8159174849112696e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.4576183977987075e-05, + "loss": 0.2624, "step": 49510 }, { - "epoch": 0.44, - "learning_rate": 2.815467075038285e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.4575065434777747e-05, + "loss": 0.2629, "step": 49520 }, { - "epoch": 0.44, - "learning_rate": 2.8150166651653004e-05, - "loss": 0.2447, + "epoch": 0.11, + "learning_rate": 4.4573946891568425e-05, + "loss": 0.2558, "step": 49530 }, { - "epoch": 0.44, - "learning_rate": 2.8145662552923162e-05, - "loss": 0.2435, + "epoch": 0.11, + "learning_rate": 4.4572828348359096e-05, + "loss": 0.2618, "step": 49540 }, { - "epoch": 0.44, - "learning_rate": 2.8141158454193316e-05, - "loss": 0.2479, + "epoch": 0.11, + "learning_rate": 4.4571709805149774e-05, + "loss": 0.2638, "step": 49550 }, { - "epoch": 0.44, - "learning_rate": 2.813665435546347e-05, - "loss": 0.2431, + "epoch": 0.11, + "learning_rate": 4.457059126194045e-05, + "loss": 0.2556, "step": 49560 }, { - "epoch": 0.44, - "learning_rate": 2.813215025673363e-05, - "loss": 0.2415, + "epoch": 0.11, + "learning_rate": 4.456947271873112e-05, + "loss": 0.2625, "step": 49570 }, { - "epoch": 0.44, - "learning_rate": 2.8127646158003785e-05, - "loss": 0.2449, + "epoch": 0.11, + "learning_rate": 4.45683541755218e-05, + "loss": 0.2569, "step": 49580 }, { - "epoch": 0.44, - "learning_rate": 2.812314205927394e-05, - "loss": 0.2485, + "epoch": 0.11, + "learning_rate": 4.456723563231248e-05, + "loss": 0.2596, "step": 49590 }, { - "epoch": 0.44, - "learning_rate": 2.8118637960544097e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.4566117089103156e-05, + "loss": 0.2633, "step": 49600 }, { - "epoch": 0.44, - "learning_rate": 2.811413386181425e-05, - "loss": 0.2441, + "epoch": 0.11, + "learning_rate": 4.4564998545893834e-05, + "loss": 0.2608, "step": 49610 }, { - "epoch": 0.44, - "learning_rate": 2.8109629763084412e-05, - "loss": 0.2476, + "epoch": 0.11, + "learning_rate": 4.4563880002684506e-05, + "loss": 0.2592, "step": 49620 }, { - "epoch": 0.44, - "learning_rate": 2.8105125664354566e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.4562761459475183e-05, + "loss": 0.2613, "step": 49630 }, { - "epoch": 0.44, - "learning_rate": 2.810062156562472e-05, - "loss": 0.2428, + "epoch": 0.11, + "learning_rate": 4.4561642916265855e-05, + "loss": 0.2596, "step": 49640 }, { - "epoch": 0.44, - "learning_rate": 2.8096117466894877e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.456052437305653e-05, + "loss": 0.2638, "step": 49650 }, { - "epoch": 0.44, - "learning_rate": 2.809161336816503e-05, - "loss": 0.2453, + "epoch": 0.11, + "learning_rate": 4.455940582984721e-05, + "loss": 0.265, "step": 49660 }, { - "epoch": 0.44, - "learning_rate": 2.8087109269435186e-05, - "loss": 0.2451, + "epoch": 0.11, + "learning_rate": 4.455828728663788e-05, + "loss": 0.2652, "step": 49670 }, { - "epoch": 0.44, - "learning_rate": 2.8082605170705347e-05, - "loss": 0.2408, + "epoch": 0.11, + "learning_rate": 4.455716874342856e-05, + "loss": 0.2627, "step": 49680 }, { - "epoch": 0.44, - "learning_rate": 2.8078101071975497e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.455605020021924e-05, + "loss": 0.2599, "step": 49690 }, { - "epoch": 0.44, - "learning_rate": 2.807359697324565e-05, - "loss": 0.2464, + "epoch": 0.11, + "learning_rate": 4.4554931657009915e-05, + "loss": 0.2583, "step": 49700 }, { - "epoch": 0.44, - "learning_rate": 2.8069092874515812e-05, - "loss": 0.2507, + "epoch": 0.11, + "learning_rate": 4.455381311380059e-05, + "loss": 0.2633, "step": 49710 }, { - "epoch": 0.44, - "learning_rate": 2.8064588775785966e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.4552694570591265e-05, + "loss": 0.2623, "step": 49720 }, { - "epoch": 0.44, - "learning_rate": 2.806008467705612e-05, - "loss": 0.2459, + "epoch": 0.11, + "learning_rate": 4.455157602738194e-05, + "loss": 0.26, "step": 49730 }, { - "epoch": 0.44, - "learning_rate": 2.8055580578326278e-05, - "loss": 0.2459, + "epoch": 0.11, + "learning_rate": 4.4550457484172614e-05, + "loss": 0.26, "step": 49740 }, { - "epoch": 0.44, - "learning_rate": 2.8051076479596432e-05, - "loss": 0.2466, + "epoch": 0.11, + "learning_rate": 4.454933894096329e-05, + "loss": 0.2616, "step": 49750 }, { - "epoch": 0.44, - "learning_rate": 2.8047022790739576e-05, - "loss": 0.2453, + "epoch": 0.11, + "learning_rate": 4.454822039775396e-05, + "loss": 0.2596, "step": 49760 }, { - "epoch": 0.44, - "learning_rate": 2.804251869200973e-05, - "loss": 0.2538, + "epoch": 0.11, + "learning_rate": 4.454710185454464e-05, + "loss": 0.2592, "step": 49770 }, { - "epoch": 0.44, - "learning_rate": 2.8038014593279887e-05, - "loss": 0.2517, + "epoch": 0.11, + "learning_rate": 4.454598331133532e-05, + "loss": 0.2594, "step": 49780 }, { - "epoch": 0.44, - "learning_rate": 2.803351049455004e-05, - "loss": 0.2493, + "epoch": 0.11, + "learning_rate": 4.4544864768125996e-05, + "loss": 0.2575, "step": 49790 }, { - "epoch": 0.44, - "learning_rate": 2.8029006395820196e-05, - "loss": 0.2488, + "epoch": 0.11, + "learning_rate": 4.4543746224916674e-05, + "loss": 0.2599, "step": 49800 }, { - "epoch": 0.44, - "learning_rate": 2.8024502297090353e-05, - "loss": 0.2478, + "epoch": 0.11, + "learning_rate": 4.4542627681707346e-05, + "loss": 0.2605, "step": 49810 }, { - "epoch": 0.44, - "learning_rate": 2.8019998198360507e-05, - "loss": 0.2422, + "epoch": 0.11, + "learning_rate": 4.4541509138498023e-05, + "loss": 0.2542, "step": 49820 }, { - "epoch": 0.44, - "learning_rate": 2.801549409963066e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.45403905952887e-05, + "loss": 0.2613, "step": 49830 }, { - "epoch": 0.44, - "learning_rate": 2.8010990000900822e-05, - "loss": 0.2487, + "epoch": 0.11, + "learning_rate": 4.453927205207937e-05, + "loss": 0.2607, "step": 49840 }, { - "epoch": 0.45, - "learning_rate": 2.8006485902170976e-05, - "loss": 0.2446, + "epoch": 0.11, + "learning_rate": 4.453815350887005e-05, + "loss": 0.2636, "step": 49850 }, { - "epoch": 0.45, - "learning_rate": 2.8001981803441134e-05, - "loss": 0.2468, + "epoch": 0.11, + "learning_rate": 4.453703496566072e-05, + "loss": 0.259, "step": 49860 }, { - "epoch": 0.45, - "learning_rate": 2.7997477704711288e-05, - "loss": 0.2429, + "epoch": 0.11, + "learning_rate": 4.45359164224514e-05, + "loss": 0.258, "step": 49870 }, { - "epoch": 0.45, - "learning_rate": 2.7992973605981442e-05, - "loss": 0.2481, + "epoch": 0.11, + "learning_rate": 4.453479787924208e-05, + "loss": 0.2555, "step": 49880 }, { - "epoch": 0.45, - "learning_rate": 2.7988469507251603e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.453367933603275e-05, + "loss": 0.2614, "step": 49890 }, { - "epoch": 0.45, - "learning_rate": 2.7983965408521757e-05, - "loss": 0.2466, + "epoch": 0.11, + "learning_rate": 4.453256079282343e-05, + "loss": 0.2646, "step": 49900 }, { - "epoch": 0.45, - "learning_rate": 2.797946130979191e-05, - "loss": 0.2472, + "epoch": 0.11, + "learning_rate": 4.4531442249614104e-05, + "loss": 0.2578, "step": 49910 }, { - "epoch": 0.45, - "learning_rate": 2.797495721106207e-05, - "loss": 0.2442, + "epoch": 0.11, + "learning_rate": 4.453032370640478e-05, + "loss": 0.2583, "step": 49920 }, { - "epoch": 0.45, - "learning_rate": 2.7970453112332223e-05, - "loss": 0.2428, + "epoch": 0.11, + "learning_rate": 4.452920516319546e-05, + "loss": 0.2616, "step": 49930 }, { - "epoch": 0.45, - "learning_rate": 2.7965949013602377e-05, - "loss": 0.2408, + "epoch": 0.11, + "learning_rate": 4.452808661998613e-05, + "loss": 0.2573, "step": 49940 }, { - "epoch": 0.45, - "learning_rate": 2.7961444914872538e-05, - "loss": 0.2505, + "epoch": 0.11, + "learning_rate": 4.452696807677681e-05, + "loss": 0.2624, "step": 49950 }, { - "epoch": 0.45, - "learning_rate": 2.7956940816142692e-05, - "loss": 0.2488, + "epoch": 0.11, + "learning_rate": 4.452584953356748e-05, + "loss": 0.2623, "step": 49960 }, { - "epoch": 0.45, - "learning_rate": 2.7952436717412846e-05, - "loss": 0.2406, + "epoch": 0.11, + "learning_rate": 4.452473099035816e-05, + "loss": 0.2603, "step": 49970 }, { - "epoch": 0.45, - "learning_rate": 2.7947932618683003e-05, - "loss": 0.24, + "epoch": 0.11, + "learning_rate": 4.4523612447148836e-05, + "loss": 0.2623, "step": 49980 }, { - "epoch": 0.45, - "learning_rate": 2.7943428519953157e-05, - "loss": 0.2512, + "epoch": 0.11, + "learning_rate": 4.452249390393951e-05, + "loss": 0.2588, "step": 49990 }, { - "epoch": 0.45, - "learning_rate": 2.793892442122332e-05, - "loss": 0.2498, + "epoch": 0.11, + "learning_rate": 4.4521375360730185e-05, + "loss": 0.2621, "step": 50000 }, { - "epoch": 0.45, - "learning_rate": 2.7934420322493472e-05, - "loss": 0.244, + "epoch": 0.11, + "learning_rate": 4.4520256817520863e-05, + "loss": 0.2659, "step": 50010 }, { - "epoch": 0.45, - "learning_rate": 2.7929916223763623e-05, - "loss": 0.2428, + "epoch": 0.11, + "learning_rate": 4.451913827431154e-05, + "loss": 0.258, "step": 50020 }, { - "epoch": 0.45, - "learning_rate": 2.7925412125033784e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.451801973110222e-05, + "loss": 0.2637, "step": 50030 }, { - "epoch": 0.45, - "learning_rate": 2.7920908026303938e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.451690118789289e-05, + "loss": 0.2539, "step": 50040 }, { - "epoch": 0.45, - "learning_rate": 2.7916403927574092e-05, - "loss": 0.2402, + "epoch": 0.11, + "learning_rate": 4.451578264468357e-05, + "loss": 0.2554, "step": 50050 }, { - "epoch": 0.45, - "learning_rate": 2.791189982884425e-05, - "loss": 0.2447, + "epoch": 0.11, + "learning_rate": 4.451466410147424e-05, + "loss": 0.2512, "step": 50060 }, { - "epoch": 0.45, - "learning_rate": 2.7907395730114404e-05, - "loss": 0.246, + "epoch": 0.11, + "learning_rate": 4.451354555826492e-05, + "loss": 0.2554, "step": 50070 }, { - "epoch": 0.45, - "learning_rate": 2.7902891631384558e-05, - "loss": 0.2454, + "epoch": 0.11, + "learning_rate": 4.451242701505559e-05, + "loss": 0.2593, "step": 50080 }, { - "epoch": 0.45, - "learning_rate": 2.789838753265472e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.4511308471846267e-05, + "loss": 0.2594, "step": 50090 }, { - "epoch": 0.45, - "learning_rate": 2.7893883433924873e-05, - "loss": 0.2458, + "epoch": 0.11, + "learning_rate": 4.4510189928636944e-05, + "loss": 0.2588, "step": 50100 }, { - "epoch": 0.45, - "learning_rate": 2.7889379335195027e-05, - "loss": 0.245, + "epoch": 0.11, + "learning_rate": 4.450907138542762e-05, + "loss": 0.2577, "step": 50110 }, { - "epoch": 0.45, - "learning_rate": 2.7884875236465185e-05, - "loss": 0.2444, + "epoch": 0.11, + "learning_rate": 4.45079528422183e-05, + "loss": 0.2623, "step": 50120 }, { - "epoch": 0.45, - "learning_rate": 2.788037113773534e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.450683429900897e-05, + "loss": 0.2567, "step": 50130 }, { - "epoch": 0.45, - "learning_rate": 2.78758670390055e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.450571575579965e-05, + "loss": 0.2612, "step": 50140 }, { - "epoch": 0.45, - "learning_rate": 2.7871362940275654e-05, - "loss": 0.2447, + "epoch": 0.11, + "learning_rate": 4.450459721259033e-05, + "loss": 0.2575, "step": 50150 }, { - "epoch": 0.45, - "learning_rate": 2.7866858841545808e-05, - "loss": 0.2501, + "epoch": 0.11, + "learning_rate": 4.4503478669381e-05, + "loss": 0.2586, "step": 50160 }, { - "epoch": 0.45, - "learning_rate": 2.7862354742815965e-05, - "loss": 0.2477, + "epoch": 0.11, + "learning_rate": 4.4502360126171676e-05, + "loss": 0.2597, "step": 50170 }, { - "epoch": 0.45, - "learning_rate": 2.785785064408612e-05, - "loss": 0.2501, + "epoch": 0.11, + "learning_rate": 4.450124158296235e-05, + "loss": 0.2619, "step": 50180 }, { - "epoch": 0.45, - "learning_rate": 2.7853346545356273e-05, - "loss": 0.2464, + "epoch": 0.11, + "learning_rate": 4.4500123039753025e-05, + "loss": 0.2572, "step": 50190 }, { - "epoch": 0.45, - "learning_rate": 2.7848842446626434e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.44990044965437e-05, + "loss": 0.2588, "step": 50200 }, { - "epoch": 0.45, - "learning_rate": 2.784433834789659e-05, - "loss": 0.2513, + "epoch": 0.11, + "learning_rate": 4.449788595333438e-05, + "loss": 0.2649, "step": 50210 }, { - "epoch": 0.45, - "learning_rate": 2.783983424916674e-05, - "loss": 0.2479, + "epoch": 0.11, + "learning_rate": 4.449676741012506e-05, + "loss": 0.258, "step": 50220 }, { - "epoch": 0.45, - "learning_rate": 2.78353301504369e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.449564886691573e-05, + "loss": 0.2543, "step": 50230 }, { - "epoch": 0.45, - "learning_rate": 2.7830826051707054e-05, - "loss": 0.2428, + "epoch": 0.11, + "learning_rate": 4.449453032370641e-05, + "loss": 0.2626, "step": 50240 }, { - "epoch": 0.45, - "learning_rate": 2.7826321952977208e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.4493411780497086e-05, + "loss": 0.2548, "step": 50250 }, { - "epoch": 0.45, - "learning_rate": 2.7821817854247366e-05, - "loss": 0.2412, + "epoch": 0.11, + "learning_rate": 4.449229323728776e-05, + "loss": 0.2523, "step": 50260 }, { - "epoch": 0.45, - "learning_rate": 2.781731375551752e-05, - "loss": 0.2527, + "epoch": 0.11, + "learning_rate": 4.4491174694078435e-05, + "loss": 0.2545, "step": 50270 }, { - "epoch": 0.45, - "learning_rate": 2.781280965678768e-05, - "loss": 0.2458, + "epoch": 0.11, + "learning_rate": 4.4490056150869106e-05, + "loss": 0.2637, "step": 50280 }, { - "epoch": 0.45, - "learning_rate": 2.7808305558057835e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.4488937607659784e-05, + "loss": 0.2546, "step": 50290 }, { - "epoch": 0.45, - "learning_rate": 2.780380145932799e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.448781906445046e-05, + "loss": 0.2595, "step": 50300 }, { - "epoch": 0.45, - "learning_rate": 2.7799297360598146e-05, - "loss": 0.245, + "epoch": 0.11, + "learning_rate": 4.448670052124114e-05, + "loss": 0.2542, "step": 50310 }, { - "epoch": 0.45, - "learning_rate": 2.77947932618683e-05, - "loss": 0.2412, + "epoch": 0.11, + "learning_rate": 4.448558197803182e-05, + "loss": 0.2661, "step": 50320 }, { - "epoch": 0.45, - "learning_rate": 2.7790289163138455e-05, - "loss": 0.2464, + "epoch": 0.11, + "learning_rate": 4.448446343482249e-05, + "loss": 0.2586, "step": 50330 }, { - "epoch": 0.45, - "learning_rate": 2.7785785064408616e-05, - "loss": 0.2487, + "epoch": 0.11, + "learning_rate": 4.448334489161317e-05, + "loss": 0.2573, "step": 50340 }, { - "epoch": 0.45, - "learning_rate": 2.778128096567877e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.4482226348403845e-05, + "loss": 0.2604, "step": 50350 }, { - "epoch": 0.45, - "learning_rate": 2.7776776866948924e-05, - "loss": 0.253, + "epoch": 0.11, + "learning_rate": 4.4481107805194516e-05, + "loss": 0.2636, "step": 50360 }, { - "epoch": 0.45, - "learning_rate": 2.777227276821908e-05, - "loss": 0.2463, + "epoch": 0.11, + "learning_rate": 4.4479989261985194e-05, + "loss": 0.2563, "step": 50370 }, { - "epoch": 0.45, - "learning_rate": 2.7767768669489235e-05, - "loss": 0.2475, + "epoch": 0.11, + "learning_rate": 4.4478870718775865e-05, + "loss": 0.2605, "step": 50380 }, { - "epoch": 0.45, - "learning_rate": 2.776326457075939e-05, - "loss": 0.2544, + "epoch": 0.11, + "learning_rate": 4.447775217556654e-05, + "loss": 0.2611, "step": 50390 }, { - "epoch": 0.45, - "learning_rate": 2.775876047202955e-05, - "loss": 0.2413, + "epoch": 0.11, + "learning_rate": 4.4476633632357215e-05, + "loss": 0.2567, "step": 50400 }, { - "epoch": 0.45, - "learning_rate": 2.7754256373299704e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.447551508914789e-05, + "loss": 0.2592, "step": 50410 }, { - "epoch": 0.45, - "learning_rate": 2.7749752274569862e-05, - "loss": 0.2514, + "epoch": 0.11, + "learning_rate": 4.447439654593857e-05, + "loss": 0.2556, "step": 50420 }, { - "epoch": 0.45, - "learning_rate": 2.7745248175840016e-05, - "loss": 0.2455, + "epoch": 0.11, + "learning_rate": 4.447327800272925e-05, + "loss": 0.2664, "step": 50430 }, { - "epoch": 0.45, - "learning_rate": 2.774074407711017e-05, - "loss": 0.2406, + "epoch": 0.11, + "learning_rate": 4.4472159459519926e-05, + "loss": 0.2617, "step": 50440 }, { - "epoch": 0.45, - "learning_rate": 2.773623997838033e-05, - "loss": 0.2473, + "epoch": 0.11, + "learning_rate": 4.44710409163106e-05, + "loss": 0.2596, "step": 50450 }, { - "epoch": 0.45, - "learning_rate": 2.773173587965048e-05, - "loss": 0.242, + "epoch": 0.11, + "learning_rate": 4.4469922373101275e-05, + "loss": 0.2533, "step": 50460 }, { - "epoch": 0.45, - "learning_rate": 2.7727231780920636e-05, - "loss": 0.2427, + "epoch": 0.11, + "learning_rate": 4.446880382989195e-05, + "loss": 0.2555, "step": 50470 }, { - "epoch": 0.45, - "learning_rate": 2.7722727682190797e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.4467685286682624e-05, + "loss": 0.2641, "step": 50480 }, { - "epoch": 0.45, - "learning_rate": 2.771822358346095e-05, - "loss": 0.2554, + "epoch": 0.11, + "learning_rate": 4.44665667434733e-05, + "loss": 0.2636, "step": 50490 }, { - "epoch": 0.45, - "learning_rate": 2.7713719484731105e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.4465448200263973e-05, + "loss": 0.2686, "step": 50500 }, { - "epoch": 0.45, - "learning_rate": 2.7709215386001262e-05, + "epoch": 0.11, + "learning_rate": 4.446432965705465e-05, "loss": 0.255, "step": 50510 }, { - "epoch": 0.45, - "learning_rate": 2.7704711287271416e-05, - "loss": 0.2503, + "epoch": 0.11, + "learning_rate": 4.446321111384533e-05, + "loss": 0.2563, "step": 50520 }, { - "epoch": 0.45, - "learning_rate": 2.770020718854157e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.446209257063601e-05, + "loss": 0.2542, "step": 50530 }, { - "epoch": 0.45, - "learning_rate": 2.769570308981173e-05, - "loss": 0.2402, + "epoch": 0.11, + "learning_rate": 4.4460974027426685e-05, + "loss": 0.267, "step": 50540 }, { - "epoch": 0.45, - "learning_rate": 2.7691198991081886e-05, - "loss": 0.2488, + "epoch": 0.11, + "learning_rate": 4.4459855484217356e-05, + "loss": 0.2612, "step": 50550 }, { - "epoch": 0.45, - "learning_rate": 2.7686694892352043e-05, - "loss": 0.2441, + "epoch": 0.11, + "learning_rate": 4.4458736941008034e-05, + "loss": 0.2589, "step": 50560 }, { - "epoch": 0.45, - "learning_rate": 2.7682190793622197e-05, - "loss": 0.2436, + "epoch": 0.11, + "learning_rate": 4.445761839779871e-05, + "loss": 0.2572, "step": 50570 }, { - "epoch": 0.45, - "learning_rate": 2.767768669489235e-05, - "loss": 0.2393, + "epoch": 0.11, + "learning_rate": 4.445649985458938e-05, + "loss": 0.2654, "step": 50580 }, { - "epoch": 0.45, - "learning_rate": 2.7673182596162512e-05, - "loss": 0.2416, + "epoch": 0.11, + "learning_rate": 4.445538131138006e-05, + "loss": 0.2584, "step": 50590 }, { - "epoch": 0.45, - "learning_rate": 2.7668678497432666e-05, - "loss": 0.2439, + "epoch": 0.11, + "learning_rate": 4.445426276817073e-05, + "loss": 0.2567, "step": 50600 }, { - "epoch": 0.45, - "learning_rate": 2.766417439870282e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.445314422496141e-05, + "loss": 0.2583, "step": 50610 }, { - "epoch": 0.45, - "learning_rate": 2.7659670299972978e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.445202568175209e-05, + "loss": 0.2622, "step": 50620 }, { - "epoch": 0.45, - "learning_rate": 2.7655166201243132e-05, - "loss": 0.2499, + "epoch": 0.11, + "learning_rate": 4.4450907138542766e-05, + "loss": 0.2657, "step": 50630 }, { - "epoch": 0.45, - "learning_rate": 2.7650662102513286e-05, - "loss": 0.2477, + "epoch": 0.11, + "learning_rate": 4.4449788595333444e-05, + "loss": 0.2548, "step": 50640 }, { - "epoch": 0.45, - "learning_rate": 2.7646158003783447e-05, - "loss": 0.2416, + "epoch": 0.11, + "learning_rate": 4.4448670052124115e-05, + "loss": 0.2634, "step": 50650 }, { - "epoch": 0.45, - "learning_rate": 2.76416539050536e-05, - "loss": 0.2403, + "epoch": 0.11, + "learning_rate": 4.444755150891479e-05, + "loss": 0.2544, "step": 50660 }, { - "epoch": 0.45, - "learning_rate": 2.7637149806323752e-05, - "loss": 0.2419, + "epoch": 0.11, + "learning_rate": 4.444643296570547e-05, + "loss": 0.2556, "step": 50670 }, { - "epoch": 0.45, - "learning_rate": 2.7632645707593913e-05, - "loss": 0.2377, + "epoch": 0.11, + "learning_rate": 4.444531442249614e-05, + "loss": 0.2639, "step": 50680 }, { - "epoch": 0.45, - "learning_rate": 2.7628141608864067e-05, - "loss": 0.2431, + "epoch": 0.11, + "learning_rate": 4.444419587928682e-05, + "loss": 0.2557, "step": 50690 }, { - "epoch": 0.45, - "learning_rate": 2.7623637510134228e-05, - "loss": 0.2512, + "epoch": 0.11, + "learning_rate": 4.444307733607749e-05, + "loss": 0.2594, "step": 50700 }, { - "epoch": 0.45, - "learning_rate": 2.761913341140438e-05, - "loss": 0.2485, + "epoch": 0.11, + "learning_rate": 4.444195879286817e-05, + "loss": 0.2592, "step": 50710 }, { - "epoch": 0.45, - "learning_rate": 2.7614629312674532e-05, - "loss": 0.2471, + "epoch": 0.11, + "learning_rate": 4.444084024965885e-05, + "loss": 0.2626, "step": 50720 }, { - "epoch": 0.45, - "learning_rate": 2.7610125213944693e-05, - "loss": 0.2383, + "epoch": 0.11, + "learning_rate": 4.4439721706449525e-05, + "loss": 0.2561, "step": 50730 }, { - "epoch": 0.45, - "learning_rate": 2.7605621115214847e-05, - "loss": 0.2468, + "epoch": 0.11, + "learning_rate": 4.44386031632402e-05, + "loss": 0.2588, "step": 50740 }, { - "epoch": 0.45, - "learning_rate": 2.7601117016485e-05, - "loss": 0.2462, + "epoch": 0.11, + "learning_rate": 4.4437484620030874e-05, + "loss": 0.2532, "step": 50750 }, { - "epoch": 0.45, - "learning_rate": 2.759661291775516e-05, - "loss": 0.2386, + "epoch": 0.11, + "learning_rate": 4.443636607682155e-05, + "loss": 0.2542, "step": 50760 }, { - "epoch": 0.45, - "learning_rate": 2.7592108819025313e-05, - "loss": 0.2524, + "epoch": 0.11, + "learning_rate": 4.443524753361222e-05, + "loss": 0.2604, "step": 50770 }, { - "epoch": 0.45, - "learning_rate": 2.7587604720295467e-05, - "loss": 0.2463, + "epoch": 0.11, + "learning_rate": 4.44341289904029e-05, + "loss": 0.2593, "step": 50780 }, { - "epoch": 0.45, - "learning_rate": 2.7583100621565628e-05, - "loss": 0.2376, + "epoch": 0.11, + "learning_rate": 4.443301044719358e-05, + "loss": 0.2578, "step": 50790 }, { - "epoch": 0.45, - "learning_rate": 2.7578596522835782e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.443189190398425e-05, + "loss": 0.2581, "step": 50800 }, { - "epoch": 0.45, - "learning_rate": 2.7574092424105936e-05, - "loss": 0.2489, + "epoch": 0.11, + "learning_rate": 4.443077336077493e-05, + "loss": 0.2571, "step": 50810 }, { - "epoch": 0.45, - "learning_rate": 2.7569588325376094e-05, - "loss": 0.2472, + "epoch": 0.11, + "learning_rate": 4.44296548175656e-05, + "loss": 0.2584, "step": 50820 }, { - "epoch": 0.45, - "learning_rate": 2.7565084226646248e-05, - "loss": 0.2424, + "epoch": 0.11, + "learning_rate": 4.442853627435628e-05, + "loss": 0.2546, "step": 50830 }, { - "epoch": 0.45, - "learning_rate": 2.756058012791641e-05, - "loss": 0.2454, + "epoch": 0.11, + "learning_rate": 4.4427417731146955e-05, + "loss": 0.256, "step": 50840 }, { - "epoch": 0.45, - "learning_rate": 2.7556076029186563e-05, - "loss": 0.2479, + "epoch": 0.11, + "learning_rate": 4.442629918793763e-05, + "loss": 0.2559, "step": 50850 }, { - "epoch": 0.45, - "learning_rate": 2.7551571930456717e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.442518064472831e-05, + "loss": 0.2596, "step": 50860 }, { - "epoch": 0.45, - "learning_rate": 2.7547067831726874e-05, - "loss": 0.2399, + "epoch": 0.11, + "learning_rate": 4.442406210151898e-05, + "loss": 0.2558, "step": 50870 }, { - "epoch": 0.45, - "learning_rate": 2.754256373299703e-05, - "loss": 0.2342, + "epoch": 0.11, + "learning_rate": 4.442294355830966e-05, + "loss": 0.2543, "step": 50880 }, { - "epoch": 0.45, - "learning_rate": 2.7538059634267183e-05, - "loss": 0.2426, + "epoch": 0.11, + "learning_rate": 4.442182501510034e-05, + "loss": 0.2598, "step": 50890 }, { - "epoch": 0.45, - "learning_rate": 2.7533555535537344e-05, - "loss": 0.2456, + "epoch": 0.11, + "learning_rate": 4.442070647189101e-05, + "loss": 0.2607, "step": 50900 }, { - "epoch": 0.45, - "learning_rate": 2.7529051436807494e-05, - "loss": 0.2426, + "epoch": 0.11, + "learning_rate": 4.441958792868169e-05, + "loss": 0.2551, "step": 50910 }, { - "epoch": 0.45, - "learning_rate": 2.752454733807765e-05, - "loss": 0.2416, + "epoch": 0.11, + "learning_rate": 4.441846938547236e-05, + "loss": 0.2578, "step": 50920 }, { - "epoch": 0.45, - "learning_rate": 2.752004323934781e-05, - "loss": 0.2484, + "epoch": 0.11, + "learning_rate": 4.4417350842263036e-05, + "loss": 0.2564, "step": 50930 }, { - "epoch": 0.45, - "learning_rate": 2.7515539140617963e-05, - "loss": 0.2399, + "epoch": 0.11, + "learning_rate": 4.4416232299053714e-05, + "loss": 0.2599, "step": 50940 }, { - "epoch": 0.45, - "learning_rate": 2.7511035041888117e-05, - "loss": 0.2432, + "epoch": 0.11, + "learning_rate": 4.441511375584439e-05, + "loss": 0.2549, "step": 50950 }, { - "epoch": 0.45, - "learning_rate": 2.7506530943158275e-05, - "loss": 0.2501, + "epoch": 0.11, + "learning_rate": 4.441399521263507e-05, + "loss": 0.257, "step": 50960 }, { - "epoch": 0.46, - "learning_rate": 2.750202684442843e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.441287666942574e-05, + "loss": 0.2546, "step": 50970 }, { - "epoch": 0.46, - "learning_rate": 2.749752274569859e-05, - "loss": 0.249, + "epoch": 0.11, + "learning_rate": 4.441175812621642e-05, + "loss": 0.2572, "step": 50980 }, { - "epoch": 0.46, - "learning_rate": 2.7493018646968744e-05, - "loss": 0.2444, + "epoch": 0.11, + "learning_rate": 4.441063958300709e-05, + "loss": 0.2606, "step": 50990 }, { - "epoch": 0.46, - "learning_rate": 2.7488514548238898e-05, - "loss": 0.2453, + "epoch": 0.11, + "learning_rate": 4.440952103979777e-05, + "loss": 0.2586, "step": 51000 }, { - "epoch": 0.46, - "learning_rate": 2.7484010449509056e-05, - "loss": 0.247, + "epoch": 0.11, + "learning_rate": 4.4408402496588446e-05, + "loss": 0.2578, "step": 51010 }, { - "epoch": 0.46, - "learning_rate": 2.747950635077921e-05, - "loss": 0.2405, + "epoch": 0.11, + "learning_rate": 4.440728395337912e-05, + "loss": 0.2563, "step": 51020 }, { - "epoch": 0.46, - "learning_rate": 2.7475002252049364e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.4406165410169795e-05, + "loss": 0.2558, "step": 51030 }, { - "epoch": 0.46, - "learning_rate": 2.7470498153319525e-05, - "loss": 0.2432, + "epoch": 0.11, + "learning_rate": 4.440504686696047e-05, + "loss": 0.2582, "step": 51040 }, { - "epoch": 0.46, - "learning_rate": 2.746599405458968e-05, - "loss": 0.2495, + "epoch": 0.11, + "learning_rate": 4.440392832375115e-05, + "loss": 0.2642, "step": 51050 }, { - "epoch": 0.46, - "learning_rate": 2.7461489955859833e-05, - "loss": 0.2486, + "epoch": 0.11, + "learning_rate": 4.440280978054183e-05, + "loss": 0.2587, "step": 51060 }, { - "epoch": 0.46, - "learning_rate": 2.745698585712999e-05, - "loss": 0.2452, + "epoch": 0.11, + "learning_rate": 4.44016912373325e-05, + "loss": 0.2558, "step": 51070 }, { - "epoch": 0.46, - "learning_rate": 2.7452481758400145e-05, - "loss": 0.2474, + "epoch": 0.11, + "learning_rate": 4.440057269412318e-05, + "loss": 0.2556, "step": 51080 }, { - "epoch": 0.46, - "learning_rate": 2.74479776596703e-05, - "loss": 0.2403, + "epoch": 0.11, + "learning_rate": 4.439945415091385e-05, + "loss": 0.2552, "step": 51090 }, { - "epoch": 0.46, - "learning_rate": 2.744347356094046e-05, - "loss": 0.2465, + "epoch": 0.11, + "learning_rate": 4.439833560770453e-05, + "loss": 0.2585, "step": 51100 }, { - "epoch": 0.46, - "learning_rate": 2.743896946221061e-05, - "loss": 0.241, + "epoch": 0.11, + "learning_rate": 4.4397217064495205e-05, + "loss": 0.2682, "step": 51110 }, { - "epoch": 0.46, - "learning_rate": 2.743446536348077e-05, - "loss": 0.2488, + "epoch": 0.11, + "learning_rate": 4.4396098521285876e-05, + "loss": 0.2564, "step": 51120 }, { - "epoch": 0.46, - "learning_rate": 2.7429961264750925e-05, - "loss": 0.2397, + "epoch": 0.11, + "learning_rate": 4.4394979978076554e-05, + "loss": 0.257, "step": 51130 }, { - "epoch": 0.46, - "learning_rate": 2.742545716602108e-05, - "loss": 0.2445, + "epoch": 0.11, + "learning_rate": 4.439386143486723e-05, + "loss": 0.2592, "step": 51140 }, { - "epoch": 0.46, - "learning_rate": 2.7420953067291237e-05, - "loss": 0.2415, + "epoch": 0.11, + "learning_rate": 4.439274289165791e-05, + "loss": 0.262, "step": 51150 }, { - "epoch": 0.46, - "learning_rate": 2.741644896856139e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.439162434844859e-05, + "loss": 0.2623, "step": 51160 }, { - "epoch": 0.46, - "learning_rate": 2.7411944869831545e-05, - "loss": 0.2437, + "epoch": 0.11, + "learning_rate": 4.439050580523926e-05, + "loss": 0.2585, "step": 51170 }, { - "epoch": 0.46, - "learning_rate": 2.7407440771101706e-05, - "loss": 0.2449, + "epoch": 0.11, + "learning_rate": 4.438938726202994e-05, + "loss": 0.2598, "step": 51180 }, { - "epoch": 0.46, - "learning_rate": 2.740293667237186e-05, - "loss": 0.2367, + "epoch": 0.11, + "learning_rate": 4.438826871882061e-05, + "loss": 0.2563, "step": 51190 }, { - "epoch": 0.46, - "learning_rate": 2.7398432573642014e-05, - "loss": 0.2452, + "epoch": 0.11, + "learning_rate": 4.4387150175611286e-05, + "loss": 0.2549, "step": 51200 }, { - "epoch": 0.46, - "learning_rate": 2.739392847491217e-05, - "loss": 0.2403, + "epoch": 0.11, + "learning_rate": 4.4386031632401964e-05, + "loss": 0.2547, "step": 51210 }, { - "epoch": 0.46, - "learning_rate": 2.7389424376182326e-05, - "loss": 0.2521, + "epoch": 0.11, + "learning_rate": 4.4384913089192635e-05, + "loss": 0.2573, "step": 51220 }, { - "epoch": 0.46, - "learning_rate": 2.738492027745248e-05, - "loss": 0.2469, + "epoch": 0.11, + "learning_rate": 4.438379454598331e-05, + "loss": 0.2557, "step": 51230 }, { - "epoch": 0.46, - "learning_rate": 2.738041617872264e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.4382676002773984e-05, + "loss": 0.254, "step": 51240 }, { - "epoch": 0.46, - "learning_rate": 2.7375912079992795e-05, - "loss": 0.2464, + "epoch": 0.11, + "learning_rate": 4.438155745956466e-05, + "loss": 0.2558, "step": 51250 }, { - "epoch": 0.46, - "learning_rate": 2.7371407981262952e-05, - "loss": 0.2476, + "epoch": 0.11, + "learning_rate": 4.438043891635535e-05, + "loss": 0.2586, "step": 51260 }, { - "epoch": 0.46, - "learning_rate": 2.7366903882533106e-05, - "loss": 0.2412, + "epoch": 0.11, + "learning_rate": 4.437932037314602e-05, + "loss": 0.2592, "step": 51270 }, { - "epoch": 0.46, - "learning_rate": 2.736239978380326e-05, - "loss": 0.2434, + "epoch": 0.11, + "learning_rate": 4.4378201829936696e-05, + "loss": 0.252, "step": 51280 }, { - "epoch": 0.46, - "learning_rate": 2.735789568507342e-05, - "loss": 0.2406, + "epoch": 0.11, + "learning_rate": 4.437708328672737e-05, + "loss": 0.2624, "step": 51290 }, { - "epoch": 0.46, - "learning_rate": 2.7353391586343576e-05, - "loss": 0.2401, + "epoch": 0.11, + "learning_rate": 4.4375964743518045e-05, + "loss": 0.2593, "step": 51300 }, { - "epoch": 0.46, - "learning_rate": 2.734888748761373e-05, - "loss": 0.2408, + "epoch": 0.11, + "learning_rate": 4.4374846200308716e-05, + "loss": 0.2586, "step": 51310 }, { - "epoch": 0.46, - "learning_rate": 2.7344383388883887e-05, - "loss": 0.2446, + "epoch": 0.11, + "learning_rate": 4.4373727657099394e-05, + "loss": 0.2614, "step": 51320 }, { - "epoch": 0.46, - "learning_rate": 2.733987929015404e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.437260911389007e-05, + "loss": 0.2574, "step": 51330 }, { - "epoch": 0.46, - "learning_rate": 2.7335375191424195e-05, - "loss": 0.2401, + "epoch": 0.11, + "learning_rate": 4.437149057068074e-05, + "loss": 0.2587, "step": 51340 }, { - "epoch": 0.46, - "learning_rate": 2.7330871092694356e-05, - "loss": 0.2444, + "epoch": 0.11, + "learning_rate": 4.437037202747142e-05, + "loss": 0.2587, "step": 51350 }, { - "epoch": 0.46, - "learning_rate": 2.7326366993964507e-05, - "loss": 0.2416, + "epoch": 0.11, + "learning_rate": 4.43692534842621e-05, + "loss": 0.2568, "step": 51360 }, { - "epoch": 0.46, - "learning_rate": 2.732186289523466e-05, - "loss": 0.2422, + "epoch": 0.11, + "learning_rate": 4.436813494105278e-05, + "loss": 0.2592, "step": 51370 }, { - "epoch": 0.46, - "learning_rate": 2.7317358796504822e-05, - "loss": 0.2438, + "epoch": 0.11, + "learning_rate": 4.4367016397843455e-05, + "loss": 0.2518, "step": 51380 }, { - "epoch": 0.46, - "learning_rate": 2.7312854697774976e-05, - "loss": 0.2453, + "epoch": 0.11, + "learning_rate": 4.4365897854634126e-05, + "loss": 0.2582, "step": 51390 }, { - "epoch": 0.46, - "learning_rate": 2.7308350599045133e-05, - "loss": 0.2395, + "epoch": 0.11, + "learning_rate": 4.4364779311424804e-05, + "loss": 0.258, "step": 51400 }, { - "epoch": 0.46, - "learning_rate": 2.7303846500315288e-05, - "loss": 0.2347, + "epoch": 0.11, + "learning_rate": 4.4363660768215475e-05, + "loss": 0.2549, "step": 51410 }, { - "epoch": 0.46, - "learning_rate": 2.7299342401585442e-05, - "loss": 0.2424, + "epoch": 0.11, + "learning_rate": 4.436254222500615e-05, + "loss": 0.2585, "step": 51420 }, { - "epoch": 0.46, - "learning_rate": 2.7294838302855603e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.436142368179683e-05, + "loss": 0.2568, "step": 51430 }, { - "epoch": 0.46, - "learning_rate": 2.7290334204125757e-05, - "loss": 0.243, + "epoch": 0.11, + "learning_rate": 4.43603051385875e-05, + "loss": 0.2605, "step": 51440 }, { - "epoch": 0.46, - "learning_rate": 2.728583010539591e-05, - "loss": 0.2458, + "epoch": 0.11, + "learning_rate": 4.435918659537818e-05, + "loss": 0.2539, "step": 51450 }, { - "epoch": 0.46, - "learning_rate": 2.7281326006666068e-05, - "loss": 0.241, + "epoch": 0.11, + "learning_rate": 4.435806805216886e-05, + "loss": 0.2603, "step": 51460 }, { - "epoch": 0.46, - "learning_rate": 2.7276821907936222e-05, - "loss": 0.2434, + "epoch": 0.11, + "learning_rate": 4.4356949508959536e-05, + "loss": 0.2538, "step": 51470 }, { - "epoch": 0.46, - "learning_rate": 2.7272317809206376e-05, - "loss": 0.2508, + "epoch": 0.11, + "learning_rate": 4.4355830965750214e-05, + "loss": 0.2612, "step": 51480 }, { - "epoch": 0.46, - "learning_rate": 2.7267813710476537e-05, - "loss": 0.2492, + "epoch": 0.11, + "learning_rate": 4.4354712422540885e-05, + "loss": 0.2632, "step": 51490 }, { - "epoch": 0.46, - "learning_rate": 2.726330961174669e-05, - "loss": 0.2409, + "epoch": 0.11, + "learning_rate": 4.435359387933156e-05, + "loss": 0.2543, "step": 51500 }, { - "epoch": 0.46, - "learning_rate": 2.7258805513016846e-05, - "loss": 0.2423, + "epoch": 0.11, + "learning_rate": 4.4352475336122234e-05, + "loss": 0.2558, "step": 51510 }, { - "epoch": 0.46, - "learning_rate": 2.7254301414287003e-05, - "loss": 0.2388, + "epoch": 0.11, + "learning_rate": 4.435135679291291e-05, + "loss": 0.2583, "step": 51520 }, { - "epoch": 0.46, - "learning_rate": 2.7249797315557157e-05, - "loss": 0.2462, + "epoch": 0.12, + "learning_rate": 4.435023824970359e-05, + "loss": 0.2558, "step": 51530 }, { - "epoch": 0.46, - "learning_rate": 2.7245293216827318e-05, - "loss": 0.2446, + "epoch": 0.12, + "learning_rate": 4.434911970649426e-05, + "loss": 0.2592, "step": 51540 }, { - "epoch": 0.46, - "learning_rate": 2.7240789118097472e-05, - "loss": 0.2399, + "epoch": 0.12, + "learning_rate": 4.434800116328494e-05, + "loss": 0.2542, "step": 51550 }, { - "epoch": 0.46, - "learning_rate": 2.7236285019367623e-05, - "loss": 0.2433, + "epoch": 0.12, + "learning_rate": 4.434688262007562e-05, + "loss": 0.2565, "step": 51560 }, { - "epoch": 0.46, - "learning_rate": 2.7231780920637784e-05, - "loss": 0.2428, + "epoch": 0.12, + "learning_rate": 4.4345764076866295e-05, + "loss": 0.2552, "step": 51570 }, { - "epoch": 0.46, - "learning_rate": 2.7227276821907938e-05, - "loss": 0.2425, + "epoch": 0.12, + "learning_rate": 4.434464553365697e-05, + "loss": 0.2576, "step": 51580 }, { - "epoch": 0.46, - "learning_rate": 2.7222772723178092e-05, - "loss": 0.2419, + "epoch": 0.12, + "learning_rate": 4.4343526990447644e-05, + "loss": 0.2573, "step": 51590 }, { - "epoch": 0.46, - "learning_rate": 2.721826862444825e-05, - "loss": 0.2465, + "epoch": 0.12, + "learning_rate": 4.434240844723832e-05, + "loss": 0.2578, "step": 51600 }, { - "epoch": 0.46, - "learning_rate": 2.7213764525718404e-05, - "loss": 0.2437, + "epoch": 0.12, + "learning_rate": 4.434128990402899e-05, + "loss": 0.2515, "step": 51610 }, { - "epoch": 0.46, - "learning_rate": 2.7209260426988558e-05, - "loss": 0.2435, + "epoch": 0.12, + "learning_rate": 4.434017136081967e-05, + "loss": 0.2511, "step": 51620 }, { - "epoch": 0.46, - "learning_rate": 2.720475632825872e-05, - "loss": 0.2439, + "epoch": 0.12, + "learning_rate": 4.433905281761034e-05, + "loss": 0.2571, "step": 51630 }, { - "epoch": 0.46, - "learning_rate": 2.7200252229528873e-05, - "loss": 0.2453, + "epoch": 0.12, + "learning_rate": 4.433793427440102e-05, + "loss": 0.255, "step": 51640 }, { - "epoch": 0.46, - "learning_rate": 2.7195748130799027e-05, - "loss": 0.2427, + "epoch": 0.12, + "learning_rate": 4.43368157311917e-05, + "loss": 0.2526, "step": 51650 }, { - "epoch": 0.46, - "learning_rate": 2.7191244032069184e-05, - "loss": 0.2422, + "epoch": 0.12, + "learning_rate": 4.433569718798237e-05, + "loss": 0.2536, "step": 51660 }, { - "epoch": 0.46, - "learning_rate": 2.718673993333934e-05, - "loss": 0.2465, + "epoch": 0.12, + "learning_rate": 4.4334578644773054e-05, + "loss": 0.2605, "step": 51670 }, { - "epoch": 0.46, - "learning_rate": 2.71822358346095e-05, - "loss": 0.247, + "epoch": 0.12, + "learning_rate": 4.4333460101563725e-05, + "loss": 0.2579, "step": 51680 }, { - "epoch": 0.46, - "learning_rate": 2.7177731735879653e-05, - "loss": 0.2462, + "epoch": 0.12, + "learning_rate": 4.43323415583544e-05, + "loss": 0.2597, "step": 51690 }, { - "epoch": 0.46, - "learning_rate": 2.7173227637149807e-05, - "loss": 0.2411, + "epoch": 0.12, + "learning_rate": 4.433122301514508e-05, + "loss": 0.255, "step": 51700 }, { - "epoch": 0.46, - "learning_rate": 2.7168723538419965e-05, - "loss": 0.2443, + "epoch": 0.12, + "learning_rate": 4.433010447193575e-05, + "loss": 0.2593, "step": 51710 }, { - "epoch": 0.46, - "learning_rate": 2.716421943969012e-05, - "loss": 0.2476, + "epoch": 0.12, + "learning_rate": 4.432898592872643e-05, + "loss": 0.2508, "step": 51720 }, { - "epoch": 0.46, - "learning_rate": 2.7159715340960273e-05, - "loss": 0.2405, + "epoch": 0.12, + "learning_rate": 4.43278673855171e-05, + "loss": 0.2547, "step": 51730 }, { - "epoch": 0.46, - "learning_rate": 2.7155211242230434e-05, - "loss": 0.2377, + "epoch": 0.12, + "learning_rate": 4.432674884230778e-05, + "loss": 0.2564, "step": 51740 }, { - "epoch": 0.46, - "learning_rate": 2.7150707143500588e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.432563029909846e-05, + "loss": 0.2575, "step": 51750 }, { - "epoch": 0.46, - "learning_rate": 2.714620304477074e-05, - "loss": 0.2404, + "epoch": 0.12, + "learning_rate": 4.432451175588913e-05, + "loss": 0.2567, "step": 51760 }, { - "epoch": 0.46, - "learning_rate": 2.71416989460409e-05, - "loss": 0.2466, + "epoch": 0.12, + "learning_rate": 4.4323393212679806e-05, + "loss": 0.249, "step": 51770 }, { - "epoch": 0.46, - "learning_rate": 2.7137194847311054e-05, - "loss": 0.243, + "epoch": 0.12, + "learning_rate": 4.4322274669470484e-05, + "loss": 0.2555, "step": 51780 }, { - "epoch": 0.46, - "learning_rate": 2.7132690748581208e-05, - "loss": 0.2433, + "epoch": 0.12, + "learning_rate": 4.432115612626116e-05, + "loss": 0.2539, "step": 51790 }, { - "epoch": 0.46, - "learning_rate": 2.7128186649851365e-05, - "loss": 0.2459, + "epoch": 0.12, + "learning_rate": 4.432003758305184e-05, + "loss": 0.2616, "step": 51800 }, { - "epoch": 0.46, - "learning_rate": 2.712368255112152e-05, - "loss": 0.2355, + "epoch": 0.12, + "learning_rate": 4.431891903984251e-05, + "loss": 0.2525, "step": 51810 }, { - "epoch": 0.46, - "learning_rate": 2.711917845239168e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.431780049663319e-05, + "loss": 0.256, "step": 51820 }, { - "epoch": 0.46, - "learning_rate": 2.7114674353661835e-05, - "loss": 0.24, + "epoch": 0.12, + "learning_rate": 4.431668195342386e-05, + "loss": 0.2541, "step": 51830 }, { - "epoch": 0.46, - "learning_rate": 2.711017025493199e-05, - "loss": 0.2431, + "epoch": 0.12, + "learning_rate": 4.431556341021454e-05, + "loss": 0.2582, "step": 51840 }, { - "epoch": 0.46, - "learning_rate": 2.710611656607513e-05, - "loss": 0.24, + "epoch": 0.12, + "learning_rate": 4.4314444867005216e-05, + "loss": 0.2559, "step": 51850 }, { - "epoch": 0.46, - "learning_rate": 2.7101612467345283e-05, - "loss": 0.2368, + "epoch": 0.12, + "learning_rate": 4.431332632379589e-05, + "loss": 0.2516, "step": 51860 }, { - "epoch": 0.46, - "learning_rate": 2.7097108368615444e-05, - "loss": 0.2381, + "epoch": 0.12, + "learning_rate": 4.4312207780586565e-05, + "loss": 0.2528, "step": 51870 }, { - "epoch": 0.46, - "learning_rate": 2.7092604269885598e-05, - "loss": 0.2394, + "epoch": 0.12, + "learning_rate": 4.431108923737724e-05, + "loss": 0.2532, "step": 51880 }, { - "epoch": 0.46, - "learning_rate": 2.708810017115575e-05, - "loss": 0.2418, + "epoch": 0.12, + "learning_rate": 4.430997069416792e-05, + "loss": 0.2614, "step": 51890 }, { - "epoch": 0.46, - "learning_rate": 2.708359607242591e-05, - "loss": 0.244, + "epoch": 0.12, + "learning_rate": 4.43088521509586e-05, + "loss": 0.2568, "step": 51900 }, { - "epoch": 0.46, - "learning_rate": 2.7079091973696064e-05, - "loss": 0.2421, + "epoch": 0.12, + "learning_rate": 4.430773360774927e-05, + "loss": 0.2584, "step": 51910 }, { - "epoch": 0.46, - "learning_rate": 2.707458787496622e-05, - "loss": 0.2454, + "epoch": 0.12, + "learning_rate": 4.430661506453995e-05, + "loss": 0.2567, "step": 51920 }, { - "epoch": 0.46, - "learning_rate": 2.7070083776236375e-05, - "loss": 0.2426, + "epoch": 0.12, + "learning_rate": 4.430549652133062e-05, + "loss": 0.2518, "step": 51930 }, { - "epoch": 0.46, - "learning_rate": 2.706557967750653e-05, - "loss": 0.2381, + "epoch": 0.12, + "learning_rate": 4.43043779781213e-05, + "loss": 0.2544, "step": 51940 }, { - "epoch": 0.46, - "learning_rate": 2.706107557877669e-05, - "loss": 0.2409, + "epoch": 0.12, + "learning_rate": 4.430325943491197e-05, + "loss": 0.2545, "step": 51950 }, { - "epoch": 0.46, - "learning_rate": 2.7056571480046844e-05, - "loss": 0.2405, + "epoch": 0.12, + "learning_rate": 4.4302140891702646e-05, + "loss": 0.2542, "step": 51960 }, { - "epoch": 0.46, - "learning_rate": 2.7052067381317e-05, - "loss": 0.245, + "epoch": 0.12, + "learning_rate": 4.4301022348493324e-05, + "loss": 0.252, "step": 51970 }, { - "epoch": 0.46, - "learning_rate": 2.7047563282587156e-05, - "loss": 0.2381, + "epoch": 0.12, + "learning_rate": 4.4299903805284e-05, + "loss": 0.2567, "step": 51980 }, { - "epoch": 0.46, - "learning_rate": 2.704305918385731e-05, - "loss": 0.2478, + "epoch": 0.12, + "learning_rate": 4.429878526207468e-05, + "loss": 0.2522, "step": 51990 }, { - "epoch": 0.46, - "learning_rate": 2.7038555085127464e-05, - "loss": 0.2339, + "epoch": 0.12, + "learning_rate": 4.429766671886535e-05, + "loss": 0.2561, "step": 52000 }, { - "epoch": 0.46, - "learning_rate": 2.7034050986397625e-05, - "loss": 0.2419, + "epoch": 0.12, + "learning_rate": 4.429654817565603e-05, + "loss": 0.2554, "step": 52010 }, { - "epoch": 0.46, - "learning_rate": 2.702954688766778e-05, - "loss": 0.2456, + "epoch": 0.12, + "learning_rate": 4.429542963244671e-05, + "loss": 0.256, "step": 52020 }, { - "epoch": 0.46, - "learning_rate": 2.7025042788937933e-05, - "loss": 0.2426, + "epoch": 0.12, + "learning_rate": 4.429431108923738e-05, + "loss": 0.2583, "step": 52030 }, { - "epoch": 0.46, - "learning_rate": 2.702053869020809e-05, - "loss": 0.2412, + "epoch": 0.12, + "learning_rate": 4.4293192546028056e-05, + "loss": 0.2612, "step": 52040 }, { - "epoch": 0.46, - "learning_rate": 2.7016034591478245e-05, - "loss": 0.2371, + "epoch": 0.12, + "learning_rate": 4.429207400281873e-05, + "loss": 0.2578, "step": 52050 }, { - "epoch": 0.46, - "learning_rate": 2.7011530492748406e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.4290955459609405e-05, + "loss": 0.2535, "step": 52060 }, { - "epoch": 0.46, - "learning_rate": 2.700702639401856e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.428983691640008e-05, + "loss": 0.255, "step": 52070 }, { - "epoch": 0.46, - "learning_rate": 2.7002522295288714e-05, - "loss": 0.248, + "epoch": 0.12, + "learning_rate": 4.4288718373190754e-05, + "loss": 0.2529, "step": 52080 }, { - "epoch": 0.47, - "learning_rate": 2.699801819655887e-05, - "loss": 0.2432, + "epoch": 0.12, + "learning_rate": 4.428759982998144e-05, + "loss": 0.2666, "step": 52090 }, { - "epoch": 0.47, - "learning_rate": 2.6993514097829026e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.428648128677211e-05, + "loss": 0.2536, "step": 52100 }, { - "epoch": 0.47, - "learning_rate": 2.698900999909918e-05, - "loss": 0.2392, + "epoch": 0.12, + "learning_rate": 4.428536274356279e-05, + "loss": 0.2514, "step": 52110 }, { - "epoch": 0.47, - "learning_rate": 2.698450590036934e-05, - "loss": 0.2418, + "epoch": 0.12, + "learning_rate": 4.4284244200353466e-05, + "loss": 0.261, "step": 52120 }, { - "epoch": 0.47, - "learning_rate": 2.698000180163949e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.428312565714414e-05, + "loss": 0.2561, "step": 52130 }, { - "epoch": 0.47, - "learning_rate": 2.6975497702909645e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.4282007113934815e-05, + "loss": 0.2561, "step": 52140 }, { - "epoch": 0.47, - "learning_rate": 2.6970993604179806e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.4280888570725486e-05, + "loss": 0.261, "step": 52150 }, { - "epoch": 0.47, - "learning_rate": 2.696648950544996e-05, - "loss": 0.2391, + "epoch": 0.12, + "learning_rate": 4.4279770027516164e-05, + "loss": 0.2548, "step": 52160 }, { - "epoch": 0.47, - "learning_rate": 2.6961985406720115e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.427865148430684e-05, + "loss": 0.2579, "step": 52170 }, { - "epoch": 0.47, - "learning_rate": 2.6957481307990272e-05, - "loss": 0.2472, + "epoch": 0.12, + "learning_rate": 4.427753294109751e-05, + "loss": 0.2555, "step": 52180 }, { - "epoch": 0.47, - "learning_rate": 2.6952977209260426e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.427641439788819e-05, + "loss": 0.2579, "step": 52190 }, { - "epoch": 0.47, - "learning_rate": 2.6948473110530587e-05, - "loss": 0.2486, + "epoch": 0.12, + "learning_rate": 4.427529585467887e-05, + "loss": 0.2537, "step": 52200 }, { - "epoch": 0.47, - "learning_rate": 2.694396901180074e-05, - "loss": 0.2429, + "epoch": 0.12, + "learning_rate": 4.427417731146955e-05, + "loss": 0.2581, "step": 52210 }, { - "epoch": 0.47, - "learning_rate": 2.6939464913070895e-05, - "loss": 0.2471, + "epoch": 0.12, + "learning_rate": 4.4273058768260225e-05, + "loss": 0.2615, "step": 52220 }, { - "epoch": 0.47, - "learning_rate": 2.6934960814341053e-05, - "loss": 0.2425, + "epoch": 0.12, + "learning_rate": 4.4271940225050896e-05, + "loss": 0.2564, "step": 52230 }, { - "epoch": 0.47, - "learning_rate": 2.6930456715611207e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.4270821681841574e-05, + "loss": 0.255, "step": 52240 }, { - "epoch": 0.47, - "learning_rate": 2.692595261688136e-05, - "loss": 0.2374, + "epoch": 0.12, + "learning_rate": 4.4269703138632245e-05, + "loss": 0.2574, "step": 52250 }, { - "epoch": 0.47, - "learning_rate": 2.6921448518151522e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.426858459542292e-05, + "loss": 0.2569, "step": 52260 }, { - "epoch": 0.47, - "learning_rate": 2.6916944419421676e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.4267466052213594e-05, + "loss": 0.2571, "step": 52270 }, { - "epoch": 0.47, - "learning_rate": 2.691244032069183e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.426634750900427e-05, + "loss": 0.2618, "step": 52280 }, { - "epoch": 0.47, - "learning_rate": 2.6907936221961988e-05, - "loss": 0.2494, + "epoch": 0.12, + "learning_rate": 4.426522896579495e-05, + "loss": 0.2602, "step": 52290 }, { - "epoch": 0.47, - "learning_rate": 2.690343212323214e-05, - "loss": 0.2435, + "epoch": 0.12, + "learning_rate": 4.426411042258563e-05, + "loss": 0.2545, "step": 52300 }, { - "epoch": 0.47, - "learning_rate": 2.6898928024502296e-05, - "loss": 0.2406, + "epoch": 0.12, + "learning_rate": 4.4262991879376306e-05, + "loss": 0.2555, "step": 52310 }, { - "epoch": 0.47, - "learning_rate": 2.6894423925772457e-05, - "loss": 0.2458, + "epoch": 0.12, + "learning_rate": 4.426187333616698e-05, + "loss": 0.2576, "step": 52320 }, { - "epoch": 0.47, - "learning_rate": 2.6889919827042607e-05, - "loss": 0.2377, + "epoch": 0.12, + "learning_rate": 4.4260754792957655e-05, + "loss": 0.2557, "step": 52330 }, { - "epoch": 0.47, - "learning_rate": 2.6885415728312768e-05, - "loss": 0.2406, + "epoch": 0.12, + "learning_rate": 4.425963624974833e-05, + "loss": 0.2541, "step": 52340 }, { - "epoch": 0.47, - "learning_rate": 2.6880911629582922e-05, - "loss": 0.2359, + "epoch": 0.12, + "learning_rate": 4.4258517706539004e-05, + "loss": 0.2523, "step": 52350 }, { - "epoch": 0.47, - "learning_rate": 2.6876407530853076e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.425739916332968e-05, + "loss": 0.2564, "step": 52360 }, { - "epoch": 0.47, - "learning_rate": 2.6871903432123234e-05, - "loss": 0.2432, + "epoch": 0.12, + "learning_rate": 4.425628062012035e-05, + "loss": 0.2521, "step": 52370 }, { - "epoch": 0.47, - "learning_rate": 2.6867399333393388e-05, - "loss": 0.2434, + "epoch": 0.12, + "learning_rate": 4.425516207691103e-05, + "loss": 0.2555, "step": 52380 }, { - "epoch": 0.47, - "learning_rate": 2.6862895234663542e-05, - "loss": 0.2509, + "epoch": 0.12, + "learning_rate": 4.425404353370171e-05, + "loss": 0.2515, "step": 52390 }, { - "epoch": 0.47, - "learning_rate": 2.6858391135933703e-05, - "loss": 0.2428, + "epoch": 0.12, + "learning_rate": 4.425292499049239e-05, + "loss": 0.2553, "step": 52400 }, { - "epoch": 0.47, - "learning_rate": 2.6853887037203857e-05, - "loss": 0.2395, + "epoch": 0.12, + "learning_rate": 4.4251806447283065e-05, + "loss": 0.2552, "step": 52410 }, { - "epoch": 0.47, - "learning_rate": 2.684938293847401e-05, - "loss": 0.2457, + "epoch": 0.12, + "learning_rate": 4.4250687904073736e-05, + "loss": 0.2521, "step": 52420 }, { - "epoch": 0.47, - "learning_rate": 2.684487883974417e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.4249569360864414e-05, + "loss": 0.2557, "step": 52430 }, { - "epoch": 0.47, - "learning_rate": 2.6840374741014323e-05, - "loss": 0.2429, + "epoch": 0.12, + "learning_rate": 4.424845081765509e-05, + "loss": 0.2513, "step": 52440 }, { - "epoch": 0.47, - "learning_rate": 2.6835870642284477e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.424733227444576e-05, + "loss": 0.2525, "step": 52450 }, { - "epoch": 0.47, - "learning_rate": 2.6831366543554638e-05, - "loss": 0.2398, + "epoch": 0.12, + "learning_rate": 4.424621373123644e-05, + "loss": 0.2598, "step": 52460 }, { - "epoch": 0.47, - "learning_rate": 2.6826862444824792e-05, - "loss": 0.2405, + "epoch": 0.12, + "learning_rate": 4.424509518802711e-05, + "loss": 0.2516, "step": 52470 }, { - "epoch": 0.47, - "learning_rate": 2.682235834609495e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.424397664481779e-05, + "loss": 0.2526, "step": 52480 }, { - "epoch": 0.47, - "learning_rate": 2.6817854247365103e-05, - "loss": 0.2473, + "epoch": 0.12, + "learning_rate": 4.424285810160847e-05, + "loss": 0.2496, "step": 52490 }, { - "epoch": 0.47, - "learning_rate": 2.6813350148635258e-05, - "loss": 0.2394, + "epoch": 0.12, + "learning_rate": 4.4241739558399146e-05, + "loss": 0.254, "step": 52500 }, { - "epoch": 0.47, - "learning_rate": 2.680884604990542e-05, - "loss": 0.2329, + "epoch": 0.12, + "learning_rate": 4.4240621015189824e-05, + "loss": 0.2556, "step": 52510 }, { - "epoch": 0.47, - "learning_rate": 2.6804341951175573e-05, - "loss": 0.2362, + "epoch": 0.12, + "learning_rate": 4.4239502471980495e-05, + "loss": 0.2547, "step": 52520 }, { - "epoch": 0.47, - "learning_rate": 2.6799837852445727e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.423838392877117e-05, + "loss": 0.2558, "step": 52530 }, { - "epoch": 0.47, - "learning_rate": 2.6795333753715884e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.423726538556185e-05, + "loss": 0.2605, "step": 52540 }, { - "epoch": 0.47, - "learning_rate": 2.6790829654986038e-05, - "loss": 0.2346, + "epoch": 0.12, + "learning_rate": 4.423614684235252e-05, + "loss": 0.2578, "step": 52550 }, { - "epoch": 0.47, - "learning_rate": 2.6786325556256192e-05, - "loss": 0.2359, + "epoch": 0.12, + "learning_rate": 4.42350282991432e-05, + "loss": 0.2561, "step": 52560 }, { - "epoch": 0.47, - "learning_rate": 2.678182145752635e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.423390975593387e-05, + "loss": 0.2558, "step": 52570 }, { - "epoch": 0.47, - "learning_rate": 2.6777317358796504e-05, - "loss": 0.2322, + "epoch": 0.12, + "learning_rate": 4.423279121272455e-05, + "loss": 0.2557, "step": 52580 }, { - "epoch": 0.47, - "learning_rate": 2.6772813260066658e-05, - "loss": 0.2414, + "epoch": 0.12, + "learning_rate": 4.423167266951522e-05, + "loss": 0.2524, "step": 52590 }, { - "epoch": 0.47, - "learning_rate": 2.676830916133682e-05, - "loss": 0.2463, + "epoch": 0.12, + "learning_rate": 4.42305541263059e-05, + "loss": 0.2568, "step": 52600 }, { - "epoch": 0.47, - "learning_rate": 2.6763805062606973e-05, - "loss": 0.2449, + "epoch": 0.12, + "learning_rate": 4.4229435583096576e-05, + "loss": 0.2574, "step": 52610 }, { - "epoch": 0.47, - "learning_rate": 2.675930096387713e-05, - "loss": 0.2437, + "epoch": 0.12, + "learning_rate": 4.4228317039887254e-05, + "loss": 0.2502, "step": 52620 }, { - "epoch": 0.47, - "learning_rate": 2.6754796865147285e-05, - "loss": 0.244, + "epoch": 0.12, + "learning_rate": 4.422719849667793e-05, + "loss": 0.2536, "step": 52630 }, { - "epoch": 0.47, - "learning_rate": 2.675029276641744e-05, - "loss": 0.2445, + "epoch": 0.12, + "learning_rate": 4.42260799534686e-05, + "loss": 0.2532, "step": 52640 }, { - "epoch": 0.47, - "learning_rate": 2.67457886676876e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.422496141025928e-05, + "loss": 0.2582, "step": 52650 }, { - "epoch": 0.47, - "learning_rate": 2.6741284568957754e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.422384286704996e-05, + "loss": 0.2572, "step": 52660 }, { - "epoch": 0.47, - "learning_rate": 2.6736780470227908e-05, - "loss": 0.2418, + "epoch": 0.12, + "learning_rate": 4.422272432384063e-05, + "loss": 0.2585, "step": 52670 }, { - "epoch": 0.47, - "learning_rate": 2.6732276371498065e-05, - "loss": 0.2407, + "epoch": 0.12, + "learning_rate": 4.422160578063131e-05, + "loss": 0.2496, "step": 52680 }, { - "epoch": 0.47, - "learning_rate": 2.672777227276822e-05, - "loss": 0.2385, + "epoch": 0.12, + "learning_rate": 4.422048723742198e-05, + "loss": 0.2595, "step": 52690 }, { - "epoch": 0.47, - "learning_rate": 2.6723268174038374e-05, - "loss": 0.2414, + "epoch": 0.12, + "learning_rate": 4.421936869421266e-05, + "loss": 0.2533, "step": 52700 }, { - "epoch": 0.47, - "learning_rate": 2.6718764075308534e-05, - "loss": 0.237, + "epoch": 0.12, + "learning_rate": 4.4218250151003335e-05, + "loss": 0.2516, "step": 52710 }, { - "epoch": 0.47, - "learning_rate": 2.671425997657869e-05, - "loss": 0.2405, + "epoch": 0.12, + "learning_rate": 4.421713160779401e-05, + "loss": 0.2522, "step": 52720 }, { - "epoch": 0.47, - "learning_rate": 2.6709755877848843e-05, - "loss": 0.2446, + "epoch": 0.12, + "learning_rate": 4.421601306458469e-05, + "loss": 0.2582, "step": 52730 }, { - "epoch": 0.47, - "learning_rate": 2.6705251779119e-05, - "loss": 0.2406, + "epoch": 0.12, + "learning_rate": 4.421489452137536e-05, + "loss": 0.2574, "step": 52740 }, { - "epoch": 0.47, - "learning_rate": 2.6700747680389154e-05, - "loss": 0.2391, + "epoch": 0.12, + "learning_rate": 4.421377597816604e-05, + "loss": 0.2576, "step": 52750 }, { - "epoch": 0.47, - "learning_rate": 2.6696243581659315e-05, - "loss": 0.2442, + "epoch": 0.12, + "learning_rate": 4.421265743495672e-05, + "loss": 0.2548, "step": 52760 }, { - "epoch": 0.47, - "learning_rate": 2.669173948292947e-05, - "loss": 0.244, + "epoch": 0.12, + "learning_rate": 4.421153889174739e-05, + "loss": 0.2575, "step": 52770 }, { - "epoch": 0.47, - "learning_rate": 2.668723538419962e-05, - "loss": 0.2453, + "epoch": 0.12, + "learning_rate": 4.421042034853807e-05, + "loss": 0.2632, "step": 52780 }, { - "epoch": 0.47, - "learning_rate": 2.668273128546978e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.420930180532874e-05, + "loss": 0.2586, "step": 52790 }, { - "epoch": 0.47, - "learning_rate": 2.6678227186739935e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.4208183262119416e-05, + "loss": 0.2593, "step": 52800 }, { - "epoch": 0.47, - "learning_rate": 2.667372308801009e-05, - "loss": 0.2474, + "epoch": 0.12, + "learning_rate": 4.4207064718910094e-05, + "loss": 0.258, "step": 52810 }, { - "epoch": 0.47, - "learning_rate": 2.6669218989280246e-05, - "loss": 0.2407, + "epoch": 0.12, + "learning_rate": 4.420594617570077e-05, + "loss": 0.2508, "step": 52820 }, { - "epoch": 0.47, - "learning_rate": 2.66647148905504e-05, - "loss": 0.238, + "epoch": 0.12, + "learning_rate": 4.420482763249145e-05, + "loss": 0.2512, "step": 52830 }, { - "epoch": 0.47, - "learning_rate": 2.6660210791820555e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.420370908928212e-05, + "loss": 0.2537, "step": 52840 }, { - "epoch": 0.47, - "learning_rate": 2.6655706693090716e-05, - "loss": 0.2447, + "epoch": 0.12, + "learning_rate": 4.42025905460728e-05, + "loss": 0.2612, "step": 52850 }, { - "epoch": 0.47, - "learning_rate": 2.665120259436087e-05, - "loss": 0.2407, + "epoch": 0.12, + "learning_rate": 4.4201472002863476e-05, + "loss": 0.2572, "step": 52860 }, { - "epoch": 0.47, - "learning_rate": 2.6646698495631024e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.420035345965415e-05, + "loss": 0.2522, "step": 52870 }, { - "epoch": 0.47, - "learning_rate": 2.664219439690118e-05, - "loss": 0.2363, + "epoch": 0.12, + "learning_rate": 4.4199234916444826e-05, + "loss": 0.2601, "step": 52880 }, { - "epoch": 0.47, - "learning_rate": 2.6637690298171335e-05, - "loss": 0.2319, + "epoch": 0.12, + "learning_rate": 4.41981163732355e-05, + "loss": 0.2642, "step": 52890 }, { - "epoch": 0.47, - "learning_rate": 2.6633186199441496e-05, - "loss": 0.2394, + "epoch": 0.12, + "learning_rate": 4.4196997830026175e-05, + "loss": 0.2552, "step": 52900 }, { - "epoch": 0.47, - "learning_rate": 2.662868210071165e-05, - "loss": 0.236, + "epoch": 0.12, + "learning_rate": 4.4195879286816846e-05, + "loss": 0.2526, "step": 52910 }, { - "epoch": 0.47, - "learning_rate": 2.6624178001981804e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.419476074360753e-05, + "loss": 0.2549, "step": 52920 }, { - "epoch": 0.47, - "learning_rate": 2.6619673903251962e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.419364220039821e-05, + "loss": 0.254, "step": 52930 }, { - "epoch": 0.47, - "learning_rate": 2.6615169804522116e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.419252365718888e-05, + "loss": 0.2563, "step": 52940 }, { - "epoch": 0.47, - "learning_rate": 2.661066570579227e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.419140511397956e-05, + "loss": 0.2544, "step": 52950 }, { - "epoch": 0.47, - "learning_rate": 2.660616160706243e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.419028657077023e-05, + "loss": 0.2545, "step": 52960 }, { - "epoch": 0.47, - "learning_rate": 2.6601657508332585e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.4189168027560907e-05, + "loss": 0.258, "step": 52970 }, { - "epoch": 0.47, - "learning_rate": 2.6597153409602736e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.4188049484351585e-05, + "loss": 0.254, "step": 52980 }, { - "epoch": 0.47, - "learning_rate": 2.6592649310872897e-05, - "loss": 0.2457, + "epoch": 0.12, + "learning_rate": 4.4186930941142256e-05, + "loss": 0.2573, "step": 52990 }, { - "epoch": 0.47, - "learning_rate": 2.658814521214305e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.4185812397932934e-05, + "loss": 0.2524, "step": 53000 }, { - "epoch": 0.47, - "learning_rate": 2.6583641113413205e-05, - "loss": 0.2412, + "epoch": 0.12, + "learning_rate": 4.4184693854723605e-05, + "loss": 0.2494, "step": 53010 }, { - "epoch": 0.47, - "learning_rate": 2.6579137014683362e-05, - "loss": 0.2464, + "epoch": 0.12, + "learning_rate": 4.418357531151428e-05, + "loss": 0.2536, "step": 53020 }, { - "epoch": 0.47, - "learning_rate": 2.6574632915953517e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.418245676830496e-05, + "loss": 0.2505, "step": 53030 }, { - "epoch": 0.47, - "learning_rate": 2.6570128817223677e-05, - "loss": 0.2419, + "epoch": 0.12, + "learning_rate": 4.418133822509564e-05, + "loss": 0.2597, "step": 53040 }, { - "epoch": 0.47, - "learning_rate": 2.656562471849383e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.4180219681886316e-05, + "loss": 0.25, "step": 53050 }, { - "epoch": 0.47, - "learning_rate": 2.6561120619763986e-05, - "loss": 0.2414, + "epoch": 0.12, + "learning_rate": 4.417910113867699e-05, + "loss": 0.251, "step": 53060 }, { - "epoch": 0.47, - "learning_rate": 2.6556616521034143e-05, - "loss": 0.2398, + "epoch": 0.12, + "learning_rate": 4.4177982595467666e-05, + "loss": 0.2522, "step": 53070 }, { - "epoch": 0.47, - "learning_rate": 2.6552112422304297e-05, - "loss": 0.2458, + "epoch": 0.12, + "learning_rate": 4.4176864052258343e-05, + "loss": 0.2606, "step": 53080 }, { - "epoch": 0.47, - "learning_rate": 2.654760832357445e-05, - "loss": 0.2368, + "epoch": 0.12, + "learning_rate": 4.4175745509049015e-05, + "loss": 0.2575, "step": 53090 }, { - "epoch": 0.47, - "learning_rate": 2.6543104224844612e-05, - "loss": 0.2364, + "epoch": 0.12, + "learning_rate": 4.417462696583969e-05, + "loss": 0.2558, "step": 53100 }, { - "epoch": 0.47, - "learning_rate": 2.6538600126114766e-05, - "loss": 0.2412, + "epoch": 0.12, + "learning_rate": 4.4173508422630364e-05, + "loss": 0.2518, "step": 53110 }, { - "epoch": 0.47, - "learning_rate": 2.653409602738492e-05, - "loss": 0.2432, + "epoch": 0.12, + "learning_rate": 4.417238987942104e-05, + "loss": 0.2574, "step": 53120 }, { - "epoch": 0.47, - "learning_rate": 2.6529591928655078e-05, - "loss": 0.2417, + "epoch": 0.12, + "learning_rate": 4.417127133621172e-05, + "loss": 0.2596, "step": 53130 }, { - "epoch": 0.47, - "learning_rate": 2.6525087829925232e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.41701527930024e-05, + "loss": 0.2602, "step": 53140 }, { - "epoch": 0.47, - "learning_rate": 2.6520583731195386e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.4169034249793075e-05, + "loss": 0.2544, "step": 53150 }, { - "epoch": 0.47, - "learning_rate": 2.6516079632465547e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.4167915706583747e-05, + "loss": 0.2578, "step": 53160 }, { - "epoch": 0.47, - "learning_rate": 2.65115755337357e-05, - "loss": 0.2395, + "epoch": 0.12, + "learning_rate": 4.4166797163374424e-05, + "loss": 0.2577, "step": 53170 }, { - "epoch": 0.47, - "learning_rate": 2.650707143500586e-05, - "loss": 0.2483, + "epoch": 0.12, + "learning_rate": 4.4165790474486026e-05, + "loss": 0.2501, "step": 53180 }, { - "epoch": 0.47, - "learning_rate": 2.6502567336276013e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.4164671931276704e-05, + "loss": 0.2506, "step": 53190 }, { - "epoch": 0.47, - "learning_rate": 2.6498063237546167e-05, - "loss": 0.2406, + "epoch": 0.12, + "learning_rate": 4.416355338806738e-05, + "loss": 0.2537, "step": 53200 }, { - "epoch": 0.48, - "learning_rate": 2.6493559138816328e-05, - "loss": 0.2421, + "epoch": 0.12, + "learning_rate": 4.416243484485806e-05, + "loss": 0.2507, "step": 53210 }, { - "epoch": 0.48, - "learning_rate": 2.648905504008648e-05, - "loss": 0.2358, + "epoch": 0.12, + "learning_rate": 4.416131630164874e-05, + "loss": 0.2559, "step": 53220 }, { - "epoch": 0.48, - "learning_rate": 2.6484550941356633e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.416019775843941e-05, + "loss": 0.2571, "step": 53230 }, { - "epoch": 0.48, - "learning_rate": 2.6480046842626793e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.415907921523009e-05, + "loss": 0.2609, "step": 53240 }, { - "epoch": 0.48, - "learning_rate": 2.6475542743896948e-05, - "loss": 0.2385, + "epoch": 0.12, + "learning_rate": 4.4157960672020765e-05, + "loss": 0.2534, "step": 53250 }, { - "epoch": 0.48, - "learning_rate": 2.64710386451671e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.4156842128811436e-05, + "loss": 0.253, "step": 53260 }, { - "epoch": 0.48, - "learning_rate": 2.646653454643726e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.4155723585602114e-05, + "loss": 0.2558, "step": 53270 }, { - "epoch": 0.48, - "learning_rate": 2.6462030447707413e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.4154605042392785e-05, + "loss": 0.256, "step": 53280 }, { - "epoch": 0.48, - "learning_rate": 2.6457526348977567e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.415348649918346e-05, + "loss": 0.2495, "step": 53290 }, { - "epoch": 0.48, - "learning_rate": 2.6453022250247728e-05, - "loss": 0.2391, + "epoch": 0.12, + "learning_rate": 4.415236795597414e-05, + "loss": 0.258, "step": 53300 }, { - "epoch": 0.48, - "learning_rate": 2.6448518151517882e-05, - "loss": 0.2362, + "epoch": 0.12, + "learning_rate": 4.415124941276482e-05, + "loss": 0.2589, "step": 53310 }, { - "epoch": 0.48, - "learning_rate": 2.644401405278804e-05, - "loss": 0.2385, + "epoch": 0.12, + "learning_rate": 4.41501308695555e-05, + "loss": 0.2584, "step": 53320 }, { - "epoch": 0.48, - "learning_rate": 2.6439509954058194e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.414901232634617e-05, + "loss": 0.2593, "step": 53330 }, { - "epoch": 0.48, - "learning_rate": 2.6435005855328348e-05, - "loss": 0.2372, + "epoch": 0.12, + "learning_rate": 4.4147893783136846e-05, + "loss": 0.2555, "step": 53340 }, { - "epoch": 0.48, - "learning_rate": 2.643050175659851e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.414677523992752e-05, + "loss": 0.2613, "step": 53350 }, { - "epoch": 0.48, - "learning_rate": 2.6425997657868663e-05, - "loss": 0.2415, + "epoch": 0.12, + "learning_rate": 4.4145656696718195e-05, + "loss": 0.2565, "step": 53360 }, { - "epoch": 0.48, - "learning_rate": 2.6421493559138817e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.414453815350887e-05, + "loss": 0.254, "step": 53370 }, { - "epoch": 0.48, - "learning_rate": 2.6416989460408975e-05, - "loss": 0.2364, + "epoch": 0.12, + "learning_rate": 4.4143419610299544e-05, + "loss": 0.2486, "step": 53380 }, { - "epoch": 0.48, - "learning_rate": 2.641248536167913e-05, - "loss": 0.2398, + "epoch": 0.12, + "learning_rate": 4.414230106709022e-05, + "loss": 0.2514, "step": 53390 }, { - "epoch": 0.48, - "learning_rate": 2.6407981262949283e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.41411825238809e-05, + "loss": 0.2541, "step": 53400 }, { - "epoch": 0.48, - "learning_rate": 2.6403477164219444e-05, - "loss": 0.2399, + "epoch": 0.12, + "learning_rate": 4.414006398067158e-05, + "loss": 0.2517, "step": 53410 }, { - "epoch": 0.48, - "learning_rate": 2.6398973065489598e-05, - "loss": 0.2363, + "epoch": 0.12, + "learning_rate": 4.4138945437462256e-05, + "loss": 0.2506, "step": 53420 }, { - "epoch": 0.48, - "learning_rate": 2.639446896675975e-05, - "loss": 0.2409, + "epoch": 0.12, + "learning_rate": 4.413782689425293e-05, + "loss": 0.2485, "step": 53430 }, { - "epoch": 0.48, - "learning_rate": 2.638996486802991e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.4136708351043605e-05, + "loss": 0.2586, "step": 53440 }, { - "epoch": 0.48, - "learning_rate": 2.6385460769300063e-05, - "loss": 0.2393, + "epoch": 0.12, + "learning_rate": 4.4135589807834276e-05, + "loss": 0.2567, "step": 53450 }, { - "epoch": 0.48, - "learning_rate": 2.6380956670570224e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.4134471264624954e-05, + "loss": 0.2524, "step": 53460 }, { - "epoch": 0.48, - "learning_rate": 2.6376452571840375e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.413335272141563e-05, + "loss": 0.2538, "step": 53470 }, { - "epoch": 0.48, - "learning_rate": 2.637194847311053e-05, - "loss": 0.2427, + "epoch": 0.12, + "learning_rate": 4.41322341782063e-05, + "loss": 0.2549, "step": 53480 }, { - "epoch": 0.48, - "learning_rate": 2.636744437438069e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.413111563499698e-05, + "loss": 0.2536, "step": 53490 }, { - "epoch": 0.48, - "learning_rate": 2.6362940275650844e-05, - "loss": 0.2414, + "epoch": 0.12, + "learning_rate": 4.412999709178766e-05, + "loss": 0.26, "step": 53500 }, { - "epoch": 0.48, - "learning_rate": 2.6358436176920998e-05, - "loss": 0.241, + "epoch": 0.12, + "learning_rate": 4.412887854857834e-05, + "loss": 0.2554, "step": 53510 }, { - "epoch": 0.48, - "learning_rate": 2.6353932078191156e-05, - "loss": 0.2348, + "epoch": 0.12, + "learning_rate": 4.4127760005369015e-05, + "loss": 0.2508, "step": 53520 }, { - "epoch": 0.48, - "learning_rate": 2.634942797946131e-05, - "loss": 0.2411, + "epoch": 0.12, + "learning_rate": 4.4126641462159686e-05, + "loss": 0.2559, "step": 53530 }, { - "epoch": 0.48, - "learning_rate": 2.6344923880731464e-05, - "loss": 0.2381, + "epoch": 0.12, + "learning_rate": 4.4125522918950364e-05, + "loss": 0.2523, "step": 53540 }, { - "epoch": 0.48, - "learning_rate": 2.6340419782001625e-05, - "loss": 0.2435, + "epoch": 0.12, + "learning_rate": 4.4124404375741035e-05, + "loss": 0.2515, "step": 53550 }, { - "epoch": 0.48, - "learning_rate": 2.633591568327178e-05, - "loss": 0.2419, + "epoch": 0.12, + "learning_rate": 4.412328583253171e-05, + "loss": 0.2567, "step": 53560 }, { - "epoch": 0.48, - "learning_rate": 2.6331411584541933e-05, - "loss": 0.2411, + "epoch": 0.12, + "learning_rate": 4.412216728932239e-05, + "loss": 0.257, "step": 53570 }, { - "epoch": 0.48, - "learning_rate": 2.632690748581209e-05, - "loss": 0.2421, + "epoch": 0.12, + "learning_rate": 4.412104874611306e-05, + "loss": 0.2589, "step": 53580 }, { - "epoch": 0.48, - "learning_rate": 2.6322403387082245e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.411993020290374e-05, + "loss": 0.2528, "step": 53590 }, { - "epoch": 0.48, - "learning_rate": 2.6317899288352406e-05, - "loss": 0.2437, + "epoch": 0.12, + "learning_rate": 4.411881165969441e-05, + "loss": 0.2529, "step": 53600 }, { - "epoch": 0.48, - "learning_rate": 2.631339518962256e-05, - "loss": 0.2424, + "epoch": 0.12, + "learning_rate": 4.411769311648509e-05, + "loss": 0.2524, "step": 53610 }, { - "epoch": 0.48, - "learning_rate": 2.6308891090892714e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.411657457327577e-05, + "loss": 0.2545, "step": 53620 }, { - "epoch": 0.48, - "learning_rate": 2.630438699216287e-05, - "loss": 0.2406, + "epoch": 0.12, + "learning_rate": 4.4115456030066445e-05, + "loss": 0.2491, "step": 53630 }, { - "epoch": 0.48, - "learning_rate": 2.6299882893433025e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.411433748685712e-05, + "loss": 0.2558, "step": 53640 }, { - "epoch": 0.48, - "learning_rate": 2.629537879470318e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.4113218943647794e-05, + "loss": 0.255, "step": 53650 }, { - "epoch": 0.48, - "learning_rate": 2.629087469597334e-05, - "loss": 0.2339, + "epoch": 0.12, + "learning_rate": 4.411210040043847e-05, + "loss": 0.2549, "step": 53660 }, { - "epoch": 0.48, - "learning_rate": 2.628637059724349e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.411098185722914e-05, + "loss": 0.2582, "step": 53670 }, { - "epoch": 0.48, - "learning_rate": 2.6281866498513645e-05, - "loss": 0.2374, + "epoch": 0.12, + "learning_rate": 4.410986331401982e-05, + "loss": 0.2524, "step": 53680 }, { - "epoch": 0.48, - "learning_rate": 2.6277362399783806e-05, - "loss": 0.2404, + "epoch": 0.12, + "learning_rate": 4.41087447708105e-05, + "loss": 0.2539, "step": 53690 }, { - "epoch": 0.48, - "learning_rate": 2.627285830105396e-05, - "loss": 0.2459, + "epoch": 0.12, + "learning_rate": 4.410762622760117e-05, + "loss": 0.2507, "step": 53700 }, { - "epoch": 0.48, - "learning_rate": 2.6268354202324114e-05, - "loss": 0.2354, + "epoch": 0.12, + "learning_rate": 4.410650768439185e-05, + "loss": 0.2503, "step": 53710 }, { - "epoch": 0.48, - "learning_rate": 2.6263850103594272e-05, - "loss": 0.2393, + "epoch": 0.12, + "learning_rate": 4.4105389141182526e-05, + "loss": 0.2541, "step": 53720 }, { - "epoch": 0.48, - "learning_rate": 2.6259346004864426e-05, - "loss": 0.2339, + "epoch": 0.12, + "learning_rate": 4.4104270597973204e-05, + "loss": 0.2552, "step": 53730 }, { - "epoch": 0.48, - "learning_rate": 2.6254841906134587e-05, - "loss": 0.2377, + "epoch": 0.12, + "learning_rate": 4.410315205476388e-05, + "loss": 0.2545, "step": 53740 }, { - "epoch": 0.48, - "learning_rate": 2.625033780740474e-05, - "loss": 0.2413, + "epoch": 0.12, + "learning_rate": 4.410203351155455e-05, + "loss": 0.2552, "step": 53750 }, { - "epoch": 0.48, - "learning_rate": 2.6245833708674895e-05, - "loss": 0.2399, + "epoch": 0.12, + "learning_rate": 4.410091496834523e-05, + "loss": 0.2595, "step": 53760 }, { - "epoch": 0.48, - "learning_rate": 2.6241329609945052e-05, - "loss": 0.2416, + "epoch": 0.12, + "learning_rate": 4.40997964251359e-05, + "loss": 0.2552, "step": 53770 }, { - "epoch": 0.48, - "learning_rate": 2.6236825511215207e-05, - "loss": 0.2465, + "epoch": 0.12, + "learning_rate": 4.409867788192658e-05, + "loss": 0.2455, "step": 53780 }, { - "epoch": 0.48, - "learning_rate": 2.623232141248536e-05, - "loss": 0.2357, + "epoch": 0.12, + "learning_rate": 4.409755933871726e-05, + "loss": 0.2545, "step": 53790 }, { - "epoch": 0.48, - "learning_rate": 2.622781731375552e-05, - "loss": 0.2398, + "epoch": 0.12, + "learning_rate": 4.409644079550793e-05, + "loss": 0.2544, "step": 53800 }, { - "epoch": 0.48, - "learning_rate": 2.6223313215025676e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.409532225229861e-05, + "loss": 0.2458, "step": 53810 }, { - "epoch": 0.48, - "learning_rate": 2.621880911629583e-05, - "loss": 0.2456, + "epoch": 0.12, + "learning_rate": 4.4094203709089285e-05, + "loss": 0.2527, "step": 53820 }, { - "epoch": 0.48, - "learning_rate": 2.6214305017565987e-05, - "loss": 0.2385, + "epoch": 0.12, + "learning_rate": 4.409308516587996e-05, + "loss": 0.2513, "step": 53830 }, { - "epoch": 0.48, - "learning_rate": 2.620980091883614e-05, - "loss": 0.2411, + "epoch": 0.12, + "learning_rate": 4.409196662267064e-05, + "loss": 0.2507, "step": 53840 }, { - "epoch": 0.48, - "learning_rate": 2.6205296820106295e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.409084807946131e-05, + "loss": 0.2503, "step": 53850 }, { - "epoch": 0.48, - "learning_rate": 2.6200792721376456e-05, - "loss": 0.2346, + "epoch": 0.12, + "learning_rate": 4.408972953625199e-05, + "loss": 0.2514, "step": 53860 }, { - "epoch": 0.48, - "learning_rate": 2.6196739032519597e-05, - "loss": 0.2372, + "epoch": 0.12, + "learning_rate": 4.408861099304266e-05, + "loss": 0.2535, "step": 53870 }, { - "epoch": 0.48, - "learning_rate": 2.619223493378975e-05, - "loss": 0.2335, + "epoch": 0.12, + "learning_rate": 4.408749244983334e-05, + "loss": 0.2566, "step": 53880 }, { - "epoch": 0.48, - "learning_rate": 2.6187730835059905e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.408637390662401e-05, + "loss": 0.2506, "step": 53890 }, { - "epoch": 0.48, - "learning_rate": 2.6183226736330062e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.408525536341469e-05, + "loss": 0.2511, "step": 53900 }, { - "epoch": 0.48, - "learning_rate": 2.6178722637600216e-05, - "loss": 0.2343, + "epoch": 0.12, + "learning_rate": 4.4084136820205366e-05, + "loss": 0.2555, "step": 53910 }, { - "epoch": 0.48, - "learning_rate": 2.617421853887037e-05, - "loss": 0.2382, + "epoch": 0.12, + "learning_rate": 4.4083018276996044e-05, + "loss": 0.2555, "step": 53920 }, { - "epoch": 0.48, - "learning_rate": 2.616971444014053e-05, - "loss": 0.2444, + "epoch": 0.12, + "learning_rate": 4.408189973378672e-05, + "loss": 0.2514, "step": 53930 }, { - "epoch": 0.48, - "learning_rate": 2.6165210341410686e-05, - "loss": 0.2414, + "epoch": 0.12, + "learning_rate": 4.408078119057739e-05, + "loss": 0.2535, "step": 53940 }, { - "epoch": 0.48, - "learning_rate": 2.6160706242680843e-05, - "loss": 0.2447, + "epoch": 0.12, + "learning_rate": 4.407966264736807e-05, + "loss": 0.2496, "step": 53950 }, { - "epoch": 0.48, - "learning_rate": 2.6156202143950997e-05, - "loss": 0.237, + "epoch": 0.12, + "learning_rate": 4.407854410415875e-05, + "loss": 0.2551, "step": 53960 }, { - "epoch": 0.48, - "learning_rate": 2.615169804522115e-05, - "loss": 0.2334, + "epoch": 0.12, + "learning_rate": 4.407742556094942e-05, + "loss": 0.2525, "step": 53970 }, { - "epoch": 0.48, - "learning_rate": 2.6147193946491312e-05, - "loss": 0.2373, + "epoch": 0.12, + "learning_rate": 4.40763070177401e-05, + "loss": 0.2547, "step": 53980 }, { - "epoch": 0.48, - "learning_rate": 2.6142689847761466e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.407518847453077e-05, + "loss": 0.2516, "step": 53990 }, { - "epoch": 0.48, - "learning_rate": 2.6138185749031617e-05, - "loss": 0.2376, + "epoch": 0.12, + "learning_rate": 4.407406993132145e-05, + "loss": 0.2486, "step": 54000 }, { - "epoch": 0.48, - "learning_rate": 2.6133681650301778e-05, - "loss": 0.2353, + "epoch": 0.12, + "learning_rate": 4.4072951388112125e-05, + "loss": 0.2531, "step": 54010 }, { - "epoch": 0.48, - "learning_rate": 2.6129177551571932e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.4071832844902796e-05, + "loss": 0.2591, "step": 54020 }, { - "epoch": 0.48, - "learning_rate": 2.6124673452842086e-05, - "loss": 0.2346, + "epoch": 0.12, + "learning_rate": 4.407071430169348e-05, + "loss": 0.256, "step": 54030 }, { - "epoch": 0.48, - "learning_rate": 2.6120169354112244e-05, - "loss": 0.2363, + "epoch": 0.12, + "learning_rate": 4.406959575848415e-05, + "loss": 0.2531, "step": 54040 }, { - "epoch": 0.48, - "learning_rate": 2.6115665255382398e-05, - "loss": 0.2334, + "epoch": 0.12, + "learning_rate": 4.406847721527483e-05, + "loss": 0.2536, "step": 54050 }, { - "epoch": 0.48, - "learning_rate": 2.6111161156652552e-05, - "loss": 0.2331, + "epoch": 0.12, + "learning_rate": 4.406735867206551e-05, + "loss": 0.2492, "step": 54060 }, { - "epoch": 0.48, - "learning_rate": 2.6106657057922713e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.406624012885618e-05, + "loss": 0.2567, "step": 54070 }, { - "epoch": 0.48, - "learning_rate": 2.6102152959192867e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.406512158564686e-05, + "loss": 0.2571, "step": 54080 }, { - "epoch": 0.48, - "learning_rate": 2.6097648860463024e-05, - "loss": 0.2329, + "epoch": 0.12, + "learning_rate": 4.406400304243753e-05, + "loss": 0.2513, "step": 54090 }, { - "epoch": 0.48, - "learning_rate": 2.609314476173318e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.4062884499228206e-05, + "loss": 0.2461, "step": 54100 }, { - "epoch": 0.48, - "learning_rate": 2.6088640663003332e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.4061765956018884e-05, + "loss": 0.2532, "step": 54110 }, { - "epoch": 0.48, - "learning_rate": 2.6084136564273493e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.4060647412809555e-05, + "loss": 0.2484, "step": 54120 }, { - "epoch": 0.48, - "learning_rate": 2.6079632465543647e-05, - "loss": 0.2367, + "epoch": 0.12, + "learning_rate": 4.405952886960023e-05, + "loss": 0.2513, "step": 54130 }, { - "epoch": 0.48, - "learning_rate": 2.60751283668138e-05, - "loss": 0.2412, + "epoch": 0.12, + "learning_rate": 4.405841032639091e-05, + "loss": 0.2556, "step": 54140 }, { - "epoch": 0.48, - "learning_rate": 2.607062426808396e-05, - "loss": 0.2393, + "epoch": 0.12, + "learning_rate": 4.405729178318159e-05, + "loss": 0.2573, "step": 54150 }, { - "epoch": 0.48, - "learning_rate": 2.6066120169354113e-05, - "loss": 0.2413, + "epoch": 0.12, + "learning_rate": 4.405617323997227e-05, + "loss": 0.2563, "step": 54160 }, { - "epoch": 0.48, - "learning_rate": 2.6061616070624267e-05, - "loss": 0.2438, + "epoch": 0.12, + "learning_rate": 4.405505469676294e-05, + "loss": 0.2603, "step": 54170 }, { - "epoch": 0.48, - "learning_rate": 2.6057111971894428e-05, - "loss": 0.239, + "epoch": 0.12, + "learning_rate": 4.4053936153553616e-05, + "loss": 0.2493, "step": 54180 }, { - "epoch": 0.48, - "learning_rate": 2.6052607873164582e-05, - "loss": 0.2395, + "epoch": 0.12, + "learning_rate": 4.405281761034429e-05, + "loss": 0.26, "step": 54190 }, { - "epoch": 0.48, - "learning_rate": 2.6048103774434733e-05, - "loss": 0.2372, + "epoch": 0.12, + "learning_rate": 4.4051699067134965e-05, + "loss": 0.2559, "step": 54200 }, { - "epoch": 0.48, - "learning_rate": 2.6043599675704894e-05, - "loss": 0.2456, + "epoch": 0.12, + "learning_rate": 4.4050580523925636e-05, + "loss": 0.2573, "step": 54210 }, { - "epoch": 0.48, - "learning_rate": 2.6039095576975048e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.4049461980716314e-05, + "loss": 0.2557, "step": 54220 }, { - "epoch": 0.48, - "learning_rate": 2.6034591478245202e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.404834343750699e-05, + "loss": 0.2608, "step": 54230 }, { - "epoch": 0.48, - "learning_rate": 2.603008737951536e-05, - "loss": 0.2366, + "epoch": 0.12, + "learning_rate": 4.404722489429767e-05, + "loss": 0.2527, "step": 54240 }, { - "epoch": 0.48, - "learning_rate": 2.6025583280785514e-05, - "loss": 0.238, + "epoch": 0.12, + "learning_rate": 4.404610635108835e-05, + "loss": 0.2601, "step": 54250 }, { - "epoch": 0.48, - "learning_rate": 2.6021079182055674e-05, - "loss": 0.2428, + "epoch": 0.12, + "learning_rate": 4.404498780787902e-05, + "loss": 0.2539, "step": 54260 }, { - "epoch": 0.48, - "learning_rate": 2.601657508332583e-05, - "loss": 0.2346, + "epoch": 0.12, + "learning_rate": 4.40438692646697e-05, + "loss": 0.2542, "step": 54270 }, { - "epoch": 0.48, - "learning_rate": 2.6012070984595983e-05, - "loss": 0.2315, + "epoch": 0.12, + "learning_rate": 4.4042750721460375e-05, + "loss": 0.2483, "step": 54280 }, { - "epoch": 0.48, - "learning_rate": 2.600756688586614e-05, - "loss": 0.2337, + "epoch": 0.12, + "learning_rate": 4.4041632178251046e-05, + "loss": 0.2517, "step": 54290 }, { - "epoch": 0.48, - "learning_rate": 2.6003062787136294e-05, - "loss": 0.2443, + "epoch": 0.12, + "learning_rate": 4.4040513635041724e-05, + "loss": 0.2564, "step": 54300 }, { - "epoch": 0.48, - "learning_rate": 2.599855868840645e-05, - "loss": 0.2374, + "epoch": 0.12, + "learning_rate": 4.4039395091832395e-05, + "loss": 0.2556, "step": 54310 }, { - "epoch": 0.48, - "learning_rate": 2.599405458967661e-05, - "loss": 0.2413, + "epoch": 0.12, + "learning_rate": 4.403827654862307e-05, + "loss": 0.2559, "step": 54320 }, { - "epoch": 0.49, - "learning_rate": 2.5989550490946763e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.403715800541375e-05, + "loss": 0.2467, "step": 54330 }, { - "epoch": 0.49, - "learning_rate": 2.5985046392216917e-05, - "loss": 0.2321, + "epoch": 0.12, + "learning_rate": 4.403603946220443e-05, + "loss": 0.2529, "step": 54340 }, { - "epoch": 0.49, - "learning_rate": 2.5980542293487075e-05, - "loss": 0.2301, + "epoch": 0.12, + "learning_rate": 4.403492091899511e-05, + "loss": 0.2589, "step": 54350 }, { - "epoch": 0.49, - "learning_rate": 2.597603819475723e-05, - "loss": 0.2381, + "epoch": 0.12, + "learning_rate": 4.403380237578578e-05, + "loss": 0.2524, "step": 54360 }, { - "epoch": 0.49, - "learning_rate": 2.5971534096027383e-05, - "loss": 0.2375, + "epoch": 0.12, + "learning_rate": 4.4032683832576456e-05, + "loss": 0.2505, "step": 54370 }, { - "epoch": 0.49, - "learning_rate": 2.5967029997297544e-05, - "loss": 0.2411, + "epoch": 0.12, + "learning_rate": 4.4031565289367134e-05, + "loss": 0.2504, "step": 54380 }, { - "epoch": 0.49, - "learning_rate": 2.5962525898567698e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.4030446746157805e-05, + "loss": 0.2494, "step": 54390 }, { - "epoch": 0.49, - "learning_rate": 2.5958021799837856e-05, - "loss": 0.2347, + "epoch": 0.12, + "learning_rate": 4.402932820294848e-05, + "loss": 0.255, "step": 54400 }, { - "epoch": 0.49, - "learning_rate": 2.595351770110801e-05, - "loss": 0.2364, + "epoch": 0.12, + "learning_rate": 4.4028209659739154e-05, + "loss": 0.2481, "step": 54410 }, { - "epoch": 0.49, - "learning_rate": 2.5949013602378164e-05, - "loss": 0.2353, + "epoch": 0.12, + "learning_rate": 4.402709111652983e-05, + "loss": 0.2482, "step": 54420 }, { - "epoch": 0.49, - "learning_rate": 2.5944509503648325e-05, - "loss": 0.2433, + "epoch": 0.12, + "learning_rate": 4.402597257332051e-05, + "loss": 0.2529, "step": 54430 }, { - "epoch": 0.49, - "learning_rate": 2.5940005404918475e-05, - "loss": 0.2431, + "epoch": 0.12, + "learning_rate": 4.402485403011118e-05, + "loss": 0.2504, "step": 54440 }, { - "epoch": 0.49, - "learning_rate": 2.593550130618863e-05, - "loss": 0.2371, + "epoch": 0.12, + "learning_rate": 4.4023735486901866e-05, + "loss": 0.2503, "step": 54450 }, { - "epoch": 0.49, - "learning_rate": 2.593099720745879e-05, - "loss": 0.2424, + "epoch": 0.12, + "learning_rate": 4.402261694369254e-05, + "loss": 0.2542, "step": 54460 }, { - "epoch": 0.49, - "learning_rate": 2.5926493108728945e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.4021498400483215e-05, + "loss": 0.2481, "step": 54470 }, { - "epoch": 0.49, - "learning_rate": 2.59219890099991e-05, - "loss": 0.2407, + "epoch": 0.12, + "learning_rate": 4.402037985727389e-05, + "loss": 0.2491, "step": 54480 }, { - "epoch": 0.49, - "learning_rate": 2.5917484911269256e-05, - "loss": 0.2364, + "epoch": 0.12, + "learning_rate": 4.4019261314064564e-05, + "loss": 0.252, "step": 54490 }, { - "epoch": 0.49, - "learning_rate": 2.591298081253941e-05, - "loss": 0.2364, + "epoch": 0.12, + "learning_rate": 4.401814277085524e-05, + "loss": 0.2551, "step": 54500 }, { - "epoch": 0.49, - "learning_rate": 2.5908476713809564e-05, - "loss": 0.2355, + "epoch": 0.12, + "learning_rate": 4.401702422764591e-05, + "loss": 0.2542, "step": 54510 }, { - "epoch": 0.49, - "learning_rate": 2.5903972615079725e-05, - "loss": 0.2373, + "epoch": 0.12, + "learning_rate": 4.401590568443659e-05, + "loss": 0.2563, "step": 54520 }, { - "epoch": 0.49, - "learning_rate": 2.589946851634988e-05, - "loss": 0.2377, + "epoch": 0.12, + "learning_rate": 4.401478714122726e-05, + "loss": 0.2543, "step": 54530 }, { - "epoch": 0.49, - "learning_rate": 2.5894964417620037e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.401366859801794e-05, + "loss": 0.2559, "step": 54540 }, { - "epoch": 0.49, - "learning_rate": 2.589046031889019e-05, - "loss": 0.2391, + "epoch": 0.12, + "learning_rate": 4.401255005480862e-05, + "loss": 0.2554, "step": 54550 }, { - "epoch": 0.49, - "learning_rate": 2.5885956220160345e-05, - "loss": 0.2391, + "epoch": 0.12, + "learning_rate": 4.4011431511599296e-05, + "loss": 0.2539, "step": 54560 }, { - "epoch": 0.49, - "learning_rate": 2.5881452121430506e-05, - "loss": 0.236, + "epoch": 0.12, + "learning_rate": 4.4010312968389974e-05, + "loss": 0.2481, "step": 54570 }, { - "epoch": 0.49, - "learning_rate": 2.587694802270066e-05, - "loss": 0.238, + "epoch": 0.12, + "learning_rate": 4.4009194425180645e-05, + "loss": 0.2509, "step": 54580 }, { - "epoch": 0.49, - "learning_rate": 2.5872443923970814e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.400807588197132e-05, + "loss": 0.2549, "step": 54590 }, { - "epoch": 0.49, - "learning_rate": 2.586793982524097e-05, - "loss": 0.237, + "epoch": 0.12, + "learning_rate": 4.4006957338762e-05, + "loss": 0.2522, "step": 54600 }, { - "epoch": 0.49, - "learning_rate": 2.5863435726511126e-05, - "loss": 0.2362, + "epoch": 0.12, + "learning_rate": 4.400583879555267e-05, + "loss": 0.253, "step": 54610 }, { - "epoch": 0.49, - "learning_rate": 2.585893162778128e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.400472025234335e-05, + "loss": 0.257, "step": 54620 }, { - "epoch": 0.49, - "learning_rate": 2.585442752905144e-05, - "loss": 0.2344, + "epoch": 0.12, + "learning_rate": 4.400360170913402e-05, + "loss": 0.2535, "step": 54630 }, { - "epoch": 0.49, - "learning_rate": 2.5849923430321595e-05, - "loss": 0.2368, + "epoch": 0.12, + "learning_rate": 4.40024831659247e-05, + "loss": 0.2512, "step": 54640 }, { - "epoch": 0.49, - "learning_rate": 2.5845419331591746e-05, - "loss": 0.2426, + "epoch": 0.12, + "learning_rate": 4.400136462271538e-05, + "loss": 0.2522, "step": 54650 }, { - "epoch": 0.49, - "learning_rate": 2.5840915232861906e-05, - "loss": 0.2394, + "epoch": 0.12, + "learning_rate": 4.4000246079506055e-05, + "loss": 0.2504, "step": 54660 }, { - "epoch": 0.49, - "learning_rate": 2.583641113413206e-05, - "loss": 0.236, + "epoch": 0.12, + "learning_rate": 4.399912753629673e-05, + "loss": 0.2505, "step": 54670 }, { - "epoch": 0.49, - "learning_rate": 2.5831907035402218e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.3998008993087404e-05, + "loss": 0.2531, "step": 54680 }, { - "epoch": 0.49, - "learning_rate": 2.5827402936672372e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.399689044987808e-05, + "loss": 0.2527, "step": 54690 }, { - "epoch": 0.49, - "learning_rate": 2.5822898837942526e-05, - "loss": 0.2415, + "epoch": 0.12, + "learning_rate": 4.399577190666876e-05, + "loss": 0.2516, "step": 54700 }, { - "epoch": 0.49, - "learning_rate": 2.5818394739212687e-05, - "loss": 0.239, + "epoch": 0.12, + "learning_rate": 4.399465336345943e-05, + "loss": 0.2475, "step": 54710 }, { - "epoch": 0.49, - "learning_rate": 2.581389064048284e-05, - "loss": 0.2367, + "epoch": 0.12, + "learning_rate": 4.399353482025011e-05, + "loss": 0.2539, "step": 54720 }, { - "epoch": 0.49, - "learning_rate": 2.5809386541752995e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.399241627704078e-05, + "loss": 0.2546, "step": 54730 }, { - "epoch": 0.49, - "learning_rate": 2.5804882443023153e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.399129773383146e-05, + "loss": 0.2435, "step": 54740 }, { - "epoch": 0.49, - "learning_rate": 2.5800378344293307e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.3990179190622136e-05, + "loss": 0.2574, "step": 54750 }, { - "epoch": 0.49, - "learning_rate": 2.579587424556346e-05, - "loss": 0.2363, + "epoch": 0.12, + "learning_rate": 4.3989060647412814e-05, + "loss": 0.2544, "step": 54760 }, { - "epoch": 0.49, - "learning_rate": 2.5791370146833622e-05, - "loss": 0.2367, + "epoch": 0.12, + "learning_rate": 4.398794210420349e-05, + "loss": 0.2538, "step": 54770 }, { - "epoch": 0.49, - "learning_rate": 2.5786866048103776e-05, - "loss": 0.239, + "epoch": 0.12, + "learning_rate": 4.398682356099416e-05, + "loss": 0.2534, "step": 54780 }, { - "epoch": 0.49, - "learning_rate": 2.578236194937393e-05, - "loss": 0.2374, + "epoch": 0.12, + "learning_rate": 4.398570501778484e-05, + "loss": 0.2488, "step": 54790 }, { - "epoch": 0.49, - "learning_rate": 2.5777857850644088e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.398458647457552e-05, + "loss": 0.253, "step": 54800 }, { - "epoch": 0.49, - "learning_rate": 2.577335375191424e-05, - "loss": 0.2393, + "epoch": 0.12, + "learning_rate": 4.398346793136619e-05, + "loss": 0.2498, "step": 54810 }, { - "epoch": 0.49, - "learning_rate": 2.5768849653184403e-05, - "loss": 0.2341, + "epoch": 0.12, + "learning_rate": 4.398234938815687e-05, + "loss": 0.2552, "step": 54820 }, { - "epoch": 0.49, - "learning_rate": 2.5764345554454557e-05, - "loss": 0.2343, + "epoch": 0.12, + "learning_rate": 4.398123084494754e-05, + "loss": 0.2536, "step": 54830 }, { - "epoch": 0.49, - "learning_rate": 2.575984145572471e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.398011230173822e-05, + "loss": 0.2564, "step": 54840 }, { - "epoch": 0.49, - "learning_rate": 2.5755337356994868e-05, - "loss": 0.2335, + "epoch": 0.12, + "learning_rate": 4.397899375852889e-05, + "loss": 0.2535, "step": 54850 }, { - "epoch": 0.49, - "learning_rate": 2.5750833258265022e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.397787521531957e-05, + "loss": 0.2535, "step": 54860 }, { - "epoch": 0.49, - "learning_rate": 2.5746329159535176e-05, - "loss": 0.2412, + "epoch": 0.12, + "learning_rate": 4.397675667211025e-05, + "loss": 0.2559, "step": 54870 }, { - "epoch": 0.49, - "learning_rate": 2.5741825060805337e-05, - "loss": 0.2378, + "epoch": 0.12, + "learning_rate": 4.397563812890092e-05, + "loss": 0.2537, "step": 54880 }, { - "epoch": 0.49, - "learning_rate": 2.5737320962075488e-05, - "loss": 0.2325, + "epoch": 0.12, + "learning_rate": 4.39745195856916e-05, + "loss": 0.2511, "step": 54890 }, { - "epoch": 0.49, - "learning_rate": 2.5732816863345642e-05, - "loss": 0.2403, + "epoch": 0.12, + "learning_rate": 4.397340104248227e-05, + "loss": 0.2509, "step": 54900 }, { - "epoch": 0.49, - "learning_rate": 2.5728312764615803e-05, - "loss": 0.2402, + "epoch": 0.12, + "learning_rate": 4.397228249927295e-05, + "loss": 0.2553, "step": 54910 }, { - "epoch": 0.49, - "learning_rate": 2.5723808665885957e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.397116395606363e-05, + "loss": 0.254, "step": 54920 }, { - "epoch": 0.49, - "learning_rate": 2.571930456715611e-05, - "loss": 0.2435, + "epoch": 0.12, + "learning_rate": 4.39700454128543e-05, + "loss": 0.2533, "step": 54930 }, { - "epoch": 0.49, - "learning_rate": 2.571480046842627e-05, - "loss": 0.2366, + "epoch": 0.12, + "learning_rate": 4.3968926869644976e-05, + "loss": 0.2532, "step": 54940 }, { - "epoch": 0.49, - "learning_rate": 2.5710296369696423e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.396780832643565e-05, + "loss": 0.2557, "step": 54950 }, { - "epoch": 0.49, - "learning_rate": 2.5705792270966584e-05, - "loss": 0.2353, + "epoch": 0.12, + "learning_rate": 4.3966689783226325e-05, + "loss": 0.2501, "step": 54960 }, { - "epoch": 0.49, - "learning_rate": 2.5701288172236738e-05, - "loss": 0.236, + "epoch": 0.12, + "learning_rate": 4.3965571240017e-05, + "loss": 0.2507, "step": 54970 }, { - "epoch": 0.49, - "learning_rate": 2.5696784073506892e-05, - "loss": 0.2374, + "epoch": 0.12, + "learning_rate": 4.396445269680768e-05, + "loss": 0.2488, "step": 54980 }, { - "epoch": 0.49, - "learning_rate": 2.569227997477705e-05, - "loss": 0.2401, + "epoch": 0.12, + "learning_rate": 4.396333415359836e-05, + "loss": 0.2493, "step": 54990 }, { - "epoch": 0.49, - "learning_rate": 2.5687775876047204e-05, - "loss": 0.2339, + "epoch": 0.12, + "learning_rate": 4.396221561038903e-05, + "loss": 0.248, "step": 55000 }, { - "epoch": 0.49, - "learning_rate": 2.5683271777317358e-05, - "loss": 0.2373, + "epoch": 0.12, + "learning_rate": 4.396109706717971e-05, + "loss": 0.2507, "step": 55010 }, { - "epoch": 0.49, - "learning_rate": 2.567876767858752e-05, - "loss": 0.2341, + "epoch": 0.12, + "learning_rate": 4.3959978523970386e-05, + "loss": 0.2562, "step": 55020 }, { - "epoch": 0.49, - "learning_rate": 2.5674263579857673e-05, - "loss": 0.2293, + "epoch": 0.12, + "learning_rate": 4.395885998076106e-05, + "loss": 0.2484, "step": 55030 }, { - "epoch": 0.49, - "learning_rate": 2.5669759481127827e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.3957741437551735e-05, + "loss": 0.2525, "step": 55040 }, { - "epoch": 0.49, - "learning_rate": 2.5665255382397984e-05, - "loss": 0.2331, + "epoch": 0.12, + "learning_rate": 4.3956622894342406e-05, + "loss": 0.2511, "step": 55050 }, { - "epoch": 0.49, - "learning_rate": 2.566075128366814e-05, - "loss": 0.233, + "epoch": 0.12, + "learning_rate": 4.3955504351133084e-05, + "loss": 0.2525, "step": 55060 }, { - "epoch": 0.49, - "learning_rate": 2.5656247184938292e-05, - "loss": 0.2417, + "epoch": 0.12, + "learning_rate": 4.395438580792376e-05, + "loss": 0.2488, "step": 55070 }, { - "epoch": 0.49, - "learning_rate": 2.5651743086208453e-05, - "loss": 0.2379, + "epoch": 0.12, + "learning_rate": 4.395326726471444e-05, + "loss": 0.2547, "step": 55080 }, { - "epoch": 0.49, - "learning_rate": 2.5647238987478604e-05, - "loss": 0.2314, + "epoch": 0.12, + "learning_rate": 4.395214872150512e-05, + "loss": 0.2544, "step": 55090 }, { - "epoch": 0.49, - "learning_rate": 2.5642734888748765e-05, - "loss": 0.2355, + "epoch": 0.12, + "learning_rate": 4.395103017829579e-05, + "loss": 0.2509, "step": 55100 }, { - "epoch": 0.49, - "learning_rate": 2.563823079001892e-05, - "loss": 0.2316, + "epoch": 0.12, + "learning_rate": 4.394991163508647e-05, + "loss": 0.2482, "step": 55110 }, { - "epoch": 0.49, - "learning_rate": 2.5633726691289073e-05, - "loss": 0.2312, + "epoch": 0.12, + "learning_rate": 4.3948793091877145e-05, + "loss": 0.2482, "step": 55120 }, { - "epoch": 0.49, - "learning_rate": 2.562922259255923e-05, - "loss": 0.2346, + "epoch": 0.12, + "learning_rate": 4.3947674548667816e-05, + "loss": 0.2494, "step": 55130 }, { - "epoch": 0.49, - "learning_rate": 2.5624718493829385e-05, - "loss": 0.238, + "epoch": 0.12, + "learning_rate": 4.3946556005458494e-05, + "loss": 0.2479, "step": 55140 }, { - "epoch": 0.49, - "learning_rate": 2.562021439509954e-05, - "loss": 0.2398, + "epoch": 0.12, + "learning_rate": 4.3945437462249165e-05, + "loss": 0.2514, "step": 55150 }, { - "epoch": 0.49, - "learning_rate": 2.56157102963697e-05, - "loss": 0.233, + "epoch": 0.12, + "learning_rate": 4.394431891903984e-05, + "loss": 0.2486, "step": 55160 }, { - "epoch": 0.49, - "learning_rate": 2.5611206197639854e-05, - "loss": 0.2318, + "epoch": 0.12, + "learning_rate": 4.394320037583052e-05, + "loss": 0.2532, "step": 55170 }, { - "epoch": 0.49, - "learning_rate": 2.5606702098910008e-05, - "loss": 0.2343, + "epoch": 0.12, + "learning_rate": 4.39420818326212e-05, + "loss": 0.2469, "step": 55180 }, { - "epoch": 0.49, - "learning_rate": 2.5602198000180165e-05, - "loss": 0.2343, + "epoch": 0.12, + "learning_rate": 4.3940963289411877e-05, + "loss": 0.2512, "step": 55190 }, { - "epoch": 0.49, - "learning_rate": 2.559769390145032e-05, - "loss": 0.2296, + "epoch": 0.12, + "learning_rate": 4.393995660052348e-05, + "loss": 0.2495, "step": 55200 }, { - "epoch": 0.49, - "learning_rate": 2.5593189802720474e-05, - "loss": 0.2325, + "epoch": 0.12, + "learning_rate": 4.3938838057314157e-05, + "loss": 0.2461, "step": 55210 }, { - "epoch": 0.49, - "learning_rate": 2.5588685703990634e-05, - "loss": 0.239, + "epoch": 0.12, + "learning_rate": 4.393771951410483e-05, + "loss": 0.2502, "step": 55220 }, { - "epoch": 0.49, - "learning_rate": 2.558418160526079e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.3936600970895506e-05, + "loss": 0.2548, "step": 55230 }, { - "epoch": 0.49, - "learning_rate": 2.5579677506530946e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.3935482427686184e-05, + "loss": 0.2566, "step": 55240 }, { - "epoch": 0.49, - "learning_rate": 2.55751734078011e-05, - "loss": 0.2397, + "epoch": 0.12, + "learning_rate": 4.393436388447686e-05, + "loss": 0.2526, "step": 55250 }, { - "epoch": 0.49, - "learning_rate": 2.5570669309071254e-05, - "loss": 0.2372, + "epoch": 0.12, + "learning_rate": 4.393324534126754e-05, + "loss": 0.2553, "step": 55260 }, { - "epoch": 0.49, - "learning_rate": 2.5566165210341415e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.393212679805821e-05, + "loss": 0.2445, "step": 55270 }, { - "epoch": 0.49, - "learning_rate": 2.556166111161157e-05, - "loss": 0.2422, + "epoch": 0.12, + "learning_rate": 4.393100825484889e-05, + "loss": 0.254, "step": 55280 }, { - "epoch": 0.49, - "learning_rate": 2.5557157012881723e-05, - "loss": 0.2324, + "epoch": 0.12, + "learning_rate": 4.392988971163956e-05, + "loss": 0.24, "step": 55290 }, { - "epoch": 0.49, - "learning_rate": 2.555265291415188e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.392877116843024e-05, + "loss": 0.2471, "step": 55300 }, { - "epoch": 0.49, - "learning_rate": 2.5548148815422035e-05, - "loss": 0.2333, + "epoch": 0.12, + "learning_rate": 4.3927652625220915e-05, + "loss": 0.2522, "step": 55310 }, { - "epoch": 0.49, - "learning_rate": 2.554364471669219e-05, - "loss": 0.2325, + "epoch": 0.12, + "learning_rate": 4.392653408201159e-05, + "loss": 0.2491, "step": 55320 }, { - "epoch": 0.49, - "learning_rate": 2.5539140617962347e-05, - "loss": 0.2298, + "epoch": 0.12, + "learning_rate": 4.3925415538802265e-05, + "loss": 0.2486, "step": 55330 }, { - "epoch": 0.49, - "learning_rate": 2.55346365192325e-05, - "loss": 0.2328, + "epoch": 0.12, + "learning_rate": 4.392429699559294e-05, + "loss": 0.2524, "step": 55340 }, { - "epoch": 0.49, - "learning_rate": 2.5530132420502655e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.392317845238362e-05, + "loss": 0.2522, "step": 55350 }, { - "epoch": 0.49, - "learning_rate": 2.5525628321772816e-05, - "loss": 0.2348, + "epoch": 0.12, + "learning_rate": 4.39220599091743e-05, + "loss": 0.2478, "step": 55360 }, { - "epoch": 0.49, - "learning_rate": 2.552112422304297e-05, - "loss": 0.2396, + "epoch": 0.12, + "learning_rate": 4.392094136596497e-05, + "loss": 0.2472, "step": 55370 }, { - "epoch": 0.49, - "learning_rate": 2.5516620124313127e-05, - "loss": 0.2336, + "epoch": 0.12, + "learning_rate": 4.391982282275565e-05, + "loss": 0.2565, "step": 55380 }, { - "epoch": 0.49, - "learning_rate": 2.551211602558328e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.391870427954632e-05, + "loss": 0.2522, "step": 55390 }, { - "epoch": 0.49, - "learning_rate": 2.5507611926853435e-05, - "loss": 0.2337, + "epoch": 0.12, + "learning_rate": 4.3917585736336997e-05, + "loss": 0.2518, "step": 55400 }, { - "epoch": 0.49, - "learning_rate": 2.5503107828123596e-05, - "loss": 0.2318, + "epoch": 0.12, + "learning_rate": 4.3916467193127674e-05, + "loss": 0.2483, "step": 55410 }, { - "epoch": 0.49, - "learning_rate": 2.549860372939375e-05, - "loss": 0.2428, + "epoch": 0.12, + "learning_rate": 4.3915348649918346e-05, + "loss": 0.2528, "step": 55420 }, { - "epoch": 0.49, - "learning_rate": 2.5494099630663905e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.3914230106709024e-05, + "loss": 0.2495, "step": 55430 }, { - "epoch": 0.49, - "learning_rate": 2.5489595531934062e-05, - "loss": 0.2388, + "epoch": 0.12, + "learning_rate": 4.39131115634997e-05, + "loss": 0.2535, "step": 55440 }, { - "epoch": 0.5, - "learning_rate": 2.5485091433204216e-05, - "loss": 0.2395, + "epoch": 0.12, + "learning_rate": 4.391199302029038e-05, + "loss": 0.2503, "step": 55450 }, { - "epoch": 0.5, - "learning_rate": 2.548058733447437e-05, - "loss": 0.2369, + "epoch": 0.12, + "learning_rate": 4.391087447708106e-05, + "loss": 0.2488, "step": 55460 }, { - "epoch": 0.5, - "learning_rate": 2.547608323574453e-05, - "loss": 0.237, + "epoch": 0.12, + "learning_rate": 4.390975593387173e-05, + "loss": 0.2498, "step": 55470 }, { - "epoch": 0.5, - "learning_rate": 2.5471579137014685e-05, - "loss": 0.2348, + "epoch": 0.12, + "learning_rate": 4.3908637390662406e-05, + "loss": 0.247, "step": 55480 }, { - "epoch": 0.5, - "learning_rate": 2.546707503828484e-05, - "loss": 0.2439, + "epoch": 0.12, + "learning_rate": 4.390751884745308e-05, + "loss": 0.2499, "step": 55490 }, { - "epoch": 0.5, - "learning_rate": 2.5462570939554997e-05, - "loss": 0.2358, + "epoch": 0.12, + "learning_rate": 4.3906400304243755e-05, + "loss": 0.2514, "step": 55500 }, { - "epoch": 0.5, - "learning_rate": 2.545806684082515e-05, - "loss": 0.2353, + "epoch": 0.12, + "learning_rate": 4.390528176103443e-05, + "loss": 0.2594, "step": 55510 }, { - "epoch": 0.5, - "learning_rate": 2.5453562742095312e-05, - "loss": 0.2354, + "epoch": 0.12, + "learning_rate": 4.3904163217825105e-05, + "loss": 0.2484, "step": 55520 }, { - "epoch": 0.5, - "learning_rate": 2.5449058643365466e-05, - "loss": 0.24, + "epoch": 0.12, + "learning_rate": 4.390304467461578e-05, + "loss": 0.2512, "step": 55530 }, { - "epoch": 0.5, - "learning_rate": 2.5444554544635617e-05, - "loss": 0.2387, + "epoch": 0.12, + "learning_rate": 4.3901926131406454e-05, + "loss": 0.2515, "step": 55540 }, { - "epoch": 0.5, - "learning_rate": 2.5440050445905778e-05, - "loss": 0.2355, + "epoch": 0.12, + "learning_rate": 4.390080758819713e-05, + "loss": 0.2476, "step": 55550 }, { - "epoch": 0.5, - "learning_rate": 2.543554634717593e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.389968904498781e-05, + "loss": 0.2537, "step": 55560 }, { - "epoch": 0.5, - "learning_rate": 2.5431042248446086e-05, - "loss": 0.2348, + "epoch": 0.12, + "learning_rate": 4.389857050177849e-05, + "loss": 0.2488, "step": 55570 }, { - "epoch": 0.5, - "learning_rate": 2.5426538149716243e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.3897451958569165e-05, + "loss": 0.2477, "step": 55580 }, { - "epoch": 0.5, - "learning_rate": 2.5422034050986397e-05, - "loss": 0.2376, + "epoch": 0.12, + "learning_rate": 4.3896333415359836e-05, + "loss": 0.2481, "step": 55590 }, { - "epoch": 0.5, - "learning_rate": 2.541752995225655e-05, - "loss": 0.2358, + "epoch": 0.12, + "learning_rate": 4.3895214872150514e-05, + "loss": 0.2494, "step": 55600 }, { - "epoch": 0.5, - "learning_rate": 2.5413025853526712e-05, - "loss": 0.236, + "epoch": 0.12, + "learning_rate": 4.3894096328941186e-05, + "loss": 0.2532, "step": 55610 }, { - "epoch": 0.5, - "learning_rate": 2.5408521754796866e-05, - "loss": 0.2368, + "epoch": 0.12, + "learning_rate": 4.3892977785731863e-05, + "loss": 0.2511, "step": 55620 }, { - "epoch": 0.5, - "learning_rate": 2.540401765606702e-05, - "loss": 0.2334, + "epoch": 0.12, + "learning_rate": 4.389185924252254e-05, + "loss": 0.2527, "step": 55630 }, { - "epoch": 0.5, - "learning_rate": 2.5399513557337178e-05, - "loss": 0.2367, + "epoch": 0.12, + "learning_rate": 4.389074069931321e-05, + "loss": 0.2502, "step": 55640 }, { - "epoch": 0.5, - "learning_rate": 2.5395009458607332e-05, - "loss": 0.2333, + "epoch": 0.12, + "learning_rate": 4.388962215610389e-05, + "loss": 0.255, "step": 55650 }, { - "epoch": 0.5, - "learning_rate": 2.5390505359877493e-05, - "loss": 0.2418, + "epoch": 0.12, + "learning_rate": 4.388850361289457e-05, + "loss": 0.2472, "step": 55660 }, { - "epoch": 0.5, - "learning_rate": 2.5386001261147647e-05, - "loss": 0.2375, + "epoch": 0.12, + "learning_rate": 4.3887385069685246e-05, + "loss": 0.247, "step": 55670 }, { - "epoch": 0.5, - "learning_rate": 2.53814971624178e-05, - "loss": 0.2308, + "epoch": 0.12, + "learning_rate": 4.3886266526475924e-05, + "loss": 0.2506, "step": 55680 }, { - "epoch": 0.5, - "learning_rate": 2.537699306368796e-05, - "loss": 0.2386, + "epoch": 0.12, + "learning_rate": 4.3885147983266595e-05, + "loss": 0.2484, "step": 55690 }, { - "epoch": 0.5, - "learning_rate": 2.5372488964958113e-05, - "loss": 0.2306, + "epoch": 0.12, + "learning_rate": 4.388402944005727e-05, + "loss": 0.2494, "step": 55700 }, { - "epoch": 0.5, - "learning_rate": 2.5367984866228267e-05, - "loss": 0.2351, + "epoch": 0.12, + "learning_rate": 4.3882910896847945e-05, + "loss": 0.2474, "step": 55710 }, { - "epoch": 0.5, - "learning_rate": 2.5363480767498428e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.388179235363862e-05, + "loss": 0.2509, "step": 55720 }, { - "epoch": 0.5, - "learning_rate": 2.5358976668768582e-05, - "loss": 0.2399, + "epoch": 0.12, + "learning_rate": 4.38806738104293e-05, + "loss": 0.2493, "step": 55730 }, { - "epoch": 0.5, - "learning_rate": 2.5354472570038733e-05, - "loss": 0.2355, + "epoch": 0.12, + "learning_rate": 4.387955526721997e-05, + "loss": 0.2482, "step": 55740 }, { - "epoch": 0.5, - "learning_rate": 2.5349968471308893e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.387843672401065e-05, + "loss": 0.2517, "step": 55750 }, { - "epoch": 0.5, - "learning_rate": 2.5345464372579048e-05, - "loss": 0.2373, + "epoch": 0.12, + "learning_rate": 4.387731818080133e-05, + "loss": 0.2476, "step": 55760 }, { - "epoch": 0.5, - "learning_rate": 2.53409602738492e-05, - "loss": 0.2342, + "epoch": 0.12, + "learning_rate": 4.3876199637592005e-05, + "loss": 0.2486, "step": 55770 }, { - "epoch": 0.5, - "learning_rate": 2.533645617511936e-05, - "loss": 0.2312, + "epoch": 0.12, + "learning_rate": 4.387508109438268e-05, + "loss": 0.25, "step": 55780 }, { - "epoch": 0.5, - "learning_rate": 2.5331952076389513e-05, - "loss": 0.2356, + "epoch": 0.12, + "learning_rate": 4.3873962551173354e-05, + "loss": 0.2484, "step": 55790 }, { - "epoch": 0.5, - "learning_rate": 2.5327447977659674e-05, - "loss": 0.2362, + "epoch": 0.12, + "learning_rate": 4.387284400796403e-05, + "loss": 0.2553, "step": 55800 }, { - "epoch": 0.5, - "learning_rate": 2.5322943878929828e-05, - "loss": 0.2376, + "epoch": 0.12, + "learning_rate": 4.3871725464754703e-05, + "loss": 0.2487, "step": 55810 }, { - "epoch": 0.5, - "learning_rate": 2.5318439780199982e-05, - "loss": 0.2349, + "epoch": 0.12, + "learning_rate": 4.387060692154538e-05, + "loss": 0.2535, "step": 55820 }, { - "epoch": 0.5, - "learning_rate": 2.531393568147014e-05, - "loss": 0.2383, + "epoch": 0.12, + "learning_rate": 4.386948837833606e-05, + "loss": 0.2477, "step": 55830 }, { - "epoch": 0.5, - "learning_rate": 2.5309431582740294e-05, - "loss": 0.2326, + "epoch": 0.12, + "learning_rate": 4.386836983512673e-05, + "loss": 0.2501, "step": 55840 }, { - "epoch": 0.5, - "learning_rate": 2.5304927484010448e-05, - "loss": 0.2319, + "epoch": 0.12, + "learning_rate": 4.386725129191741e-05, + "loss": 0.2483, "step": 55850 }, { - "epoch": 0.5, - "learning_rate": 2.530042338528061e-05, - "loss": 0.2418, + "epoch": 0.12, + "learning_rate": 4.3866132748708086e-05, + "loss": 0.2596, "step": 55860 }, { - "epoch": 0.5, - "learning_rate": 2.5295919286550763e-05, - "loss": 0.2361, + "epoch": 0.12, + "learning_rate": 4.3865014205498764e-05, + "loss": 0.2507, "step": 55870 }, { - "epoch": 0.5, - "learning_rate": 2.5291415187820917e-05, - "loss": 0.2325, + "epoch": 0.12, + "learning_rate": 4.3863895662289435e-05, + "loss": 0.2495, "step": 55880 }, { - "epoch": 0.5, - "learning_rate": 2.5286911089091075e-05, - "loss": 0.2343, + "epoch": 0.12, + "learning_rate": 4.386277711908011e-05, + "loss": 0.2473, "step": 55890 }, { - "epoch": 0.5, - "learning_rate": 2.528240699036123e-05, - "loss": 0.2359, + "epoch": 0.12, + "learning_rate": 4.386165857587079e-05, + "loss": 0.2509, "step": 55900 }, { - "epoch": 0.5, - "learning_rate": 2.5277902891631383e-05, - "loss": 0.2339, + "epoch": 0.12, + "learning_rate": 4.386054003266146e-05, + "loss": 0.2519, "step": 55910 }, { - "epoch": 0.5, - "learning_rate": 2.5273398792901544e-05, - "loss": 0.2308, + "epoch": 0.12, + "learning_rate": 4.385942148945214e-05, + "loss": 0.2494, "step": 55920 }, { - "epoch": 0.5, - "learning_rate": 2.5268894694171698e-05, - "loss": 0.2309, + "epoch": 0.12, + "learning_rate": 4.385830294624281e-05, + "loss": 0.2458, "step": 55930 }, { - "epoch": 0.5, - "learning_rate": 2.5264390595441855e-05, - "loss": 0.2408, + "epoch": 0.12, + "learning_rate": 4.385718440303349e-05, + "loss": 0.2518, "step": 55940 }, { - "epoch": 0.5, - "learning_rate": 2.525988649671201e-05, - "loss": 0.2331, + "epoch": 0.12, + "learning_rate": 4.385606585982417e-05, + "loss": 0.2507, "step": 55950 }, { - "epoch": 0.5, - "learning_rate": 2.5255382397982164e-05, - "loss": 0.2384, + "epoch": 0.12, + "learning_rate": 4.385494731661484e-05, + "loss": 0.2528, "step": 55960 }, { - "epoch": 0.5, - "learning_rate": 2.5250878299252324e-05, - "loss": 0.2311, + "epoch": 0.12, + "learning_rate": 4.3853828773405516e-05, + "loss": 0.2497, "step": 55970 }, { - "epoch": 0.5, - "learning_rate": 2.5246374200522475e-05, - "loss": 0.2345, + "epoch": 0.12, + "learning_rate": 4.3852710230196194e-05, + "loss": 0.247, "step": 55980 }, { - "epoch": 0.5, - "learning_rate": 2.524187010179263e-05, - "loss": 0.233, + "epoch": 0.12, + "learning_rate": 4.385159168698687e-05, + "loss": 0.2468, "step": 55990 }, { - "epoch": 0.5, - "learning_rate": 2.523736600306279e-05, - "loss": 0.2351, - "step": 56000 - }, - { - "epoch": 0.5, - "eval_NEIMS_canon_smiles": 0.9386833333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.0307, - "eval_NEIMS_daylight_tanimoto_simil": 0.4244121859887462, - "eval_NEIMS_exact_mols": 0.030566666666666666, - "eval_NEIMS_exact_smiles": 0.029716666666666666, - "eval_NEIMS_loss": 0.2517029643058777, - "eval_NEIMS_matched_formulas": 0.5088333333333334, - "eval_NEIMS_morgan_tanimoto_simil": 0.3239689600499408, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.03075, - "eval_NEIMS_runtime": 713.1519, - "eval_NEIMS_samples_per_second": 84.134, - "eval_NEIMS_steps_per_second": 1.315, - "step": 56000 - }, - { - "epoch": 0.5, - "eval_RASSP_canon_smiles": 0.9284903329214946, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.07466524192740508, - "eval_RASSP_daylight_tanimoto_simil": 0.524916680553281, - "eval_RASSP_exact_mols": 0.07439810331585801, - "eval_RASSP_exact_smiles": 0.07197715964871272, - "eval_RASSP_loss": 0.19337597489356995, - "eval_RASSP_matched_formulas": 0.6685310715597556, - "eval_RASSP_morgan_tanimoto_simil": 0.3899155475340412, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.07453167262163155, - "eval_RASSP_runtime": 814.8474, - "eval_RASSP_samples_per_second": 73.503, - "eval_RASSP_steps_per_second": 1.149, - "step": 56000 - }, - { - "epoch": 0.5, - "eval_NIST_canon_smiles": 0.8920041168328778, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.009972672747276147, - "eval_NIST_daylight_tanimoto_simil": 0.26198516526580995, - "eval_NIST_exact_mols": 0.00958228342264968, - "eval_NIST_exact_smiles": 0.00890797458920396, - "eval_NIST_loss": 1.4831839799880981, - "eval_NIST_matched_formulas": 0.069631259537921, - "eval_NIST_morgan_tanimoto_simil": 0.21832936310122283, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.009866202931468929, - "eval_NIST_runtime": 465.4465, - "eval_NIST_samples_per_second": 60.538, - "eval_NIST_steps_per_second": 0.947, + "epoch": 0.12, + "learning_rate": 4.385047314377755e-05, + "loss": 0.2433, "step": 56000 }, { - "epoch": 0.5, - "learning_rate": 2.5232861904332944e-05, - "loss": 0.2325, + "epoch": 0.13, + "learning_rate": 4.384935460056822e-05, + "loss": 0.2537, "step": 56010 }, { - "epoch": 0.5, - "learning_rate": 2.52283578056031e-05, - "loss": 0.2358, + "epoch": 0.13, + "learning_rate": 4.38482360573589e-05, + "loss": 0.2522, "step": 56020 }, { - "epoch": 0.5, - "learning_rate": 2.5223853706873256e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.384711751414957e-05, + "loss": 0.2505, "step": 56030 }, { - "epoch": 0.5, - "learning_rate": 2.521934960814341e-05, - "loss": 0.2399, + "epoch": 0.13, + "learning_rate": 4.384599897094025e-05, + "loss": 0.2494, "step": 56040 }, { - "epoch": 0.5, - "learning_rate": 2.5214845509413564e-05, - "loss": 0.2371, + "epoch": 0.13, + "learning_rate": 4.3844880427730926e-05, + "loss": 0.2524, "step": 56050 }, { - "epoch": 0.5, - "learning_rate": 2.5210341410683725e-05, - "loss": 0.239, + "epoch": 0.13, + "learning_rate": 4.38437618845216e-05, + "loss": 0.249, "step": 56060 }, { - "epoch": 0.5, - "learning_rate": 2.520583731195388e-05, - "loss": 0.2405, + "epoch": 0.13, + "learning_rate": 4.3842643341312275e-05, + "loss": 0.2557, "step": 56070 }, { - "epoch": 0.5, - "learning_rate": 2.5201333213224037e-05, - "loss": 0.2391, + "epoch": 0.13, + "learning_rate": 4.384152479810295e-05, + "loss": 0.2512, "step": 56080 }, { - "epoch": 0.5, - "learning_rate": 2.519682911449419e-05, - "loss": 0.2389, + "epoch": 0.13, + "learning_rate": 4.384040625489363e-05, + "loss": 0.2519, "step": 56090 }, { - "epoch": 0.5, - "learning_rate": 2.5192325015764345e-05, - "loss": 0.2392, + "epoch": 0.13, + "learning_rate": 4.383928771168431e-05, + "loss": 0.2437, "step": 56100 }, { - "epoch": 0.5, - "learning_rate": 2.5188271326907485e-05, - "loss": 0.2382, + "epoch": 0.13, + "learning_rate": 4.383816916847498e-05, + "loss": 0.2505, "step": 56110 }, { - "epoch": 0.5, - "learning_rate": 2.518376722817764e-05, - "loss": 0.24, + "epoch": 0.13, + "learning_rate": 4.383705062526566e-05, + "loss": 0.2478, "step": 56120 }, { - "epoch": 0.5, - "learning_rate": 2.51792631294478e-05, - "loss": 0.2312, + "epoch": 0.13, + "learning_rate": 4.383593208205633e-05, + "loss": 0.2537, "step": 56130 }, { - "epoch": 0.5, - "learning_rate": 2.5174759030717954e-05, - "loss": 0.2368, + "epoch": 0.13, + "learning_rate": 4.383481353884701e-05, + "loss": 0.2439, "step": 56140 }, { - "epoch": 0.5, - "learning_rate": 2.517025493198811e-05, - "loss": 0.2377, + "epoch": 0.13, + "learning_rate": 4.3833694995637685e-05, + "loss": 0.2521, "step": 56150 }, { - "epoch": 0.5, - "learning_rate": 2.5165750833258266e-05, - "loss": 0.2339, + "epoch": 0.13, + "learning_rate": 4.3832576452428356e-05, + "loss": 0.2506, "step": 56160 }, { - "epoch": 0.5, - "learning_rate": 2.516124673452842e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.3831457909219034e-05, + "loss": 0.2484, "step": 56170 }, { - "epoch": 0.5, - "learning_rate": 2.515674263579858e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.383033936600971e-05, + "loss": 0.2437, "step": 56180 }, { - "epoch": 0.5, - "learning_rate": 2.5152238537068735e-05, - "loss": 0.2396, + "epoch": 0.13, + "learning_rate": 4.382922082280039e-05, + "loss": 0.2432, "step": 56190 }, { - "epoch": 0.5, - "learning_rate": 2.514773443833889e-05, - "loss": 0.2324, + "epoch": 0.13, + "learning_rate": 4.382810227959106e-05, + "loss": 0.2544, "step": 56200 }, { - "epoch": 0.5, - "learning_rate": 2.5143230339609046e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.382698373638174e-05, + "loss": 0.2465, "step": 56210 }, { - "epoch": 0.5, - "learning_rate": 2.51387262408792e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.382586519317242e-05, + "loss": 0.2526, "step": 56220 }, { - "epoch": 0.5, - "learning_rate": 2.5134222142149355e-05, - "loss": 0.2374, + "epoch": 0.13, + "learning_rate": 4.382474664996309e-05, + "loss": 0.2521, "step": 56230 }, { - "epoch": 0.5, - "learning_rate": 2.5129718043419516e-05, - "loss": 0.2364, + "epoch": 0.13, + "learning_rate": 4.3823628106753766e-05, + "loss": 0.2523, "step": 56240 }, { - "epoch": 0.5, - "learning_rate": 2.512521394468967e-05, - "loss": 0.2336, + "epoch": 0.13, + "learning_rate": 4.382250956354444e-05, + "loss": 0.2536, "step": 56250 }, { - "epoch": 0.5, - "learning_rate": 2.5120709845959824e-05, - "loss": 0.2349, + "epoch": 0.13, + "learning_rate": 4.3821391020335115e-05, + "loss": 0.2458, "step": 56260 }, { - "epoch": 0.5, - "learning_rate": 2.511620574722998e-05, - "loss": 0.2343, + "epoch": 0.13, + "learning_rate": 4.382027247712579e-05, + "loss": 0.2514, "step": 56270 }, { - "epoch": 0.5, - "learning_rate": 2.5111701648500135e-05, - "loss": 0.2376, + "epoch": 0.13, + "learning_rate": 4.381915393391647e-05, + "loss": 0.2475, "step": 56280 }, { - "epoch": 0.5, - "learning_rate": 2.5107197549770296e-05, - "loss": 0.2366, + "epoch": 0.13, + "learning_rate": 4.381803539070715e-05, + "loss": 0.2506, "step": 56290 }, { - "epoch": 0.5, - "learning_rate": 2.510269345104045e-05, - "loss": 0.2299, + "epoch": 0.13, + "learning_rate": 4.381691684749782e-05, + "loss": 0.2549, "step": 56300 }, { - "epoch": 0.5, - "learning_rate": 2.50981893523106e-05, - "loss": 0.2397, + "epoch": 0.13, + "learning_rate": 4.38157983042885e-05, + "loss": 0.255, "step": 56310 }, { - "epoch": 0.5, - "learning_rate": 2.5093685253580762e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.3814679761079176e-05, + "loss": 0.2483, "step": 56320 }, { - "epoch": 0.5, - "learning_rate": 2.5089181154850916e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.381356121786985e-05, + "loss": 0.2512, "step": 56330 }, { - "epoch": 0.5, - "learning_rate": 2.508467705612107e-05, - "loss": 0.2372, + "epoch": 0.13, + "learning_rate": 4.3812442674660525e-05, + "loss": 0.2491, "step": 56340 }, { - "epoch": 0.5, - "learning_rate": 2.5080172957391228e-05, - "loss": 0.2387, + "epoch": 0.13, + "learning_rate": 4.3811324131451196e-05, + "loss": 0.2538, "step": 56350 }, { - "epoch": 0.5, - "learning_rate": 2.5075668858661382e-05, - "loss": 0.2336, + "epoch": 0.13, + "learning_rate": 4.3810205588241874e-05, + "loss": 0.2513, "step": 56360 }, { - "epoch": 0.5, - "learning_rate": 2.5071164759931536e-05, - "loss": 0.2378, + "epoch": 0.13, + "learning_rate": 4.380908704503255e-05, + "loss": 0.2509, "step": 56370 }, { - "epoch": 0.5, - "learning_rate": 2.5066660661201697e-05, - "loss": 0.2327, + "epoch": 0.13, + "learning_rate": 4.380796850182322e-05, + "loss": 0.2437, "step": 56380 }, { - "epoch": 0.5, - "learning_rate": 2.506215656247185e-05, - "loss": 0.2324, + "epoch": 0.13, + "learning_rate": 4.380684995861391e-05, + "loss": 0.2466, "step": 56390 }, { - "epoch": 0.5, - "learning_rate": 2.5057652463742005e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.380573141540458e-05, + "loss": 0.2484, "step": 56400 }, { - "epoch": 0.5, - "learning_rate": 2.5053148365012162e-05, - "loss": 0.2331, + "epoch": 0.13, + "learning_rate": 4.380461287219526e-05, + "loss": 0.246, "step": 56410 }, { - "epoch": 0.5, - "learning_rate": 2.5048644266282317e-05, - "loss": 0.2386, + "epoch": 0.13, + "learning_rate": 4.3803494328985935e-05, + "loss": 0.2542, "step": 56420 }, { - "epoch": 0.5, - "learning_rate": 2.5044140167552477e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.3802375785776606e-05, + "loss": 0.2473, "step": 56430 }, { - "epoch": 0.5, - "learning_rate": 2.503963606882263e-05, - "loss": 0.2405, + "epoch": 0.13, + "learning_rate": 4.3801257242567284e-05, + "loss": 0.2498, "step": 56440 }, { - "epoch": 0.5, - "learning_rate": 2.5035131970092786e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.3800138699357955e-05, + "loss": 0.2481, "step": 56450 }, { - "epoch": 0.5, - "learning_rate": 2.5030627871362943e-05, - "loss": 0.239, + "epoch": 0.13, + "learning_rate": 4.379902015614863e-05, + "loss": 0.2512, "step": 56460 }, { - "epoch": 0.5, - "learning_rate": 2.5026123772633097e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.379790161293931e-05, + "loss": 0.2508, "step": 56470 }, { - "epoch": 0.5, - "learning_rate": 2.502161967390325e-05, - "loss": 0.2314, + "epoch": 0.13, + "learning_rate": 4.379678306972998e-05, + "loss": 0.2485, "step": 56480 }, { - "epoch": 0.5, - "learning_rate": 2.5017115575173412e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.379566452652066e-05, + "loss": 0.2449, "step": 56490 }, { - "epoch": 0.5, - "learning_rate": 2.5012611476443566e-05, - "loss": 0.2336, + "epoch": 0.13, + "learning_rate": 4.379454598331134e-05, + "loss": 0.2403, "step": 56500 }, { - "epoch": 0.5, - "learning_rate": 2.5008107377713717e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.3793427440102016e-05, + "loss": 0.2503, "step": 56510 }, { - "epoch": 0.5, - "learning_rate": 2.5003603278983878e-05, - "loss": 0.2388, + "epoch": 0.13, + "learning_rate": 4.379230889689269e-05, + "loss": 0.2435, "step": 56520 }, { - "epoch": 0.5, - "learning_rate": 2.4999099180254032e-05, - "loss": 0.2364, + "epoch": 0.13, + "learning_rate": 4.3791190353683365e-05, + "loss": 0.2479, "step": 56530 }, { - "epoch": 0.5, - "learning_rate": 2.499459508152419e-05, - "loss": 0.2387, + "epoch": 0.13, + "learning_rate": 4.379007181047404e-05, + "loss": 0.2477, "step": 56540 }, { - "epoch": 0.5, - "learning_rate": 2.4990090982794344e-05, - "loss": 0.2433, + "epoch": 0.13, + "learning_rate": 4.3788953267264714e-05, + "loss": 0.2432, "step": 56550 }, { - "epoch": 0.5, - "learning_rate": 2.4985586884064498e-05, - "loss": 0.2341, + "epoch": 0.13, + "learning_rate": 4.378783472405539e-05, + "loss": 0.2483, "step": 56560 }, { - "epoch": 0.51, - "learning_rate": 2.4981082785334655e-05, - "loss": 0.2343, + "epoch": 0.13, + "learning_rate": 4.378671618084606e-05, + "loss": 0.2516, "step": 56570 }, { - "epoch": 0.51, - "learning_rate": 2.4976578686604813e-05, - "loss": 0.2307, + "epoch": 0.13, + "learning_rate": 4.378559763763674e-05, + "loss": 0.2498, "step": 56580 }, { - "epoch": 0.51, - "learning_rate": 2.4972074587874967e-05, - "loss": 0.2331, + "epoch": 0.13, + "learning_rate": 4.378447909442742e-05, + "loss": 0.2494, "step": 56590 }, { - "epoch": 0.51, - "learning_rate": 2.4967570489145124e-05, - "loss": 0.2349, + "epoch": 0.13, + "learning_rate": 4.37833605512181e-05, + "loss": 0.2544, "step": 56600 }, { - "epoch": 0.51, - "learning_rate": 2.496306639041528e-05, - "loss": 0.2388, + "epoch": 0.13, + "learning_rate": 4.3782242008008775e-05, + "loss": 0.2462, "step": 56610 }, { - "epoch": 0.51, - "learning_rate": 2.4958562291685436e-05, - "loss": 0.2312, + "epoch": 0.13, + "learning_rate": 4.3781123464799446e-05, + "loss": 0.2395, "step": 56620 }, { - "epoch": 0.51, - "learning_rate": 2.495405819295559e-05, - "loss": 0.2423, + "epoch": 0.13, + "learning_rate": 4.3780004921590124e-05, + "loss": 0.2457, "step": 56630 }, { - "epoch": 0.51, - "learning_rate": 2.4949554094225747e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.37788863783808e-05, + "loss": 0.2525, "step": 56640 }, { - "epoch": 0.51, - "learning_rate": 2.49450499954959e-05, - "loss": 0.2362, + "epoch": 0.13, + "learning_rate": 4.377776783517147e-05, + "loss": 0.2457, "step": 56650 }, { - "epoch": 0.51, - "learning_rate": 2.4940545896766056e-05, - "loss": 0.2307, + "epoch": 0.13, + "learning_rate": 4.377664929196215e-05, + "loss": 0.2482, "step": 56660 }, { - "epoch": 0.51, - "learning_rate": 2.4936041798036213e-05, - "loss": 0.2281, + "epoch": 0.13, + "learning_rate": 4.377553074875282e-05, + "loss": 0.2483, "step": 56670 }, { - "epoch": 0.51, - "learning_rate": 2.493153769930637e-05, - "loss": 0.2344, + "epoch": 0.13, + "learning_rate": 4.37744122055435e-05, + "loss": 0.2579, "step": 56680 }, { - "epoch": 0.51, - "learning_rate": 2.4927033600576528e-05, - "loss": 0.2341, + "epoch": 0.13, + "learning_rate": 4.377329366233418e-05, + "loss": 0.2493, "step": 56690 }, { - "epoch": 0.51, - "learning_rate": 2.4922529501846682e-05, - "loss": 0.2291, + "epoch": 0.13, + "learning_rate": 4.3772175119124856e-05, + "loss": 0.2486, "step": 56700 }, { - "epoch": 0.51, - "learning_rate": 2.4918025403116836e-05, - "loss": 0.2341, + "epoch": 0.13, + "learning_rate": 4.3771056575915534e-05, + "loss": 0.2448, "step": 56710 }, { - "epoch": 0.51, - "learning_rate": 2.4913521304386994e-05, - "loss": 0.2323, + "epoch": 0.13, + "learning_rate": 4.3769938032706205e-05, + "loss": 0.2489, "step": 56720 }, { - "epoch": 0.51, - "learning_rate": 2.4909017205657148e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.376881948949688e-05, + "loss": 0.2434, "step": 56730 }, { - "epoch": 0.51, - "learning_rate": 2.4904513106927305e-05, - "loss": 0.2355, + "epoch": 0.13, + "learning_rate": 4.376770094628756e-05, + "loss": 0.2512, "step": 56740 }, { - "epoch": 0.51, - "learning_rate": 2.4900009008197463e-05, - "loss": 0.2357, + "epoch": 0.13, + "learning_rate": 4.376658240307823e-05, + "loss": 0.2517, "step": 56750 }, { - "epoch": 0.51, - "learning_rate": 2.4895504909467617e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.376546385986891e-05, + "loss": 0.2415, "step": 56760 }, { - "epoch": 0.51, - "learning_rate": 2.489100081073777e-05, - "loss": 0.237, + "epoch": 0.13, + "learning_rate": 4.376434531665958e-05, + "loss": 0.2459, "step": 56770 }, { - "epoch": 0.51, - "learning_rate": 2.488649671200793e-05, - "loss": 0.2307, + "epoch": 0.13, + "learning_rate": 4.376322677345026e-05, + "loss": 0.2433, "step": 56780 }, { - "epoch": 0.51, - "learning_rate": 2.4881992613278086e-05, - "loss": 0.2285, + "epoch": 0.13, + "learning_rate": 4.376210823024093e-05, + "loss": 0.2512, "step": 56790 }, { - "epoch": 0.51, - "learning_rate": 2.487748851454824e-05, - "loss": 0.241, + "epoch": 0.13, + "learning_rate": 4.376098968703161e-05, + "loss": 0.2448, "step": 56800 }, { - "epoch": 0.51, - "learning_rate": 2.4872984415818394e-05, - "loss": 0.2333, + "epoch": 0.13, + "learning_rate": 4.375987114382229e-05, + "loss": 0.2483, "step": 56810 }, { - "epoch": 0.51, - "learning_rate": 2.4868480317088552e-05, - "loss": 0.2307, + "epoch": 0.13, + "learning_rate": 4.3758752600612964e-05, + "loss": 0.2487, "step": 56820 }, { - "epoch": 0.51, - "learning_rate": 2.486397621835871e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.375763405740364e-05, + "loss": 0.249, "step": 56830 }, { - "epoch": 0.51, - "learning_rate": 2.4859472119628863e-05, - "loss": 0.2321, + "epoch": 0.13, + "learning_rate": 4.375651551419431e-05, + "loss": 0.2503, "step": 56840 }, { - "epoch": 0.51, - "learning_rate": 2.485496802089902e-05, - "loss": 0.2366, + "epoch": 0.13, + "learning_rate": 4.375539697098499e-05, + "loss": 0.251, "step": 56850 }, { - "epoch": 0.51, - "learning_rate": 2.4850463922169175e-05, - "loss": 0.2377, + "epoch": 0.13, + "learning_rate": 4.375427842777567e-05, + "loss": 0.2454, "step": 56860 }, { - "epoch": 0.51, - "learning_rate": 2.484595982343933e-05, - "loss": 0.236, + "epoch": 0.13, + "learning_rate": 4.375315988456634e-05, + "loss": 0.2496, "step": 56870 }, { - "epoch": 0.51, - "learning_rate": 2.4841455724709487e-05, - "loss": 0.2339, + "epoch": 0.13, + "learning_rate": 4.375204134135702e-05, + "loss": 0.2496, "step": 56880 }, { - "epoch": 0.51, - "learning_rate": 2.4836951625979644e-05, - "loss": 0.2277, + "epoch": 0.13, + "learning_rate": 4.375092279814769e-05, + "loss": 0.251, "step": 56890 }, { - "epoch": 0.51, - "learning_rate": 2.4832447527249798e-05, - "loss": 0.2309, + "epoch": 0.13, + "learning_rate": 4.374980425493837e-05, + "loss": 0.2455, "step": 56900 }, { - "epoch": 0.51, - "learning_rate": 2.4827943428519952e-05, - "loss": 0.2367, + "epoch": 0.13, + "learning_rate": 4.3748685711729045e-05, + "loss": 0.2517, "step": 56910 }, { - "epoch": 0.51, - "learning_rate": 2.482343932979011e-05, - "loss": 0.2382, + "epoch": 0.13, + "learning_rate": 4.374756716851972e-05, + "loss": 0.2512, "step": 56920 }, { - "epoch": 0.51, - "learning_rate": 2.4818935231060267e-05, - "loss": 0.2414, + "epoch": 0.13, + "learning_rate": 4.37464486253104e-05, + "loss": 0.2483, "step": 56930 }, { - "epoch": 0.51, - "learning_rate": 2.481443113233042e-05, - "loss": 0.2368, + "epoch": 0.13, + "learning_rate": 4.374533008210107e-05, + "loss": 0.2511, "step": 56940 }, { - "epoch": 0.51, - "learning_rate": 2.480992703360058e-05, - "loss": 0.2402, + "epoch": 0.13, + "learning_rate": 4.374421153889175e-05, + "loss": 0.2461, "step": 56950 }, { - "epoch": 0.51, - "learning_rate": 2.4805422934870733e-05, - "loss": 0.234, + "epoch": 0.13, + "learning_rate": 4.374309299568243e-05, + "loss": 0.2509, "step": 56960 }, { - "epoch": 0.51, - "learning_rate": 2.480091883614089e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.37419744524731e-05, + "loss": 0.2503, "step": 56970 }, { - "epoch": 0.51, - "learning_rate": 2.4796414737411045e-05, - "loss": 0.2358, + "epoch": 0.13, + "learning_rate": 4.374085590926378e-05, + "loss": 0.2469, "step": 56980 }, { - "epoch": 0.51, - "learning_rate": 2.4791910638681202e-05, - "loss": 0.2292, + "epoch": 0.13, + "learning_rate": 4.373973736605445e-05, + "loss": 0.2495, "step": 56990 }, { - "epoch": 0.51, - "learning_rate": 2.4787406539951356e-05, - "loss": 0.2303, + "epoch": 0.13, + "learning_rate": 4.3738618822845126e-05, + "loss": 0.2491, "step": 57000 }, { - "epoch": 0.51, - "learning_rate": 2.478290244122151e-05, - "loss": 0.2303, + "epoch": 0.13, + "learning_rate": 4.3737500279635804e-05, + "loss": 0.2536, "step": 57010 }, { - "epoch": 0.51, - "learning_rate": 2.4778398342491668e-05, - "loss": 0.2362, + "epoch": 0.13, + "learning_rate": 4.373638173642648e-05, + "loss": 0.2455, "step": 57020 }, { - "epoch": 0.51, - "learning_rate": 2.4773894243761825e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.373526319321716e-05, + "loss": 0.247, "step": 57030 }, { - "epoch": 0.51, - "learning_rate": 2.4769390145031983e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.373414465000783e-05, + "loss": 0.2483, "step": 57040 }, { - "epoch": 0.51, - "learning_rate": 2.4764886046302137e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.373302610679851e-05, + "loss": 0.246, "step": 57050 }, { - "epoch": 0.51, - "learning_rate": 2.476038194757229e-05, - "loss": 0.2342, + "epoch": 0.13, + "learning_rate": 4.373190756358919e-05, + "loss": 0.2502, "step": 57060 }, { - "epoch": 0.51, - "learning_rate": 2.475587784884245e-05, - "loss": 0.2375, + "epoch": 0.13, + "learning_rate": 4.373078902037986e-05, + "loss": 0.2516, "step": 57070 }, { - "epoch": 0.51, - "learning_rate": 2.4751373750112603e-05, - "loss": 0.2322, + "epoch": 0.13, + "learning_rate": 4.3729670477170536e-05, + "loss": 0.245, "step": 57080 }, { - "epoch": 0.51, - "learning_rate": 2.474686965138276e-05, - "loss": 0.2373, + "epoch": 0.13, + "learning_rate": 4.372855193396121e-05, + "loss": 0.2543, "step": 57090 }, { - "epoch": 0.51, - "learning_rate": 2.4742365552652914e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.3727433390751885e-05, + "loss": 0.2516, "step": 57100 }, { - "epoch": 0.51, - "learning_rate": 2.4737861453923072e-05, - "loss": 0.2302, + "epoch": 0.13, + "learning_rate": 4.372631484754256e-05, + "loss": 0.2537, "step": 57110 }, { - "epoch": 0.51, - "learning_rate": 2.4733357355193226e-05, - "loss": 0.2304, + "epoch": 0.13, + "learning_rate": 4.372519630433324e-05, + "loss": 0.2504, "step": 57120 }, { - "epoch": 0.51, - "learning_rate": 2.4728853256463383e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.372407776112392e-05, + "loss": 0.2492, "step": 57130 }, { - "epoch": 0.51, - "learning_rate": 2.472434915773354e-05, - "loss": 0.2377, + "epoch": 0.13, + "learning_rate": 4.372295921791459e-05, + "loss": 0.2486, "step": 57140 }, { - "epoch": 0.51, - "learning_rate": 2.4719845059003695e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.372184067470527e-05, + "loss": 0.249, "step": 57150 }, { - "epoch": 0.51, - "learning_rate": 2.471534096027385e-05, - "loss": 0.2327, + "epoch": 0.13, + "learning_rate": 4.372072213149594e-05, + "loss": 0.2466, "step": 57160 }, { - "epoch": 0.51, - "learning_rate": 2.4710836861544006e-05, - "loss": 0.2333, + "epoch": 0.13, + "learning_rate": 4.371960358828662e-05, + "loss": 0.2518, "step": 57170 }, { - "epoch": 0.51, - "learning_rate": 2.4706332762814164e-05, - "loss": 0.2263, + "epoch": 0.13, + "learning_rate": 4.3718485045077295e-05, + "loss": 0.2433, "step": 57180 }, { - "epoch": 0.51, - "learning_rate": 2.4701828664084318e-05, - "loss": 0.2281, + "epoch": 0.13, + "learning_rate": 4.3717366501867966e-05, + "loss": 0.2472, "step": 57190 }, { - "epoch": 0.51, - "learning_rate": 2.4697324565354472e-05, - "loss": 0.2297, + "epoch": 0.13, + "learning_rate": 4.371635981297958e-05, + "loss": 0.2452, "step": 57200 }, { - "epoch": 0.51, - "learning_rate": 2.469282046662463e-05, - "loss": 0.2297, + "epoch": 0.13, + "learning_rate": 4.371524126977025e-05, + "loss": 0.2493, "step": 57210 }, { - "epoch": 0.51, - "learning_rate": 2.4688316367894784e-05, - "loss": 0.2371, + "epoch": 0.13, + "learning_rate": 4.371412272656093e-05, + "loss": 0.2542, "step": 57220 }, { - "epoch": 0.51, - "learning_rate": 2.468381226916494e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.37130041833516e-05, + "loss": 0.244, "step": 57230 }, { - "epoch": 0.51, - "learning_rate": 2.46793081704351e-05, - "loss": 0.2267, + "epoch": 0.13, + "learning_rate": 4.371188564014228e-05, + "loss": 0.2441, "step": 57240 }, { - "epoch": 0.51, - "learning_rate": 2.4674804071705253e-05, - "loss": 0.2358, + "epoch": 0.13, + "learning_rate": 4.371076709693296e-05, + "loss": 0.2486, "step": 57250 }, { - "epoch": 0.51, - "learning_rate": 2.4670299972975407e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.370964855372363e-05, + "loss": 0.2461, "step": 57260 }, { - "epoch": 0.51, - "learning_rate": 2.4665795874245564e-05, - "loss": 0.235, + "epoch": 0.13, + "learning_rate": 4.370853001051431e-05, + "loss": 0.2437, "step": 57270 }, { - "epoch": 0.51, - "learning_rate": 2.4661291775515722e-05, - "loss": 0.234, + "epoch": 0.13, + "learning_rate": 4.3707411467304985e-05, + "loss": 0.2499, "step": 57280 }, { - "epoch": 0.51, - "learning_rate": 2.4656787676785876e-05, - "loss": 0.2347, + "epoch": 0.13, + "learning_rate": 4.370629292409566e-05, + "loss": 0.2495, "step": 57290 }, { - "epoch": 0.51, - "learning_rate": 2.465228357805603e-05, - "loss": 0.2381, + "epoch": 0.13, + "learning_rate": 4.370517438088634e-05, + "loss": 0.2489, "step": 57300 }, { - "epoch": 0.51, - "learning_rate": 2.4647779479326188e-05, - "loss": 0.2268, + "epoch": 0.13, + "learning_rate": 4.370405583767701e-05, + "loss": 0.2443, "step": 57310 }, { - "epoch": 0.51, - "learning_rate": 2.4643275380596345e-05, - "loss": 0.2366, + "epoch": 0.13, + "learning_rate": 4.370293729446769e-05, + "loss": 0.2452, "step": 57320 }, { - "epoch": 0.51, - "learning_rate": 2.46387712818665e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.370181875125836e-05, + "loss": 0.245, "step": 57330 }, { - "epoch": 0.51, - "learning_rate": 2.4634267183136657e-05, - "loss": 0.2359, + "epoch": 0.13, + "learning_rate": 4.370070020804904e-05, + "loss": 0.2451, "step": 57340 }, { - "epoch": 0.51, - "learning_rate": 2.462976308440681e-05, - "loss": 0.231, + "epoch": 0.13, + "learning_rate": 4.369958166483972e-05, + "loss": 0.2471, "step": 57350 }, { - "epoch": 0.51, - "learning_rate": 2.4625258985676965e-05, - "loss": 0.2285, + "epoch": 0.13, + "learning_rate": 4.369846312163039e-05, + "loss": 0.2451, "step": 57360 }, { - "epoch": 0.51, - "learning_rate": 2.4620754886947122e-05, - "loss": 0.2369, + "epoch": 0.13, + "learning_rate": 4.3697344578421066e-05, + "loss": 0.2472, "step": 57370 }, { - "epoch": 0.51, - "learning_rate": 2.461625078821728e-05, - "loss": 0.2353, + "epoch": 0.13, + "learning_rate": 4.369622603521174e-05, + "loss": 0.2443, "step": 57380 }, { - "epoch": 0.51, - "learning_rate": 2.4611746689487437e-05, - "loss": 0.2285, + "epoch": 0.13, + "learning_rate": 4.369510749200242e-05, + "loss": 0.2458, "step": 57390 }, { - "epoch": 0.51, - "learning_rate": 2.460724259075759e-05, - "loss": 0.2294, + "epoch": 0.13, + "learning_rate": 4.36939889487931e-05, + "loss": 0.2502, "step": 57400 }, { - "epoch": 0.51, - "learning_rate": 2.4602738492027746e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.369287040558377e-05, + "loss": 0.245, "step": 57410 }, { - "epoch": 0.51, - "learning_rate": 2.4598234393297903e-05, - "loss": 0.2272, + "epoch": 0.13, + "learning_rate": 4.369175186237445e-05, + "loss": 0.2513, "step": 57420 }, { - "epoch": 0.51, - "learning_rate": 2.4593730294568057e-05, - "loss": 0.2402, + "epoch": 0.13, + "learning_rate": 4.369063331916512e-05, + "loss": 0.2532, "step": 57430 }, { - "epoch": 0.51, - "learning_rate": 2.4589226195838215e-05, - "loss": 0.2276, + "epoch": 0.13, + "learning_rate": 4.36895147759558e-05, + "loss": 0.2476, "step": 57440 }, { - "epoch": 0.51, - "learning_rate": 2.458472209710837e-05, - "loss": 0.2383, + "epoch": 0.13, + "learning_rate": 4.3688396232746476e-05, + "loss": 0.2506, "step": 57450 }, { - "epoch": 0.51, - "learning_rate": 2.4580217998378526e-05, - "loss": 0.2363, + "epoch": 0.13, + "learning_rate": 4.368727768953715e-05, + "loss": 0.2523, "step": 57460 }, { - "epoch": 0.51, - "learning_rate": 2.457571389964868e-05, - "loss": 0.2347, + "epoch": 0.13, + "learning_rate": 4.3686159146327825e-05, + "loss": 0.2449, "step": 57470 }, { - "epoch": 0.51, - "learning_rate": 2.4571209800918838e-05, - "loss": 0.2323, + "epoch": 0.13, + "learning_rate": 4.3685040603118496e-05, + "loss": 0.2453, "step": 57480 }, { - "epoch": 0.51, - "learning_rate": 2.4566705702188995e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.3683922059909174e-05, + "loss": 0.2479, "step": 57490 }, { - "epoch": 0.51, - "learning_rate": 2.456220160345915e-05, - "loss": 0.2344, + "epoch": 0.13, + "learning_rate": 4.368280351669985e-05, + "loss": 0.25, "step": 57500 }, { - "epoch": 0.51, - "learning_rate": 2.4557697504729304e-05, - "loss": 0.2379, + "epoch": 0.13, + "learning_rate": 4.368168497349053e-05, + "loss": 0.2419, "step": 57510 }, { - "epoch": 0.51, - "learning_rate": 2.455319340599946e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.368056643028121e-05, + "loss": 0.2466, "step": 57520 }, { - "epoch": 0.51, - "learning_rate": 2.454868930726962e-05, - "loss": 0.2317, + "epoch": 0.13, + "learning_rate": 4.367944788707188e-05, + "loss": 0.2428, "step": 57530 }, { - "epoch": 0.51, - "learning_rate": 2.4544185208539773e-05, - "loss": 0.2298, + "epoch": 0.13, + "learning_rate": 4.367832934386256e-05, + "loss": 0.2443, "step": 57540 }, { - "epoch": 0.51, - "learning_rate": 2.4539681109809927e-05, - "loss": 0.2341, + "epoch": 0.13, + "learning_rate": 4.367721080065323e-05, + "loss": 0.2511, "step": 57550 }, { - "epoch": 0.51, - "learning_rate": 2.4535177011080084e-05, - "loss": 0.2374, + "epoch": 0.13, + "learning_rate": 4.3676092257443906e-05, + "loss": 0.2502, "step": 57560 }, { - "epoch": 0.51, - "learning_rate": 2.453067291235024e-05, - "loss": 0.2273, + "epoch": 0.13, + "learning_rate": 4.3674973714234584e-05, + "loss": 0.253, "step": 57570 }, { - "epoch": 0.51, - "learning_rate": 2.4526168813620396e-05, - "loss": 0.2321, + "epoch": 0.13, + "learning_rate": 4.3673855171025255e-05, + "loss": 0.2469, "step": 57580 }, { - "epoch": 0.51, - "learning_rate": 2.4521664714890553e-05, - "loss": 0.2311, + "epoch": 0.13, + "learning_rate": 4.367273662781593e-05, + "loss": 0.2464, "step": 57590 }, { - "epoch": 0.51, - "learning_rate": 2.4517160616160707e-05, - "loss": 0.2281, + "epoch": 0.13, + "learning_rate": 4.367161808460661e-05, + "loss": 0.247, "step": 57600 }, { - "epoch": 0.51, - "learning_rate": 2.451265651743086e-05, - "loss": 0.2358, + "epoch": 0.13, + "learning_rate": 4.367049954139729e-05, + "loss": 0.252, "step": 57610 }, { - "epoch": 0.51, - "learning_rate": 2.450815241870102e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.3669380998187967e-05, + "loss": 0.2488, "step": 57620 }, { - "epoch": 0.51, - "learning_rate": 2.4503648319971177e-05, - "loss": 0.2359, + "epoch": 0.13, + "learning_rate": 4.366826245497864e-05, + "loss": 0.2446, "step": 57630 }, { - "epoch": 0.51, - "learning_rate": 2.449914422124133e-05, - "loss": 0.2363, + "epoch": 0.13, + "learning_rate": 4.3667143911769316e-05, + "loss": 0.242, "step": 57640 }, { - "epoch": 0.51, - "learning_rate": 2.4494640122511485e-05, - "loss": 0.2313, + "epoch": 0.13, + "learning_rate": 4.366602536855999e-05, + "loss": 0.2439, "step": 57650 }, { - "epoch": 0.51, - "learning_rate": 2.4490136023781642e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.3664906825350665e-05, + "loss": 0.2515, "step": 57660 }, { - "epoch": 0.51, - "learning_rate": 2.44856319250518e-05, - "loss": 0.2366, + "epoch": 0.13, + "learning_rate": 4.366378828214134e-05, + "loss": 0.2481, "step": 57670 }, { - "epoch": 0.51, - "learning_rate": 2.4481127826321954e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.3662669738932014e-05, + "loss": 0.2473, "step": 57680 }, { - "epoch": 0.52, - "learning_rate": 2.447662372759211e-05, - "loss": 0.2312, + "epoch": 0.13, + "learning_rate": 4.366155119572269e-05, + "loss": 0.2472, "step": 57690 }, { - "epoch": 0.52, - "learning_rate": 2.4472119628862265e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.366043265251337e-05, + "loss": 0.2521, "step": 57700 }, { - "epoch": 0.52, - "learning_rate": 2.446761553013242e-05, - "loss": 0.2288, + "epoch": 0.13, + "learning_rate": 4.365931410930405e-05, + "loss": 0.2441, "step": 57710 }, { - "epoch": 0.52, - "learning_rate": 2.4463111431402577e-05, - "loss": 0.2367, + "epoch": 0.13, + "learning_rate": 4.3658195566094725e-05, + "loss": 0.2451, "step": 57720 }, { - "epoch": 0.52, - "learning_rate": 2.4458607332672735e-05, - "loss": 0.2355, + "epoch": 0.13, + "learning_rate": 4.36570770228854e-05, + "loss": 0.2466, "step": 57730 }, { - "epoch": 0.52, - "learning_rate": 2.4454103233942892e-05, - "loss": 0.231, + "epoch": 0.13, + "learning_rate": 4.3655958479676075e-05, + "loss": 0.2473, "step": 57740 }, { - "epoch": 0.52, - "learning_rate": 2.4449599135213043e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.3654839936466746e-05, + "loss": 0.2514, "step": 57750 }, { - "epoch": 0.52, - "learning_rate": 2.44450950364832e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.3653721393257424e-05, + "loss": 0.2528, "step": 57760 }, { - "epoch": 0.52, - "learning_rate": 2.4440590937753358e-05, - "loss": 0.2272, + "epoch": 0.13, + "learning_rate": 4.36526028500481e-05, + "loss": 0.2461, "step": 57770 }, { - "epoch": 0.52, - "learning_rate": 2.4436086839023512e-05, - "loss": 0.2331, + "epoch": 0.13, + "learning_rate": 4.365148430683877e-05, + "loss": 0.2448, "step": 57780 }, { - "epoch": 0.52, - "learning_rate": 2.443158274029367e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.365036576362945e-05, + "loss": 0.2507, "step": 57790 }, { - "epoch": 0.52, - "learning_rate": 2.4427078641563823e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.364924722042013e-05, + "loss": 0.2459, "step": 57800 }, { - "epoch": 0.52, - "learning_rate": 2.442257454283398e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.3648128677210806e-05, + "loss": 0.2465, "step": 57810 }, { - "epoch": 0.52, - "learning_rate": 2.4418070444104135e-05, - "loss": 0.2313, + "epoch": 0.13, + "learning_rate": 4.364701013400148e-05, + "loss": 0.2481, "step": 57820 }, { - "epoch": 0.52, - "learning_rate": 2.4413566345374293e-05, - "loss": 0.233, + "epoch": 0.13, + "learning_rate": 4.3645891590792156e-05, + "loss": 0.2539, "step": 57830 }, { - "epoch": 0.52, - "learning_rate": 2.440906224664445e-05, - "loss": 0.2286, + "epoch": 0.13, + "learning_rate": 4.3644773047582833e-05, + "loss": 0.2452, "step": 57840 }, { - "epoch": 0.52, - "learning_rate": 2.44045581479146e-05, - "loss": 0.235, + "epoch": 0.13, + "learning_rate": 4.3643654504373505e-05, + "loss": 0.2484, "step": 57850 }, { - "epoch": 0.52, - "learning_rate": 2.4400054049184758e-05, - "loss": 0.233, + "epoch": 0.13, + "learning_rate": 4.364253596116418e-05, + "loss": 0.2476, "step": 57860 }, { - "epoch": 0.52, - "learning_rate": 2.4395549950454916e-05, - "loss": 0.2392, + "epoch": 0.13, + "learning_rate": 4.3641417417954854e-05, + "loss": 0.2496, "step": 57870 }, { - "epoch": 0.52, - "learning_rate": 2.4391045851725073e-05, - "loss": 0.234, + "epoch": 0.13, + "learning_rate": 4.364029887474553e-05, + "loss": 0.2439, "step": 57880 }, { - "epoch": 0.52, - "learning_rate": 2.4386541752995227e-05, - "loss": 0.2314, + "epoch": 0.13, + "learning_rate": 4.363918033153621e-05, + "loss": 0.2442, "step": 57890 }, { - "epoch": 0.52, - "learning_rate": 2.438203765426538e-05, - "loss": 0.228, + "epoch": 0.13, + "learning_rate": 4.363806178832688e-05, + "loss": 0.2496, "step": 57900 }, { - "epoch": 0.52, - "learning_rate": 2.437753355553554e-05, - "loss": 0.238, + "epoch": 0.13, + "learning_rate": 4.363694324511756e-05, + "loss": 0.2472, "step": 57910 }, { - "epoch": 0.52, - "learning_rate": 2.4373029456805693e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.3635824701908237e-05, + "loss": 0.2471, "step": 57920 }, { - "epoch": 0.52, - "learning_rate": 2.436852535807585e-05, - "loss": 0.2302, + "epoch": 0.13, + "learning_rate": 4.3634706158698915e-05, + "loss": 0.2451, "step": 57930 }, { - "epoch": 0.52, - "learning_rate": 2.4364021259346008e-05, - "loss": 0.2325, + "epoch": 0.13, + "learning_rate": 4.363358761548959e-05, + "loss": 0.2424, "step": 57940 }, { - "epoch": 0.52, - "learning_rate": 2.4359517160616162e-05, - "loss": 0.2343, + "epoch": 0.13, + "learning_rate": 4.3632469072280264e-05, + "loss": 0.2511, "step": 57950 }, { - "epoch": 0.52, - "learning_rate": 2.4355013061886316e-05, - "loss": 0.2274, + "epoch": 0.13, + "learning_rate": 4.363135052907094e-05, + "loss": 0.2484, "step": 57960 }, { - "epoch": 0.52, - "learning_rate": 2.4350508963156474e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.363023198586161e-05, + "loss": 0.2449, "step": 57970 }, { - "epoch": 0.52, - "learning_rate": 2.434600486442663e-05, - "loss": 0.2337, + "epoch": 0.13, + "learning_rate": 4.362911344265229e-05, + "loss": 0.2482, "step": 57980 }, { - "epoch": 0.52, - "learning_rate": 2.4341500765696785e-05, - "loss": 0.227, + "epoch": 0.13, + "learning_rate": 4.362799489944297e-05, + "loss": 0.2435, "step": 57990 }, { - "epoch": 0.52, - "learning_rate": 2.433699666696694e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.362687635623364e-05, + "loss": 0.2449, "step": 58000 }, { - "epoch": 0.52, - "learning_rate": 2.4332492568237097e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.362575781302432e-05, + "loss": 0.2486, "step": 58010 }, { - "epoch": 0.52, - "learning_rate": 2.4327988469507254e-05, - "loss": 0.2339, + "epoch": 0.13, + "learning_rate": 4.3624639269814996e-05, + "loss": 0.2429, "step": 58020 }, { - "epoch": 0.52, - "learning_rate": 2.432348437077741e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.3623520726605673e-05, + "loss": 0.2465, "step": 58030 }, { - "epoch": 0.52, - "learning_rate": 2.4318980272047566e-05, - "loss": 0.2264, + "epoch": 0.13, + "learning_rate": 4.362240218339635e-05, + "loss": 0.2493, "step": 58040 }, { - "epoch": 0.52, - "learning_rate": 2.431447617331772e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.362128364018702e-05, + "loss": 0.246, "step": 58050 }, { - "epoch": 0.52, - "learning_rate": 2.4309972074587874e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.36201650969777e-05, + "loss": 0.2463, "step": 58060 }, { - "epoch": 0.52, - "learning_rate": 2.4305467975858032e-05, - "loss": 0.2345, + "epoch": 0.13, + "learning_rate": 4.361904655376837e-05, + "loss": 0.2475, "step": 58070 }, { - "epoch": 0.52, - "learning_rate": 2.430096387712819e-05, - "loss": 0.2381, + "epoch": 0.13, + "learning_rate": 4.361792801055905e-05, + "loss": 0.2493, "step": 58080 }, { - "epoch": 0.52, - "learning_rate": 2.4296459778398343e-05, - "loss": 0.237, + "epoch": 0.13, + "learning_rate": 4.361680946734973e-05, + "loss": 0.2463, "step": 58090 }, { - "epoch": 0.52, - "learning_rate": 2.4291955679668497e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.36156909241404e-05, + "loss": 0.2401, "step": 58100 }, { - "epoch": 0.52, - "learning_rate": 2.4287451580938655e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.3614572380931077e-05, + "loss": 0.242, "step": 58110 }, { - "epoch": 0.52, - "learning_rate": 2.4282947482208812e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.3613453837721754e-05, + "loss": 0.2514, "step": 58120 }, { - "epoch": 0.52, - "learning_rate": 2.4278443383478966e-05, - "loss": 0.2326, + "epoch": 0.13, + "learning_rate": 4.361233529451243e-05, + "loss": 0.2396, "step": 58130 }, { - "epoch": 0.52, - "learning_rate": 2.4273939284749124e-05, - "loss": 0.2267, + "epoch": 0.13, + "learning_rate": 4.3611216751303104e-05, + "loss": 0.2508, "step": 58140 }, { - "epoch": 0.52, - "learning_rate": 2.4269435186019278e-05, - "loss": 0.2404, + "epoch": 0.13, + "learning_rate": 4.361009820809378e-05, + "loss": 0.2466, "step": 58150 }, { - "epoch": 0.52, - "learning_rate": 2.4264931087289436e-05, - "loss": 0.2271, + "epoch": 0.13, + "learning_rate": 4.360897966488446e-05, + "loss": 0.2449, "step": 58160 }, { - "epoch": 0.52, - "learning_rate": 2.426042698855959e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.360786112167513e-05, + "loss": 0.2505, "step": 58170 }, { - "epoch": 0.52, - "learning_rate": 2.4255922889829747e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.360674257846581e-05, + "loss": 0.2514, "step": 58180 }, { - "epoch": 0.52, - "learning_rate": 2.4251418791099905e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.360562403525648e-05, + "loss": 0.2562, "step": 58190 }, { - "epoch": 0.52, - "learning_rate": 2.4246914692370055e-05, - "loss": 0.2317, + "epoch": 0.13, + "learning_rate": 4.360450549204716e-05, + "loss": 0.247, "step": 58200 }, { - "epoch": 0.52, - "learning_rate": 2.42428610035132e-05, - "loss": 0.2408, + "epoch": 0.13, + "learning_rate": 4.3603386948837836e-05, + "loss": 0.25, "step": 58210 }, { - "epoch": 0.52, - "learning_rate": 2.4238356904783353e-05, - "loss": 0.2254, + "epoch": 0.13, + "learning_rate": 4.3602268405628513e-05, + "loss": 0.2488, "step": 58220 }, { - "epoch": 0.52, - "learning_rate": 2.4233852806053507e-05, - "loss": 0.2297, + "epoch": 0.13, + "learning_rate": 4.360114986241919e-05, + "loss": 0.2436, "step": 58230 }, { - "epoch": 0.52, - "learning_rate": 2.4229348707323665e-05, - "loss": 0.2272, + "epoch": 0.13, + "learning_rate": 4.360003131920986e-05, + "loss": 0.2449, "step": 58240 }, { - "epoch": 0.52, - "learning_rate": 2.4224844608593822e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.359891277600054e-05, + "loss": 0.2511, "step": 58250 }, { - "epoch": 0.52, - "learning_rate": 2.422034050986398e-05, - "loss": 0.2314, + "epoch": 0.13, + "learning_rate": 4.359779423279122e-05, + "loss": 0.253, "step": 58260 }, { - "epoch": 0.52, - "learning_rate": 2.4215836411134134e-05, - "loss": 0.2268, + "epoch": 0.13, + "learning_rate": 4.359667568958189e-05, + "loss": 0.2462, "step": 58270 }, { - "epoch": 0.52, - "learning_rate": 2.4211332312404288e-05, - "loss": 0.231, + "epoch": 0.13, + "learning_rate": 4.359555714637257e-05, + "loss": 0.2508, "step": 58280 }, { - "epoch": 0.52, - "learning_rate": 2.4206828213674446e-05, - "loss": 0.23, + "epoch": 0.13, + "learning_rate": 4.359443860316324e-05, + "loss": 0.2445, "step": 58290 }, { - "epoch": 0.52, - "learning_rate": 2.42023241149446e-05, - "loss": 0.2334, + "epoch": 0.13, + "learning_rate": 4.3593320059953917e-05, + "loss": 0.2454, "step": 58300 }, { - "epoch": 0.52, - "learning_rate": 2.4197820016214757e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.3592201516744594e-05, + "loss": 0.2403, "step": 58310 }, { - "epoch": 0.52, - "learning_rate": 2.419331591748491e-05, - "loss": 0.2255, + "epoch": 0.13, + "learning_rate": 4.3591082973535266e-05, + "loss": 0.2421, "step": 58320 }, { - "epoch": 0.52, - "learning_rate": 2.418881181875507e-05, - "loss": 0.2362, + "epoch": 0.13, + "learning_rate": 4.3589964430325944e-05, + "loss": 0.247, "step": 58330 }, { - "epoch": 0.52, - "learning_rate": 2.4184307720025223e-05, - "loss": 0.2284, + "epoch": 0.13, + "learning_rate": 4.358884588711662e-05, + "loss": 0.2451, "step": 58340 }, { - "epoch": 0.52, - "learning_rate": 2.417980362129538e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.35877273439073e-05, + "loss": 0.2413, "step": 58350 }, { - "epoch": 0.52, - "learning_rate": 2.4175299522565538e-05, - "loss": 0.2322, + "epoch": 0.13, + "learning_rate": 4.358660880069798e-05, + "loss": 0.2489, "step": 58360 }, { - "epoch": 0.52, - "learning_rate": 2.4170795423835692e-05, - "loss": 0.228, + "epoch": 0.13, + "learning_rate": 4.358549025748865e-05, + "loss": 0.2486, "step": 58370 }, { - "epoch": 0.52, - "learning_rate": 2.4166291325105846e-05, - "loss": 0.2304, + "epoch": 0.13, + "learning_rate": 4.3584371714279326e-05, + "loss": 0.2473, "step": 58380 }, { - "epoch": 0.52, - "learning_rate": 2.4161787226376004e-05, - "loss": 0.2314, + "epoch": 0.13, + "learning_rate": 4.358325317107e-05, + "loss": 0.2433, "step": 58390 }, { - "epoch": 0.52, - "learning_rate": 2.415728312764616e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.3582134627860675e-05, + "loss": 0.2465, "step": 58400 }, { - "epoch": 0.52, - "learning_rate": 2.4152779028916315e-05, - "loss": 0.2292, + "epoch": 0.13, + "learning_rate": 4.3581016084651353e-05, + "loss": 0.2523, "step": 58410 }, { - "epoch": 0.52, - "learning_rate": 2.414827493018647e-05, - "loss": 0.2382, + "epoch": 0.13, + "learning_rate": 4.3579897541442025e-05, + "loss": 0.2493, "step": 58420 }, { - "epoch": 0.52, - "learning_rate": 2.4143770831456627e-05, - "loss": 0.2335, + "epoch": 0.13, + "learning_rate": 4.35787789982327e-05, + "loss": 0.2402, "step": 58430 }, { - "epoch": 0.52, - "learning_rate": 2.413926673272678e-05, - "loss": 0.2257, + "epoch": 0.13, + "learning_rate": 4.357766045502338e-05, + "loss": 0.2409, "step": 58440 }, { - "epoch": 0.52, - "learning_rate": 2.413476263399694e-05, - "loss": 0.2302, + "epoch": 0.13, + "learning_rate": 4.357654191181406e-05, + "loss": 0.2495, "step": 58450 }, { - "epoch": 0.52, - "learning_rate": 2.4130258535267096e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.357542336860473e-05, + "loss": 0.2475, "step": 58460 }, { - "epoch": 0.52, - "learning_rate": 2.412575443653725e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.357430482539541e-05, + "loss": 0.2476, "step": 58470 }, { - "epoch": 0.52, - "learning_rate": 2.4121250337807404e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.3573186282186085e-05, + "loss": 0.2454, "step": 58480 }, { - "epoch": 0.52, - "learning_rate": 2.411674623907756e-05, - "loss": 0.2381, + "epoch": 0.13, + "learning_rate": 4.3572067738976756e-05, + "loss": 0.2472, "step": 58490 }, { - "epoch": 0.52, - "learning_rate": 2.411224214034772e-05, - "loss": 0.2322, + "epoch": 0.13, + "learning_rate": 4.3570949195767434e-05, + "loss": 0.2472, "step": 58500 }, { - "epoch": 0.52, - "learning_rate": 2.4107738041617873e-05, - "loss": 0.234, + "epoch": 0.13, + "learning_rate": 4.3569830652558106e-05, + "loss": 0.2434, "step": 58510 }, { - "epoch": 0.52, - "learning_rate": 2.4103233942888027e-05, - "loss": 0.2353, + "epoch": 0.13, + "learning_rate": 4.3568712109348783e-05, + "loss": 0.2474, "step": 58520 }, { - "epoch": 0.52, - "learning_rate": 2.4098729844158185e-05, - "loss": 0.2312, + "epoch": 0.13, + "learning_rate": 4.356759356613946e-05, + "loss": 0.246, "step": 58530 }, { - "epoch": 0.52, - "learning_rate": 2.4094225745428342e-05, - "loss": 0.2378, + "epoch": 0.13, + "learning_rate": 4.356647502293014e-05, + "loss": 0.2421, "step": 58540 }, { - "epoch": 0.52, - "learning_rate": 2.4089721646698496e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.356535647972082e-05, + "loss": 0.2457, "step": 58550 }, { - "epoch": 0.52, - "learning_rate": 2.4085217547968654e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.356423793651149e-05, + "loss": 0.2557, "step": 58560 }, { - "epoch": 0.52, - "learning_rate": 2.4080713449238808e-05, - "loss": 0.227, + "epoch": 0.13, + "learning_rate": 4.3563119393302166e-05, + "loss": 0.2403, "step": 58570 }, { - "epoch": 0.52, - "learning_rate": 2.4076209350508962e-05, - "loss": 0.2372, + "epoch": 0.13, + "learning_rate": 4.3562000850092844e-05, + "loss": 0.2489, "step": 58580 }, { - "epoch": 0.52, - "learning_rate": 2.407170525177912e-05, - "loss": 0.236, + "epoch": 0.13, + "learning_rate": 4.3560882306883515e-05, + "loss": 0.2446, "step": 58590 }, { - "epoch": 0.52, - "learning_rate": 2.4067201153049277e-05, - "loss": 0.2318, + "epoch": 0.13, + "learning_rate": 4.355976376367419e-05, + "loss": 0.2507, "step": 58600 }, { - "epoch": 0.52, - "learning_rate": 2.4062697054319434e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.3558645220464865e-05, + "loss": 0.2439, "step": 58610 }, { - "epoch": 0.52, - "learning_rate": 2.4058192955589585e-05, - "loss": 0.2293, + "epoch": 0.13, + "learning_rate": 4.355752667725554e-05, + "loss": 0.2466, "step": 58620 }, { - "epoch": 0.52, - "learning_rate": 2.4053688856859743e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.355640813404622e-05, + "loss": 0.251, "step": 58630 }, { - "epoch": 0.52, - "learning_rate": 2.40491847581299e-05, - "loss": 0.2237, + "epoch": 0.13, + "learning_rate": 4.35552895908369e-05, + "loss": 0.241, "step": 58640 }, { - "epoch": 0.52, - "learning_rate": 2.4044680659400054e-05, - "loss": 0.2323, + "epoch": 0.13, + "learning_rate": 4.3554171047627576e-05, + "loss": 0.2477, "step": 58650 }, { - "epoch": 0.52, - "learning_rate": 2.4040176560670212e-05, - "loss": 0.2291, + "epoch": 0.13, + "learning_rate": 4.355305250441825e-05, + "loss": 0.2448, "step": 58660 }, { - "epoch": 0.52, - "learning_rate": 2.4035672461940366e-05, - "loss": 0.2271, + "epoch": 0.13, + "learning_rate": 4.3551933961208925e-05, + "loss": 0.2444, "step": 58670 }, { - "epoch": 0.52, - "learning_rate": 2.4031168363210523e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.35508154179996e-05, + "loss": 0.2482, "step": 58680 }, { - "epoch": 0.52, - "learning_rate": 2.4026664264480677e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.3549696874790274e-05, + "loss": 0.243, "step": 58690 }, { - "epoch": 0.52, - "learning_rate": 2.4022160165750835e-05, - "loss": 0.2394, + "epoch": 0.13, + "learning_rate": 4.354857833158095e-05, + "loss": 0.249, "step": 58700 }, { - "epoch": 0.52, - "learning_rate": 2.4017656067020992e-05, - "loss": 0.2326, + "epoch": 0.13, + "learning_rate": 4.3547459788371623e-05, + "loss": 0.2437, "step": 58710 }, { - "epoch": 0.52, - "learning_rate": 2.4013151968291147e-05, - "loss": 0.2258, + "epoch": 0.13, + "learning_rate": 4.35463412451623e-05, + "loss": 0.2453, "step": 58720 }, { - "epoch": 0.52, - "learning_rate": 2.40086478695613e-05, - "loss": 0.2304, + "epoch": 0.13, + "learning_rate": 4.354522270195298e-05, + "loss": 0.2463, "step": 58730 }, { - "epoch": 0.52, - "learning_rate": 2.4004143770831458e-05, - "loss": 0.2307, + "epoch": 0.13, + "learning_rate": 4.354410415874365e-05, + "loss": 0.2477, "step": 58740 }, { - "epoch": 0.52, - "learning_rate": 2.3999639672101616e-05, - "loss": 0.2331, + "epoch": 0.13, + "learning_rate": 4.3542985615534335e-05, + "loss": 0.248, "step": 58750 }, { - "epoch": 0.52, - "learning_rate": 2.399513557337177e-05, - "loss": 0.2242, + "epoch": 0.13, + "learning_rate": 4.3541867072325006e-05, + "loss": 0.2432, "step": 58760 }, { - "epoch": 0.52, - "learning_rate": 2.3990631474641924e-05, - "loss": 0.2254, + "epoch": 0.13, + "learning_rate": 4.3540748529115684e-05, + "loss": 0.2416, "step": 58770 }, { - "epoch": 0.52, - "learning_rate": 2.398612737591208e-05, - "loss": 0.2367, + "epoch": 0.13, + "learning_rate": 4.3539629985906355e-05, + "loss": 0.2461, "step": 58780 }, { - "epoch": 0.52, - "learning_rate": 2.3981623277182235e-05, - "loss": 0.2333, + "epoch": 0.13, + "learning_rate": 4.353851144269703e-05, + "loss": 0.2517, "step": 58790 }, { - "epoch": 0.52, - "learning_rate": 2.3977119178452393e-05, - "loss": 0.231, + "epoch": 0.13, + "learning_rate": 4.353739289948771e-05, + "loss": 0.2474, "step": 58800 }, { - "epoch": 0.53, - "learning_rate": 2.397261507972255e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.353627435627838e-05, + "loss": 0.2467, "step": 58810 }, { - "epoch": 0.53, - "learning_rate": 2.3968110980992705e-05, - "loss": 0.2238, + "epoch": 0.13, + "learning_rate": 4.353515581306906e-05, + "loss": 0.2472, "step": 58820 }, { - "epoch": 0.53, - "learning_rate": 2.396360688226286e-05, - "loss": 0.23, + "epoch": 0.13, + "learning_rate": 4.353403726985973e-05, + "loss": 0.246, "step": 58830 }, { - "epoch": 0.53, - "learning_rate": 2.3959102783533016e-05, - "loss": 0.2312, + "epoch": 0.13, + "learning_rate": 4.353291872665041e-05, + "loss": 0.2459, "step": 58840 }, { - "epoch": 0.53, - "learning_rate": 2.3954598684803174e-05, - "loss": 0.2237, + "epoch": 0.13, + "learning_rate": 4.353180018344109e-05, + "loss": 0.2406, "step": 58850 }, { - "epoch": 0.53, - "learning_rate": 2.3950094586073328e-05, - "loss": 0.2304, + "epoch": 0.13, + "learning_rate": 4.3530681640231765e-05, + "loss": 0.2424, "step": 58860 }, { - "epoch": 0.53, - "learning_rate": 2.3945590487343482e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.352956309702244e-05, + "loss": 0.2427, "step": 58870 }, { - "epoch": 0.53, - "learning_rate": 2.394108638861364e-05, - "loss": 0.2325, + "epoch": 0.13, + "learning_rate": 4.3528444553813114e-05, + "loss": 0.2467, "step": 58880 }, { - "epoch": 0.53, - "learning_rate": 2.3936582289883797e-05, - "loss": 0.2336, + "epoch": 0.13, + "learning_rate": 4.352732601060379e-05, + "loss": 0.2423, "step": 58890 }, { - "epoch": 0.53, - "learning_rate": 2.393207819115395e-05, - "loss": 0.2303, + "epoch": 0.13, + "learning_rate": 4.352620746739447e-05, + "loss": 0.2482, "step": 58900 }, { - "epoch": 0.53, - "learning_rate": 2.392757409242411e-05, - "loss": 0.2285, + "epoch": 0.13, + "learning_rate": 4.352508892418514e-05, + "loss": 0.2388, "step": 58910 }, { - "epoch": 0.53, - "learning_rate": 2.3923069993694263e-05, - "loss": 0.2304, + "epoch": 0.13, + "learning_rate": 4.352397038097582e-05, + "loss": 0.2439, "step": 58920 }, { - "epoch": 0.53, - "learning_rate": 2.3918565894964417e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.352285183776649e-05, + "loss": 0.2438, "step": 58930 }, { - "epoch": 0.53, - "learning_rate": 2.3914061796234574e-05, - "loss": 0.2371, + "epoch": 0.13, + "learning_rate": 4.352173329455717e-05, + "loss": 0.2461, "step": 58940 }, { - "epoch": 0.53, - "learning_rate": 2.390955769750473e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.3520614751347846e-05, + "loss": 0.2438, "step": 58950 }, { - "epoch": 0.53, - "learning_rate": 2.390505359877489e-05, - "loss": 0.2353, + "epoch": 0.13, + "learning_rate": 4.3519496208138524e-05, + "loss": 0.2443, "step": 58960 }, { - "epoch": 0.53, - "learning_rate": 2.390054950004504e-05, - "loss": 0.2293, + "epoch": 0.13, + "learning_rate": 4.35183776649292e-05, + "loss": 0.2405, "step": 58970 }, { - "epoch": 0.53, - "learning_rate": 2.3896045401315197e-05, - "loss": 0.23, + "epoch": 0.13, + "learning_rate": 4.351725912171987e-05, + "loss": 0.2509, "step": 58980 }, { - "epoch": 0.53, - "learning_rate": 2.3891541302585355e-05, - "loss": 0.2268, + "epoch": 0.13, + "learning_rate": 4.351614057851055e-05, + "loss": 0.2404, "step": 58990 }, { - "epoch": 0.53, - "learning_rate": 2.388703720385551e-05, - "loss": 0.2351, + "epoch": 0.13, + "learning_rate": 4.351502203530123e-05, + "loss": 0.246, "step": 59000 }, { - "epoch": 0.53, - "learning_rate": 2.3882533105125666e-05, - "loss": 0.223, + "epoch": 0.13, + "learning_rate": 4.35139034920919e-05, + "loss": 0.2424, "step": 59010 }, { - "epoch": 0.53, - "learning_rate": 2.387802900639582e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.351278494888258e-05, + "loss": 0.252, "step": 59020 }, { - "epoch": 0.53, - "learning_rate": 2.3873524907665978e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.351166640567325e-05, + "loss": 0.2449, "step": 59030 }, { - "epoch": 0.53, - "learning_rate": 2.3869020808936132e-05, - "loss": 0.2264, + "epoch": 0.13, + "learning_rate": 4.351054786246393e-05, + "loss": 0.2437, "step": 59040 }, { - "epoch": 0.53, - "learning_rate": 2.386451671020629e-05, - "loss": 0.2271, + "epoch": 0.13, + "learning_rate": 4.3509429319254605e-05, + "loss": 0.2473, "step": 59050 }, { - "epoch": 0.53, - "learning_rate": 2.3860012611476447e-05, - "loss": 0.2284, + "epoch": 0.13, + "learning_rate": 4.350831077604528e-05, + "loss": 0.244, "step": 59060 }, { - "epoch": 0.53, - "learning_rate": 2.3855508512746598e-05, - "loss": 0.2253, + "epoch": 0.13, + "learning_rate": 4.350719223283596e-05, + "loss": 0.2415, "step": 59070 }, { - "epoch": 0.53, - "learning_rate": 2.3851004414016755e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.350607368962663e-05, + "loss": 0.2461, "step": 59080 }, { - "epoch": 0.53, - "learning_rate": 2.3846500315286913e-05, - "loss": 0.2294, + "epoch": 0.13, + "learning_rate": 4.350495514641731e-05, + "loss": 0.2461, "step": 59090 }, { - "epoch": 0.53, - "learning_rate": 2.384199621655707e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.350383660320798e-05, + "loss": 0.2429, "step": 59100 }, { - "epoch": 0.53, - "learning_rate": 2.3837492117827224e-05, - "loss": 0.2325, + "epoch": 0.13, + "learning_rate": 4.350271805999866e-05, + "loss": 0.2449, "step": 59110 }, { - "epoch": 0.53, - "learning_rate": 2.383298801909738e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.350159951678934e-05, + "loss": 0.2435, "step": 59120 }, { - "epoch": 0.53, - "learning_rate": 2.3828483920367536e-05, - "loss": 0.2287, + "epoch": 0.13, + "learning_rate": 4.350048097358001e-05, + "loss": 0.2455, "step": 59130 }, { - "epoch": 0.53, - "learning_rate": 2.382397982163769e-05, - "loss": 0.2271, + "epoch": 0.13, + "learning_rate": 4.3499362430370686e-05, + "loss": 0.242, "step": 59140 }, { - "epoch": 0.53, - "learning_rate": 2.3819475722907848e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.349824388716136e-05, + "loss": 0.2408, "step": 59150 }, { - "epoch": 0.53, - "learning_rate": 2.3814971624178005e-05, - "loss": 0.2305, + "epoch": 0.13, + "learning_rate": 4.349712534395204e-05, + "loss": 0.2455, "step": 59160 }, { - "epoch": 0.53, - "learning_rate": 2.381046752544816e-05, - "loss": 0.2328, + "epoch": 0.13, + "learning_rate": 4.349600680074272e-05, + "loss": 0.2452, "step": 59170 }, { - "epoch": 0.53, - "learning_rate": 2.3805963426718313e-05, - "loss": 0.235, + "epoch": 0.13, + "learning_rate": 4.349488825753339e-05, + "loss": 0.2443, "step": 59180 }, { - "epoch": 0.53, - "learning_rate": 2.380145932798847e-05, - "loss": 0.2405, + "epoch": 0.13, + "learning_rate": 4.349376971432407e-05, + "loss": 0.2458, "step": 59190 }, { - "epoch": 0.53, - "learning_rate": 2.3796955229258628e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.349265117111474e-05, + "loss": 0.2434, "step": 59200 }, { - "epoch": 0.53, - "learning_rate": 2.3792451130528782e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.349164448222635e-05, + "loss": 0.247, "step": 59210 }, { - "epoch": 0.53, - "learning_rate": 2.3787947031798936e-05, - "loss": 0.2326, + "epoch": 0.13, + "learning_rate": 4.349052593901703e-05, + "loss": 0.2406, "step": 59220 }, { - "epoch": 0.53, - "learning_rate": 2.3783442933069094e-05, - "loss": 0.2343, + "epoch": 0.13, + "learning_rate": 4.3489407395807705e-05, + "loss": 0.2412, "step": 59230 }, { - "epoch": 0.53, - "learning_rate": 2.377893883433925e-05, - "loss": 0.2336, + "epoch": 0.13, + "learning_rate": 4.348828885259838e-05, + "loss": 0.2432, "step": 59240 }, { - "epoch": 0.53, - "learning_rate": 2.3774434735609406e-05, - "loss": 0.227, + "epoch": 0.13, + "learning_rate": 4.3487170309389054e-05, + "loss": 0.2461, "step": 59250 }, { - "epoch": 0.53, - "learning_rate": 2.3769930636879563e-05, - "loss": 0.2329, + "epoch": 0.13, + "learning_rate": 4.348605176617973e-05, + "loss": 0.2461, "step": 59260 }, { - "epoch": 0.53, - "learning_rate": 2.3765426538149717e-05, - "loss": 0.2273, + "epoch": 0.13, + "learning_rate": 4.34849332229704e-05, + "loss": 0.2479, "step": 59270 }, { - "epoch": 0.53, - "learning_rate": 2.376092243941987e-05, - "loss": 0.2321, + "epoch": 0.13, + "learning_rate": 4.348381467976108e-05, + "loss": 0.2456, "step": 59280 }, { - "epoch": 0.53, - "learning_rate": 2.375641834069003e-05, - "loss": 0.2267, + "epoch": 0.13, + "learning_rate": 4.348269613655176e-05, + "loss": 0.2427, "step": 59290 }, { - "epoch": 0.53, - "learning_rate": 2.3751914241960186e-05, - "loss": 0.2317, + "epoch": 0.13, + "learning_rate": 4.348157759334243e-05, + "loss": 0.2373, "step": 59300 }, { - "epoch": 0.53, - "learning_rate": 2.374741014323034e-05, - "loss": 0.2299, + "epoch": 0.13, + "learning_rate": 4.348045905013311e-05, + "loss": 0.2462, "step": 59310 }, { - "epoch": 0.53, - "learning_rate": 2.3742906044500494e-05, - "loss": 0.221, + "epoch": 0.13, + "learning_rate": 4.347934050692378e-05, + "loss": 0.2464, "step": 59320 }, { - "epoch": 0.53, - "learning_rate": 2.3738401945770652e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.3478221963714464e-05, + "loss": 0.2425, "step": 59330 }, { - "epoch": 0.53, - "learning_rate": 2.373389784704081e-05, - "loss": 0.2284, + "epoch": 0.13, + "learning_rate": 4.347710342050514e-05, + "loss": 0.2472, "step": 59340 }, { - "epoch": 0.53, - "learning_rate": 2.3729393748310964e-05, - "loss": 0.2339, + "epoch": 0.13, + "learning_rate": 4.347598487729581e-05, + "loss": 0.2454, "step": 59350 }, { - "epoch": 0.53, - "learning_rate": 2.372488964958112e-05, - "loss": 0.227, + "epoch": 0.13, + "learning_rate": 4.347486633408649e-05, + "loss": 0.2476, "step": 59360 }, { - "epoch": 0.53, - "learning_rate": 2.3720385550851275e-05, - "loss": 0.2219, + "epoch": 0.13, + "learning_rate": 4.347374779087716e-05, + "loss": 0.2459, "step": 59370 }, { - "epoch": 0.53, - "learning_rate": 2.3715881452121433e-05, - "loss": 0.2254, + "epoch": 0.13, + "learning_rate": 4.347262924766784e-05, + "loss": 0.2456, "step": 59380 }, { - "epoch": 0.53, - "learning_rate": 2.3711377353391587e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.347151070445852e-05, + "loss": 0.24, "step": 59390 }, { - "epoch": 0.53, - "learning_rate": 2.3706873254661744e-05, - "loss": 0.2274, + "epoch": 0.13, + "learning_rate": 4.347039216124919e-05, + "loss": 0.2419, "step": 59400 }, { - "epoch": 0.53, - "learning_rate": 2.37023691559319e-05, - "loss": 0.2223, + "epoch": 0.13, + "learning_rate": 4.346927361803987e-05, + "loss": 0.2413, "step": 59410 }, { - "epoch": 0.53, - "learning_rate": 2.3697865057202052e-05, - "loss": 0.2271, + "epoch": 0.13, + "learning_rate": 4.346815507483054e-05, + "loss": 0.2447, "step": 59420 }, { - "epoch": 0.53, - "learning_rate": 2.369336095847221e-05, - "loss": 0.2306, + "epoch": 0.13, + "learning_rate": 4.3467036531621216e-05, + "loss": 0.2434, "step": 59430 }, { - "epoch": 0.53, - "learning_rate": 2.3688856859742367e-05, - "loss": 0.2302, + "epoch": 0.13, + "learning_rate": 4.3465917988411894e-05, + "loss": 0.241, "step": 59440 }, { - "epoch": 0.53, - "learning_rate": 2.3684352761012525e-05, - "loss": 0.2299, + "epoch": 0.13, + "learning_rate": 4.346479944520257e-05, + "loss": 0.2425, "step": 59450 }, { - "epoch": 0.53, - "learning_rate": 2.367984866228268e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.346368090199325e-05, + "loss": 0.2464, "step": 59460 }, { - "epoch": 0.53, - "learning_rate": 2.3675344563552833e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.346256235878392e-05, + "loss": 0.2416, "step": 59470 }, { - "epoch": 0.53, - "learning_rate": 2.367084046482299e-05, - "loss": 0.2299, + "epoch": 0.13, + "learning_rate": 4.34614438155746e-05, + "loss": 0.2532, "step": 59480 }, { - "epoch": 0.53, - "learning_rate": 2.3666336366093145e-05, - "loss": 0.2287, + "epoch": 0.13, + "learning_rate": 4.346032527236527e-05, + "loss": 0.2479, "step": 59490 }, { - "epoch": 0.53, - "learning_rate": 2.3661832267363302e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.345920672915595e-05, + "loss": 0.2499, "step": 59500 }, { - "epoch": 0.53, - "learning_rate": 2.365732816863346e-05, - "loss": 0.2334, + "epoch": 0.13, + "learning_rate": 4.3458088185946626e-05, + "loss": 0.2468, "step": 59510 }, { - "epoch": 0.53, - "learning_rate": 2.3652824069903614e-05, - "loss": 0.2286, + "epoch": 0.13, + "learning_rate": 4.34569696427373e-05, + "loss": 0.2432, "step": 59520 }, { - "epoch": 0.53, - "learning_rate": 2.3648319971173768e-05, - "loss": 0.231, + "epoch": 0.13, + "learning_rate": 4.3455851099527975e-05, + "loss": 0.2414, "step": 59530 }, { - "epoch": 0.53, - "learning_rate": 2.3643815872443925e-05, - "loss": 0.236, + "epoch": 0.13, + "learning_rate": 4.345473255631865e-05, + "loss": 0.2426, "step": 59540 }, { - "epoch": 0.53, - "learning_rate": 2.3639311773714083e-05, - "loss": 0.2355, + "epoch": 0.13, + "learning_rate": 4.345361401310933e-05, + "loss": 0.2431, "step": 59550 }, { - "epoch": 0.53, - "learning_rate": 2.3634807674984237e-05, - "loss": 0.2317, + "epoch": 0.13, + "learning_rate": 4.345249546990001e-05, + "loss": 0.244, "step": 59560 }, { - "epoch": 0.53, - "learning_rate": 2.363030357625439e-05, - "loss": 0.2321, + "epoch": 0.13, + "learning_rate": 4.345137692669068e-05, + "loss": 0.2516, "step": 59570 }, { - "epoch": 0.53, - "learning_rate": 2.362579947752455e-05, - "loss": 0.2249, + "epoch": 0.13, + "learning_rate": 4.345025838348136e-05, + "loss": 0.2466, "step": 59580 }, { - "epoch": 0.53, - "learning_rate": 2.3621295378794706e-05, - "loss": 0.2276, + "epoch": 0.13, + "learning_rate": 4.344913984027203e-05, + "loss": 0.2424, "step": 59590 }, { - "epoch": 0.53, - "learning_rate": 2.361679128006486e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.344802129706271e-05, + "loss": 0.2506, "step": 59600 }, { - "epoch": 0.53, - "learning_rate": 2.3612287181335018e-05, - "loss": 0.2249, + "epoch": 0.13, + "learning_rate": 4.3446902753853385e-05, + "loss": 0.2473, "step": 59610 }, { - "epoch": 0.53, - "learning_rate": 2.3607783082605172e-05, - "loss": 0.2255, + "epoch": 0.13, + "learning_rate": 4.3445784210644056e-05, + "loss": 0.2446, "step": 59620 }, { - "epoch": 0.53, - "learning_rate": 2.3603278983875326e-05, - "loss": 0.2308, + "epoch": 0.13, + "learning_rate": 4.3444665667434734e-05, + "loss": 0.2496, "step": 59630 }, { - "epoch": 0.53, - "learning_rate": 2.3598774885145483e-05, - "loss": 0.2305, + "epoch": 0.13, + "learning_rate": 4.344354712422541e-05, + "loss": 0.2385, "step": 59640 }, { - "epoch": 0.53, - "learning_rate": 2.359427078641564e-05, - "loss": 0.2278, + "epoch": 0.13, + "learning_rate": 4.344242858101609e-05, + "loss": 0.2491, "step": 59650 }, { - "epoch": 0.53, - "learning_rate": 2.3589766687685795e-05, - "loss": 0.2257, + "epoch": 0.13, + "learning_rate": 4.344131003780677e-05, + "loss": 0.246, "step": 59660 }, { - "epoch": 0.53, - "learning_rate": 2.358526258895595e-05, - "loss": 0.2254, + "epoch": 0.13, + "learning_rate": 4.344019149459744e-05, + "loss": 0.249, "step": 59670 }, { - "epoch": 0.53, - "learning_rate": 2.3580758490226107e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.343907295138812e-05, + "loss": 0.2462, "step": 59680 }, { - "epoch": 0.53, - "learning_rate": 2.3576254391496264e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.343795440817879e-05, + "loss": 0.2462, "step": 59690 }, { - "epoch": 0.53, - "learning_rate": 2.3571750292766418e-05, - "loss": 0.2308, + "epoch": 0.13, + "learning_rate": 4.3436835864969466e-05, + "loss": 0.2524, "step": 59700 }, { - "epoch": 0.53, - "learning_rate": 2.3567246194036576e-05, - "loss": 0.2241, + "epoch": 0.13, + "learning_rate": 4.3435717321760144e-05, + "loss": 0.2467, "step": 59710 }, { - "epoch": 0.53, - "learning_rate": 2.356274209530673e-05, - "loss": 0.2354, + "epoch": 0.13, + "learning_rate": 4.3434598778550815e-05, + "loss": 0.2483, "step": 59720 }, { - "epoch": 0.53, - "learning_rate": 2.3558237996576887e-05, - "loss": 0.2308, + "epoch": 0.13, + "learning_rate": 4.343348023534149e-05, + "loss": 0.2438, "step": 59730 }, { - "epoch": 0.53, - "learning_rate": 2.355373389784704e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.343236169213217e-05, + "loss": 0.244, "step": 59740 }, { - "epoch": 0.53, - "learning_rate": 2.35492297991172e-05, - "loss": 0.2247, + "epoch": 0.13, + "learning_rate": 4.343124314892285e-05, + "loss": 0.2443, "step": 59750 }, { - "epoch": 0.53, - "learning_rate": 2.3544725700387353e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.343012460571352e-05, + "loss": 0.2426, "step": 59760 }, { - "epoch": 0.53, - "learning_rate": 2.3540221601657507e-05, - "loss": 0.2277, + "epoch": 0.13, + "learning_rate": 4.34290060625042e-05, + "loss": 0.2485, "step": 59770 }, { - "epoch": 0.53, - "learning_rate": 2.3535717502927665e-05, - "loss": 0.2283, + "epoch": 0.13, + "learning_rate": 4.3427887519294876e-05, + "loss": 0.2441, "step": 59780 }, { - "epoch": 0.53, - "learning_rate": 2.3531213404197822e-05, - "loss": 0.2246, + "epoch": 0.13, + "learning_rate": 4.342676897608555e-05, + "loss": 0.2421, "step": 59790 }, { - "epoch": 0.53, - "learning_rate": 2.352670930546798e-05, - "loss": 0.2324, + "epoch": 0.13, + "learning_rate": 4.3425650432876225e-05, + "loss": 0.2421, "step": 59800 }, { - "epoch": 0.53, - "learning_rate": 2.3522205206738134e-05, - "loss": 0.2294, + "epoch": 0.13, + "learning_rate": 4.3424531889666896e-05, + "loss": 0.2486, "step": 59810 }, { - "epoch": 0.53, - "learning_rate": 2.3517701108008288e-05, - "loss": 0.225, + "epoch": 0.13, + "learning_rate": 4.3423413346457574e-05, + "loss": 0.2432, "step": 59820 }, { - "epoch": 0.53, - "learning_rate": 2.3513197009278445e-05, - "loss": 0.2303, + "epoch": 0.13, + "learning_rate": 4.342229480324825e-05, + "loss": 0.2472, "step": 59830 }, { - "epoch": 0.53, - "learning_rate": 2.35086929105486e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.342117626003892e-05, + "loss": 0.2442, "step": 59840 }, { - "epoch": 0.53, - "learning_rate": 2.3504188811818757e-05, - "loss": 0.2332, + "epoch": 0.13, + "learning_rate": 4.34200577168296e-05, + "loss": 0.25, "step": 59850 }, { - "epoch": 0.53, - "learning_rate": 2.349968471308891e-05, - "loss": 0.2239, + "epoch": 0.13, + "learning_rate": 4.341893917362028e-05, + "loss": 0.2444, "step": 59860 }, { - "epoch": 0.53, - "learning_rate": 2.349518061435907e-05, - "loss": 0.2279, + "epoch": 0.13, + "learning_rate": 4.341782063041096e-05, + "loss": 0.2491, "step": 59870 }, { - "epoch": 0.53, - "learning_rate": 2.3490676515629223e-05, - "loss": 0.2348, + "epoch": 0.13, + "learning_rate": 4.3416702087201635e-05, + "loss": 0.2488, "step": 59880 }, { - "epoch": 0.53, - "learning_rate": 2.348617241689938e-05, - "loss": 0.228, + "epoch": 0.13, + "learning_rate": 4.3415583543992306e-05, + "loss": 0.2501, "step": 59890 }, { - "epoch": 0.53, - "learning_rate": 2.3481668318169538e-05, - "loss": 0.2323, + "epoch": 0.13, + "learning_rate": 4.3414465000782984e-05, + "loss": 0.2452, "step": 59900 }, { - "epoch": 0.53, - "learning_rate": 2.347716421943969e-05, - "loss": 0.2321, + "epoch": 0.13, + "learning_rate": 4.3413346457573655e-05, + "loss": 0.2414, "step": 59910 }, { - "epoch": 0.53, - "learning_rate": 2.3472660120709846e-05, - "loss": 0.2281, + "epoch": 0.13, + "learning_rate": 4.341222791436433e-05, + "loss": 0.2485, "step": 59920 }, { - "epoch": 0.54, - "learning_rate": 2.3468156021980003e-05, - "loss": 0.2273, + "epoch": 0.13, + "learning_rate": 4.341110937115501e-05, + "loss": 0.2455, "step": 59930 }, { - "epoch": 0.54, - "learning_rate": 2.346365192325016e-05, - "loss": 0.2305, + "epoch": 0.13, + "learning_rate": 4.340999082794568e-05, + "loss": 0.2429, "step": 59940 }, { - "epoch": 0.54, - "learning_rate": 2.3459147824520315e-05, - "loss": 0.2261, + "epoch": 0.13, + "learning_rate": 4.340887228473636e-05, + "loss": 0.2437, "step": 59950 }, { - "epoch": 0.54, - "learning_rate": 2.345464372579047e-05, - "loss": 0.2237, + "epoch": 0.13, + "learning_rate": 4.340775374152704e-05, + "loss": 0.238, "step": 59960 }, { - "epoch": 0.54, - "learning_rate": 2.3450139627060626e-05, - "loss": 0.2318, + "epoch": 0.13, + "learning_rate": 4.3406635198317716e-05, + "loss": 0.2401, "step": 59970 }, { - "epoch": 0.54, - "learning_rate": 2.344563552833078e-05, - "loss": 0.2234, + "epoch": 0.13, + "learning_rate": 4.3405516655108394e-05, + "loss": 0.2385, "step": 59980 }, { - "epoch": 0.54, - "learning_rate": 2.3441131429600938e-05, - "loss": 0.2281, + "epoch": 0.13, + "learning_rate": 4.3404398111899065e-05, + "loss": 0.2432, "step": 59990 }, { - "epoch": 0.54, - "learning_rate": 2.3436627330871095e-05, - "loss": 0.2311, + "epoch": 0.13, + "learning_rate": 4.340327956868974e-05, + "loss": 0.24, "step": 60000 }, { - "epoch": 0.54, - "learning_rate": 2.343212323214125e-05, - "loss": 0.2289, + "epoch": 0.13, + "learning_rate": 4.3402161025480414e-05, + "loss": 0.2473, "step": 60010 }, { - "epoch": 0.54, - "learning_rate": 2.3427619133411404e-05, - "loss": 0.2313, + "epoch": 0.13, + "learning_rate": 4.340104248227109e-05, + "loss": 0.2437, "step": 60020 }, { - "epoch": 0.54, - "learning_rate": 2.342311503468156e-05, - "loss": 0.2346, + "epoch": 0.13, + "learning_rate": 4.339992393906177e-05, + "loss": 0.2462, "step": 60030 }, { - "epoch": 0.54, - "learning_rate": 2.341861093595172e-05, - "loss": 0.2265, + "epoch": 0.13, + "learning_rate": 4.339880539585244e-05, + "loss": 0.2443, "step": 60040 }, { - "epoch": 0.54, - "learning_rate": 2.3414106837221873e-05, - "loss": 0.2293, + "epoch": 0.13, + "learning_rate": 4.339768685264312e-05, + "loss": 0.2426, "step": 60050 }, { - "epoch": 0.54, - "learning_rate": 2.3409602738492027e-05, - "loss": 0.2261, + "epoch": 0.13, + "learning_rate": 4.33965683094338e-05, + "loss": 0.2471, "step": 60060 }, { - "epoch": 0.54, - "learning_rate": 2.3405098639762184e-05, - "loss": 0.2287, + "epoch": 0.13, + "learning_rate": 4.3395449766224475e-05, + "loss": 0.2438, "step": 60070 }, { - "epoch": 0.54, - "learning_rate": 2.3400594541032342e-05, - "loss": 0.2314, + "epoch": 0.13, + "learning_rate": 4.3394331223015146e-05, + "loss": 0.241, "step": 60080 }, { - "epoch": 0.54, - "learning_rate": 2.3396090442302496e-05, - "loss": 0.2292, + "epoch": 0.13, + "learning_rate": 4.3393212679805824e-05, + "loss": 0.2498, "step": 60090 }, { - "epoch": 0.54, - "learning_rate": 2.3391586343572653e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.33920941365965e-05, + "loss": 0.2483, "step": 60100 }, { - "epoch": 0.54, - "learning_rate": 2.3387082244842808e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.339097559338717e-05, + "loss": 0.244, "step": 60110 }, { - "epoch": 0.54, - "learning_rate": 2.338257814611296e-05, - "loss": 0.2302, + "epoch": 0.13, + "learning_rate": 4.338985705017785e-05, + "loss": 0.2503, "step": 60120 }, { - "epoch": 0.54, - "learning_rate": 2.337807404738312e-05, - "loss": 0.2319, + "epoch": 0.13, + "learning_rate": 4.338873850696852e-05, + "loss": 0.2462, "step": 60130 }, { - "epoch": 0.54, - "learning_rate": 2.3373569948653277e-05, - "loss": 0.2268, + "epoch": 0.13, + "learning_rate": 4.33876199637592e-05, + "loss": 0.241, "step": 60140 }, { - "epoch": 0.54, - "learning_rate": 2.3369065849923434e-05, - "loss": 0.2303, + "epoch": 0.13, + "learning_rate": 4.338650142054988e-05, + "loss": 0.2447, "step": 60150 }, { - "epoch": 0.54, - "learning_rate": 2.3364561751193588e-05, - "loss": 0.2286, + "epoch": 0.13, + "learning_rate": 4.3385382877340556e-05, + "loss": 0.2463, "step": 60160 }, { - "epoch": 0.54, - "learning_rate": 2.3360057652463742e-05, - "loss": 0.2344, + "epoch": 0.13, + "learning_rate": 4.3384264334131234e-05, + "loss": 0.2433, "step": 60170 }, { - "epoch": 0.54, - "learning_rate": 2.33555535537339e-05, - "loss": 0.229, + "epoch": 0.13, + "learning_rate": 4.3383145790921905e-05, + "loss": 0.2393, "step": 60180 }, { - "epoch": 0.54, - "learning_rate": 2.3351049455004054e-05, - "loss": 0.2342, + "epoch": 0.13, + "learning_rate": 4.338202724771258e-05, + "loss": 0.2437, "step": 60190 }, { - "epoch": 0.54, - "learning_rate": 2.334654535627421e-05, - "loss": 0.2343, + "epoch": 0.13, + "learning_rate": 4.338090870450326e-05, + "loss": 0.2445, "step": 60200 }, { - "epoch": 0.54, - "learning_rate": 2.3342041257544366e-05, - "loss": 0.233, + "epoch": 0.13, + "learning_rate": 4.337979016129393e-05, + "loss": 0.2442, "step": 60210 }, { - "epoch": 0.54, - "learning_rate": 2.3337537158814523e-05, - "loss": 0.2234, + "epoch": 0.13, + "learning_rate": 4.337867161808461e-05, + "loss": 0.2446, "step": 60220 }, { - "epoch": 0.54, - "learning_rate": 2.3333033060084677e-05, - "loss": 0.2308, + "epoch": 0.13, + "learning_rate": 4.337755307487528e-05, + "loss": 0.2497, "step": 60230 }, { - "epoch": 0.54, - "learning_rate": 2.3328528961354835e-05, - "loss": 0.233, + "epoch": 0.13, + "learning_rate": 4.337643453166596e-05, + "loss": 0.2449, "step": 60240 }, { - "epoch": 0.54, - "learning_rate": 2.3324024862624992e-05, - "loss": 0.2285, + "epoch": 0.13, + "learning_rate": 4.337531598845664e-05, + "loss": 0.248, "step": 60250 }, { - "epoch": 0.54, - "learning_rate": 2.3319520763895146e-05, - "loss": 0.2309, + "epoch": 0.13, + "learning_rate": 4.337419744524731e-05, + "loss": 0.2374, "step": 60260 }, { - "epoch": 0.54, - "learning_rate": 2.33150166651653e-05, - "loss": 0.2309, + "epoch": 0.13, + "learning_rate": 4.3373078902037986e-05, + "loss": 0.2425, "step": 60270 }, { - "epoch": 0.54, - "learning_rate": 2.3310512566435458e-05, - "loss": 0.2315, + "epoch": 0.13, + "learning_rate": 4.3371960358828664e-05, + "loss": 0.2454, "step": 60280 }, { - "epoch": 0.54, - "learning_rate": 2.3306008467705615e-05, - "loss": 0.2292, + "epoch": 0.13, + "learning_rate": 4.337084181561934e-05, + "loss": 0.2432, "step": 60290 }, { - "epoch": 0.54, - "learning_rate": 2.330150436897577e-05, - "loss": 0.2324, + "epoch": 0.13, + "learning_rate": 4.336972327241002e-05, + "loss": 0.2494, "step": 60300 }, { - "epoch": 0.54, - "learning_rate": 2.3297000270245924e-05, - "loss": 0.2313, + "epoch": 0.13, + "learning_rate": 4.336860472920069e-05, + "loss": 0.2508, "step": 60310 }, { - "epoch": 0.54, - "learning_rate": 2.329249617151608e-05, - "loss": 0.2288, + "epoch": 0.13, + "learning_rate": 4.336748618599137e-05, + "loss": 0.2424, "step": 60320 }, { - "epoch": 0.54, - "learning_rate": 2.3287992072786235e-05, - "loss": 0.2318, + "epoch": 0.13, + "learning_rate": 4.336636764278204e-05, + "loss": 0.2433, "step": 60330 }, { - "epoch": 0.54, - "learning_rate": 2.3283938383929376e-05, - "loss": 0.2316, + "epoch": 0.13, + "learning_rate": 4.336524909957272e-05, + "loss": 0.2429, "step": 60340 }, { - "epoch": 0.54, - "learning_rate": 2.3279434285199533e-05, - "loss": 0.224, + "epoch": 0.13, + "learning_rate": 4.3364130556363396e-05, + "loss": 0.2413, "step": 60350 }, { - "epoch": 0.54, - "learning_rate": 2.3274930186469687e-05, - "loss": 0.2301, + "epoch": 0.13, + "learning_rate": 4.336301201315407e-05, + "loss": 0.2487, "step": 60360 }, { - "epoch": 0.54, - "learning_rate": 2.3270426087739845e-05, - "loss": 0.2255, + "epoch": 0.13, + "learning_rate": 4.3361893469944745e-05, + "loss": 0.2461, "step": 60370 }, { - "epoch": 0.54, - "learning_rate": 2.3265921989010002e-05, - "loss": 0.2297, + "epoch": 0.13, + "learning_rate": 4.336077492673542e-05, + "loss": 0.2426, "step": 60380 }, { - "epoch": 0.54, - "learning_rate": 2.3261417890280156e-05, - "loss": 0.2275, + "epoch": 0.13, + "learning_rate": 4.33596563835261e-05, + "loss": 0.2411, "step": 60390 }, { - "epoch": 0.54, - "learning_rate": 2.325691379155031e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.335853784031677e-05, + "loss": 0.2498, "step": 60400 }, { - "epoch": 0.54, - "learning_rate": 2.3252409692820468e-05, - "loss": 0.2265, + "epoch": 0.13, + "learning_rate": 4.335741929710745e-05, + "loss": 0.2484, "step": 60410 }, { - "epoch": 0.54, - "learning_rate": 2.3247905594090625e-05, - "loss": 0.2202, + "epoch": 0.13, + "learning_rate": 4.335630075389813e-05, + "loss": 0.2453, "step": 60420 }, { - "epoch": 0.54, - "learning_rate": 2.324340149536078e-05, - "loss": 0.2309, + "epoch": 0.13, + "learning_rate": 4.33551822106888e-05, + "loss": 0.2439, "step": 60430 }, { - "epoch": 0.54, - "learning_rate": 2.3238897396630934e-05, - "loss": 0.2259, + "epoch": 0.13, + "learning_rate": 4.335406366747948e-05, + "loss": 0.2518, "step": 60440 }, { - "epoch": 0.54, - "learning_rate": 2.323439329790109e-05, - "loss": 0.2379, + "epoch": 0.13, + "learning_rate": 4.335294512427015e-05, + "loss": 0.2515, "step": 60450 }, { - "epoch": 0.54, - "learning_rate": 2.322988919917125e-05, - "loss": 0.2279, + "epoch": 0.13, + "learning_rate": 4.3351826581060826e-05, + "loss": 0.251, "step": 60460 }, { - "epoch": 0.54, - "learning_rate": 2.3225385100441403e-05, - "loss": 0.232, + "epoch": 0.13, + "learning_rate": 4.3350708037851504e-05, + "loss": 0.2446, "step": 60470 }, { - "epoch": 0.54, - "learning_rate": 2.322088100171156e-05, - "loss": 0.2295, + "epoch": 0.13, + "learning_rate": 4.334958949464218e-05, + "loss": 0.2499, "step": 60480 }, { - "epoch": 0.54, - "learning_rate": 2.3216376902981714e-05, - "loss": 0.223, + "epoch": 0.14, + "learning_rate": 4.334847095143286e-05, + "loss": 0.2405, "step": 60490 }, { - "epoch": 0.54, - "learning_rate": 2.3211872804251868e-05, - "loss": 0.2314, + "epoch": 0.14, + "learning_rate": 4.334735240822353e-05, + "loss": 0.2449, "step": 60500 }, { - "epoch": 0.54, - "learning_rate": 2.3207368705522026e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.334623386501421e-05, + "loss": 0.2492, "step": 60510 }, { - "epoch": 0.54, - "learning_rate": 2.3202864606792183e-05, - "loss": 0.2295, + "epoch": 0.14, + "learning_rate": 4.3345115321804887e-05, + "loss": 0.2457, "step": 60520 }, { - "epoch": 0.54, - "learning_rate": 2.3198360508062337e-05, - "loss": 0.2368, + "epoch": 0.14, + "learning_rate": 4.334399677859556e-05, + "loss": 0.24, "step": 60530 }, { - "epoch": 0.54, - "learning_rate": 2.319385640933249e-05, - "loss": 0.2285, + "epoch": 0.14, + "learning_rate": 4.3342878235386236e-05, + "loss": 0.2495, "step": 60540 }, { - "epoch": 0.54, - "learning_rate": 2.318935231060265e-05, - "loss": 0.2266, + "epoch": 0.14, + "learning_rate": 4.334175969217691e-05, + "loss": 0.2436, "step": 60550 }, { - "epoch": 0.54, - "learning_rate": 2.3184848211872806e-05, - "loss": 0.2253, + "epoch": 0.14, + "learning_rate": 4.3340641148967585e-05, + "loss": 0.2367, "step": 60560 }, { - "epoch": 0.54, - "learning_rate": 2.318034411314296e-05, - "loss": 0.2275, + "epoch": 0.14, + "learning_rate": 4.333952260575826e-05, + "loss": 0.246, "step": 60570 }, { - "epoch": 0.54, - "learning_rate": 2.3175840014413118e-05, - "loss": 0.2264, + "epoch": 0.14, + "learning_rate": 4.333840406254894e-05, + "loss": 0.2363, "step": 60580 }, { - "epoch": 0.54, - "learning_rate": 2.3171335915683272e-05, - "loss": 0.2227, + "epoch": 0.14, + "learning_rate": 4.333728551933962e-05, + "loss": 0.2433, "step": 60590 }, { - "epoch": 0.54, - "learning_rate": 2.316683181695343e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.333616697613029e-05, + "loss": 0.2396, "step": 60600 }, { - "epoch": 0.54, - "learning_rate": 2.3162327718223584e-05, - "loss": 0.2235, + "epoch": 0.14, + "learning_rate": 4.333504843292097e-05, + "loss": 0.2491, "step": 60610 }, { - "epoch": 0.54, - "learning_rate": 2.315782361949374e-05, - "loss": 0.2265, + "epoch": 0.14, + "learning_rate": 4.3333929889711645e-05, + "loss": 0.2437, "step": 60620 }, { - "epoch": 0.54, - "learning_rate": 2.3153319520763895e-05, - "loss": 0.2293, + "epoch": 0.14, + "learning_rate": 4.333281134650232e-05, + "loss": 0.2402, "step": 60630 }, { - "epoch": 0.54, - "learning_rate": 2.314881542203405e-05, - "loss": 0.2288, + "epoch": 0.14, + "learning_rate": 4.3331692803292995e-05, + "loss": 0.2445, "step": 60640 }, { - "epoch": 0.54, - "learning_rate": 2.3144311323304207e-05, - "loss": 0.2289, + "epoch": 0.14, + "learning_rate": 4.3330574260083666e-05, + "loss": 0.2445, "step": 60650 }, { - "epoch": 0.54, - "learning_rate": 2.3139807224574364e-05, - "loss": 0.2289, + "epoch": 0.14, + "learning_rate": 4.3329455716874344e-05, + "loss": 0.2493, "step": 60660 }, { - "epoch": 0.54, - "learning_rate": 2.3135303125844522e-05, - "loss": 0.2284, + "epoch": 0.14, + "learning_rate": 4.332833717366502e-05, + "loss": 0.2459, "step": 60670 }, { - "epoch": 0.54, - "learning_rate": 2.3130799027114676e-05, - "loss": 0.2266, + "epoch": 0.14, + "learning_rate": 4.332721863045569e-05, + "loss": 0.2438, "step": 60680 }, { - "epoch": 0.54, - "learning_rate": 2.312629492838483e-05, - "loss": 0.2227, + "epoch": 0.14, + "learning_rate": 4.332610008724638e-05, + "loss": 0.2403, "step": 60690 }, { - "epoch": 0.54, - "learning_rate": 2.3121790829654988e-05, - "loss": 0.2286, + "epoch": 0.14, + "learning_rate": 4.332498154403705e-05, + "loss": 0.2468, "step": 60700 }, { - "epoch": 0.54, - "learning_rate": 2.3117286730925142e-05, - "loss": 0.2285, + "epoch": 0.14, + "learning_rate": 4.3323863000827727e-05, + "loss": 0.2451, "step": 60710 }, { - "epoch": 0.54, - "learning_rate": 2.31127826321953e-05, - "loss": 0.2244, + "epoch": 0.14, + "learning_rate": 4.33227444576184e-05, + "loss": 0.2462, "step": 60720 }, { - "epoch": 0.54, - "learning_rate": 2.3108278533465453e-05, - "loss": 0.2222, + "epoch": 0.14, + "learning_rate": 4.3321625914409076e-05, + "loss": 0.2426, "step": 60730 }, { - "epoch": 0.54, - "learning_rate": 2.310377443473561e-05, - "loss": 0.2258, + "epoch": 0.14, + "learning_rate": 4.3320507371199754e-05, + "loss": 0.2381, "step": 60740 }, { - "epoch": 0.54, - "learning_rate": 2.3099270336005765e-05, - "loss": 0.2296, + "epoch": 0.14, + "learning_rate": 4.3319388827990425e-05, + "loss": 0.2433, "step": 60750 }, { - "epoch": 0.54, - "learning_rate": 2.3094766237275922e-05, - "loss": 0.2314, + "epoch": 0.14, + "learning_rate": 4.33182702847811e-05, + "loss": 0.2442, "step": 60760 }, { - "epoch": 0.54, - "learning_rate": 2.309026213854608e-05, - "loss": 0.2284, + "epoch": 0.14, + "learning_rate": 4.3317151741571774e-05, + "loss": 0.2458, "step": 60770 }, { - "epoch": 0.54, - "learning_rate": 2.3085758039816234e-05, - "loss": 0.2268, + "epoch": 0.14, + "learning_rate": 4.331603319836245e-05, + "loss": 0.2404, "step": 60780 }, { - "epoch": 0.54, - "learning_rate": 2.3081253941086388e-05, - "loss": 0.2255, + "epoch": 0.14, + "learning_rate": 4.331491465515313e-05, + "loss": 0.2456, "step": 60790 }, { - "epoch": 0.54, - "learning_rate": 2.3076749842356546e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.331379611194381e-05, + "loss": 0.2402, "step": 60800 }, { - "epoch": 0.54, - "learning_rate": 2.3072245743626703e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.3312677568734485e-05, + "loss": 0.2402, "step": 60810 }, { - "epoch": 0.54, - "learning_rate": 2.3067741644896857e-05, - "loss": 0.2315, + "epoch": 0.14, + "learning_rate": 4.3311559025525157e-05, + "loss": 0.2394, "step": 60820 }, { - "epoch": 0.54, - "learning_rate": 2.3063237546167015e-05, - "loss": 0.2316, + "epoch": 0.14, + "learning_rate": 4.3310440482315835e-05, + "loss": 0.2439, "step": 60830 }, { - "epoch": 0.54, - "learning_rate": 2.305873344743717e-05, - "loss": 0.2332, + "epoch": 0.14, + "learning_rate": 4.330932193910651e-05, + "loss": 0.2471, "step": 60840 }, { - "epoch": 0.54, - "learning_rate": 2.3054229348707323e-05, - "loss": 0.2286, + "epoch": 0.14, + "learning_rate": 4.3308203395897184e-05, + "loss": 0.2401, "step": 60850 }, { - "epoch": 0.54, - "learning_rate": 2.304972524997748e-05, - "loss": 0.2251, + "epoch": 0.14, + "learning_rate": 4.330708485268786e-05, + "loss": 0.2452, "step": 60860 }, { - "epoch": 0.54, - "learning_rate": 2.3045221151247638e-05, - "loss": 0.2235, + "epoch": 0.14, + "learning_rate": 4.330596630947853e-05, + "loss": 0.2436, "step": 60870 }, { - "epoch": 0.54, - "learning_rate": 2.3040717052517792e-05, - "loss": 0.2322, + "epoch": 0.14, + "learning_rate": 4.330484776626921e-05, + "loss": 0.248, "step": 60880 }, { - "epoch": 0.54, - "learning_rate": 2.3036212953787946e-05, - "loss": 0.2298, + "epoch": 0.14, + "learning_rate": 4.330372922305989e-05, + "loss": 0.2468, "step": 60890 }, { - "epoch": 0.54, - "learning_rate": 2.3031708855058104e-05, - "loss": 0.2302, + "epoch": 0.14, + "learning_rate": 4.3302610679850566e-05, + "loss": 0.2442, "step": 60900 }, { - "epoch": 0.54, - "learning_rate": 2.302720475632826e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.3301492136641244e-05, + "loss": 0.2425, "step": 60910 }, { - "epoch": 0.54, - "learning_rate": 2.3022700657598415e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.3300373593431916e-05, + "loss": 0.2424, "step": 60920 }, { - "epoch": 0.54, - "learning_rate": 2.3018196558868573e-05, - "loss": 0.2338, + "epoch": 0.14, + "learning_rate": 4.3299255050222593e-05, + "loss": 0.2453, "step": 60930 }, { - "epoch": 0.54, - "learning_rate": 2.3013692460138727e-05, - "loss": 0.2327, + "epoch": 0.14, + "learning_rate": 4.329813650701327e-05, + "loss": 0.247, "step": 60940 }, { - "epoch": 0.54, - "learning_rate": 2.3009188361408884e-05, - "loss": 0.2357, + "epoch": 0.14, + "learning_rate": 4.329701796380394e-05, + "loss": 0.2444, "step": 60950 }, { - "epoch": 0.54, - "learning_rate": 2.300468426267904e-05, - "loss": 0.2304, + "epoch": 0.14, + "learning_rate": 4.329589942059462e-05, + "loss": 0.2444, "step": 60960 }, { - "epoch": 0.54, - "learning_rate": 2.3000180163949196e-05, - "loss": 0.2295, + "epoch": 0.14, + "learning_rate": 4.329478087738529e-05, + "loss": 0.2425, "step": 60970 }, { - "epoch": 0.54, - "learning_rate": 2.299567606521935e-05, - "loss": 0.2303, + "epoch": 0.14, + "learning_rate": 4.329366233417597e-05, + "loss": 0.2395, "step": 60980 }, { - "epoch": 0.54, - "learning_rate": 2.2991171966489504e-05, - "loss": 0.2295, + "epoch": 0.14, + "learning_rate": 4.329254379096665e-05, + "loss": 0.2416, "step": 60990 }, { - "epoch": 0.54, - "learning_rate": 2.298666786775966e-05, - "loss": 0.2267, + "epoch": 0.14, + "learning_rate": 4.3291425247757325e-05, + "loss": 0.2438, "step": 61000 }, { - "epoch": 0.54, - "learning_rate": 2.298216376902982e-05, - "loss": 0.2271, + "epoch": 0.14, + "learning_rate": 4.3290306704548e-05, + "loss": 0.2421, "step": 61010 }, { - "epoch": 0.54, - "learning_rate": 2.2977659670299977e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.3289188161338675e-05, + "loss": 0.2467, "step": 61020 }, { - "epoch": 0.54, - "learning_rate": 2.297315557157013e-05, - "loss": 0.2303, + "epoch": 0.14, + "learning_rate": 4.328806961812935e-05, + "loss": 0.2434, "step": 61030 }, { - "epoch": 0.54, - "learning_rate": 2.2968651472840285e-05, - "loss": 0.2372, + "epoch": 0.14, + "learning_rate": 4.3286951074920024e-05, + "loss": 0.2445, "step": 61040 }, { - "epoch": 0.55, - "learning_rate": 2.2964147374110442e-05, - "loss": 0.2304, + "epoch": 0.14, + "learning_rate": 4.32858325317107e-05, + "loss": 0.2474, "step": 61050 }, { - "epoch": 0.55, - "learning_rate": 2.2959643275380596e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.328471398850138e-05, + "loss": 0.2402, "step": 61060 }, { - "epoch": 0.55, - "learning_rate": 2.2955139176650754e-05, - "loss": 0.2237, + "epoch": 0.14, + "learning_rate": 4.328359544529205e-05, + "loss": 0.2405, "step": 61070 }, { - "epoch": 0.55, - "learning_rate": 2.2950635077920908e-05, - "loss": 0.2292, + "epoch": 0.14, + "learning_rate": 4.328247690208273e-05, + "loss": 0.2421, "step": 61080 }, { - "epoch": 0.55, - "learning_rate": 2.2946130979191065e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.32813583588734e-05, + "loss": 0.2433, "step": 61090 }, { - "epoch": 0.55, - "learning_rate": 2.294162688046122e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.328023981566408e-05, + "loss": 0.2428, "step": 61100 }, { - "epoch": 0.55, - "learning_rate": 2.2937122781731377e-05, - "loss": 0.2287, + "epoch": 0.14, + "learning_rate": 4.327912127245476e-05, + "loss": 0.2446, "step": 61110 }, { - "epoch": 0.55, - "learning_rate": 2.2932618683001535e-05, - "loss": 0.233, + "epoch": 0.14, + "learning_rate": 4.3278002729245433e-05, + "loss": 0.2359, "step": 61120 }, { - "epoch": 0.55, - "learning_rate": 2.292811458427169e-05, - "loss": 0.2285, + "epoch": 0.14, + "learning_rate": 4.327688418603611e-05, + "loss": 0.2401, "step": 61130 }, { - "epoch": 0.55, - "learning_rate": 2.2923610485541843e-05, - "loss": 0.2326, + "epoch": 0.14, + "learning_rate": 4.327576564282678e-05, + "loss": 0.2459, "step": 61140 }, { - "epoch": 0.55, - "learning_rate": 2.2919106386812e-05, - "loss": 0.2263, + "epoch": 0.14, + "learning_rate": 4.327464709961746e-05, + "loss": 0.2457, "step": 61150 }, { - "epoch": 0.55, - "learning_rate": 2.2914602288082158e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.327352855640814e-05, + "loss": 0.2406, "step": 61160 }, { - "epoch": 0.55, - "learning_rate": 2.2910098189352312e-05, - "loss": 0.2224, + "epoch": 0.14, + "learning_rate": 4.327241001319881e-05, + "loss": 0.2433, "step": 61170 }, { - "epoch": 0.55, - "learning_rate": 2.2905594090622466e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.327129146998949e-05, + "loss": 0.2396, "step": 61180 }, { - "epoch": 0.55, - "learning_rate": 2.2901089991892623e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.327017292678016e-05, + "loss": 0.2417, "step": 61190 }, { - "epoch": 0.55, - "learning_rate": 2.2896585893162778e-05, - "loss": 0.2282, + "epoch": 0.14, + "learning_rate": 4.3269054383570837e-05, + "loss": 0.2414, "step": 61200 }, { - "epoch": 0.55, - "learning_rate": 2.2892081794432935e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.3267935840361514e-05, + "loss": 0.2393, "step": 61210 }, { - "epoch": 0.55, - "learning_rate": 2.2887577695703093e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.326681729715219e-05, + "loss": 0.2414, "step": 61220 }, { - "epoch": 0.55, - "learning_rate": 2.2883073596973247e-05, - "loss": 0.2235, + "epoch": 0.14, + "learning_rate": 4.326569875394287e-05, + "loss": 0.2402, "step": 61230 }, { - "epoch": 0.55, - "learning_rate": 2.28785694982434e-05, - "loss": 0.23, + "epoch": 0.14, + "learning_rate": 4.326458021073354e-05, + "loss": 0.2467, "step": 61240 }, { - "epoch": 0.55, - "learning_rate": 2.2874065399513558e-05, - "loss": 0.2261, + "epoch": 0.14, + "learning_rate": 4.326346166752422e-05, + "loss": 0.2399, "step": 61250 }, { - "epoch": 0.55, - "learning_rate": 2.2869561300783716e-05, - "loss": 0.2219, + "epoch": 0.14, + "learning_rate": 4.326245497863582e-05, + "loss": 0.2415, "step": 61260 }, { - "epoch": 0.55, - "learning_rate": 2.286505720205387e-05, - "loss": 0.2279, + "epoch": 0.14, + "learning_rate": 4.32613364354265e-05, + "loss": 0.2397, "step": 61270 }, { - "epoch": 0.55, - "learning_rate": 2.2860553103324024e-05, - "loss": 0.2302, + "epoch": 0.14, + "learning_rate": 4.3260217892217184e-05, + "loss": 0.237, "step": 61280 }, { - "epoch": 0.55, - "learning_rate": 2.285604900459418e-05, - "loss": 0.2317, + "epoch": 0.14, + "learning_rate": 4.3259099349007855e-05, + "loss": 0.2435, "step": 61290 }, { - "epoch": 0.55, - "learning_rate": 2.285154490586434e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.325798080579853e-05, + "loss": 0.2414, "step": 61300 }, { - "epoch": 0.55, - "learning_rate": 2.2847040807134493e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.3256862262589204e-05, + "loss": 0.2401, "step": 61310 }, { - "epoch": 0.55, - "learning_rate": 2.284253670840465e-05, - "loss": 0.2283, + "epoch": 0.14, + "learning_rate": 4.325574371937988e-05, + "loss": 0.2409, "step": 61320 }, { - "epoch": 0.55, - "learning_rate": 2.2838032609674805e-05, - "loss": 0.2283, + "epoch": 0.14, + "learning_rate": 4.325462517617056e-05, + "loss": 0.2417, "step": 61330 }, { - "epoch": 0.55, - "learning_rate": 2.283352851094496e-05, - "loss": 0.2232, + "epoch": 0.14, + "learning_rate": 4.325350663296123e-05, + "loss": 0.248, "step": 61340 }, { - "epoch": 0.55, - "learning_rate": 2.2829024412215116e-05, - "loss": 0.2278, + "epoch": 0.14, + "learning_rate": 4.325238808975191e-05, + "loss": 0.2384, "step": 61350 }, { - "epoch": 0.55, - "learning_rate": 2.2824520313485274e-05, - "loss": 0.2237, + "epoch": 0.14, + "learning_rate": 4.325126954654258e-05, + "loss": 0.2452, "step": 61360 }, { - "epoch": 0.55, - "learning_rate": 2.282001621475543e-05, - "loss": 0.2264, + "epoch": 0.14, + "learning_rate": 4.325015100333326e-05, + "loss": 0.2443, "step": 61370 }, { - "epoch": 0.55, - "learning_rate": 2.2815512116025582e-05, - "loss": 0.2285, + "epoch": 0.14, + "learning_rate": 4.3249032460123936e-05, + "loss": 0.2412, "step": 61380 }, { - "epoch": 0.55, - "learning_rate": 2.281100801729574e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.3247913916914614e-05, + "loss": 0.2408, "step": 61390 }, { - "epoch": 0.55, - "learning_rate": 2.2806503918565897e-05, - "loss": 0.2318, + "epoch": 0.14, + "learning_rate": 4.324679537370529e-05, + "loss": 0.2476, "step": 61400 }, { - "epoch": 0.55, - "learning_rate": 2.280199981983605e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.324567683049596e-05, + "loss": 0.2424, "step": 61410 }, { - "epoch": 0.55, - "learning_rate": 2.279749572110621e-05, - "loss": 0.2342, + "epoch": 0.14, + "learning_rate": 4.324455828728664e-05, + "loss": 0.2458, "step": 61420 }, { - "epoch": 0.55, - "learning_rate": 2.2792991622376363e-05, - "loss": 0.2297, + "epoch": 0.14, + "learning_rate": 4.324343974407731e-05, + "loss": 0.2423, "step": 61430 }, { - "epoch": 0.55, - "learning_rate": 2.278848752364652e-05, - "loss": 0.2283, + "epoch": 0.14, + "learning_rate": 4.324232120086799e-05, + "loss": 0.2414, "step": 61440 }, { - "epoch": 0.55, - "learning_rate": 2.2783983424916674e-05, - "loss": 0.2218, + "epoch": 0.14, + "learning_rate": 4.324120265765867e-05, + "loss": 0.2373, "step": 61450 }, { - "epoch": 0.55, - "learning_rate": 2.277947932618683e-05, - "loss": 0.2289, + "epoch": 0.14, + "learning_rate": 4.324008411444934e-05, + "loss": 0.2413, "step": 61460 }, { - "epoch": 0.55, - "learning_rate": 2.277497522745699e-05, - "loss": 0.2333, + "epoch": 0.14, + "learning_rate": 4.323896557124002e-05, + "loss": 0.2411, "step": 61470 }, { - "epoch": 0.55, - "learning_rate": 2.2770471128727143e-05, - "loss": 0.2334, + "epoch": 0.14, + "learning_rate": 4.3237847028030695e-05, + "loss": 0.2424, "step": 61480 }, { - "epoch": 0.55, - "learning_rate": 2.2765967029997297e-05, - "loss": 0.2282, + "epoch": 0.14, + "learning_rate": 4.323672848482137e-05, + "loss": 0.2438, "step": 61490 }, { - "epoch": 0.55, - "learning_rate": 2.2761462931267455e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.323560994161205e-05, + "loss": 0.2365, "step": 61500 }, { - "epoch": 0.55, - "learning_rate": 2.2756958832537612e-05, - "loss": 0.2278, + "epoch": 0.14, + "learning_rate": 4.323449139840272e-05, + "loss": 0.2399, "step": 61510 }, { - "epoch": 0.55, - "learning_rate": 2.2752454733807766e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.32333728551934e-05, + "loss": 0.244, "step": 61520 }, { - "epoch": 0.55, - "learning_rate": 2.274795063507792e-05, - "loss": 0.23, + "epoch": 0.14, + "learning_rate": 4.323225431198407e-05, + "loss": 0.2394, "step": 61530 }, { - "epoch": 0.55, - "learning_rate": 2.2743446536348078e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.323113576877475e-05, + "loss": 0.2444, "step": 61540 }, { - "epoch": 0.55, - "learning_rate": 2.2738942437618232e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.323001722556543e-05, + "loss": 0.2388, "step": 61550 }, { - "epoch": 0.55, - "learning_rate": 2.273443833888839e-05, - "loss": 0.2269, + "epoch": 0.14, + "learning_rate": 4.32288986823561e-05, + "loss": 0.2395, "step": 61560 }, { - "epoch": 0.55, - "learning_rate": 2.2729934240158547e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.3227780139146776e-05, + "loss": 0.2418, "step": 61570 }, { - "epoch": 0.55, - "learning_rate": 2.27254301414287e-05, - "loss": 0.2297, + "epoch": 0.14, + "learning_rate": 4.3226661595937454e-05, + "loss": 0.2497, "step": 61580 }, { - "epoch": 0.55, - "learning_rate": 2.2720926042698855e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.322554305272813e-05, + "loss": 0.2415, "step": 61590 }, { - "epoch": 0.55, - "learning_rate": 2.2716421943969013e-05, - "loss": 0.2269, + "epoch": 0.14, + "learning_rate": 4.322442450951881e-05, + "loss": 0.242, "step": 61600 }, { - "epoch": 0.55, - "learning_rate": 2.271191784523917e-05, - "loss": 0.2266, + "epoch": 0.14, + "learning_rate": 4.322330596630948e-05, + "loss": 0.2432, "step": 61610 }, { - "epoch": 0.55, - "learning_rate": 2.2707413746509324e-05, - "loss": 0.2234, + "epoch": 0.14, + "learning_rate": 4.322218742310016e-05, + "loss": 0.24, "step": 61620 }, { - "epoch": 0.55, - "learning_rate": 2.270290964777948e-05, - "loss": 0.2251, + "epoch": 0.14, + "learning_rate": 4.322106887989083e-05, + "loss": 0.2449, "step": 61630 }, { - "epoch": 0.55, - "learning_rate": 2.2698405549049636e-05, - "loss": 0.2295, + "epoch": 0.14, + "learning_rate": 4.321995033668151e-05, + "loss": 0.2405, "step": 61640 }, { - "epoch": 0.55, - "learning_rate": 2.2693901450319794e-05, - "loss": 0.2315, + "epoch": 0.14, + "learning_rate": 4.3218831793472186e-05, + "loss": 0.2417, "step": 61650 }, { - "epoch": 0.55, - "learning_rate": 2.2689397351589948e-05, - "loss": 0.2277, + "epoch": 0.14, + "learning_rate": 4.321771325026286e-05, + "loss": 0.2454, "step": 61660 }, { - "epoch": 0.55, - "learning_rate": 2.2684893252860105e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.3216594707053535e-05, + "loss": 0.2393, "step": 61670 }, { - "epoch": 0.55, - "learning_rate": 2.268038915413026e-05, - "loss": 0.2277, + "epoch": 0.14, + "learning_rate": 4.3215476163844206e-05, + "loss": 0.2434, "step": 61680 }, { - "epoch": 0.55, - "learning_rate": 2.2675885055400413e-05, - "loss": 0.2291, + "epoch": 0.14, + "learning_rate": 4.321435762063489e-05, + "loss": 0.2376, "step": 61690 }, { - "epoch": 0.55, - "learning_rate": 2.267138095667057e-05, - "loss": 0.2277, + "epoch": 0.14, + "learning_rate": 4.321323907742557e-05, + "loss": 0.2395, "step": 61700 }, { - "epoch": 0.55, - "learning_rate": 2.266687685794073e-05, - "loss": 0.2281, + "epoch": 0.14, + "learning_rate": 4.321212053421624e-05, + "loss": 0.2402, "step": 61710 }, { - "epoch": 0.55, - "learning_rate": 2.2662372759210886e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.321100199100692e-05, + "loss": 0.2434, "step": 61720 }, { - "epoch": 0.55, - "learning_rate": 2.2657868660481037e-05, - "loss": 0.2217, + "epoch": 0.14, + "learning_rate": 4.320988344779759e-05, + "loss": 0.2396, "step": 61730 }, { - "epoch": 0.55, - "learning_rate": 2.2653364561751194e-05, - "loss": 0.2176, + "epoch": 0.14, + "learning_rate": 4.320876490458827e-05, + "loss": 0.2435, "step": 61740 }, { - "epoch": 0.55, - "learning_rate": 2.264886046302135e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.320764636137894e-05, + "loss": 0.2416, "step": 61750 }, { - "epoch": 0.55, - "learning_rate": 2.2644356364291506e-05, - "loss": 0.2284, + "epoch": 0.14, + "learning_rate": 4.3206527818169616e-05, + "loss": 0.2393, "step": 61760 }, { - "epoch": 0.55, - "learning_rate": 2.2639852265561663e-05, - "loss": 0.2263, + "epoch": 0.14, + "learning_rate": 4.3205409274960294e-05, + "loss": 0.2402, "step": 61770 }, { - "epoch": 0.55, - "learning_rate": 2.2635348166831817e-05, - "loss": 0.2285, + "epoch": 0.14, + "learning_rate": 4.3204290731750965e-05, + "loss": 0.2393, "step": 61780 }, { - "epoch": 0.55, - "learning_rate": 2.2630844068101975e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.320317218854164e-05, + "loss": 0.2391, "step": 61790 }, { - "epoch": 0.55, - "learning_rate": 2.262633996937213e-05, - "loss": 0.2273, + "epoch": 0.14, + "learning_rate": 4.320205364533232e-05, + "loss": 0.2412, "step": 61800 }, { - "epoch": 0.55, - "learning_rate": 2.2621835870642286e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.3200935102123e-05, + "loss": 0.2472, "step": 61810 }, { - "epoch": 0.55, - "learning_rate": 2.2617331771912444e-05, - "loss": 0.2266, + "epoch": 0.14, + "learning_rate": 4.319981655891368e-05, + "loss": 0.2434, "step": 61820 }, { - "epoch": 0.55, - "learning_rate": 2.2612827673182595e-05, - "loss": 0.234, + "epoch": 0.14, + "learning_rate": 4.319869801570435e-05, + "loss": 0.2428, "step": 61830 }, { - "epoch": 0.55, - "learning_rate": 2.2608323574452752e-05, - "loss": 0.2323, + "epoch": 0.14, + "learning_rate": 4.3197579472495026e-05, + "loss": 0.2409, "step": 61840 }, { - "epoch": 0.55, - "learning_rate": 2.260381947572291e-05, - "loss": 0.2309, + "epoch": 0.14, + "learning_rate": 4.31964609292857e-05, + "loss": 0.2463, "step": 61850 }, { - "epoch": 0.55, - "learning_rate": 2.2599315376993067e-05, - "loss": 0.2269, + "epoch": 0.14, + "learning_rate": 4.3195342386076375e-05, + "loss": 0.2394, "step": 61860 }, { - "epoch": 0.55, - "learning_rate": 2.259481127826322e-05, - "loss": 0.2268, + "epoch": 0.14, + "learning_rate": 4.319422384286705e-05, + "loss": 0.2399, "step": 61870 }, { - "epoch": 0.55, - "learning_rate": 2.2590307179533375e-05, - "loss": 0.2255, + "epoch": 0.14, + "learning_rate": 4.3193105299657724e-05, + "loss": 0.2482, "step": 61880 }, { - "epoch": 0.55, - "learning_rate": 2.2585803080803533e-05, - "loss": 0.2253, + "epoch": 0.14, + "learning_rate": 4.31919867564484e-05, + "loss": 0.2418, "step": 61890 }, { - "epoch": 0.55, - "learning_rate": 2.2581298982073687e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.319086821323908e-05, + "loss": 0.235, "step": 61900 }, { - "epoch": 0.55, - "learning_rate": 2.2576794883343844e-05, - "loss": 0.2241, + "epoch": 0.14, + "learning_rate": 4.318974967002976e-05, + "loss": 0.2383, "step": 61910 }, { - "epoch": 0.55, - "learning_rate": 2.2572290784614002e-05, - "loss": 0.2334, + "epoch": 0.14, + "learning_rate": 4.3188631126820436e-05, + "loss": 0.2381, "step": 61920 }, { - "epoch": 0.55, - "learning_rate": 2.2567786685884156e-05, - "loss": 0.2181, + "epoch": 0.14, + "learning_rate": 4.318751258361111e-05, + "loss": 0.2437, "step": 61930 }, { - "epoch": 0.55, - "learning_rate": 2.256328258715431e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.3186394040401785e-05, + "loss": 0.2419, "step": 61940 }, { - "epoch": 0.55, - "learning_rate": 2.2558778488424467e-05, - "loss": 0.2278, + "epoch": 0.14, + "learning_rate": 4.3185275497192456e-05, + "loss": 0.242, "step": 61950 }, { - "epoch": 0.55, - "learning_rate": 2.2554274389694625e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.3184156953983134e-05, + "loss": 0.2421, "step": 61960 }, { - "epoch": 0.55, - "learning_rate": 2.254977029096478e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.318303841077381e-05, + "loss": 0.2379, "step": 61970 }, { - "epoch": 0.55, - "learning_rate": 2.2545266192234933e-05, - "loss": 0.2239, + "epoch": 0.14, + "learning_rate": 4.318191986756448e-05, + "loss": 0.2403, "step": 61980 }, { - "epoch": 0.55, - "learning_rate": 2.254076209350509e-05, - "loss": 0.228, + "epoch": 0.14, + "learning_rate": 4.318080132435516e-05, + "loss": 0.2461, "step": 61990 }, { - "epoch": 0.55, - "learning_rate": 2.2536257994775248e-05, - "loss": 0.2275, + "epoch": 0.14, + "learning_rate": 4.317968278114584e-05, + "loss": 0.2357, "step": 62000 }, { - "epoch": 0.55, - "learning_rate": 2.2531753896045402e-05, - "loss": 0.2229, + "epoch": 0.14, + "learning_rate": 4.317856423793652e-05, + "loss": 0.2362, "step": 62010 }, { - "epoch": 0.55, - "learning_rate": 2.252724979731556e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.3177445694727195e-05, + "loss": 0.2441, "step": 62020 }, { - "epoch": 0.55, - "learning_rate": 2.2522745698585714e-05, - "loss": 0.2233, + "epoch": 0.14, + "learning_rate": 4.3176327151517866e-05, + "loss": 0.2443, "step": 62030 }, { - "epoch": 0.55, - "learning_rate": 2.2518241599855868e-05, - "loss": 0.2191, + "epoch": 0.14, + "learning_rate": 4.3175208608308544e-05, + "loss": 0.2382, "step": 62040 }, { - "epoch": 0.55, - "learning_rate": 2.2513737501126025e-05, - "loss": 0.2275, + "epoch": 0.14, + "learning_rate": 4.3174090065099215e-05, + "loss": 0.2401, "step": 62050 }, { - "epoch": 0.55, - "learning_rate": 2.2509233402396183e-05, - "loss": 0.2312, + "epoch": 0.14, + "learning_rate": 4.317297152188989e-05, + "loss": 0.2418, "step": 62060 }, { - "epoch": 0.55, - "learning_rate": 2.2504729303666337e-05, - "loss": 0.2282, + "epoch": 0.14, + "learning_rate": 4.3171852978680564e-05, + "loss": 0.2413, "step": 62070 }, { - "epoch": 0.55, - "learning_rate": 2.250022520493649e-05, - "loss": 0.2323, + "epoch": 0.14, + "learning_rate": 4.317073443547124e-05, + "loss": 0.2432, "step": 62080 }, { - "epoch": 0.55, - "learning_rate": 2.249572110620665e-05, - "loss": 0.2246, + "epoch": 0.14, + "learning_rate": 4.316961589226192e-05, + "loss": 0.2452, "step": 62090 }, { - "epoch": 0.55, - "learning_rate": 2.2491217007476806e-05, - "loss": 0.2262, + "epoch": 0.14, + "learning_rate": 4.31684973490526e-05, + "loss": 0.2468, "step": 62100 }, { - "epoch": 0.55, - "learning_rate": 2.248671290874696e-05, - "loss": 0.2256, + "epoch": 0.14, + "learning_rate": 4.3167378805843276e-05, + "loss": 0.2438, "step": 62110 }, { - "epoch": 0.55, - "learning_rate": 2.2482208810017118e-05, - "loss": 0.2248, + "epoch": 0.14, + "learning_rate": 4.316626026263395e-05, + "loss": 0.2438, "step": 62120 }, { - "epoch": 0.55, - "learning_rate": 2.2477704711287272e-05, - "loss": 0.2234, + "epoch": 0.14, + "learning_rate": 4.3165141719424625e-05, + "loss": 0.2469, "step": 62130 }, { - "epoch": 0.55, - "learning_rate": 2.247320061255743e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.31640231762153e-05, + "loss": 0.2404, "step": 62140 }, { - "epoch": 0.55, - "learning_rate": 2.2468696513827583e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.3162904633005974e-05, + "loss": 0.2366, "step": 62150 }, { - "epoch": 0.55, - "learning_rate": 2.246419241509774e-05, - "loss": 0.233, + "epoch": 0.14, + "learning_rate": 4.316178608979665e-05, + "loss": 0.2457, "step": 62160 }, { - "epoch": 0.56, - "learning_rate": 2.2459688316367895e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.316066754658732e-05, + "loss": 0.2423, "step": 62170 }, { - "epoch": 0.56, - "learning_rate": 2.245518421763805e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.3159549003378e-05, + "loss": 0.2422, "step": 62180 }, { - "epoch": 0.56, - "learning_rate": 2.2450680118908207e-05, - "loss": 0.2265, + "epoch": 0.14, + "learning_rate": 4.315843046016868e-05, + "loss": 0.2437, "step": 62190 }, { - "epoch": 0.56, - "learning_rate": 2.2446176020178364e-05, - "loss": 0.2296, + "epoch": 0.14, + "learning_rate": 4.315731191695935e-05, + "loss": 0.242, "step": 62200 }, { - "epoch": 0.56, - "learning_rate": 2.244167192144852e-05, - "loss": 0.2265, + "epoch": 0.14, + "learning_rate": 4.315619337375003e-05, + "loss": 0.2412, "step": 62210 }, { - "epoch": 0.56, - "learning_rate": 2.2437167822718676e-05, - "loss": 0.2295, + "epoch": 0.14, + "learning_rate": 4.3155074830540706e-05, + "loss": 0.2411, "step": 62220 }, { - "epoch": 0.56, - "learning_rate": 2.243266372398883e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.3153956287331384e-05, + "loss": 0.2391, "step": 62230 }, { - "epoch": 0.56, - "learning_rate": 2.2428159625258987e-05, - "loss": 0.2262, + "epoch": 0.14, + "learning_rate": 4.315283774412206e-05, + "loss": 0.2405, "step": 62240 }, { - "epoch": 0.56, - "learning_rate": 2.242365552652914e-05, - "loss": 0.2222, + "epoch": 0.14, + "learning_rate": 4.315171920091273e-05, + "loss": 0.2375, "step": 62250 }, { - "epoch": 0.56, - "learning_rate": 2.24191514277993e-05, - "loss": 0.224, + "epoch": 0.14, + "learning_rate": 4.315060065770341e-05, + "loss": 0.2395, "step": 62260 }, { - "epoch": 0.56, - "learning_rate": 2.2414647329069456e-05, - "loss": 0.2274, + "epoch": 0.14, + "learning_rate": 4.314948211449408e-05, + "loss": 0.2391, "step": 62270 }, { - "epoch": 0.56, - "learning_rate": 2.241014323033961e-05, - "loss": 0.2238, + "epoch": 0.14, + "learning_rate": 4.314836357128476e-05, + "loss": 0.2401, "step": 62280 }, { - "epoch": 0.56, - "learning_rate": 2.2405639131609765e-05, - "loss": 0.2287, + "epoch": 0.14, + "learning_rate": 4.314724502807544e-05, + "loss": 0.2407, "step": 62290 }, { - "epoch": 0.56, - "learning_rate": 2.2401135032879922e-05, - "loss": 0.2191, + "epoch": 0.14, + "learning_rate": 4.314612648486611e-05, + "loss": 0.2383, "step": 62300 }, { - "epoch": 0.56, - "learning_rate": 2.239663093415008e-05, - "loss": 0.222, + "epoch": 0.14, + "learning_rate": 4.314500794165679e-05, + "loss": 0.2451, "step": 62310 }, { - "epoch": 0.56, - "learning_rate": 2.2392126835420234e-05, - "loss": 0.2296, + "epoch": 0.14, + "learning_rate": 4.3143889398447465e-05, + "loss": 0.2415, "step": 62320 }, { - "epoch": 0.56, - "learning_rate": 2.2387622736690388e-05, - "loss": 0.2246, + "epoch": 0.14, + "learning_rate": 4.314277085523814e-05, + "loss": 0.2379, "step": 62330 }, { - "epoch": 0.56, - "learning_rate": 2.2383118637960545e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.3141652312028814e-05, + "loss": 0.2408, "step": 62340 }, { - "epoch": 0.56, - "learning_rate": 2.2378614539230703e-05, - "loss": 0.2326, + "epoch": 0.14, + "learning_rate": 4.314053376881949e-05, + "loss": 0.2418, "step": 62350 }, { - "epoch": 0.56, - "learning_rate": 2.2374110440500857e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.313941522561017e-05, + "loss": 0.2428, "step": 62360 }, { - "epoch": 0.56, - "learning_rate": 2.2369606341771014e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.313829668240084e-05, + "loss": 0.2449, "step": 62370 }, { - "epoch": 0.56, - "learning_rate": 2.236510224304117e-05, - "loss": 0.2263, + "epoch": 0.14, + "learning_rate": 4.313717813919152e-05, + "loss": 0.2411, "step": 62380 }, { - "epoch": 0.56, - "learning_rate": 2.2360598144311323e-05, - "loss": 0.2267, + "epoch": 0.14, + "learning_rate": 4.313605959598219e-05, + "loss": 0.2404, "step": 62390 }, { - "epoch": 0.56, - "learning_rate": 2.235609404558148e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.313494105277287e-05, + "loss": 0.2372, "step": 62400 }, { - "epoch": 0.56, - "learning_rate": 2.2351589946851638e-05, - "loss": 0.2226, + "epoch": 0.14, + "learning_rate": 4.3133822509563546e-05, + "loss": 0.2426, "step": 62410 }, { - "epoch": 0.56, - "learning_rate": 2.2347085848121792e-05, - "loss": 0.2238, + "epoch": 0.14, + "learning_rate": 4.3132703966354224e-05, + "loss": 0.2399, "step": 62420 }, { - "epoch": 0.56, - "learning_rate": 2.2342581749391946e-05, - "loss": 0.2268, + "epoch": 0.14, + "learning_rate": 4.31315854231449e-05, + "loss": 0.2344, "step": 62430 }, { - "epoch": 0.56, - "learning_rate": 2.2338077650662103e-05, - "loss": 0.2244, + "epoch": 0.14, + "learning_rate": 4.313046687993557e-05, + "loss": 0.2457, "step": 62440 }, { - "epoch": 0.56, - "learning_rate": 2.233357355193226e-05, - "loss": 0.2266, + "epoch": 0.14, + "learning_rate": 4.312934833672625e-05, + "loss": 0.2413, "step": 62450 }, { - "epoch": 0.56, - "learning_rate": 2.2329069453202415e-05, - "loss": 0.2238, + "epoch": 0.14, + "learning_rate": 4.312822979351693e-05, + "loss": 0.2424, "step": 62460 }, { - "epoch": 0.56, - "learning_rate": 2.2324565354472572e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.31271112503076e-05, + "loss": 0.2424, "step": 62470 }, { - "epoch": 0.56, - "learning_rate": 2.2320061255742726e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.312599270709828e-05, + "loss": 0.2478, "step": 62480 }, { - "epoch": 0.56, - "learning_rate": 2.2315557157012884e-05, - "loss": 0.2309, + "epoch": 0.14, + "learning_rate": 4.312487416388895e-05, + "loss": 0.2468, "step": 62490 }, { - "epoch": 0.56, - "learning_rate": 2.2311053058283038e-05, - "loss": 0.223, + "epoch": 0.14, + "learning_rate": 4.312375562067963e-05, + "loss": 0.2403, "step": 62500 }, { - "epoch": 0.56, - "learning_rate": 2.2306548959553196e-05, - "loss": 0.2284, + "epoch": 0.14, + "learning_rate": 4.3122637077470305e-05, + "loss": 0.2426, "step": 62510 }, { - "epoch": 0.56, - "learning_rate": 2.230204486082335e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.312151853426098e-05, + "loss": 0.242, "step": 62520 }, { - "epoch": 0.56, - "learning_rate": 2.2297540762093504e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.312039999105166e-05, + "loss": 0.2435, "step": 62530 }, { - "epoch": 0.56, - "learning_rate": 2.229303666336366e-05, - "loss": 0.223, + "epoch": 0.14, + "learning_rate": 4.311928144784233e-05, + "loss": 0.2365, "step": 62540 }, { - "epoch": 0.56, - "learning_rate": 2.228853256463382e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.311816290463301e-05, + "loss": 0.2383, "step": 62550 }, { - "epoch": 0.56, - "learning_rate": 2.2284028465903976e-05, - "loss": 0.2269, + "epoch": 0.14, + "learning_rate": 4.311704436142369e-05, + "loss": 0.2407, "step": 62560 }, { - "epoch": 0.56, - "learning_rate": 2.227952436717413e-05, - "loss": 0.2207, + "epoch": 0.14, + "learning_rate": 4.311592581821436e-05, + "loss": 0.244, "step": 62570 }, { - "epoch": 0.56, - "learning_rate": 2.2275020268444284e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.311480727500504e-05, + "loss": 0.237, "step": 62580 }, { - "epoch": 0.56, - "learning_rate": 2.2270516169714442e-05, - "loss": 0.2183, + "epoch": 0.14, + "learning_rate": 4.311368873179571e-05, + "loss": 0.2348, "step": 62590 }, { - "epoch": 0.56, - "learning_rate": 2.2266012070984596e-05, - "loss": 0.2251, + "epoch": 0.14, + "learning_rate": 4.3112570188586386e-05, + "loss": 0.2403, "step": 62600 }, { - "epoch": 0.56, - "learning_rate": 2.2261507972254754e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.3111451645377064e-05, + "loss": 0.2397, "step": 62610 }, { - "epoch": 0.56, - "learning_rate": 2.2257003873524908e-05, - "loss": 0.2147, + "epoch": 0.14, + "learning_rate": 4.3110333102167735e-05, + "loss": 0.2347, "step": 62620 }, { - "epoch": 0.56, - "learning_rate": 2.2252499774795065e-05, - "loss": 0.2274, + "epoch": 0.14, + "learning_rate": 4.310921455895841e-05, + "loss": 0.2428, "step": 62630 }, { - "epoch": 0.56, - "learning_rate": 2.224799567606522e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.310809601574909e-05, + "loss": 0.2394, "step": 62640 }, { - "epoch": 0.56, - "learning_rate": 2.2243491577335377e-05, - "loss": 0.2323, + "epoch": 0.14, + "learning_rate": 4.310697747253977e-05, + "loss": 0.2365, "step": 62650 }, { - "epoch": 0.56, - "learning_rate": 2.2238987478605534e-05, - "loss": 0.2267, + "epoch": 0.14, + "learning_rate": 4.310585892933044e-05, + "loss": 0.2438, "step": 62660 }, { - "epoch": 0.56, - "learning_rate": 2.223448337987569e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.310474038612112e-05, + "loss": 0.239, "step": 62670 }, { - "epoch": 0.56, - "learning_rate": 2.2229979281145842e-05, - "loss": 0.2207, + "epoch": 0.14, + "learning_rate": 4.3103621842911796e-05, + "loss": 0.2419, "step": 62680 }, { - "epoch": 0.56, - "learning_rate": 2.2225475182416e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.310250329970247e-05, + "loss": 0.2414, "step": 62690 }, { - "epoch": 0.56, - "learning_rate": 2.2220971083686157e-05, - "loss": 0.2219, + "epoch": 0.14, + "learning_rate": 4.3101384756493145e-05, + "loss": 0.2402, "step": 62700 }, { - "epoch": 0.56, - "learning_rate": 2.221646698495631e-05, - "loss": 0.2203, + "epoch": 0.14, + "learning_rate": 4.3100266213283816e-05, + "loss": 0.2396, "step": 62710 }, { - "epoch": 0.56, - "learning_rate": 2.2211962886226466e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.3099147670074494e-05, + "loss": 0.2361, "step": 62720 }, { - "epoch": 0.56, - "learning_rate": 2.2207458787496623e-05, - "loss": 0.23, + "epoch": 0.14, + "learning_rate": 4.309802912686517e-05, + "loss": 0.2392, "step": 62730 }, { - "epoch": 0.56, - "learning_rate": 2.2202954688766777e-05, - "loss": 0.2332, + "epoch": 0.14, + "learning_rate": 4.309691058365585e-05, + "loss": 0.2408, "step": 62740 }, { - "epoch": 0.56, - "learning_rate": 2.2198450590036935e-05, - "loss": 0.2251, + "epoch": 0.14, + "learning_rate": 4.309579204044653e-05, + "loss": 0.239, "step": 62750 }, { - "epoch": 0.56, - "learning_rate": 2.2193946491307092e-05, - "loss": 0.2301, + "epoch": 0.14, + "learning_rate": 4.30946734972372e-05, + "loss": 0.238, "step": 62760 }, { - "epoch": 0.56, - "learning_rate": 2.2189442392577246e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.309355495402788e-05, + "loss": 0.2352, "step": 62770 }, { - "epoch": 0.56, - "learning_rate": 2.21849382938474e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.3092436410818555e-05, + "loss": 0.2447, "step": 62780 }, { - "epoch": 0.56, - "learning_rate": 2.2180434195117558e-05, - "loss": 0.2214, + "epoch": 0.14, + "learning_rate": 4.3091317867609226e-05, + "loss": 0.2377, "step": 62790 }, { - "epoch": 0.56, - "learning_rate": 2.2175930096387715e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.3090199324399904e-05, + "loss": 0.2398, "step": 62800 }, { - "epoch": 0.56, - "learning_rate": 2.2171876407530852e-05, - "loss": 0.222, + "epoch": 0.14, + "learning_rate": 4.3089080781190575e-05, + "loss": 0.2415, "step": 62810 }, { - "epoch": 0.56, - "learning_rate": 2.216737230880101e-05, - "loss": 0.2282, + "epoch": 0.14, + "learning_rate": 4.308796223798125e-05, + "loss": 0.2427, "step": 62820 }, { - "epoch": 0.56, - "learning_rate": 2.2162868210071167e-05, - "loss": 0.2312, + "epoch": 0.14, + "learning_rate": 4.308684369477193e-05, + "loss": 0.2439, "step": 62830 }, { - "epoch": 0.56, - "learning_rate": 2.215836411134132e-05, - "loss": 0.2355, + "epoch": 0.14, + "learning_rate": 4.308572515156261e-05, + "loss": 0.2436, "step": 62840 }, { - "epoch": 0.56, - "learning_rate": 2.2153860012611476e-05, - "loss": 0.234, + "epoch": 0.14, + "learning_rate": 4.308460660835329e-05, + "loss": 0.241, "step": 62850 }, { - "epoch": 0.56, - "learning_rate": 2.2149355913881633e-05, - "loss": 0.2296, + "epoch": 0.14, + "learning_rate": 4.308348806514396e-05, + "loss": 0.2401, "step": 62860 }, { - "epoch": 0.56, - "learning_rate": 2.214485181515179e-05, - "loss": 0.2298, + "epoch": 0.14, + "learning_rate": 4.3082369521934636e-05, + "loss": 0.2388, "step": 62870 }, { - "epoch": 0.56, - "learning_rate": 2.2140347716421945e-05, - "loss": 0.2332, + "epoch": 0.14, + "learning_rate": 4.3081250978725314e-05, + "loss": 0.239, "step": 62880 }, { - "epoch": 0.56, - "learning_rate": 2.2135843617692102e-05, - "loss": 0.2225, + "epoch": 0.14, + "learning_rate": 4.3080132435515985e-05, + "loss": 0.239, "step": 62890 }, { - "epoch": 0.56, - "learning_rate": 2.2131339518962256e-05, - "loss": 0.2242, + "epoch": 0.14, + "learning_rate": 4.307901389230666e-05, + "loss": 0.239, "step": 62900 }, { - "epoch": 0.56, - "learning_rate": 2.212683542023241e-05, - "loss": 0.228, + "epoch": 0.14, + "learning_rate": 4.3077895349097334e-05, + "loss": 0.2353, "step": 62910 }, { - "epoch": 0.56, - "learning_rate": 2.2122331321502568e-05, - "loss": 0.2196, + "epoch": 0.14, + "learning_rate": 4.307677680588801e-05, + "loss": 0.239, "step": 62920 }, { - "epoch": 0.56, - "learning_rate": 2.2117827222772725e-05, - "loss": 0.2297, + "epoch": 0.14, + "learning_rate": 4.307565826267869e-05, + "loss": 0.2436, "step": 62930 }, { - "epoch": 0.56, - "learning_rate": 2.2113323124042883e-05, - "loss": 0.2303, + "epoch": 0.14, + "learning_rate": 4.307453971946937e-05, + "loss": 0.24, "step": 62940 }, { - "epoch": 0.56, - "learning_rate": 2.2108819025313034e-05, - "loss": 0.2248, + "epoch": 0.14, + "learning_rate": 4.3073421176260046e-05, + "loss": 0.2382, "step": 62950 }, { - "epoch": 0.56, - "learning_rate": 2.210431492658319e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.307230263305072e-05, + "loss": 0.2356, "step": 62960 }, { - "epoch": 0.56, - "learning_rate": 2.209981082785335e-05, - "loss": 0.2197, + "epoch": 0.14, + "learning_rate": 4.3071184089841395e-05, + "loss": 0.2395, "step": 62970 }, { - "epoch": 0.56, - "learning_rate": 2.2095306729123503e-05, - "loss": 0.2262, + "epoch": 0.14, + "learning_rate": 4.3070065546632066e-05, + "loss": 0.2369, "step": 62980 }, { - "epoch": 0.56, - "learning_rate": 2.209080263039366e-05, - "loss": 0.2224, + "epoch": 0.14, + "learning_rate": 4.3068947003422744e-05, + "loss": 0.2443, "step": 62990 }, { - "epoch": 0.56, - "learning_rate": 2.2086298531663814e-05, - "loss": 0.2204, + "epoch": 0.14, + "learning_rate": 4.306782846021342e-05, + "loss": 0.2392, "step": 63000 }, { - "epoch": 0.56, - "learning_rate": 2.2081794432933972e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.306670991700409e-05, + "loss": 0.2352, "step": 63010 }, { - "epoch": 0.56, - "learning_rate": 2.2077290334204126e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.306559137379477e-05, + "loss": 0.2359, "step": 63020 }, { - "epoch": 0.56, - "learning_rate": 2.2072786235474283e-05, - "loss": 0.2265, + "epoch": 0.14, + "learning_rate": 4.306447283058544e-05, + "loss": 0.2381, "step": 63030 }, { - "epoch": 0.56, - "learning_rate": 2.206828213674444e-05, - "loss": 0.228, + "epoch": 0.14, + "learning_rate": 4.306335428737612e-05, + "loss": 0.2419, "step": 63040 }, { - "epoch": 0.56, - "learning_rate": 2.206377803801459e-05, - "loss": 0.2214, + "epoch": 0.14, + "learning_rate": 4.3062235744166805e-05, + "loss": 0.2406, "step": 63050 }, { - "epoch": 0.56, - "learning_rate": 2.205927393928475e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.3061117200957476e-05, + "loss": 0.2339, "step": 63060 }, { - "epoch": 0.56, - "learning_rate": 2.2054769840554907e-05, - "loss": 0.2238, + "epoch": 0.14, + "learning_rate": 4.3059998657748154e-05, + "loss": 0.2411, "step": 63070 }, { - "epoch": 0.56, - "learning_rate": 2.2050265741825064e-05, - "loss": 0.2241, + "epoch": 0.14, + "learning_rate": 4.3058880114538825e-05, + "loss": 0.2431, "step": 63080 }, { - "epoch": 0.56, - "learning_rate": 2.2045761643095218e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.30577615713295e-05, + "loss": 0.2411, "step": 63090 }, { - "epoch": 0.56, - "learning_rate": 2.2041257544365372e-05, - "loss": 0.2194, + "epoch": 0.14, + "learning_rate": 4.305664302812018e-05, + "loss": 0.2388, "step": 63100 }, { - "epoch": 0.56, - "learning_rate": 2.203675344563553e-05, - "loss": 0.231, + "epoch": 0.14, + "learning_rate": 4.305552448491085e-05, + "loss": 0.2464, "step": 63110 }, { - "epoch": 0.56, - "learning_rate": 2.2032249346905684e-05, - "loss": 0.2217, + "epoch": 0.14, + "learning_rate": 4.305440594170153e-05, + "loss": 0.2356, "step": 63120 }, { - "epoch": 0.56, - "learning_rate": 2.202774524817584e-05, - "loss": 0.2268, + "epoch": 0.14, + "learning_rate": 4.30532873984922e-05, + "loss": 0.2471, "step": 63130 }, { - "epoch": 0.56, - "learning_rate": 2.2023241149446e-05, - "loss": 0.2258, + "epoch": 0.14, + "learning_rate": 4.305216885528288e-05, + "loss": 0.2398, "step": 63140 }, { - "epoch": 0.56, - "learning_rate": 2.2018737050716153e-05, - "loss": 0.2237, + "epoch": 0.14, + "learning_rate": 4.305105031207356e-05, + "loss": 0.235, "step": 63150 }, { - "epoch": 0.56, - "learning_rate": 2.2014232951986307e-05, - "loss": 0.2231, + "epoch": 0.14, + "learning_rate": 4.3049931768864235e-05, + "loss": 0.2379, "step": 63160 }, { - "epoch": 0.56, - "learning_rate": 2.2009728853256465e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.304881322565491e-05, + "loss": 0.2431, "step": 63170 }, { - "epoch": 0.56, - "learning_rate": 2.2005224754526622e-05, - "loss": 0.222, + "epoch": 0.14, + "learning_rate": 4.3047694682445584e-05, + "loss": 0.2383, "step": 63180 }, { - "epoch": 0.56, - "learning_rate": 2.2000720655796776e-05, - "loss": 0.2315, + "epoch": 0.14, + "learning_rate": 4.304657613923626e-05, + "loss": 0.2362, "step": 63190 }, { - "epoch": 0.56, - "learning_rate": 2.199621655706693e-05, - "loss": 0.2177, + "epoch": 0.14, + "learning_rate": 4.304545759602694e-05, + "loss": 0.2388, "step": 63200 }, { - "epoch": 0.56, - "learning_rate": 2.1991712458337088e-05, - "loss": 0.2233, + "epoch": 0.14, + "learning_rate": 4.304433905281761e-05, + "loss": 0.2388, "step": 63210 }, { - "epoch": 0.56, - "learning_rate": 2.1987208359607245e-05, - "loss": 0.2238, + "epoch": 0.14, + "learning_rate": 4.304322050960829e-05, + "loss": 0.2344, "step": 63220 }, { - "epoch": 0.56, - "learning_rate": 2.19827042608774e-05, - "loss": 0.2183, + "epoch": 0.14, + "learning_rate": 4.304210196639896e-05, + "loss": 0.2345, "step": 63230 }, { - "epoch": 0.56, - "learning_rate": 2.1978200162147557e-05, - "loss": 0.2239, + "epoch": 0.14, + "learning_rate": 4.304098342318964e-05, + "loss": 0.2371, "step": 63240 }, { - "epoch": 0.56, - "learning_rate": 2.197369606341771e-05, - "loss": 0.2211, + "epoch": 0.14, + "learning_rate": 4.3039864879980316e-05, + "loss": 0.2446, "step": 63250 }, { - "epoch": 0.56, - "learning_rate": 2.1969191964687865e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.3038746336770994e-05, + "loss": 0.2425, "step": 63260 }, { - "epoch": 0.56, - "learning_rate": 2.1964687865958023e-05, - "loss": 0.221, + "epoch": 0.14, + "learning_rate": 4.303762779356167e-05, + "loss": 0.2375, "step": 63270 }, { - "epoch": 0.56, - "learning_rate": 2.196018376722818e-05, - "loss": 0.2248, + "epoch": 0.14, + "learning_rate": 4.303650925035234e-05, + "loss": 0.2382, "step": 63280 }, { - "epoch": 0.57, - "learning_rate": 2.1955679668498334e-05, - "loss": 0.2208, + "epoch": 0.14, + "learning_rate": 4.303539070714302e-05, + "loss": 0.2433, "step": 63290 }, { - "epoch": 0.57, - "learning_rate": 2.1951175569768488e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.303438401825462e-05, + "loss": 0.2382, "step": 63300 }, { - "epoch": 0.57, - "learning_rate": 2.1946671471038646e-05, - "loss": 0.22, + "epoch": 0.14, + "learning_rate": 4.30332654750453e-05, + "loss": 0.2372, "step": 63310 }, { - "epoch": 0.57, - "learning_rate": 2.1942167372308803e-05, - "loss": 0.2173, + "epoch": 0.14, + "learning_rate": 4.303214693183598e-05, + "loss": 0.235, "step": 63320 }, { - "epoch": 0.57, - "learning_rate": 2.1937663273578957e-05, - "loss": 0.22, + "epoch": 0.14, + "learning_rate": 4.3031028388626656e-05, + "loss": 0.2379, "step": 63330 }, { - "epoch": 0.57, - "learning_rate": 2.1933159174849115e-05, - "loss": 0.221, + "epoch": 0.14, + "learning_rate": 4.3029909845417334e-05, + "loss": 0.2363, "step": 63340 }, { - "epoch": 0.57, - "learning_rate": 2.192865507611927e-05, - "loss": 0.2218, + "epoch": 0.14, + "learning_rate": 4.3028791302208005e-05, + "loss": 0.2379, "step": 63350 }, { - "epoch": 0.57, - "learning_rate": 2.1924150977389426e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.3027672758998683e-05, + "loss": 0.2406, "step": 63360 }, { - "epoch": 0.57, - "learning_rate": 2.191964687865958e-05, - "loss": 0.2214, + "epoch": 0.14, + "learning_rate": 4.3026554215789355e-05, + "loss": 0.2398, "step": 63370 }, { - "epoch": 0.57, - "learning_rate": 2.1915142779929738e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.302543567258003e-05, + "loss": 0.2355, "step": 63380 }, { - "epoch": 0.57, - "learning_rate": 2.1910638681199892e-05, - "loss": 0.2304, + "epoch": 0.14, + "learning_rate": 4.302431712937071e-05, + "loss": 0.2421, "step": 63390 }, { - "epoch": 0.57, - "learning_rate": 2.1906134582470046e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.302319858616138e-05, + "loss": 0.2391, "step": 63400 }, { - "epoch": 0.57, - "learning_rate": 2.1901630483740204e-05, - "loss": 0.2262, + "epoch": 0.14, + "learning_rate": 4.302208004295206e-05, + "loss": 0.2455, "step": 63410 }, { - "epoch": 0.57, - "learning_rate": 2.189712638501036e-05, - "loss": 0.2256, + "epoch": 0.14, + "learning_rate": 4.302096149974274e-05, + "loss": 0.2385, "step": 63420 }, { - "epoch": 0.57, - "learning_rate": 2.189262228628052e-05, - "loss": 0.2317, + "epoch": 0.14, + "learning_rate": 4.3019842956533415e-05, + "loss": 0.2361, "step": 63430 }, { - "epoch": 0.57, - "learning_rate": 2.1888118187550673e-05, - "loss": 0.2248, + "epoch": 0.14, + "learning_rate": 4.301872441332409e-05, + "loss": 0.2357, "step": 63440 }, { - "epoch": 0.57, - "learning_rate": 2.1883614088820827e-05, - "loss": 0.2097, + "epoch": 0.14, + "learning_rate": 4.3017605870114764e-05, + "loss": 0.2355, "step": 63450 }, { - "epoch": 0.57, - "learning_rate": 2.1879109990090984e-05, - "loss": 0.2217, + "epoch": 0.14, + "learning_rate": 4.301648732690544e-05, + "loss": 0.2458, "step": 63460 }, { - "epoch": 0.57, - "learning_rate": 2.187460589136114e-05, - "loss": 0.223, + "epoch": 0.14, + "learning_rate": 4.3015368783696113e-05, + "loss": 0.2352, "step": 63470 }, { - "epoch": 0.57, - "learning_rate": 2.1870101792631296e-05, - "loss": 0.2246, + "epoch": 0.14, + "learning_rate": 4.301425024048679e-05, + "loss": 0.2391, "step": 63480 }, { - "epoch": 0.57, - "learning_rate": 2.186559769390145e-05, - "loss": 0.2203, + "epoch": 0.14, + "learning_rate": 4.301313169727747e-05, + "loss": 0.2432, "step": 63490 }, { - "epoch": 0.57, - "learning_rate": 2.1861093595171608e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.301201315406814e-05, + "loss": 0.236, "step": 63500 }, { - "epoch": 0.57, - "learning_rate": 2.185658949644176e-05, - "loss": 0.2287, + "epoch": 0.14, + "learning_rate": 4.301089461085882e-05, + "loss": 0.2406, "step": 63510 }, { - "epoch": 0.57, - "learning_rate": 2.185208539771192e-05, - "loss": 0.2283, + "epoch": 0.14, + "learning_rate": 4.3009776067649496e-05, + "loss": 0.2396, "step": 63520 }, { - "epoch": 0.57, - "learning_rate": 2.1847581298982077e-05, - "loss": 0.2196, + "epoch": 0.14, + "learning_rate": 4.3008657524440174e-05, + "loss": 0.2388, "step": 63530 }, { - "epoch": 0.57, - "learning_rate": 2.184307720025223e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.300753898123085e-05, + "loss": 0.2315, "step": 63540 }, { - "epoch": 0.57, - "learning_rate": 2.1838573101522385e-05, - "loss": 0.2179, + "epoch": 0.14, + "learning_rate": 4.300642043802152e-05, + "loss": 0.2389, "step": 63550 }, { - "epoch": 0.57, - "learning_rate": 2.1834069002792542e-05, - "loss": 0.2182, + "epoch": 0.14, + "learning_rate": 4.30053018948122e-05, + "loss": 0.2389, "step": 63560 }, { - "epoch": 0.57, - "learning_rate": 2.18295649040627e-05, - "loss": 0.2196, + "epoch": 0.14, + "learning_rate": 4.300418335160287e-05, + "loss": 0.2405, "step": 63570 }, { - "epoch": 0.57, - "learning_rate": 2.1825060805332854e-05, - "loss": 0.2226, + "epoch": 0.14, + "learning_rate": 4.300306480839355e-05, + "loss": 0.2381, "step": 63580 }, { - "epoch": 0.57, - "learning_rate": 2.182055670660301e-05, - "loss": 0.2271, + "epoch": 0.14, + "learning_rate": 4.300194626518423e-05, + "loss": 0.2407, "step": 63590 }, { - "epoch": 0.57, - "learning_rate": 2.1816052607873166e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.30008277219749e-05, + "loss": 0.2402, "step": 63600 }, { - "epoch": 0.57, - "learning_rate": 2.181154850914332e-05, - "loss": 0.2208, + "epoch": 0.14, + "learning_rate": 4.299970917876558e-05, + "loss": 0.2406, "step": 63610 }, { - "epoch": 0.57, - "learning_rate": 2.1807044410413477e-05, - "loss": 0.2198, + "epoch": 0.14, + "learning_rate": 4.299859063555625e-05, + "loss": 0.2349, "step": 63620 }, { - "epoch": 0.57, - "learning_rate": 2.1802540311683635e-05, - "loss": 0.2232, + "epoch": 0.14, + "learning_rate": 4.299747209234693e-05, + "loss": 0.2394, "step": 63630 }, { - "epoch": 0.57, - "learning_rate": 2.179803621295379e-05, - "loss": 0.2223, + "epoch": 0.14, + "learning_rate": 4.299635354913761e-05, + "loss": 0.2421, "step": 63640 }, { - "epoch": 0.57, - "learning_rate": 2.1793532114223943e-05, - "loss": 0.2271, + "epoch": 0.14, + "learning_rate": 4.299523500592828e-05, + "loss": 0.2385, "step": 63650 }, { - "epoch": 0.57, - "learning_rate": 2.17890280154941e-05, - "loss": 0.2185, + "epoch": 0.14, + "learning_rate": 4.299411646271896e-05, + "loss": 0.2402, "step": 63660 }, { - "epoch": 0.57, - "learning_rate": 2.1784523916764258e-05, - "loss": 0.2302, + "epoch": 0.14, + "learning_rate": 4.299299791950963e-05, + "loss": 0.2442, "step": 63670 }, { - "epoch": 0.57, - "learning_rate": 2.1780019818034412e-05, - "loss": 0.2265, + "epoch": 0.14, + "learning_rate": 4.299187937630031e-05, + "loss": 0.2445, "step": 63680 }, { - "epoch": 0.57, - "learning_rate": 2.177551571930457e-05, - "loss": 0.2299, + "epoch": 0.14, + "learning_rate": 4.299076083309098e-05, + "loss": 0.2377, "step": 63690 }, { - "epoch": 0.57, - "learning_rate": 2.1771011620574724e-05, - "loss": 0.2215, + "epoch": 0.14, + "learning_rate": 4.298964228988166e-05, + "loss": 0.2461, "step": 63700 }, { - "epoch": 0.57, - "learning_rate": 2.176650752184488e-05, - "loss": 0.2273, + "epoch": 0.14, + "learning_rate": 4.2988523746672336e-05, + "loss": 0.238, "step": 63710 }, { - "epoch": 0.57, - "learning_rate": 2.1762003423115035e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.298740520346301e-05, + "loss": 0.2363, "step": 63720 }, { - "epoch": 0.57, - "learning_rate": 2.1757499324385193e-05, - "loss": 0.2232, + "epoch": 0.14, + "learning_rate": 4.2986286660253685e-05, + "loss": 0.2335, "step": 63730 }, { - "epoch": 0.57, - "learning_rate": 2.1752995225655347e-05, - "loss": 0.2217, + "epoch": 0.14, + "learning_rate": 4.298516811704436e-05, + "loss": 0.2389, "step": 63740 }, { - "epoch": 0.57, - "learning_rate": 2.17484911269255e-05, - "loss": 0.2162, + "epoch": 0.14, + "learning_rate": 4.298404957383504e-05, + "loss": 0.2433, "step": 63750 }, { - "epoch": 0.57, - "learning_rate": 2.174398702819566e-05, - "loss": 0.2234, + "epoch": 0.14, + "learning_rate": 4.298293103062572e-05, + "loss": 0.2367, "step": 63760 }, { - "epoch": 0.57, - "learning_rate": 2.1739482929465816e-05, - "loss": 0.2185, + "epoch": 0.14, + "learning_rate": 4.298181248741639e-05, + "loss": 0.2433, "step": 63770 }, { - "epoch": 0.57, - "learning_rate": 2.1734978830735973e-05, - "loss": 0.2179, + "epoch": 0.14, + "learning_rate": 4.298069394420707e-05, + "loss": 0.2392, "step": 63780 }, { - "epoch": 0.57, - "learning_rate": 2.1730474732006127e-05, - "loss": 0.2227, + "epoch": 0.14, + "learning_rate": 4.297957540099774e-05, + "loss": 0.2411, "step": 63790 }, { - "epoch": 0.57, - "learning_rate": 2.172597063327628e-05, - "loss": 0.227, + "epoch": 0.14, + "learning_rate": 4.297845685778842e-05, + "loss": 0.2355, "step": 63800 }, { - "epoch": 0.57, - "learning_rate": 2.172146653454644e-05, - "loss": 0.2243, + "epoch": 0.14, + "learning_rate": 4.2977338314579095e-05, + "loss": 0.2371, "step": 63810 }, { - "epoch": 0.57, - "learning_rate": 2.1716962435816593e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.2976219771369766e-05, + "loss": 0.2388, "step": 63820 }, { - "epoch": 0.57, - "learning_rate": 2.171245833708675e-05, - "loss": 0.2262, + "epoch": 0.14, + "learning_rate": 4.2975101228160444e-05, + "loss": 0.237, "step": 63830 }, { - "epoch": 0.57, - "learning_rate": 2.1707954238356905e-05, - "loss": 0.2215, + "epoch": 0.14, + "learning_rate": 4.297398268495112e-05, + "loss": 0.2411, "step": 63840 }, { - "epoch": 0.57, - "learning_rate": 2.1703450139627062e-05, - "loss": 0.2261, + "epoch": 0.14, + "learning_rate": 4.29728641417418e-05, + "loss": 0.2371, "step": 63850 }, { - "epoch": 0.57, - "learning_rate": 2.1698946040897216e-05, - "loss": 0.2271, + "epoch": 0.14, + "learning_rate": 4.297174559853248e-05, + "loss": 0.2442, "step": 63860 }, { - "epoch": 0.57, - "learning_rate": 2.1694441942167374e-05, - "loss": 0.2195, + "epoch": 0.14, + "learning_rate": 4.297062705532315e-05, + "loss": 0.2367, "step": 63870 }, { - "epoch": 0.57, - "learning_rate": 2.168993784343753e-05, - "loss": 0.2222, + "epoch": 0.14, + "learning_rate": 4.296950851211383e-05, + "loss": 0.2332, "step": 63880 }, { - "epoch": 0.57, - "learning_rate": 2.1685433744707685e-05, - "loss": 0.2203, + "epoch": 0.14, + "learning_rate": 4.29683899689045e-05, + "loss": 0.2435, "step": 63890 }, { - "epoch": 0.57, - "learning_rate": 2.168092964597784e-05, - "loss": 0.2229, + "epoch": 0.14, + "learning_rate": 4.2967271425695176e-05, + "loss": 0.2389, "step": 63900 }, { - "epoch": 0.57, - "learning_rate": 2.1676425547247997e-05, - "loss": 0.2215, + "epoch": 0.14, + "learning_rate": 4.2966152882485854e-05, + "loss": 0.2422, "step": 63910 }, { - "epoch": 0.57, - "learning_rate": 2.1671921448518154e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.2965034339276525e-05, + "loss": 0.2401, "step": 63920 }, { - "epoch": 0.57, - "learning_rate": 2.166741734978831e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.29639157960672e-05, + "loss": 0.2449, "step": 63930 }, { - "epoch": 0.57, - "learning_rate": 2.1662913251058463e-05, - "loss": 0.2205, + "epoch": 0.14, + "learning_rate": 4.296279725285788e-05, + "loss": 0.2408, "step": 63940 }, { - "epoch": 0.57, - "learning_rate": 2.165840915232862e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.296167870964856e-05, + "loss": 0.238, "step": 63950 }, { - "epoch": 0.57, - "learning_rate": 2.1653905053598774e-05, - "loss": 0.2189, + "epoch": 0.14, + "learning_rate": 4.296056016643924e-05, + "loss": 0.2331, "step": 63960 }, { - "epoch": 0.57, - "learning_rate": 2.1649400954868932e-05, - "loss": 0.2226, + "epoch": 0.14, + "learning_rate": 4.295944162322991e-05, + "loss": 0.2341, "step": 63970 }, { - "epoch": 0.57, - "learning_rate": 2.164489685613909e-05, - "loss": 0.2276, + "epoch": 0.14, + "learning_rate": 4.2958323080020586e-05, + "loss": 0.2385, "step": 63980 }, { - "epoch": 0.57, - "learning_rate": 2.1640392757409243e-05, - "loss": 0.2272, + "epoch": 0.14, + "learning_rate": 4.295720453681126e-05, + "loss": 0.2385, "step": 63990 }, { - "epoch": 0.57, - "learning_rate": 2.1635888658679397e-05, - "loss": 0.2168, + "epoch": 0.14, + "learning_rate": 4.2956085993601935e-05, + "loss": 0.2392, "step": 64000 }, { - "epoch": 0.57, - "eval_NEIMS_canon_smiles": 0.9400666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.03925, - "eval_NEIMS_daylight_tanimoto_simil": 0.4345703712458914, - "eval_NEIMS_exact_mols": 0.03911666666666667, - "eval_NEIMS_exact_smiles": 0.037816666666666665, - "eval_NEIMS_loss": 0.24026688933372498, - "eval_NEIMS_matched_formulas": 0.5316666666666666, - "eval_NEIMS_morgan_tanimoto_simil": 0.33559208040238414, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0393, - "eval_NEIMS_runtime": 712.3444, - "eval_NEIMS_samples_per_second": 84.229, - "eval_NEIMS_steps_per_second": 1.317, + "epoch": 0.14, + "eval_NEIMS_canon_smiles": 0.9379166666666666, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.035133333333333336, + "eval_NEIMS_daylight_tanimoto_simil": 0.42944555336681517, + "eval_NEIMS_exact_mols": 0.03496666666666667, + "eval_NEIMS_exact_smiles": 0.034, + "eval_NEIMS_loss": 0.2440522164106369, + "eval_NEIMS_matched_formulas": 0.5060666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.3304066777709656, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.03528333333333333, + "eval_NEIMS_runtime": 734.5568, + "eval_NEIMS_samples_per_second": 81.682, + "eval_NEIMS_steps_per_second": 1.277, "step": 64000 }, { - "epoch": 0.57, - "eval_RASSP_canon_smiles": 0.9279059672087354, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.09319798310348282, - "eval_RASSP_daylight_tanimoto_simil": 0.5470292273063273, - "eval_RASSP_exact_mols": 0.09276388285971883, - "eval_RASSP_exact_smiles": 0.08915751160383344, - "eval_RASSP_loss": 0.18058153986930847, - "eval_RASSP_matched_formulas": 0.7011219821684976, - "eval_RASSP_morgan_tanimoto_simil": 0.411355893083842, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.09286405983904898, - "eval_RASSP_runtime": 814.2028, - "eval_RASSP_samples_per_second": 73.562, - "eval_RASSP_steps_per_second": 1.15, + "epoch": 0.14, + "eval_RASSP_canon_smiles": 0.9299762914482252, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.05145757504925368, + "eval_RASSP_daylight_tanimoto_simil": 0.49653172479487334, + "eval_RASSP_exact_mols": 0.05124052492737169, + "eval_RASSP_exact_smiles": 0.04917020068788192, + "eval_RASSP_loss": 0.2142479419708252, + "eval_RASSP_matched_formulas": 0.6556082412261662, + "eval_RASSP_morgan_tanimoto_simil": 0.35643510968712533, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.051290613417036765, + "eval_RASSP_runtime": 835.173, + "eval_RASSP_samples_per_second": 71.714, + "eval_RASSP_steps_per_second": 1.121, "step": 64000 }, { - "epoch": 0.57, - "eval_NIST_canon_smiles": 0.8854739681300351, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.009795223054264116, - "eval_NIST_daylight_tanimoto_simil": 0.2610283945884308, - "eval_NIST_exact_mols": 0.00947581360684246, - "eval_NIST_exact_smiles": 0.008801504773396742, - "eval_NIST_loss": 1.4489023685455322, - "eval_NIST_matched_formulas": 0.07829080455690812, - "eval_NIST_morgan_tanimoto_simil": 0.21492784860372788, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.009724243177059303, - "eval_NIST_runtime": 455.6201, - "eval_NIST_samples_per_second": 61.843, - "eval_NIST_steps_per_second": 0.968, + "epoch": 0.14, + "eval_NEIMS_old_canon_smiles": 0.9368666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.03506666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.42794334100771836, + "eval_NEIMS_old_exact_mols": 0.034833333333333334, + "eval_NEIMS_old_exact_smiles": 0.033666666666666664, + "eval_NEIMS_old_loss": 0.24411624670028687, + "eval_NEIMS_old_matched_formulas": 0.5007666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.3298159362063147, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.035133333333333336, + "eval_NEIMS_old_runtime": 369.9489, + "eval_NEIMS_old_samples_per_second": 81.092, + "eval_NEIMS_old_steps_per_second": 1.268, "step": 64000 }, { - "epoch": 0.57, - "learning_rate": 2.1631384559949555e-05, - "loss": 0.222, + "epoch": 0.14, + "eval_RASSP_old_canon_smiles": 0.9300230253278606, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.05966563219541496, + "eval_RASSP_old_daylight_tanimoto_simil": 0.5067513261988231, + "eval_RASSP_old_exact_mols": 0.05933193179163747, + "eval_RASSP_old_exact_smiles": 0.05712950912670604, + "eval_RASSP_old_loss": 0.2068203091621399, + "eval_RASSP_old_matched_formulas": 0.6680682083625321, + "eval_RASSP_old_morgan_tanimoto_simil": 0.36880133173493246, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.05956552207428171, + "eval_RASSP_old_runtime": 413.8616, + "eval_RASSP_old_samples_per_second": 72.408, + "eval_RASSP_old_steps_per_second": 1.133, + "step": 64000 + }, + { + "epoch": 0.14, + "eval_NIST_canon_smiles": 0.8833090818752883, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.010717961457926677, + "eval_NIST_daylight_tanimoto_simil": 0.2606462806922709, + "eval_NIST_exact_mols": 0.010434041949107428, + "eval_NIST_exact_smiles": 0.010008162685878553, + "eval_NIST_loss": 1.8626171350479126, + "eval_NIST_matched_formulas": 0.07328672321396884, + "eval_NIST_morgan_tanimoto_simil": 0.2160201213667236, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.010717961457926677, + "eval_NIST_runtime": 464.2306, + "eval_NIST_samples_per_second": 60.696, + "eval_NIST_steps_per_second": 0.95, + "step": 64000 + }, + { + "epoch": 0.14, + "learning_rate": 4.2954967450392606e-05, + "loss": 0.2416, "step": 64010 }, { - "epoch": 0.57, - "learning_rate": 2.1626880461219712e-05, - "loss": 0.2292, + "epoch": 0.14, + "learning_rate": 4.2953848907183284e-05, + "loss": 0.2353, "step": 64020 }, { - "epoch": 0.57, - "learning_rate": 2.1622376362489867e-05, - "loss": 0.2222, + "epoch": 0.14, + "learning_rate": 4.295273036397396e-05, + "loss": 0.2363, "step": 64030 }, { - "epoch": 0.57, - "learning_rate": 2.161787226376002e-05, - "loss": 0.2226, + "epoch": 0.14, + "learning_rate": 4.2951611820764633e-05, + "loss": 0.2368, "step": 64040 }, { - "epoch": 0.57, - "learning_rate": 2.1613368165030178e-05, - "loss": 0.2268, + "epoch": 0.14, + "learning_rate": 4.295049327755532e-05, + "loss": 0.2408, "step": 64050 }, { - "epoch": 0.57, - "learning_rate": 2.1608864066300336e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.294937473434599e-05, + "loss": 0.2402, "step": 64060 }, { - "epoch": 0.57, - "learning_rate": 2.160435996757049e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.294825619113667e-05, + "loss": 0.2407, "step": 64070 }, { - "epoch": 0.57, - "learning_rate": 2.1599855868840647e-05, - "loss": 0.2219, + "epoch": 0.14, + "learning_rate": 4.2947137647927345e-05, + "loss": 0.2377, "step": 64080 }, { - "epoch": 0.57, - "learning_rate": 2.15953517701108e-05, - "loss": 0.2211, + "epoch": 0.14, + "learning_rate": 4.2946019104718016e-05, + "loss": 0.2398, "step": 64090 }, { - "epoch": 0.57, - "learning_rate": 2.1590847671380955e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.2944900561508694e-05, + "loss": 0.2347, "step": 64100 }, { - "epoch": 0.57, - "learning_rate": 2.1586343572651113e-05, - "loss": 0.2235, + "epoch": 0.14, + "learning_rate": 4.2943782018299365e-05, + "loss": 0.2371, "step": 64110 }, { - "epoch": 0.57, - "learning_rate": 2.158183947392127e-05, - "loss": 0.2244, + "epoch": 0.14, + "learning_rate": 4.294266347509004e-05, + "loss": 0.24, "step": 64120 }, { - "epoch": 0.57, - "learning_rate": 2.1577335375191428e-05, - "loss": 0.2233, + "epoch": 0.14, + "learning_rate": 4.294154493188072e-05, + "loss": 0.2363, "step": 64130 }, { - "epoch": 0.57, - "learning_rate": 2.157283127646158e-05, - "loss": 0.219, + "epoch": 0.14, + "learning_rate": 4.294042638867139e-05, + "loss": 0.2403, "step": 64140 }, { - "epoch": 0.57, - "learning_rate": 2.1568327177731736e-05, - "loss": 0.2228, + "epoch": 0.14, + "learning_rate": 4.293930784546207e-05, + "loss": 0.2346, "step": 64150 }, { - "epoch": 0.57, - "learning_rate": 2.1563823079001894e-05, - "loss": 0.2207, + "epoch": 0.14, + "learning_rate": 4.293818930225275e-05, + "loss": 0.2393, "step": 64160 }, { - "epoch": 0.57, - "learning_rate": 2.1559318980272048e-05, - "loss": 0.2172, + "epoch": 0.14, + "learning_rate": 4.2937070759043426e-05, + "loss": 0.2399, "step": 64170 }, { - "epoch": 0.57, - "learning_rate": 2.1554814881542205e-05, - "loss": 0.2191, + "epoch": 0.14, + "learning_rate": 4.2935952215834104e-05, + "loss": 0.2344, "step": 64180 }, { - "epoch": 0.57, - "learning_rate": 2.155031078281236e-05, - "loss": 0.2241, + "epoch": 0.14, + "learning_rate": 4.2934833672624775e-05, + "loss": 0.2387, "step": 64190 }, { - "epoch": 0.57, - "learning_rate": 2.1545806684082517e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.293371512941545e-05, + "loss": 0.2355, "step": 64200 }, { - "epoch": 0.57, - "learning_rate": 2.154130258535267e-05, - "loss": 0.2225, + "epoch": 0.14, + "learning_rate": 4.2932596586206124e-05, + "loss": 0.2413, "step": 64210 }, { - "epoch": 0.57, - "learning_rate": 2.153679848662283e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.29314780429968e-05, + "loss": 0.2368, "step": 64220 }, { - "epoch": 0.57, - "learning_rate": 2.1532294387892986e-05, - "loss": 0.2251, + "epoch": 0.14, + "learning_rate": 4.293035949978748e-05, + "loss": 0.2407, "step": 64230 }, { - "epoch": 0.57, - "learning_rate": 2.152779028916314e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.292924095657815e-05, + "loss": 0.2409, "step": 64240 }, { - "epoch": 0.57, - "learning_rate": 2.1523286190433294e-05, - "loss": 0.226, + "epoch": 0.14, + "learning_rate": 4.292812241336883e-05, + "loss": 0.2362, "step": 64250 }, { - "epoch": 0.57, - "learning_rate": 2.151878209170345e-05, - "loss": 0.2212, + "epoch": 0.14, + "learning_rate": 4.292700387015951e-05, + "loss": 0.2401, "step": 64260 }, { - "epoch": 0.57, - "learning_rate": 2.151427799297361e-05, - "loss": 0.2237, + "epoch": 0.14, + "learning_rate": 4.2925885326950185e-05, + "loss": 0.2375, "step": 64270 }, { - "epoch": 0.57, - "learning_rate": 2.1509773894243763e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.292476678374086e-05, + "loss": 0.2349, "step": 64280 }, { - "epoch": 0.57, - "learning_rate": 2.1505269795513917e-05, - "loss": 0.2189, + "epoch": 0.14, + "learning_rate": 4.2923648240531534e-05, + "loss": 0.239, "step": 64290 }, { - "epoch": 0.57, - "learning_rate": 2.1500765696784075e-05, - "loss": 0.2202, + "epoch": 0.14, + "learning_rate": 4.292252969732221e-05, + "loss": 0.24, "step": 64300 }, { - "epoch": 0.57, - "learning_rate": 2.149626159805423e-05, - "loss": 0.2168, + "epoch": 0.14, + "learning_rate": 4.292141115411288e-05, + "loss": 0.2329, "step": 64310 }, { - "epoch": 0.57, - "learning_rate": 2.1491757499324386e-05, - "loss": 0.2185, + "epoch": 0.14, + "learning_rate": 4.292029261090356e-05, + "loss": 0.234, "step": 64320 }, { - "epoch": 0.57, - "learning_rate": 2.1487253400594544e-05, - "loss": 0.2198, + "epoch": 0.14, + "learning_rate": 4.291917406769423e-05, + "loss": 0.2405, "step": 64330 }, { - "epoch": 0.57, - "learning_rate": 2.1482749301864698e-05, - "loss": 0.22, + "epoch": 0.14, + "learning_rate": 4.291805552448491e-05, + "loss": 0.2386, "step": 64340 }, { - "epoch": 0.57, - "learning_rate": 2.1478245203134852e-05, - "loss": 0.2188, + "epoch": 0.14, + "learning_rate": 4.291693698127559e-05, + "loss": 0.2453, "step": 64350 }, { - "epoch": 0.57, - "learning_rate": 2.147374110440501e-05, - "loss": 0.2311, + "epoch": 0.14, + "learning_rate": 4.2915818438066266e-05, + "loss": 0.2371, "step": 64360 }, { - "epoch": 0.57, - "learning_rate": 2.1469237005675167e-05, - "loss": 0.2191, + "epoch": 0.14, + "learning_rate": 4.2914699894856944e-05, + "loss": 0.2415, "step": 64370 }, { - "epoch": 0.57, - "learning_rate": 2.146473290694532e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.2913581351647615e-05, + "loss": 0.2423, "step": 64380 }, { - "epoch": 0.57, - "learning_rate": 2.1460228808215475e-05, - "loss": 0.2126, + "epoch": 0.14, + "learning_rate": 4.291246280843829e-05, + "loss": 0.2372, "step": 64390 }, { - "epoch": 0.57, - "learning_rate": 2.1455724709485633e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.291134426522897e-05, + "loss": 0.2385, "step": 64400 }, { - "epoch": 0.58, - "learning_rate": 2.145122061075579e-05, - "loss": 0.2274, + "epoch": 0.14, + "learning_rate": 4.291022572201964e-05, + "loss": 0.2365, "step": 64410 }, { - "epoch": 0.58, - "learning_rate": 2.1446716512025944e-05, - "loss": 0.2231, + "epoch": 0.14, + "learning_rate": 4.290910717881032e-05, + "loss": 0.2405, "step": 64420 }, { - "epoch": 0.58, - "learning_rate": 2.1442212413296102e-05, - "loss": 0.2267, + "epoch": 0.14, + "learning_rate": 4.290798863560099e-05, + "loss": 0.2383, "step": 64430 }, { - "epoch": 0.58, - "learning_rate": 2.1437708314566256e-05, - "loss": 0.2263, + "epoch": 0.14, + "learning_rate": 4.290687009239167e-05, + "loss": 0.2452, "step": 64440 }, { - "epoch": 0.58, - "learning_rate": 2.143320421583641e-05, - "loss": 0.2185, + "epoch": 0.14, + "learning_rate": 4.290575154918235e-05, + "loss": 0.2439, "step": 64450 }, { - "epoch": 0.58, - "learning_rate": 2.1428700117106568e-05, - "loss": 0.225, + "epoch": 0.14, + "learning_rate": 4.2904633005973025e-05, + "loss": 0.233, "step": 64460 }, { - "epoch": 0.58, - "learning_rate": 2.1424196018376725e-05, - "loss": 0.2204, + "epoch": 0.14, + "learning_rate": 4.29035144627637e-05, + "loss": 0.2403, "step": 64470 }, { - "epoch": 0.58, - "learning_rate": 2.1419691919646883e-05, - "loss": 0.2189, + "epoch": 0.14, + "learning_rate": 4.2902395919554374e-05, + "loss": 0.2422, "step": 64480 }, { - "epoch": 0.58, - "learning_rate": 2.1415187820917033e-05, - "loss": 0.2177, + "epoch": 0.14, + "learning_rate": 4.290127737634505e-05, + "loss": 0.236, "step": 64490 }, { - "epoch": 0.58, - "learning_rate": 2.141068372218719e-05, - "loss": 0.2256, + "epoch": 0.14, + "learning_rate": 4.290015883313573e-05, + "loss": 0.2336, "step": 64500 }, { - "epoch": 0.58, - "learning_rate": 2.1406179623457348e-05, - "loss": 0.2193, + "epoch": 0.14, + "learning_rate": 4.28990402899264e-05, + "loss": 0.2444, "step": 64510 }, { - "epoch": 0.58, - "learning_rate": 2.1401675524727502e-05, - "loss": 0.2225, + "epoch": 0.14, + "learning_rate": 4.289792174671708e-05, + "loss": 0.2379, "step": 64520 }, { - "epoch": 0.58, - "learning_rate": 2.139717142599766e-05, - "loss": 0.2199, + "epoch": 0.14, + "learning_rate": 4.289680320350775e-05, + "loss": 0.2346, "step": 64530 }, { - "epoch": 0.58, - "learning_rate": 2.1392667327267814e-05, - "loss": 0.2231, + "epoch": 0.14, + "learning_rate": 4.289568466029843e-05, + "loss": 0.2413, "step": 64540 }, { - "epoch": 0.58, - "learning_rate": 2.138816322853797e-05, - "loss": 0.2321, + "epoch": 0.14, + "learning_rate": 4.2894566117089106e-05, + "loss": 0.2379, "step": 64550 }, { - "epoch": 0.58, - "learning_rate": 2.1383659129808126e-05, - "loss": 0.2218, + "epoch": 0.14, + "learning_rate": 4.289344757387978e-05, + "loss": 0.2384, "step": 64560 }, { - "epoch": 0.58, - "learning_rate": 2.1379155031078283e-05, - "loss": 0.2246, + "epoch": 0.14, + "learning_rate": 4.2892329030670455e-05, + "loss": 0.2415, "step": 64570 }, { - "epoch": 0.58, - "learning_rate": 2.137465093234844e-05, - "loss": 0.2222, + "epoch": 0.14, + "learning_rate": 4.289121048746113e-05, + "loss": 0.2377, "step": 64580 }, { - "epoch": 0.58, - "learning_rate": 2.137014683361859e-05, - "loss": 0.224, + "epoch": 0.14, + "learning_rate": 4.289009194425181e-05, + "loss": 0.2418, "step": 64590 }, { - "epoch": 0.58, - "learning_rate": 2.136564273488875e-05, - "loss": 0.2265, - "step": 64600 + "epoch": 0.14, + "learning_rate": 4.288897340104249e-05, + "loss": 0.2439, + "step": 64600 }, { - "epoch": 0.58, - "learning_rate": 2.1361138636158906e-05, - "loss": 0.2225, + "epoch": 0.14, + "learning_rate": 4.288785485783316e-05, + "loss": 0.2388, "step": 64610 }, { - "epoch": 0.58, - "learning_rate": 2.1356634537429064e-05, - "loss": 0.2211, + "epoch": 0.14, + "learning_rate": 4.288673631462384e-05, + "loss": 0.2429, "step": 64620 }, { - "epoch": 0.58, - "learning_rate": 2.1352130438699218e-05, - "loss": 0.2208, + "epoch": 0.14, + "learning_rate": 4.288561777141451e-05, + "loss": 0.2381, "step": 64630 }, { - "epoch": 0.58, - "learning_rate": 2.1347626339969372e-05, - "loss": 0.2257, + "epoch": 0.14, + "learning_rate": 4.288449922820519e-05, + "loss": 0.2353, "step": 64640 }, { - "epoch": 0.58, - "learning_rate": 2.134312224123953e-05, - "loss": 0.2245, + "epoch": 0.14, + "learning_rate": 4.288338068499586e-05, + "loss": 0.2393, "step": 64650 }, { - "epoch": 0.58, - "learning_rate": 2.1338618142509684e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.2882262141786536e-05, + "loss": 0.2326, "step": 64660 }, { - "epoch": 0.58, - "learning_rate": 2.133411404377984e-05, - "loss": 0.2259, + "epoch": 0.14, + "learning_rate": 4.2881143598577214e-05, + "loss": 0.2405, "step": 64670 }, { - "epoch": 0.58, - "learning_rate": 2.132960994505e-05, - "loss": 0.2212, + "epoch": 0.14, + "learning_rate": 4.288002505536789e-05, + "loss": 0.2365, "step": 64680 }, { - "epoch": 0.58, - "learning_rate": 2.1325105846320153e-05, - "loss": 0.2221, + "epoch": 0.14, + "learning_rate": 4.287890651215857e-05, + "loss": 0.2339, "step": 64690 }, { - "epoch": 0.58, - "learning_rate": 2.1320601747590307e-05, - "loss": 0.2228, + "epoch": 0.14, + "learning_rate": 4.287778796894924e-05, + "loss": 0.2403, "step": 64700 }, { - "epoch": 0.58, - "learning_rate": 2.1316097648860464e-05, - "loss": 0.2282, + "epoch": 0.14, + "learning_rate": 4.287666942573992e-05, + "loss": 0.2426, "step": 64710 }, { - "epoch": 0.58, - "learning_rate": 2.1311593550130622e-05, - "loss": 0.2252, + "epoch": 0.14, + "learning_rate": 4.28755508825306e-05, + "loss": 0.23, "step": 64720 }, { - "epoch": 0.58, - "learning_rate": 2.1307089451400776e-05, - "loss": 0.223, + "epoch": 0.14, + "learning_rate": 4.287443233932127e-05, + "loss": 0.2338, "step": 64730 }, { - "epoch": 0.58, - "learning_rate": 2.130258535267093e-05, - "loss": 0.2279, + "epoch": 0.14, + "learning_rate": 4.2873313796111946e-05, + "loss": 0.2314, "step": 64740 }, { - "epoch": 0.58, - "learning_rate": 2.1298081253941087e-05, - "loss": 0.2274, + "epoch": 0.14, + "learning_rate": 4.287219525290262e-05, + "loss": 0.2371, "step": 64750 }, { - "epoch": 0.58, - "learning_rate": 2.1293577155211245e-05, - "loss": 0.2216, + "epoch": 0.14, + "learning_rate": 4.2871076709693295e-05, + "loss": 0.2403, "step": 64760 }, { - "epoch": 0.58, - "learning_rate": 2.12890730564814e-05, - "loss": 0.2247, + "epoch": 0.14, + "learning_rate": 4.286995816648397e-05, + "loss": 0.2351, "step": 64770 }, { - "epoch": 0.58, - "learning_rate": 2.1284568957751556e-05, - "loss": 0.2191, + "epoch": 0.14, + "learning_rate": 4.286883962327465e-05, + "loss": 0.2354, "step": 64780 }, { - "epoch": 0.58, - "learning_rate": 2.128006485902171e-05, - "loss": 0.2198, + "epoch": 0.14, + "learning_rate": 4.286772108006533e-05, + "loss": 0.241, "step": 64790 }, { - "epoch": 0.58, - "learning_rate": 2.1275560760291865e-05, - "loss": 0.2209, + "epoch": 0.14, + "learning_rate": 4.2866602536856e-05, + "loss": 0.2363, "step": 64800 }, { - "epoch": 0.58, - "learning_rate": 2.1271056661562022e-05, - "loss": 0.2153, + "epoch": 0.14, + "learning_rate": 4.286548399364668e-05, + "loss": 0.2351, "step": 64810 }, { - "epoch": 0.58, - "learning_rate": 2.126655256283218e-05, - "loss": 0.2182, + "epoch": 0.14, + "learning_rate": 4.2864365450437356e-05, + "loss": 0.2379, "step": 64820 }, { - "epoch": 0.58, - "learning_rate": 2.1262498873975317e-05, - "loss": 0.2198, + "epoch": 0.14, + "learning_rate": 4.286324690722803e-05, + "loss": 0.237, "step": 64830 }, { - "epoch": 0.58, - "learning_rate": 2.1257994775245474e-05, - "loss": 0.2218, + "epoch": 0.14, + "learning_rate": 4.2862128364018705e-05, + "loss": 0.2403, "step": 64840 }, { - "epoch": 0.58, - "learning_rate": 2.125349067651563e-05, - "loss": 0.2169, + "epoch": 0.14, + "learning_rate": 4.2861009820809376e-05, + "loss": 0.2359, "step": 64850 }, { - "epoch": 0.58, - "learning_rate": 2.1248986577785786e-05, - "loss": 0.2181, + "epoch": 0.14, + "learning_rate": 4.2859891277600054e-05, + "loss": 0.235, "step": 64860 }, { - "epoch": 0.58, - "learning_rate": 2.124448247905594e-05, - "loss": 0.2166, + "epoch": 0.14, + "learning_rate": 4.285877273439073e-05, + "loss": 0.2431, "step": 64870 }, { - "epoch": 0.58, - "learning_rate": 2.1239978380326097e-05, - "loss": 0.2189, + "epoch": 0.14, + "learning_rate": 4.285765419118141e-05, + "loss": 0.243, "step": 64880 }, { - "epoch": 0.58, - "learning_rate": 2.1235474281596255e-05, - "loss": 0.2185, + "epoch": 0.14, + "learning_rate": 4.285653564797209e-05, + "loss": 0.2365, "step": 64890 }, { - "epoch": 0.58, - "learning_rate": 2.123097018286641e-05, - "loss": 0.22, + "epoch": 0.14, + "learning_rate": 4.285541710476276e-05, + "loss": 0.236, "step": 64900 }, { - "epoch": 0.58, - "learning_rate": 2.1226466084136566e-05, - "loss": 0.2239, + "epoch": 0.14, + "learning_rate": 4.285429856155344e-05, + "loss": 0.2413, "step": 64910 }, { - "epoch": 0.58, - "learning_rate": 2.122196198540672e-05, - "loss": 0.219, + "epoch": 0.14, + "learning_rate": 4.2853180018344115e-05, + "loss": 0.2372, "step": 64920 }, { - "epoch": 0.58, - "learning_rate": 2.1217457886676878e-05, - "loss": 0.2202, + "epoch": 0.14, + "learning_rate": 4.2852061475134786e-05, + "loss": 0.2348, "step": 64930 }, { - "epoch": 0.58, - "learning_rate": 2.1212953787947032e-05, - "loss": 0.2228, + "epoch": 0.14, + "learning_rate": 4.2850942931925464e-05, + "loss": 0.2371, "step": 64940 }, { - "epoch": 0.58, - "learning_rate": 2.120844968921719e-05, - "loss": 0.2254, + "epoch": 0.14, + "learning_rate": 4.2849824388716135e-05, + "loss": 0.2356, "step": 64950 }, { - "epoch": 0.58, - "learning_rate": 2.1203945590487344e-05, - "loss": 0.2263, + "epoch": 0.14, + "learning_rate": 4.284870584550681e-05, + "loss": 0.2376, "step": 64960 }, { - "epoch": 0.58, - "learning_rate": 2.1199441491757498e-05, - "loss": 0.222, + "epoch": 0.15, + "learning_rate": 4.2847587302297484e-05, + "loss": 0.2381, "step": 64970 }, { - "epoch": 0.58, - "learning_rate": 2.1194937393027655e-05, - "loss": 0.2209, + "epoch": 0.15, + "learning_rate": 4.284646875908816e-05, + "loss": 0.2417, "step": 64980 }, { - "epoch": 0.58, - "learning_rate": 2.1190433294297813e-05, - "loss": 0.2179, + "epoch": 0.15, + "learning_rate": 4.284535021587884e-05, + "loss": 0.2384, "step": 64990 }, { - "epoch": 0.58, - "learning_rate": 2.118592919556797e-05, - "loss": 0.2256, + "epoch": 0.15, + "learning_rate": 4.284423167266952e-05, + "loss": 0.2369, "step": 65000 }, { - "epoch": 0.58, - "learning_rate": 2.1181425096838124e-05, - "loss": 0.2243, + "epoch": 0.15, + "learning_rate": 4.2843113129460196e-05, + "loss": 0.2373, "step": 65010 }, { - "epoch": 0.58, - "learning_rate": 2.117692099810828e-05, - "loss": 0.2232, + "epoch": 0.15, + "learning_rate": 4.284199458625087e-05, + "loss": 0.2404, "step": 65020 }, { - "epoch": 0.58, - "learning_rate": 2.1172416899378436e-05, - "loss": 0.2224, + "epoch": 0.15, + "learning_rate": 4.2840876043041545e-05, + "loss": 0.2353, "step": 65030 }, { - "epoch": 0.58, - "learning_rate": 2.116791280064859e-05, - "loss": 0.2228, + "epoch": 0.15, + "learning_rate": 4.283975749983222e-05, + "loss": 0.2337, "step": 65040 }, { - "epoch": 0.58, - "learning_rate": 2.1163408701918748e-05, - "loss": 0.2223, + "epoch": 0.15, + "learning_rate": 4.2838638956622894e-05, + "loss": 0.2446, "step": 65050 }, { - "epoch": 0.58, - "learning_rate": 2.1158904603188902e-05, - "loss": 0.2203, + "epoch": 0.15, + "learning_rate": 4.283752041341357e-05, + "loss": 0.2357, "step": 65060 }, { - "epoch": 0.58, - "learning_rate": 2.115440050445906e-05, - "loss": 0.2212, + "epoch": 0.15, + "learning_rate": 4.283640187020424e-05, + "loss": 0.2353, "step": 65070 }, { - "epoch": 0.58, - "learning_rate": 2.1149896405729213e-05, - "loss": 0.2187, + "epoch": 0.15, + "learning_rate": 4.283528332699492e-05, + "loss": 0.2396, "step": 65080 }, { - "epoch": 0.58, - "learning_rate": 2.114539230699937e-05, - "loss": 0.2226, + "epoch": 0.15, + "learning_rate": 4.28341647837856e-05, + "loss": 0.2336, "step": 65090 }, { - "epoch": 0.58, - "learning_rate": 2.114088820826953e-05, - "loss": 0.2207, + "epoch": 0.15, + "learning_rate": 4.283304624057628e-05, + "loss": 0.2411, "step": 65100 }, { - "epoch": 0.58, - "learning_rate": 2.1136384109539682e-05, - "loss": 0.224, + "epoch": 0.15, + "learning_rate": 4.2831927697366955e-05, + "loss": 0.2382, "step": 65110 }, { - "epoch": 0.58, - "learning_rate": 2.1131880010809837e-05, - "loss": 0.2266, + "epoch": 0.15, + "learning_rate": 4.2830809154157626e-05, + "loss": 0.2363, "step": 65120 }, { - "epoch": 0.58, - "learning_rate": 2.1127375912079994e-05, - "loss": 0.2252, + "epoch": 0.15, + "learning_rate": 4.2829690610948304e-05, + "loss": 0.2353, "step": 65130 }, { - "epoch": 0.58, - "learning_rate": 2.112287181335015e-05, - "loss": 0.2225, + "epoch": 0.15, + "learning_rate": 4.282857206773898e-05, + "loss": 0.236, "step": 65140 }, { - "epoch": 0.58, - "learning_rate": 2.1118367714620306e-05, - "loss": 0.2203, + "epoch": 0.15, + "learning_rate": 4.282745352452965e-05, + "loss": 0.2377, "step": 65150 }, { - "epoch": 0.58, - "learning_rate": 2.111386361589046e-05, - "loss": 0.2206, + "epoch": 0.15, + "learning_rate": 4.282633498132033e-05, + "loss": 0.2377, "step": 65160 }, { - "epoch": 0.58, - "learning_rate": 2.1109359517160617e-05, - "loss": 0.226, + "epoch": 0.15, + "learning_rate": 4.2825216438111e-05, + "loss": 0.2421, "step": 65170 }, { - "epoch": 0.58, - "learning_rate": 2.110485541843077e-05, - "loss": 0.2224, + "epoch": 0.15, + "learning_rate": 4.282409789490168e-05, + "loss": 0.2392, "step": 65180 }, { - "epoch": 0.58, - "learning_rate": 2.110035131970093e-05, - "loss": 0.2188, + "epoch": 0.15, + "learning_rate": 4.282297935169236e-05, + "loss": 0.2353, "step": 65190 }, { - "epoch": 0.58, - "learning_rate": 2.1095847220971086e-05, - "loss": 0.2209, + "epoch": 0.15, + "learning_rate": 4.2821860808483036e-05, + "loss": 0.2392, "step": 65200 }, { - "epoch": 0.58, - "learning_rate": 2.109134312224124e-05, - "loss": 0.2219, + "epoch": 0.15, + "learning_rate": 4.2820742265273714e-05, + "loss": 0.236, "step": 65210 }, { - "epoch": 0.58, - "learning_rate": 2.1086839023511395e-05, - "loss": 0.2284, + "epoch": 0.15, + "learning_rate": 4.2819623722064385e-05, + "loss": 0.233, "step": 65220 }, { - "epoch": 0.58, - "learning_rate": 2.1082334924781552e-05, - "loss": 0.2158, + "epoch": 0.15, + "learning_rate": 4.281850517885506e-05, + "loss": 0.2339, "step": 65230 }, { - "epoch": 0.58, - "learning_rate": 2.107783082605171e-05, - "loss": 0.2227, + "epoch": 0.15, + "learning_rate": 4.281738663564574e-05, + "loss": 0.2317, "step": 65240 }, { - "epoch": 0.58, - "learning_rate": 2.1073326727321864e-05, - "loss": 0.2202, + "epoch": 0.15, + "learning_rate": 4.281626809243641e-05, + "loss": 0.2427, "step": 65250 }, { - "epoch": 0.58, - "learning_rate": 2.1068822628592018e-05, - "loss": 0.2212, + "epoch": 0.15, + "learning_rate": 4.281514954922709e-05, + "loss": 0.243, "step": 65260 }, { - "epoch": 0.58, - "learning_rate": 2.1064318529862175e-05, - "loss": 0.2181, + "epoch": 0.15, + "learning_rate": 4.281403100601776e-05, + "loss": 0.2426, "step": 65270 }, { - "epoch": 0.58, - "learning_rate": 2.1059814431132333e-05, - "loss": 0.2178, + "epoch": 0.15, + "learning_rate": 4.281291246280844e-05, + "loss": 0.2367, "step": 65280 }, { - "epoch": 0.58, - "learning_rate": 2.1055310332402487e-05, - "loss": 0.2153, + "epoch": 0.15, + "learning_rate": 4.281179391959912e-05, + "loss": 0.2359, "step": 65290 }, { - "epoch": 0.58, - "learning_rate": 2.1050806233672644e-05, - "loss": 0.226, + "epoch": 0.15, + "learning_rate": 4.2810675376389795e-05, + "loss": 0.2391, "step": 65300 }, { - "epoch": 0.58, - "learning_rate": 2.10463021349428e-05, - "loss": 0.2195, + "epoch": 0.15, + "learning_rate": 4.280955683318047e-05, + "loss": 0.2367, "step": 65310 }, { - "epoch": 0.58, - "learning_rate": 2.1041798036212952e-05, - "loss": 0.2225, + "epoch": 0.15, + "learning_rate": 4.2808438289971144e-05, + "loss": 0.2345, "step": 65320 }, { - "epoch": 0.58, - "learning_rate": 2.103729393748311e-05, - "loss": 0.2132, + "epoch": 0.15, + "learning_rate": 4.280731974676182e-05, + "loss": 0.2345, "step": 65330 }, { - "epoch": 0.58, - "learning_rate": 2.1032789838753267e-05, - "loss": 0.22, + "epoch": 0.15, + "learning_rate": 4.280620120355249e-05, + "loss": 0.2358, "step": 65340 }, { - "epoch": 0.58, - "learning_rate": 2.1028285740023425e-05, - "loss": 0.2203, + "epoch": 0.15, + "learning_rate": 4.28051945146641e-05, + "loss": 0.2377, "step": 65350 }, { - "epoch": 0.58, - "learning_rate": 2.1023781641293576e-05, - "loss": 0.2179, + "epoch": 0.15, + "learning_rate": 4.280407597145478e-05, + "loss": 0.2355, "step": 65360 }, { - "epoch": 0.58, - "learning_rate": 2.1019277542563733e-05, - "loss": 0.2249, + "epoch": 0.15, + "learning_rate": 4.280295742824546e-05, + "loss": 0.2358, "step": 65370 }, { - "epoch": 0.58, - "learning_rate": 2.101477344383389e-05, - "loss": 0.2201, + "epoch": 0.15, + "learning_rate": 4.2801838885036136e-05, + "loss": 0.2368, "step": 65380 }, { - "epoch": 0.58, - "learning_rate": 2.1010269345104045e-05, - "loss": 0.2176, + "epoch": 0.15, + "learning_rate": 4.280072034182681e-05, + "loss": 0.2379, "step": 65390 }, { - "epoch": 0.58, - "learning_rate": 2.1005765246374202e-05, - "loss": 0.2183, + "epoch": 0.15, + "learning_rate": 4.2799601798617485e-05, + "loss": 0.2327, "step": 65400 }, { - "epoch": 0.58, - "learning_rate": 2.1001261147644356e-05, - "loss": 0.2245, + "epoch": 0.15, + "learning_rate": 4.2798483255408156e-05, + "loss": 0.242, "step": 65410 }, { - "epoch": 0.58, - "learning_rate": 2.0996757048914514e-05, - "loss": 0.2246, + "epoch": 0.15, + "learning_rate": 4.2797364712198834e-05, + "loss": 0.2362, "step": 65420 }, { - "epoch": 0.58, - "learning_rate": 2.0992252950184668e-05, - "loss": 0.2214, + "epoch": 0.15, + "learning_rate": 4.279624616898951e-05, + "loss": 0.24, "step": 65430 }, { - "epoch": 0.58, - "learning_rate": 2.0987748851454825e-05, - "loss": 0.2177, + "epoch": 0.15, + "learning_rate": 4.279512762578018e-05, + "loss": 0.2361, "step": 65440 }, { - "epoch": 0.58, - "learning_rate": 2.0983244752724983e-05, - "loss": 0.2202, + "epoch": 0.15, + "learning_rate": 4.279400908257086e-05, + "loss": 0.2341, "step": 65450 }, { - "epoch": 0.58, - "learning_rate": 2.0978740653995134e-05, - "loss": 0.2198, + "epoch": 0.15, + "learning_rate": 4.279289053936154e-05, + "loss": 0.2391, "step": 65460 }, { - "epoch": 0.58, - "learning_rate": 2.097423655526529e-05, - "loss": 0.225, + "epoch": 0.15, + "learning_rate": 4.2791771996152217e-05, + "loss": 0.24, "step": 65470 }, { - "epoch": 0.58, - "learning_rate": 2.096973245653545e-05, - "loss": 0.2175, + "epoch": 0.15, + "learning_rate": 4.2790653452942894e-05, + "loss": 0.2369, "step": 65480 }, { - "epoch": 0.58, - "learning_rate": 2.0965228357805606e-05, - "loss": 0.2123, + "epoch": 0.15, + "learning_rate": 4.2789534909733566e-05, + "loss": 0.2352, "step": 65490 }, { - "epoch": 0.58, - "learning_rate": 2.096072425907576e-05, - "loss": 0.2198, + "epoch": 0.15, + "learning_rate": 4.2788416366524244e-05, + "loss": 0.2379, "step": 65500 }, { - "epoch": 0.58, - "learning_rate": 2.0956220160345914e-05, - "loss": 0.22, + "epoch": 0.15, + "learning_rate": 4.2787297823314915e-05, + "loss": 0.2368, "step": 65510 }, { - "epoch": 0.58, - "learning_rate": 2.0951716061616072e-05, - "loss": 0.2208, + "epoch": 0.15, + "learning_rate": 4.278617928010559e-05, + "loss": 0.2341, "step": 65520 }, { - "epoch": 0.59, - "learning_rate": 2.0947211962886226e-05, - "loss": 0.2222, + "epoch": 0.15, + "learning_rate": 4.278506073689627e-05, + "loss": 0.2462, "step": 65530 }, { - "epoch": 0.59, - "learning_rate": 2.0942707864156383e-05, - "loss": 0.2186, + "epoch": 0.15, + "learning_rate": 4.278394219368694e-05, + "loss": 0.2383, "step": 65540 }, { - "epoch": 0.59, - "learning_rate": 2.093820376542654e-05, - "loss": 0.2164, + "epoch": 0.15, + "learning_rate": 4.278282365047762e-05, + "loss": 0.2425, "step": 65550 }, { - "epoch": 0.59, - "learning_rate": 2.0933699666696695e-05, - "loss": 0.221, + "epoch": 0.15, + "learning_rate": 4.278170510726829e-05, + "loss": 0.2355, "step": 65560 }, { - "epoch": 0.59, - "learning_rate": 2.092919556796685e-05, - "loss": 0.2204, + "epoch": 0.15, + "learning_rate": 4.278058656405897e-05, + "loss": 0.2391, "step": 65570 }, { - "epoch": 0.59, - "learning_rate": 2.0924691469237007e-05, - "loss": 0.2295, + "epoch": 0.15, + "learning_rate": 4.2779468020849653e-05, + "loss": 0.2369, "step": 65580 }, { - "epoch": 0.59, - "learning_rate": 2.0920187370507164e-05, - "loss": 0.219, + "epoch": 0.15, + "learning_rate": 4.2778349477640325e-05, + "loss": 0.2382, "step": 65590 }, { - "epoch": 0.59, - "learning_rate": 2.0915683271777318e-05, - "loss": 0.2187, + "epoch": 0.15, + "learning_rate": 4.2777230934431e-05, + "loss": 0.2381, "step": 65600 }, { - "epoch": 0.59, - "learning_rate": 2.0911179173047472e-05, - "loss": 0.2256, + "epoch": 0.15, + "learning_rate": 4.2776112391221674e-05, + "loss": 0.2363, "step": 65610 }, { - "epoch": 0.59, - "learning_rate": 2.090667507431763e-05, - "loss": 0.2246, + "epoch": 0.15, + "learning_rate": 4.277499384801235e-05, + "loss": 0.2371, "step": 65620 }, { - "epoch": 0.59, - "learning_rate": 2.0902170975587787e-05, - "loss": 0.2144, + "epoch": 0.15, + "learning_rate": 4.277387530480302e-05, + "loss": 0.2406, "step": 65630 }, { - "epoch": 0.59, - "learning_rate": 2.089766687685794e-05, - "loss": 0.2189, + "epoch": 0.15, + "learning_rate": 4.27727567615937e-05, + "loss": 0.2331, "step": 65640 }, { - "epoch": 0.59, - "learning_rate": 2.08931627781281e-05, - "loss": 0.2192, + "epoch": 0.15, + "learning_rate": 4.277163821838438e-05, + "loss": 0.2387, "step": 65650 }, { - "epoch": 0.59, - "learning_rate": 2.0888658679398253e-05, - "loss": 0.2246, + "epoch": 0.15, + "learning_rate": 4.277051967517505e-05, + "loss": 0.2338, "step": 65660 }, { - "epoch": 0.59, - "learning_rate": 2.0884154580668407e-05, - "loss": 0.2187, + "epoch": 0.15, + "learning_rate": 4.276940113196573e-05, + "loss": 0.2418, "step": 65670 }, { - "epoch": 0.59, - "learning_rate": 2.0879650481938565e-05, - "loss": 0.2184, + "epoch": 0.15, + "learning_rate": 4.2768282588756406e-05, + "loss": 0.2366, "step": 65680 }, { - "epoch": 0.59, - "learning_rate": 2.0875146383208722e-05, - "loss": 0.2127, + "epoch": 0.15, + "learning_rate": 4.2767164045547084e-05, + "loss": 0.2391, "step": 65690 }, { - "epoch": 0.59, - "learning_rate": 2.087064228447888e-05, - "loss": 0.2202, + "epoch": 0.15, + "learning_rate": 4.276604550233776e-05, + "loss": 0.2446, "step": 65700 }, { - "epoch": 0.59, - "learning_rate": 2.086613818574903e-05, - "loss": 0.2221, + "epoch": 0.15, + "learning_rate": 4.276492695912843e-05, + "loss": 0.2345, "step": 65710 }, { - "epoch": 0.59, - "learning_rate": 2.0861634087019188e-05, - "loss": 0.219, + "epoch": 0.15, + "learning_rate": 4.276380841591911e-05, + "loss": 0.2396, "step": 65720 }, { - "epoch": 0.59, - "learning_rate": 2.0857129988289345e-05, - "loss": 0.2216, + "epoch": 0.15, + "learning_rate": 4.276268987270978e-05, + "loss": 0.2372, "step": 65730 }, { - "epoch": 0.59, - "learning_rate": 2.08526258895595e-05, - "loss": 0.2193, + "epoch": 0.15, + "learning_rate": 4.276157132950046e-05, + "loss": 0.2355, "step": 65740 }, { - "epoch": 0.59, - "learning_rate": 2.0848121790829657e-05, - "loss": 0.2208, + "epoch": 0.15, + "learning_rate": 4.276045278629114e-05, + "loss": 0.2345, "step": 65750 }, { - "epoch": 0.59, - "learning_rate": 2.084361769209981e-05, - "loss": 0.2139, + "epoch": 0.15, + "learning_rate": 4.275933424308181e-05, + "loss": 0.2366, "step": 65760 }, { - "epoch": 0.59, - "learning_rate": 2.083911359336997e-05, - "loss": 0.2183, + "epoch": 0.15, + "learning_rate": 4.2758215699872487e-05, + "loss": 0.237, "step": 65770 }, { - "epoch": 0.59, - "learning_rate": 2.0834609494640123e-05, - "loss": 0.2257, + "epoch": 0.15, + "learning_rate": 4.2757097156663165e-05, + "loss": 0.2356, "step": 65780 }, { - "epoch": 0.59, - "learning_rate": 2.083010539591028e-05, - "loss": 0.222, + "epoch": 0.15, + "learning_rate": 4.275597861345384e-05, + "loss": 0.2344, "step": 65790 }, { - "epoch": 0.59, - "learning_rate": 2.0825601297180438e-05, - "loss": 0.2174, + "epoch": 0.15, + "learning_rate": 4.275486007024452e-05, + "loss": 0.2406, "step": 65800 }, { - "epoch": 0.59, - "learning_rate": 2.0821097198450588e-05, - "loss": 0.223, + "epoch": 0.15, + "learning_rate": 4.275374152703519e-05, + "loss": 0.2343, "step": 65810 }, { - "epoch": 0.59, - "learning_rate": 2.0816593099720746e-05, - "loss": 0.2195, + "epoch": 0.15, + "learning_rate": 4.275262298382587e-05, + "loss": 0.2334, "step": 65820 }, { - "epoch": 0.59, - "learning_rate": 2.0812089000990903e-05, - "loss": 0.2185, + "epoch": 0.15, + "learning_rate": 4.275150444061654e-05, + "loss": 0.2349, "step": 65830 }, { - "epoch": 0.59, - "learning_rate": 2.080758490226106e-05, - "loss": 0.2189, + "epoch": 0.15, + "learning_rate": 4.275038589740722e-05, + "loss": 0.2381, "step": 65840 }, { - "epoch": 0.59, - "learning_rate": 2.0803080803531215e-05, - "loss": 0.2213, + "epoch": 0.15, + "learning_rate": 4.2749267354197896e-05, + "loss": 0.2371, "step": 65850 }, { - "epoch": 0.59, - "learning_rate": 2.079857670480137e-05, - "loss": 0.2189, + "epoch": 0.15, + "learning_rate": 4.274814881098857e-05, + "loss": 0.2423, "step": 65860 }, { - "epoch": 0.59, - "learning_rate": 2.0794072606071526e-05, - "loss": 0.2193, + "epoch": 0.15, + "learning_rate": 4.2747030267779246e-05, + "loss": 0.2326, "step": 65870 }, { - "epoch": 0.59, - "learning_rate": 2.078956850734168e-05, - "loss": 0.2214, + "epoch": 0.15, + "learning_rate": 4.2745911724569923e-05, + "loss": 0.236, "step": 65880 }, { - "epoch": 0.59, - "learning_rate": 2.0785064408611838e-05, - "loss": 0.219, + "epoch": 0.15, + "learning_rate": 4.27447931813606e-05, + "loss": 0.2321, "step": 65890 }, { - "epoch": 0.59, - "learning_rate": 2.0780560309881996e-05, - "loss": 0.2195, + "epoch": 0.15, + "learning_rate": 4.274367463815128e-05, + "loss": 0.2337, "step": 65900 }, { - "epoch": 0.59, - "learning_rate": 2.077605621115215e-05, - "loss": 0.2146, + "epoch": 0.15, + "learning_rate": 4.274255609494195e-05, + "loss": 0.2389, "step": 65910 }, { - "epoch": 0.59, - "learning_rate": 2.0771552112422304e-05, - "loss": 0.2176, + "epoch": 0.15, + "learning_rate": 4.274143755173263e-05, + "loss": 0.2375, "step": 65920 }, { - "epoch": 0.59, - "learning_rate": 2.076704801369246e-05, - "loss": 0.2194, + "epoch": 0.15, + "learning_rate": 4.27403190085233e-05, + "loss": 0.2295, "step": 65930 }, { - "epoch": 0.59, - "learning_rate": 2.076254391496262e-05, - "loss": 0.2155, + "epoch": 0.15, + "learning_rate": 4.273920046531398e-05, + "loss": 0.238, "step": 65940 }, { - "epoch": 0.59, - "learning_rate": 2.0758039816232773e-05, - "loss": 0.2232, + "epoch": 0.15, + "learning_rate": 4.273808192210465e-05, + "loss": 0.2332, "step": 65950 }, { - "epoch": 0.59, - "learning_rate": 2.0753535717502927e-05, - "loss": 0.217, + "epoch": 0.15, + "learning_rate": 4.2736963378895327e-05, + "loss": 0.2387, "step": 65960 }, { - "epoch": 0.59, - "learning_rate": 2.0749031618773084e-05, - "loss": 0.2162, + "epoch": 0.15, + "learning_rate": 4.2735844835686004e-05, + "loss": 0.232, "step": 65970 }, { - "epoch": 0.59, - "learning_rate": 2.0744527520043242e-05, - "loss": 0.2248, + "epoch": 0.15, + "learning_rate": 4.2734726292476676e-05, + "loss": 0.2354, "step": 65980 }, { - "epoch": 0.59, - "learning_rate": 2.0740023421313396e-05, - "loss": 0.217, + "epoch": 0.15, + "learning_rate": 4.273360774926736e-05, + "loss": 0.2381, "step": 65990 }, { - "epoch": 0.59, - "learning_rate": 2.0735519322583554e-05, - "loss": 0.2239, + "epoch": 0.15, + "learning_rate": 4.273248920605803e-05, + "loss": 0.2403, "step": 66000 }, { - "epoch": 0.59, - "learning_rate": 2.0731015223853708e-05, - "loss": 0.2155, + "epoch": 0.15, + "learning_rate": 4.273137066284871e-05, + "loss": 0.2421, "step": 66010 }, { - "epoch": 0.59, - "learning_rate": 2.0726511125123862e-05, - "loss": 0.2198, + "epoch": 0.15, + "learning_rate": 4.273025211963939e-05, + "loss": 0.2358, "step": 66020 }, { - "epoch": 0.59, - "learning_rate": 2.072200702639402e-05, - "loss": 0.216, + "epoch": 0.15, + "learning_rate": 4.272913357643006e-05, + "loss": 0.2387, "step": 66030 }, { - "epoch": 0.59, - "learning_rate": 2.0717502927664177e-05, - "loss": 0.2197, + "epoch": 0.15, + "learning_rate": 4.2728015033220736e-05, + "loss": 0.2408, "step": 66040 }, { - "epoch": 0.59, - "learning_rate": 2.071299882893433e-05, - "loss": 0.2137, + "epoch": 0.15, + "learning_rate": 4.272689649001141e-05, + "loss": 0.2411, "step": 66050 }, { - "epoch": 0.59, - "learning_rate": 2.0708494730204485e-05, - "loss": 0.2114, + "epoch": 0.15, + "learning_rate": 4.2725777946802086e-05, + "loss": 0.2393, "step": 66060 }, { - "epoch": 0.59, - "learning_rate": 2.0703990631474642e-05, - "loss": 0.2237, + "epoch": 0.15, + "learning_rate": 4.2724659403592763e-05, + "loss": 0.2397, "step": 66070 }, { - "epoch": 0.59, - "learning_rate": 2.06994865327448e-05, - "loss": 0.2101, + "epoch": 0.15, + "learning_rate": 4.2723540860383435e-05, + "loss": 0.2375, "step": 66080 }, { - "epoch": 0.59, - "learning_rate": 2.0694982434014954e-05, - "loss": 0.2151, + "epoch": 0.15, + "learning_rate": 4.272242231717411e-05, + "loss": 0.2358, "step": 66090 }, { - "epoch": 0.59, - "learning_rate": 2.069047833528511e-05, - "loss": 0.2136, + "epoch": 0.15, + "learning_rate": 4.272130377396479e-05, + "loss": 0.2369, "step": 66100 }, { - "epoch": 0.59, - "learning_rate": 2.0685974236555266e-05, - "loss": 0.2147, + "epoch": 0.15, + "learning_rate": 4.272018523075547e-05, + "loss": 0.2321, "step": 66110 }, { - "epoch": 0.59, - "learning_rate": 2.0681470137825423e-05, - "loss": 0.2157, + "epoch": 0.15, + "learning_rate": 4.2719066687546146e-05, + "loss": 0.2364, "step": 66120 }, { - "epoch": 0.59, - "learning_rate": 2.0676966039095577e-05, - "loss": 0.2157, + "epoch": 0.15, + "learning_rate": 4.271794814433682e-05, + "loss": 0.2338, "step": 66130 }, { - "epoch": 0.59, - "learning_rate": 2.0672461940365735e-05, - "loss": 0.2133, + "epoch": 0.15, + "learning_rate": 4.2716829601127495e-05, + "loss": 0.2344, "step": 66140 }, { - "epoch": 0.59, - "learning_rate": 2.066795784163589e-05, - "loss": 0.2047, + "epoch": 0.15, + "learning_rate": 4.2715711057918167e-05, + "loss": 0.2326, "step": 66150 }, { - "epoch": 0.59, - "learning_rate": 2.0663453742906043e-05, - "loss": 0.2187, + "epoch": 0.15, + "learning_rate": 4.2714592514708844e-05, + "loss": 0.2345, "step": 66160 }, { - "epoch": 0.59, - "learning_rate": 2.06589496441762e-05, - "loss": 0.216, + "epoch": 0.15, + "learning_rate": 4.271347397149952e-05, + "loss": 0.2331, "step": 66170 }, { - "epoch": 0.59, - "learning_rate": 2.0654445545446358e-05, - "loss": 0.2133, + "epoch": 0.15, + "learning_rate": 4.2712355428290194e-05, + "loss": 0.2368, "step": 66180 }, { - "epoch": 0.59, - "learning_rate": 2.0649941446716515e-05, - "loss": 0.2154, + "epoch": 0.15, + "learning_rate": 4.271123688508087e-05, + "loss": 0.2345, "step": 66190 }, { - "epoch": 0.59, - "learning_rate": 2.064543734798667e-05, - "loss": 0.2174, + "epoch": 0.15, + "learning_rate": 4.271011834187155e-05, + "loss": 0.2336, "step": 66200 }, { - "epoch": 0.59, - "learning_rate": 2.0640933249256824e-05, - "loss": 0.2121, + "epoch": 0.15, + "learning_rate": 4.270899979866223e-05, + "loss": 0.2334, "step": 66210 }, { - "epoch": 0.59, - "learning_rate": 2.063642915052698e-05, - "loss": 0.2147, + "epoch": 0.15, + "learning_rate": 4.2707881255452905e-05, + "loss": 0.2314, "step": 66220 }, { - "epoch": 0.59, - "learning_rate": 2.0631925051797135e-05, - "loss": 0.215, + "epoch": 0.15, + "learning_rate": 4.2706762712243576e-05, + "loss": 0.2327, "step": 66230 }, { - "epoch": 0.59, - "learning_rate": 2.0627420953067293e-05, - "loss": 0.212, + "epoch": 0.15, + "learning_rate": 4.2705644169034254e-05, + "loss": 0.2308, "step": 66240 }, { - "epoch": 0.59, - "learning_rate": 2.0622916854337447e-05, - "loss": 0.2161, + "epoch": 0.15, + "learning_rate": 4.2704525625824925e-05, + "loss": 0.2374, "step": 66250 }, { - "epoch": 0.59, - "learning_rate": 2.0618412755607604e-05, - "loss": 0.214, + "epoch": 0.15, + "learning_rate": 4.2703407082615603e-05, + "loss": 0.2382, "step": 66260 }, { - "epoch": 0.59, - "learning_rate": 2.061390865687776e-05, - "loss": 0.2104, + "epoch": 0.15, + "learning_rate": 4.2702288539406275e-05, + "loss": 0.2375, "step": 66270 }, { - "epoch": 0.59, - "learning_rate": 2.0609404558147916e-05, - "loss": 0.215, + "epoch": 0.15, + "learning_rate": 4.270116999619695e-05, + "loss": 0.2392, "step": 66280 }, { - "epoch": 0.59, - "learning_rate": 2.0604900459418073e-05, - "loss": 0.2139, + "epoch": 0.15, + "learning_rate": 4.270005145298763e-05, + "loss": 0.2306, "step": 66290 }, { - "epoch": 0.59, - "learning_rate": 2.0600396360688227e-05, - "loss": 0.2144, + "epoch": 0.15, + "learning_rate": 4.269893290977831e-05, + "loss": 0.2387, "step": 66300 }, { - "epoch": 0.59, - "learning_rate": 2.059589226195838e-05, - "loss": 0.2164, + "epoch": 0.15, + "learning_rate": 4.2697814366568986e-05, + "loss": 0.2322, "step": 66310 }, { - "epoch": 0.59, - "learning_rate": 2.059138816322854e-05, - "loss": 0.2084, + "epoch": 0.15, + "learning_rate": 4.269669582335966e-05, + "loss": 0.237, "step": 66320 }, { - "epoch": 0.59, - "learning_rate": 2.0586884064498697e-05, - "loss": 0.2132, + "epoch": 0.15, + "learning_rate": 4.2695577280150335e-05, + "loss": 0.2327, "step": 66330 }, { - "epoch": 0.59, - "learning_rate": 2.058237996576885e-05, - "loss": 0.2207, + "epoch": 0.15, + "learning_rate": 4.269445873694101e-05, + "loss": 0.2312, "step": 66340 }, { - "epoch": 0.59, - "learning_rate": 2.0577875867039008e-05, - "loss": 0.2121, + "epoch": 0.15, + "learning_rate": 4.2693340193731684e-05, + "loss": 0.2307, "step": 66350 }, { - "epoch": 0.59, - "learning_rate": 2.0573371768309162e-05, - "loss": 0.207, + "epoch": 0.15, + "learning_rate": 4.269222165052236e-05, + "loss": 0.2367, "step": 66360 }, { - "epoch": 0.59, - "learning_rate": 2.0568867669579316e-05, - "loss": 0.2184, + "epoch": 0.15, + "learning_rate": 4.2691103107313034e-05, + "loss": 0.2333, "step": 66370 }, { - "epoch": 0.59, - "learning_rate": 2.0564363570849474e-05, - "loss": 0.2106, + "epoch": 0.15, + "learning_rate": 4.268998456410371e-05, + "loss": 0.2325, "step": 66380 }, { - "epoch": 0.59, - "learning_rate": 2.055985947211963e-05, - "loss": 0.208, + "epoch": 0.15, + "learning_rate": 4.268886602089439e-05, + "loss": 0.237, "step": 66390 }, { - "epoch": 0.59, - "learning_rate": 2.0555355373389785e-05, - "loss": 0.2147, + "epoch": 0.15, + "learning_rate": 4.268774747768506e-05, + "loss": 0.235, "step": 66400 }, { - "epoch": 0.59, - "learning_rate": 2.055085127465994e-05, - "loss": 0.211, + "epoch": 0.15, + "learning_rate": 4.2686628934475745e-05, + "loss": 0.2389, "step": 66410 }, { - "epoch": 0.59, - "learning_rate": 2.0546347175930097e-05, - "loss": 0.2123, + "epoch": 0.15, + "learning_rate": 4.2685510391266416e-05, + "loss": 0.2385, "step": 66420 }, { - "epoch": 0.59, - "learning_rate": 2.0541843077200255e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.2684391848057094e-05, + "loss": 0.235, "step": 66430 }, { - "epoch": 0.59, - "learning_rate": 2.053733897847041e-05, - "loss": 0.2149, + "epoch": 0.15, + "learning_rate": 4.268327330484777e-05, + "loss": 0.2335, "step": 66440 }, { - "epoch": 0.59, - "learning_rate": 2.0532834879740566e-05, - "loss": 0.2162, + "epoch": 0.15, + "learning_rate": 4.268215476163844e-05, + "loss": 0.2358, "step": 66450 }, { - "epoch": 0.59, - "learning_rate": 2.052833078101072e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.268103621842912e-05, + "loss": 0.2344, "step": 66460 }, { - "epoch": 0.59, - "learning_rate": 2.0523826682280878e-05, - "loss": 0.2109, + "epoch": 0.15, + "learning_rate": 4.267991767521979e-05, + "loss": 0.2351, "step": 66470 }, { - "epoch": 0.59, - "learning_rate": 2.0519322583551032e-05, - "loss": 0.2093, + "epoch": 0.15, + "learning_rate": 4.267879913201047e-05, + "loss": 0.2334, "step": 66480 }, { - "epoch": 0.59, - "learning_rate": 2.051481848482119e-05, - "loss": 0.2152, + "epoch": 0.15, + "learning_rate": 4.267768058880115e-05, + "loss": 0.2385, "step": 66490 }, { - "epoch": 0.59, - "learning_rate": 2.0510314386091343e-05, - "loss": 0.2177, + "epoch": 0.15, + "learning_rate": 4.267656204559182e-05, + "loss": 0.2326, "step": 66500 }, { - "epoch": 0.59, - "learning_rate": 2.0505810287361498e-05, - "loss": 0.2163, + "epoch": 0.15, + "learning_rate": 4.26754435023825e-05, + "loss": 0.2319, "step": 66510 }, { - "epoch": 0.59, - "learning_rate": 2.0501306188631655e-05, - "loss": 0.2166, + "epoch": 0.15, + "learning_rate": 4.2674324959173175e-05, + "loss": 0.239, "step": 66520 }, { - "epoch": 0.59, - "learning_rate": 2.0496802089901813e-05, - "loss": 0.2152, + "epoch": 0.15, + "learning_rate": 4.267320641596385e-05, + "loss": 0.2345, "step": 66530 }, { - "epoch": 0.59, - "learning_rate": 2.049229799117197e-05, - "loss": 0.2149, + "epoch": 0.15, + "learning_rate": 4.267208787275453e-05, + "loss": 0.2328, "step": 66540 }, { - "epoch": 0.59, - "learning_rate": 2.0487793892442124e-05, - "loss": 0.2102, + "epoch": 0.15, + "learning_rate": 4.26709693295452e-05, + "loss": 0.2357, "step": 66550 }, { - "epoch": 0.59, - "learning_rate": 2.0483289793712278e-05, - "loss": 0.2124, + "epoch": 0.15, + "learning_rate": 4.266985078633588e-05, + "loss": 0.2364, "step": 66560 }, { - "epoch": 0.59, - "learning_rate": 2.0478785694982436e-05, - "loss": 0.2197, + "epoch": 0.15, + "learning_rate": 4.266873224312655e-05, + "loss": 0.2375, "step": 66570 }, { - "epoch": 0.59, - "learning_rate": 2.047428159625259e-05, - "loss": 0.2146, + "epoch": 0.15, + "learning_rate": 4.266761369991723e-05, + "loss": 0.239, "step": 66580 }, { - "epoch": 0.59, - "learning_rate": 2.0469777497522747e-05, - "loss": 0.2134, + "epoch": 0.15, + "learning_rate": 4.26664951567079e-05, + "loss": 0.2365, "step": 66590 }, { - "epoch": 0.59, - "learning_rate": 2.04652733987929e-05, - "loss": 0.2102, + "epoch": 0.15, + "learning_rate": 4.266537661349858e-05, + "loss": 0.235, "step": 66600 }, { - "epoch": 0.59, - "learning_rate": 2.046076930006306e-05, - "loss": 0.2108, + "epoch": 0.15, + "learning_rate": 4.2664258070289256e-05, + "loss": 0.2398, "step": 66610 }, { - "epoch": 0.59, - "learning_rate": 2.0456265201333213e-05, - "loss": 0.2088, + "epoch": 0.15, + "learning_rate": 4.2663139527079934e-05, + "loss": 0.2326, "step": 66620 }, { - "epoch": 0.59, - "learning_rate": 2.045176110260337e-05, - "loss": 0.2113, + "epoch": 0.15, + "learning_rate": 4.266202098387061e-05, + "loss": 0.2373, "step": 66630 }, { - "epoch": 0.59, - "learning_rate": 2.0447257003873528e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.266090244066128e-05, + "loss": 0.2403, "step": 66640 }, { - "epoch": 0.6, - "learning_rate": 2.0442752905143682e-05, - "loss": 0.1995, + "epoch": 0.15, + "learning_rate": 4.265978389745196e-05, + "loss": 0.2393, "step": 66650 }, { - "epoch": 0.6, - "learning_rate": 2.0438248806413836e-05, - "loss": 0.2111, + "epoch": 0.15, + "learning_rate": 4.265866535424264e-05, + "loss": 0.2342, "step": 66660 }, { - "epoch": 0.6, - "learning_rate": 2.0433744707683994e-05, - "loss": 0.2135, + "epoch": 0.15, + "learning_rate": 4.265754681103331e-05, + "loss": 0.2357, "step": 66670 }, { - "epoch": 0.6, - "learning_rate": 2.042924060895415e-05, - "loss": 0.2124, + "epoch": 0.15, + "learning_rate": 4.265642826782399e-05, + "loss": 0.236, "step": 66680 }, { - "epoch": 0.6, - "learning_rate": 2.0424736510224305e-05, - "loss": 0.2062, + "epoch": 0.15, + "learning_rate": 4.265530972461466e-05, + "loss": 0.238, "step": 66690 }, { - "epoch": 0.6, - "learning_rate": 2.042023241149446e-05, - "loss": 0.2099, + "epoch": 0.15, + "learning_rate": 4.265419118140534e-05, + "loss": 0.2364, "step": 66700 }, { - "epoch": 0.6, - "learning_rate": 2.0415728312764617e-05, - "loss": 0.2109, + "epoch": 0.15, + "learning_rate": 4.2653072638196015e-05, + "loss": 0.2275, "step": 66710 }, { - "epoch": 0.6, - "learning_rate": 2.041122421403477e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.265195409498669e-05, + "loss": 0.226, "step": 66720 }, { - "epoch": 0.6, - "learning_rate": 2.040672011530493e-05, - "loss": 0.2077, + "epoch": 0.15, + "learning_rate": 4.265083555177737e-05, + "loss": 0.23, "step": 66730 }, { - "epoch": 0.6, - "learning_rate": 2.0402216016575086e-05, - "loss": 0.2084, + "epoch": 0.15, + "learning_rate": 4.264971700856804e-05, + "loss": 0.2393, "step": 66740 }, { - "epoch": 0.6, - "learning_rate": 2.039771191784524e-05, - "loss": 0.2184, + "epoch": 0.15, + "learning_rate": 4.264859846535872e-05, + "loss": 0.2325, "step": 66750 }, { - "epoch": 0.6, - "learning_rate": 2.0393207819115394e-05, - "loss": 0.2064, + "epoch": 0.15, + "learning_rate": 4.26474799221494e-05, + "loss": 0.2401, "step": 66760 }, { - "epoch": 0.6, - "learning_rate": 2.038870372038555e-05, - "loss": 0.2169, + "epoch": 0.15, + "learning_rate": 4.264636137894007e-05, + "loss": 0.2313, "step": 66770 }, { - "epoch": 0.6, - "learning_rate": 2.038419962165571e-05, - "loss": 0.2108, + "epoch": 0.15, + "learning_rate": 4.264524283573075e-05, + "loss": 0.2352, "step": 66780 }, { - "epoch": 0.6, - "learning_rate": 2.0379695522925863e-05, - "loss": 0.2088, + "epoch": 0.15, + "learning_rate": 4.264412429252142e-05, + "loss": 0.241, "step": 66790 }, { - "epoch": 0.6, - "learning_rate": 2.0375191424196017e-05, - "loss": 0.2067, + "epoch": 0.15, + "learning_rate": 4.2643005749312096e-05, + "loss": 0.2374, "step": 66800 }, { - "epoch": 0.6, - "learning_rate": 2.0370687325466175e-05, - "loss": 0.2071, + "epoch": 0.15, + "learning_rate": 4.2641887206102774e-05, + "loss": 0.2334, "step": 66810 }, { - "epoch": 0.6, - "learning_rate": 2.0366183226736332e-05, - "loss": 0.2207, + "epoch": 0.15, + "learning_rate": 4.264076866289345e-05, + "loss": 0.2355, "step": 66820 }, { - "epoch": 0.6, - "learning_rate": 2.0361679128006486e-05, - "loss": 0.2173, + "epoch": 0.15, + "learning_rate": 4.263965011968413e-05, + "loss": 0.2307, "step": 66830 }, { - "epoch": 0.6, - "learning_rate": 2.0357175029276644e-05, - "loss": 0.2154, + "epoch": 0.15, + "learning_rate": 4.26385315764748e-05, + "loss": 0.2427, "step": 66840 }, { - "epoch": 0.6, - "learning_rate": 2.0352670930546798e-05, - "loss": 0.2093, + "epoch": 0.15, + "learning_rate": 4.263741303326548e-05, + "loss": 0.2332, "step": 66850 }, { - "epoch": 0.6, - "learning_rate": 2.0348166831816952e-05, - "loss": 0.2149, + "epoch": 0.15, + "learning_rate": 4.263629449005616e-05, + "loss": 0.236, "step": 66860 }, { - "epoch": 0.6, - "learning_rate": 2.034366273308711e-05, - "loss": 0.2121, + "epoch": 0.15, + "learning_rate": 4.263517594684683e-05, + "loss": 0.2341, "step": 66870 }, { - "epoch": 0.6, - "learning_rate": 2.033960904423025e-05, - "loss": 0.2107, + "epoch": 0.15, + "learning_rate": 4.2634057403637506e-05, + "loss": 0.2421, "step": 66880 }, { - "epoch": 0.6, - "learning_rate": 2.0335104945500404e-05, - "loss": 0.2075, + "epoch": 0.15, + "learning_rate": 4.263293886042818e-05, + "loss": 0.234, "step": 66890 }, { - "epoch": 0.6, - "learning_rate": 2.033060084677056e-05, - "loss": 0.2097, + "epoch": 0.15, + "learning_rate": 4.2631820317218855e-05, + "loss": 0.2338, "step": 66900 }, { - "epoch": 0.6, - "learning_rate": 2.032609674804072e-05, - "loss": 0.2191, + "epoch": 0.15, + "learning_rate": 4.2630701774009526e-05, + "loss": 0.237, "step": 66910 }, { - "epoch": 0.6, - "learning_rate": 2.0321592649310873e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.2629583230800204e-05, + "loss": 0.2354, "step": 66920 }, { - "epoch": 0.6, - "learning_rate": 2.0317088550581027e-05, - "loss": 0.2028, + "epoch": 0.15, + "learning_rate": 4.262846468759088e-05, + "loss": 0.2325, "step": 66930 }, { - "epoch": 0.6, - "learning_rate": 2.0312584451851185e-05, - "loss": 0.2102, + "epoch": 0.15, + "learning_rate": 4.262734614438156e-05, + "loss": 0.23, "step": 66940 }, { - "epoch": 0.6, - "learning_rate": 2.0308080353121342e-05, - "loss": 0.2018, + "epoch": 0.15, + "learning_rate": 4.262622760117224e-05, + "loss": 0.2336, "step": 66950 }, { - "epoch": 0.6, - "learning_rate": 2.0303576254391496e-05, - "loss": 0.2092, + "epoch": 0.15, + "learning_rate": 4.262510905796291e-05, + "loss": 0.2351, "step": 66960 }, { - "epoch": 0.6, - "learning_rate": 2.0299072155661654e-05, - "loss": 0.2031, + "epoch": 0.15, + "learning_rate": 4.262399051475359e-05, + "loss": 0.2335, "step": 66970 }, { - "epoch": 0.6, - "learning_rate": 2.0294568056931808e-05, - "loss": 0.2103, + "epoch": 0.15, + "learning_rate": 4.2622871971544265e-05, + "loss": 0.2392, "step": 66980 }, { - "epoch": 0.6, - "learning_rate": 2.0290063958201966e-05, - "loss": 0.2088, + "epoch": 0.15, + "learning_rate": 4.2621753428334936e-05, + "loss": 0.2405, "step": 66990 }, { - "epoch": 0.6, - "learning_rate": 2.028555985947212e-05, - "loss": 0.2127, + "epoch": 0.15, + "learning_rate": 4.2620634885125614e-05, + "loss": 0.2329, "step": 67000 }, { - "epoch": 0.6, - "learning_rate": 2.0281055760742277e-05, - "loss": 0.2084, + "epoch": 0.15, + "learning_rate": 4.2619516341916285e-05, + "loss": 0.2426, "step": 67010 }, { - "epoch": 0.6, - "learning_rate": 2.0276551662012435e-05, - "loss": 0.2085, + "epoch": 0.15, + "learning_rate": 4.261839779870696e-05, + "loss": 0.2377, "step": 67020 }, { - "epoch": 0.6, - "learning_rate": 2.0272047563282585e-05, - "loss": 0.2067, + "epoch": 0.15, + "learning_rate": 4.261727925549764e-05, + "loss": 0.2384, "step": 67030 }, { - "epoch": 0.6, - "learning_rate": 2.0267543464552743e-05, - "loss": 0.2027, + "epoch": 0.15, + "learning_rate": 4.261616071228832e-05, + "loss": 0.2353, "step": 67040 }, { - "epoch": 0.6, - "learning_rate": 2.02630393658229e-05, - "loss": 0.2138, + "epoch": 0.15, + "learning_rate": 4.2615042169079e-05, + "loss": 0.2385, "step": 67050 }, { - "epoch": 0.6, - "learning_rate": 2.0258535267093058e-05, - "loss": 0.2037, + "epoch": 0.15, + "learning_rate": 4.261392362586967e-05, + "loss": 0.2377, "step": 67060 }, { - "epoch": 0.6, - "learning_rate": 2.0254031168363212e-05, - "loss": 0.2141, + "epoch": 0.15, + "learning_rate": 4.2612805082660346e-05, + "loss": 0.2402, "step": 67070 }, { - "epoch": 0.6, - "learning_rate": 2.0249527069633366e-05, - "loss": 0.2182, + "epoch": 0.15, + "learning_rate": 4.2611686539451024e-05, + "loss": 0.238, "step": 67080 }, { - "epoch": 0.6, - "learning_rate": 2.0245022970903524e-05, - "loss": 0.2003, + "epoch": 0.15, + "learning_rate": 4.2610567996241695e-05, + "loss": 0.2332, "step": 67090 }, { - "epoch": 0.6, - "learning_rate": 2.0240518872173678e-05, - "loss": 0.2066, + "epoch": 0.15, + "learning_rate": 4.260944945303237e-05, + "loss": 0.2327, "step": 67100 }, { - "epoch": 0.6, - "learning_rate": 2.0236014773443835e-05, - "loss": 0.2074, + "epoch": 0.15, + "learning_rate": 4.2608330909823044e-05, + "loss": 0.2315, "step": 67110 }, { - "epoch": 0.6, - "learning_rate": 2.0231510674713993e-05, - "loss": 0.2019, + "epoch": 0.15, + "learning_rate": 4.260721236661372e-05, + "loss": 0.2289, "step": 67120 }, { - "epoch": 0.6, - "learning_rate": 2.0227006575984147e-05, - "loss": 0.2053, + "epoch": 0.15, + "learning_rate": 4.26060938234044e-05, + "loss": 0.2273, "step": 67130 }, { - "epoch": 0.6, - "learning_rate": 2.02225024772543e-05, - "loss": 0.2058, + "epoch": 0.15, + "learning_rate": 4.260497528019508e-05, + "loss": 0.2341, "step": 67140 }, { - "epoch": 0.6, - "learning_rate": 2.0217998378524458e-05, - "loss": 0.2131, + "epoch": 0.15, + "learning_rate": 4.2603856736985756e-05, + "loss": 0.2312, "step": 67150 }, { - "epoch": 0.6, - "learning_rate": 2.0213494279794616e-05, - "loss": 0.2077, + "epoch": 0.15, + "learning_rate": 4.260273819377643e-05, + "loss": 0.2356, "step": 67160 }, { - "epoch": 0.6, - "learning_rate": 2.020899018106477e-05, - "loss": 0.2139, + "epoch": 0.15, + "learning_rate": 4.2601619650567105e-05, + "loss": 0.2331, "step": 67170 }, { - "epoch": 0.6, - "learning_rate": 2.0204486082334924e-05, - "loss": 0.2076, + "epoch": 0.15, + "learning_rate": 4.260050110735778e-05, + "loss": 0.2303, "step": 67180 }, { - "epoch": 0.6, - "learning_rate": 2.019998198360508e-05, - "loss": 0.2148, + "epoch": 0.15, + "learning_rate": 4.2599382564148454e-05, + "loss": 0.2378, "step": 67190 }, { - "epoch": 0.6, - "learning_rate": 2.019547788487524e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.259826402093913e-05, + "loss": 0.2337, "step": 67200 }, { - "epoch": 0.6, - "learning_rate": 2.0190973786145393e-05, - "loss": 0.2062, + "epoch": 0.15, + "learning_rate": 4.25971454777298e-05, + "loss": 0.2362, "step": 67210 }, { - "epoch": 0.6, - "learning_rate": 2.018646968741555e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.259602693452048e-05, + "loss": 0.2313, "step": 67220 }, { - "epoch": 0.6, - "learning_rate": 2.0181965588685705e-05, - "loss": 0.2142, + "epoch": 0.15, + "learning_rate": 4.259490839131116e-05, + "loss": 0.2322, "step": 67230 }, { - "epoch": 0.6, - "learning_rate": 2.017746148995586e-05, - "loss": 0.2099, + "epoch": 0.15, + "learning_rate": 4.259378984810184e-05, + "loss": 0.2327, "step": 67240 }, { - "epoch": 0.6, - "learning_rate": 2.0172957391226016e-05, - "loss": 0.2043, + "epoch": 0.15, + "learning_rate": 4.2592671304892515e-05, + "loss": 0.2384, "step": 67250 }, { - "epoch": 0.6, - "learning_rate": 2.0168453292496174e-05, - "loss": 0.2043, + "epoch": 0.15, + "learning_rate": 4.2591552761683186e-05, + "loss": 0.2412, "step": 67260 }, { - "epoch": 0.6, - "learning_rate": 2.0163949193766328e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.2590434218473864e-05, + "loss": 0.238, "step": 67270 }, { - "epoch": 0.6, - "learning_rate": 2.0159445095036482e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.2589315675264535e-05, + "loss": 0.2338, "step": 67280 }, { - "epoch": 0.6, - "learning_rate": 2.015494099630664e-05, - "loss": 0.2091, + "epoch": 0.15, + "learning_rate": 4.258819713205521e-05, + "loss": 0.2348, "step": 67290 }, { - "epoch": 0.6, - "learning_rate": 2.0150436897576797e-05, - "loss": 0.211, + "epoch": 0.15, + "learning_rate": 4.258707858884589e-05, + "loss": 0.2283, "step": 67300 }, { - "epoch": 0.6, - "learning_rate": 2.014593279884695e-05, - "loss": 0.2097, + "epoch": 0.15, + "learning_rate": 4.258596004563656e-05, + "loss": 0.2271, "step": 67310 }, { - "epoch": 0.6, - "learning_rate": 2.014142870011711e-05, - "loss": 0.2112, + "epoch": 0.15, + "learning_rate": 4.258484150242724e-05, + "loss": 0.2294, "step": 67320 }, { - "epoch": 0.6, - "learning_rate": 2.0136924601387263e-05, - "loss": 0.2115, + "epoch": 0.15, + "learning_rate": 4.258372295921791e-05, + "loss": 0.231, "step": 67330 }, { - "epoch": 0.6, - "learning_rate": 2.013242050265742e-05, - "loss": 0.2059, + "epoch": 0.15, + "learning_rate": 4.258260441600859e-05, + "loss": 0.2361, "step": 67340 }, { - "epoch": 0.6, - "learning_rate": 2.0127916403927574e-05, - "loss": 0.216, + "epoch": 0.15, + "learning_rate": 4.258148587279927e-05, + "loss": 0.2318, "step": 67350 }, { - "epoch": 0.6, - "learning_rate": 2.0123412305197732e-05, - "loss": 0.2087, + "epoch": 0.15, + "learning_rate": 4.2580479183910876e-05, + "loss": 0.2335, "step": 67360 }, { - "epoch": 0.6, - "learning_rate": 2.0118908206467886e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.2579360640701554e-05, + "loss": 0.2314, "step": 67370 }, { - "epoch": 0.6, - "learning_rate": 2.011440410773804e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.2578242097492225e-05, + "loss": 0.2335, "step": 67380 }, { - "epoch": 0.6, - "learning_rate": 2.0109900009008197e-05, - "loss": 0.2094, + "epoch": 0.15, + "learning_rate": 4.25771235542829e-05, + "loss": 0.2334, "step": 67390 }, { - "epoch": 0.6, - "learning_rate": 2.0105395910278355e-05, - "loss": 0.2064, + "epoch": 0.15, + "learning_rate": 4.257600501107358e-05, + "loss": 0.2395, "step": 67400 }, { - "epoch": 0.6, - "learning_rate": 2.0100891811548512e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.257488646786426e-05, + "loss": 0.2299, "step": 67410 }, { - "epoch": 0.6, - "learning_rate": 2.0096387712818667e-05, - "loss": 0.2038, + "epoch": 0.15, + "learning_rate": 4.257376792465494e-05, + "loss": 0.2312, "step": 67420 }, { - "epoch": 0.6, - "learning_rate": 2.009188361408882e-05, - "loss": 0.204, + "epoch": 0.15, + "learning_rate": 4.257264938144561e-05, + "loss": 0.2354, "step": 67430 }, { - "epoch": 0.6, - "learning_rate": 2.0087379515358978e-05, - "loss": 0.2116, + "epoch": 0.15, + "learning_rate": 4.2571530838236286e-05, + "loss": 0.2331, "step": 67440 }, { - "epoch": 0.6, - "learning_rate": 2.0082875416629132e-05, - "loss": 0.2093, + "epoch": 0.15, + "learning_rate": 4.257041229502696e-05, + "loss": 0.236, "step": 67450 }, { - "epoch": 0.6, - "learning_rate": 2.007837131789929e-05, - "loss": 0.2115, + "epoch": 0.15, + "learning_rate": 4.2569293751817635e-05, + "loss": 0.2319, "step": 67460 }, { - "epoch": 0.6, - "learning_rate": 2.0073867219169444e-05, - "loss": 0.2106, + "epoch": 0.15, + "learning_rate": 4.256817520860831e-05, + "loss": 0.2281, "step": 67470 }, { - "epoch": 0.6, - "learning_rate": 2.00693631204396e-05, - "loss": 0.2118, + "epoch": 0.15, + "learning_rate": 4.2567056665398984e-05, + "loss": 0.2328, "step": 67480 }, { - "epoch": 0.6, - "learning_rate": 2.0064859021709755e-05, - "loss": 0.2102, + "epoch": 0.15, + "learning_rate": 4.256593812218966e-05, + "loss": 0.2315, "step": 67490 }, { - "epoch": 0.6, - "learning_rate": 2.0060354922979913e-05, - "loss": 0.2151, + "epoch": 0.15, + "learning_rate": 4.256481957898033e-05, + "loss": 0.2354, "step": 67500 }, { - "epoch": 0.6, - "learning_rate": 2.005585082425007e-05, - "loss": 0.2161, + "epoch": 0.15, + "learning_rate": 4.256370103577101e-05, + "loss": 0.2368, "step": 67510 }, { - "epoch": 0.6, - "learning_rate": 2.0051346725520225e-05, - "loss": 0.2106, + "epoch": 0.15, + "learning_rate": 4.2562582492561696e-05, + "loss": 0.2335, "step": 67520 }, { - "epoch": 0.6, - "learning_rate": 2.004684262679038e-05, - "loss": 0.2095, + "epoch": 0.15, + "learning_rate": 4.256146394935237e-05, + "loss": 0.2303, "step": 67530 }, { - "epoch": 0.6, - "learning_rate": 2.0042338528060536e-05, - "loss": 0.2071, + "epoch": 0.15, + "learning_rate": 4.2560345406143045e-05, + "loss": 0.2258, "step": 67540 }, { - "epoch": 0.6, - "learning_rate": 2.0037834429330694e-05, - "loss": 0.2123, + "epoch": 0.15, + "learning_rate": 4.2559226862933716e-05, + "loss": 0.2331, "step": 67550 }, { - "epoch": 0.6, - "learning_rate": 2.0033330330600848e-05, - "loss": 0.2101, + "epoch": 0.15, + "learning_rate": 4.2558108319724394e-05, + "loss": 0.233, "step": 67560 }, { - "epoch": 0.6, - "learning_rate": 2.0028826231871002e-05, - "loss": 0.205, + "epoch": 0.15, + "learning_rate": 4.255698977651507e-05, + "loss": 0.2311, "step": 67570 }, { - "epoch": 0.6, - "learning_rate": 2.002432213314116e-05, - "loss": 0.2093, + "epoch": 0.15, + "learning_rate": 4.255587123330574e-05, + "loss": 0.2337, "step": 67580 }, { - "epoch": 0.6, - "learning_rate": 2.0019818034411313e-05, - "loss": 0.2125, + "epoch": 0.15, + "learning_rate": 4.255475269009642e-05, + "loss": 0.2345, "step": 67590 }, { - "epoch": 0.6, - "learning_rate": 2.001531393568147e-05, - "loss": 0.2018, + "epoch": 0.15, + "learning_rate": 4.255363414688709e-05, + "loss": 0.2315, "step": 67600 }, { - "epoch": 0.6, - "learning_rate": 2.001080983695163e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.255251560367777e-05, + "loss": 0.2344, "step": 67610 }, { - "epoch": 0.6, - "learning_rate": 2.0006305738221783e-05, - "loss": 0.206, + "epoch": 0.15, + "learning_rate": 4.255139706046845e-05, + "loss": 0.234, "step": 67620 }, { - "epoch": 0.6, - "learning_rate": 2.0001801639491937e-05, - "loss": 0.2091, + "epoch": 0.15, + "learning_rate": 4.2550278517259126e-05, + "loss": 0.2357, "step": 67630 }, { - "epoch": 0.6, - "learning_rate": 1.9997297540762094e-05, - "loss": 0.2132, + "epoch": 0.15, + "learning_rate": 4.2549159974049804e-05, + "loss": 0.2322, "step": 67640 }, { - "epoch": 0.6, - "learning_rate": 1.999279344203225e-05, - "loss": 0.2103, + "epoch": 0.15, + "learning_rate": 4.2548041430840475e-05, + "loss": 0.2332, "step": 67650 }, { - "epoch": 0.6, - "learning_rate": 1.9988289343302406e-05, - "loss": 0.2083, + "epoch": 0.15, + "learning_rate": 4.254692288763115e-05, + "loss": 0.2318, "step": 67660 }, { - "epoch": 0.6, - "learning_rate": 1.9983785244572563e-05, - "loss": 0.2124, + "epoch": 0.15, + "learning_rate": 4.2545804344421824e-05, + "loss": 0.2297, "step": 67670 }, { - "epoch": 0.6, - "learning_rate": 1.9979281145842717e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.25446858012125e-05, + "loss": 0.2346, "step": 67680 }, { - "epoch": 0.6, - "learning_rate": 1.9974777047112875e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.254356725800318e-05, + "loss": 0.2329, "step": 67690 }, { - "epoch": 0.6, - "learning_rate": 1.997027294838303e-05, - "loss": 0.2077, + "epoch": 0.15, + "learning_rate": 4.254244871479385e-05, + "loss": 0.2344, "step": 67700 }, { - "epoch": 0.6, - "learning_rate": 1.9965768849653186e-05, - "loss": 0.206, + "epoch": 0.15, + "learning_rate": 4.254133017158453e-05, + "loss": 0.2385, "step": 67710 }, { - "epoch": 0.6, - "learning_rate": 1.996126475092334e-05, - "loss": 0.2041, + "epoch": 0.15, + "learning_rate": 4.254021162837521e-05, + "loss": 0.2398, "step": 67720 }, { - "epoch": 0.6, - "learning_rate": 1.9956760652193495e-05, - "loss": 0.2078, + "epoch": 0.15, + "learning_rate": 4.2539093085165885e-05, + "loss": 0.2305, "step": 67730 }, { - "epoch": 0.6, - "learning_rate": 1.9952256553463652e-05, - "loss": 0.2085, + "epoch": 0.15, + "learning_rate": 4.253797454195656e-05, + "loss": 0.2338, "step": 67740 }, { - "epoch": 0.6, - "learning_rate": 1.994775245473381e-05, - "loss": 0.2144, + "epoch": 0.15, + "learning_rate": 4.2536855998747234e-05, + "loss": 0.237, "step": 67750 }, { - "epoch": 0.6, - "learning_rate": 1.9943248356003967e-05, - "loss": 0.2128, + "epoch": 0.15, + "learning_rate": 4.253573745553791e-05, + "loss": 0.2329, "step": 67760 }, { - "epoch": 0.61, - "learning_rate": 1.993874425727412e-05, - "loss": 0.2078, + "epoch": 0.15, + "learning_rate": 4.253461891232858e-05, + "loss": 0.234, "step": 67770 }, { - "epoch": 0.61, - "learning_rate": 1.9934240158544275e-05, - "loss": 0.1997, + "epoch": 0.15, + "learning_rate": 4.253350036911926e-05, + "loss": 0.2281, "step": 67780 }, { - "epoch": 0.61, - "learning_rate": 1.9929736059814433e-05, - "loss": 0.2041, + "epoch": 0.15, + "learning_rate": 4.253238182590994e-05, + "loss": 0.2355, "step": 67790 }, { - "epoch": 0.61, - "learning_rate": 1.9925231961084587e-05, - "loss": 0.2056, + "epoch": 0.15, + "learning_rate": 4.253126328270061e-05, + "loss": 0.2392, "step": 67800 }, { - "epoch": 0.61, - "learning_rate": 1.9920727862354744e-05, - "loss": 0.2133, + "epoch": 0.15, + "learning_rate": 4.253014473949129e-05, + "loss": 0.2313, "step": 67810 }, { - "epoch": 0.61, - "learning_rate": 1.99162237636249e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.2529026196281966e-05, + "loss": 0.2308, "step": 67820 }, { - "epoch": 0.61, - "learning_rate": 1.9911719664895056e-05, - "loss": 0.2028, + "epoch": 0.15, + "learning_rate": 4.2527907653072644e-05, + "loss": 0.2288, "step": 67830 }, { - "epoch": 0.61, - "learning_rate": 1.990721556616521e-05, - "loss": 0.205, + "epoch": 0.15, + "learning_rate": 4.252678910986332e-05, + "loss": 0.2303, "step": 67840 }, { - "epoch": 0.61, - "learning_rate": 1.9902711467435368e-05, - "loss": 0.2061, + "epoch": 0.15, + "learning_rate": 4.252567056665399e-05, + "loss": 0.2289, "step": 67850 }, { - "epoch": 0.61, - "learning_rate": 1.9898207368705525e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.252455202344467e-05, + "loss": 0.2266, "step": 67860 }, { - "epoch": 0.61, - "learning_rate": 1.989370326997568e-05, - "loss": 0.2162, + "epoch": 0.15, + "learning_rate": 4.252343348023534e-05, + "loss": 0.2302, "step": 67870 }, { - "epoch": 0.61, - "learning_rate": 1.9889199171245833e-05, - "loss": 0.2072, + "epoch": 0.15, + "learning_rate": 4.252231493702602e-05, + "loss": 0.2337, "step": 67880 }, { - "epoch": 0.61, - "learning_rate": 1.988469507251599e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.25211963938167e-05, + "loss": 0.2332, "step": 67890 }, { - "epoch": 0.61, - "learning_rate": 1.9880190973786148e-05, - "loss": 0.2099, + "epoch": 0.15, + "learning_rate": 4.252007785060737e-05, + "loss": 0.2325, "step": 67900 }, { - "epoch": 0.61, - "learning_rate": 1.9875686875056302e-05, - "loss": 0.2112, + "epoch": 0.15, + "learning_rate": 4.251895930739805e-05, + "loss": 0.2315, "step": 67910 }, { - "epoch": 0.61, - "learning_rate": 1.9871182776326456e-05, - "loss": 0.2071, + "epoch": 0.15, + "learning_rate": 4.251784076418872e-05, + "loss": 0.2334, "step": 67920 }, { - "epoch": 0.61, - "learning_rate": 1.9866678677596614e-05, - "loss": 0.2125, + "epoch": 0.15, + "learning_rate": 4.2516722220979396e-05, + "loss": 0.2276, "step": 67930 }, { - "epoch": 0.61, - "learning_rate": 1.9862174578866768e-05, - "loss": 0.2146, + "epoch": 0.15, + "learning_rate": 4.2515603677770074e-05, + "loss": 0.2411, "step": 67940 }, { - "epoch": 0.61, - "learning_rate": 1.9857670480136926e-05, - "loss": 0.2074, + "epoch": 0.15, + "learning_rate": 4.251448513456075e-05, + "loss": 0.2365, "step": 67950 }, { - "epoch": 0.61, - "learning_rate": 1.9853166381407083e-05, - "loss": 0.2132, + "epoch": 0.15, + "learning_rate": 4.251336659135143e-05, + "loss": 0.2309, "step": 67960 }, { - "epoch": 0.61, - "learning_rate": 1.9848662282677237e-05, - "loss": 0.2059, + "epoch": 0.15, + "learning_rate": 4.25122480481421e-05, + "loss": 0.2291, "step": 67970 }, { - "epoch": 0.61, - "learning_rate": 1.984415818394739e-05, - "loss": 0.2105, + "epoch": 0.15, + "learning_rate": 4.251112950493278e-05, + "loss": 0.2331, "step": 67980 }, { - "epoch": 0.61, - "learning_rate": 1.983965408521755e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.251001096172345e-05, + "loss": 0.2389, "step": 67990 }, { - "epoch": 0.61, - "learning_rate": 1.9835149986487706e-05, - "loss": 0.2111, + "epoch": 0.15, + "learning_rate": 4.250889241851413e-05, + "loss": 0.2382, "step": 68000 }, { - "epoch": 0.61, - "learning_rate": 1.983064588775786e-05, - "loss": 0.2115, + "epoch": 0.15, + "learning_rate": 4.2507773875304806e-05, + "loss": 0.2331, "step": 68010 }, { - "epoch": 0.61, - "learning_rate": 1.9826141789028014e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.250665533209548e-05, + "loss": 0.2311, "step": 68020 }, { - "epoch": 0.61, - "learning_rate": 1.9821637690298172e-05, - "loss": 0.2084, + "epoch": 0.15, + "learning_rate": 4.2505536788886155e-05, + "loss": 0.2311, "step": 68030 }, { - "epoch": 0.61, - "learning_rate": 1.981713359156833e-05, - "loss": 0.2068, + "epoch": 0.15, + "learning_rate": 4.250441824567683e-05, + "loss": 0.2387, "step": 68040 }, { - "epoch": 0.61, - "learning_rate": 1.9812629492838484e-05, - "loss": 0.2115, + "epoch": 0.15, + "learning_rate": 4.250329970246751e-05, + "loss": 0.2273, "step": 68050 }, { - "epoch": 0.61, - "learning_rate": 1.980812539410864e-05, - "loss": 0.208, + "epoch": 0.15, + "learning_rate": 4.250218115925819e-05, + "loss": 0.2352, "step": 68060 }, { - "epoch": 0.61, - "learning_rate": 1.9803621295378795e-05, - "loss": 0.208, + "epoch": 0.15, + "learning_rate": 4.250106261604886e-05, + "loss": 0.2289, "step": 68070 }, { - "epoch": 0.61, - "learning_rate": 1.979911719664895e-05, - "loss": 0.2111, + "epoch": 0.15, + "learning_rate": 4.249994407283954e-05, + "loss": 0.2347, "step": 68080 }, { - "epoch": 0.61, - "learning_rate": 1.9794613097919107e-05, - "loss": 0.2136, + "epoch": 0.15, + "learning_rate": 4.249882552963021e-05, + "loss": 0.2294, "step": 68090 }, { - "epoch": 0.61, - "learning_rate": 1.9790108999189264e-05, - "loss": 0.2036, + "epoch": 0.15, + "learning_rate": 4.249770698642089e-05, + "loss": 0.2329, "step": 68100 }, { - "epoch": 0.61, - "learning_rate": 1.978560490045942e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.2496588443211565e-05, + "loss": 0.2336, "step": 68110 }, { - "epoch": 0.61, - "learning_rate": 1.9781100801729572e-05, - "loss": 0.2102, + "epoch": 0.15, + "learning_rate": 4.2495469900002236e-05, + "loss": 0.2331, "step": 68120 }, { - "epoch": 0.61, - "learning_rate": 1.977659670299973e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.2494351356792914e-05, + "loss": 0.2302, "step": 68130 }, { - "epoch": 0.61, - "learning_rate": 1.9772092604269887e-05, - "loss": 0.2075, + "epoch": 0.15, + "learning_rate": 4.249323281358359e-05, + "loss": 0.2284, "step": 68140 }, { - "epoch": 0.61, - "learning_rate": 1.976758850554004e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.249211427037427e-05, + "loss": 0.2281, "step": 68150 }, { - "epoch": 0.61, - "learning_rate": 1.97630844068102e-05, - "loss": 0.2071, + "epoch": 0.15, + "learning_rate": 4.249099572716495e-05, + "loss": 0.2316, "step": 68160 }, { - "epoch": 0.61, - "learning_rate": 1.9758580308080353e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.248987718395562e-05, + "loss": 0.2393, "step": 68170 }, { - "epoch": 0.61, - "learning_rate": 1.975407620935051e-05, - "loss": 0.2076, + "epoch": 0.15, + "learning_rate": 4.2488758640746297e-05, + "loss": 0.2344, "step": 68180 }, { - "epoch": 0.61, - "learning_rate": 1.9749572110620665e-05, - "loss": 0.2108, + "epoch": 0.15, + "learning_rate": 4.248764009753697e-05, + "loss": 0.234, "step": 68190 }, { - "epoch": 0.61, - "learning_rate": 1.9745068011890822e-05, - "loss": 0.206, + "epoch": 0.15, + "learning_rate": 4.2486521554327646e-05, + "loss": 0.2374, "step": 68200 }, { - "epoch": 0.61, - "learning_rate": 1.974056391316098e-05, - "loss": 0.2127, + "epoch": 0.15, + "learning_rate": 4.248540301111832e-05, + "loss": 0.2354, "step": 68210 }, { - "epoch": 0.61, - "learning_rate": 1.973605981443113e-05, - "loss": 0.2107, + "epoch": 0.15, + "learning_rate": 4.2484284467908995e-05, + "loss": 0.2314, "step": 68220 }, { - "epoch": 0.61, - "learning_rate": 1.9731555715701288e-05, - "loss": 0.2121, + "epoch": 0.15, + "learning_rate": 4.248316592469967e-05, + "loss": 0.2363, "step": 68230 }, { - "epoch": 0.61, - "learning_rate": 1.9727051616971445e-05, - "loss": 0.2051, + "epoch": 0.15, + "learning_rate": 4.248204738149035e-05, + "loss": 0.2346, "step": 68240 }, { - "epoch": 0.61, - "learning_rate": 1.9722547518241603e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.248092883828103e-05, + "loss": 0.2361, "step": 68250 }, { - "epoch": 0.61, - "learning_rate": 1.9718043419511757e-05, - "loss": 0.2085, + "epoch": 0.15, + "learning_rate": 4.24798102950717e-05, + "loss": 0.2329, "step": 68260 }, { - "epoch": 0.61, - "learning_rate": 1.971353932078191e-05, - "loss": 0.2066, + "epoch": 0.15, + "learning_rate": 4.247869175186238e-05, + "loss": 0.231, "step": 68270 }, { - "epoch": 0.61, - "learning_rate": 1.970903522205207e-05, - "loss": 0.2082, + "epoch": 0.15, + "learning_rate": 4.2477573208653056e-05, + "loss": 0.2366, "step": 68280 }, { - "epoch": 0.61, - "learning_rate": 1.9704531123322223e-05, - "loss": 0.2094, + "epoch": 0.15, + "learning_rate": 4.247645466544373e-05, + "loss": 0.2374, "step": 68290 }, { - "epoch": 0.61, - "learning_rate": 1.970002702459238e-05, - "loss": 0.2107, + "epoch": 0.15, + "learning_rate": 4.2475336122234405e-05, + "loss": 0.2275, "step": 68300 }, { - "epoch": 0.61, - "learning_rate": 1.9695522925862538e-05, - "loss": 0.2094, + "epoch": 0.15, + "learning_rate": 4.2474217579025076e-05, + "loss": 0.234, "step": 68310 }, { - "epoch": 0.61, - "learning_rate": 1.9691018827132692e-05, - "loss": 0.2119, + "epoch": 0.15, + "learning_rate": 4.2473099035815754e-05, + "loss": 0.2398, "step": 68320 }, { - "epoch": 0.61, - "learning_rate": 1.9686514728402846e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.247198049260643e-05, + "loss": 0.232, "step": 68330 }, { - "epoch": 0.61, - "learning_rate": 1.9682010629673003e-05, - "loss": 0.2037, + "epoch": 0.15, + "learning_rate": 4.24708619493971e-05, + "loss": 0.2393, "step": 68340 }, { - "epoch": 0.61, - "learning_rate": 1.967750653094316e-05, - "loss": 0.2096, + "epoch": 0.15, + "learning_rate": 4.246974340618779e-05, + "loss": 0.2328, "step": 68350 }, { - "epoch": 0.61, - "learning_rate": 1.9673002432213315e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.246862486297846e-05, + "loss": 0.2372, "step": 68360 }, { - "epoch": 0.61, - "learning_rate": 1.966849833348347e-05, - "loss": 0.2039, + "epoch": 0.15, + "learning_rate": 4.2467506319769137e-05, + "loss": 0.229, "step": 68370 }, { - "epoch": 0.61, - "learning_rate": 1.9663994234753627e-05, - "loss": 0.2105, + "epoch": 0.15, + "learning_rate": 4.2466387776559814e-05, + "loss": 0.236, "step": 68380 }, { - "epoch": 0.61, - "learning_rate": 1.9659490136023784e-05, - "loss": 0.2083, + "epoch": 0.15, + "learning_rate": 4.2465269233350486e-05, + "loss": 0.2348, "step": 68390 }, { - "epoch": 0.61, - "learning_rate": 1.9654986037293938e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.2464150690141164e-05, + "loss": 0.2313, "step": 68400 }, { - "epoch": 0.61, - "learning_rate": 1.9650481938564096e-05, - "loss": 0.2178, + "epoch": 0.15, + "learning_rate": 4.2463032146931835e-05, + "loss": 0.2314, "step": 68410 }, { - "epoch": 0.61, - "learning_rate": 1.964597783983425e-05, - "loss": 0.2064, + "epoch": 0.15, + "learning_rate": 4.246191360372251e-05, + "loss": 0.2312, "step": 68420 }, { - "epoch": 0.61, - "learning_rate": 1.9641473741104404e-05, - "loss": 0.2054, + "epoch": 0.15, + "learning_rate": 4.246079506051319e-05, + "loss": 0.237, "step": 68430 }, { - "epoch": 0.61, - "learning_rate": 1.963696964237456e-05, - "loss": 0.2049, + "epoch": 0.15, + "learning_rate": 4.245967651730386e-05, + "loss": 0.2374, "step": 68440 }, { - "epoch": 0.61, - "learning_rate": 1.963246554364472e-05, - "loss": 0.2137, + "epoch": 0.15, + "learning_rate": 4.245855797409454e-05, + "loss": 0.2348, "step": 68450 }, { - "epoch": 0.61, - "learning_rate": 1.9627961444914876e-05, - "loss": 0.2009, + "epoch": 0.15, + "learning_rate": 4.245743943088522e-05, + "loss": 0.2315, "step": 68460 }, { - "epoch": 0.61, - "learning_rate": 1.9623457346185027e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.2456320887675895e-05, + "loss": 0.2326, "step": 68470 }, { - "epoch": 0.61, - "learning_rate": 1.9618953247455185e-05, - "loss": 0.2045, + "epoch": 0.15, + "learning_rate": 4.2455202344466573e-05, + "loss": 0.2275, "step": 68480 }, { - "epoch": 0.61, - "learning_rate": 1.9614449148725342e-05, - "loss": 0.2064, + "epoch": 0.15, + "learning_rate": 4.2454083801257245e-05, + "loss": 0.2331, "step": 68490 }, { - "epoch": 0.61, - "learning_rate": 1.9609945049995496e-05, - "loss": 0.2058, + "epoch": 0.15, + "learning_rate": 4.245296525804792e-05, + "loss": 0.237, "step": 68500 }, { - "epoch": 0.61, - "learning_rate": 1.9605440951265654e-05, - "loss": 0.2094, + "epoch": 0.15, + "learning_rate": 4.2451846714838594e-05, + "loss": 0.2321, "step": 68510 }, { - "epoch": 0.61, - "learning_rate": 1.9600936852535808e-05, - "loss": 0.2139, + "epoch": 0.15, + "learning_rate": 4.245072817162927e-05, + "loss": 0.2347, "step": 68520 }, { - "epoch": 0.61, - "learning_rate": 1.9596432753805965e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.244960962841994e-05, + "loss": 0.2301, "step": 68530 }, { - "epoch": 0.61, - "learning_rate": 1.959192865507612e-05, - "loss": 0.2077, + "epoch": 0.15, + "learning_rate": 4.244849108521062e-05, + "loss": 0.2336, "step": 68540 }, { - "epoch": 0.61, - "learning_rate": 1.9587424556346277e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.24473725420013e-05, + "loss": 0.2397, "step": 68550 }, { - "epoch": 0.61, - "learning_rate": 1.9582920457616434e-05, - "loss": 0.211, + "epoch": 0.15, + "learning_rate": 4.2446253998791977e-05, + "loss": 0.2295, "step": 68560 }, { - "epoch": 0.61, - "learning_rate": 1.9578416358886585e-05, - "loss": 0.2075, + "epoch": 0.15, + "learning_rate": 4.2445135455582654e-05, + "loss": 0.2306, "step": 68570 }, { - "epoch": 0.61, - "learning_rate": 1.9573912260156743e-05, - "loss": 0.2088, + "epoch": 0.15, + "learning_rate": 4.2444016912373326e-05, + "loss": 0.231, "step": 68580 }, { - "epoch": 0.61, - "learning_rate": 1.95694081614269e-05, - "loss": 0.2033, + "epoch": 0.15, + "learning_rate": 4.2442898369164004e-05, + "loss": 0.2332, "step": 68590 }, { - "epoch": 0.61, - "learning_rate": 1.9564904062697057e-05, - "loss": 0.2068, + "epoch": 0.15, + "learning_rate": 4.244177982595468e-05, + "loss": 0.2322, "step": 68600 }, { - "epoch": 0.61, - "learning_rate": 1.956039996396721e-05, - "loss": 0.2063, + "epoch": 0.15, + "learning_rate": 4.244066128274535e-05, + "loss": 0.2297, "step": 68610 }, { - "epoch": 0.61, - "learning_rate": 1.9555895865237366e-05, - "loss": 0.2049, + "epoch": 0.15, + "learning_rate": 4.243954273953603e-05, + "loss": 0.2329, "step": 68620 }, { - "epoch": 0.61, - "learning_rate": 1.9551391766507523e-05, - "loss": 0.203, + "epoch": 0.15, + "learning_rate": 4.24384241963267e-05, + "loss": 0.2362, "step": 68630 }, { - "epoch": 0.61, - "learning_rate": 1.9546887667777677e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.243730565311738e-05, + "loss": 0.2394, "step": 68640 }, { - "epoch": 0.61, - "learning_rate": 1.9542383569047835e-05, - "loss": 0.2116, + "epoch": 0.15, + "learning_rate": 4.243618710990806e-05, + "loss": 0.2341, "step": 68650 }, { - "epoch": 0.61, - "learning_rate": 1.9537879470317992e-05, - "loss": 0.2094, + "epoch": 0.15, + "learning_rate": 4.2435068566698735e-05, + "loss": 0.2315, "step": 68660 }, { - "epoch": 0.61, - "learning_rate": 1.9533375371588146e-05, - "loss": 0.2068, + "epoch": 0.15, + "learning_rate": 4.243395002348941e-05, + "loss": 0.2337, "step": 68670 }, { - "epoch": 0.61, - "learning_rate": 1.95288712728583e-05, - "loss": 0.2062, + "epoch": 0.15, + "learning_rate": 4.2432831480280085e-05, + "loss": 0.2275, "step": 68680 }, { - "epoch": 0.61, - "learning_rate": 1.9524367174128458e-05, - "loss": 0.2049, + "epoch": 0.15, + "learning_rate": 4.243171293707076e-05, + "loss": 0.2339, "step": 68690 }, { - "epoch": 0.61, - "learning_rate": 1.9519863075398615e-05, - "loss": 0.2045, + "epoch": 0.15, + "learning_rate": 4.243059439386144e-05, + "loss": 0.2305, "step": 68700 }, { - "epoch": 0.61, - "learning_rate": 1.951535897666877e-05, - "loss": 0.2053, + "epoch": 0.15, + "learning_rate": 4.242947585065211e-05, + "loss": 0.2312, "step": 68710 }, { - "epoch": 0.61, - "learning_rate": 1.9510854877938924e-05, - "loss": 0.2071, + "epoch": 0.15, + "learning_rate": 4.242835730744279e-05, + "loss": 0.2292, "step": 68720 }, { - "epoch": 0.61, - "learning_rate": 1.950635077920908e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.242723876423346e-05, + "loss": 0.2312, "step": 68730 }, { - "epoch": 0.61, - "learning_rate": 1.950184668047924e-05, - "loss": 0.2088, + "epoch": 0.15, + "learning_rate": 4.242612022102414e-05, + "loss": 0.2343, "step": 68740 }, { - "epoch": 0.61, - "learning_rate": 1.9497342581749393e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.2425001677814816e-05, + "loss": 0.2335, "step": 68750 }, { - "epoch": 0.61, - "learning_rate": 1.949283848301955e-05, - "loss": 0.2129, + "epoch": 0.15, + "learning_rate": 4.2423883134605494e-05, + "loss": 0.2287, "step": 68760 }, { - "epoch": 0.61, - "learning_rate": 1.9488334384289704e-05, - "loss": 0.2068, + "epoch": 0.15, + "learning_rate": 4.242276459139617e-05, + "loss": 0.2352, "step": 68770 }, { - "epoch": 0.61, - "learning_rate": 1.948383028555986e-05, - "loss": 0.2076, + "epoch": 0.15, + "learning_rate": 4.2421646048186843e-05, + "loss": 0.2326, "step": 68780 }, { - "epoch": 0.61, - "learning_rate": 1.9479326186830016e-05, - "loss": 0.2056, + "epoch": 0.15, + "learning_rate": 4.242052750497752e-05, + "loss": 0.2334, "step": 68790 }, { - "epoch": 0.61, - "learning_rate": 1.9474822088100173e-05, - "loss": 0.2111, + "epoch": 0.15, + "learning_rate": 4.24194089617682e-05, + "loss": 0.2292, "step": 68800 }, { - "epoch": 0.61, - "learning_rate": 1.9470317989370328e-05, - "loss": 0.1977, + "epoch": 0.15, + "learning_rate": 4.241829041855887e-05, + "loss": 0.2365, "step": 68810 }, { - "epoch": 0.61, - "learning_rate": 1.946581389064048e-05, - "loss": 0.2042, + "epoch": 0.15, + "learning_rate": 4.241717187534955e-05, + "loss": 0.2324, "step": 68820 }, { - "epoch": 0.61, - "learning_rate": 1.946130979191064e-05, - "loss": 0.2081, + "epoch": 0.15, + "learning_rate": 4.241605333214022e-05, + "loss": 0.2364, "step": 68830 }, { - "epoch": 0.61, - "learning_rate": 1.9456805693180797e-05, - "loss": 0.2072, + "epoch": 0.15, + "learning_rate": 4.24149347889309e-05, + "loss": 0.2338, "step": 68840 }, { - "epoch": 0.61, - "learning_rate": 1.945230159445095e-05, - "loss": 0.2106, + "epoch": 0.15, + "learning_rate": 4.241381624572157e-05, + "loss": 0.2291, "step": 68850 }, { - "epoch": 0.61, - "learning_rate": 1.9447797495721108e-05, - "loss": 0.207, + "epoch": 0.15, + "learning_rate": 4.2412697702512247e-05, + "loss": 0.228, "step": 68860 }, { - "epoch": 0.61, - "learning_rate": 1.9443293396991262e-05, - "loss": 0.2069, + "epoch": 0.15, + "learning_rate": 4.2411579159302925e-05, + "loss": 0.2322, "step": 68870 }, { - "epoch": 0.61, - "learning_rate": 1.943878929826142e-05, - "loss": 0.2055, + "epoch": 0.15, + "learning_rate": 4.24104606160936e-05, + "loss": 0.2307, "step": 68880 }, { - "epoch": 0.62, - "learning_rate": 1.9434285199531574e-05, - "loss": 0.2061, + "epoch": 0.15, + "learning_rate": 4.240934207288428e-05, + "loss": 0.2322, "step": 68890 }, { - "epoch": 0.62, - "learning_rate": 1.942978110080173e-05, - "loss": 0.211, + "epoch": 0.15, + "learning_rate": 4.240822352967495e-05, + "loss": 0.2329, "step": 68900 }, { - "epoch": 0.62, - "learning_rate": 1.9425277002071886e-05, - "loss": 0.2033, + "epoch": 0.15, + "learning_rate": 4.240710498646563e-05, + "loss": 0.2325, "step": 68910 }, { - "epoch": 0.62, - "learning_rate": 1.942077290334204e-05, - "loss": 0.2098, + "epoch": 0.15, + "learning_rate": 4.240598644325631e-05, + "loss": 0.2355, "step": 68920 }, { - "epoch": 0.62, - "learning_rate": 1.9416268804612197e-05, - "loss": 0.2113, + "epoch": 0.15, + "learning_rate": 4.240486790004698e-05, + "loss": 0.2337, "step": 68930 }, { - "epoch": 0.62, - "learning_rate": 1.9411764705882355e-05, - "loss": 0.2032, + "epoch": 0.15, + "learning_rate": 4.2403749356837656e-05, + "loss": 0.2337, "step": 68940 }, { - "epoch": 0.62, - "learning_rate": 1.9407260607152512e-05, - "loss": 0.2091, + "epoch": 0.15, + "learning_rate": 4.240263081362833e-05, + "loss": 0.2326, "step": 68950 }, { - "epoch": 0.62, - "learning_rate": 1.9402756508422666e-05, - "loss": 0.2057, + "epoch": 0.15, + "learning_rate": 4.2401512270419006e-05, + "loss": 0.2331, "step": 68960 }, { - "epoch": 0.62, - "learning_rate": 1.939825240969282e-05, - "loss": 0.2049, + "epoch": 0.15, + "learning_rate": 4.2400393727209683e-05, + "loss": 0.2347, "step": 68970 }, { - "epoch": 0.62, - "learning_rate": 1.9393748310962978e-05, - "loss": 0.2079, + "epoch": 0.15, + "learning_rate": 4.239927518400036e-05, + "loss": 0.236, "step": 68980 }, { - "epoch": 0.62, - "learning_rate": 1.9389244212233132e-05, - "loss": 0.1995, + "epoch": 0.15, + "learning_rate": 4.239815664079104e-05, + "loss": 0.2305, "step": 68990 }, { - "epoch": 0.62, - "learning_rate": 1.938474011350329e-05, - "loss": 0.2056, + "epoch": 0.15, + "learning_rate": 4.239703809758171e-05, + "loss": 0.2314, "step": 69000 }, { - "epoch": 0.62, - "learning_rate": 1.9380236014773444e-05, - "loss": 0.2035, + "epoch": 0.15, + "learning_rate": 4.239591955437239e-05, + "loss": 0.2277, "step": 69010 }, { - "epoch": 0.62, - "learning_rate": 1.93757319160436e-05, - "loss": 0.2053, + "epoch": 0.15, + "learning_rate": 4.2394801011163066e-05, + "loss": 0.2288, "step": 69020 }, { - "epoch": 0.62, - "learning_rate": 1.9371227817313755e-05, - "loss": 0.2064, + "epoch": 0.15, + "learning_rate": 4.239368246795374e-05, + "loss": 0.2318, "step": 69030 }, { - "epoch": 0.62, - "learning_rate": 1.9366723718583913e-05, - "loss": 0.2078, + "epoch": 0.15, + "learning_rate": 4.2392563924744415e-05, + "loss": 0.2369, "step": 69040 }, { - "epoch": 0.62, - "learning_rate": 1.936221961985407e-05, - "loss": 0.2119, + "epoch": 0.15, + "learning_rate": 4.2391445381535087e-05, + "loss": 0.2263, "step": 69050 }, { - "epoch": 0.62, - "learning_rate": 1.9357715521124224e-05, - "loss": 0.2057, + "epoch": 0.15, + "learning_rate": 4.2390326838325764e-05, + "loss": 0.2335, "step": 69060 }, { - "epoch": 0.62, - "learning_rate": 1.935321142239438e-05, - "loss": 0.21, + "epoch": 0.15, + "learning_rate": 4.238920829511644e-05, + "loss": 0.2327, "step": 69070 }, { - "epoch": 0.62, - "learning_rate": 1.9348707323664536e-05, - "loss": 0.2052, + "epoch": 0.15, + "learning_rate": 4.238808975190712e-05, + "loss": 0.2357, "step": 69080 }, { - "epoch": 0.62, - "learning_rate": 1.9344203224934693e-05, - "loss": 0.1972, + "epoch": 0.15, + "learning_rate": 4.23869712086978e-05, + "loss": 0.2311, "step": 69090 }, { - "epoch": 0.62, - "learning_rate": 1.9339699126204847e-05, - "loss": 0.2074, + "epoch": 0.15, + "learning_rate": 4.238585266548847e-05, + "loss": 0.2336, "step": 69100 }, { - "epoch": 0.62, - "learning_rate": 1.9335195027475005e-05, - "loss": 0.2091, + "epoch": 0.15, + "learning_rate": 4.238473412227915e-05, + "loss": 0.236, "step": 69110 }, { - "epoch": 0.62, - "learning_rate": 1.933069092874516e-05, - "loss": 0.2107, + "epoch": 0.15, + "learning_rate": 4.2383615579069825e-05, + "loss": 0.2361, "step": 69120 }, { - "epoch": 0.62, - "learning_rate": 1.9326186830015313e-05, - "loss": 0.2034, + "epoch": 0.15, + "learning_rate": 4.2382497035860496e-05, + "loss": 0.2308, "step": 69130 }, { - "epoch": 0.62, - "learning_rate": 1.932168273128547e-05, - "loss": 0.2068, + "epoch": 0.15, + "learning_rate": 4.2381378492651174e-05, + "loss": 0.2252, "step": 69140 }, { - "epoch": 0.62, - "learning_rate": 1.9317178632555628e-05, - "loss": 0.2096, + "epoch": 0.15, + "learning_rate": 4.2380259949441845e-05, + "loss": 0.2316, "step": 69150 }, { - "epoch": 0.62, - "learning_rate": 1.9312674533825782e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.2379141406232523e-05, + "loss": 0.2316, "step": 69160 }, { - "epoch": 0.62, - "learning_rate": 1.9308170435095936e-05, - "loss": 0.2097, + "epoch": 0.15, + "learning_rate": 4.2378022863023195e-05, + "loss": 0.2315, "step": 69170 }, { - "epoch": 0.62, - "learning_rate": 1.9303666336366094e-05, - "loss": 0.2115, + "epoch": 0.15, + "learning_rate": 4.237690431981388e-05, + "loss": 0.235, "step": 69180 }, { - "epoch": 0.62, - "learning_rate": 1.929916223763625e-05, - "loss": 0.2073, + "epoch": 0.15, + "learning_rate": 4.237578577660456e-05, + "loss": 0.2354, "step": 69190 }, { - "epoch": 0.62, - "learning_rate": 1.9294658138906405e-05, - "loss": 0.2011, + "epoch": 0.15, + "learning_rate": 4.237466723339523e-05, + "loss": 0.2323, "step": 69200 }, { - "epoch": 0.62, - "learning_rate": 1.9290154040176563e-05, - "loss": 0.2031, + "epoch": 0.15, + "learning_rate": 4.2373548690185906e-05, + "loss": 0.2288, "step": 69210 }, { - "epoch": 0.62, - "learning_rate": 1.9285649941446717e-05, - "loss": 0.2005, + "epoch": 0.15, + "learning_rate": 4.237243014697658e-05, + "loss": 0.2286, "step": 69220 }, { - "epoch": 0.62, - "learning_rate": 1.9281596252589857e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.2371311603767255e-05, + "loss": 0.2312, "step": 69230 }, { - "epoch": 0.62, - "learning_rate": 1.927709215386001e-05, - "loss": 0.1991, + "epoch": 0.15, + "learning_rate": 4.237019306055793e-05, + "loss": 0.2297, "step": 69240 }, { - "epoch": 0.62, - "learning_rate": 1.927258805513017e-05, - "loss": 0.2003, + "epoch": 0.15, + "learning_rate": 4.2369074517348604e-05, + "loss": 0.2309, "step": 69250 }, { - "epoch": 0.62, - "learning_rate": 1.9268083956400326e-05, - "loss": 0.2062, + "epoch": 0.15, + "learning_rate": 4.236795597413928e-05, + "loss": 0.2306, "step": 69260 }, { - "epoch": 0.62, - "learning_rate": 1.926357985767048e-05, - "loss": 0.2015, + "epoch": 0.15, + "learning_rate": 4.2366837430929954e-05, + "loss": 0.2298, "step": 69270 }, { - "epoch": 0.62, - "learning_rate": 1.9259075758940638e-05, - "loss": 0.2, + "epoch": 0.15, + "learning_rate": 4.236571888772063e-05, + "loss": 0.2307, "step": 69280 }, { - "epoch": 0.62, - "learning_rate": 1.9254571660210792e-05, - "loss": 0.2012, + "epoch": 0.15, + "learning_rate": 4.236460034451131e-05, + "loss": 0.2256, "step": 69290 }, { - "epoch": 0.62, - "learning_rate": 1.9250067561480946e-05, - "loss": 0.2082, + "epoch": 0.15, + "learning_rate": 4.236348180130199e-05, + "loss": 0.2289, "step": 69300 }, { - "epoch": 0.62, - "learning_rate": 1.9245563462751104e-05, - "loss": 0.209, + "epoch": 0.15, + "learning_rate": 4.2362363258092665e-05, + "loss": 0.2266, "step": 69310 }, { - "epoch": 0.62, - "learning_rate": 1.924105936402126e-05, - "loss": 0.2056, + "epoch": 0.15, + "learning_rate": 4.2361244714883336e-05, + "loss": 0.2296, "step": 69320 }, { - "epoch": 0.62, - "learning_rate": 1.923655526529142e-05, - "loss": 0.2109, + "epoch": 0.15, + "learning_rate": 4.2360126171674014e-05, + "loss": 0.2345, "step": 69330 }, { - "epoch": 0.62, - "learning_rate": 1.923205116656157e-05, - "loss": 0.2087, + "epoch": 0.15, + "learning_rate": 4.235900762846469e-05, + "loss": 0.2355, "step": 69340 }, { - "epoch": 0.62, - "learning_rate": 1.9227547067831727e-05, - "loss": 0.2086, + "epoch": 0.15, + "learning_rate": 4.2357889085255363e-05, + "loss": 0.2337, "step": 69350 }, { - "epoch": 0.62, - "learning_rate": 1.9223042969101884e-05, - "loss": 0.2065, + "epoch": 0.15, + "learning_rate": 4.235688239636698e-05, + "loss": 0.2333, "step": 69360 }, { - "epoch": 0.62, - "learning_rate": 1.921853887037204e-05, - "loss": 0.2087, + "epoch": 0.15, + "learning_rate": 4.235576385315765e-05, + "loss": 0.2353, "step": 69370 }, { - "epoch": 0.62, - "learning_rate": 1.9214034771642196e-05, - "loss": 0.2105, + "epoch": 0.15, + "learning_rate": 4.235464530994833e-05, + "loss": 0.2298, "step": 69380 }, { - "epoch": 0.62, - "learning_rate": 1.920953067291235e-05, - "loss": 0.216, + "epoch": 0.15, + "learning_rate": 4.2353526766739e-05, + "loss": 0.2273, "step": 69390 }, { - "epoch": 0.62, - "learning_rate": 1.9205026574182508e-05, - "loss": 0.2126, + "epoch": 0.15, + "learning_rate": 4.235240822352968e-05, + "loss": 0.2259, "step": 69400 }, { - "epoch": 0.62, - "learning_rate": 1.9200522475452662e-05, - "loss": 0.2074, + "epoch": 0.15, + "learning_rate": 4.2351289680320355e-05, + "loss": 0.2315, "step": 69410 }, { - "epoch": 0.62, - "learning_rate": 1.919601837672282e-05, - "loss": 0.2108, + "epoch": 0.15, + "learning_rate": 4.2350171137111026e-05, + "loss": 0.2295, "step": 69420 }, { - "epoch": 0.62, - "learning_rate": 1.9191514277992977e-05, - "loss": 0.2022, + "epoch": 0.15, + "learning_rate": 4.2349052593901704e-05, + "loss": 0.23, "step": 69430 }, { - "epoch": 0.62, - "learning_rate": 1.9187010179263127e-05, - "loss": 0.2108, + "epoch": 0.15, + "learning_rate": 4.2347934050692375e-05, + "loss": 0.2296, "step": 69440 }, { - "epoch": 0.62, - "learning_rate": 1.9182506080533285e-05, - "loss": 0.2066, + "epoch": 0.16, + "learning_rate": 4.234681550748305e-05, + "loss": 0.2321, "step": 69450 }, { - "epoch": 0.62, - "learning_rate": 1.9178001981803442e-05, - "loss": 0.2087, + "epoch": 0.16, + "learning_rate": 4.234569696427373e-05, + "loss": 0.2356, "step": 69460 }, { - "epoch": 0.62, - "learning_rate": 1.91734978830736e-05, - "loss": 0.2072, + "epoch": 0.16, + "learning_rate": 4.234457842106441e-05, + "loss": 0.2314, "step": 69470 }, { - "epoch": 0.62, - "learning_rate": 1.9168993784343754e-05, - "loss": 0.2072, + "epoch": 0.16, + "learning_rate": 4.234345987785509e-05, + "loss": 0.2329, "step": 69480 }, { - "epoch": 0.62, - "learning_rate": 1.9164489685613908e-05, - "loss": 0.2064, + "epoch": 0.16, + "learning_rate": 4.234234133464576e-05, + "loss": 0.2267, "step": 69490 }, { - "epoch": 0.62, - "learning_rate": 1.9159985586884066e-05, - "loss": 0.199, + "epoch": 0.16, + "learning_rate": 4.2341222791436436e-05, + "loss": 0.2369, "step": 69500 }, { - "epoch": 0.62, - "learning_rate": 1.915548148815422e-05, - "loss": 0.206, + "epoch": 0.16, + "learning_rate": 4.2340104248227114e-05, + "loss": 0.2333, "step": 69510 }, { - "epoch": 0.62, - "learning_rate": 1.9150977389424377e-05, - "loss": 0.2086, + "epoch": 0.16, + "learning_rate": 4.2338985705017785e-05, + "loss": 0.2287, "step": 69520 }, { - "epoch": 0.62, - "learning_rate": 1.9146473290694535e-05, - "loss": 0.2044, + "epoch": 0.16, + "learning_rate": 4.233786716180846e-05, + "loss": 0.2323, "step": 69530 }, { - "epoch": 0.62, - "learning_rate": 1.914196919196469e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.2336748618599134e-05, + "loss": 0.237, "step": 69540 }, { - "epoch": 0.62, - "learning_rate": 1.9137465093234843e-05, - "loss": 0.2044, + "epoch": 0.16, + "learning_rate": 4.233563007538981e-05, + "loss": 0.2279, "step": 69550 }, { - "epoch": 0.62, - "learning_rate": 1.9132960994505e-05, - "loss": 0.2099, + "epoch": 0.16, + "learning_rate": 4.233451153218049e-05, + "loss": 0.2385, "step": 69560 }, { - "epoch": 0.62, - "learning_rate": 1.9128456895775158e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.233339298897117e-05, + "loss": 0.2346, "step": 69570 }, { - "epoch": 0.62, - "learning_rate": 1.9123952797045312e-05, - "loss": 0.2082, + "epoch": 0.16, + "learning_rate": 4.2332274445761846e-05, + "loss": 0.2332, "step": 69580 }, { - "epoch": 0.62, - "learning_rate": 1.9119448698315466e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.233115590255252e-05, + "loss": 0.2278, "step": 69590 }, { - "epoch": 0.62, - "learning_rate": 1.9114944599585624e-05, - "loss": 0.2115, + "epoch": 0.16, + "learning_rate": 4.2330037359343195e-05, + "loss": 0.2316, "step": 69600 }, { - "epoch": 0.62, - "learning_rate": 1.911044050085578e-05, - "loss": 0.2045, + "epoch": 0.16, + "learning_rate": 4.2328918816133866e-05, + "loss": 0.2349, "step": 69610 }, { - "epoch": 0.62, - "learning_rate": 1.9105936402125935e-05, - "loss": 0.2086, + "epoch": 0.16, + "learning_rate": 4.2327800272924544e-05, + "loss": 0.2341, "step": 69620 }, { - "epoch": 0.62, - "learning_rate": 1.9101432303396093e-05, - "loss": 0.2063, + "epoch": 0.16, + "learning_rate": 4.232668172971522e-05, + "loss": 0.2315, "step": 69630 }, { - "epoch": 0.62, - "learning_rate": 1.9096928204666247e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.232556318650589e-05, + "loss": 0.234, "step": 69640 }, { - "epoch": 0.62, - "learning_rate": 1.90924241059364e-05, - "loss": 0.2088, + "epoch": 0.16, + "learning_rate": 4.232444464329657e-05, + "loss": 0.2268, "step": 69650 }, { - "epoch": 0.62, - "learning_rate": 1.908792000720656e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.232332610008725e-05, + "loss": 0.237, "step": 69660 }, { - "epoch": 0.62, - "learning_rate": 1.9083415908476716e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.232220755687793e-05, + "loss": 0.2289, "step": 69670 }, { - "epoch": 0.62, - "learning_rate": 1.907891180974687e-05, - "loss": 0.2133, + "epoch": 0.16, + "learning_rate": 4.2321089013668605e-05, + "loss": 0.2328, "step": 69680 }, { - "epoch": 0.62, - "learning_rate": 1.9074407711017024e-05, - "loss": 0.2054, + "epoch": 0.16, + "learning_rate": 4.2319970470459276e-05, + "loss": 0.2331, "step": 69690 }, { - "epoch": 0.62, - "learning_rate": 1.906990361228718e-05, - "loss": 0.2026, + "epoch": 0.16, + "learning_rate": 4.2318851927249954e-05, + "loss": 0.228, "step": 69700 }, { - "epoch": 0.62, - "learning_rate": 1.906539951355734e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.2317733384040625e-05, + "loss": 0.2373, "step": 69710 }, { - "epoch": 0.62, - "learning_rate": 1.9060895414827493e-05, - "loss": 0.213, + "epoch": 0.16, + "learning_rate": 4.23166148408313e-05, + "loss": 0.2331, "step": 69720 }, { - "epoch": 0.62, - "learning_rate": 1.905639131609765e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.231549629762198e-05, + "loss": 0.2319, "step": 69730 }, { - "epoch": 0.62, - "learning_rate": 1.9051887217367805e-05, - "loss": 0.205, + "epoch": 0.16, + "learning_rate": 4.231437775441265e-05, + "loss": 0.2372, "step": 69740 }, { - "epoch": 0.62, - "learning_rate": 1.9047383118637962e-05, - "loss": 0.2048, + "epoch": 0.16, + "learning_rate": 4.231325921120333e-05, + "loss": 0.2285, "step": 69750 }, { - "epoch": 0.62, - "learning_rate": 1.9042879019908116e-05, - "loss": 0.2053, + "epoch": 0.16, + "learning_rate": 4.231214066799401e-05, + "loss": 0.2311, "step": 69760 }, { - "epoch": 0.62, - "learning_rate": 1.9038374921178274e-05, - "loss": 0.2085, + "epoch": 0.16, + "learning_rate": 4.2311022124784686e-05, + "loss": 0.2319, "step": 69770 }, { - "epoch": 0.62, - "learning_rate": 1.903387082244843e-05, - "loss": 0.2083, + "epoch": 0.16, + "learning_rate": 4.2309903581575364e-05, + "loss": 0.2332, "step": 69780 }, { - "epoch": 0.62, - "learning_rate": 1.9029366723718582e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.2308785038366035e-05, + "loss": 0.2309, "step": 69790 }, { - "epoch": 0.62, - "learning_rate": 1.902486262498874e-05, - "loss": 0.2078, + "epoch": 0.16, + "learning_rate": 4.230766649515671e-05, + "loss": 0.2364, "step": 69800 }, { - "epoch": 0.62, - "learning_rate": 1.9020358526258897e-05, - "loss": 0.2064, + "epoch": 0.16, + "learning_rate": 4.2306547951947384e-05, + "loss": 0.2299, "step": 69810 }, { - "epoch": 0.62, - "learning_rate": 1.9015854427529055e-05, - "loss": 0.2115, + "epoch": 0.16, + "learning_rate": 4.230542940873806e-05, + "loss": 0.228, "step": 69820 }, { - "epoch": 0.62, - "learning_rate": 1.901135032879921e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.230431086552874e-05, + "loss": 0.2324, "step": 69830 }, { - "epoch": 0.62, - "learning_rate": 1.9006846230069363e-05, - "loss": 0.2073, + "epoch": 0.16, + "learning_rate": 4.230319232231941e-05, + "loss": 0.2365, "step": 69840 }, { - "epoch": 0.62, - "learning_rate": 1.900234213133952e-05, - "loss": 0.206, + "epoch": 0.16, + "learning_rate": 4.230207377911009e-05, + "loss": 0.2299, "step": 69850 }, { - "epoch": 0.62, - "learning_rate": 1.8997838032609674e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.230095523590076e-05, + "loss": 0.2265, "step": 69860 }, { - "epoch": 0.62, - "learning_rate": 1.8993333933879832e-05, - "loss": 0.2055, + "epoch": 0.16, + "learning_rate": 4.229983669269144e-05, + "loss": 0.2306, "step": 69870 }, { - "epoch": 0.62, - "learning_rate": 1.898882983514999e-05, - "loss": 0.2029, + "epoch": 0.16, + "learning_rate": 4.2298718149482116e-05, + "loss": 0.2334, "step": 69880 }, { - "epoch": 0.62, - "learning_rate": 1.8984325736420143e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.2297599606272794e-05, + "loss": 0.2304, "step": 69890 }, { - "epoch": 0.62, - "learning_rate": 1.8979821637690298e-05, - "loss": 0.207, + "epoch": 0.16, + "learning_rate": 4.229648106306347e-05, + "loss": 0.2279, "step": 69900 }, { - "epoch": 0.62, - "learning_rate": 1.8975317538960455e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.229536251985414e-05, + "loss": 0.2312, "step": 69910 }, { - "epoch": 0.62, - "learning_rate": 1.8970813440230613e-05, - "loss": 0.2078, + "epoch": 0.16, + "learning_rate": 4.229424397664482e-05, + "loss": 0.2312, "step": 69920 }, { - "epoch": 0.62, - "learning_rate": 1.8966309341500767e-05, - "loss": 0.2072, + "epoch": 0.16, + "learning_rate": 4.229312543343549e-05, + "loss": 0.2281, "step": 69930 }, { - "epoch": 0.62, - "learning_rate": 1.896180524277092e-05, - "loss": 0.2065, + "epoch": 0.16, + "learning_rate": 4.229200689022617e-05, + "loss": 0.2308, "step": 69940 }, { - "epoch": 0.62, - "learning_rate": 1.8957301144041078e-05, - "loss": 0.2055, + "epoch": 0.16, + "learning_rate": 4.229088834701685e-05, + "loss": 0.2332, "step": 69950 }, { - "epoch": 0.62, - "learning_rate": 1.8952797045311236e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.228976980380752e-05, + "loss": 0.2294, "step": 69960 }, { - "epoch": 0.62, - "learning_rate": 1.894829294658139e-05, - "loss": 0.2062, + "epoch": 0.16, + "learning_rate": 4.22886512605982e-05, + "loss": 0.2344, "step": 69970 }, { - "epoch": 0.62, - "learning_rate": 1.8943788847851547e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.2287532717388875e-05, + "loss": 0.2267, "step": 69980 }, { - "epoch": 0.62, - "learning_rate": 1.89392847491217e-05, - "loss": 0.2085, + "epoch": 0.16, + "learning_rate": 4.228641417417955e-05, + "loss": 0.228, "step": 69990 }, { - "epoch": 0.62, - "learning_rate": 1.8934780650391856e-05, - "loss": 0.2131, + "epoch": 0.16, + "learning_rate": 4.228529563097023e-05, + "loss": 0.2347, "step": 70000 }, { - "epoch": 0.63, - "learning_rate": 1.8930276551662013e-05, - "loss": 0.2083, + "epoch": 0.16, + "learning_rate": 4.22841770877609e-05, + "loss": 0.2259, "step": 70010 }, { - "epoch": 0.63, - "learning_rate": 1.892577245293217e-05, - "loss": 0.1996, + "epoch": 0.16, + "learning_rate": 4.228305854455158e-05, + "loss": 0.2301, "step": 70020 }, { - "epoch": 0.63, - "learning_rate": 1.8921268354202325e-05, - "loss": 0.2099, + "epoch": 0.16, + "learning_rate": 4.228194000134225e-05, + "loss": 0.2343, "step": 70030 }, { - "epoch": 0.63, - "learning_rate": 1.891676425547248e-05, - "loss": 0.2089, + "epoch": 0.16, + "learning_rate": 4.228082145813293e-05, + "loss": 0.2299, "step": 70040 }, { - "epoch": 0.63, - "learning_rate": 1.8912260156742636e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.227970291492361e-05, + "loss": 0.2294, "step": 70050 }, { - "epoch": 0.63, - "learning_rate": 1.8907756058012794e-05, - "loss": 0.2077, + "epoch": 0.16, + "learning_rate": 4.227858437171428e-05, + "loss": 0.2334, "step": 70060 }, { - "epoch": 0.63, - "learning_rate": 1.8903251959282948e-05, - "loss": 0.2092, + "epoch": 0.16, + "learning_rate": 4.2277465828504956e-05, + "loss": 0.2327, "step": 70070 }, { - "epoch": 0.63, - "learning_rate": 1.8898747860553105e-05, - "loss": 0.2042, + "epoch": 0.16, + "learning_rate": 4.2276347285295634e-05, + "loss": 0.2349, "step": 70080 }, { - "epoch": 0.63, - "learning_rate": 1.889424376182326e-05, - "loss": 0.1994, + "epoch": 0.16, + "learning_rate": 4.227522874208631e-05, + "loss": 0.2265, "step": 70090 }, { - "epoch": 0.63, - "learning_rate": 1.8889739663093417e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.227411019887699e-05, + "loss": 0.2274, "step": 70100 }, { - "epoch": 0.63, - "learning_rate": 1.888523556436357e-05, - "loss": 0.2034, + "epoch": 0.16, + "learning_rate": 4.227299165566766e-05, + "loss": 0.2348, "step": 70110 }, { - "epoch": 0.63, - "learning_rate": 1.888073146563373e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.227187311245834e-05, + "loss": 0.2316, "step": 70120 }, { - "epoch": 0.63, - "learning_rate": 1.8876227366903883e-05, - "loss": 0.2077, + "epoch": 0.16, + "learning_rate": 4.227075456924901e-05, + "loss": 0.2273, "step": 70130 }, { - "epoch": 0.63, - "learning_rate": 1.8871723268174037e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.226963602603969e-05, + "loss": 0.2309, "step": 70140 }, { - "epoch": 0.63, - "learning_rate": 1.8867219169444194e-05, - "loss": 0.2117, + "epoch": 0.16, + "learning_rate": 4.2268517482830366e-05, + "loss": 0.235, "step": 70150 }, { - "epoch": 0.63, - "learning_rate": 1.886271507071435e-05, - "loss": 0.2099, + "epoch": 0.16, + "learning_rate": 4.226739893962104e-05, + "loss": 0.2345, "step": 70160 }, { - "epoch": 0.63, - "learning_rate": 1.885821097198451e-05, - "loss": 0.2062, + "epoch": 0.16, + "learning_rate": 4.2266280396411715e-05, + "loss": 0.2289, "step": 70170 }, { - "epoch": 0.63, - "learning_rate": 1.8853706873254663e-05, - "loss": 0.2019, + "epoch": 0.16, + "learning_rate": 4.226516185320239e-05, + "loss": 0.2289, "step": 70180 }, { - "epoch": 0.63, - "learning_rate": 1.8849202774524817e-05, - "loss": 0.1999, + "epoch": 0.16, + "learning_rate": 4.226404330999307e-05, + "loss": 0.2296, "step": 70190 }, { - "epoch": 0.63, - "learning_rate": 1.8844698675794975e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.226292476678374e-05, + "loss": 0.2334, "step": 70200 }, { - "epoch": 0.63, - "learning_rate": 1.884019457706513e-05, - "loss": 0.2153, + "epoch": 0.16, + "learning_rate": 4.226180622357442e-05, + "loss": 0.2319, "step": 70210 }, { - "epoch": 0.63, - "learning_rate": 1.8835690478335286e-05, - "loss": 0.2065, + "epoch": 0.16, + "learning_rate": 4.22606876803651e-05, + "loss": 0.2321, "step": 70220 }, { - "epoch": 0.63, - "learning_rate": 1.883118637960544e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.225956913715577e-05, + "loss": 0.2352, "step": 70230 }, { - "epoch": 0.63, - "learning_rate": 1.8826682280875598e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.225845059394645e-05, + "loss": 0.2311, "step": 70240 }, { - "epoch": 0.63, - "learning_rate": 1.8822178182145752e-05, - "loss": 0.207, + "epoch": 0.16, + "learning_rate": 4.225733205073712e-05, + "loss": 0.2256, "step": 70250 }, { - "epoch": 0.63, - "learning_rate": 1.881767408341591e-05, - "loss": 0.198, + "epoch": 0.16, + "learning_rate": 4.2256213507527796e-05, + "loss": 0.2325, "step": 70260 }, { - "epoch": 0.63, - "learning_rate": 1.8813169984686067e-05, - "loss": 0.2099, + "epoch": 0.16, + "learning_rate": 4.2255094964318474e-05, + "loss": 0.238, "step": 70270 }, { - "epoch": 0.63, - "learning_rate": 1.880866588595622e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.2253976421109145e-05, + "loss": 0.2356, "step": 70280 }, { - "epoch": 0.63, - "learning_rate": 1.8804161787226375e-05, - "loss": 0.2064, + "epoch": 0.16, + "learning_rate": 4.225285787789982e-05, + "loss": 0.2317, "step": 70290 }, { - "epoch": 0.63, - "learning_rate": 1.8799657688496533e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.22517393346905e-05, + "loss": 0.2297, "step": 70300 }, { - "epoch": 0.63, - "learning_rate": 1.879515358976669e-05, - "loss": 0.2046, + "epoch": 0.16, + "learning_rate": 4.225062079148118e-05, + "loss": 0.2303, "step": 70310 }, { - "epoch": 0.63, - "learning_rate": 1.8790649491036844e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.224950224827186e-05, + "loss": 0.2304, "step": 70320 }, { - "epoch": 0.63, - "learning_rate": 1.8786145392307e-05, - "loss": 0.2013, + "epoch": 0.16, + "learning_rate": 4.224838370506253e-05, + "loss": 0.2275, "step": 70330 }, { - "epoch": 0.63, - "learning_rate": 1.8781641293577156e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.2247265161853206e-05, + "loss": 0.2247, "step": 70340 }, { - "epoch": 0.63, - "learning_rate": 1.877713719484731e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.224614661864388e-05, + "loss": 0.2309, "step": 70350 }, { - "epoch": 0.63, - "learning_rate": 1.8772633096117468e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.2245028075434555e-05, + "loss": 0.2361, "step": 70360 }, { - "epoch": 0.63, - "learning_rate": 1.8768128997387625e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.224390953222523e-05, + "loss": 0.2291, "step": 70370 }, { - "epoch": 0.63, - "learning_rate": 1.876362489865778e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.2242790989015904e-05, + "loss": 0.2268, "step": 70380 }, { - "epoch": 0.63, - "learning_rate": 1.8759120799927933e-05, - "loss": 0.208, + "epoch": 0.16, + "learning_rate": 4.224167244580658e-05, + "loss": 0.2368, "step": 70390 }, { - "epoch": 0.63, - "learning_rate": 1.875461670119809e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.224055390259726e-05, + "loss": 0.2323, "step": 70400 }, { - "epoch": 0.63, - "learning_rate": 1.875011260246825e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.223943535938794e-05, + "loss": 0.2331, "step": 70410 }, { - "epoch": 0.63, - "learning_rate": 1.8745608503738402e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.2238316816178616e-05, + "loss": 0.2325, "step": 70420 }, { - "epoch": 0.63, - "learning_rate": 1.874110440500856e-05, - "loss": 0.206, + "epoch": 0.16, + "learning_rate": 4.223719827296929e-05, + "loss": 0.2322, "step": 70430 }, { - "epoch": 0.63, - "learning_rate": 1.8736600306278714e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.2236079729759965e-05, + "loss": 0.2331, "step": 70440 }, { - "epoch": 0.63, - "learning_rate": 1.873209620754887e-05, - "loss": 0.2046, + "epoch": 0.16, + "learning_rate": 4.2234961186550636e-05, + "loss": 0.2292, "step": 70450 }, { - "epoch": 0.63, - "learning_rate": 1.8727592108819026e-05, - "loss": 0.209, + "epoch": 0.16, + "learning_rate": 4.2233842643341314e-05, + "loss": 0.2337, "step": 70460 }, { - "epoch": 0.63, - "learning_rate": 1.8723088010089183e-05, - "loss": 0.2082, + "epoch": 0.16, + "learning_rate": 4.223272410013199e-05, + "loss": 0.2387, "step": 70470 }, { - "epoch": 0.63, - "learning_rate": 1.8718583911359337e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.223160555692266e-05, + "loss": 0.2273, "step": 70480 }, { - "epoch": 0.63, - "learning_rate": 1.871407981262949e-05, - "loss": 0.1967, + "epoch": 0.16, + "learning_rate": 4.223048701371334e-05, + "loss": 0.2291, "step": 70490 }, { - "epoch": 0.63, - "learning_rate": 1.870957571389965e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.222936847050402e-05, + "loss": 0.2296, "step": 70500 }, { - "epoch": 0.63, - "learning_rate": 1.8705071615169806e-05, - "loss": 0.2093, + "epoch": 0.16, + "learning_rate": 4.22282499272947e-05, + "loss": 0.2298, "step": 70510 }, { - "epoch": 0.63, - "learning_rate": 1.8700567516439964e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.222713138408537e-05, + "loss": 0.2336, "step": 70520 }, { - "epoch": 0.63, - "learning_rate": 1.8696063417710118e-05, - "loss": 0.2079, + "epoch": 0.16, + "learning_rate": 4.2226012840876046e-05, + "loss": 0.2261, "step": 70530 }, { - "epoch": 0.63, - "learning_rate": 1.8691559318980272e-05, - "loss": 0.203, + "epoch": 0.16, + "learning_rate": 4.2224894297666724e-05, + "loss": 0.2276, "step": 70540 }, { - "epoch": 0.63, - "learning_rate": 1.868705522025043e-05, - "loss": 0.2079, + "epoch": 0.16, + "learning_rate": 4.2223775754457395e-05, + "loss": 0.2277, "step": 70550 }, { - "epoch": 0.63, - "learning_rate": 1.8682551121520584e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.222265721124807e-05, + "loss": 0.2367, "step": 70560 }, { - "epoch": 0.63, - "learning_rate": 1.867804702279074e-05, - "loss": 0.2082, + "epoch": 0.16, + "learning_rate": 4.2221538668038744e-05, + "loss": 0.2397, "step": 70570 }, { - "epoch": 0.63, - "learning_rate": 1.8673542924060895e-05, - "loss": 0.2045, + "epoch": 0.16, + "learning_rate": 4.222042012482942e-05, + "loss": 0.2319, "step": 70580 }, { - "epoch": 0.63, - "learning_rate": 1.8669038825331053e-05, - "loss": 0.2047, + "epoch": 0.16, + "learning_rate": 4.22193015816201e-05, + "loss": 0.2279, "step": 70590 }, { - "epoch": 0.63, - "learning_rate": 1.8664534726601207e-05, - "loss": 0.2024, + "epoch": 0.16, + "learning_rate": 4.221818303841078e-05, + "loss": 0.2275, "step": 70600 }, { - "epoch": 0.63, - "learning_rate": 1.8660030627871364e-05, - "loss": 0.2034, + "epoch": 0.16, + "learning_rate": 4.2217064495201456e-05, + "loss": 0.2288, "step": 70610 }, { - "epoch": 0.63, - "learning_rate": 1.8655526529141522e-05, - "loss": 0.2053, + "epoch": 0.16, + "learning_rate": 4.221594595199213e-05, + "loss": 0.2296, "step": 70620 }, { - "epoch": 0.63, - "learning_rate": 1.8651022430411676e-05, - "loss": 0.2067, + "epoch": 0.16, + "learning_rate": 4.2214827408782805e-05, + "loss": 0.2261, "step": 70630 }, { - "epoch": 0.63, - "learning_rate": 1.864651833168183e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.221370886557348e-05, + "loss": 0.2322, "step": 70640 }, { - "epoch": 0.63, - "learning_rate": 1.8642014232951987e-05, - "loss": 0.204, + "epoch": 0.16, + "learning_rate": 4.2212590322364154e-05, + "loss": 0.2301, "step": 70650 }, { - "epoch": 0.63, - "learning_rate": 1.8637510134222145e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.221147177915483e-05, + "loss": 0.2342, "step": 70660 }, { - "epoch": 0.63, - "learning_rate": 1.86330060354923e-05, - "loss": 0.2045, + "epoch": 0.16, + "learning_rate": 4.22103532359455e-05, + "loss": 0.2255, "step": 70670 }, { - "epoch": 0.63, - "learning_rate": 1.8628501936762453e-05, - "loss": 0.1991, + "epoch": 0.16, + "learning_rate": 4.220923469273618e-05, + "loss": 0.2339, "step": 70680 }, { - "epoch": 0.63, - "learning_rate": 1.862399783803261e-05, - "loss": 0.2045, + "epoch": 0.16, + "learning_rate": 4.220811614952686e-05, + "loss": 0.2367, "step": 70690 }, { - "epoch": 0.63, - "learning_rate": 1.8619493739302765e-05, - "loss": 0.2029, + "epoch": 0.16, + "learning_rate": 4.220699760631753e-05, + "loss": 0.2287, "step": 70700 }, { - "epoch": 0.63, - "learning_rate": 1.8614989640572922e-05, - "loss": 0.2098, + "epoch": 0.16, + "learning_rate": 4.2205879063108215e-05, + "loss": 0.2277, "step": 70710 }, { - "epoch": 0.63, - "learning_rate": 1.861048554184308e-05, - "loss": 0.2064, + "epoch": 0.16, + "learning_rate": 4.2204760519898886e-05, + "loss": 0.2354, "step": 70720 }, { - "epoch": 0.63, - "learning_rate": 1.8605981443113234e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.2203641976689564e-05, + "loss": 0.2372, "step": 70730 }, { - "epoch": 0.63, - "learning_rate": 1.8601477344383388e-05, - "loss": 0.2044, + "epoch": 0.16, + "learning_rate": 4.220252343348024e-05, + "loss": 0.2333, "step": 70740 }, { - "epoch": 0.63, - "learning_rate": 1.8596973245653545e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.220140489027091e-05, + "loss": 0.2296, "step": 70750 }, { - "epoch": 0.63, - "learning_rate": 1.8592469146923703e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.220028634706159e-05, + "loss": 0.229, "step": 70760 }, { - "epoch": 0.63, - "learning_rate": 1.8587965048193857e-05, - "loss": 0.2077, + "epoch": 0.16, + "learning_rate": 4.219916780385226e-05, + "loss": 0.2311, "step": 70770 }, { - "epoch": 0.63, - "learning_rate": 1.858346094946401e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.219804926064294e-05, + "loss": 0.2282, "step": 70780 }, { - "epoch": 0.63, - "learning_rate": 1.857895685073417e-05, - "loss": 0.1976, + "epoch": 0.16, + "learning_rate": 4.219693071743362e-05, + "loss": 0.2288, "step": 70790 }, { - "epoch": 0.63, - "learning_rate": 1.8574452752004326e-05, - "loss": 0.2035, + "epoch": 0.16, + "learning_rate": 4.219581217422429e-05, + "loss": 0.2279, "step": 70800 }, { - "epoch": 0.63, - "learning_rate": 1.856994865327448e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.219469363101497e-05, + "loss": 0.2269, "step": 70810 }, { - "epoch": 0.63, - "learning_rate": 1.8565444554544638e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.2193575087805645e-05, + "loss": 0.2275, "step": 70820 }, { - "epoch": 0.63, - "learning_rate": 1.8560940455814792e-05, - "loss": 0.1986, + "epoch": 0.16, + "learning_rate": 4.219245654459632e-05, + "loss": 0.2271, "step": 70830 }, { - "epoch": 0.63, - "learning_rate": 1.8556436357084946e-05, - "loss": 0.2086, + "epoch": 0.16, + "learning_rate": 4.2191338001386994e-05, + "loss": 0.2317, "step": 70840 }, { - "epoch": 0.63, - "learning_rate": 1.8551932258355103e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.219021945817767e-05, + "loss": 0.2304, "step": 70850 }, { - "epoch": 0.63, - "learning_rate": 1.854742815962526e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.218910091496835e-05, + "loss": 0.2305, "step": 70860 }, { - "epoch": 0.63, - "learning_rate": 1.854292406089542e-05, - "loss": 0.2071, + "epoch": 0.16, + "learning_rate": 4.218798237175902e-05, + "loss": 0.2276, "step": 70870 }, { - "epoch": 0.63, - "learning_rate": 1.853841996216557e-05, - "loss": 0.2059, + "epoch": 0.16, + "learning_rate": 4.21868638285497e-05, + "loss": 0.2269, "step": 70880 }, { - "epoch": 0.63, - "learning_rate": 1.8533915863435727e-05, - "loss": 0.1988, + "epoch": 0.16, + "learning_rate": 4.218574528534037e-05, + "loss": 0.2342, "step": 70890 }, { - "epoch": 0.63, - "learning_rate": 1.8529411764705884e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.218462674213105e-05, + "loss": 0.2398, "step": 70900 }, { - "epoch": 0.63, - "learning_rate": 1.8524907665976038e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.2183508198921726e-05, + "loss": 0.2328, "step": 70910 }, { - "epoch": 0.63, - "learning_rate": 1.8520403567246196e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.2182389655712404e-05, + "loss": 0.2282, "step": 70920 }, { - "epoch": 0.63, - "learning_rate": 1.851589946851635e-05, - "loss": 0.2122, + "epoch": 0.16, + "learning_rate": 4.218127111250308e-05, + "loss": 0.2334, "step": 70930 }, { - "epoch": 0.63, - "learning_rate": 1.8511395369786507e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.218015256929375e-05, + "loss": 0.235, "step": 70940 }, { - "epoch": 0.63, - "learning_rate": 1.850689127105666e-05, - "loss": 0.2036, + "epoch": 0.16, + "learning_rate": 4.217903402608443e-05, + "loss": 0.227, "step": 70950 }, { - "epoch": 0.63, - "learning_rate": 1.850238717232682e-05, - "loss": 0.2065, + "epoch": 0.16, + "learning_rate": 4.217791548287511e-05, + "loss": 0.2237, "step": 70960 }, { - "epoch": 0.63, - "learning_rate": 1.8497883073596976e-05, - "loss": 0.1976, + "epoch": 0.16, + "learning_rate": 4.217679693966578e-05, + "loss": 0.2263, "step": 70970 }, { - "epoch": 0.63, - "learning_rate": 1.8493378974867127e-05, - "loss": 0.2023, + "epoch": 0.16, + "learning_rate": 4.217567839645646e-05, + "loss": 0.2319, "step": 70980 }, { - "epoch": 0.63, - "learning_rate": 1.8488874876137285e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.217455985324713e-05, + "loss": 0.2307, "step": 70990 }, { - "epoch": 0.63, - "learning_rate": 1.8484370777407442e-05, - "loss": 0.2092, + "epoch": 0.16, + "learning_rate": 4.217344131003781e-05, + "loss": 0.2314, "step": 71000 }, { - "epoch": 0.63, - "learning_rate": 1.84798666786776e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.2172322766828485e-05, + "loss": 0.2263, "step": 71010 }, { - "epoch": 0.63, - "learning_rate": 1.8475362579947754e-05, - "loss": 0.2019, + "epoch": 0.16, + "learning_rate": 4.217120422361916e-05, + "loss": 0.2285, "step": 71020 }, { - "epoch": 0.63, - "learning_rate": 1.8470858481217908e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.217008568040984e-05, + "loss": 0.2299, "step": 71030 }, { - "epoch": 0.63, - "learning_rate": 1.8466354382488065e-05, - "loss": 0.2068, + "epoch": 0.16, + "learning_rate": 4.216896713720051e-05, + "loss": 0.2255, "step": 71040 }, { - "epoch": 0.63, - "learning_rate": 1.846185028375822e-05, - "loss": 0.2008, + "epoch": 0.16, + "learning_rate": 4.216784859399119e-05, + "loss": 0.2265, "step": 71050 }, { - "epoch": 0.63, - "learning_rate": 1.8457346185028377e-05, - "loss": 0.2085, + "epoch": 0.16, + "learning_rate": 4.216673005078187e-05, + "loss": 0.228, "step": 71060 }, { - "epoch": 0.63, - "learning_rate": 1.8452842086298534e-05, - "loss": 0.2039, + "epoch": 0.16, + "learning_rate": 4.216561150757254e-05, + "loss": 0.2263, "step": 71070 }, { - "epoch": 0.63, - "learning_rate": 1.844833798756869e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.2164492964363217e-05, + "loss": 0.2316, "step": 71080 }, { - "epoch": 0.63, - "learning_rate": 1.8443833888838843e-05, - "loss": 0.2086, + "epoch": 0.16, + "learning_rate": 4.216337442115389e-05, + "loss": 0.2296, "step": 71090 }, { - "epoch": 0.63, - "learning_rate": 1.8439329790109e-05, - "loss": 0.2036, + "epoch": 0.16, + "learning_rate": 4.2162255877944566e-05, + "loss": 0.2276, "step": 71100 }, { - "epoch": 0.63, - "learning_rate": 1.8434825691379158e-05, - "loss": 0.2002, + "epoch": 0.16, + "learning_rate": 4.216113733473524e-05, + "loss": 0.2307, "step": 71110 }, { - "epoch": 0.63, - "learning_rate": 1.843032159264931e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.216001879152592e-05, + "loss": 0.2373, "step": 71120 }, { - "epoch": 0.64, - "learning_rate": 1.8425817493919466e-05, - "loss": 0.2062, + "epoch": 0.16, + "learning_rate": 4.21589002483166e-05, + "loss": 0.2282, "step": 71130 }, { - "epoch": 0.64, - "learning_rate": 1.8421313395189623e-05, - "loss": 0.2079, + "epoch": 0.16, + "learning_rate": 4.215778170510727e-05, + "loss": 0.2336, "step": 71140 }, { - "epoch": 0.64, - "learning_rate": 1.841680929645978e-05, - "loss": 0.2048, + "epoch": 0.16, + "learning_rate": 4.215666316189795e-05, + "loss": 0.2309, "step": 71150 }, { - "epoch": 0.64, - "learning_rate": 1.8412305197729935e-05, - "loss": 0.2088, + "epoch": 0.16, + "learning_rate": 4.215554461868862e-05, + "loss": 0.2281, "step": 71160 }, { - "epoch": 0.64, - "learning_rate": 1.8407801099000092e-05, - "loss": 0.1988, + "epoch": 0.16, + "learning_rate": 4.21544260754793e-05, + "loss": 0.228, "step": 71170 }, { - "epoch": 0.64, - "learning_rate": 1.8403297000270246e-05, - "loss": 0.2001, + "epoch": 0.16, + "learning_rate": 4.2153307532269976e-05, + "loss": 0.2313, "step": 71180 }, { - "epoch": 0.64, - "learning_rate": 1.83987929015404e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.215218898906065e-05, + "loss": 0.2259, "step": 71190 }, { - "epoch": 0.64, - "learning_rate": 1.8394288802810558e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.2151070445851325e-05, + "loss": 0.2244, "step": 71200 }, { - "epoch": 0.64, - "learning_rate": 1.8389784704080716e-05, - "loss": 0.2078, + "epoch": 0.16, + "learning_rate": 4.2149951902641996e-05, + "loss": 0.229, "step": 71210 }, { - "epoch": 0.64, - "learning_rate": 1.8385280605350873e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.2148833359432674e-05, + "loss": 0.2245, "step": 71220 }, { - "epoch": 0.64, - "learning_rate": 1.8380776506621024e-05, - "loss": 0.2076, + "epoch": 0.16, + "learning_rate": 4.214771481622335e-05, + "loss": 0.23, "step": 71230 }, { - "epoch": 0.64, - "learning_rate": 1.837627240789118e-05, - "loss": 0.1981, + "epoch": 0.16, + "learning_rate": 4.214659627301403e-05, + "loss": 0.2313, "step": 71240 }, { - "epoch": 0.64, - "learning_rate": 1.837176830916134e-05, - "loss": 0.2124, + "epoch": 0.16, + "learning_rate": 4.214547772980471e-05, + "loss": 0.2301, "step": 71250 }, { - "epoch": 0.64, - "learning_rate": 1.8367264210431493e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.214435918659538e-05, + "loss": 0.2264, "step": 71260 }, { - "epoch": 0.64, - "learning_rate": 1.836276011170165e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.2143240643386057e-05, + "loss": 0.2233, "step": 71270 }, { - "epoch": 0.64, - "learning_rate": 1.8358256012971804e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.2142122100176734e-05, + "loss": 0.2283, "step": 71280 }, { - "epoch": 0.64, - "learning_rate": 1.8354202324114945e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.2141003556967406e-05, + "loss": 0.2313, "step": 71290 }, { - "epoch": 0.64, - "learning_rate": 1.8349698225385102e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.2139885013758084e-05, + "loss": 0.2357, "step": 71300 }, { - "epoch": 0.64, - "learning_rate": 1.8345194126655256e-05, - "loss": 0.1998, + "epoch": 0.16, + "learning_rate": 4.2138766470548755e-05, + "loss": 0.2263, "step": 71310 }, { - "epoch": 0.64, - "learning_rate": 1.8340690027925414e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.213764792733943e-05, + "loss": 0.2268, "step": 71320 }, { - "epoch": 0.64, - "learning_rate": 1.8336185929195568e-05, - "loss": 0.2016, + "epoch": 0.16, + "learning_rate": 4.213652938413011e-05, + "loss": 0.2293, "step": 71330 }, { - "epoch": 0.64, - "learning_rate": 1.8331681830465726e-05, - "loss": 0.1981, + "epoch": 0.16, + "learning_rate": 4.213541084092079e-05, + "loss": 0.2312, "step": 71340 }, { - "epoch": 0.64, - "learning_rate": 1.832717773173588e-05, - "loss": 0.2146, + "epoch": 0.16, + "learning_rate": 4.2134292297711466e-05, + "loss": 0.2329, "step": 71350 }, { - "epoch": 0.64, - "learning_rate": 1.8322673633006034e-05, - "loss": 0.2121, + "epoch": 0.16, + "learning_rate": 4.213317375450214e-05, + "loss": 0.2277, "step": 71360 }, { - "epoch": 0.64, - "learning_rate": 1.831816953427619e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.2132167065613746e-05, + "loss": 0.2264, "step": 71370 }, { - "epoch": 0.64, - "learning_rate": 1.831366543554635e-05, - "loss": 0.206, + "epoch": 0.16, + "learning_rate": 4.213104852240442e-05, + "loss": 0.231, "step": 71380 }, { - "epoch": 0.64, - "learning_rate": 1.8309161336816506e-05, - "loss": 0.2066, + "epoch": 0.16, + "learning_rate": 4.2129929979195095e-05, + "loss": 0.226, "step": 71390 }, { - "epoch": 0.64, - "learning_rate": 1.830465723808666e-05, - "loss": 0.2003, + "epoch": 0.16, + "learning_rate": 4.212881143598577e-05, + "loss": 0.2286, "step": 71400 }, { - "epoch": 0.64, - "learning_rate": 1.8300153139356814e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.212769289277645e-05, + "loss": 0.2298, "step": 71410 }, { - "epoch": 0.64, - "learning_rate": 1.8295649040626972e-05, - "loss": 0.2037, + "epoch": 0.16, + "learning_rate": 4.212657434956713e-05, + "loss": 0.2387, "step": 71420 }, { - "epoch": 0.64, - "learning_rate": 1.8291144941897126e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.21254558063578e-05, + "loss": 0.2338, "step": 71430 }, { - "epoch": 0.64, - "learning_rate": 1.8286640843167283e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.212433726314848e-05, + "loss": 0.2277, "step": 71440 }, { - "epoch": 0.64, - "learning_rate": 1.8282136744437438e-05, - "loss": 0.2046, + "epoch": 0.16, + "learning_rate": 4.2123218719939156e-05, + "loss": 0.229, "step": 71450 }, { - "epoch": 0.64, - "learning_rate": 1.8277632645707595e-05, - "loss": 0.2073, + "epoch": 0.16, + "learning_rate": 4.212210017672983e-05, + "loss": 0.2289, "step": 71460 }, { - "epoch": 0.64, - "learning_rate": 1.827312854697775e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.2120981633520505e-05, + "loss": 0.2225, "step": 71470 }, { - "epoch": 0.64, - "learning_rate": 1.8268624448247907e-05, - "loss": 0.2027, + "epoch": 0.16, + "learning_rate": 4.2119863090311176e-05, + "loss": 0.2288, "step": 71480 }, { - "epoch": 0.64, - "learning_rate": 1.8264120349518064e-05, - "loss": 0.2034, + "epoch": 0.16, + "learning_rate": 4.2118744547101854e-05, + "loss": 0.2247, "step": 71490 }, { - "epoch": 0.64, - "learning_rate": 1.8259616250788218e-05, - "loss": 0.2042, + "epoch": 0.16, + "learning_rate": 4.211762600389253e-05, + "loss": 0.2344, "step": 71500 }, { - "epoch": 0.64, - "learning_rate": 1.8255112152058372e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.211650746068321e-05, + "loss": 0.2315, "step": 71510 }, { - "epoch": 0.64, - "learning_rate": 1.825060805332853e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.211538891747389e-05, + "loss": 0.232, "step": 71520 }, { - "epoch": 0.64, - "learning_rate": 1.8246103954598687e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.211427037426456e-05, + "loss": 0.2311, "step": 71530 }, { - "epoch": 0.64, - "learning_rate": 1.824159985586884e-05, - "loss": 0.206, + "epoch": 0.16, + "learning_rate": 4.211315183105524e-05, + "loss": 0.2298, "step": 71540 }, { - "epoch": 0.64, - "learning_rate": 1.8237095757138996e-05, - "loss": 0.201, + "epoch": 0.16, + "learning_rate": 4.211203328784591e-05, + "loss": 0.2244, "step": 71550 }, { - "epoch": 0.64, - "learning_rate": 1.8232591658409153e-05, - "loss": 0.2026, + "epoch": 0.16, + "learning_rate": 4.2110914744636586e-05, + "loss": 0.2261, "step": 71560 }, { - "epoch": 0.64, - "learning_rate": 1.8228087559679307e-05, - "loss": 0.1997, + "epoch": 0.16, + "learning_rate": 4.2109796201427264e-05, + "loss": 0.2296, "step": 71570 }, { - "epoch": 0.64, - "learning_rate": 1.8223583460949465e-05, - "loss": 0.2023, + "epoch": 0.16, + "learning_rate": 4.2108677658217935e-05, + "loss": 0.2311, "step": 71580 }, { - "epoch": 0.64, - "learning_rate": 1.8219079362219622e-05, - "loss": 0.2014, + "epoch": 0.16, + "learning_rate": 4.210755911500861e-05, + "loss": 0.2293, "step": 71590 }, { - "epoch": 0.64, - "learning_rate": 1.8214575263489776e-05, - "loss": 0.2066, + "epoch": 0.16, + "learning_rate": 4.210644057179929e-05, + "loss": 0.2276, "step": 71600 }, { - "epoch": 0.64, - "learning_rate": 1.821007116475993e-05, - "loss": 0.2047, + "epoch": 0.16, + "learning_rate": 4.210532202858997e-05, + "loss": 0.2342, "step": 71610 }, { - "epoch": 0.64, - "learning_rate": 1.8205567066030088e-05, - "loss": 0.2035, + "epoch": 0.16, + "learning_rate": 4.210420348538065e-05, + "loss": 0.2274, "step": 71620 }, { - "epoch": 0.64, - "learning_rate": 1.8201062967300245e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.210308494217132e-05, + "loss": 0.2284, "step": 71630 }, { - "epoch": 0.64, - "learning_rate": 1.81965588685704e-05, - "loss": 0.2003, + "epoch": 0.16, + "learning_rate": 4.2101966398961996e-05, + "loss": 0.2268, "step": 71640 }, { - "epoch": 0.64, - "learning_rate": 1.8192054769840554e-05, - "loss": 0.2095, + "epoch": 0.16, + "learning_rate": 4.210084785575267e-05, + "loss": 0.2325, "step": 71650 }, { - "epoch": 0.64, - "learning_rate": 1.818755067111071e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.2099729312543345e-05, + "loss": 0.2248, "step": 71660 }, { - "epoch": 0.64, - "learning_rate": 1.818304657238087e-05, - "loss": 0.2023, + "epoch": 0.16, + "learning_rate": 4.209861076933402e-05, + "loss": 0.2265, "step": 71670 }, { - "epoch": 0.64, - "learning_rate": 1.8178542473651023e-05, - "loss": 0.2072, + "epoch": 0.16, + "learning_rate": 4.2097492226124694e-05, + "loss": 0.227, "step": 71680 }, { - "epoch": 0.64, - "learning_rate": 1.817403837492118e-05, - "loss": 0.2007, + "epoch": 0.16, + "learning_rate": 4.209637368291537e-05, + "loss": 0.2296, "step": 71690 }, { - "epoch": 0.64, - "learning_rate": 1.8169534276191334e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.209525513970605e-05, + "loss": 0.229, "step": 71700 }, { - "epoch": 0.64, - "learning_rate": 1.816503017746149e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.209413659649673e-05, + "loss": 0.2321, "step": 71710 }, { - "epoch": 0.64, - "learning_rate": 1.8160526078731646e-05, - "loss": 0.2086, + "epoch": 0.16, + "learning_rate": 4.2093018053287406e-05, + "loss": 0.2282, "step": 71720 }, { - "epoch": 0.64, - "learning_rate": 1.8156021980001803e-05, - "loss": 0.209, + "epoch": 0.16, + "learning_rate": 4.209189951007808e-05, + "loss": 0.2279, "step": 71730 }, { - "epoch": 0.64, - "learning_rate": 1.815151788127196e-05, - "loss": 0.2026, + "epoch": 0.16, + "learning_rate": 4.2090780966868755e-05, + "loss": 0.2358, "step": 71740 }, { - "epoch": 0.64, - "learning_rate": 1.8147013782542115e-05, - "loss": 0.2044, + "epoch": 0.16, + "learning_rate": 4.2089662423659426e-05, + "loss": 0.2262, "step": 71750 }, { - "epoch": 0.64, - "learning_rate": 1.814250968381227e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.2088543880450104e-05, + "loss": 0.2253, "step": 71760 }, { - "epoch": 0.64, - "learning_rate": 1.8138005585082427e-05, - "loss": 0.208, + "epoch": 0.16, + "learning_rate": 4.208742533724078e-05, + "loss": 0.229, "step": 71770 }, { - "epoch": 0.64, - "learning_rate": 1.813350148635258e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.208630679403145e-05, + "loss": 0.222, "step": 71780 }, { - "epoch": 0.64, - "learning_rate": 1.8128997387622738e-05, - "loss": 0.2039, + "epoch": 0.16, + "learning_rate": 4.208518825082213e-05, + "loss": 0.2339, "step": 71790 }, { - "epoch": 0.64, - "learning_rate": 1.8124493288892892e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.20840697076128e-05, + "loss": 0.229, "step": 71800 }, { - "epoch": 0.64, - "learning_rate": 1.811998919016305e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.208295116440348e-05, + "loss": 0.2237, "step": 71810 }, { - "epoch": 0.64, - "learning_rate": 1.8115485091433204e-05, - "loss": 0.2054, + "epoch": 0.16, + "learning_rate": 4.208183262119416e-05, + "loss": 0.2327, "step": 71820 }, { - "epoch": 0.64, - "learning_rate": 1.811098099270336e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.2080714077984836e-05, + "loss": 0.2297, "step": 71830 }, { - "epoch": 0.64, - "learning_rate": 1.810647689397352e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.2079595534775514e-05, + "loss": 0.2353, "step": 71840 }, { - "epoch": 0.64, - "learning_rate": 1.8101972795243673e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.2078476991566185e-05, + "loss": 0.2293, "step": 71850 }, { - "epoch": 0.64, - "learning_rate": 1.8097468696513827e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.207735844835686e-05, + "loss": 0.2245, "step": 71860 }, { - "epoch": 0.64, - "learning_rate": 1.8092964597783985e-05, - "loss": 0.2095, + "epoch": 0.16, + "learning_rate": 4.2076239905147534e-05, + "loss": 0.2322, "step": 71870 }, { - "epoch": 0.64, - "learning_rate": 1.8088460499054142e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.207512136193821e-05, + "loss": 0.2313, "step": 71880 }, { - "epoch": 0.64, - "learning_rate": 1.8083956400324296e-05, - "loss": 0.2027, + "epoch": 0.16, + "learning_rate": 4.207400281872889e-05, + "loss": 0.2284, "step": 71890 }, { - "epoch": 0.64, - "learning_rate": 1.807945230159445e-05, - "loss": 0.2013, + "epoch": 0.16, + "learning_rate": 4.207288427551956e-05, + "loss": 0.2239, "step": 71900 }, { - "epoch": 0.64, - "learning_rate": 1.8074948202864608e-05, - "loss": 0.205, + "epoch": 0.16, + "learning_rate": 4.207176573231024e-05, + "loss": 0.231, "step": 71910 }, { - "epoch": 0.64, - "learning_rate": 1.8070444104134762e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.207064718910092e-05, + "loss": 0.2288, "step": 71920 }, { - "epoch": 0.64, - "learning_rate": 1.806594000540492e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.2069528645891595e-05, + "loss": 0.2265, "step": 71930 }, { - "epoch": 0.64, - "learning_rate": 1.8061435906675077e-05, - "loss": 0.2078, + "epoch": 0.16, + "learning_rate": 4.206841010268227e-05, + "loss": 0.2328, "step": 71940 }, { - "epoch": 0.64, - "learning_rate": 1.805693180794523e-05, - "loss": 0.1991, + "epoch": 0.16, + "learning_rate": 4.2067291559472944e-05, + "loss": 0.2306, "step": 71950 }, { - "epoch": 0.64, - "learning_rate": 1.8052427709215385e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.206617301626362e-05, + "loss": 0.2247, "step": 71960 }, { - "epoch": 0.64, - "learning_rate": 1.8047923610485542e-05, - "loss": 0.203, + "epoch": 0.16, + "learning_rate": 4.206505447305429e-05, + "loss": 0.2332, "step": 71970 }, { - "epoch": 0.64, - "learning_rate": 1.80434195117557e-05, - "loss": 0.1987, + "epoch": 0.16, + "learning_rate": 4.206393592984497e-05, + "loss": 0.2287, "step": 71980 }, { - "epoch": 0.64, - "learning_rate": 1.8038915413025854e-05, - "loss": 0.2013, + "epoch": 0.16, + "learning_rate": 4.206281738663565e-05, + "loss": 0.2321, "step": 71990 }, { - "epoch": 0.64, - "learning_rate": 1.8034411314296008e-05, - "loss": 0.2053, - "step": 72000 - }, - { - "epoch": 0.64, - "eval_NEIMS_canon_smiles": 0.9437333333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.04493333333333333, - "eval_NEIMS_daylight_tanimoto_simil": 0.4432652596162006, - "eval_NEIMS_exact_mols": 0.04465, - "eval_NEIMS_exact_smiles": 0.04305, - "eval_NEIMS_loss": 0.2352963238954544, - "eval_NEIMS_matched_formulas": 0.5242666666666667, - "eval_NEIMS_morgan_tanimoto_simil": 0.3444219567794077, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.044866666666666666, - "eval_NEIMS_runtime": 714.831, - "eval_NEIMS_samples_per_second": 83.936, - "eval_NEIMS_steps_per_second": 1.312, - "step": 72000 - }, - { - "epoch": 0.64, - "eval_RASSP_canon_smiles": 0.933449093398337, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.10435102013557285, - "eval_RASSP_daylight_tanimoto_simil": 0.5564372091100196, - "eval_RASSP_exact_mols": 0.10396700838147394, - "eval_RASSP_exact_smiles": 0.1006277757371356, - "eval_RASSP_loss": 0.17497843503952026, - "eval_RASSP_matched_formulas": 0.7069155508064247, - "eval_RASSP_morgan_tanimoto_simil": 0.42292690292996077, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.10403379303436071, - "eval_RASSP_runtime": 814.6418, - "eval_RASSP_samples_per_second": 73.522, - "eval_RASSP_steps_per_second": 1.149, - "step": 72000 - }, - { - "epoch": 0.64, - "eval_NIST_canon_smiles": 0.886858075735529, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.01164069986158924, - "eval_NIST_daylight_tanimoto_simil": 0.264120852504151, - "eval_NIST_exact_mols": 0.011214820598360365, - "eval_NIST_exact_smiles": 0.010292082194697804, - "eval_NIST_loss": 1.469948649406433, - "eval_NIST_matched_formulas": 0.07598395854775171, - "eval_NIST_morgan_tanimoto_simil": 0.21686319882447022, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01164069986158924, - "eval_NIST_runtime": 460.465, - "eval_NIST_samples_per_second": 61.192, - "eval_NIST_steps_per_second": 0.958, + "epoch": 0.16, + "learning_rate": 4.206169884342632e-05, + "loss": 0.2261, "step": 72000 }, { - "epoch": 0.64, - "learning_rate": 1.8029907215566166e-05, - "loss": 0.2084, + "epoch": 0.16, + "learning_rate": 4.2060580300217e-05, + "loss": 0.2286, "step": 72010 }, { - "epoch": 0.64, - "learning_rate": 1.8025403116836323e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.2059461757007676e-05, + "loss": 0.231, "step": 72020 }, { - "epoch": 0.64, - "learning_rate": 1.8020899018106477e-05, - "loss": 0.2041, + "epoch": 0.16, + "learning_rate": 4.2058343213798354e-05, + "loss": 0.2286, "step": 72030 }, { - "epoch": 0.64, - "learning_rate": 1.8016394919376635e-05, - "loss": 0.2053, + "epoch": 0.16, + "learning_rate": 4.205722467058903e-05, + "loss": 0.2327, "step": 72040 }, { - "epoch": 0.64, - "learning_rate": 1.801189082064679e-05, - "loss": 0.2039, + "epoch": 0.16, + "learning_rate": 4.20561061273797e-05, + "loss": 0.2315, "step": 72050 }, { - "epoch": 0.64, - "learning_rate": 1.8007386721916943e-05, - "loss": 0.2023, + "epoch": 0.16, + "learning_rate": 4.205498758417038e-05, + "loss": 0.2347, "step": 72060 }, { - "epoch": 0.64, - "learning_rate": 1.80028826231871e-05, - "loss": 0.2014, + "epoch": 0.16, + "learning_rate": 4.205386904096105e-05, + "loss": 0.2286, "step": 72070 }, { - "epoch": 0.64, - "learning_rate": 1.7998378524457258e-05, - "loss": 0.2092, + "epoch": 0.16, + "learning_rate": 4.205275049775173e-05, + "loss": 0.225, "step": 72080 }, { - "epoch": 0.64, - "learning_rate": 1.7993874425727415e-05, - "loss": 0.2053, + "epoch": 0.16, + "learning_rate": 4.205163195454241e-05, + "loss": 0.2331, "step": 72090 }, { - "epoch": 0.64, - "learning_rate": 1.7989370326997566e-05, - "loss": 0.2067, + "epoch": 0.16, + "learning_rate": 4.205051341133308e-05, + "loss": 0.223, "step": 72100 }, { - "epoch": 0.64, - "learning_rate": 1.7984866228267724e-05, - "loss": 0.2023, + "epoch": 0.16, + "learning_rate": 4.204939486812376e-05, + "loss": 0.2249, "step": 72110 }, { - "epoch": 0.64, - "learning_rate": 1.798036212953788e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.2048276324914435e-05, + "loss": 0.2223, "step": 72120 }, { - "epoch": 0.64, - "learning_rate": 1.7975858030808035e-05, - "loss": 0.2007, + "epoch": 0.16, + "learning_rate": 4.204715778170511e-05, + "loss": 0.232, "step": 72130 }, { - "epoch": 0.64, - "learning_rate": 1.7971353932078193e-05, - "loss": 0.2017, + "epoch": 0.16, + "learning_rate": 4.2046039238495784e-05, + "loss": 0.2321, "step": 72140 }, { - "epoch": 0.64, - "learning_rate": 1.7966849833348347e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.204492069528646e-05, + "loss": 0.2325, "step": 72150 }, { - "epoch": 0.64, - "learning_rate": 1.7962345734618504e-05, - "loss": 0.2067, + "epoch": 0.16, + "learning_rate": 4.204380215207714e-05, + "loss": 0.2317, "step": 72160 }, { - "epoch": 0.64, - "learning_rate": 1.795784163588866e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.204268360886781e-05, + "loss": 0.2245, "step": 72170 }, { - "epoch": 0.64, - "learning_rate": 1.7953337537158816e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.204156506565849e-05, + "loss": 0.2223, "step": 72180 }, { - "epoch": 0.64, - "learning_rate": 1.7948833438428973e-05, - "loss": 0.1973, + "epoch": 0.16, + "learning_rate": 4.204044652244916e-05, + "loss": 0.2211, "step": 72190 }, { - "epoch": 0.64, - "learning_rate": 1.7944329339699124e-05, - "loss": 0.2088, + "epoch": 0.16, + "learning_rate": 4.203932797923984e-05, + "loss": 0.2285, "step": 72200 }, { - "epoch": 0.64, - "learning_rate": 1.793982524096928e-05, - "loss": 0.1975, + "epoch": 0.16, + "learning_rate": 4.2038209436030516e-05, + "loss": 0.2303, "step": 72210 }, { - "epoch": 0.64, - "learning_rate": 1.793532114223944e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.203709089282119e-05, + "loss": 0.229, "step": 72220 }, { - "epoch": 0.64, - "learning_rate": 1.7930817043509597e-05, - "loss": 0.1998, + "epoch": 0.16, + "learning_rate": 4.2035972349611865e-05, + "loss": 0.2307, "step": 72230 }, { - "epoch": 0.64, - "learning_rate": 1.792631294477975e-05, - "loss": 0.1966, + "epoch": 0.16, + "learning_rate": 4.203485380640254e-05, + "loss": 0.2315, "step": 72240 }, { - "epoch": 0.65, - "learning_rate": 1.7921808846049905e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.203373526319322e-05, + "loss": 0.2299, "step": 72250 }, { - "epoch": 0.65, - "learning_rate": 1.7917304747320062e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.20326167199839e-05, + "loss": 0.2248, "step": 72260 }, { - "epoch": 0.65, - "learning_rate": 1.7912800648590216e-05, - "loss": 0.2082, + "epoch": 0.16, + "learning_rate": 4.203149817677457e-05, + "loss": 0.2275, "step": 72270 }, { - "epoch": 0.65, - "learning_rate": 1.7908296549860374e-05, - "loss": 0.2035, + "epoch": 0.16, + "learning_rate": 4.203037963356525e-05, + "loss": 0.2285, "step": 72280 }, { - "epoch": 0.65, - "learning_rate": 1.790379245113053e-05, - "loss": 0.2047, + "epoch": 0.16, + "learning_rate": 4.202926109035592e-05, + "loss": 0.2224, "step": 72290 }, { - "epoch": 0.65, - "learning_rate": 1.7899288352400686e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.20281425471466e-05, + "loss": 0.2332, "step": 72300 }, { - "epoch": 0.65, - "learning_rate": 1.789478425367084e-05, - "loss": 0.2002, + "epoch": 0.16, + "learning_rate": 4.2027024003937275e-05, + "loss": 0.2272, "step": 72310 }, { - "epoch": 0.65, - "learning_rate": 1.7890280154940997e-05, - "loss": 0.1968, + "epoch": 0.16, + "learning_rate": 4.2025905460727946e-05, + "loss": 0.2316, "step": 72320 }, { - "epoch": 0.65, - "learning_rate": 1.7885776056211155e-05, - "loss": 0.1959, + "epoch": 0.16, + "learning_rate": 4.2024786917518624e-05, + "loss": 0.2245, "step": 72330 }, { - "epoch": 0.65, - "learning_rate": 1.788127195748131e-05, - "loss": 0.2076, + "epoch": 0.16, + "learning_rate": 4.20236683743093e-05, + "loss": 0.2285, "step": 72340 }, { - "epoch": 0.65, - "learning_rate": 1.7876767858751463e-05, - "loss": 0.1988, + "epoch": 0.16, + "learning_rate": 4.202254983109998e-05, + "loss": 0.2269, "step": 72350 }, { - "epoch": 0.65, - "learning_rate": 1.787226376002162e-05, - "loss": 0.2009, + "epoch": 0.16, + "learning_rate": 4.202143128789066e-05, + "loss": 0.2263, "step": 72360 }, { - "epoch": 0.65, - "learning_rate": 1.7867759661291778e-05, - "loss": 0.2069, + "epoch": 0.16, + "learning_rate": 4.202031274468133e-05, + "loss": 0.2293, "step": 72370 }, { - "epoch": 0.65, - "learning_rate": 1.7863255562561932e-05, - "loss": 0.2003, + "epoch": 0.16, + "learning_rate": 4.201919420147201e-05, + "loss": 0.2292, "step": 72380 }, { - "epoch": 0.65, - "learning_rate": 1.785875146383209e-05, - "loss": 0.1995, + "epoch": 0.16, + "learning_rate": 4.201807565826268e-05, + "loss": 0.2252, "step": 72390 }, { - "epoch": 0.65, - "learning_rate": 1.7854247365102244e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.2016957115053356e-05, + "loss": 0.2234, "step": 72400 }, { - "epoch": 0.65, - "learning_rate": 1.7849743266372398e-05, - "loss": 0.2106, + "epoch": 0.16, + "learning_rate": 4.2015838571844034e-05, + "loss": 0.2271, "step": 72410 }, { - "epoch": 0.65, - "learning_rate": 1.7845239167642555e-05, - "loss": 0.204, + "epoch": 0.16, + "learning_rate": 4.2014720028634705e-05, + "loss": 0.2246, "step": 72420 }, { - "epoch": 0.65, - "learning_rate": 1.7840735068912713e-05, - "loss": 0.2034, + "epoch": 0.16, + "learning_rate": 4.201360148542538e-05, + "loss": 0.2337, "step": 72430 }, { - "epoch": 0.65, - "learning_rate": 1.7836230970182867e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.201248294221606e-05, + "loss": 0.2328, "step": 72440 }, { - "epoch": 0.65, - "learning_rate": 1.783172687145302e-05, - "loss": 0.2063, + "epoch": 0.16, + "learning_rate": 4.201136439900674e-05, + "loss": 0.2267, "step": 72450 }, { - "epoch": 0.65, - "learning_rate": 1.7827222772723178e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.201024585579741e-05, + "loss": 0.2317, "step": 72460 }, { - "epoch": 0.65, - "learning_rate": 1.7822718673993336e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.200912731258809e-05, + "loss": 0.2352, "step": 72470 }, { - "epoch": 0.65, - "learning_rate": 1.781821457526349e-05, - "loss": 0.2016, + "epoch": 0.16, + "learning_rate": 4.2008008769378766e-05, + "loss": 0.2281, "step": 72480 }, { - "epoch": 0.65, - "learning_rate": 1.7813710476533647e-05, - "loss": 0.1965, + "epoch": 0.16, + "learning_rate": 4.200689022616944e-05, + "loss": 0.2324, "step": 72490 }, { - "epoch": 0.65, - "learning_rate": 1.78092063778038e-05, - "loss": 0.204, + "epoch": 0.16, + "learning_rate": 4.2005771682960115e-05, + "loss": 0.2282, "step": 72500 }, { - "epoch": 0.65, - "learning_rate": 1.780470227907396e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.2004653139750786e-05, + "loss": 0.2244, "step": 72510 }, { - "epoch": 0.65, - "learning_rate": 1.7800198180344113e-05, - "loss": 0.2069, + "epoch": 0.16, + "learning_rate": 4.2003534596541464e-05, + "loss": 0.2303, "step": 72520 }, { - "epoch": 0.65, - "learning_rate": 1.779569408161427e-05, - "loss": 0.2, + "epoch": 0.16, + "learning_rate": 4.200241605333214e-05, + "loss": 0.2223, "step": 72530 }, { - "epoch": 0.65, - "learning_rate": 1.7791189982884428e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.200129751012282e-05, + "loss": 0.2272, "step": 72540 }, { - "epoch": 0.65, - "learning_rate": 1.778668588415458e-05, - "loss": 0.205, + "epoch": 0.16, + "learning_rate": 4.20001789669135e-05, + "loss": 0.2251, "step": 72550 }, { - "epoch": 0.65, - "learning_rate": 1.7782181785424736e-05, - "loss": 0.1961, + "epoch": 0.16, + "learning_rate": 4.199906042370417e-05, + "loss": 0.2241, "step": 72560 }, { - "epoch": 0.65, - "learning_rate": 1.7777677686694894e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.199794188049485e-05, + "loss": 0.2293, "step": 72570 }, { - "epoch": 0.65, - "learning_rate": 1.777317358796505e-05, - "loss": 0.1994, + "epoch": 0.16, + "learning_rate": 4.1996823337285525e-05, + "loss": 0.2278, "step": 72580 }, { - "epoch": 0.65, - "learning_rate": 1.7768669489235205e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.1995704794076196e-05, + "loss": 0.2309, "step": 72590 }, { - "epoch": 0.65, - "learning_rate": 1.776416539050536e-05, - "loss": 0.1978, + "epoch": 0.16, + "learning_rate": 4.1994586250866874e-05, + "loss": 0.2222, "step": 72600 }, { - "epoch": 0.65, - "learning_rate": 1.7759661291775517e-05, - "loss": 0.2046, + "epoch": 0.16, + "learning_rate": 4.1993467707657545e-05, + "loss": 0.2274, "step": 72610 }, { - "epoch": 0.65, - "learning_rate": 1.775515719304567e-05, - "loss": 0.2042, + "epoch": 0.16, + "learning_rate": 4.199234916444822e-05, + "loss": 0.2291, "step": 72620 }, { - "epoch": 0.65, - "learning_rate": 1.775065309431583e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.19912306212389e-05, + "loss": 0.2294, "step": 72630 }, { - "epoch": 0.65, - "learning_rate": 1.7746148995585986e-05, - "loss": 0.2043, + "epoch": 0.16, + "learning_rate": 4.199011207802957e-05, + "loss": 0.2263, "step": 72640 }, { - "epoch": 0.65, - "learning_rate": 1.774164489685614e-05, - "loss": 0.2081, + "epoch": 0.16, + "learning_rate": 4.198899353482026e-05, + "loss": 0.2279, "step": 72650 }, { - "epoch": 0.65, - "learning_rate": 1.7737140798126294e-05, - "loss": 0.1993, + "epoch": 0.16, + "learning_rate": 4.198787499161093e-05, + "loss": 0.2341, "step": 72660 }, { - "epoch": 0.65, - "learning_rate": 1.7732636699396452e-05, - "loss": 0.2054, + "epoch": 0.16, + "learning_rate": 4.1986756448401606e-05, + "loss": 0.2253, "step": 72670 }, { - "epoch": 0.65, - "learning_rate": 1.772813260066661e-05, - "loss": 0.207, + "epoch": 0.16, + "learning_rate": 4.1985637905192284e-05, + "loss": 0.232, "step": 72680 }, { - "epoch": 0.65, - "learning_rate": 1.7723628501936763e-05, - "loss": 0.2052, + "epoch": 0.16, + "learning_rate": 4.1984519361982955e-05, + "loss": 0.2265, "step": 72690 }, { - "epoch": 0.65, - "learning_rate": 1.7719124403206917e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.198340081877363e-05, + "loss": 0.2257, "step": 72700 }, { - "epoch": 0.65, - "learning_rate": 1.7714620304477075e-05, - "loss": 0.2066, + "epoch": 0.16, + "learning_rate": 4.1982282275564304e-05, + "loss": 0.2258, "step": 72710 }, { - "epoch": 0.65, - "learning_rate": 1.7710116205747232e-05, - "loss": 0.2014, + "epoch": 0.16, + "learning_rate": 4.198116373235498e-05, + "loss": 0.2321, "step": 72720 }, { - "epoch": 0.65, - "learning_rate": 1.7705612107017387e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.198004518914566e-05, + "loss": 0.2236, "step": 72730 }, { - "epoch": 0.65, - "learning_rate": 1.7701108008287544e-05, - "loss": 0.2013, + "epoch": 0.16, + "learning_rate": 4.197892664593633e-05, + "loss": 0.231, "step": 72740 }, { - "epoch": 0.65, - "learning_rate": 1.7696603909557698e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.197780810272701e-05, + "loss": 0.232, "step": 72750 }, { - "epoch": 0.65, - "learning_rate": 1.7692099810827852e-05, - "loss": 0.1943, + "epoch": 0.16, + "learning_rate": 4.197668955951769e-05, + "loss": 0.2247, "step": 72760 }, { - "epoch": 0.65, - "learning_rate": 1.768759571209801e-05, - "loss": 0.1996, + "epoch": 0.16, + "learning_rate": 4.1975571016308365e-05, + "loss": 0.2287, "step": 72770 }, { - "epoch": 0.65, - "learning_rate": 1.7683091613368167e-05, - "loss": 0.1973, + "epoch": 0.16, + "learning_rate": 4.1974452473099036e-05, + "loss": 0.2278, "step": 72780 }, { - "epoch": 0.65, - "learning_rate": 1.767858751463832e-05, - "loss": 0.2007, + "epoch": 0.16, + "learning_rate": 4.1973333929889714e-05, + "loss": 0.2299, "step": 72790 }, { - "epoch": 0.65, - "learning_rate": 1.7674083415908475e-05, - "loss": 0.1985, + "epoch": 0.16, + "learning_rate": 4.197221538668039e-05, + "loss": 0.2312, "step": 72800 }, { - "epoch": 0.65, - "learning_rate": 1.7669579317178633e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.197109684347106e-05, + "loss": 0.2223, "step": 72810 }, { - "epoch": 0.65, - "learning_rate": 1.766507521844879e-05, - "loss": 0.1982, + "epoch": 0.16, + "learning_rate": 4.196997830026174e-05, + "loss": 0.2247, "step": 72820 }, { - "epoch": 0.65, - "learning_rate": 1.7660571119718945e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.196885975705241e-05, + "loss": 0.2284, "step": 72830 }, { - "epoch": 0.65, - "learning_rate": 1.7656067020989102e-05, - "loss": 0.2067, + "epoch": 0.16, + "learning_rate": 4.196774121384309e-05, + "loss": 0.2248, "step": 72840 }, { - "epoch": 0.65, - "learning_rate": 1.7651562922259256e-05, - "loss": 0.1982, + "epoch": 0.16, + "learning_rate": 4.196662267063377e-05, + "loss": 0.2238, "step": 72850 }, { - "epoch": 0.65, - "learning_rate": 1.7647058823529414e-05, - "loss": 0.2014, + "epoch": 0.16, + "learning_rate": 4.1965504127424446e-05, + "loss": 0.225, "step": 72860 }, { - "epoch": 0.65, - "learning_rate": 1.7642554724799568e-05, - "loss": 0.1974, + "epoch": 0.16, + "learning_rate": 4.1964385584215124e-05, + "loss": 0.2285, "step": 72870 }, { - "epoch": 0.65, - "learning_rate": 1.7638050626069725e-05, - "loss": 0.2024, + "epoch": 0.16, + "learning_rate": 4.1963267041005795e-05, + "loss": 0.2265, "step": 72880 }, { - "epoch": 0.65, - "learning_rate": 1.763354652733988e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.196214849779647e-05, + "loss": 0.2296, "step": 72890 }, { - "epoch": 0.65, - "learning_rate": 1.7629042428610033e-05, - "loss": 0.1998, + "epoch": 0.16, + "learning_rate": 4.196102995458715e-05, + "loss": 0.2333, "step": 72900 }, { - "epoch": 0.65, - "learning_rate": 1.762453832988019e-05, - "loss": 0.2054, + "epoch": 0.16, + "learning_rate": 4.195991141137782e-05, + "loss": 0.2279, "step": 72910 }, { - "epoch": 0.65, - "learning_rate": 1.762003423115035e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.19587928681685e-05, + "loss": 0.2253, "step": 72920 }, { - "epoch": 0.65, - "learning_rate": 1.7615530132420506e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.195767432495917e-05, + "loss": 0.2249, "step": 72930 }, { - "epoch": 0.65, - "learning_rate": 1.761102603369066e-05, - "loss": 0.2036, + "epoch": 0.16, + "learning_rate": 4.195655578174985e-05, + "loss": 0.2318, "step": 72940 }, { - "epoch": 0.65, - "learning_rate": 1.7606521934960814e-05, - "loss": 0.2105, + "epoch": 0.16, + "learning_rate": 4.195543723854053e-05, + "loss": 0.2291, "step": 72950 }, { - "epoch": 0.65, - "learning_rate": 1.760201783623097e-05, - "loss": 0.2026, + "epoch": 0.16, + "learning_rate": 4.1954318695331205e-05, + "loss": 0.2293, "step": 72960 }, { - "epoch": 0.65, - "learning_rate": 1.7597513737501126e-05, - "loss": 0.2047, + "epoch": 0.16, + "learning_rate": 4.195320015212188e-05, + "loss": 0.2271, "step": 72970 }, { - "epoch": 0.65, - "learning_rate": 1.7593009638771283e-05, - "loss": 0.2084, + "epoch": 0.16, + "learning_rate": 4.1952081608912554e-05, + "loss": 0.2266, "step": 72980 }, { - "epoch": 0.65, - "learning_rate": 1.7588505540041437e-05, - "loss": 0.2027, + "epoch": 0.16, + "learning_rate": 4.195096306570323e-05, + "loss": 0.2289, "step": 72990 }, { - "epoch": 0.65, - "learning_rate": 1.7584001441311595e-05, - "loss": 0.1996, + "epoch": 0.16, + "learning_rate": 4.194984452249391e-05, + "loss": 0.2251, "step": 73000 }, { - "epoch": 0.65, - "learning_rate": 1.757949734258175e-05, - "loss": 0.194, + "epoch": 0.16, + "learning_rate": 4.194872597928458e-05, + "loss": 0.2284, "step": 73010 }, { - "epoch": 0.65, - "learning_rate": 1.7574993243851906e-05, - "loss": 0.2069, + "epoch": 0.16, + "learning_rate": 4.194760743607526e-05, + "loss": 0.2281, "step": 73020 }, { - "epoch": 0.65, - "learning_rate": 1.7570489145122064e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.194648889286593e-05, + "loss": 0.2279, "step": 73030 }, { - "epoch": 0.65, - "learning_rate": 1.7565985046392218e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.194537034965661e-05, + "loss": 0.2243, "step": 73040 }, { - "epoch": 0.65, - "learning_rate": 1.7561480947662372e-05, - "loss": 0.2071, + "epoch": 0.16, + "learning_rate": 4.1944251806447286e-05, + "loss": 0.2241, "step": 73050 }, { - "epoch": 0.65, - "learning_rate": 1.755697684893253e-05, - "loss": 0.2085, + "epoch": 0.16, + "learning_rate": 4.194313326323796e-05, + "loss": 0.2281, "step": 73060 }, { - "epoch": 0.65, - "learning_rate": 1.7552472750202687e-05, - "loss": 0.2036, + "epoch": 0.16, + "learning_rate": 4.194201472002864e-05, + "loss": 0.2352, "step": 73070 }, { - "epoch": 0.65, - "learning_rate": 1.754796865147284e-05, - "loss": 0.2024, + "epoch": 0.16, + "learning_rate": 4.194089617681931e-05, + "loss": 0.2255, "step": 73080 }, { - "epoch": 0.65, - "learning_rate": 1.7543464552742995e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.193977763360999e-05, + "loss": 0.2271, "step": 73090 }, { - "epoch": 0.65, - "learning_rate": 1.7538960454013153e-05, - "loss": 0.1966, + "epoch": 0.16, + "learning_rate": 4.193865909040066e-05, + "loss": 0.2297, "step": 73100 }, { - "epoch": 0.65, - "learning_rate": 1.7534456355283307e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.193754054719134e-05, + "loss": 0.2252, "step": 73110 }, { - "epoch": 0.65, - "learning_rate": 1.7529952256553464e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.193642200398202e-05, + "loss": 0.2259, "step": 73120 }, { - "epoch": 0.65, - "learning_rate": 1.7525448157823622e-05, - "loss": 0.1977, + "epoch": 0.16, + "learning_rate": 4.193530346077269e-05, + "loss": 0.2328, "step": 73130 }, { - "epoch": 0.65, - "learning_rate": 1.7520944059093776e-05, - "loss": 0.2027, + "epoch": 0.16, + "learning_rate": 4.193418491756337e-05, + "loss": 0.2262, "step": 73140 }, { - "epoch": 0.65, - "learning_rate": 1.751643996036393e-05, - "loss": 0.1964, + "epoch": 0.16, + "learning_rate": 4.193306637435404e-05, + "loss": 0.2309, "step": 73150 }, { - "epoch": 0.65, - "learning_rate": 1.7511935861634088e-05, - "loss": 0.1992, + "epoch": 0.16, + "learning_rate": 4.1931947831144716e-05, + "loss": 0.2244, "step": 73160 }, { - "epoch": 0.65, - "learning_rate": 1.7507431762904245e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.1930829287935394e-05, + "loss": 0.2324, "step": 73170 }, { - "epoch": 0.65, - "learning_rate": 1.75029276641744e-05, - "loss": 0.1994, + "epoch": 0.16, + "learning_rate": 4.192971074472607e-05, + "loss": 0.2254, "step": 73180 }, { - "epoch": 0.65, - "learning_rate": 1.7498423565444557e-05, - "loss": 0.2068, + "epoch": 0.16, + "learning_rate": 4.192859220151675e-05, + "loss": 0.2285, "step": 73190 }, { - "epoch": 0.65, - "learning_rate": 1.749391946671471e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.192747365830742e-05, + "loss": 0.2304, "step": 73200 }, { - "epoch": 0.65, - "learning_rate": 1.7489415367984868e-05, - "loss": 0.1982, + "epoch": 0.16, + "learning_rate": 4.19263551150981e-05, + "loss": 0.2282, "step": 73210 }, { - "epoch": 0.65, - "learning_rate": 1.7484911269255022e-05, - "loss": 0.2051, + "epoch": 0.16, + "learning_rate": 4.192523657188878e-05, + "loss": 0.2236, "step": 73220 }, { - "epoch": 0.65, - "learning_rate": 1.748040717052518e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.192411802867945e-05, + "loss": 0.2254, "step": 73230 }, { - "epoch": 0.65, - "learning_rate": 1.7475903071795334e-05, - "loss": 0.2029, + "epoch": 0.16, + "learning_rate": 4.1922999485470126e-05, + "loss": 0.2316, "step": 73240 }, { - "epoch": 0.65, - "learning_rate": 1.7471398973065488e-05, - "loss": 0.2053, + "epoch": 0.16, + "learning_rate": 4.19218809422608e-05, + "loss": 0.2253, "step": 73250 }, { - "epoch": 0.65, - "learning_rate": 1.7466894874335646e-05, - "loss": 0.2009, + "epoch": 0.16, + "learning_rate": 4.1920762399051475e-05, + "loss": 0.223, "step": 73260 }, { - "epoch": 0.65, - "learning_rate": 1.7462390775605803e-05, - "loss": 0.2048, + "epoch": 0.16, + "learning_rate": 4.191964385584215e-05, + "loss": 0.2248, "step": 73270 }, { - "epoch": 0.65, - "learning_rate": 1.745788667687596e-05, - "loss": 0.2049, + "epoch": 0.16, + "learning_rate": 4.191852531263283e-05, + "loss": 0.2234, "step": 73280 }, { - "epoch": 0.65, - "learning_rate": 1.7453382578146115e-05, - "loss": 0.1988, + "epoch": 0.16, + "learning_rate": 4.191740676942351e-05, + "loss": 0.221, "step": 73290 }, { - "epoch": 0.65, - "learning_rate": 1.744887847941627e-05, - "loss": 0.2027, + "epoch": 0.16, + "learning_rate": 4.191628822621418e-05, + "loss": 0.2282, "step": 73300 }, { - "epoch": 0.65, - "learning_rate": 1.7444374380686426e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.191516968300486e-05, + "loss": 0.2327, "step": 73310 }, { - "epoch": 0.65, - "learning_rate": 1.743987028195658e-05, - "loss": 0.2037, + "epoch": 0.16, + "learning_rate": 4.1914051139795536e-05, + "loss": 0.2274, "step": 73320 }, { - "epoch": 0.65, - "learning_rate": 1.7435366183226738e-05, - "loss": 0.2012, + "epoch": 0.16, + "learning_rate": 4.191293259658621e-05, + "loss": 0.2273, "step": 73330 }, { - "epoch": 0.65, - "learning_rate": 1.7430862084496892e-05, - "loss": 0.199, + "epoch": 0.16, + "learning_rate": 4.1911814053376885e-05, + "loss": 0.2238, "step": 73340 }, { - "epoch": 0.65, - "learning_rate": 1.742635798576705e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.1910695510167556e-05, + "loss": 0.2252, "step": 73350 }, { - "epoch": 0.65, - "learning_rate": 1.7421853887037204e-05, - "loss": 0.1993, + "epoch": 0.16, + "learning_rate": 4.1909576966958234e-05, + "loss": 0.2246, "step": 73360 }, { - "epoch": 0.66, - "learning_rate": 1.741734978830736e-05, - "loss": 0.2064, + "epoch": 0.16, + "learning_rate": 4.190845842374891e-05, + "loss": 0.2254, "step": 73370 }, { - "epoch": 0.66, - "learning_rate": 1.741284568957752e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.190745173486052e-05, + "loss": 0.226, "step": 73380 }, { - "epoch": 0.66, - "learning_rate": 1.7408341590847673e-05, - "loss": 0.1979, + "epoch": 0.16, + "learning_rate": 4.19063331916512e-05, + "loss": 0.2245, "step": 73390 }, { - "epoch": 0.66, - "learning_rate": 1.7403837492117827e-05, - "loss": 0.205, + "epoch": 0.16, + "learning_rate": 4.190521464844187e-05, + "loss": 0.2235, "step": 73400 }, { - "epoch": 0.66, - "learning_rate": 1.7399333393387984e-05, - "loss": 0.2066, + "epoch": 0.16, + "learning_rate": 4.190409610523255e-05, + "loss": 0.2218, "step": 73410 }, { - "epoch": 0.66, - "learning_rate": 1.739482929465814e-05, - "loss": 0.2039, + "epoch": 0.16, + "learning_rate": 4.190297756202322e-05, + "loss": 0.23, "step": 73420 }, { - "epoch": 0.66, - "learning_rate": 1.7390325195928296e-05, - "loss": 0.2019, + "epoch": 0.16, + "learning_rate": 4.19018590188139e-05, + "loss": 0.2294, "step": 73430 }, { - "epoch": 0.66, - "learning_rate": 1.738582109719845e-05, - "loss": 0.2019, + "epoch": 0.16, + "learning_rate": 4.1900740475604575e-05, + "loss": 0.23, "step": 73440 }, { - "epoch": 0.66, - "learning_rate": 1.7381316998468607e-05, - "loss": 0.203, + "epoch": 0.16, + "learning_rate": 4.189962193239525e-05, + "loss": 0.23, "step": 73450 }, { - "epoch": 0.66, - "learning_rate": 1.737681289973876e-05, - "loss": 0.2032, + "epoch": 0.16, + "learning_rate": 4.189850338918593e-05, + "loss": 0.2234, "step": 73460 }, { - "epoch": 0.66, - "learning_rate": 1.737230880100892e-05, - "loss": 0.202, + "epoch": 0.16, + "learning_rate": 4.18973848459766e-05, + "loss": 0.2224, "step": 73470 }, { - "epoch": 0.66, - "learning_rate": 1.7367804702279076e-05, - "loss": 0.1998, + "epoch": 0.16, + "learning_rate": 4.189626630276728e-05, + "loss": 0.2254, "step": 73480 }, { - "epoch": 0.66, - "learning_rate": 1.736330060354923e-05, - "loss": 0.2062, + "epoch": 0.16, + "learning_rate": 4.189514775955795e-05, + "loss": 0.2272, "step": 73490 }, { - "epoch": 0.66, - "learning_rate": 1.7358796504819385e-05, - "loss": 0.1978, + "epoch": 0.16, + "learning_rate": 4.189402921634863e-05, + "loss": 0.2251, "step": 73500 }, { - "epoch": 0.66, - "learning_rate": 1.7354292406089542e-05, - "loss": 0.1992, + "epoch": 0.16, + "learning_rate": 4.1892910673139307e-05, + "loss": 0.2299, "step": 73510 }, { - "epoch": 0.66, - "learning_rate": 1.73497883073597e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.189179212992998e-05, + "loss": 0.2253, "step": 73520 }, { - "epoch": 0.66, - "learning_rate": 1.7345284208629854e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.1890673586720656e-05, + "loss": 0.2268, "step": 73530 }, { - "epoch": 0.66, - "learning_rate": 1.7340780109900008e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.1889555043511334e-05, + "loss": 0.2236, "step": 73540 }, { - "epoch": 0.66, - "learning_rate": 1.7336276011170165e-05, - "loss": 0.2047, + "epoch": 0.16, + "learning_rate": 4.188843650030201e-05, + "loss": 0.2253, "step": 73550 }, { - "epoch": 0.66, - "learning_rate": 1.7331771912440323e-05, - "loss": 0.2035, + "epoch": 0.16, + "learning_rate": 4.188731795709269e-05, + "loss": 0.2287, "step": 73560 }, { - "epoch": 0.66, - "learning_rate": 1.7327267813710477e-05, - "loss": 0.1995, + "epoch": 0.16, + "learning_rate": 4.188619941388336e-05, + "loss": 0.2289, "step": 73570 }, { - "epoch": 0.66, - "learning_rate": 1.7322763714980634e-05, - "loss": 0.1976, + "epoch": 0.16, + "learning_rate": 4.188508087067404e-05, + "loss": 0.2289, "step": 73580 }, { - "epoch": 0.66, - "learning_rate": 1.731825961625079e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.188396232746471e-05, + "loss": 0.2258, "step": 73590 }, { - "epoch": 0.66, - "learning_rate": 1.7313755517520943e-05, - "loss": 0.2007, + "epoch": 0.16, + "learning_rate": 4.188284378425539e-05, + "loss": 0.2267, "step": 73600 }, { - "epoch": 0.66, - "learning_rate": 1.7309701828664086e-05, - "loss": 0.1989, + "epoch": 0.16, + "learning_rate": 4.1881725241046065e-05, + "loss": 0.2258, "step": 73610 }, { - "epoch": 0.66, - "learning_rate": 1.730519772993424e-05, - "loss": 0.2015, + "epoch": 0.16, + "learning_rate": 4.1880606697836737e-05, + "loss": 0.23, "step": 73620 }, { - "epoch": 0.66, - "learning_rate": 1.7300693631204395e-05, - "loss": 0.2038, + "epoch": 0.16, + "learning_rate": 4.1879488154627415e-05, + "loss": 0.2262, "step": 73630 }, { - "epoch": 0.66, - "learning_rate": 1.7296189532474552e-05, - "loss": 0.2028, + "epoch": 0.16, + "learning_rate": 4.1878369611418086e-05, + "loss": 0.2321, "step": 73640 }, { - "epoch": 0.66, - "learning_rate": 1.729168543374471e-05, - "loss": 0.1958, + "epoch": 0.16, + "learning_rate": 4.187725106820877e-05, + "loss": 0.2307, "step": 73650 }, { - "epoch": 0.66, - "learning_rate": 1.7287181335014864e-05, - "loss": 0.1953, + "epoch": 0.16, + "learning_rate": 4.187613252499945e-05, + "loss": 0.2238, "step": 73660 }, { - "epoch": 0.66, - "learning_rate": 1.7282677236285018e-05, - "loss": 0.2058, + "epoch": 0.16, + "learning_rate": 4.187501398179012e-05, + "loss": 0.228, "step": 73670 }, { - "epoch": 0.66, - "learning_rate": 1.7278173137555175e-05, - "loss": 0.2025, + "epoch": 0.16, + "learning_rate": 4.18738954385808e-05, + "loss": 0.2265, "step": 73680 }, { - "epoch": 0.66, - "learning_rate": 1.7273669038825333e-05, - "loss": 0.2087, + "epoch": 0.16, + "learning_rate": 4.187277689537147e-05, + "loss": 0.2289, "step": 73690 }, { - "epoch": 0.66, - "learning_rate": 1.7269164940095487e-05, - "loss": 0.2089, + "epoch": 0.16, + "learning_rate": 4.1871658352162146e-05, + "loss": 0.2287, "step": 73700 }, { - "epoch": 0.66, - "learning_rate": 1.7264660841365644e-05, - "loss": 0.204, + "epoch": 0.16, + "learning_rate": 4.1870539808952824e-05, + "loss": 0.2284, "step": 73710 }, { - "epoch": 0.66, - "learning_rate": 1.72601567426358e-05, - "loss": 0.2006, + "epoch": 0.16, + "learning_rate": 4.1869421265743496e-05, + "loss": 0.2242, "step": 73720 }, { - "epoch": 0.66, - "learning_rate": 1.7255652643905956e-05, - "loss": 0.1996, + "epoch": 0.16, + "learning_rate": 4.1868302722534173e-05, + "loss": 0.2279, "step": 73730 }, { - "epoch": 0.66, - "learning_rate": 1.725114854517611e-05, - "loss": 0.2056, + "epoch": 0.16, + "learning_rate": 4.1867184179324845e-05, + "loss": 0.2235, "step": 73740 }, { - "epoch": 0.66, - "learning_rate": 1.7246644446446268e-05, - "loss": 0.2026, + "epoch": 0.16, + "learning_rate": 4.186606563611552e-05, + "loss": 0.2279, "step": 73750 }, { - "epoch": 0.66, - "learning_rate": 1.7242140347716422e-05, - "loss": 0.2011, + "epoch": 0.16, + "learning_rate": 4.18649470929062e-05, + "loss": 0.2268, "step": 73760 }, { - "epoch": 0.66, - "learning_rate": 1.7237636248986576e-05, - "loss": 0.2017, + "epoch": 0.16, + "learning_rate": 4.186382854969688e-05, + "loss": 0.2235, "step": 73770 }, { - "epoch": 0.66, - "learning_rate": 1.7233132150256733e-05, - "loss": 0.2057, + "epoch": 0.16, + "learning_rate": 4.1862710006487556e-05, + "loss": 0.225, "step": 73780 }, { - "epoch": 0.66, - "learning_rate": 1.722862805152689e-05, - "loss": 0.2024, + "epoch": 0.16, + "learning_rate": 4.186159146327823e-05, + "loss": 0.2329, "step": 73790 }, { - "epoch": 0.66, - "learning_rate": 1.7224123952797048e-05, - "loss": 0.1989, + "epoch": 0.16, + "learning_rate": 4.1860472920068905e-05, + "loss": 0.2256, "step": 73800 }, { - "epoch": 0.66, - "learning_rate": 1.7219619854067202e-05, - "loss": 0.1998, + "epoch": 0.16, + "learning_rate": 4.1859354376859577e-05, + "loss": 0.2305, "step": 73810 }, { - "epoch": 0.66, - "learning_rate": 1.7215115755337357e-05, - "loss": 0.2033, + "epoch": 0.16, + "learning_rate": 4.1858235833650254e-05, + "loss": 0.2284, "step": 73820 }, { - "epoch": 0.66, - "learning_rate": 1.7210611656607514e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.185711729044093e-05, + "loss": 0.221, "step": 73830 }, { - "epoch": 0.66, - "learning_rate": 1.7206107557877668e-05, - "loss": 0.1997, + "epoch": 0.16, + "learning_rate": 4.1855998747231604e-05, + "loss": 0.2244, "step": 73840 }, { - "epoch": 0.66, - "learning_rate": 1.7201603459147826e-05, - "loss": 0.1993, + "epoch": 0.16, + "learning_rate": 4.185488020402228e-05, + "loss": 0.223, "step": 73850 }, { - "epoch": 0.66, - "learning_rate": 1.7197099360417983e-05, - "loss": 0.197, + "epoch": 0.16, + "learning_rate": 4.185376166081296e-05, + "loss": 0.2264, "step": 73860 }, { - "epoch": 0.66, - "learning_rate": 1.7192595261688137e-05, - "loss": 0.2021, + "epoch": 0.16, + "learning_rate": 4.185264311760364e-05, + "loss": 0.2248, "step": 73870 }, { - "epoch": 0.66, - "learning_rate": 1.718809116295829e-05, - "loss": 0.2031, + "epoch": 0.16, + "learning_rate": 4.1851524574394315e-05, + "loss": 0.2243, "step": 73880 }, { - "epoch": 0.66, - "learning_rate": 1.718358706422845e-05, - "loss": 0.2022, + "epoch": 0.16, + "learning_rate": 4.1850406031184986e-05, + "loss": 0.228, "step": 73890 }, { - "epoch": 0.66, - "learning_rate": 1.7179082965498606e-05, - "loss": 0.2061, + "epoch": 0.16, + "learning_rate": 4.1849287487975664e-05, + "loss": 0.231, "step": 73900 }, { - "epoch": 0.66, - "learning_rate": 1.717457886676876e-05, - "loss": 0.1981, + "epoch": 0.16, + "learning_rate": 4.1848168944766336e-05, + "loss": 0.2274, "step": 73910 }, { - "epoch": 0.66, - "learning_rate": 1.7170074768038914e-05, - "loss": 0.2004, + "epoch": 0.16, + "learning_rate": 4.1847050401557013e-05, + "loss": 0.226, "step": 73920 }, { - "epoch": 0.66, - "learning_rate": 1.7165570669309072e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.184593185834769e-05, + "loss": 0.2198, "step": 73930 }, { - "epoch": 0.66, - "learning_rate": 1.716106657057923e-05, - "loss": 0.2014, + "epoch": 0.17, + "learning_rate": 4.184481331513836e-05, + "loss": 0.2238, "step": 73940 }, { - "epoch": 0.66, - "learning_rate": 1.7156562471849384e-05, - "loss": 0.2005, + "epoch": 0.17, + "learning_rate": 4.184369477192904e-05, + "loss": 0.2248, "step": 73950 }, { - "epoch": 0.66, - "learning_rate": 1.715205837311954e-05, - "loss": 0.195, + "epoch": 0.17, + "learning_rate": 4.184257622871972e-05, + "loss": 0.2191, "step": 73960 }, { - "epoch": 0.66, - "learning_rate": 1.7147554274389695e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.1841457685510396e-05, + "loss": 0.2268, "step": 73970 }, { - "epoch": 0.66, - "learning_rate": 1.714305017565985e-05, - "loss": 0.1981, + "epoch": 0.17, + "learning_rate": 4.1840339142301074e-05, + "loss": 0.223, "step": 73980 }, { - "epoch": 0.66, - "learning_rate": 1.7138546076930007e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.1839220599091745e-05, + "loss": 0.2364, "step": 73990 }, { - "epoch": 0.66, - "learning_rate": 1.7134041978200164e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.183810205588242e-05, + "loss": 0.2272, "step": 74000 }, { - "epoch": 0.66, - "learning_rate": 1.712953787947032e-05, - "loss": 0.2008, + "epoch": 0.17, + "learning_rate": 4.1836983512673094e-05, + "loss": 0.2237, "step": 74010 }, { - "epoch": 0.66, - "learning_rate": 1.7125033780740472e-05, - "loss": 0.2052, + "epoch": 0.17, + "learning_rate": 4.183586496946377e-05, + "loss": 0.2307, "step": 74020 }, { - "epoch": 0.66, - "learning_rate": 1.712052968201063e-05, - "loss": 0.2042, + "epoch": 0.17, + "learning_rate": 4.183474642625445e-05, + "loss": 0.2273, "step": 74030 }, { - "epoch": 0.66, - "learning_rate": 1.7116025583280787e-05, - "loss": 0.2025, + "epoch": 0.17, + "learning_rate": 4.183362788304512e-05, + "loss": 0.2218, "step": 74040 }, { - "epoch": 0.66, - "learning_rate": 1.711152148455094e-05, - "loss": 0.2051, + "epoch": 0.17, + "learning_rate": 4.18325093398358e-05, + "loss": 0.2263, "step": 74050 }, { - "epoch": 0.66, - "learning_rate": 1.71070173858211e-05, - "loss": 0.2032, + "epoch": 0.17, + "learning_rate": 4.183139079662648e-05, + "loss": 0.2225, "step": 74060 }, { - "epoch": 0.66, - "learning_rate": 1.7102513287091253e-05, - "loss": 0.2002, + "epoch": 0.17, + "learning_rate": 4.1830272253417155e-05, + "loss": 0.2256, "step": 74070 }, { - "epoch": 0.66, - "learning_rate": 1.709800918836141e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.1829153710207826e-05, + "loss": 0.2291, "step": 74080 }, { - "epoch": 0.66, - "learning_rate": 1.7093505089631565e-05, - "loss": 0.1913, + "epoch": 0.17, + "learning_rate": 4.1828035166998504e-05, + "loss": 0.2292, "step": 74090 }, { - "epoch": 0.66, - "learning_rate": 1.7089000990901722e-05, - "loss": 0.1961, + "epoch": 0.17, + "learning_rate": 4.182691662378918e-05, + "loss": 0.2226, "step": 74100 }, { - "epoch": 0.66, - "learning_rate": 1.7084496892171876e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.1825798080579853e-05, + "loss": 0.2258, "step": 74110 }, { - "epoch": 0.66, - "learning_rate": 1.707999279344203e-05, - "loss": 0.1977, + "epoch": 0.17, + "learning_rate": 4.182467953737053e-05, + "loss": 0.2288, "step": 74120 }, { - "epoch": 0.66, - "learning_rate": 1.7075488694712188e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.18235609941612e-05, + "loss": 0.2287, "step": 74130 }, { - "epoch": 0.66, - "learning_rate": 1.7070984595982345e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.182244245095188e-05, + "loss": 0.2207, "step": 74140 }, { - "epoch": 0.66, - "learning_rate": 1.7066480497252503e-05, - "loss": 0.2091, + "epoch": 0.17, + "learning_rate": 4.182132390774256e-05, + "loss": 0.2297, "step": 74150 }, { - "epoch": 0.66, - "learning_rate": 1.7061976398522657e-05, - "loss": 0.2009, + "epoch": 0.17, + "learning_rate": 4.182020536453323e-05, + "loss": 0.2302, "step": 74160 }, { - "epoch": 0.66, - "learning_rate": 1.705747229979281e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.181908682132391e-05, + "loss": 0.2273, "step": 74170 }, { - "epoch": 0.66, - "learning_rate": 1.705296820106297e-05, - "loss": 0.1996, + "epoch": 0.17, + "learning_rate": 4.1817968278114585e-05, + "loss": 0.2271, "step": 74180 }, { - "epoch": 0.66, - "learning_rate": 1.7048464102333123e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.181684973490526e-05, + "loss": 0.2234, "step": 74190 }, { - "epoch": 0.66, - "learning_rate": 1.704396000360328e-05, - "loss": 0.2066, + "epoch": 0.17, + "learning_rate": 4.181573119169594e-05, + "loss": 0.23, "step": 74200 }, { - "epoch": 0.66, - "learning_rate": 1.7039455904873434e-05, - "loss": 0.2021, + "epoch": 0.17, + "learning_rate": 4.181461264848661e-05, + "loss": 0.2305, "step": 74210 }, { - "epoch": 0.66, - "learning_rate": 1.7034951806143592e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.181349410527729e-05, + "loss": 0.2251, "step": 74220 }, { - "epoch": 0.66, - "learning_rate": 1.7030447707413746e-05, - "loss": 0.2042, + "epoch": 0.17, + "learning_rate": 4.181237556206796e-05, + "loss": 0.2311, "step": 74230 }, { - "epoch": 0.66, - "learning_rate": 1.7025943608683903e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.181125701885864e-05, + "loss": 0.2288, "step": 74240 }, { - "epoch": 0.66, - "learning_rate": 1.702143950995406e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.181013847564932e-05, + "loss": 0.2288, "step": 74250 }, { - "epoch": 0.66, - "learning_rate": 1.7016935411224215e-05, - "loss": 0.2085, + "epoch": 0.17, + "learning_rate": 4.180901993243999e-05, + "loss": 0.2201, "step": 74260 }, { - "epoch": 0.66, - "learning_rate": 1.701243131249437e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.1807901389230666e-05, + "loss": 0.2249, "step": 74270 }, { - "epoch": 0.66, - "learning_rate": 1.7007927213764527e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.1806782846021344e-05, + "loss": 0.2247, "step": 74280 }, { - "epoch": 0.66, - "learning_rate": 1.7003423115034684e-05, - "loss": 0.2009, + "epoch": 0.17, + "learning_rate": 4.180566430281202e-05, + "loss": 0.2327, "step": 74290 }, { - "epoch": 0.66, - "learning_rate": 1.6998919016304838e-05, - "loss": 0.2031, + "epoch": 0.17, + "learning_rate": 4.18045457596027e-05, + "loss": 0.2278, "step": 74300 }, { - "epoch": 0.66, - "learning_rate": 1.6994414917574992e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.180342721639337e-05, + "loss": 0.2264, "step": 74310 }, { - "epoch": 0.66, - "learning_rate": 1.698991081884515e-05, - "loss": 0.195, + "epoch": 0.17, + "learning_rate": 4.180230867318405e-05, + "loss": 0.2248, "step": 74320 }, { - "epoch": 0.66, - "learning_rate": 1.6985406720115304e-05, - "loss": 0.1977, + "epoch": 0.17, + "learning_rate": 4.180119012997472e-05, + "loss": 0.2254, "step": 74330 }, { - "epoch": 0.66, - "learning_rate": 1.698090262138546e-05, - "loss": 0.2068, + "epoch": 0.17, + "learning_rate": 4.18000715867654e-05, + "loss": 0.2311, "step": 74340 }, { - "epoch": 0.66, - "learning_rate": 1.697639852265562e-05, - "loss": 0.1984, + "epoch": 0.17, + "learning_rate": 4.1798953043556076e-05, + "loss": 0.2289, "step": 74350 }, { - "epoch": 0.66, - "learning_rate": 1.6971894423925773e-05, - "loss": 0.2029, + "epoch": 0.17, + "learning_rate": 4.179783450034675e-05, + "loss": 0.2219, "step": 74360 }, { - "epoch": 0.66, - "learning_rate": 1.6967390325195927e-05, - "loss": 0.2004, + "epoch": 0.17, + "learning_rate": 4.1796715957137425e-05, + "loss": 0.2299, "step": 74370 }, { - "epoch": 0.66, - "learning_rate": 1.6962886226466085e-05, - "loss": 0.1975, + "epoch": 0.17, + "learning_rate": 4.17955974139281e-05, + "loss": 0.226, "step": 74380 }, { - "epoch": 0.66, - "learning_rate": 1.6958382127736242e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.179447887071878e-05, + "loss": 0.2243, "step": 74390 }, { - "epoch": 0.66, - "learning_rate": 1.6953878029006396e-05, - "loss": 0.1948, + "epoch": 0.17, + "learning_rate": 4.179336032750945e-05, + "loss": 0.2233, "step": 74400 }, { - "epoch": 0.66, - "learning_rate": 1.694937393027655e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.179224178430013e-05, + "loss": 0.2267, "step": 74410 }, { - "epoch": 0.66, - "learning_rate": 1.6944869831546708e-05, - "loss": 0.2034, + "epoch": 0.17, + "learning_rate": 4.179112324109081e-05, + "loss": 0.2261, "step": 74420 }, { - "epoch": 0.66, - "learning_rate": 1.6940365732816865e-05, - "loss": 0.2022, + "epoch": 0.17, + "learning_rate": 4.179000469788148e-05, + "loss": 0.2224, "step": 74430 }, { - "epoch": 0.66, - "learning_rate": 1.693586163408702e-05, - "loss": 0.2001, + "epoch": 0.17, + "learning_rate": 4.178888615467216e-05, + "loss": 0.2264, "step": 74440 }, { - "epoch": 0.66, - "learning_rate": 1.6931357535357177e-05, - "loss": 0.1964, + "epoch": 0.17, + "learning_rate": 4.178776761146283e-05, + "loss": 0.2266, "step": 74450 }, { - "epoch": 0.66, - "learning_rate": 1.692685343662733e-05, - "loss": 0.2002, + "epoch": 0.17, + "learning_rate": 4.1786649068253506e-05, + "loss": 0.224, "step": 74460 }, { - "epoch": 0.66, - "learning_rate": 1.6922349337897485e-05, - "loss": 0.1971, + "epoch": 0.17, + "learning_rate": 4.1785530525044184e-05, + "loss": 0.2229, "step": 74470 }, { - "epoch": 0.66, - "learning_rate": 1.6917845239167643e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.178441198183486e-05, + "loss": 0.2212, "step": 74480 }, { - "epoch": 0.67, - "learning_rate": 1.69133411404378e-05, - "loss": 0.1949, + "epoch": 0.17, + "learning_rate": 4.178329343862554e-05, + "loss": 0.22, "step": 74490 }, { - "epoch": 0.67, - "learning_rate": 1.6908837041707958e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.178217489541621e-05, + "loss": 0.2234, "step": 74500 }, { - "epoch": 0.67, - "learning_rate": 1.690433294297811e-05, - "loss": 0.1945, + "epoch": 0.17, + "learning_rate": 4.178105635220689e-05, + "loss": 0.2267, "step": 74510 }, { - "epoch": 0.67, - "learning_rate": 1.6899828844248266e-05, - "loss": 0.1991, + "epoch": 0.17, + "learning_rate": 4.177993780899757e-05, + "loss": 0.2234, "step": 74520 }, { - "epoch": 0.67, - "learning_rate": 1.6895324745518423e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.177881926578824e-05, + "loss": 0.2214, "step": 74530 }, { - "epoch": 0.67, - "learning_rate": 1.6890820646788577e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.1777700722578916e-05, + "loss": 0.2301, "step": 74540 }, { - "epoch": 0.67, - "learning_rate": 1.6886316548058735e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.177658217936959e-05, + "loss": 0.2187, "step": 74550 }, { - "epoch": 0.67, - "learning_rate": 1.688181244932889e-05, - "loss": 0.2088, + "epoch": 0.17, + "learning_rate": 4.1775463636160265e-05, + "loss": 0.2258, "step": 74560 }, { - "epoch": 0.67, - "learning_rate": 1.6877308350599046e-05, - "loss": 0.2001, + "epoch": 0.17, + "learning_rate": 4.177434509295094e-05, + "loss": 0.2268, "step": 74570 }, { - "epoch": 0.67, - "learning_rate": 1.68728042518692e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.1773226549741614e-05, + "loss": 0.2246, "step": 74580 }, { - "epoch": 0.67, - "learning_rate": 1.6868300153139358e-05, - "loss": 0.1981, + "epoch": 0.17, + "learning_rate": 4.177210800653229e-05, + "loss": 0.2298, "step": 74590 }, { - "epoch": 0.67, - "learning_rate": 1.6863796054409516e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.177098946332297e-05, + "loss": 0.2279, "step": 74600 }, { - "epoch": 0.67, - "learning_rate": 1.685929195567967e-05, - "loss": 0.1975, + "epoch": 0.17, + "learning_rate": 4.176987092011365e-05, + "loss": 0.2214, "step": 74610 }, { - "epoch": 0.67, - "learning_rate": 1.6854787856949824e-05, - "loss": 0.1984, + "epoch": 0.17, + "learning_rate": 4.1768752376904326e-05, + "loss": 0.2244, "step": 74620 }, { - "epoch": 0.67, - "learning_rate": 1.685028375821998e-05, - "loss": 0.199, + "epoch": 0.17, + "learning_rate": 4.1767633833695e-05, + "loss": 0.2274, "step": 74630 }, { - "epoch": 0.67, - "learning_rate": 1.684577965949014e-05, - "loss": 0.1989, + "epoch": 0.17, + "learning_rate": 4.1766515290485675e-05, + "loss": 0.2206, "step": 74640 }, { - "epoch": 0.67, - "learning_rate": 1.6841275560760293e-05, - "loss": 0.2051, + "epoch": 0.17, + "learning_rate": 4.1765396747276346e-05, + "loss": 0.2217, "step": 74650 }, { - "epoch": 0.67, - "learning_rate": 1.6836771462030447e-05, - "loss": 0.2019, + "epoch": 0.17, + "learning_rate": 4.1764278204067024e-05, + "loss": 0.2226, "step": 74660 }, { - "epoch": 0.67, - "learning_rate": 1.6832267363300604e-05, - "loss": 0.2, + "epoch": 0.17, + "learning_rate": 4.17631596608577e-05, + "loss": 0.2245, "step": 74670 }, { - "epoch": 0.67, - "learning_rate": 1.682776326457076e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.176204111764837e-05, + "loss": 0.2328, "step": 74680 }, { - "epoch": 0.67, - "learning_rate": 1.6823259165840916e-05, - "loss": 0.1974, + "epoch": 0.17, + "learning_rate": 4.176092257443905e-05, + "loss": 0.2188, "step": 74690 }, { - "epoch": 0.67, - "learning_rate": 1.6818755067111074e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.175980403122973e-05, + "loss": 0.2296, "step": 74700 }, { - "epoch": 0.67, - "learning_rate": 1.6814250968381228e-05, - "loss": 0.2025, + "epoch": 0.17, + "learning_rate": 4.175868548802041e-05, + "loss": 0.2201, "step": 74710 }, { - "epoch": 0.67, - "learning_rate": 1.6809746869651382e-05, - "loss": 0.1949, + "epoch": 0.17, + "learning_rate": 4.175756694481108e-05, + "loss": 0.2271, "step": 74720 }, { - "epoch": 0.67, - "learning_rate": 1.680524277092154e-05, - "loss": 0.2084, + "epoch": 0.17, + "learning_rate": 4.1756448401601756e-05, + "loss": 0.227, "step": 74730 }, { - "epoch": 0.67, - "learning_rate": 1.6800738672191697e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.1755329858392434e-05, + "loss": 0.2262, "step": 74740 }, { - "epoch": 0.67, - "learning_rate": 1.679623457346185e-05, - "loss": 0.2018, + "epoch": 0.17, + "learning_rate": 4.1754211315183105e-05, + "loss": 0.2177, "step": 74750 }, { - "epoch": 0.67, - "learning_rate": 1.6791730474732005e-05, - "loss": 0.2107, + "epoch": 0.17, + "learning_rate": 4.175309277197378e-05, + "loss": 0.2249, "step": 74760 }, { - "epoch": 0.67, - "learning_rate": 1.6787226376002162e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.1751974228764454e-05, + "loss": 0.2295, "step": 74770 }, { - "epoch": 0.67, - "learning_rate": 1.678272227727232e-05, - "loss": 0.2031, + "epoch": 0.17, + "learning_rate": 4.175085568555513e-05, + "loss": 0.2257, "step": 74780 }, { - "epoch": 0.67, - "learning_rate": 1.6778218178542474e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.174973714234581e-05, + "loss": 0.2214, "step": 74790 }, { - "epoch": 0.67, - "learning_rate": 1.677371407981263e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.174861859913649e-05, + "loss": 0.2268, "step": 74800 }, { - "epoch": 0.67, - "learning_rate": 1.6769209981082786e-05, - "loss": 0.191, + "epoch": 0.17, + "learning_rate": 4.1747500055927166e-05, + "loss": 0.2288, "step": 74810 }, { - "epoch": 0.67, - "learning_rate": 1.676470588235294e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.174638151271784e-05, + "loss": 0.2271, "step": 74820 }, { - "epoch": 0.67, - "learning_rate": 1.6760201783623097e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.1745262969508515e-05, + "loss": 0.2259, "step": 74830 }, { - "epoch": 0.67, - "learning_rate": 1.6755697684893255e-05, - "loss": 0.2018, + "epoch": 0.17, + "learning_rate": 4.174414442629919e-05, + "loss": 0.2148, "step": 74840 }, { - "epoch": 0.67, - "learning_rate": 1.6751193586163412e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.1743025883089864e-05, + "loss": 0.2204, "step": 74850 }, { - "epoch": 0.67, - "learning_rate": 1.6746689487433563e-05, - "loss": 0.1942, + "epoch": 0.17, + "learning_rate": 4.174190733988054e-05, + "loss": 0.2296, "step": 74860 }, { - "epoch": 0.67, - "learning_rate": 1.674218538870372e-05, - "loss": 0.207, + "epoch": 0.17, + "learning_rate": 4.174078879667121e-05, + "loss": 0.2277, "step": 74870 }, { - "epoch": 0.67, - "learning_rate": 1.6737681289973878e-05, - "loss": 0.2015, + "epoch": 0.17, + "learning_rate": 4.173967025346189e-05, + "loss": 0.2251, "step": 74880 }, { - "epoch": 0.67, - "learning_rate": 1.6733177191244032e-05, - "loss": 0.2, + "epoch": 0.17, + "learning_rate": 4.173855171025257e-05, + "loss": 0.2252, "step": 74890 }, { - "epoch": 0.67, - "learning_rate": 1.672867309251419e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.173743316704325e-05, + "loss": 0.2175, "step": 74900 }, { - "epoch": 0.67, - "learning_rate": 1.6724168993784344e-05, - "loss": 0.1992, + "epoch": 0.17, + "learning_rate": 4.1736314623833925e-05, + "loss": 0.2258, "step": 74910 }, { - "epoch": 0.67, - "learning_rate": 1.67196648950545e-05, - "loss": 0.1982, + "epoch": 0.17, + "learning_rate": 4.1735196080624596e-05, + "loss": 0.221, "step": 74920 }, { - "epoch": 0.67, - "learning_rate": 1.6715160796324655e-05, - "loss": 0.2005, + "epoch": 0.17, + "learning_rate": 4.1734077537415274e-05, + "loss": 0.2268, "step": 74930 }, { - "epoch": 0.67, - "learning_rate": 1.6710656697594813e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.173295899420595e-05, + "loss": 0.2282, "step": 74940 }, { - "epoch": 0.67, - "learning_rate": 1.670615259886497e-05, - "loss": 0.2114, + "epoch": 0.17, + "learning_rate": 4.173184045099662e-05, + "loss": 0.2243, "step": 74950 }, { - "epoch": 0.67, - "learning_rate": 1.670164850013512e-05, - "loss": 0.1989, + "epoch": 0.17, + "learning_rate": 4.17307219077873e-05, + "loss": 0.2247, "step": 74960 }, { - "epoch": 0.67, - "learning_rate": 1.669714440140528e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.172960336457797e-05, + "loss": 0.2254, "step": 74970 }, { - "epoch": 0.67, - "learning_rate": 1.6692640302675436e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.172848482136865e-05, + "loss": 0.225, "step": 74980 }, { - "epoch": 0.67, - "learning_rate": 1.6688136203945593e-05, - "loss": 0.1935, + "epoch": 0.17, + "learning_rate": 4.172736627815933e-05, + "loss": 0.2235, "step": 74990 }, { - "epoch": 0.67, - "learning_rate": 1.6683632105215747e-05, - "loss": 0.2023, + "epoch": 0.17, + "learning_rate": 4.172624773495e-05, + "loss": 0.2286, "step": 75000 }, { - "epoch": 0.67, - "learning_rate": 1.66791280064859e-05, - "loss": 0.1925, + "epoch": 0.17, + "learning_rate": 4.1725129191740684e-05, + "loss": 0.2253, "step": 75010 }, { - "epoch": 0.67, - "learning_rate": 1.667462390775606e-05, - "loss": 0.1965, + "epoch": 0.17, + "learning_rate": 4.1724010648531355e-05, + "loss": 0.2249, "step": 75020 }, { - "epoch": 0.67, - "learning_rate": 1.6670119809026213e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.172289210532203e-05, + "loss": 0.2265, "step": 75030 }, { - "epoch": 0.67, - "learning_rate": 1.666561571029637e-05, - "loss": 0.2037, + "epoch": 0.17, + "learning_rate": 4.1721773562112704e-05, + "loss": 0.2296, "step": 75040 }, { - "epoch": 0.67, - "learning_rate": 1.6661111611566528e-05, - "loss": 0.1995, + "epoch": 0.17, + "learning_rate": 4.172065501890338e-05, + "loss": 0.225, "step": 75050 }, { - "epoch": 0.67, - "learning_rate": 1.6656607512836682e-05, - "loss": 0.1936, + "epoch": 0.17, + "learning_rate": 4.171953647569406e-05, + "loss": 0.2289, "step": 75060 }, { - "epoch": 0.67, - "learning_rate": 1.6652103414106836e-05, - "loss": 0.2037, + "epoch": 0.17, + "learning_rate": 4.171841793248473e-05, + "loss": 0.2228, "step": 75070 }, { - "epoch": 0.67, - "learning_rate": 1.6647599315376994e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.171729938927541e-05, + "loss": 0.2268, "step": 75080 }, { - "epoch": 0.67, - "learning_rate": 1.664309521664715e-05, - "loss": 0.2044, + "epoch": 0.17, + "learning_rate": 4.171618084606608e-05, + "loss": 0.2239, "step": 75090 }, { - "epoch": 0.67, - "learning_rate": 1.6638591117917305e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.171506230285676e-05, + "loss": 0.2241, "step": 75100 }, { - "epoch": 0.67, - "learning_rate": 1.663408701918746e-05, - "loss": 0.1941, + "epoch": 0.17, + "learning_rate": 4.1713943759647436e-05, + "loss": 0.2208, "step": 75110 }, { - "epoch": 0.67, - "learning_rate": 1.6629582920457617e-05, - "loss": 0.1968, + "epoch": 0.17, + "learning_rate": 4.1712825216438114e-05, + "loss": 0.225, "step": 75120 }, { - "epoch": 0.67, - "learning_rate": 1.6625078821727775e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.171170667322879e-05, + "loss": 0.2287, "step": 75130 }, { - "epoch": 0.67, - "learning_rate": 1.662057472299793e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.171058813001946e-05, + "loss": 0.2235, "step": 75140 }, { - "epoch": 0.67, - "learning_rate": 1.6616070624268086e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.170946958681014e-05, + "loss": 0.225, "step": 75150 }, { - "epoch": 0.67, - "learning_rate": 1.661156652553824e-05, - "loss": 0.203, + "epoch": 0.17, + "learning_rate": 4.170835104360082e-05, + "loss": 0.2224, "step": 75160 }, { - "epoch": 0.67, - "learning_rate": 1.6607062426808394e-05, - "loss": 0.2052, + "epoch": 0.17, + "learning_rate": 4.170723250039149e-05, + "loss": 0.2274, "step": 75170 }, { - "epoch": 0.67, - "learning_rate": 1.6602558328078552e-05, - "loss": 0.2039, + "epoch": 0.17, + "learning_rate": 4.170611395718217e-05, + "loss": 0.223, "step": 75180 }, { - "epoch": 0.67, - "learning_rate": 1.659805422934871e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.170499541397284e-05, + "loss": 0.2273, "step": 75190 }, { - "epoch": 0.67, - "learning_rate": 1.6593550130618863e-05, - "loss": 0.2043, + "epoch": 0.17, + "learning_rate": 4.170387687076352e-05, + "loss": 0.2251, "step": 75200 }, { - "epoch": 0.67, - "learning_rate": 1.6589046031889018e-05, - "loss": 0.1989, + "epoch": 0.17, + "learning_rate": 4.1702758327554195e-05, + "loss": 0.221, "step": 75210 }, { - "epoch": 0.67, - "learning_rate": 1.6584541933159175e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.170163978434487e-05, + "loss": 0.2275, "step": 75220 }, { - "epoch": 0.67, - "learning_rate": 1.6580037834429333e-05, - "loss": 0.2057, + "epoch": 0.17, + "learning_rate": 4.170052124113555e-05, + "loss": 0.2248, "step": 75230 }, { - "epoch": 0.67, - "learning_rate": 1.6575533735699487e-05, - "loss": 0.205, + "epoch": 0.17, + "learning_rate": 4.169940269792622e-05, + "loss": 0.2201, "step": 75240 }, { - "epoch": 0.67, - "learning_rate": 1.6571029636969644e-05, - "loss": 0.1959, + "epoch": 0.17, + "learning_rate": 4.16982841547169e-05, + "loss": 0.2204, "step": 75250 }, { - "epoch": 0.67, - "learning_rate": 1.6566525538239798e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.169716561150758e-05, + "loss": 0.2218, "step": 75260 }, { - "epoch": 0.67, - "learning_rate": 1.6562021439509956e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.169604706829825e-05, + "loss": 0.2283, "step": 75270 }, { - "epoch": 0.67, - "learning_rate": 1.655751734078011e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.169492852508893e-05, + "loss": 0.2257, "step": 75280 }, { - "epoch": 0.67, - "learning_rate": 1.6553013242050267e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.16938099818796e-05, + "loss": 0.2303, "step": 75290 }, { - "epoch": 0.67, - "learning_rate": 1.6548509143320425e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.1692691438670276e-05, + "loss": 0.2292, "step": 75300 }, { - "epoch": 0.67, - "learning_rate": 1.6544005044590576e-05, - "loss": 0.2041, + "epoch": 0.17, + "learning_rate": 4.1691572895460954e-05, + "loss": 0.224, "step": 75310 }, { - "epoch": 0.67, - "learning_rate": 1.6539500945860733e-05, - "loss": 0.2004, + "epoch": 0.17, + "learning_rate": 4.169045435225163e-05, + "loss": 0.2208, "step": 75320 }, { - "epoch": 0.67, - "learning_rate": 1.653499684713089e-05, - "loss": 0.2008, + "epoch": 0.17, + "learning_rate": 4.168933580904231e-05, + "loss": 0.2266, "step": 75330 }, { - "epoch": 0.67, - "learning_rate": 1.6530492748401048e-05, - "loss": 0.1981, + "epoch": 0.17, + "learning_rate": 4.168821726583298e-05, + "loss": 0.2221, "step": 75340 }, { - "epoch": 0.67, - "learning_rate": 1.6525988649671202e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.168709872262366e-05, + "loss": 0.2242, "step": 75350 }, { - "epoch": 0.67, - "learning_rate": 1.6521484550941356e-05, - "loss": 0.2031, + "epoch": 0.17, + "learning_rate": 4.168598017941433e-05, + "loss": 0.2252, "step": 75360 }, { - "epoch": 0.67, - "learning_rate": 1.6516980452211514e-05, - "loss": 0.2014, + "epoch": 0.17, + "learning_rate": 4.168486163620501e-05, + "loss": 0.2298, "step": 75370 }, { - "epoch": 0.67, - "learning_rate": 1.6512476353481668e-05, - "loss": 0.2064, + "epoch": 0.17, + "learning_rate": 4.1683743092995686e-05, + "loss": 0.2256, "step": 75380 }, { - "epoch": 0.67, - "learning_rate": 1.6507972254751825e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.1682736404107295e-05, + "loss": 0.2221, "step": 75390 }, { - "epoch": 0.67, - "learning_rate": 1.6503468156021983e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.168161786089797e-05, + "loss": 0.2222, "step": 75400 }, { - "epoch": 0.67, - "learning_rate": 1.6498964057292137e-05, - "loss": 0.1968, + "epoch": 0.17, + "learning_rate": 4.1680499317688644e-05, + "loss": 0.2239, "step": 75410 }, { - "epoch": 0.67, - "learning_rate": 1.649445995856229e-05, - "loss": 0.2021, + "epoch": 0.17, + "learning_rate": 4.167938077447932e-05, + "loss": 0.2279, "step": 75420 }, { - "epoch": 0.67, - "learning_rate": 1.648995585983245e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.167826223126999e-05, + "loss": 0.2263, "step": 75430 }, { - "epoch": 0.67, - "learning_rate": 1.6485451761102606e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.167714368806067e-05, + "loss": 0.2218, "step": 75440 }, { - "epoch": 0.67, - "learning_rate": 1.648094766237276e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.167602514485135e-05, + "loss": 0.2237, "step": 75450 }, { - "epoch": 0.67, - "learning_rate": 1.6476443563642914e-05, - "loss": 0.1981, + "epoch": 0.17, + "learning_rate": 4.167490660164202e-05, + "loss": 0.2252, "step": 75460 }, { - "epoch": 0.67, - "learning_rate": 1.647193946491307e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.16737880584327e-05, + "loss": 0.2188, "step": 75470 }, { - "epoch": 0.67, - "learning_rate": 1.646743536618323e-05, - "loss": 0.1949, + "epoch": 0.17, + "learning_rate": 4.1672669515223376e-05, + "loss": 0.2253, "step": 75480 }, { - "epoch": 0.67, - "learning_rate": 1.6462931267453383e-05, - "loss": 0.1991, + "epoch": 0.17, + "learning_rate": 4.1671550972014054e-05, + "loss": 0.2272, "step": 75490 }, { - "epoch": 0.67, - "learning_rate": 1.645842716872354e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.167043242880473e-05, + "loss": 0.228, "step": 75500 }, { - "epoch": 0.67, - "learning_rate": 1.6453923069993695e-05, - "loss": 0.2067, + "epoch": 0.17, + "learning_rate": 4.16693138855954e-05, + "loss": 0.2287, "step": 75510 }, { - "epoch": 0.67, - "learning_rate": 1.644941897126385e-05, - "loss": 0.203, + "epoch": 0.17, + "learning_rate": 4.166819534238608e-05, + "loss": 0.2252, "step": 75520 }, { - "epoch": 0.67, - "learning_rate": 1.6444914872534006e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.166707679917675e-05, + "loss": 0.2261, "step": 75530 }, { - "epoch": 0.67, - "learning_rate": 1.6440410773804164e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.166595825596743e-05, + "loss": 0.2258, "step": 75540 }, { - "epoch": 0.67, - "learning_rate": 1.6435906675074318e-05, - "loss": 0.1952, + "epoch": 0.17, + "learning_rate": 4.166483971275811e-05, + "loss": 0.2307, "step": 75550 }, { - "epoch": 0.67, - "learning_rate": 1.6431402576344472e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.166372116954878e-05, + "loss": 0.2266, "step": 75560 }, { - "epoch": 0.67, - "learning_rate": 1.642689847761463e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.166260262633946e-05, + "loss": 0.2221, "step": 75570 }, { - "epoch": 0.67, - "learning_rate": 1.6422394378884787e-05, - "loss": 0.203, + "epoch": 0.17, + "learning_rate": 4.166148408313013e-05, + "loss": 0.2236, "step": 75580 }, { - "epoch": 0.67, - "learning_rate": 1.641789028015494e-05, - "loss": 0.2033, + "epoch": 0.17, + "learning_rate": 4.166036553992081e-05, + "loss": 0.2267, "step": 75590 }, { - "epoch": 0.67, - "learning_rate": 1.64133861814251e-05, - "loss": 0.1969, + "epoch": 0.17, + "learning_rate": 4.165924699671149e-05, + "loss": 0.2291, "step": 75600 }, { - "epoch": 0.68, - "learning_rate": 1.6408882082695253e-05, - "loss": 0.2074, + "epoch": 0.17, + "learning_rate": 4.165812845350216e-05, + "loss": 0.2261, "step": 75610 }, { - "epoch": 0.68, - "learning_rate": 1.640437798396541e-05, - "loss": 0.2015, + "epoch": 0.17, + "learning_rate": 4.165700991029284e-05, + "loss": 0.224, "step": 75620 }, { - "epoch": 0.68, - "learning_rate": 1.6399873885235564e-05, - "loss": 0.1977, + "epoch": 0.17, + "learning_rate": 4.165589136708351e-05, + "loss": 0.2204, "step": 75630 }, { - "epoch": 0.68, - "learning_rate": 1.6395369786505722e-05, - "loss": 0.2022, + "epoch": 0.17, + "learning_rate": 4.165477282387419e-05, + "loss": 0.2225, "step": 75640 }, { - "epoch": 0.68, - "learning_rate": 1.6390865687775876e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.165365428066487e-05, + "loss": 0.2232, "step": 75650 }, { - "epoch": 0.68, - "learning_rate": 1.638636158904603e-05, - "loss": 0.2031, + "epoch": 0.17, + "learning_rate": 4.165253573745554e-05, + "loss": 0.2235, "step": 75660 }, { - "epoch": 0.68, - "learning_rate": 1.6381857490316188e-05, - "loss": 0.1984, + "epoch": 0.17, + "learning_rate": 4.1651417194246216e-05, + "loss": 0.2247, "step": 75670 }, { - "epoch": 0.68, - "learning_rate": 1.6377353391586345e-05, - "loss": 0.2042, + "epoch": 0.17, + "learning_rate": 4.165029865103689e-05, + "loss": 0.226, "step": 75680 }, { - "epoch": 0.68, - "learning_rate": 1.6372849292856503e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.1649180107827565e-05, + "loss": 0.2271, "step": 75690 }, { - "epoch": 0.68, - "learning_rate": 1.6368345194126657e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.164806156461824e-05, + "loss": 0.2208, "step": 75700 }, { - "epoch": 0.68, - "learning_rate": 1.636384109539681e-05, - "loss": 0.2008, + "epoch": 0.17, + "learning_rate": 4.164694302140892e-05, + "loss": 0.2236, "step": 75710 }, { - "epoch": 0.68, - "learning_rate": 1.635933699666697e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.16458244781996e-05, + "loss": 0.2284, "step": 75720 }, { - "epoch": 0.68, - "learning_rate": 1.6354832897937122e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.164470593499027e-05, + "loss": 0.2233, "step": 75730 }, { - "epoch": 0.68, - "learning_rate": 1.635032879920728e-05, - "loss": 0.1959, + "epoch": 0.17, + "learning_rate": 4.164358739178095e-05, + "loss": 0.2239, "step": 75740 }, { - "epoch": 0.68, - "learning_rate": 1.6345824700477434e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.164246884857162e-05, + "loss": 0.2238, "step": 75750 }, { - "epoch": 0.68, - "learning_rate": 1.634132060174759e-05, - "loss": 0.1968, + "epoch": 0.17, + "learning_rate": 4.16413503053623e-05, + "loss": 0.2192, "step": 75760 }, { - "epoch": 0.68, - "learning_rate": 1.6336816503017746e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.1640231762152975e-05, + "loss": 0.2243, "step": 75770 }, { - "epoch": 0.68, - "learning_rate": 1.6332312404287903e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.1639113218943646e-05, + "loss": 0.2228, "step": 75780 }, { - "epoch": 0.68, - "learning_rate": 1.632780830555806e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.1637994675734324e-05, + "loss": 0.2247, "step": 75790 }, { - "epoch": 0.68, - "learning_rate": 1.6323304206828215e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.1636876132525e-05, + "loss": 0.2225, "step": 75800 }, { - "epoch": 0.68, - "learning_rate": 1.631880010809837e-05, - "loss": 0.1958, + "epoch": 0.17, + "learning_rate": 4.163575758931568e-05, + "loss": 0.2273, "step": 75810 }, { - "epoch": 0.68, - "learning_rate": 1.6314296009368526e-05, - "loss": 0.2012, + "epoch": 0.17, + "learning_rate": 4.163463904610636e-05, + "loss": 0.2226, "step": 75820 }, { - "epoch": 0.68, - "learning_rate": 1.6309791910638684e-05, - "loss": 0.205, + "epoch": 0.17, + "learning_rate": 4.163352050289703e-05, + "loss": 0.227, "step": 75830 }, { - "epoch": 0.68, - "learning_rate": 1.6305287811908838e-05, - "loss": 0.1963, + "epoch": 0.17, + "learning_rate": 4.163240195968771e-05, + "loss": 0.2215, "step": 75840 }, { - "epoch": 0.68, - "learning_rate": 1.6300783713178992e-05, - "loss": 0.1967, + "epoch": 0.17, + "learning_rate": 4.163128341647838e-05, + "loss": 0.2257, "step": 75850 }, { - "epoch": 0.68, - "learning_rate": 1.629627961444915e-05, - "loss": 0.2043, + "epoch": 0.17, + "learning_rate": 4.1630164873269056e-05, + "loss": 0.2196, "step": 75860 }, { - "epoch": 0.68, - "learning_rate": 1.6291775515719304e-05, - "loss": 0.1933, + "epoch": 0.17, + "learning_rate": 4.1629046330059734e-05, + "loss": 0.2261, "step": 75870 }, { - "epoch": 0.68, - "learning_rate": 1.628727141698946e-05, - "loss": 0.2008, + "epoch": 0.17, + "learning_rate": 4.1627927786850405e-05, + "loss": 0.2227, "step": 75880 }, { - "epoch": 0.68, - "learning_rate": 1.628276731825962e-05, - "loss": 0.2003, + "epoch": 0.17, + "learning_rate": 4.162680924364108e-05, + "loss": 0.2243, "step": 75890 }, { - "epoch": 0.68, - "learning_rate": 1.6278263219529773e-05, - "loss": 0.1958, + "epoch": 0.17, + "learning_rate": 4.162569070043176e-05, + "loss": 0.229, "step": 75900 }, { - "epoch": 0.68, - "learning_rate": 1.6273759120799927e-05, - "loss": 0.2091, + "epoch": 0.17, + "learning_rate": 4.162457215722244e-05, + "loss": 0.2265, "step": 75910 }, { - "epoch": 0.68, - "learning_rate": 1.6269255022070084e-05, - "loss": 0.195, + "epoch": 0.17, + "learning_rate": 4.1623453614013116e-05, + "loss": 0.2241, "step": 75920 }, { - "epoch": 0.68, - "learning_rate": 1.6264750923340242e-05, - "loss": 0.2077, + "epoch": 0.17, + "learning_rate": 4.162233507080379e-05, + "loss": 0.2218, "step": 75930 }, { - "epoch": 0.68, - "learning_rate": 1.6260246824610396e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.1621216527594466e-05, + "loss": 0.2166, "step": 75940 }, { - "epoch": 0.68, - "learning_rate": 1.6255742725880553e-05, - "loss": 0.2018, + "epoch": 0.17, + "learning_rate": 4.162009798438514e-05, + "loss": 0.2243, "step": 75950 }, { - "epoch": 0.68, - "learning_rate": 1.6251238627150707e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.1618979441175815e-05, + "loss": 0.2302, "step": 75960 }, { - "epoch": 0.68, - "learning_rate": 1.6247184938293848e-05, - "loss": 0.2025, + "epoch": 0.17, + "learning_rate": 4.161786089796649e-05, + "loss": 0.228, "step": 75970 }, { - "epoch": 0.68, - "learning_rate": 1.6242680839564002e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.1616742354757164e-05, + "loss": 0.234, "step": 75980 }, { - "epoch": 0.68, - "learning_rate": 1.623817674083416e-05, - "loss": 0.204, + "epoch": 0.17, + "learning_rate": 4.161562381154784e-05, + "loss": 0.2243, "step": 75990 }, { - "epoch": 0.68, - "learning_rate": 1.6233672642104317e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.161450526833851e-05, + "loss": 0.2249, "step": 76000 }, { - "epoch": 0.68, - "learning_rate": 1.622916854337447e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.16133867251292e-05, + "loss": 0.2144, "step": 76010 }, { - "epoch": 0.68, - "learning_rate": 1.622466444464463e-05, - "loss": 0.1944, + "epoch": 0.17, + "learning_rate": 4.1612268181919875e-05, + "loss": 0.2229, "step": 76020 }, { - "epoch": 0.68, - "learning_rate": 1.6220160345914783e-05, - "loss": 0.1964, + "epoch": 0.17, + "learning_rate": 4.1611149638710547e-05, + "loss": 0.221, "step": 76030 }, { - "epoch": 0.68, - "learning_rate": 1.6215656247184937e-05, - "loss": 0.2014, + "epoch": 0.17, + "learning_rate": 4.1610031095501225e-05, + "loss": 0.2252, "step": 76040 }, { - "epoch": 0.68, - "learning_rate": 1.6211152148455094e-05, - "loss": 0.2019, + "epoch": 0.17, + "learning_rate": 4.1608912552291896e-05, + "loss": 0.2282, "step": 76050 }, { - "epoch": 0.68, - "learning_rate": 1.6206648049725252e-05, - "loss": 0.1961, + "epoch": 0.17, + "learning_rate": 4.1607794009082574e-05, + "loss": 0.2208, "step": 76060 }, { - "epoch": 0.68, - "learning_rate": 1.620214395099541e-05, - "loss": 0.1927, + "epoch": 0.17, + "learning_rate": 4.1606675465873245e-05, + "loss": 0.2284, "step": 76070 }, { - "epoch": 0.68, - "learning_rate": 1.619763985226556e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.160555692266392e-05, + "loss": 0.2251, "step": 76080 }, { - "epoch": 0.68, - "learning_rate": 1.6193135753535717e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.16044383794546e-05, + "loss": 0.2292, "step": 76090 }, { - "epoch": 0.68, - "learning_rate": 1.6188631654805875e-05, - "loss": 0.2077, + "epoch": 0.17, + "learning_rate": 4.160331983624527e-05, + "loss": 0.2227, "step": 76100 }, { - "epoch": 0.68, - "learning_rate": 1.618412755607603e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.160220129303595e-05, + "loss": 0.2272, "step": 76110 }, { - "epoch": 0.68, - "learning_rate": 1.6179623457346187e-05, - "loss": 0.2027, + "epoch": 0.17, + "learning_rate": 4.160108274982663e-05, + "loss": 0.2277, "step": 76120 }, { - "epoch": 0.68, - "learning_rate": 1.617511935861634e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.1599964206617306e-05, + "loss": 0.2233, "step": 76130 }, { - "epoch": 0.68, - "learning_rate": 1.6170615259886498e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.1598845663407983e-05, + "loss": 0.2206, "step": 76140 }, { - "epoch": 0.68, - "learning_rate": 1.6166111161156652e-05, - "loss": 0.1977, + "epoch": 0.17, + "learning_rate": 4.1597727120198655e-05, + "loss": 0.2207, "step": 76150 }, { - "epoch": 0.68, - "learning_rate": 1.616160706242681e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.159660857698933e-05, + "loss": 0.2276, "step": 76160 }, { - "epoch": 0.68, - "learning_rate": 1.6157102963696967e-05, - "loss": 0.2014, + "epoch": 0.17, + "learning_rate": 4.1595490033780004e-05, + "loss": 0.2209, "step": 76170 }, { - "epoch": 0.68, - "learning_rate": 1.6152598864967118e-05, - "loss": 0.2044, + "epoch": 0.17, + "learning_rate": 4.159437149057068e-05, + "loss": 0.2263, "step": 76180 }, { - "epoch": 0.68, - "learning_rate": 1.6148094766237275e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.159325294736136e-05, + "loss": 0.2205, "step": 76190 }, { - "epoch": 0.68, - "learning_rate": 1.6143590667507433e-05, - "loss": 0.2039, + "epoch": 0.17, + "learning_rate": 4.159213440415203e-05, + "loss": 0.2234, "step": 76200 }, { - "epoch": 0.68, - "learning_rate": 1.613908656877759e-05, - "loss": 0.2019, + "epoch": 0.17, + "learning_rate": 4.159101586094271e-05, + "loss": 0.2225, "step": 76210 }, { - "epoch": 0.68, - "learning_rate": 1.6134582470047745e-05, - "loss": 0.195, + "epoch": 0.17, + "learning_rate": 4.1589897317733387e-05, + "loss": 0.2238, "step": 76220 }, { - "epoch": 0.68, - "learning_rate": 1.61300783713179e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.1588778774524064e-05, + "loss": 0.2218, "step": 76230 }, { - "epoch": 0.68, - "learning_rate": 1.6125574272588056e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.158766023131474e-05, + "loss": 0.2219, "step": 76240 }, { - "epoch": 0.68, - "learning_rate": 1.612107017385821e-05, - "loss": 0.1964, + "epoch": 0.17, + "learning_rate": 4.1586541688105414e-05, + "loss": 0.2203, "step": 76250 }, { - "epoch": 0.68, - "learning_rate": 1.6116566075128368e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.158542314489609e-05, + "loss": 0.22, "step": 76260 }, { - "epoch": 0.68, - "learning_rate": 1.6112061976398525e-05, - "loss": 0.1952, + "epoch": 0.17, + "learning_rate": 4.158430460168676e-05, + "loss": 0.2258, "step": 76270 }, { - "epoch": 0.68, - "learning_rate": 1.610755787766868e-05, - "loss": 0.1939, + "epoch": 0.17, + "learning_rate": 4.158318605847744e-05, + "loss": 0.2226, "step": 76280 }, { - "epoch": 0.68, - "learning_rate": 1.6103053778938833e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.158206751526812e-05, + "loss": 0.2238, "step": 76290 }, { - "epoch": 0.68, - "learning_rate": 1.609854968020899e-05, - "loss": 0.2015, + "epoch": 0.17, + "learning_rate": 4.158094897205879e-05, + "loss": 0.2183, "step": 76300 }, { - "epoch": 0.68, - "learning_rate": 1.609404558147915e-05, - "loss": 0.2082, + "epoch": 0.17, + "learning_rate": 4.157983042884947e-05, + "loss": 0.2222, "step": 76310 }, { - "epoch": 0.68, - "learning_rate": 1.6089541482749302e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.1578711885640145e-05, + "loss": 0.2289, "step": 76320 }, { - "epoch": 0.68, - "learning_rate": 1.6085037384019457e-05, - "loss": 0.2013, + "epoch": 0.17, + "learning_rate": 4.1577593342430823e-05, + "loss": 0.2255, "step": 76330 }, { - "epoch": 0.68, - "learning_rate": 1.6080533285289614e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.15764747992215e-05, + "loss": 0.2211, "step": 76340 }, { - "epoch": 0.68, - "learning_rate": 1.607602918655977e-05, - "loss": 0.197, + "epoch": 0.17, + "learning_rate": 4.157535625601217e-05, + "loss": 0.226, "step": 76350 }, { - "epoch": 0.68, - "learning_rate": 1.6071525087829926e-05, - "loss": 0.2021, + "epoch": 0.17, + "learning_rate": 4.157423771280285e-05, + "loss": 0.2268, "step": 76360 }, { - "epoch": 0.68, - "learning_rate": 1.6067020989100083e-05, - "loss": 0.2006, + "epoch": 0.17, + "learning_rate": 4.157311916959352e-05, + "loss": 0.2209, "step": 76370 }, { - "epoch": 0.68, - "learning_rate": 1.6062516890370237e-05, - "loss": 0.2003, + "epoch": 0.17, + "learning_rate": 4.15720006263842e-05, + "loss": 0.2214, "step": 76380 }, { - "epoch": 0.68, - "learning_rate": 1.605801279164039e-05, - "loss": 0.1924, + "epoch": 0.17, + "learning_rate": 4.157088208317487e-05, + "loss": 0.2221, "step": 76390 }, { - "epoch": 0.68, - "learning_rate": 1.605350869291055e-05, - "loss": 0.1976, + "epoch": 0.17, + "learning_rate": 4.156976353996555e-05, + "loss": 0.2275, "step": 76400 }, { - "epoch": 0.68, - "learning_rate": 1.6049004594180706e-05, - "loss": 0.1982, + "epoch": 0.17, + "learning_rate": 4.1568644996756227e-05, + "loss": 0.2207, "step": 76410 }, { - "epoch": 0.68, - "learning_rate": 1.604450049545086e-05, - "loss": 0.2025, + "epoch": 0.17, + "learning_rate": 4.1567526453546904e-05, + "loss": 0.2237, "step": 76420 }, { - "epoch": 0.68, - "learning_rate": 1.6039996396721015e-05, - "loss": 0.1956, + "epoch": 0.17, + "learning_rate": 4.156640791033758e-05, + "loss": 0.224, "step": 76430 }, { - "epoch": 0.68, - "learning_rate": 1.6035492297991172e-05, - "loss": 0.1958, + "epoch": 0.17, + "learning_rate": 4.1565289367128254e-05, + "loss": 0.2234, "step": 76440 }, { - "epoch": 0.68, - "learning_rate": 1.603098819926133e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.156417082391893e-05, + "loss": 0.2228, "step": 76450 }, { - "epoch": 0.68, - "learning_rate": 1.6026484100531484e-05, - "loss": 0.1984, + "epoch": 0.17, + "learning_rate": 4.156305228070961e-05, + "loss": 0.2319, "step": 76460 }, { - "epoch": 0.68, - "learning_rate": 1.602198000180164e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.156193373750028e-05, + "loss": 0.216, "step": 76470 }, { - "epoch": 0.68, - "learning_rate": 1.6017475903071795e-05, - "loss": 0.2057, + "epoch": 0.17, + "learning_rate": 4.156081519429096e-05, + "loss": 0.2269, "step": 76480 }, { - "epoch": 0.68, - "learning_rate": 1.6012971804341953e-05, - "loss": 0.1972, + "epoch": 0.17, + "learning_rate": 4.155969665108163e-05, + "loss": 0.2269, "step": 76490 }, { - "epoch": 0.68, - "learning_rate": 1.6008467705612107e-05, - "loss": 0.2013, + "epoch": 0.17, + "learning_rate": 4.155857810787231e-05, + "loss": 0.2237, "step": 76500 }, { - "epoch": 0.68, - "learning_rate": 1.6003963606882264e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.1557459564662985e-05, + "loss": 0.225, "step": 76510 }, { - "epoch": 0.68, - "learning_rate": 1.599945950815242e-05, - "loss": 0.1988, + "epoch": 0.17, + "learning_rate": 4.155634102145366e-05, + "loss": 0.2217, "step": 76520 }, { - "epoch": 0.68, - "learning_rate": 1.5994955409422573e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.1555222478244335e-05, + "loss": 0.221, "step": 76530 }, { - "epoch": 0.68, - "learning_rate": 1.599045131069273e-05, - "loss": 0.2057, + "epoch": 0.17, + "learning_rate": 4.155410393503501e-05, + "loss": 0.2255, "step": 76540 }, { - "epoch": 0.68, - "learning_rate": 1.5985947211962888e-05, - "loss": 0.1912, + "epoch": 0.17, + "learning_rate": 4.155298539182569e-05, + "loss": 0.2191, "step": 76550 }, { - "epoch": 0.68, - "learning_rate": 1.5981443113233045e-05, - "loss": 0.1931, + "epoch": 0.17, + "learning_rate": 4.155186684861637e-05, + "loss": 0.224, "step": 76560 }, { - "epoch": 0.68, - "learning_rate": 1.59769390145032e-05, - "loss": 0.1919, + "epoch": 0.17, + "learning_rate": 4.155074830540704e-05, + "loss": 0.2216, "step": 76570 }, { - "epoch": 0.68, - "learning_rate": 1.5972434915773353e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.154962976219772e-05, + "loss": 0.2255, "step": 76580 }, { - "epoch": 0.68, - "learning_rate": 1.596793081704351e-05, - "loss": 0.1992, + "epoch": 0.17, + "learning_rate": 4.154851121898839e-05, + "loss": 0.2179, "step": 76590 }, { - "epoch": 0.68, - "learning_rate": 1.5963426718313665e-05, - "loss": 0.1977, + "epoch": 0.17, + "learning_rate": 4.1547392675779066e-05, + "loss": 0.2242, "step": 76600 }, { - "epoch": 0.68, - "learning_rate": 1.5958922619583822e-05, - "loss": 0.2, + "epoch": 0.17, + "learning_rate": 4.1546274132569744e-05, + "loss": 0.221, "step": 76610 }, { - "epoch": 0.68, - "learning_rate": 1.595441852085398e-05, - "loss": 0.2021, + "epoch": 0.17, + "learning_rate": 4.1545155589360416e-05, + "loss": 0.2303, "step": 76620 }, { - "epoch": 0.68, - "learning_rate": 1.5949914422124134e-05, - "loss": 0.2066, + "epoch": 0.17, + "learning_rate": 4.1544037046151093e-05, + "loss": 0.2211, "step": 76630 }, { - "epoch": 0.68, - "learning_rate": 1.5945410323394288e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.154291850294177e-05, + "loss": 0.2241, "step": 76640 }, { - "epoch": 0.68, - "learning_rate": 1.5940906224664446e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.154179995973245e-05, + "loss": 0.2215, "step": 76650 }, { - "epoch": 0.68, - "learning_rate": 1.5936402125934603e-05, - "loss": 0.1974, + "epoch": 0.17, + "learning_rate": 4.154068141652312e-05, + "loss": 0.2219, "step": 76660 }, { - "epoch": 0.68, - "learning_rate": 1.5931898027204757e-05, - "loss": 0.2039, + "epoch": 0.17, + "learning_rate": 4.15395628733138e-05, + "loss": 0.2195, "step": 76670 }, { - "epoch": 0.68, - "learning_rate": 1.592739392847491e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.1538444330104476e-05, + "loss": 0.2266, "step": 76680 }, { - "epoch": 0.68, - "learning_rate": 1.592288982974507e-05, - "loss": 0.2045, + "epoch": 0.17, + "learning_rate": 4.153732578689515e-05, + "loss": 0.2196, "step": 76690 }, { - "epoch": 0.68, - "learning_rate": 1.5918385731015226e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.1536207243685825e-05, + "loss": 0.2254, "step": 76700 }, { - "epoch": 0.68, - "learning_rate": 1.591388163228538e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.1535088700476497e-05, + "loss": 0.2266, "step": 76710 }, { - "epoch": 0.68, - "learning_rate": 1.5909377533555538e-05, - "loss": 0.1955, + "epoch": 0.17, + "learning_rate": 4.1533970157267175e-05, + "loss": 0.2206, "step": 76720 }, { - "epoch": 0.69, - "learning_rate": 1.5904873434825692e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.153285161405785e-05, + "loss": 0.2156, "step": 76730 }, { - "epoch": 0.69, - "learning_rate": 1.5900369336095846e-05, - "loss": 0.1938, + "epoch": 0.17, + "learning_rate": 4.153173307084853e-05, + "loss": 0.2264, "step": 76740 }, { - "epoch": 0.69, - "learning_rate": 1.5895865237366003e-05, - "loss": 0.1919, + "epoch": 0.17, + "learning_rate": 4.153061452763921e-05, + "loss": 0.2282, "step": 76750 }, { - "epoch": 0.69, - "learning_rate": 1.589136113863616e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.152949598442988e-05, + "loss": 0.2221, "step": 76760 }, { - "epoch": 0.69, - "learning_rate": 1.5886857039906315e-05, - "loss": 0.2, + "epoch": 0.17, + "learning_rate": 4.152837744122056e-05, + "loss": 0.2186, "step": 76770 }, { - "epoch": 0.69, - "learning_rate": 1.588235294117647e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.1527258898011235e-05, + "loss": 0.2182, "step": 76780 }, { - "epoch": 0.69, - "learning_rate": 1.5877848842446627e-05, - "loss": 0.2047, + "epoch": 0.17, + "learning_rate": 4.1526140354801906e-05, + "loss": 0.2206, "step": 76790 }, { - "epoch": 0.69, - "learning_rate": 1.5873344743716784e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.1525021811592584e-05, + "loss": 0.2195, "step": 76800 }, { - "epoch": 0.69, - "learning_rate": 1.5868840644986938e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.1523903268383256e-05, + "loss": 0.2285, "step": 76810 }, { - "epoch": 0.69, - "learning_rate": 1.5864336546257096e-05, - "loss": 0.2064, + "epoch": 0.17, + "learning_rate": 4.1522784725173933e-05, + "loss": 0.2238, "step": 76820 }, { - "epoch": 0.69, - "learning_rate": 1.585983244752725e-05, - "loss": 0.1948, + "epoch": 0.17, + "learning_rate": 4.152166618196461e-05, + "loss": 0.2197, "step": 76830 }, { - "epoch": 0.69, - "learning_rate": 1.5855328348797407e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.152054763875529e-05, + "loss": 0.2288, "step": 76840 }, { - "epoch": 0.69, - "learning_rate": 1.585082425006756e-05, - "loss": 0.1926, + "epoch": 0.17, + "learning_rate": 4.151942909554597e-05, + "loss": 0.2195, "step": 76850 }, { - "epoch": 0.69, - "learning_rate": 1.584632015133772e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.151831055233664e-05, + "loss": 0.2179, "step": 76860 }, { - "epoch": 0.69, - "learning_rate": 1.5841816052607873e-05, - "loss": 0.202, + "epoch": 0.17, + "learning_rate": 4.1517192009127316e-05, + "loss": 0.2217, "step": 76870 }, { - "epoch": 0.69, - "learning_rate": 1.5837311953878027e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.1516073465917994e-05, + "loss": 0.2261, "step": 76880 }, { - "epoch": 0.69, - "learning_rate": 1.5832807855148185e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.1514954922708665e-05, + "loss": 0.2234, "step": 76890 }, { - "epoch": 0.69, - "learning_rate": 1.5828303756418342e-05, - "loss": 0.2003, + "epoch": 0.17, + "learning_rate": 4.151383637949934e-05, + "loss": 0.2247, "step": 76900 }, { - "epoch": 0.69, - "learning_rate": 1.58237996576885e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.1512717836290014e-05, + "loss": 0.2241, "step": 76910 }, { - "epoch": 0.69, - "learning_rate": 1.5819295558958654e-05, - "loss": 0.2013, + "epoch": 0.17, + "learning_rate": 4.151159929308069e-05, + "loss": 0.223, "step": 76920 }, { - "epoch": 0.69, - "learning_rate": 1.5814791460228808e-05, - "loss": 0.2059, + "epoch": 0.17, + "learning_rate": 4.151048074987137e-05, + "loss": 0.226, "step": 76930 }, { - "epoch": 0.69, - "learning_rate": 1.5810287361498965e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.150936220666204e-05, + "loss": 0.2292, "step": 76940 }, { - "epoch": 0.69, - "learning_rate": 1.580578326276912e-05, - "loss": 0.1959, + "epoch": 0.17, + "learning_rate": 4.150824366345272e-05, + "loss": 0.2226, "step": 76950 }, { - "epoch": 0.69, - "learning_rate": 1.5801279164039277e-05, - "loss": 0.1974, + "epoch": 0.17, + "learning_rate": 4.15071251202434e-05, + "loss": 0.2215, "step": 76960 }, { - "epoch": 0.69, - "learning_rate": 1.579677506530943e-05, - "loss": 0.2001, + "epoch": 0.17, + "learning_rate": 4.1506006577034075e-05, + "loss": 0.222, "step": 76970 }, { - "epoch": 0.69, - "learning_rate": 1.579227096657959e-05, - "loss": 0.1983, + "epoch": 0.17, + "learning_rate": 4.1504888033824746e-05, + "loss": 0.2238, "step": 76980 }, { - "epoch": 0.69, - "learning_rate": 1.5787766867849743e-05, - "loss": 0.2009, + "epoch": 0.17, + "learning_rate": 4.1503769490615424e-05, + "loss": 0.2207, "step": 76990 }, { - "epoch": 0.69, - "learning_rate": 1.57832627691199e-05, - "loss": 0.2021, + "epoch": 0.17, + "learning_rate": 4.15026509474061e-05, + "loss": 0.225, "step": 77000 }, { - "epoch": 0.69, - "learning_rate": 1.5778758670390058e-05, - "loss": 0.1965, + "epoch": 0.17, + "learning_rate": 4.1501532404196773e-05, + "loss": 0.2253, "step": 77010 }, { - "epoch": 0.69, - "learning_rate": 1.5774254571660212e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.150041386098745e-05, + "loss": 0.2288, "step": 77020 }, { - "epoch": 0.69, - "learning_rate": 1.5769750472930366e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.149929531777812e-05, + "loss": 0.2252, "step": 77030 }, { - "epoch": 0.69, - "learning_rate": 1.5765246374200523e-05, - "loss": 0.2015, + "epoch": 0.17, + "learning_rate": 4.14981767745688e-05, + "loss": 0.2307, "step": 77040 }, { - "epoch": 0.69, - "learning_rate": 1.576074227547068e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.149705823135948e-05, + "loss": 0.2244, "step": 77050 }, { - "epoch": 0.69, - "learning_rate": 1.5756238176740835e-05, - "loss": 0.1964, + "epoch": 0.17, + "learning_rate": 4.1495939688150156e-05, + "loss": 0.2203, "step": 77060 }, { - "epoch": 0.69, - "learning_rate": 1.575173407801099e-05, - "loss": 0.1957, + "epoch": 0.17, + "learning_rate": 4.1494821144940834e-05, + "loss": 0.2258, "step": 77070 }, { - "epoch": 0.69, - "learning_rate": 1.5747229979281147e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.1493702601731505e-05, + "loss": 0.2205, "step": 77080 }, { - "epoch": 0.69, - "learning_rate": 1.57427258805513e-05, - "loss": 0.1976, + "epoch": 0.17, + "learning_rate": 4.149258405852218e-05, + "loss": 0.2203, "step": 77090 }, { - "epoch": 0.69, - "learning_rate": 1.5738221781821458e-05, - "loss": 0.2017, + "epoch": 0.17, + "learning_rate": 4.149146551531286e-05, + "loss": 0.2205, "step": 77100 }, { - "epoch": 0.69, - "learning_rate": 1.5733717683091616e-05, - "loss": 0.2011, + "epoch": 0.17, + "learning_rate": 4.149034697210353e-05, + "loss": 0.2286, "step": 77110 }, { - "epoch": 0.69, - "learning_rate": 1.572921358436177e-05, - "loss": 0.2026, + "epoch": 0.17, + "learning_rate": 4.148922842889421e-05, + "loss": 0.224, "step": 77120 }, { - "epoch": 0.69, - "learning_rate": 1.5724709485631924e-05, - "loss": 0.2014, + "epoch": 0.17, + "learning_rate": 4.148810988568488e-05, + "loss": 0.2207, "step": 77130 }, { - "epoch": 0.69, - "learning_rate": 1.572020538690208e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.148699134247556e-05, + "loss": 0.2278, "step": 77140 }, { - "epoch": 0.69, - "learning_rate": 1.571570128817224e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.148587279926624e-05, + "loss": 0.22, "step": 77150 }, { - "epoch": 0.69, - "learning_rate": 1.5711197189442393e-05, - "loss": 0.1971, + "epoch": 0.17, + "learning_rate": 4.1484754256056915e-05, + "loss": 0.2212, "step": 77160 }, { - "epoch": 0.69, - "learning_rate": 1.5706693090712547e-05, - "loss": 0.1931, + "epoch": 0.17, + "learning_rate": 4.148363571284759e-05, + "loss": 0.2274, "step": 77170 }, { - "epoch": 0.69, - "learning_rate": 1.5702188991982705e-05, - "loss": 0.1997, + "epoch": 0.17, + "learning_rate": 4.1482517169638264e-05, + "loss": 0.2306, "step": 77180 }, { - "epoch": 0.69, - "learning_rate": 1.5697684893252862e-05, - "loss": 0.1996, + "epoch": 0.17, + "learning_rate": 4.148139862642894e-05, + "loss": 0.2232, "step": 77190 }, { - "epoch": 0.69, - "learning_rate": 1.5693180794523016e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.148028008321962e-05, + "loss": 0.2234, "step": 77200 }, { - "epoch": 0.69, - "learning_rate": 1.5688676695793174e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.147916154001029e-05, + "loss": 0.2187, "step": 77210 }, { - "epoch": 0.69, - "learning_rate": 1.5684172597063328e-05, - "loss": 0.2022, + "epoch": 0.17, + "learning_rate": 4.147804299680097e-05, + "loss": 0.2205, "step": 77220 }, { - "epoch": 0.69, - "learning_rate": 1.5679668498333482e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.147692445359164e-05, + "loss": 0.2243, "step": 77230 }, { - "epoch": 0.69, - "learning_rate": 1.567516439960364e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.147580591038232e-05, + "loss": 0.2258, "step": 77240 }, { - "epoch": 0.69, - "learning_rate": 1.5670660300873797e-05, - "loss": 0.1967, + "epoch": 0.17, + "learning_rate": 4.1474687367172996e-05, + "loss": 0.2218, "step": 77250 }, { - "epoch": 0.69, - "learning_rate": 1.5666156202143954e-05, - "loss": 0.2023, + "epoch": 0.17, + "learning_rate": 4.1473568823963674e-05, + "loss": 0.2286, "step": 77260 }, { - "epoch": 0.69, - "learning_rate": 1.566165210341411e-05, - "loss": 0.1935, + "epoch": 0.17, + "learning_rate": 4.147245028075435e-05, + "loss": 0.2246, "step": 77270 }, { - "epoch": 0.69, - "learning_rate": 1.5657148004684262e-05, - "loss": 0.1937, + "epoch": 0.17, + "learning_rate": 4.147133173754502e-05, + "loss": 0.223, "step": 77280 }, { - "epoch": 0.69, - "learning_rate": 1.565264390595442e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.14702131943357e-05, + "loss": 0.2217, "step": 77290 }, { - "epoch": 0.69, - "learning_rate": 1.5648139807224574e-05, - "loss": 0.2066, + "epoch": 0.17, + "learning_rate": 4.146909465112637e-05, + "loss": 0.2246, "step": 77300 }, { - "epoch": 0.69, - "learning_rate": 1.564363570849473e-05, - "loss": 0.1945, + "epoch": 0.17, + "learning_rate": 4.146797610791705e-05, + "loss": 0.2242, "step": 77310 }, { - "epoch": 0.69, - "learning_rate": 1.5639131609764886e-05, - "loss": 0.2001, + "epoch": 0.17, + "learning_rate": 4.146685756470773e-05, + "loss": 0.2226, "step": 77320 }, { - "epoch": 0.69, - "learning_rate": 1.5634627511035043e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.14657390214984e-05, + "loss": 0.2239, "step": 77330 }, { - "epoch": 0.69, - "learning_rate": 1.5630123412305197e-05, - "loss": 0.1957, + "epoch": 0.17, + "learning_rate": 4.146462047828908e-05, + "loss": 0.2198, "step": 77340 }, { - "epoch": 0.69, - "learning_rate": 1.5625619313575355e-05, - "loss": 0.206, + "epoch": 0.17, + "learning_rate": 4.146350193507975e-05, + "loss": 0.2182, "step": 77350 }, { - "epoch": 0.69, - "learning_rate": 1.5621115214845512e-05, - "loss": 0.2038, + "epoch": 0.17, + "learning_rate": 4.1462383391870426e-05, + "loss": 0.2287, "step": 77360 }, { - "epoch": 0.69, - "learning_rate": 1.5616611116115666e-05, - "loss": 0.1942, + "epoch": 0.17, + "learning_rate": 4.146126484866111e-05, + "loss": 0.2281, "step": 77370 }, { - "epoch": 0.69, - "learning_rate": 1.561210701738582e-05, - "loss": 0.1956, + "epoch": 0.17, + "learning_rate": 4.146014630545178e-05, + "loss": 0.2234, "step": 77380 }, { - "epoch": 0.69, - "learning_rate": 1.5607602918655978e-05, - "loss": 0.1972, + "epoch": 0.17, + "learning_rate": 4.145902776224246e-05, + "loss": 0.2257, "step": 77390 }, { - "epoch": 0.69, - "learning_rate": 1.5603098819926135e-05, - "loss": 0.2008, + "epoch": 0.17, + "learning_rate": 4.145790921903313e-05, + "loss": 0.2209, "step": 77400 }, { - "epoch": 0.69, - "learning_rate": 1.559859472119629e-05, - "loss": 0.1933, + "epoch": 0.17, + "learning_rate": 4.145679067582381e-05, + "loss": 0.2167, "step": 77410 }, { - "epoch": 0.69, - "learning_rate": 1.5594090622466444e-05, - "loss": 0.2019, + "epoch": 0.17, + "learning_rate": 4.145567213261449e-05, + "loss": 0.2266, "step": 77420 }, { - "epoch": 0.69, - "learning_rate": 1.55895865237366e-05, - "loss": 0.2035, + "epoch": 0.17, + "learning_rate": 4.145455358940516e-05, + "loss": 0.2255, "step": 77430 }, { - "epoch": 0.69, - "learning_rate": 1.5585082425006755e-05, - "loss": 0.1952, + "epoch": 0.17, + "learning_rate": 4.1453546900516774e-05, + "loss": 0.222, "step": 77440 }, { - "epoch": 0.69, - "learning_rate": 1.5580578326276913e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.1452428357307445e-05, + "loss": 0.2182, "step": 77450 }, { - "epoch": 0.69, - "learning_rate": 1.557607422754707e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.145130981409812e-05, + "loss": 0.2201, "step": 77460 }, { - "epoch": 0.69, - "learning_rate": 1.5571570128817224e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.1450191270888794e-05, + "loss": 0.2252, "step": 77470 }, { - "epoch": 0.69, - "learning_rate": 1.556706603008738e-05, - "loss": 0.1992, + "epoch": 0.17, + "learning_rate": 4.144907272767947e-05, + "loss": 0.2226, "step": 77480 }, { - "epoch": 0.69, - "learning_rate": 1.5562561931357536e-05, - "loss": 0.196, + "epoch": 0.17, + "learning_rate": 4.144795418447015e-05, + "loss": 0.2212, "step": 77490 }, { - "epoch": 0.69, - "learning_rate": 1.5558057832627693e-05, - "loss": 0.1959, + "epoch": 0.17, + "learning_rate": 4.144683564126082e-05, + "loss": 0.2195, "step": 77500 }, { - "epoch": 0.69, - "learning_rate": 1.5553553733897848e-05, - "loss": 0.1958, + "epoch": 0.17, + "learning_rate": 4.14457170980515e-05, + "loss": 0.2197, "step": 77510 }, { - "epoch": 0.69, - "learning_rate": 1.5549049635168e-05, - "loss": 0.2019, + "epoch": 0.17, + "learning_rate": 4.144459855484217e-05, + "loss": 0.2263, "step": 77520 }, { - "epoch": 0.69, - "learning_rate": 1.554454553643816e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.144348001163285e-05, + "loss": 0.224, "step": 77530 }, { - "epoch": 0.69, - "learning_rate": 1.5540041437708317e-05, - "loss": 0.2013, + "epoch": 0.17, + "learning_rate": 4.144236146842353e-05, + "loss": 0.2249, "step": 77540 }, { - "epoch": 0.69, - "learning_rate": 1.553553733897847e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.1441242925214204e-05, + "loss": 0.2215, "step": 77550 }, { - "epoch": 0.69, - "learning_rate": 1.5531033240248628e-05, - "loss": 0.1995, + "epoch": 0.17, + "learning_rate": 4.144012438200488e-05, + "loss": 0.2214, "step": 77560 }, { - "epoch": 0.69, - "learning_rate": 1.5526529141518782e-05, - "loss": 0.1996, + "epoch": 0.17, + "learning_rate": 4.143900583879555e-05, + "loss": 0.2174, "step": 77570 }, { - "epoch": 0.69, - "learning_rate": 1.5522025042788936e-05, - "loss": 0.1966, + "epoch": 0.17, + "learning_rate": 4.143788729558623e-05, + "loss": 0.2283, "step": 77580 }, { - "epoch": 0.69, - "learning_rate": 1.5517520944059094e-05, - "loss": 0.1953, + "epoch": 0.17, + "learning_rate": 4.143676875237691e-05, + "loss": 0.2228, "step": 77590 }, { - "epoch": 0.69, - "learning_rate": 1.551301684532925e-05, - "loss": 0.1944, + "epoch": 0.17, + "learning_rate": 4.143565020916758e-05, + "loss": 0.2235, "step": 77600 }, { - "epoch": 0.69, - "learning_rate": 1.550851274659941e-05, - "loss": 0.1956, + "epoch": 0.17, + "learning_rate": 4.143453166595826e-05, + "loss": 0.2234, "step": 77610 }, { - "epoch": 0.69, - "learning_rate": 1.550400864786956e-05, - "loss": 0.1976, + "epoch": 0.17, + "learning_rate": 4.143341312274893e-05, + "loss": 0.2201, "step": 77620 }, { - "epoch": 0.69, - "learning_rate": 1.5499504549139717e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.143229457953961e-05, + "loss": 0.2232, "step": 77630 }, { - "epoch": 0.69, - "learning_rate": 1.5495000450409875e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.1431176036330285e-05, + "loss": 0.2193, "step": 77640 }, { - "epoch": 0.69, - "learning_rate": 1.549049635168003e-05, - "loss": 0.1941, + "epoch": 0.17, + "learning_rate": 4.143005749312096e-05, + "loss": 0.2259, "step": 77650 }, { - "epoch": 0.69, - "learning_rate": 1.5485992252950186e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.142893894991164e-05, + "loss": 0.217, "step": 77660 }, { - "epoch": 0.69, - "learning_rate": 1.548148815422034e-05, - "loss": 0.1965, + "epoch": 0.17, + "learning_rate": 4.142782040670231e-05, + "loss": 0.2191, "step": 77670 }, { - "epoch": 0.69, - "learning_rate": 1.5476984055490498e-05, - "loss": 0.1957, + "epoch": 0.17, + "learning_rate": 4.142670186349299e-05, + "loss": 0.2173, "step": 77680 }, { - "epoch": 0.69, - "learning_rate": 1.5472479956760652e-05, - "loss": 0.1963, + "epoch": 0.17, + "learning_rate": 4.142558332028366e-05, + "loss": 0.2232, "step": 77690 }, { - "epoch": 0.69, - "learning_rate": 1.546797585803081e-05, - "loss": 0.2033, + "epoch": 0.17, + "learning_rate": 4.142446477707434e-05, + "loss": 0.2245, "step": 77700 }, { - "epoch": 0.69, - "learning_rate": 1.5463471759300967e-05, - "loss": 0.2018, + "epoch": 0.17, + "learning_rate": 4.142334623386502e-05, + "loss": 0.2239, "step": 77710 }, { - "epoch": 0.69, - "learning_rate": 1.5458967660571118e-05, - "loss": 0.2016, + "epoch": 0.17, + "learning_rate": 4.142222769065569e-05, + "loss": 0.2251, "step": 77720 }, { - "epoch": 0.69, - "learning_rate": 1.5454463561841275e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.1421109147446366e-05, + "loss": 0.2182, "step": 77730 }, { - "epoch": 0.69, - "learning_rate": 1.5449959463111433e-05, - "loss": 0.1911, + "epoch": 0.17, + "learning_rate": 4.1419990604237044e-05, + "loss": 0.2182, "step": 77740 }, { - "epoch": 0.69, - "learning_rate": 1.544545536438159e-05, - "loss": 0.1987, + "epoch": 0.17, + "learning_rate": 4.141887206102772e-05, + "loss": 0.2201, "step": 77750 }, { - "epoch": 0.69, - "learning_rate": 1.5440951265651744e-05, - "loss": 0.1979, + "epoch": 0.17, + "learning_rate": 4.14177535178184e-05, + "loss": 0.2228, "step": 77760 }, { - "epoch": 0.69, - "learning_rate": 1.5436447166921898e-05, - "loss": 0.2005, + "epoch": 0.17, + "learning_rate": 4.141663497460907e-05, + "loss": 0.2231, "step": 77770 }, { - "epoch": 0.69, - "learning_rate": 1.5431943068192056e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.141551643139975e-05, + "loss": 0.2281, "step": 77780 }, { - "epoch": 0.69, - "learning_rate": 1.542743896946221e-05, - "loss": 0.1935, + "epoch": 0.17, + "learning_rate": 4.141439788819042e-05, + "loss": 0.219, "step": 77790 }, { - "epoch": 0.69, - "learning_rate": 1.5422934870732367e-05, - "loss": 0.1955, + "epoch": 0.17, + "learning_rate": 4.14132793449811e-05, + "loss": 0.217, "step": 77800 }, { - "epoch": 0.69, - "learning_rate": 1.5418430772002525e-05, - "loss": 0.199, + "epoch": 0.17, + "learning_rate": 4.1412160801771776e-05, + "loss": 0.2267, "step": 77810 }, { - "epoch": 0.69, - "learning_rate": 1.541392667327268e-05, - "loss": 0.1999, + "epoch": 0.17, + "learning_rate": 4.141104225856245e-05, + "loss": 0.2251, "step": 77820 }, { - "epoch": 0.69, - "learning_rate": 1.5409422574542833e-05, - "loss": 0.1914, + "epoch": 0.17, + "learning_rate": 4.1409923715353125e-05, + "loss": 0.2164, "step": 77830 }, { - "epoch": 0.69, - "learning_rate": 1.540491847581299e-05, - "loss": 0.1949, + "epoch": 0.17, + "learning_rate": 4.14088051721438e-05, + "loss": 0.2238, "step": 77840 }, { - "epoch": 0.7, - "learning_rate": 1.5400414377083148e-05, - "loss": 0.2007, + "epoch": 0.17, + "learning_rate": 4.140768662893448e-05, + "loss": 0.2203, "step": 77850 }, { - "epoch": 0.7, - "learning_rate": 1.5395910278353302e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.140656808572516e-05, + "loss": 0.2163, "step": 77860 }, { - "epoch": 0.7, - "learning_rate": 1.5391406179623456e-05, - "loss": 0.2054, + "epoch": 0.17, + "learning_rate": 4.140544954251583e-05, + "loss": 0.2233, "step": 77870 }, { - "epoch": 0.7, - "learning_rate": 1.5386902080893614e-05, - "loss": 0.2002, + "epoch": 0.17, + "learning_rate": 4.140433099930651e-05, + "loss": 0.2195, "step": 77880 }, { - "epoch": 0.7, - "learning_rate": 1.538239798216377e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.140321245609718e-05, + "loss": 0.2231, "step": 77890 }, { - "epoch": 0.7, - "learning_rate": 1.5377893883433925e-05, - "loss": 0.2005, + "epoch": 0.17, + "learning_rate": 4.140209391288786e-05, + "loss": 0.2244, "step": 77900 }, { - "epoch": 0.7, - "learning_rate": 1.5373389784704083e-05, - "loss": 0.1932, + "epoch": 0.17, + "learning_rate": 4.1400975369678535e-05, + "loss": 0.2254, "step": 77910 }, { - "epoch": 0.7, - "learning_rate": 1.5368885685974237e-05, - "loss": 0.2049, + "epoch": 0.17, + "learning_rate": 4.1399856826469206e-05, + "loss": 0.2246, "step": 77920 }, { - "epoch": 0.7, - "learning_rate": 1.536438158724439e-05, - "loss": 0.1972, + "epoch": 0.17, + "learning_rate": 4.1398738283259884e-05, + "loss": 0.2248, "step": 77930 }, { - "epoch": 0.7, - "learning_rate": 1.535987748851455e-05, - "loss": 0.198, + "epoch": 0.17, + "learning_rate": 4.1397619740050555e-05, + "loss": 0.2195, "step": 77940 }, { - "epoch": 0.7, - "learning_rate": 1.5355373389784706e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.139650119684124e-05, + "loss": 0.2218, "step": 77950 }, { - "epoch": 0.7, - "learning_rate": 1.535086929105486e-05, - "loss": 0.1995, + "epoch": 0.17, + "learning_rate": 4.139538265363192e-05, + "loss": 0.2206, "step": 77960 }, { - "epoch": 0.7, - "learning_rate": 1.5346365192325014e-05, - "loss": 0.1963, + "epoch": 0.17, + "learning_rate": 4.139426411042259e-05, + "loss": 0.225, "step": 77970 }, { - "epoch": 0.7, - "learning_rate": 1.5341861093595172e-05, - "loss": 0.2013, + "epoch": 0.17, + "learning_rate": 4.139314556721327e-05, + "loss": 0.2199, "step": 77980 }, { - "epoch": 0.7, - "learning_rate": 1.533735699486533e-05, - "loss": 0.2029, + "epoch": 0.17, + "learning_rate": 4.139202702400394e-05, + "loss": 0.2209, "step": 77990 }, { - "epoch": 0.7, - "learning_rate": 1.5332852896135483e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.1390908480794616e-05, + "loss": 0.2233, "step": 78000 }, { - "epoch": 0.7, - "learning_rate": 1.532834879740564e-05, - "loss": 0.1978, + "epoch": 0.17, + "learning_rate": 4.138978993758529e-05, + "loss": 0.2207, "step": 78010 }, { - "epoch": 0.7, - "learning_rate": 1.5323844698675795e-05, - "loss": 0.1963, + "epoch": 0.17, + "learning_rate": 4.1388671394375965e-05, + "loss": 0.2255, "step": 78020 }, { - "epoch": 0.7, - "learning_rate": 1.5319340599945952e-05, - "loss": 0.1993, + "epoch": 0.17, + "learning_rate": 4.138755285116664e-05, + "loss": 0.2263, "step": 78030 }, { - "epoch": 0.7, - "learning_rate": 1.5314836501216107e-05, - "loss": 0.1952, + "epoch": 0.17, + "learning_rate": 4.1386434307957314e-05, + "loss": 0.2224, "step": 78040 }, { - "epoch": 0.7, - "learning_rate": 1.5310332402486264e-05, - "loss": 0.1969, + "epoch": 0.17, + "learning_rate": 4.138531576474799e-05, + "loss": 0.223, "step": 78050 }, { - "epoch": 0.7, - "learning_rate": 1.530582830375642e-05, - "loss": 0.1867, + "epoch": 0.17, + "learning_rate": 4.138419722153867e-05, + "loss": 0.2131, "step": 78060 }, { - "epoch": 0.7, - "learning_rate": 1.5301324205026572e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.138307867832935e-05, + "loss": 0.223, "step": 78070 }, { - "epoch": 0.7, - "learning_rate": 1.529682010629673e-05, - "loss": 0.1909, + "epoch": 0.17, + "learning_rate": 4.1381960135120026e-05, + "loss": 0.2264, "step": 78080 }, { - "epoch": 0.7, - "learning_rate": 1.5292316007566887e-05, - "loss": 0.1954, + "epoch": 0.17, + "learning_rate": 4.13808415919107e-05, + "loss": 0.2255, "step": 78090 }, { - "epoch": 0.7, - "learning_rate": 1.5287811908837045e-05, - "loss": 0.1958, + "epoch": 0.17, + "learning_rate": 4.1379723048701375e-05, + "loss": 0.2185, "step": 78100 }, { - "epoch": 0.7, - "learning_rate": 1.52833078101072e-05, - "loss": 0.1907, + "epoch": 0.17, + "learning_rate": 4.1378604505492046e-05, + "loss": 0.2254, "step": 78110 }, { - "epoch": 0.7, - "learning_rate": 1.5278803711377353e-05, - "loss": 0.1948, + "epoch": 0.17, + "learning_rate": 4.1377485962282724e-05, + "loss": 0.2203, "step": 78120 }, { - "epoch": 0.7, - "learning_rate": 1.527429961264751e-05, - "loss": 0.2002, + "epoch": 0.17, + "learning_rate": 4.13763674190734e-05, + "loss": 0.2219, "step": 78130 }, { - "epoch": 0.7, - "learning_rate": 1.5269795513917665e-05, - "loss": 0.1932, + "epoch": 0.17, + "learning_rate": 4.137524887586407e-05, + "loss": 0.2222, "step": 78140 }, { - "epoch": 0.7, - "learning_rate": 1.5265291415187822e-05, - "loss": 0.1985, + "epoch": 0.17, + "learning_rate": 4.137413033265475e-05, + "loss": 0.2221, "step": 78150 }, { - "epoch": 0.7, - "learning_rate": 1.526078731645798e-05, - "loss": 0.1998, + "epoch": 0.17, + "learning_rate": 4.137301178944543e-05, + "loss": 0.2243, "step": 78160 }, { - "epoch": 0.7, - "learning_rate": 1.5256283217728135e-05, - "loss": 0.2015, + "epoch": 0.17, + "learning_rate": 4.137189324623611e-05, + "loss": 0.2213, "step": 78170 }, { - "epoch": 0.7, - "learning_rate": 1.5251779118998288e-05, - "loss": 0.1963, + "epoch": 0.17, + "learning_rate": 4.1370774703026785e-05, + "loss": 0.2239, "step": 78180 }, { - "epoch": 0.7, - "learning_rate": 1.5247275020268445e-05, - "loss": 0.1953, + "epoch": 0.17, + "learning_rate": 4.1369656159817456e-05, + "loss": 0.2226, "step": 78190 }, { - "epoch": 0.7, - "learning_rate": 1.5242770921538601e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.1368537616608134e-05, + "loss": 0.2202, "step": 78200 }, { - "epoch": 0.7, - "learning_rate": 1.5238266822808755e-05, - "loss": 0.1969, + "epoch": 0.17, + "learning_rate": 4.1367419073398805e-05, + "loss": 0.2262, "step": 78210 }, { - "epoch": 0.7, - "learning_rate": 1.5233762724078913e-05, - "loss": 0.1972, + "epoch": 0.17, + "learning_rate": 4.136630053018948e-05, + "loss": 0.227, "step": 78220 }, { - "epoch": 0.7, - "learning_rate": 1.5229258625349068e-05, - "loss": 0.1994, + "epoch": 0.17, + "learning_rate": 4.136518198698016e-05, + "loss": 0.2171, "step": 78230 }, { - "epoch": 0.7, - "learning_rate": 1.5224754526619226e-05, - "loss": 0.201, + "epoch": 0.17, + "learning_rate": 4.136406344377083e-05, + "loss": 0.2171, "step": 78240 }, { - "epoch": 0.7, - "learning_rate": 1.522025042788938e-05, - "loss": 0.1975, + "epoch": 0.17, + "learning_rate": 4.136294490056151e-05, + "loss": 0.2272, "step": 78250 }, { - "epoch": 0.7, - "learning_rate": 1.5215746329159536e-05, - "loss": 0.193, + "epoch": 0.17, + "learning_rate": 4.136182635735219e-05, + "loss": 0.2208, "step": 78260 }, { - "epoch": 0.7, - "learning_rate": 1.5211242230429693e-05, - "loss": 0.1951, + "epoch": 0.17, + "learning_rate": 4.1360707814142866e-05, + "loss": 0.221, "step": 78270 }, { - "epoch": 0.7, - "learning_rate": 1.5206738131699846e-05, - "loss": 0.1933, + "epoch": 0.17, + "learning_rate": 4.1359589270933544e-05, + "loss": 0.2209, "step": 78280 }, { - "epoch": 0.7, - "learning_rate": 1.5202234032970003e-05, - "loss": 0.1935, + "epoch": 0.17, + "learning_rate": 4.1358470727724215e-05, + "loss": 0.2221, "step": 78290 }, { - "epoch": 0.7, - "learning_rate": 1.5197729934240159e-05, - "loss": 0.202, + "epoch": 0.17, + "learning_rate": 4.135735218451489e-05, + "loss": 0.2187, "step": 78300 }, { - "epoch": 0.7, - "learning_rate": 1.5193225835510316e-05, - "loss": 0.1986, + "epoch": 0.17, + "learning_rate": 4.1356233641305564e-05, + "loss": 0.2217, "step": 78310 }, { - "epoch": 0.7, - "learning_rate": 1.518872173678047e-05, - "loss": 0.196, + "epoch": 0.17, + "learning_rate": 4.135511509809624e-05, + "loss": 0.2253, "step": 78320 }, { - "epoch": 0.7, - "learning_rate": 1.5184217638050626e-05, - "loss": 0.1935, + "epoch": 0.17, + "learning_rate": 4.135399655488691e-05, + "loss": 0.2222, "step": 78330 }, { - "epoch": 0.7, - "learning_rate": 1.5179713539320784e-05, - "loss": 0.1921, + "epoch": 0.17, + "learning_rate": 4.135287801167759e-05, + "loss": 0.2227, "step": 78340 }, { - "epoch": 0.7, - "learning_rate": 1.5175209440590938e-05, - "loss": 0.1923, + "epoch": 0.17, + "learning_rate": 4.135175946846827e-05, + "loss": 0.2236, "step": 78350 }, { - "epoch": 0.7, - "learning_rate": 1.5170705341861094e-05, - "loss": 0.1928, + "epoch": 0.17, + "learning_rate": 4.135064092525894e-05, + "loss": 0.2175, "step": 78360 }, { - "epoch": 0.7, - "learning_rate": 1.5166201243131251e-05, - "loss": 0.1959, + "epoch": 0.17, + "learning_rate": 4.1349522382049625e-05, + "loss": 0.2216, "step": 78370 }, { - "epoch": 0.7, - "learning_rate": 1.5161697144401407e-05, - "loss": 0.1973, + "epoch": 0.17, + "learning_rate": 4.1348403838840296e-05, + "loss": 0.2201, "step": 78380 }, { - "epoch": 0.7, - "learning_rate": 1.5157193045671561e-05, - "loss": 0.1992, + "epoch": 0.17, + "learning_rate": 4.1347285295630974e-05, + "loss": 0.2232, "step": 78390 }, { - "epoch": 0.7, - "learning_rate": 1.5152688946941717e-05, - "loss": 0.1949, + "epoch": 0.17, + "learning_rate": 4.134616675242165e-05, + "loss": 0.2177, "step": 78400 }, { - "epoch": 0.7, - "learning_rate": 1.5148184848211874e-05, - "loss": 0.1976, + "epoch": 0.18, + "learning_rate": 4.134504820921232e-05, + "loss": 0.2223, "step": 78410 }, { - "epoch": 0.7, - "learning_rate": 1.5143680749482029e-05, - "loss": 0.2016, + "epoch": 0.18, + "learning_rate": 4.1343929666003e-05, + "loss": 0.2217, "step": 78420 }, { - "epoch": 0.7, - "learning_rate": 1.5139176650752184e-05, - "loss": 0.1945, + "epoch": 0.18, + "learning_rate": 4.134281112279367e-05, + "loss": 0.22, "step": 78430 }, { - "epoch": 0.7, - "learning_rate": 1.5134672552022342e-05, - "loss": 0.1974, + "epoch": 0.18, + "learning_rate": 4.134169257958435e-05, + "loss": 0.2267, "step": 78440 }, { - "epoch": 0.7, - "learning_rate": 1.5130168453292498e-05, - "loss": 0.1984, + "epoch": 0.18, + "learning_rate": 4.134057403637503e-05, + "loss": 0.2253, "step": 78450 }, { - "epoch": 0.7, - "learning_rate": 1.5125664354562652e-05, - "loss": 0.2012, + "epoch": 0.18, + "learning_rate": 4.13394554931657e-05, + "loss": 0.2191, "step": 78460 }, { - "epoch": 0.7, - "learning_rate": 1.512116025583281e-05, - "loss": 0.1993, + "epoch": 0.18, + "learning_rate": 4.133833694995638e-05, + "loss": 0.226, "step": 78470 }, { - "epoch": 0.7, - "learning_rate": 1.5116656157102965e-05, - "loss": 0.1993, + "epoch": 0.18, + "learning_rate": 4.1337218406747055e-05, + "loss": 0.22, "step": 78480 }, { - "epoch": 0.7, - "learning_rate": 1.5112152058373119e-05, - "loss": 0.1909, + "epoch": 0.18, + "learning_rate": 4.133609986353773e-05, + "loss": 0.2288, "step": 78490 }, { - "epoch": 0.7, - "learning_rate": 1.5107647959643275e-05, - "loss": 0.1977, + "epoch": 0.18, + "learning_rate": 4.133498132032841e-05, + "loss": 0.2247, "step": 78500 }, { - "epoch": 0.7, - "learning_rate": 1.5103143860913432e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.133386277711908e-05, + "loss": 0.2274, "step": 78510 }, { - "epoch": 0.7, - "learning_rate": 1.5098639762183588e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.133274423390976e-05, + "loss": 0.2202, "step": 78520 }, { - "epoch": 0.7, - "learning_rate": 1.5094135663453742e-05, - "loss": 0.1945, + "epoch": 0.18, + "learning_rate": 4.133162569070043e-05, + "loss": 0.2229, "step": 78530 }, { - "epoch": 0.7, - "learning_rate": 1.50896315647239e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.133050714749111e-05, + "loss": 0.2229, "step": 78540 }, { - "epoch": 0.7, - "learning_rate": 1.5085127465994056e-05, - "loss": 0.2003, + "epoch": 0.18, + "learning_rate": 4.132938860428179e-05, + "loss": 0.22, "step": 78550 }, { - "epoch": 0.7, - "learning_rate": 1.508062336726421e-05, - "loss": 0.1956, + "epoch": 0.18, + "learning_rate": 4.132827006107246e-05, + "loss": 0.2205, "step": 78560 }, { - "epoch": 0.7, - "learning_rate": 1.5076119268534367e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.1327151517863136e-05, + "loss": 0.2205, "step": 78570 }, { - "epoch": 0.7, - "learning_rate": 1.5071615169804523e-05, - "loss": 0.1913, + "epoch": 0.18, + "learning_rate": 4.1326032974653814e-05, + "loss": 0.2235, "step": 78580 }, { - "epoch": 0.7, - "learning_rate": 1.506711107107468e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.132491443144449e-05, + "loss": 0.227, "step": 78590 }, { - "epoch": 0.7, - "learning_rate": 1.5062606972344833e-05, - "loss": 0.1991, + "epoch": 0.18, + "learning_rate": 4.132379588823517e-05, + "loss": 0.2195, "step": 78600 }, { - "epoch": 0.7, - "learning_rate": 1.505810287361499e-05, - "loss": 0.1964, + "epoch": 0.18, + "learning_rate": 4.132267734502584e-05, + "loss": 0.2194, "step": 78610 }, { - "epoch": 0.7, - "learning_rate": 1.5053598774885146e-05, - "loss": 0.1992, + "epoch": 0.18, + "learning_rate": 4.132155880181652e-05, + "loss": 0.2224, "step": 78620 }, { - "epoch": 0.7, - "learning_rate": 1.50490946761553e-05, - "loss": 0.1976, + "epoch": 0.18, + "learning_rate": 4.132044025860719e-05, + "loss": 0.2199, "step": 78630 }, { - "epoch": 0.7, - "learning_rate": 1.5044590577425458e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.131932171539787e-05, + "loss": 0.2239, "step": 78640 }, { - "epoch": 0.7, - "learning_rate": 1.5040086478695614e-05, - "loss": 0.1983, + "epoch": 0.18, + "learning_rate": 4.131820317218854e-05, + "loss": 0.2312, "step": 78650 }, { - "epoch": 0.7, - "learning_rate": 1.5035582379965771e-05, - "loss": 0.2033, + "epoch": 0.18, + "learning_rate": 4.131708462897922e-05, + "loss": 0.2248, "step": 78660 }, { - "epoch": 0.7, - "learning_rate": 1.5031078281235925e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.1315966085769895e-05, + "loss": 0.218, "step": 78670 }, { - "epoch": 0.7, - "learning_rate": 1.5026574182506081e-05, - "loss": 0.1964, + "epoch": 0.18, + "learning_rate": 4.131484754256057e-05, + "loss": 0.2259, "step": 78680 }, { - "epoch": 0.7, - "learning_rate": 1.5022070083776238e-05, - "loss": 0.2033, + "epoch": 0.18, + "learning_rate": 4.131372899935125e-05, + "loss": 0.2206, "step": 78690 }, { - "epoch": 0.7, - "learning_rate": 1.5017565985046393e-05, - "loss": 0.1954, + "epoch": 0.18, + "learning_rate": 4.131261045614192e-05, + "loss": 0.2269, "step": 78700 }, { - "epoch": 0.7, - "learning_rate": 1.5013061886316548e-05, - "loss": 0.1977, + "epoch": 0.18, + "learning_rate": 4.13114919129326e-05, + "loss": 0.2234, "step": 78710 }, { - "epoch": 0.7, - "learning_rate": 1.5008557787586706e-05, - "loss": 0.1998, + "epoch": 0.18, + "learning_rate": 4.131037336972328e-05, + "loss": 0.2219, "step": 78720 }, { - "epoch": 0.7, - "learning_rate": 1.5004053688856862e-05, - "loss": 0.1971, + "epoch": 0.18, + "learning_rate": 4.130925482651395e-05, + "loss": 0.2215, "step": 78730 }, { - "epoch": 0.7, - "learning_rate": 1.4999549590127016e-05, - "loss": 0.1944, + "epoch": 0.18, + "learning_rate": 4.130813628330463e-05, + "loss": 0.2215, "step": 78740 }, { - "epoch": 0.7, - "learning_rate": 1.4995045491397172e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.13070177400953e-05, + "loss": 0.229, "step": 78750 }, { - "epoch": 0.7, - "learning_rate": 1.4990541392667329e-05, - "loss": 0.1993, + "epoch": 0.18, + "learning_rate": 4.1305899196885976e-05, + "loss": 0.2214, "step": 78760 }, { - "epoch": 0.7, - "learning_rate": 1.4986037293937483e-05, - "loss": 0.205, + "epoch": 0.18, + "learning_rate": 4.1304780653676654e-05, + "loss": 0.2221, "step": 78770 }, { - "epoch": 0.7, - "learning_rate": 1.4981533195207639e-05, - "loss": 0.1982, + "epoch": 0.18, + "learning_rate": 4.130366211046733e-05, + "loss": 0.2287, "step": 78780 }, { - "epoch": 0.7, - "learning_rate": 1.4977029096477796e-05, - "loss": 0.2039, + "epoch": 0.18, + "learning_rate": 4.130254356725801e-05, + "loss": 0.2212, "step": 78790 }, { - "epoch": 0.7, - "learning_rate": 1.4972524997747952e-05, - "loss": 0.1975, + "epoch": 0.18, + "learning_rate": 4.130142502404868e-05, + "loss": 0.2171, "step": 78800 }, { - "epoch": 0.7, - "learning_rate": 1.4968020899018106e-05, - "loss": 0.1914, + "epoch": 0.18, + "learning_rate": 4.130030648083936e-05, + "loss": 0.2225, "step": 78810 }, { - "epoch": 0.7, - "learning_rate": 1.4963516800288264e-05, - "loss": 0.1885, + "epoch": 0.18, + "learning_rate": 4.1299187937630036e-05, + "loss": 0.2224, "step": 78820 }, { - "epoch": 0.7, - "learning_rate": 1.495901270155842e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.129806939442071e-05, + "loss": 0.2252, "step": 78830 }, { - "epoch": 0.7, - "learning_rate": 1.4954508602828574e-05, - "loss": 0.1999, + "epoch": 0.18, + "learning_rate": 4.1296950851211386e-05, + "loss": 0.2216, "step": 78840 }, { - "epoch": 0.7, - "learning_rate": 1.495000450409873e-05, - "loss": 0.1997, + "epoch": 0.18, + "learning_rate": 4.129583230800206e-05, + "loss": 0.2202, "step": 78850 }, { - "epoch": 0.7, - "learning_rate": 1.4945500405368887e-05, - "loss": 0.1911, + "epoch": 0.18, + "learning_rate": 4.1294713764792735e-05, + "loss": 0.2245, "step": 78860 }, { - "epoch": 0.7, - "learning_rate": 1.4940996306639043e-05, - "loss": 0.1893, + "epoch": 0.18, + "learning_rate": 4.129359522158341e-05, + "loss": 0.2202, "step": 78870 }, { - "epoch": 0.7, - "learning_rate": 1.4936492207909197e-05, - "loss": 0.1958, + "epoch": 0.18, + "learning_rate": 4.1292476678374084e-05, + "loss": 0.2159, "step": 78880 }, { - "epoch": 0.7, - "learning_rate": 1.4931988109179354e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.129135813516476e-05, + "loss": 0.2286, "step": 78890 }, { - "epoch": 0.7, - "learning_rate": 1.492748401044951e-05, - "loss": 0.1936, + "epoch": 0.18, + "learning_rate": 4.129023959195544e-05, + "loss": 0.224, "step": 78900 }, { - "epoch": 0.7, - "learning_rate": 1.4922979911719664e-05, - "loss": 0.1938, + "epoch": 0.18, + "learning_rate": 4.128912104874612e-05, + "loss": 0.2186, "step": 78910 }, { - "epoch": 0.7, - "learning_rate": 1.4918475812989822e-05, - "loss": 0.2027, + "epoch": 0.18, + "learning_rate": 4.1288002505536795e-05, + "loss": 0.218, "step": 78920 }, { - "epoch": 0.7, - "learning_rate": 1.4913971714259978e-05, - "loss": 0.1995, + "epoch": 0.18, + "learning_rate": 4.1286883962327467e-05, + "loss": 0.2212, "step": 78930 }, { - "epoch": 0.7, - "learning_rate": 1.4909467615530135e-05, - "loss": 0.1912, + "epoch": 0.18, + "learning_rate": 4.1285765419118145e-05, + "loss": 0.223, "step": 78940 }, { - "epoch": 0.7, - "learning_rate": 1.4904963516800288e-05, - "loss": 0.1981, + "epoch": 0.18, + "learning_rate": 4.1284646875908816e-05, + "loss": 0.2183, "step": 78950 }, { - "epoch": 0.7, - "learning_rate": 1.4900459418070445e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.1283528332699494e-05, + "loss": 0.2169, "step": 78960 }, { - "epoch": 0.71, - "learning_rate": 1.48959553193406e-05, - "loss": 0.2011, + "epoch": 0.18, + "learning_rate": 4.1282409789490165e-05, + "loss": 0.2195, "step": 78970 }, { - "epoch": 0.71, - "learning_rate": 1.4891451220610755e-05, - "loss": 0.1986, + "epoch": 0.18, + "learning_rate": 4.128129124628084e-05, + "loss": 0.2234, "step": 78980 }, { - "epoch": 0.71, - "learning_rate": 1.4886947121880912e-05, - "loss": 0.1984, + "epoch": 0.18, + "learning_rate": 4.128017270307152e-05, + "loss": 0.2225, "step": 78990 }, { - "epoch": 0.71, - "learning_rate": 1.4882443023151068e-05, - "loss": 0.1966, + "epoch": 0.18, + "learning_rate": 4.12790541598622e-05, + "loss": 0.2204, "step": 79000 }, { - "epoch": 0.71, - "learning_rate": 1.4877938924421226e-05, - "loss": 0.1984, + "epoch": 0.18, + "learning_rate": 4.1277935616652876e-05, + "loss": 0.2167, "step": 79010 }, { - "epoch": 0.71, - "learning_rate": 1.487343482569138e-05, - "loss": 0.1995, + "epoch": 0.18, + "learning_rate": 4.127681707344355e-05, + "loss": 0.2169, "step": 79020 }, { - "epoch": 0.71, - "learning_rate": 1.4868930726961536e-05, - "loss": 0.2027, + "epoch": 0.18, + "learning_rate": 4.1275698530234226e-05, + "loss": 0.2205, "step": 79030 }, { - "epoch": 0.71, - "learning_rate": 1.4864426628231693e-05, - "loss": 0.2015, + "epoch": 0.18, + "learning_rate": 4.1274579987024903e-05, + "loss": 0.2198, "step": 79040 }, { - "epoch": 0.71, - "learning_rate": 1.4859922529501846e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.1273461443815575e-05, + "loss": 0.2153, "step": 79050 }, { - "epoch": 0.71, - "learning_rate": 1.4855418430772003e-05, - "loss": 0.1956, + "epoch": 0.18, + "learning_rate": 4.127234290060625e-05, + "loss": 0.2206, "step": 79060 }, { - "epoch": 0.71, - "learning_rate": 1.4850914332042159e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.1271224357396924e-05, + "loss": 0.2224, "step": 79070 }, { - "epoch": 0.71, - "learning_rate": 1.4846410233312316e-05, - "loss": 0.1898, + "epoch": 0.18, + "learning_rate": 4.12701058141876e-05, + "loss": 0.2192, "step": 79080 }, { - "epoch": 0.71, - "learning_rate": 1.484190613458247e-05, - "loss": 0.1953, + "epoch": 0.18, + "learning_rate": 4.126898727097828e-05, + "loss": 0.2219, "step": 79090 }, { - "epoch": 0.71, - "learning_rate": 1.4837402035852626e-05, - "loss": 0.1947, + "epoch": 0.18, + "learning_rate": 4.126786872776896e-05, + "loss": 0.2251, "step": 79100 }, { - "epoch": 0.71, - "learning_rate": 1.4832897937122784e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.1266750184559635e-05, + "loss": 0.2206, "step": 79110 }, { - "epoch": 0.71, - "learning_rate": 1.4828393838392938e-05, - "loss": 0.1985, + "epoch": 0.18, + "learning_rate": 4.1265631641350307e-05, + "loss": 0.2231, "step": 79120 }, { - "epoch": 0.71, - "learning_rate": 1.4823889739663094e-05, - "loss": 0.198, + "epoch": 0.18, + "learning_rate": 4.1264513098140984e-05, + "loss": 0.2186, "step": 79130 }, { - "epoch": 0.71, - "learning_rate": 1.4819385640933251e-05, - "loss": 0.1994, + "epoch": 0.18, + "learning_rate": 4.126339455493166e-05, + "loss": 0.2215, "step": 79140 }, { - "epoch": 0.71, - "learning_rate": 1.4814881542203407e-05, - "loss": 0.1906, + "epoch": 0.18, + "learning_rate": 4.1262276011722334e-05, + "loss": 0.2204, "step": 79150 }, { - "epoch": 0.71, - "learning_rate": 1.4810377443473561e-05, - "loss": 0.1897, + "epoch": 0.18, + "learning_rate": 4.126115746851301e-05, + "loss": 0.2245, "step": 79160 }, { - "epoch": 0.71, - "learning_rate": 1.4805873344743717e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.126003892530368e-05, + "loss": 0.2181, "step": 79170 }, { - "epoch": 0.71, - "learning_rate": 1.4801369246013874e-05, - "loss": 0.1947, + "epoch": 0.18, + "learning_rate": 4.125892038209436e-05, + "loss": 0.218, "step": 79180 }, { - "epoch": 0.71, - "learning_rate": 1.4796865147284028e-05, - "loss": 0.1986, + "epoch": 0.18, + "learning_rate": 4.125780183888504e-05, + "loss": 0.2202, "step": 79190 }, { - "epoch": 0.71, - "learning_rate": 1.4792361048554184e-05, - "loss": 0.1973, + "epoch": 0.18, + "learning_rate": 4.1256683295675716e-05, + "loss": 0.2212, "step": 79200 }, { - "epoch": 0.71, - "learning_rate": 1.4787856949824342e-05, - "loss": 0.1924, + "epoch": 0.18, + "learning_rate": 4.1255564752466394e-05, + "loss": 0.2207, "step": 79210 }, { - "epoch": 0.71, - "learning_rate": 1.4783352851094497e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.1254446209257066e-05, + "loss": 0.2245, "step": 79220 }, { - "epoch": 0.71, - "learning_rate": 1.4778848752364652e-05, - "loss": 0.1982, + "epoch": 0.18, + "learning_rate": 4.1253327666047743e-05, + "loss": 0.2198, "step": 79230 }, { - "epoch": 0.71, - "learning_rate": 1.4774344653634809e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.125220912283842e-05, + "loss": 0.2231, "step": 79240 }, { - "epoch": 0.71, - "learning_rate": 1.4769840554904965e-05, - "loss": 0.1994, + "epoch": 0.18, + "learning_rate": 4.125109057962909e-05, + "loss": 0.2186, "step": 79250 }, { - "epoch": 0.71, - "learning_rate": 1.4765336456175119e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.124997203641977e-05, + "loss": 0.2208, "step": 79260 }, { - "epoch": 0.71, - "learning_rate": 1.4760832357445275e-05, - "loss": 0.1947, + "epoch": 0.18, + "learning_rate": 4.124885349321044e-05, + "loss": 0.2197, "step": 79270 }, { - "epoch": 0.71, - "learning_rate": 1.4756328258715432e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.124773495000112e-05, + "loss": 0.223, "step": 79280 }, { - "epoch": 0.71, - "learning_rate": 1.4751824159985588e-05, - "loss": 0.1961, + "epoch": 0.18, + "learning_rate": 4.124661640679179e-05, + "loss": 0.2227, "step": 79290 }, { - "epoch": 0.71, - "learning_rate": 1.4747320061255742e-05, - "loss": 0.1982, + "epoch": 0.18, + "learning_rate": 4.124549786358247e-05, + "loss": 0.2186, "step": 79300 }, { - "epoch": 0.71, - "learning_rate": 1.47428159625259e-05, - "loss": 0.1983, + "epoch": 0.18, + "learning_rate": 4.1244379320373147e-05, + "loss": 0.2231, "step": 79310 }, { - "epoch": 0.71, - "learning_rate": 1.4738311863796055e-05, - "loss": 0.1978, + "epoch": 0.18, + "learning_rate": 4.1243260777163824e-05, + "loss": 0.2214, "step": 79320 }, { - "epoch": 0.71, - "learning_rate": 1.473380776506621e-05, - "loss": 0.1979, + "epoch": 0.18, + "learning_rate": 4.12421422339545e-05, + "loss": 0.2135, "step": 79330 }, { - "epoch": 0.71, - "learning_rate": 1.4729303666336367e-05, - "loss": 0.1972, + "epoch": 0.18, + "learning_rate": 4.1241023690745174e-05, + "loss": 0.2245, "step": 79340 }, { - "epoch": 0.71, - "learning_rate": 1.4724799567606523e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.123990514753585e-05, + "loss": 0.2166, "step": 79350 }, { - "epoch": 0.71, - "learning_rate": 1.472029546887668e-05, - "loss": 0.1944, + "epoch": 0.18, + "learning_rate": 4.123878660432653e-05, + "loss": 0.2231, "step": 79360 }, { - "epoch": 0.71, - "learning_rate": 1.4715791370146834e-05, - "loss": 0.1923, + "epoch": 0.18, + "learning_rate": 4.12376680611172e-05, + "loss": 0.2205, "step": 79370 }, { - "epoch": 0.71, - "learning_rate": 1.471128727141699e-05, - "loss": 0.2019, + "epoch": 0.18, + "learning_rate": 4.123654951790788e-05, + "loss": 0.2243, "step": 79380 }, { - "epoch": 0.71, - "learning_rate": 1.4706783172687146e-05, - "loss": 0.1903, + "epoch": 0.18, + "learning_rate": 4.123543097469855e-05, + "loss": 0.2197, "step": 79390 }, { - "epoch": 0.71, - "learning_rate": 1.47022790739573e-05, - "loss": 0.1936, + "epoch": 0.18, + "learning_rate": 4.123431243148923e-05, + "loss": 0.2189, "step": 79400 }, { - "epoch": 0.71, - "learning_rate": 1.4697774975227458e-05, - "loss": 0.1984, + "epoch": 0.18, + "learning_rate": 4.1233193888279905e-05, + "loss": 0.2223, "step": 79410 }, { - "epoch": 0.71, - "learning_rate": 1.4693270876497613e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.1232075345070583e-05, + "loss": 0.225, "step": 79420 }, { - "epoch": 0.71, - "learning_rate": 1.4688766777767771e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.123095680186126e-05, + "loss": 0.2203, "step": 79430 }, { - "epoch": 0.71, - "learning_rate": 1.4684262679037925e-05, - "loss": 0.1956, + "epoch": 0.18, + "learning_rate": 4.122983825865193e-05, + "loss": 0.2197, "step": 79440 }, { - "epoch": 0.71, - "learning_rate": 1.467975858030808e-05, - "loss": 0.2013, + "epoch": 0.18, + "learning_rate": 4.122871971544261e-05, + "loss": 0.2214, "step": 79450 }, { - "epoch": 0.71, - "learning_rate": 1.4675254481578238e-05, - "loss": 0.1961, + "epoch": 0.18, + "learning_rate": 4.122760117223329e-05, + "loss": 0.2185, "step": 79460 }, { - "epoch": 0.71, - "learning_rate": 1.4670750382848392e-05, - "loss": 0.2032, + "epoch": 0.18, + "learning_rate": 4.122659448334489e-05, + "loss": 0.2207, "step": 79470 }, { - "epoch": 0.71, - "learning_rate": 1.4666246284118548e-05, - "loss": 0.1986, + "epoch": 0.18, + "learning_rate": 4.1225475940135575e-05, + "loss": 0.2167, "step": 79480 }, { - "epoch": 0.71, - "learning_rate": 1.4661742185388706e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.1224357396926246e-05, + "loss": 0.2187, "step": 79490 }, { - "epoch": 0.71, - "learning_rate": 1.4657238086658862e-05, - "loss": 0.1957, + "epoch": 0.18, + "learning_rate": 4.1223238853716924e-05, + "loss": 0.2195, "step": 79500 }, { - "epoch": 0.71, - "learning_rate": 1.4652733987929016e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.1222120310507595e-05, + "loss": 0.2155, "step": 79510 }, { - "epoch": 0.71, - "learning_rate": 1.4648229889199171e-05, - "loss": 0.1933, + "epoch": 0.18, + "learning_rate": 4.122100176729827e-05, + "loss": 0.2207, "step": 79520 }, { - "epoch": 0.71, - "learning_rate": 1.4643725790469329e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.121988322408895e-05, + "loss": 0.2204, "step": 79530 }, { - "epoch": 0.71, - "learning_rate": 1.4639221691739483e-05, - "loss": 0.1944, + "epoch": 0.18, + "learning_rate": 4.121876468087962e-05, + "loss": 0.2212, "step": 79540 }, { - "epoch": 0.71, - "learning_rate": 1.4634717593009639e-05, - "loss": 0.206, + "epoch": 0.18, + "learning_rate": 4.12176461376703e-05, + "loss": 0.2201, "step": 79550 }, { - "epoch": 0.71, - "learning_rate": 1.4630213494279796e-05, - "loss": 0.2023, + "epoch": 0.18, + "learning_rate": 4.121652759446097e-05, + "loss": 0.2184, "step": 79560 }, { - "epoch": 0.71, - "learning_rate": 1.4625709395549952e-05, - "loss": 0.1988, + "epoch": 0.18, + "learning_rate": 4.121540905125165e-05, + "loss": 0.2227, "step": 79570 }, { - "epoch": 0.71, - "learning_rate": 1.4621205296820106e-05, - "loss": 0.2009, + "epoch": 0.18, + "learning_rate": 4.121429050804233e-05, + "loss": 0.2164, "step": 79580 }, { - "epoch": 0.71, - "learning_rate": 1.4616701198090264e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.1213171964833005e-05, + "loss": 0.2171, "step": 79590 }, { - "epoch": 0.71, - "learning_rate": 1.461219709936042e-05, - "loss": 0.201, + "epoch": 0.18, + "learning_rate": 4.121205342162368e-05, + "loss": 0.2211, "step": 79600 }, { - "epoch": 0.71, - "learning_rate": 1.4607693000630574e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.1210934878414354e-05, + "loss": 0.2226, "step": 79610 }, { - "epoch": 0.71, - "learning_rate": 1.460318890190073e-05, - "loss": 0.1965, + "epoch": 0.18, + "learning_rate": 4.120981633520503e-05, + "loss": 0.2249, "step": 79620 }, { - "epoch": 0.71, - "learning_rate": 1.4598684803170887e-05, - "loss": 0.1924, + "epoch": 0.18, + "learning_rate": 4.12086977919957e-05, + "loss": 0.2176, "step": 79630 }, { - "epoch": 0.71, - "learning_rate": 1.4594180704441043e-05, - "loss": 0.1914, + "epoch": 0.18, + "learning_rate": 4.120757924878638e-05, + "loss": 0.2179, "step": 79640 }, { - "epoch": 0.71, - "learning_rate": 1.4589676605711197e-05, - "loss": 0.1979, + "epoch": 0.18, + "learning_rate": 4.120646070557706e-05, + "loss": 0.2242, "step": 79650 }, { - "epoch": 0.71, - "learning_rate": 1.4585172506981354e-05, - "loss": 0.1983, + "epoch": 0.18, + "learning_rate": 4.120534216236773e-05, + "loss": 0.2213, "step": 79660 }, { - "epoch": 0.71, - "learning_rate": 1.458066840825151e-05, - "loss": 0.1916, + "epoch": 0.18, + "learning_rate": 4.120422361915841e-05, + "loss": 0.2199, "step": 79670 }, { - "epoch": 0.71, - "learning_rate": 1.4576164309521664e-05, - "loss": 0.1986, + "epoch": 0.18, + "learning_rate": 4.1203105075949086e-05, + "loss": 0.2265, "step": 79680 }, { - "epoch": 0.71, - "learning_rate": 1.4571660210791822e-05, - "loss": 0.191, + "epoch": 0.18, + "learning_rate": 4.1201986532739764e-05, + "loss": 0.2212, "step": 79690 }, { - "epoch": 0.71, - "learning_rate": 1.4567156112061977e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.120086798953044e-05, + "loss": 0.2131, "step": 79700 }, { - "epoch": 0.71, - "learning_rate": 1.4562652013332135e-05, - "loss": 0.1937, + "epoch": 0.18, + "learning_rate": 4.119974944632111e-05, + "loss": 0.2214, "step": 79710 }, { - "epoch": 0.71, - "learning_rate": 1.4558147914602287e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.119863090311179e-05, + "loss": 0.2216, "step": 79720 }, { - "epoch": 0.71, - "learning_rate": 1.4553643815872445e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.119751235990246e-05, + "loss": 0.2234, "step": 79730 }, { - "epoch": 0.71, - "learning_rate": 1.45491397171426e-05, - "loss": 0.198, + "epoch": 0.18, + "learning_rate": 4.119639381669314e-05, + "loss": 0.2254, "step": 79740 }, { - "epoch": 0.71, - "learning_rate": 1.4544635618412755e-05, - "loss": 0.1984, + "epoch": 0.18, + "learning_rate": 4.119527527348382e-05, + "loss": 0.2241, "step": 79750 }, { - "epoch": 0.71, - "learning_rate": 1.4540131519682912e-05, - "loss": 0.1949, + "epoch": 0.18, + "learning_rate": 4.119415673027449e-05, + "loss": 0.2198, "step": 79760 }, { - "epoch": 0.71, - "learning_rate": 1.4535627420953068e-05, - "loss": 0.1962, + "epoch": 0.18, + "learning_rate": 4.119303818706517e-05, + "loss": 0.2243, "step": 79770 }, { - "epoch": 0.71, - "learning_rate": 1.4531123322223226e-05, - "loss": 0.1937, + "epoch": 0.18, + "learning_rate": 4.1191919643855845e-05, + "loss": 0.2209, "step": 79780 }, { - "epoch": 0.71, - "learning_rate": 1.452661922349338e-05, - "loss": 0.1979, + "epoch": 0.18, + "learning_rate": 4.119080110064652e-05, + "loss": 0.2196, "step": 79790 }, { - "epoch": 0.71, - "learning_rate": 1.4522115124763535e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.11896825574372e-05, + "loss": 0.2203, "step": 79800 }, { - "epoch": 0.71, - "learning_rate": 1.4517611026033693e-05, - "loss": 0.1996, + "epoch": 0.18, + "learning_rate": 4.118856401422787e-05, + "loss": 0.2179, "step": 79810 }, { - "epoch": 0.71, - "learning_rate": 1.4513106927303845e-05, - "loss": 0.1977, + "epoch": 0.18, + "learning_rate": 4.118744547101855e-05, + "loss": 0.2227, "step": 79820 }, { - "epoch": 0.71, - "learning_rate": 1.4508602828574003e-05, - "loss": 0.1999, + "epoch": 0.18, + "learning_rate": 4.118632692780922e-05, + "loss": 0.2185, "step": 79830 }, { - "epoch": 0.71, - "learning_rate": 1.4504098729844159e-05, - "loss": 0.1942, + "epoch": 0.18, + "learning_rate": 4.11852083845999e-05, + "loss": 0.2178, "step": 79840 }, { - "epoch": 0.71, - "learning_rate": 1.4499594631114316e-05, - "loss": 0.1958, + "epoch": 0.18, + "learning_rate": 4.118408984139058e-05, + "loss": 0.2206, "step": 79850 }, { - "epoch": 0.71, - "learning_rate": 1.449509053238447e-05, - "loss": 0.1954, + "epoch": 0.18, + "learning_rate": 4.118297129818125e-05, + "loss": 0.2172, "step": 79860 }, { - "epoch": 0.71, - "learning_rate": 1.4490586433654626e-05, - "loss": 0.1991, + "epoch": 0.18, + "learning_rate": 4.1181852754971926e-05, + "loss": 0.22, "step": 79870 }, { - "epoch": 0.71, - "learning_rate": 1.4486082334924784e-05, - "loss": 0.1914, + "epoch": 0.18, + "learning_rate": 4.11807342117626e-05, + "loss": 0.2226, "step": 79880 }, { - "epoch": 0.71, - "learning_rate": 1.4481578236194938e-05, - "loss": 0.1999, + "epoch": 0.18, + "learning_rate": 4.1179615668553275e-05, + "loss": 0.2148, "step": 79890 }, { - "epoch": 0.71, - "learning_rate": 1.4477074137465093e-05, - "loss": 0.1977, + "epoch": 0.18, + "learning_rate": 4.117849712534396e-05, + "loss": 0.2247, "step": 79900 }, { - "epoch": 0.71, - "learning_rate": 1.4472570038735251e-05, - "loss": 0.198, + "epoch": 0.18, + "learning_rate": 4.117737858213463e-05, + "loss": 0.2181, "step": 79910 }, { - "epoch": 0.71, - "learning_rate": 1.4468065940005407e-05, - "loss": 0.1973, + "epoch": 0.18, + "learning_rate": 4.117626003892531e-05, + "loss": 0.2212, "step": 79920 }, { - "epoch": 0.71, - "learning_rate": 1.4463561841275561e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.117514149571598e-05, + "loss": 0.2188, "step": 79930 }, { - "epoch": 0.71, - "learning_rate": 1.4459057742545717e-05, - "loss": 0.1987, + "epoch": 0.18, + "learning_rate": 4.117402295250666e-05, + "loss": 0.2177, "step": 79940 }, { - "epoch": 0.71, - "learning_rate": 1.4454553643815874e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.117290440929733e-05, + "loss": 0.2156, "step": 79950 }, { - "epoch": 0.71, - "learning_rate": 1.4450049545086028e-05, - "loss": 0.1979, + "epoch": 0.18, + "learning_rate": 4.117178586608801e-05, + "loss": 0.2185, "step": 79960 }, { - "epoch": 0.71, - "learning_rate": 1.4445545446356184e-05, - "loss": 0.193, + "epoch": 0.18, + "learning_rate": 4.1170667322878685e-05, + "loss": 0.2243, "step": 79970 }, { - "epoch": 0.71, - "learning_rate": 1.4441491757499326e-05, - "loss": 0.198, + "epoch": 0.18, + "learning_rate": 4.1169548779669356e-05, + "loss": 0.2162, "step": 79980 }, { - "epoch": 0.71, - "learning_rate": 1.443698765876948e-05, - "loss": 0.1971, + "epoch": 0.18, + "learning_rate": 4.1168430236460034e-05, + "loss": 0.2208, "step": 79990 }, { - "epoch": 0.71, - "learning_rate": 1.4432483560039636e-05, - "loss": 0.1834, + "epoch": 0.18, + "learning_rate": 4.116731169325071e-05, + "loss": 0.2175, "step": 80000 }, { - "epoch": 0.71, - "eval_NEIMS_canon_smiles": 0.938, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.04953333333333333, - "eval_NEIMS_daylight_tanimoto_simil": 0.44968452256661257, - "eval_NEIMS_exact_mols": 0.04933333333333333, - "eval_NEIMS_exact_smiles": 0.04761666666666667, - "eval_NEIMS_loss": 0.22744505107402802, - "eval_NEIMS_matched_formulas": 0.55905, - "eval_NEIMS_morgan_tanimoto_simil": 0.3516388449474886, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.04951666666666667, - "eval_NEIMS_runtime": 716.2027, - "eval_NEIMS_samples_per_second": 83.775, - "eval_NEIMS_steps_per_second": 1.31, + "epoch": 0.18, + "eval_NEIMS_canon_smiles": 0.9415166666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.0485, + "eval_NEIMS_daylight_tanimoto_simil": 0.4511667022686158, + "eval_NEIMS_exact_mols": 0.04836666666666667, + "eval_NEIMS_exact_smiles": 0.04683333333333333, + "eval_NEIMS_loss": 0.22870874404907227, + "eval_NEIMS_matched_formulas": 0.5432333333333333, + "eval_NEIMS_morgan_tanimoto_simil": 0.3513279231285358, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.04861666666666667, + "eval_NEIMS_runtime": 736.5216, + "eval_NEIMS_samples_per_second": 81.464, + "eval_NEIMS_steps_per_second": 1.274, "step": 80000 }, { - "epoch": 0.71, - "eval_RASSP_canon_smiles": 0.9306608341403145, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.12171502988613217, - "eval_RASSP_daylight_tanimoto_simil": 0.5728757311086445, - "eval_RASSP_exact_mols": 0.1210638795204862, - "eval_RASSP_exact_smiles": 0.11730724279560557, - "eval_RASSP_loss": 0.16591234505176544, - "eval_RASSP_matched_formulas": 0.7293551941763783, - "eval_RASSP_morgan_tanimoto_simil": 0.44149813310147595, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.12113066417337295, - "eval_RASSP_runtime": 819.4147, - "eval_RASSP_samples_per_second": 73.094, - "eval_RASSP_steps_per_second": 1.142, + "epoch": 0.18, + "eval_RASSP_canon_smiles": 0.9400106855444619, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.07115904765084984, + "eval_RASSP_daylight_tanimoto_simil": 0.5241805887603844, + "eval_RASSP_exact_mols": 0.07089190903930277, + "eval_RASSP_exact_smiles": 0.06870471165726116, + "eval_RASSP_loss": 0.19560155272483826, + "eval_RASSP_matched_formulas": 0.6866964971449561, + "eval_RASSP_morgan_tanimoto_simil": 0.3849319936707296, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.07097538985541123, + "eval_RASSP_runtime": 830.5396, + "eval_RASSP_samples_per_second": 72.115, + "eval_RASSP_steps_per_second": 1.127, "step": 80000 }, { - "epoch": 0.71, - "eval_NIST_canon_smiles": 0.8830251623664691, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.012740887958263832, - "eval_NIST_daylight_tanimoto_simil": 0.2658825257202243, - "eval_NIST_exact_mols": 0.012066579124818113, - "eval_NIST_exact_smiles": 0.01107286084395074, - "eval_NIST_loss": 1.4652163982391357, - "eval_NIST_matched_formulas": 0.08137842921531746, - "eval_NIST_morgan_tanimoto_simil": 0.22094277641876273, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01266990808105902, - "eval_NIST_runtime": 497.5527, - "eval_NIST_samples_per_second": 56.631, - "eval_NIST_steps_per_second": 0.886, + "epoch": 0.18, + "eval_NEIMS_old_canon_smiles": 0.9411666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.046533333333333336, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.44859899773813644, + "eval_NEIMS_old_exact_mols": 0.0464, + "eval_NEIMS_old_exact_smiles": 0.045, + "eval_NEIMS_old_loss": 0.22890639305114746, + "eval_NEIMS_old_matched_formulas": 0.5366333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.3509535040462155, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.0466, + "eval_NEIMS_old_runtime": 369.713, + "eval_NEIMS_old_samples_per_second": 81.144, + "eval_NEIMS_old_steps_per_second": 1.269, "step": 80000 }, { - "epoch": 0.71, - "learning_rate": 1.4427979461309794e-05, - "loss": 0.1916, + "epoch": 0.18, + "eval_RASSP_old_canon_smiles": 0.936496813161144, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.08232388961190643, + "eval_RASSP_old_daylight_tanimoto_simil": 0.5363767523512335, + "eval_RASSP_old_exact_mols": 0.08192344912737344, + "eval_RASSP_old_exact_smiles": 0.07922047585677579, + "eval_RASSP_old_loss": 0.1869024783372879, + "eval_RASSP_old_matched_formulas": 0.7012046584576367, + "eval_RASSP_old_morgan_tanimoto_simil": 0.3991348888794767, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.08199018920812894, + "eval_RASSP_old_runtime": 413.6781, + "eval_RASSP_old_samples_per_second": 72.44, + "eval_RASSP_old_steps_per_second": 1.134, + "step": 80000 + }, + { + "epoch": 0.18, + "eval_NIST_canon_smiles": 0.8857578876388544, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.013947545870745644, + "eval_NIST_daylight_tanimoto_simil": 0.2685925928357821, + "eval_NIST_exact_mols": 0.013166767221492707, + "eval_NIST_exact_smiles": 0.012173048940625333, + "eval_NIST_loss": 1.8574224710464478, + "eval_NIST_matched_formulas": 0.08066863044326933, + "eval_NIST_morgan_tanimoto_simil": 0.22136583173749372, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.013557156546119175, + "eval_NIST_runtime": 474.6805, + "eval_NIST_samples_per_second": 59.36, + "eval_NIST_steps_per_second": 0.929, + "step": 80000 + }, + { + "epoch": 0.18, + "learning_rate": 4.116619315004139e-05, + "loss": 0.2205, "step": 80010 }, { - "epoch": 0.71, - "learning_rate": 1.442347536257995e-05, - "loss": 0.1936, + "epoch": 0.18, + "learning_rate": 4.116507460683207e-05, + "loss": 0.221, "step": 80020 }, { - "epoch": 0.71, - "learning_rate": 1.4418971263850103e-05, - "loss": 0.1983, + "epoch": 0.18, + "learning_rate": 4.116395606362274e-05, + "loss": 0.2204, "step": 80030 }, { - "epoch": 0.71, - "learning_rate": 1.4414467165120261e-05, - "loss": 0.1966, + "epoch": 0.18, + "learning_rate": 4.116283752041342e-05, + "loss": 0.2231, "step": 80040 }, { - "epoch": 0.71, - "learning_rate": 1.4409963066390417e-05, - "loss": 0.1965, + "epoch": 0.18, + "learning_rate": 4.116171897720409e-05, + "loss": 0.2223, "step": 80050 }, { - "epoch": 0.71, - "learning_rate": 1.440545896766057e-05, - "loss": 0.197, + "epoch": 0.18, + "learning_rate": 4.1160600433994766e-05, + "loss": 0.2234, "step": 80060 }, { - "epoch": 0.71, - "learning_rate": 1.4400954868930727e-05, - "loss": 0.1922, + "epoch": 0.18, + "learning_rate": 4.1159481890785444e-05, + "loss": 0.2192, "step": 80070 }, { - "epoch": 0.71, - "learning_rate": 1.4396450770200884e-05, - "loss": 0.1991, + "epoch": 0.18, + "learning_rate": 4.1158363347576115e-05, + "loss": 0.2203, "step": 80080 }, { - "epoch": 0.72, - "learning_rate": 1.439194667147104e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.115724480436679e-05, + "loss": 0.2201, "step": 80090 }, { - "epoch": 0.72, - "learning_rate": 1.4387442572741194e-05, - "loss": 0.1965, + "epoch": 0.18, + "learning_rate": 4.115612626115747e-05, + "loss": 0.2235, "step": 80100 }, { - "epoch": 0.72, - "learning_rate": 1.4382938474011351e-05, - "loss": 0.1991, + "epoch": 0.18, + "learning_rate": 4.115500771794815e-05, + "loss": 0.2237, "step": 80110 }, { - "epoch": 0.72, - "learning_rate": 1.4378434375281507e-05, - "loss": 0.1903, + "epoch": 0.18, + "learning_rate": 4.115388917473883e-05, + "loss": 0.2209, "step": 80120 }, { - "epoch": 0.72, - "learning_rate": 1.4373930276551661e-05, - "loss": 0.1976, + "epoch": 0.18, + "learning_rate": 4.11527706315295e-05, + "loss": 0.2192, "step": 80130 }, { - "epoch": 0.72, - "learning_rate": 1.4369426177821819e-05, - "loss": 0.1935, + "epoch": 0.18, + "learning_rate": 4.1151652088320176e-05, + "loss": 0.2187, "step": 80140 }, { - "epoch": 0.72, - "learning_rate": 1.4364922079091975e-05, - "loss": 0.2009, + "epoch": 0.18, + "learning_rate": 4.115053354511085e-05, + "loss": 0.2164, "step": 80150 }, { - "epoch": 0.72, - "learning_rate": 1.4360417980362132e-05, - "loss": 0.1994, + "epoch": 0.18, + "learning_rate": 4.1149415001901525e-05, + "loss": 0.2201, "step": 80160 }, { - "epoch": 0.72, - "learning_rate": 1.4355913881632285e-05, - "loss": 0.1943, + "epoch": 0.18, + "learning_rate": 4.11482964586922e-05, + "loss": 0.2227, "step": 80170 }, { - "epoch": 0.72, - "learning_rate": 1.4351409782902442e-05, - "loss": 0.1922, + "epoch": 0.18, + "learning_rate": 4.1147177915482874e-05, + "loss": 0.2178, "step": 80180 }, { - "epoch": 0.72, - "learning_rate": 1.4346905684172598e-05, - "loss": 0.1975, + "epoch": 0.18, + "learning_rate": 4.114605937227355e-05, + "loss": 0.2158, "step": 80190 }, { - "epoch": 0.72, - "learning_rate": 1.4342401585442752e-05, - "loss": 0.1924, + "epoch": 0.18, + "learning_rate": 4.114494082906423e-05, + "loss": 0.2182, "step": 80200 }, { - "epoch": 0.72, - "learning_rate": 1.433789748671291e-05, - "loss": 0.1952, + "epoch": 0.18, + "learning_rate": 4.114382228585491e-05, + "loss": 0.2183, "step": 80210 }, { - "epoch": 0.72, - "learning_rate": 1.4333393387983065e-05, - "loss": 0.2005, + "epoch": 0.18, + "learning_rate": 4.1142703742645586e-05, + "loss": 0.2228, "step": 80220 }, { - "epoch": 0.72, - "learning_rate": 1.4328889289253223e-05, - "loss": 0.1913, + "epoch": 0.18, + "learning_rate": 4.114158519943626e-05, + "loss": 0.2208, "step": 80230 }, { - "epoch": 0.72, - "learning_rate": 1.4324385190523377e-05, - "loss": 0.1877, + "epoch": 0.18, + "learning_rate": 4.1140466656226935e-05, + "loss": 0.2267, "step": 80240 }, { - "epoch": 0.72, - "learning_rate": 1.4319881091793533e-05, - "loss": 0.1959, + "epoch": 0.18, + "learning_rate": 4.1139348113017606e-05, + "loss": 0.2187, "step": 80250 }, { - "epoch": 0.72, - "learning_rate": 1.431537699306369e-05, - "loss": 0.2045, + "epoch": 0.18, + "learning_rate": 4.1138229569808284e-05, + "loss": 0.2181, "step": 80260 }, { - "epoch": 0.72, - "learning_rate": 1.4310872894333843e-05, - "loss": 0.2024, + "epoch": 0.18, + "learning_rate": 4.1137111026598955e-05, + "loss": 0.223, "step": 80270 }, { - "epoch": 0.72, - "learning_rate": 1.4306368795604e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.113599248338963e-05, + "loss": 0.2203, "step": 80280 }, { - "epoch": 0.72, - "learning_rate": 1.4301864696874156e-05, - "loss": 0.1975, + "epoch": 0.18, + "learning_rate": 4.113487394018031e-05, + "loss": 0.22, "step": 80290 }, { - "epoch": 0.72, - "learning_rate": 1.4297360598144313e-05, - "loss": 0.1943, + "epoch": 0.18, + "learning_rate": 4.113375539697098e-05, + "loss": 0.2214, "step": 80300 }, { - "epoch": 0.72, - "learning_rate": 1.4292856499414467e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.113263685376167e-05, + "loss": 0.221, "step": 80310 }, { - "epoch": 0.72, - "learning_rate": 1.4288352400684623e-05, - "loss": 0.1922, + "epoch": 0.18, + "learning_rate": 4.113151831055234e-05, + "loss": 0.2202, "step": 80320 }, { - "epoch": 0.72, - "learning_rate": 1.428384830195478e-05, - "loss": 0.1916, + "epoch": 0.18, + "learning_rate": 4.1130399767343016e-05, + "loss": 0.2166, "step": 80330 }, { - "epoch": 0.72, - "learning_rate": 1.4279344203224935e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.1129281224133694e-05, + "loss": 0.2249, "step": 80340 }, { - "epoch": 0.72, - "learning_rate": 1.427484010449509e-05, - "loss": 0.1947, + "epoch": 0.18, + "learning_rate": 4.1128162680924365e-05, + "loss": 0.2169, "step": 80350 }, { - "epoch": 0.72, - "learning_rate": 1.4270336005765248e-05, - "loss": 0.1938, + "epoch": 0.18, + "learning_rate": 4.112704413771504e-05, + "loss": 0.2205, "step": 80360 }, { - "epoch": 0.72, - "learning_rate": 1.4265831907035404e-05, - "loss": 0.1992, + "epoch": 0.18, + "learning_rate": 4.1125925594505714e-05, + "loss": 0.213, "step": 80370 }, { - "epoch": 0.72, - "learning_rate": 1.4261327808305558e-05, - "loss": 0.1995, + "epoch": 0.18, + "learning_rate": 4.112480705129639e-05, + "loss": 0.2243, "step": 80380 }, { - "epoch": 0.72, - "learning_rate": 1.4256823709575714e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.112368850808707e-05, + "loss": 0.2226, "step": 80390 }, { - "epoch": 0.72, - "learning_rate": 1.4252319610845871e-05, - "loss": 0.1897, + "epoch": 0.18, + "learning_rate": 4.112256996487774e-05, + "loss": 0.2171, "step": 80400 }, { - "epoch": 0.72, - "learning_rate": 1.4247815512116025e-05, - "loss": 0.2022, + "epoch": 0.18, + "learning_rate": 4.112145142166842e-05, + "loss": 0.2194, "step": 80410 }, { - "epoch": 0.72, - "learning_rate": 1.4243311413386181e-05, - "loss": 0.1969, + "epoch": 0.18, + "learning_rate": 4.11203328784591e-05, + "loss": 0.2194, "step": 80420 }, { - "epoch": 0.72, - "learning_rate": 1.4238807314656339e-05, - "loss": 0.1914, + "epoch": 0.18, + "learning_rate": 4.1119214335249775e-05, + "loss": 0.2196, "step": 80430 }, { - "epoch": 0.72, - "learning_rate": 1.4234303215926495e-05, - "loss": 0.192, + "epoch": 0.18, + "learning_rate": 4.111809579204045e-05, + "loss": 0.2182, "step": 80440 }, { - "epoch": 0.72, - "learning_rate": 1.4229799117196649e-05, - "loss": 0.1907, + "epoch": 0.18, + "learning_rate": 4.1116977248831124e-05, + "loss": 0.2194, "step": 80450 }, { - "epoch": 0.72, - "learning_rate": 1.4225295018466806e-05, - "loss": 0.19, + "epoch": 0.18, + "learning_rate": 4.11158587056218e-05, + "loss": 0.2177, "step": 80460 }, { - "epoch": 0.72, - "learning_rate": 1.4220790919736962e-05, - "loss": 0.2, + "epoch": 0.18, + "learning_rate": 4.111474016241247e-05, + "loss": 0.224, "step": 80470 }, { - "epoch": 0.72, - "learning_rate": 1.4216286821007116e-05, - "loss": 0.1979, + "epoch": 0.18, + "learning_rate": 4.111362161920315e-05, + "loss": 0.213, "step": 80480 }, { - "epoch": 0.72, - "learning_rate": 1.4211782722277272e-05, - "loss": 0.1969, + "epoch": 0.18, + "learning_rate": 4.111250307599383e-05, + "loss": 0.2166, "step": 80490 }, { - "epoch": 0.72, - "learning_rate": 1.420727862354743e-05, - "loss": 0.1936, + "epoch": 0.18, + "learning_rate": 4.11113845327845e-05, + "loss": 0.2208, "step": 80500 }, { - "epoch": 0.72, - "learning_rate": 1.4202774524817585e-05, - "loss": 0.1972, + "epoch": 0.18, + "learning_rate": 4.111026598957518e-05, + "loss": 0.2212, "step": 80510 }, { - "epoch": 0.72, - "learning_rate": 1.419827042608774e-05, - "loss": 0.193, + "epoch": 0.18, + "learning_rate": 4.1109147446365856e-05, + "loss": 0.215, "step": 80520 }, { - "epoch": 0.72, - "learning_rate": 1.4193766327357897e-05, - "loss": 0.1923, + "epoch": 0.18, + "learning_rate": 4.1108028903156534e-05, + "loss": 0.2144, "step": 80530 }, { - "epoch": 0.72, - "learning_rate": 1.4189262228628053e-05, - "loss": 0.1965, + "epoch": 0.18, + "learning_rate": 4.110691035994721e-05, + "loss": 0.2193, "step": 80540 }, { - "epoch": 0.72, - "learning_rate": 1.4184758129898207e-05, - "loss": 0.1976, + "epoch": 0.18, + "learning_rate": 4.110579181673788e-05, + "loss": 0.222, "step": 80550 }, { - "epoch": 0.72, - "learning_rate": 1.4180254031168364e-05, - "loss": 0.1916, + "epoch": 0.18, + "learning_rate": 4.110467327352856e-05, + "loss": 0.2191, "step": 80560 }, { - "epoch": 0.72, - "learning_rate": 1.417574993243852e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.110355473031923e-05, + "loss": 0.2233, "step": 80570 }, { - "epoch": 0.72, - "learning_rate": 1.4171245833708677e-05, - "loss": 0.1934, + "epoch": 0.18, + "learning_rate": 4.110243618710991e-05, + "loss": 0.2179, "step": 80580 }, { - "epoch": 0.72, - "learning_rate": 1.416674173497883e-05, - "loss": 0.1992, + "epoch": 0.18, + "learning_rate": 4.110131764390058e-05, + "loss": 0.2189, "step": 80590 }, { - "epoch": 0.72, - "learning_rate": 1.4162237636248987e-05, - "loss": 0.1982, + "epoch": 0.18, + "learning_rate": 4.110019910069126e-05, + "loss": 0.2239, "step": 80600 }, { - "epoch": 0.72, - "learning_rate": 1.4157733537519143e-05, - "loss": 0.1983, + "epoch": 0.18, + "learning_rate": 4.109908055748194e-05, + "loss": 0.228, "step": 80610 }, { - "epoch": 0.72, - "learning_rate": 1.4153229438789297e-05, - "loss": 0.201, + "epoch": 0.18, + "learning_rate": 4.1097962014272615e-05, + "loss": 0.2122, "step": 80620 }, { - "epoch": 0.72, - "learning_rate": 1.4148725340059455e-05, - "loss": 0.202, + "epoch": 0.18, + "learning_rate": 4.109684347106329e-05, + "loss": 0.2169, "step": 80630 }, { - "epoch": 0.72, - "learning_rate": 1.414422124132961e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.1095724927853964e-05, + "loss": 0.2221, "step": 80640 }, { - "epoch": 0.72, - "learning_rate": 1.4139717142599768e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.109460638464464e-05, + "loss": 0.2204, "step": 80650 }, { - "epoch": 0.72, - "learning_rate": 1.4135213043869922e-05, - "loss": 0.197, + "epoch": 0.18, + "learning_rate": 4.109348784143532e-05, + "loss": 0.219, "step": 80660 }, { - "epoch": 0.72, - "learning_rate": 1.4130708945140078e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.109236929822599e-05, + "loss": 0.2235, "step": 80670 }, { - "epoch": 0.72, - "learning_rate": 1.4126204846410235e-05, - "loss": 0.191, + "epoch": 0.18, + "learning_rate": 4.109125075501667e-05, + "loss": 0.2176, "step": 80680 }, { - "epoch": 0.72, - "learning_rate": 1.412170074768039e-05, - "loss": 0.1962, + "epoch": 0.18, + "learning_rate": 4.109013221180734e-05, + "loss": 0.2183, "step": 80690 }, { - "epoch": 0.72, - "learning_rate": 1.4117196648950545e-05, - "loss": 0.1996, + "epoch": 0.18, + "learning_rate": 4.108901366859802e-05, + "loss": 0.2137, "step": 80700 }, { - "epoch": 0.72, - "learning_rate": 1.4112692550220701e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.1087895125388696e-05, + "loss": 0.2163, "step": 80710 }, { - "epoch": 0.72, - "learning_rate": 1.4108188451490859e-05, - "loss": 0.1954, + "epoch": 0.18, + "learning_rate": 4.1086776582179374e-05, + "loss": 0.2183, "step": 80720 }, { - "epoch": 0.72, - "learning_rate": 1.4103684352761013e-05, - "loss": 0.1929, + "epoch": 0.18, + "learning_rate": 4.108565803897005e-05, + "loss": 0.2159, "step": 80730 }, { - "epoch": 0.72, - "learning_rate": 1.4099180254031168e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.108453949576072e-05, + "loss": 0.2199, "step": 80740 }, { - "epoch": 0.72, - "learning_rate": 1.4094676155301326e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.10834209525514e-05, + "loss": 0.2235, "step": 80750 }, { - "epoch": 0.72, - "learning_rate": 1.409017205657148e-05, - "loss": 0.1894, + "epoch": 0.18, + "learning_rate": 4.108230240934208e-05, + "loss": 0.2244, "step": 80760 }, { - "epoch": 0.72, - "learning_rate": 1.4085667957841636e-05, - "loss": 0.1953, + "epoch": 0.18, + "learning_rate": 4.108118386613275e-05, + "loss": 0.2215, "step": 80770 }, { - "epoch": 0.72, - "learning_rate": 1.4081163859111793e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.108006532292343e-05, + "loss": 0.2125, "step": 80780 }, { - "epoch": 0.72, - "learning_rate": 1.407665976038195e-05, - "loss": 0.1959, + "epoch": 0.18, + "learning_rate": 4.10789467797141e-05, + "loss": 0.2253, "step": 80790 }, { - "epoch": 0.72, - "learning_rate": 1.4072155661652103e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.107782823650478e-05, + "loss": 0.2164, "step": 80800 }, { - "epoch": 0.72, - "learning_rate": 1.406765156292226e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.1076709693295455e-05, + "loss": 0.2245, "step": 80810 }, { - "epoch": 0.72, - "learning_rate": 1.4063147464192417e-05, - "loss": 0.1974, + "epoch": 0.18, + "learning_rate": 4.1075591150086126e-05, + "loss": 0.2198, "step": 80820 }, { - "epoch": 0.72, - "learning_rate": 1.405864336546257e-05, - "loss": 0.1953, + "epoch": 0.18, + "learning_rate": 4.1074472606876804e-05, + "loss": 0.2164, "step": 80830 }, { - "epoch": 0.72, - "learning_rate": 1.4054139266732726e-05, - "loss": 0.1918, + "epoch": 0.18, + "learning_rate": 4.107335406366748e-05, + "loss": 0.2242, "step": 80840 }, { - "epoch": 0.72, - "learning_rate": 1.4049635168002884e-05, - "loss": 0.196, + "epoch": 0.18, + "learning_rate": 4.107223552045816e-05, + "loss": 0.2169, "step": 80850 }, { - "epoch": 0.72, - "learning_rate": 1.404513106927304e-05, - "loss": 0.1956, + "epoch": 0.18, + "learning_rate": 4.107111697724884e-05, + "loss": 0.2189, "step": 80860 }, { - "epoch": 0.72, - "learning_rate": 1.4040626970543194e-05, - "loss": 0.191, + "epoch": 0.18, + "learning_rate": 4.106999843403951e-05, + "loss": 0.2107, "step": 80870 }, { - "epoch": 0.72, - "learning_rate": 1.4036122871813351e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.106887989083019e-05, + "loss": 0.2235, "step": 80880 }, { - "epoch": 0.72, - "learning_rate": 1.4031618773083507e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.106776134762086e-05, + "loss": 0.217, "step": 80890 }, { - "epoch": 0.72, - "learning_rate": 1.4027114674353661e-05, - "loss": 0.2011, + "epoch": 0.18, + "learning_rate": 4.1066642804411536e-05, + "loss": 0.2191, "step": 80900 }, { - "epoch": 0.72, - "learning_rate": 1.4022610575623819e-05, - "loss": 0.1894, + "epoch": 0.18, + "learning_rate": 4.106552426120221e-05, + "loss": 0.2219, "step": 80910 }, { - "epoch": 0.72, - "learning_rate": 1.4018106476893975e-05, - "loss": 0.1949, + "epoch": 0.18, + "learning_rate": 4.1064405717992885e-05, + "loss": 0.215, "step": 80920 }, { - "epoch": 0.72, - "learning_rate": 1.4013602378164132e-05, - "loss": 0.1943, + "epoch": 0.18, + "learning_rate": 4.106328717478356e-05, + "loss": 0.2183, "step": 80930 }, { - "epoch": 0.72, - "learning_rate": 1.4009098279434284e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.106216863157424e-05, + "loss": 0.2215, "step": 80940 }, { - "epoch": 0.72, - "learning_rate": 1.4004594180704442e-05, - "loss": 0.196, + "epoch": 0.18, + "learning_rate": 4.106105008836492e-05, + "loss": 0.218, "step": 80950 }, { - "epoch": 0.72, - "learning_rate": 1.4000090081974598e-05, - "loss": 0.1907, + "epoch": 0.18, + "learning_rate": 4.105993154515559e-05, + "loss": 0.2209, "step": 80960 }, { - "epoch": 0.72, - "learning_rate": 1.3995585983244752e-05, - "loss": 0.1898, + "epoch": 0.18, + "learning_rate": 4.105881300194627e-05, + "loss": 0.2122, "step": 80970 }, { - "epoch": 0.72, - "learning_rate": 1.399108188451491e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.1057694458736946e-05, + "loss": 0.2252, "step": 80980 }, { - "epoch": 0.72, - "learning_rate": 1.3986577785785065e-05, - "loss": 0.1869, + "epoch": 0.18, + "learning_rate": 4.105657591552762e-05, + "loss": 0.2264, "step": 80990 }, { - "epoch": 0.72, - "learning_rate": 1.3982073687055223e-05, - "loss": 0.1942, + "epoch": 0.18, + "learning_rate": 4.1055457372318295e-05, + "loss": 0.2196, "step": 81000 }, { - "epoch": 0.72, - "learning_rate": 1.3977569588325377e-05, - "loss": 0.1874, + "epoch": 0.18, + "learning_rate": 4.1054338829108966e-05, + "loss": 0.2252, "step": 81010 }, { - "epoch": 0.72, - "learning_rate": 1.3973065489595533e-05, - "loss": 0.1959, + "epoch": 0.18, + "learning_rate": 4.1053220285899644e-05, + "loss": 0.221, "step": 81020 }, { - "epoch": 0.72, - "learning_rate": 1.396856139086569e-05, - "loss": 0.1933, + "epoch": 0.18, + "learning_rate": 4.105210174269032e-05, + "loss": 0.2209, "step": 81030 }, { - "epoch": 0.72, - "learning_rate": 1.3964057292135842e-05, - "loss": 0.1962, + "epoch": 0.18, + "learning_rate": 4.1050983199481e-05, + "loss": 0.2165, "step": 81040 }, { - "epoch": 0.72, - "learning_rate": 1.3959553193406e-05, - "loss": 0.1959, + "epoch": 0.18, + "learning_rate": 4.104986465627168e-05, + "loss": 0.2151, "step": 81050 }, { - "epoch": 0.72, - "learning_rate": 1.3955049094676156e-05, - "loss": 0.1922, + "epoch": 0.18, + "learning_rate": 4.104874611306235e-05, + "loss": 0.219, "step": 81060 }, { - "epoch": 0.72, - "learning_rate": 1.3950544995946313e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.104762756985303e-05, + "loss": 0.2203, "step": 81070 }, { - "epoch": 0.72, - "learning_rate": 1.3946040897216467e-05, - "loss": 0.1994, + "epoch": 0.18, + "learning_rate": 4.1046509026643705e-05, + "loss": 0.2161, "step": 81080 }, { - "epoch": 0.72, - "learning_rate": 1.3941536798486623e-05, - "loss": 0.1922, + "epoch": 0.18, + "learning_rate": 4.1045390483434376e-05, + "loss": 0.2169, "step": 81090 }, { - "epoch": 0.72, - "learning_rate": 1.393703269975678e-05, - "loss": 0.192, + "epoch": 0.18, + "learning_rate": 4.1044271940225054e-05, + "loss": 0.2186, "step": 81100 }, { - "epoch": 0.72, - "learning_rate": 1.3932528601026935e-05, - "loss": 0.2026, + "epoch": 0.18, + "learning_rate": 4.1043153397015725e-05, + "loss": 0.2239, "step": 81110 }, { - "epoch": 0.72, - "learning_rate": 1.392802450229709e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.10420348538064e-05, + "loss": 0.2197, "step": 81120 }, { - "epoch": 0.72, - "learning_rate": 1.3923520403567248e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.104091631059708e-05, + "loss": 0.2214, "step": 81130 }, { - "epoch": 0.72, - "learning_rate": 1.3919016304837404e-05, - "loss": 0.192, + "epoch": 0.18, + "learning_rate": 4.103979776738776e-05, + "loss": 0.2178, "step": 81140 }, { - "epoch": 0.72, - "learning_rate": 1.3914512206107558e-05, - "loss": 0.197, + "epoch": 0.18, + "learning_rate": 4.1038679224178437e-05, + "loss": 0.2179, "step": 81150 }, { - "epoch": 0.72, - "learning_rate": 1.3910008107377714e-05, - "loss": 0.2011, + "epoch": 0.18, + "learning_rate": 4.103756068096911e-05, + "loss": 0.222, "step": 81160 }, { - "epoch": 0.72, - "learning_rate": 1.3905504008647871e-05, - "loss": 0.1933, + "epoch": 0.18, + "learning_rate": 4.1036442137759786e-05, + "loss": 0.2186, "step": 81170 }, { - "epoch": 0.72, - "learning_rate": 1.3900999909918025e-05, - "loss": 0.1957, + "epoch": 0.18, + "learning_rate": 4.1035323594550464e-05, + "loss": 0.2204, "step": 81180 }, { - "epoch": 0.72, - "learning_rate": 1.3896495811188181e-05, - "loss": 0.1995, + "epoch": 0.18, + "learning_rate": 4.1034205051341135e-05, + "loss": 0.2215, "step": 81190 }, { - "epoch": 0.72, - "learning_rate": 1.3891991712458339e-05, - "loss": 0.1938, + "epoch": 0.18, + "learning_rate": 4.103308650813181e-05, + "loss": 0.214, "step": 81200 }, { - "epoch": 0.73, - "learning_rate": 1.3887487613728494e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.1031967964922484e-05, + "loss": 0.2161, "step": 81210 }, { - "epoch": 0.73, - "learning_rate": 1.3882983514998648e-05, - "loss": 0.1967, + "epoch": 0.18, + "learning_rate": 4.103084942171316e-05, + "loss": 0.221, "step": 81220 }, { - "epoch": 0.73, - "learning_rate": 1.3878479416268806e-05, - "loss": 0.1951, + "epoch": 0.18, + "learning_rate": 4.102973087850383e-05, + "loss": 0.224, "step": 81230 }, { - "epoch": 0.73, - "learning_rate": 1.3873975317538962e-05, - "loss": 0.1953, + "epoch": 0.18, + "learning_rate": 4.102861233529451e-05, + "loss": 0.2177, "step": 81240 }, { - "epoch": 0.73, - "learning_rate": 1.3869471218809116e-05, - "loss": 0.1942, + "epoch": 0.18, + "learning_rate": 4.102749379208519e-05, + "loss": 0.2172, "step": 81250 }, { - "epoch": 0.73, - "learning_rate": 1.3864967120079272e-05, - "loss": 0.2024, + "epoch": 0.18, + "learning_rate": 4.102637524887587e-05, + "loss": 0.2217, "step": 81260 }, { - "epoch": 0.73, - "learning_rate": 1.386046302134943e-05, - "loss": 0.1981, + "epoch": 0.18, + "learning_rate": 4.1025256705666545e-05, + "loss": 0.222, "step": 81270 }, { - "epoch": 0.73, - "learning_rate": 1.3855958922619585e-05, - "loss": 0.2014, + "epoch": 0.18, + "learning_rate": 4.1024138162457216e-05, + "loss": 0.2264, "step": 81280 }, { - "epoch": 0.73, - "learning_rate": 1.3851454823889739e-05, - "loss": 0.196, + "epoch": 0.18, + "learning_rate": 4.1023019619247894e-05, + "loss": 0.2205, "step": 81290 }, { - "epoch": 0.73, - "learning_rate": 1.3846950725159897e-05, - "loss": 0.1972, + "epoch": 0.18, + "learning_rate": 4.102190107603857e-05, + "loss": 0.2197, "step": 81300 }, { - "epoch": 0.73, - "learning_rate": 1.3842446626430052e-05, - "loss": 0.1946, + "epoch": 0.18, + "learning_rate": 4.102078253282924e-05, + "loss": 0.2192, "step": 81310 }, { - "epoch": 0.73, - "learning_rate": 1.3837942527700206e-05, - "loss": 0.1991, + "epoch": 0.18, + "learning_rate": 4.101966398961992e-05, + "loss": 0.2247, "step": 81320 }, { - "epoch": 0.73, - "learning_rate": 1.3833438428970364e-05, - "loss": 0.1957, + "epoch": 0.18, + "learning_rate": 4.101854544641059e-05, + "loss": 0.222, "step": 81330 }, { - "epoch": 0.73, - "learning_rate": 1.382893433024052e-05, - "loss": 0.2002, + "epoch": 0.18, + "learning_rate": 4.101742690320127e-05, + "loss": 0.2168, "step": 81340 }, { - "epoch": 0.73, - "learning_rate": 1.3824430231510677e-05, - "loss": 0.1921, + "epoch": 0.18, + "learning_rate": 4.101630835999195e-05, + "loss": 0.21, "step": 81350 }, { - "epoch": 0.73, - "learning_rate": 1.381992613278083e-05, - "loss": 0.2011, + "epoch": 0.18, + "learning_rate": 4.1015189816782626e-05, + "loss": 0.22, "step": 81360 }, { - "epoch": 0.73, - "learning_rate": 1.3815422034050987e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.1014071273573304e-05, + "loss": 0.2212, "step": 81370 }, { - "epoch": 0.73, - "learning_rate": 1.3810917935321143e-05, - "loss": 0.1915, + "epoch": 0.18, + "learning_rate": 4.1012952730363975e-05, + "loss": 0.2181, "step": 81380 }, { - "epoch": 0.73, - "learning_rate": 1.3806413836591297e-05, - "loss": 0.1913, + "epoch": 0.18, + "learning_rate": 4.101183418715465e-05, + "loss": 0.2163, "step": 81390 }, { - "epoch": 0.73, - "learning_rate": 1.3801909737861455e-05, - "loss": 0.1935, + "epoch": 0.18, + "learning_rate": 4.101071564394533e-05, + "loss": 0.2136, "step": 81400 }, { - "epoch": 0.73, - "learning_rate": 1.379740563913161e-05, - "loss": 0.1989, + "epoch": 0.18, + "learning_rate": 4.1009597100736e-05, + "loss": 0.2181, "step": 81410 }, { - "epoch": 0.73, - "learning_rate": 1.3792901540401768e-05, - "loss": 0.1996, + "epoch": 0.18, + "learning_rate": 4.100847855752668e-05, + "loss": 0.2141, "step": 81420 }, { - "epoch": 0.73, - "learning_rate": 1.3788397441671922e-05, - "loss": 0.1957, + "epoch": 0.18, + "learning_rate": 4.100736001431735e-05, + "loss": 0.2153, "step": 81430 }, { - "epoch": 0.73, - "learning_rate": 1.3783893342942078e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.100624147110803e-05, + "loss": 0.2201, "step": 81440 }, { - "epoch": 0.73, - "learning_rate": 1.3779389244212235e-05, - "loss": 0.1995, + "epoch": 0.18, + "learning_rate": 4.100512292789871e-05, + "loss": 0.2212, "step": 81450 }, { - "epoch": 0.73, - "learning_rate": 1.377488514548239e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.1004004384689385e-05, + "loss": 0.2134, "step": 81460 }, { - "epoch": 0.73, - "learning_rate": 1.3770381046752545e-05, - "loss": 0.1923, + "epoch": 0.18, + "learning_rate": 4.100299769580099e-05, + "loss": 0.2148, "step": 81470 }, { - "epoch": 0.73, - "learning_rate": 1.3765876948022703e-05, - "loss": 0.1943, + "epoch": 0.18, + "learning_rate": 4.1001879152591665e-05, + "loss": 0.2142, "step": 81480 }, { - "epoch": 0.73, - "learning_rate": 1.3761372849292858e-05, - "loss": 0.1944, + "epoch": 0.18, + "learning_rate": 4.100076060938234e-05, + "loss": 0.22, "step": 81490 }, { - "epoch": 0.73, - "learning_rate": 1.3756868750563013e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.0999642066173014e-05, + "loss": 0.2206, "step": 81500 }, { - "epoch": 0.73, - "learning_rate": 1.3752364651833168e-05, - "loss": 0.1911, + "epoch": 0.18, + "learning_rate": 4.099852352296369e-05, + "loss": 0.2172, "step": 81510 }, { - "epoch": 0.73, - "learning_rate": 1.3747860553103326e-05, - "loss": 0.1896, + "epoch": 0.18, + "learning_rate": 4.099740497975437e-05, + "loss": 0.2205, "step": 81520 }, { - "epoch": 0.73, - "learning_rate": 1.374335645437348e-05, - "loss": 0.1914, + "epoch": 0.18, + "learning_rate": 4.099628643654505e-05, + "loss": 0.2212, "step": 81530 }, { - "epoch": 0.73, - "learning_rate": 1.3738852355643636e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.0995167893335725e-05, + "loss": 0.2208, "step": 81540 }, { - "epoch": 0.73, - "learning_rate": 1.3734348256913793e-05, - "loss": 0.1873, + "epoch": 0.18, + "learning_rate": 4.0994049350126396e-05, + "loss": 0.2213, "step": 81550 }, { - "epoch": 0.73, - "learning_rate": 1.3729844158183949e-05, - "loss": 0.1898, + "epoch": 0.18, + "learning_rate": 4.0992930806917074e-05, + "loss": 0.2165, "step": 81560 }, { - "epoch": 0.73, - "learning_rate": 1.3725340059454103e-05, - "loss": 0.1969, + "epoch": 0.18, + "learning_rate": 4.099181226370775e-05, + "loss": 0.2167, "step": 81570 }, { - "epoch": 0.73, - "learning_rate": 1.372083596072426e-05, - "loss": 0.1988, + "epoch": 0.18, + "learning_rate": 4.0990693720498423e-05, + "loss": 0.2192, "step": 81580 }, { - "epoch": 0.73, - "learning_rate": 1.3716331861994416e-05, - "loss": 0.1927, + "epoch": 0.18, + "learning_rate": 4.09895751772891e-05, + "loss": 0.2209, "step": 81590 }, { - "epoch": 0.73, - "learning_rate": 1.371182776326457e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.098845663407977e-05, + "loss": 0.22, "step": 81600 }, { - "epoch": 0.73, - "learning_rate": 1.3707323664534726e-05, - "loss": 0.1942, + "epoch": 0.18, + "learning_rate": 4.098733809087045e-05, + "loss": 0.2205, "step": 81610 }, { - "epoch": 0.73, - "learning_rate": 1.3702819565804884e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.098621954766113e-05, + "loss": 0.2138, "step": 81620 }, { - "epoch": 0.73, - "learning_rate": 1.369831546707504e-05, - "loss": 0.1919, + "epoch": 0.18, + "learning_rate": 4.0985101004451806e-05, + "loss": 0.2184, "step": 81630 }, { - "epoch": 0.73, - "learning_rate": 1.3693811368345194e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.0983982461242484e-05, + "loss": 0.2209, "step": 81640 }, { - "epoch": 0.73, - "learning_rate": 1.3689307269615351e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.0982863918033155e-05, + "loss": 0.2187, "step": 81650 }, { - "epoch": 0.73, - "learning_rate": 1.3684803170885507e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.098174537482383e-05, + "loss": 0.2169, "step": 81660 }, { - "epoch": 0.73, - "learning_rate": 1.3680299072155661e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.0980626831614505e-05, + "loss": 0.2215, "step": 81670 }, { - "epoch": 0.73, - "learning_rate": 1.3675794973425819e-05, - "loss": 0.1975, + "epoch": 0.18, + "learning_rate": 4.097950828840518e-05, + "loss": 0.2186, "step": 81680 }, { - "epoch": 0.73, - "learning_rate": 1.3671290874695974e-05, - "loss": 0.1949, + "epoch": 0.18, + "learning_rate": 4.097838974519586e-05, + "loss": 0.2143, "step": 81690 }, { - "epoch": 0.73, - "learning_rate": 1.3666786775966132e-05, - "loss": 0.1945, + "epoch": 0.18, + "learning_rate": 4.097727120198653e-05, + "loss": 0.2134, "step": 81700 }, { - "epoch": 0.73, - "learning_rate": 1.3662282677236284e-05, - "loss": 0.1902, + "epoch": 0.18, + "learning_rate": 4.097615265877721e-05, + "loss": 0.2164, "step": 81710 }, { - "epoch": 0.73, - "learning_rate": 1.3657778578506442e-05, - "loss": 0.1961, + "epoch": 0.18, + "learning_rate": 4.097503411556789e-05, + "loss": 0.2188, "step": 81720 }, { - "epoch": 0.73, - "learning_rate": 1.3653274479776598e-05, - "loss": 0.1971, + "epoch": 0.18, + "learning_rate": 4.0973915572358565e-05, + "loss": 0.2164, "step": 81730 }, { - "epoch": 0.73, - "learning_rate": 1.3648770381046752e-05, - "loss": 0.194, + "epoch": 0.18, + "learning_rate": 4.097279702914924e-05, + "loss": 0.2198, "step": 81740 }, { - "epoch": 0.73, - "learning_rate": 1.364426628231691e-05, - "loss": 0.1955, + "epoch": 0.18, + "learning_rate": 4.0971678485939914e-05, + "loss": 0.2156, "step": 81750 }, { - "epoch": 0.73, - "learning_rate": 1.3639762183587065e-05, - "loss": 0.1975, + "epoch": 0.18, + "learning_rate": 4.097055994273059e-05, + "loss": 0.2157, "step": 81760 }, { - "epoch": 0.73, - "learning_rate": 1.3635258084857222e-05, - "loss": 0.1992, + "epoch": 0.18, + "learning_rate": 4.0969441399521263e-05, + "loss": 0.2206, "step": 81770 }, { - "epoch": 0.73, - "learning_rate": 1.3630753986127377e-05, - "loss": 0.202, + "epoch": 0.18, + "learning_rate": 4.096832285631194e-05, + "loss": 0.2251, "step": 81780 }, { - "epoch": 0.73, - "learning_rate": 1.3626249887397532e-05, - "loss": 0.19, + "epoch": 0.18, + "learning_rate": 4.096720431310262e-05, + "loss": 0.2271, "step": 81790 }, { - "epoch": 0.73, - "learning_rate": 1.362174578866769e-05, - "loss": 0.1977, + "epoch": 0.18, + "learning_rate": 4.096608576989329e-05, + "loss": 0.2199, "step": 81800 }, { - "epoch": 0.73, - "learning_rate": 1.3617241689937842e-05, - "loss": 0.1918, + "epoch": 0.18, + "learning_rate": 4.096496722668397e-05, + "loss": 0.2197, "step": 81810 }, { - "epoch": 0.73, - "learning_rate": 1.3612737591208e-05, - "loss": 0.1949, + "epoch": 0.18, + "learning_rate": 4.096384868347464e-05, + "loss": 0.2128, "step": 81820 }, { - "epoch": 0.73, - "learning_rate": 1.3608233492478156e-05, - "loss": 0.196, + "epoch": 0.18, + "learning_rate": 4.096273014026532e-05, + "loss": 0.2192, "step": 81830 }, { - "epoch": 0.73, - "learning_rate": 1.3603729393748313e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.0961611597056e-05, + "loss": 0.2177, "step": 81840 }, { - "epoch": 0.73, - "learning_rate": 1.3599225295018467e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.096049305384667e-05, + "loss": 0.2123, "step": 81850 }, { - "epoch": 0.73, - "learning_rate": 1.3594721196288623e-05, - "loss": 0.195, + "epoch": 0.18, + "learning_rate": 4.095937451063735e-05, + "loss": 0.2253, "step": 81860 }, { - "epoch": 0.73, - "learning_rate": 1.359021709755878e-05, - "loss": 0.1916, + "epoch": 0.18, + "learning_rate": 4.095825596742802e-05, + "loss": 0.2143, "step": 81870 }, { - "epoch": 0.73, - "learning_rate": 1.3585712998828935e-05, - "loss": 0.1954, + "epoch": 0.18, + "learning_rate": 4.09571374242187e-05, + "loss": 0.2147, "step": 81880 }, { - "epoch": 0.73, - "learning_rate": 1.358120890009909e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.095601888100938e-05, + "loss": 0.2131, "step": 81890 }, { - "epoch": 0.73, - "learning_rate": 1.3576704801369248e-05, - "loss": 0.1962, + "epoch": 0.18, + "learning_rate": 4.095490033780005e-05, + "loss": 0.2233, "step": 81900 }, { - "epoch": 0.73, - "learning_rate": 1.3572200702639404e-05, - "loss": 0.1931, + "epoch": 0.18, + "learning_rate": 4.095378179459073e-05, + "loss": 0.2206, "step": 81910 }, { - "epoch": 0.73, - "learning_rate": 1.3567696603909558e-05, - "loss": 0.1915, + "epoch": 0.18, + "learning_rate": 4.09526632513814e-05, + "loss": 0.2245, "step": 81920 }, { - "epoch": 0.73, - "learning_rate": 1.3563192505179714e-05, - "loss": 0.1908, + "epoch": 0.18, + "learning_rate": 4.0951544708172076e-05, + "loss": 0.2222, "step": 81930 }, { - "epoch": 0.73, - "learning_rate": 1.3558688406449871e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.0950426164962754e-05, + "loss": 0.2131, "step": 81940 }, { - "epoch": 0.73, - "learning_rate": 1.3554184307720025e-05, - "loss": 0.1934, + "epoch": 0.18, + "learning_rate": 4.094930762175343e-05, + "loss": 0.2161, "step": 81950 }, { - "epoch": 0.73, - "learning_rate": 1.3549680208990181e-05, - "loss": 0.1988, + "epoch": 0.18, + "learning_rate": 4.094818907854411e-05, + "loss": 0.2235, "step": 81960 }, { - "epoch": 0.73, - "learning_rate": 1.3545176110260338e-05, - "loss": 0.1912, + "epoch": 0.18, + "learning_rate": 4.094707053533478e-05, + "loss": 0.2211, "step": 81970 }, { - "epoch": 0.73, - "learning_rate": 1.3540672011530494e-05, - "loss": 0.1968, + "epoch": 0.18, + "learning_rate": 4.094595199212546e-05, + "loss": 0.2217, "step": 81980 }, { - "epoch": 0.73, - "learning_rate": 1.3536618322673633e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.094483344891613e-05, + "loss": 0.2195, "step": 81990 }, { - "epoch": 0.73, - "learning_rate": 1.353211422394379e-05, - "loss": 0.1915, + "epoch": 0.18, + "learning_rate": 4.094371490570681e-05, + "loss": 0.2216, "step": 82000 }, { - "epoch": 0.73, - "learning_rate": 1.3527610125213946e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.0942596362497486e-05, + "loss": 0.2181, "step": 82010 }, { - "epoch": 0.73, - "learning_rate": 1.35231060264841e-05, - "loss": 0.1933, + "epoch": 0.18, + "learning_rate": 4.094147781928816e-05, + "loss": 0.2178, "step": 82020 }, { - "epoch": 0.73, - "learning_rate": 1.3518601927754256e-05, - "loss": 0.1889, + "epoch": 0.18, + "learning_rate": 4.0940359276078835e-05, + "loss": 0.2177, "step": 82030 }, { - "epoch": 0.73, - "learning_rate": 1.3514097829024414e-05, - "loss": 0.1982, + "epoch": 0.18, + "learning_rate": 4.093924073286951e-05, + "loss": 0.2154, "step": 82040 }, { - "epoch": 0.73, - "learning_rate": 1.3509593730294568e-05, - "loss": 0.191, + "epoch": 0.18, + "learning_rate": 4.093812218966019e-05, + "loss": 0.2211, "step": 82050 }, { - "epoch": 0.73, - "learning_rate": 1.3505089631564723e-05, - "loss": 0.1961, + "epoch": 0.18, + "learning_rate": 4.093700364645087e-05, + "loss": 0.2152, "step": 82060 }, { - "epoch": 0.73, - "learning_rate": 1.3500585532834881e-05, - "loss": 0.1952, + "epoch": 0.18, + "learning_rate": 4.093588510324154e-05, + "loss": 0.2157, "step": 82070 }, { - "epoch": 0.73, - "learning_rate": 1.3496081434105037e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.093476656003222e-05, + "loss": 0.2156, "step": 82080 }, { - "epoch": 0.73, - "learning_rate": 1.3491577335375191e-05, - "loss": 0.1924, + "epoch": 0.18, + "learning_rate": 4.093364801682289e-05, + "loss": 0.2166, "step": 82090 }, { - "epoch": 0.73, - "learning_rate": 1.3487073236645348e-05, - "loss": 0.1921, + "epoch": 0.18, + "learning_rate": 4.093252947361357e-05, + "loss": 0.2161, "step": 82100 }, { - "epoch": 0.73, - "learning_rate": 1.3482569137915504e-05, - "loss": 0.1974, + "epoch": 0.18, + "learning_rate": 4.0931410930404245e-05, + "loss": 0.219, "step": 82110 }, { - "epoch": 0.73, - "learning_rate": 1.3478065039185658e-05, - "loss": 0.1915, + "epoch": 0.18, + "learning_rate": 4.0930292387194916e-05, + "loss": 0.2189, "step": 82120 }, { - "epoch": 0.73, - "learning_rate": 1.3473560940455816e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.0929173843985594e-05, + "loss": 0.2169, "step": 82130 }, { - "epoch": 0.73, - "learning_rate": 1.3469056841725972e-05, - "loss": 0.1902, + "epoch": 0.18, + "learning_rate": 4.092805530077627e-05, + "loss": 0.2146, "step": 82140 }, { - "epoch": 0.73, - "learning_rate": 1.3464552742996129e-05, - "loss": 0.1926, + "epoch": 0.18, + "learning_rate": 4.092693675756695e-05, + "loss": 0.219, "step": 82150 }, { - "epoch": 0.73, - "learning_rate": 1.3460048644266281e-05, - "loss": 0.1965, + "epoch": 0.18, + "learning_rate": 4.092581821435763e-05, + "loss": 0.219, "step": 82160 }, { - "epoch": 0.73, - "learning_rate": 1.3455544545536439e-05, - "loss": 0.1903, + "epoch": 0.18, + "learning_rate": 4.09246996711483e-05, + "loss": 0.2207, "step": 82170 }, { - "epoch": 0.73, - "learning_rate": 1.3451040446806595e-05, - "loss": 0.2005, + "epoch": 0.18, + "learning_rate": 4.092358112793898e-05, + "loss": 0.2195, "step": 82180 }, { - "epoch": 0.73, - "learning_rate": 1.3446536348076749e-05, - "loss": 0.1936, + "epoch": 0.18, + "learning_rate": 4.092246258472965e-05, + "loss": 0.2183, "step": 82190 }, { - "epoch": 0.73, - "learning_rate": 1.3442032249346906e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.0921344041520326e-05, + "loss": 0.22, "step": 82200 }, { - "epoch": 0.73, - "learning_rate": 1.3437528150617062e-05, - "loss": 0.1958, + "epoch": 0.18, + "learning_rate": 4.0920225498311e-05, + "loss": 0.2205, "step": 82210 }, { - "epoch": 0.73, - "learning_rate": 1.343302405188722e-05, - "loss": 0.1987, + "epoch": 0.18, + "learning_rate": 4.0919106955101675e-05, + "loss": 0.2199, "step": 82220 }, { - "epoch": 0.73, - "learning_rate": 1.3428519953157374e-05, - "loss": 0.193, + "epoch": 0.18, + "learning_rate": 4.091798841189235e-05, + "loss": 0.2169, "step": 82230 }, { - "epoch": 0.73, - "learning_rate": 1.342401585442753e-05, - "loss": 0.1923, + "epoch": 0.18, + "learning_rate": 4.0916869868683024e-05, + "loss": 0.2201, "step": 82240 }, { - "epoch": 0.73, - "learning_rate": 1.3419511755697687e-05, - "loss": 0.1959, + "epoch": 0.18, + "learning_rate": 4.09157513254737e-05, + "loss": 0.2172, "step": 82250 }, { - "epoch": 0.73, - "learning_rate": 1.341500765696784e-05, - "loss": 0.1879, + "epoch": 0.18, + "learning_rate": 4.091463278226438e-05, + "loss": 0.2141, "step": 82260 }, { - "epoch": 0.73, - "learning_rate": 1.3410503558237997e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.091351423905506e-05, + "loss": 0.2181, "step": 82270 }, { - "epoch": 0.73, - "learning_rate": 1.3405999459508153e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.0912395695845736e-05, + "loss": 0.2187, "step": 82280 }, { - "epoch": 0.73, - "learning_rate": 1.340149536077831e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.091127715263641e-05, + "loss": 0.2138, "step": 82290 }, { - "epoch": 0.73, - "learning_rate": 1.3396991262048464e-05, - "loss": 0.1935, + "epoch": 0.18, + "learning_rate": 4.0910158609427085e-05, + "loss": 0.2125, "step": 82300 }, { - "epoch": 0.73, - "learning_rate": 1.339248716331862e-05, - "loss": 0.1958, + "epoch": 0.18, + "learning_rate": 4.0909040066217756e-05, + "loss": 0.2122, "step": 82310 }, { - "epoch": 0.73, - "learning_rate": 1.3387983064588778e-05, - "loss": 0.1907, + "epoch": 0.18, + "learning_rate": 4.0907921523008434e-05, + "loss": 0.213, "step": 82320 }, { - "epoch": 0.74, - "learning_rate": 1.3383478965858932e-05, - "loss": 0.1918, + "epoch": 0.18, + "learning_rate": 4.090680297979911e-05, + "loss": 0.2148, "step": 82330 }, { - "epoch": 0.74, - "learning_rate": 1.3378974867129088e-05, - "loss": 0.1976, + "epoch": 0.18, + "learning_rate": 4.090568443658978e-05, + "loss": 0.2157, "step": 82340 }, { - "epoch": 0.74, - "learning_rate": 1.3374470768399245e-05, - "loss": 0.198, + "epoch": 0.18, + "learning_rate": 4.090456589338046e-05, + "loss": 0.2179, "step": 82350 }, { - "epoch": 0.74, - "learning_rate": 1.33699666696694e-05, - "loss": 0.1953, + "epoch": 0.18, + "learning_rate": 4.090344735017114e-05, + "loss": 0.2193, "step": 82360 }, { - "epoch": 0.74, - "learning_rate": 1.3365462570939555e-05, - "loss": 0.1963, + "epoch": 0.18, + "learning_rate": 4.090232880696182e-05, + "loss": 0.2187, "step": 82370 }, { - "epoch": 0.74, - "learning_rate": 1.336095847220971e-05, - "loss": 0.1929, + "epoch": 0.18, + "learning_rate": 4.0901210263752495e-05, + "loss": 0.2121, "step": 82380 }, { - "epoch": 0.74, - "learning_rate": 1.3356454373479868e-05, - "loss": 0.1956, + "epoch": 0.18, + "learning_rate": 4.0900091720543166e-05, + "loss": 0.2129, "step": 82390 }, { - "epoch": 0.74, - "learning_rate": 1.3351950274750022e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.0898973177333844e-05, + "loss": 0.2175, "step": 82400 }, { - "epoch": 0.74, - "learning_rate": 1.3347446176020178e-05, - "loss": 0.1962, + "epoch": 0.18, + "learning_rate": 4.0897854634124515e-05, + "loss": 0.2215, "step": 82410 }, { - "epoch": 0.74, - "learning_rate": 1.3342942077290336e-05, - "loss": 0.1974, + "epoch": 0.18, + "learning_rate": 4.089673609091519e-05, + "loss": 0.2179, "step": 82420 }, { - "epoch": 0.74, - "learning_rate": 1.3338437978560491e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.089561754770587e-05, + "loss": 0.2158, "step": 82430 }, { - "epoch": 0.74, - "learning_rate": 1.3333933879830646e-05, - "loss": 0.1897, + "epoch": 0.18, + "learning_rate": 4.089449900449654e-05, + "loss": 0.2183, "step": 82440 }, { - "epoch": 0.74, - "learning_rate": 1.3329429781100803e-05, - "loss": 0.1935, + "epoch": 0.18, + "learning_rate": 4.089338046128722e-05, + "loss": 0.2153, "step": 82450 }, { - "epoch": 0.74, - "learning_rate": 1.3324925682370959e-05, - "loss": 0.1929, + "epoch": 0.18, + "learning_rate": 4.08922619180779e-05, + "loss": 0.214, "step": 82460 }, { - "epoch": 0.74, - "learning_rate": 1.3320421583641113e-05, - "loss": 0.1916, + "epoch": 0.18, + "learning_rate": 4.0891143374868576e-05, + "loss": 0.2197, "step": 82470 }, { - "epoch": 0.74, - "learning_rate": 1.3315917484911269e-05, - "loss": 0.1886, + "epoch": 0.18, + "learning_rate": 4.0890024831659254e-05, + "loss": 0.2101, "step": 82480 }, { - "epoch": 0.74, - "learning_rate": 1.3311413386181426e-05, - "loss": 0.1924, + "epoch": 0.18, + "learning_rate": 4.0888906288449925e-05, + "loss": 0.2137, "step": 82490 }, { - "epoch": 0.74, - "learning_rate": 1.3306909287451582e-05, - "loss": 0.196, + "epoch": 0.18, + "learning_rate": 4.08877877452406e-05, + "loss": 0.2144, "step": 82500 }, { - "epoch": 0.74, - "learning_rate": 1.3302405188721736e-05, - "loss": 0.1934, + "epoch": 0.18, + "learning_rate": 4.0886669202031274e-05, + "loss": 0.2206, "step": 82510 }, { - "epoch": 0.74, - "learning_rate": 1.3297901089991894e-05, - "loss": 0.1917, + "epoch": 0.18, + "learning_rate": 4.088555065882195e-05, + "loss": 0.2171, "step": 82520 }, { - "epoch": 0.74, - "learning_rate": 1.329339699126205e-05, - "loss": 0.193, + "epoch": 0.18, + "learning_rate": 4.088443211561262e-05, + "loss": 0.2184, "step": 82530 }, { - "epoch": 0.74, - "learning_rate": 1.3288892892532203e-05, - "loss": 0.1892, + "epoch": 0.18, + "learning_rate": 4.08833135724033e-05, + "loss": 0.2203, "step": 82540 }, { - "epoch": 0.74, - "learning_rate": 1.3284388793802361e-05, - "loss": 0.1957, + "epoch": 0.18, + "learning_rate": 4.088219502919398e-05, + "loss": 0.2149, "step": 82550 }, { - "epoch": 0.74, - "learning_rate": 1.3279884695072517e-05, - "loss": 0.1945, + "epoch": 0.18, + "learning_rate": 4.088107648598466e-05, + "loss": 0.2101, "step": 82560 }, { - "epoch": 0.74, - "learning_rate": 1.3275380596342674e-05, - "loss": 0.199, + "epoch": 0.18, + "learning_rate": 4.0879957942775335e-05, + "loss": 0.2174, "step": 82570 }, { - "epoch": 0.74, - "learning_rate": 1.3270876497612827e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.0878839399566006e-05, + "loss": 0.2184, "step": 82580 }, { - "epoch": 0.74, - "learning_rate": 1.3266372398882984e-05, - "loss": 0.1939, + "epoch": 0.18, + "learning_rate": 4.0877720856356684e-05, + "loss": 0.2173, "step": 82590 }, { - "epoch": 0.74, - "learning_rate": 1.326186830015314e-05, - "loss": 0.1942, + "epoch": 0.18, + "learning_rate": 4.087660231314736e-05, + "loss": 0.2204, "step": 82600 }, { - "epoch": 0.74, - "learning_rate": 1.3257364201423294e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.087548376993803e-05, + "loss": 0.2188, "step": 82610 }, { - "epoch": 0.74, - "learning_rate": 1.3252860102693452e-05, - "loss": 0.1915, + "epoch": 0.18, + "learning_rate": 4.087436522672871e-05, + "loss": 0.2174, "step": 82620 }, { - "epoch": 0.74, - "learning_rate": 1.3248356003963607e-05, - "loss": 0.1933, + "epoch": 0.18, + "learning_rate": 4.087324668351938e-05, + "loss": 0.2213, "step": 82630 }, { - "epoch": 0.74, - "learning_rate": 1.3243851905233765e-05, - "loss": 0.197, + "epoch": 0.18, + "learning_rate": 4.087212814031006e-05, + "loss": 0.2174, "step": 82640 }, { - "epoch": 0.74, - "learning_rate": 1.3239347806503919e-05, - "loss": 0.1938, + "epoch": 0.18, + "learning_rate": 4.087100959710074e-05, + "loss": 0.2154, "step": 82650 }, { - "epoch": 0.74, - "learning_rate": 1.3234843707774075e-05, - "loss": 0.1928, + "epoch": 0.18, + "learning_rate": 4.086989105389141e-05, + "loss": 0.2191, "step": 82660 }, { - "epoch": 0.74, - "learning_rate": 1.3230339609044232e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.0868772510682094e-05, + "loss": 0.213, "step": 82670 }, { - "epoch": 0.74, - "learning_rate": 1.3225835510314385e-05, - "loss": 0.1908, + "epoch": 0.18, + "learning_rate": 4.0867653967472765e-05, + "loss": 0.2191, "step": 82680 }, { - "epoch": 0.74, - "learning_rate": 1.3221331411584542e-05, - "loss": 0.1925, + "epoch": 0.18, + "learning_rate": 4.086653542426344e-05, + "loss": 0.2202, "step": 82690 }, { - "epoch": 0.74, - "learning_rate": 1.3216827312854698e-05, - "loss": 0.193, + "epoch": 0.18, + "learning_rate": 4.086541688105412e-05, + "loss": 0.2143, "step": 82700 }, { - "epoch": 0.74, - "learning_rate": 1.3212323214124855e-05, - "loss": 0.1926, + "epoch": 0.18, + "learning_rate": 4.086429833784479e-05, + "loss": 0.2201, "step": 82710 }, { - "epoch": 0.74, - "learning_rate": 1.320781911539501e-05, - "loss": 0.1907, + "epoch": 0.18, + "learning_rate": 4.086317979463547e-05, + "loss": 0.2184, "step": 82720 }, { - "epoch": 0.74, - "learning_rate": 1.3203315016665165e-05, - "loss": 0.1895, + "epoch": 0.18, + "learning_rate": 4.086206125142614e-05, + "loss": 0.2203, "step": 82730 }, { - "epoch": 0.74, - "learning_rate": 1.3198810917935323e-05, - "loss": 0.1941, + "epoch": 0.18, + "learning_rate": 4.086094270821682e-05, + "loss": 0.2194, "step": 82740 }, { - "epoch": 0.74, - "learning_rate": 1.3194306819205477e-05, - "loss": 0.1934, + "epoch": 0.18, + "learning_rate": 4.08598241650075e-05, + "loss": 0.2171, "step": 82750 }, { - "epoch": 0.74, - "learning_rate": 1.3189802720475633e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.085870562179817e-05, + "loss": 0.2139, "step": 82760 }, { - "epoch": 0.74, - "learning_rate": 1.318529862174579e-05, - "loss": 0.1876, + "epoch": 0.18, + "learning_rate": 4.0857587078588846e-05, + "loss": 0.2122, "step": 82770 }, { - "epoch": 0.74, - "learning_rate": 1.3180794523015946e-05, - "loss": 0.1993, + "epoch": 0.18, + "learning_rate": 4.0856468535379524e-05, + "loss": 0.2209, "step": 82780 }, { - "epoch": 0.74, - "learning_rate": 1.31762904242861e-05, - "loss": 0.1927, + "epoch": 0.18, + "learning_rate": 4.08553499921702e-05, + "loss": 0.2132, "step": 82790 }, { - "epoch": 0.74, - "learning_rate": 1.3171786325556258e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.085423144896088e-05, + "loss": 0.2147, "step": 82800 }, { - "epoch": 0.74, - "learning_rate": 1.3167282226826413e-05, - "loss": 0.1932, + "epoch": 0.18, + "learning_rate": 4.085311290575155e-05, + "loss": 0.2139, "step": 82810 }, { - "epoch": 0.74, - "learning_rate": 1.3162778128096568e-05, - "loss": 0.1905, + "epoch": 0.18, + "learning_rate": 4.085199436254223e-05, + "loss": 0.2182, "step": 82820 }, { - "epoch": 0.74, - "learning_rate": 1.3158274029366723e-05, - "loss": 0.1949, + "epoch": 0.18, + "learning_rate": 4.08508758193329e-05, + "loss": 0.2156, "step": 82830 }, { - "epoch": 0.74, - "learning_rate": 1.315376993063688e-05, - "loss": 0.1981, + "epoch": 0.18, + "learning_rate": 4.084975727612358e-05, + "loss": 0.2171, "step": 82840 }, { - "epoch": 0.74, - "learning_rate": 1.3149265831907037e-05, - "loss": 0.1904, + "epoch": 0.18, + "learning_rate": 4.084863873291425e-05, + "loss": 0.2186, "step": 82850 }, { - "epoch": 0.74, - "learning_rate": 1.314476173317719e-05, - "loss": 0.1948, + "epoch": 0.18, + "learning_rate": 4.084752018970493e-05, + "loss": 0.2158, "step": 82860 }, { - "epoch": 0.74, - "learning_rate": 1.3140257634447348e-05, - "loss": 0.1927, + "epoch": 0.18, + "learning_rate": 4.0846401646495605e-05, + "loss": 0.2133, "step": 82870 }, { - "epoch": 0.74, - "learning_rate": 1.3135753535717504e-05, - "loss": 0.1926, + "epoch": 0.18, + "learning_rate": 4.084528310328628e-05, + "loss": 0.2157, "step": 82880 }, { - "epoch": 0.74, - "learning_rate": 1.3131249436987658e-05, - "loss": 0.192, + "epoch": 0.19, + "learning_rate": 4.084416456007696e-05, + "loss": 0.2132, "step": 82890 }, { - "epoch": 0.74, - "learning_rate": 1.3126745338257816e-05, - "loss": 0.1896, + "epoch": 0.19, + "learning_rate": 4.084304601686763e-05, + "loss": 0.2202, "step": 82900 }, { - "epoch": 0.74, - "learning_rate": 1.3122241239527971e-05, - "loss": 0.1936, + "epoch": 0.19, + "learning_rate": 4.084192747365831e-05, + "loss": 0.2211, "step": 82910 }, { - "epoch": 0.74, - "learning_rate": 1.3117737140798129e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.084080893044899e-05, + "loss": 0.2155, "step": 82920 }, { - "epoch": 0.74, - "learning_rate": 1.3113233042068281e-05, - "loss": 0.1939, + "epoch": 0.19, + "learning_rate": 4.083969038723966e-05, + "loss": 0.218, "step": 82930 }, { - "epoch": 0.74, - "learning_rate": 1.3108728943338439e-05, - "loss": 0.196, + "epoch": 0.19, + "learning_rate": 4.083857184403034e-05, + "loss": 0.2167, "step": 82940 }, { - "epoch": 0.74, - "learning_rate": 1.3104224844608595e-05, - "loss": 0.1997, + "epoch": 0.19, + "learning_rate": 4.083745330082101e-05, + "loss": 0.214, "step": 82950 }, { - "epoch": 0.74, - "learning_rate": 1.3099720745878749e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.0836334757611686e-05, + "loss": 0.2176, "step": 82960 }, { - "epoch": 0.74, - "learning_rate": 1.3095216647148906e-05, - "loss": 0.1929, + "epoch": 0.19, + "learning_rate": 4.0835216214402364e-05, + "loss": 0.2235, "step": 82970 }, { - "epoch": 0.74, - "learning_rate": 1.3090712548419062e-05, - "loss": 0.1956, + "epoch": 0.19, + "learning_rate": 4.083409767119304e-05, + "loss": 0.2193, "step": 82980 }, { - "epoch": 0.74, - "learning_rate": 1.308620844968922e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.083297912798372e-05, + "loss": 0.2155, "step": 82990 }, { - "epoch": 0.74, - "learning_rate": 1.3081704350959374e-05, - "loss": 0.1964, + "epoch": 0.19, + "learning_rate": 4.083186058477439e-05, + "loss": 0.2179, "step": 83000 }, { - "epoch": 0.74, - "learning_rate": 1.307720025222953e-05, - "loss": 0.1871, + "epoch": 0.19, + "learning_rate": 4.083074204156507e-05, + "loss": 0.2171, "step": 83010 }, { - "epoch": 0.74, - "learning_rate": 1.3072696153499687e-05, - "loss": 0.1959, + "epoch": 0.19, + "learning_rate": 4.082962349835575e-05, + "loss": 0.2167, "step": 83020 }, { - "epoch": 0.74, - "learning_rate": 1.306819205476984e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.082850495514642e-05, + "loss": 0.2123, "step": 83030 }, { - "epoch": 0.74, - "learning_rate": 1.3063687956039997e-05, - "loss": 0.1976, + "epoch": 0.19, + "learning_rate": 4.0827386411937096e-05, + "loss": 0.2136, "step": 83040 }, { - "epoch": 0.74, - "learning_rate": 1.3059183857310153e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.082626786872777e-05, + "loss": 0.2111, "step": 83050 }, { - "epoch": 0.74, - "learning_rate": 1.305467975858031e-05, - "loss": 0.197, + "epoch": 0.19, + "learning_rate": 4.0825149325518445e-05, + "loss": 0.2152, "step": 83060 }, { - "epoch": 0.74, - "learning_rate": 1.3050175659850464e-05, - "loss": 0.193, + "epoch": 0.19, + "learning_rate": 4.082403078230912e-05, + "loss": 0.2216, "step": 83070 }, { - "epoch": 0.74, - "learning_rate": 1.304567156112062e-05, - "loss": 0.1967, + "epoch": 0.19, + "learning_rate": 4.08229122390998e-05, + "loss": 0.2125, "step": 83080 }, { - "epoch": 0.74, - "learning_rate": 1.3041167462390777e-05, - "loss": 0.194, + "epoch": 0.19, + "learning_rate": 4.082179369589048e-05, + "loss": 0.2127, "step": 83090 }, { - "epoch": 0.74, - "learning_rate": 1.3036663363660932e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.082067515268115e-05, + "loss": 0.2174, "step": 83100 }, { - "epoch": 0.74, - "learning_rate": 1.3032159264931087e-05, - "loss": 0.1903, + "epoch": 0.19, + "learning_rate": 4.081955660947183e-05, + "loss": 0.2147, "step": 83110 }, { - "epoch": 0.74, - "learning_rate": 1.3027655166201245e-05, - "loss": 0.1918, + "epoch": 0.19, + "learning_rate": 4.0818438066262506e-05, + "loss": 0.2166, "step": 83120 }, { - "epoch": 0.74, - "learning_rate": 1.30231510674714e-05, - "loss": 0.1944, + "epoch": 0.19, + "learning_rate": 4.081731952305318e-05, + "loss": 0.2164, "step": 83130 }, { - "epoch": 0.74, - "learning_rate": 1.3018646968741555e-05, - "loss": 0.1951, + "epoch": 0.19, + "learning_rate": 4.0816200979843855e-05, + "loss": 0.2233, "step": 83140 }, { - "epoch": 0.74, - "learning_rate": 1.301414287001171e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.0815082436634526e-05, + "loss": 0.217, "step": 83150 }, { - "epoch": 0.74, - "learning_rate": 1.3009638771281868e-05, - "loss": 0.1912, + "epoch": 0.19, + "learning_rate": 4.0813963893425204e-05, + "loss": 0.2256, "step": 83160 }, { - "epoch": 0.74, - "learning_rate": 1.3005134672552022e-05, - "loss": 0.1981, + "epoch": 0.19, + "learning_rate": 4.0812845350215875e-05, + "loss": 0.2137, "step": 83170 }, { - "epoch": 0.74, - "learning_rate": 1.3000630573822178e-05, - "loss": 0.1948, + "epoch": 0.19, + "learning_rate": 4.081172680700655e-05, + "loss": 0.2223, "step": 83180 }, { - "epoch": 0.74, - "learning_rate": 1.2996126475092335e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.081060826379723e-05, + "loss": 0.2306, "step": 83190 }, { - "epoch": 0.74, - "learning_rate": 1.2991622376362491e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.080948972058791e-05, + "loss": 0.217, "step": 83200 }, { - "epoch": 0.74, - "learning_rate": 1.2987118277632645e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.080837117737859e-05, + "loss": 0.2159, "step": 83210 }, { - "epoch": 0.74, - "learning_rate": 1.2982614178902803e-05, - "loss": 0.1997, + "epoch": 0.19, + "learning_rate": 4.080725263416926e-05, + "loss": 0.2176, "step": 83220 }, { - "epoch": 0.74, - "learning_rate": 1.2978110080172959e-05, - "loss": 0.1972, + "epoch": 0.19, + "learning_rate": 4.0806134090959936e-05, + "loss": 0.2101, "step": 83230 }, { - "epoch": 0.74, - "learning_rate": 1.2973605981443113e-05, - "loss": 0.1948, + "epoch": 0.19, + "learning_rate": 4.0805015547750614e-05, + "loss": 0.2224, "step": 83240 }, { - "epoch": 0.74, - "learning_rate": 1.2969101882713269e-05, - "loss": 0.1889, + "epoch": 0.19, + "learning_rate": 4.0803897004541285e-05, + "loss": 0.2173, "step": 83250 }, { - "epoch": 0.74, - "learning_rate": 1.2964597783983426e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.080277846133196e-05, + "loss": 0.2221, "step": 83260 }, { - "epoch": 0.74, - "learning_rate": 1.2960093685253582e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.0801659918122634e-05, + "loss": 0.2181, "step": 83270 }, { - "epoch": 0.74, - "learning_rate": 1.2955589586523736e-05, - "loss": 0.1959, + "epoch": 0.19, + "learning_rate": 4.080054137491331e-05, + "loss": 0.2114, "step": 83280 }, { - "epoch": 0.74, - "learning_rate": 1.2951085487793893e-05, - "loss": 0.1906, + "epoch": 0.19, + "learning_rate": 4.079942283170399e-05, + "loss": 0.2213, "step": 83290 }, { - "epoch": 0.74, - "learning_rate": 1.294658138906405e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.079830428849467e-05, + "loss": 0.2212, "step": 83300 }, { - "epoch": 0.74, - "learning_rate": 1.2942077290334203e-05, - "loss": 0.2009, + "epoch": 0.19, + "learning_rate": 4.0797185745285346e-05, + "loss": 0.2225, "step": 83310 }, { - "epoch": 0.74, - "learning_rate": 1.293757319160436e-05, - "loss": 0.1842, + "epoch": 0.19, + "learning_rate": 4.079606720207602e-05, + "loss": 0.2159, "step": 83320 }, { - "epoch": 0.74, - "learning_rate": 1.2933069092874517e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0794948658866695e-05, + "loss": 0.2133, "step": 83330 }, { - "epoch": 0.74, - "learning_rate": 1.2928564994144674e-05, - "loss": 0.1849, + "epoch": 0.19, + "learning_rate": 4.079383011565737e-05, + "loss": 0.2194, "step": 83340 }, { - "epoch": 0.74, - "learning_rate": 1.2924060895414827e-05, - "loss": 0.1974, + "epoch": 0.19, + "learning_rate": 4.0792711572448044e-05, + "loss": 0.2173, "step": 83350 }, { - "epoch": 0.74, - "learning_rate": 1.2919556796684984e-05, - "loss": 0.1946, + "epoch": 0.19, + "learning_rate": 4.079159302923872e-05, + "loss": 0.2187, "step": 83360 }, { - "epoch": 0.74, - "learning_rate": 1.291505269795514e-05, - "loss": 0.194, + "epoch": 0.19, + "learning_rate": 4.079047448602939e-05, + "loss": 0.2182, "step": 83370 }, { - "epoch": 0.74, - "learning_rate": 1.2910548599225294e-05, - "loss": 0.1954, + "epoch": 0.19, + "learning_rate": 4.078935594282007e-05, + "loss": 0.2156, "step": 83380 }, { - "epoch": 0.74, - "learning_rate": 1.2906044500495451e-05, - "loss": 0.1929, + "epoch": 0.19, + "learning_rate": 4.078823739961075e-05, + "loss": 0.2119, "step": 83390 }, { - "epoch": 0.74, - "learning_rate": 1.2901540401765607e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.078711885640143e-05, + "loss": 0.2128, "step": 83400 }, { - "epoch": 0.74, - "learning_rate": 1.2897036303035765e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.0786000313192105e-05, + "loss": 0.2122, "step": 83410 }, { - "epoch": 0.74, - "learning_rate": 1.2892532204305919e-05, - "loss": 0.1994, + "epoch": 0.19, + "learning_rate": 4.0784881769982776e-05, + "loss": 0.2221, "step": 83420 }, { - "epoch": 0.74, - "learning_rate": 1.2888028105576075e-05, - "loss": 0.1921, + "epoch": 0.19, + "learning_rate": 4.0783763226773454e-05, + "loss": 0.2166, "step": 83430 }, { - "epoch": 0.74, - "learning_rate": 1.2883524006846232e-05, - "loss": 0.1918, + "epoch": 0.19, + "learning_rate": 4.078264468356413e-05, + "loss": 0.2177, "step": 83440 }, { - "epoch": 0.75, - "learning_rate": 1.2879019908116386e-05, - "loss": 0.1944, + "epoch": 0.19, + "learning_rate": 4.07815261403548e-05, + "loss": 0.222, "step": 83450 }, { - "epoch": 0.75, - "learning_rate": 1.2874515809386542e-05, - "loss": 0.1889, + "epoch": 0.19, + "learning_rate": 4.078040759714548e-05, + "loss": 0.2115, "step": 83460 }, { - "epoch": 0.75, - "learning_rate": 1.2870011710656698e-05, - "loss": 0.1935, + "epoch": 0.19, + "learning_rate": 4.077928905393615e-05, + "loss": 0.2192, "step": 83470 }, { - "epoch": 0.75, - "learning_rate": 1.2865507611926855e-05, - "loss": 0.1906, + "epoch": 0.19, + "learning_rate": 4.077817051072683e-05, + "loss": 0.2171, "step": 83480 }, { - "epoch": 0.75, - "learning_rate": 1.286100351319701e-05, - "loss": 0.1958, + "epoch": 0.19, + "learning_rate": 4.077716382183844e-05, + "loss": 0.218, "step": 83490 }, { - "epoch": 0.75, - "learning_rate": 1.2856499414467165e-05, - "loss": 0.1912, + "epoch": 0.19, + "learning_rate": 4.077604527862912e-05, + "loss": 0.2115, "step": 83500 }, { - "epoch": 0.75, - "learning_rate": 1.2851995315737323e-05, - "loss": 0.1918, + "epoch": 0.19, + "learning_rate": 4.0774926735419795e-05, + "loss": 0.2189, "step": 83510 }, { - "epoch": 0.75, - "learning_rate": 1.2847491217007477e-05, - "loss": 0.1938, + "epoch": 0.19, + "learning_rate": 4.0773808192210466e-05, + "loss": 0.2132, "step": 83520 }, { - "epoch": 0.75, - "learning_rate": 1.2842987118277633e-05, - "loss": 0.1888, + "epoch": 0.19, + "learning_rate": 4.0772689649001144e-05, + "loss": 0.2221, "step": 83530 }, { - "epoch": 0.75, - "learning_rate": 1.283848301954779e-05, - "loss": 0.1936, + "epoch": 0.19, + "learning_rate": 4.0771571105791815e-05, + "loss": 0.2173, "step": 83540 }, { - "epoch": 0.75, - "learning_rate": 1.2833978920817946e-05, - "loss": 0.1915, + "epoch": 0.19, + "learning_rate": 4.077045256258249e-05, + "loss": 0.2193, "step": 83550 }, { - "epoch": 0.75, - "learning_rate": 1.28294748220881e-05, - "loss": 0.1955, + "epoch": 0.19, + "learning_rate": 4.076933401937317e-05, + "loss": 0.216, "step": 83560 }, { - "epoch": 0.75, - "learning_rate": 1.2824970723358257e-05, - "loss": 0.1875, + "epoch": 0.19, + "learning_rate": 4.076821547616385e-05, + "loss": 0.2228, "step": 83570 }, { - "epoch": 0.75, - "learning_rate": 1.2820466624628413e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0767096932954527e-05, + "loss": 0.2188, "step": 83580 }, { - "epoch": 0.75, - "learning_rate": 1.2815962525898567e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.07659783897452e-05, + "loss": 0.2207, "step": 83590 }, { - "epoch": 0.75, - "learning_rate": 1.2811458427168723e-05, - "loss": 0.1921, + "epoch": 0.19, + "learning_rate": 4.0764859846535876e-05, + "loss": 0.2165, "step": 83600 }, { - "epoch": 0.75, - "learning_rate": 1.280695432843888e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.076374130332655e-05, + "loss": 0.2188, "step": 83610 }, { - "epoch": 0.75, - "learning_rate": 1.2802450229709036e-05, - "loss": 0.1966, + "epoch": 0.19, + "learning_rate": 4.0762622760117225e-05, + "loss": 0.2126, "step": 83620 }, { - "epoch": 0.75, - "learning_rate": 1.279794613097919e-05, - "loss": 0.1967, + "epoch": 0.19, + "learning_rate": 4.07615042169079e-05, + "loss": 0.2143, "step": 83630 }, { - "epoch": 0.75, - "learning_rate": 1.2793442032249348e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.0760385673698574e-05, + "loss": 0.2173, "step": 83640 }, { - "epoch": 0.75, - "learning_rate": 1.2788937933519504e-05, - "loss": 0.1951, + "epoch": 0.19, + "learning_rate": 4.075926713048925e-05, + "loss": 0.2154, "step": 83650 }, { - "epoch": 0.75, - "learning_rate": 1.2784433834789658e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.075814858727993e-05, + "loss": 0.2126, "step": 83660 }, { - "epoch": 0.75, - "learning_rate": 1.2779929736059815e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.075703004407061e-05, + "loss": 0.2189, "step": 83670 }, { - "epoch": 0.75, - "learning_rate": 1.2775425637329971e-05, - "loss": 0.19, + "epoch": 0.19, + "learning_rate": 4.0755911500861285e-05, + "loss": 0.2177, "step": 83680 }, { - "epoch": 0.75, - "learning_rate": 1.2770921538600129e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.075479295765196e-05, + "loss": 0.2137, "step": 83690 }, { - "epoch": 0.75, - "learning_rate": 1.2766417439870281e-05, - "loss": 0.1861, + "epoch": 0.19, + "learning_rate": 4.0753674414442635e-05, + "loss": 0.2135, "step": 83700 }, { - "epoch": 0.75, - "learning_rate": 1.2761913341140439e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.0752555871233306e-05, + "loss": 0.214, "step": 83710 }, { - "epoch": 0.75, - "learning_rate": 1.2757409242410594e-05, - "loss": 0.1967, + "epoch": 0.19, + "learning_rate": 4.0751437328023984e-05, + "loss": 0.2177, "step": 83720 }, { - "epoch": 0.75, - "learning_rate": 1.2752905143680749e-05, - "loss": 0.1971, + "epoch": 0.19, + "learning_rate": 4.075031878481466e-05, + "loss": 0.2152, "step": 83730 }, { - "epoch": 0.75, - "learning_rate": 1.2748401044950906e-05, - "loss": 0.1927, + "epoch": 0.19, + "learning_rate": 4.074920024160533e-05, + "loss": 0.2174, "step": 83740 }, { - "epoch": 0.75, - "learning_rate": 1.2743896946221062e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.074808169839601e-05, + "loss": 0.2156, "step": 83750 }, { - "epoch": 0.75, - "learning_rate": 1.273939284749122e-05, - "loss": 0.1965, + "epoch": 0.19, + "learning_rate": 4.074696315518668e-05, + "loss": 0.2102, "step": 83760 }, { - "epoch": 0.75, - "learning_rate": 1.2734888748761373e-05, - "loss": 0.192, + "epoch": 0.19, + "learning_rate": 4.074584461197736e-05, + "loss": 0.214, "step": 83770 }, { - "epoch": 0.75, - "learning_rate": 1.273038465003153e-05, - "loss": 0.1877, + "epoch": 0.19, + "learning_rate": 4.074472606876804e-05, + "loss": 0.2142, "step": 83780 }, { - "epoch": 0.75, - "learning_rate": 1.2725880551301687e-05, - "loss": 0.1918, + "epoch": 0.19, + "learning_rate": 4.0743607525558716e-05, + "loss": 0.2178, "step": 83790 }, { - "epoch": 0.75, - "learning_rate": 1.2721376452571839e-05, - "loss": 0.1946, + "epoch": 0.19, + "learning_rate": 4.0742488982349393e-05, + "loss": 0.2153, "step": 83800 }, { - "epoch": 0.75, - "learning_rate": 1.2716872353841997e-05, - "loss": 0.1963, + "epoch": 0.19, + "learning_rate": 4.0741370439140065e-05, + "loss": 0.2213, "step": 83810 }, { - "epoch": 0.75, - "learning_rate": 1.2712368255112152e-05, - "loss": 0.1871, + "epoch": 0.19, + "learning_rate": 4.074025189593074e-05, + "loss": 0.2145, "step": 83820 }, { - "epoch": 0.75, - "learning_rate": 1.270786415638231e-05, - "loss": 0.1866, + "epoch": 0.19, + "learning_rate": 4.073913335272142e-05, + "loss": 0.2198, "step": 83830 }, { - "epoch": 0.75, - "learning_rate": 1.2703360057652464e-05, - "loss": 0.193, + "epoch": 0.19, + "learning_rate": 4.073801480951209e-05, + "loss": 0.214, "step": 83840 }, { - "epoch": 0.75, - "learning_rate": 1.269885595892262e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.073689626630277e-05, + "loss": 0.2135, "step": 83850 }, { - "epoch": 0.75, - "learning_rate": 1.2694351860192777e-05, - "loss": 0.1949, + "epoch": 0.19, + "learning_rate": 4.073577772309344e-05, + "loss": 0.2152, "step": 83860 }, { - "epoch": 0.75, - "learning_rate": 1.2689847761462931e-05, - "loss": 0.192, + "epoch": 0.19, + "learning_rate": 4.073465917988412e-05, + "loss": 0.2159, "step": 83870 }, { - "epoch": 0.75, - "learning_rate": 1.2685343662733087e-05, - "loss": 0.1989, + "epoch": 0.19, + "learning_rate": 4.0733540636674797e-05, + "loss": 0.2139, "step": 83880 }, { - "epoch": 0.75, - "learning_rate": 1.2680839564003245e-05, - "loss": 0.1927, + "epoch": 0.19, + "learning_rate": 4.0732422093465475e-05, + "loss": 0.2147, "step": 83890 }, { - "epoch": 0.75, - "learning_rate": 1.26763354652734e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.073130355025615e-05, + "loss": 0.2203, "step": 83900 }, { - "epoch": 0.75, - "learning_rate": 1.2671831366543555e-05, - "loss": 0.1902, + "epoch": 0.19, + "learning_rate": 4.0730185007046824e-05, + "loss": 0.2156, "step": 83910 }, { - "epoch": 0.75, - "learning_rate": 1.266732726781371e-05, - "loss": 0.1952, + "epoch": 0.19, + "learning_rate": 4.07290664638375e-05, + "loss": 0.2174, "step": 83920 }, { - "epoch": 0.75, - "learning_rate": 1.2662823169083868e-05, - "loss": 0.1939, + "epoch": 0.19, + "learning_rate": 4.072794792062817e-05, + "loss": 0.2193, "step": 83930 }, { - "epoch": 0.75, - "learning_rate": 1.2658319070354022e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.072682937741885e-05, + "loss": 0.2142, "step": 83940 }, { - "epoch": 0.75, - "learning_rate": 1.2653814971624178e-05, - "loss": 0.1954, + "epoch": 0.19, + "learning_rate": 4.072571083420953e-05, + "loss": 0.2132, "step": 83950 }, { - "epoch": 0.75, - "learning_rate": 1.2649310872894335e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.07245922910002e-05, + "loss": 0.2109, "step": 83960 }, { - "epoch": 0.75, - "learning_rate": 1.2644806774164491e-05, - "loss": 0.181, + "epoch": 0.19, + "learning_rate": 4.072347374779088e-05, + "loss": 0.2101, "step": 83970 }, { - "epoch": 0.75, - "learning_rate": 1.2640302675434645e-05, - "loss": 0.1945, + "epoch": 0.19, + "learning_rate": 4.0722355204581556e-05, + "loss": 0.2159, "step": 83980 }, { - "epoch": 0.75, - "learning_rate": 1.2635798576704803e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.0721236661372233e-05, + "loss": 0.2131, "step": 83990 }, { - "epoch": 0.75, - "learning_rate": 1.2631294477974958e-05, - "loss": 0.1937, + "epoch": 0.19, + "learning_rate": 4.072011811816291e-05, + "loss": 0.2147, "step": 84000 }, { - "epoch": 0.75, - "learning_rate": 1.2627240789118097e-05, - "loss": 0.1903, + "epoch": 0.19, + "learning_rate": 4.071899957495358e-05, + "loss": 0.2162, "step": 84010 }, { - "epoch": 0.75, - "learning_rate": 1.2622736690388253e-05, - "loss": 0.1987, + "epoch": 0.19, + "learning_rate": 4.071788103174426e-05, + "loss": 0.2167, "step": 84020 }, { - "epoch": 0.75, - "learning_rate": 1.261823259165841e-05, - "loss": 0.1952, + "epoch": 0.19, + "learning_rate": 4.071676248853493e-05, + "loss": 0.2095, "step": 84030 }, { - "epoch": 0.75, - "learning_rate": 1.2613728492928565e-05, - "loss": 0.1883, + "epoch": 0.19, + "learning_rate": 4.071564394532561e-05, + "loss": 0.213, "step": 84040 }, { - "epoch": 0.75, - "learning_rate": 1.260922439419872e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.071452540211629e-05, + "loss": 0.2157, "step": 84050 }, { - "epoch": 0.75, - "learning_rate": 1.2604720295468878e-05, - "loss": 0.1896, + "epoch": 0.19, + "learning_rate": 4.071340685890696e-05, + "loss": 0.2111, "step": 84060 }, { - "epoch": 0.75, - "learning_rate": 1.2600216196739034e-05, - "loss": 0.1892, + "epoch": 0.19, + "learning_rate": 4.0712288315697637e-05, + "loss": 0.2142, "step": 84070 }, { - "epoch": 0.75, - "learning_rate": 1.2595712098009188e-05, - "loss": 0.1989, + "epoch": 0.19, + "learning_rate": 4.0711169772488314e-05, + "loss": 0.2197, "step": 84080 }, { - "epoch": 0.75, - "learning_rate": 1.2591207999279345e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.071005122927899e-05, + "loss": 0.2178, "step": 84090 }, { - "epoch": 0.75, - "learning_rate": 1.2586703900549501e-05, - "loss": 0.1963, + "epoch": 0.19, + "learning_rate": 4.070893268606967e-05, + "loss": 0.2181, "step": 84100 }, { - "epoch": 0.75, - "learning_rate": 1.2582199801819655e-05, - "loss": 0.1949, + "epoch": 0.19, + "learning_rate": 4.070781414286034e-05, + "loss": 0.2214, "step": 84110 }, { - "epoch": 0.75, - "learning_rate": 1.2577695703089813e-05, - "loss": 0.1892, + "epoch": 0.19, + "learning_rate": 4.070669559965102e-05, + "loss": 0.2155, "step": 84120 }, { - "epoch": 0.75, - "learning_rate": 1.2573191604359968e-05, - "loss": 0.1896, + "epoch": 0.19, + "learning_rate": 4.070557705644169e-05, + "loss": 0.2147, "step": 84130 }, { - "epoch": 0.75, - "learning_rate": 1.2568687505630124e-05, - "loss": 0.1943, + "epoch": 0.19, + "learning_rate": 4.070445851323237e-05, + "loss": 0.215, "step": 84140 }, { - "epoch": 0.75, - "learning_rate": 1.2564183406900278e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.0703339970023046e-05, + "loss": 0.2145, "step": 84150 }, { - "epoch": 0.75, - "learning_rate": 1.2559679308170436e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.070222142681372e-05, + "loss": 0.2138, "step": 84160 }, { - "epoch": 0.75, - "learning_rate": 1.2555175209440592e-05, - "loss": 0.1936, + "epoch": 0.19, + "learning_rate": 4.0701102883604396e-05, + "loss": 0.2156, "step": 84170 }, { - "epoch": 0.75, - "learning_rate": 1.2550671110710746e-05, - "loss": 0.1927, + "epoch": 0.19, + "learning_rate": 4.069998434039507e-05, + "loss": 0.2193, "step": 84180 }, { - "epoch": 0.75, - "learning_rate": 1.2546167011980903e-05, - "loss": 0.1932, + "epoch": 0.19, + "learning_rate": 4.0698865797185745e-05, + "loss": 0.2185, "step": 84190 }, { - "epoch": 0.75, - "learning_rate": 1.2541662913251059e-05, - "loss": 0.1927, + "epoch": 0.19, + "learning_rate": 4.069774725397642e-05, + "loss": 0.2129, "step": 84200 }, { - "epoch": 0.75, - "learning_rate": 1.2537158814521217e-05, - "loss": 0.1934, + "epoch": 0.19, + "learning_rate": 4.06966287107671e-05, + "loss": 0.2213, "step": 84210 }, { - "epoch": 0.75, - "learning_rate": 1.253265471579137e-05, - "loss": 0.1879, + "epoch": 0.19, + "learning_rate": 4.069551016755778e-05, + "loss": 0.2154, "step": 84220 }, { - "epoch": 0.75, - "learning_rate": 1.2528150617061526e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.069439162434845e-05, + "loss": 0.2128, "step": 84230 }, { - "epoch": 0.75, - "learning_rate": 1.2523646518331684e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.069327308113913e-05, + "loss": 0.2133, "step": 84240 }, { - "epoch": 0.75, - "learning_rate": 1.2519142419601836e-05, - "loss": 0.197, + "epoch": 0.19, + "learning_rate": 4.06921545379298e-05, + "loss": 0.2212, "step": 84250 }, { - "epoch": 0.75, - "learning_rate": 1.2514638320871994e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.0691035994720477e-05, + "loss": 0.2173, "step": 84260 }, { - "epoch": 0.75, - "learning_rate": 1.251013422214215e-05, - "loss": 0.1885, + "epoch": 0.19, + "learning_rate": 4.0689917451511154e-05, + "loss": 0.2109, "step": 84270 }, { - "epoch": 0.75, - "learning_rate": 1.2505630123412307e-05, - "loss": 0.1891, + "epoch": 0.19, + "learning_rate": 4.0688798908301826e-05, + "loss": 0.2191, "step": 84280 }, { - "epoch": 0.75, - "learning_rate": 1.2501126024682461e-05, - "loss": 0.1948, + "epoch": 0.19, + "learning_rate": 4.0687680365092504e-05, + "loss": 0.2227, "step": 84290 }, { - "epoch": 0.75, - "learning_rate": 1.2496621925952617e-05, - "loss": 0.1931, + "epoch": 0.19, + "learning_rate": 4.068656182188318e-05, + "loss": 0.2138, "step": 84300 }, { - "epoch": 0.75, - "learning_rate": 1.2492117827222773e-05, - "loss": 0.1927, + "epoch": 0.19, + "learning_rate": 4.068544327867386e-05, + "loss": 0.2165, "step": 84310 }, { - "epoch": 0.75, - "learning_rate": 1.2487613728492929e-05, - "loss": 0.1928, + "epoch": 0.19, + "learning_rate": 4.068432473546454e-05, + "loss": 0.2097, "step": 84320 }, { - "epoch": 0.75, - "learning_rate": 1.2483109629763084e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.068320619225521e-05, + "loss": 0.2105, "step": 84330 }, { - "epoch": 0.75, - "learning_rate": 1.2478605531033242e-05, - "loss": 0.1911, + "epoch": 0.19, + "learning_rate": 4.0682087649045886e-05, + "loss": 0.2161, "step": 84340 }, { - "epoch": 0.75, - "learning_rate": 1.2474101432303396e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.068096910583656e-05, + "loss": 0.2169, "step": 84350 }, { - "epoch": 0.75, - "learning_rate": 1.2469597333573554e-05, - "loss": 0.19, + "epoch": 0.19, + "learning_rate": 4.0679850562627235e-05, + "loss": 0.2153, "step": 84360 }, { - "epoch": 0.75, - "learning_rate": 1.2465093234843708e-05, - "loss": 0.1934, + "epoch": 0.19, + "learning_rate": 4.0678732019417913e-05, + "loss": 0.2122, "step": 84370 }, { - "epoch": 0.75, - "learning_rate": 1.2460589136113863e-05, - "loss": 0.1963, + "epoch": 0.19, + "learning_rate": 4.0677613476208585e-05, + "loss": 0.2161, "step": 84380 }, { - "epoch": 0.75, - "learning_rate": 1.2456085037384021e-05, - "loss": 0.1964, + "epoch": 0.19, + "learning_rate": 4.067649493299926e-05, + "loss": 0.2165, "step": 84390 }, { - "epoch": 0.75, - "learning_rate": 1.2451580938654175e-05, - "loss": 0.1922, + "epoch": 0.19, + "learning_rate": 4.067537638978994e-05, + "loss": 0.2147, "step": 84400 }, { - "epoch": 0.75, - "learning_rate": 1.2447076839924332e-05, - "loss": 0.186, + "epoch": 0.19, + "learning_rate": 4.067425784658062e-05, + "loss": 0.2139, "step": 84410 }, { - "epoch": 0.75, - "learning_rate": 1.2442572741194487e-05, - "loss": 0.201, + "epoch": 0.19, + "learning_rate": 4.0673139303371296e-05, + "loss": 0.215, "step": 84420 }, { - "epoch": 0.75, - "learning_rate": 1.2438068642464644e-05, - "loss": 0.185, + "epoch": 0.19, + "learning_rate": 4.067202076016197e-05, + "loss": 0.218, "step": 84430 }, { - "epoch": 0.75, - "learning_rate": 1.24335645437348e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.0670902216952645e-05, + "loss": 0.219, "step": 84440 }, { - "epoch": 0.75, - "learning_rate": 1.2429060445004954e-05, - "loss": 0.1921, + "epoch": 0.19, + "learning_rate": 4.0669783673743316e-05, + "loss": 0.2118, "step": 84450 }, { - "epoch": 0.75, - "learning_rate": 1.2424556346275111e-05, - "loss": 0.1921, + "epoch": 0.19, + "learning_rate": 4.0668665130533994e-05, + "loss": 0.212, "step": 84460 }, { - "epoch": 0.75, - "learning_rate": 1.2420052247545266e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.066754658732467e-05, + "loss": 0.2177, "step": 84470 }, { - "epoch": 0.75, - "learning_rate": 1.2415548148815423e-05, - "loss": 0.1828, + "epoch": 0.19, + "learning_rate": 4.0666428044115344e-05, + "loss": 0.2152, "step": 84480 }, { - "epoch": 0.75, - "learning_rate": 1.2411044050085579e-05, - "loss": 0.1935, + "epoch": 0.19, + "learning_rate": 4.066530950090602e-05, + "loss": 0.2134, "step": 84490 }, { - "epoch": 0.75, - "learning_rate": 1.2406539951355735e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.06641909576967e-05, + "loss": 0.2135, "step": 84500 }, { - "epoch": 0.75, - "learning_rate": 1.240203585262589e-05, - "loss": 0.1902, + "epoch": 0.19, + "learning_rate": 4.066307241448738e-05, + "loss": 0.2159, "step": 84510 }, { - "epoch": 0.75, - "learning_rate": 1.2397531753896045e-05, - "loss": 0.1896, + "epoch": 0.19, + "learning_rate": 4.066195387127805e-05, + "loss": 0.2153, "step": 84520 }, { - "epoch": 0.75, - "learning_rate": 1.2393027655166202e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.0660835328068726e-05, + "loss": 0.2127, "step": 84530 }, { - "epoch": 0.75, - "learning_rate": 1.2388523556436358e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0659716784859404e-05, + "loss": 0.2141, "step": 84540 }, { - "epoch": 0.75, - "learning_rate": 1.2384019457706514e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.0658598241650075e-05, + "loss": 0.217, "step": 84550 }, { - "epoch": 0.75, - "learning_rate": 1.237951535897667e-05, - "loss": 0.1922, + "epoch": 0.19, + "learning_rate": 4.065747969844075e-05, + "loss": 0.2118, "step": 84560 }, { - "epoch": 0.76, - "learning_rate": 1.2375011260246825e-05, - "loss": 0.194, + "epoch": 0.19, + "learning_rate": 4.0656361155231425e-05, + "loss": 0.2134, "step": 84570 }, { - "epoch": 0.76, - "learning_rate": 1.2370507161516981e-05, - "loss": 0.1895, + "epoch": 0.19, + "learning_rate": 4.06552426120221e-05, + "loss": 0.2139, "step": 84580 }, { - "epoch": 0.76, - "learning_rate": 1.2366003062787137e-05, - "loss": 0.194, + "epoch": 0.19, + "learning_rate": 4.065412406881278e-05, + "loss": 0.2142, "step": 84590 }, { - "epoch": 0.76, - "learning_rate": 1.2361498964057293e-05, - "loss": 0.1936, + "epoch": 0.19, + "learning_rate": 4.065300552560345e-05, + "loss": 0.2118, "step": 84600 }, { - "epoch": 0.76, - "learning_rate": 1.2356994865327448e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.0651886982394136e-05, + "loss": 0.2174, "step": 84610 }, { - "epoch": 0.76, - "learning_rate": 1.2352490766597604e-05, - "loss": 0.191, + "epoch": 0.19, + "learning_rate": 4.065076843918481e-05, + "loss": 0.221, "step": 84620 }, { - "epoch": 0.76, - "learning_rate": 1.234798666786776e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.0649649895975485e-05, + "loss": 0.2139, "step": 84630 }, { - "epoch": 0.76, - "learning_rate": 1.2343482569137916e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.064853135276616e-05, + "loss": 0.2152, "step": 84640 }, { - "epoch": 0.76, - "learning_rate": 1.2338978470408072e-05, - "loss": 0.1857, + "epoch": 0.19, + "learning_rate": 4.0647412809556834e-05, + "loss": 0.2169, "step": 84650 }, { - "epoch": 0.76, - "learning_rate": 1.2334474371678227e-05, - "loss": 0.1868, + "epoch": 0.19, + "learning_rate": 4.064629426634751e-05, + "loss": 0.2113, "step": 84660 }, { - "epoch": 0.76, - "learning_rate": 1.2329970272948383e-05, - "loss": 0.1867, + "epoch": 0.19, + "learning_rate": 4.0645175723138183e-05, + "loss": 0.2144, "step": 84670 }, { - "epoch": 0.76, - "learning_rate": 1.2325466174218539e-05, - "loss": 0.1946, + "epoch": 0.19, + "learning_rate": 4.064405717992886e-05, + "loss": 0.2214, "step": 84680 }, { - "epoch": 0.76, - "learning_rate": 1.2320962075488695e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.064293863671954e-05, + "loss": 0.2175, "step": 84690 }, { - "epoch": 0.76, - "learning_rate": 1.231645797675885e-05, - "loss": 0.1883, + "epoch": 0.19, + "learning_rate": 4.064182009351021e-05, + "loss": 0.2167, "step": 84700 }, { - "epoch": 0.76, - "learning_rate": 1.2311953878029008e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.064070155030089e-05, + "loss": 0.2152, "step": 84710 }, { - "epoch": 0.76, - "learning_rate": 1.2307449779299162e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.0639583007091566e-05, + "loss": 0.2222, "step": 84720 }, { - "epoch": 0.76, - "learning_rate": 1.2302945680569318e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.0638464463882244e-05, + "loss": 0.2161, "step": 84730 }, { - "epoch": 0.76, - "learning_rate": 1.2298441581839474e-05, - "loss": 0.1903, + "epoch": 0.19, + "learning_rate": 4.063734592067292e-05, + "loss": 0.2174, "step": 84740 }, { - "epoch": 0.76, - "learning_rate": 1.229393748310963e-05, - "loss": 0.1939, + "epoch": 0.19, + "learning_rate": 4.063622737746359e-05, + "loss": 0.2144, "step": 84750 }, { - "epoch": 0.76, - "learning_rate": 1.2289433384379787e-05, - "loss": 0.1975, + "epoch": 0.19, + "learning_rate": 4.063510883425427e-05, + "loss": 0.2114, "step": 84760 }, { - "epoch": 0.76, - "learning_rate": 1.2284929285649941e-05, - "loss": 0.1845, + "epoch": 0.19, + "learning_rate": 4.063399029104494e-05, + "loss": 0.2208, "step": 84770 }, { - "epoch": 0.76, - "learning_rate": 1.2280425186920099e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.063287174783562e-05, + "loss": 0.2131, "step": 84780 }, { - "epoch": 0.76, - "learning_rate": 1.2275921088190253e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.06317532046263e-05, + "loss": 0.2139, "step": 84790 }, { - "epoch": 0.76, - "learning_rate": 1.2271416989460409e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.063063466141697e-05, + "loss": 0.2164, "step": 84800 }, { - "epoch": 0.76, - "learning_rate": 1.2266912890730566e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.062951611820765e-05, + "loss": 0.2147, "step": 84810 }, { - "epoch": 0.76, - "learning_rate": 1.226240879200072e-05, - "loss": 0.1935, + "epoch": 0.19, + "learning_rate": 4.0628397574998325e-05, + "loss": 0.2194, "step": 84820 }, { - "epoch": 0.76, - "learning_rate": 1.2257904693270878e-05, - "loss": 0.1802, + "epoch": 0.19, + "learning_rate": 4.0627279031789e-05, + "loss": 0.2199, "step": 84830 }, { - "epoch": 0.76, - "learning_rate": 1.2253400594541034e-05, - "loss": 0.1891, + "epoch": 0.19, + "learning_rate": 4.0626160488579674e-05, + "loss": 0.2187, "step": 84840 }, { - "epoch": 0.76, - "learning_rate": 1.224889649581119e-05, - "loss": 0.1981, + "epoch": 0.19, + "learning_rate": 4.062504194537035e-05, + "loss": 0.2133, "step": 84850 }, { - "epoch": 0.76, - "learning_rate": 1.2244392397081345e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.062392340216103e-05, + "loss": 0.2176, "step": 84860 }, { - "epoch": 0.76, - "learning_rate": 1.22398882983515e-05, - "loss": 0.1958, + "epoch": 0.19, + "learning_rate": 4.06228048589517e-05, + "loss": 0.214, "step": 84870 }, { - "epoch": 0.76, - "learning_rate": 1.2235384199621657e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.062168631574238e-05, + "loss": 0.2118, "step": 84880 }, { - "epoch": 0.76, - "learning_rate": 1.2230880100891813e-05, - "loss": 0.1859, + "epoch": 0.19, + "learning_rate": 4.062056777253305e-05, + "loss": 0.2143, "step": 84890 }, { - "epoch": 0.76, - "learning_rate": 1.2226376002161968e-05, - "loss": 0.1847, + "epoch": 0.19, + "learning_rate": 4.061944922932373e-05, + "loss": 0.216, "step": 84900 }, { - "epoch": 0.76, - "learning_rate": 1.2221871903432124e-05, - "loss": 0.1975, + "epoch": 0.19, + "learning_rate": 4.0618330686114406e-05, + "loss": 0.217, "step": 84910 }, { - "epoch": 0.76, - "learning_rate": 1.221736780470228e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.0617212142905084e-05, + "loss": 0.2168, "step": 84920 }, { - "epoch": 0.76, - "learning_rate": 1.2212863705972436e-05, - "loss": 0.191, + "epoch": 0.19, + "learning_rate": 4.061609359969576e-05, + "loss": 0.2198, "step": 84930 }, { - "epoch": 0.76, - "learning_rate": 1.2208359607242591e-05, - "loss": 0.1937, + "epoch": 0.19, + "learning_rate": 4.061497505648643e-05, + "loss": 0.2178, "step": 84940 }, { - "epoch": 0.76, - "learning_rate": 1.2203855508512747e-05, - "loss": 0.186, + "epoch": 0.19, + "learning_rate": 4.061385651327711e-05, + "loss": 0.2096, "step": 84950 }, { - "epoch": 0.76, - "learning_rate": 1.2199351409782903e-05, - "loss": 0.1857, + "epoch": 0.19, + "learning_rate": 4.061273797006779e-05, + "loss": 0.2197, "step": 84960 }, { - "epoch": 0.76, - "learning_rate": 1.2194847311053059e-05, - "loss": 0.1889, + "epoch": 0.19, + "learning_rate": 4.061161942685846e-05, + "loss": 0.2134, "step": 84970 }, { - "epoch": 0.76, - "learning_rate": 1.2190343212323215e-05, - "loss": 0.1928, + "epoch": 0.19, + "learning_rate": 4.061050088364914e-05, + "loss": 0.2152, "step": 84980 }, { - "epoch": 0.76, - "learning_rate": 1.218583911359337e-05, - "loss": 0.1902, + "epoch": 0.19, + "learning_rate": 4.060938234043981e-05, + "loss": 0.2151, "step": 84990 }, { - "epoch": 0.76, - "learning_rate": 1.2181335014863526e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.060826379723049e-05, + "loss": 0.2181, "step": 85000 }, { - "epoch": 0.76, - "learning_rate": 1.2176830916133682e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0607145254021165e-05, + "loss": 0.2162, "step": 85010 }, { - "epoch": 0.76, - "learning_rate": 1.2172326817403838e-05, - "loss": 0.1896, + "epoch": 0.19, + "learning_rate": 4.0606026710811836e-05, + "loss": 0.2181, "step": 85020 }, { - "epoch": 0.76, - "learning_rate": 1.2167822718673994e-05, - "loss": 0.1889, + "epoch": 0.19, + "learning_rate": 4.060490816760252e-05, + "loss": 0.2134, "step": 85030 }, { - "epoch": 0.76, - "learning_rate": 1.216331861994415e-05, - "loss": 0.1941, + "epoch": 0.19, + "learning_rate": 4.060378962439319e-05, + "loss": 0.2192, "step": 85040 }, { - "epoch": 0.76, - "learning_rate": 1.2158814521214305e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.060267108118387e-05, + "loss": 0.2164, "step": 85050 }, { - "epoch": 0.76, - "learning_rate": 1.2154310422484463e-05, - "loss": 0.187, + "epoch": 0.19, + "learning_rate": 4.060155253797455e-05, + "loss": 0.213, "step": 85060 }, { - "epoch": 0.76, - "learning_rate": 1.2149806323754617e-05, - "loss": 0.1917, + "epoch": 0.19, + "learning_rate": 4.060043399476522e-05, + "loss": 0.2128, "step": 85070 }, { - "epoch": 0.76, - "learning_rate": 1.2145302225024773e-05, - "loss": 0.1915, + "epoch": 0.19, + "learning_rate": 4.05993154515559e-05, + "loss": 0.216, "step": 85080 }, { - "epoch": 0.76, - "learning_rate": 1.2140798126294928e-05, - "loss": 0.1965, + "epoch": 0.19, + "learning_rate": 4.059819690834657e-05, + "loss": 0.2115, "step": 85090 }, { - "epoch": 0.76, - "learning_rate": 1.2136294027565084e-05, - "loss": 0.1945, + "epoch": 0.19, + "learning_rate": 4.0597078365137246e-05, + "loss": 0.2119, "step": 85100 }, { - "epoch": 0.76, - "learning_rate": 1.2131789928835242e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.0595959821927924e-05, + "loss": 0.2183, "step": 85110 }, { - "epoch": 0.76, - "learning_rate": 1.2127285830105396e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.0594841278718595e-05, + "loss": 0.2197, "step": 85120 }, { - "epoch": 0.76, - "learning_rate": 1.2122781731375553e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.059372273550927e-05, + "loss": 0.2203, "step": 85130 }, { - "epoch": 0.76, - "learning_rate": 1.2118277632645707e-05, - "loss": 0.1941, + "epoch": 0.19, + "learning_rate": 4.059260419229995e-05, + "loss": 0.2173, "step": 85140 }, { - "epoch": 0.76, - "learning_rate": 1.2113773533915863e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.059148564909063e-05, + "loss": 0.2163, "step": 85150 }, { - "epoch": 0.76, - "learning_rate": 1.210926943518602e-05, - "loss": 0.1945, + "epoch": 0.19, + "learning_rate": 4.05903671058813e-05, + "loss": 0.2158, "step": 85160 }, { - "epoch": 0.76, - "learning_rate": 1.2104765336456175e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.058924856267198e-05, + "loss": 0.217, "step": 85170 }, { - "epoch": 0.76, - "learning_rate": 1.2100261237726332e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.0588130019462656e-05, + "loss": 0.2116, "step": 85180 }, { - "epoch": 0.76, - "learning_rate": 1.2095757138996486e-05, - "loss": 0.1935, + "epoch": 0.19, + "learning_rate": 4.058701147625333e-05, + "loss": 0.2165, "step": 85190 }, { - "epoch": 0.76, - "learning_rate": 1.2091253040266644e-05, - "loss": 0.1918, + "epoch": 0.19, + "learning_rate": 4.0585892933044005e-05, + "loss": 0.2151, "step": 85200 }, { - "epoch": 0.76, - "learning_rate": 1.20867489415368e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.0584774389834676e-05, + "loss": 0.2203, "step": 85210 }, { - "epoch": 0.76, - "learning_rate": 1.2082244842806954e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.0583655846625354e-05, + "loss": 0.2142, "step": 85220 }, { - "epoch": 0.76, - "learning_rate": 1.2077740744077111e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.058253730341603e-05, + "loss": 0.2095, "step": 85230 }, { - "epoch": 0.76, - "learning_rate": 1.2073236645347265e-05, - "loss": 0.1933, + "epoch": 0.19, + "learning_rate": 4.058141876020671e-05, + "loss": 0.2176, "step": 85240 }, { - "epoch": 0.76, - "learning_rate": 1.2068732546617423e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.058030021699739e-05, + "loss": 0.2071, "step": 85250 }, { - "epoch": 0.76, - "learning_rate": 1.2064228447887579e-05, - "loss": 0.1953, + "epoch": 0.19, + "learning_rate": 4.057918167378806e-05, + "loss": 0.2154, "step": 85260 }, { - "epoch": 0.76, - "learning_rate": 1.2059724349157735e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.057806313057874e-05, + "loss": 0.2165, "step": 85270 }, { - "epoch": 0.76, - "learning_rate": 1.205522025042789e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.0576944587369415e-05, + "loss": 0.2047, "step": 85280 }, { - "epoch": 0.76, - "learning_rate": 1.2050716151698044e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.0575826044160086e-05, + "loss": 0.2112, "step": 85290 }, { - "epoch": 0.76, - "learning_rate": 1.2046212052968202e-05, - "loss": 0.1885, + "epoch": 0.19, + "learning_rate": 4.0574707500950764e-05, + "loss": 0.2213, "step": 85300 }, { - "epoch": 0.76, - "learning_rate": 1.2041707954238358e-05, - "loss": 0.1885, + "epoch": 0.19, + "learning_rate": 4.0573588957741435e-05, + "loss": 0.2163, "step": 85310 }, { - "epoch": 0.76, - "learning_rate": 1.2037203855508514e-05, - "loss": 0.1994, + "epoch": 0.19, + "learning_rate": 4.057247041453211e-05, + "loss": 0.2178, "step": 85320 }, { - "epoch": 0.76, - "learning_rate": 1.203269975677867e-05, - "loss": 0.1921, + "epoch": 0.19, + "learning_rate": 4.057135187132279e-05, + "loss": 0.2163, "step": 85330 }, { - "epoch": 0.76, - "learning_rate": 1.2028195658048825e-05, - "loss": 0.1897, + "epoch": 0.19, + "learning_rate": 4.057023332811347e-05, + "loss": 0.2172, "step": 85340 }, { - "epoch": 0.76, - "learning_rate": 1.2023691559318981e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.056911478490415e-05, + "loss": 0.2118, "step": 85350 }, { - "epoch": 0.76, - "learning_rate": 1.2019187460589137e-05, - "loss": 0.1888, + "epoch": 0.19, + "learning_rate": 4.056799624169482e-05, + "loss": 0.2115, "step": 85360 }, { - "epoch": 0.76, - "learning_rate": 1.2014683361859293e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.0566877698485496e-05, + "loss": 0.217, "step": 85370 }, { - "epoch": 0.76, - "learning_rate": 1.2010179263129448e-05, - "loss": 0.1837, + "epoch": 0.19, + "learning_rate": 4.0565759155276174e-05, + "loss": 0.2124, "step": 85380 }, { - "epoch": 0.76, - "learning_rate": 1.2005675164399604e-05, - "loss": 0.187, + "epoch": 0.19, + "learning_rate": 4.0564640612066845e-05, + "loss": 0.2137, "step": 85390 }, { - "epoch": 0.76, - "learning_rate": 1.200117106566976e-05, - "loss": 0.1831, + "epoch": 0.19, + "learning_rate": 4.056352206885752e-05, + "loss": 0.2141, "step": 85400 }, { - "epoch": 0.76, - "learning_rate": 1.1996666966939916e-05, - "loss": 0.1878, + "epoch": 0.19, + "learning_rate": 4.0562403525648194e-05, + "loss": 0.2155, "step": 85410 }, { - "epoch": 0.76, - "learning_rate": 1.1992162868210071e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.056128498243887e-05, + "loss": 0.2151, "step": 85420 }, { - "epoch": 0.76, - "learning_rate": 1.1987658769480227e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.056016643922954e-05, + "loss": 0.2192, "step": 85430 }, { - "epoch": 0.76, - "learning_rate": 1.1983154670750383e-05, - "loss": 0.1862, + "epoch": 0.19, + "learning_rate": 4.055904789602023e-05, + "loss": 0.2128, "step": 85440 }, { - "epoch": 0.76, - "learning_rate": 1.1978650572020539e-05, - "loss": 0.1967, + "epoch": 0.19, + "learning_rate": 4.0557929352810906e-05, + "loss": 0.2171, "step": 85450 }, { - "epoch": 0.76, - "learning_rate": 1.1974146473290695e-05, - "loss": 0.1848, + "epoch": 0.19, + "learning_rate": 4.055681080960158e-05, + "loss": 0.2123, "step": 85460 }, { - "epoch": 0.76, - "learning_rate": 1.196964237456085e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.0555692266392255e-05, + "loss": 0.2153, "step": 85470 }, { - "epoch": 0.76, - "learning_rate": 1.1965138275831008e-05, - "loss": 0.1903, + "epoch": 0.19, + "learning_rate": 4.0554573723182926e-05, + "loss": 0.219, "step": 85480 }, { - "epoch": 0.76, - "learning_rate": 1.1960634177101162e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0553567034294535e-05, + "loss": 0.2115, "step": 85490 }, { - "epoch": 0.76, - "learning_rate": 1.1956130078371318e-05, - "loss": 0.1959, + "epoch": 0.19, + "learning_rate": 4.055244849108521e-05, + "loss": 0.2085, "step": 85500 }, { - "epoch": 0.76, - "learning_rate": 1.1951625979641474e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.055132994787589e-05, + "loss": 0.2082, "step": 85510 }, { - "epoch": 0.76, - "learning_rate": 1.194712188091163e-05, - "loss": 0.188, + "epoch": 0.19, + "learning_rate": 4.055021140466657e-05, + "loss": 0.2273, "step": 85520 }, { - "epoch": 0.76, - "learning_rate": 1.1942617782181787e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.054909286145724e-05, + "loss": 0.2171, "step": 85530 }, { - "epoch": 0.76, - "learning_rate": 1.1938113683451941e-05, - "loss": 0.1901, + "epoch": 0.19, + "learning_rate": 4.054797431824792e-05, + "loss": 0.2156, "step": 85540 }, { - "epoch": 0.76, - "learning_rate": 1.1933609584722099e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.054685577503859e-05, + "loss": 0.2092, "step": 85550 }, { - "epoch": 0.76, - "learning_rate": 1.1929105485992254e-05, - "loss": 0.1912, + "epoch": 0.19, + "learning_rate": 4.054573723182927e-05, + "loss": 0.2158, "step": 85560 }, { - "epoch": 0.76, - "learning_rate": 1.1924601387262408e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.0544618688619945e-05, + "loss": 0.212, "step": 85570 }, { - "epoch": 0.76, - "learning_rate": 1.1920097288532566e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.0543500145410616e-05, + "loss": 0.2168, "step": 85580 }, { - "epoch": 0.76, - "learning_rate": 1.191559318980272e-05, - "loss": 0.1911, + "epoch": 0.19, + "learning_rate": 4.0542381602201294e-05, + "loss": 0.2185, "step": 85590 }, { - "epoch": 0.76, - "learning_rate": 1.1911089091072878e-05, - "loss": 0.1932, + "epoch": 0.19, + "learning_rate": 4.0541263058991965e-05, + "loss": 0.2208, "step": 85600 }, { - "epoch": 0.76, - "learning_rate": 1.1906584992343033e-05, - "loss": 0.1911, + "epoch": 0.19, + "learning_rate": 4.054014451578265e-05, + "loss": 0.2124, "step": 85610 }, { - "epoch": 0.76, - "learning_rate": 1.1902080893613189e-05, - "loss": 0.1823, + "epoch": 0.19, + "learning_rate": 4.053902597257333e-05, + "loss": 0.2118, "step": 85620 }, { - "epoch": 0.76, - "learning_rate": 1.1897576794883345e-05, - "loss": 0.1964, + "epoch": 0.19, + "learning_rate": 4.0537907429364e-05, + "loss": 0.2167, "step": 85630 }, { - "epoch": 0.76, - "learning_rate": 1.1893072696153499e-05, - "loss": 0.1892, + "epoch": 0.19, + "learning_rate": 4.053678888615468e-05, + "loss": 0.2109, "step": 85640 }, { - "epoch": 0.76, - "learning_rate": 1.1888568597423657e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.053567034294535e-05, + "loss": 0.2132, "step": 85650 }, { - "epoch": 0.76, - "learning_rate": 1.1884064498693812e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.0534551799736026e-05, + "loss": 0.2134, "step": 85660 }, { - "epoch": 0.76, - "learning_rate": 1.1879560399963968e-05, - "loss": 0.1912, + "epoch": 0.19, + "learning_rate": 4.0533433256526704e-05, + "loss": 0.2144, "step": 85670 }, { - "epoch": 0.76, - "learning_rate": 1.1875056301234124e-05, - "loss": 0.1906, + "epoch": 0.19, + "learning_rate": 4.0532314713317375e-05, + "loss": 0.2171, "step": 85680 }, { - "epoch": 0.77, - "learning_rate": 1.187055220250428e-05, - "loss": 0.1865, + "epoch": 0.19, + "learning_rate": 4.053119617010805e-05, + "loss": 0.2108, "step": 85690 }, { - "epoch": 0.77, - "learning_rate": 1.1866048103774436e-05, - "loss": 0.1868, + "epoch": 0.19, + "learning_rate": 4.0530077626898724e-05, + "loss": 0.2184, "step": 85700 }, { - "epoch": 0.77, - "learning_rate": 1.1861544005044591e-05, - "loss": 0.1901, + "epoch": 0.19, + "learning_rate": 4.05289590836894e-05, + "loss": 0.2138, "step": 85710 }, { - "epoch": 0.77, - "learning_rate": 1.1857039906314747e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.052784054048008e-05, + "loss": 0.2161, "step": 85720 }, { - "epoch": 0.77, - "learning_rate": 1.1852535807584903e-05, - "loss": 0.1871, + "epoch": 0.19, + "learning_rate": 4.052672199727076e-05, + "loss": 0.2133, "step": 85730 }, { - "epoch": 0.77, - "learning_rate": 1.1848031708855059e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.0525603454061436e-05, + "loss": 0.2142, "step": 85740 }, { - "epoch": 0.77, - "learning_rate": 1.1843527610125215e-05, - "loss": 0.1916, + "epoch": 0.19, + "learning_rate": 4.052448491085211e-05, + "loss": 0.2148, "step": 85750 }, { - "epoch": 0.77, - "learning_rate": 1.183902351139537e-05, - "loss": 0.1883, + "epoch": 0.19, + "learning_rate": 4.0523366367642785e-05, + "loss": 0.2131, "step": 85760 }, { - "epoch": 0.77, - "learning_rate": 1.1834519412665526e-05, - "loss": 0.1873, + "epoch": 0.19, + "learning_rate": 4.052224782443346e-05, + "loss": 0.2152, "step": 85770 }, { - "epoch": 0.77, - "learning_rate": 1.1830015313935682e-05, - "loss": 0.1855, + "epoch": 0.19, + "learning_rate": 4.0521129281224134e-05, + "loss": 0.2117, "step": 85780 }, { - "epoch": 0.77, - "learning_rate": 1.1825511215205838e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.052001073801481e-05, + "loss": 0.2137, "step": 85790 }, { - "epoch": 0.77, - "learning_rate": 1.1821007116475994e-05, - "loss": 0.1847, + "epoch": 0.19, + "learning_rate": 4.051889219480548e-05, + "loss": 0.2168, "step": 85800 }, { - "epoch": 0.77, - "learning_rate": 1.181650301774615e-05, - "loss": 0.1887, + "epoch": 0.19, + "learning_rate": 4.051777365159616e-05, + "loss": 0.212, "step": 85810 }, { - "epoch": 0.77, - "learning_rate": 1.1811998919016305e-05, - "loss": 0.1837, + "epoch": 0.19, + "learning_rate": 4.051665510838684e-05, + "loss": 0.2151, "step": 85820 }, { - "epoch": 0.77, - "learning_rate": 1.1807494820286463e-05, - "loss": 0.1865, + "epoch": 0.19, + "learning_rate": 4.051553656517752e-05, + "loss": 0.2217, "step": 85830 }, { - "epoch": 0.77, - "learning_rate": 1.1802990721556617e-05, - "loss": 0.1897, + "epoch": 0.19, + "learning_rate": 4.0514418021968195e-05, + "loss": 0.2137, "step": 85840 }, { - "epoch": 0.77, - "learning_rate": 1.1798486622826773e-05, - "loss": 0.1875, + "epoch": 0.19, + "learning_rate": 4.0513299478758866e-05, + "loss": 0.2077, "step": 85850 }, { - "epoch": 0.77, - "learning_rate": 1.1793982524096928e-05, - "loss": 0.192, + "epoch": 0.19, + "learning_rate": 4.0512180935549544e-05, + "loss": 0.2091, "step": 85860 }, { - "epoch": 0.77, - "learning_rate": 1.1789478425367084e-05, - "loss": 0.1908, + "epoch": 0.19, + "learning_rate": 4.0511062392340215e-05, + "loss": 0.2146, "step": 85870 }, { - "epoch": 0.77, - "learning_rate": 1.1784974326637242e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.050994384913089e-05, + "loss": 0.214, "step": 85880 }, { - "epoch": 0.77, - "learning_rate": 1.1780470227907396e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.050882530592157e-05, + "loss": 0.2147, "step": 85890 }, { - "epoch": 0.77, - "learning_rate": 1.1775966129177553e-05, - "loss": 0.1931, + "epoch": 0.19, + "learning_rate": 4.050770676271224e-05, + "loss": 0.2125, "step": 85900 }, { - "epoch": 0.77, - "learning_rate": 1.1771462030447707e-05, - "loss": 0.1861, + "epoch": 0.19, + "learning_rate": 4.050658821950292e-05, + "loss": 0.2121, "step": 85910 }, { - "epoch": 0.77, - "learning_rate": 1.1766957931717863e-05, - "loss": 0.1855, + "epoch": 0.19, + "learning_rate": 4.05054696762936e-05, + "loss": 0.2132, "step": 85920 }, { - "epoch": 0.77, - "learning_rate": 1.176245383298802e-05, - "loss": 0.1942, + "epoch": 0.19, + "learning_rate": 4.0504351133084276e-05, + "loss": 0.2129, "step": 85930 }, { - "epoch": 0.77, - "learning_rate": 1.1757949734258175e-05, - "loss": 0.1928, + "epoch": 0.19, + "learning_rate": 4.0503232589874954e-05, + "loss": 0.2124, "step": 85940 }, { - "epoch": 0.77, - "learning_rate": 1.1753445635528332e-05, - "loss": 0.1819, + "epoch": 0.19, + "learning_rate": 4.0502114046665625e-05, + "loss": 0.2134, "step": 85950 }, { - "epoch": 0.77, - "learning_rate": 1.1748941536798486e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.05009955034563e-05, + "loss": 0.2098, "step": 85960 }, { - "epoch": 0.77, - "learning_rate": 1.1744437438068644e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.0499876960246974e-05, + "loss": 0.2141, "step": 85970 }, { - "epoch": 0.77, - "learning_rate": 1.17399333393388e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.049875841703765e-05, + "loss": 0.2129, "step": 85980 }, { - "epoch": 0.77, - "learning_rate": 1.1735429240608954e-05, - "loss": 0.1835, + "epoch": 0.19, + "learning_rate": 4.049763987382833e-05, + "loss": 0.2208, "step": 85990 }, { - "epoch": 0.77, - "learning_rate": 1.1730925141879111e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.0496521330619e-05, + "loss": 0.2099, "step": 86000 }, { - "epoch": 0.77, - "learning_rate": 1.1726421043149265e-05, - "loss": 0.1891, + "epoch": 0.19, + "learning_rate": 4.049540278740968e-05, + "loss": 0.2181, "step": 86010 }, { - "epoch": 0.77, - "learning_rate": 1.1721916944419423e-05, - "loss": 0.193, + "epoch": 0.19, + "learning_rate": 4.049428424420036e-05, + "loss": 0.2166, "step": 86020 }, { - "epoch": 0.77, - "learning_rate": 1.1717863255562563e-05, - "loss": 0.1895, + "epoch": 0.19, + "learning_rate": 4.0493165700991035e-05, + "loss": 0.217, "step": 86030 }, { - "epoch": 0.77, - "learning_rate": 1.1713359156832717e-05, - "loss": 0.1908, + "epoch": 0.19, + "learning_rate": 4.049204715778171e-05, + "loss": 0.2149, "step": 86040 }, { - "epoch": 0.77, - "learning_rate": 1.1708855058102875e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.0490928614572384e-05, + "loss": 0.213, "step": 86050 }, { - "epoch": 0.77, - "learning_rate": 1.1704350959373029e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.048981007136306e-05, + "loss": 0.216, "step": 86060 }, { - "epoch": 0.77, - "learning_rate": 1.1699846860643186e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.048869152815373e-05, + "loss": 0.2136, "step": 86070 }, { - "epoch": 0.77, - "learning_rate": 1.1695342761913342e-05, - "loss": 0.1939, + "epoch": 0.19, + "learning_rate": 4.048757298494441e-05, + "loss": 0.2189, "step": 86080 }, { - "epoch": 0.77, - "learning_rate": 1.1690838663183498e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.048645444173509e-05, + "loss": 0.2135, "step": 86090 }, { - "epoch": 0.77, - "learning_rate": 1.1686334564453654e-05, - "loss": 0.1911, + "epoch": 0.19, + "learning_rate": 4.048533589852576e-05, + "loss": 0.2165, "step": 86100 }, { - "epoch": 0.77, - "learning_rate": 1.1681830465723808e-05, - "loss": 0.1892, + "epoch": 0.19, + "learning_rate": 4.048421735531644e-05, + "loss": 0.2183, "step": 86110 }, { - "epoch": 0.77, - "learning_rate": 1.1677326366993965e-05, - "loss": 0.1917, + "epoch": 0.19, + "learning_rate": 4.048309881210711e-05, + "loss": 0.2129, "step": 86120 }, { - "epoch": 0.77, - "learning_rate": 1.1672822268264121e-05, - "loss": 0.1956, + "epoch": 0.19, + "learning_rate": 4.048198026889779e-05, + "loss": 0.2108, "step": 86130 }, { - "epoch": 0.77, - "learning_rate": 1.1668318169534277e-05, - "loss": 0.1876, + "epoch": 0.19, + "learning_rate": 4.0480861725688465e-05, + "loss": 0.2087, "step": 86140 }, { - "epoch": 0.77, - "learning_rate": 1.1663814070804433e-05, - "loss": 0.1847, + "epoch": 0.19, + "learning_rate": 4.047974318247914e-05, + "loss": 0.211, "step": 86150 }, { - "epoch": 0.77, - "learning_rate": 1.1659309972074589e-05, - "loss": 0.1931, + "epoch": 0.19, + "learning_rate": 4.047862463926982e-05, + "loss": 0.2184, "step": 86160 }, { - "epoch": 0.77, - "learning_rate": 1.1654805873344744e-05, - "loss": 0.1891, + "epoch": 0.19, + "learning_rate": 4.047750609606049e-05, + "loss": 0.2152, "step": 86170 }, { - "epoch": 0.77, - "learning_rate": 1.16503017746149e-05, - "loss": 0.1836, + "epoch": 0.19, + "learning_rate": 4.047638755285117e-05, + "loss": 0.2164, "step": 86180 }, { - "epoch": 0.77, - "learning_rate": 1.1645797675885056e-05, - "loss": 0.1895, + "epoch": 0.19, + "learning_rate": 4.047526900964184e-05, + "loss": 0.2121, "step": 86190 }, { - "epoch": 0.77, - "learning_rate": 1.1641293577155212e-05, - "loss": 0.1853, + "epoch": 0.19, + "learning_rate": 4.047415046643252e-05, + "loss": 0.2136, "step": 86200 }, { - "epoch": 0.77, - "learning_rate": 1.1636789478425368e-05, - "loss": 0.1901, + "epoch": 0.19, + "learning_rate": 4.04730319232232e-05, + "loss": 0.2163, "step": 86210 }, { - "epoch": 0.77, - "learning_rate": 1.1632285379695523e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.047191338001387e-05, + "loss": 0.2169, "step": 86220 }, { - "epoch": 0.77, - "learning_rate": 1.162778128096568e-05, - "loss": 0.1924, + "epoch": 0.19, + "learning_rate": 4.0470794836804546e-05, + "loss": 0.2108, "step": 86230 }, { - "epoch": 0.77, - "learning_rate": 1.1623277182235835e-05, - "loss": 0.192, + "epoch": 0.19, + "learning_rate": 4.0469676293595224e-05, + "loss": 0.2154, "step": 86240 }, { - "epoch": 0.77, - "learning_rate": 1.161877308350599e-05, - "loss": 0.1855, + "epoch": 0.19, + "learning_rate": 4.04685577503859e-05, + "loss": 0.2138, "step": 86250 }, { - "epoch": 0.77, - "learning_rate": 1.1614268984776147e-05, - "loss": 0.1856, + "epoch": 0.19, + "learning_rate": 4.046743920717658e-05, + "loss": 0.2108, "step": 86260 }, { - "epoch": 0.77, - "learning_rate": 1.1609764886046302e-05, - "loss": 0.1891, + "epoch": 0.19, + "learning_rate": 4.046632066396725e-05, + "loss": 0.2093, "step": 86270 }, { - "epoch": 0.77, - "learning_rate": 1.160526078731646e-05, - "loss": 0.1894, + "epoch": 0.19, + "learning_rate": 4.046520212075793e-05, + "loss": 0.2117, "step": 86280 }, { - "epoch": 0.77, - "learning_rate": 1.1600756688586614e-05, - "loss": 0.1843, + "epoch": 0.19, + "learning_rate": 4.04640835775486e-05, + "loss": 0.2124, "step": 86290 }, { - "epoch": 0.77, - "learning_rate": 1.1596252589856771e-05, - "loss": 0.1879, + "epoch": 0.19, + "learning_rate": 4.046296503433928e-05, + "loss": 0.2169, "step": 86300 }, { - "epoch": 0.77, - "learning_rate": 1.1591748491126926e-05, - "loss": 0.1857, + "epoch": 0.19, + "learning_rate": 4.0461846491129956e-05, + "loss": 0.2148, "step": 86310 }, { - "epoch": 0.77, - "learning_rate": 1.1587244392397081e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.046072794792063e-05, + "loss": 0.2115, "step": 86320 }, { - "epoch": 0.77, - "learning_rate": 1.1582740293667239e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.0459609404711305e-05, + "loss": 0.2118, "step": 86330 }, { - "epoch": 0.77, - "learning_rate": 1.1578236194937393e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.045849086150198e-05, + "loss": 0.2117, "step": 86340 }, { - "epoch": 0.77, - "learning_rate": 1.157373209620755e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.045737231829266e-05, + "loss": 0.2145, "step": 86350 }, { - "epoch": 0.77, - "learning_rate": 1.1569227997477704e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.045625377508334e-05, + "loss": 0.2095, "step": 86360 }, { - "epoch": 0.77, - "learning_rate": 1.1564723898747862e-05, - "loss": 0.1919, + "epoch": 0.19, + "learning_rate": 4.045513523187401e-05, + "loss": 0.2112, "step": 86370 }, { - "epoch": 0.77, - "learning_rate": 1.1560219800018018e-05, - "loss": 0.19, + "epoch": 0.19, + "learning_rate": 4.045401668866469e-05, + "loss": 0.2141, "step": 86380 }, { - "epoch": 0.77, - "learning_rate": 1.1555715701288172e-05, - "loss": 0.1815, + "epoch": 0.19, + "learning_rate": 4.045289814545536e-05, + "loss": 0.2138, "step": 86390 }, { - "epoch": 0.77, - "learning_rate": 1.155121160255833e-05, - "loss": 0.1833, + "epoch": 0.19, + "learning_rate": 4.045177960224604e-05, + "loss": 0.2165, "step": 86400 }, { - "epoch": 0.77, - "learning_rate": 1.1546707503828483e-05, - "loss": 0.1894, + "epoch": 0.19, + "learning_rate": 4.0450661059036715e-05, + "loss": 0.212, "step": 86410 }, { - "epoch": 0.77, - "learning_rate": 1.1542203405098641e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.0449542515827386e-05, + "loss": 0.2105, "step": 86420 }, { - "epoch": 0.77, - "learning_rate": 1.1537699306368797e-05, - "loss": 0.1888, + "epoch": 0.19, + "learning_rate": 4.0448423972618064e-05, + "loss": 0.2102, "step": 86430 }, { - "epoch": 0.77, - "learning_rate": 1.1533195207638953e-05, - "loss": 0.1886, + "epoch": 0.19, + "learning_rate": 4.044730542940874e-05, + "loss": 0.2173, "step": 86440 }, { - "epoch": 0.77, - "learning_rate": 1.1528691108909108e-05, - "loss": 0.1931, + "epoch": 0.19, + "learning_rate": 4.044618688619942e-05, + "loss": 0.2143, "step": 86450 }, { - "epoch": 0.77, - "learning_rate": 1.1524187010179262e-05, - "loss": 0.1959, + "epoch": 0.19, + "learning_rate": 4.044506834299009e-05, + "loss": 0.2104, "step": 86460 }, { - "epoch": 0.77, - "learning_rate": 1.151968291144942e-05, - "loss": 0.1876, + "epoch": 0.19, + "learning_rate": 4.044394979978077e-05, + "loss": 0.2131, "step": 86470 }, { - "epoch": 0.77, - "learning_rate": 1.1515178812719576e-05, - "loss": 0.1856, + "epoch": 0.19, + "learning_rate": 4.0442831256571447e-05, + "loss": 0.2119, "step": 86480 }, { - "epoch": 0.77, - "learning_rate": 1.1510674713989732e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.044171271336212e-05, + "loss": 0.2105, "step": 86490 }, { - "epoch": 0.77, - "learning_rate": 1.1506170615259887e-05, - "loss": 0.1944, + "epoch": 0.19, + "learning_rate": 4.0440594170152796e-05, + "loss": 0.2128, "step": 86500 }, { - "epoch": 0.77, - "learning_rate": 1.1501666516530043e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.043947562694347e-05, + "loss": 0.2131, "step": 86510 }, { - "epoch": 0.77, - "learning_rate": 1.1497162417800199e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.0438357083734145e-05, + "loss": 0.2146, "step": 86520 }, { - "epoch": 0.77, - "learning_rate": 1.1492658319070355e-05, - "loss": 0.1861, + "epoch": 0.19, + "learning_rate": 4.043723854052482e-05, + "loss": 0.2147, "step": 86530 }, { - "epoch": 0.77, - "learning_rate": 1.148815422034051e-05, - "loss": 0.1929, + "epoch": 0.19, + "learning_rate": 4.0436119997315494e-05, + "loss": 0.215, "step": 86540 }, { - "epoch": 0.77, - "learning_rate": 1.1483650121610666e-05, - "loss": 0.1835, + "epoch": 0.19, + "learning_rate": 4.043500145410617e-05, + "loss": 0.211, "step": 86550 }, { - "epoch": 0.77, - "learning_rate": 1.1479146022880822e-05, - "loss": 0.1879, + "epoch": 0.19, + "learning_rate": 4.043388291089685e-05, + "loss": 0.2103, "step": 86560 }, { - "epoch": 0.77, - "learning_rate": 1.1474641924150978e-05, - "loss": 0.1857, + "epoch": 0.19, + "learning_rate": 4.043276436768753e-05, + "loss": 0.2114, "step": 86570 }, { - "epoch": 0.77, - "learning_rate": 1.1470137825421134e-05, - "loss": 0.1841, + "epoch": 0.19, + "learning_rate": 4.0431645824478205e-05, + "loss": 0.2116, "step": 86580 }, { - "epoch": 0.77, - "learning_rate": 1.146563372669129e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.043052728126888e-05, + "loss": 0.2117, "step": 86590 }, { - "epoch": 0.77, - "learning_rate": 1.1461129627961445e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.0429408738059555e-05, + "loss": 0.2187, "step": 86600 }, { - "epoch": 0.77, - "learning_rate": 1.1456625529231601e-05, - "loss": 0.1851, + "epoch": 0.19, + "learning_rate": 4.0428290194850226e-05, + "loss": 0.218, "step": 86610 }, { - "epoch": 0.77, - "learning_rate": 1.1452121430501757e-05, - "loss": 0.187, + "epoch": 0.19, + "learning_rate": 4.0427171651640904e-05, + "loss": 0.2109, "step": 86620 }, { - "epoch": 0.77, - "learning_rate": 1.1447617331771913e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.042605310843158e-05, + "loss": 0.213, "step": 86630 }, { - "epoch": 0.77, - "learning_rate": 1.1443113233042069e-05, - "loss": 0.1844, + "epoch": 0.19, + "learning_rate": 4.042493456522225e-05, + "loss": 0.2139, "step": 86640 }, { - "epoch": 0.77, - "learning_rate": 1.1438609134312226e-05, - "loss": 0.1859, + "epoch": 0.19, + "learning_rate": 4.042381602201293e-05, + "loss": 0.2089, "step": 86650 }, { - "epoch": 0.77, - "learning_rate": 1.143410503558238e-05, - "loss": 0.188, + "epoch": 0.19, + "learning_rate": 4.042269747880361e-05, + "loss": 0.2091, "step": 86660 }, { - "epoch": 0.77, - "learning_rate": 1.1429600936852536e-05, - "loss": 0.1959, + "epoch": 0.19, + "learning_rate": 4.0421578935594287e-05, + "loss": 0.2093, "step": 86670 }, { - "epoch": 0.77, - "learning_rate": 1.1425096838122692e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.0420460392384964e-05, + "loss": 0.2121, "step": 86680 }, { - "epoch": 0.77, - "learning_rate": 1.1420592739392848e-05, - "loss": 0.1851, + "epoch": 0.19, + "learning_rate": 4.0419341849175636e-05, + "loss": 0.2131, "step": 86690 }, { - "epoch": 0.77, - "learning_rate": 1.1416088640663005e-05, - "loss": 0.1825, + "epoch": 0.19, + "learning_rate": 4.0418223305966314e-05, + "loss": 0.2108, "step": 86700 }, { - "epoch": 0.77, - "learning_rate": 1.1411584541933159e-05, - "loss": 0.1888, + "epoch": 0.19, + "learning_rate": 4.0417104762756985e-05, + "loss": 0.2079, "step": 86710 }, { - "epoch": 0.77, - "learning_rate": 1.1407080443203315e-05, - "loss": 0.1909, + "epoch": 0.19, + "learning_rate": 4.041598621954766e-05, + "loss": 0.2183, "step": 86720 }, { - "epoch": 0.77, - "learning_rate": 1.140257634447347e-05, - "loss": 0.186, + "epoch": 0.19, + "learning_rate": 4.041486767633834e-05, + "loss": 0.2136, "step": 86730 }, { - "epoch": 0.77, - "learning_rate": 1.1398072245743627e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.041374913312901e-05, + "loss": 0.2161, "step": 86740 }, { - "epoch": 0.77, - "learning_rate": 1.1393568147013784e-05, - "loss": 0.1935, + "epoch": 0.19, + "learning_rate": 4.041263058991969e-05, + "loss": 0.2127, "step": 86750 }, { - "epoch": 0.77, - "learning_rate": 1.1389064048283938e-05, - "loss": 0.1962, + "epoch": 0.19, + "learning_rate": 4.041151204671037e-05, + "loss": 0.213, "step": 86760 }, { - "epoch": 0.77, - "learning_rate": 1.1384559949554096e-05, - "loss": 0.1928, + "epoch": 0.19, + "learning_rate": 4.0410393503501045e-05, + "loss": 0.2066, "step": 86770 }, { - "epoch": 0.77, - "learning_rate": 1.138005585082425e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.0409274960291717e-05, + "loss": 0.2137, "step": 86780 }, { - "epoch": 0.77, - "learning_rate": 1.1375551752094406e-05, - "loss": 0.1865, + "epoch": 0.19, + "learning_rate": 4.0408156417082395e-05, + "loss": 0.2135, "step": 86790 }, { - "epoch": 0.77, - "learning_rate": 1.1371047653364563e-05, - "loss": 0.1965, + "epoch": 0.19, + "learning_rate": 4.040703787387307e-05, + "loss": 0.2119, "step": 86800 }, { - "epoch": 0.78, - "learning_rate": 1.1366543554634717e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.0405919330663744e-05, + "loss": 0.2121, "step": 86810 }, { - "epoch": 0.78, - "learning_rate": 1.1362039455904875e-05, - "loss": 0.186, + "epoch": 0.19, + "learning_rate": 4.040480078745442e-05, + "loss": 0.2087, "step": 86820 }, { - "epoch": 0.78, - "learning_rate": 1.1357535357175029e-05, - "loss": 0.1925, + "epoch": 0.19, + "learning_rate": 4.040368224424509e-05, + "loss": 0.2095, "step": 86830 }, { - "epoch": 0.78, - "learning_rate": 1.1353031258445186e-05, - "loss": 0.1881, + "epoch": 0.19, + "learning_rate": 4.040256370103577e-05, + "loss": 0.2079, "step": 86840 }, { - "epoch": 0.78, - "learning_rate": 1.1348527159715342e-05, - "loss": 0.1885, + "epoch": 0.19, + "learning_rate": 4.040144515782645e-05, + "loss": 0.2087, "step": 86850 }, { - "epoch": 0.78, - "learning_rate": 1.1344023060985496e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.0400326614617126e-05, + "loss": 0.2123, "step": 86860 }, { - "epoch": 0.78, - "learning_rate": 1.1339518962255654e-05, - "loss": 0.1932, + "epoch": 0.19, + "learning_rate": 4.0399208071407804e-05, + "loss": 0.2146, "step": 86870 }, { - "epoch": 0.78, - "learning_rate": 1.133501486352581e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.0398089528198476e-05, + "loss": 0.2174, "step": 86880 }, { - "epoch": 0.78, - "learning_rate": 1.1330510764795965e-05, - "loss": 0.191, + "epoch": 0.19, + "learning_rate": 4.0396970984989153e-05, + "loss": 0.2135, "step": 86890 }, { - "epoch": 0.78, - "learning_rate": 1.1326006666066121e-05, - "loss": 0.1876, + "epoch": 0.19, + "learning_rate": 4.039585244177983e-05, + "loss": 0.2133, "step": 86900 }, { - "epoch": 0.78, - "learning_rate": 1.1321502567336277e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.03947338985705e-05, + "loss": 0.2177, "step": 86910 }, { - "epoch": 0.78, - "learning_rate": 1.1316998468606433e-05, - "loss": 0.1902, + "epoch": 0.19, + "learning_rate": 4.039361535536118e-05, + "loss": 0.2113, "step": 86920 }, { - "epoch": 0.78, - "learning_rate": 1.1312494369876588e-05, - "loss": 0.1812, + "epoch": 0.19, + "learning_rate": 4.039249681215185e-05, + "loss": 0.2068, "step": 86930 }, { - "epoch": 0.78, - "learning_rate": 1.1307990271146744e-05, - "loss": 0.1944, + "epoch": 0.19, + "learning_rate": 4.039137826894253e-05, + "loss": 0.2084, "step": 86940 }, { - "epoch": 0.78, - "learning_rate": 1.13034861724169e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.039025972573321e-05, + "loss": 0.2143, "step": 86950 }, { - "epoch": 0.78, - "learning_rate": 1.1298982073687056e-05, - "loss": 0.1842, + "epoch": 0.19, + "learning_rate": 4.038914118252388e-05, + "loss": 0.2119, "step": 86960 }, { - "epoch": 0.78, - "learning_rate": 1.1294477974957212e-05, - "loss": 0.1923, + "epoch": 0.19, + "learning_rate": 4.038802263931456e-05, + "loss": 0.2192, "step": 86970 }, { - "epoch": 0.78, - "learning_rate": 1.1289973876227367e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.0386904096105235e-05, + "loss": 0.2131, "step": 86980 }, { - "epoch": 0.78, - "learning_rate": 1.1285469777497523e-05, - "loss": 0.1911, + "epoch": 0.19, + "learning_rate": 4.038578555289591e-05, + "loss": 0.2188, "step": 86990 }, { - "epoch": 0.78, - "learning_rate": 1.1280965678767679e-05, - "loss": 0.1908, + "epoch": 0.19, + "learning_rate": 4.038466700968659e-05, + "loss": 0.2154, "step": 87000 }, { - "epoch": 0.78, - "learning_rate": 1.1276461580037835e-05, - "loss": 0.185, + "epoch": 0.19, + "learning_rate": 4.038354846647726e-05, + "loss": 0.2155, "step": 87010 }, { - "epoch": 0.78, - "learning_rate": 1.127195748130799e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.038242992326794e-05, + "loss": 0.2167, "step": 87020 }, { - "epoch": 0.78, - "learning_rate": 1.1267453382578146e-05, - "loss": 0.1913, + "epoch": 0.19, + "learning_rate": 4.038131138005861e-05, + "loss": 0.2168, "step": 87030 }, { - "epoch": 0.78, - "learning_rate": 1.1262949283848302e-05, - "loss": 0.1931, + "epoch": 0.19, + "learning_rate": 4.038019283684929e-05, + "loss": 0.2165, "step": 87040 }, { - "epoch": 0.78, - "learning_rate": 1.125844518511846e-05, - "loss": 0.1905, + "epoch": 0.19, + "learning_rate": 4.0379074293639966e-05, + "loss": 0.2155, "step": 87050 }, { - "epoch": 0.78, - "learning_rate": 1.1253941086388614e-05, - "loss": 0.1876, + "epoch": 0.19, + "learning_rate": 4.037795575043064e-05, + "loss": 0.2126, "step": 87060 }, { - "epoch": 0.78, - "learning_rate": 1.124943698765877e-05, - "loss": 0.187, + "epoch": 0.19, + "learning_rate": 4.0376837207221316e-05, + "loss": 0.2111, "step": 87070 }, { - "epoch": 0.78, - "learning_rate": 1.1244932888928925e-05, - "loss": 0.1922, + "epoch": 0.19, + "learning_rate": 4.0375718664011993e-05, + "loss": 0.2111, "step": 87080 }, { - "epoch": 0.78, - "learning_rate": 1.1240428790199081e-05, - "loss": 0.1898, + "epoch": 0.19, + "learning_rate": 4.037460012080267e-05, + "loss": 0.2096, "step": 87090 }, { - "epoch": 0.78, - "learning_rate": 1.1235924691469239e-05, - "loss": 0.1907, + "epoch": 0.19, + "learning_rate": 4.037348157759334e-05, + "loss": 0.2103, "step": 87100 }, { - "epoch": 0.78, - "learning_rate": 1.1231420592739393e-05, - "loss": 0.1834, + "epoch": 0.19, + "learning_rate": 4.037236303438402e-05, + "loss": 0.2103, "step": 87110 }, { - "epoch": 0.78, - "learning_rate": 1.122691649400955e-05, - "loss": 0.1866, + "epoch": 0.19, + "learning_rate": 4.03712444911747e-05, + "loss": 0.2154, "step": 87120 }, { - "epoch": 0.78, - "learning_rate": 1.1222412395279704e-05, - "loss": 0.1874, + "epoch": 0.19, + "learning_rate": 4.037012594796537e-05, + "loss": 0.2176, "step": 87130 }, { - "epoch": 0.78, - "learning_rate": 1.121790829654986e-05, - "loss": 0.1924, + "epoch": 0.19, + "learning_rate": 4.036900740475605e-05, + "loss": 0.2176, "step": 87140 }, { - "epoch": 0.78, - "learning_rate": 1.1213404197820018e-05, - "loss": 0.1904, + "epoch": 0.19, + "learning_rate": 4.036788886154672e-05, + "loss": 0.2147, "step": 87150 }, { - "epoch": 0.78, - "learning_rate": 1.1208900099090172e-05, - "loss": 0.1922, + "epoch": 0.19, + "learning_rate": 4.0366770318337397e-05, + "loss": 0.2175, "step": 87160 }, { - "epoch": 0.78, - "learning_rate": 1.120439600036033e-05, - "loss": 0.1941, + "epoch": 0.19, + "learning_rate": 4.0365651775128074e-05, + "loss": 0.2163, "step": 87170 }, { - "epoch": 0.78, - "learning_rate": 1.1199891901630483e-05, - "loss": 0.1835, + "epoch": 0.19, + "learning_rate": 4.036453323191875e-05, + "loss": 0.2076, "step": 87180 }, { - "epoch": 0.78, - "learning_rate": 1.119538780290064e-05, - "loss": 0.1879, + "epoch": 0.19, + "learning_rate": 4.036341468870943e-05, + "loss": 0.2185, "step": 87190 }, { - "epoch": 0.78, - "learning_rate": 1.1190883704170797e-05, - "loss": 0.1869, + "epoch": 0.19, + "learning_rate": 4.03622961455001e-05, + "loss": 0.2113, "step": 87200 }, { - "epoch": 0.78, - "learning_rate": 1.118637960544095e-05, - "loss": 0.1906, + "epoch": 0.19, + "learning_rate": 4.036117760229078e-05, + "loss": 0.2129, "step": 87210 }, { - "epoch": 0.78, - "learning_rate": 1.1181875506711108e-05, - "loss": 0.19, + "epoch": 0.19, + "learning_rate": 4.036005905908146e-05, + "loss": 0.2141, "step": 87220 }, { - "epoch": 0.78, - "learning_rate": 1.1177371407981262e-05, - "loss": 0.189, + "epoch": 0.19, + "learning_rate": 4.035894051587213e-05, + "loss": 0.2155, "step": 87230 }, { - "epoch": 0.78, - "learning_rate": 1.117286730925142e-05, - "loss": 0.1873, + "epoch": 0.19, + "learning_rate": 4.0357821972662806e-05, + "loss": 0.2125, "step": 87240 }, { - "epoch": 0.78, - "learning_rate": 1.1168363210521576e-05, - "loss": 0.1876, + "epoch": 0.19, + "learning_rate": 4.035670342945348e-05, + "loss": 0.2145, "step": 87250 }, { - "epoch": 0.78, - "learning_rate": 1.1163859111791731e-05, - "loss": 0.1892, + "epoch": 0.19, + "learning_rate": 4.0355584886244155e-05, + "loss": 0.2159, "step": 87260 }, { - "epoch": 0.78, - "learning_rate": 1.1159355013061887e-05, - "loss": 0.1882, + "epoch": 0.19, + "learning_rate": 4.0354466343034833e-05, + "loss": 0.2086, "step": 87270 }, { - "epoch": 0.78, - "learning_rate": 1.1154850914332041e-05, - "loss": 0.1884, + "epoch": 0.19, + "learning_rate": 4.035334779982551e-05, + "loss": 0.2085, "step": 87280 }, { - "epoch": 0.78, - "learning_rate": 1.1150346815602199e-05, - "loss": 0.1926, + "epoch": 0.19, + "learning_rate": 4.035222925661619e-05, + "loss": 0.2186, "step": 87290 }, { - "epoch": 0.78, - "learning_rate": 1.1145842716872355e-05, - "loss": 0.19, + "epoch": 0.19, + "learning_rate": 4.035111071340686e-05, + "loss": 0.2096, "step": 87300 }, { - "epoch": 0.78, - "learning_rate": 1.114133861814251e-05, - "loss": 0.1841, + "epoch": 0.19, + "learning_rate": 4.034999217019754e-05, + "loss": 0.2117, "step": 87310 }, { - "epoch": 0.78, - "learning_rate": 1.1136834519412666e-05, - "loss": 0.1899, + "epoch": 0.19, + "learning_rate": 4.0348873626988216e-05, + "loss": 0.2162, "step": 87320 }, { - "epoch": 0.78, - "learning_rate": 1.1132330420682822e-05, - "loss": 0.1914, + "epoch": 0.19, + "learning_rate": 4.034775508377889e-05, + "loss": 0.2173, "step": 87330 }, { - "epoch": 0.78, - "learning_rate": 1.1127826321952978e-05, - "loss": 0.1971, + "epoch": 0.19, + "learning_rate": 4.0346636540569565e-05, + "loss": 0.2182, "step": 87340 }, { - "epoch": 0.78, - "learning_rate": 1.1123322223223134e-05, - "loss": 0.181, + "epoch": 0.19, + "learning_rate": 4.0345517997360237e-05, + "loss": 0.2087, "step": 87350 }, { - "epoch": 0.78, - "learning_rate": 1.111881812449329e-05, - "loss": 0.1813, + "epoch": 0.19, + "learning_rate": 4.0344399454150914e-05, + "loss": 0.2121, "step": 87360 }, { - "epoch": 0.78, - "learning_rate": 1.1114314025763445e-05, - "loss": 0.1887, + "epoch": 0.2, + "learning_rate": 4.034328091094159e-05, + "loss": 0.2085, "step": 87370 }, { - "epoch": 0.78, - "learning_rate": 1.1109809927033601e-05, - "loss": 0.1785, + "epoch": 0.2, + "learning_rate": 4.0342162367732264e-05, + "loss": 0.2189, "step": 87380 }, { - "epoch": 0.78, - "learning_rate": 1.1105305828303757e-05, - "loss": 0.1889, + "epoch": 0.2, + "learning_rate": 4.034104382452295e-05, + "loss": 0.2132, "step": 87390 }, { - "epoch": 0.78, - "learning_rate": 1.1100801729573913e-05, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.033992528131362e-05, + "loss": 0.2084, "step": 87400 }, { - "epoch": 0.78, - "learning_rate": 1.1096297630844068e-05, - "loss": 0.1852, + "epoch": 0.2, + "learning_rate": 4.03388067381043e-05, + "loss": 0.2212, "step": 87410 }, { - "epoch": 0.78, - "learning_rate": 1.1091793532114224e-05, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.033768819489497e-05, + "loss": 0.2145, "step": 87420 }, { - "epoch": 0.78, - "learning_rate": 1.108728943338438e-05, - "loss": 0.1902, + "epoch": 0.2, + "learning_rate": 4.0336569651685646e-05, + "loss": 0.2066, "step": 87430 }, { - "epoch": 0.78, - "learning_rate": 1.1082785334654536e-05, - "loss": 0.1832, + "epoch": 0.2, + "learning_rate": 4.0335451108476324e-05, + "loss": 0.2153, "step": 87440 }, { - "epoch": 0.78, - "learning_rate": 1.1078281235924692e-05, - "loss": 0.1821, + "epoch": 0.2, + "learning_rate": 4.0334332565266995e-05, + "loss": 0.2115, "step": 87450 }, { - "epoch": 0.78, - "learning_rate": 1.1073777137194847e-05, - "loss": 0.1887, + "epoch": 0.2, + "learning_rate": 4.033321402205767e-05, + "loss": 0.2114, "step": 87460 }, { - "epoch": 0.78, - "learning_rate": 1.1069273038465005e-05, - "loss": 0.1897, + "epoch": 0.2, + "learning_rate": 4.0332095478848345e-05, + "loss": 0.2087, "step": 87470 }, { - "epoch": 0.78, - "learning_rate": 1.1064768939735159e-05, - "loss": 0.1907, + "epoch": 0.2, + "learning_rate": 4.033097693563902e-05, + "loss": 0.2123, "step": 87480 }, { - "epoch": 0.78, - "learning_rate": 1.1060264841005315e-05, - "loss": 0.1849, + "epoch": 0.2, + "learning_rate": 4.03298583924297e-05, + "loss": 0.218, "step": 87490 }, { - "epoch": 0.78, - "learning_rate": 1.105576074227547e-05, - "loss": 0.1905, + "epoch": 0.2, + "learning_rate": 4.032885170354131e-05, + "loss": 0.2129, "step": 87500 }, { - "epoch": 0.78, - "learning_rate": 1.1051256643545626e-05, - "loss": 0.1808, + "epoch": 0.2, + "learning_rate": 4.032773316033199e-05, + "loss": 0.2146, "step": 87510 }, { - "epoch": 0.78, - "learning_rate": 1.1046752544815784e-05, - "loss": 0.188, + "epoch": 0.2, + "learning_rate": 4.032661461712266e-05, + "loss": 0.2219, "step": 87520 }, { - "epoch": 0.78, - "learning_rate": 1.1042248446085938e-05, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 4.0325496073913336e-05, + "loss": 0.21, "step": 87530 }, { - "epoch": 0.78, - "learning_rate": 1.1037744347356095e-05, - "loss": 0.1867, + "epoch": 0.2, + "learning_rate": 4.032437753070401e-05, + "loss": 0.2111, "step": 87540 }, { - "epoch": 0.78, - "learning_rate": 1.103324024862625e-05, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.032325898749469e-05, + "loss": 0.2059, "step": 87550 }, { - "epoch": 0.78, - "learning_rate": 1.1028736149896405e-05, - "loss": 0.19, + "epoch": 0.2, + "learning_rate": 4.032214044428537e-05, + "loss": 0.2133, "step": 87560 }, { - "epoch": 0.78, - "learning_rate": 1.1024232051166563e-05, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 4.032102190107604e-05, + "loss": 0.2142, "step": 87570 }, { - "epoch": 0.78, - "learning_rate": 1.1019727952436717e-05, - "loss": 0.1909, + "epoch": 0.2, + "learning_rate": 4.031990335786672e-05, + "loss": 0.212, "step": 87580 }, { - "epoch": 0.78, - "learning_rate": 1.1015223853706874e-05, - "loss": 0.192, + "epoch": 0.2, + "learning_rate": 4.031878481465739e-05, + "loss": 0.2148, "step": 87590 }, { - "epoch": 0.78, - "learning_rate": 1.101071975497703e-05, - "loss": 0.1842, + "epoch": 0.2, + "learning_rate": 4.031766627144807e-05, + "loss": 0.2132, "step": 87600 }, { - "epoch": 0.78, - "learning_rate": 1.1006215656247186e-05, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 4.0316547728238746e-05, + "loss": 0.2123, "step": 87610 }, { - "epoch": 0.78, - "learning_rate": 1.1001711557517342e-05, - "loss": 0.1874, + "epoch": 0.2, + "learning_rate": 4.031542918502942e-05, + "loss": 0.2059, "step": 87620 }, { - "epoch": 0.78, - "learning_rate": 1.0997207458787496e-05, - "loss": 0.1825, + "epoch": 0.2, + "learning_rate": 4.0314310641820095e-05, + "loss": 0.2119, "step": 87630 }, { - "epoch": 0.78, - "learning_rate": 1.0992703360057653e-05, - "loss": 0.1894, + "epoch": 0.2, + "learning_rate": 4.0313192098610766e-05, + "loss": 0.2154, "step": 87640 }, { - "epoch": 0.78, - "learning_rate": 1.098819926132781e-05, - "loss": 0.1838, + "epoch": 0.2, + "learning_rate": 4.0312073555401444e-05, + "loss": 0.2084, "step": 87650 }, { - "epoch": 0.78, - "learning_rate": 1.0983695162597965e-05, - "loss": 0.188, + "epoch": 0.2, + "learning_rate": 4.031095501219212e-05, + "loss": 0.2098, "step": 87660 }, { - "epoch": 0.78, - "learning_rate": 1.097919106386812e-05, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.03098364689828e-05, + "loss": 0.2144, "step": 87670 }, { - "epoch": 0.78, - "learning_rate": 1.0974686965138277e-05, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 4.030871792577348e-05, + "loss": 0.2102, "step": 87680 }, { - "epoch": 0.78, - "learning_rate": 1.0970182866408432e-05, - "loss": 0.1916, + "epoch": 0.2, + "learning_rate": 4.030759938256415e-05, + "loss": 0.2098, "step": 87690 }, { - "epoch": 0.78, - "learning_rate": 1.0965678767678588e-05, - "loss": 0.1832, + "epoch": 0.2, + "learning_rate": 4.030648083935483e-05, + "loss": 0.2113, "step": 87700 }, { - "epoch": 0.78, - "learning_rate": 1.0961174668948744e-05, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.0305362296145505e-05, + "loss": 0.2134, "step": 87710 }, { - "epoch": 0.78, - "learning_rate": 1.09566705702189e-05, - "loss": 0.1925, + "epoch": 0.2, + "learning_rate": 4.0304243752936176e-05, + "loss": 0.2103, "step": 87720 }, { - "epoch": 0.78, - "learning_rate": 1.0952166471489056e-05, - "loss": 0.1837, + "epoch": 0.2, + "learning_rate": 4.0303125209726854e-05, + "loss": 0.213, "step": 87730 }, { - "epoch": 0.78, - "learning_rate": 1.0947662372759211e-05, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.0302006666517525e-05, + "loss": 0.2151, "step": 87740 }, { - "epoch": 0.78, - "learning_rate": 1.0943158274029367e-05, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 4.03008881233082e-05, + "loss": 0.2089, "step": 87750 }, { - "epoch": 0.78, - "learning_rate": 1.0938654175299523e-05, - "loss": 0.1866, + "epoch": 0.2, + "learning_rate": 4.029976958009888e-05, + "loss": 0.214, "step": 87760 }, { - "epoch": 0.78, - "learning_rate": 1.0934150076569679e-05, - "loss": 0.1901, + "epoch": 0.2, + "learning_rate": 4.029865103688956e-05, + "loss": 0.2157, "step": 87770 }, { - "epoch": 0.78, - "learning_rate": 1.0929645977839835e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.029753249368024e-05, + "loss": 0.2117, "step": 87780 }, { - "epoch": 0.78, - "learning_rate": 1.092514187910999e-05, - "loss": 0.1903, + "epoch": 0.2, + "learning_rate": 4.029641395047091e-05, + "loss": 0.2086, "step": 87790 }, { - "epoch": 0.78, - "learning_rate": 1.0920637780380146e-05, - "loss": 0.1927, + "epoch": 0.2, + "learning_rate": 4.0295295407261586e-05, + "loss": 0.2165, "step": 87800 }, { - "epoch": 0.78, - "learning_rate": 1.0916133681650302e-05, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 4.029417686405226e-05, + "loss": 0.2141, "step": 87810 }, { - "epoch": 0.78, - "learning_rate": 1.091162958292046e-05, - "loss": 0.194, + "epoch": 0.2, + "learning_rate": 4.0293058320842935e-05, + "loss": 0.212, "step": 87820 }, { - "epoch": 0.78, - "learning_rate": 1.0907125484190614e-05, - "loss": 0.1921, + "epoch": 0.2, + "learning_rate": 4.029193977763361e-05, + "loss": 0.2152, "step": 87830 }, { - "epoch": 0.78, - "learning_rate": 1.090262138546077e-05, - "loss": 0.1927, + "epoch": 0.2, + "learning_rate": 4.0290821234424284e-05, + "loss": 0.2123, "step": 87840 }, { - "epoch": 0.78, - "learning_rate": 1.0898117286730925e-05, - "loss": 0.1918, + "epoch": 0.2, + "learning_rate": 4.028970269121496e-05, + "loss": 0.2126, "step": 87850 }, { - "epoch": 0.78, - "learning_rate": 1.0893613188001081e-05, - "loss": 0.1857, + "epoch": 0.2, + "learning_rate": 4.028858414800564e-05, + "loss": 0.2157, "step": 87860 }, { - "epoch": 0.78, - "learning_rate": 1.0889109089271238e-05, - "loss": 0.184, + "epoch": 0.2, + "learning_rate": 4.028746560479632e-05, + "loss": 0.2073, "step": 87870 }, { - "epoch": 0.78, - "learning_rate": 1.0884604990541393e-05, - "loss": 0.1926, + "epoch": 0.2, + "learning_rate": 4.0286347061586996e-05, + "loss": 0.2103, "step": 87880 }, { - "epoch": 0.78, - "learning_rate": 1.088010089181155e-05, - "loss": 0.1947, + "epoch": 0.2, + "learning_rate": 4.028522851837767e-05, + "loss": 0.2089, "step": 87890 }, { - "epoch": 0.78, - "learning_rate": 1.0875596793081704e-05, - "loss": 0.1851, + "epoch": 0.2, + "learning_rate": 4.0284109975168345e-05, + "loss": 0.2152, "step": 87900 }, { - "epoch": 0.78, - "learning_rate": 1.087109269435186e-05, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 4.0282991431959016e-05, + "loss": 0.2117, "step": 87910 }, { - "epoch": 0.78, - "learning_rate": 1.0866588595622017e-05, - "loss": 0.1915, + "epoch": 0.2, + "learning_rate": 4.0281872888749694e-05, + "loss": 0.216, "step": 87920 }, { - "epoch": 0.79, - "learning_rate": 1.0862084496892172e-05, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 4.028075434554037e-05, + "loss": 0.2109, "step": 87930 }, { - "epoch": 0.79, - "learning_rate": 1.0857580398162329e-05, - "loss": 0.1902, + "epoch": 0.2, + "learning_rate": 4.027963580233104e-05, + "loss": 0.2122, "step": 87940 }, { - "epoch": 0.79, - "learning_rate": 1.0853076299432483e-05, - "loss": 0.1925, + "epoch": 0.2, + "learning_rate": 4.027851725912172e-05, + "loss": 0.2121, "step": 87950 }, { - "epoch": 0.79, - "learning_rate": 1.084857220070264e-05, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 4.027739871591239e-05, + "loss": 0.2105, "step": 87960 }, { - "epoch": 0.79, - "learning_rate": 1.0844068101972796e-05, - "loss": 0.1869, + "epoch": 0.2, + "learning_rate": 4.027628017270308e-05, + "loss": 0.2115, "step": 87970 }, { - "epoch": 0.79, - "learning_rate": 1.083956400324295e-05, - "loss": 0.1937, + "epoch": 0.2, + "learning_rate": 4.0275161629493755e-05, + "loss": 0.2161, "step": 87980 }, { - "epoch": 0.79, - "learning_rate": 1.0835059904513108e-05, - "loss": 0.189, + "epoch": 0.2, + "learning_rate": 4.0274043086284426e-05, + "loss": 0.2127, "step": 87990 }, { - "epoch": 0.79, - "learning_rate": 1.0830555805783262e-05, - "loss": 0.1923, - "step": 88000 - }, - { - "epoch": 0.79, - "eval_NEIMS_canon_smiles": 0.9387333333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.05748333333333333, - "eval_NEIMS_daylight_tanimoto_simil": 0.46029620466408705, - "eval_NEIMS_exact_mols": 0.05728333333333333, - "eval_NEIMS_exact_smiles": 0.05525, - "eval_NEIMS_loss": 0.21825504302978516, - "eval_NEIMS_matched_formulas": 0.5685166666666667, - "eval_NEIMS_morgan_tanimoto_simil": 0.36367257426355964, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.05765, - "eval_NEIMS_runtime": 714.9592, - "eval_NEIMS_samples_per_second": 83.921, - "eval_NEIMS_steps_per_second": 1.312, - "step": 88000 - }, - { - "epoch": 0.79, - "eval_RASSP_canon_smiles": 0.934050155274318, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.13558954152335792, - "eval_RASSP_daylight_tanimoto_simil": 0.5863277874216708, - "eval_RASSP_exact_mols": 0.13492169499449028, - "eval_RASSP_exact_smiles": 0.130063111496978, - "eval_RASSP_loss": 0.15727342665195465, - "eval_RASSP_matched_formulas": 0.7488897051457575, - "eval_RASSP_morgan_tanimoto_simil": 0.45645551107265253, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.1350719604634855, - "eval_RASSP_runtime": 816.8086, - "eval_RASSP_samples_per_second": 73.327, - "eval_RASSP_steps_per_second": 1.146, - "step": 88000 - }, - { - "epoch": 0.79, - "eval_NIST_canon_smiles": 0.882315363594421, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.013166767221492707, - "eval_NIST_daylight_tanimoto_simil": 0.27067425568062337, - "eval_NIST_exact_mols": 0.01238598857223977, - "eval_NIST_exact_smiles": 0.01125031053696277, - "eval_NIST_loss": 1.4268168210983276, - "eval_NIST_matched_formulas": 0.08808602761117224, - "eval_NIST_morgan_tanimoto_simil": 0.22409104597515142, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.013095787344287894, - "eval_NIST_runtime": 467.8554, - "eval_NIST_samples_per_second": 60.226, - "eval_NIST_steps_per_second": 0.943, + "epoch": 0.2, + "learning_rate": 4.0272924543075104e-05, + "loss": 0.2167, "step": 88000 }, { - "epoch": 0.79, - "learning_rate": 1.082605170705342e-05, - "loss": 0.1873, + "epoch": 0.2, + "learning_rate": 4.0271805999865775e-05, + "loss": 0.2153, "step": 88010 }, { - "epoch": 0.79, - "learning_rate": 1.0821547608323575e-05, - "loss": 0.1932, + "epoch": 0.2, + "learning_rate": 4.027068745665645e-05, + "loss": 0.2126, "step": 88020 }, { - "epoch": 0.79, - "learning_rate": 1.0817493919466714e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.026956891344713e-05, + "loss": 0.2123, "step": 88030 }, { - "epoch": 0.79, - "learning_rate": 1.0812989820736872e-05, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 4.02684503702378e-05, + "loss": 0.2111, "step": 88040 }, { - "epoch": 0.79, - "learning_rate": 1.0808485722007026e-05, - "loss": 0.1893, + "epoch": 0.2, + "learning_rate": 4.026733182702848e-05, + "loss": 0.2113, "step": 88050 }, { - "epoch": 0.79, - "learning_rate": 1.0803981623277183e-05, - "loss": 0.1822, + "epoch": 0.2, + "learning_rate": 4.026621328381915e-05, + "loss": 0.2198, "step": 88060 }, { - "epoch": 0.79, - "learning_rate": 1.0799477524547339e-05, - "loss": 0.188, + "epoch": 0.2, + "learning_rate": 4.026509474060983e-05, + "loss": 0.2148, "step": 88070 }, { - "epoch": 0.79, - "learning_rate": 1.0794973425817495e-05, - "loss": 0.1882, + "epoch": 0.2, + "learning_rate": 4.026397619740051e-05, + "loss": 0.2154, "step": 88080 }, { - "epoch": 0.79, - "learning_rate": 1.079046932708765e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.0262857654191185e-05, + "loss": 0.2162, "step": 88090 }, { - "epoch": 0.79, - "learning_rate": 1.0785965228357805e-05, - "loss": 0.19, + "epoch": 0.2, + "learning_rate": 4.026173911098186e-05, + "loss": 0.2102, "step": 88100 }, { - "epoch": 0.79, - "learning_rate": 1.0781461129627962e-05, - "loss": 0.1902, + "epoch": 0.2, + "learning_rate": 4.0260620567772534e-05, + "loss": 0.2161, "step": 88110 }, { - "epoch": 0.79, - "learning_rate": 1.0776957030898118e-05, - "loss": 0.1865, + "epoch": 0.2, + "learning_rate": 4.025950202456321e-05, + "loss": 0.2082, "step": 88120 }, { - "epoch": 0.79, - "learning_rate": 1.0772452932168274e-05, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.025838348135388e-05, + "loss": 0.2102, "step": 88130 }, { - "epoch": 0.79, - "learning_rate": 1.076794883343843e-05, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 4.025726493814456e-05, + "loss": 0.2099, "step": 88140 }, { - "epoch": 0.79, - "learning_rate": 1.0763444734708585e-05, - "loss": 0.1894, + "epoch": 0.2, + "learning_rate": 4.025614639493524e-05, + "loss": 0.2118, "step": 88150 }, { - "epoch": 0.79, - "learning_rate": 1.0758940635978741e-05, - "loss": 0.1849, + "epoch": 0.2, + "learning_rate": 4.025502785172591e-05, + "loss": 0.2113, "step": 88160 }, { - "epoch": 0.79, - "learning_rate": 1.0754436537248897e-05, - "loss": 0.1933, + "epoch": 0.2, + "learning_rate": 4.025390930851659e-05, + "loss": 0.2116, "step": 88170 }, { - "epoch": 0.79, - "learning_rate": 1.0749932438519053e-05, - "loss": 0.1912, + "epoch": 0.2, + "learning_rate": 4.0252790765307266e-05, + "loss": 0.2113, "step": 88180 }, { - "epoch": 0.79, - "learning_rate": 1.0745428339789209e-05, - "loss": 0.1851, + "epoch": 0.2, + "learning_rate": 4.0251672222097944e-05, + "loss": 0.214, "step": 88190 }, { - "epoch": 0.79, - "learning_rate": 1.0740924241059364e-05, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 4.025055367888862e-05, + "loss": 0.2165, "step": 88200 }, { - "epoch": 0.79, - "learning_rate": 1.073642014232952e-05, - "loss": 0.1915, + "epoch": 0.2, + "learning_rate": 4.024943513567929e-05, + "loss": 0.2144, "step": 88210 }, { - "epoch": 0.79, - "learning_rate": 1.0731916043599676e-05, - "loss": 0.186, + "epoch": 0.2, + "learning_rate": 4.024831659246997e-05, + "loss": 0.2107, "step": 88220 }, { - "epoch": 0.79, - "learning_rate": 1.0727411944869832e-05, - "loss": 0.1833, + "epoch": 0.2, + "learning_rate": 4.024719804926064e-05, + "loss": 0.2081, "step": 88230 }, { - "epoch": 0.79, - "learning_rate": 1.0722907846139988e-05, - "loss": 0.1841, + "epoch": 0.2, + "learning_rate": 4.024607950605132e-05, + "loss": 0.2169, "step": 88240 }, { - "epoch": 0.79, - "learning_rate": 1.0718403747410143e-05, - "loss": 0.1814, + "epoch": 0.2, + "learning_rate": 4.0244960962842e-05, + "loss": 0.2183, "step": 88250 }, { - "epoch": 0.79, - "learning_rate": 1.07138996486803e-05, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 4.024384241963267e-05, + "loss": 0.218, "step": 88260 }, { - "epoch": 0.79, - "learning_rate": 1.0709395549950457e-05, - "loss": 0.193, + "epoch": 0.2, + "learning_rate": 4.024272387642335e-05, + "loss": 0.2106, "step": 88270 }, { - "epoch": 0.79, - "learning_rate": 1.070489145122061e-05, - "loss": 0.1821, + "epoch": 0.2, + "learning_rate": 4.0241605333214025e-05, + "loss": 0.2077, "step": 88280 }, { - "epoch": 0.79, - "learning_rate": 1.0700387352490768e-05, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.02404867900047e-05, + "loss": 0.2107, "step": 88290 }, { - "epoch": 0.79, - "learning_rate": 1.0695883253760922e-05, - "loss": 0.1882, + "epoch": 0.2, + "learning_rate": 4.023936824679538e-05, + "loss": 0.2118, "step": 88300 }, { - "epoch": 0.79, - "learning_rate": 1.0691379155031078e-05, - "loss": 0.1903, + "epoch": 0.2, + "learning_rate": 4.023824970358605e-05, + "loss": 0.2216, "step": 88310 }, { - "epoch": 0.79, - "learning_rate": 1.0686875056301236e-05, - "loss": 0.1894, + "epoch": 0.2, + "learning_rate": 4.023713116037673e-05, + "loss": 0.212, "step": 88320 }, { - "epoch": 0.79, - "learning_rate": 1.068237095757139e-05, - "loss": 0.1875, + "epoch": 0.2, + "learning_rate": 4.02360126171674e-05, + "loss": 0.2113, "step": 88330 }, { - "epoch": 0.79, - "learning_rate": 1.0677866858841547e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.023489407395808e-05, + "loss": 0.2163, "step": 88340 }, { - "epoch": 0.79, - "learning_rate": 1.0673362760111701e-05, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 4.023377553074876e-05, + "loss": 0.2102, "step": 88350 }, { - "epoch": 0.79, - "learning_rate": 1.0668858661381859e-05, - "loss": 0.193, + "epoch": 0.2, + "learning_rate": 4.023265698753943e-05, + "loss": 0.2156, "step": 88360 }, { - "epoch": 0.79, - "learning_rate": 1.0664354562652015e-05, - "loss": 0.1906, + "epoch": 0.2, + "learning_rate": 4.0231538444330106e-05, + "loss": 0.2161, "step": 88370 }, { - "epoch": 0.79, - "learning_rate": 1.0659850463922169e-05, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.0230419901120784e-05, + "loss": 0.209, "step": 88380 }, { - "epoch": 0.79, - "learning_rate": 1.0655346365192326e-05, - "loss": 0.1921, + "epoch": 0.2, + "learning_rate": 4.022930135791146e-05, + "loss": 0.2127, "step": 88390 }, { - "epoch": 0.79, - "learning_rate": 1.065084226646248e-05, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 4.022818281470213e-05, + "loss": 0.2137, "step": 88400 }, { - "epoch": 0.79, - "learning_rate": 1.0646338167732638e-05, - "loss": 0.1902, + "epoch": 0.2, + "learning_rate": 4.022706427149281e-05, + "loss": 0.2118, "step": 88410 }, { - "epoch": 0.79, - "learning_rate": 1.0641834069002794e-05, - "loss": 0.1787, + "epoch": 0.2, + "learning_rate": 4.022594572828349e-05, + "loss": 0.2171, "step": 88420 }, { - "epoch": 0.79, - "learning_rate": 1.063732997027295e-05, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 4.022482718507416e-05, + "loss": 0.2122, "step": 88430 }, { - "epoch": 0.79, - "learning_rate": 1.0632825871543105e-05, - "loss": 0.1867, + "epoch": 0.2, + "learning_rate": 4.022370864186484e-05, + "loss": 0.2154, "step": 88440 }, { - "epoch": 0.79, - "learning_rate": 1.062832177281326e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.022259009865551e-05, + "loss": 0.21, "step": 88450 }, { - "epoch": 0.79, - "learning_rate": 1.0623817674083417e-05, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.022147155544619e-05, + "loss": 0.2047, "step": 88460 }, { - "epoch": 0.79, - "learning_rate": 1.0619313575353573e-05, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 4.0220353012236865e-05, + "loss": 0.2132, "step": 88470 }, { - "epoch": 0.79, - "learning_rate": 1.0614809476623728e-05, - "loss": 0.1949, + "epoch": 0.2, + "learning_rate": 4.0219234469027536e-05, + "loss": 0.2065, "step": 88480 }, { - "epoch": 0.79, - "learning_rate": 1.0610305377893884e-05, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 4.0218115925818214e-05, + "loss": 0.2079, "step": 88490 }, { - "epoch": 0.79, - "learning_rate": 1.060580127916404e-05, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 4.021699738260889e-05, + "loss": 0.2144, "step": 88500 }, { - "epoch": 0.79, - "learning_rate": 1.0601297180434196e-05, - "loss": 0.1942, + "epoch": 0.2, + "learning_rate": 4.021587883939957e-05, + "loss": 0.2133, "step": 88510 }, { - "epoch": 0.79, - "learning_rate": 1.0596793081704352e-05, - "loss": 0.1884, + "epoch": 0.2, + "learning_rate": 4.021476029619025e-05, + "loss": 0.2095, "step": 88520 }, { - "epoch": 0.79, - "learning_rate": 1.0592288982974507e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.021364175298092e-05, + "loss": 0.2188, "step": 88530 }, { - "epoch": 0.79, - "learning_rate": 1.0587784884244663e-05, - "loss": 0.1867, + "epoch": 0.2, + "learning_rate": 4.02125232097716e-05, + "loss": 0.2134, "step": 88540 }, { - "epoch": 0.79, - "learning_rate": 1.0583280785514819e-05, - "loss": 0.1889, + "epoch": 0.2, + "learning_rate": 4.021140466656227e-05, + "loss": 0.2171, "step": 88550 }, { - "epoch": 0.79, - "learning_rate": 1.0578776686784975e-05, - "loss": 0.1883, + "epoch": 0.2, + "learning_rate": 4.0210286123352946e-05, + "loss": 0.2125, "step": 88560 }, { - "epoch": 0.79, - "learning_rate": 1.057427258805513e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.0209167580143624e-05, + "loss": 0.2136, "step": 88570 }, { - "epoch": 0.79, - "learning_rate": 1.0569768489325286e-05, - "loss": 0.1867, + "epoch": 0.2, + "learning_rate": 4.0208049036934295e-05, + "loss": 0.2116, "step": 88580 }, { - "epoch": 0.79, - "learning_rate": 1.0565264390595442e-05, - "loss": 0.1815, + "epoch": 0.2, + "learning_rate": 4.020693049372497e-05, + "loss": 0.2132, "step": 88590 }, { - "epoch": 0.79, - "learning_rate": 1.0560760291865598e-05, - "loss": 0.1942, + "epoch": 0.2, + "learning_rate": 4.020581195051565e-05, + "loss": 0.21, "step": 88600 }, { - "epoch": 0.79, - "learning_rate": 1.0556256193135754e-05, - "loss": 0.1898, + "epoch": 0.2, + "learning_rate": 4.020469340730633e-05, + "loss": 0.2093, "step": 88610 }, { - "epoch": 0.79, - "learning_rate": 1.055175209440591e-05, - "loss": 0.1882, + "epoch": 0.2, + "learning_rate": 4.020357486409701e-05, + "loss": 0.2126, "step": 88620 }, { - "epoch": 0.79, - "learning_rate": 1.0547247995676065e-05, - "loss": 0.1869, + "epoch": 0.2, + "learning_rate": 4.020245632088768e-05, + "loss": 0.2138, "step": 88630 }, { - "epoch": 0.79, - "learning_rate": 1.0542743896946223e-05, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.0201337777678356e-05, + "loss": 0.2155, "step": 88640 }, { - "epoch": 0.79, - "learning_rate": 1.0538239798216377e-05, - "loss": 0.1825, + "epoch": 0.2, + "learning_rate": 4.020021923446903e-05, + "loss": 0.2163, "step": 88650 }, { - "epoch": 0.79, - "learning_rate": 1.0533735699486533e-05, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 4.0199100691259705e-05, + "loss": 0.2141, "step": 88660 }, { - "epoch": 0.79, - "learning_rate": 1.0529231600756689e-05, - "loss": 0.1876, + "epoch": 0.2, + "learning_rate": 4.019798214805038e-05, + "loss": 0.2106, "step": 88670 }, { - "epoch": 0.79, - "learning_rate": 1.0524727502026844e-05, - "loss": 0.1907, + "epoch": 0.2, + "learning_rate": 4.0196863604841054e-05, + "loss": 0.2052, "step": 88680 }, { - "epoch": 0.79, - "learning_rate": 1.0520223403297002e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.019574506163173e-05, + "loss": 0.2098, "step": 88690 }, { - "epoch": 0.79, - "learning_rate": 1.0515719304567156e-05, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.019462651842241e-05, + "loss": 0.2117, "step": 88700 }, { - "epoch": 0.79, - "learning_rate": 1.0511215205837313e-05, - "loss": 0.1884, + "epoch": 0.2, + "learning_rate": 4.019350797521309e-05, + "loss": 0.2082, "step": 88710 }, { - "epoch": 0.79, - "learning_rate": 1.0506711107107468e-05, - "loss": 0.1878, + "epoch": 0.2, + "learning_rate": 4.019238943200376e-05, + "loss": 0.2113, "step": 88720 }, { - "epoch": 0.79, - "learning_rate": 1.0502207008377623e-05, - "loss": 0.1895, + "epoch": 0.2, + "learning_rate": 4.019127088879444e-05, + "loss": 0.209, "step": 88730 }, { - "epoch": 0.79, - "learning_rate": 1.0497702909647781e-05, - "loss": 0.1822, + "epoch": 0.2, + "learning_rate": 4.0190152345585115e-05, + "loss": 0.2137, "step": 88740 }, { - "epoch": 0.79, - "learning_rate": 1.0493198810917935e-05, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.0189033802375786e-05, + "loss": 0.2103, "step": 88750 }, { - "epoch": 0.79, - "learning_rate": 1.0488694712188092e-05, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 4.0187915259166464e-05, + "loss": 0.2051, "step": 88760 }, { - "epoch": 0.79, - "learning_rate": 1.0484190613458247e-05, - "loss": 0.1955, + "epoch": 0.2, + "learning_rate": 4.0186796715957135e-05, + "loss": 0.2148, "step": 88770 }, { - "epoch": 0.79, - "learning_rate": 1.0479686514728404e-05, - "loss": 0.1878, + "epoch": 0.2, + "learning_rate": 4.018567817274781e-05, + "loss": 0.2158, "step": 88780 }, { - "epoch": 0.79, - "learning_rate": 1.047518241599856e-05, - "loss": 0.1913, + "epoch": 0.2, + "learning_rate": 4.018455962953849e-05, + "loss": 0.2127, "step": 88790 }, { - "epoch": 0.79, - "learning_rate": 1.0470678317268714e-05, - "loss": 0.1877, + "epoch": 0.2, + "learning_rate": 4.018344108632917e-05, + "loss": 0.2128, "step": 88800 }, { - "epoch": 0.79, - "learning_rate": 1.0466174218538871e-05, - "loss": 0.1861, + "epoch": 0.2, + "learning_rate": 4.018232254311985e-05, + "loss": 0.2057, "step": 88810 }, { - "epoch": 0.79, - "learning_rate": 1.0461670119809026e-05, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 4.018120399991052e-05, + "loss": 0.208, "step": 88820 }, { - "epoch": 0.79, - "learning_rate": 1.0457166021079183e-05, - "loss": 0.1865, + "epoch": 0.2, + "learning_rate": 4.0180085456701196e-05, + "loss": 0.2074, "step": 88830 }, { - "epoch": 0.79, - "learning_rate": 1.0452661922349339e-05, - "loss": 0.1832, + "epoch": 0.2, + "learning_rate": 4.0178966913491874e-05, + "loss": 0.2134, "step": 88840 }, { - "epoch": 0.79, - "learning_rate": 1.0448157823619495e-05, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 4.0177848370282545e-05, + "loss": 0.2107, "step": 88850 }, { - "epoch": 0.79, - "learning_rate": 1.044365372488965e-05, - "loss": 0.1827, + "epoch": 0.2, + "learning_rate": 4.017672982707322e-05, + "loss": 0.2114, "step": 88860 }, { - "epoch": 0.79, - "learning_rate": 1.0439149626159805e-05, - "loss": 0.179, + "epoch": 0.2, + "learning_rate": 4.0175611283863894e-05, + "loss": 0.2089, "step": 88870 }, { - "epoch": 0.79, - "learning_rate": 1.0434645527429962e-05, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.017449274065457e-05, + "loss": 0.2134, "step": 88880 }, { - "epoch": 0.79, - "learning_rate": 1.0430141428700118e-05, - "loss": 0.1877, + "epoch": 0.2, + "learning_rate": 4.017337419744525e-05, + "loss": 0.211, "step": 88890 }, { - "epoch": 0.79, - "learning_rate": 1.0425637329970274e-05, - "loss": 0.1825, + "epoch": 0.2, + "learning_rate": 4.017225565423592e-05, + "loss": 0.2103, "step": 88900 }, { - "epoch": 0.79, - "learning_rate": 1.042113323124043e-05, - "loss": 0.1883, + "epoch": 0.2, + "learning_rate": 4.01711371110266e-05, + "loss": 0.2107, "step": 88910 }, { - "epoch": 0.79, - "learning_rate": 1.0416629132510585e-05, - "loss": 0.1801, + "epoch": 0.2, + "learning_rate": 4.017001856781728e-05, + "loss": 0.2079, "step": 88920 }, { - "epoch": 0.79, - "learning_rate": 1.0412125033780741e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.0168900024607955e-05, + "loss": 0.2144, "step": 88930 }, { - "epoch": 0.79, - "learning_rate": 1.0407620935050897e-05, - "loss": 0.1947, + "epoch": 0.2, + "learning_rate": 4.016778148139863e-05, + "loss": 0.2103, "step": 88940 }, { - "epoch": 0.79, - "learning_rate": 1.0403116836321053e-05, - "loss": 0.1834, + "epoch": 0.2, + "learning_rate": 4.0166662938189304e-05, + "loss": 0.203, "step": 88950 }, { - "epoch": 0.79, - "learning_rate": 1.0398612737591208e-05, - "loss": 0.1854, + "epoch": 0.2, + "learning_rate": 4.016554439497998e-05, + "loss": 0.2093, "step": 88960 }, { - "epoch": 0.79, - "learning_rate": 1.0394108638861364e-05, - "loss": 0.1869, + "epoch": 0.2, + "learning_rate": 4.016442585177065e-05, + "loss": 0.2126, "step": 88970 }, { - "epoch": 0.79, - "learning_rate": 1.038960454013152e-05, - "loss": 0.1883, + "epoch": 0.2, + "learning_rate": 4.016330730856133e-05, + "loss": 0.2111, "step": 88980 }, { - "epoch": 0.79, - "learning_rate": 1.0385100441401678e-05, - "loss": 0.1878, + "epoch": 0.2, + "learning_rate": 4.016218876535201e-05, + "loss": 0.2048, "step": 88990 }, { - "epoch": 0.79, - "learning_rate": 1.0380596342671832e-05, - "loss": 0.1861, + "epoch": 0.2, + "learning_rate": 4.016107022214268e-05, + "loss": 0.2108, "step": 89000 }, { - "epoch": 0.79, - "learning_rate": 1.0376092243941987e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.015995167893336e-05, + "loss": 0.2096, "step": 89010 }, { - "epoch": 0.79, - "learning_rate": 1.0371588145212143e-05, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.0158833135724036e-05, + "loss": 0.2118, "step": 89020 }, { - "epoch": 0.79, - "learning_rate": 1.0367084046482299e-05, - "loss": 0.1934, + "epoch": 0.2, + "learning_rate": 4.0157714592514714e-05, + "loss": 0.2054, "step": 89030 }, { - "epoch": 0.79, - "learning_rate": 1.0362579947752457e-05, - "loss": 0.1885, + "epoch": 0.2, + "learning_rate": 4.0156596049305385e-05, + "loss": 0.2085, "step": 89040 }, { - "epoch": 0.8, - "learning_rate": 1.035807584902261e-05, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.015547750609606e-05, + "loss": 0.2065, "step": 89050 }, { - "epoch": 0.8, - "learning_rate": 1.0353571750292768e-05, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 4.015435896288674e-05, + "loss": 0.2081, "step": 89060 }, { - "epoch": 0.8, - "learning_rate": 1.0349067651562922e-05, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.015324041967741e-05, + "loss": 0.2099, "step": 89070 }, { - "epoch": 0.8, - "learning_rate": 1.0344563552833078e-05, - "loss": 0.1877, + "epoch": 0.2, + "learning_rate": 4.015212187646809e-05, + "loss": 0.2088, "step": 89080 }, { - "epoch": 0.8, - "learning_rate": 1.0340059454103236e-05, - "loss": 0.1849, + "epoch": 0.2, + "learning_rate": 4.015100333325876e-05, + "loss": 0.2128, "step": 89090 }, { - "epoch": 0.8, - "learning_rate": 1.033555535537339e-05, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.014988479004944e-05, + "loss": 0.2134, "step": 89100 }, { - "epoch": 0.8, - "learning_rate": 1.0331051256643547e-05, - "loss": 0.1827, + "epoch": 0.2, + "learning_rate": 4.014876624684012e-05, + "loss": 0.2112, "step": 89110 }, { - "epoch": 0.8, - "learning_rate": 1.0326547157913701e-05, - "loss": 0.1885, + "epoch": 0.2, + "learning_rate": 4.0147647703630795e-05, + "loss": 0.2152, "step": 89120 }, { - "epoch": 0.8, - "learning_rate": 1.0322043059183857e-05, - "loss": 0.1921, + "epoch": 0.2, + "learning_rate": 4.014652916042147e-05, + "loss": 0.211, "step": 89130 }, { - "epoch": 0.8, - "learning_rate": 1.0317538960454015e-05, - "loss": 0.1792, + "epoch": 0.2, + "learning_rate": 4.0145410617212144e-05, + "loss": 0.2144, "step": 89140 }, { - "epoch": 0.8, - "learning_rate": 1.0313034861724169e-05, - "loss": 0.1806, + "epoch": 0.2, + "learning_rate": 4.014429207400282e-05, + "loss": 0.2088, "step": 89150 }, { - "epoch": 0.8, - "learning_rate": 1.0308530762994326e-05, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 4.01431735307935e-05, + "loss": 0.2085, "step": 89160 }, { - "epoch": 0.8, - "learning_rate": 1.030402666426448e-05, - "loss": 0.1861, + "epoch": 0.2, + "learning_rate": 4.014205498758417e-05, + "loss": 0.2089, "step": 89170 }, { - "epoch": 0.8, - "learning_rate": 1.0299522565534638e-05, - "loss": 0.1908, + "epoch": 0.2, + "learning_rate": 4.014093644437485e-05, + "loss": 0.2155, "step": 89180 }, { - "epoch": 0.8, - "learning_rate": 1.0295018466804794e-05, - "loss": 0.192, + "epoch": 0.2, + "learning_rate": 4.013981790116552e-05, + "loss": 0.2112, "step": 89190 }, { - "epoch": 0.8, - "learning_rate": 1.0290514368074948e-05, - "loss": 0.1893, + "epoch": 0.2, + "learning_rate": 4.01386993579562e-05, + "loss": 0.215, "step": 89200 }, { - "epoch": 0.8, - "learning_rate": 1.0286010269345105e-05, - "loss": 0.1912, + "epoch": 0.2, + "learning_rate": 4.0137580814746876e-05, + "loss": 0.2134, "step": 89210 }, { - "epoch": 0.8, - "learning_rate": 1.028150617061526e-05, - "loss": 0.188, + "epoch": 0.2, + "learning_rate": 4.0136462271537554e-05, + "loss": 0.2126, "step": 89220 }, { - "epoch": 0.8, - "learning_rate": 1.0277002071885417e-05, - "loss": 0.1816, + "epoch": 0.2, + "learning_rate": 4.013534372832823e-05, + "loss": 0.2108, "step": 89230 }, { - "epoch": 0.8, - "learning_rate": 1.0272497973155572e-05, - "loss": 0.1808, + "epoch": 0.2, + "learning_rate": 4.01342251851189e-05, + "loss": 0.2064, "step": 89240 }, { - "epoch": 0.8, - "learning_rate": 1.0267993874425728e-05, - "loss": 0.186, + "epoch": 0.2, + "learning_rate": 4.013310664190958e-05, + "loss": 0.2132, "step": 89250 }, { - "epoch": 0.8, - "learning_rate": 1.0263489775695884e-05, - "loss": 0.1952, + "epoch": 0.2, + "learning_rate": 4.013198809870026e-05, + "loss": 0.2162, "step": 89260 }, { - "epoch": 0.8, - "learning_rate": 1.0258985676966038e-05, - "loss": 0.1829, + "epoch": 0.2, + "learning_rate": 4.013086955549093e-05, + "loss": 0.2072, "step": 89270 }, { - "epoch": 0.8, - "learning_rate": 1.0254481578236196e-05, - "loss": 0.1875, + "epoch": 0.2, + "learning_rate": 4.012975101228161e-05, + "loss": 0.2116, "step": 89280 }, { - "epoch": 0.8, - "learning_rate": 1.0249977479506351e-05, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.012863246907228e-05, + "loss": 0.2099, "step": 89290 }, { - "epoch": 0.8, - "learning_rate": 1.0245473380776507e-05, - "loss": 0.1899, + "epoch": 0.2, + "learning_rate": 4.012751392586296e-05, + "loss": 0.2107, "step": 89300 }, { - "epoch": 0.8, - "learning_rate": 1.0240969282046663e-05, - "loss": 0.1897, + "epoch": 0.2, + "learning_rate": 4.0126395382653635e-05, + "loss": 0.2043, "step": 89310 }, { - "epoch": 0.8, - "learning_rate": 1.0236465183316819e-05, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.0125276839444306e-05, + "loss": 0.2106, "step": 89320 }, { - "epoch": 0.8, - "learning_rate": 1.0231961084586975e-05, - "loss": 0.1908, + "epoch": 0.2, + "learning_rate": 4.012415829623499e-05, + "loss": 0.213, "step": 89330 }, { - "epoch": 0.8, - "learning_rate": 1.022745698585713e-05, - "loss": 0.1857, + "epoch": 0.2, + "learning_rate": 4.012303975302566e-05, + "loss": 0.2105, "step": 89340 }, { - "epoch": 0.8, - "learning_rate": 1.0222952887127286e-05, - "loss": 0.1862, + "epoch": 0.2, + "learning_rate": 4.012192120981634e-05, + "loss": 0.212, "step": 89350 }, { - "epoch": 0.8, - "learning_rate": 1.0218448788397442e-05, - "loss": 0.1841, + "epoch": 0.2, + "learning_rate": 4.012080266660701e-05, + "loss": 0.2106, "step": 89360 }, { - "epoch": 0.8, - "learning_rate": 1.0213944689667598e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.011968412339769e-05, + "loss": 0.2112, "step": 89370 }, { - "epoch": 0.8, - "learning_rate": 1.0209440590937754e-05, - "loss": 0.1875, + "epoch": 0.2, + "learning_rate": 4.0118565580188367e-05, + "loss": 0.2154, "step": 89380 }, { - "epoch": 0.8, - "learning_rate": 1.020493649220791e-05, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 4.011744703697904e-05, + "loss": 0.2098, "step": 89390 }, { - "epoch": 0.8, - "learning_rate": 1.0200432393478065e-05, - "loss": 0.1869, + "epoch": 0.2, + "learning_rate": 4.0116328493769716e-05, + "loss": 0.2183, "step": 89400 }, { - "epoch": 0.8, - "learning_rate": 1.0195928294748221e-05, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 4.011520995056039e-05, + "loss": 0.2099, "step": 89410 }, { - "epoch": 0.8, - "learning_rate": 1.0191424196018377e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.0114091407351065e-05, + "loss": 0.2099, "step": 89420 }, { - "epoch": 0.8, - "learning_rate": 1.0186920097288533e-05, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.011297286414174e-05, + "loss": 0.2156, "step": 89430 }, { - "epoch": 0.8, - "learning_rate": 1.0182415998558688e-05, - "loss": 0.1874, + "epoch": 0.2, + "learning_rate": 4.011185432093242e-05, + "loss": 0.2123, "step": 89440 }, { - "epoch": 0.8, - "learning_rate": 1.0177911899828844e-05, - "loss": 0.1876, + "epoch": 0.2, + "learning_rate": 4.01107357777231e-05, + "loss": 0.2076, "step": 89450 }, { - "epoch": 0.8, - "learning_rate": 1.0173407801099002e-05, - "loss": 0.1887, + "epoch": 0.2, + "learning_rate": 4.010961723451377e-05, + "loss": 0.2112, "step": 89460 }, { - "epoch": 0.8, - "learning_rate": 1.0168903702369156e-05, - "loss": 0.1885, + "epoch": 0.2, + "learning_rate": 4.010849869130445e-05, + "loss": 0.213, "step": 89470 }, { - "epoch": 0.8, - "learning_rate": 1.0164399603639312e-05, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 4.0107380148095126e-05, + "loss": 0.2161, "step": 89480 }, { - "epoch": 0.8, - "learning_rate": 1.0159895504909467e-05, - "loss": 0.1945, + "epoch": 0.2, + "learning_rate": 4.01062616048858e-05, + "loss": 0.215, "step": 89490 }, { - "epoch": 0.8, - "learning_rate": 1.0155391406179623e-05, - "loss": 0.1846, + "epoch": 0.2, + "learning_rate": 4.010525491599741e-05, + "loss": 0.2065, "step": 89500 }, { - "epoch": 0.8, - "learning_rate": 1.015088730744978e-05, - "loss": 0.1838, + "epoch": 0.2, + "learning_rate": 4.010413637278808e-05, + "loss": 0.2082, "step": 89510 }, { - "epoch": 0.8, - "learning_rate": 1.0146383208719935e-05, - "loss": 0.1838, + "epoch": 0.2, + "learning_rate": 4.010301782957876e-05, + "loss": 0.2089, "step": 89520 }, { - "epoch": 0.8, - "learning_rate": 1.0141879109990092e-05, - "loss": 0.189, + "epoch": 0.2, + "learning_rate": 4.010189928636943e-05, + "loss": 0.2169, "step": 89530 }, { - "epoch": 0.8, - "learning_rate": 1.0137375011260246e-05, - "loss": 0.1882, + "epoch": 0.2, + "learning_rate": 4.010078074316011e-05, + "loss": 0.2156, "step": 89540 }, { - "epoch": 0.8, - "learning_rate": 1.0132870912530402e-05, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.009966219995079e-05, + "loss": 0.216, "step": 89550 }, { - "epoch": 0.8, - "learning_rate": 1.012836681380056e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.009854365674146e-05, + "loss": 0.2117, "step": 89560 }, { - "epoch": 0.8, - "learning_rate": 1.0123862715070714e-05, - "loss": 0.1907, + "epoch": 0.2, + "learning_rate": 4.009742511353214e-05, + "loss": 0.2139, "step": 89570 }, { - "epoch": 0.8, - "learning_rate": 1.0119358616340871e-05, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 4.009630657032281e-05, + "loss": 0.2058, "step": 89580 }, { - "epoch": 0.8, - "learning_rate": 1.0114854517611025e-05, - "loss": 0.1846, + "epoch": 0.2, + "learning_rate": 4.0095188027113486e-05, + "loss": 0.2088, "step": 89590 }, { - "epoch": 0.8, - "learning_rate": 1.0110350418881183e-05, - "loss": 0.1912, + "epoch": 0.2, + "learning_rate": 4.0094069483904164e-05, + "loss": 0.2096, "step": 89600 }, { - "epoch": 0.8, - "learning_rate": 1.0105846320151339e-05, - "loss": 0.1822, + "epoch": 0.2, + "learning_rate": 4.009295094069484e-05, + "loss": 0.2139, "step": 89610 }, { - "epoch": 0.8, - "learning_rate": 1.0101342221421493e-05, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 4.009183239748552e-05, + "loss": 0.2109, "step": 89620 }, { - "epoch": 0.8, - "learning_rate": 1.009683812269165e-05, - "loss": 0.1885, + "epoch": 0.2, + "learning_rate": 4.009071385427619e-05, + "loss": 0.211, "step": 89630 }, { - "epoch": 0.8, - "learning_rate": 1.0092334023961806e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.008959531106687e-05, + "loss": 0.2146, "step": 89640 }, { - "epoch": 0.8, - "learning_rate": 1.0087829925231962e-05, - "loss": 0.1851, + "epoch": 0.2, + "learning_rate": 4.008847676785755e-05, + "loss": 0.2144, "step": 89650 }, { - "epoch": 0.8, - "learning_rate": 1.0083325826502118e-05, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.008735822464822e-05, + "loss": 0.212, "step": 89660 }, { - "epoch": 0.8, - "learning_rate": 1.0078821727772274e-05, - "loss": 0.1907, + "epoch": 0.2, + "learning_rate": 4.0086239681438896e-05, + "loss": 0.2147, "step": 89670 }, { - "epoch": 0.8, - "learning_rate": 1.007431762904243e-05, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 4.008512113822957e-05, + "loss": 0.2139, "step": 89680 }, { - "epoch": 0.8, - "learning_rate": 1.0069813530312585e-05, - "loss": 0.1849, + "epoch": 0.2, + "learning_rate": 4.0084002595020245e-05, + "loss": 0.2091, "step": 89690 }, { - "epoch": 0.8, - "learning_rate": 1.0065309431582741e-05, - "loss": 0.1811, + "epoch": 0.2, + "learning_rate": 4.008288405181092e-05, + "loss": 0.2169, "step": 89700 }, { - "epoch": 0.8, - "learning_rate": 1.0060805332852897e-05, - "loss": 0.1882, + "epoch": 0.2, + "learning_rate": 4.00817655086016e-05, + "loss": 0.2118, "step": 89710 }, { - "epoch": 0.8, - "learning_rate": 1.0056301234123052e-05, - "loss": 0.1899, + "epoch": 0.2, + "learning_rate": 4.008064696539228e-05, + "loss": 0.2099, "step": 89720 }, { - "epoch": 0.8, - "learning_rate": 1.0051797135393208e-05, - "loss": 0.1861, + "epoch": 0.2, + "learning_rate": 4.007952842218295e-05, + "loss": 0.2114, "step": 89730 }, { - "epoch": 0.8, - "learning_rate": 1.0047293036663364e-05, - "loss": 0.1911, + "epoch": 0.2, + "learning_rate": 4.007840987897363e-05, + "loss": 0.2136, "step": 89740 }, { - "epoch": 0.8, - "learning_rate": 1.004278893793352e-05, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 4.00772913357643e-05, + "loss": 0.2091, "step": 89750 }, { - "epoch": 0.8, - "learning_rate": 1.0038284839203676e-05, - "loss": 0.1828, + "epoch": 0.2, + "learning_rate": 4.007617279255498e-05, + "loss": 0.212, "step": 89760 }, { - "epoch": 0.8, - "learning_rate": 1.0033780740473831e-05, - "loss": 0.1781, + "epoch": 0.2, + "learning_rate": 4.0075054249345655e-05, + "loss": 0.2143, "step": 89770 }, { - "epoch": 0.8, - "learning_rate": 1.0029276641743987e-05, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 4.0073935706136326e-05, + "loss": 0.2113, "step": 89780 }, { - "epoch": 0.8, - "learning_rate": 1.0024772543014143e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.0072817162927004e-05, + "loss": 0.2113, "step": 89790 }, { - "epoch": 0.8, - "learning_rate": 1.0020268444284299e-05, - "loss": 0.1815, + "epoch": 0.2, + "learning_rate": 4.007169861971768e-05, + "loss": 0.2134, "step": 89800 }, { - "epoch": 0.8, - "learning_rate": 1.0015764345554456e-05, - "loss": 0.187, + "epoch": 0.2, + "learning_rate": 4.007058007650836e-05, + "loss": 0.2112, "step": 89810 }, { - "epoch": 0.8, - "learning_rate": 1.001126024682461e-05, - "loss": 0.1839, + "epoch": 0.2, + "learning_rate": 4.006946153329904e-05, + "loss": 0.206, "step": 89820 }, { - "epoch": 0.8, - "learning_rate": 1.0006756148094766e-05, - "loss": 0.1851, + "epoch": 0.2, + "learning_rate": 4.006834299008971e-05, + "loss": 0.2147, "step": 89830 }, { - "epoch": 0.8, - "learning_rate": 1.0002252049364922e-05, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.006722444688039e-05, + "loss": 0.2112, "step": 89840 }, { - "epoch": 0.8, - "learning_rate": 9.997747950635078e-06, - "loss": 0.1877, + "epoch": 0.2, + "learning_rate": 4.006610590367106e-05, + "loss": 0.2139, "step": 89850 }, { - "epoch": 0.8, - "learning_rate": 9.993243851905235e-06, - "loss": 0.1888, + "epoch": 0.2, + "learning_rate": 4.0064987360461736e-05, + "loss": 0.2081, "step": 89860 }, { - "epoch": 0.8, - "learning_rate": 9.98873975317539e-06, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 4.0063868817252414e-05, + "loss": 0.2165, "step": 89870 }, { - "epoch": 0.8, - "learning_rate": 9.984235654445547e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.0062750274043085e-05, + "loss": 0.2118, "step": 89880 }, { - "epoch": 0.8, - "learning_rate": 9.979731555715701e-06, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 4.006163173083376e-05, + "loss": 0.216, "step": 89890 }, { - "epoch": 0.8, - "learning_rate": 9.975227456985857e-06, - "loss": 0.1889, + "epoch": 0.2, + "learning_rate": 4.0060513187624434e-05, + "loss": 0.2139, "step": 89900 }, { - "epoch": 0.8, - "learning_rate": 9.970723358256014e-06, - "loss": 0.1864, + "epoch": 0.2, + "learning_rate": 4.005939464441512e-05, + "loss": 0.2088, "step": 89910 }, { - "epoch": 0.8, - "learning_rate": 9.966219259526168e-06, - "loss": 0.1858, + "epoch": 0.2, + "learning_rate": 4.00582761012058e-05, + "loss": 0.2144, "step": 89920 }, { - "epoch": 0.8, - "learning_rate": 9.961715160796326e-06, - "loss": 0.1842, + "epoch": 0.2, + "learning_rate": 4.005715755799647e-05, + "loss": 0.2042, "step": 89930 }, { - "epoch": 0.8, - "learning_rate": 9.95721106206648e-06, - "loss": 0.1821, + "epoch": 0.2, + "learning_rate": 4.0056039014787146e-05, + "loss": 0.2162, "step": 89940 }, { - "epoch": 0.8, - "learning_rate": 9.952706963336638e-06, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 4.005492047157782e-05, + "loss": 0.2158, "step": 89950 }, { - "epoch": 0.8, - "learning_rate": 9.948202864606793e-06, - "loss": 0.1897, + "epoch": 0.2, + "learning_rate": 4.0053801928368495e-05, + "loss": 0.2075, "step": 89960 }, { - "epoch": 0.8, - "learning_rate": 9.943698765876947e-06, - "loss": 0.1877, + "epoch": 0.2, + "learning_rate": 4.005268338515917e-05, + "loss": 0.2173, "step": 89970 }, { - "epoch": 0.8, - "learning_rate": 9.939194667147105e-06, - "loss": 0.1915, + "epoch": 0.2, + "learning_rate": 4.0051564841949844e-05, + "loss": 0.211, "step": 89980 }, { - "epoch": 0.8, - "learning_rate": 9.934690568417259e-06, - "loss": 0.1851, + "epoch": 0.2, + "learning_rate": 4.005044629874052e-05, + "loss": 0.2066, "step": 89990 }, { - "epoch": 0.8, - "learning_rate": 9.930186469687417e-06, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 4.0049327755531193e-05, + "loss": 0.2115, "step": 90000 }, { - "epoch": 0.8, - "learning_rate": 9.925682370957572e-06, - "loss": 0.1856, + "epoch": 0.2, + "learning_rate": 4.004820921232187e-05, + "loss": 0.2106, "step": 90010 }, { - "epoch": 0.8, - "learning_rate": 9.921178272227728e-06, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 4.004709066911255e-05, + "loss": 0.2103, "step": 90020 }, { - "epoch": 0.8, - "learning_rate": 9.916674173497884e-06, - "loss": 0.1887, + "epoch": 0.2, + "learning_rate": 4.004597212590323e-05, + "loss": 0.2095, "step": 90030 }, { - "epoch": 0.8, - "learning_rate": 9.912620484641023e-06, - "loss": 0.1919, + "epoch": 0.2, + "learning_rate": 4.0044853582693905e-05, + "loss": 0.2094, "step": 90040 }, { - "epoch": 0.8, - "learning_rate": 9.90811638591118e-06, - "loss": 0.1873, + "epoch": 0.2, + "learning_rate": 4.0043735039484576e-05, + "loss": 0.21, "step": 90050 }, { - "epoch": 0.8, - "learning_rate": 9.903612287181336e-06, - "loss": 0.1842, + "epoch": 0.2, + "learning_rate": 4.0042616496275254e-05, + "loss": 0.2113, "step": 90060 }, { - "epoch": 0.8, - "learning_rate": 9.899108188451492e-06, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 4.0041497953065925e-05, + "loss": 0.2162, "step": 90070 }, { - "epoch": 0.8, - "learning_rate": 9.894604089721648e-06, - "loss": 0.1931, + "epoch": 0.2, + "learning_rate": 4.00403794098566e-05, + "loss": 0.2127, "step": 90080 }, { - "epoch": 0.8, - "learning_rate": 9.890099990991802e-06, - "loss": 0.1833, + "epoch": 0.2, + "learning_rate": 4.003926086664728e-05, + "loss": 0.2071, "step": 90090 }, { - "epoch": 0.8, - "learning_rate": 9.885595892261959e-06, - "loss": 0.186, + "epoch": 0.2, + "learning_rate": 4.003814232343795e-05, + "loss": 0.2062, "step": 90100 }, { - "epoch": 0.8, - "learning_rate": 9.881091793532115e-06, - "loss": 0.1874, + "epoch": 0.2, + "learning_rate": 4.003702378022863e-05, + "loss": 0.2138, "step": 90110 }, { - "epoch": 0.8, - "learning_rate": 9.87658769480227e-06, - "loss": 0.1831, + "epoch": 0.2, + "learning_rate": 4.003590523701931e-05, + "loss": 0.2103, "step": 90120 }, { - "epoch": 0.8, - "learning_rate": 9.872083596072427e-06, - "loss": 0.1824, + "epoch": 0.2, + "learning_rate": 4.0034786693809986e-05, + "loss": 0.2135, "step": 90130 }, { - "epoch": 0.8, - "learning_rate": 9.867579497342582e-06, - "loss": 0.1784, + "epoch": 0.2, + "learning_rate": 4.0033668150600664e-05, + "loss": 0.2088, "step": 90140 }, { - "epoch": 0.8, - "learning_rate": 9.863075398612738e-06, - "loss": 0.1826, + "epoch": 0.2, + "learning_rate": 4.0032549607391335e-05, + "loss": 0.2121, "step": 90150 }, { - "epoch": 0.8, - "learning_rate": 9.858571299882894e-06, - "loss": 0.1846, + "epoch": 0.2, + "learning_rate": 4.003143106418201e-05, + "loss": 0.2113, "step": 90160 }, { - "epoch": 0.81, - "learning_rate": 9.85406720115305e-06, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 4.0030312520972684e-05, + "loss": 0.208, "step": 90170 }, { - "epoch": 0.81, - "learning_rate": 9.849563102423205e-06, - "loss": 0.1772, + "epoch": 0.2, + "learning_rate": 4.002919397776336e-05, + "loss": 0.2094, "step": 90180 }, { - "epoch": 0.81, - "learning_rate": 9.845059003693361e-06, - "loss": 0.1857, + "epoch": 0.2, + "learning_rate": 4.002807543455404e-05, + "loss": 0.2093, "step": 90190 }, { - "epoch": 0.81, - "learning_rate": 9.840554904963517e-06, - "loss": 0.186, + "epoch": 0.2, + "learning_rate": 4.002695689134471e-05, + "loss": 0.214, "step": 90200 }, { - "epoch": 0.81, - "learning_rate": 9.836050806233673e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.002583834813539e-05, + "loss": 0.2135, "step": 90210 }, { - "epoch": 0.81, - "learning_rate": 9.831546707503829e-06, - "loss": 0.1858, + "epoch": 0.2, + "learning_rate": 4.002471980492607e-05, + "loss": 0.2097, "step": 90220 }, { - "epoch": 0.81, - "learning_rate": 9.827042608773984e-06, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 4.0023601261716745e-05, + "loss": 0.2109, "step": 90230 }, { - "epoch": 0.81, - "learning_rate": 9.82253851004414e-06, - "loss": 0.1874, + "epoch": 0.2, + "learning_rate": 4.002248271850742e-05, + "loss": 0.2067, "step": 90240 }, { - "epoch": 0.81, - "learning_rate": 9.818034411314296e-06, - "loss": 0.185, + "epoch": 0.2, + "learning_rate": 4.0021364175298094e-05, + "loss": 0.2089, "step": 90250 }, { - "epoch": 0.81, - "learning_rate": 9.813530312584452e-06, - "loss": 0.1894, + "epoch": 0.2, + "learning_rate": 4.002024563208877e-05, + "loss": 0.2111, "step": 90260 }, { - "epoch": 0.81, - "learning_rate": 9.809026213854608e-06, - "loss": 0.1919, + "epoch": 0.2, + "learning_rate": 4.001912708887944e-05, + "loss": 0.2106, "step": 90270 }, { - "epoch": 0.81, - "learning_rate": 9.804522115124765e-06, - "loss": 0.1901, + "epoch": 0.2, + "learning_rate": 4.001800854567012e-05, + "loss": 0.2132, "step": 90280 }, { - "epoch": 0.81, - "learning_rate": 9.80001801639492e-06, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.00168900024608e-05, + "loss": 0.2109, "step": 90290 }, { - "epoch": 0.81, - "learning_rate": 9.795513917665075e-06, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 4.001577145925147e-05, + "loss": 0.2169, "step": 90300 }, { - "epoch": 0.81, - "learning_rate": 9.791009818935233e-06, - "loss": 0.1879, + "epoch": 0.2, + "learning_rate": 4.001465291604215e-05, + "loss": 0.2043, "step": 90310 }, { - "epoch": 0.81, - "learning_rate": 9.786505720205387e-06, - "loss": 0.1819, + "epoch": 0.2, + "learning_rate": 4.001353437283282e-05, + "loss": 0.2093, "step": 90320 }, { - "epoch": 0.81, - "learning_rate": 9.782001621475544e-06, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 4.0012415829623504e-05, + "loss": 0.2085, "step": 90330 }, { - "epoch": 0.81, - "learning_rate": 9.777497522745698e-06, - "loss": 0.1942, + "epoch": 0.2, + "learning_rate": 4.001129728641418e-05, + "loss": 0.211, "step": 90340 }, { - "epoch": 0.81, - "learning_rate": 9.772993424015856e-06, - "loss": 0.1884, + "epoch": 0.2, + "learning_rate": 4.001017874320485e-05, + "loss": 0.2107, "step": 90350 }, { - "epoch": 0.81, - "learning_rate": 9.768489325286012e-06, - "loss": 0.1846, + "epoch": 0.2, + "learning_rate": 4.000906019999553e-05, + "loss": 0.2142, "step": 90360 }, { - "epoch": 0.81, - "learning_rate": 9.763985226556166e-06, - "loss": 0.1907, + "epoch": 0.2, + "learning_rate": 4.00079416567862e-05, + "loss": 0.2078, "step": 90370 }, { - "epoch": 0.81, - "learning_rate": 9.759481127826323e-06, - "loss": 0.1834, + "epoch": 0.2, + "learning_rate": 4.000682311357688e-05, + "loss": 0.2074, "step": 90380 }, { - "epoch": 0.81, - "learning_rate": 9.754977029096477e-06, - "loss": 0.1865, + "epoch": 0.2, + "learning_rate": 4.000570457036755e-05, + "loss": 0.2142, "step": 90390 }, { - "epoch": 0.81, - "learning_rate": 9.750472930366635e-06, - "loss": 0.1875, + "epoch": 0.2, + "learning_rate": 4.000458602715823e-05, + "loss": 0.2104, "step": 90400 }, { - "epoch": 0.81, - "learning_rate": 9.74596883163679e-06, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 4.000346748394891e-05, + "loss": 0.2103, "step": 90410 }, { - "epoch": 0.81, - "learning_rate": 9.741464732906946e-06, - "loss": 0.1905, + "epoch": 0.2, + "learning_rate": 4.000234894073958e-05, + "loss": 0.2131, "step": 90420 }, { - "epoch": 0.81, - "learning_rate": 9.736960634177102e-06, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 4.0001230397530256e-05, + "loss": 0.2056, "step": 90430 }, { - "epoch": 0.81, - "learning_rate": 9.732456535447256e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 4.0000111854320934e-05, + "loss": 0.2108, "step": 90440 }, { - "epoch": 0.81, - "learning_rate": 9.727952436717414e-06, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 3.999899331111161e-05, + "loss": 0.2083, "step": 90450 }, { - "epoch": 0.81, - "learning_rate": 9.72344833798757e-06, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 3.999787476790229e-05, + "loss": 0.2125, "step": 90460 }, { - "epoch": 0.81, - "learning_rate": 9.718944239257725e-06, - "loss": 0.1916, + "epoch": 0.2, + "learning_rate": 3.999675622469296e-05, + "loss": 0.2107, "step": 90470 }, { - "epoch": 0.81, - "learning_rate": 9.714440140527881e-06, - "loss": 0.1823, + "epoch": 0.2, + "learning_rate": 3.999563768148364e-05, + "loss": 0.2083, "step": 90480 }, { - "epoch": 0.81, - "learning_rate": 9.709936041798037e-06, - "loss": 0.1833, + "epoch": 0.2, + "learning_rate": 3.999451913827431e-05, + "loss": 0.2094, "step": 90490 }, { - "epoch": 0.81, - "learning_rate": 9.705431943068193e-06, - "loss": 0.1852, + "epoch": 0.2, + "learning_rate": 3.999340059506499e-05, + "loss": 0.209, "step": 90500 }, { - "epoch": 0.81, - "learning_rate": 9.700927844338349e-06, - "loss": 0.1808, + "epoch": 0.2, + "learning_rate": 3.9992282051855666e-05, + "loss": 0.2111, "step": 90510 }, { - "epoch": 0.81, - "learning_rate": 9.696423745608504e-06, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 3.999116350864634e-05, + "loss": 0.209, "step": 90520 }, { - "epoch": 0.81, - "learning_rate": 9.69191964687866e-06, - "loss": 0.1819, + "epoch": 0.2, + "learning_rate": 3.9990044965437015e-05, + "loss": 0.215, "step": 90530 }, { - "epoch": 0.81, - "learning_rate": 9.687415548148816e-06, - "loss": 0.1838, + "epoch": 0.2, + "learning_rate": 3.998892642222769e-05, + "loss": 0.2068, "step": 90540 }, { - "epoch": 0.81, - "learning_rate": 9.682911449418972e-06, - "loss": 0.1893, + "epoch": 0.2, + "learning_rate": 3.998780787901837e-05, + "loss": 0.2134, "step": 90550 }, { - "epoch": 0.81, - "learning_rate": 9.678407350689128e-06, - "loss": 0.183, + "epoch": 0.2, + "learning_rate": 3.998668933580905e-05, + "loss": 0.2081, "step": 90560 }, { - "epoch": 0.81, - "learning_rate": 9.673903251959283e-06, - "loss": 0.1858, + "epoch": 0.2, + "learning_rate": 3.998557079259972e-05, + "loss": 0.2115, "step": 90570 }, { - "epoch": 0.81, - "learning_rate": 9.669399153229439e-06, - "loss": 0.1843, + "epoch": 0.2, + "learning_rate": 3.99844522493904e-05, + "loss": 0.2069, "step": 90580 }, { - "epoch": 0.81, - "learning_rate": 9.664895054499595e-06, - "loss": 0.1898, + "epoch": 0.2, + "learning_rate": 3.998333370618107e-05, + "loss": 0.2076, "step": 90590 }, { - "epoch": 0.81, - "learning_rate": 9.66039095576975e-06, - "loss": 0.1806, + "epoch": 0.2, + "learning_rate": 3.998221516297175e-05, + "loss": 0.2074, "step": 90600 }, { - "epoch": 0.81, - "learning_rate": 9.655886857039907e-06, - "loss": 0.1906, + "epoch": 0.2, + "learning_rate": 3.9981096619762425e-05, + "loss": 0.2129, "step": 90610 }, { - "epoch": 0.81, - "learning_rate": 9.651382758310062e-06, - "loss": 0.1854, + "epoch": 0.2, + "learning_rate": 3.9979978076553096e-05, + "loss": 0.2038, "step": 90620 }, { - "epoch": 0.81, - "learning_rate": 9.64687865958022e-06, - "loss": 0.1795, + "epoch": 0.2, + "learning_rate": 3.9978859533343774e-05, + "loss": 0.2069, "step": 90630 }, { - "epoch": 0.81, - "learning_rate": 9.642374560850374e-06, - "loss": 0.1853, + "epoch": 0.2, + "learning_rate": 3.997774099013445e-05, + "loss": 0.2149, "step": 90640 }, { - "epoch": 0.81, - "learning_rate": 9.63787046212053e-06, - "loss": 0.1858, + "epoch": 0.2, + "learning_rate": 3.997662244692513e-05, + "loss": 0.2068, "step": 90650 }, { - "epoch": 0.81, - "learning_rate": 9.633366363390685e-06, - "loss": 0.1865, + "epoch": 0.2, + "learning_rate": 3.997550390371581e-05, + "loss": 0.2084, "step": 90660 }, { - "epoch": 0.81, - "learning_rate": 9.628862264660841e-06, - "loss": 0.18, + "epoch": 0.2, + "learning_rate": 3.997438536050648e-05, + "loss": 0.2093, "step": 90670 }, { - "epoch": 0.81, - "learning_rate": 9.624358165930999e-06, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 3.997326681729716e-05, + "loss": 0.2063, "step": 90680 }, { - "epoch": 0.81, - "learning_rate": 9.619854067201153e-06, - "loss": 0.1917, + "epoch": 0.2, + "learning_rate": 3.997214827408783e-05, + "loss": 0.2082, "step": 90690 }, { - "epoch": 0.81, - "learning_rate": 9.61534996847131e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 3.9971029730878506e-05, + "loss": 0.2045, "step": 90700 }, { - "epoch": 0.81, - "learning_rate": 9.610845869741464e-06, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 3.996991118766918e-05, + "loss": 0.2133, "step": 90710 }, { - "epoch": 0.81, - "learning_rate": 9.60634177101162e-06, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 3.9968792644459855e-05, + "loss": 0.2072, "step": 90720 }, { - "epoch": 0.81, - "learning_rate": 9.601837672281778e-06, - "loss": 0.1858, + "epoch": 0.2, + "learning_rate": 3.996767410125053e-05, + "loss": 0.2079, "step": 90730 }, { - "epoch": 0.81, - "learning_rate": 9.597333573551932e-06, - "loss": 0.1825, + "epoch": 0.2, + "learning_rate": 3.996655555804121e-05, + "loss": 0.2123, "step": 90740 }, { - "epoch": 0.81, - "learning_rate": 9.59282947482209e-06, - "loss": 0.1853, + "epoch": 0.2, + "learning_rate": 3.996543701483189e-05, + "loss": 0.2112, "step": 90750 }, { - "epoch": 0.81, - "learning_rate": 9.588325376092243e-06, - "loss": 0.1864, + "epoch": 0.2, + "learning_rate": 3.996431847162256e-05, + "loss": 0.2197, "step": 90760 }, { - "epoch": 0.81, - "learning_rate": 9.583821277362401e-06, - "loss": 0.1911, + "epoch": 0.2, + "learning_rate": 3.996319992841324e-05, + "loss": 0.2113, "step": 90770 }, { - "epoch": 0.81, - "learning_rate": 9.579317178632557e-06, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 3.9962081385203916e-05, + "loss": 0.2057, "step": 90780 }, { - "epoch": 0.81, - "learning_rate": 9.574813079902711e-06, - "loss": 0.1797, + "epoch": 0.2, + "learning_rate": 3.996096284199459e-05, + "loss": 0.208, "step": 90790 }, { - "epoch": 0.81, - "learning_rate": 9.570308981172868e-06, - "loss": 0.1891, + "epoch": 0.2, + "learning_rate": 3.9959844298785265e-05, + "loss": 0.2085, "step": 90800 }, { - "epoch": 0.81, - "learning_rate": 9.565804882443022e-06, - "loss": 0.1823, + "epoch": 0.2, + "learning_rate": 3.9958725755575936e-05, + "loss": 0.2163, "step": 90810 }, { - "epoch": 0.81, - "learning_rate": 9.56130078371318e-06, - "loss": 0.1834, + "epoch": 0.2, + "learning_rate": 3.9957607212366614e-05, + "loss": 0.2083, "step": 90820 }, { - "epoch": 0.81, - "learning_rate": 9.556796684983336e-06, - "loss": 0.1833, + "epoch": 0.2, + "learning_rate": 3.995648866915729e-05, + "loss": 0.2089, "step": 90830 }, { - "epoch": 0.81, - "learning_rate": 9.552292586253492e-06, - "loss": 0.1817, + "epoch": 0.2, + "learning_rate": 3.995537012594796e-05, + "loss": 0.2102, "step": 90840 }, { - "epoch": 0.81, - "learning_rate": 9.547788487523647e-06, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 3.995425158273864e-05, + "loss": 0.2122, "step": 90850 }, { - "epoch": 0.81, - "learning_rate": 9.543284388793801e-06, - "loss": 0.1898, + "epoch": 0.2, + "learning_rate": 3.995313303952932e-05, + "loss": 0.2086, "step": 90860 }, { - "epoch": 0.81, - "learning_rate": 9.538780290063959e-06, - "loss": 0.1814, + "epoch": 0.2, + "learning_rate": 3.995201449632e-05, + "loss": 0.2127, "step": 90870 }, { - "epoch": 0.81, - "learning_rate": 9.534276191334115e-06, - "loss": 0.1795, + "epoch": 0.2, + "learning_rate": 3.9950895953110675e-05, + "loss": 0.2126, "step": 90880 }, { - "epoch": 0.81, - "learning_rate": 9.52977209260427e-06, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 3.9949777409901346e-05, + "loss": 0.2062, "step": 90890 }, { - "epoch": 0.81, - "learning_rate": 9.525267993874426e-06, - "loss": 0.1803, + "epoch": 0.2, + "learning_rate": 3.9948658866692024e-05, + "loss": 0.2081, "step": 90900 }, { - "epoch": 0.81, - "learning_rate": 9.520763895144582e-06, - "loss": 0.182, + "epoch": 0.2, + "learning_rate": 3.9947540323482695e-05, + "loss": 0.2113, "step": 90910 }, { - "epoch": 0.81, - "learning_rate": 9.516259796414738e-06, - "loss": 0.1844, + "epoch": 0.2, + "learning_rate": 3.994642178027337e-05, + "loss": 0.2094, "step": 90920 }, { - "epoch": 0.81, - "learning_rate": 9.511755697684894e-06, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 3.994530323706405e-05, + "loss": 0.2101, "step": 90930 }, { - "epoch": 0.81, - "learning_rate": 9.50725159895505e-06, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 3.994418469385472e-05, + "loss": 0.2058, "step": 90940 }, { - "epoch": 0.81, - "learning_rate": 9.502747500225205e-06, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 3.99430661506454e-05, + "loss": 0.2082, "step": 90950 }, { - "epoch": 0.81, - "learning_rate": 9.498243401495361e-06, - "loss": 0.1848, + "epoch": 0.2, + "learning_rate": 3.994194760743608e-05, + "loss": 0.2078, "step": 90960 }, { - "epoch": 0.81, - "learning_rate": 9.493739302765517e-06, - "loss": 0.1917, + "epoch": 0.2, + "learning_rate": 3.9940829064226756e-05, + "loss": 0.2075, "step": 90970 }, { - "epoch": 0.81, - "learning_rate": 9.489235204035673e-06, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 3.993971052101743e-05, + "loss": 0.2083, "step": 90980 }, { - "epoch": 0.81, - "learning_rate": 9.484731105305829e-06, - "loss": 0.1874, + "epoch": 0.2, + "learning_rate": 3.9938591977808105e-05, + "loss": 0.2112, "step": 90990 }, { - "epoch": 0.81, - "learning_rate": 9.480227006575984e-06, - "loss": 0.1881, + "epoch": 0.2, + "learning_rate": 3.993747343459878e-05, + "loss": 0.2132, "step": 91000 }, { - "epoch": 0.81, - "learning_rate": 9.47572290784614e-06, - "loss": 0.1849, + "epoch": 0.2, + "learning_rate": 3.9936354891389454e-05, + "loss": 0.214, "step": 91010 }, { - "epoch": 0.81, - "learning_rate": 9.471218809116296e-06, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 3.993523634818013e-05, + "loss": 0.2065, "step": 91020 }, { - "epoch": 0.81, - "learning_rate": 9.466714710386453e-06, - "loss": 0.1846, + "epoch": 0.2, + "learning_rate": 3.99341178049708e-05, + "loss": 0.2161, "step": 91030 }, { - "epoch": 0.81, - "learning_rate": 9.462210611656608e-06, - "loss": 0.1828, + "epoch": 0.2, + "learning_rate": 3.993299926176148e-05, + "loss": 0.2107, "step": 91040 }, { - "epoch": 0.81, - "learning_rate": 9.457706512926765e-06, - "loss": 0.189, + "epoch": 0.2, + "learning_rate": 3.993188071855216e-05, + "loss": 0.204, "step": 91050 }, { - "epoch": 0.81, - "learning_rate": 9.453202414196919e-06, - "loss": 0.1787, + "epoch": 0.2, + "learning_rate": 3.993076217534284e-05, + "loss": 0.2043, "step": 91060 }, { - "epoch": 0.81, - "learning_rate": 9.448698315467075e-06, - "loss": 0.182, + "epoch": 0.2, + "learning_rate": 3.9929643632133515e-05, + "loss": 0.2047, "step": 91070 }, { - "epoch": 0.81, - "learning_rate": 9.444194216737232e-06, - "loss": 0.1871, + "epoch": 0.2, + "learning_rate": 3.9928525088924186e-05, + "loss": 0.2085, "step": 91080 }, { - "epoch": 0.81, - "learning_rate": 9.439690118007387e-06, - "loss": 0.1862, + "epoch": 0.2, + "learning_rate": 3.9927406545714864e-05, + "loss": 0.2071, "step": 91090 }, { - "epoch": 0.81, - "learning_rate": 9.435186019277544e-06, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 3.992628800250554e-05, + "loss": 0.2097, "step": 91100 }, { - "epoch": 0.81, - "learning_rate": 9.430681920547698e-06, - "loss": 0.1818, + "epoch": 0.2, + "learning_rate": 3.992516945929621e-05, + "loss": 0.2099, "step": 91110 }, { - "epoch": 0.81, - "learning_rate": 9.426177821817856e-06, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 3.992405091608689e-05, + "loss": 0.21, "step": 91120 }, { - "epoch": 0.81, - "learning_rate": 9.421673723088011e-06, - "loss": 0.1899, + "epoch": 0.2, + "learning_rate": 3.992293237287756e-05, + "loss": 0.2062, "step": 91130 }, { - "epoch": 0.81, - "learning_rate": 9.417169624358165e-06, - "loss": 0.1829, + "epoch": 0.2, + "learning_rate": 3.992181382966824e-05, + "loss": 0.2093, "step": 91140 }, { - "epoch": 0.81, - "learning_rate": 9.412665525628323e-06, - "loss": 0.1895, + "epoch": 0.2, + "learning_rate": 3.992069528645892e-05, + "loss": 0.2064, "step": 91150 }, { - "epoch": 0.81, - "learning_rate": 9.408161426898477e-06, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 3.9919576743249596e-05, + "loss": 0.2096, "step": 91160 }, { - "epoch": 0.81, - "learning_rate": 9.403657328168635e-06, - "loss": 0.1876, + "epoch": 0.2, + "learning_rate": 3.9918458200040274e-05, + "loss": 0.2142, "step": 91170 }, { - "epoch": 0.81, - "learning_rate": 9.39915322943879e-06, - "loss": 0.1826, + "epoch": 0.2, + "learning_rate": 3.9917339656830945e-05, + "loss": 0.2115, "step": 91180 }, { - "epoch": 0.81, - "learning_rate": 9.394649130708946e-06, - "loss": 0.184, + "epoch": 0.2, + "learning_rate": 3.991622111362162e-05, + "loss": 0.2103, "step": 91190 }, { - "epoch": 0.81, - "learning_rate": 9.390145031979102e-06, - "loss": 0.1873, + "epoch": 0.2, + "learning_rate": 3.99151025704123e-05, + "loss": 0.2108, "step": 91200 }, { - "epoch": 0.81, - "learning_rate": 9.385640933249256e-06, - "loss": 0.1847, + "epoch": 0.2, + "learning_rate": 3.991398402720297e-05, + "loss": 0.2108, "step": 91210 }, { - "epoch": 0.81, - "learning_rate": 9.381136834519414e-06, - "loss": 0.1918, + "epoch": 0.2, + "learning_rate": 3.991286548399365e-05, + "loss": 0.2107, "step": 91220 }, { - "epoch": 0.81, - "learning_rate": 9.37663273578957e-06, - "loss": 0.1906, + "epoch": 0.2, + "learning_rate": 3.991174694078432e-05, + "loss": 0.2087, "step": 91230 }, { - "epoch": 0.81, - "learning_rate": 9.372128637059725e-06, - "loss": 0.1884, + "epoch": 0.2, + "learning_rate": 3.9910628397575e-05, + "loss": 0.2063, "step": 91240 }, { - "epoch": 0.81, - "learning_rate": 9.367624538329881e-06, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 3.990950985436568e-05, + "loss": 0.2094, "step": 91250 }, { - "epoch": 0.81, - "learning_rate": 9.363120439600037e-06, - "loss": 0.1892, + "epoch": 0.2, + "learning_rate": 3.990839131115635e-05, + "loss": 0.2052, "step": 91260 }, { - "epoch": 0.81, - "learning_rate": 9.358616340870193e-06, - "loss": 0.1813, + "epoch": 0.2, + "learning_rate": 3.9907272767947026e-05, + "loss": 0.2053, "step": 91270 }, { - "epoch": 0.81, - "learning_rate": 9.354112242140348e-06, - "loss": 0.182, + "epoch": 0.2, + "learning_rate": 3.9906154224737704e-05, + "loss": 0.2116, "step": 91280 }, { - "epoch": 0.82, - "learning_rate": 9.349608143410504e-06, - "loss": 0.1852, + "epoch": 0.2, + "learning_rate": 3.990503568152838e-05, + "loss": 0.21, "step": 91290 }, { - "epoch": 0.82, - "learning_rate": 9.34510404468066e-06, - "loss": 0.188, + "epoch": 0.2, + "learning_rate": 3.990391713831905e-05, + "loss": 0.2052, "step": 91300 }, { - "epoch": 0.82, - "learning_rate": 9.340599945950816e-06, - "loss": 0.1895, + "epoch": 0.2, + "learning_rate": 3.990279859510973e-05, + "loss": 0.2093, "step": 91310 }, { - "epoch": 0.82, - "learning_rate": 9.336095847220972e-06, - "loss": 0.1943, + "epoch": 0.2, + "learning_rate": 3.990168005190041e-05, + "loss": 0.2102, "step": 91320 }, { - "epoch": 0.82, - "learning_rate": 9.331591748491127e-06, - "loss": 0.1813, + "epoch": 0.2, + "learning_rate": 3.990056150869108e-05, + "loss": 0.2079, "step": 91330 }, { - "epoch": 0.82, - "learning_rate": 9.327087649761283e-06, - "loss": 0.1852, + "epoch": 0.2, + "learning_rate": 3.989944296548176e-05, + "loss": 0.2095, "step": 91340 }, { - "epoch": 0.82, - "learning_rate": 9.322583551031439e-06, - "loss": 0.1876, + "epoch": 0.2, + "learning_rate": 3.989832442227243e-05, + "loss": 0.2122, "step": 91350 }, { - "epoch": 0.82, - "learning_rate": 9.318079452301595e-06, - "loss": 0.1783, + "epoch": 0.2, + "learning_rate": 3.989720587906311e-05, + "loss": 0.2135, "step": 91360 }, { - "epoch": 0.82, - "learning_rate": 9.31357535357175e-06, - "loss": 0.1795, + "epoch": 0.2, + "learning_rate": 3.9896087335853785e-05, + "loss": 0.2103, "step": 91370 }, { - "epoch": 0.82, - "learning_rate": 9.309071254841906e-06, - "loss": 0.186, + "epoch": 0.2, + "learning_rate": 3.989496879264446e-05, + "loss": 0.2135, "step": 91380 }, { - "epoch": 0.82, - "learning_rate": 9.304567156112062e-06, - "loss": 0.1832, + "epoch": 0.2, + "learning_rate": 3.989385024943514e-05, + "loss": 0.2137, "step": 91390 }, { - "epoch": 0.82, - "learning_rate": 9.30006305738222e-06, - "loss": 0.1815, + "epoch": 0.2, + "learning_rate": 3.989273170622581e-05, + "loss": 0.2102, "step": 91400 }, { - "epoch": 0.82, - "learning_rate": 9.295558958652374e-06, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 3.989161316301649e-05, + "loss": 0.2086, "step": 91410 }, { - "epoch": 0.82, - "learning_rate": 9.29105485992253e-06, - "loss": 0.182, + "epoch": 0.2, + "learning_rate": 3.989049461980717e-05, + "loss": 0.2107, "step": 91420 }, { - "epoch": 0.82, - "learning_rate": 9.286550761192685e-06, - "loss": 0.1834, + "epoch": 0.2, + "learning_rate": 3.988937607659784e-05, + "loss": 0.2095, "step": 91430 }, { - "epoch": 0.82, - "learning_rate": 9.282046662462841e-06, - "loss": 0.1786, + "epoch": 0.2, + "learning_rate": 3.988825753338852e-05, + "loss": 0.2102, "step": 91440 }, { - "epoch": 0.82, - "learning_rate": 9.277542563732999e-06, - "loss": 0.1826, + "epoch": 0.2, + "learning_rate": 3.988713899017919e-05, + "loss": 0.2106, "step": 91450 }, { - "epoch": 0.82, - "learning_rate": 9.273038465003153e-06, - "loss": 0.1843, + "epoch": 0.2, + "learning_rate": 3.9886020446969866e-05, + "loss": 0.2058, "step": 91460 }, { - "epoch": 0.82, - "learning_rate": 9.26853436627331e-06, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 3.9884901903760544e-05, + "loss": 0.2124, "step": 91470 }, { - "epoch": 0.82, - "learning_rate": 9.264030267543464e-06, - "loss": 0.1786, + "epoch": 0.2, + "learning_rate": 3.988378336055122e-05, + "loss": 0.2139, "step": 91480 }, { - "epoch": 0.82, - "learning_rate": 9.25952616881362e-06, - "loss": 0.1842, + "epoch": 0.2, + "learning_rate": 3.98826648173419e-05, + "loss": 0.2173, "step": 91490 }, { - "epoch": 0.82, - "learning_rate": 9.255022070083778e-06, - "loss": 0.1866, + "epoch": 0.2, + "learning_rate": 3.988154627413257e-05, + "loss": 0.2106, "step": 91500 }, { - "epoch": 0.82, - "learning_rate": 9.250517971353932e-06, - "loss": 0.1868, + "epoch": 0.2, + "learning_rate": 3.988042773092325e-05, + "loss": 0.2055, "step": 91510 }, { - "epoch": 0.82, - "learning_rate": 9.24601387262409e-06, - "loss": 0.1843, + "epoch": 0.2, + "learning_rate": 3.987942104203485e-05, + "loss": 0.2039, "step": 91520 }, { - "epoch": 0.82, - "learning_rate": 9.241509773894243e-06, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 3.987830249882553e-05, + "loss": 0.2029, "step": 91530 }, { - "epoch": 0.82, - "learning_rate": 9.237005675164399e-06, - "loss": 0.1813, + "epoch": 0.2, + "learning_rate": 3.987718395561621e-05, + "loss": 0.217, "step": 91540 }, { - "epoch": 0.82, - "learning_rate": 9.232501576434557e-06, - "loss": 0.1812, + "epoch": 0.2, + "learning_rate": 3.9876065412406885e-05, + "loss": 0.209, "step": 91550 }, { - "epoch": 0.82, - "learning_rate": 9.22799747770471e-06, - "loss": 0.1835, + "epoch": 0.2, + "learning_rate": 3.987494686919756e-05, + "loss": 0.2155, "step": 91560 }, { - "epoch": 0.82, - "learning_rate": 9.223493378974868e-06, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 3.9873828325988234e-05, + "loss": 0.205, "step": 91570 }, { - "epoch": 0.82, - "learning_rate": 9.218989280245022e-06, - "loss": 0.175, + "epoch": 0.2, + "learning_rate": 3.987270978277891e-05, + "loss": 0.2154, "step": 91580 }, { - "epoch": 0.82, - "learning_rate": 9.21448518151518e-06, - "loss": 0.181, + "epoch": 0.2, + "learning_rate": 3.987159123956959e-05, + "loss": 0.2083, "step": 91590 }, { - "epoch": 0.82, - "learning_rate": 9.209981082785336e-06, - "loss": 0.1744, + "epoch": 0.2, + "learning_rate": 3.987047269636026e-05, + "loss": 0.2094, "step": 91600 }, { - "epoch": 0.82, - "learning_rate": 9.20547698405549e-06, - "loss": 0.18, + "epoch": 0.2, + "learning_rate": 3.986935415315094e-05, + "loss": 0.2104, "step": 91610 }, { - "epoch": 0.82, - "learning_rate": 9.200972885325647e-06, - "loss": 0.18, + "epoch": 0.2, + "learning_rate": 3.986823560994161e-05, + "loss": 0.2089, "step": 91620 }, { - "epoch": 0.82, - "learning_rate": 9.196468786595801e-06, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 3.986711706673229e-05, + "loss": 0.2115, "step": 91630 }, { - "epoch": 0.82, - "learning_rate": 9.191964687865959e-06, - "loss": 0.1845, + "epoch": 0.2, + "learning_rate": 3.9865998523522966e-05, + "loss": 0.2107, "step": 91640 }, { - "epoch": 0.82, - "learning_rate": 9.187460589136115e-06, - "loss": 0.1883, + "epoch": 0.2, + "learning_rate": 3.9864879980313644e-05, + "loss": 0.2107, "step": 91650 }, { - "epoch": 0.82, - "learning_rate": 9.18295649040627e-06, - "loss": 0.1886, + "epoch": 0.2, + "learning_rate": 3.986376143710432e-05, + "loss": 0.2073, "step": 91660 }, { - "epoch": 0.82, - "learning_rate": 9.178452391676426e-06, - "loss": 0.1855, + "epoch": 0.2, + "learning_rate": 3.986264289389499e-05, + "loss": 0.2128, "step": 91670 }, { - "epoch": 0.82, - "learning_rate": 9.173948292946582e-06, - "loss": 0.1876, + "epoch": 0.2, + "learning_rate": 3.986152435068567e-05, + "loss": 0.2025, "step": 91680 }, { - "epoch": 0.82, - "learning_rate": 9.169444194216738e-06, - "loss": 0.1829, + "epoch": 0.2, + "learning_rate": 3.986040580747634e-05, + "loss": 0.2121, "step": 91690 }, { - "epoch": 0.82, - "learning_rate": 9.164940095486894e-06, - "loss": 0.1818, + "epoch": 0.2, + "learning_rate": 3.985928726426702e-05, + "loss": 0.2118, "step": 91700 }, { - "epoch": 0.82, - "learning_rate": 9.16043599675705e-06, - "loss": 0.1838, + "epoch": 0.2, + "learning_rate": 3.98581687210577e-05, + "loss": 0.2079, "step": 91710 }, { - "epoch": 0.82, - "learning_rate": 9.155931898027205e-06, - "loss": 0.1836, + "epoch": 0.2, + "learning_rate": 3.985705017784837e-05, + "loss": 0.2105, "step": 91720 }, { - "epoch": 0.82, - "learning_rate": 9.151427799297361e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 3.9855931634639047e-05, + "loss": 0.2151, "step": 91730 }, { - "epoch": 0.82, - "learning_rate": 9.146923700567517e-06, - "loss": 0.191, + "epoch": 0.2, + "learning_rate": 3.9854813091429725e-05, + "loss": 0.2085, "step": 91740 }, { - "epoch": 0.82, - "learning_rate": 9.142419601837673e-06, - "loss": 0.18, + "epoch": 0.2, + "learning_rate": 3.98536945482204e-05, + "loss": 0.2079, "step": 91750 }, { - "epoch": 0.82, - "learning_rate": 9.137915503107828e-06, - "loss": 0.1856, + "epoch": 0.2, + "learning_rate": 3.985257600501108e-05, + "loss": 0.2071, "step": 91760 }, { - "epoch": 0.82, - "learning_rate": 9.133411404377984e-06, - "loss": 0.1872, + "epoch": 0.2, + "learning_rate": 3.985145746180175e-05, + "loss": 0.2101, "step": 91770 }, { - "epoch": 0.82, - "learning_rate": 9.12890730564814e-06, - "loss": 0.1804, + "epoch": 0.2, + "learning_rate": 3.985033891859243e-05, + "loss": 0.2064, "step": 91780 }, { - "epoch": 0.82, - "learning_rate": 9.124403206918296e-06, - "loss": 0.1842, + "epoch": 0.2, + "learning_rate": 3.98492203753831e-05, + "loss": 0.2057, "step": 91790 }, { - "epoch": 0.82, - "learning_rate": 9.119899108188453e-06, - "loss": 0.1834, + "epoch": 0.2, + "learning_rate": 3.984810183217378e-05, + "loss": 0.212, "step": 91800 }, { - "epoch": 0.82, - "learning_rate": 9.115395009458607e-06, - "loss": 0.1859, + "epoch": 0.2, + "learning_rate": 3.9846983288964456e-05, + "loss": 0.2128, "step": 91810 }, { - "epoch": 0.82, - "learning_rate": 9.110890910728763e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 3.984586474575513e-05, + "loss": 0.2077, "step": 91820 }, { - "epoch": 0.82, - "learning_rate": 9.106386811998919e-06, - "loss": 0.1863, + "epoch": 0.2, + "learning_rate": 3.9844746202545806e-05, + "loss": 0.2081, "step": 91830 }, { - "epoch": 0.82, - "learning_rate": 9.101882713269075e-06, - "loss": 0.1885, + "epoch": 0.2, + "learning_rate": 3.984362765933648e-05, + "loss": 0.2082, "step": 91840 }, { - "epoch": 0.82, - "learning_rate": 9.097378614539232e-06, - "loss": 0.1877, + "epoch": 0.21, + "learning_rate": 3.9842509116127155e-05, + "loss": 0.2077, "step": 91850 }, { - "epoch": 0.82, - "learning_rate": 9.092874515809386e-06, - "loss": 0.1867, + "epoch": 0.21, + "learning_rate": 3.984139057291784e-05, + "loss": 0.214, "step": 91860 }, { - "epoch": 0.82, - "learning_rate": 9.088370417079544e-06, - "loss": 0.1889, + "epoch": 0.21, + "learning_rate": 3.984027202970851e-05, + "loss": 0.2113, "step": 91870 }, { - "epoch": 0.82, - "learning_rate": 9.083866318349698e-06, - "loss": 0.1877, + "epoch": 0.21, + "learning_rate": 3.983915348649919e-05, + "loss": 0.2088, "step": 91880 }, { - "epoch": 0.82, - "learning_rate": 9.079362219619854e-06, - "loss": 0.1822, + "epoch": 0.21, + "learning_rate": 3.983803494328986e-05, + "loss": 0.2051, "step": 91890 }, { - "epoch": 0.82, - "learning_rate": 9.074858120890011e-06, - "loss": 0.1842, + "epoch": 0.21, + "learning_rate": 3.983691640008054e-05, + "loss": 0.2111, "step": 91900 }, { - "epoch": 0.82, - "learning_rate": 9.070354022160165e-06, - "loss": 0.1875, + "epoch": 0.21, + "learning_rate": 3.9835797856871215e-05, + "loss": 0.2116, "step": 91910 }, { - "epoch": 0.82, - "learning_rate": 9.065849923430323e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.9834679313661887e-05, + "loss": 0.2109, "step": 91920 }, { - "epoch": 0.82, - "learning_rate": 9.061345824700477e-06, - "loss": 0.1886, + "epoch": 0.21, + "learning_rate": 3.9833560770452564e-05, + "loss": 0.2077, "step": 91930 }, { - "epoch": 0.82, - "learning_rate": 9.056841725970634e-06, - "loss": 0.1863, + "epoch": 0.21, + "learning_rate": 3.9832442227243236e-05, + "loss": 0.2104, "step": 91940 }, { - "epoch": 0.82, - "learning_rate": 9.05233762724079e-06, - "loss": 0.1826, + "epoch": 0.21, + "learning_rate": 3.9831323684033914e-05, + "loss": 0.2053, "step": 91950 }, { - "epoch": 0.82, - "learning_rate": 9.047833528510944e-06, - "loss": 0.1876, + "epoch": 0.21, + "learning_rate": 3.983020514082459e-05, + "loss": 0.2118, "step": 91960 }, { - "epoch": 0.82, - "learning_rate": 9.043329429781102e-06, - "loss": 0.1859, + "epoch": 0.21, + "learning_rate": 3.982908659761527e-05, + "loss": 0.2107, "step": 91970 }, { - "epoch": 0.82, - "learning_rate": 9.038825331051256e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.982796805440595e-05, + "loss": 0.2069, "step": 91980 }, { - "epoch": 0.82, - "learning_rate": 9.034321232321413e-06, - "loss": 0.1816, + "epoch": 0.21, + "learning_rate": 3.982684951119662e-05, + "loss": 0.2046, "step": 91990 }, { - "epoch": 0.82, - "learning_rate": 9.02981713359157e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.9825730967987296e-05, + "loss": 0.2104, "step": 92000 }, { - "epoch": 0.82, - "learning_rate": 9.025313034861725e-06, - "loss": 0.1855, + "epoch": 0.21, + "learning_rate": 3.982461242477797e-05, + "loss": 0.2048, "step": 92010 }, { - "epoch": 0.82, - "learning_rate": 9.02080893613188e-06, - "loss": 0.1838, + "epoch": 0.21, + "learning_rate": 3.9823493881568646e-05, + "loss": 0.2125, "step": 92020 }, { - "epoch": 0.82, - "learning_rate": 9.016304837402035e-06, - "loss": 0.1864, + "epoch": 0.21, + "learning_rate": 3.9822375338359323e-05, + "loss": 0.2057, "step": 92030 }, { - "epoch": 0.82, - "learning_rate": 9.011800738672192e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.9821256795149995e-05, + "loss": 0.2081, "step": 92040 }, { - "epoch": 0.82, - "learning_rate": 9.007747049815333e-06, - "loss": 0.1868, + "epoch": 0.21, + "learning_rate": 3.982013825194067e-05, + "loss": 0.2102, "step": 92050 }, { - "epoch": 0.82, - "learning_rate": 9.003242951085489e-06, - "loss": 0.1881, + "epoch": 0.21, + "learning_rate": 3.981901970873135e-05, + "loss": 0.2095, "step": 92060 }, { - "epoch": 0.82, - "learning_rate": 8.998738852355644e-06, - "loss": 0.1794, + "epoch": 0.21, + "learning_rate": 3.981790116552203e-05, + "loss": 0.2094, "step": 92070 }, { - "epoch": 0.82, - "learning_rate": 8.994234753625798e-06, - "loss": 0.1893, + "epoch": 0.21, + "learning_rate": 3.9816782622312706e-05, + "loss": 0.2082, "step": 92080 }, { - "epoch": 0.82, - "learning_rate": 8.989730654895956e-06, - "loss": 0.1801, + "epoch": 0.21, + "learning_rate": 3.981566407910338e-05, + "loss": 0.2129, "step": 92090 }, { - "epoch": 0.82, - "learning_rate": 8.985226556166112e-06, - "loss": 0.1852, + "epoch": 0.21, + "learning_rate": 3.9814545535894055e-05, + "loss": 0.2048, "step": 92100 }, { - "epoch": 0.82, - "learning_rate": 8.980722457436268e-06, - "loss": 0.1827, + "epoch": 0.21, + "learning_rate": 3.9813426992684727e-05, + "loss": 0.2118, "step": 92110 }, { - "epoch": 0.82, - "learning_rate": 8.976218358706423e-06, - "loss": 0.1822, + "epoch": 0.21, + "learning_rate": 3.9812308449475404e-05, + "loss": 0.2082, "step": 92120 }, { - "epoch": 0.82, - "learning_rate": 8.97171425997658e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.981118990626608e-05, + "loss": 0.2118, "step": 92130 }, { - "epoch": 0.82, - "learning_rate": 8.967210161246735e-06, - "loss": 0.1857, + "epoch": 0.21, + "learning_rate": 3.9810071363056754e-05, + "loss": 0.212, "step": 92140 }, { - "epoch": 0.82, - "learning_rate": 8.96270606251689e-06, - "loss": 0.1799, + "epoch": 0.21, + "learning_rate": 3.980895281984743e-05, + "loss": 0.2081, "step": 92150 }, { - "epoch": 0.82, - "learning_rate": 8.958201963787047e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.980783427663811e-05, + "loss": 0.2085, "step": 92160 }, { - "epoch": 0.82, - "learning_rate": 8.953697865057202e-06, - "loss": 0.1847, + "epoch": 0.21, + "learning_rate": 3.980671573342879e-05, + "loss": 0.2067, "step": 92170 }, { - "epoch": 0.82, - "learning_rate": 8.949193766327358e-06, - "loss": 0.1906, + "epoch": 0.21, + "learning_rate": 3.9805597190219465e-05, + "loss": 0.2076, "step": 92180 }, { - "epoch": 0.82, - "learning_rate": 8.944689667597514e-06, - "loss": 0.191, + "epoch": 0.21, + "learning_rate": 3.9804478647010136e-05, + "loss": 0.2131, "step": 92190 }, { - "epoch": 0.82, - "learning_rate": 8.94018556886767e-06, - "loss": 0.187, + "epoch": 0.21, + "learning_rate": 3.9803360103800814e-05, + "loss": 0.2098, "step": 92200 }, { - "epoch": 0.82, - "learning_rate": 8.935681470137826e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.9802241560591485e-05, + "loss": 0.2025, "step": 92210 }, { - "epoch": 0.82, - "learning_rate": 8.931177371407981e-06, - "loss": 0.1851, + "epoch": 0.21, + "learning_rate": 3.9801123017382163e-05, + "loss": 0.2141, "step": 92220 }, { - "epoch": 0.82, - "learning_rate": 8.926673272678137e-06, - "loss": 0.1874, + "epoch": 0.21, + "learning_rate": 3.980000447417284e-05, + "loss": 0.2059, "step": 92230 }, { - "epoch": 0.82, - "learning_rate": 8.922169173948293e-06, - "loss": 0.1847, + "epoch": 0.21, + "learning_rate": 3.979888593096351e-05, + "loss": 0.2124, "step": 92240 }, { - "epoch": 0.82, - "learning_rate": 8.917665075218449e-06, - "loss": 0.1856, + "epoch": 0.21, + "learning_rate": 3.979776738775419e-05, + "loss": 0.2105, "step": 92250 }, { - "epoch": 0.82, - "learning_rate": 8.913160976488605e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.979664884454486e-05, + "loss": 0.2096, "step": 92260 }, { - "epoch": 0.82, - "learning_rate": 8.908656877758762e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.9795530301335546e-05, + "loss": 0.2077, "step": 92270 }, { - "epoch": 0.82, - "learning_rate": 8.904152779028916e-06, - "loss": 0.189, + "epoch": 0.21, + "learning_rate": 3.9794411758126224e-05, + "loss": 0.2188, "step": 92280 }, { - "epoch": 0.82, - "learning_rate": 8.899648680299072e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.9793293214916895e-05, + "loss": 0.2162, "step": 92290 }, { - "epoch": 0.82, - "learning_rate": 8.895144581569228e-06, - "loss": 0.1803, + "epoch": 0.21, + "learning_rate": 3.979217467170757e-05, + "loss": 0.212, "step": 92300 }, { - "epoch": 0.82, - "learning_rate": 8.890640482839384e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.9791056128498244e-05, + "loss": 0.206, "step": 92310 }, { - "epoch": 0.82, - "learning_rate": 8.886136384109541e-06, - "loss": 0.1843, + "epoch": 0.21, + "learning_rate": 3.978993758528892e-05, + "loss": 0.2089, "step": 92320 }, { - "epoch": 0.82, - "learning_rate": 8.881632285379695e-06, - "loss": 0.1808, + "epoch": 0.21, + "learning_rate": 3.9788819042079594e-05, + "loss": 0.2143, "step": 92330 }, { - "epoch": 0.82, - "learning_rate": 8.877128186649853e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.978770049887027e-05, + "loss": 0.2143, "step": 92340 }, { - "epoch": 0.82, - "learning_rate": 8.872624087920008e-06, - "loss": 0.1886, + "epoch": 0.21, + "learning_rate": 3.978658195566095e-05, + "loss": 0.2103, "step": 92350 }, { - "epoch": 0.82, - "learning_rate": 8.868119989190163e-06, - "loss": 0.183, + "epoch": 0.21, + "learning_rate": 3.978546341245162e-05, + "loss": 0.2117, "step": 92360 }, { - "epoch": 0.82, - "learning_rate": 8.86361589046032e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.97843448692423e-05, + "loss": 0.2058, "step": 92370 }, { - "epoch": 0.82, - "learning_rate": 8.859111791730474e-06, - "loss": 0.1876, + "epoch": 0.21, + "learning_rate": 3.9783226326032976e-05, + "loss": 0.208, "step": 92380 }, { - "epoch": 0.82, - "learning_rate": 8.854607693000632e-06, - "loss": 0.1865, + "epoch": 0.21, + "learning_rate": 3.9782107782823654e-05, + "loss": 0.2062, "step": 92390 }, { - "epoch": 0.82, - "learning_rate": 8.850103594270787e-06, - "loss": 0.1845, + "epoch": 0.21, + "learning_rate": 3.978098923961433e-05, + "loss": 0.2029, "step": 92400 }, { - "epoch": 0.83, - "learning_rate": 8.845599495540943e-06, - "loss": 0.1801, + "epoch": 0.21, + "learning_rate": 3.9779870696405e-05, + "loss": 0.208, "step": 92410 }, { - "epoch": 0.83, - "learning_rate": 8.841095396811099e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.977875215319568e-05, + "loss": 0.2066, "step": 92420 }, { - "epoch": 0.83, - "learning_rate": 8.836591298081253e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.977763360998635e-05, + "loss": 0.2041, "step": 92430 }, { - "epoch": 0.83, - "learning_rate": 8.83208719935141e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.977651506677703e-05, + "loss": 0.2058, "step": 92440 }, { - "epoch": 0.83, - "learning_rate": 8.827583100621566e-06, - "loss": 0.1851, + "epoch": 0.21, + "learning_rate": 3.977539652356771e-05, + "loss": 0.2106, "step": 92450 }, { - "epoch": 0.83, - "learning_rate": 8.823079001891722e-06, - "loss": 0.1779, + "epoch": 0.21, + "learning_rate": 3.977427798035838e-05, + "loss": 0.2086, "step": 92460 }, { - "epoch": 0.83, - "learning_rate": 8.818574903161878e-06, - "loss": 0.1855, + "epoch": 0.21, + "learning_rate": 3.977315943714906e-05, + "loss": 0.2166, "step": 92470 }, { - "epoch": 0.83, - "learning_rate": 8.814070804432034e-06, - "loss": 0.1837, + "epoch": 0.21, + "learning_rate": 3.9772040893939735e-05, + "loss": 0.2116, "step": 92480 }, { - "epoch": 0.83, - "learning_rate": 8.80956670570219e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.977092235073041e-05, + "loss": 0.2087, "step": 92490 }, { - "epoch": 0.83, - "learning_rate": 8.805062606972345e-06, - "loss": 0.1886, + "epoch": 0.21, + "learning_rate": 3.976980380752109e-05, + "loss": 0.2117, "step": 92500 }, { - "epoch": 0.83, - "learning_rate": 8.800558508242501e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.976868526431176e-05, + "loss": 0.2071, "step": 92510 }, { - "epoch": 0.83, - "learning_rate": 8.796054409512657e-06, - "loss": 0.1825, + "epoch": 0.21, + "learning_rate": 3.976756672110244e-05, + "loss": 0.2057, "step": 92520 }, { - "epoch": 0.83, - "learning_rate": 8.791550310782813e-06, - "loss": 0.1827, + "epoch": 0.21, + "learning_rate": 3.976644817789311e-05, + "loss": 0.2109, "step": 92530 }, { - "epoch": 0.83, - "learning_rate": 8.787046212052969e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.976532963468379e-05, + "loss": 0.2069, "step": 92540 }, { - "epoch": 0.83, - "learning_rate": 8.782542113323124e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.976421109147447e-05, + "loss": 0.2025, "step": 92550 }, { - "epoch": 0.83, - "learning_rate": 8.77803801459328e-06, - "loss": 0.1873, + "epoch": 0.21, + "learning_rate": 3.976309254826514e-05, + "loss": 0.206, "step": 92560 }, { - "epoch": 0.83, - "learning_rate": 8.773533915863436e-06, - "loss": 0.1872, + "epoch": 0.21, + "learning_rate": 3.9761974005055816e-05, + "loss": 0.2077, "step": 92570 }, { - "epoch": 0.83, - "learning_rate": 8.769029817133592e-06, - "loss": 0.1851, + "epoch": 0.21, + "learning_rate": 3.9760855461846494e-05, + "loss": 0.2117, "step": 92580 }, { - "epoch": 0.83, - "learning_rate": 8.764525718403748e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.975973691863717e-05, + "loss": 0.2068, "step": 92590 }, { - "epoch": 0.83, - "learning_rate": 8.760021619673903e-06, - "loss": 0.1822, + "epoch": 0.21, + "learning_rate": 3.975861837542785e-05, + "loss": 0.2044, "step": 92600 }, { - "epoch": 0.83, - "learning_rate": 8.75551752094406e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.975749983221852e-05, + "loss": 0.2089, "step": 92610 }, { - "epoch": 0.83, - "learning_rate": 8.751013422214217e-06, - "loss": 0.1891, + "epoch": 0.21, + "learning_rate": 3.97563812890092e-05, + "loss": 0.2071, "step": 92620 }, { - "epoch": 0.83, - "learning_rate": 8.74650932348437e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.975526274579987e-05, + "loss": 0.2085, "step": 92630 }, { - "epoch": 0.83, - "learning_rate": 8.742005224754527e-06, - "loss": 0.1782, + "epoch": 0.21, + "learning_rate": 3.975414420259055e-05, + "loss": 0.2052, "step": 92640 }, { - "epoch": 0.83, - "learning_rate": 8.737501126024682e-06, - "loss": 0.1845, + "epoch": 0.21, + "learning_rate": 3.975302565938122e-05, + "loss": 0.2119, "step": 92650 }, { - "epoch": 0.83, - "learning_rate": 8.732997027294838e-06, - "loss": 0.1845, + "epoch": 0.21, + "learning_rate": 3.97519071161719e-05, + "loss": 0.2066, "step": 92660 }, { - "epoch": 0.83, - "learning_rate": 8.728492928564996e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.9750788572962575e-05, + "loss": 0.2085, "step": 92670 }, { - "epoch": 0.83, - "learning_rate": 8.72398882983515e-06, - "loss": 0.1773, + "epoch": 0.21, + "learning_rate": 3.974967002975325e-05, + "loss": 0.2097, "step": 92680 }, { - "epoch": 0.83, - "learning_rate": 8.719484731105307e-06, - "loss": 0.1834, + "epoch": 0.21, + "learning_rate": 3.974855148654393e-05, + "loss": 0.208, "step": 92690 }, { - "epoch": 0.83, - "learning_rate": 8.714980632375461e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.97474329433346e-05, + "loss": 0.2076, "step": 92700 }, { - "epoch": 0.83, - "learning_rate": 8.710476533645617e-06, - "loss": 0.1868, + "epoch": 0.21, + "learning_rate": 3.974631440012528e-05, + "loss": 0.2099, "step": 92710 }, { - "epoch": 0.83, - "learning_rate": 8.705972434915775e-06, - "loss": 0.1843, + "epoch": 0.21, + "learning_rate": 3.974519585691596e-05, + "loss": 0.2078, "step": 92720 }, { - "epoch": 0.83, - "learning_rate": 8.701468336185929e-06, - "loss": 0.1877, + "epoch": 0.21, + "learning_rate": 3.974407731370663e-05, + "loss": 0.2083, "step": 92730 }, { - "epoch": 0.83, - "learning_rate": 8.696964237456086e-06, - "loss": 0.1796, + "epoch": 0.21, + "learning_rate": 3.974295877049731e-05, + "loss": 0.2132, "step": 92740 }, { - "epoch": 0.83, - "learning_rate": 8.69246013872624e-06, - "loss": 0.1794, + "epoch": 0.21, + "learning_rate": 3.974184022728798e-05, + "loss": 0.2099, "step": 92750 }, { - "epoch": 0.83, - "learning_rate": 8.687956039996398e-06, - "loss": 0.1791, + "epoch": 0.21, + "learning_rate": 3.9740721684078656e-05, + "loss": 0.2051, "step": 92760 }, { - "epoch": 0.83, - "learning_rate": 8.683451941266554e-06, - "loss": 0.1776, + "epoch": 0.21, + "learning_rate": 3.9739603140869334e-05, + "loss": 0.2084, "step": 92770 }, { - "epoch": 0.83, - "learning_rate": 8.678947842536708e-06, - "loss": 0.1838, + "epoch": 0.21, + "learning_rate": 3.9738484597660005e-05, + "loss": 0.2156, "step": 92780 }, { - "epoch": 0.83, - "learning_rate": 8.674443743806865e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.973736605445068e-05, + "loss": 0.2018, "step": 92790 }, { - "epoch": 0.83, - "learning_rate": 8.66993964507702e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.973624751124136e-05, + "loss": 0.2082, "step": 92800 }, { - "epoch": 0.83, - "learning_rate": 8.665435546347177e-06, - "loss": 0.181, + "epoch": 0.21, + "learning_rate": 3.973512896803204e-05, + "loss": 0.2095, "step": 92810 }, { - "epoch": 0.83, - "learning_rate": 8.660931447617333e-06, - "loss": 0.1849, + "epoch": 0.21, + "learning_rate": 3.973401042482272e-05, + "loss": 0.2093, "step": 92820 }, { - "epoch": 0.83, - "learning_rate": 8.656427348887488e-06, - "loss": 0.187, + "epoch": 0.21, + "learning_rate": 3.973289188161339e-05, + "loss": 0.2092, "step": 92830 }, { - "epoch": 0.83, - "learning_rate": 8.651923250157644e-06, - "loss": 0.186, + "epoch": 0.21, + "learning_rate": 3.9731773338404066e-05, + "loss": 0.2102, "step": 92840 }, { - "epoch": 0.83, - "learning_rate": 8.647419151427798e-06, - "loss": 0.1796, + "epoch": 0.21, + "learning_rate": 3.973065479519474e-05, + "loss": 0.2098, "step": 92850 }, { - "epoch": 0.83, - "learning_rate": 8.642915052697956e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.9729536251985415e-05, + "loss": 0.2071, "step": 92860 }, { - "epoch": 0.83, - "learning_rate": 8.638410953968112e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.972841770877609e-05, + "loss": 0.2058, "step": 92870 }, { - "epoch": 0.83, - "learning_rate": 8.633906855238267e-06, - "loss": 0.1766, + "epoch": 0.21, + "learning_rate": 3.9727299165566764e-05, + "loss": 0.2097, "step": 92880 }, { - "epoch": 0.83, - "learning_rate": 8.629402756508423e-06, - "loss": 0.1859, + "epoch": 0.21, + "learning_rate": 3.972618062235744e-05, + "loss": 0.2046, "step": 92890 }, { - "epoch": 0.83, - "learning_rate": 8.624898657778579e-06, - "loss": 0.1866, + "epoch": 0.21, + "learning_rate": 3.972506207914812e-05, + "loss": 0.2058, "step": 92900 }, { - "epoch": 0.83, - "learning_rate": 8.620394559048735e-06, - "loss": 0.1817, + "epoch": 0.21, + "learning_rate": 3.97239435359388e-05, + "loss": 0.2085, "step": 92910 }, { - "epoch": 0.83, - "learning_rate": 8.61589046031889e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.9722824992729476e-05, + "loss": 0.2145, "step": 92920 }, { - "epoch": 0.83, - "learning_rate": 8.611386361589046e-06, - "loss": 0.1855, + "epoch": 0.21, + "learning_rate": 3.972170644952015e-05, + "loss": 0.2062, "step": 92930 }, { - "epoch": 0.83, - "learning_rate": 8.606882262859202e-06, - "loss": 0.1859, + "epoch": 0.21, + "learning_rate": 3.9720587906310825e-05, + "loss": 0.2129, "step": 92940 }, { - "epoch": 0.83, - "learning_rate": 8.602378164129358e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.9719469363101496e-05, + "loss": 0.2129, "step": 92950 }, { - "epoch": 0.83, - "learning_rate": 8.597874065399514e-06, - "loss": 0.1878, + "epoch": 0.21, + "learning_rate": 3.9718350819892174e-05, + "loss": 0.2126, "step": 92960 }, { - "epoch": 0.83, - "learning_rate": 8.59336996666967e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.9717232276682845e-05, + "loss": 0.2055, "step": 92970 }, { - "epoch": 0.83, - "learning_rate": 8.588865867939825e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.971611373347352e-05, + "loss": 0.2105, "step": 92980 }, { - "epoch": 0.83, - "learning_rate": 8.584361769209981e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.97149951902642e-05, + "loss": 0.2085, "step": 92990 }, { - "epoch": 0.83, - "learning_rate": 8.579857670480137e-06, - "loss": 0.1841, + "epoch": 0.21, + "learning_rate": 3.971387664705488e-05, + "loss": 0.213, "step": 93000 }, { - "epoch": 0.83, - "learning_rate": 8.575353571750293e-06, - "loss": 0.1848, + "epoch": 0.21, + "learning_rate": 3.971275810384556e-05, + "loss": 0.2071, "step": 93010 }, { - "epoch": 0.83, - "learning_rate": 8.570849473020449e-06, - "loss": 0.1872, + "epoch": 0.21, + "learning_rate": 3.971163956063623e-05, + "loss": 0.2114, "step": 93020 }, { - "epoch": 0.83, - "learning_rate": 8.566345374290604e-06, - "loss": 0.1879, + "epoch": 0.21, + "learning_rate": 3.9710521017426906e-05, + "loss": 0.2172, "step": 93030 }, { - "epoch": 0.83, - "learning_rate": 8.561841275560762e-06, - "loss": 0.1816, + "epoch": 0.21, + "learning_rate": 3.9709402474217584e-05, + "loss": 0.2033, "step": 93040 }, { - "epoch": 0.83, - "learning_rate": 8.557337176830916e-06, - "loss": 0.1836, + "epoch": 0.21, + "learning_rate": 3.9708283931008255e-05, + "loss": 0.2019, "step": 93050 }, { - "epoch": 0.83, - "learning_rate": 8.552833078101072e-06, - "loss": 0.1841, + "epoch": 0.21, + "learning_rate": 3.970716538779893e-05, + "loss": 0.2119, "step": 93060 }, { - "epoch": 0.83, - "learning_rate": 8.54832897937123e-06, - "loss": 0.1867, + "epoch": 0.21, + "learning_rate": 3.9706046844589604e-05, + "loss": 0.2106, "step": 93070 }, { - "epoch": 0.83, - "learning_rate": 8.543824880641383e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.970492830138028e-05, + "loss": 0.2067, "step": 93080 }, { - "epoch": 0.83, - "learning_rate": 8.539320781911541e-06, - "loss": 0.1785, + "epoch": 0.21, + "learning_rate": 3.970380975817096e-05, + "loss": 0.2061, "step": 93090 }, { - "epoch": 0.83, - "learning_rate": 8.534816683181695e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.970269121496164e-05, + "loss": 0.2071, "step": 93100 }, { - "epoch": 0.83, - "learning_rate": 8.530312584451852e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.9701572671752316e-05, + "loss": 0.204, "step": 93110 }, { - "epoch": 0.83, - "learning_rate": 8.525808485722008e-06, - "loss": 0.1864, + "epoch": 0.21, + "learning_rate": 3.970045412854299e-05, + "loss": 0.2044, "step": 93120 }, { - "epoch": 0.83, - "learning_rate": 8.521304386992162e-06, - "loss": 0.186, + "epoch": 0.21, + "learning_rate": 3.9699335585333665e-05, + "loss": 0.2098, "step": 93130 }, { - "epoch": 0.83, - "learning_rate": 8.51680028826232e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.969821704212434e-05, + "loss": 0.2059, "step": 93140 }, { - "epoch": 0.83, - "learning_rate": 8.512296189532474e-06, - "loss": 0.1837, + "epoch": 0.21, + "learning_rate": 3.9697098498915014e-05, + "loss": 0.2045, "step": 93150 }, { - "epoch": 0.83, - "learning_rate": 8.507792090802631e-06, - "loss": 0.1826, + "epoch": 0.21, + "learning_rate": 3.969597995570569e-05, + "loss": 0.2067, "step": 93160 }, { - "epoch": 0.83, - "learning_rate": 8.503287992072787e-06, - "loss": 0.1865, + "epoch": 0.21, + "learning_rate": 3.969486141249636e-05, + "loss": 0.2095, "step": 93170 }, { - "epoch": 0.83, - "learning_rate": 8.498783893342943e-06, - "loss": 0.187, + "epoch": 0.21, + "learning_rate": 3.969374286928704e-05, + "loss": 0.2103, "step": 93180 }, { - "epoch": 0.83, - "learning_rate": 8.494279794613099e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.969262432607772e-05, + "loss": 0.1995, "step": 93190 }, { - "epoch": 0.83, - "learning_rate": 8.489775695883253e-06, - "loss": 0.1892, + "epoch": 0.21, + "learning_rate": 3.969150578286839e-05, + "loss": 0.2071, "step": 93200 }, { - "epoch": 0.83, - "learning_rate": 8.48527159715341e-06, - "loss": 0.1801, + "epoch": 0.21, + "learning_rate": 3.969038723965907e-05, + "loss": 0.2103, "step": 93210 }, { - "epoch": 0.83, - "learning_rate": 8.480767498423566e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.9689268696449746e-05, + "loss": 0.206, "step": 93220 }, { - "epoch": 0.83, - "learning_rate": 8.476263399693722e-06, - "loss": 0.1785, + "epoch": 0.21, + "learning_rate": 3.9688150153240424e-05, + "loss": 0.2052, "step": 93230 }, { - "epoch": 0.83, - "learning_rate": 8.471759300963878e-06, - "loss": 0.1868, + "epoch": 0.21, + "learning_rate": 3.96870316100311e-05, + "loss": 0.2101, "step": 93240 }, { - "epoch": 0.83, - "learning_rate": 8.467255202234034e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.968591306682177e-05, + "loss": 0.2035, "step": 93250 }, { - "epoch": 0.83, - "learning_rate": 8.46275110350419e-06, - "loss": 0.1837, + "epoch": 0.21, + "learning_rate": 3.968479452361245e-05, + "loss": 0.2036, "step": 93260 }, { - "epoch": 0.83, - "learning_rate": 8.458247004774345e-06, - "loss": 0.1816, + "epoch": 0.21, + "learning_rate": 3.968367598040312e-05, + "loss": 0.2076, "step": 93270 }, { - "epoch": 0.83, - "learning_rate": 8.453742906044501e-06, - "loss": 0.1838, + "epoch": 0.21, + "learning_rate": 3.96825574371938e-05, + "loss": 0.2036, "step": 93280 }, { - "epoch": 0.83, - "learning_rate": 8.449238807314657e-06, - "loss": 0.1854, + "epoch": 0.21, + "learning_rate": 3.968143889398447e-05, + "loss": 0.2066, "step": 93290 }, { - "epoch": 0.83, - "learning_rate": 8.444734708584813e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.968032035077515e-05, + "loss": 0.2059, "step": 93300 }, { - "epoch": 0.83, - "learning_rate": 8.440230609854968e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.967920180756583e-05, + "loss": 0.2021, "step": 93310 }, { - "epoch": 0.83, - "learning_rate": 8.435726511125124e-06, - "loss": 0.1804, + "epoch": 0.21, + "learning_rate": 3.9678083264356505e-05, + "loss": 0.2119, "step": 93320 }, { - "epoch": 0.83, - "learning_rate": 8.43122241239528e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.967696472114718e-05, + "loss": 0.206, "step": 93330 }, { - "epoch": 0.83, - "learning_rate": 8.426718313665436e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.9675846177937854e-05, + "loss": 0.2075, "step": 93340 }, { - "epoch": 0.83, - "learning_rate": 8.422214214935592e-06, - "loss": 0.1889, + "epoch": 0.21, + "learning_rate": 3.967472763472853e-05, + "loss": 0.212, "step": 93350 }, { - "epoch": 0.83, - "learning_rate": 8.417710116205747e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.967360909151921e-05, + "loss": 0.2084, "step": 93360 }, { - "epoch": 0.83, - "learning_rate": 8.413206017475903e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.967249054830988e-05, + "loss": 0.2086, "step": 93370 }, { - "epoch": 0.83, - "learning_rate": 8.408701918746059e-06, - "loss": 0.1845, + "epoch": 0.21, + "learning_rate": 3.967137200510056e-05, + "loss": 0.2078, "step": 93380 }, { - "epoch": 0.83, - "learning_rate": 8.404197820016217e-06, - "loss": 0.1853, + "epoch": 0.21, + "learning_rate": 3.967025346189123e-05, + "loss": 0.2027, "step": 93390 }, { - "epoch": 0.83, - "learning_rate": 8.39969372128637e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.966913491868191e-05, + "loss": 0.2063, "step": 93400 }, { - "epoch": 0.83, - "learning_rate": 8.395189622556526e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.9668016375472586e-05, + "loss": 0.2084, "step": 93410 }, { - "epoch": 0.83, - "learning_rate": 8.390685523826682e-06, - "loss": 0.1866, + "epoch": 0.21, + "learning_rate": 3.9666897832263264e-05, + "loss": 0.2065, "step": 93420 }, { - "epoch": 0.83, - "learning_rate": 8.386181425096838e-06, - "loss": 0.1798, + "epoch": 0.21, + "learning_rate": 3.966577928905394e-05, + "loss": 0.2086, "step": 93430 }, { - "epoch": 0.83, - "learning_rate": 8.381677326366996e-06, - "loss": 0.1817, + "epoch": 0.21, + "learning_rate": 3.966466074584461e-05, + "loss": 0.2086, "step": 93440 }, { - "epoch": 0.83, - "learning_rate": 8.37717322763715e-06, - "loss": 0.1824, + "epoch": 0.21, + "learning_rate": 3.966354220263529e-05, + "loss": 0.2093, "step": 93450 }, { - "epoch": 0.83, - "learning_rate": 8.372669128907307e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.966242365942597e-05, + "loss": 0.2076, "step": 93460 }, { - "epoch": 0.83, - "learning_rate": 8.368165030177461e-06, - "loss": 0.1838, + "epoch": 0.21, + "learning_rate": 3.966130511621664e-05, + "loss": 0.2105, "step": 93470 }, { - "epoch": 0.83, - "learning_rate": 8.363660931447617e-06, - "loss": 0.181, + "epoch": 0.21, + "learning_rate": 3.966018657300732e-05, + "loss": 0.2065, "step": 93480 }, { - "epoch": 0.83, - "learning_rate": 8.359156832717775e-06, - "loss": 0.1863, + "epoch": 0.21, + "learning_rate": 3.965906802979799e-05, + "loss": 0.2048, "step": 93490 }, { - "epoch": 0.83, - "learning_rate": 8.354652733987929e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.965794948658867e-05, + "loss": 0.2052, "step": 93500 }, { - "epoch": 0.83, - "learning_rate": 8.350148635258086e-06, - "loss": 0.1783, + "epoch": 0.21, + "learning_rate": 3.9656830943379345e-05, + "loss": 0.2104, "step": 93510 }, { - "epoch": 0.83, - "learning_rate": 8.34564453652824e-06, - "loss": 0.1863, + "epoch": 0.21, + "learning_rate": 3.9655824254490954e-05, + "loss": 0.213, "step": 93520 }, { - "epoch": 0.84, - "learning_rate": 8.341140437798398e-06, - "loss": 0.1866, + "epoch": 0.21, + "learning_rate": 3.965470571128163e-05, + "loss": 0.2104, "step": 93530 }, { - "epoch": 0.84, - "learning_rate": 8.336636339068553e-06, - "loss": 0.1858, + "epoch": 0.21, + "learning_rate": 3.96535871680723e-05, + "loss": 0.2096, "step": 93540 }, { - "epoch": 0.84, - "learning_rate": 8.332132240338708e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.965246862486298e-05, + "loss": 0.2041, "step": 93550 }, { - "epoch": 0.84, - "learning_rate": 8.327628141608865e-06, - "loss": 0.1855, + "epoch": 0.21, + "learning_rate": 3.965135008165365e-05, + "loss": 0.2074, "step": 93560 }, { - "epoch": 0.84, - "learning_rate": 8.32312404287902e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.965023153844433e-05, + "loss": 0.207, "step": 93570 }, { - "epoch": 0.84, - "learning_rate": 8.318619944149177e-06, - "loss": 0.1846, + "epoch": 0.21, + "learning_rate": 3.964911299523501e-05, + "loss": 0.208, "step": 93580 }, { - "epoch": 0.84, - "learning_rate": 8.314115845419332e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.9647994452025686e-05, + "loss": 0.2048, "step": 93590 }, { - "epoch": 0.84, - "learning_rate": 8.309611746689488e-06, - "loss": 0.1783, + "epoch": 0.21, + "learning_rate": 3.9646875908816364e-05, + "loss": 0.2027, "step": 93600 }, { - "epoch": 0.84, - "learning_rate": 8.305107647959644e-06, - "loss": 0.1776, + "epoch": 0.21, + "learning_rate": 3.9645757365607035e-05, + "loss": 0.2066, "step": 93610 }, { - "epoch": 0.84, - "learning_rate": 8.300603549229798e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.964463882239771e-05, + "loss": 0.2074, "step": 93620 }, { - "epoch": 0.84, - "learning_rate": 8.296099450499956e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.9643520279188384e-05, + "loss": 0.2086, "step": 93630 }, { - "epoch": 0.84, - "learning_rate": 8.291595351770111e-06, - "loss": 0.1771, + "epoch": 0.21, + "learning_rate": 3.964240173597906e-05, + "loss": 0.2022, "step": 93640 }, { - "epoch": 0.84, - "learning_rate": 8.287091253040267e-06, - "loss": 0.1871, + "epoch": 0.21, + "learning_rate": 3.964128319276974e-05, + "loss": 0.2058, "step": 93650 }, { - "epoch": 0.84, - "learning_rate": 8.282587154310423e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.964016464956041e-05, + "loss": 0.2117, "step": 93660 }, { - "epoch": 0.84, - "learning_rate": 8.278083055580579e-06, - "loss": 0.1851, + "epoch": 0.21, + "learning_rate": 3.963904610635109e-05, + "loss": 0.2058, "step": 93670 }, { - "epoch": 0.84, - "learning_rate": 8.273578956850735e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.963792756314177e-05, + "loss": 0.2094, "step": 93680 }, { - "epoch": 0.84, - "learning_rate": 8.26907485812089e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.9636809019932445e-05, + "loss": 0.2165, "step": 93690 }, { - "epoch": 0.84, - "learning_rate": 8.264570759391046e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.963569047672312e-05, + "loss": 0.207, "step": 93700 }, { - "epoch": 0.84, - "learning_rate": 8.260066660661202e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.9634571933513794e-05, + "loss": 0.2016, "step": 93710 }, { - "epoch": 0.84, - "learning_rate": 8.255562561931358e-06, - "loss": 0.1889, + "epoch": 0.21, + "learning_rate": 3.963345339030447e-05, + "loss": 0.2142, "step": 93720 }, { - "epoch": 0.84, - "learning_rate": 8.251058463201514e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.963233484709514e-05, + "loss": 0.2045, "step": 93730 }, { - "epoch": 0.84, - "learning_rate": 8.24655436447167e-06, - "loss": 0.1845, + "epoch": 0.21, + "learning_rate": 3.963121630388582e-05, + "loss": 0.2099, "step": 93740 }, { - "epoch": 0.84, - "learning_rate": 8.242050265741825e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.96300977606765e-05, + "loss": 0.2055, "step": 93750 }, { - "epoch": 0.84, - "learning_rate": 8.237546167011981e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.962897921746717e-05, + "loss": 0.2107, "step": 93760 }, { - "epoch": 0.84, - "learning_rate": 8.233042068282137e-06, - "loss": 0.1781, + "epoch": 0.21, + "learning_rate": 3.962786067425785e-05, + "loss": 0.2068, "step": 93770 }, { - "epoch": 0.84, - "learning_rate": 8.228537969552293e-06, - "loss": 0.1842, + "epoch": 0.21, + "learning_rate": 3.962674213104852e-05, + "loss": 0.2079, "step": 93780 }, { - "epoch": 0.84, - "learning_rate": 8.22403387082245e-06, - "loss": 0.1867, + "epoch": 0.21, + "learning_rate": 3.96256235878392e-05, + "loss": 0.2021, "step": 93790 }, { - "epoch": 0.84, - "learning_rate": 8.219529772092604e-06, - "loss": 0.183, + "epoch": 0.21, + "learning_rate": 3.962450504462988e-05, + "loss": 0.204, "step": 93800 }, { - "epoch": 0.84, - "learning_rate": 8.215025673362762e-06, - "loss": 0.1854, + "epoch": 0.21, + "learning_rate": 3.962338650142055e-05, + "loss": 0.2051, "step": 93810 }, { - "epoch": 0.84, - "learning_rate": 8.210521574632916e-06, - "loss": 0.1843, + "epoch": 0.21, + "learning_rate": 3.962226795821123e-05, + "loss": 0.2079, "step": 93820 }, { - "epoch": 0.84, - "learning_rate": 8.206017475903072e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.96211494150019e-05, + "loss": 0.2062, "step": 93830 }, { - "epoch": 0.84, - "learning_rate": 8.201513377173229e-06, - "loss": 0.1803, + "epoch": 0.21, + "learning_rate": 3.962003087179258e-05, + "loss": 0.2055, "step": 93840 }, { - "epoch": 0.84, - "learning_rate": 8.197009278443383e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.961891232858326e-05, + "loss": 0.2076, "step": 93850 }, { - "epoch": 0.84, - "learning_rate": 8.19250517971354e-06, - "loss": 0.1795, + "epoch": 0.21, + "learning_rate": 3.961779378537393e-05, + "loss": 0.2035, "step": 93860 }, { - "epoch": 0.84, - "learning_rate": 8.188001080983695e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.961667524216461e-05, + "loss": 0.2064, "step": 93870 }, { - "epoch": 0.84, - "learning_rate": 8.183496982253852e-06, - "loss": 0.1831, + "epoch": 0.21, + "learning_rate": 3.961555669895528e-05, + "loss": 0.207, "step": 93880 }, { - "epoch": 0.84, - "learning_rate": 8.178992883524008e-06, - "loss": 0.181, + "epoch": 0.21, + "learning_rate": 3.9614438155745956e-05, + "loss": 0.205, "step": 93890 }, { - "epoch": 0.84, - "learning_rate": 8.174488784794162e-06, - "loss": 0.1786, + "epoch": 0.21, + "learning_rate": 3.9613319612536634e-05, + "loss": 0.2061, "step": 93900 }, { - "epoch": 0.84, - "learning_rate": 8.16998468606432e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.961220106932731e-05, + "loss": 0.204, "step": 93910 }, { - "epoch": 0.84, - "learning_rate": 8.165480587334474e-06, - "loss": 0.1796, + "epoch": 0.21, + "learning_rate": 3.961108252611799e-05, + "loss": 0.2114, "step": 93920 }, { - "epoch": 0.84, - "learning_rate": 8.160976488604631e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.960996398290866e-05, + "loss": 0.204, "step": 93930 }, { - "epoch": 0.84, - "learning_rate": 8.156472389874787e-06, - "loss": 0.1857, + "epoch": 0.21, + "learning_rate": 3.960884543969934e-05, + "loss": 0.2112, "step": 93940 }, { - "epoch": 0.84, - "learning_rate": 8.151968291144941e-06, - "loss": 0.1885, + "epoch": 0.21, + "learning_rate": 3.960772689649001e-05, + "loss": 0.2078, "step": 93950 }, { - "epoch": 0.84, - "learning_rate": 8.147464192415099e-06, - "loss": 0.1827, + "epoch": 0.21, + "learning_rate": 3.960660835328069e-05, + "loss": 0.2077, "step": 93960 }, { - "epoch": 0.84, - "learning_rate": 8.142960093685253e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.9605489810071366e-05, + "loss": 0.2056, "step": 93970 }, { - "epoch": 0.84, - "learning_rate": 8.13845599495541e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.960437126686204e-05, + "loss": 0.209, "step": 93980 }, { - "epoch": 0.84, - "learning_rate": 8.133951896225566e-06, - "loss": 0.1769, + "epoch": 0.21, + "learning_rate": 3.9603252723652715e-05, + "loss": 0.2039, "step": 93990 }, { - "epoch": 0.84, - "learning_rate": 8.129447797495722e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.960213418044339e-05, + "loss": 0.2026, "step": 94000 }, { - "epoch": 0.84, - "learning_rate": 8.124943698765878e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.960101563723407e-05, + "loss": 0.209, "step": 94010 }, { - "epoch": 0.84, - "learning_rate": 8.120439600036032e-06, - "loss": 0.1848, + "epoch": 0.21, + "learning_rate": 3.959989709402475e-05, + "loss": 0.2109, "step": 94020 }, { - "epoch": 0.84, - "learning_rate": 8.11593550130619e-06, - "loss": 0.1887, + "epoch": 0.21, + "learning_rate": 3.959877855081542e-05, + "loss": 0.2136, "step": 94030 }, { - "epoch": 0.84, - "learning_rate": 8.111431402576345e-06, - "loss": 0.1802, + "epoch": 0.21, + "learning_rate": 3.95976600076061e-05, + "loss": 0.2091, "step": 94040 }, { - "epoch": 0.84, - "learning_rate": 8.106927303846501e-06, - "loss": 0.1871, + "epoch": 0.21, + "learning_rate": 3.959654146439677e-05, + "loss": 0.2022, "step": 94050 }, { - "epoch": 0.84, - "learning_rate": 8.102873614989641e-06, - "loss": 0.1785, + "epoch": 0.21, + "learning_rate": 3.959542292118745e-05, + "loss": 0.2038, "step": 94060 }, { - "epoch": 0.84, - "learning_rate": 8.098369516259795e-06, - "loss": 0.1841, + "epoch": 0.21, + "learning_rate": 3.9594304377978125e-05, + "loss": 0.208, "step": 94070 }, { - "epoch": 0.84, - "learning_rate": 8.093865417529953e-06, - "loss": 0.1856, + "epoch": 0.21, + "learning_rate": 3.9593185834768796e-05, + "loss": 0.2053, "step": 94080 }, { - "epoch": 0.84, - "learning_rate": 8.089361318800109e-06, - "loss": 0.1816, + "epoch": 0.21, + "learning_rate": 3.9592067291559474e-05, + "loss": 0.2082, "step": 94090 }, { - "epoch": 0.84, - "learning_rate": 8.084857220070264e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.959094874835015e-05, + "loss": 0.2076, "step": 94100 }, { - "epoch": 0.84, - "learning_rate": 8.08035312134042e-06, - "loss": 0.1897, + "epoch": 0.21, + "learning_rate": 3.958983020514083e-05, + "loss": 0.2016, "step": 94110 }, { - "epoch": 0.84, - "learning_rate": 8.075849022610576e-06, - "loss": 0.1809, + "epoch": 0.21, + "learning_rate": 3.958871166193151e-05, + "loss": 0.2025, "step": 94120 }, { - "epoch": 0.84, - "learning_rate": 8.071344923880732e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.958759311872218e-05, + "loss": 0.2092, "step": 94130 }, { - "epoch": 0.84, - "learning_rate": 8.066840825150888e-06, - "loss": 0.1857, + "epoch": 0.21, + "learning_rate": 3.9586474575512857e-05, + "loss": 0.2109, "step": 94140 }, { - "epoch": 0.84, - "learning_rate": 8.062336726421043e-06, - "loss": 0.176, + "epoch": 0.21, + "learning_rate": 3.958535603230353e-05, + "loss": 0.2071, "step": 94150 }, { - "epoch": 0.84, - "learning_rate": 8.0578326276912e-06, - "loss": 0.1789, + "epoch": 0.21, + "learning_rate": 3.9584237489094206e-05, + "loss": 0.204, "step": 94160 }, { - "epoch": 0.84, - "learning_rate": 8.053328528961355e-06, - "loss": 0.1788, + "epoch": 0.21, + "learning_rate": 3.9583118945884884e-05, + "loss": 0.2054, "step": 94170 }, { - "epoch": 0.84, - "learning_rate": 8.048824430231511e-06, - "loss": 0.1836, + "epoch": 0.21, + "learning_rate": 3.9582000402675555e-05, + "loss": 0.204, "step": 94180 }, { - "epoch": 0.84, - "learning_rate": 8.044320331501667e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.958088185946623e-05, + "loss": 0.2106, "step": 94190 }, { - "epoch": 0.84, - "learning_rate": 8.039816232771822e-06, - "loss": 0.1863, + "epoch": 0.21, + "learning_rate": 3.9579763316256904e-05, + "loss": 0.2079, "step": 94200 }, { - "epoch": 0.84, - "learning_rate": 8.035312134041978e-06, - "loss": 0.1788, + "epoch": 0.21, + "learning_rate": 3.957864477304758e-05, + "loss": 0.208, "step": 94210 }, { - "epoch": 0.84, - "learning_rate": 8.030808035312134e-06, - "loss": 0.1894, + "epoch": 0.21, + "learning_rate": 3.9577526229838266e-05, + "loss": 0.2031, "step": 94220 }, { - "epoch": 0.84, - "learning_rate": 8.02630393658229e-06, - "loss": 0.1864, + "epoch": 0.21, + "learning_rate": 3.957640768662894e-05, + "loss": 0.2044, "step": 94230 }, { - "epoch": 0.84, - "learning_rate": 8.021799837852446e-06, - "loss": 0.183, + "epoch": 0.21, + "learning_rate": 3.9575289143419616e-05, + "loss": 0.2063, "step": 94240 }, { - "epoch": 0.84, - "learning_rate": 8.017295739122601e-06, - "loss": 0.1838, + "epoch": 0.21, + "learning_rate": 3.957417060021029e-05, + "loss": 0.2048, "step": 94250 }, { - "epoch": 0.84, - "learning_rate": 8.012791640392759e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.9573052057000965e-05, + "loss": 0.2116, "step": 94260 }, { - "epoch": 0.84, - "learning_rate": 8.008287541662913e-06, - "loss": 0.1859, + "epoch": 0.21, + "learning_rate": 3.9571933513791636e-05, + "loss": 0.2133, "step": 94270 }, { - "epoch": 0.84, - "learning_rate": 8.003783442933069e-06, - "loss": 0.1835, + "epoch": 0.21, + "learning_rate": 3.9570814970582314e-05, + "loss": 0.2054, "step": 94280 }, { - "epoch": 0.84, - "learning_rate": 7.999279344203225e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.956969642737299e-05, + "loss": 0.2087, "step": 94290 }, { - "epoch": 0.84, - "learning_rate": 7.99477524547338e-06, - "loss": 0.179, + "epoch": 0.21, + "learning_rate": 3.956857788416366e-05, + "loss": 0.2034, "step": 94300 }, { - "epoch": 0.84, - "learning_rate": 7.990271146743538e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.956745934095434e-05, + "loss": 0.2008, "step": 94310 }, { - "epoch": 0.84, - "learning_rate": 7.985767048013692e-06, - "loss": 0.1854, + "epoch": 0.21, + "learning_rate": 3.956634079774502e-05, + "loss": 0.2033, "step": 94320 }, { - "epoch": 0.84, - "learning_rate": 7.98126294928385e-06, - "loss": 0.1861, + "epoch": 0.21, + "learning_rate": 3.9565222254535697e-05, + "loss": 0.2127, "step": 94330 }, { - "epoch": 0.84, - "learning_rate": 7.976758850554004e-06, - "loss": 0.1783, + "epoch": 0.21, + "learning_rate": 3.9564103711326374e-05, + "loss": 0.2053, "step": 94340 }, { - "epoch": 0.84, - "learning_rate": 7.97225475182416e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.9562985168117046e-05, + "loss": 0.2038, "step": 94350 }, { - "epoch": 0.84, - "learning_rate": 7.967750653094317e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.9561866624907724e-05, + "loss": 0.2027, "step": 94360 }, { - "epoch": 0.84, - "learning_rate": 7.963246554364471e-06, - "loss": 0.181, + "epoch": 0.21, + "learning_rate": 3.9560748081698395e-05, + "loss": 0.2078, "step": 94370 }, { - "epoch": 0.84, - "learning_rate": 7.958742455634629e-06, - "loss": 0.1853, + "epoch": 0.21, + "learning_rate": 3.955962953848907e-05, + "loss": 0.2023, "step": 94380 }, { - "epoch": 0.84, - "learning_rate": 7.954238356904784e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.955851099527975e-05, + "loss": 0.2113, "step": 94390 }, { - "epoch": 0.84, - "learning_rate": 7.94973425817494e-06, - "loss": 0.1808, + "epoch": 0.21, + "learning_rate": 3.955739245207042e-05, + "loss": 0.2085, "step": 94400 }, { - "epoch": 0.84, - "learning_rate": 7.945230159445096e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.95562739088611e-05, + "loss": 0.2043, "step": 94410 }, { - "epoch": 0.84, - "learning_rate": 7.94072606071525e-06, - "loss": 0.1848, + "epoch": 0.21, + "learning_rate": 3.955515536565178e-05, + "loss": 0.208, "step": 94420 }, { - "epoch": 0.84, - "learning_rate": 7.936221961985408e-06, - "loss": 0.1846, + "epoch": 0.21, + "learning_rate": 3.9554036822442455e-05, + "loss": 0.2101, "step": 94430 }, { - "epoch": 0.84, - "learning_rate": 7.931717863255563e-06, - "loss": 0.187, + "epoch": 0.21, + "learning_rate": 3.9552918279233133e-05, + "loss": 0.2004, "step": 94440 }, { - "epoch": 0.84, - "learning_rate": 7.927213764525719e-06, - "loss": 0.183, + "epoch": 0.21, + "learning_rate": 3.9551799736023805e-05, + "loss": 0.2052, "step": 94450 }, { - "epoch": 0.84, - "learning_rate": 7.922709665795875e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.955068119281448e-05, + "loss": 0.1991, "step": 94460 }, { - "epoch": 0.84, - "learning_rate": 7.91820556706603e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.9549562649605154e-05, + "loss": 0.2041, "step": 94470 }, { - "epoch": 0.84, - "learning_rate": 7.913701468336186e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.954844410639583e-05, + "loss": 0.2103, "step": 94480 }, { - "epoch": 0.84, - "learning_rate": 7.909197369606342e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.954732556318651e-05, + "loss": 0.2091, "step": 94490 }, { - "epoch": 0.84, - "learning_rate": 7.904693270876498e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.954620701997718e-05, + "loss": 0.2092, "step": 94500 }, { - "epoch": 0.84, - "learning_rate": 7.900189172146654e-06, - "loss": 0.1804, + "epoch": 0.21, + "learning_rate": 3.954508847676786e-05, + "loss": 0.2105, "step": 94510 }, { - "epoch": 0.84, - "learning_rate": 7.89568507341681e-06, - "loss": 0.1767, + "epoch": 0.21, + "learning_rate": 3.9543969933558537e-05, + "loss": 0.2014, "step": 94520 }, { - "epoch": 0.84, - "learning_rate": 7.891180974686965e-06, - "loss": 0.1852, + "epoch": 0.21, + "learning_rate": 3.9542851390349214e-05, + "loss": 0.1994, "step": 94530 }, { - "epoch": 0.84, - "learning_rate": 7.886676875957121e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.954173284713989e-05, + "loss": 0.206, "step": 94540 }, { - "epoch": 0.84, - "learning_rate": 7.882172777227277e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.9540614303930564e-05, + "loss": 0.2038, "step": 94550 }, { - "epoch": 0.84, - "learning_rate": 7.877668678497433e-06, - "loss": 0.1887, + "epoch": 0.21, + "learning_rate": 3.953949576072124e-05, + "loss": 0.2024, "step": 94560 }, { - "epoch": 0.84, - "learning_rate": 7.873614989640573e-06, - "loss": 0.1774, + "epoch": 0.21, + "learning_rate": 3.953837721751191e-05, + "loss": 0.2094, "step": 94570 }, { - "epoch": 0.84, - "learning_rate": 7.869110890910729e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.953725867430259e-05, + "loss": 0.2049, "step": 94580 }, { - "epoch": 0.84, - "learning_rate": 7.864606792180885e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.953614013109326e-05, + "loss": 0.2084, "step": 94590 }, { - "epoch": 0.84, - "learning_rate": 7.86010269345104e-06, - "loss": 0.1783, + "epoch": 0.21, + "learning_rate": 3.953502158788394e-05, + "loss": 0.2062, "step": 94600 }, { - "epoch": 0.84, - "learning_rate": 7.855598594721196e-06, - "loss": 0.1891, + "epoch": 0.21, + "learning_rate": 3.953390304467462e-05, + "loss": 0.2089, "step": 94610 }, { - "epoch": 0.84, - "learning_rate": 7.851094495991352e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.953278450146529e-05, + "loss": 0.2064, "step": 94620 }, { - "epoch": 0.84, - "learning_rate": 7.846590397261508e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.9531665958255973e-05, + "loss": 0.2087, "step": 94630 }, { - "epoch": 0.84, - "learning_rate": 7.842086298531664e-06, - "loss": 0.1826, + "epoch": 0.21, + "learning_rate": 3.9530547415046645e-05, + "loss": 0.2095, "step": 94640 }, { - "epoch": 0.85, - "learning_rate": 7.83758219980182e-06, - "loss": 0.1853, + "epoch": 0.21, + "learning_rate": 3.952942887183732e-05, + "loss": 0.2094, "step": 94650 }, { - "epoch": 0.85, - "learning_rate": 7.833078101071977e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.9528310328628e-05, + "loss": 0.2078, "step": 94660 }, { - "epoch": 0.85, - "learning_rate": 7.828574002342131e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.952719178541867e-05, + "loss": 0.2104, "step": 94670 }, { - "epoch": 0.85, - "learning_rate": 7.824069903612287e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.952607324220935e-05, + "loss": 0.2125, "step": 94680 }, { - "epoch": 0.85, - "learning_rate": 7.819565804882443e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.952495469900002e-05, + "loss": 0.2077, "step": 94690 }, { - "epoch": 0.85, - "learning_rate": 7.815061706152599e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.95238361557907e-05, + "loss": 0.2064, "step": 94700 }, { - "epoch": 0.85, - "learning_rate": 7.810557607422756e-06, - "loss": 0.1835, + "epoch": 0.21, + "learning_rate": 3.9522717612581376e-05, + "loss": 0.1994, "step": 94710 }, { - "epoch": 0.85, - "learning_rate": 7.80605350869291e-06, - "loss": 0.1825, + "epoch": 0.21, + "learning_rate": 3.952159906937205e-05, + "loss": 0.2054, "step": 94720 }, { - "epoch": 0.85, - "learning_rate": 7.801549409963068e-06, - "loss": 0.1802, + "epoch": 0.21, + "learning_rate": 3.9520480526162726e-05, + "loss": 0.2089, "step": 94730 }, { - "epoch": 0.85, - "learning_rate": 7.797045311233222e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.9519361982953403e-05, + "loss": 0.2088, "step": 94740 }, { - "epoch": 0.85, - "learning_rate": 7.792541212503378e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.951824343974408e-05, + "loss": 0.207, "step": 94750 }, { - "epoch": 0.85, - "learning_rate": 7.788037113773535e-06, - "loss": 0.1816, + "epoch": 0.21, + "learning_rate": 3.951712489653476e-05, + "loss": 0.2116, "step": 94760 }, { - "epoch": 0.85, - "learning_rate": 7.78353301504369e-06, - "loss": 0.1786, + "epoch": 0.21, + "learning_rate": 3.951600635332543e-05, + "loss": 0.2103, "step": 94770 }, { - "epoch": 0.85, - "learning_rate": 7.779028916313847e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.951488781011611e-05, + "loss": 0.1993, "step": 94780 }, { - "epoch": 0.85, - "learning_rate": 7.774524817584e-06, - "loss": 0.1822, + "epoch": 0.21, + "learning_rate": 3.951376926690678e-05, + "loss": 0.2079, "step": 94790 }, { - "epoch": 0.85, - "learning_rate": 7.770020718854158e-06, - "loss": 0.1817, + "epoch": 0.21, + "learning_rate": 3.951265072369746e-05, + "loss": 0.2118, "step": 94800 }, { - "epoch": 0.85, - "learning_rate": 7.765516620124314e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.9511532180488135e-05, + "loss": 0.1998, "step": 94810 }, { - "epoch": 0.85, - "learning_rate": 7.761012521394468e-06, - "loss": 0.1837, + "epoch": 0.21, + "learning_rate": 3.9510413637278807e-05, + "loss": 0.2111, "step": 94820 }, { - "epoch": 0.85, - "learning_rate": 7.756508422664626e-06, - "loss": 0.1788, + "epoch": 0.21, + "learning_rate": 3.9509295094069485e-05, + "loss": 0.2019, "step": 94830 }, { - "epoch": 0.85, - "learning_rate": 7.75200432393478e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.950817655086016e-05, + "loss": 0.2066, "step": 94840 }, { - "epoch": 0.85, - "learning_rate": 7.747500225204937e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.950705800765084e-05, + "loss": 0.2093, "step": 94850 }, { - "epoch": 0.85, - "learning_rate": 7.742996126475093e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.950593946444152e-05, + "loss": 0.2042, "step": 94860 }, { - "epoch": 0.85, - "learning_rate": 7.738492027745249e-06, - "loss": 0.1856, + "epoch": 0.21, + "learning_rate": 3.950482092123219e-05, + "loss": 0.2044, "step": 94870 }, { - "epoch": 0.85, - "learning_rate": 7.733987929015405e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.950370237802287e-05, + "loss": 0.2051, "step": 94880 }, { - "epoch": 0.85, - "learning_rate": 7.729483830285559e-06, - "loss": 0.1875, + "epoch": 0.21, + "learning_rate": 3.950258383481354e-05, + "loss": 0.2118, "step": 94890 }, { - "epoch": 0.85, - "learning_rate": 7.724979731555716e-06, - "loss": 0.1775, + "epoch": 0.21, + "learning_rate": 3.9501465291604216e-05, + "loss": 0.2086, "step": 94900 }, { - "epoch": 0.85, - "learning_rate": 7.720475632825872e-06, - "loss": 0.1803, + "epoch": 0.21, + "learning_rate": 3.950034674839489e-05, + "loss": 0.2047, "step": 94910 }, { - "epoch": 0.85, - "learning_rate": 7.715971534096028e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.9499228205185566e-05, + "loss": 0.2071, "step": 94920 }, { - "epoch": 0.85, - "learning_rate": 7.711467435366184e-06, - "loss": 0.1799, + "epoch": 0.21, + "learning_rate": 3.9498109661976243e-05, + "loss": 0.2044, "step": 94930 }, { - "epoch": 0.85, - "learning_rate": 7.70696333663634e-06, - "loss": 0.1776, + "epoch": 0.21, + "learning_rate": 3.949699111876692e-05, + "loss": 0.2086, "step": 94940 }, { - "epoch": 0.85, - "learning_rate": 7.702459237906495e-06, - "loss": 0.1762, + "epoch": 0.21, + "learning_rate": 3.94958725755576e-05, + "loss": 0.1985, "step": 94950 }, { - "epoch": 0.85, - "learning_rate": 7.697955139176651e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.949475403234827e-05, + "loss": 0.21, "step": 94960 }, { - "epoch": 0.85, - "learning_rate": 7.693451040446807e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.949363548913895e-05, + "loss": 0.1997, "step": 94970 }, { - "epoch": 0.85, - "learning_rate": 7.688946941716963e-06, - "loss": 0.1847, + "epoch": 0.21, + "learning_rate": 3.9492516945929626e-05, + "loss": 0.2079, "step": 94980 }, { - "epoch": 0.85, - "learning_rate": 7.684442842987118e-06, - "loss": 0.1807, + "epoch": 0.21, + "learning_rate": 3.94913984027203e-05, + "loss": 0.2106, "step": 94990 }, { - "epoch": 0.85, - "learning_rate": 7.679938744257274e-06, - "loss": 0.1824, + "epoch": 0.21, + "learning_rate": 3.9490279859510975e-05, + "loss": 0.2063, "step": 95000 }, { - "epoch": 0.85, - "learning_rate": 7.67543464552743e-06, - "loss": 0.1811, + "epoch": 0.21, + "learning_rate": 3.9489161316301647e-05, + "loss": 0.2102, "step": 95010 }, { - "epoch": 0.85, - "learning_rate": 7.670930546797586e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.9488042773092324e-05, + "loss": 0.2043, "step": 95020 }, { - "epoch": 0.85, - "learning_rate": 7.666426448067742e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.9486924229883e-05, + "loss": 0.2103, "step": 95030 }, { - "epoch": 0.85, - "learning_rate": 7.661922349337897e-06, - "loss": 0.1826, + "epoch": 0.21, + "learning_rate": 3.948580568667368e-05, + "loss": 0.2041, "step": 95040 }, { - "epoch": 0.85, - "learning_rate": 7.657418250608053e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.948468714346436e-05, + "loss": 0.2037, "step": 95050 }, { - "epoch": 0.85, - "learning_rate": 7.65291415187821e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.948356860025503e-05, + "loss": 0.2122, "step": 95060 }, { - "epoch": 0.85, - "learning_rate": 7.648410053148365e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.948245005704571e-05, + "loss": 0.2049, "step": 95070 }, { - "epoch": 0.85, - "learning_rate": 7.643905954418522e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.9481331513836385e-05, + "loss": 0.206, "step": 95080 }, { - "epoch": 0.85, - "learning_rate": 7.639401855688676e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.9480212970627056e-05, + "loss": 0.2064, "step": 95090 }, { - "epoch": 0.85, - "learning_rate": 7.634897756958832e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.9479094427417734e-05, + "loss": 0.2103, "step": 95100 }, { - "epoch": 0.85, - "learning_rate": 7.63039365822899e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.9477975884208405e-05, + "loss": 0.2055, "step": 95110 }, { - "epoch": 0.85, - "learning_rate": 7.625889559499144e-06, - "loss": 0.1862, + "epoch": 0.21, + "learning_rate": 3.9476857340999083e-05, + "loss": 0.2052, "step": 95120 }, { - "epoch": 0.85, - "learning_rate": 7.6213854607693005e-06, - "loss": 0.1857, + "epoch": 0.21, + "learning_rate": 3.947573879778976e-05, + "loss": 0.2076, "step": 95130 }, { - "epoch": 0.85, - "learning_rate": 7.616881362039456e-06, - "loss": 0.1764, + "epoch": 0.21, + "learning_rate": 3.947462025458043e-05, + "loss": 0.2098, "step": 95140 }, { - "epoch": 0.85, - "learning_rate": 7.612377263309613e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.947350171137111e-05, + "loss": 0.2056, "step": 95150 }, { - "epoch": 0.85, - "learning_rate": 7.607873164579768e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.947238316816179e-05, + "loss": 0.208, "step": 95160 }, { - "epoch": 0.85, - "learning_rate": 7.603369065849923e-06, - "loss": 0.1796, + "epoch": 0.21, + "learning_rate": 3.9471264624952466e-05, + "loss": 0.2073, "step": 95170 }, { - "epoch": 0.85, - "learning_rate": 7.5988649671200795e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.9470146081743144e-05, + "loss": 0.2085, "step": 95180 }, { - "epoch": 0.85, - "learning_rate": 7.594360868390235e-06, - "loss": 0.1846, + "epoch": 0.21, + "learning_rate": 3.9469027538533815e-05, + "loss": 0.2032, "step": 95190 }, { - "epoch": 0.85, - "learning_rate": 7.589856769660392e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.946790899532449e-05, + "loss": 0.2037, "step": 95200 }, { - "epoch": 0.85, - "learning_rate": 7.585352670930547e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.9466790452115164e-05, + "loss": 0.2093, "step": 95210 }, { - "epoch": 0.85, - "learning_rate": 7.5808485722007035e-06, - "loss": 0.1856, + "epoch": 0.21, + "learning_rate": 3.946567190890584e-05, + "loss": 0.2092, "step": 95220 }, { - "epoch": 0.85, - "learning_rate": 7.5763444734708585e-06, - "loss": 0.1781, + "epoch": 0.21, + "learning_rate": 3.9464553365696514e-05, + "loss": 0.2075, "step": 95230 }, { - "epoch": 0.85, - "learning_rate": 7.571840374741014e-06, - "loss": 0.1823, + "epoch": 0.21, + "learning_rate": 3.946343482248719e-05, + "loss": 0.2061, "step": 95240 }, { - "epoch": 0.85, - "learning_rate": 7.567336276011171e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.946231627927787e-05, + "loss": 0.2136, "step": 95250 }, { - "epoch": 0.85, - "learning_rate": 7.562832177281326e-06, - "loss": 0.1858, + "epoch": 0.21, + "learning_rate": 3.946119773606855e-05, + "loss": 0.2023, "step": 95260 }, { - "epoch": 0.85, - "learning_rate": 7.5583280785514825e-06, - "loss": 0.1795, + "epoch": 0.21, + "learning_rate": 3.9460079192859225e-05, + "loss": 0.2037, "step": 95270 }, { - "epoch": 0.85, - "learning_rate": 7.5538239798216375e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.9458960649649896e-05, + "loss": 0.2116, "step": 95280 }, { - "epoch": 0.85, - "learning_rate": 7.549319881091794e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.9457842106440574e-05, + "loss": 0.2111, "step": 95290 }, { - "epoch": 0.85, - "learning_rate": 7.54481578236195e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.945672356323125e-05, + "loss": 0.2093, "step": 95300 }, { - "epoch": 0.85, - "learning_rate": 7.540311683632105e-06, - "loss": 0.1829, + "epoch": 0.21, + "learning_rate": 3.9455605020021923e-05, + "loss": 0.2045, "step": 95310 }, { - "epoch": 0.85, - "learning_rate": 7.5358075849022615e-06, - "loss": 0.1779, + "epoch": 0.21, + "learning_rate": 3.94544864768126e-05, + "loss": 0.2091, "step": 95320 }, { - "epoch": 0.85, - "learning_rate": 7.5313034861724165e-06, - "loss": 0.1835, + "epoch": 0.21, + "learning_rate": 3.945336793360327e-05, + "loss": 0.2049, "step": 95330 }, { - "epoch": 0.85, - "learning_rate": 7.526799387442573e-06, - "loss": 0.1867, + "epoch": 0.21, + "learning_rate": 3.945224939039395e-05, + "loss": 0.2116, "step": 95340 }, { - "epoch": 0.85, - "learning_rate": 7.522295288712729e-06, - "loss": 0.1824, + "epoch": 0.21, + "learning_rate": 3.945113084718463e-05, + "loss": 0.2029, "step": 95350 }, { - "epoch": 0.85, - "learning_rate": 7.5177911899828855e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.9450012303975306e-05, + "loss": 0.202, "step": 95360 }, { - "epoch": 0.85, - "learning_rate": 7.5132870912530405e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.9448893760765984e-05, + "loss": 0.2044, "step": 95370 }, { - "epoch": 0.85, - "learning_rate": 7.508782992523196e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.9447775217556655e-05, + "loss": 0.201, "step": 95380 }, { - "epoch": 0.85, - "learning_rate": 7.504278893793353e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.944665667434733e-05, + "loss": 0.2054, "step": 95390 }, { - "epoch": 0.85, - "learning_rate": 7.499774795063508e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.944553813113801e-05, + "loss": 0.2037, "step": 95400 }, { - "epoch": 0.85, - "learning_rate": 7.4952706963336645e-06, - "loss": 0.1808, + "epoch": 0.21, + "learning_rate": 3.944441958792868e-05, + "loss": 0.2044, "step": 95410 }, { - "epoch": 0.85, - "learning_rate": 7.4907665976038195e-06, - "loss": 0.1768, + "epoch": 0.21, + "learning_rate": 3.944330104471936e-05, + "loss": 0.2013, "step": 95420 }, { - "epoch": 0.85, - "learning_rate": 7.486262498873976e-06, - "loss": 0.1796, + "epoch": 0.21, + "learning_rate": 3.944218250151003e-05, + "loss": 0.2065, "step": 95430 }, { - "epoch": 0.85, - "learning_rate": 7.481758400144132e-06, - "loss": 0.1835, + "epoch": 0.21, + "learning_rate": 3.944106395830071e-05, + "loss": 0.2096, "step": 95440 }, { - "epoch": 0.85, - "learning_rate": 7.477254301414287e-06, - "loss": 0.1788, + "epoch": 0.21, + "learning_rate": 3.943994541509139e-05, + "loss": 0.2029, "step": 95450 }, { - "epoch": 0.85, - "learning_rate": 7.4727502026844435e-06, - "loss": 0.1857, + "epoch": 0.21, + "learning_rate": 3.9438826871882065e-05, + "loss": 0.2055, "step": 95460 }, { - "epoch": 0.85, - "learning_rate": 7.4682461039545985e-06, - "loss": 0.1895, + "epoch": 0.21, + "learning_rate": 3.943770832867274e-05, + "loss": 0.21, "step": 95470 }, { - "epoch": 0.85, - "learning_rate": 7.463742005224755e-06, - "loss": 0.1805, + "epoch": 0.21, + "learning_rate": 3.9436589785463414e-05, + "loss": 0.2051, "step": 95480 }, { - "epoch": 0.85, - "learning_rate": 7.459237906494911e-06, - "loss": 0.1806, + "epoch": 0.21, + "learning_rate": 3.943547124225409e-05, + "loss": 0.2087, "step": 95490 }, { - "epoch": 0.85, - "learning_rate": 7.4547338077650676e-06, - "loss": 0.1795, + "epoch": 0.21, + "learning_rate": 3.943435269904477e-05, + "loss": 0.2046, "step": 95500 }, { - "epoch": 0.85, - "learning_rate": 7.4502297090352225e-06, - "loss": 0.1839, + "epoch": 0.21, + "learning_rate": 3.943323415583544e-05, + "loss": 0.2015, "step": 95510 }, { - "epoch": 0.85, - "learning_rate": 7.4457256103053775e-06, - "loss": 0.1752, + "epoch": 0.21, + "learning_rate": 3.943211561262612e-05, + "loss": 0.2023, "step": 95520 }, { - "epoch": 0.85, - "learning_rate": 7.441221511575534e-06, - "loss": 0.1793, + "epoch": 0.21, + "learning_rate": 3.943099706941679e-05, + "loss": 0.201, "step": 95530 }, { - "epoch": 0.85, - "learning_rate": 7.43671741284569e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.942987852620747e-05, + "loss": 0.2132, "step": 95540 }, { - "epoch": 0.85, - "learning_rate": 7.4322133141158466e-06, - "loss": 0.1919, + "epoch": 0.21, + "learning_rate": 3.942875998299814e-05, + "loss": 0.2046, "step": 95550 }, { - "epoch": 0.85, - "learning_rate": 7.4277092153860015e-06, - "loss": 0.1804, + "epoch": 0.21, + "learning_rate": 3.942764143978882e-05, + "loss": 0.21, "step": 95560 }, { - "epoch": 0.85, - "learning_rate": 7.423205116656158e-06, - "loss": 0.1822, + "epoch": 0.21, + "learning_rate": 3.9426522896579495e-05, + "loss": 0.2086, "step": 95570 }, { - "epoch": 0.85, - "learning_rate": 7.418701017926313e-06, - "loss": 0.1929, + "epoch": 0.21, + "learning_rate": 3.942540435337017e-05, + "loss": 0.2026, "step": 95580 }, { - "epoch": 0.85, - "learning_rate": 7.414196919196469e-06, - "loss": 0.1808, + "epoch": 0.21, + "learning_rate": 3.942428581016085e-05, + "loss": 0.2089, "step": 95590 }, { - "epoch": 0.85, - "learning_rate": 7.4096928204666256e-06, - "loss": 0.1779, + "epoch": 0.21, + "learning_rate": 3.942316726695152e-05, + "loss": 0.2015, "step": 95600 }, { - "epoch": 0.85, - "learning_rate": 7.4051887217367805e-06, - "loss": 0.1834, + "epoch": 0.21, + "learning_rate": 3.94220487237422e-05, + "loss": 0.2122, "step": 95610 }, { - "epoch": 0.85, - "learning_rate": 7.400684623006937e-06, - "loss": 0.1807, + "epoch": 0.21, + "learning_rate": 3.942104203485381e-05, + "loss": 0.2018, "step": 95620 }, { - "epoch": 0.85, - "learning_rate": 7.396180524277092e-06, - "loss": 0.1842, + "epoch": 0.21, + "learning_rate": 3.941992349164449e-05, + "loss": 0.2033, "step": 95630 }, { - "epoch": 0.85, - "learning_rate": 7.391676425547249e-06, - "loss": 0.1834, + "epoch": 0.21, + "learning_rate": 3.9418804948435165e-05, + "loss": 0.2026, "step": 95640 }, { - "epoch": 0.85, - "learning_rate": 7.3871723268174045e-06, - "loss": 0.1792, + "epoch": 0.21, + "learning_rate": 3.9417686405225836e-05, + "loss": 0.2058, "step": 95650 }, { - "epoch": 0.85, - "learning_rate": 7.3826682280875595e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.9416567862016514e-05, + "loss": 0.2039, "step": 95660 }, { - "epoch": 0.85, - "learning_rate": 7.378164129357716e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.9415449318807185e-05, + "loss": 0.2048, "step": 95670 }, { - "epoch": 0.85, - "learning_rate": 7.373660030627871e-06, - "loss": 0.1815, + "epoch": 0.21, + "learning_rate": 3.941433077559786e-05, + "loss": 0.2081, "step": 95680 }, { - "epoch": 0.85, - "learning_rate": 7.369155931898028e-06, - "loss": 0.1759, + "epoch": 0.21, + "learning_rate": 3.941321223238854e-05, + "loss": 0.2036, "step": 95690 }, { - "epoch": 0.85, - "learning_rate": 7.3646518331681835e-06, - "loss": 0.1789, + "epoch": 0.21, + "learning_rate": 3.941209368917921e-05, + "loss": 0.2062, "step": 95700 }, { - "epoch": 0.85, - "learning_rate": 7.36014773443834e-06, - "loss": 0.1873, + "epoch": 0.21, + "learning_rate": 3.941097514596989e-05, + "loss": 0.2075, "step": 95710 }, { - "epoch": 0.85, - "learning_rate": 7.355643635708495e-06, - "loss": 0.1806, + "epoch": 0.21, + "learning_rate": 3.940985660276056e-05, + "loss": 0.204, "step": 95720 }, { - "epoch": 0.85, - "learning_rate": 7.35113953697865e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.940873805955124e-05, + "loss": 0.2033, "step": 95730 }, { - "epoch": 0.85, - "learning_rate": 7.346635438248807e-06, - "loss": 0.1802, + "epoch": 0.21, + "learning_rate": 3.940761951634192e-05, + "loss": 0.204, "step": 95740 }, { - "epoch": 0.85, - "learning_rate": 7.3421313395189625e-06, - "loss": 0.178, + "epoch": 0.21, + "learning_rate": 3.9406500973132595e-05, + "loss": 0.2052, "step": 95750 }, { - "epoch": 0.85, - "learning_rate": 7.337627240789119e-06, - "loss": 0.183, + "epoch": 0.21, + "learning_rate": 3.940538242992327e-05, + "loss": 0.2095, "step": 95760 }, { - "epoch": 0.86, - "learning_rate": 7.333123142059274e-06, - "loss": 0.1776, + "epoch": 0.21, + "learning_rate": 3.9404263886713944e-05, + "loss": 0.2056, "step": 95770 }, { - "epoch": 0.86, - "learning_rate": 7.328619043329431e-06, - "loss": 0.1809, + "epoch": 0.21, + "learning_rate": 3.940314534350462e-05, + "loss": 0.2055, "step": 95780 }, { - "epoch": 0.86, - "learning_rate": 7.324114944599586e-06, - "loss": 0.1883, + "epoch": 0.21, + "learning_rate": 3.94020268002953e-05, + "loss": 0.2056, "step": 95790 }, { - "epoch": 0.86, - "learning_rate": 7.3196108458697415e-06, - "loss": 0.1844, + "epoch": 0.21, + "learning_rate": 3.940090825708597e-05, + "loss": 0.2062, "step": 95800 }, { - "epoch": 0.86, - "learning_rate": 7.315106747139898e-06, - "loss": 0.1917, + "epoch": 0.21, + "learning_rate": 3.939978971387665e-05, + "loss": 0.2004, "step": 95810 }, { - "epoch": 0.86, - "learning_rate": 7.310602648410053e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.939867117066732e-05, + "loss": 0.2088, "step": 95820 }, { - "epoch": 0.86, - "learning_rate": 7.30609854968021e-06, - "loss": 0.1828, + "epoch": 0.21, + "learning_rate": 3.9397552627458e-05, + "loss": 0.205, "step": 95830 }, { - "epoch": 0.86, - "learning_rate": 7.301594450950365e-06, - "loss": 0.184, + "epoch": 0.21, + "learning_rate": 3.9396434084248676e-05, + "loss": 0.2066, "step": 95840 }, { - "epoch": 0.86, - "learning_rate": 7.297090352220521e-06, - "loss": 0.1853, + "epoch": 0.21, + "learning_rate": 3.9395315541039354e-05, + "loss": 0.2113, "step": 95850 }, { - "epoch": 0.86, - "learning_rate": 7.292586253490677e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.939419699783003e-05, + "loss": 0.1993, "step": 95860 }, { - "epoch": 0.86, - "learning_rate": 7.288082154760832e-06, - "loss": 0.1901, + "epoch": 0.21, + "learning_rate": 3.93930784546207e-05, + "loss": 0.2022, "step": 95870 }, { - "epoch": 0.86, - "learning_rate": 7.283578056030989e-06, - "loss": 0.1836, + "epoch": 0.21, + "learning_rate": 3.939195991141138e-05, + "loss": 0.2054, "step": 95880 }, { - "epoch": 0.86, - "learning_rate": 7.279073957301144e-06, - "loss": 0.1813, + "epoch": 0.21, + "learning_rate": 3.939084136820206e-05, + "loss": 0.2092, "step": 95890 }, { - "epoch": 0.86, - "learning_rate": 7.2745698585713e-06, - "loss": 0.1812, + "epoch": 0.21, + "learning_rate": 3.938972282499273e-05, + "loss": 0.211, "step": 95900 }, { - "epoch": 0.86, - "learning_rate": 7.270065759841456e-06, - "loss": 0.1757, + "epoch": 0.21, + "learning_rate": 3.938860428178341e-05, + "loss": 0.2059, "step": 95910 }, { - "epoch": 0.86, - "learning_rate": 7.265561661111613e-06, - "loss": 0.1769, + "epoch": 0.21, + "learning_rate": 3.938748573857408e-05, + "loss": 0.2055, "step": 95920 }, { - "epoch": 0.86, - "learning_rate": 7.261057562381768e-06, - "loss": 0.1892, + "epoch": 0.21, + "learning_rate": 3.938636719536476e-05, + "loss": 0.2077, "step": 95930 }, { - "epoch": 0.86, - "learning_rate": 7.256553463651923e-06, - "loss": 0.1797, + "epoch": 0.21, + "learning_rate": 3.9385248652155435e-05, + "loss": 0.2027, "step": 95940 }, { - "epoch": 0.86, - "learning_rate": 7.252049364922079e-06, - "loss": 0.1842, + "epoch": 0.21, + "learning_rate": 3.938413010894611e-05, + "loss": 0.2024, "step": 95950 }, { - "epoch": 0.86, - "learning_rate": 7.247545266192235e-06, - "loss": 0.1849, + "epoch": 0.21, + "learning_rate": 3.938301156573679e-05, + "loss": 0.2066, "step": 95960 }, { - "epoch": 0.86, - "learning_rate": 7.243041167462392e-06, - "loss": 0.185, + "epoch": 0.21, + "learning_rate": 3.938189302252746e-05, + "loss": 0.206, "step": 95970 }, { - "epoch": 0.86, - "learning_rate": 7.238537068732547e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.938077447931814e-05, + "loss": 0.2047, "step": 95980 }, { - "epoch": 0.86, - "learning_rate": 7.234032970002703e-06, - "loss": 0.1821, + "epoch": 0.21, + "learning_rate": 3.937965593610881e-05, + "loss": 0.2104, "step": 95990 }, { - "epoch": 0.86, - "learning_rate": 7.229528871272858e-06, - "loss": 0.1803, + "epoch": 0.21, + "learning_rate": 3.937853739289949e-05, + "loss": 0.2045, "step": 96000 }, { - "epoch": 0.86, - "eval_NEIMS_canon_smiles": 0.9448, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.06445, - "eval_NEIMS_daylight_tanimoto_simil": 0.4672603673886566, - "eval_NEIMS_exact_mols": 0.0642, - "eval_NEIMS_exact_smiles": 0.06233333333333333, - "eval_NEIMS_loss": 0.21077434718608856, - "eval_NEIMS_matched_formulas": 0.5876333333333333, - "eval_NEIMS_morgan_tanimoto_simil": 0.3718269128473269, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.06463333333333333, - "eval_NEIMS_runtime": 710.2144, - "eval_NEIMS_samples_per_second": 84.482, - "eval_NEIMS_steps_per_second": 1.321, + "epoch": 0.21, + "eval_NEIMS_canon_smiles": 0.9498833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.05853333333333333, + "eval_NEIMS_daylight_tanimoto_simil": 0.4627459933756142, + "eval_NEIMS_exact_mols": 0.05843333333333333, + "eval_NEIMS_exact_smiles": 0.05675, + "eval_NEIMS_loss": 0.21724660694599152, + "eval_NEIMS_matched_formulas": 0.5455166666666666, + "eval_NEIMS_morgan_tanimoto_simil": 0.36668735368261884, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.05878333333333333, + "eval_NEIMS_runtime": 740.4336, + "eval_NEIMS_samples_per_second": 81.034, + "eval_NEIMS_steps_per_second": 1.267, "step": 96000 }, { - "epoch": 0.86, - "eval_RASSP_canon_smiles": 0.9370220723277791, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.15273650115203527, - "eval_RASSP_daylight_tanimoto_simil": 0.5978313703107301, - "eval_RASSP_exact_mols": 0.15213543927605436, - "eval_RASSP_exact_smiles": 0.14769425985908438, - "eval_RASSP_loss": 0.14983013272285461, - "eval_RASSP_matched_formulas": 0.7636658095969546, - "eval_RASSP_morgan_tanimoto_simil": 0.47045272905034535, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.1522356162553845, - "eval_RASSP_runtime": 816.8397, - "eval_RASSP_samples_per_second": 73.324, - "eval_RASSP_steps_per_second": 1.146, + "epoch": 0.21, + "eval_RASSP_canon_smiles": 0.9467392393228036, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.0864360369986977, + "eval_RASSP_daylight_tanimoto_simil": 0.542271450331729, + "eval_RASSP_exact_mols": 0.08615220222392894, + "eval_RASSP_exact_smiles": 0.08359768925101012, + "eval_RASSP_loss": 0.1830580234527588, + "eval_RASSP_matched_formulas": 0.6968477643837446, + "eval_RASSP_morgan_tanimoto_simil": 0.404296418018788, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.0862189868768157, + "eval_RASSP_runtime": 837.3787, + "eval_RASSP_samples_per_second": 71.526, + "eval_RASSP_steps_per_second": 1.118, "step": 96000 }, { - "epoch": 0.86, - "eval_NIST_canon_smiles": 0.8822798736558186, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.01266990808105902, - "eval_NIST_daylight_tanimoto_simil": 0.2704161303006068, - "eval_NIST_exact_mols": 0.01210206906342052, - "eval_NIST_exact_smiles": 0.011321290414167583, - "eval_NIST_loss": 1.4756792783737183, - "eval_NIST_matched_formulas": 0.08922170564644923, - "eval_NIST_morgan_tanimoto_simil": 0.22269916852825272, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01266990808105902, - "eval_NIST_runtime": 463.6612, - "eval_NIST_samples_per_second": 60.771, - "eval_NIST_steps_per_second": 0.951, + "epoch": 0.21, + "eval_NEIMS_old_canon_smiles": 0.9500666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.058, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.462089647874399, + "eval_NEIMS_old_exact_mols": 0.05776666666666667, + "eval_NEIMS_old_exact_smiles": 0.05603333333333333, + "eval_NEIMS_old_loss": 0.21671070158481598, + "eval_NEIMS_old_matched_formulas": 0.5479666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.3669061040722215, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.058133333333333335, + "eval_NEIMS_old_runtime": 371.9528, + "eval_NEIMS_old_samples_per_second": 80.655, + "eval_NEIMS_old_steps_per_second": 1.261, "step": 96000 }, { - "epoch": 0.86, - "learning_rate": 7.225024772543014e-06, - "loss": 0.1818, + "epoch": 0.21, + "eval_RASSP_old_canon_smiles": 0.9460740147495579, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.10328027496913271, + "eval_RASSP_old_daylight_tanimoto_simil": 0.5593726994617684, + "eval_RASSP_old_exact_mols": 0.10287983448459972, + "eval_RASSP_old_exact_smiles": 0.10004338105249107, + "eval_RASSP_old_loss": 0.1748560518026352, + "eval_RASSP_old_matched_formulas": 0.7140854940434478, + "eval_RASSP_old_morgan_tanimoto_simil": 0.42418436017487615, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.10301331464611072, + "eval_RASSP_old_runtime": 414.896, + "eval_RASSP_old_samples_per_second": 72.228, + "eval_RASSP_old_steps_per_second": 1.13, + "step": 96000 + }, + { + "epoch": 0.21, + "eval_NIST_canon_smiles": 0.8761401142776023, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.015793022678070767, + "eval_NIST_daylight_tanimoto_simil": 0.27161352261198485, + "eval_NIST_exact_mols": 0.015438123292046704, + "eval_NIST_exact_smiles": 0.014479894949781738, + "eval_NIST_loss": 1.8289155960083008, + "eval_NIST_matched_formulas": 0.08993150441849736, + "eval_NIST_morgan_tanimoto_simil": 0.22712913944048627, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.015686552862263548, + "eval_NIST_runtime": 526.0596, + "eval_NIST_samples_per_second": 53.562, + "eval_NIST_steps_per_second": 0.838, + "step": 96000 + }, + { + "epoch": 0.21, + "learning_rate": 3.937741884969017e-05, + "loss": 0.2048, "step": 96010 }, { - "epoch": 0.86, - "learning_rate": 7.220520673813171e-06, - "loss": 0.1834, + "epoch": 0.21, + "learning_rate": 3.937630030648084e-05, + "loss": 0.2062, "step": 96020 }, { - "epoch": 0.86, - "learning_rate": 7.216016575083326e-06, - "loss": 0.1807, + "epoch": 0.21, + "learning_rate": 3.9375181763271516e-05, + "loss": 0.2048, "step": 96030 }, { - "epoch": 0.86, - "learning_rate": 7.211512476353482e-06, - "loss": 0.1799, + "epoch": 0.21, + "learning_rate": 3.9374063220062194e-05, + "loss": 0.2047, "step": 96040 }, { - "epoch": 0.86, - "learning_rate": 7.207008377623637e-06, - "loss": 0.1806, + "epoch": 0.21, + "learning_rate": 3.937294467685287e-05, + "loss": 0.2104, "step": 96050 }, { - "epoch": 0.86, - "learning_rate": 7.202504278893794e-06, - "loss": 0.1786, + "epoch": 0.21, + "learning_rate": 3.937182613364355e-05, + "loss": 0.2086, "step": 96060 }, { - "epoch": 0.86, - "learning_rate": 7.19800018016395e-06, - "loss": 0.1833, + "epoch": 0.21, + "learning_rate": 3.937070759043422e-05, + "loss": 0.2085, "step": 96070 }, { - "epoch": 0.86, - "learning_rate": 7.193496081434105e-06, - "loss": 0.1819, + "epoch": 0.21, + "learning_rate": 3.93695890472249e-05, + "loss": 0.2026, "step": 96080 }, { - "epoch": 0.86, - "learning_rate": 7.188991982704261e-06, - "loss": 0.1786, + "epoch": 0.21, + "learning_rate": 3.936847050401557e-05, + "loss": 0.2036, "step": 96090 }, { - "epoch": 0.86, - "learning_rate": 7.184487883974417e-06, - "loss": 0.1779, + "epoch": 0.21, + "learning_rate": 3.936735196080625e-05, + "loss": 0.2118, "step": 96100 }, { - "epoch": 0.86, - "learning_rate": 7.179983785244574e-06, - "loss": 0.1775, + "epoch": 0.21, + "learning_rate": 3.9366233417596926e-05, + "loss": 0.2114, "step": 96110 }, { - "epoch": 0.86, - "learning_rate": 7.175479686514729e-06, - "loss": 0.1814, + "epoch": 0.21, + "learning_rate": 3.93651148743876e-05, + "loss": 0.2085, "step": 96120 }, { - "epoch": 0.86, - "learning_rate": 7.170975587784885e-06, - "loss": 0.1794, + "epoch": 0.21, + "learning_rate": 3.9363996331178275e-05, + "loss": 0.2081, "step": 96130 }, { - "epoch": 0.86, - "learning_rate": 7.16647148905504e-06, - "loss": 0.1807, + "epoch": 0.21, + "learning_rate": 3.9362877787968946e-05, + "loss": 0.2039, "step": 96140 }, { - "epoch": 0.86, - "learning_rate": 7.161967390325196e-06, - "loss": 0.187, + "epoch": 0.21, + "learning_rate": 3.9361759244759624e-05, + "loss": 0.2069, "step": 96150 }, { - "epoch": 0.86, - "learning_rate": 7.157463291595353e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.936064070155031e-05, + "loss": 0.2057, "step": 96160 }, { - "epoch": 0.86, - "learning_rate": 7.152959192865508e-06, - "loss": 0.1824, + "epoch": 0.21, + "learning_rate": 3.935952215834098e-05, + "loss": 0.2037, "step": 96170 }, { - "epoch": 0.86, - "learning_rate": 7.148455094135664e-06, - "loss": 0.1818, + "epoch": 0.21, + "learning_rate": 3.935840361513166e-05, + "loss": 0.2069, "step": 96180 }, { - "epoch": 0.86, - "learning_rate": 7.143950995405819e-06, - "loss": 0.175, + "epoch": 0.21, + "learning_rate": 3.935728507192233e-05, + "loss": 0.2061, "step": 96190 }, { - "epoch": 0.86, - "learning_rate": 7.139446896675976e-06, - "loss": 0.1771, + "epoch": 0.21, + "learning_rate": 3.935616652871301e-05, + "loss": 0.2047, "step": 96200 }, { - "epoch": 0.86, - "learning_rate": 7.134942797946132e-06, - "loss": 0.18, + "epoch": 0.21, + "learning_rate": 3.9355047985503685e-05, + "loss": 0.2001, "step": 96210 }, { - "epoch": 0.86, - "learning_rate": 7.130438699216287e-06, - "loss": 0.1823, + "epoch": 0.21, + "learning_rate": 3.9353929442294356e-05, + "loss": 0.2017, "step": 96220 }, { - "epoch": 0.86, - "learning_rate": 7.125934600486443e-06, - "loss": 0.1817, + "epoch": 0.21, + "learning_rate": 3.9352810899085034e-05, + "loss": 0.2072, "step": 96230 }, { - "epoch": 0.86, - "learning_rate": 7.121430501756598e-06, - "loss": 0.1872, + "epoch": 0.21, + "learning_rate": 3.9351692355875705e-05, + "loss": 0.2065, "step": 96240 }, { - "epoch": 0.86, - "learning_rate": 7.116926403026755e-06, - "loss": 0.182, + "epoch": 0.21, + "learning_rate": 3.935057381266638e-05, + "loss": 0.2037, "step": 96250 }, { - "epoch": 0.86, - "learning_rate": 7.112422304296911e-06, - "loss": 0.1836, + "epoch": 0.21, + "learning_rate": 3.934945526945706e-05, + "loss": 0.2043, "step": 96260 }, { - "epoch": 0.86, - "learning_rate": 7.107918205567067e-06, - "loss": 0.1832, + "epoch": 0.21, + "learning_rate": 3.934833672624774e-05, + "loss": 0.2059, "step": 96270 }, { - "epoch": 0.86, - "learning_rate": 7.103414106837222e-06, - "loss": 0.1798, + "epoch": 0.21, + "learning_rate": 3.934721818303842e-05, + "loss": 0.2084, "step": 96280 }, { - "epoch": 0.86, - "learning_rate": 7.098910008107377e-06, - "loss": 0.1781, + "epoch": 0.21, + "learning_rate": 3.934609963982909e-05, + "loss": 0.208, "step": 96290 }, { - "epoch": 0.86, - "learning_rate": 7.094405909377534e-06, - "loss": 0.1824, + "epoch": 0.21, + "learning_rate": 3.9344981096619766e-05, + "loss": 0.2033, "step": 96300 }, { - "epoch": 0.86, - "learning_rate": 7.08990181064769e-06, - "loss": 0.1835, + "epoch": 0.21, + "learning_rate": 3.934386255341044e-05, + "loss": 0.2081, "step": 96310 }, { - "epoch": 0.86, - "learning_rate": 7.085397711917846e-06, - "loss": 0.1791, + "epoch": 0.21, + "learning_rate": 3.9342744010201115e-05, + "loss": 0.2027, "step": 96320 }, { - "epoch": 0.86, - "learning_rate": 7.080893613188001e-06, - "loss": 0.1769, + "epoch": 0.22, + "learning_rate": 3.934162546699179e-05, + "loss": 0.2084, "step": 96330 }, { - "epoch": 0.86, - "learning_rate": 7.076389514458158e-06, - "loss": 0.1789, + "epoch": 0.22, + "learning_rate": 3.9340506923782464e-05, + "loss": 0.204, "step": 96340 }, { - "epoch": 0.86, - "learning_rate": 7.071885415728313e-06, - "loss": 0.1768, + "epoch": 0.22, + "learning_rate": 3.933938838057314e-05, + "loss": 0.2023, "step": 96350 }, { - "epoch": 0.86, - "learning_rate": 7.067381316998469e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.933826983736382e-05, + "loss": 0.2059, "step": 96360 }, { - "epoch": 0.86, - "learning_rate": 7.062877218268625e-06, - "loss": 0.1873, + "epoch": 0.22, + "learning_rate": 3.93371512941545e-05, + "loss": 0.2072, "step": 96370 }, { - "epoch": 0.86, - "learning_rate": 7.05837311953878e-06, - "loss": 0.1811, + "epoch": 0.22, + "learning_rate": 3.9336032750945176e-05, + "loss": 0.2013, "step": 96380 }, { - "epoch": 0.86, - "learning_rate": 7.053869020808937e-06, - "loss": 0.1745, + "epoch": 0.22, + "learning_rate": 3.933491420773585e-05, + "loss": 0.2048, "step": 96390 }, { - "epoch": 0.86, - "learning_rate": 7.049364922079092e-06, - "loss": 0.1781, + "epoch": 0.22, + "learning_rate": 3.9333795664526525e-05, + "loss": 0.2077, "step": 96400 }, { - "epoch": 0.86, - "learning_rate": 7.044860823349248e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.9332677121317196e-05, + "loss": 0.2093, "step": 96410 }, { - "epoch": 0.86, - "learning_rate": 7.040356724619404e-06, - "loss": 0.1806, + "epoch": 0.22, + "learning_rate": 3.9331558578107874e-05, + "loss": 0.1993, "step": 96420 }, { - "epoch": 0.86, - "learning_rate": 7.035852625889559e-06, - "loss": 0.1818, + "epoch": 0.22, + "learning_rate": 3.933044003489855e-05, + "loss": 0.2075, "step": 96430 }, { - "epoch": 0.86, - "learning_rate": 7.031348527159716e-06, - "loss": 0.183, + "epoch": 0.22, + "learning_rate": 3.932932149168922e-05, + "loss": 0.1991, "step": 96440 }, { - "epoch": 0.86, - "learning_rate": 7.026844428429871e-06, - "loss": 0.1818, + "epoch": 0.22, + "learning_rate": 3.93282029484799e-05, + "loss": 0.2048, "step": 96450 }, { - "epoch": 0.86, - "learning_rate": 7.022340329700028e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.932708440527058e-05, + "loss": 0.2041, "step": 96460 }, { - "epoch": 0.86, - "learning_rate": 7.017836230970183e-06, - "loss": 0.175, + "epoch": 0.22, + "learning_rate": 3.932596586206126e-05, + "loss": 0.2073, "step": 96470 }, { - "epoch": 0.86, - "learning_rate": 7.013332132240338e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.9324847318851935e-05, + "loss": 0.2004, "step": 96480 }, { - "epoch": 0.86, - "learning_rate": 7.008828033510495e-06, - "loss": 0.1843, + "epoch": 0.22, + "learning_rate": 3.9323728775642606e-05, + "loss": 0.21, "step": 96490 }, { - "epoch": 0.86, - "learning_rate": 7.00432393478065e-06, - "loss": 0.1828, + "epoch": 0.22, + "learning_rate": 3.9322610232433284e-05, + "loss": 0.2079, "step": 96500 }, { - "epoch": 0.86, - "learning_rate": 6.9998198360508066e-06, - "loss": 0.1809, + "epoch": 0.22, + "learning_rate": 3.9321491689223955e-05, + "loss": 0.2028, "step": 96510 }, { - "epoch": 0.86, - "learning_rate": 6.995315737320962e-06, - "loss": 0.1816, + "epoch": 0.22, + "learning_rate": 3.932037314601463e-05, + "loss": 0.2027, "step": 96520 }, { - "epoch": 0.86, - "learning_rate": 6.990811638591119e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.9319254602805304e-05, + "loss": 0.2053, "step": 96530 }, { - "epoch": 0.86, - "learning_rate": 6.986307539861274e-06, - "loss": 0.1818, + "epoch": 0.22, + "learning_rate": 3.931813605959598e-05, + "loss": 0.209, "step": 96540 }, { - "epoch": 0.86, - "learning_rate": 6.981803441131429e-06, - "loss": 0.1789, + "epoch": 0.22, + "learning_rate": 3.931701751638666e-05, + "loss": 0.2037, "step": 96550 }, { - "epoch": 0.86, - "learning_rate": 6.9772993424015856e-06, - "loss": 0.1806, + "epoch": 0.22, + "learning_rate": 3.931589897317733e-05, + "loss": 0.2018, "step": 96560 }, { - "epoch": 0.86, - "learning_rate": 6.972795243671741e-06, - "loss": 0.1796, + "epoch": 0.22, + "learning_rate": 3.9314780429968016e-05, + "loss": 0.2085, "step": 96570 }, { - "epoch": 0.86, - "learning_rate": 6.968291144941898e-06, - "loss": 0.1828, + "epoch": 0.22, + "learning_rate": 3.931366188675869e-05, + "loss": 0.2054, "step": 96580 }, { - "epoch": 0.86, - "learning_rate": 6.963787046212053e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.9312543343549365e-05, + "loss": 0.205, "step": 96590 }, { - "epoch": 0.86, - "learning_rate": 6.95928294748221e-06, - "loss": 0.1796, + "epoch": 0.22, + "learning_rate": 3.931142480034004e-05, + "loss": 0.2043, "step": 96600 }, { - "epoch": 0.86, - "learning_rate": 6.9547788487523645e-06, - "loss": 0.1811, + "epoch": 0.22, + "learning_rate": 3.9310306257130714e-05, + "loss": 0.2069, "step": 96610 }, { - "epoch": 0.86, - "learning_rate": 6.95027475002252e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.930918771392139e-05, + "loss": 0.2076, "step": 96620 }, { - "epoch": 0.86, - "learning_rate": 6.945770651292677e-06, - "loss": 0.1896, + "epoch": 0.22, + "learning_rate": 3.930806917071206e-05, + "loss": 0.2048, "step": 96630 }, { - "epoch": 0.86, - "learning_rate": 6.941266552562832e-06, - "loss": 0.1827, + "epoch": 0.22, + "learning_rate": 3.930695062750274e-05, + "loss": 0.2009, "step": 96640 }, { - "epoch": 0.86, - "learning_rate": 6.936762453832989e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.930583208429342e-05, + "loss": 0.2045, "step": 96650 }, { - "epoch": 0.86, - "learning_rate": 6.9322583551031435e-06, - "loss": 0.1812, + "epoch": 0.22, + "learning_rate": 3.930471354108409e-05, + "loss": 0.2098, "step": 96660 }, { - "epoch": 0.86, - "learning_rate": 6.9277542563733e-06, - "loss": 0.1847, + "epoch": 0.22, + "learning_rate": 3.930359499787477e-05, + "loss": 0.2011, "step": 96670 }, { - "epoch": 0.86, - "learning_rate": 6.923250157643456e-06, - "loss": 0.1781, + "epoch": 0.22, + "learning_rate": 3.9302476454665446e-05, + "loss": 0.2022, "step": 96680 }, { - "epoch": 0.86, - "learning_rate": 6.918746058913611e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.9301357911456124e-05, + "loss": 0.2079, "step": 96690 }, { - "epoch": 0.86, - "learning_rate": 6.914241960183768e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.93002393682468e-05, + "loss": 0.2076, "step": 96700 }, { - "epoch": 0.86, - "learning_rate": 6.9097378614539225e-06, - "loss": 0.1756, + "epoch": 0.22, + "learning_rate": 3.929912082503747e-05, + "loss": 0.2063, "step": 96710 }, { - "epoch": 0.86, - "learning_rate": 6.905233762724079e-06, - "loss": 0.1784, + "epoch": 0.22, + "learning_rate": 3.929800228182815e-05, + "loss": 0.2015, "step": 96720 }, { - "epoch": 0.86, - "learning_rate": 6.900729663994235e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.929688373861882e-05, + "loss": 0.2011, "step": 96730 }, { - "epoch": 0.86, - "learning_rate": 6.896225565264392e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.92957651954095e-05, + "loss": 0.2072, "step": 96740 }, { - "epoch": 0.86, - "learning_rate": 6.8917214665345466e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.929464665220018e-05, + "loss": 0.2088, "step": 96750 }, { - "epoch": 0.86, - "learning_rate": 6.887217367804702e-06, - "loss": 0.1786, + "epoch": 0.22, + "learning_rate": 3.929352810899085e-05, + "loss": 0.203, "step": 96760 }, { - "epoch": 0.86, - "learning_rate": 6.882713269074858e-06, - "loss": 0.1856, + "epoch": 0.22, + "learning_rate": 3.929240956578153e-05, + "loss": 0.2077, "step": 96770 }, { - "epoch": 0.86, - "learning_rate": 6.878209170345014e-06, - "loss": 0.1833, + "epoch": 0.22, + "learning_rate": 3.9291291022572205e-05, + "loss": 0.2032, "step": 96780 }, { - "epoch": 0.86, - "learning_rate": 6.873705071615171e-06, - "loss": 0.1787, + "epoch": 0.22, + "learning_rate": 3.929017247936288e-05, + "loss": 0.2025, "step": 96790 }, { - "epoch": 0.86, - "learning_rate": 6.8692009728853256e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.928905393615356e-05, + "loss": 0.2055, "step": 96800 }, { - "epoch": 0.86, - "learning_rate": 6.864696874155482e-06, - "loss": 0.1777, + "epoch": 0.22, + "learning_rate": 3.928793539294423e-05, + "loss": 0.2047, "step": 96810 }, { - "epoch": 0.86, - "learning_rate": 6.860192775425638e-06, - "loss": 0.1766, + "epoch": 0.22, + "learning_rate": 3.928681684973491e-05, + "loss": 0.1988, "step": 96820 }, { - "epoch": 0.86, - "learning_rate": 6.855688676695793e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.928569830652558e-05, + "loss": 0.2056, "step": 96830 }, { - "epoch": 0.86, - "learning_rate": 6.85118457796595e-06, - "loss": 0.1754, + "epoch": 0.22, + "learning_rate": 3.928457976331626e-05, + "loss": 0.199, "step": 96840 }, { - "epoch": 0.86, - "learning_rate": 6.8466804792361046e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.928346122010693e-05, + "loss": 0.2094, "step": 96850 }, { - "epoch": 0.86, - "learning_rate": 6.842176380506261e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.928234267689761e-05, + "loss": 0.2018, "step": 96860 }, { - "epoch": 0.86, - "learning_rate": 6.837672281776417e-06, - "loss": 0.1828, + "epoch": 0.22, + "learning_rate": 3.9281224133688286e-05, + "loss": 0.2024, "step": 96870 }, { - "epoch": 0.86, - "learning_rate": 6.833168183046574e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.9280105590478964e-05, + "loss": 0.2015, "step": 96880 }, { - "epoch": 0.87, - "learning_rate": 6.828664084316729e-06, - "loss": 0.1807, + "epoch": 0.22, + "learning_rate": 3.927898704726964e-05, + "loss": 0.203, "step": 96890 }, { - "epoch": 0.87, - "learning_rate": 6.8241599855868835e-06, - "loss": 0.1743, + "epoch": 0.22, + "learning_rate": 3.927786850406031e-05, + "loss": 0.2078, "step": 96900 }, { - "epoch": 0.87, - "learning_rate": 6.81965588685704e-06, - "loss": 0.1834, + "epoch": 0.22, + "learning_rate": 3.927674996085099e-05, + "loss": 0.2051, "step": 96910 }, { - "epoch": 0.87, - "learning_rate": 6.815151788127196e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.927563141764167e-05, + "loss": 0.197, "step": 96920 }, { - "epoch": 0.87, - "learning_rate": 6.810647689397353e-06, - "loss": 0.1918, + "epoch": 0.22, + "learning_rate": 3.927451287443234e-05, + "loss": 0.2009, "step": 96930 }, { - "epoch": 0.87, - "learning_rate": 6.806143590667508e-06, - "loss": 0.1759, + "epoch": 0.22, + "learning_rate": 3.927339433122302e-05, + "loss": 0.2073, "step": 96940 }, { - "epoch": 0.87, - "learning_rate": 6.801639491937664e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.927227578801369e-05, + "loss": 0.2012, "step": 96950 }, { - "epoch": 0.87, - "learning_rate": 6.797135393207819e-06, - "loss": 0.1773, + "epoch": 0.22, + "learning_rate": 3.927115724480437e-05, + "loss": 0.2049, "step": 96960 }, { - "epoch": 0.87, - "learning_rate": 6.792631294477975e-06, - "loss": 0.1851, + "epoch": 0.22, + "learning_rate": 3.9270038701595045e-05, + "loss": 0.2071, "step": 96970 }, { - "epoch": 0.87, - "learning_rate": 6.788127195748132e-06, - "loss": 0.1848, + "epoch": 0.22, + "learning_rate": 3.9268920158385716e-05, + "loss": 0.207, "step": 96980 }, { - "epoch": 0.87, - "learning_rate": 6.7836230970182866e-06, - "loss": 0.1761, + "epoch": 0.22, + "learning_rate": 3.92678016151764e-05, + "loss": 0.2002, "step": 96990 }, { - "epoch": 0.87, - "learning_rate": 6.779118998288443e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.926668307196707e-05, + "loss": 0.2036, "step": 97000 }, { - "epoch": 0.87, - "learning_rate": 6.774614899558598e-06, - "loss": 0.1831, + "epoch": 0.22, + "learning_rate": 3.926556452875775e-05, + "loss": 0.2051, "step": 97010 }, { - "epoch": 0.87, - "learning_rate": 6.770110800828755e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.926444598554843e-05, + "loss": 0.2024, "step": 97020 }, { - "epoch": 0.87, - "learning_rate": 6.765606702098911e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.92633274423391e-05, + "loss": 0.2043, "step": 97030 }, { - "epoch": 0.87, - "learning_rate": 6.7611026033690656e-06, - "loss": 0.1872, + "epoch": 0.22, + "learning_rate": 3.9262208899129777e-05, + "loss": 0.2052, "step": 97040 }, { - "epoch": 0.87, - "learning_rate": 6.756598504639222e-06, - "loss": 0.1808, + "epoch": 0.22, + "learning_rate": 3.926109035592045e-05, + "loss": 0.2027, "step": 97050 }, { - "epoch": 0.87, - "learning_rate": 6.752094405909377e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.9259971812711126e-05, + "loss": 0.1986, "step": 97060 }, { - "epoch": 0.87, - "learning_rate": 6.747590307179534e-06, - "loss": 0.182, + "epoch": 0.22, + "learning_rate": 3.9258853269501804e-05, + "loss": 0.2059, "step": 97070 }, { - "epoch": 0.87, - "learning_rate": 6.74308620844969e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.9257734726292475e-05, + "loss": 0.2, "step": 97080 }, { - "epoch": 0.87, - "learning_rate": 6.738582109719846e-06, - "loss": 0.1836, + "epoch": 0.22, + "learning_rate": 3.925661618308315e-05, + "loss": 0.2062, "step": 97090 }, { - "epoch": 0.87, - "learning_rate": 6.734078010990001e-06, - "loss": 0.1808, + "epoch": 0.22, + "learning_rate": 3.925549763987383e-05, + "loss": 0.2062, "step": 97100 }, { - "epoch": 0.87, - "learning_rate": 6.729573912260156e-06, - "loss": 0.1836, + "epoch": 0.22, + "learning_rate": 3.925437909666451e-05, + "loss": 0.1995, "step": 97110 }, { - "epoch": 0.87, - "learning_rate": 6.725069813530313e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.9253260553455186e-05, + "loss": 0.2048, "step": 97120 }, { - "epoch": 0.87, - "learning_rate": 6.720565714800469e-06, - "loss": 0.1816, + "epoch": 0.22, + "learning_rate": 3.925214201024586e-05, + "loss": 0.203, "step": 97130 }, { - "epoch": 0.87, - "learning_rate": 6.716061616070625e-06, - "loss": 0.1764, + "epoch": 0.22, + "learning_rate": 3.9251023467036536e-05, + "loss": 0.1999, "step": 97140 }, { - "epoch": 0.87, - "learning_rate": 6.71155751734078e-06, - "loss": 0.1851, + "epoch": 0.22, + "learning_rate": 3.924990492382721e-05, + "loss": 0.2001, "step": 97150 }, { - "epoch": 0.87, - "learning_rate": 6.707053418610937e-06, - "loss": 0.1846, + "epoch": 0.22, + "learning_rate": 3.9248786380617885e-05, + "loss": 0.2023, "step": 97160 }, { - "epoch": 0.87, - "learning_rate": 6.702549319881092e-06, - "loss": 0.1814, + "epoch": 0.22, + "learning_rate": 3.9247667837408556e-05, + "loss": 0.2003, "step": 97170 }, { - "epoch": 0.87, - "learning_rate": 6.698045221151248e-06, - "loss": 0.1813, + "epoch": 0.22, + "learning_rate": 3.9246549294199234e-05, + "loss": 0.2003, "step": 97180 }, { - "epoch": 0.87, - "learning_rate": 6.693541122421404e-06, - "loss": 0.1848, + "epoch": 0.22, + "learning_rate": 3.924543075098991e-05, + "loss": 0.2113, "step": 97190 }, { - "epoch": 0.87, - "learning_rate": 6.689037023691559e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.924431220778059e-05, + "loss": 0.2032, "step": 97200 }, { - "epoch": 0.87, - "learning_rate": 6.684532924961716e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.924319366457127e-05, + "loss": 0.206, "step": 97210 }, { - "epoch": 0.87, - "learning_rate": 6.680028826231871e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.924207512136194e-05, + "loss": 0.2042, "step": 97220 }, { - "epoch": 0.87, - "learning_rate": 6.675524727502027e-06, - "loss": 0.1824, + "epoch": 0.22, + "learning_rate": 3.9240956578152617e-05, + "loss": 0.2073, "step": 97230 }, { - "epoch": 0.87, - "learning_rate": 6.671020628772183e-06, - "loss": 0.1766, + "epoch": 0.22, + "learning_rate": 3.9239838034943294e-05, + "loss": 0.2072, "step": 97240 }, { - "epoch": 0.87, - "learning_rate": 6.666516530042338e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.9238719491733966e-05, + "loss": 0.2019, "step": 97250 }, { - "epoch": 0.87, - "learning_rate": 6.662012431312495e-06, - "loss": 0.183, + "epoch": 0.22, + "learning_rate": 3.9237600948524644e-05, + "loss": 0.2049, "step": 97260 }, { - "epoch": 0.87, - "learning_rate": 6.65750833258265e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.9236482405315315e-05, + "loss": 0.2024, "step": 97270 }, { - "epoch": 0.87, - "learning_rate": 6.653004233852806e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.923536386210599e-05, + "loss": 0.2024, "step": 97280 }, { - "epoch": 0.87, - "learning_rate": 6.648500135122962e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.923424531889667e-05, + "loss": 0.2024, "step": 97290 }, { - "epoch": 0.87, - "learning_rate": 6.643996036393119e-06, - "loss": 0.183, + "epoch": 0.22, + "learning_rate": 3.923312677568735e-05, + "loss": 0.2024, "step": 97300 }, { - "epoch": 0.87, - "learning_rate": 6.639491937663274e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.9232008232478026e-05, + "loss": 0.1985, "step": 97310 }, { - "epoch": 0.87, - "learning_rate": 6.634987838933429e-06, - "loss": 0.1771, + "epoch": 0.22, + "learning_rate": 3.92308896892687e-05, + "loss": 0.202, "step": 97320 }, { - "epoch": 0.87, - "learning_rate": 6.630483740203585e-06, - "loss": 0.1811, + "epoch": 0.22, + "learning_rate": 3.9229771146059376e-05, + "loss": 0.2044, "step": 97330 }, { - "epoch": 0.87, - "learning_rate": 6.625979641473741e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.9228652602850053e-05, + "loss": 0.2029, "step": 97340 }, { - "epoch": 0.87, - "learning_rate": 6.621475542743898e-06, - "loss": 0.1847, + "epoch": 0.22, + "learning_rate": 3.9227534059640725e-05, + "loss": 0.2017, "step": 97350 }, { - "epoch": 0.87, - "learning_rate": 6.616971444014053e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.92264155164314e-05, + "loss": 0.2095, "step": 97360 }, { - "epoch": 0.87, - "learning_rate": 6.6124673452842094e-06, - "loss": 0.1752, + "epoch": 0.22, + "learning_rate": 3.9225296973222074e-05, + "loss": 0.2089, "step": 97370 }, { - "epoch": 0.87, - "learning_rate": 6.607963246554364e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.922417843001275e-05, + "loss": 0.2019, "step": 97380 }, { - "epoch": 0.87, - "learning_rate": 6.60345914782452e-06, - "loss": 0.1787, + "epoch": 0.22, + "learning_rate": 3.922305988680343e-05, + "loss": 0.2035, "step": 97390 }, { - "epoch": 0.87, - "learning_rate": 6.598955049094677e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.922194134359411e-05, + "loss": 0.2023, "step": 97400 }, { - "epoch": 0.87, - "learning_rate": 6.594450950364832e-06, - "loss": 0.1875, + "epoch": 0.22, + "learning_rate": 3.9220822800384785e-05, + "loss": 0.1987, "step": 97410 }, { - "epoch": 0.87, - "learning_rate": 6.5899468516349884e-06, - "loss": 0.1736, + "epoch": 0.22, + "learning_rate": 3.9219704257175457e-05, + "loss": 0.2022, "step": 97420 }, { - "epoch": 0.87, - "learning_rate": 6.585442752905143e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.9218585713966134e-05, + "loss": 0.2036, "step": 97430 }, { - "epoch": 0.87, - "learning_rate": 6.5809386541753e-06, - "loss": 0.1796, + "epoch": 0.22, + "learning_rate": 3.921746717075681e-05, + "loss": 0.2057, "step": 97440 }, { - "epoch": 0.87, - "learning_rate": 6.576434555445456e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.9216348627547484e-05, + "loss": 0.2024, "step": 97450 }, { - "epoch": 0.87, - "learning_rate": 6.571930456715611e-06, - "loss": 0.1814, + "epoch": 0.22, + "learning_rate": 3.921523008433816e-05, + "loss": 0.2037, "step": 97460 }, { - "epoch": 0.87, - "learning_rate": 6.567426357985767e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.921411154112883e-05, + "loss": 0.2012, "step": 97470 }, { - "epoch": 0.87, - "learning_rate": 6.562922259255923e-06, - "loss": 0.1838, + "epoch": 0.22, + "learning_rate": 3.921299299791951e-05, + "loss": 0.2012, "step": 97480 }, { - "epoch": 0.87, - "learning_rate": 6.558418160526079e-06, - "loss": 0.1848, + "epoch": 0.22, + "learning_rate": 3.921187445471018e-05, + "loss": 0.2074, "step": 97490 }, { - "epoch": 0.87, - "learning_rate": 6.553914061796235e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.921075591150086e-05, + "loss": 0.2046, "step": 97500 }, { - "epoch": 0.87, - "learning_rate": 6.5494099630663915e-06, - "loss": 0.1838, + "epoch": 0.22, + "learning_rate": 3.920963736829154e-05, + "loss": 0.2067, "step": 97510 }, { - "epoch": 0.87, - "learning_rate": 6.544905864336546e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.9208518825082215e-05, + "loss": 0.2052, "step": 97520 }, { - "epoch": 0.87, - "learning_rate": 6.540401765606702e-06, - "loss": 0.1869, + "epoch": 0.22, + "learning_rate": 3.9207400281872893e-05, + "loss": 0.2021, "step": 97530 }, { - "epoch": 0.87, - "learning_rate": 6.535897666876859e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.9206281738663565e-05, + "loss": 0.2005, "step": 97540 }, { - "epoch": 0.87, - "learning_rate": 6.531393568147014e-06, - "loss": 0.1798, + "epoch": 0.22, + "learning_rate": 3.920516319545424e-05, + "loss": 0.2049, "step": 97550 }, { - "epoch": 0.87, - "learning_rate": 6.5268894694171705e-06, - "loss": 0.176, + "epoch": 0.22, + "learning_rate": 3.920404465224492e-05, + "loss": 0.2019, "step": 97560 }, { - "epoch": 0.87, - "learning_rate": 6.522385370687325e-06, - "loss": 0.1757, + "epoch": 0.22, + "learning_rate": 3.920292610903559e-05, + "loss": 0.2027, "step": 97570 }, { - "epoch": 0.87, - "learning_rate": 6.517881271957482e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.920180756582627e-05, + "loss": 0.2069, "step": 97580 }, { - "epoch": 0.87, - "learning_rate": 6.513377173227638e-06, - "loss": 0.1844, + "epoch": 0.22, + "learning_rate": 3.920068902261694e-05, + "loss": 0.1981, "step": 97590 }, { - "epoch": 0.87, - "learning_rate": 6.508873074497793e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.919957047940762e-05, + "loss": 0.2049, "step": 97600 }, { - "epoch": 0.87, - "learning_rate": 6.5043689757679494e-06, - "loss": 0.18, + "epoch": 0.22, + "learning_rate": 3.9198451936198296e-05, + "loss": 0.2021, "step": 97610 }, { - "epoch": 0.87, - "learning_rate": 6.499864877038104e-06, - "loss": 0.1825, + "epoch": 0.22, + "learning_rate": 3.9197333392988974e-05, + "loss": 0.2021, "step": 97620 }, { - "epoch": 0.87, - "learning_rate": 6.495360778308261e-06, - "loss": 0.1785, + "epoch": 0.22, + "learning_rate": 3.919621484977965e-05, + "loss": 0.2114, "step": 97630 }, { - "epoch": 0.87, - "learning_rate": 6.490856679578417e-06, - "loss": 0.1807, + "epoch": 0.22, + "learning_rate": 3.9195096306570324e-05, + "loss": 0.2024, "step": 97640 }, { - "epoch": 0.87, - "learning_rate": 6.4863525808485735e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.9193977763361e-05, + "loss": 0.2008, "step": 97650 }, { - "epoch": 0.87, - "learning_rate": 6.4818484821187284e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.919285922015168e-05, + "loss": 0.2025, "step": 97660 }, { - "epoch": 0.87, - "learning_rate": 6.477344383388883e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.919174067694235e-05, + "loss": 0.2151, "step": 97670 }, { - "epoch": 0.87, - "learning_rate": 6.47284028465904e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.919062213373303e-05, + "loss": 0.2092, "step": 97680 }, { - "epoch": 0.87, - "learning_rate": 6.468336185929196e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.918961544484464e-05, + "loss": 0.2069, "step": 97690 }, { - "epoch": 0.87, - "learning_rate": 6.4638320871993525e-06, - "loss": 0.1785, + "epoch": 0.22, + "learning_rate": 3.9188496901635315e-05, + "loss": 0.2032, "step": 97700 }, { - "epoch": 0.87, - "learning_rate": 6.459327988469507e-06, - "loss": 0.1856, + "epoch": 0.22, + "learning_rate": 3.9187378358425986e-05, + "loss": 0.2019, "step": 97710 }, { - "epoch": 0.87, - "learning_rate": 6.454823889739664e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.9186259815216664e-05, + "loss": 0.2055, "step": 97720 }, { - "epoch": 0.87, - "learning_rate": 6.450319791009819e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.918514127200734e-05, + "loss": 0.2025, "step": 97730 }, { - "epoch": 0.87, - "learning_rate": 6.445815692279975e-06, - "loss": 0.184, + "epoch": 0.22, + "learning_rate": 3.918402272879801e-05, + "loss": 0.2093, "step": 97740 }, { - "epoch": 0.87, - "learning_rate": 6.4413115935501315e-06, - "loss": 0.1783, + "epoch": 0.22, + "learning_rate": 3.918290418558869e-05, + "loss": 0.2032, "step": 97750 }, { - "epoch": 0.87, - "learning_rate": 6.436807494820286e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.918178564237936e-05, + "loss": 0.2045, "step": 97760 }, { - "epoch": 0.87, - "learning_rate": 6.432303396090443e-06, - "loss": 0.1711, + "epoch": 0.22, + "learning_rate": 3.918066709917004e-05, + "loss": 0.2033, "step": 97770 }, { - "epoch": 0.87, - "learning_rate": 6.427799297360598e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.917954855596072e-05, + "loss": 0.2033, "step": 97780 }, { - "epoch": 0.87, - "learning_rate": 6.423295198630755e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.9178430012751396e-05, + "loss": 0.2015, "step": 97790 }, { - "epoch": 0.87, - "learning_rate": 6.4187910999009105e-06, - "loss": 0.1798, + "epoch": 0.22, + "learning_rate": 3.9177311469542074e-05, + "loss": 0.2031, "step": 97800 }, { - "epoch": 0.87, - "learning_rate": 6.414287001171065e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.9176192926332745e-05, + "loss": 0.2075, "step": 97810 }, { - "epoch": 0.87, - "learning_rate": 6.409782902441222e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.917507438312342e-05, + "loss": 0.2001, "step": 97820 }, { - "epoch": 0.87, - "learning_rate": 6.405278803711377e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.91739558399141e-05, + "loss": 0.2019, "step": 97830 }, { - "epoch": 0.87, - "learning_rate": 6.400774704981534e-06, - "loss": 0.1766, + "epoch": 0.22, + "learning_rate": 3.917283729670477e-05, + "loss": 0.2047, "step": 97840 }, { - "epoch": 0.87, - "learning_rate": 6.3962706062516894e-06, - "loss": 0.1886, + "epoch": 0.22, + "learning_rate": 3.917171875349545e-05, + "loss": 0.2032, "step": 97850 }, { - "epoch": 0.87, - "learning_rate": 6.391766507521846e-06, - "loss": 0.1765, + "epoch": 0.22, + "learning_rate": 3.917060021028612e-05, + "loss": 0.203, "step": 97860 }, { - "epoch": 0.87, - "learning_rate": 6.387262408792001e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.91694816670768e-05, + "loss": 0.2051, "step": 97870 }, { - "epoch": 0.87, - "learning_rate": 6.382758310062156e-06, - "loss": 0.1861, + "epoch": 0.22, + "learning_rate": 3.916836312386748e-05, + "loss": 0.2043, "step": 97880 }, { - "epoch": 0.87, - "learning_rate": 6.378254211332313e-06, - "loss": 0.1764, + "epoch": 0.22, + "learning_rate": 3.9167244580658155e-05, + "loss": 0.2022, "step": 97890 }, { - "epoch": 0.87, - "learning_rate": 6.3737501126024684e-06, - "loss": 0.1826, + "epoch": 0.22, + "learning_rate": 3.916612603744883e-05, + "loss": 0.2033, "step": 97900 }, { - "epoch": 0.87, - "learning_rate": 6.369246013872625e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.9165007494239504e-05, + "loss": 0.2074, "step": 97910 }, { - "epoch": 0.87, - "learning_rate": 6.36474191514278e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.916388895103018e-05, + "loss": 0.2091, "step": 97920 }, { - "epoch": 0.87, - "learning_rate": 6.360237816412937e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.916277040782085e-05, + "loss": 0.2141, "step": 97930 }, { - "epoch": 0.87, - "learning_rate": 6.355733717683092e-06, - "loss": 0.1809, + "epoch": 0.22, + "learning_rate": 3.916165186461153e-05, + "loss": 0.2077, "step": 97940 }, { - "epoch": 0.87, - "learning_rate": 6.3512296189532474e-06, - "loss": 0.1806, + "epoch": 0.22, + "learning_rate": 3.916053332140221e-05, + "loss": 0.2034, "step": 97950 }, { - "epoch": 0.87, - "learning_rate": 6.346725520223404e-06, - "loss": 0.1848, + "epoch": 0.22, + "learning_rate": 3.915941477819288e-05, + "loss": 0.2105, "step": 97960 }, { - "epoch": 0.87, - "learning_rate": 6.342221421493559e-06, - "loss": 0.184, + "epoch": 0.22, + "learning_rate": 3.915829623498356e-05, + "loss": 0.2014, "step": 97970 }, { - "epoch": 0.87, - "learning_rate": 6.337717322763716e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.9157177691774236e-05, + "loss": 0.2065, "step": 97980 }, { - "epoch": 0.87, - "learning_rate": 6.333213224033871e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.9156059148564914e-05, + "loss": 0.2091, "step": 97990 }, { - "epoch": 0.87, - "learning_rate": 6.328709125304027e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.915494060535559e-05, + "loss": 0.2014, "step": 98000 }, { - "epoch": 0.88, - "learning_rate": 6.324205026574183e-06, - "loss": 0.1822, - "step": 98010 + "epoch": 0.22, + "learning_rate": 3.915382206214626e-05, + "loss": 0.2049, + "step": 98010 }, { - "epoch": 0.88, - "learning_rate": 6.319700927844338e-06, - "loss": 0.1784, + "epoch": 0.22, + "learning_rate": 3.915270351893694e-05, + "loss": 0.208, "step": 98020 }, { - "epoch": 0.88, - "learning_rate": 6.315196829114495e-06, - "loss": 0.175, + "epoch": 0.22, + "learning_rate": 3.915158497572761e-05, + "loss": 0.2, "step": 98030 }, { - "epoch": 0.88, - "learning_rate": 6.31069273038465e-06, - "loss": 0.1731, + "epoch": 0.22, + "learning_rate": 3.915046643251829e-05, + "loss": 0.2029, "step": 98040 }, { - "epoch": 0.88, - "learning_rate": 6.306188631654806e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.914934788930897e-05, + "loss": 0.1977, "step": 98050 }, { - "epoch": 0.88, - "learning_rate": 6.301684532924962e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.914822934609964e-05, + "loss": 0.1994, "step": 98060 }, { - "epoch": 0.88, - "learning_rate": 6.297180434195119e-06, - "loss": 0.184, + "epoch": 0.22, + "learning_rate": 3.914711080289032e-05, + "loss": 0.2014, "step": 98070 }, { - "epoch": 0.88, - "learning_rate": 6.292676335465274e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.914599225968099e-05, + "loss": 0.1993, "step": 98080 }, { - "epoch": 0.88, - "learning_rate": 6.288172236735429e-06, - "loss": 0.1827, + "epoch": 0.22, + "learning_rate": 3.9144873716471666e-05, + "loss": 0.2046, "step": 98090 }, { - "epoch": 0.88, - "learning_rate": 6.283668138005585e-06, - "loss": 0.1739, + "epoch": 0.22, + "learning_rate": 3.9143755173262344e-05, + "loss": 0.2019, "step": 98100 }, { - "epoch": 0.88, - "learning_rate": 6.279164039275741e-06, - "loss": 0.1771, + "epoch": 0.22, + "learning_rate": 3.914263663005302e-05, + "loss": 0.2052, "step": 98110 }, { - "epoch": 0.88, - "learning_rate": 6.274659940545898e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.91415180868437e-05, + "loss": 0.2023, "step": 98120 }, { - "epoch": 0.88, - "learning_rate": 6.270155841816053e-06, - "loss": 0.1872, + "epoch": 0.22, + "learning_rate": 3.914039954363437e-05, + "loss": 0.2061, "step": 98130 }, { - "epoch": 0.88, - "learning_rate": 6.265651743086209e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.913928100042505e-05, + "loss": 0.2058, "step": 98140 }, { - "epoch": 0.88, - "learning_rate": 6.261147644356364e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.913816245721573e-05, + "loss": 0.2081, "step": 98150 }, { - "epoch": 0.88, - "learning_rate": 6.25664354562652e-06, - "loss": 0.1897, + "epoch": 0.22, + "learning_rate": 3.91370439140064e-05, + "loss": 0.1995, "step": 98160 }, { - "epoch": 0.88, - "learning_rate": 6.252139446896677e-06, - "loss": 0.1862, + "epoch": 0.22, + "learning_rate": 3.9135925370797076e-05, + "loss": 0.2082, "step": 98170 }, { - "epoch": 0.88, - "learning_rate": 6.247635348166832e-06, - "loss": 0.1877, + "epoch": 0.22, + "learning_rate": 3.913480682758775e-05, + "loss": 0.2062, "step": 98180 }, { - "epoch": 0.88, - "learning_rate": 6.2431312494369874e-06, - "loss": 0.1791, + "epoch": 0.22, + "learning_rate": 3.9133688284378425e-05, + "loss": 0.2014, "step": 98190 }, { - "epoch": 0.88, - "learning_rate": 6.238627150707144e-06, - "loss": 0.182, + "epoch": 0.22, + "learning_rate": 3.91325697411691e-05, + "loss": 0.2006, "step": 98200 }, { - "epoch": 0.88, - "learning_rate": 6.2341230519773e-06, - "loss": 0.1842, + "epoch": 0.22, + "learning_rate": 3.913145119795978e-05, + "loss": 0.2002, "step": 98210 }, { - "epoch": 0.88, - "learning_rate": 6.229618953247456e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.913033265475046e-05, + "loss": 0.1991, "step": 98220 }, { - "epoch": 0.88, - "learning_rate": 6.2251148545176115e-06, - "loss": 0.182, + "epoch": 0.22, + "learning_rate": 3.912921411154113e-05, + "loss": 0.2067, "step": 98230 }, { - "epoch": 0.88, - "learning_rate": 6.220610755787767e-06, - "loss": 0.1777, + "epoch": 0.22, + "learning_rate": 3.912809556833181e-05, + "loss": 0.2023, "step": 98240 }, { - "epoch": 0.88, - "learning_rate": 6.216106657057923e-06, - "loss": 0.1818, + "epoch": 0.22, + "learning_rate": 3.912697702512248e-05, + "loss": 0.2041, "step": 98250 }, { - "epoch": 0.88, - "learning_rate": 6.211602558328079e-06, - "loss": 0.1791, + "epoch": 0.22, + "learning_rate": 3.912585848191316e-05, + "loss": 0.2016, "step": 98260 }, { - "epoch": 0.88, - "learning_rate": 6.207098459598235e-06, - "loss": 0.1841, + "epoch": 0.22, + "learning_rate": 3.9124739938703835e-05, + "loss": 0.2004, "step": 98270 }, { - "epoch": 0.88, - "learning_rate": 6.2025943608683905e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.9123621395494506e-05, + "loss": 0.199, "step": 98280 }, { - "epoch": 0.88, - "learning_rate": 6.198090262138546e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.9122502852285184e-05, + "loss": 0.2023, "step": 98290 }, { - "epoch": 0.88, - "learning_rate": 6.193586163408702e-06, - "loss": 0.1765, + "epoch": 0.22, + "learning_rate": 3.912138430907586e-05, + "loss": 0.206, "step": 98300 }, { - "epoch": 0.88, - "learning_rate": 6.189082064678859e-06, - "loss": 0.1742, + "epoch": 0.22, + "learning_rate": 3.912026576586654e-05, + "loss": 0.2072, "step": 98310 }, { - "epoch": 0.88, - "learning_rate": 6.184577965949014e-06, - "loss": 0.1836, + "epoch": 0.22, + "learning_rate": 3.911914722265722e-05, + "loss": 0.2009, "step": 98320 }, { - "epoch": 0.88, - "learning_rate": 6.1800738672191694e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.911802867944789e-05, + "loss": 0.2066, "step": 98330 }, { - "epoch": 0.88, - "learning_rate": 6.175569768489325e-06, - "loss": 0.1809, + "epoch": 0.22, + "learning_rate": 3.911691013623857e-05, + "loss": 0.2044, "step": 98340 }, { - "epoch": 0.88, - "learning_rate": 6.171065669759481e-06, - "loss": 0.1827, + "epoch": 0.22, + "learning_rate": 3.911579159302924e-05, + "loss": 0.2057, "step": 98350 }, { - "epoch": 0.88, - "learning_rate": 6.166561571029638e-06, - "loss": 0.1763, + "epoch": 0.22, + "learning_rate": 3.9114673049819916e-05, + "loss": 0.2067, "step": 98360 }, { - "epoch": 0.88, - "learning_rate": 6.1620574722997935e-06, - "loss": 0.1788, + "epoch": 0.22, + "learning_rate": 3.9113554506610594e-05, + "loss": 0.2006, "step": 98370 }, { - "epoch": 0.88, - "learning_rate": 6.157553373569949e-06, - "loss": 0.1831, + "epoch": 0.22, + "learning_rate": 3.9112435963401265e-05, + "loss": 0.2036, "step": 98380 }, { - "epoch": 0.88, - "learning_rate": 6.153049274840104e-06, - "loss": 0.1852, + "epoch": 0.22, + "learning_rate": 3.911131742019194e-05, + "loss": 0.2032, "step": 98390 }, { - "epoch": 0.88, - "learning_rate": 6.14854517611026e-06, - "loss": 0.1729, + "epoch": 0.22, + "learning_rate": 3.911019887698262e-05, + "loss": 0.2017, "step": 98400 }, { - "epoch": 0.88, - "learning_rate": 6.144041077380417e-06, - "loss": 0.1825, + "epoch": 0.22, + "learning_rate": 3.91090803337733e-05, + "loss": 0.2035, "step": 98410 }, { - "epoch": 0.88, - "learning_rate": 6.1395369786505725e-06, - "loss": 0.1798, + "epoch": 0.22, + "learning_rate": 3.910796179056398e-05, + "loss": 0.2052, "step": 98420 }, { - "epoch": 0.88, - "learning_rate": 6.135032879920728e-06, - "loss": 0.1755, + "epoch": 0.22, + "learning_rate": 3.910684324735465e-05, + "loss": 0.21, "step": 98430 }, { - "epoch": 0.88, - "learning_rate": 6.130528781190884e-06, - "loss": 0.1844, + "epoch": 0.22, + "learning_rate": 3.9105724704145326e-05, + "loss": 0.2074, "step": 98440 }, { - "epoch": 0.88, - "learning_rate": 6.12602468246104e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.9104606160936e-05, + "loss": 0.2027, "step": 98450 }, { - "epoch": 0.88, - "learning_rate": 6.121520583731196e-06, - "loss": 0.1864, + "epoch": 0.22, + "learning_rate": 3.9103487617726675e-05, + "loss": 0.2042, "step": 98460 }, { - "epoch": 0.88, - "learning_rate": 6.1170164850013515e-06, - "loss": 0.1849, + "epoch": 0.22, + "learning_rate": 3.910236907451735e-05, + "loss": 0.2061, "step": 98470 }, { - "epoch": 0.88, - "learning_rate": 6.112512386271507e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.9101250531308024e-05, + "loss": 0.2126, "step": 98480 }, { - "epoch": 0.88, - "learning_rate": 6.108008287541663e-06, - "loss": 0.1858, + "epoch": 0.22, + "learning_rate": 3.91001319880987e-05, + "loss": 0.2066, "step": 98490 }, { - "epoch": 0.88, - "learning_rate": 6.103504188811819e-06, - "loss": 0.185, + "epoch": 0.22, + "learning_rate": 3.909901344488937e-05, + "loss": 0.2086, "step": 98500 }, { - "epoch": 0.88, - "learning_rate": 6.099000090081975e-06, - "loss": 0.1807, + "epoch": 0.22, + "learning_rate": 3.909789490168005e-05, + "loss": 0.2036, "step": 98510 }, { - "epoch": 0.88, - "learning_rate": 6.094495991352131e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.909677635847073e-05, + "loss": 0.2062, "step": 98520 }, { - "epoch": 0.88, - "learning_rate": 6.089991892622286e-06, - "loss": 0.1878, + "epoch": 0.22, + "learning_rate": 3.909565781526141e-05, + "loss": 0.1994, "step": 98530 }, { - "epoch": 0.88, - "learning_rate": 6.085487793892442e-06, - "loss": 0.1748, + "epoch": 0.22, + "learning_rate": 3.9094539272052085e-05, + "loss": 0.1999, "step": 98540 }, { - "epoch": 0.88, - "learning_rate": 6.080983695162598e-06, - "loss": 0.184, + "epoch": 0.22, + "learning_rate": 3.9093420728842756e-05, + "loss": 0.204, "step": 98550 }, { - "epoch": 0.88, - "learning_rate": 6.0764795964327545e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.9092302185633434e-05, + "loss": 0.1982, "step": 98560 }, { - "epoch": 0.88, - "learning_rate": 6.07197549770291e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.9091183642424105e-05, + "loss": 0.2022, "step": 98570 }, { - "epoch": 0.88, - "learning_rate": 6.067471398973066e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.909006509921478e-05, + "loss": 0.2068, "step": 98580 }, { - "epoch": 0.88, - "learning_rate": 6.063417710116206e-06, - "loss": 0.1784, + "epoch": 0.22, + "learning_rate": 3.908894655600546e-05, + "loss": 0.1955, "step": 98590 }, { - "epoch": 0.88, - "learning_rate": 6.0589136113863614e-06, - "loss": 0.1814, + "epoch": 0.22, + "learning_rate": 3.908782801279613e-05, + "loss": 0.2054, "step": 98600 }, { - "epoch": 0.88, - "learning_rate": 6.054409512656518e-06, - "loss": 0.1798, + "epoch": 0.22, + "learning_rate": 3.908670946958681e-05, + "loss": 0.201, "step": 98610 }, { - "epoch": 0.88, - "learning_rate": 6.049905413926674e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.908559092637749e-05, + "loss": 0.1984, "step": 98620 }, { - "epoch": 0.88, - "learning_rate": 6.04540131519683e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.9084472383168166e-05, + "loss": 0.2012, "step": 98630 }, { - "epoch": 0.88, - "learning_rate": 6.0408972164669855e-06, - "loss": 0.183, + "epoch": 0.22, + "learning_rate": 3.9083353839958844e-05, + "loss": 0.2076, "step": 98640 }, { - "epoch": 0.88, - "learning_rate": 6.03639311773714e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.9082235296749515e-05, + "loss": 0.2068, "step": 98650 }, { - "epoch": 0.88, - "learning_rate": 6.031889019007297e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.908111675354019e-05, + "loss": 0.2045, "step": 98660 }, { - "epoch": 0.88, - "learning_rate": 6.027384920277453e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.9079998210330864e-05, + "loss": 0.2032, "step": 98670 }, { - "epoch": 0.88, - "learning_rate": 6.022880821547609e-06, - "loss": 0.1843, + "epoch": 0.22, + "learning_rate": 3.907887966712154e-05, + "loss": 0.2075, "step": 98680 }, { - "epoch": 0.88, - "learning_rate": 6.0183767228177645e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.907776112391222e-05, + "loss": 0.2052, "step": 98690 }, { - "epoch": 0.88, - "learning_rate": 6.01387262408792e-06, - "loss": 0.1738, + "epoch": 0.22, + "learning_rate": 3.907664258070289e-05, + "loss": 0.2012, "step": 98700 }, { - "epoch": 0.88, - "learning_rate": 6.009368525358076e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.907552403749357e-05, + "loss": 0.2032, "step": 98710 }, { - "epoch": 0.88, - "learning_rate": 6.004864426628232e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.907440549428425e-05, + "loss": 0.2019, "step": 98720 }, { - "epoch": 0.88, - "learning_rate": 6.000360327898388e-06, - "loss": 0.1787, + "epoch": 0.22, + "learning_rate": 3.9073286951074925e-05, + "loss": 0.1986, "step": 98730 }, { - "epoch": 0.88, - "learning_rate": 5.9958562291685435e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.90721684078656e-05, + "loss": 0.204, "step": 98740 }, { - "epoch": 0.88, - "learning_rate": 5.991352130438699e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.9071049864656274e-05, + "loss": 0.2077, "step": 98750 }, { - "epoch": 0.88, - "learning_rate": 5.986848031708855e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.906993132144695e-05, + "loss": 0.2017, "step": 98760 }, { - "epoch": 0.88, - "learning_rate": 5.982343932979012e-06, - "loss": 0.1829, + "epoch": 0.22, + "learning_rate": 3.906881277823762e-05, + "loss": 0.2032, "step": 98770 }, { - "epoch": 0.88, - "learning_rate": 5.9778398342491675e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.90676942350283e-05, + "loss": 0.202, "step": 98780 }, { - "epoch": 0.88, - "learning_rate": 5.9733357355193224e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.906657569181898e-05, + "loss": 0.2031, "step": 98790 }, { - "epoch": 0.88, - "learning_rate": 5.968831636789478e-06, - "loss": 0.1701, + "epoch": 0.22, + "learning_rate": 3.906545714860965e-05, + "loss": 0.2052, "step": 98800 }, { - "epoch": 0.88, - "learning_rate": 5.964327538059634e-06, - "loss": 0.1814, + "epoch": 0.22, + "learning_rate": 3.906433860540033e-05, + "loss": 0.2007, "step": 98810 }, { - "epoch": 0.88, - "learning_rate": 5.959823439329791e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.9063220062191006e-05, + "loss": 0.1992, "step": 98820 }, { - "epoch": 0.88, - "learning_rate": 5.9553193405999465e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.9062101518981684e-05, + "loss": 0.2087, "step": 98830 }, { - "epoch": 0.88, - "learning_rate": 5.950815241870102e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.9060982975772355e-05, + "loss": 0.2027, "step": 98840 }, { - "epoch": 0.88, - "learning_rate": 5.946311143140258e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.905986443256303e-05, + "loss": 0.2069, "step": 98850 }, { - "epoch": 0.88, - "learning_rate": 5.941807044410414e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.905874588935371e-05, + "loss": 0.1965, "step": 98860 }, { - "epoch": 0.88, - "learning_rate": 5.93730294568057e-06, - "loss": 0.1854, + "epoch": 0.22, + "learning_rate": 3.905762734614438e-05, + "loss": 0.2003, "step": 98870 }, { - "epoch": 0.88, - "learning_rate": 5.9327988469507255e-06, - "loss": 0.1847, + "epoch": 0.22, + "learning_rate": 3.905650880293506e-05, + "loss": 0.2053, "step": 98880 }, { - "epoch": 0.88, - "learning_rate": 5.928294748220881e-06, - "loss": 0.1783, + "epoch": 0.22, + "learning_rate": 3.905539025972573e-05, + "loss": 0.2043, "step": 98890 }, { - "epoch": 0.88, - "learning_rate": 5.923790649491037e-06, - "loss": 0.1825, + "epoch": 0.22, + "learning_rate": 3.905427171651641e-05, + "loss": 0.201, "step": 98900 }, { - "epoch": 0.88, - "learning_rate": 5.919286550761193e-06, - "loss": 0.174, + "epoch": 0.22, + "learning_rate": 3.905315317330709e-05, + "loss": 0.2041, "step": 98910 }, { - "epoch": 0.88, - "learning_rate": 5.9147824520313495e-06, - "loss": 0.1768, + "epoch": 0.22, + "learning_rate": 3.905203463009776e-05, + "loss": 0.2037, "step": 98920 }, { - "epoch": 0.88, - "learning_rate": 5.9102783533015045e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.905091608688844e-05, + "loss": 0.2051, "step": 98930 }, { - "epoch": 0.88, - "learning_rate": 5.90577425457166e-06, - "loss": 0.1802, + "epoch": 0.22, + "learning_rate": 3.9049797543679114e-05, + "loss": 0.1999, "step": 98940 }, { - "epoch": 0.88, - "learning_rate": 5.901270155841816e-06, - "loss": 0.1802, + "epoch": 0.22, + "learning_rate": 3.904867900046979e-05, + "loss": 0.2059, "step": 98950 }, { - "epoch": 0.88, - "learning_rate": 5.896766057111972e-06, - "loss": 0.1813, + "epoch": 0.22, + "learning_rate": 3.904756045726047e-05, + "loss": 0.2023, "step": 98960 }, { - "epoch": 0.88, - "learning_rate": 5.8922619583821285e-06, - "loss": 0.1836, + "epoch": 0.22, + "learning_rate": 3.904644191405114e-05, + "loss": 0.2065, "step": 98970 }, { - "epoch": 0.88, - "learning_rate": 5.887757859652284e-06, - "loss": 0.1839, + "epoch": 0.22, + "learning_rate": 3.904532337084182e-05, + "loss": 0.206, "step": 98980 }, { - "epoch": 0.88, - "learning_rate": 5.88325376092244e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.904420482763249e-05, + "loss": 0.2031, "step": 98990 }, { - "epoch": 0.88, - "learning_rate": 5.878749662192595e-06, - "loss": 0.1784, + "epoch": 0.22, + "learning_rate": 3.904308628442317e-05, + "loss": 0.2014, "step": 99000 }, { - "epoch": 0.88, - "learning_rate": 5.874245563462751e-06, - "loss": 0.1753, + "epoch": 0.22, + "learning_rate": 3.9041967741213846e-05, + "loss": 0.2041, "step": 99010 }, { - "epoch": 0.88, - "learning_rate": 5.8697414647329075e-06, - "loss": 0.1846, + "epoch": 0.22, + "learning_rate": 3.904084919800452e-05, + "loss": 0.1987, "step": 99020 }, { - "epoch": 0.88, - "learning_rate": 5.865237366003063e-06, - "loss": 0.1719, + "epoch": 0.22, + "learning_rate": 3.9039730654795195e-05, + "loss": 0.2042, "step": 99030 }, { - "epoch": 0.88, - "learning_rate": 5.860733267273219e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.903861211158587e-05, + "loss": 0.2019, "step": 99040 }, { - "epoch": 0.88, - "learning_rate": 5.856229168543375e-06, - "loss": 0.1845, + "epoch": 0.22, + "learning_rate": 3.903749356837655e-05, + "loss": 0.2011, "step": 99050 }, { - "epoch": 0.88, - "learning_rate": 5.851725069813531e-06, - "loss": 0.1798, + "epoch": 0.22, + "learning_rate": 3.903637502516723e-05, + "loss": 0.2005, "step": 99060 }, { - "epoch": 0.88, - "learning_rate": 5.8472209710836865e-06, - "loss": 0.1747, + "epoch": 0.22, + "learning_rate": 3.90352564819579e-05, + "loss": 0.2042, "step": 99070 }, { - "epoch": 0.88, - "learning_rate": 5.842716872353842e-06, - "loss": 0.1762, + "epoch": 0.22, + "learning_rate": 3.903413793874858e-05, + "loss": 0.1984, "step": 99080 }, { - "epoch": 0.88, - "learning_rate": 5.838212773623998e-06, - "loss": 0.1763, + "epoch": 0.22, + "learning_rate": 3.903301939553925e-05, + "loss": 0.2001, "step": 99090 }, { - "epoch": 0.88, - "learning_rate": 5.833708674894154e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.903190085232993e-05, + "loss": 0.2065, "step": 99100 }, { - "epoch": 0.88, - "learning_rate": 5.82920457616431e-06, - "loss": 0.1743, + "epoch": 0.22, + "learning_rate": 3.9030782309120605e-05, + "loss": 0.204, "step": 99110 }, { - "epoch": 0.88, - "learning_rate": 5.8247004774344655e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.9029663765911276e-05, + "loss": 0.2002, "step": 99120 }, { - "epoch": 0.89, - "learning_rate": 5.820196378704622e-06, - "loss": 0.1813, + "epoch": 0.22, + "learning_rate": 3.9028545222701954e-05, + "loss": 0.2081, "step": 99130 }, { - "epoch": 0.89, - "learning_rate": 5.815692279974777e-06, - "loss": 0.1844, + "epoch": 0.22, + "learning_rate": 3.902742667949263e-05, + "loss": 0.2074, "step": 99140 }, { - "epoch": 0.89, - "learning_rate": 5.811188181244933e-06, - "loss": 0.1847, + "epoch": 0.22, + "learning_rate": 3.902630813628331e-05, + "loss": 0.2026, "step": 99150 }, { - "epoch": 0.89, - "learning_rate": 5.806684082515089e-06, - "loss": 0.185, + "epoch": 0.22, + "learning_rate": 3.902518959307398e-05, + "loss": 0.2027, "step": 99160 }, { - "epoch": 0.89, - "learning_rate": 5.8021799837852445e-06, - "loss": 0.1847, + "epoch": 0.22, + "learning_rate": 3.902407104986466e-05, + "loss": 0.2031, "step": 99170 }, { - "epoch": 0.89, - "learning_rate": 5.797675885055401e-06, - "loss": 0.1772, + "epoch": 0.22, + "learning_rate": 3.902295250665534e-05, + "loss": 0.2007, "step": 99180 }, { - "epoch": 0.89, - "learning_rate": 5.793171786325557e-06, - "loss": 0.1785, + "epoch": 0.22, + "learning_rate": 3.902183396344601e-05, + "loss": 0.1999, "step": 99190 }, { - "epoch": 0.89, - "learning_rate": 5.788667687595713e-06, - "loss": 0.1739, + "epoch": 0.22, + "learning_rate": 3.9020715420236686e-05, + "loss": 0.2006, "step": 99200 }, { - "epoch": 0.89, - "learning_rate": 5.784163588865868e-06, - "loss": 0.1799, + "epoch": 0.22, + "learning_rate": 3.901959687702736e-05, + "loss": 0.205, "step": 99210 }, { - "epoch": 0.89, - "learning_rate": 5.779659490136024e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.9018478333818035e-05, + "loss": 0.2002, "step": 99220 }, { - "epoch": 0.89, - "learning_rate": 5.77515539140618e-06, - "loss": 0.1815, + "epoch": 0.22, + "learning_rate": 3.901735979060871e-05, + "loss": 0.2025, "step": 99230 }, { - "epoch": 0.89, - "learning_rate": 5.770651292676336e-06, - "loss": 0.1824, + "epoch": 0.22, + "learning_rate": 3.901624124739939e-05, + "loss": 0.2019, "step": 99240 }, { - "epoch": 0.89, - "learning_rate": 5.766147193946492e-06, - "loss": 0.174, + "epoch": 0.22, + "learning_rate": 3.901512270419007e-05, + "loss": 0.1982, "step": 99250 }, { - "epoch": 0.89, - "learning_rate": 5.7616430952166475e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.901400416098074e-05, + "loss": 0.2008, "step": 99260 }, { - "epoch": 0.89, - "learning_rate": 5.757138996486803e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.901288561777142e-05, + "loss": 0.203, "step": 99270 }, { - "epoch": 0.89, - "learning_rate": 5.752634897756959e-06, - "loss": 0.1841, + "epoch": 0.22, + "learning_rate": 3.9011767074562096e-05, + "loss": 0.2061, "step": 99280 }, { - "epoch": 0.89, - "learning_rate": 5.748130799027115e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.901064853135277e-05, + "loss": 0.1989, "step": 99290 }, { - "epoch": 0.89, - "learning_rate": 5.743626700297271e-06, - "loss": 0.1804, + "epoch": 0.22, + "learning_rate": 3.9009529988143445e-05, + "loss": 0.2021, "step": 99300 }, { - "epoch": 0.89, - "learning_rate": 5.7391226015674265e-06, - "loss": 0.1762, + "epoch": 0.22, + "learning_rate": 3.9008411444934116e-05, + "loss": 0.2026, "step": 99310 }, { - "epoch": 0.89, - "learning_rate": 5.734618502837582e-06, - "loss": 0.1828, + "epoch": 0.22, + "learning_rate": 3.9007292901724794e-05, + "loss": 0.2019, "step": 99320 }, { - "epoch": 0.89, - "learning_rate": 5.730114404107739e-06, - "loss": 0.1839, + "epoch": 0.22, + "learning_rate": 3.900617435851547e-05, + "loss": 0.1984, "step": 99330 }, { - "epoch": 0.89, - "learning_rate": 5.725610305377895e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.900505581530614e-05, + "loss": 0.2035, "step": 99340 }, { - "epoch": 0.89, - "learning_rate": 5.72110620664805e-06, - "loss": 0.1833, + "epoch": 0.22, + "learning_rate": 3.900393727209683e-05, + "loss": 0.2001, "step": 99350 }, { - "epoch": 0.89, - "learning_rate": 5.7166021079182055e-06, - "loss": 0.1808, + "epoch": 0.22, + "learning_rate": 3.90028187288875e-05, + "loss": 0.1994, "step": 99360 }, { - "epoch": 0.89, - "learning_rate": 5.712098009188361e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.900170018567818e-05, + "loss": 0.203, "step": 99370 }, { - "epoch": 0.89, - "learning_rate": 5.707593910458518e-06, - "loss": 0.1844, + "epoch": 0.22, + "learning_rate": 3.9000581642468855e-05, + "loss": 0.2046, "step": 99380 }, { - "epoch": 0.89, - "learning_rate": 5.703089811728674e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.8999463099259526e-05, + "loss": 0.2051, "step": 99390 }, { - "epoch": 0.89, - "learning_rate": 5.6985857129988295e-06, - "loss": 0.1799, + "epoch": 0.22, + "learning_rate": 3.8998344556050204e-05, + "loss": 0.2019, "step": 99400 }, { - "epoch": 0.89, - "learning_rate": 5.6940816142689845e-06, - "loss": 0.1787, + "epoch": 0.22, + "learning_rate": 3.8997226012840875e-05, + "loss": 0.2044, "step": 99410 }, { - "epoch": 0.89, - "learning_rate": 5.68957751553914e-06, - "loss": 0.1802, + "epoch": 0.22, + "learning_rate": 3.899610746963155e-05, + "loss": 0.2034, "step": 99420 }, { - "epoch": 0.89, - "learning_rate": 5.685073416809297e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.8994988926422224e-05, + "loss": 0.2064, "step": 99430 }, { - "epoch": 0.89, - "learning_rate": 5.680569318079453e-06, - "loss": 0.1791, + "epoch": 0.22, + "learning_rate": 3.89938703832129e-05, + "loss": 0.2068, "step": 99440 }, { - "epoch": 0.89, - "learning_rate": 5.6760652193496085e-06, - "loss": 0.1852, + "epoch": 0.22, + "learning_rate": 3.899275184000358e-05, + "loss": 0.1998, "step": 99450 }, { - "epoch": 0.89, - "learning_rate": 5.671561120619764e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.899163329679426e-05, + "loss": 0.2006, "step": 99460 }, { - "epoch": 0.89, - "learning_rate": 5.66705702188992e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.8990514753584936e-05, + "loss": 0.2048, "step": 99470 }, { - "epoch": 0.89, - "learning_rate": 5.662552923160076e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.898939621037561e-05, + "loss": 0.2033, "step": 99480 }, { - "epoch": 0.89, - "learning_rate": 5.658048824430232e-06, - "loss": 0.1827, + "epoch": 0.22, + "learning_rate": 3.8988277667166285e-05, + "loss": 0.2059, "step": 99490 }, { - "epoch": 0.89, - "learning_rate": 5.6535447257003875e-06, - "loss": 0.184, + "epoch": 0.22, + "learning_rate": 3.898715912395696e-05, + "loss": 0.2034, "step": 99500 }, { - "epoch": 0.89, - "learning_rate": 5.649040626970543e-06, - "loss": 0.1808, + "epoch": 0.22, + "learning_rate": 3.8986040580747634e-05, + "loss": 0.1999, "step": 99510 }, { - "epoch": 0.89, - "learning_rate": 5.644536528240699e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.898492203753831e-05, + "loss": 0.2021, "step": 99520 }, { - "epoch": 0.89, - "learning_rate": 5.640032429510855e-06, - "loss": 0.1788, + "epoch": 0.22, + "learning_rate": 3.898380349432898e-05, + "loss": 0.2034, "step": 99530 }, { - "epoch": 0.89, - "learning_rate": 5.6355283307810115e-06, - "loss": 0.1786, + "epoch": 0.22, + "learning_rate": 3.898268495111966e-05, + "loss": 0.2034, "step": 99540 }, { - "epoch": 0.89, - "learning_rate": 5.6310242320511665e-06, - "loss": 0.1787, + "epoch": 0.22, + "learning_rate": 3.898156640791034e-05, + "loss": 0.2016, "step": 99550 }, { - "epoch": 0.89, - "learning_rate": 5.626520133321322e-06, - "loss": 0.1821, + "epoch": 0.22, + "learning_rate": 3.898044786470102e-05, + "loss": 0.2013, "step": 99560 }, { - "epoch": 0.89, - "learning_rate": 5.622016034591478e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.8979329321491695e-05, + "loss": 0.2002, "step": 99570 }, { - "epoch": 0.89, - "learning_rate": 5.617511935861635e-06, - "loss": 0.1784, + "epoch": 0.22, + "learning_rate": 3.8978210778282366e-05, + "loss": 0.2023, "step": 99580 }, { - "epoch": 0.89, - "learning_rate": 5.6130078371317905e-06, - "loss": 0.1832, + "epoch": 0.22, + "learning_rate": 3.8977092235073044e-05, + "loss": 0.2078, "step": 99590 }, { - "epoch": 0.89, - "learning_rate": 5.608503738401946e-06, - "loss": 0.1788, + "epoch": 0.22, + "learning_rate": 3.897597369186372e-05, + "loss": 0.2028, "step": 99600 }, { - "epoch": 0.89, - "learning_rate": 5.603999639672102e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.897485514865439e-05, + "loss": 0.202, "step": 99610 }, { - "epoch": 0.89, - "learning_rate": 5.599495540942257e-06, - "loss": 0.1763, + "epoch": 0.22, + "learning_rate": 3.897373660544507e-05, + "loss": 0.2029, "step": 99620 }, { - "epoch": 0.89, - "learning_rate": 5.594991442212414e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.897261806223574e-05, + "loss": 0.2024, "step": 99630 }, { - "epoch": 0.89, - "learning_rate": 5.5904873434825695e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.897149951902642e-05, + "loss": 0.2067, "step": 99640 }, { - "epoch": 0.89, - "learning_rate": 5.585983244752725e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.89703809758171e-05, + "loss": 0.2046, "step": 99650 }, { - "epoch": 0.89, - "learning_rate": 5.581479146022881e-06, - "loss": 0.1816, + "epoch": 0.22, + "learning_rate": 3.8969262432607776e-05, + "loss": 0.2066, "step": 99660 }, { - "epoch": 0.89, - "learning_rate": 5.576975047293037e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.8968143889398454e-05, + "loss": 0.2088, "step": 99670 }, { - "epoch": 0.89, - "learning_rate": 5.572470948563193e-06, - "loss": 0.1814, + "epoch": 0.22, + "learning_rate": 3.8967025346189125e-05, + "loss": 0.2037, "step": 99680 }, { - "epoch": 0.89, - "learning_rate": 5.5679668498333485e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.8966018657300733e-05, + "loss": 0.2067, "step": 99690 }, { - "epoch": 0.89, - "learning_rate": 5.563462751103504e-06, - "loss": 0.173, + "epoch": 0.22, + "learning_rate": 3.8964900114091405e-05, + "loss": 0.2048, "step": 99700 }, { - "epoch": 0.89, - "learning_rate": 5.55895865237366e-06, - "loss": 0.1786, + "epoch": 0.22, + "learning_rate": 3.896378157088208e-05, + "loss": 0.2087, "step": 99710 }, { - "epoch": 0.89, - "learning_rate": 5.554454553643816e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.896266302767276e-05, + "loss": 0.1946, "step": 99720 }, { - "epoch": 0.89, - "learning_rate": 5.549950454913972e-06, - "loss": 0.1848, + "epoch": 0.22, + "learning_rate": 3.896154448446344e-05, + "loss": 0.2042, "step": 99730 }, { - "epoch": 0.89, - "learning_rate": 5.545446356184128e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.8960425941254116e-05, + "loss": 0.1984, "step": 99740 }, { - "epoch": 0.89, - "learning_rate": 5.540942257454284e-06, - "loss": 0.1757, + "epoch": 0.22, + "learning_rate": 3.895930739804479e-05, + "loss": 0.198, "step": 99750 }, { - "epoch": 0.89, - "learning_rate": 5.536438158724439e-06, - "loss": 0.1789, + "epoch": 0.22, + "learning_rate": 3.8958188854835465e-05, + "loss": 0.2063, "step": 99760 }, { - "epoch": 0.89, - "learning_rate": 5.531934059994595e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.895707031162614e-05, + "loss": 0.2002, "step": 99770 }, { - "epoch": 0.89, - "learning_rate": 5.527429961264751e-06, - "loss": 0.1764, + "epoch": 0.22, + "learning_rate": 3.8955951768416814e-05, + "loss": 0.201, "step": 99780 }, { - "epoch": 0.89, - "learning_rate": 5.522925862534907e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.895483322520749e-05, + "loss": 0.2006, "step": 99790 }, { - "epoch": 0.89, - "learning_rate": 5.518421763805063e-06, - "loss": 0.1764, + "epoch": 0.22, + "learning_rate": 3.8953714681998164e-05, + "loss": 0.1977, "step": 99800 }, { - "epoch": 0.89, - "learning_rate": 5.513917665075219e-06, - "loss": 0.1797, + "epoch": 0.22, + "learning_rate": 3.895259613878884e-05, + "loss": 0.203, "step": 99810 }, { - "epoch": 0.89, - "learning_rate": 5.509413566345375e-06, - "loss": 0.1765, + "epoch": 0.22, + "learning_rate": 3.895147759557952e-05, + "loss": 0.2007, "step": 99820 }, { - "epoch": 0.89, - "learning_rate": 5.50490946761553e-06, - "loss": 0.1846, + "epoch": 0.22, + "learning_rate": 3.89503590523702e-05, + "loss": 0.1987, "step": 99830 }, { - "epoch": 0.89, - "learning_rate": 5.500405368885686e-06, - "loss": 0.1807, + "epoch": 0.22, + "learning_rate": 3.8949240509160875e-05, + "loss": 0.2063, "step": 99840 }, { - "epoch": 0.89, - "learning_rate": 5.495901270155842e-06, - "loss": 0.1721, + "epoch": 0.22, + "learning_rate": 3.8948121965951546e-05, + "loss": 0.2067, "step": 99850 }, { - "epoch": 0.89, - "learning_rate": 5.491397171425998e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.8947003422742224e-05, + "loss": 0.207, "step": 99860 }, { - "epoch": 0.89, - "learning_rate": 5.486893072696154e-06, - "loss": 0.1735, + "epoch": 0.22, + "learning_rate": 3.8945884879532896e-05, + "loss": 0.2017, "step": 99870 }, { - "epoch": 0.89, - "learning_rate": 5.4823889739663095e-06, - "loss": 0.1838, + "epoch": 0.22, + "learning_rate": 3.8944766336323573e-05, + "loss": 0.2006, "step": 99880 }, { - "epoch": 0.89, - "learning_rate": 5.477884875236465e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.894364779311425e-05, + "loss": 0.2049, "step": 99890 }, { - "epoch": 0.89, - "learning_rate": 5.473380776506621e-06, - "loss": 0.1854, + "epoch": 0.22, + "learning_rate": 3.894252924990492e-05, + "loss": 0.1993, "step": 99900 }, { - "epoch": 0.89, - "learning_rate": 5.468876677776777e-06, - "loss": 0.1764, + "epoch": 0.22, + "learning_rate": 3.89414107066956e-05, + "loss": 0.2049, "step": 99910 }, { - "epoch": 0.89, - "learning_rate": 5.464372579046933e-06, - "loss": 0.1743, + "epoch": 0.22, + "learning_rate": 3.894029216348627e-05, + "loss": 0.1948, "step": 99920 }, { - "epoch": 0.89, - "learning_rate": 5.4598684803170885e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.8939173620276956e-05, + "loss": 0.2035, "step": 99930 }, { - "epoch": 0.89, - "learning_rate": 5.455364381587245e-06, - "loss": 0.1743, + "epoch": 0.22, + "learning_rate": 3.8938055077067634e-05, + "loss": 0.2018, "step": 99940 }, { - "epoch": 0.89, - "learning_rate": 5.450860282857401e-06, - "loss": 0.1754, + "epoch": 0.22, + "learning_rate": 3.8936936533858305e-05, + "loss": 0.2019, "step": 99950 }, { - "epoch": 0.89, - "learning_rate": 5.446356184127557e-06, - "loss": 0.1837, + "epoch": 0.22, + "learning_rate": 3.893581799064898e-05, + "loss": 0.208, "step": 99960 }, { - "epoch": 0.89, - "learning_rate": 5.441852085397712e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.8934699447439654e-05, + "loss": 0.2006, "step": 99970 }, { - "epoch": 0.89, - "learning_rate": 5.4373479866678675e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.893358090423033e-05, + "loss": 0.1991, "step": 99980 }, { - "epoch": 0.89, - "learning_rate": 5.432843887938024e-06, - "loss": 0.1768, + "epoch": 0.22, + "learning_rate": 3.893246236102101e-05, + "loss": 0.2011, "step": 99990 }, { - "epoch": 0.89, - "learning_rate": 5.42833978920818e-06, - "loss": 0.1754, + "epoch": 0.22, + "learning_rate": 3.893134381781168e-05, + "loss": 0.2021, "step": 100000 }, { - "epoch": 0.89, - "learning_rate": 5.423835690478336e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.893022527460236e-05, + "loss": 0.2053, "step": 100010 }, { - "epoch": 0.89, - "learning_rate": 5.4193315917484915e-06, - "loss": 0.1791, + "epoch": 0.22, + "learning_rate": 3.892910673139303e-05, + "loss": 0.1967, "step": 100020 }, { - "epoch": 0.89, - "learning_rate": 5.414827493018647e-06, - "loss": 0.1792, + "epoch": 0.22, + "learning_rate": 3.892798818818371e-05, + "loss": 0.2033, "step": 100030 }, { - "epoch": 0.89, - "learning_rate": 5.410323394288803e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.8926869644974386e-05, + "loss": 0.2029, "step": 100040 }, { - "epoch": 0.89, - "learning_rate": 5.405819295558959e-06, - "loss": 0.1773, + "epoch": 0.22, + "learning_rate": 3.8925751101765064e-05, + "loss": 0.2, "step": 100050 }, { - "epoch": 0.89, - "learning_rate": 5.401315196829115e-06, - "loss": 0.182, + "epoch": 0.22, + "learning_rate": 3.892463255855574e-05, + "loss": 0.1999, "step": 100060 }, { - "epoch": 0.89, - "learning_rate": 5.3968110980992705e-06, - "loss": 0.1753, + "epoch": 0.22, + "learning_rate": 3.8923514015346413e-05, + "loss": 0.2021, "step": 100070 }, { - "epoch": 0.89, - "learning_rate": 5.392306999369426e-06, - "loss": 0.1777, + "epoch": 0.22, + "learning_rate": 3.892239547213709e-05, + "loss": 0.2085, "step": 100080 }, { - "epoch": 0.89, - "learning_rate": 5.387802900639582e-06, - "loss": 0.1753, + "epoch": 0.22, + "learning_rate": 3.892127692892777e-05, + "loss": 0.1999, "step": 100090 }, { - "epoch": 0.89, - "learning_rate": 5.383298801909739e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.892015838571844e-05, + "loss": 0.1988, "step": 100100 }, { - "epoch": 0.89, - "learning_rate": 5.378794703179894e-06, - "loss": 0.1776, + "epoch": 0.22, + "learning_rate": 3.891903984250912e-05, + "loss": 0.2031, "step": 100110 }, { - "epoch": 0.89, - "learning_rate": 5.3742906044500495e-06, - "loss": 0.1811, + "epoch": 0.22, + "learning_rate": 3.891792129929979e-05, + "loss": 0.2039, "step": 100120 }, { - "epoch": 0.89, - "learning_rate": 5.369786505720205e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.891680275609047e-05, + "loss": 0.1987, "step": 100130 }, { - "epoch": 0.89, - "learning_rate": 5.365282406990361e-06, - "loss": 0.1719, + "epoch": 0.22, + "learning_rate": 3.8915684212881145e-05, + "loss": 0.2039, "step": 100140 }, { - "epoch": 0.89, - "learning_rate": 5.360778308260518e-06, - "loss": 0.1768, + "epoch": 0.22, + "learning_rate": 3.891456566967182e-05, + "loss": 0.202, "step": 100150 }, { - "epoch": 0.89, - "learning_rate": 5.3562742095306736e-06, - "loss": 0.1795, + "epoch": 0.22, + "learning_rate": 3.89134471264625e-05, + "loss": 0.1989, "step": 100160 }, { - "epoch": 0.89, - "learning_rate": 5.351770110800829e-06, - "loss": 0.1822, + "epoch": 0.22, + "learning_rate": 3.891232858325317e-05, + "loss": 0.2068, "step": 100170 }, { - "epoch": 0.89, - "learning_rate": 5.347266012070984e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.891121004004385e-05, + "loss": 0.2033, "step": 100180 }, { - "epoch": 0.89, - "learning_rate": 5.34276191334114e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.891009149683452e-05, + "loss": 0.1987, "step": 100190 }, { - "epoch": 0.89, - "learning_rate": 5.338257814611297e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.89089729536252e-05, + "loss": 0.2028, "step": 100200 }, { - "epoch": 0.89, - "learning_rate": 5.3337537158814526e-06, - "loss": 0.1765, + "epoch": 0.22, + "learning_rate": 3.890785441041588e-05, + "loss": 0.2053, "step": 100210 }, { - "epoch": 0.89, - "learning_rate": 5.329249617151608e-06, - "loss": 0.1778, + "epoch": 0.22, + "learning_rate": 3.890673586720655e-05, + "loss": 0.2024, "step": 100220 }, { - "epoch": 0.89, - "learning_rate": 5.324745518421764e-06, - "loss": 0.177, + "epoch": 0.22, + "learning_rate": 3.8905617323997226e-05, + "loss": 0.1985, "step": 100230 }, { - "epoch": 0.89, - "learning_rate": 5.32024141969192e-06, - "loss": 0.1741, + "epoch": 0.22, + "learning_rate": 3.8904498780787904e-05, + "loss": 0.198, "step": 100240 }, { - "epoch": 0.9, - "learning_rate": 5.315737320962076e-06, - "loss": 0.1796, + "epoch": 0.22, + "learning_rate": 3.890338023757858e-05, + "loss": 0.2042, "step": 100250 }, { - "epoch": 0.9, - "learning_rate": 5.3112332222322315e-06, - "loss": 0.18, + "epoch": 0.22, + "learning_rate": 3.890226169436926e-05, + "loss": 0.1971, "step": 100260 }, { - "epoch": 0.9, - "learning_rate": 5.306729123502387e-06, - "loss": 0.1741, + "epoch": 0.22, + "learning_rate": 3.890114315115993e-05, + "loss": 0.2067, "step": 100270 }, { - "epoch": 0.9, - "learning_rate": 5.302225024772543e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.890002460795061e-05, + "loss": 0.2077, "step": 100280 }, { - "epoch": 0.9, - "learning_rate": 5.297720926042699e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.889890606474128e-05, + "loss": 0.2032, "step": 100290 }, { - "epoch": 0.9, - "learning_rate": 5.293216827312856e-06, - "loss": 0.1806, + "epoch": 0.22, + "learning_rate": 3.889778752153196e-05, + "loss": 0.2004, "step": 100300 }, { - "epoch": 0.9, - "learning_rate": 5.288712728583011e-06, - "loss": 0.1824, + "epoch": 0.22, + "learning_rate": 3.8896668978322636e-05, + "loss": 0.2029, "step": 100310 }, { - "epoch": 0.9, - "learning_rate": 5.284208629853166e-06, - "loss": 0.1761, + "epoch": 0.22, + "learning_rate": 3.889555043511331e-05, + "loss": 0.1992, "step": 100320 }, { - "epoch": 0.9, - "learning_rate": 5.279704531123322e-06, - "loss": 0.1809, + "epoch": 0.22, + "learning_rate": 3.8894431891903985e-05, + "loss": 0.2057, "step": 100330 }, { - "epoch": 0.9, - "learning_rate": 5.275200432393478e-06, - "loss": 0.1753, + "epoch": 0.22, + "learning_rate": 3.889331334869466e-05, + "loss": 0.2065, "step": 100340 }, { - "epoch": 0.9, - "learning_rate": 5.2706963336636346e-06, - "loss": 0.1831, + "epoch": 0.22, + "learning_rate": 3.889219480548534e-05, + "loss": 0.2033, "step": 100350 }, { - "epoch": 0.9, - "learning_rate": 5.26619223493379e-06, - "loss": 0.1779, + "epoch": 0.22, + "learning_rate": 3.889107626227602e-05, + "loss": 0.1918, "step": 100360 }, { - "epoch": 0.9, - "learning_rate": 5.261688136203946e-06, - "loss": 0.1796, + "epoch": 0.22, + "learning_rate": 3.888995771906669e-05, + "loss": 0.1992, "step": 100370 }, { - "epoch": 0.9, - "learning_rate": 5.257184037474102e-06, - "loss": 0.1813, + "epoch": 0.22, + "learning_rate": 3.888883917585737e-05, + "loss": 0.1977, "step": 100380 }, { - "epoch": 0.9, - "learning_rate": 5.252679938744257e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.888772063264804e-05, + "loss": 0.2016, "step": 100390 }, { - "epoch": 0.9, - "learning_rate": 5.2481758400144136e-06, - "loss": 0.179, + "epoch": 0.22, + "learning_rate": 3.888660208943872e-05, + "loss": 0.2003, "step": 100400 }, { - "epoch": 0.9, - "learning_rate": 5.243671741284569e-06, - "loss": 0.1769, + "epoch": 0.22, + "learning_rate": 3.8885483546229395e-05, + "loss": 0.2006, "step": 100410 }, { - "epoch": 0.9, - "learning_rate": 5.239167642554725e-06, - "loss": 0.174, + "epoch": 0.22, + "learning_rate": 3.8884365003020066e-05, + "loss": 0.208, "step": 100420 }, { - "epoch": 0.9, - "learning_rate": 5.234663543824881e-06, - "loss": 0.1794, + "epoch": 0.22, + "learning_rate": 3.8883246459810744e-05, + "loss": 0.2082, "step": 100430 }, { - "epoch": 0.9, - "learning_rate": 5.230159445095037e-06, - "loss": 0.1783, + "epoch": 0.22, + "learning_rate": 3.8882127916601415e-05, + "loss": 0.2094, "step": 100440 }, { - "epoch": 0.9, - "learning_rate": 5.2256553463651926e-06, - "loss": 0.1774, + "epoch": 0.22, + "learning_rate": 3.888100937339209e-05, + "loss": 0.2027, "step": 100450 }, { - "epoch": 0.9, - "learning_rate": 5.221151247635348e-06, - "loss": 0.1865, + "epoch": 0.22, + "learning_rate": 3.887989083018277e-05, + "loss": 0.202, "step": 100460 }, { - "epoch": 0.9, - "learning_rate": 5.216647148905504e-06, - "loss": 0.1736, + "epoch": 0.22, + "learning_rate": 3.887877228697345e-05, + "loss": 0.203, "step": 100470 }, { - "epoch": 0.9, - "learning_rate": 5.21214305017566e-06, - "loss": 0.177, + "epoch": 0.22, + "learning_rate": 3.887765374376413e-05, + "loss": 0.1993, "step": 100480 }, { - "epoch": 0.9, - "learning_rate": 5.207638951445816e-06, - "loss": 0.1793, + "epoch": 0.22, + "learning_rate": 3.88765352005548e-05, + "loss": 0.2064, "step": 100490 }, { - "epoch": 0.9, - "learning_rate": 5.2031348527159715e-06, - "loss": 0.1807, + "epoch": 0.22, + "learning_rate": 3.8875416657345476e-05, + "loss": 0.2074, "step": 100500 }, { - "epoch": 0.9, - "learning_rate": 5.198630753986128e-06, - "loss": 0.1817, + "epoch": 0.22, + "learning_rate": 3.887429811413615e-05, + "loss": 0.2006, "step": 100510 }, { - "epoch": 0.9, - "learning_rate": 5.194126655256284e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.8873179570926825e-05, + "loss": 0.2069, "step": 100520 }, { - "epoch": 0.9, - "learning_rate": 5.189622556526439e-06, - "loss": 0.175, + "epoch": 0.22, + "learning_rate": 3.88720610277175e-05, + "loss": 0.2016, "step": 100530 }, { - "epoch": 0.9, - "learning_rate": 5.185118457796595e-06, - "loss": 0.178, + "epoch": 0.22, + "learning_rate": 3.8870942484508174e-05, + "loss": 0.2042, "step": 100540 }, { - "epoch": 0.9, - "learning_rate": 5.1806143590667505e-06, - "loss": 0.1768, + "epoch": 0.22, + "learning_rate": 3.886982394129885e-05, + "loss": 0.197, "step": 100550 }, { - "epoch": 0.9, - "learning_rate": 5.176110260336907e-06, - "loss": 0.1747, + "epoch": 0.22, + "learning_rate": 3.886870539808953e-05, + "loss": 0.2042, "step": 100560 }, { - "epoch": 0.9, - "learning_rate": 5.171606161607063e-06, - "loss": 0.1766, + "epoch": 0.22, + "learning_rate": 3.886758685488021e-05, + "loss": 0.202, "step": 100570 }, { - "epoch": 0.9, - "learning_rate": 5.167102062877219e-06, - "loss": 0.1714, + "epoch": 0.22, + "learning_rate": 3.8866468311670886e-05, + "loss": 0.1948, "step": 100580 }, { - "epoch": 0.9, - "learning_rate": 5.162597964147374e-06, - "loss": 0.1788, + "epoch": 0.22, + "learning_rate": 3.886534976846156e-05, + "loss": 0.2017, "step": 100590 }, { - "epoch": 0.9, - "learning_rate": 5.158544275290515e-06, - "loss": 0.1761, + "epoch": 0.22, + "learning_rate": 3.8864231225252235e-05, + "loss": 0.2023, "step": 100600 }, { - "epoch": 0.9, - "learning_rate": 5.154040176560671e-06, - "loss": 0.1785, + "epoch": 0.22, + "learning_rate": 3.8863112682042906e-05, + "loss": 0.199, "step": 100610 }, { - "epoch": 0.9, - "learning_rate": 5.1495360778308266e-06, - "loss": 0.1805, + "epoch": 0.22, + "learning_rate": 3.8861994138833584e-05, + "loss": 0.1988, "step": 100620 }, { - "epoch": 0.9, - "learning_rate": 5.145031979100982e-06, - "loss": 0.1773, + "epoch": 0.22, + "learning_rate": 3.886087559562426e-05, + "loss": 0.201, "step": 100630 }, { - "epoch": 0.9, - "learning_rate": 5.140527880371137e-06, - "loss": 0.1862, + "epoch": 0.22, + "learning_rate": 3.885975705241493e-05, + "loss": 0.2027, "step": 100640 }, { - "epoch": 0.9, - "learning_rate": 5.136023781641294e-06, - "loss": 0.1844, + "epoch": 0.22, + "learning_rate": 3.885863850920561e-05, + "loss": 0.2015, "step": 100650 }, { - "epoch": 0.9, - "learning_rate": 5.13151968291145e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.885751996599629e-05, + "loss": 0.1972, "step": 100660 }, { - "epoch": 0.9, - "learning_rate": 5.1270155841816055e-06, - "loss": 0.1777, + "epoch": 0.22, + "learning_rate": 3.885640142278697e-05, + "loss": 0.1994, "step": 100670 }, { - "epoch": 0.9, - "learning_rate": 5.122511485451761e-06, - "loss": 0.1823, + "epoch": 0.22, + "learning_rate": 3.8855282879577645e-05, + "loss": 0.2051, "step": 100680 }, { - "epoch": 0.9, - "learning_rate": 5.118007386721917e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.8854164336368316e-05, + "loss": 0.2007, "step": 100690 }, { - "epoch": 0.9, - "learning_rate": 5.113503287992073e-06, - "loss": 0.1748, + "epoch": 0.22, + "learning_rate": 3.8853045793158994e-05, + "loss": 0.2064, "step": 100700 }, { - "epoch": 0.9, - "learning_rate": 5.108999189262229e-06, - "loss": 0.1762, + "epoch": 0.22, + "learning_rate": 3.8851927249949665e-05, + "loss": 0.1985, "step": 100710 }, { - "epoch": 0.9, - "learning_rate": 5.1044950905323845e-06, - "loss": 0.1801, + "epoch": 0.22, + "learning_rate": 3.885080870674034e-05, + "loss": 0.2015, "step": 100720 }, { - "epoch": 0.9, - "learning_rate": 5.09999099180254e-06, - "loss": 0.1818, + "epoch": 0.22, + "learning_rate": 3.884969016353102e-05, + "loss": 0.2032, "step": 100730 }, { - "epoch": 0.9, - "learning_rate": 5.095486893072696e-06, - "loss": 0.1772, + "epoch": 0.22, + "learning_rate": 3.884857162032169e-05, + "loss": 0.205, "step": 100740 }, { - "epoch": 0.9, - "learning_rate": 5.090982794342852e-06, - "loss": 0.1782, + "epoch": 0.22, + "learning_rate": 3.884745307711237e-05, + "loss": 0.1968, "step": 100750 }, { - "epoch": 0.9, - "learning_rate": 5.086478695613009e-06, - "loss": 0.1773, + "epoch": 0.22, + "learning_rate": 3.884633453390305e-05, + "loss": 0.2053, "step": 100760 }, { - "epoch": 0.9, - "learning_rate": 5.081974596883164e-06, - "loss": 0.1751, + "epoch": 0.22, + "learning_rate": 3.8845215990693726e-05, + "loss": 0.2033, "step": 100770 }, { - "epoch": 0.9, - "learning_rate": 5.077470498153319e-06, - "loss": 0.1803, + "epoch": 0.22, + "learning_rate": 3.88440974474844e-05, + "loss": 0.2011, "step": 100780 }, { - "epoch": 0.9, - "learning_rate": 5.072966399423475e-06, - "loss": 0.1775, + "epoch": 0.22, + "learning_rate": 3.8842978904275075e-05, + "loss": 0.1982, "step": 100790 }, { - "epoch": 0.9, - "learning_rate": 5.068462300693631e-06, - "loss": 0.181, + "epoch": 0.22, + "learning_rate": 3.884186036106575e-05, + "loss": 0.1958, "step": 100800 }, { - "epoch": 0.9, - "learning_rate": 5.0639582019637876e-06, - "loss": 0.1762, + "epoch": 0.23, + "learning_rate": 3.8840741817856424e-05, + "loss": 0.1981, "step": 100810 }, { - "epoch": 0.9, - "learning_rate": 5.059454103233943e-06, - "loss": 0.1807, + "epoch": 0.23, + "learning_rate": 3.88396232746471e-05, + "loss": 0.1996, "step": 100820 }, { - "epoch": 0.9, - "learning_rate": 5.054950004504099e-06, - "loss": 0.1812, + "epoch": 0.23, + "learning_rate": 3.883850473143777e-05, + "loss": 0.2013, "step": 100830 }, { - "epoch": 0.9, - "learning_rate": 5.050445905774255e-06, - "loss": 0.183, + "epoch": 0.23, + "learning_rate": 3.883738618822845e-05, + "loss": 0.2017, "step": 100840 }, { - "epoch": 0.9, - "learning_rate": 5.04594180704441e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.883626764501913e-05, + "loss": 0.2018, "step": 100850 }, { - "epoch": 0.9, - "learning_rate": 5.0414377083145666e-06, - "loss": 0.1767, + "epoch": 0.23, + "learning_rate": 3.88351491018098e-05, + "loss": 0.2041, "step": 100860 }, { - "epoch": 0.9, - "learning_rate": 5.036933609584722e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.883403055860048e-05, + "loss": 0.2002, "step": 100870 }, { - "epoch": 0.9, - "learning_rate": 5.032429510854878e-06, - "loss": 0.1713, + "epoch": 0.23, + "learning_rate": 3.8832912015391156e-05, + "loss": 0.1941, "step": 100880 }, { - "epoch": 0.9, - "learning_rate": 5.027925412125034e-06, - "loss": 0.1797, + "epoch": 0.23, + "learning_rate": 3.8831793472181834e-05, + "loss": 0.1978, "step": 100890 }, { - "epoch": 0.9, - "learning_rate": 5.02342131339519e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.883067492897251e-05, + "loss": 0.1973, "step": 100900 }, { - "epoch": 0.9, - "learning_rate": 5.018917214665346e-06, - "loss": 0.1753, + "epoch": 0.23, + "learning_rate": 3.882955638576318e-05, + "loss": 0.2005, "step": 100910 }, { - "epoch": 0.9, - "learning_rate": 5.014413115935501e-06, - "loss": 0.1773, + "epoch": 0.23, + "learning_rate": 3.882843784255386e-05, + "loss": 0.1978, "step": 100920 }, { - "epoch": 0.9, - "learning_rate": 5.009909017205657e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.882731929934453e-05, + "loss": 0.2002, "step": 100930 }, { - "epoch": 0.9, - "learning_rate": 5.005404918475813e-06, - "loss": 0.175, + "epoch": 0.23, + "learning_rate": 3.882620075613521e-05, + "loss": 0.1985, "step": 100940 }, { - "epoch": 0.9, - "learning_rate": 5.000900819745969e-06, - "loss": 0.1807, + "epoch": 0.23, + "learning_rate": 3.882508221292589e-05, + "loss": 0.2036, "step": 100950 }, { - "epoch": 0.9, - "learning_rate": 4.996396721016125e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.882396366971656e-05, + "loss": 0.2054, "step": 100960 }, { - "epoch": 0.9, - "learning_rate": 4.991892622286281e-06, - "loss": 0.1789, + "epoch": 0.23, + "learning_rate": 3.882284512650724e-05, + "loss": 0.2053, "step": 100970 }, { - "epoch": 0.9, - "learning_rate": 4.987388523556437e-06, - "loss": 0.173, + "epoch": 0.23, + "learning_rate": 3.8821726583297915e-05, + "loss": 0.2003, "step": 100980 }, { - "epoch": 0.9, - "learning_rate": 4.982884424826592e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.882060804008859e-05, + "loss": 0.1998, "step": 100990 }, { - "epoch": 0.9, - "learning_rate": 4.978380326096748e-06, - "loss": 0.179, + "epoch": 0.23, + "learning_rate": 3.881948949687927e-05, + "loss": 0.2061, "step": 101000 }, { - "epoch": 0.9, - "learning_rate": 4.973876227366904e-06, - "loss": 0.1762, + "epoch": 0.23, + "learning_rate": 3.881837095366994e-05, + "loss": 0.2075, "step": 101010 }, { - "epoch": 0.9, - "learning_rate": 4.96937212863706e-06, - "loss": 0.1789, + "epoch": 0.23, + "learning_rate": 3.881725241046062e-05, + "loss": 0.2021, "step": 101020 }, { - "epoch": 0.9, - "learning_rate": 4.964868029907216e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.881613386725129e-05, + "loss": 0.2014, "step": 101030 }, { - "epoch": 0.9, - "learning_rate": 4.960363931177372e-06, - "loss": 0.182, + "epoch": 0.23, + "learning_rate": 3.881501532404197e-05, + "loss": 0.1991, "step": 101040 }, { - "epoch": 0.9, - "learning_rate": 4.9558598324475276e-06, - "loss": 0.1855, + "epoch": 0.23, + "learning_rate": 3.881389678083265e-05, + "loss": 0.1981, "step": 101050 }, { - "epoch": 0.9, - "learning_rate": 4.951355733717683e-06, - "loss": 0.1749, + "epoch": 0.23, + "learning_rate": 3.881277823762332e-05, + "loss": 0.203, "step": 101060 }, { - "epoch": 0.9, - "learning_rate": 4.946851634987839e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.8811659694413996e-05, + "loss": 0.1985, "step": 101070 }, { - "epoch": 0.9, - "learning_rate": 4.942347536257995e-06, - "loss": 0.1794, + "epoch": 0.23, + "learning_rate": 3.8810541151204674e-05, + "loss": 0.1994, "step": 101080 }, { - "epoch": 0.9, - "learning_rate": 4.937843437528151e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.880942260799535e-05, + "loss": 0.2011, "step": 101090 }, { - "epoch": 0.9, - "learning_rate": 4.9333393387983066e-06, - "loss": 0.1827, + "epoch": 0.23, + "learning_rate": 3.880830406478602e-05, + "loss": 0.1993, "step": 101100 }, { - "epoch": 0.9, - "learning_rate": 4.928835240068462e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.88071855215767e-05, + "loss": 0.2045, "step": 101110 }, { - "epoch": 0.9, - "learning_rate": 4.924331141338619e-06, - "loss": 0.182, + "epoch": 0.23, + "learning_rate": 3.880606697836738e-05, + "loss": 0.2008, "step": 101120 }, { - "epoch": 0.9, - "learning_rate": 4.919827042608774e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.880494843515805e-05, + "loss": 0.1941, "step": 101130 }, { - "epoch": 0.9, - "learning_rate": 4.91532294387893e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.880382989194873e-05, + "loss": 0.2052, "step": 101140 }, { - "epoch": 0.9, - "learning_rate": 4.9108188451490856e-06, - "loss": 0.1808, + "epoch": 0.23, + "learning_rate": 3.88027113487394e-05, + "loss": 0.1994, "step": 101150 }, { - "epoch": 0.9, - "learning_rate": 4.906314746419241e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.880159280553008e-05, + "loss": 0.2034, "step": 101160 }, { - "epoch": 0.9, - "learning_rate": 4.901810647689398e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.8800474262320755e-05, + "loss": 0.2008, "step": 101170 }, { - "epoch": 0.9, - "learning_rate": 4.897306548959554e-06, - "loss": 0.181, + "epoch": 0.23, + "learning_rate": 3.879935571911143e-05, + "loss": 0.2024, "step": 101180 }, { - "epoch": 0.9, - "learning_rate": 4.89280245022971e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.879823717590211e-05, + "loss": 0.1977, "step": 101190 }, { - "epoch": 0.9, - "learning_rate": 4.8882983514998645e-06, - "loss": 0.1756, + "epoch": 0.23, + "learning_rate": 3.879711863269278e-05, + "loss": 0.2063, "step": 101200 }, { - "epoch": 0.9, - "learning_rate": 4.88379425277002e-06, - "loss": 0.175, + "epoch": 0.23, + "learning_rate": 3.879600008948346e-05, + "loss": 0.2016, "step": 101210 }, { - "epoch": 0.9, - "learning_rate": 4.879290154040177e-06, - "loss": 0.1753, + "epoch": 0.23, + "learning_rate": 3.879488154627414e-05, + "loss": 0.2022, "step": 101220 }, { - "epoch": 0.9, - "learning_rate": 4.874786055310333e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.879376300306481e-05, + "loss": 0.1964, "step": 101230 }, { - "epoch": 0.9, - "learning_rate": 4.870281956580489e-06, - "loss": 0.178, + "epoch": 0.23, + "learning_rate": 3.879264445985549e-05, + "loss": 0.1942, "step": 101240 }, { - "epoch": 0.9, - "learning_rate": 4.865777857850644e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.879152591664616e-05, + "loss": 0.2018, "step": 101250 }, { - "epoch": 0.9, - "learning_rate": 4.8612737591208e-06, - "loss": 0.1769, + "epoch": 0.23, + "learning_rate": 3.8790407373436836e-05, + "loss": 0.1982, "step": 101260 }, { - "epoch": 0.9, - "learning_rate": 4.856769660390956e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.8789288830227514e-05, + "loss": 0.1997, "step": 101270 }, { - "epoch": 0.9, - "learning_rate": 4.852265561661112e-06, - "loss": 0.1733, + "epoch": 0.23, + "learning_rate": 3.8788170287018185e-05, + "loss": 0.1982, "step": 101280 }, { - "epoch": 0.9, - "learning_rate": 4.8477614629312676e-06, - "loss": 0.1814, + "epoch": 0.23, + "learning_rate": 3.878705174380887e-05, + "loss": 0.2022, "step": 101290 }, { - "epoch": 0.9, - "learning_rate": 4.843257364201423e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.878593320059954e-05, + "loss": 0.2006, "step": 101300 }, { - "epoch": 0.9, - "learning_rate": 4.838753265471579e-06, - "loss": 0.1813, + "epoch": 0.23, + "learning_rate": 3.878481465739022e-05, + "loss": 0.1999, "step": 101310 }, { - "epoch": 0.9, - "learning_rate": 4.834249166741736e-06, - "loss": 0.1782, + "epoch": 0.23, + "learning_rate": 3.87836961141809e-05, + "loss": 0.2015, "step": 101320 }, { - "epoch": 0.9, - "learning_rate": 4.829745068011892e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.878257757097157e-05, + "loss": 0.1968, "step": 101330 }, { - "epoch": 0.9, - "learning_rate": 4.8252409692820466e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.8781459027762246e-05, + "loss": 0.1986, "step": 101340 }, { - "epoch": 0.9, - "learning_rate": 4.820736870552202e-06, - "loss": 0.1726, + "epoch": 0.23, + "learning_rate": 3.878034048455292e-05, + "loss": 0.2064, "step": 101350 }, { - "epoch": 0.9, - "learning_rate": 4.816232771822358e-06, - "loss": 0.174, + "epoch": 0.23, + "learning_rate": 3.8779221941343595e-05, + "loss": 0.2027, "step": 101360 }, { - "epoch": 0.91, - "learning_rate": 4.811728673092515e-06, - "loss": 0.1802, + "epoch": 0.23, + "learning_rate": 3.877810339813427e-05, + "loss": 0.2012, "step": 101370 }, { - "epoch": 0.91, - "learning_rate": 4.807224574362671e-06, - "loss": 0.1729, + "epoch": 0.23, + "learning_rate": 3.8776984854924944e-05, + "loss": 0.2028, "step": 101380 }, { - "epoch": 0.91, - "learning_rate": 4.802720475632826e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.877586631171562e-05, + "loss": 0.1941, "step": 101390 }, { - "epoch": 0.91, - "learning_rate": 4.798216376902982e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.87747477685063e-05, + "loss": 0.2047, "step": 101400 }, { - "epoch": 0.91, - "learning_rate": 4.793712278173137e-06, - "loss": 0.1738, + "epoch": 0.23, + "learning_rate": 3.877362922529698e-05, + "loss": 0.2016, "step": 101410 }, { - "epoch": 0.91, - "learning_rate": 4.789208179443294e-06, - "loss": 0.1762, + "epoch": 0.23, + "learning_rate": 3.877251068208765e-05, + "loss": 0.2036, "step": 101420 }, { - "epoch": 0.91, - "learning_rate": 4.78470408071345e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.877139213887833e-05, + "loss": 0.2031, "step": 101430 }, { - "epoch": 0.91, - "learning_rate": 4.780199981983605e-06, - "loss": 0.1741, + "epoch": 0.23, + "learning_rate": 3.8770273595669005e-05, + "loss": 0.201, "step": 101440 }, { - "epoch": 0.91, - "learning_rate": 4.775695883253761e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.8769155052459676e-05, + "loss": 0.1984, "step": 101450 }, { - "epoch": 0.91, - "learning_rate": 4.771191784523917e-06, - "loss": 0.1838, + "epoch": 0.23, + "learning_rate": 3.8768036509250354e-05, + "loss": 0.1956, "step": 101460 }, { - "epoch": 0.91, - "learning_rate": 4.766687685794073e-06, - "loss": 0.177, + "epoch": 0.23, + "learning_rate": 3.8766917966041025e-05, + "loss": 0.1991, "step": 101470 }, { - "epoch": 0.91, - "learning_rate": 4.762183587064229e-06, - "loss": 0.1823, + "epoch": 0.23, + "learning_rate": 3.87657994228317e-05, + "loss": 0.1985, "step": 101480 }, { - "epoch": 0.91, - "learning_rate": 4.757679488334384e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.876468087962238e-05, + "loss": 0.2028, "step": 101490 }, { - "epoch": 0.91, - "learning_rate": 4.75317538960454e-06, - "loss": 0.1746, + "epoch": 0.23, + "learning_rate": 3.876356233641306e-05, + "loss": 0.1968, "step": 101500 }, { - "epoch": 0.91, - "learning_rate": 4.748671290874696e-06, - "loss": 0.1755, + "epoch": 0.23, + "learning_rate": 3.876244379320374e-05, + "loss": 0.2011, "step": 101510 }, { - "epoch": 0.91, - "learning_rate": 4.744167192144852e-06, - "loss": 0.18, + "epoch": 0.23, + "learning_rate": 3.876132524999441e-05, + "loss": 0.1968, "step": 101520 }, { - "epoch": 0.91, - "learning_rate": 4.739663093415008e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.8760206706785086e-05, + "loss": 0.2035, "step": 101530 }, { - "epoch": 0.91, - "learning_rate": 4.735158994685164e-06, - "loss": 0.1742, + "epoch": 0.23, + "learning_rate": 3.8759088163575764e-05, + "loss": 0.207, "step": 101540 }, { - "epoch": 0.91, - "learning_rate": 4.730654895955319e-06, - "loss": 0.1768, + "epoch": 0.23, + "learning_rate": 3.8757969620366435e-05, + "loss": 0.1982, "step": 101550 }, { - "epoch": 0.91, - "learning_rate": 4.726150797225475e-06, - "loss": 0.1809, + "epoch": 0.23, + "learning_rate": 3.875685107715711e-05, + "loss": 0.1936, "step": 101560 }, { - "epoch": 0.91, - "learning_rate": 4.721646698495631e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.8755732533947784e-05, + "loss": 0.1972, "step": 101570 }, { - "epoch": 0.91, - "learning_rate": 4.717142599765787e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.875461399073846e-05, + "loss": 0.1988, "step": 101580 }, { - "epoch": 0.91, - "learning_rate": 4.712638501035943e-06, - "loss": 0.1722, + "epoch": 0.23, + "learning_rate": 3.875349544752914e-05, + "loss": 0.2, "step": 101590 }, { - "epoch": 0.91, - "learning_rate": 4.708134402306099e-06, - "loss": 0.1705, + "epoch": 0.23, + "learning_rate": 3.875237690431982e-05, + "loss": 0.208, "step": 101600 }, { - "epoch": 0.91, - "learning_rate": 4.703630303576255e-06, - "loss": 0.1735, + "epoch": 0.23, + "learning_rate": 3.8751258361110496e-05, + "loss": 0.2017, "step": 101610 }, { - "epoch": 0.91, - "learning_rate": 4.699126204846411e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.875013981790117e-05, + "loss": 0.1973, "step": 101620 }, { - "epoch": 0.91, - "learning_rate": 4.694622106116566e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.8749021274691845e-05, + "loss": 0.2075, "step": 101630 }, { - "epoch": 0.91, - "learning_rate": 4.690118007386722e-06, - "loss": 0.1733, + "epoch": 0.23, + "learning_rate": 3.874790273148252e-05, + "loss": 0.2021, "step": 101640 }, { - "epoch": 0.91, - "learning_rate": 4.685613908656878e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.8746784188273194e-05, + "loss": 0.2042, "step": 101650 }, { - "epoch": 0.91, - "learning_rate": 4.681109809927034e-06, - "loss": 0.1794, + "epoch": 0.23, + "learning_rate": 3.874566564506387e-05, + "loss": 0.2018, "step": 101660 }, { - "epoch": 0.91, - "learning_rate": 4.67660571119719e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.874454710185454e-05, + "loss": 0.2044, "step": 101670 }, { - "epoch": 0.91, - "learning_rate": 4.672101612467346e-06, - "loss": 0.1823, + "epoch": 0.23, + "learning_rate": 3.874342855864522e-05, + "loss": 0.2036, "step": 101680 }, { - "epoch": 0.91, - "learning_rate": 4.667597513737501e-06, - "loss": 0.1817, + "epoch": 0.23, + "learning_rate": 3.87423100154359e-05, + "loss": 0.2003, "step": 101690 }, { - "epoch": 0.91, - "learning_rate": 4.663093415007657e-06, - "loss": 0.174, + "epoch": 0.23, + "learning_rate": 3.874119147222657e-05, + "loss": 0.2017, "step": 101700 }, { - "epoch": 0.91, - "learning_rate": 4.658589316277813e-06, - "loss": 0.1728, + "epoch": 0.23, + "learning_rate": 3.8740184783338186e-05, + "loss": 0.1992, "step": 101710 }, { - "epoch": 0.91, - "learning_rate": 4.654085217547969e-06, - "loss": 0.1727, + "epoch": 0.23, + "learning_rate": 3.873906624012886e-05, + "loss": 0.2015, "step": 101720 }, { - "epoch": 0.91, - "learning_rate": 4.649581118818125e-06, - "loss": 0.177, + "epoch": 0.23, + "learning_rate": 3.8737947696919535e-05, + "loss": 0.2058, "step": 101730 }, { - "epoch": 0.91, - "learning_rate": 4.645077020088281e-06, - "loss": 0.1815, + "epoch": 0.23, + "learning_rate": 3.8736829153710206e-05, + "loss": 0.1998, "step": 101740 }, { - "epoch": 0.91, - "learning_rate": 4.640572921358437e-06, - "loss": 0.1731, + "epoch": 0.23, + "learning_rate": 3.8735710610500884e-05, + "loss": 0.1992, "step": 101750 }, { - "epoch": 0.91, - "learning_rate": 4.636068822628592e-06, - "loss": 0.1837, + "epoch": 0.23, + "learning_rate": 3.873459206729156e-05, + "loss": 0.1986, "step": 101760 }, { - "epoch": 0.91, - "learning_rate": 4.6315647238987476e-06, - "loss": 0.1861, + "epoch": 0.23, + "learning_rate": 3.873347352408224e-05, + "loss": 0.1993, "step": 101770 }, { - "epoch": 0.91, - "learning_rate": 4.627060625168904e-06, - "loss": 0.1752, + "epoch": 0.23, + "learning_rate": 3.873235498087292e-05, + "loss": 0.1994, "step": 101780 }, { - "epoch": 0.91, - "learning_rate": 4.62255652643906e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.873123643766359e-05, + "loss": 0.2032, "step": 101790 }, { - "epoch": 0.91, - "learning_rate": 4.618052427709216e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.873011789445427e-05, + "loss": 0.1989, "step": 101800 }, { - "epoch": 0.91, - "learning_rate": 4.613548328979372e-06, - "loss": 0.1715, + "epoch": 0.23, + "learning_rate": 3.872899935124494e-05, + "loss": 0.2004, "step": 101810 }, { - "epoch": 0.91, - "learning_rate": 4.6090442302495266e-06, - "loss": 0.1759, + "epoch": 0.23, + "learning_rate": 3.8727880808035616e-05, + "loss": 0.1964, "step": 101820 }, { - "epoch": 0.91, - "learning_rate": 4.604540131519683e-06, - "loss": 0.1787, + "epoch": 0.23, + "learning_rate": 3.8726762264826294e-05, + "loss": 0.2003, "step": 101830 }, { - "epoch": 0.91, - "learning_rate": 4.600036032789839e-06, - "loss": 0.182, + "epoch": 0.23, + "learning_rate": 3.8725643721616965e-05, + "loss": 0.1979, "step": 101840 }, { - "epoch": 0.91, - "learning_rate": 4.595531934059995e-06, - "loss": 0.1752, + "epoch": 0.23, + "learning_rate": 3.872452517840764e-05, + "loss": 0.2024, "step": 101850 }, { - "epoch": 0.91, - "learning_rate": 4.591027835330151e-06, - "loss": 0.1807, + "epoch": 0.23, + "learning_rate": 3.8723406635198314e-05, + "loss": 0.201, "step": 101860 }, { - "epoch": 0.91, - "learning_rate": 4.586523736600306e-06, - "loss": 0.1794, + "epoch": 0.23, + "learning_rate": 3.8722288091989e-05, + "loss": 0.202, "step": 101870 }, { - "epoch": 0.91, - "learning_rate": 4.582019637870462e-06, - "loss": 0.18, + "epoch": 0.23, + "learning_rate": 3.8721169548779676e-05, + "loss": 0.1993, "step": 101880 }, { - "epoch": 0.91, - "learning_rate": 4.577515539140618e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.872005100557035e-05, + "loss": 0.1999, "step": 101890 }, { - "epoch": 0.91, - "learning_rate": 4.573011440410774e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.8718932462361026e-05, + "loss": 0.2028, "step": 101900 }, { - "epoch": 0.91, - "learning_rate": 4.56850734168093e-06, - "loss": 0.1809, + "epoch": 0.23, + "learning_rate": 3.87178139191517e-05, + "loss": 0.2004, "step": 101910 }, { - "epoch": 0.91, - "learning_rate": 4.564003242951085e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.8716695375942375e-05, + "loss": 0.1967, "step": 101920 }, { - "epoch": 0.91, - "learning_rate": 4.559499144221241e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.871557683273305e-05, + "loss": 0.2039, "step": 101930 }, { - "epoch": 0.91, - "learning_rate": 4.554995045491398e-06, - "loss": 0.1768, + "epoch": 0.23, + "learning_rate": 3.8714458289523724e-05, + "loss": 0.2048, "step": 101940 }, { - "epoch": 0.91, - "learning_rate": 4.550490946761554e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.87133397463144e-05, + "loss": 0.2009, "step": 101950 }, { - "epoch": 0.91, - "learning_rate": 4.545986848031709e-06, - "loss": 0.1762, + "epoch": 0.23, + "learning_rate": 3.871222120310507e-05, + "loss": 0.2028, "step": 101960 }, { - "epoch": 0.91, - "learning_rate": 4.541482749301864e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.871110265989575e-05, + "loss": 0.2023, "step": 101970 }, { - "epoch": 0.91, - "learning_rate": 4.536978650572021e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.870998411668643e-05, + "loss": 0.2079, "step": 101980 }, { - "epoch": 0.91, - "learning_rate": 4.532474551842177e-06, - "loss": 0.173, + "epoch": 0.23, + "learning_rate": 3.8708865573477107e-05, + "loss": 0.2004, "step": 101990 }, { - "epoch": 0.91, - "learning_rate": 4.527970453112333e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.8707747030267785e-05, + "loss": 0.2062, "step": 102000 }, { - "epoch": 0.91, - "learning_rate": 4.523466354382488e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.8706628487058456e-05, + "loss": 0.2019, "step": 102010 }, { - "epoch": 0.91, - "learning_rate": 4.518962255652644e-06, - "loss": 0.1798, + "epoch": 0.23, + "learning_rate": 3.8705509943849134e-05, + "loss": 0.2053, "step": 102020 }, { - "epoch": 0.91, - "learning_rate": 4.5144581569228e-06, - "loss": 0.1755, + "epoch": 0.23, + "learning_rate": 3.870439140063981e-05, + "loss": 0.1988, "step": 102030 }, { - "epoch": 0.91, - "learning_rate": 4.509954058192956e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.870327285743048e-05, + "loss": 0.1968, "step": 102040 }, { - "epoch": 0.91, - "learning_rate": 4.505449959463112e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.870215431422116e-05, + "loss": 0.1953, "step": 102050 }, { - "epoch": 0.91, - "learning_rate": 4.500945860733267e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.870103577101183e-05, + "loss": 0.1977, "step": 102060 }, { - "epoch": 0.91, - "learning_rate": 4.496441762003423e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.869991722780251e-05, + "loss": 0.2007, "step": 102070 }, { - "epoch": 0.91, - "learning_rate": 4.491937663273579e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.869879868459319e-05, + "loss": 0.2044, "step": 102080 }, { - "epoch": 0.91, - "learning_rate": 4.487433564543736e-06, - "loss": 0.1811, + "epoch": 0.23, + "learning_rate": 3.8697680141383866e-05, + "loss": 0.2016, "step": 102090 }, { - "epoch": 0.91, - "learning_rate": 4.482929465813891e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.8696561598174543e-05, + "loss": 0.1979, "step": 102100 }, { - "epoch": 0.91, - "learning_rate": 4.478425367084046e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.8695443054965215e-05, + "loss": 0.1973, "step": 102110 }, { - "epoch": 0.91, - "learning_rate": 4.473921268354202e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.869432451175589e-05, + "loss": 0.201, "step": 102120 }, { - "epoch": 0.91, - "learning_rate": 4.469417169624358e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.8693205968546564e-05, + "loss": 0.1988, "step": 102130 }, { - "epoch": 0.91, - "learning_rate": 4.464913070894515e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.869208742533724e-05, + "loss": 0.2024, "step": 102140 }, { - "epoch": 0.91, - "learning_rate": 4.4604089721646704e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.869096888212792e-05, + "loss": 0.205, "step": 102150 }, { - "epoch": 0.91, - "learning_rate": 4.455904873434826e-06, - "loss": 0.1775, + "epoch": 0.23, + "learning_rate": 3.868985033891859e-05, + "loss": 0.2038, "step": 102160 }, { - "epoch": 0.91, - "learning_rate": 4.451400774704981e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.868873179570927e-05, + "loss": 0.2049, "step": 102170 }, { - "epoch": 0.91, - "learning_rate": 4.446896675975137e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.8687613252499947e-05, + "loss": 0.2029, "step": 102180 }, { - "epoch": 0.91, - "learning_rate": 4.442392577245294e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.8686494709290624e-05, + "loss": 0.1938, "step": 102190 }, { - "epoch": 0.91, - "learning_rate": 4.4378884785154494e-06, - "loss": 0.1797, + "epoch": 0.23, + "learning_rate": 3.86853761660813e-05, + "loss": 0.2021, "step": 102200 }, { - "epoch": 0.91, - "learning_rate": 4.433384379785605e-06, - "loss": 0.1749, + "epoch": 0.23, + "learning_rate": 3.8684257622871974e-05, + "loss": 0.1985, "step": 102210 }, { - "epoch": 0.91, - "learning_rate": 4.428880281055761e-06, - "loss": 0.173, + "epoch": 0.23, + "learning_rate": 3.868313907966265e-05, + "loss": 0.1952, "step": 102220 }, { - "epoch": 0.91, - "learning_rate": 4.424376182325917e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.868202053645332e-05, + "loss": 0.1959, "step": 102230 }, { - "epoch": 0.91, - "learning_rate": 4.419872083596073e-06, - "loss": 0.1716, + "epoch": 0.23, + "learning_rate": 3.8680901993244e-05, + "loss": 0.2027, "step": 102240 }, { - "epoch": 0.91, - "learning_rate": 4.4153679848662284e-06, - "loss": 0.1812, + "epoch": 0.23, + "learning_rate": 3.867978345003468e-05, + "loss": 0.1984, "step": 102250 }, { - "epoch": 0.91, - "learning_rate": 4.410863886136384e-06, - "loss": 0.1733, + "epoch": 0.23, + "learning_rate": 3.867866490682535e-05, + "loss": 0.2016, "step": 102260 }, { - "epoch": 0.91, - "learning_rate": 4.40635978740654e-06, - "loss": 0.1747, + "epoch": 0.23, + "learning_rate": 3.867754636361603e-05, + "loss": 0.2033, "step": 102270 }, { - "epoch": 0.91, - "learning_rate": 4.401855688676696e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.86764278204067e-05, + "loss": 0.1993, "step": 102280 }, { - "epoch": 0.91, - "learning_rate": 4.397351589946852e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.8675309277197383e-05, + "loss": 0.2007, "step": 102290 }, { - "epoch": 0.91, - "learning_rate": 4.392847491217008e-06, - "loss": 0.1773, + "epoch": 0.23, + "learning_rate": 3.867419073398806e-05, + "loss": 0.2002, "step": 102300 }, { - "epoch": 0.91, - "learning_rate": 4.388343392487163e-06, - "loss": 0.1717, + "epoch": 0.23, + "learning_rate": 3.867307219077873e-05, + "loss": 0.1987, "step": 102310 }, { - "epoch": 0.91, - "learning_rate": 4.383839293757319e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.867195364756941e-05, + "loss": 0.1999, "step": 102320 }, { - "epoch": 0.91, - "learning_rate": 4.379335195027475e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.867083510436008e-05, + "loss": 0.2011, "step": 102330 }, { - "epoch": 0.91, - "learning_rate": 4.3748310962976315e-06, - "loss": 0.1813, + "epoch": 0.23, + "learning_rate": 3.866971656115076e-05, + "loss": 0.1996, "step": 102340 }, { - "epoch": 0.91, - "learning_rate": 4.370326997567787e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.866859801794144e-05, + "loss": 0.196, "step": 102350 }, { - "epoch": 0.91, - "learning_rate": 4.365822898837943e-06, - "loss": 0.1703, + "epoch": 0.23, + "learning_rate": 3.866747947473211e-05, + "loss": 0.2019, "step": 102360 }, { - "epoch": 0.91, - "learning_rate": 4.361318800108099e-06, - "loss": 0.177, + "epoch": 0.23, + "learning_rate": 3.8666360931522787e-05, + "loss": 0.2053, "step": 102370 }, { - "epoch": 0.91, - "learning_rate": 4.356814701378254e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.866524238831346e-05, + "loss": 0.2047, "step": 102380 }, { - "epoch": 0.91, - "learning_rate": 4.3523106026484104e-06, - "loss": 0.178, + "epoch": 0.23, + "learning_rate": 3.8664123845104136e-05, + "loss": 0.2027, "step": 102390 }, { - "epoch": 0.91, - "learning_rate": 4.347806503918566e-06, - "loss": 0.1844, + "epoch": 0.23, + "learning_rate": 3.8663005301894814e-05, + "loss": 0.1972, "step": 102400 }, { - "epoch": 0.91, - "learning_rate": 4.343302405188722e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.866188675868549e-05, + "loss": 0.2009, "step": 102410 }, { - "epoch": 0.91, - "learning_rate": 4.338798306458878e-06, - "loss": 0.1709, + "epoch": 0.23, + "learning_rate": 3.866076821547617e-05, + "loss": 0.2075, "step": 102420 }, { - "epoch": 0.91, - "learning_rate": 4.334294207729034e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.865964967226684e-05, + "loss": 0.2015, "step": 102430 }, { - "epoch": 0.91, - "learning_rate": 4.3297901089991894e-06, - "loss": 0.1722, + "epoch": 0.23, + "learning_rate": 3.865853112905752e-05, + "loss": 0.2001, "step": 102440 }, { - "epoch": 0.91, - "learning_rate": 4.325286010269345e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.865741258584819e-05, + "loss": 0.2021, "step": 102450 }, { - "epoch": 0.91, - "learning_rate": 4.320781911539501e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.865629404263887e-05, + "loss": 0.1931, "step": 102460 }, { - "epoch": 0.91, - "learning_rate": 4.316277812809657e-06, - "loss": 0.1738, + "epoch": 0.23, + "learning_rate": 3.8655175499429545e-05, + "loss": 0.1961, "step": 102470 }, { - "epoch": 0.91, - "learning_rate": 4.311773714079813e-06, - "loss": 0.1812, + "epoch": 0.23, + "learning_rate": 3.865405695622022e-05, + "loss": 0.2026, "step": 102480 }, { - "epoch": 0.92, - "learning_rate": 4.3072696153499684e-06, - "loss": 0.1803, + "epoch": 0.23, + "learning_rate": 3.8652938413010895e-05, + "loss": 0.2028, "step": 102490 }, { - "epoch": 0.92, - "learning_rate": 4.302765516620125e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.865181986980157e-05, + "loss": 0.1941, "step": 102500 }, { - "epoch": 0.92, - "learning_rate": 4.298261417890281e-06, - "loss": 0.1809, + "epoch": 0.23, + "learning_rate": 3.865070132659225e-05, + "loss": 0.1936, "step": 102510 }, { - "epoch": 0.92, - "learning_rate": 4.293757319160436e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.864958278338293e-05, + "loss": 0.1927, "step": 102520 }, { - "epoch": 0.92, - "learning_rate": 4.289253220430592e-06, - "loss": 0.1768, + "epoch": 0.23, + "learning_rate": 3.86484642401736e-05, + "loss": 0.1972, "step": 102530 }, { - "epoch": 0.92, - "learning_rate": 4.284749121700747e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.864734569696428e-05, + "loss": 0.2044, "step": 102540 }, { - "epoch": 0.92, - "learning_rate": 4.280245022970904e-06, - "loss": 0.1808, + "epoch": 0.23, + "learning_rate": 3.864622715375495e-05, + "loss": 0.1953, "step": 102550 }, { - "epoch": 0.92, - "learning_rate": 4.27574092424106e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.8645108610545626e-05, + "loss": 0.1969, "step": 102560 }, { - "epoch": 0.92, - "learning_rate": 4.271236825511216e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.8643990067336304e-05, + "loss": 0.2039, "step": 102570 }, { - "epoch": 0.92, - "learning_rate": 4.2667327267813715e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.8642871524126976e-05, + "loss": 0.2028, "step": 102580 }, { - "epoch": 0.92, - "learning_rate": 4.262228628051526e-06, - "loss": 0.1814, + "epoch": 0.23, + "learning_rate": 3.8641752980917653e-05, + "loss": 0.2011, "step": 102590 }, { - "epoch": 0.92, - "learning_rate": 4.257724529321683e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.864063443770833e-05, + "loss": 0.1986, "step": 102600 }, { - "epoch": 0.92, - "learning_rate": 4.253220430591839e-06, - "loss": 0.1741, + "epoch": 0.23, + "learning_rate": 3.863951589449901e-05, + "loss": 0.2001, "step": 102610 }, { - "epoch": 0.92, - "learning_rate": 4.249166741734979e-06, - "loss": 0.1789, + "epoch": 0.23, + "learning_rate": 3.863839735128969e-05, + "loss": 0.205, "step": 102620 }, { - "epoch": 0.92, - "learning_rate": 4.244662643005135e-06, - "loss": 0.1767, + "epoch": 0.23, + "learning_rate": 3.863727880808036e-05, + "loss": 0.1987, "step": 102630 }, { - "epoch": 0.92, - "learning_rate": 4.240158544275291e-06, - "loss": 0.1731, + "epoch": 0.23, + "learning_rate": 3.8636160264871036e-05, + "loss": 0.1965, "step": 102640 }, { - "epoch": 0.92, - "learning_rate": 4.235654445545447e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.863504172166171e-05, + "loss": 0.1992, "step": 102650 }, { - "epoch": 0.92, - "learning_rate": 4.2311503468156024e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.8633923178452385e-05, + "loss": 0.1985, "step": 102660 }, { - "epoch": 0.92, - "learning_rate": 4.226646248085758e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.863280463524306e-05, + "loss": 0.199, "step": 102670 }, { - "epoch": 0.92, - "learning_rate": 4.222142149355914e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.8631686092033735e-05, + "loss": 0.2039, "step": 102680 }, { - "epoch": 0.92, - "learning_rate": 4.21763805062607e-06, - "loss": 0.1741, + "epoch": 0.23, + "learning_rate": 3.863056754882441e-05, + "loss": 0.1952, "step": 102690 }, { - "epoch": 0.92, - "learning_rate": 4.2131339518962265e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.862944900561509e-05, + "loss": 0.2015, "step": 102700 }, { - "epoch": 0.92, - "learning_rate": 4.208629853166381e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.862833046240577e-05, + "loss": 0.2028, "step": 102710 }, { - "epoch": 0.92, - "learning_rate": 4.204125754436537e-06, - "loss": 0.1848, + "epoch": 0.23, + "learning_rate": 3.862721191919644e-05, + "loss": 0.2005, "step": 102720 }, { - "epoch": 0.92, - "learning_rate": 4.199621655706693e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.862609337598712e-05, + "loss": 0.2013, "step": 102730 }, { - "epoch": 0.92, - "learning_rate": 4.195117556976849e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.8624974832777795e-05, + "loss": 0.1964, "step": 102740 }, { - "epoch": 0.92, - "learning_rate": 4.1906134582470055e-06, - "loss": 0.1828, + "epoch": 0.23, + "learning_rate": 3.8623856289568466e-05, + "loss": 0.2027, "step": 102750 }, { - "epoch": 0.92, - "learning_rate": 4.186109359517161e-06, - "loss": 0.1794, + "epoch": 0.23, + "learning_rate": 3.8622737746359144e-05, + "loss": 0.2012, "step": 102760 }, { - "epoch": 0.92, - "learning_rate": 4.181605260787317e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.8621619203149816e-05, + "loss": 0.2001, "step": 102770 }, { - "epoch": 0.92, - "learning_rate": 4.177101162057472e-06, - "loss": 0.177, + "epoch": 0.23, + "learning_rate": 3.8620500659940493e-05, + "loss": 0.2031, "step": 102780 }, { - "epoch": 0.92, - "learning_rate": 4.172597063327628e-06, - "loss": 0.1767, + "epoch": 0.23, + "learning_rate": 3.861938211673117e-05, + "loss": 0.1949, "step": 102790 }, { - "epoch": 0.92, - "learning_rate": 4.1680929645977845e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.861826357352184e-05, + "loss": 0.1975, "step": 102800 }, { - "epoch": 0.92, - "learning_rate": 4.16358886586794e-06, - "loss": 0.1851, + "epoch": 0.23, + "learning_rate": 3.861714503031252e-05, + "loss": 0.1982, "step": 102810 }, { - "epoch": 0.92, - "learning_rate": 4.159084767138096e-06, - "loss": 0.1811, + "epoch": 0.23, + "learning_rate": 3.86160264871032e-05, + "loss": 0.2053, "step": 102820 }, { - "epoch": 0.92, - "learning_rate": 4.154580668408252e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.8614907943893876e-05, + "loss": 0.2021, "step": 102830 }, { - "epoch": 0.92, - "learning_rate": 4.150076569678408e-06, - "loss": 0.1828, + "epoch": 0.23, + "learning_rate": 3.8613789400684554e-05, + "loss": 0.2028, "step": 102840 }, { - "epoch": 0.92, - "learning_rate": 4.1455724709485634e-06, - "loss": 0.1792, + "epoch": 0.23, + "learning_rate": 3.8612670857475225e-05, + "loss": 0.1968, "step": 102850 }, { - "epoch": 0.92, - "learning_rate": 4.141068372218719e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.86115523142659e-05, + "loss": 0.2024, "step": 102860 }, { - "epoch": 0.92, - "learning_rate": 4.136564273488875e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.8610433771056574e-05, + "loss": 0.1961, "step": 102870 }, { - "epoch": 0.92, - "learning_rate": 4.132060174759031e-06, - "loss": 0.1762, + "epoch": 0.23, + "learning_rate": 3.860931522784725e-05, + "loss": 0.1976, "step": 102880 }, { - "epoch": 0.92, - "learning_rate": 4.127556076029187e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.860819668463793e-05, + "loss": 0.2017, "step": 102890 }, { - "epoch": 0.92, - "learning_rate": 4.1230519772993424e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.86070781414286e-05, + "loss": 0.1995, "step": 102900 }, { - "epoch": 0.92, - "learning_rate": 4.118547878569499e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.860595959821928e-05, + "loss": 0.1932, "step": 102910 }, { - "epoch": 0.92, - "learning_rate": 4.114043779839654e-06, - "loss": 0.1704, + "epoch": 0.23, + "learning_rate": 3.860484105500996e-05, + "loss": 0.1981, "step": 102920 }, { - "epoch": 0.92, - "learning_rate": 4.10953968110981e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.8603722511800635e-05, + "loss": 0.1958, "step": 102930 }, { - "epoch": 0.92, - "learning_rate": 4.105035582379966e-06, - "loss": 0.1734, + "epoch": 0.23, + "learning_rate": 3.860260396859131e-05, + "loss": 0.196, "step": 102940 }, { - "epoch": 0.92, - "learning_rate": 4.100531483650122e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.8601485425381984e-05, + "loss": 0.2018, "step": 102950 }, { - "epoch": 0.92, - "learning_rate": 4.096027384920278e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.860036688217266e-05, + "loss": 0.2048, "step": 102960 }, { - "epoch": 0.92, - "learning_rate": 4.091523286190434e-06, - "loss": 0.1734, + "epoch": 0.23, + "learning_rate": 3.8599248338963333e-05, + "loss": 0.1958, "step": 102970 }, { - "epoch": 0.92, - "learning_rate": 4.08701918746059e-06, - "loss": 0.1759, + "epoch": 0.23, + "learning_rate": 3.859812979575401e-05, + "loss": 0.2023, "step": 102980 }, { - "epoch": 0.92, - "learning_rate": 4.082515088730745e-06, - "loss": 0.1805, + "epoch": 0.23, + "learning_rate": 3.859701125254469e-05, + "loss": 0.2, "step": 102990 }, { - "epoch": 0.92, - "learning_rate": 4.078010990000901e-06, - "loss": 0.1717, + "epoch": 0.23, + "learning_rate": 3.859589270933536e-05, + "loss": 0.1946, "step": 103000 }, { - "epoch": 0.92, - "learning_rate": 4.073506891271057e-06, - "loss": 0.18, + "epoch": 0.23, + "learning_rate": 3.859477416612604e-05, + "loss": 0.2035, "step": 103010 }, { - "epoch": 0.92, - "learning_rate": 4.069002792541213e-06, - "loss": 0.1769, + "epoch": 0.23, + "learning_rate": 3.8593655622916716e-05, + "loss": 0.2033, "step": 103020 }, { - "epoch": 0.92, - "learning_rate": 4.064498693811369e-06, - "loss": 0.1721, + "epoch": 0.23, + "learning_rate": 3.8592537079707394e-05, + "loss": 0.1938, "step": 103030 }, { - "epoch": 0.92, - "learning_rate": 4.0599945950815245e-06, - "loss": 0.1688, + "epoch": 0.23, + "learning_rate": 3.8591418536498065e-05, + "loss": 0.202, "step": 103040 }, { - "epoch": 0.92, - "learning_rate": 4.05549049635168e-06, - "loss": 0.1744, + "epoch": 0.23, + "learning_rate": 3.859029999328874e-05, + "loss": 0.2035, "step": 103050 }, { - "epoch": 0.92, - "learning_rate": 4.050986397621836e-06, - "loss": 0.1808, + "epoch": 0.23, + "learning_rate": 3.858918145007942e-05, + "loss": 0.205, "step": 103060 }, { - "epoch": 0.92, - "learning_rate": 4.046482298891992e-06, - "loss": 0.1814, + "epoch": 0.23, + "learning_rate": 3.858806290687009e-05, + "loss": 0.1949, "step": 103070 }, { - "epoch": 0.92, - "learning_rate": 4.041978200162148e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.858694436366077e-05, + "loss": 0.2015, "step": 103080 }, { - "epoch": 0.92, - "learning_rate": 4.0374741014323034e-06, - "loss": 0.1726, + "epoch": 0.23, + "learning_rate": 3.858582582045144e-05, + "loss": 0.2027, "step": 103090 }, { - "epoch": 0.92, - "learning_rate": 4.032970002702459e-06, - "loss": 0.1723, + "epoch": 0.23, + "learning_rate": 3.858470727724212e-05, + "loss": 0.2005, "step": 103100 }, { - "epoch": 0.92, - "learning_rate": 4.028465903972616e-06, - "loss": 0.178, + "epoch": 0.23, + "learning_rate": 3.85835887340328e-05, + "loss": 0.1955, "step": 103110 }, { - "epoch": 0.92, - "learning_rate": 4.023961805242771e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.8582470190823475e-05, + "loss": 0.2015, "step": 103120 }, { - "epoch": 0.92, - "learning_rate": 4.019457706512927e-06, - "loss": 0.1727, + "epoch": 0.23, + "learning_rate": 3.858135164761415e-05, + "loss": 0.1996, "step": 103130 }, { - "epoch": 0.92, - "learning_rate": 4.0149536077830824e-06, - "loss": 0.1861, + "epoch": 0.23, + "learning_rate": 3.8580233104404824e-05, + "loss": 0.1989, "step": 103140 }, { - "epoch": 0.92, - "learning_rate": 4.010449509053238e-06, - "loss": 0.1739, + "epoch": 0.23, + "learning_rate": 3.85791145611955e-05, + "loss": 0.1993, "step": 103150 }, { - "epoch": 0.92, - "learning_rate": 4.005945410323395e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.857799601798618e-05, + "loss": 0.2012, "step": 103160 }, { - "epoch": 0.92, - "learning_rate": 4.001441311593551e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.857687747477685e-05, + "loss": 0.1999, "step": 103170 }, { - "epoch": 0.92, - "learning_rate": 3.9969372128637065e-06, - "loss": 0.1811, + "epoch": 0.23, + "learning_rate": 3.857575893156753e-05, + "loss": 0.2006, "step": 103180 }, { - "epoch": 0.92, - "learning_rate": 3.9924331141338614e-06, - "loss": 0.1734, + "epoch": 0.23, + "learning_rate": 3.85746403883582e-05, + "loss": 0.2018, "step": 103190 }, { - "epoch": 0.92, - "learning_rate": 3.987929015404017e-06, - "loss": 0.1759, + "epoch": 0.23, + "learning_rate": 3.857352184514888e-05, + "loss": 0.1961, "step": 103200 }, { - "epoch": 0.92, - "learning_rate": 3.983424916674174e-06, - "loss": 0.182, + "epoch": 0.23, + "learning_rate": 3.8572403301939556e-05, + "loss": 0.2005, "step": 103210 }, { - "epoch": 0.92, - "learning_rate": 3.97892081794433e-06, - "loss": 0.1791, + "epoch": 0.23, + "learning_rate": 3.857128475873023e-05, + "loss": 0.2022, "step": 103220 }, { - "epoch": 0.92, - "learning_rate": 3.9744167192144855e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.8570166215520905e-05, + "loss": 0.2016, "step": 103230 }, { - "epoch": 0.92, - "learning_rate": 3.969912620484641e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.856904767231158e-05, + "loss": 0.2056, "step": 103240 }, { - "epoch": 0.92, - "learning_rate": 3.965408521754797e-06, - "loss": 0.1821, + "epoch": 0.23, + "learning_rate": 3.856792912910226e-05, + "loss": 0.2018, "step": 103250 }, { - "epoch": 0.92, - "learning_rate": 3.960904423024953e-06, - "loss": 0.1737, + "epoch": 0.23, + "learning_rate": 3.856681058589294e-05, + "loss": 0.2014, "step": 103260 }, { - "epoch": 0.92, - "learning_rate": 3.956400324295109e-06, - "loss": 0.1752, + "epoch": 0.23, + "learning_rate": 3.856569204268361e-05, + "loss": 0.2004, "step": 103270 }, { - "epoch": 0.92, - "learning_rate": 3.9518962255652645e-06, - "loss": 0.1743, + "epoch": 0.23, + "learning_rate": 3.856457349947429e-05, + "loss": 0.2066, "step": 103280 }, { - "epoch": 0.92, - "learning_rate": 3.94739212683542e-06, - "loss": 0.1742, + "epoch": 0.23, + "learning_rate": 3.856345495626496e-05, + "loss": 0.2011, "step": 103290 }, { - "epoch": 0.92, - "learning_rate": 3.942888028105576e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.856233641305564e-05, + "loss": 0.2017, "step": 103300 }, { - "epoch": 0.92, - "learning_rate": 3.938383929375733e-06, - "loss": 0.1733, + "epoch": 0.23, + "learning_rate": 3.8561217869846315e-05, + "loss": 0.2019, "step": 103310 }, { - "epoch": 0.92, - "learning_rate": 3.9338798306458885e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.8560099326636986e-05, + "loss": 0.2038, "step": 103320 }, { - "epoch": 0.92, - "learning_rate": 3.9293757319160434e-06, - "loss": 0.1756, + "epoch": 0.23, + "learning_rate": 3.8558980783427664e-05, + "loss": 0.1961, "step": 103330 }, { - "epoch": 0.92, - "learning_rate": 3.924871633186199e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.855786224021834e-05, + "loss": 0.198, "step": 103340 }, { - "epoch": 0.92, - "learning_rate": 3.920367534456355e-06, - "loss": 0.1807, + "epoch": 0.23, + "learning_rate": 3.855674369700902e-05, + "loss": 0.1996, "step": 103350 }, { - "epoch": 0.92, - "learning_rate": 3.915863435726512e-06, - "loss": 0.1715, + "epoch": 0.23, + "learning_rate": 3.855562515379969e-05, + "loss": 0.2008, "step": 103360 }, { - "epoch": 0.92, - "learning_rate": 3.9113593369966675e-06, - "loss": 0.179, + "epoch": 0.23, + "learning_rate": 3.855450661059037e-05, + "loss": 0.1993, "step": 103370 }, { - "epoch": 0.92, - "learning_rate": 3.906855238266823e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.855338806738105e-05, + "loss": 0.2068, "step": 103380 }, { - "epoch": 0.92, - "learning_rate": 3.902351139536979e-06, - "loss": 0.1736, + "epoch": 0.23, + "learning_rate": 3.855226952417172e-05, + "loss": 0.1984, "step": 103390 }, { - "epoch": 0.92, - "learning_rate": 3.897847040807134e-06, - "loss": 0.1793, + "epoch": 0.23, + "learning_rate": 3.8551150980962396e-05, + "loss": 0.2001, "step": 103400 }, { - "epoch": 0.92, - "learning_rate": 3.893342942077291e-06, - "loss": 0.1787, + "epoch": 0.23, + "learning_rate": 3.855003243775307e-05, + "loss": 0.197, "step": 103410 }, { - "epoch": 0.92, - "learning_rate": 3.8888388433474465e-06, - "loss": 0.1719, + "epoch": 0.23, + "learning_rate": 3.8548913894543745e-05, + "loss": 0.1994, "step": 103420 }, { - "epoch": 0.92, - "learning_rate": 3.884334744617602e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.854779535133442e-05, + "loss": 0.1991, "step": 103430 }, { - "epoch": 0.92, - "learning_rate": 3.879830645887758e-06, - "loss": 0.1755, + "epoch": 0.23, + "learning_rate": 3.85466768081251e-05, + "loss": 0.2044, "step": 103440 }, { - "epoch": 0.92, - "learning_rate": 3.875326547157914e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.854555826491578e-05, + "loss": 0.1996, "step": 103450 }, { - "epoch": 0.92, - "learning_rate": 3.87082244842807e-06, - "loss": 0.1737, + "epoch": 0.23, + "learning_rate": 3.854443972170645e-05, + "loss": 0.2015, "step": 103460 }, { - "epoch": 0.92, - "learning_rate": 3.8663183496982255e-06, - "loss": 0.175, + "epoch": 0.23, + "learning_rate": 3.854332117849713e-05, + "loss": 0.2005, "step": 103470 }, { - "epoch": 0.92, - "learning_rate": 3.861814250968381e-06, - "loss": 0.174, + "epoch": 0.23, + "learning_rate": 3.8542202635287806e-05, + "loss": 0.1968, "step": 103480 }, { - "epoch": 0.92, - "learning_rate": 3.857310152238537e-06, - "loss": 0.1727, + "epoch": 0.23, + "learning_rate": 3.854108409207848e-05, + "loss": 0.1951, "step": 103490 }, { - "epoch": 0.92, - "learning_rate": 3.852806053508693e-06, - "loss": 0.1695, + "epoch": 0.23, + "learning_rate": 3.8539965548869155e-05, + "loss": 0.1973, "step": 103500 }, { - "epoch": 0.92, - "learning_rate": 3.848301954778849e-06, - "loss": 0.1789, + "epoch": 0.23, + "learning_rate": 3.8538847005659826e-05, + "loss": 0.2037, "step": 103510 }, { - "epoch": 0.92, - "learning_rate": 3.843797856049005e-06, - "loss": 0.1798, + "epoch": 0.23, + "learning_rate": 3.8537728462450504e-05, + "loss": 0.1997, "step": 103520 }, { - "epoch": 0.92, - "learning_rate": 3.839293757319161e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.853660991924118e-05, + "loss": 0.2023, "step": 103530 }, { - "epoch": 0.92, - "learning_rate": 3.834789658589316e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.853549137603186e-05, + "loss": 0.1995, "step": 103540 }, { - "epoch": 0.92, - "learning_rate": 3.830285559859472e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.853437283282254e-05, + "loss": 0.1926, "step": 103550 }, { - "epoch": 0.92, - "learning_rate": 3.825781461129628e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.853325428961321e-05, + "loss": 0.1956, "step": 103560 }, { - "epoch": 0.92, - "learning_rate": 3.821277362399784e-06, - "loss": 0.174, + "epoch": 0.23, + "learning_rate": 3.853213574640389e-05, + "loss": 0.1984, "step": 103570 }, { - "epoch": 0.92, - "learning_rate": 3.81677326366994e-06, - "loss": 0.1694, + "epoch": 0.23, + "learning_rate": 3.8531017203194565e-05, + "loss": 0.1963, "step": 103580 }, { - "epoch": 0.92, - "learning_rate": 3.812269164940096e-06, - "loss": 0.173, + "epoch": 0.23, + "learning_rate": 3.8529898659985236e-05, + "loss": 0.1997, "step": 103590 }, { - "epoch": 0.92, - "learning_rate": 3.8077650662102517e-06, - "loss": 0.1792, + "epoch": 0.23, + "learning_rate": 3.8528780116775914e-05, + "loss": 0.1995, "step": 103600 }, { - "epoch": 0.93, - "learning_rate": 3.803260967480407e-06, - "loss": 0.1825, + "epoch": 0.23, + "learning_rate": 3.852777342788752e-05, + "loss": 0.1995, "step": 103610 }, { - "epoch": 0.93, - "learning_rate": 3.798756868750563e-06, - "loss": 0.1759, + "epoch": 0.23, + "learning_rate": 3.85266548846782e-05, + "loss": 0.1926, "step": 103620 }, { - "epoch": 0.93, - "learning_rate": 3.794252770020719e-06, - "loss": 0.1749, + "epoch": 0.23, + "learning_rate": 3.852553634146887e-05, + "loss": 0.1961, "step": 103630 }, { - "epoch": 0.93, - "learning_rate": 3.789748671290875e-06, - "loss": 0.1775, + "epoch": 0.23, + "learning_rate": 3.852441779825955e-05, + "loss": 0.202, "step": 103640 }, { - "epoch": 0.93, - "learning_rate": 3.7852445725610307e-06, - "loss": 0.1744, + "epoch": 0.23, + "learning_rate": 3.852329925505023e-05, + "loss": 0.1988, "step": 103650 }, { - "epoch": 0.93, - "learning_rate": 3.780740473831187e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.85221807118409e-05, + "loss": 0.2007, "step": 103660 }, { - "epoch": 0.93, - "learning_rate": 3.7762363751013427e-06, - "loss": 0.1729, + "epoch": 0.23, + "learning_rate": 3.852106216863158e-05, + "loss": 0.2015, "step": 103670 }, { - "epoch": 0.93, - "learning_rate": 3.771732276371498e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.851994362542225e-05, + "loss": 0.205, "step": 103680 }, { - "epoch": 0.93, - "learning_rate": 3.767228177641654e-06, - "loss": 0.1773, + "epoch": 0.23, + "learning_rate": 3.8518825082212926e-05, + "loss": 0.1988, "step": 103690 }, { - "epoch": 0.93, - "learning_rate": 3.7627240789118097e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.8517706539003604e-05, + "loss": 0.195, "step": 103700 }, { - "epoch": 0.93, - "learning_rate": 3.758219980181966e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.851658799579428e-05, + "loss": 0.2013, "step": 103710 }, { - "epoch": 0.93, - "learning_rate": 3.7537158814521217e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.851546945258496e-05, + "loss": 0.2032, "step": 103720 }, { - "epoch": 0.93, - "learning_rate": 3.7492117827222775e-06, - "loss": 0.1775, + "epoch": 0.23, + "learning_rate": 3.851435090937563e-05, + "loss": 0.1964, "step": 103730 }, { - "epoch": 0.93, - "learning_rate": 3.7447076839924337e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.851323236616631e-05, + "loss": 0.1992, "step": 103740 }, { - "epoch": 0.93, - "learning_rate": 3.7402035852625887e-06, - "loss": 0.1738, + "epoch": 0.23, + "learning_rate": 3.851211382295698e-05, + "loss": 0.1971, "step": 103750 }, { - "epoch": 0.93, - "learning_rate": 3.735699486532745e-06, - "loss": 0.177, + "epoch": 0.23, + "learning_rate": 3.851099527974766e-05, + "loss": 0.1998, "step": 103760 }, { - "epoch": 0.93, - "learning_rate": 3.7311953878029007e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.8509876736538336e-05, + "loss": 0.1963, "step": 103770 }, { - "epoch": 0.93, - "learning_rate": 3.7266912890730565e-06, - "loss": 0.1741, + "epoch": 0.23, + "learning_rate": 3.850875819332901e-05, + "loss": 0.1951, "step": 103780 }, { - "epoch": 0.93, - "learning_rate": 3.7221871903432127e-06, - "loss": 0.172, + "epoch": 0.23, + "learning_rate": 3.8507639650119685e-05, + "loss": 0.1993, "step": 103790 }, { - "epoch": 0.93, - "learning_rate": 3.7176830916133685e-06, - "loss": 0.1746, + "epoch": 0.23, + "learning_rate": 3.8506521106910356e-05, + "loss": 0.2, "step": 103800 }, { - "epoch": 0.93, - "learning_rate": 3.7131789928835243e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.8505402563701034e-05, + "loss": 0.1982, "step": 103810 }, { - "epoch": 0.93, - "learning_rate": 3.7086748941536797e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.850428402049172e-05, + "loss": 0.2012, "step": 103820 }, { - "epoch": 0.93, - "learning_rate": 3.704170795423836e-06, - "loss": 0.1773, + "epoch": 0.23, + "learning_rate": 3.850316547728239e-05, + "loss": 0.2004, "step": 103830 }, { - "epoch": 0.93, - "learning_rate": 3.6996666966939917e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.850204693407307e-05, + "loss": 0.1934, "step": 103840 }, { - "epoch": 0.93, - "learning_rate": 3.6951625979641475e-06, - "loss": 0.1787, + "epoch": 0.23, + "learning_rate": 3.850092839086374e-05, + "loss": 0.1926, "step": 103850 }, { - "epoch": 0.93, - "learning_rate": 3.6906584992343037e-06, - "loss": 0.1726, + "epoch": 0.23, + "learning_rate": 3.849980984765442e-05, + "loss": 0.1988, "step": 103860 }, { - "epoch": 0.93, - "learning_rate": 3.6861544005044595e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.8498691304445095e-05, + "loss": 0.2018, "step": 103870 }, { - "epoch": 0.93, - "learning_rate": 3.6816503017746153e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.8497572761235766e-05, + "loss": 0.2016, "step": 103880 }, { - "epoch": 0.93, - "learning_rate": 3.6771462030447707e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.8496454218026444e-05, + "loss": 0.2008, "step": 103890 }, { - "epoch": 0.93, - "learning_rate": 3.6726421043149265e-06, - "loss": 0.1787, + "epoch": 0.23, + "learning_rate": 3.8495335674817115e-05, + "loss": 0.1967, "step": 103900 }, { - "epoch": 0.93, - "learning_rate": 3.6681380055850827e-06, - "loss": 0.1826, + "epoch": 0.23, + "learning_rate": 3.849421713160779e-05, + "loss": 0.1969, "step": 103910 }, { - "epoch": 0.93, - "learning_rate": 3.6636339068552385e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.849309858839847e-05, + "loss": 0.1997, "step": 103920 }, { - "epoch": 0.93, - "learning_rate": 3.6591298081253943e-06, - "loss": 0.1738, + "epoch": 0.23, + "learning_rate": 3.849198004518915e-05, + "loss": 0.1948, "step": 103930 }, { - "epoch": 0.93, - "learning_rate": 3.6546257093955505e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.849086150197983e-05, + "loss": 0.1993, "step": 103940 }, { - "epoch": 0.93, - "learning_rate": 3.6501216106657063e-06, - "loss": 0.1765, + "epoch": 0.23, + "learning_rate": 3.84897429587705e-05, + "loss": 0.1954, "step": 103950 }, { - "epoch": 0.93, - "learning_rate": 3.6456175119358617e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.8488624415561176e-05, + "loss": 0.1977, "step": 103960 }, { - "epoch": 0.93, - "learning_rate": 3.6411134132060175e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.8487505872351854e-05, + "loss": 0.204, "step": 103970 }, { - "epoch": 0.93, - "learning_rate": 3.6366093144761733e-06, - "loss": 0.1804, + "epoch": 0.23, + "learning_rate": 3.8486387329142525e-05, + "loss": 0.1973, "step": 103980 }, { - "epoch": 0.93, - "learning_rate": 3.6321052157463295e-06, - "loss": 0.1772, + "epoch": 0.23, + "learning_rate": 3.84852687859332e-05, + "loss": 0.1955, "step": 103990 }, { - "epoch": 0.93, - "learning_rate": 3.6276011170164853e-06, - "loss": 0.1796, - "step": 104000 - }, - { - "epoch": 0.93, - "eval_NEIMS_canon_smiles": 0.9435833333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.07121666666666666, - "eval_NEIMS_daylight_tanimoto_simil": 0.47393896052800716, - "eval_NEIMS_exact_mols": 0.07103333333333334, - "eval_NEIMS_exact_smiles": 0.06931666666666667, - "eval_NEIMS_loss": 0.20564579963684082, - "eval_NEIMS_matched_formulas": 0.6034666666666667, - "eval_NEIMS_morgan_tanimoto_simil": 0.3786909203467994, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0714, - "eval_NEIMS_runtime": 714.9764, - "eval_NEIMS_samples_per_second": 83.919, - "eval_NEIMS_steps_per_second": 1.312, - "step": 104000 - }, - { - "epoch": 0.93, - "eval_RASSP_canon_smiles": 0.9392092697098207, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.1658596854442849, - "eval_RASSP_daylight_tanimoto_simil": 0.6079714885990567, - "eval_RASSP_exact_mols": 0.1652419274050823, - "eval_RASSP_exact_smiles": 0.16050021705012188, - "eval_RASSP_loss": 0.14461752772331238, - "eval_RASSP_matched_formulas": 0.7783584332320432, - "eval_RASSP_morgan_tanimoto_simil": 0.48231341268363775, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.16542558520052092, - "eval_RASSP_runtime": 816.0852, - "eval_RASSP_samples_per_second": 73.392, - "eval_RASSP_steps_per_second": 1.147, - "step": 104000 - }, - { - "epoch": 0.93, - "eval_NIST_canon_smiles": 0.8845867196649749, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.013805586116336019, - "eval_NIST_daylight_tanimoto_simil": 0.272257324898437, - "eval_NIST_exact_mols": 0.013486176668914362, - "eval_NIST_exact_smiles": 0.012598928203854207, - "eval_NIST_loss": 1.4478906393051147, - "eval_NIST_matched_formulas": 0.09422578698938851, - "eval_NIST_morgan_tanimoto_simil": 0.22477003460350337, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.013947545870745644, - "eval_NIST_runtime": 472.0033, - "eval_NIST_samples_per_second": 59.697, - "eval_NIST_steps_per_second": 0.934, + "epoch": 0.23, + "learning_rate": 3.8484150242723874e-05, + "loss": 0.1972, "step": 104000 }, { - "epoch": 0.93, - "learning_rate": 3.623097018286641e-06, - "loss": 0.1807, + "epoch": 0.23, + "learning_rate": 3.848303169951455e-05, + "loss": 0.1966, "step": 104010 }, { - "epoch": 0.93, - "learning_rate": 3.6185929195567973e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.848191315630523e-05, + "loss": 0.1995, "step": 104020 }, { - "epoch": 0.93, - "learning_rate": 3.6140888208269523e-06, - "loss": 0.172, + "epoch": 0.23, + "learning_rate": 3.848079461309591e-05, + "loss": 0.198, "step": 104030 }, { - "epoch": 0.93, - "learning_rate": 3.6095847220971085e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.8479676069886586e-05, + "loss": 0.194, "step": 104040 }, { - "epoch": 0.93, - "learning_rate": 3.6050806233672643e-06, - "loss": 0.1718, + "epoch": 0.23, + "learning_rate": 3.847855752667726e-05, + "loss": 0.1974, "step": 104050 }, { - "epoch": 0.93, - "learning_rate": 3.60057652463742e-06, - "loss": 0.1692, + "epoch": 0.23, + "learning_rate": 3.8477438983467935e-05, + "loss": 0.195, "step": 104060 }, { - "epoch": 0.93, - "learning_rate": 3.5960724259075763e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.8476320440258606e-05, + "loss": 0.2017, "step": 104070 }, { - "epoch": 0.93, - "learning_rate": 3.591568327177732e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.8475201897049284e-05, + "loss": 0.2, "step": 104080 }, { - "epoch": 0.93, - "learning_rate": 3.587064228447888e-06, - "loss": 0.1749, + "epoch": 0.23, + "learning_rate": 3.847408335383996e-05, + "loss": 0.202, "step": 104090 }, { - "epoch": 0.93, - "learning_rate": 3.5825601297180433e-06, - "loss": 0.1801, + "epoch": 0.23, + "learning_rate": 3.847296481063063e-05, + "loss": 0.1937, "step": 104100 }, { - "epoch": 0.93, - "learning_rate": 3.578056030988199e-06, - "loss": 0.1785, + "epoch": 0.23, + "learning_rate": 3.847184626742131e-05, + "loss": 0.1972, "step": 104110 }, { - "epoch": 0.93, - "learning_rate": 3.5735519322583553e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.847072772421199e-05, + "loss": 0.1954, "step": 104120 }, { - "epoch": 0.93, - "learning_rate": 3.569047833528511e-06, - "loss": 0.1775, + "epoch": 0.23, + "learning_rate": 3.846960918100267e-05, + "loss": 0.1997, "step": 104130 }, { - "epoch": 0.93, - "learning_rate": 3.564543734798667e-06, - "loss": 0.1746, + "epoch": 0.23, + "learning_rate": 3.8468490637793345e-05, + "loss": 0.1988, "step": 104140 }, { - "epoch": 0.93, - "learning_rate": 3.560039636068823e-06, - "loss": 0.1785, + "epoch": 0.23, + "learning_rate": 3.8467372094584016e-05, + "loss": 0.1988, "step": 104150 }, { - "epoch": 0.93, - "learning_rate": 3.555535537338979e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.8466253551374694e-05, + "loss": 0.2006, "step": 104160 }, { - "epoch": 0.93, - "learning_rate": 3.5510314386091343e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.8465135008165365e-05, + "loss": 0.1989, "step": 104170 }, { - "epoch": 0.93, - "learning_rate": 3.54652733987929e-06, - "loss": 0.1775, + "epoch": 0.23, + "learning_rate": 3.846401646495604e-05, + "loss": 0.2003, "step": 104180 }, { - "epoch": 0.93, - "learning_rate": 3.5420232411494463e-06, - "loss": 0.1851, + "epoch": 0.23, + "learning_rate": 3.846289792174672e-05, + "loss": 0.1974, "step": 104190 }, { - "epoch": 0.93, - "learning_rate": 3.537519142419602e-06, - "loss": 0.1785, + "epoch": 0.23, + "learning_rate": 3.846177937853739e-05, + "loss": 0.1976, "step": 104200 }, { - "epoch": 0.93, - "learning_rate": 3.533015043689758e-06, - "loss": 0.1728, + "epoch": 0.23, + "learning_rate": 3.846066083532807e-05, + "loss": 0.1995, "step": 104210 }, { - "epoch": 0.93, - "learning_rate": 3.528510944959914e-06, - "loss": 0.1788, + "epoch": 0.23, + "learning_rate": 3.845954229211874e-05, + "loss": 0.2044, "step": 104220 }, { - "epoch": 0.93, - "learning_rate": 3.524006846230069e-06, - "loss": 0.1729, + "epoch": 0.23, + "learning_rate": 3.8458423748909426e-05, + "loss": 0.1993, "step": 104230 }, { - "epoch": 0.93, - "learning_rate": 3.5195027475002253e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.8457305205700104e-05, + "loss": 0.1957, "step": 104240 }, { - "epoch": 0.93, - "learning_rate": 3.514998648770381e-06, - "loss": 0.1715, + "epoch": 0.23, + "learning_rate": 3.8456186662490775e-05, + "loss": 0.1953, "step": 104250 }, { - "epoch": 0.93, - "learning_rate": 3.510494550040537e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.845506811928145e-05, + "loss": 0.1954, "step": 104260 }, { - "epoch": 0.93, - "learning_rate": 3.505990451310693e-06, - "loss": 0.1725, + "epoch": 0.23, + "learning_rate": 3.8453949576072124e-05, + "loss": 0.1957, "step": 104270 }, { - "epoch": 0.93, - "learning_rate": 3.501486352580849e-06, - "loss": 0.1737, + "epoch": 0.23, + "learning_rate": 3.84528310328628e-05, + "loss": 0.2039, "step": 104280 }, { - "epoch": 0.93, - "learning_rate": 3.4969822538510047e-06, - "loss": 0.1746, + "epoch": 0.23, + "learning_rate": 3.845171248965348e-05, + "loss": 0.1956, "step": 104290 }, { - "epoch": 0.93, - "learning_rate": 3.49247815512116e-06, - "loss": 0.178, + "epoch": 0.23, + "learning_rate": 3.845059394644415e-05, + "loss": 0.2008, "step": 104300 }, { - "epoch": 0.93, - "learning_rate": 3.487974056391316e-06, - "loss": 0.1796, + "epoch": 0.23, + "learning_rate": 3.844947540323483e-05, + "loss": 0.2005, "step": 104310 }, { - "epoch": 0.93, - "learning_rate": 3.483469957661472e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.84483568600255e-05, + "loss": 0.1964, "step": 104320 }, { - "epoch": 0.93, - "learning_rate": 3.478965858931628e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.844723831681618e-05, + "loss": 0.2042, "step": 104330 }, { - "epoch": 0.93, - "learning_rate": 3.4744617602017837e-06, - "loss": 0.1779, + "epoch": 0.23, + "learning_rate": 3.8446119773606856e-05, + "loss": 0.193, "step": 104340 }, { - "epoch": 0.93, - "learning_rate": 3.46995766147194e-06, - "loss": 0.1703, + "epoch": 0.23, + "learning_rate": 3.8445001230397534e-05, + "loss": 0.2013, "step": 104350 }, { - "epoch": 0.93, - "learning_rate": 3.4654535627420957e-06, - "loss": 0.1688, + "epoch": 0.23, + "learning_rate": 3.844388268718821e-05, + "loss": 0.1945, "step": 104360 }, { - "epoch": 0.93, - "learning_rate": 3.460949464012251e-06, - "loss": 0.1794, + "epoch": 0.23, + "learning_rate": 3.844276414397888e-05, + "loss": 0.1927, "step": 104370 }, { - "epoch": 0.93, - "learning_rate": 3.456445365282407e-06, - "loss": 0.1791, + "epoch": 0.23, + "learning_rate": 3.844164560076956e-05, + "loss": 0.1944, "step": 104380 }, { - "epoch": 0.93, - "learning_rate": 3.4519412665525627e-06, - "loss": 0.1791, + "epoch": 0.23, + "learning_rate": 3.844052705756023e-05, + "loss": 0.1973, "step": 104390 }, { - "epoch": 0.93, - "learning_rate": 3.447437167822719e-06, - "loss": 0.18, + "epoch": 0.23, + "learning_rate": 3.843940851435091e-05, + "loss": 0.1954, "step": 104400 }, { - "epoch": 0.93, - "learning_rate": 3.4429330690928747e-06, - "loss": 0.175, + "epoch": 0.23, + "learning_rate": 3.843828997114159e-05, + "loss": 0.2018, "step": 104410 }, { - "epoch": 0.93, - "learning_rate": 3.4384289703630305e-06, - "loss": 0.1716, + "epoch": 0.23, + "learning_rate": 3.843717142793226e-05, + "loss": 0.2017, "step": 104420 }, { - "epoch": 0.93, - "learning_rate": 3.4339248716331867e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.843605288472294e-05, + "loss": 0.1992, "step": 104430 }, { - "epoch": 0.93, - "learning_rate": 3.4294207729033417e-06, - "loss": 0.1721, + "epoch": 0.23, + "learning_rate": 3.8434934341513615e-05, + "loss": 0.1993, "step": 104440 }, { - "epoch": 0.93, - "learning_rate": 3.424916674173498e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.843381579830429e-05, + "loss": 0.1992, "step": 104450 }, { - "epoch": 0.93, - "learning_rate": 3.4204125754436537e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.843269725509497e-05, + "loss": 0.2012, "step": 104460 }, { - "epoch": 0.93, - "learning_rate": 3.4159084767138095e-06, - "loss": 0.1774, + "epoch": 0.23, + "learning_rate": 3.843157871188564e-05, + "loss": 0.1963, "step": 104470 }, { - "epoch": 0.93, - "learning_rate": 3.4114043779839657e-06, - "loss": 0.1767, + "epoch": 0.23, + "learning_rate": 3.843046016867632e-05, + "loss": 0.1939, "step": 104480 }, { - "epoch": 0.93, - "learning_rate": 3.4069002792541215e-06, - "loss": 0.1744, + "epoch": 0.23, + "learning_rate": 3.842934162546699e-05, + "loss": 0.1994, "step": 104490 }, { - "epoch": 0.93, - "learning_rate": 3.4023961805242773e-06, - "loss": 0.1769, + "epoch": 0.23, + "learning_rate": 3.842822308225767e-05, + "loss": 0.1974, "step": 104500 }, { - "epoch": 0.93, - "learning_rate": 3.3978920817944327e-06, - "loss": 0.1719, + "epoch": 0.23, + "learning_rate": 3.842710453904835e-05, + "loss": 0.1961, "step": 104510 }, { - "epoch": 0.93, - "learning_rate": 3.393387983064589e-06, - "loss": 0.1703, + "epoch": 0.23, + "learning_rate": 3.842598599583902e-05, + "loss": 0.1965, "step": 104520 }, { - "epoch": 0.93, - "learning_rate": 3.3888838843347447e-06, - "loss": 0.1713, + "epoch": 0.23, + "learning_rate": 3.8424867452629696e-05, + "loss": 0.1953, "step": 104530 }, { - "epoch": 0.93, - "learning_rate": 3.3843797856049005e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.8423748909420374e-05, + "loss": 0.2032, "step": 104540 }, { - "epoch": 0.93, - "learning_rate": 3.3798756868750567e-06, - "loss": 0.176, + "epoch": 0.23, + "learning_rate": 3.842263036621105e-05, + "loss": 0.201, "step": 104550 }, { - "epoch": 0.93, - "learning_rate": 3.3753715881452125e-06, - "loss": 0.1689, + "epoch": 0.23, + "learning_rate": 3.842151182300173e-05, + "loss": 0.2031, "step": 104560 }, { - "epoch": 0.93, - "learning_rate": 3.3708674894153683e-06, - "loss": 0.1792, + "epoch": 0.23, + "learning_rate": 3.84203932797924e-05, + "loss": 0.2017, "step": 104570 }, { - "epoch": 0.93, - "learning_rate": 3.3663633906855237e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.841927473658308e-05, + "loss": 0.2028, "step": 104580 }, { - "epoch": 0.93, - "learning_rate": 3.3618592919556795e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.841815619337375e-05, + "loss": 0.1944, "step": 104590 }, { - "epoch": 0.93, - "learning_rate": 3.3573551932258357e-06, - "loss": 0.18, + "epoch": 0.23, + "learning_rate": 3.841703765016443e-05, + "loss": 0.1975, "step": 104600 }, { - "epoch": 0.93, - "learning_rate": 3.3528510944959915e-06, - "loss": 0.1768, + "epoch": 0.23, + "learning_rate": 3.8415919106955106e-05, + "loss": 0.1953, "step": 104610 }, { - "epoch": 0.93, - "learning_rate": 3.348797405639132e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.841480056374578e-05, + "loss": 0.197, "step": 104620 }, { - "epoch": 0.93, - "learning_rate": 3.3442933069092873e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.8413682020536455e-05, + "loss": 0.196, "step": 104630 }, { - "epoch": 0.93, - "learning_rate": 3.339789208179443e-06, - "loss": 0.1707, + "epoch": 0.23, + "learning_rate": 3.841256347732713e-05, + "loss": 0.1955, "step": 104640 }, { - "epoch": 0.93, - "learning_rate": 3.3352851094495993e-06, - "loss": 0.1723, + "epoch": 0.23, + "learning_rate": 3.841144493411781e-05, + "loss": 0.1987, "step": 104650 }, { - "epoch": 0.93, - "learning_rate": 3.330781010719755e-06, - "loss": 0.1715, + "epoch": 0.23, + "learning_rate": 3.841032639090849e-05, + "loss": 0.1954, "step": 104660 }, { - "epoch": 0.93, - "learning_rate": 3.326276911989911e-06, - "loss": 0.1778, + "epoch": 0.23, + "learning_rate": 3.840920784769916e-05, + "loss": 0.1954, "step": 104670 }, { - "epoch": 0.93, - "learning_rate": 3.321772813260067e-06, - "loss": 0.1769, + "epoch": 0.23, + "learning_rate": 3.840808930448984e-05, + "loss": 0.1993, "step": 104680 }, { - "epoch": 0.93, - "learning_rate": 3.317268714530223e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.840697076128051e-05, + "loss": 0.2006, "step": 104690 }, { - "epoch": 0.93, - "learning_rate": 3.3127646158003783e-06, - "loss": 0.1777, + "epoch": 0.23, + "learning_rate": 3.840585221807119e-05, + "loss": 0.2004, "step": 104700 }, { - "epoch": 0.93, - "learning_rate": 3.308260517070534e-06, - "loss": 0.1688, + "epoch": 0.23, + "learning_rate": 3.840473367486186e-05, + "loss": 0.1995, "step": 104710 }, { - "epoch": 0.93, - "learning_rate": 3.30375641834069e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.8403615131652536e-05, + "loss": 0.2005, "step": 104720 }, { - "epoch": 0.94, - "learning_rate": 3.299252319610846e-06, - "loss": 0.1744, + "epoch": 0.23, + "learning_rate": 3.8402496588443214e-05, + "loss": 0.1964, "step": 104730 }, { - "epoch": 0.94, - "learning_rate": 3.294748220881002e-06, - "loss": 0.1773, + "epoch": 0.23, + "learning_rate": 3.8401378045233885e-05, + "loss": 0.1946, "step": 104740 }, { - "epoch": 0.94, - "learning_rate": 3.2902441221511577e-06, - "loss": 0.1704, + "epoch": 0.23, + "learning_rate": 3.840025950202456e-05, + "loss": 0.2003, "step": 104750 }, { - "epoch": 0.94, - "learning_rate": 3.285740023421314e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.839914095881524e-05, + "loss": 0.2024, "step": 104760 }, { - "epoch": 0.94, - "learning_rate": 3.281235924691469e-06, - "loss": 0.1753, + "epoch": 0.23, + "learning_rate": 3.839802241560592e-05, + "loss": 0.2018, "step": 104770 }, { - "epoch": 0.94, - "learning_rate": 3.276731825961625e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.8396903872396597e-05, + "loss": 0.1955, "step": 104780 }, { - "epoch": 0.94, - "learning_rate": 3.272227727231781e-06, - "loss": 0.1782, + "epoch": 0.23, + "learning_rate": 3.839578532918727e-05, + "loss": 0.2023, "step": 104790 }, { - "epoch": 0.94, - "learning_rate": 3.2677236285019367e-06, - "loss": 0.1764, + "epoch": 0.23, + "learning_rate": 3.8394666785977946e-05, + "loss": 0.1926, "step": 104800 }, { - "epoch": 0.94, - "learning_rate": 3.263219529772093e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.839354824276862e-05, + "loss": 0.2016, "step": 104810 }, { - "epoch": 0.94, - "learning_rate": 3.2587154310422487e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.8392429699559295e-05, + "loss": 0.1979, "step": 104820 }, { - "epoch": 0.94, - "learning_rate": 3.254211332312405e-06, - "loss": 0.1749, + "epoch": 0.23, + "learning_rate": 3.839131115634997e-05, + "loss": 0.2018, "step": 104830 }, { - "epoch": 0.94, - "learning_rate": 3.24970723358256e-06, - "loss": 0.1811, + "epoch": 0.23, + "learning_rate": 3.8390192613140644e-05, + "loss": 0.199, "step": 104840 }, { - "epoch": 0.94, - "learning_rate": 3.245203134852716e-06, - "loss": 0.179, + "epoch": 0.23, + "learning_rate": 3.838907406993132e-05, + "loss": 0.1965, "step": 104850 }, { - "epoch": 0.94, - "learning_rate": 3.240699036122872e-06, - "loss": 0.1727, + "epoch": 0.23, + "learning_rate": 3.8387955526722e-05, + "loss": 0.1998, "step": 104860 }, { - "epoch": 0.94, - "learning_rate": 3.2361949373930277e-06, - "loss": 0.1787, + "epoch": 0.23, + "learning_rate": 3.838683698351268e-05, + "loss": 0.2, "step": 104870 }, { - "epoch": 0.94, - "learning_rate": 3.231690838663184e-06, - "loss": 0.1783, + "epoch": 0.23, + "learning_rate": 3.8385718440303355e-05, + "loss": 0.1955, "step": 104880 }, { - "epoch": 0.94, - "learning_rate": 3.2271867399333397e-06, - "loss": 0.1737, + "epoch": 0.23, + "learning_rate": 3.8384599897094027e-05, + "loss": 0.1939, "step": 104890 }, { - "epoch": 0.94, - "learning_rate": 3.2226826412034955e-06, - "loss": 0.1714, + "epoch": 0.23, + "learning_rate": 3.8383481353884705e-05, + "loss": 0.2006, "step": 104900 }, { - "epoch": 0.94, - "learning_rate": 3.218178542473651e-06, - "loss": 0.1722, + "epoch": 0.23, + "learning_rate": 3.8382362810675376e-05, + "loss": 0.2011, "step": 104910 }, { - "epoch": 0.94, - "learning_rate": 3.2136744437438067e-06, - "loss": 0.1744, + "epoch": 0.23, + "learning_rate": 3.8381244267466054e-05, + "loss": 0.2004, "step": 104920 }, { - "epoch": 0.94, - "learning_rate": 3.209170345013963e-06, - "loss": 0.1703, + "epoch": 0.23, + "learning_rate": 3.838012572425673e-05, + "loss": 0.197, "step": 104930 }, { - "epoch": 0.94, - "learning_rate": 3.2046662462841187e-06, - "loss": 0.1741, + "epoch": 0.23, + "learning_rate": 3.83790071810474e-05, + "loss": 0.2007, "step": 104940 }, { - "epoch": 0.94, - "learning_rate": 3.2001621475542745e-06, - "loss": 0.1761, + "epoch": 0.23, + "learning_rate": 3.837788863783808e-05, + "loss": 0.1932, "step": 104950 }, { - "epoch": 0.94, - "learning_rate": 3.1956580488244307e-06, - "loss": 0.1808, + "epoch": 0.23, + "learning_rate": 3.837677009462876e-05, + "loss": 0.2025, "step": 104960 }, { - "epoch": 0.94, - "learning_rate": 3.1911539500945865e-06, - "loss": 0.1724, + "epoch": 0.23, + "learning_rate": 3.8375651551419436e-05, + "loss": 0.2011, "step": 104970 }, { - "epoch": 0.94, - "learning_rate": 3.186649851364742e-06, - "loss": 0.174, + "epoch": 0.23, + "learning_rate": 3.8374533008210114e-05, + "loss": 0.1985, "step": 104980 }, { - "epoch": 0.94, - "learning_rate": 3.1821457526348977e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.8373414465000786e-05, + "loss": 0.1956, "step": 104990 }, { - "epoch": 0.94, - "learning_rate": 3.1776416539050535e-06, - "loss": 0.1714, + "epoch": 0.23, + "learning_rate": 3.8372295921791463e-05, + "loss": 0.1943, "step": 105000 }, { - "epoch": 0.94, - "learning_rate": 3.1731375551752097e-06, - "loss": 0.1801, + "epoch": 0.23, + "learning_rate": 3.8371177378582135e-05, + "loss": 0.191, "step": 105010 }, { - "epoch": 0.94, - "learning_rate": 3.1686334564453655e-06, - "loss": 0.175, + "epoch": 0.23, + "learning_rate": 3.837005883537281e-05, + "loss": 0.1984, "step": 105020 }, { - "epoch": 0.94, - "learning_rate": 3.1641293577155213e-06, - "loss": 0.1795, + "epoch": 0.23, + "learning_rate": 3.8368940292163484e-05, + "loss": 0.1949, "step": 105030 }, { - "epoch": 0.94, - "learning_rate": 3.1596252589856776e-06, - "loss": 0.1786, + "epoch": 0.23, + "learning_rate": 3.836782174895416e-05, + "loss": 0.2007, "step": 105040 }, { - "epoch": 0.94, - "learning_rate": 3.1551211602558325e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.836670320574484e-05, + "loss": 0.1927, "step": 105050 }, { - "epoch": 0.94, - "learning_rate": 3.1506170615259887e-06, - "loss": 0.1799, + "epoch": 0.23, + "learning_rate": 3.836558466253552e-05, + "loss": 0.1973, "step": 105060 }, { - "epoch": 0.94, - "learning_rate": 3.1461129627961445e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.8364466119326195e-05, + "loss": 0.1946, "step": 105070 }, { - "epoch": 0.94, - "learning_rate": 3.1416088640663003e-06, - "loss": 0.1763, + "epoch": 0.23, + "learning_rate": 3.8363347576116867e-05, + "loss": 0.1957, "step": 105080 }, { - "epoch": 0.94, - "learning_rate": 3.1371047653364565e-06, - "loss": 0.1766, + "epoch": 0.23, + "learning_rate": 3.8362229032907544e-05, + "loss": 0.2004, "step": 105090 }, { - "epoch": 0.94, - "learning_rate": 3.1326006666066123e-06, - "loss": 0.1755, + "epoch": 0.23, + "learning_rate": 3.836111048969822e-05, + "loss": 0.2019, "step": 105100 }, { - "epoch": 0.94, - "learning_rate": 3.128096567876768e-06, - "loss": 0.1757, + "epoch": 0.23, + "learning_rate": 3.8359991946488894e-05, + "loss": 0.2004, "step": 105110 }, { - "epoch": 0.94, - "learning_rate": 3.123592469146924e-06, - "loss": 0.1768, + "epoch": 0.23, + "learning_rate": 3.835887340327957e-05, + "loss": 0.2034, "step": 105120 }, { - "epoch": 0.94, - "learning_rate": 3.1190883704170793e-06, - "loss": 0.1734, + "epoch": 0.23, + "learning_rate": 3.835775486007024e-05, + "loss": 0.197, "step": 105130 }, { - "epoch": 0.94, - "learning_rate": 3.1145842716872355e-06, - "loss": 0.1753, + "epoch": 0.23, + "learning_rate": 3.835663631686092e-05, + "loss": 0.2043, "step": 105140 }, { - "epoch": 0.94, - "learning_rate": 3.1100801729573913e-06, - "loss": 0.1751, + "epoch": 0.23, + "learning_rate": 3.83555177736516e-05, + "loss": 0.1956, "step": 105150 }, { - "epoch": 0.94, - "learning_rate": 3.105576074227547e-06, - "loss": 0.1758, + "epoch": 0.23, + "learning_rate": 3.835439923044227e-05, + "loss": 0.1995, "step": 105160 }, { - "epoch": 0.94, - "learning_rate": 3.101071975497703e-06, - "loss": 0.1722, + "epoch": 0.23, + "learning_rate": 3.835328068723295e-05, + "loss": 0.1952, "step": 105170 }, { - "epoch": 0.94, - "learning_rate": 3.0965678767678587e-06, - "loss": 0.1736, + "epoch": 0.23, + "learning_rate": 3.8352162144023626e-05, + "loss": 0.196, "step": 105180 }, { - "epoch": 0.94, - "learning_rate": 3.092063778038015e-06, - "loss": 0.1718, + "epoch": 0.23, + "learning_rate": 3.8351043600814303e-05, + "loss": 0.1944, "step": 105190 }, { - "epoch": 0.94, - "learning_rate": 3.0875596793081703e-06, - "loss": 0.1784, + "epoch": 0.23, + "learning_rate": 3.834992505760498e-05, + "loss": 0.1981, "step": 105200 }, { - "epoch": 0.94, - "learning_rate": 3.0830555805783265e-06, - "loss": 0.1745, + "epoch": 0.23, + "learning_rate": 3.834880651439565e-05, + "loss": 0.1979, "step": 105210 }, { - "epoch": 0.94, - "learning_rate": 3.0785514818484823e-06, - "loss": 0.1776, + "epoch": 0.23, + "learning_rate": 3.834768797118633e-05, + "loss": 0.2007, "step": 105220 }, { - "epoch": 0.94, - "learning_rate": 3.074047383118638e-06, - "loss": 0.1771, + "epoch": 0.23, + "learning_rate": 3.8346569427977e-05, + "loss": 0.195, "step": 105230 }, { - "epoch": 0.94, - "learning_rate": 3.069543284388794e-06, - "loss": 0.1738, + "epoch": 0.23, + "learning_rate": 3.834545088476768e-05, + "loss": 0.197, "step": 105240 }, { - "epoch": 0.94, - "learning_rate": 3.0650391856589497e-06, - "loss": 0.1713, + "epoch": 0.23, + "learning_rate": 3.834433234155836e-05, + "loss": 0.1992, "step": 105250 }, { - "epoch": 0.94, - "learning_rate": 3.0605350869291055e-06, - "loss": 0.1754, + "epoch": 0.23, + "learning_rate": 3.834321379834903e-05, + "loss": 0.1971, "step": 105260 }, { - "epoch": 0.94, - "learning_rate": 3.0560309881992613e-06, - "loss": 0.1732, + "epoch": 0.23, + "learning_rate": 3.8342095255139707e-05, + "loss": 0.1961, "step": 105270 }, { - "epoch": 0.94, - "learning_rate": 3.051526889469417e-06, - "loss": 0.1752, + "epoch": 0.23, + "learning_rate": 3.8340976711930384e-05, + "loss": 0.1959, "step": 105280 }, { - "epoch": 0.94, - "learning_rate": 3.0470227907395734e-06, - "loss": 0.1754, + "epoch": 0.24, + "learning_rate": 3.833985816872106e-05, + "loss": 0.1993, "step": 105290 }, { - "epoch": 0.94, - "learning_rate": 3.042518692009729e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.8338739625511734e-05, + "loss": 0.1957, "step": 105300 }, { - "epoch": 0.94, - "learning_rate": 3.0380145932798845e-06, - "loss": 0.1788, + "epoch": 0.24, + "learning_rate": 3.833762108230241e-05, + "loss": 0.1966, "step": 105310 }, { - "epoch": 0.94, - "learning_rate": 3.0335104945500408e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.833650253909309e-05, + "loss": 0.2044, "step": 105320 }, { - "epoch": 0.94, - "learning_rate": 3.0290063958201965e-06, - "loss": 0.1797, + "epoch": 0.24, + "learning_rate": 3.833538399588376e-05, + "loss": 0.2009, "step": 105330 }, { - "epoch": 0.94, - "learning_rate": 3.0245022970903523e-06, - "loss": 0.1824, + "epoch": 0.24, + "learning_rate": 3.833426545267444e-05, + "loss": 0.2023, "step": 105340 }, { - "epoch": 0.94, - "learning_rate": 3.019998198360508e-06, - "loss": 0.1773, + "epoch": 0.24, + "learning_rate": 3.833314690946511e-05, + "loss": 0.1971, "step": 105350 }, { - "epoch": 0.94, - "learning_rate": 3.015494099630664e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.833202836625579e-05, + "loss": 0.1984, "step": 105360 }, { - "epoch": 0.94, - "learning_rate": 3.01099000090082e-06, - "loss": 0.1853, + "epoch": 0.24, + "learning_rate": 3.8330909823046465e-05, + "loss": 0.1984, "step": 105370 }, { - "epoch": 0.94, - "learning_rate": 3.0064859021709755e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.8329791279837143e-05, + "loss": 0.195, "step": 105380 }, { - "epoch": 0.94, - "learning_rate": 3.0019818034411318e-06, - "loss": 0.1805, + "epoch": 0.24, + "learning_rate": 3.832867273662782e-05, + "loss": 0.1937, "step": 105390 }, { - "epoch": 0.94, - "learning_rate": 2.9974777047112876e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.832755419341849e-05, + "loss": 0.197, "step": 105400 }, { - "epoch": 0.94, - "learning_rate": 2.992973605981443e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.832643565020917e-05, + "loss": 0.1965, "step": 105410 }, { - "epoch": 0.94, - "learning_rate": 2.988469507251599e-06, - "loss": 0.1715, + "epoch": 0.24, + "learning_rate": 3.832531710699985e-05, + "loss": 0.2016, "step": 105420 }, { - "epoch": 0.94, - "learning_rate": 2.983965408521755e-06, - "loss": 0.1759, + "epoch": 0.24, + "learning_rate": 3.832419856379052e-05, + "loss": 0.2051, "step": 105430 }, { - "epoch": 0.94, - "learning_rate": 2.9794613097919108e-06, - "loss": 0.1757, + "epoch": 0.24, + "learning_rate": 3.83230800205812e-05, + "loss": 0.2015, "step": 105440 }, { - "epoch": 0.94, - "learning_rate": 2.9749572110620666e-06, - "loss": 0.1781, + "epoch": 0.24, + "learning_rate": 3.832196147737187e-05, + "loss": 0.1943, "step": 105450 }, { - "epoch": 0.94, - "learning_rate": 2.9704531123322223e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.8320842934162547e-05, + "loss": 0.1967, "step": 105460 }, { - "epoch": 0.94, - "learning_rate": 2.9659490136023786e-06, - "loss": 0.1738, + "epoch": 0.24, + "learning_rate": 3.8319724390953224e-05, + "loss": 0.1939, "step": 105470 }, { - "epoch": 0.94, - "learning_rate": 2.961444914872534e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.83186058477439e-05, + "loss": 0.2005, "step": 105480 }, { - "epoch": 0.94, - "learning_rate": 2.9569408161426897e-06, - "loss": 0.1707, + "epoch": 0.24, + "learning_rate": 3.831748730453458e-05, + "loss": 0.197, "step": 105490 }, { - "epoch": 0.94, - "learning_rate": 2.952436717412846e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.831636876132525e-05, + "loss": 0.1969, "step": 105500 }, { - "epoch": 0.94, - "learning_rate": 2.9479326186830018e-06, - "loss": 0.1757, + "epoch": 0.24, + "learning_rate": 3.831525021811593e-05, + "loss": 0.2015, "step": 105510 }, { - "epoch": 0.94, - "learning_rate": 2.9434285199531576e-06, - "loss": 0.1777, + "epoch": 0.24, + "learning_rate": 3.831413167490661e-05, + "loss": 0.195, "step": 105520 }, { - "epoch": 0.94, - "learning_rate": 2.9389244212233134e-06, - "loss": 0.1724, + "epoch": 0.24, + "learning_rate": 3.831301313169728e-05, + "loss": 0.2008, "step": 105530 }, { - "epoch": 0.94, - "learning_rate": 2.934420322493469e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.8311894588487956e-05, + "loss": 0.1974, "step": 105540 }, { - "epoch": 0.94, - "learning_rate": 2.929916223763625e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.831077604527863e-05, + "loss": 0.1993, "step": 105550 }, { - "epoch": 0.94, - "learning_rate": 2.9254121250337808e-06, - "loss": 0.1779, + "epoch": 0.24, + "learning_rate": 3.8309657502069305e-05, + "loss": 0.1952, "step": 105560 }, { - "epoch": 0.94, - "learning_rate": 2.920908026303937e-06, - "loss": 0.1759, + "epoch": 0.24, + "learning_rate": 3.830853895885998e-05, + "loss": 0.1997, "step": 105570 }, { - "epoch": 0.94, - "learning_rate": 2.9164039275740928e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.8307420415650655e-05, + "loss": 0.1975, "step": 105580 }, { - "epoch": 0.94, - "learning_rate": 2.911899828844248e-06, - "loss": 0.1817, + "epoch": 0.24, + "learning_rate": 3.830630187244133e-05, + "loss": 0.2022, "step": 105590 }, { - "epoch": 0.94, - "learning_rate": 2.9073957301144044e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.830518332923201e-05, + "loss": 0.1956, "step": 105600 }, { - "epoch": 0.94, - "learning_rate": 2.90289163138456e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.830406478602269e-05, + "loss": 0.1919, "step": 105610 }, { - "epoch": 0.94, - "learning_rate": 2.898387532654716e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.830294624281336e-05, + "loss": 0.2024, "step": 105620 }, { - "epoch": 0.94, - "learning_rate": 2.8938834339248718e-06, - "loss": 0.1687, + "epoch": 0.24, + "learning_rate": 3.830182769960404e-05, + "loss": 0.1963, "step": 105630 }, { - "epoch": 0.94, - "learning_rate": 2.8893793351950276e-06, - "loss": 0.1727, + "epoch": 0.24, + "learning_rate": 3.8300709156394715e-05, + "loss": 0.196, "step": 105640 }, { - "epoch": 0.94, - "learning_rate": 2.8848752364651838e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.8299590613185386e-05, + "loss": 0.1996, "step": 105650 }, { - "epoch": 0.94, - "learning_rate": 2.880371137735339e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.8298472069976064e-05, + "loss": 0.1972, "step": 105660 }, { - "epoch": 0.94, - "learning_rate": 2.875867039005495e-06, - "loss": 0.1788, + "epoch": 0.24, + "learning_rate": 3.8297353526766736e-05, + "loss": 0.1987, "step": 105670 }, { - "epoch": 0.94, - "learning_rate": 2.871362940275651e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.8296234983557413e-05, + "loss": 0.1959, "step": 105680 }, { - "epoch": 0.94, - "learning_rate": 2.8668588415458066e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.829511644034809e-05, + "loss": 0.2015, "step": 105690 }, { - "epoch": 0.94, - "learning_rate": 2.8628051526889474e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.829399789713877e-05, + "loss": 0.2002, "step": 105700 }, { - "epoch": 0.94, - "learning_rate": 2.8583010539591027e-06, - "loss": 0.1826, + "epoch": 0.24, + "learning_rate": 3.829287935392945e-05, + "loss": 0.2037, "step": 105710 }, { - "epoch": 0.94, - "learning_rate": 2.853796955229259e-06, - "loss": 0.1782, + "epoch": 0.24, + "learning_rate": 3.829176081072012e-05, + "loss": 0.1894, "step": 105720 }, { - "epoch": 0.94, - "learning_rate": 2.8492928564994148e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.8290642267510796e-05, + "loss": 0.2019, "step": 105730 }, { - "epoch": 0.94, - "learning_rate": 2.84478875776957e-06, - "loss": 0.1702, + "epoch": 0.24, + "learning_rate": 3.8289523724301474e-05, + "loss": 0.2, "step": 105740 }, { - "epoch": 0.94, - "learning_rate": 2.8402846590397264e-06, - "loss": 0.1775, + "epoch": 0.24, + "learning_rate": 3.8288405181092145e-05, + "loss": 0.1978, "step": 105750 }, { - "epoch": 0.94, - "learning_rate": 2.835780560309882e-06, - "loss": 0.192, + "epoch": 0.24, + "learning_rate": 3.828728663788282e-05, + "loss": 0.1975, "step": 105760 }, { - "epoch": 0.94, - "learning_rate": 2.831276461580038e-06, - "loss": 0.1789, + "epoch": 0.24, + "learning_rate": 3.8286168094673495e-05, + "loss": 0.1995, "step": 105770 }, { - "epoch": 0.94, - "learning_rate": 2.8267723628501937e-06, - "loss": 0.1799, + "epoch": 0.24, + "learning_rate": 3.828504955146417e-05, + "loss": 0.1974, "step": 105780 }, { - "epoch": 0.94, - "learning_rate": 2.8222682641203495e-06, - "loss": 0.176, + "epoch": 0.24, + "learning_rate": 3.828393100825485e-05, + "loss": 0.1986, "step": 105790 }, { - "epoch": 0.94, - "learning_rate": 2.8177641653905058e-06, - "loss": 0.178, + "epoch": 0.24, + "learning_rate": 3.828281246504553e-05, + "loss": 0.1986, "step": 105800 }, { - "epoch": 0.94, - "learning_rate": 2.813260066660661e-06, - "loss": 0.1761, + "epoch": 0.24, + "learning_rate": 3.8281693921836206e-05, + "loss": 0.1953, "step": 105810 }, { - "epoch": 0.94, - "learning_rate": 2.8087559679308174e-06, - "loss": 0.179, + "epoch": 0.24, + "learning_rate": 3.828057537862688e-05, + "loss": 0.1978, "step": 105820 }, { - "epoch": 0.94, - "learning_rate": 2.804251869200973e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.8279456835417555e-05, + "loss": 0.2011, "step": 105830 }, { - "epoch": 0.94, - "learning_rate": 2.7997477704711285e-06, - "loss": 0.1815, + "epoch": 0.24, + "learning_rate": 3.827833829220823e-05, + "loss": 0.1976, "step": 105840 }, { - "epoch": 0.95, - "learning_rate": 2.7952436717412848e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.8277219748998904e-05, + "loss": 0.1957, "step": 105850 }, { - "epoch": 0.95, - "learning_rate": 2.7907395730114406e-06, - "loss": 0.1799, + "epoch": 0.24, + "learning_rate": 3.827610120578958e-05, + "loss": 0.1972, "step": 105860 }, { - "epoch": 0.95, - "learning_rate": 2.7862354742815964e-06, - "loss": 0.1801, + "epoch": 0.24, + "learning_rate": 3.8274982662580253e-05, + "loss": 0.1955, "step": 105870 }, { - "epoch": 0.95, - "learning_rate": 2.781731375551752e-06, - "loss": 0.1711, + "epoch": 0.24, + "learning_rate": 3.827386411937093e-05, + "loss": 0.1939, "step": 105880 }, { - "epoch": 0.95, - "learning_rate": 2.777227276821908e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.827274557616161e-05, + "loss": 0.1996, "step": 105890 }, { - "epoch": 0.95, - "learning_rate": 2.772723178092064e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.827162703295229e-05, + "loss": 0.1975, "step": 105900 }, { - "epoch": 0.95, - "learning_rate": 2.7682190793622195e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.8270508489742965e-05, + "loss": 0.1946, "step": 105910 }, { - "epoch": 0.95, - "learning_rate": 2.7637149806323753e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.8269389946533636e-05, + "loss": 0.2024, "step": 105920 }, { - "epoch": 0.95, - "learning_rate": 2.7592108819025316e-06, - "loss": 0.1742, + "epoch": 0.24, + "learning_rate": 3.8268271403324314e-05, + "loss": 0.2032, "step": 105930 }, { - "epoch": 0.95, - "learning_rate": 2.7547067831726874e-06, - "loss": 0.1718, + "epoch": 0.24, + "learning_rate": 3.8267152860114985e-05, + "loss": 0.1979, "step": 105940 }, { - "epoch": 0.95, - "learning_rate": 2.750202684442843e-06, - "loss": 0.1784, + "epoch": 0.24, + "learning_rate": 3.826603431690566e-05, + "loss": 0.1941, "step": 105950 }, { - "epoch": 0.95, - "learning_rate": 2.745698585712999e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.826491577369634e-05, + "loss": 0.1948, "step": 105960 }, { - "epoch": 0.95, - "learning_rate": 2.7411944869831548e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.826379723048701e-05, + "loss": 0.1952, "step": 105970 }, { - "epoch": 0.95, - "learning_rate": 2.7366903882533106e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.826267868727769e-05, + "loss": 0.1953, "step": 105980 }, { - "epoch": 0.95, - "learning_rate": 2.7321862895234664e-06, - "loss": 0.1806, + "epoch": 0.24, + "learning_rate": 3.826156014406836e-05, + "loss": 0.1996, "step": 105990 }, { - "epoch": 0.95, - "learning_rate": 2.7276821907936226e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.826044160085904e-05, + "loss": 0.1985, "step": 106000 }, { - "epoch": 0.95, - "learning_rate": 2.7231780920637784e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.8259323057649724e-05, + "loss": 0.199, "step": 106010 }, { - "epoch": 0.95, - "learning_rate": 2.7186739933339337e-06, - "loss": 0.1761, + "epoch": 0.24, + "learning_rate": 3.8258204514440395e-05, + "loss": 0.1952, "step": 106020 }, { - "epoch": 0.95, - "learning_rate": 2.71416989460409e-06, - "loss": 0.1833, + "epoch": 0.24, + "learning_rate": 3.825708597123107e-05, + "loss": 0.1983, "step": 106030 }, { - "epoch": 0.95, - "learning_rate": 2.7096657958742458e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.8255967428021744e-05, + "loss": 0.1955, "step": 106040 }, { - "epoch": 0.95, - "learning_rate": 2.7051616971444016e-06, - "loss": 0.1752, + "epoch": 0.24, + "learning_rate": 3.825484888481242e-05, + "loss": 0.1941, "step": 106050 }, { - "epoch": 0.95, - "learning_rate": 2.7006575984145574e-06, - "loss": 0.1817, + "epoch": 0.24, + "learning_rate": 3.82537303416031e-05, + "loss": 0.1993, "step": 106060 }, { - "epoch": 0.95, - "learning_rate": 2.696153499684713e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.825261179839377e-05, + "loss": 0.1969, "step": 106070 }, { - "epoch": 0.95, - "learning_rate": 2.6916494009548694e-06, - "loss": 0.172, + "epoch": 0.24, + "learning_rate": 3.825149325518445e-05, + "loss": 0.1968, "step": 106080 }, { - "epoch": 0.95, - "learning_rate": 2.6871453022250248e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.825037471197512e-05, + "loss": 0.198, "step": 106090 }, { - "epoch": 0.95, - "learning_rate": 2.6826412034951806e-06, - "loss": 0.1786, + "epoch": 0.24, + "learning_rate": 3.82492561687658e-05, + "loss": 0.1939, "step": 106100 }, { - "epoch": 0.95, - "learning_rate": 2.6781371047653368e-06, - "loss": 0.1771, + "epoch": 0.24, + "learning_rate": 3.8248137625556476e-05, + "loss": 0.1919, "step": 106110 }, { - "epoch": 0.95, - "learning_rate": 2.673633006035492e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.8247019082347154e-05, + "loss": 0.1994, "step": 106120 }, { - "epoch": 0.95, - "learning_rate": 2.6691289073056484e-06, - "loss": 0.1767, + "epoch": 0.24, + "learning_rate": 3.824590053913783e-05, + "loss": 0.1974, "step": 106130 }, { - "epoch": 0.95, - "learning_rate": 2.664624808575804e-06, - "loss": 0.1759, + "epoch": 0.24, + "learning_rate": 3.82447819959285e-05, + "loss": 0.1989, "step": 106140 }, { - "epoch": 0.95, - "learning_rate": 2.66012070984596e-06, - "loss": 0.1827, + "epoch": 0.24, + "learning_rate": 3.824366345271918e-05, + "loss": 0.1957, "step": 106150 }, { - "epoch": 0.95, - "learning_rate": 2.6556166111161158e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.824254490950986e-05, + "loss": 0.2008, "step": 106160 }, { - "epoch": 0.95, - "learning_rate": 2.6511125123862716e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.824142636630053e-05, + "loss": 0.2041, "step": 106170 }, { - "epoch": 0.95, - "learning_rate": 2.646608413656428e-06, - "loss": 0.1818, + "epoch": 0.24, + "learning_rate": 3.824030782309121e-05, + "loss": 0.1984, "step": 106180 }, { - "epoch": 0.95, - "learning_rate": 2.642104314926583e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.823918927988188e-05, + "loss": 0.1994, "step": 106190 }, { - "epoch": 0.95, - "learning_rate": 2.637600216196739e-06, - "loss": 0.1795, + "epoch": 0.24, + "learning_rate": 3.823807073667256e-05, + "loss": 0.1969, "step": 106200 }, { - "epoch": 0.95, - "learning_rate": 2.633096117466895e-06, - "loss": 0.1701, + "epoch": 0.24, + "learning_rate": 3.8236952193463235e-05, + "loss": 0.1982, "step": 106210 }, { - "epoch": 0.95, - "learning_rate": 2.628592018737051e-06, - "loss": 0.1792, + "epoch": 0.24, + "learning_rate": 3.823583365025391e-05, + "loss": 0.2002, "step": 106220 }, { - "epoch": 0.95, - "learning_rate": 2.6240879200072068e-06, - "loss": 0.1745, + "epoch": 0.24, + "learning_rate": 3.823471510704459e-05, + "loss": 0.1976, "step": 106230 }, { - "epoch": 0.95, - "learning_rate": 2.6195838212773626e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.823359656383526e-05, + "loss": 0.1991, "step": 106240 }, { - "epoch": 0.95, - "learning_rate": 2.6150797225475184e-06, - "loss": 0.1728, + "epoch": 0.24, + "learning_rate": 3.823247802062594e-05, + "loss": 0.1971, "step": 106250 }, { - "epoch": 0.95, - "learning_rate": 2.610575623817674e-06, - "loss": 0.1787, + "epoch": 0.24, + "learning_rate": 3.823135947741661e-05, + "loss": 0.1943, "step": 106260 }, { - "epoch": 0.95, - "learning_rate": 2.60607152508783e-06, - "loss": 0.1774, + "epoch": 0.24, + "learning_rate": 3.823024093420729e-05, + "loss": 0.1944, "step": 106270 }, { - "epoch": 0.95, - "learning_rate": 2.6015674263579858e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.822912239099797e-05, + "loss": 0.2027, "step": 106280 }, { - "epoch": 0.95, - "learning_rate": 2.597063327628142e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.822800384778864e-05, + "loss": 0.204, "step": 106290 }, { - "epoch": 0.95, - "learning_rate": 2.5925592288982974e-06, - "loss": 0.177, + "epoch": 0.24, + "learning_rate": 3.8226885304579316e-05, + "loss": 0.1972, "step": 106300 }, { - "epoch": 0.95, - "learning_rate": 2.5880551301684536e-06, - "loss": 0.1729, + "epoch": 0.24, + "learning_rate": 3.8225766761369994e-05, + "loss": 0.1994, "step": 106310 }, { - "epoch": 0.95, - "learning_rate": 2.5835510314386094e-06, - "loss": 0.1717, + "epoch": 0.24, + "learning_rate": 3.822464821816067e-05, + "loss": 0.1989, "step": 106320 }, { - "epoch": 0.95, - "learning_rate": 2.579046932708765e-06, - "loss": 0.1775, + "epoch": 0.24, + "learning_rate": 3.822352967495135e-05, + "loss": 0.2011, "step": 106330 }, { - "epoch": 0.95, - "learning_rate": 2.574542833978921e-06, - "loss": 0.172, + "epoch": 0.24, + "learning_rate": 3.822241113174202e-05, + "loss": 0.1978, "step": 106340 }, { - "epoch": 0.95, - "learning_rate": 2.5700387352490768e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.82212925885327e-05, + "loss": 0.1967, "step": 106350 }, { - "epoch": 0.95, - "learning_rate": 2.5655346365192326e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.822017404532337e-05, + "loss": 0.2024, "step": 106360 }, { - "epoch": 0.95, - "learning_rate": 2.5610305377893884e-06, - "loss": 0.1711, + "epoch": 0.24, + "learning_rate": 3.821905550211405e-05, + "loss": 0.1992, "step": 106370 }, { - "epoch": 0.95, - "learning_rate": 2.556526439059544e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.8217936958904726e-05, + "loss": 0.1997, "step": 106380 }, { - "epoch": 0.95, - "learning_rate": 2.5520223403297004e-06, - "loss": 0.1742, + "epoch": 0.24, + "learning_rate": 3.82168184156954e-05, + "loss": 0.1966, "step": 106390 }, { - "epoch": 0.95, - "learning_rate": 2.5475182415998558e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.8215699872486075e-05, + "loss": 0.1965, "step": 106400 }, { - "epoch": 0.95, - "learning_rate": 2.543014142870012e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.8214581329276746e-05, + "loss": 0.1963, "step": 106410 }, { - "epoch": 0.95, - "learning_rate": 2.538510044140168e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.821346278606743e-05, + "loss": 0.1956, "step": 106420 }, { - "epoch": 0.95, - "learning_rate": 2.534005945410323e-06, - "loss": 0.1769, + "epoch": 0.24, + "learning_rate": 3.821234424285811e-05, + "loss": 0.1949, "step": 106430 }, { - "epoch": 0.95, - "learning_rate": 2.5295018466804794e-06, - "loss": 0.1725, + "epoch": 0.24, + "learning_rate": 3.821122569964878e-05, + "loss": 0.1954, "step": 106440 }, { - "epoch": 0.95, - "learning_rate": 2.524997747950635e-06, - "loss": 0.1728, + "epoch": 0.24, + "learning_rate": 3.821010715643946e-05, + "loss": 0.1966, "step": 106450 }, { - "epoch": 0.95, - "learning_rate": 2.520493649220791e-06, - "loss": 0.1705, + "epoch": 0.24, + "learning_rate": 3.820898861323013e-05, + "loss": 0.1964, "step": 106460 }, { - "epoch": 0.95, - "learning_rate": 2.5159895504909468e-06, - "loss": 0.1801, + "epoch": 0.24, + "learning_rate": 3.820787007002081e-05, + "loss": 0.2023, "step": 106470 }, { - "epoch": 0.95, - "learning_rate": 2.5114854517611026e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.8206751526811485e-05, + "loss": 0.1942, "step": 106480 }, { - "epoch": 0.95, - "learning_rate": 2.506981353031259e-06, - "loss": 0.1807, + "epoch": 0.24, + "learning_rate": 3.8205632983602156e-05, + "loss": 0.1995, "step": 106490 }, { - "epoch": 0.95, - "learning_rate": 2.502477254301414e-06, - "loss": 0.1729, + "epoch": 0.24, + "learning_rate": 3.8204514440392834e-05, + "loss": 0.1974, "step": 106500 }, { - "epoch": 0.95, - "learning_rate": 2.4979731555715704e-06, - "loss": 0.1817, + "epoch": 0.24, + "learning_rate": 3.8203395897183505e-05, + "loss": 0.1939, "step": 106510 }, { - "epoch": 0.95, - "learning_rate": 2.493469056841726e-06, - "loss": 0.1814, + "epoch": 0.24, + "learning_rate": 3.820227735397418e-05, + "loss": 0.1949, "step": 106520 }, { - "epoch": 0.95, - "learning_rate": 2.488964958111882e-06, - "loss": 0.179, + "epoch": 0.24, + "learning_rate": 3.820115881076486e-05, + "loss": 0.1964, "step": 106530 }, { - "epoch": 0.95, - "learning_rate": 2.484460859382038e-06, - "loss": 0.1714, + "epoch": 0.24, + "learning_rate": 3.820004026755554e-05, + "loss": 0.1996, "step": 106540 }, { - "epoch": 0.95, - "learning_rate": 2.4799567606521936e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.819892172434622e-05, + "loss": 0.1969, "step": 106550 }, { - "epoch": 0.95, - "learning_rate": 2.4754526619223494e-06, - "loss": 0.1832, + "epoch": 0.24, + "learning_rate": 3.819780318113689e-05, + "loss": 0.2011, "step": 106560 }, { - "epoch": 0.95, - "learning_rate": 2.470948563192505e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.8196684637927566e-05, + "loss": 0.1975, "step": 106570 }, { - "epoch": 0.95, - "learning_rate": 2.466444464462661e-06, - "loss": 0.1782, + "epoch": 0.24, + "learning_rate": 3.819556609471824e-05, + "loss": 0.1956, "step": 106580 }, { - "epoch": 0.95, - "learning_rate": 2.461940365732817e-06, - "loss": 0.1773, + "epoch": 0.24, + "learning_rate": 3.8194447551508915e-05, + "loss": 0.1924, "step": 106590 }, { - "epoch": 0.95, - "learning_rate": 2.457436267002973e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.819332900829959e-05, + "loss": 0.1971, "step": 106600 }, { - "epoch": 0.95, - "learning_rate": 2.4529321682731284e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.8192210465090264e-05, + "loss": 0.2012, "step": 106610 }, { - "epoch": 0.95, - "learning_rate": 2.4484280695432846e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.819109192188094e-05, + "loss": 0.1939, "step": 106620 }, { - "epoch": 0.95, - "learning_rate": 2.4439239708134404e-06, - "loss": 0.1705, + "epoch": 0.24, + "learning_rate": 3.818997337867162e-05, + "loss": 0.2027, "step": 106630 }, { - "epoch": 0.95, - "learning_rate": 2.439419872083596e-06, - "loss": 0.1817, + "epoch": 0.24, + "learning_rate": 3.81888548354623e-05, + "loss": 0.1988, "step": 106640 }, { - "epoch": 0.95, - "learning_rate": 2.434915773353752e-06, - "loss": 0.172, + "epoch": 0.24, + "learning_rate": 3.8187736292252976e-05, + "loss": 0.1986, "step": 106650 }, { - "epoch": 0.95, - "learning_rate": 2.430411674623908e-06, - "loss": 0.176, + "epoch": 0.24, + "learning_rate": 3.818661774904365e-05, + "loss": 0.1925, "step": 106660 }, { - "epoch": 0.95, - "learning_rate": 2.425907575894064e-06, - "loss": 0.1693, + "epoch": 0.24, + "learning_rate": 3.8185499205834325e-05, + "loss": 0.1965, "step": 106670 }, { - "epoch": 0.95, - "learning_rate": 2.4214034771642194e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.8184380662624996e-05, + "loss": 0.1957, "step": 106680 }, { - "epoch": 0.95, - "learning_rate": 2.4168993784343756e-06, - "loss": 0.1752, + "epoch": 0.24, + "learning_rate": 3.8183262119415674e-05, + "loss": 0.1917, "step": 106690 }, { - "epoch": 0.95, - "learning_rate": 2.4123952797045314e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.818214357620635e-05, + "loss": 0.191, "step": 106700 }, { - "epoch": 0.95, - "learning_rate": 2.4078911809746868e-06, - "loss": 0.1775, + "epoch": 0.24, + "learning_rate": 3.818102503299702e-05, + "loss": 0.201, "step": 106710 }, { - "epoch": 0.95, - "learning_rate": 2.403387082244843e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.81799064897877e-05, + "loss": 0.1979, "step": 106720 }, { - "epoch": 0.95, - "learning_rate": 2.398882983514999e-06, - "loss": 0.1757, + "epoch": 0.24, + "learning_rate": 3.817878794657838e-05, + "loss": 0.1985, "step": 106730 }, { - "epoch": 0.95, - "learning_rate": 2.3943788847851546e-06, - "loss": 0.1713, + "epoch": 0.24, + "learning_rate": 3.817766940336906e-05, + "loss": 0.1951, "step": 106740 }, { - "epoch": 0.95, - "learning_rate": 2.3898747860553104e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.8176550860159735e-05, + "loss": 0.1934, "step": 106750 }, { - "epoch": 0.95, - "learning_rate": 2.385370687325466e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.8175432316950406e-05, + "loss": 0.1926, "step": 106760 }, { - "epoch": 0.95, - "learning_rate": 2.3808665885956224e-06, - "loss": 0.1731, + "epoch": 0.24, + "learning_rate": 3.8174313773741084e-05, + "loss": 0.1949, "step": 106770 }, { - "epoch": 0.95, - "learning_rate": 2.376362489865778e-06, - "loss": 0.1718, + "epoch": 0.24, + "learning_rate": 3.8173195230531755e-05, + "loss": 0.1987, "step": 106780 }, { - "epoch": 0.95, - "learning_rate": 2.3718583911359336e-06, - "loss": 0.1707, + "epoch": 0.24, + "learning_rate": 3.817207668732243e-05, + "loss": 0.1957, "step": 106790 }, { - "epoch": 0.95, - "learning_rate": 2.36735429240609e-06, - "loss": 0.1824, + "epoch": 0.24, + "learning_rate": 3.817095814411311e-05, + "loss": 0.1902, "step": 106800 }, { - "epoch": 0.95, - "learning_rate": 2.3628501936762456e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.816983960090378e-05, + "loss": 0.1973, "step": 106810 }, { - "epoch": 0.95, - "learning_rate": 2.3583460949464014e-06, - "loss": 0.1761, + "epoch": 0.24, + "learning_rate": 3.816872105769446e-05, + "loss": 0.1946, "step": 106820 }, { - "epoch": 0.95, - "learning_rate": 2.353841996216557e-06, - "loss": 0.1782, + "epoch": 0.24, + "learning_rate": 3.816760251448513e-05, + "loss": 0.1912, "step": 106830 }, { - "epoch": 0.95, - "learning_rate": 2.349337897486713e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.8166483971275816e-05, + "loss": 0.1943, "step": 106840 }, { - "epoch": 0.95, - "learning_rate": 2.344833798756869e-06, - "loss": 0.1742, + "epoch": 0.24, + "learning_rate": 3.8165365428066494e-05, + "loss": 0.1995, "step": 106850 }, { - "epoch": 0.95, - "learning_rate": 2.3403297000270246e-06, - "loss": 0.1731, + "epoch": 0.24, + "learning_rate": 3.8164246884857165e-05, + "loss": 0.1942, "step": 106860 }, { - "epoch": 0.95, - "learning_rate": 2.335825601297181e-06, - "loss": 0.1699, + "epoch": 0.24, + "learning_rate": 3.816312834164784e-05, + "loss": 0.2002, "step": 106870 }, { - "epoch": 0.95, - "learning_rate": 2.3313215025673366e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.8162009798438514e-05, + "loss": 0.2007, "step": 106880 }, { - "epoch": 0.95, - "learning_rate": 2.326817403837492e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.816089125522919e-05, + "loss": 0.2005, "step": 106890 }, { - "epoch": 0.95, - "learning_rate": 2.3223133051076482e-06, - "loss": 0.1719, + "epoch": 0.24, + "learning_rate": 3.815977271201986e-05, + "loss": 0.2018, "step": 106900 }, { - "epoch": 0.95, - "learning_rate": 2.317809206377804e-06, - "loss": 0.1717, + "epoch": 0.24, + "learning_rate": 3.815865416881054e-05, + "loss": 0.1948, "step": 106910 }, { - "epoch": 0.95, - "learning_rate": 2.31330510764796e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.815753562560122e-05, + "loss": 0.1917, "step": 106920 }, { - "epoch": 0.95, - "learning_rate": 2.3088010089181156e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.815641708239189e-05, + "loss": 0.1999, "step": 106930 }, { - "epoch": 0.95, - "learning_rate": 2.3042969101882714e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.815529853918257e-05, + "loss": 0.2036, "step": 106940 }, { - "epoch": 0.95, - "learning_rate": 2.299792811458427e-06, - "loss": 0.1714, + "epoch": 0.24, + "learning_rate": 3.8154179995973246e-05, + "loss": 0.1937, "step": 106950 }, { - "epoch": 0.95, - "learning_rate": 2.295288712728583e-06, - "loss": 0.1808, + "epoch": 0.24, + "learning_rate": 3.8153061452763924e-05, + "loss": 0.1999, "step": 106960 }, { - "epoch": 0.96, - "learning_rate": 2.290784613998739e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.81519429095546e-05, + "loss": 0.1985, "step": 106970 }, { - "epoch": 0.96, - "learning_rate": 2.286280515268895e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.815082436634527e-05, + "loss": 0.197, "step": 106980 }, { - "epoch": 0.96, - "learning_rate": 2.2817764165390504e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.814970582313595e-05, + "loss": 0.1965, "step": 106990 }, { - "epoch": 0.96, - "learning_rate": 2.2772723178092066e-06, - "loss": 0.1706, + "epoch": 0.24, + "learning_rate": 3.814858727992662e-05, + "loss": 0.1984, "step": 107000 }, { - "epoch": 0.96, - "learning_rate": 2.2727682190793624e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.81474687367173e-05, + "loss": 0.2003, "step": 107010 }, { - "epoch": 0.96, - "learning_rate": 2.268264120349518e-06, - "loss": 0.18, + "epoch": 0.24, + "learning_rate": 3.814635019350798e-05, + "loss": 0.1996, "step": 107020 }, { - "epoch": 0.96, - "learning_rate": 2.263760021619674e-06, - "loss": 0.1704, + "epoch": 0.24, + "learning_rate": 3.814523165029865e-05, + "loss": 0.1925, "step": 107030 }, { - "epoch": 0.96, - "learning_rate": 2.25925592288983e-06, - "loss": 0.1708, + "epoch": 0.24, + "learning_rate": 3.814411310708933e-05, + "loss": 0.1978, "step": 107040 }, { - "epoch": 0.96, - "learning_rate": 2.254751824159986e-06, - "loss": 0.1726, + "epoch": 0.24, + "learning_rate": 3.8142994563880005e-05, + "loss": 0.1958, "step": 107050 }, { - "epoch": 0.96, - "learning_rate": 2.2502477254301414e-06, - "loss": 0.1713, + "epoch": 0.24, + "learning_rate": 3.814187602067068e-05, + "loss": 0.1969, "step": 107060 }, { - "epoch": 0.96, - "learning_rate": 2.245743626700297e-06, - "loss": 0.1759, + "epoch": 0.24, + "learning_rate": 3.814075747746136e-05, + "loss": 0.2016, "step": 107070 }, { - "epoch": 0.96, - "learning_rate": 2.2412395279704534e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.813963893425203e-05, + "loss": 0.1926, "step": 107080 }, { - "epoch": 0.96, - "learning_rate": 2.236735429240609e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.813852039104271e-05, + "loss": 0.1949, "step": 107090 }, { - "epoch": 0.96, - "learning_rate": 2.232231330510765e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.813740184783338e-05, + "loss": 0.1985, "step": 107100 }, { - "epoch": 0.96, - "learning_rate": 2.227727231780921e-06, - "loss": 0.1731, + "epoch": 0.24, + "learning_rate": 3.813628330462406e-05, + "loss": 0.1997, "step": 107110 }, { - "epoch": 0.96, - "learning_rate": 2.2232231330510766e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.813516476141474e-05, + "loss": 0.1933, "step": 107120 }, { - "epoch": 0.96, - "learning_rate": 2.2187190343212324e-06, - "loss": 0.1779, + "epoch": 0.24, + "learning_rate": 3.813404621820541e-05, + "loss": 0.1949, "step": 107130 }, { - "epoch": 0.96, - "learning_rate": 2.2142149355913882e-06, - "loss": 0.1772, + "epoch": 0.24, + "learning_rate": 3.8132927674996086e-05, + "loss": 0.2025, "step": 107140 }, { - "epoch": 0.96, - "learning_rate": 2.209710836861544e-06, - "loss": 0.1721, + "epoch": 0.24, + "learning_rate": 3.8131809131786764e-05, + "loss": 0.1939, "step": 107150 }, { - "epoch": 0.96, - "learning_rate": 2.2052067381317e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.813069058857744e-05, + "loss": 0.2016, "step": 107160 }, { - "epoch": 0.96, - "learning_rate": 2.2007026394018556e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.812957204536812e-05, + "loss": 0.1979, "step": 107170 }, { - "epoch": 0.96, - "learning_rate": 2.196198540672012e-06, - "loss": 0.1724, + "epoch": 0.24, + "learning_rate": 3.812845350215879e-05, + "loss": 0.199, "step": 107180 }, { - "epoch": 0.96, - "learning_rate": 2.1916944419421676e-06, - "loss": 0.1692, + "epoch": 0.24, + "learning_rate": 3.812733495894947e-05, + "loss": 0.2021, "step": 107190 }, { - "epoch": 0.96, - "learning_rate": 2.187190343212323e-06, - "loss": 0.1707, + "epoch": 0.24, + "learning_rate": 3.812621641574014e-05, + "loss": 0.1934, "step": 107200 }, { - "epoch": 0.96, - "learning_rate": 2.1826862444824792e-06, - "loss": 0.1705, + "epoch": 0.24, + "learning_rate": 3.812509787253082e-05, + "loss": 0.1965, "step": 107210 }, { - "epoch": 0.96, - "learning_rate": 2.178182145752635e-06, - "loss": 0.1787, + "epoch": 0.24, + "learning_rate": 3.812397932932149e-05, + "loss": 0.1974, "step": 107220 }, { - "epoch": 0.96, - "learning_rate": 2.173678047022791e-06, - "loss": 0.18, + "epoch": 0.24, + "learning_rate": 3.812286078611217e-05, + "loss": 0.1936, "step": 107230 }, { - "epoch": 0.96, - "learning_rate": 2.1691739482929466e-06, - "loss": 0.1719, + "epoch": 0.24, + "learning_rate": 3.8121742242902845e-05, + "loss": 0.1974, "step": 107240 }, { - "epoch": 0.96, - "learning_rate": 2.1646698495631024e-06, - "loss": 0.1772, + "epoch": 0.24, + "learning_rate": 3.812062369969352e-05, + "loss": 0.2021, "step": 107250 }, { - "epoch": 0.96, - "learning_rate": 2.1601657508332586e-06, - "loss": 0.1747, + "epoch": 0.24, + "learning_rate": 3.81195051564842e-05, + "loss": 0.1976, "step": 107260 }, { - "epoch": 0.96, - "learning_rate": 2.155661652103414e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.811838661327487e-05, + "loss": 0.1997, "step": 107270 }, { - "epoch": 0.96, - "learning_rate": 2.1511575533735702e-06, - "loss": 0.1773, + "epoch": 0.24, + "learning_rate": 3.811726807006555e-05, + "loss": 0.1993, "step": 107280 }, { - "epoch": 0.96, - "learning_rate": 2.146653454643726e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.811614952685623e-05, + "loss": 0.2019, "step": 107290 }, { - "epoch": 0.96, - "learning_rate": 2.1421493559138814e-06, - "loss": 0.175, + "epoch": 0.24, + "learning_rate": 3.81150309836469e-05, + "loss": 0.1983, "step": 107300 }, { - "epoch": 0.96, - "learning_rate": 2.1376452571840376e-06, - "loss": 0.1747, + "epoch": 0.24, + "learning_rate": 3.811391244043758e-05, + "loss": 0.1982, "step": 107310 }, { - "epoch": 0.96, - "learning_rate": 2.1331411584541934e-06, - "loss": 0.1774, + "epoch": 0.24, + "learning_rate": 3.811279389722825e-05, + "loss": 0.1965, "step": 107320 }, { - "epoch": 0.96, - "learning_rate": 2.1286370597243492e-06, - "loss": 0.1829, + "epoch": 0.24, + "learning_rate": 3.8111675354018926e-05, + "loss": 0.1981, "step": 107330 }, { - "epoch": 0.96, - "learning_rate": 2.124132960994505e-06, - "loss": 0.1683, + "epoch": 0.24, + "learning_rate": 3.8110556810809604e-05, + "loss": 0.197, "step": 107340 }, { - "epoch": 0.96, - "learning_rate": 2.119628862264661e-06, - "loss": 0.1767, + "epoch": 0.24, + "learning_rate": 3.8109438267600275e-05, + "loss": 0.1923, "step": 107350 }, { - "epoch": 0.96, - "learning_rate": 2.115124763534817e-06, - "loss": 0.1747, + "epoch": 0.24, + "learning_rate": 3.810831972439095e-05, + "loss": 0.1983, "step": 107360 }, { - "epoch": 0.96, - "learning_rate": 2.1106206648049724e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.810720118118163e-05, + "loss": 0.1985, "step": 107370 }, { - "epoch": 0.96, - "learning_rate": 2.1061165660751282e-06, - "loss": 0.1781, + "epoch": 0.24, + "learning_rate": 3.810608263797231e-05, + "loss": 0.1977, "step": 107380 }, { - "epoch": 0.96, - "learning_rate": 2.1016124673452844e-06, - "loss": 0.1746, + "epoch": 0.24, + "learning_rate": 3.810496409476299e-05, + "loss": 0.1965, "step": 107390 }, { - "epoch": 0.96, - "learning_rate": 2.0971083686154402e-06, - "loss": 0.1751, + "epoch": 0.24, + "learning_rate": 3.810384555155366e-05, + "loss": 0.1985, "step": 107400 }, { - "epoch": 0.96, - "learning_rate": 2.092604269885596e-06, - "loss": 0.1779, + "epoch": 0.24, + "learning_rate": 3.8102727008344336e-05, + "loss": 0.1987, "step": 107410 }, { - "epoch": 0.96, - "learning_rate": 2.088100171155752e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.810160846513501e-05, + "loss": 0.1998, "step": 107420 }, { - "epoch": 0.96, - "learning_rate": 2.0835960724259076e-06, - "loss": 0.1716, + "epoch": 0.24, + "learning_rate": 3.8100489921925685e-05, + "loss": 0.2017, "step": 107430 }, { - "epoch": 0.96, - "learning_rate": 2.0790919736960634e-06, - "loss": 0.1745, + "epoch": 0.24, + "learning_rate": 3.809937137871636e-05, + "loss": 0.1984, "step": 107440 }, { - "epoch": 0.96, - "learning_rate": 2.0745878749662192e-06, - "loss": 0.172, + "epoch": 0.24, + "learning_rate": 3.8098252835507034e-05, + "loss": 0.1998, "step": 107450 }, { - "epoch": 0.96, - "learning_rate": 2.0700837762363755e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.809713429229771e-05, + "loss": 0.1983, "step": 107460 }, { - "epoch": 0.96, - "learning_rate": 2.0655796775065313e-06, - "loss": 0.1792, + "epoch": 0.24, + "learning_rate": 3.809601574908839e-05, + "loss": 0.1939, "step": 107470 }, { - "epoch": 0.96, - "learning_rate": 2.0610755787766866e-06, - "loss": 0.1757, + "epoch": 0.24, + "learning_rate": 3.809489720587907e-05, + "loss": 0.1951, "step": 107480 }, { - "epoch": 0.96, - "learning_rate": 2.056571480046843e-06, - "loss": 0.1704, + "epoch": 0.24, + "learning_rate": 3.8093778662669746e-05, + "loss": 0.1991, "step": 107490 }, { - "epoch": 0.96, - "learning_rate": 2.0520673813169986e-06, - "loss": 0.1754, + "epoch": 0.24, + "learning_rate": 3.809266011946042e-05, + "loss": 0.1971, "step": 107500 }, { - "epoch": 0.96, - "learning_rate": 2.0475632825871544e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.8091541576251095e-05, + "loss": 0.2008, "step": 107510 }, { - "epoch": 0.96, - "learning_rate": 2.0430591838573102e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.8090423033041766e-05, + "loss": 0.1932, "step": 107520 }, { - "epoch": 0.96, - "learning_rate": 2.038555085127466e-06, - "loss": 0.1727, + "epoch": 0.24, + "learning_rate": 3.8089304489832444e-05, + "loss": 0.1981, "step": 107530 }, { - "epoch": 0.96, - "learning_rate": 2.034050986397622e-06, - "loss": 0.1745, + "epoch": 0.24, + "learning_rate": 3.8088185946623115e-05, + "loss": 0.1913, "step": 107540 }, { - "epoch": 0.96, - "learning_rate": 2.0295468876677776e-06, - "loss": 0.1773, + "epoch": 0.24, + "learning_rate": 3.808706740341379e-05, + "loss": 0.1959, "step": 107550 }, { - "epoch": 0.96, - "learning_rate": 2.0250427889379334e-06, - "loss": 0.1719, + "epoch": 0.24, + "learning_rate": 3.808594886020447e-05, + "loss": 0.1989, "step": 107560 }, { - "epoch": 0.96, - "learning_rate": 2.0205386902080897e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.808483031699515e-05, + "loss": 0.2009, "step": 107570 }, { - "epoch": 0.96, - "learning_rate": 2.016034591478245e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.808371177378583e-05, + "loss": 0.1935, "step": 107580 }, { - "epoch": 0.96, - "learning_rate": 2.0115304927484013e-06, - "loss": 0.1728, + "epoch": 0.24, + "learning_rate": 3.80825932305765e-05, + "loss": 0.1946, "step": 107590 }, { - "epoch": 0.96, - "learning_rate": 2.007026394018557e-06, - "loss": 0.1726, + "epoch": 0.24, + "learning_rate": 3.8081474687367176e-05, + "loss": 0.1944, "step": 107600 }, { - "epoch": 0.96, - "learning_rate": 2.002522295288713e-06, - "loss": 0.1727, + "epoch": 0.24, + "learning_rate": 3.8080356144157854e-05, + "loss": 0.1918, "step": 107610 }, { - "epoch": 0.96, - "learning_rate": 1.9980181965588686e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.8079349455269456e-05, + "loss": 0.1998, "step": 107620 }, { - "epoch": 0.96, - "learning_rate": 1.9935140978290244e-06, - "loss": 0.175, + "epoch": 0.24, + "learning_rate": 3.8078230912060134e-05, + "loss": 0.1944, "step": 107630 }, { - "epoch": 0.96, - "learning_rate": 1.9890099990991807e-06, - "loss": 0.171, + "epoch": 0.24, + "learning_rate": 3.807711236885081e-05, + "loss": 0.1983, "step": 107640 }, { - "epoch": 0.96, - "learning_rate": 1.984505900369336e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.807599382564149e-05, + "loss": 0.1902, "step": 107650 }, { - "epoch": 0.96, - "learning_rate": 1.980001801639492e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.807487528243216e-05, + "loss": 0.1927, "step": 107660 }, { - "epoch": 0.96, - "learning_rate": 1.975497702909648e-06, - "loss": 0.1811, + "epoch": 0.24, + "learning_rate": 3.807375673922284e-05, + "loss": 0.1967, "step": 107670 }, { - "epoch": 0.96, - "learning_rate": 1.9709936041798034e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.8072638196013517e-05, + "loss": 0.1944, "step": 107680 }, { - "epoch": 0.96, - "learning_rate": 1.9664895054499597e-06, - "loss": 0.1802, + "epoch": 0.24, + "learning_rate": 3.807151965280419e-05, + "loss": 0.1998, "step": 107690 }, { - "epoch": 0.96, - "learning_rate": 1.9619854067201155e-06, - "loss": 0.1771, + "epoch": 0.24, + "learning_rate": 3.8070401109594866e-05, + "loss": 0.1946, "step": 107700 }, { - "epoch": 0.96, - "learning_rate": 1.9574813079902713e-06, - "loss": 0.1747, + "epoch": 0.24, + "learning_rate": 3.806928256638554e-05, + "loss": 0.1993, "step": 107710 }, { - "epoch": 0.96, - "learning_rate": 1.952977209260427e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.8068164023176215e-05, + "loss": 0.1978, "step": 107720 }, { - "epoch": 0.96, - "learning_rate": 1.948473110530583e-06, - "loss": 0.1783, + "epoch": 0.24, + "learning_rate": 3.806704547996689e-05, + "loss": 0.1939, "step": 107730 }, { - "epoch": 0.96, - "learning_rate": 1.9439690118007386e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.806592693675757e-05, + "loss": 0.1969, "step": 107740 }, { - "epoch": 0.96, - "learning_rate": 1.9394649130708944e-06, - "loss": 0.1742, + "epoch": 0.24, + "learning_rate": 3.806480839354825e-05, + "loss": 0.1961, "step": 107750 }, { - "epoch": 0.96, - "learning_rate": 1.9349608143410502e-06, - "loss": 0.1779, + "epoch": 0.24, + "learning_rate": 3.806368985033892e-05, + "loss": 0.1915, "step": 107760 }, { - "epoch": 0.96, - "learning_rate": 1.9304567156112065e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.80625713071296e-05, + "loss": 0.199, "step": 107770 }, { - "epoch": 0.96, - "learning_rate": 1.9259526168813623e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.8061452763920275e-05, + "loss": 0.1907, "step": 107780 }, { - "epoch": 0.96, - "learning_rate": 1.921448518151518e-06, - "loss": 0.1746, + "epoch": 0.24, + "learning_rate": 3.806033422071095e-05, + "loss": 0.1928, "step": 107790 }, { - "epoch": 0.96, - "learning_rate": 1.916944419421674e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.8059215677501625e-05, + "loss": 0.1978, "step": 107800 }, { - "epoch": 0.96, - "learning_rate": 1.9124403206918297e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.8058097134292296e-05, + "loss": 0.2011, "step": 107810 }, { - "epoch": 0.96, - "learning_rate": 1.9079362219619855e-06, - "loss": 0.1742, + "epoch": 0.24, + "learning_rate": 3.8056978591082974e-05, + "loss": 0.2039, "step": 107820 }, { - "epoch": 0.96, - "learning_rate": 1.9034321232321413e-06, - "loss": 0.1746, + "epoch": 0.24, + "learning_rate": 3.805586004787365e-05, + "loss": 0.1988, "step": 107830 }, { - "epoch": 0.96, - "learning_rate": 1.8989280245022973e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.805474150466433e-05, + "loss": 0.2027, "step": 107840 }, { - "epoch": 0.96, - "learning_rate": 1.8944239257724533e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.805362296145501e-05, + "loss": 0.1987, "step": 107850 }, { - "epoch": 0.96, - "learning_rate": 1.8899198270426089e-06, - "loss": 0.1746, + "epoch": 0.24, + "learning_rate": 3.805250441824568e-05, + "loss": 0.1939, "step": 107860 }, { - "epoch": 0.96, - "learning_rate": 1.8854157283127647e-06, - "loss": 0.1701, + "epoch": 0.24, + "learning_rate": 3.8051385875036356e-05, + "loss": 0.1958, "step": 107870 }, { - "epoch": 0.96, - "learning_rate": 1.8809116295829207e-06, - "loss": 0.1821, + "epoch": 0.24, + "learning_rate": 3.8050267331827034e-05, + "loss": 0.1944, "step": 107880 }, { - "epoch": 0.96, - "learning_rate": 1.8764075308530763e-06, - "loss": 0.1745, + "epoch": 0.24, + "learning_rate": 3.8049148788617706e-05, + "loss": 0.1986, "step": 107890 }, { - "epoch": 0.96, - "learning_rate": 1.8719034321232323e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.8048030245408383e-05, + "loss": 0.1972, "step": 107900 }, { - "epoch": 0.96, - "learning_rate": 1.867399333393388e-06, - "loss": 0.1717, + "epoch": 0.24, + "learning_rate": 3.8046911702199055e-05, + "loss": 0.1939, "step": 107910 }, { - "epoch": 0.96, - "learning_rate": 1.862895234663544e-06, - "loss": 0.1715, + "epoch": 0.24, + "learning_rate": 3.804579315898973e-05, + "loss": 0.1947, "step": 107920 }, { - "epoch": 0.96, - "learning_rate": 1.8583911359336997e-06, - "loss": 0.1751, + "epoch": 0.24, + "learning_rate": 3.8044674615780404e-05, + "loss": 0.2039, "step": 107930 }, { - "epoch": 0.96, - "learning_rate": 1.8538870372038557e-06, - "loss": 0.1783, + "epoch": 0.24, + "learning_rate": 3.804355607257108e-05, + "loss": 0.1982, "step": 107940 }, { - "epoch": 0.96, - "learning_rate": 1.8493829384740115e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.8042437529361766e-05, + "loss": 0.1932, "step": 107950 }, { - "epoch": 0.96, - "learning_rate": 1.844878839744167e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.804131898615244e-05, + "loss": 0.1986, "step": 107960 }, { - "epoch": 0.96, - "learning_rate": 1.840374741014323e-06, - "loss": 0.1737, + "epoch": 0.24, + "learning_rate": 3.8040200442943115e-05, + "loss": 0.1931, "step": 107970 }, { - "epoch": 0.96, - "learning_rate": 1.835870642284479e-06, - "loss": 0.1782, + "epoch": 0.24, + "learning_rate": 3.8039081899733787e-05, + "loss": 0.1903, "step": 107980 }, { - "epoch": 0.96, - "learning_rate": 1.8313665435546349e-06, - "loss": 0.1784, + "epoch": 0.24, + "learning_rate": 3.8037963356524465e-05, + "loss": 0.1956, "step": 107990 }, { - "epoch": 0.96, - "learning_rate": 1.8268624448247905e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.803684481331514e-05, + "loss": 0.1912, "step": 108000 }, { - "epoch": 0.96, - "learning_rate": 1.8223583460949465e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.8035726270105814e-05, + "loss": 0.1914, "step": 108010 }, { - "epoch": 0.96, - "learning_rate": 1.8178542473651025e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.803460772689649e-05, + "loss": 0.198, "step": 108020 }, { - "epoch": 0.96, - "learning_rate": 1.813350148635258e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.803348918368716e-05, + "loss": 0.1956, "step": 108030 }, { - "epoch": 0.96, - "learning_rate": 1.808846049905414e-06, - "loss": 0.1761, + "epoch": 0.24, + "learning_rate": 3.803237064047784e-05, + "loss": 0.1927, "step": 108040 }, { - "epoch": 0.96, - "learning_rate": 1.8043419511755699e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.803125209726852e-05, + "loss": 0.1924, "step": 108050 }, { - "epoch": 0.96, - "learning_rate": 1.7998378524457259e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.8030133554059196e-05, + "loss": 0.1907, "step": 108060 }, { - "epoch": 0.96, - "learning_rate": 1.7953337537158815e-06, - "loss": 0.1697, + "epoch": 0.24, + "learning_rate": 3.8029015010849874e-05, + "loss": 0.1946, "step": 108070 }, { - "epoch": 0.96, - "learning_rate": 1.7908296549860375e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.8027896467640546e-05, + "loss": 0.1972, "step": 108080 }, { - "epoch": 0.97, - "learning_rate": 1.7863255562561933e-06, - "loss": 0.1728, + "epoch": 0.24, + "learning_rate": 3.8026777924431223e-05, + "loss": 0.1996, "step": 108090 }, { - "epoch": 0.97, - "learning_rate": 1.7818214575263489e-06, - "loss": 0.175, + "epoch": 0.24, + "learning_rate": 3.80256593812219e-05, + "loss": 0.1906, "step": 108100 }, { - "epoch": 0.97, - "learning_rate": 1.7773173587965049e-06, - "loss": 0.1789, + "epoch": 0.24, + "learning_rate": 3.802454083801257e-05, + "loss": 0.1954, "step": 108110 }, { - "epoch": 0.97, - "learning_rate": 1.7728132600666609e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.802342229480325e-05, + "loss": 0.1967, "step": 108120 }, { - "epoch": 0.97, - "learning_rate": 1.7683091613368167e-06, - "loss": 0.1772, + "epoch": 0.24, + "learning_rate": 3.802230375159392e-05, + "loss": 0.1924, "step": 108130 }, { - "epoch": 0.97, - "learning_rate": 1.7638050626069723e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.80211852083846e-05, + "loss": 0.1952, "step": 108140 }, { - "epoch": 0.97, - "learning_rate": 1.7593009638771283e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.802006666517528e-05, + "loss": 0.1954, "step": 108150 }, { - "epoch": 0.97, - "learning_rate": 1.7547968651472843e-06, - "loss": 0.1767, + "epoch": 0.24, + "learning_rate": 3.8018948121965955e-05, + "loss": 0.2031, "step": 108160 }, { - "epoch": 0.97, - "learning_rate": 1.7502927664174399e-06, - "loss": 0.1774, + "epoch": 0.24, + "learning_rate": 3.801782957875663e-05, + "loss": 0.1993, "step": 108170 }, { - "epoch": 0.97, - "learning_rate": 1.7457886676875957e-06, - "loss": 0.1705, + "epoch": 0.24, + "learning_rate": 3.8016711035547304e-05, + "loss": 0.1931, "step": 108180 }, { - "epoch": 0.97, - "learning_rate": 1.7412845689577517e-06, - "loss": 0.1714, + "epoch": 0.24, + "learning_rate": 3.801559249233798e-05, + "loss": 0.1988, "step": 108190 }, { - "epoch": 0.97, - "learning_rate": 1.7367804702279073e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.8014473949128654e-05, + "loss": 0.1927, "step": 108200 }, { - "epoch": 0.97, - "learning_rate": 1.7322763714980633e-06, - "loss": 0.1787, + "epoch": 0.24, + "learning_rate": 3.801335540591933e-05, + "loss": 0.1921, "step": 108210 }, { - "epoch": 0.97, - "learning_rate": 1.7277722727682193e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.801223686271001e-05, + "loss": 0.197, "step": 108220 }, { - "epoch": 0.97, - "learning_rate": 1.723268174038375e-06, - "loss": 0.1847, + "epoch": 0.24, + "learning_rate": 3.801111831950068e-05, + "loss": 0.1966, "step": 108230 }, { - "epoch": 0.97, - "learning_rate": 1.7187640753085307e-06, - "loss": 0.1689, + "epoch": 0.24, + "learning_rate": 3.800999977629136e-05, + "loss": 0.1916, "step": 108240 }, { - "epoch": 0.97, - "learning_rate": 1.7142599765786867e-06, - "loss": 0.1706, + "epoch": 0.24, + "learning_rate": 3.8008881233082036e-05, + "loss": 0.1954, "step": 108250 }, { - "epoch": 0.97, - "learning_rate": 1.7097558778488427e-06, - "loss": 0.1743, + "epoch": 0.24, + "learning_rate": 3.8007762689872714e-05, + "loss": 0.1924, "step": 108260 }, { - "epoch": 0.97, - "learning_rate": 1.7052517791189983e-06, - "loss": 0.1779, + "epoch": 0.24, + "learning_rate": 3.800664414666339e-05, + "loss": 0.1948, "step": 108270 }, { - "epoch": 0.97, - "learning_rate": 1.700747680389154e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.8005525603454063e-05, + "loss": 0.1958, "step": 108280 }, { - "epoch": 0.97, - "learning_rate": 1.69624358165931e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.800440706024474e-05, + "loss": 0.1942, "step": 108290 }, { - "epoch": 0.97, - "learning_rate": 1.691739482929466e-06, - "loss": 0.1839, + "epoch": 0.24, + "learning_rate": 3.800328851703541e-05, + "loss": 0.1926, "step": 108300 }, { - "epoch": 0.97, - "learning_rate": 1.6872353841996217e-06, - "loss": 0.1746, + "epoch": 0.24, + "learning_rate": 3.800216997382609e-05, + "loss": 0.1939, "step": 108310 }, { - "epoch": 0.97, - "learning_rate": 1.6827312854697775e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.800105143061677e-05, + "loss": 0.2021, "step": 108320 }, { - "epoch": 0.97, - "learning_rate": 1.6782271867399335e-06, - "loss": 0.1806, + "epoch": 0.24, + "learning_rate": 3.799993288740744e-05, + "loss": 0.1981, "step": 108330 }, { - "epoch": 0.97, - "learning_rate": 1.673723088010089e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.799881434419812e-05, + "loss": 0.1972, "step": 108340 }, { - "epoch": 0.97, - "learning_rate": 1.669218989280245e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.799769580098879e-05, + "loss": 0.192, "step": 108350 }, { - "epoch": 0.97, - "learning_rate": 1.6647148905504009e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.7996577257779467e-05, + "loss": 0.1937, "step": 108360 }, { - "epoch": 0.97, - "learning_rate": 1.6602107918205569e-06, - "loss": 0.1799, + "epoch": 0.24, + "learning_rate": 3.799545871457015e-05, + "loss": 0.1964, "step": 108370 }, { - "epoch": 0.97, - "learning_rate": 1.6557066930907125e-06, - "loss": 0.1763, + "epoch": 0.24, + "learning_rate": 3.799434017136082e-05, + "loss": 0.1971, "step": 108380 }, { - "epoch": 0.97, - "learning_rate": 1.6512025943608685e-06, - "loss": 0.1774, + "epoch": 0.24, + "learning_rate": 3.79932216281515e-05, + "loss": 0.1984, "step": 108390 }, { - "epoch": 0.97, - "learning_rate": 1.6466984956310245e-06, - "loss": 0.17, + "epoch": 0.24, + "learning_rate": 3.799210308494217e-05, + "loss": 0.1958, "step": 108400 }, { - "epoch": 0.97, - "learning_rate": 1.64219439690118e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.799098454173285e-05, + "loss": 0.194, "step": 108410 }, { - "epoch": 0.97, - "learning_rate": 1.6376902981713359e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.798986599852353e-05, + "loss": 0.1929, "step": 108420 }, { - "epoch": 0.97, - "learning_rate": 1.6331861994414919e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.79887474553142e-05, + "loss": 0.1991, "step": 108430 }, { - "epoch": 0.97, - "learning_rate": 1.628682100711648e-06, - "loss": 0.1663, + "epoch": 0.24, + "learning_rate": 3.7987628912104876e-05, + "loss": 0.1985, "step": 108440 }, { - "epoch": 0.97, - "learning_rate": 1.6241780019818035e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.798651036889555e-05, + "loss": 0.1929, "step": 108450 }, { - "epoch": 0.97, - "learning_rate": 1.6196739032519593e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.7985391825686225e-05, + "loss": 0.1949, "step": 108460 }, { - "epoch": 0.97, - "learning_rate": 1.6151698045221153e-06, - "loss": 0.1808, + "epoch": 0.24, + "learning_rate": 3.7984273282476903e-05, + "loss": 0.1968, "step": 108470 }, { - "epoch": 0.97, - "learning_rate": 1.6106657057922709e-06, - "loss": 0.171, + "epoch": 0.24, + "learning_rate": 3.798315473926758e-05, + "loss": 0.1924, "step": 108480 }, { - "epoch": 0.97, - "learning_rate": 1.6061616070624269e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.798203619605826e-05, + "loss": 0.1955, "step": 108490 }, { - "epoch": 0.97, - "learning_rate": 1.6016575083325827e-06, - "loss": 0.179, + "epoch": 0.24, + "learning_rate": 3.798091765284893e-05, + "loss": 0.1934, "step": 108500 }, { - "epoch": 0.97, - "learning_rate": 1.5971534096027387e-06, - "loss": 0.175, + "epoch": 0.24, + "learning_rate": 3.797979910963961e-05, + "loss": 0.1956, "step": 108510 }, { - "epoch": 0.97, - "learning_rate": 1.5926493108728943e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.797868056643028e-05, + "loss": 0.1969, "step": 108520 }, { - "epoch": 0.97, - "learning_rate": 1.5881452121430503e-06, - "loss": 0.1771, + "epoch": 0.24, + "learning_rate": 3.797756202322096e-05, + "loss": 0.1953, "step": 108530 }, { - "epoch": 0.97, - "learning_rate": 1.583641113413206e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.7976443480011635e-05, + "loss": 0.1993, "step": 108540 }, { - "epoch": 0.97, - "learning_rate": 1.579137014683362e-06, - "loss": 0.1769, + "epoch": 0.24, + "learning_rate": 3.7975324936802306e-05, + "loss": 0.1937, "step": 108550 }, { - "epoch": 0.97, - "learning_rate": 1.5746329159535177e-06, - "loss": 0.1751, + "epoch": 0.24, + "learning_rate": 3.7974206393592984e-05, + "loss": 0.196, "step": 108560 }, { - "epoch": 0.97, - "learning_rate": 1.5701288172236737e-06, - "loss": 0.1729, + "epoch": 0.24, + "learning_rate": 3.797308785038366e-05, + "loss": 0.1951, "step": 108570 }, { - "epoch": 0.97, - "learning_rate": 1.5656247184938297e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.797196930717434e-05, + "loss": 0.2012, "step": 108580 }, { - "epoch": 0.97, - "learning_rate": 1.5611206197639853e-06, - "loss": 0.1695, + "epoch": 0.24, + "learning_rate": 3.797085076396502e-05, + "loss": 0.199, "step": 108590 }, { - "epoch": 0.97, - "learning_rate": 1.556616521034141e-06, - "loss": 0.1721, + "epoch": 0.24, + "learning_rate": 3.796973222075569e-05, + "loss": 0.1998, "step": 108600 }, { - "epoch": 0.97, - "learning_rate": 1.552112422304297e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.796861367754637e-05, + "loss": 0.1941, "step": 108610 }, { - "epoch": 0.97, - "learning_rate": 1.547608323574453e-06, - "loss": 0.1729, + "epoch": 0.24, + "learning_rate": 3.796749513433704e-05, + "loss": 0.1976, "step": 108620 }, { - "epoch": 0.97, - "learning_rate": 1.5431042248446087e-06, - "loss": 0.1717, + "epoch": 0.24, + "learning_rate": 3.7966376591127716e-05, + "loss": 0.1953, "step": 108630 }, { - "epoch": 0.97, - "learning_rate": 1.5386001261147645e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.7965258047918394e-05, + "loss": 0.2031, "step": 108640 }, { - "epoch": 0.97, - "learning_rate": 1.5340960273849203e-06, - "loss": 0.177, + "epoch": 0.24, + "learning_rate": 3.7964139504709065e-05, + "loss": 0.1938, "step": 108650 }, { - "epoch": 0.97, - "learning_rate": 1.529591928655076e-06, - "loss": 0.176, + "epoch": 0.24, + "learning_rate": 3.796302096149974e-05, + "loss": 0.197, "step": 108660 }, { - "epoch": 0.97, - "learning_rate": 1.5250878299252321e-06, - "loss": 0.1748, + "epoch": 0.24, + "learning_rate": 3.796190241829042e-05, + "loss": 0.1947, "step": 108670 }, { - "epoch": 0.97, - "learning_rate": 1.520583731195388e-06, - "loss": 0.1672, + "epoch": 0.24, + "learning_rate": 3.79607838750811e-05, + "loss": 0.1982, "step": 108680 }, { - "epoch": 0.97, - "learning_rate": 1.5160796324655437e-06, - "loss": 0.1681, + "epoch": 0.24, + "learning_rate": 3.795966533187178e-05, + "loss": 0.1911, "step": 108690 }, { - "epoch": 0.97, - "learning_rate": 1.5115755337356995e-06, - "loss": 0.1721, + "epoch": 0.24, + "learning_rate": 3.795854678866245e-05, + "loss": 0.1961, "step": 108700 }, { - "epoch": 0.97, - "learning_rate": 1.5070714350058555e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.7957428245453126e-05, + "loss": 0.1938, "step": 108710 }, { - "epoch": 0.97, - "learning_rate": 1.5025673362760113e-06, - "loss": 0.1712, + "epoch": 0.24, + "learning_rate": 3.79563097022438e-05, + "loss": 0.1955, "step": 108720 }, { - "epoch": 0.97, - "learning_rate": 1.4980632375461671e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.7955191159034475e-05, + "loss": 0.1962, "step": 108730 }, { - "epoch": 0.97, - "learning_rate": 1.493559138816323e-06, - "loss": 0.1715, + "epoch": 0.24, + "learning_rate": 3.795407261582515e-05, + "loss": 0.1934, "step": 108740 }, { - "epoch": 0.97, - "learning_rate": 1.4890550400864787e-06, - "loss": 0.1682, + "epoch": 0.24, + "learning_rate": 3.7952954072615824e-05, + "loss": 0.1981, "step": 108750 }, { - "epoch": 0.97, - "learning_rate": 1.4845509413566347e-06, - "loss": 0.1764, + "epoch": 0.24, + "learning_rate": 3.79518355294065e-05, + "loss": 0.1932, "step": 108760 }, { - "epoch": 0.97, - "learning_rate": 1.4800468426267905e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.7950716986197173e-05, + "loss": 0.1962, "step": 108770 }, { - "epoch": 0.97, - "learning_rate": 1.4755427438969463e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.794959844298786e-05, + "loss": 0.2023, "step": 108780 }, { - "epoch": 0.97, - "learning_rate": 1.4710386451671021e-06, - "loss": 0.1787, + "epoch": 0.24, + "learning_rate": 3.7948479899778536e-05, + "loss": 0.1948, "step": 108790 }, { - "epoch": 0.97, - "learning_rate": 1.466534546437258e-06, - "loss": 0.1834, + "epoch": 0.24, + "learning_rate": 3.794736135656921e-05, + "loss": 0.1983, "step": 108800 }, { - "epoch": 0.97, - "learning_rate": 1.462030447707414e-06, - "loss": 0.1752, + "epoch": 0.24, + "learning_rate": 3.7946242813359885e-05, + "loss": 0.1933, "step": 108810 }, { - "epoch": 0.97, - "learning_rate": 1.4575263489775697e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.7945124270150556e-05, + "loss": 0.1955, "step": 108820 }, { - "epoch": 0.97, - "learning_rate": 1.4530222502477255e-06, - "loss": 0.1729, + "epoch": 0.24, + "learning_rate": 3.7944005726941234e-05, + "loss": 0.1911, "step": 108830 }, { - "epoch": 0.97, - "learning_rate": 1.4485181515178813e-06, - "loss": 0.1721, + "epoch": 0.24, + "learning_rate": 3.7942887183731905e-05, + "loss": 0.1947, "step": 108840 }, { - "epoch": 0.97, - "learning_rate": 1.4440140527880373e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.794176864052258e-05, + "loss": 0.1881, "step": 108850 }, { - "epoch": 0.97, - "learning_rate": 1.4395099540581931e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.794065009731326e-05, + "loss": 0.1899, "step": 108860 }, { - "epoch": 0.97, - "learning_rate": 1.4350058553283487e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.793953155410393e-05, + "loss": 0.1981, "step": 108870 }, { - "epoch": 0.97, - "learning_rate": 1.4305017565985047e-06, - "loss": 0.1754, + "epoch": 0.24, + "learning_rate": 3.793841301089461e-05, + "loss": 0.183, "step": 108880 }, { - "epoch": 0.97, - "learning_rate": 1.4259976578686605e-06, - "loss": 0.1667, + "epoch": 0.24, + "learning_rate": 3.793729446768529e-05, + "loss": 0.1994, "step": 108890 }, { - "epoch": 0.97, - "learning_rate": 1.4214935591388165e-06, - "loss": 0.1707, + "epoch": 0.24, + "learning_rate": 3.7936175924475966e-05, + "loss": 0.1925, "step": 108900 }, { - "epoch": 0.97, - "learning_rate": 1.4169894604089723e-06, - "loss": 0.1777, + "epoch": 0.24, + "learning_rate": 3.7935057381266644e-05, + "loss": 0.2006, "step": 108910 }, { - "epoch": 0.97, - "learning_rate": 1.412485361679128e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.7933938838057315e-05, + "loss": 0.1926, "step": 108920 }, { - "epoch": 0.97, - "learning_rate": 1.407981262949284e-06, - "loss": 0.1719, + "epoch": 0.24, + "learning_rate": 3.793282029484799e-05, + "loss": 0.193, "step": 108930 }, { - "epoch": 0.97, - "learning_rate": 1.4034771642194397e-06, - "loss": 0.1717, + "epoch": 0.24, + "learning_rate": 3.7931701751638664e-05, + "loss": 0.1958, "step": 108940 }, { - "epoch": 0.97, - "learning_rate": 1.3989730654895957e-06, - "loss": 0.1781, + "epoch": 0.24, + "learning_rate": 3.793058320842934e-05, + "loss": 0.1996, "step": 108950 }, { - "epoch": 0.97, - "learning_rate": 1.3944689667597513e-06, - "loss": 0.1752, + "epoch": 0.24, + "learning_rate": 3.792946466522002e-05, + "loss": 0.1968, "step": 108960 }, { - "epoch": 0.97, - "learning_rate": 1.3899648680299073e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.792834612201069e-05, + "loss": 0.1967, "step": 108970 }, { - "epoch": 0.97, - "learning_rate": 1.3854607693000631e-06, - "loss": 0.171, + "epoch": 0.24, + "learning_rate": 3.792722757880137e-05, + "loss": 0.1947, "step": 108980 }, { - "epoch": 0.97, - "learning_rate": 1.380956670570219e-06, - "loss": 0.1736, + "epoch": 0.24, + "learning_rate": 3.792610903559205e-05, + "loss": 0.1938, "step": 108990 }, { - "epoch": 0.97, - "learning_rate": 1.376452571840375e-06, - "loss": 0.1708, + "epoch": 0.24, + "learning_rate": 3.7924990492382725e-05, + "loss": 0.1917, "step": 109000 }, { - "epoch": 0.97, - "learning_rate": 1.3719484731105305e-06, - "loss": 0.173, + "epoch": 0.24, + "learning_rate": 3.79238719491734e-05, + "loss": 0.1977, "step": 109010 }, { - "epoch": 0.97, - "learning_rate": 1.3674443743806865e-06, - "loss": 0.1769, + "epoch": 0.24, + "learning_rate": 3.7922753405964074e-05, + "loss": 0.1998, "step": 109020 }, { - "epoch": 0.97, - "learning_rate": 1.3629402756508423e-06, - "loss": 0.1703, + "epoch": 0.24, + "learning_rate": 3.792163486275475e-05, + "loss": 0.2054, "step": 109030 }, { - "epoch": 0.97, - "learning_rate": 1.3584361769209983e-06, - "loss": 0.1757, + "epoch": 0.24, + "learning_rate": 3.792051631954542e-05, + "loss": 0.1952, "step": 109040 }, { - "epoch": 0.97, - "learning_rate": 1.353932078191154e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.79193977763361e-05, + "loss": 0.1989, "step": 109050 }, { - "epoch": 0.97, - "learning_rate": 1.3494279794613097e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.791827923312678e-05, + "loss": 0.1932, "step": 109060 }, { - "epoch": 0.97, - "learning_rate": 1.3449238807314657e-06, - "loss": 0.1686, + "epoch": 0.24, + "learning_rate": 3.791716068991745e-05, + "loss": 0.1948, "step": 109070 }, { - "epoch": 0.97, - "learning_rate": 1.3404197820016215e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.791604214670813e-05, + "loss": 0.1969, "step": 109080 }, { - "epoch": 0.97, - "learning_rate": 1.3359156832717775e-06, - "loss": 0.1762, + "epoch": 0.24, + "learning_rate": 3.7914923603498806e-05, + "loss": 0.1941, "step": 109090 }, { - "epoch": 0.97, - "learning_rate": 1.3314115845419331e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.7913805060289484e-05, + "loss": 0.195, "step": 109100 }, { - "epoch": 0.97, - "learning_rate": 1.3269074858120891e-06, - "loss": 0.1756, + "epoch": 0.24, + "learning_rate": 3.791268651708016e-05, + "loss": 0.1921, "step": 109110 }, { - "epoch": 0.97, - "learning_rate": 1.322403387082245e-06, - "loss": 0.1696, + "epoch": 0.24, + "learning_rate": 3.791156797387083e-05, + "loss": 0.1968, "step": 109120 }, { - "epoch": 0.97, - "learning_rate": 1.3178992883524007e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.791044943066151e-05, + "loss": 0.1956, "step": 109130 }, { - "epoch": 0.97, - "learning_rate": 1.3133951896225565e-06, - "loss": 0.1788, + "epoch": 0.24, + "learning_rate": 3.790933088745218e-05, + "loss": 0.1903, "step": 109140 }, { - "epoch": 0.97, - "learning_rate": 1.3088910908927123e-06, - "loss": 0.1791, + "epoch": 0.24, + "learning_rate": 3.790821234424286e-05, + "loss": 0.1952, "step": 109150 }, { - "epoch": 0.97, - "learning_rate": 1.3043869921628683e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.790709380103353e-05, + "loss": 0.1974, "step": 109160 }, { - "epoch": 0.97, - "learning_rate": 1.2998828934330241e-06, - "loss": 0.1776, + "epoch": 0.24, + "learning_rate": 3.790597525782421e-05, + "loss": 0.1963, "step": 109170 }, { - "epoch": 0.97, - "learning_rate": 1.2953787947031801e-06, - "loss": 0.1822, + "epoch": 0.24, + "learning_rate": 3.790485671461489e-05, + "loss": 0.1969, "step": 109180 }, { - "epoch": 0.97, - "learning_rate": 1.2908746959733357e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.790373817140556e-05, + "loss": 0.1977, "step": 109190 }, { - "epoch": 0.97, - "learning_rate": 1.2863705972434915e-06, - "loss": 0.176, + "epoch": 0.24, + "learning_rate": 3.790261962819624e-05, + "loss": 0.1966, "step": 109200 }, { - "epoch": 0.98, - "learning_rate": 1.2818664985136475e-06, - "loss": 0.1749, + "epoch": 0.24, + "learning_rate": 3.7901501084986914e-05, + "loss": 0.1927, "step": 109210 }, { - "epoch": 0.98, - "learning_rate": 1.2773623997838033e-06, - "loss": 0.175, + "epoch": 0.24, + "learning_rate": 3.790038254177759e-05, + "loss": 0.1945, "step": 109220 }, { - "epoch": 0.98, - "learning_rate": 1.2728583010539591e-06, - "loss": 0.1765, + "epoch": 0.24, + "learning_rate": 3.789926399856827e-05, + "loss": 0.1954, "step": 109230 }, { - "epoch": 0.98, - "learning_rate": 1.268354202324115e-06, - "loss": 0.1716, + "epoch": 0.24, + "learning_rate": 3.789814545535894e-05, + "loss": 0.1901, "step": 109240 }, { - "epoch": 0.98, - "learning_rate": 1.2638501035942707e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.789702691214962e-05, + "loss": 0.1925, "step": 109250 }, { - "epoch": 0.98, - "learning_rate": 1.2593460048644267e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.789590836894029e-05, + "loss": 0.1971, "step": 109260 }, { - "epoch": 0.98, - "learning_rate": 1.2548419061345825e-06, - "loss": 0.1703, + "epoch": 0.24, + "learning_rate": 3.789478982573097e-05, + "loss": 0.1961, "step": 109270 }, { - "epoch": 0.98, - "learning_rate": 1.2503378074047383e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.7893671282521646e-05, + "loss": 0.1946, "step": 109280 }, { - "epoch": 0.98, - "learning_rate": 1.2458337086748941e-06, - "loss": 0.1759, + "epoch": 0.24, + "learning_rate": 3.789255273931232e-05, + "loss": 0.1923, "step": 109290 }, { - "epoch": 0.98, - "learning_rate": 1.2413296099450501e-06, - "loss": 0.176, + "epoch": 0.24, + "learning_rate": 3.7891434196102995e-05, + "loss": 0.1956, "step": 109300 }, { - "epoch": 0.98, - "learning_rate": 1.236825511215206e-06, - "loss": 0.1769, + "epoch": 0.24, + "learning_rate": 3.789031565289367e-05, + "loss": 0.1968, "step": 109310 }, { - "epoch": 0.98, - "learning_rate": 1.2323214124853617e-06, - "loss": 0.1774, + "epoch": 0.24, + "learning_rate": 3.788919710968435e-05, + "loss": 0.1933, "step": 109320 }, { - "epoch": 0.98, - "learning_rate": 1.2278173137555175e-06, - "loss": 0.1795, + "epoch": 0.24, + "learning_rate": 3.788807856647503e-05, + "loss": 0.1927, "step": 109330 }, { - "epoch": 0.98, - "learning_rate": 1.2233132150256733e-06, - "loss": 0.1719, + "epoch": 0.24, + "learning_rate": 3.78869600232657e-05, + "loss": 0.1983, "step": 109340 }, { - "epoch": 0.98, - "learning_rate": 1.2188091162958293e-06, - "loss": 0.1773, + "epoch": 0.24, + "learning_rate": 3.788584148005638e-05, + "loss": 0.1925, "step": 109350 }, { - "epoch": 0.98, - "learning_rate": 1.2143050175659851e-06, - "loss": 0.1728, + "epoch": 0.24, + "learning_rate": 3.788472293684705e-05, + "loss": 0.1902, "step": 109360 }, { - "epoch": 0.98, - "learning_rate": 1.209800918836141e-06, - "loss": 0.1709, + "epoch": 0.24, + "learning_rate": 3.788360439363773e-05, + "loss": 0.1966, "step": 109370 }, { - "epoch": 0.98, - "learning_rate": 1.2052968201062967e-06, - "loss": 0.1768, + "epoch": 0.24, + "learning_rate": 3.7882485850428405e-05, + "loss": 0.1905, "step": 109380 }, { - "epoch": 0.98, - "learning_rate": 1.2007927213764525e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.7881367307219076e-05, + "loss": 0.1919, "step": 109390 }, { - "epoch": 0.98, - "learning_rate": 1.1962886226466085e-06, - "loss": 0.1801, + "epoch": 0.24, + "learning_rate": 3.7880248764009754e-05, + "loss": 0.1946, "step": 109400 }, { - "epoch": 0.98, - "learning_rate": 1.1917845239167643e-06, - "loss": 0.1805, + "epoch": 0.24, + "learning_rate": 3.787913022080043e-05, + "loss": 0.1949, "step": 109410 }, { - "epoch": 0.98, - "learning_rate": 1.1872804251869201e-06, - "loss": 0.1744, + "epoch": 0.24, + "learning_rate": 3.787801167759111e-05, + "loss": 0.1945, "step": 109420 }, { - "epoch": 0.98, - "learning_rate": 1.182776326457076e-06, - "loss": 0.1784, + "epoch": 0.24, + "learning_rate": 3.787689313438179e-05, + "loss": 0.1959, "step": 109430 }, { - "epoch": 0.98, - "learning_rate": 1.1787226376002161e-06, - "loss": 0.1724, + "epoch": 0.24, + "learning_rate": 3.787577459117246e-05, + "loss": 0.195, "step": 109440 }, { - "epoch": 0.98, - "learning_rate": 1.1742185388703721e-06, - "loss": 0.1802, + "epoch": 0.24, + "learning_rate": 3.787465604796314e-05, + "loss": 0.1913, "step": 109450 }, { - "epoch": 0.98, - "learning_rate": 1.169714440140528e-06, - "loss": 0.1702, + "epoch": 0.24, + "learning_rate": 3.787353750475381e-05, + "loss": 0.1955, "step": 109460 }, { - "epoch": 0.98, - "learning_rate": 1.165210341410684e-06, - "loss": 0.1687, + "epoch": 0.24, + "learning_rate": 3.7872418961544486e-05, + "loss": 0.1985, "step": 109470 }, { - "epoch": 0.98, - "learning_rate": 1.1607062426808395e-06, - "loss": 0.1785, + "epoch": 0.24, + "learning_rate": 3.787130041833516e-05, + "loss": 0.2013, "step": 109480 }, { - "epoch": 0.98, - "learning_rate": 1.1562021439509955e-06, - "loss": 0.1753, + "epoch": 0.24, + "learning_rate": 3.7870181875125835e-05, + "loss": 0.1992, "step": 109490 }, { - "epoch": 0.98, - "learning_rate": 1.1516980452211513e-06, - "loss": 0.1766, + "epoch": 0.24, + "learning_rate": 3.786906333191651e-05, + "loss": 0.1946, "step": 109500 }, { - "epoch": 0.98, - "learning_rate": 1.1471939464913071e-06, - "loss": 0.174, + "epoch": 0.24, + "learning_rate": 3.786794478870719e-05, + "loss": 0.1981, "step": 109510 }, { - "epoch": 0.98, - "learning_rate": 1.142689847761463e-06, - "loss": 0.1745, + "epoch": 0.24, + "learning_rate": 3.786682624549787e-05, + "loss": 0.1976, "step": 109520 }, { - "epoch": 0.98, - "learning_rate": 1.1381857490316187e-06, - "loss": 0.1733, + "epoch": 0.24, + "learning_rate": 3.786570770228854e-05, + "loss": 0.1928, "step": 109530 }, { - "epoch": 0.98, - "learning_rate": 1.1336816503017747e-06, - "loss": 0.1741, + "epoch": 0.24, + "learning_rate": 3.786458915907922e-05, + "loss": 0.196, "step": 109540 }, { - "epoch": 0.98, - "learning_rate": 1.1291775515719305e-06, - "loss": 0.1725, + "epoch": 0.24, + "learning_rate": 3.7863470615869896e-05, + "loss": 0.1952, "step": 109550 }, { - "epoch": 0.98, - "learning_rate": 1.1246734528420863e-06, - "loss": 0.1724, + "epoch": 0.24, + "learning_rate": 3.786235207266057e-05, + "loss": 0.1876, "step": 109560 }, { - "epoch": 0.98, - "learning_rate": 1.1201693541122421e-06, - "loss": 0.1758, + "epoch": 0.24, + "learning_rate": 3.7861233529451245e-05, + "loss": 0.1942, "step": 109570 }, { - "epoch": 0.98, - "learning_rate": 1.115665255382398e-06, - "loss": 0.1771, + "epoch": 0.24, + "learning_rate": 3.7860114986241916e-05, + "loss": 0.1968, "step": 109580 }, { - "epoch": 0.98, - "learning_rate": 1.111161156652554e-06, - "loss": 0.1732, + "epoch": 0.24, + "learning_rate": 3.7858996443032594e-05, + "loss": 0.1973, "step": 109590 }, { - "epoch": 0.98, - "learning_rate": 1.1066570579227097e-06, - "loss": 0.1808, + "epoch": 0.24, + "learning_rate": 3.785787789982327e-05, + "loss": 0.1959, "step": 109600 }, { - "epoch": 0.98, - "learning_rate": 1.1021529591928655e-06, - "loss": 0.1731, + "epoch": 0.24, + "learning_rate": 3.785675935661395e-05, + "loss": 0.1911, "step": 109610 }, { - "epoch": 0.98, - "learning_rate": 1.0976488604630213e-06, - "loss": 0.1723, + "epoch": 0.24, + "learning_rate": 3.785575266772556e-05, + "loss": 0.1977, "step": 109620 }, { - "epoch": 0.98, - "learning_rate": 1.0931447617331771e-06, - "loss": 0.1711, + "epoch": 0.24, + "learning_rate": 3.785463412451623e-05, + "loss": 0.1968, "step": 109630 }, { - "epoch": 0.98, - "learning_rate": 1.0886406630033331e-06, - "loss": 0.1704, + "epoch": 0.24, + "learning_rate": 3.785351558130691e-05, + "loss": 0.1932, "step": 109640 }, { - "epoch": 0.98, - "learning_rate": 1.084136564273489e-06, - "loss": 0.1712, + "epoch": 0.24, + "learning_rate": 3.785239703809758e-05, + "loss": 0.1957, "step": 109650 }, { - "epoch": 0.98, - "learning_rate": 1.0796324655436447e-06, - "loss": 0.1663, + "epoch": 0.24, + "learning_rate": 3.785127849488826e-05, + "loss": 0.1937, "step": 109660 }, { - "epoch": 0.98, - "learning_rate": 1.0751283668138005e-06, - "loss": 0.1739, + "epoch": 0.24, + "learning_rate": 3.7850159951678935e-05, + "loss": 0.1892, "step": 109670 }, { - "epoch": 0.98, - "learning_rate": 1.0706242680839565e-06, - "loss": 0.1734, + "epoch": 0.24, + "learning_rate": 3.784904140846961e-05, + "loss": 0.1959, "step": 109680 }, { - "epoch": 0.98, - "learning_rate": 1.0661201693541123e-06, - "loss": 0.1727, + "epoch": 0.24, + "learning_rate": 3.784792286526029e-05, + "loss": 0.1957, "step": 109690 }, { - "epoch": 0.98, - "learning_rate": 1.0616160706242681e-06, - "loss": 0.172, + "epoch": 0.24, + "learning_rate": 3.784680432205096e-05, + "loss": 0.1998, "step": 109700 }, { - "epoch": 0.98, - "learning_rate": 1.057111971894424e-06, - "loss": 0.1784, + "epoch": 0.24, + "learning_rate": 3.784568577884164e-05, + "loss": 0.1931, "step": 109710 }, { - "epoch": 0.98, - "learning_rate": 1.0526078731645797e-06, - "loss": 0.1755, + "epoch": 0.24, + "learning_rate": 3.784456723563232e-05, + "loss": 0.1932, "step": 109720 }, { - "epoch": 0.98, - "learning_rate": 1.0481037744347357e-06, - "loss": 0.1789, + "epoch": 0.24, + "learning_rate": 3.784344869242299e-05, + "loss": 0.1942, "step": 109730 }, { - "epoch": 0.98, - "learning_rate": 1.0435996757048915e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.784233014921367e-05, + "loss": 0.1958, "step": 109740 }, { - "epoch": 0.98, - "learning_rate": 1.0390955769750473e-06, - "loss": 0.1735, + "epoch": 0.24, + "learning_rate": 3.784121160600434e-05, + "loss": 0.1987, "step": 109750 }, { - "epoch": 0.98, - "learning_rate": 1.0345914782452031e-06, - "loss": 0.1778, + "epoch": 0.24, + "learning_rate": 3.7840093062795016e-05, + "loss": 0.1931, "step": 109760 }, { - "epoch": 0.98, - "learning_rate": 1.030087379515359e-06, - "loss": 0.1635, + "epoch": 0.25, + "learning_rate": 3.7838974519585694e-05, + "loss": 0.1976, "step": 109770 }, { - "epoch": 0.98, - "learning_rate": 1.025583280785515e-06, - "loss": 0.1769, + "epoch": 0.25, + "learning_rate": 3.783785597637637e-05, + "loss": 0.1947, "step": 109780 }, { - "epoch": 0.98, - "learning_rate": 1.0210791820556707e-06, - "loss": 0.1722, + "epoch": 0.25, + "learning_rate": 3.783673743316705e-05, + "loss": 0.2002, "step": 109790 }, { - "epoch": 0.98, - "learning_rate": 1.0165750833258265e-06, - "loss": 0.1655, + "epoch": 0.25, + "learning_rate": 3.783561888995772e-05, + "loss": 0.1949, "step": 109800 }, { - "epoch": 0.98, - "learning_rate": 1.0120709845959823e-06, - "loss": 0.1635, + "epoch": 0.25, + "learning_rate": 3.78345003467484e-05, + "loss": 0.1957, "step": 109810 }, { - "epoch": 0.98, - "learning_rate": 1.0075668858661381e-06, - "loss": 0.1718, + "epoch": 0.25, + "learning_rate": 3.783338180353908e-05, + "loss": 0.1944, "step": 109820 }, { - "epoch": 0.98, - "learning_rate": 1.0030627871362941e-06, - "loss": 0.174, + "epoch": 0.25, + "learning_rate": 3.783226326032975e-05, + "loss": 0.1957, "step": 109830 }, { - "epoch": 0.98, - "learning_rate": 9.9855868840645e-07, - "loss": 0.1737, + "epoch": 0.25, + "learning_rate": 3.7831144717120426e-05, + "loss": 0.1911, "step": 109840 }, { - "epoch": 0.98, - "learning_rate": 9.940545896766057e-07, - "loss": 0.175, + "epoch": 0.25, + "learning_rate": 3.78300261739111e-05, + "loss": 0.1998, "step": 109850 }, { - "epoch": 0.98, - "learning_rate": 9.895504909467615e-07, - "loss": 0.1736, + "epoch": 0.25, + "learning_rate": 3.7828907630701775e-05, + "loss": 0.1914, "step": 109860 }, { - "epoch": 0.98, - "learning_rate": 9.850463922169176e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.7827789087492446e-05, + "loss": 0.1973, "step": 109870 }, { - "epoch": 0.98, - "learning_rate": 9.805422934870733e-07, - "loss": 0.1799, + "epoch": 0.25, + "learning_rate": 3.7826670544283124e-05, + "loss": 0.1961, "step": 109880 }, { - "epoch": 0.98, - "learning_rate": 9.760381947572291e-07, - "loss": 0.1747, + "epoch": 0.25, + "learning_rate": 3.78255520010738e-05, + "loss": 0.2006, "step": 109890 }, { - "epoch": 0.98, - "learning_rate": 9.71534096027385e-07, - "loss": 0.173, + "epoch": 0.25, + "learning_rate": 3.782443345786448e-05, + "loss": 0.1948, "step": 109900 }, { - "epoch": 0.98, - "learning_rate": 9.670299972975407e-07, - "loss": 0.176, + "epoch": 0.25, + "learning_rate": 3.782331491465516e-05, + "loss": 0.1923, "step": 109910 }, { - "epoch": 0.98, - "learning_rate": 9.625258985676968e-07, - "loss": 0.1785, + "epoch": 0.25, + "learning_rate": 3.782219637144583e-05, + "loss": 0.1987, "step": 109920 }, { - "epoch": 0.98, - "learning_rate": 9.580217998378526e-07, - "loss": 0.1725, + "epoch": 0.25, + "learning_rate": 3.782107782823651e-05, + "loss": 0.1885, "step": 109930 }, { - "epoch": 0.98, - "learning_rate": 9.535177011080085e-07, - "loss": 0.1704, + "epoch": 0.25, + "learning_rate": 3.7819959285027185e-05, + "loss": 0.1925, "step": 109940 }, { - "epoch": 0.98, - "learning_rate": 9.490136023781641e-07, - "loss": 0.1812, + "epoch": 0.25, + "learning_rate": 3.7818840741817856e-05, + "loss": 0.1936, "step": 109950 }, { - "epoch": 0.98, - "learning_rate": 9.445095036483199e-07, - "loss": 0.1737, + "epoch": 0.25, + "learning_rate": 3.7817722198608534e-05, + "loss": 0.2019, "step": 109960 }, { - "epoch": 0.98, - "learning_rate": 9.400054049184759e-07, - "loss": 0.1744, + "epoch": 0.25, + "learning_rate": 3.7816603655399205e-05, + "loss": 0.1947, "step": 109970 }, { - "epoch": 0.98, - "learning_rate": 9.355013061886316e-07, - "loss": 0.1771, + "epoch": 0.25, + "learning_rate": 3.781548511218988e-05, + "loss": 0.1971, "step": 109980 }, { - "epoch": 0.98, - "learning_rate": 9.309972074587876e-07, - "loss": 0.1756, + "epoch": 0.25, + "learning_rate": 3.781436656898056e-05, + "loss": 0.1916, "step": 109990 }, { - "epoch": 0.98, - "learning_rate": 9.264931087289434e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.781324802577124e-05, + "loss": 0.196, "step": 110000 }, { - "epoch": 0.98, - "learning_rate": 9.219890099990993e-07, - "loss": 0.176, + "epoch": 0.25, + "learning_rate": 3.781212948256192e-05, + "loss": 0.1984, "step": 110010 }, { - "epoch": 0.98, - "learning_rate": 9.17484911269255e-07, - "loss": 0.1794, + "epoch": 0.25, + "learning_rate": 3.781101093935259e-05, + "loss": 0.197, "step": 110020 }, { - "epoch": 0.98, - "learning_rate": 9.129808125394109e-07, - "loss": 0.1708, + "epoch": 0.25, + "learning_rate": 3.7809892396143266e-05, + "loss": 0.1942, "step": 110030 }, { - "epoch": 0.98, - "learning_rate": 9.084767138095668e-07, - "loss": 0.1685, + "epoch": 0.25, + "learning_rate": 3.7808773852933944e-05, + "loss": 0.1974, "step": 110040 }, { - "epoch": 0.98, - "learning_rate": 9.039726150797226e-07, - "loss": 0.1778, + "epoch": 0.25, + "learning_rate": 3.7807655309724615e-05, + "loss": 0.1947, "step": 110050 }, { - "epoch": 0.98, - "learning_rate": 8.994685163498785e-07, - "loss": 0.1751, + "epoch": 0.25, + "learning_rate": 3.780653676651529e-05, + "loss": 0.192, "step": 110060 }, { - "epoch": 0.98, - "learning_rate": 8.949644176200343e-07, - "loss": 0.1783, + "epoch": 0.25, + "learning_rate": 3.7805418223305964e-05, + "loss": 0.196, "step": 110070 }, { - "epoch": 0.98, - "learning_rate": 8.904603188901902e-07, - "loss": 0.1731, + "epoch": 0.25, + "learning_rate": 3.780429968009664e-05, + "loss": 0.2009, "step": 110080 }, { - "epoch": 0.98, - "learning_rate": 8.85956220160346e-07, - "loss": 0.1686, + "epoch": 0.25, + "learning_rate": 3.780318113688732e-05, + "loss": 0.1897, "step": 110090 }, { - "epoch": 0.98, - "learning_rate": 8.814521214305018e-07, - "loss": 0.1728, + "epoch": 0.25, + "learning_rate": 3.7802062593678e-05, + "loss": 0.199, "step": 110100 }, { - "epoch": 0.98, - "learning_rate": 8.769480227006577e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.7800944050468676e-05, + "loss": 0.1949, "step": 110110 }, { - "epoch": 0.98, - "learning_rate": 8.724439239708135e-07, - "loss": 0.1722, + "epoch": 0.25, + "learning_rate": 3.779982550725935e-05, + "loss": 0.1951, "step": 110120 }, { - "epoch": 0.98, - "learning_rate": 8.679398252409694e-07, - "loss": 0.1719, + "epoch": 0.25, + "learning_rate": 3.7798706964050025e-05, + "loss": 0.1957, "step": 110130 }, { - "epoch": 0.98, - "learning_rate": 8.634357265111252e-07, - "loss": 0.1732, + "epoch": 0.25, + "learning_rate": 3.77975884208407e-05, + "loss": 0.1979, "step": 110140 }, { - "epoch": 0.98, - "learning_rate": 8.58931627781281e-07, - "loss": 0.1705, + "epoch": 0.25, + "learning_rate": 3.7796469877631374e-05, + "loss": 0.1967, "step": 110150 }, { - "epoch": 0.98, - "learning_rate": 8.544275290514369e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.779535133442205e-05, + "loss": 0.1943, "step": 110160 }, { - "epoch": 0.98, - "learning_rate": 8.499234303215927e-07, - "loss": 0.1708, + "epoch": 0.25, + "learning_rate": 3.779423279121272e-05, + "loss": 0.1982, "step": 110170 }, { - "epoch": 0.98, - "learning_rate": 8.454193315917486e-07, - "loss": 0.1666, + "epoch": 0.25, + "learning_rate": 3.77931142480034e-05, + "loss": 0.1888, "step": 110180 }, { - "epoch": 0.98, - "learning_rate": 8.409152328619044e-07, - "loss": 0.1813, + "epoch": 0.25, + "learning_rate": 3.779199570479408e-05, + "loss": 0.1934, "step": 110190 }, { - "epoch": 0.98, - "learning_rate": 8.364111341320603e-07, - "loss": 0.171, + "epoch": 0.25, + "learning_rate": 3.7790877161584757e-05, + "loss": 0.1916, "step": 110200 }, { - "epoch": 0.98, - "learning_rate": 8.319070354022161e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.7789758618375435e-05, + "loss": 0.1924, "step": 110210 }, { - "epoch": 0.98, - "learning_rate": 8.274029366723719e-07, - "loss": 0.1761, + "epoch": 0.25, + "learning_rate": 3.7788640075166106e-05, + "loss": 0.1894, "step": 110220 }, { - "epoch": 0.98, - "learning_rate": 8.228988379425278e-07, - "loss": 0.1778, + "epoch": 0.25, + "learning_rate": 3.7787521531956784e-05, + "loss": 0.1963, "step": 110230 }, { - "epoch": 0.98, - "learning_rate": 8.183947392126836e-07, - "loss": 0.1673, + "epoch": 0.25, + "learning_rate": 3.7786402988747455e-05, + "loss": 0.1951, "step": 110240 }, { - "epoch": 0.98, - "learning_rate": 8.138906404828395e-07, - "loss": 0.1733, + "epoch": 0.25, + "learning_rate": 3.778528444553813e-05, + "loss": 0.1967, "step": 110250 }, { - "epoch": 0.98, - "learning_rate": 8.093865417529953e-07, - "loss": 0.1745, + "epoch": 0.25, + "learning_rate": 3.778416590232881e-05, + "loss": 0.189, "step": 110260 }, { - "epoch": 0.98, - "learning_rate": 8.048824430231512e-07, - "loss": 0.1803, + "epoch": 0.25, + "learning_rate": 3.778304735911948e-05, + "loss": 0.195, "step": 110270 }, { - "epoch": 0.98, - "learning_rate": 8.00378344293307e-07, - "loss": 0.1824, + "epoch": 0.25, + "learning_rate": 3.778192881591016e-05, + "loss": 0.1999, "step": 110280 }, { - "epoch": 0.98, - "learning_rate": 7.958742455634628e-07, - "loss": 0.1752, + "epoch": 0.25, + "learning_rate": 3.778081027270083e-05, + "loss": 0.1941, "step": 110290 }, { - "epoch": 0.98, - "learning_rate": 7.913701468336187e-07, - "loss": 0.1792, + "epoch": 0.25, + "learning_rate": 3.777969172949151e-05, + "loss": 0.1943, "step": 110300 }, { - "epoch": 0.98, - "learning_rate": 7.868660481037745e-07, - "loss": 0.1731, + "epoch": 0.25, + "learning_rate": 3.7778573186282193e-05, + "loss": 0.1896, "step": 110310 }, { - "epoch": 0.98, - "learning_rate": 7.823619493739304e-07, - "loss": 0.1738, + "epoch": 0.25, + "learning_rate": 3.7777454643072865e-05, + "loss": 0.1928, "step": 110320 }, { - "epoch": 0.99, - "learning_rate": 7.778578506440862e-07, - "loss": 0.1771, + "epoch": 0.25, + "learning_rate": 3.777633609986354e-05, + "loss": 0.1903, "step": 110330 }, { - "epoch": 0.99, - "learning_rate": 7.73353751914242e-07, - "loss": 0.1681, + "epoch": 0.25, + "learning_rate": 3.7775217556654214e-05, + "loss": 0.1953, "step": 110340 }, { - "epoch": 0.99, - "learning_rate": 7.688496531843979e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.777409901344489e-05, + "loss": 0.1976, "step": 110350 }, { - "epoch": 0.99, - "learning_rate": 7.643455544545537e-07, - "loss": 0.1718, + "epoch": 0.25, + "learning_rate": 3.777298047023557e-05, + "loss": 0.1973, "step": 110360 }, { - "epoch": 0.99, - "learning_rate": 7.598414557247096e-07, - "loss": 0.1703, + "epoch": 0.25, + "learning_rate": 3.777186192702624e-05, + "loss": 0.1931, "step": 110370 }, { - "epoch": 0.99, - "learning_rate": 7.553373569948654e-07, - "loss": 0.1765, + "epoch": 0.25, + "learning_rate": 3.777074338381692e-05, + "loss": 0.1894, "step": 110380 }, { - "epoch": 0.99, - "learning_rate": 7.508332582650212e-07, - "loss": 0.176, + "epoch": 0.25, + "learning_rate": 3.776962484060759e-05, + "loss": 0.1925, "step": 110390 }, { - "epoch": 0.99, - "learning_rate": 7.463291595351771e-07, - "loss": 0.1742, + "epoch": 0.25, + "learning_rate": 3.776850629739827e-05, + "loss": 0.194, "step": 110400 }, { - "epoch": 0.99, - "learning_rate": 7.418250608053329e-07, - "loss": 0.1736, + "epoch": 0.25, + "learning_rate": 3.7767387754188946e-05, + "loss": 0.1951, "step": 110410 }, { - "epoch": 0.99, - "learning_rate": 7.373209620754888e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.7766269210979624e-05, + "loss": 0.2001, "step": 110420 }, { - "epoch": 0.99, - "learning_rate": 7.328168633456446e-07, - "loss": 0.1701, + "epoch": 0.25, + "learning_rate": 3.77651506677703e-05, + "loss": 0.1946, "step": 110430 }, { - "epoch": 0.99, - "learning_rate": 7.283127646158005e-07, - "loss": 0.1767, + "epoch": 0.25, + "learning_rate": 3.776403212456097e-05, + "loss": 0.1943, "step": 110440 }, { - "epoch": 0.99, - "learning_rate": 7.238086658859562e-07, - "loss": 0.1728, + "epoch": 0.25, + "learning_rate": 3.776291358135165e-05, + "loss": 0.1915, "step": 110450 }, { - "epoch": 0.99, - "learning_rate": 7.193045671561121e-07, - "loss": 0.1782, + "epoch": 0.25, + "learning_rate": 3.776179503814233e-05, + "loss": 0.1932, "step": 110460 }, { - "epoch": 0.99, - "learning_rate": 7.14800468426268e-07, - "loss": 0.1733, + "epoch": 0.25, + "learning_rate": 3.7760676494933e-05, + "loss": 0.1994, "step": 110470 }, { - "epoch": 0.99, - "learning_rate": 7.102963696964238e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.775955795172368e-05, + "loss": 0.1928, "step": 110480 }, { - "epoch": 0.99, - "learning_rate": 7.057922709665797e-07, - "loss": 0.177, + "epoch": 0.25, + "learning_rate": 3.775843940851435e-05, + "loss": 0.1978, "step": 110490 }, { - "epoch": 0.99, - "learning_rate": 7.012881722367355e-07, - "loss": 0.169, + "epoch": 0.25, + "learning_rate": 3.775732086530503e-05, + "loss": 0.1942, "step": 110500 }, { - "epoch": 0.99, - "learning_rate": 6.967840735068913e-07, - "loss": 0.1783, + "epoch": 0.25, + "learning_rate": 3.7756202322095705e-05, + "loss": 0.1924, "step": 110510 }, { - "epoch": 0.99, - "learning_rate": 6.922799747770471e-07, - "loss": 0.1767, + "epoch": 0.25, + "learning_rate": 3.775508377888638e-05, + "loss": 0.1907, "step": 110520 }, { - "epoch": 0.99, - "learning_rate": 6.87775876047203e-07, - "loss": 0.1748, + "epoch": 0.25, + "learning_rate": 3.775396523567706e-05, + "loss": 0.1874, "step": 110530 }, { - "epoch": 0.99, - "learning_rate": 6.832717773173588e-07, - "loss": 0.1712, + "epoch": 0.25, + "learning_rate": 3.775284669246773e-05, + "loss": 0.1928, "step": 110540 }, { - "epoch": 0.99, - "learning_rate": 6.787676785875147e-07, - "loss": 0.1716, + "epoch": 0.25, + "learning_rate": 3.775172814925841e-05, + "loss": 0.1938, "step": 110550 }, { - "epoch": 0.99, - "learning_rate": 6.742635798576706e-07, - "loss": 0.175, + "epoch": 0.25, + "learning_rate": 3.775060960604908e-05, + "loss": 0.1969, "step": 110560 }, { - "epoch": 0.99, - "learning_rate": 6.697594811278264e-07, - "loss": 0.1754, + "epoch": 0.25, + "learning_rate": 3.774949106283976e-05, + "loss": 0.1956, "step": 110570 }, { - "epoch": 0.99, - "learning_rate": 6.652553823979822e-07, - "loss": 0.1784, + "epoch": 0.25, + "learning_rate": 3.7748372519630437e-05, + "loss": 0.1899, "step": 110580 }, { - "epoch": 0.99, - "learning_rate": 6.60751283668138e-07, - "loss": 0.1717, + "epoch": 0.25, + "learning_rate": 3.774725397642111e-05, + "loss": 0.1949, "step": 110590 }, { - "epoch": 0.99, - "learning_rate": 6.562471849382939e-07, - "loss": 0.1768, + "epoch": 0.25, + "learning_rate": 3.7746135433211786e-05, + "loss": 0.2006, "step": 110600 }, { - "epoch": 0.99, - "learning_rate": 6.517430862084497e-07, - "loss": 0.1772, + "epoch": 0.25, + "learning_rate": 3.7745016890002464e-05, + "loss": 0.1963, "step": 110610 }, { - "epoch": 0.99, - "learning_rate": 6.472389874786056e-07, - "loss": 0.1715, + "epoch": 0.25, + "learning_rate": 3.774389834679314e-05, + "loss": 0.1933, "step": 110620 }, { - "epoch": 0.99, - "learning_rate": 6.427348887487614e-07, - "loss": 0.1739, + "epoch": 0.25, + "learning_rate": 3.774277980358382e-05, + "loss": 0.1941, "step": 110630 }, { - "epoch": 0.99, - "learning_rate": 6.382307900189172e-07, - "loss": 0.1784, + "epoch": 0.25, + "learning_rate": 3.774166126037449e-05, + "loss": 0.1921, "step": 110640 }, { - "epoch": 0.99, - "learning_rate": 6.337266912890731e-07, - "loss": 0.1755, + "epoch": 0.25, + "learning_rate": 3.774054271716517e-05, + "loss": 0.19, "step": 110650 }, { - "epoch": 0.99, - "learning_rate": 6.292225925592289e-07, - "loss": 0.1771, + "epoch": 0.25, + "learning_rate": 3.773942417395584e-05, + "loss": 0.1959, "step": 110660 }, { - "epoch": 0.99, - "learning_rate": 6.247184938293848e-07, - "loss": 0.1683, + "epoch": 0.25, + "learning_rate": 3.773830563074652e-05, + "loss": 0.1889, "step": 110670 }, { - "epoch": 0.99, - "learning_rate": 6.202143950995406e-07, - "loss": 0.176, + "epoch": 0.25, + "learning_rate": 3.7737187087537195e-05, + "loss": 0.1922, "step": 110680 }, { - "epoch": 0.99, - "learning_rate": 6.157102963696965e-07, - "loss": 0.1706, + "epoch": 0.25, + "learning_rate": 3.773606854432787e-05, + "loss": 0.1912, "step": 110690 }, { - "epoch": 0.99, - "learning_rate": 6.112061976398523e-07, - "loss": 0.1759, + "epoch": 0.25, + "learning_rate": 3.7734950001118545e-05, + "loss": 0.1948, "step": 110700 }, { - "epoch": 0.99, - "learning_rate": 6.067020989100081e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.7733831457909216e-05, + "loss": 0.1966, "step": 110710 }, { - "epoch": 0.99, - "learning_rate": 6.02198000180164e-07, - "loss": 0.1797, + "epoch": 0.25, + "learning_rate": 3.7732712914699894e-05, + "loss": 0.1917, "step": 110720 }, { - "epoch": 0.99, - "learning_rate": 5.976939014503198e-07, - "loss": 0.1658, + "epoch": 0.25, + "learning_rate": 3.773159437149058e-05, + "loss": 0.1918, "step": 110730 }, { - "epoch": 0.99, - "learning_rate": 5.931898027204757e-07, - "loss": 0.178, + "epoch": 0.25, + "learning_rate": 3.773047582828125e-05, + "loss": 0.1915, "step": 110740 }, { - "epoch": 0.99, - "learning_rate": 5.886857039906315e-07, - "loss": 0.1756, + "epoch": 0.25, + "learning_rate": 3.772935728507193e-05, + "loss": 0.1913, "step": 110750 }, { - "epoch": 0.99, - "learning_rate": 5.841816052607874e-07, - "loss": 0.1763, + "epoch": 0.25, + "learning_rate": 3.77282387418626e-05, + "loss": 0.1859, "step": 110760 }, { - "epoch": 0.99, - "learning_rate": 5.796775065309432e-07, - "loss": 0.1778, + "epoch": 0.25, + "learning_rate": 3.7727120198653277e-05, + "loss": 0.2001, "step": 110770 }, { - "epoch": 0.99, - "learning_rate": 5.75173407801099e-07, - "loss": 0.1733, + "epoch": 0.25, + "learning_rate": 3.7726001655443954e-05, + "loss": 0.1917, "step": 110780 }, { - "epoch": 0.99, - "learning_rate": 5.706693090712549e-07, - "loss": 0.1725, + "epoch": 0.25, + "learning_rate": 3.7724883112234626e-05, + "loss": 0.1971, "step": 110790 }, { - "epoch": 0.99, - "learning_rate": 5.661652103414107e-07, - "loss": 0.1747, + "epoch": 0.25, + "learning_rate": 3.7723764569025304e-05, + "loss": 0.1964, "step": 110800 }, { - "epoch": 0.99, - "learning_rate": 5.616611116115666e-07, - "loss": 0.1716, + "epoch": 0.25, + "learning_rate": 3.7722646025815975e-05, + "loss": 0.1954, "step": 110810 }, { - "epoch": 0.99, - "learning_rate": 5.571570128817224e-07, - "loss": 0.1714, + "epoch": 0.25, + "learning_rate": 3.772152748260665e-05, + "loss": 0.1923, "step": 110820 }, { - "epoch": 0.99, - "learning_rate": 5.526529141518783e-07, - "loss": 0.1681, + "epoch": 0.25, + "learning_rate": 3.772040893939733e-05, + "loss": 0.1946, "step": 110830 }, { - "epoch": 0.99, - "learning_rate": 5.48148815422034e-07, - "loss": 0.1752, + "epoch": 0.25, + "learning_rate": 3.771929039618801e-05, + "loss": 0.198, "step": 110840 }, { - "epoch": 0.99, - "learning_rate": 5.436447166921899e-07, - "loss": 0.1721, + "epoch": 0.25, + "learning_rate": 3.7718171852978686e-05, + "loss": 0.1946, "step": 110850 }, { - "epoch": 0.99, - "learning_rate": 5.391406179623458e-07, - "loss": 0.173, + "epoch": 0.25, + "learning_rate": 3.771705330976936e-05, + "loss": 0.1919, "step": 110860 }, { - "epoch": 0.99, - "learning_rate": 5.346365192325016e-07, - "loss": 0.1741, + "epoch": 0.25, + "learning_rate": 3.7715934766560035e-05, + "loss": 0.1952, "step": 110870 }, { - "epoch": 0.99, - "learning_rate": 5.301324205026575e-07, - "loss": 0.181, + "epoch": 0.25, + "learning_rate": 3.7714816223350707e-05, + "loss": 0.1938, "step": 110880 }, { - "epoch": 0.99, - "learning_rate": 5.256283217728133e-07, - "loss": 0.1715, + "epoch": 0.25, + "learning_rate": 3.7713697680141385e-05, + "loss": 0.1966, "step": 110890 }, { - "epoch": 0.99, - "learning_rate": 5.211242230429692e-07, - "loss": 0.1764, + "epoch": 0.25, + "learning_rate": 3.771257913693206e-05, + "loss": 0.1903, "step": 110900 }, { - "epoch": 0.99, - "learning_rate": 5.166201243131249e-07, - "loss": 0.1756, + "epoch": 0.25, + "learning_rate": 3.7711460593722734e-05, + "loss": 0.1925, "step": 110910 }, { - "epoch": 0.99, - "learning_rate": 5.121160255832808e-07, - "loss": 0.1811, + "epoch": 0.25, + "learning_rate": 3.771034205051341e-05, + "loss": 0.1969, "step": 110920 }, { - "epoch": 0.99, - "learning_rate": 5.076119268534366e-07, - "loss": 0.1703, + "epoch": 0.25, + "learning_rate": 3.770922350730409e-05, + "loss": 0.1963, "step": 110930 }, { - "epoch": 0.99, - "learning_rate": 5.031078281235925e-07, - "loss": 0.1733, + "epoch": 0.25, + "learning_rate": 3.770810496409477e-05, + "loss": 0.1943, "step": 110940 }, { - "epoch": 0.99, - "learning_rate": 4.986037293937484e-07, - "loss": 0.1743, + "epoch": 0.25, + "learning_rate": 3.7706986420885445e-05, + "loss": 0.1961, "step": 110950 }, { - "epoch": 0.99, - "learning_rate": 4.940996306639042e-07, - "loss": 0.1727, + "epoch": 0.25, + "learning_rate": 3.7705867877676116e-05, + "loss": 0.194, "step": 110960 }, { - "epoch": 0.99, - "learning_rate": 4.8959553193406e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.7704749334466794e-05, + "loss": 0.1923, "step": 110970 }, { - "epoch": 0.99, - "learning_rate": 4.850914332042158e-07, - "loss": 0.1707, + "epoch": 0.25, + "learning_rate": 3.7703630791257466e-05, + "loss": 0.1955, "step": 110980 }, { - "epoch": 0.99, - "learning_rate": 4.805873344743717e-07, - "loss": 0.1768, + "epoch": 0.25, + "learning_rate": 3.7702512248048143e-05, + "loss": 0.1924, "step": 110990 }, { - "epoch": 0.99, - "learning_rate": 4.7608323574452756e-07, - "loss": 0.174, + "epoch": 0.25, + "learning_rate": 3.770139370483882e-05, + "loss": 0.194, "step": 111000 }, { - "epoch": 0.99, - "learning_rate": 4.715791370146834e-07, - "loss": 0.1765, + "epoch": 0.25, + "learning_rate": 3.770027516162949e-05, + "loss": 0.1898, "step": 111010 }, { - "epoch": 0.99, - "learning_rate": 4.6707503828483926e-07, - "loss": 0.177, + "epoch": 0.25, + "learning_rate": 3.769915661842017e-05, + "loss": 0.194, "step": 111020 }, { - "epoch": 0.99, - "learning_rate": 4.625709395549951e-07, - "loss": 0.1735, + "epoch": 0.25, + "learning_rate": 3.769803807521085e-05, + "loss": 0.1954, "step": 111030 }, { - "epoch": 0.99, - "learning_rate": 4.5806684082515085e-07, - "loss": 0.1758, + "epoch": 0.25, + "learning_rate": 3.7696919532001526e-05, + "loss": 0.1966, "step": 111040 }, { - "epoch": 0.99, - "learning_rate": 4.535627420953067e-07, - "loss": 0.174, + "epoch": 0.25, + "learning_rate": 3.7695800988792204e-05, + "loss": 0.1954, "step": 111050 }, { - "epoch": 0.99, - "learning_rate": 4.490586433654626e-07, - "loss": 0.1782, + "epoch": 0.25, + "learning_rate": 3.7694682445582875e-05, + "loss": 0.1957, "step": 111060 }, { - "epoch": 0.99, - "learning_rate": 4.4455454463561846e-07, - "loss": 0.1797, + "epoch": 0.25, + "learning_rate": 3.769356390237355e-05, + "loss": 0.193, "step": 111070 }, { - "epoch": 0.99, - "learning_rate": 4.400504459057743e-07, - "loss": 0.1744, + "epoch": 0.25, + "learning_rate": 3.7692445359164224e-05, + "loss": 0.2006, "step": 111080 }, { - "epoch": 0.99, - "learning_rate": 4.3554634717593016e-07, - "loss": 0.172, + "epoch": 0.25, + "learning_rate": 3.76913268159549e-05, + "loss": 0.1921, "step": 111090 }, { - "epoch": 0.99, - "learning_rate": 4.310422484460859e-07, - "loss": 0.1732, + "epoch": 0.25, + "learning_rate": 3.7690208272745574e-05, + "loss": 0.1904, "step": 111100 }, { - "epoch": 0.99, - "learning_rate": 4.2653814971624176e-07, - "loss": 0.1754, + "epoch": 0.25, + "learning_rate": 3.768908972953625e-05, + "loss": 0.1956, "step": 111110 }, { - "epoch": 0.99, - "learning_rate": 4.220340509863976e-07, - "loss": 0.1732, + "epoch": 0.25, + "learning_rate": 3.768797118632693e-05, + "loss": 0.196, "step": 111120 }, { - "epoch": 0.99, - "learning_rate": 4.1752995225655346e-07, - "loss": 0.1726, + "epoch": 0.25, + "learning_rate": 3.76868526431176e-05, + "loss": 0.1929, "step": 111130 }, { - "epoch": 0.99, - "learning_rate": 4.130258535267093e-07, - "loss": 0.1745, + "epoch": 0.25, + "learning_rate": 3.7685734099908285e-05, + "loss": 0.1924, "step": 111140 }, { - "epoch": 0.99, - "learning_rate": 4.085217547968652e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.7684615556698956e-05, + "loss": 0.1919, "step": 111150 }, { - "epoch": 0.99, - "learning_rate": 4.0401765606702107e-07, - "loss": 0.1781, + "epoch": 0.25, + "learning_rate": 3.7683497013489634e-05, + "loss": 0.1951, "step": 111160 }, { - "epoch": 0.99, - "learning_rate": 3.995135573371768e-07, - "loss": 0.1734, + "epoch": 0.25, + "learning_rate": 3.768237847028031e-05, + "loss": 0.1961, "step": 111170 }, { - "epoch": 0.99, - "learning_rate": 3.9500945860733266e-07, - "loss": 0.1724, + "epoch": 0.25, + "learning_rate": 3.7681259927070983e-05, + "loss": 0.1929, "step": 111180 }, { - "epoch": 0.99, - "learning_rate": 3.905053598774885e-07, - "loss": 0.1771, + "epoch": 0.25, + "learning_rate": 3.768014138386166e-05, + "loss": 0.1936, "step": 111190 }, { - "epoch": 0.99, - "learning_rate": 3.8600126114764436e-07, - "loss": 0.1731, + "epoch": 0.25, + "learning_rate": 3.767902284065233e-05, + "loss": 0.1916, "step": 111200 }, { - "epoch": 0.99, - "learning_rate": 3.814971624178002e-07, - "loss": 0.1678, + "epoch": 0.25, + "learning_rate": 3.767790429744301e-05, + "loss": 0.1937, "step": 111210 }, { - "epoch": 0.99, - "learning_rate": 3.7699306368795607e-07, - "loss": 0.1759, + "epoch": 0.25, + "learning_rate": 3.767678575423369e-05, + "loss": 0.1884, "step": 111220 }, { - "epoch": 0.99, - "learning_rate": 3.724889649581119e-07, - "loss": 0.1794, + "epoch": 0.25, + "learning_rate": 3.767566721102436e-05, + "loss": 0.1919, "step": 111230 }, { - "epoch": 0.99, - "learning_rate": 3.6798486622826777e-07, - "loss": 0.1769, + "epoch": 0.25, + "learning_rate": 3.767454866781504e-05, + "loss": 0.1945, "step": 111240 }, { - "epoch": 0.99, - "learning_rate": 3.6348076749842357e-07, - "loss": 0.1762, + "epoch": 0.25, + "learning_rate": 3.7673430124605715e-05, + "loss": 0.1939, "step": 111250 }, { - "epoch": 0.99, - "learning_rate": 3.589766687685794e-07, - "loss": 0.1741, + "epoch": 0.25, + "learning_rate": 3.767231158139639e-05, + "loss": 0.199, "step": 111260 }, { - "epoch": 0.99, - "learning_rate": 3.5447257003873527e-07, - "loss": 0.1723, + "epoch": 0.25, + "learning_rate": 3.767119303818707e-05, + "loss": 0.1922, "step": 111270 }, { - "epoch": 0.99, - "learning_rate": 3.4996847130889107e-07, - "loss": 0.1778, + "epoch": 0.25, + "learning_rate": 3.767007449497774e-05, + "loss": 0.1939, "step": 111280 }, { - "epoch": 0.99, - "learning_rate": 3.454643725790469e-07, - "loss": 0.1814, + "epoch": 0.25, + "learning_rate": 3.766895595176842e-05, + "loss": 0.1974, "step": 111290 }, { - "epoch": 0.99, - "learning_rate": 3.409602738492028e-07, - "loss": 0.1765, + "epoch": 0.25, + "learning_rate": 3.766783740855909e-05, + "loss": 0.1965, "step": 111300 }, { - "epoch": 0.99, - "learning_rate": 3.3645617511935867e-07, - "loss": 0.1758, + "epoch": 0.25, + "learning_rate": 3.766671886534977e-05, + "loss": 0.1907, "step": 111310 }, { - "epoch": 0.99, - "learning_rate": 3.3195207638951447e-07, - "loss": 0.1739, + "epoch": 0.25, + "learning_rate": 3.766560032214045e-05, + "loss": 0.1935, "step": 111320 }, { - "epoch": 0.99, - "learning_rate": 3.274479776596703e-07, - "loss": 0.1771, + "epoch": 0.25, + "learning_rate": 3.766448177893112e-05, + "loss": 0.1981, "step": 111330 }, { - "epoch": 0.99, - "learning_rate": 3.2294387892982617e-07, - "loss": 0.1778, + "epoch": 0.25, + "learning_rate": 3.7663363235721796e-05, + "loss": 0.1946, "step": 111340 }, { - "epoch": 0.99, - "learning_rate": 3.1843978019998197e-07, - "loss": 0.1727, + "epoch": 0.25, + "learning_rate": 3.7662244692512474e-05, + "loss": 0.195, "step": 111350 }, { - "epoch": 0.99, - "learning_rate": 3.139356814701378e-07, - "loss": 0.1774, + "epoch": 0.25, + "learning_rate": 3.766112614930315e-05, + "loss": 0.1969, "step": 111360 }, { - "epoch": 0.99, - "learning_rate": 3.094315827402937e-07, - "loss": 0.173, + "epoch": 0.25, + "learning_rate": 3.766000760609383e-05, + "loss": 0.1971, "step": 111370 }, { - "epoch": 0.99, - "learning_rate": 3.049274840104495e-07, - "loss": 0.1745, + "epoch": 0.25, + "learning_rate": 3.76588890628845e-05, + "loss": 0.1937, "step": 111380 }, { - "epoch": 0.99, - "learning_rate": 3.004233852806054e-07, - "loss": 0.1757, + "epoch": 0.25, + "learning_rate": 3.765777051967518e-05, + "loss": 0.1948, "step": 111390 }, { - "epoch": 0.99, - "learning_rate": 2.9591928655076123e-07, - "loss": 0.1796, + "epoch": 0.25, + "learning_rate": 3.765665197646585e-05, + "loss": 0.2001, "step": 111400 }, { - "epoch": 0.99, - "learning_rate": 2.914151878209171e-07, - "loss": 0.1683, + "epoch": 0.25, + "learning_rate": 3.765553343325653e-05, + "loss": 0.1951, "step": 111410 }, { - "epoch": 0.99, - "learning_rate": 2.869110890910729e-07, - "loss": 0.1757, + "epoch": 0.25, + "learning_rate": 3.76544148900472e-05, + "loss": 0.1951, "step": 111420 }, { - "epoch": 0.99, - "learning_rate": 2.8240699036122873e-07, - "loss": 0.1814, + "epoch": 0.25, + "learning_rate": 3.765329634683788e-05, + "loss": 0.1992, "step": 111430 }, { - "epoch": 0.99, - "learning_rate": 2.779028916313846e-07, - "loss": 0.1723, + "epoch": 0.25, + "learning_rate": 3.7652177803628555e-05, + "loss": 0.1977, "step": 111440 }, { - "epoch": 1.0, - "learning_rate": 2.733987929015404e-07, - "loss": 0.174, + "epoch": 0.25, + "learning_rate": 3.765105926041923e-05, + "loss": 0.1942, "step": 111450 }, { - "epoch": 1.0, - "learning_rate": 2.688946941716963e-07, - "loss": 0.1738, + "epoch": 0.25, + "learning_rate": 3.764994071720991e-05, + "loss": 0.1992, "step": 111460 }, { - "epoch": 1.0, - "learning_rate": 2.6439059544185213e-07, - "loss": 0.169, + "epoch": 0.25, + "learning_rate": 3.764882217400058e-05, + "loss": 0.1891, "step": 111470 }, { - "epoch": 1.0, - "learning_rate": 2.5988649671200793e-07, - "loss": 0.172, + "epoch": 0.25, + "learning_rate": 3.764770363079126e-05, + "loss": 0.1976, "step": 111480 }, { - "epoch": 1.0, - "learning_rate": 2.553823979821638e-07, - "loss": 0.177, + "epoch": 0.25, + "learning_rate": 3.764658508758194e-05, + "loss": 0.1946, "step": 111490 }, { - "epoch": 1.0, - "learning_rate": 2.5087829925231963e-07, - "loss": 0.1788, + "epoch": 0.25, + "learning_rate": 3.764546654437261e-05, + "loss": 0.1936, "step": 111500 }, { - "epoch": 1.0, - "learning_rate": 2.4637420052247543e-07, - "loss": 0.1758, + "epoch": 0.25, + "learning_rate": 3.764434800116329e-05, + "loss": 0.1932, "step": 111510 }, { - "epoch": 1.0, - "learning_rate": 2.418701017926313e-07, - "loss": 0.1747, + "epoch": 0.25, + "learning_rate": 3.764322945795396e-05, + "loss": 0.1926, "step": 111520 }, { - "epoch": 1.0, - "learning_rate": 2.3736600306278716e-07, - "loss": 0.1759, + "epoch": 0.25, + "learning_rate": 3.7642110914744636e-05, + "loss": 0.194, "step": 111530 }, { - "epoch": 1.0, - "learning_rate": 2.32861904332943e-07, - "loss": 0.1739, + "epoch": 0.25, + "learning_rate": 3.7640992371535314e-05, + "loss": 0.1933, "step": 111540 }, { - "epoch": 1.0, - "learning_rate": 2.283578056030988e-07, - "loss": 0.174, + "epoch": 0.25, + "learning_rate": 3.763987382832599e-05, + "loss": 0.1919, "step": 111550 }, { - "epoch": 1.0, - "learning_rate": 2.2385370687325468e-07, - "loss": 0.1739, + "epoch": 0.25, + "learning_rate": 3.763875528511667e-05, + "loss": 0.1946, "step": 111560 }, { - "epoch": 1.0, - "learning_rate": 2.1934960814341054e-07, - "loss": 0.1717, + "epoch": 0.25, + "learning_rate": 3.763763674190734e-05, + "loss": 0.1939, "step": 111570 }, { - "epoch": 1.0, - "learning_rate": 2.1484550941356633e-07, - "loss": 0.1775, + "epoch": 0.25, + "learning_rate": 3.763651819869802e-05, + "loss": 0.1954, "step": 111580 }, { - "epoch": 1.0, - "learning_rate": 2.1034141068372218e-07, - "loss": 0.1821, + "epoch": 0.25, + "learning_rate": 3.76353996554887e-05, + "loss": 0.1985, "step": 111590 }, { - "epoch": 1.0, - "learning_rate": 2.0583731195387806e-07, - "loss": 0.1766, + "epoch": 0.25, + "learning_rate": 3.763428111227937e-05, + "loss": 0.1886, "step": 111600 }, { - "epoch": 1.0, - "learning_rate": 2.0133321322403386e-07, - "loss": 0.1834, + "epoch": 0.25, + "learning_rate": 3.7633162569070046e-05, + "loss": 0.1925, "step": 111610 }, { - "epoch": 1.0, - "learning_rate": 1.968291144941897e-07, - "loss": 0.1749, + "epoch": 0.25, + "learning_rate": 3.763204402586072e-05, + "loss": 0.2024, "step": 111620 }, { - "epoch": 1.0, - "learning_rate": 1.9232501576434556e-07, - "loss": 0.1676, + "epoch": 0.25, + "learning_rate": 3.7630925482651395e-05, + "loss": 0.1895, "step": 111630 }, { - "epoch": 1.0, - "learning_rate": 1.8782091703450141e-07, - "loss": 0.1719, + "epoch": 0.25, + "learning_rate": 3.762980693944207e-05, + "loss": 0.2032, "step": 111640 }, { - "epoch": 1.0, - "learning_rate": 1.8331681830465724e-07, - "loss": 0.1681, + "epoch": 0.25, + "learning_rate": 3.7628688396232744e-05, + "loss": 0.1968, "step": 111650 }, { - "epoch": 1.0, - "learning_rate": 1.788127195748131e-07, - "loss": 0.1734, + "epoch": 0.25, + "learning_rate": 3.762756985302342e-05, + "loss": 0.1936, "step": 111660 }, { - "epoch": 1.0, - "learning_rate": 1.7430862084496891e-07, - "loss": 0.1816, + "epoch": 0.25, + "learning_rate": 3.762656316413503e-05, + "loss": 0.1984, "step": 111670 }, { - "epoch": 1.0, - "learning_rate": 1.698045221151248e-07, - "loss": 0.1786, + "epoch": 0.25, + "learning_rate": 3.762544462092571e-05, + "loss": 0.1887, "step": 111680 }, { - "epoch": 1.0, - "learning_rate": 1.6530042338528062e-07, - "loss": 0.1774, + "epoch": 0.25, + "learning_rate": 3.762432607771638e-05, + "loss": 0.1921, "step": 111690 }, { - "epoch": 1.0, - "learning_rate": 1.6079632465543644e-07, - "loss": 0.1697, + "epoch": 0.25, + "learning_rate": 3.762320753450706e-05, + "loss": 0.1932, "step": 111700 }, { - "epoch": 1.0, - "learning_rate": 1.562922259255923e-07, - "loss": 0.1793, + "epoch": 0.25, + "learning_rate": 3.7622088991297736e-05, + "loss": 0.1925, "step": 111710 }, { - "epoch": 1.0, - "learning_rate": 1.5178812719574814e-07, - "loss": 0.1763, + "epoch": 0.25, + "learning_rate": 3.7620970448088414e-05, + "loss": 0.1967, "step": 111720 }, { - "epoch": 1.0, - "learning_rate": 1.47284028465904e-07, - "loss": 0.177, + "epoch": 0.25, + "learning_rate": 3.761985190487909e-05, + "loss": 0.1902, "step": 111730 }, { - "epoch": 1.0, - "learning_rate": 1.4277992973605982e-07, - "loss": 0.1744, + "epoch": 0.25, + "learning_rate": 3.761873336166976e-05, + "loss": 0.1931, "step": 111740 }, { - "epoch": 1.0, - "learning_rate": 1.3827583100621567e-07, - "loss": 0.1711, + "epoch": 0.25, + "learning_rate": 3.761761481846044e-05, + "loss": 0.1961, "step": 111750 }, { - "epoch": 1.0, - "learning_rate": 1.3377173227637152e-07, - "loss": 0.18, + "epoch": 0.25, + "learning_rate": 3.761649627525112e-05, + "loss": 0.1952, "step": 111760 }, { - "epoch": 1.0, - "learning_rate": 1.2926763354652734e-07, - "loss": 0.1758, + "epoch": 0.25, + "learning_rate": 3.761537773204179e-05, + "loss": 0.1952, "step": 111770 }, { - "epoch": 1.0, - "learning_rate": 1.2476353481668317e-07, - "loss": 0.1696, + "epoch": 0.25, + "learning_rate": 3.761425918883247e-05, + "loss": 0.1885, "step": 111780 }, { - "epoch": 1.0, - "learning_rate": 1.2025943608683902e-07, - "loss": 0.1767, + "epoch": 0.25, + "learning_rate": 3.761314064562314e-05, + "loss": 0.1965, "step": 111790 }, { - "epoch": 1.0, - "learning_rate": 1.1575533735699487e-07, - "loss": 0.1738, + "epoch": 0.25, + "learning_rate": 3.761202210241382e-05, + "loss": 0.1919, "step": 111800 }, { - "epoch": 1.0, - "learning_rate": 1.1125123862715072e-07, - "loss": 0.1728, + "epoch": 0.25, + "learning_rate": 3.761090355920449e-05, + "loss": 0.1923, "step": 111810 }, { - "epoch": 1.0, - "learning_rate": 1.0674713989730655e-07, - "loss": 0.1736, + "epoch": 0.25, + "learning_rate": 3.7609785015995166e-05, + "loss": 0.1917, "step": 111820 }, { - "epoch": 1.0, - "learning_rate": 1.0224304116746239e-07, - "loss": 0.1759, + "epoch": 0.25, + "learning_rate": 3.7608666472785844e-05, + "loss": 0.1907, "step": 111830 }, { - "epoch": 1.0, - "learning_rate": 9.773894243761824e-08, - "loss": 0.177, + "epoch": 0.25, + "learning_rate": 3.760754792957652e-05, + "loss": 0.1941, "step": 111840 }, { - "epoch": 1.0, - "learning_rate": 9.323484370777407e-08, - "loss": 0.1823, + "epoch": 0.25, + "learning_rate": 3.76064293863672e-05, + "loss": 0.1909, "step": 111850 }, { - "epoch": 1.0, - "learning_rate": 8.873074497792991e-08, - "loss": 0.1713, + "epoch": 0.25, + "learning_rate": 3.760531084315787e-05, + "loss": 0.1941, "step": 111860 }, { - "epoch": 1.0, - "learning_rate": 8.422664624808576e-08, - "loss": 0.1751, + "epoch": 0.25, + "learning_rate": 3.760419229994855e-05, + "loss": 0.1993, "step": 111870 }, { - "epoch": 1.0, - "learning_rate": 7.97225475182416e-08, - "loss": 0.1753, + "epoch": 0.25, + "learning_rate": 3.760307375673923e-05, + "loss": 0.1922, "step": 111880 }, { - "epoch": 1.0, - "learning_rate": 7.521844878839745e-08, - "loss": 0.1681, + "epoch": 0.25, + "learning_rate": 3.76019552135299e-05, + "loss": 0.1903, "step": 111890 }, { - "epoch": 1.0, - "learning_rate": 7.071435005855329e-08, - "loss": 0.1769, + "epoch": 0.25, + "learning_rate": 3.7600836670320576e-05, + "loss": 0.1956, "step": 111900 }, { - "epoch": 1.0, - "learning_rate": 6.621025132870913e-08, - "loss": 0.1796, + "epoch": 0.25, + "learning_rate": 3.759971812711125e-05, + "loss": 0.194, "step": 111910 }, { - "epoch": 1.0, - "learning_rate": 6.170615259886497e-08, - "loss": 0.1766, + "epoch": 0.25, + "learning_rate": 3.7598599583901925e-05, + "loss": 0.1918, "step": 111920 }, { - "epoch": 1.0, - "learning_rate": 5.7202053869020816e-08, - "loss": 0.1833, + "epoch": 0.25, + "learning_rate": 3.75974810406926e-05, + "loss": 0.1961, "step": 111930 }, { - "epoch": 1.0, - "learning_rate": 5.269795513917665e-08, - "loss": 0.1735, + "epoch": 0.25, + "learning_rate": 3.759636249748328e-05, + "loss": 0.193, "step": 111940 }, { - "epoch": 1.0, - "learning_rate": 4.819385640933249e-08, - "loss": 0.1722, + "epoch": 0.25, + "learning_rate": 3.759524395427396e-05, + "loss": 0.1917, "step": 111950 }, { - "epoch": 1.0, - "learning_rate": 4.3689757679488336e-08, - "loss": 0.1766, + "epoch": 0.25, + "learning_rate": 3.759412541106463e-05, + "loss": 0.1941, "step": 111960 }, { - "epoch": 1.0, - "learning_rate": 3.918565894964418e-08, - "loss": 0.179, + "epoch": 0.25, + "learning_rate": 3.759300686785531e-05, + "loss": 0.1929, "step": 111970 }, { - "epoch": 1.0, - "learning_rate": 3.468156021980002e-08, - "loss": 0.1757, + "epoch": 0.25, + "learning_rate": 3.7591888324645986e-05, + "loss": 0.1922, "step": 111980 }, { - "epoch": 1.0, - "learning_rate": 3.017746148995586e-08, - "loss": 0.1714, + "epoch": 0.25, + "learning_rate": 3.759076978143666e-05, + "loss": 0.1923, "step": 111990 }, { - "epoch": 1.0, - "learning_rate": 2.56733627601117e-08, - "loss": 0.1766, + "epoch": 0.25, + "learning_rate": 3.7589651238227335e-05, + "loss": 0.1931, "step": 112000 }, { - "epoch": 1.0, - "eval_NEIMS_canon_smiles": 0.9432666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.07473333333333333, - "eval_NEIMS_daylight_tanimoto_simil": 0.4783567710399878, - "eval_NEIMS_exact_mols": 0.07451666666666666, - "eval_NEIMS_exact_smiles": 0.0725, - "eval_NEIMS_loss": 0.20215021073818207, - "eval_NEIMS_matched_formulas": 0.6087833333333333, - "eval_NEIMS_morgan_tanimoto_simil": 0.38383660502114564, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0749, - "eval_NEIMS_runtime": 711.5776, - "eval_NEIMS_samples_per_second": 84.32, - "eval_NEIMS_steps_per_second": 1.318, + "epoch": 0.25, + "eval_NEIMS_canon_smiles": 0.9438166666666666, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.07533333333333334, + "eval_NEIMS_daylight_tanimoto_simil": 0.48100685168927676, + "eval_NEIMS_exact_mols": 0.07513333333333333, + "eval_NEIMS_exact_smiles": 0.07303333333333334, + "eval_NEIMS_loss": 0.20116521418094635, + "eval_NEIMS_matched_formulas": 0.59435, + "eval_NEIMS_morgan_tanimoto_simil": 0.3858328604169866, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.0755, + "eval_NEIMS_runtime": 728.0957, + "eval_NEIMS_samples_per_second": 82.407, + "eval_NEIMS_steps_per_second": 1.288, "step": 112000 }, { - "epoch": 1.0, - "eval_RASSP_canon_smiles": 0.9381574114268542, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.17480882893111163, - "eval_RASSP_daylight_tanimoto_simil": 0.6164718810327274, - "eval_RASSP_exact_mols": 0.1740575015861355, - "eval_RASSP_exact_smiles": 0.16873142551841586, - "eval_RASSP_loss": 0.1408979892730713, - "eval_RASSP_matched_formulas": 0.7876414999833038, - "eval_RASSP_morgan_tanimoto_simil": 0.49130529407527207, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.1742411593815741, - "eval_RASSP_runtime": 817.2133, - "eval_RASSP_samples_per_second": 73.291, - "eval_RASSP_steps_per_second": 1.145, + "epoch": 0.25, + "eval_RASSP_canon_smiles": 0.9421310982736167, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.11127992787257489, + "eval_RASSP_daylight_tanimoto_simil": 0.5654091959681335, + "eval_RASSP_exact_mols": 0.1108625237920326, + "eval_RASSP_exact_smiles": 0.10775703743279794, + "eval_RASSP_loss": 0.1681843250989914, + "eval_RASSP_matched_formulas": 0.7465021538050556, + "eval_RASSP_morgan_tanimoto_simil": 0.4299862695660526, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.11102948542424951, + "eval_RASSP_runtime": 826.2602, + "eval_RASSP_samples_per_second": 72.488, + "eval_RASSP_steps_per_second": 1.133, "step": 112000 }, { - "epoch": 1.0, - "eval_NIST_canon_smiles": 0.8848706391737943, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.014870284274408205, - "eval_NIST_daylight_tanimoto_simil": 0.27571158259102035, - "eval_NIST_exact_mols": 0.014124995563757676, - "eval_NIST_exact_smiles": 0.013202257160095113, - "eval_NIST_loss": 1.4582798480987549, - "eval_NIST_matched_formulas": 0.09571636441068956, - "eval_NIST_morgan_tanimoto_simil": 0.22850929188519337, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.014799304397203393, - "eval_NIST_runtime": 457.2134, - "eval_NIST_samples_per_second": 61.628, - "eval_NIST_steps_per_second": 0.965, + "epoch": 0.25, + "eval_NEIMS_old_canon_smiles": 0.9429333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.07166666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.47869746154540566, + "eval_NEIMS_old_exact_mols": 0.0715, + "eval_NEIMS_old_exact_smiles": 0.0697, + "eval_NEIMS_old_loss": 0.20139415562152863, + "eval_NEIMS_old_matched_formulas": 0.5894333333333334, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.38431657996115237, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.0718, + "eval_NEIMS_old_runtime": 367.9435, + "eval_NEIMS_old_samples_per_second": 81.534, + "eval_NEIMS_old_steps_per_second": 1.275, "step": 112000 }, { - "epoch": 0.5, - "learning_rate": 2.512151921438501e-05, - "loss": 0.1783, + "epoch": 0.25, + "eval_RASSP_old_canon_smiles": 0.9385991257049421, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.12497080121466947, + "eval_RASSP_old_daylight_tanimoto_simil": 0.5770304994972082, + "eval_RASSP_old_exact_mols": 0.12463710081089198, + "eval_RASSP_old_exact_smiles": 0.12073280608669537, + "eval_RASSP_old_loss": 0.16078603267669678, + "eval_RASSP_old_matched_formulas": 0.7614042112990956, + "eval_RASSP_old_morgan_tanimoto_simil": 0.4453930988784098, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.12483732105315848, + "eval_RASSP_old_runtime": 411.3735, + "eval_RASSP_old_samples_per_second": 72.846, + "eval_RASSP_old_steps_per_second": 1.14, + "step": 112000 + }, + { + "epoch": 0.25, + "eval_NIST_canon_smiles": 0.8720232813997232, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.017035170529154986, + "eval_NIST_daylight_tanimoto_simil": 0.2772030175426879, + "eval_NIST_exact_mols": 0.016467331511516484, + "eval_NIST_exact_smiles": 0.015686552862263548, + "eval_NIST_loss": 1.8994195461273193, + "eval_NIST_matched_formulas": 0.09507754551584625, + "eval_NIST_morgan_tanimoto_simil": 0.2328965963113517, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.016822230897540546, + "eval_NIST_runtime": 470.4196, + "eval_NIST_samples_per_second": 59.898, + "eval_NIST_steps_per_second": 0.937, + "step": 112000 + }, + { + "epoch": 0.25, + "learning_rate": 3.7588532695018006e-05, + "loss": 0.1936, "step": 112010 }, { - "epoch": 0.5, - "learning_rate": 2.5119277162459082e-05, - "loss": 0.1825, + "epoch": 0.25, + "learning_rate": 3.7587414151808684e-05, + "loss": 0.1918, "step": 112020 }, { - "epoch": 0.5, - "learning_rate": 2.511703511053316e-05, - "loss": 0.1838, + "epoch": 0.25, + "learning_rate": 3.758629560859936e-05, + "loss": 0.1974, "step": 112030 }, { - "epoch": 0.5, - "learning_rate": 2.511479305860724e-05, - "loss": 0.1909, + "epoch": 0.25, + "learning_rate": 3.758517706539004e-05, + "loss": 0.1884, "step": 112040 }, { - "epoch": 0.5, - "learning_rate": 2.5112551006681318e-05, - "loss": 0.1775, + "epoch": 0.25, + "learning_rate": 3.758405852218072e-05, + "loss": 0.1962, "step": 112050 }, { - "epoch": 0.5, - "learning_rate": 2.5110308954755397e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.758293997897139e-05, + "loss": 0.1938, "step": 112060 }, { - "epoch": 0.5, - "learning_rate": 2.510806690282947e-05, - "loss": 0.1879, + "epoch": 0.25, + "learning_rate": 3.758182143576207e-05, + "loss": 0.1977, "step": 112070 }, { - "epoch": 0.5, - "learning_rate": 2.5105824850903547e-05, - "loss": 0.1831, + "epoch": 0.25, + "learning_rate": 3.7580702892552745e-05, + "loss": 0.2029, "step": 112080 }, { - "epoch": 0.5, - "learning_rate": 2.5103582798977626e-05, - "loss": 0.1938, + "epoch": 0.25, + "learning_rate": 3.7579584349343416e-05, + "loss": 0.1878, "step": 112090 }, { - "epoch": 0.5, - "learning_rate": 2.5101340747051705e-05, - "loss": 0.1872, + "epoch": 0.25, + "learning_rate": 3.7578465806134094e-05, + "loss": 0.1907, "step": 112100 }, { - "epoch": 0.5, - "learning_rate": 2.5099098695125777e-05, - "loss": 0.1933, + "epoch": 0.25, + "learning_rate": 3.7577347262924765e-05, + "loss": 0.1951, "step": 112110 }, { - "epoch": 0.5, - "learning_rate": 2.5096856643199855e-05, - "loss": 0.1944, + "epoch": 0.25, + "learning_rate": 3.757622871971544e-05, + "loss": 0.1915, "step": 112120 }, { - "epoch": 0.5, - "learning_rate": 2.5094614591273934e-05, - "loss": 0.1942, + "epoch": 0.25, + "learning_rate": 3.757511017650612e-05, + "loss": 0.1986, "step": 112130 }, { - "epoch": 0.5, - "learning_rate": 2.5092372539348013e-05, - "loss": 0.1931, + "epoch": 0.25, + "learning_rate": 3.75739916332968e-05, + "loss": 0.1953, "step": 112140 }, { - "epoch": 0.5, - "learning_rate": 2.509013048742209e-05, - "loss": 0.1868, + "epoch": 0.25, + "learning_rate": 3.757287309008748e-05, + "loss": 0.1925, "step": 112150 }, { - "epoch": 0.5, - "learning_rate": 2.5087888435496164e-05, - "loss": 0.189, + "epoch": 0.25, + "learning_rate": 3.757175454687815e-05, + "loss": 0.1909, "step": 112160 }, { - "epoch": 0.5, - "learning_rate": 2.5085646383570242e-05, - "loss": 0.1844, + "epoch": 0.25, + "learning_rate": 3.7570636003668826e-05, + "loss": 0.1938, "step": 112170 }, { - "epoch": 0.5, - "learning_rate": 2.508340433164432e-05, - "loss": 0.1913, + "epoch": 0.25, + "learning_rate": 3.75695174604595e-05, + "loss": 0.1903, "step": 112180 }, { - "epoch": 0.5, - "learning_rate": 2.50811622797184e-05, - "loss": 0.1951, + "epoch": 0.25, + "learning_rate": 3.7568398917250175e-05, + "loss": 0.1966, "step": 112190 }, { - "epoch": 0.5, - "learning_rate": 2.507892022779248e-05, - "loss": 0.1938, + "epoch": 0.25, + "learning_rate": 3.756728037404085e-05, + "loss": 0.1988, "step": 112200 }, { - "epoch": 0.5, - "learning_rate": 2.5076678175866554e-05, - "loss": 0.1935, + "epoch": 0.25, + "learning_rate": 3.7566161830831524e-05, + "loss": 0.1924, "step": 112210 }, { - "epoch": 0.5, - "learning_rate": 2.5074436123940632e-05, - "loss": 0.1912, + "epoch": 0.25, + "learning_rate": 3.75650432876222e-05, + "loss": 0.1964, "step": 112220 }, { - "epoch": 0.5, - "learning_rate": 2.507219407201471e-05, - "loss": 0.1888, + "epoch": 0.25, + "learning_rate": 3.756392474441287e-05, + "loss": 0.1919, "step": 112230 }, { - "epoch": 0.5, - "learning_rate": 2.506995202008879e-05, - "loss": 0.1921, + "epoch": 0.25, + "learning_rate": 3.756280620120355e-05, + "loss": 0.1935, "step": 112240 }, { - "epoch": 0.5, - "learning_rate": 2.5067709968162862e-05, - "loss": 0.1907, + "epoch": 0.25, + "learning_rate": 3.756168765799423e-05, + "loss": 0.1954, "step": 112250 }, { - "epoch": 0.5, - "learning_rate": 2.506546791623694e-05, - "loss": 0.1887, + "epoch": 0.25, + "learning_rate": 3.756056911478491e-05, + "loss": 0.1968, "step": 112260 }, { - "epoch": 0.5, - "learning_rate": 2.506322586431102e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.7559450571575585e-05, + "loss": 0.1899, "step": 112270 }, { - "epoch": 0.5, - "learning_rate": 2.5060983812385098e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.7558332028366256e-05, + "loss": 0.1902, "step": 112280 }, { - "epoch": 0.5, - "learning_rate": 2.5058741760459177e-05, - "loss": 0.1907, + "epoch": 0.25, + "learning_rate": 3.7557213485156934e-05, + "loss": 0.1923, "step": 112290 }, { - "epoch": 0.5, - "learning_rate": 2.505649970853325e-05, - "loss": 0.1942, + "epoch": 0.25, + "learning_rate": 3.755609494194761e-05, + "loss": 0.1951, "step": 112300 }, { - "epoch": 0.5, - "learning_rate": 2.5054257656607327e-05, - "loss": 0.1913, + "epoch": 0.25, + "learning_rate": 3.755497639873828e-05, + "loss": 0.1896, "step": 112310 }, { - "epoch": 0.5, - "learning_rate": 2.5052015604681406e-05, - "loss": 0.1896, + "epoch": 0.25, + "learning_rate": 3.755385785552896e-05, + "loss": 0.1891, "step": 112320 }, { - "epoch": 0.5, - "learning_rate": 2.5049773552755485e-05, - "loss": 0.1879, + "epoch": 0.25, + "learning_rate": 3.755273931231963e-05, + "loss": 0.1966, "step": 112330 }, { - "epoch": 0.5, - "learning_rate": 2.5047531500829564e-05, - "loss": 0.1908, + "epoch": 0.25, + "learning_rate": 3.755162076911031e-05, + "loss": 0.1931, "step": 112340 }, { - "epoch": 0.5, - "learning_rate": 2.5045289448903635e-05, - "loss": 0.1867, + "epoch": 0.25, + "learning_rate": 3.755050222590099e-05, + "loss": 0.1919, "step": 112350 }, { - "epoch": 0.5, - "learning_rate": 2.5043047396977714e-05, - "loss": 0.1942, + "epoch": 0.25, + "learning_rate": 3.7549383682691666e-05, + "loss": 0.1943, "step": 112360 }, { - "epoch": 0.5, - "learning_rate": 2.5040805345051793e-05, - "loss": 0.1898, + "epoch": 0.25, + "learning_rate": 3.7548265139482344e-05, + "loss": 0.1963, "step": 112370 }, { - "epoch": 0.5, - "learning_rate": 2.503856329312587e-05, - "loss": 0.1938, + "epoch": 0.25, + "learning_rate": 3.7547146596273015e-05, + "loss": 0.1878, "step": 112380 }, { - "epoch": 0.5, - "learning_rate": 2.5036321241199944e-05, - "loss": 0.1878, + "epoch": 0.25, + "learning_rate": 3.754602805306369e-05, + "loss": 0.1887, "step": 112390 }, { - "epoch": 0.5, - "learning_rate": 2.5034079189274022e-05, - "loss": 0.1905, + "epoch": 0.25, + "learning_rate": 3.754490950985437e-05, + "loss": 0.189, "step": 112400 }, { - "epoch": 0.5, - "learning_rate": 2.50318371373481e-05, - "loss": 0.1902, + "epoch": 0.25, + "learning_rate": 3.754379096664504e-05, + "loss": 0.1946, "step": 112410 }, { - "epoch": 0.5, - "learning_rate": 2.502959508542218e-05, - "loss": 0.1877, + "epoch": 0.25, + "learning_rate": 3.754267242343572e-05, + "loss": 0.1968, "step": 112420 }, { - "epoch": 0.5, - "learning_rate": 2.502735303349626e-05, - "loss": 0.1965, + "epoch": 0.25, + "learning_rate": 3.754155388022639e-05, + "loss": 0.1944, "step": 112430 }, { - "epoch": 0.5, - "learning_rate": 2.5025110981570334e-05, - "loss": 0.1977, + "epoch": 0.25, + "learning_rate": 3.754043533701707e-05, + "loss": 0.1923, "step": 112440 }, { - "epoch": 0.5, - "learning_rate": 2.502286892964441e-05, - "loss": 0.1858, + "epoch": 0.25, + "learning_rate": 3.753931679380775e-05, + "loss": 0.1915, "step": 112450 }, { - "epoch": 0.5, - "learning_rate": 2.5020626877718488e-05, - "loss": 0.1936, + "epoch": 0.25, + "learning_rate": 3.7538198250598425e-05, + "loss": 0.1927, "step": 112460 }, { - "epoch": 0.5, - "learning_rate": 2.5018384825792567e-05, - "loss": 0.186, + "epoch": 0.25, + "learning_rate": 3.75370797073891e-05, + "loss": 0.194, "step": 112470 }, { - "epoch": 0.5, - "learning_rate": 2.5016142773866645e-05, - "loss": 0.1916, + "epoch": 0.25, + "learning_rate": 3.7535961164179774e-05, + "loss": 0.1831, "step": 112480 }, { - "epoch": 0.5, - "learning_rate": 2.501390072194072e-05, - "loss": 0.191, + "epoch": 0.25, + "learning_rate": 3.753484262097045e-05, + "loss": 0.194, "step": 112490 }, { - "epoch": 0.5, - "learning_rate": 2.50116586700148e-05, - "loss": 0.1903, + "epoch": 0.25, + "learning_rate": 3.753372407776112e-05, + "loss": 0.1975, "step": 112500 }, { - "epoch": 0.5, - "learning_rate": 2.5009416618088878e-05, - "loss": 0.1965, + "epoch": 0.25, + "learning_rate": 3.75326055345518e-05, + "loss": 0.1921, "step": 112510 }, { - "epoch": 0.5, - "learning_rate": 2.5007174566162957e-05, - "loss": 0.1918, + "epoch": 0.25, + "learning_rate": 3.753148699134248e-05, + "loss": 0.1917, "step": 112520 }, { - "epoch": 0.5, - "learning_rate": 2.500493251423703e-05, + "epoch": 0.25, + "learning_rate": 3.753036844813315e-05, "loss": 0.1967, "step": 112530 }, { - "epoch": 0.5, - "learning_rate": 2.5002690462311107e-05, - "loss": 0.1908, + "epoch": 0.25, + "learning_rate": 3.752924990492383e-05, + "loss": 0.1947, "step": 112540 }, { - "epoch": 0.5, - "learning_rate": 2.5000448410385186e-05, - "loss": 0.1914, + "epoch": 0.25, + "learning_rate": 3.7528131361714506e-05, + "loss": 0.1883, "step": 112550 }, { - "epoch": 0.5, - "learning_rate": 2.4998206358459265e-05, - "loss": 0.1947, + "epoch": 0.25, + "learning_rate": 3.7527012818505184e-05, + "loss": 0.1943, "step": 112560 }, { - "epoch": 0.5, - "learning_rate": 2.499596430653334e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.752589427529586e-05, + "loss": 0.1916, "step": 112570 }, { - "epoch": 0.5, - "learning_rate": 2.499372225460742e-05, - "loss": 0.1873, + "epoch": 0.25, + "learning_rate": 3.752477573208653e-05, + "loss": 0.1934, "step": 112580 }, { - "epoch": 0.5, - "learning_rate": 2.4991480202681494e-05, - "loss": 0.1933, + "epoch": 0.25, + "learning_rate": 3.752365718887721e-05, + "loss": 0.1885, "step": 112590 }, { - "epoch": 0.5, - "learning_rate": 2.4989238150755573e-05, - "loss": 0.1879, + "epoch": 0.25, + "learning_rate": 3.752253864566788e-05, + "loss": 0.1909, "step": 112600 }, { - "epoch": 0.5, - "learning_rate": 2.498699609882965e-05, - "loss": 0.1928, + "epoch": 0.25, + "learning_rate": 3.752142010245856e-05, + "loss": 0.1962, "step": 112610 }, { - "epoch": 0.5, - "learning_rate": 2.4984754046903727e-05, - "loss": 0.1926, + "epoch": 0.25, + "learning_rate": 3.752030155924924e-05, + "loss": 0.1911, "step": 112620 }, { - "epoch": 0.5, - "learning_rate": 2.4982511994977806e-05, - "loss": 0.1954, + "epoch": 0.25, + "learning_rate": 3.751918301603991e-05, + "loss": 0.2, "step": 112630 }, { - "epoch": 0.5, - "learning_rate": 2.498026994305188e-05, - "loss": 0.1932, + "epoch": 0.25, + "learning_rate": 3.751806447283059e-05, + "loss": 0.1887, "step": 112640 }, { - "epoch": 0.5, - "learning_rate": 2.497802789112596e-05, - "loss": 0.1852, + "epoch": 0.25, + "learning_rate": 3.751694592962126e-05, + "loss": 0.1893, "step": 112650 }, { - "epoch": 0.5, - "learning_rate": 2.4975785839200035e-05, - "loss": 0.1891, + "epoch": 0.25, + "learning_rate": 3.7515827386411936e-05, + "loss": 0.1942, "step": 112660 }, { - "epoch": 0.5, - "learning_rate": 2.4973543787274114e-05, - "loss": 0.1865, + "epoch": 0.25, + "learning_rate": 3.751470884320262e-05, + "loss": 0.1936, "step": 112670 }, { - "epoch": 0.5, - "learning_rate": 2.4971301735348193e-05, - "loss": 0.1922, + "epoch": 0.25, + "learning_rate": 3.751359029999329e-05, + "loss": 0.197, "step": 112680 }, { - "epoch": 0.5, - "learning_rate": 2.4969059683422268e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.751247175678397e-05, + "loss": 0.1902, "step": 112690 }, { - "epoch": 0.5, - "learning_rate": 2.4966817631496347e-05, - "loss": 0.1909, + "epoch": 0.25, + "learning_rate": 3.751135321357464e-05, + "loss": 0.1946, "step": 112700 }, { - "epoch": 0.5, - "learning_rate": 2.4964575579570422e-05, - "loss": 0.1895, + "epoch": 0.25, + "learning_rate": 3.751023467036532e-05, + "loss": 0.1971, "step": 112710 }, { - "epoch": 0.5, - "learning_rate": 2.49623335276445e-05, - "loss": 0.195, + "epoch": 0.25, + "learning_rate": 3.7509116127156e-05, + "loss": 0.1899, "step": 112720 }, { - "epoch": 0.5, - "learning_rate": 2.496009147571858e-05, - "loss": 0.1904, + "epoch": 0.25, + "learning_rate": 3.750799758394667e-05, + "loss": 0.1879, "step": 112730 }, { - "epoch": 0.5, - "learning_rate": 2.4957849423792655e-05, - "loss": 0.1898, + "epoch": 0.25, + "learning_rate": 3.7506879040737346e-05, + "loss": 0.189, "step": 112740 }, { - "epoch": 0.5, - "learning_rate": 2.4955607371866733e-05, - "loss": 0.1909, + "epoch": 0.25, + "learning_rate": 3.750576049752802e-05, + "loss": 0.1905, "step": 112750 }, { - "epoch": 0.5, - "learning_rate": 2.4953365319940812e-05, - "loss": 0.1872, + "epoch": 0.25, + "learning_rate": 3.7504641954318695e-05, + "loss": 0.1917, "step": 112760 }, { - "epoch": 0.5, - "learning_rate": 2.495112326801489e-05, - "loss": 0.1877, + "epoch": 0.25, + "learning_rate": 3.750352341110937e-05, + "loss": 0.19, "step": 112770 }, { - "epoch": 0.5, - "learning_rate": 2.4948881216088966e-05, - "loss": 0.1908, + "epoch": 0.25, + "learning_rate": 3.750240486790005e-05, + "loss": 0.1926, "step": 112780 }, { - "epoch": 0.5, - "learning_rate": 2.4946639164163045e-05, - "loss": 0.1866, + "epoch": 0.25, + "learning_rate": 3.750128632469073e-05, + "loss": 0.1991, "step": 112790 }, { - "epoch": 0.5, - "learning_rate": 2.494439711223712e-05, - "loss": 0.1918, + "epoch": 0.25, + "learning_rate": 3.75001677814814e-05, + "loss": 0.1923, "step": 112800 }, { - "epoch": 0.5, - "learning_rate": 2.49421550603112e-05, - "loss": 0.1908, + "epoch": 0.25, + "learning_rate": 3.749904923827208e-05, + "loss": 0.1928, "step": 112810 }, { - "epoch": 0.5, - "learning_rate": 2.4939913008385278e-05, - "loss": 0.1844, + "epoch": 0.25, + "learning_rate": 3.749793069506275e-05, + "loss": 0.1905, "step": 112820 }, { - "epoch": 0.5, - "learning_rate": 2.4937670956459353e-05, - "loss": 0.1958, + "epoch": 0.25, + "learning_rate": 3.749681215185343e-05, + "loss": 0.187, "step": 112830 }, { - "epoch": 0.5, - "learning_rate": 2.493542890453343e-05, - "loss": 0.191, + "epoch": 0.25, + "learning_rate": 3.7495693608644105e-05, + "loss": 0.1904, "step": 112840 }, { - "epoch": 0.5, - "learning_rate": 2.4933186852607507e-05, - "loss": 0.1894, + "epoch": 0.25, + "learning_rate": 3.7494575065434776e-05, + "loss": 0.1932, "step": 112850 }, { - "epoch": 0.5, - "learning_rate": 2.4930944800681586e-05, - "loss": 0.1896, + "epoch": 0.25, + "learning_rate": 3.7493456522225454e-05, + "loss": 0.195, "step": 112860 }, { - "epoch": 0.5, - "learning_rate": 2.492870274875566e-05, - "loss": 0.19, + "epoch": 0.25, + "learning_rate": 3.749233797901613e-05, + "loss": 0.1946, "step": 112870 }, { - "epoch": 0.5, - "learning_rate": 2.492646069682974e-05, - "loss": 0.1892, + "epoch": 0.25, + "learning_rate": 3.749121943580681e-05, + "loss": 0.1977, "step": 112880 }, { - "epoch": 0.5, - "learning_rate": 2.492421864490382e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.749010089259749e-05, + "loss": 0.1934, "step": 112890 }, { - "epoch": 0.5, - "learning_rate": 2.4921976592977894e-05, - "loss": 0.1897, + "epoch": 0.25, + "learning_rate": 3.748898234938816e-05, + "loss": 0.1947, "step": 112900 }, { - "epoch": 0.5, - "learning_rate": 2.4919734541051973e-05, - "loss": 0.1871, + "epoch": 0.25, + "learning_rate": 3.748786380617884e-05, + "loss": 0.1952, "step": 112910 }, { - "epoch": 0.5, - "learning_rate": 2.4917492489126048e-05, - "loss": 0.1886, + "epoch": 0.25, + "learning_rate": 3.748674526296951e-05, + "loss": 0.1925, "step": 112920 }, { - "epoch": 0.5, - "learning_rate": 2.4915250437200127e-05, - "loss": 0.1909, + "epoch": 0.25, + "learning_rate": 3.7485626719760186e-05, + "loss": 0.1936, "step": 112930 }, { - "epoch": 0.5, - "learning_rate": 2.4913008385274202e-05, - "loss": 0.19, + "epoch": 0.25, + "learning_rate": 3.7484508176550864e-05, + "loss": 0.1957, "step": 112940 }, { - "epoch": 0.5, - "learning_rate": 2.491076633334828e-05, - "loss": 0.1938, + "epoch": 0.25, + "learning_rate": 3.7483389633341535e-05, + "loss": 0.1915, "step": 112950 }, { - "epoch": 0.5, - "learning_rate": 2.490852428142236e-05, - "loss": 0.1914, + "epoch": 0.25, + "learning_rate": 3.748227109013221e-05, + "loss": 0.1917, "step": 112960 }, { - "epoch": 0.5, - "learning_rate": 2.4906282229496435e-05, - "loss": 0.186, + "epoch": 0.25, + "learning_rate": 3.748115254692289e-05, + "loss": 0.1851, "step": 112970 }, { - "epoch": 0.5, - "learning_rate": 2.4904040177570513e-05, - "loss": 0.1844, + "epoch": 0.25, + "learning_rate": 3.748003400371357e-05, + "loss": 0.1976, "step": 112980 }, { - "epoch": 0.5, - "learning_rate": 2.490179812564459e-05, - "loss": 0.1922, + "epoch": 0.25, + "learning_rate": 3.7478915460504247e-05, + "loss": 0.1905, "step": 112990 }, { - "epoch": 0.5, - "learning_rate": 2.4899556073718667e-05, - "loss": 0.193, + "epoch": 0.25, + "learning_rate": 3.747779691729492e-05, + "loss": 0.1926, "step": 113000 }, { - "epoch": 0.5, - "learning_rate": 2.4897314021792746e-05, - "loss": 0.192, + "epoch": 0.25, + "learning_rate": 3.7476678374085596e-05, + "loss": 0.1956, "step": 113010 }, { - "epoch": 0.5, - "learning_rate": 2.4895071969866825e-05, - "loss": 0.1938, + "epoch": 0.25, + "learning_rate": 3.747555983087627e-05, + "loss": 0.1926, "step": 113020 }, { - "epoch": 0.5, - "learning_rate": 2.4892829917940904e-05, - "loss": 0.1918, + "epoch": 0.25, + "learning_rate": 3.7474441287666945e-05, + "loss": 0.1939, "step": 113030 }, { - "epoch": 0.5, - "learning_rate": 2.489058786601498e-05, - "loss": 0.1888, + "epoch": 0.25, + "learning_rate": 3.747332274445762e-05, + "loss": 0.198, "step": 113040 }, { - "epoch": 0.5, - "learning_rate": 2.4888345814089058e-05, - "loss": 0.1916, + "epoch": 0.25, + "learning_rate": 3.7472204201248294e-05, + "loss": 0.1931, "step": 113050 }, { - "epoch": 0.5, - "learning_rate": 2.4886103762163133e-05, - "loss": 0.1862, + "epoch": 0.25, + "learning_rate": 3.747108565803897e-05, + "loss": 0.1937, "step": 113060 }, { - "epoch": 0.5, - "learning_rate": 2.488386171023721e-05, - "loss": 0.1894, + "epoch": 0.25, + "learning_rate": 3.746996711482964e-05, + "loss": 0.1951, "step": 113070 }, { - "epoch": 0.5, - "learning_rate": 2.4881619658311287e-05, - "loss": 0.1868, + "epoch": 0.25, + "learning_rate": 3.746884857162032e-05, + "loss": 0.192, "step": 113080 }, { - "epoch": 0.5, - "learning_rate": 2.4879377606385366e-05, - "loss": 0.1855, + "epoch": 0.25, + "learning_rate": 3.7467730028411e-05, + "loss": 0.1879, "step": 113090 }, { - "epoch": 0.5, - "learning_rate": 2.4877135554459444e-05, - "loss": 0.185, + "epoch": 0.25, + "learning_rate": 3.746661148520168e-05, + "loss": 0.1929, "step": 113100 }, { - "epoch": 0.5, - "learning_rate": 2.487489350253352e-05, - "loss": 0.1881, + "epoch": 0.25, + "learning_rate": 3.7465492941992355e-05, + "loss": 0.1899, "step": 113110 }, { - "epoch": 0.5, - "learning_rate": 2.48726514506076e-05, - "loss": 0.1874, + "epoch": 0.25, + "learning_rate": 3.7464374398783026e-05, + "loss": 0.1961, "step": 113120 }, { - "epoch": 0.51, - "learning_rate": 2.4870409398681674e-05, - "loss": 0.1918, + "epoch": 0.25, + "learning_rate": 3.7463255855573704e-05, + "loss": 0.193, "step": 113130 }, { - "epoch": 0.51, - "learning_rate": 2.4868167346755753e-05, - "loss": 0.1848, + "epoch": 0.25, + "learning_rate": 3.7462137312364375e-05, + "loss": 0.1962, "step": 113140 }, { - "epoch": 0.51, - "learning_rate": 2.4865925294829828e-05, - "loss": 0.1896, + "epoch": 0.25, + "learning_rate": 3.746101876915505e-05, + "loss": 0.1957, "step": 113150 }, { - "epoch": 0.51, - "learning_rate": 2.4863683242903907e-05, - "loss": 0.1881, + "epoch": 0.25, + "learning_rate": 3.745990022594573e-05, + "loss": 0.1942, "step": 113160 }, { - "epoch": 0.51, - "learning_rate": 2.4861441190977985e-05, - "loss": 0.1885, + "epoch": 0.25, + "learning_rate": 3.74587816827364e-05, + "loss": 0.1905, "step": 113170 }, { - "epoch": 0.51, - "learning_rate": 2.485919913905206e-05, - "loss": 0.1866, + "epoch": 0.25, + "learning_rate": 3.745766313952708e-05, + "loss": 0.1915, "step": 113180 }, { - "epoch": 0.51, - "learning_rate": 2.485695708712614e-05, - "loss": 0.1845, + "epoch": 0.25, + "learning_rate": 3.745654459631776e-05, + "loss": 0.1908, "step": 113190 }, { - "epoch": 0.51, - "learning_rate": 2.4854715035200215e-05, - "loss": 0.1839, + "epoch": 0.25, + "learning_rate": 3.7455426053108436e-05, + "loss": 0.1946, "step": 113200 }, { - "epoch": 0.51, - "learning_rate": 2.4852472983274293e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.7454307509899113e-05, + "loss": 0.1886, "step": 113210 }, { - "epoch": 0.51, - "learning_rate": 2.485023093134837e-05, - "loss": 0.1932, + "epoch": 0.25, + "learning_rate": 3.7453188966689785e-05, + "loss": 0.1921, "step": 113220 }, { - "epoch": 0.51, - "learning_rate": 2.4847988879422447e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.745207042348046e-05, + "loss": 0.1906, "step": 113230 }, { - "epoch": 0.51, - "learning_rate": 2.4845746827496526e-05, - "loss": 0.1816, + "epoch": 0.25, + "learning_rate": 3.7450951880271134e-05, + "loss": 0.1946, "step": 113240 }, { - "epoch": 0.51, - "learning_rate": 2.48435047755706e-05, - "loss": 0.1942, + "epoch": 0.25, + "learning_rate": 3.744983333706181e-05, + "loss": 0.1903, "step": 113250 }, { - "epoch": 0.51, - "learning_rate": 2.484126272364468e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.744871479385249e-05, + "loss": 0.1904, "step": 113260 }, { - "epoch": 0.51, - "learning_rate": 2.483902067171876e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.744759625064316e-05, + "loss": 0.1945, "step": 113270 }, { - "epoch": 0.51, - "learning_rate": 2.4836778619792834e-05, - "loss": 0.1842, + "epoch": 0.25, + "learning_rate": 3.744647770743384e-05, + "loss": 0.1994, "step": 113280 }, { - "epoch": 0.51, - "learning_rate": 2.4834536567866913e-05, - "loss": 0.1922, + "epoch": 0.25, + "learning_rate": 3.7445359164224517e-05, + "loss": 0.1882, "step": 113290 }, { - "epoch": 0.51, - "learning_rate": 2.4832294515940992e-05, - "loss": 0.1902, + "epoch": 0.25, + "learning_rate": 3.7444240621015195e-05, + "loss": 0.193, "step": 113300 }, { - "epoch": 0.51, - "learning_rate": 2.483005246401507e-05, - "loss": 0.1886, + "epoch": 0.25, + "learning_rate": 3.744312207780587e-05, + "loss": 0.1936, "step": 113310 }, { - "epoch": 0.51, - "learning_rate": 2.4827810412089146e-05, - "loss": 0.1854, + "epoch": 0.25, + "learning_rate": 3.7442003534596544e-05, + "loss": 0.1913, "step": 113320 }, { - "epoch": 0.51, - "learning_rate": 2.4825568360163224e-05, - "loss": 0.1813, + "epoch": 0.25, + "learning_rate": 3.744088499138722e-05, + "loss": 0.1948, "step": 113330 }, { - "epoch": 0.51, - "learning_rate": 2.48233263082373e-05, - "loss": 0.1875, + "epoch": 0.25, + "learning_rate": 3.743976644817789e-05, + "loss": 0.1881, "step": 113340 }, { - "epoch": 0.51, - "learning_rate": 2.482108425631138e-05, - "loss": 0.1926, + "epoch": 0.25, + "learning_rate": 3.743864790496857e-05, + "loss": 0.1871, "step": 113350 }, { - "epoch": 0.51, - "learning_rate": 2.4818842204385454e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.743752936175925e-05, + "loss": 0.1975, "step": 113360 }, { - "epoch": 0.51, - "learning_rate": 2.4816600152459533e-05, - "loss": 0.1868, + "epoch": 0.25, + "learning_rate": 3.743641081854992e-05, + "loss": 0.1929, "step": 113370 }, { - "epoch": 0.51, - "learning_rate": 2.481435810053361e-05, - "loss": 0.1827, + "epoch": 0.25, + "learning_rate": 3.74352922753406e-05, + "loss": 0.1824, "step": 113380 }, { - "epoch": 0.51, - "learning_rate": 2.4812116048607687e-05, - "loss": 0.1909, + "epoch": 0.25, + "learning_rate": 3.7434173732131276e-05, + "loss": 0.1934, "step": 113390 }, { - "epoch": 0.51, - "learning_rate": 2.4809873996681765e-05, - "loss": 0.1865, + "epoch": 0.25, + "learning_rate": 3.7433055188921953e-05, + "loss": 0.1936, "step": 113400 }, { - "epoch": 0.51, - "learning_rate": 2.480763194475584e-05, - "loss": 0.1846, + "epoch": 0.25, + "learning_rate": 3.7431936645712625e-05, + "loss": 0.1916, "step": 113410 }, { - "epoch": 0.51, - "learning_rate": 2.480538989282992e-05, - "loss": 0.1866, + "epoch": 0.25, + "learning_rate": 3.74308181025033e-05, + "loss": 0.1934, "step": 113420 }, { - "epoch": 0.51, - "learning_rate": 2.4803147840903995e-05, - "loss": 0.1907, + "epoch": 0.25, + "learning_rate": 3.742969955929398e-05, + "loss": 0.189, "step": 113430 }, { - "epoch": 0.51, - "learning_rate": 2.4800905788978073e-05, - "loss": 0.1863, + "epoch": 0.25, + "learning_rate": 3.742858101608465e-05, + "loss": 0.1963, "step": 113440 }, { - "epoch": 0.51, - "learning_rate": 2.4798663737052152e-05, - "loss": 0.1914, + "epoch": 0.25, + "learning_rate": 3.742746247287533e-05, + "loss": 0.1915, "step": 113450 }, { - "epoch": 0.51, - "learning_rate": 2.4796421685126227e-05, - "loss": 0.1873, + "epoch": 0.25, + "learning_rate": 3.7426343929666e-05, + "loss": 0.1963, "step": 113460 }, { - "epoch": 0.51, - "learning_rate": 2.4794179633200306e-05, - "loss": 0.189, + "epoch": 0.25, + "learning_rate": 3.742522538645668e-05, + "loss": 0.1934, "step": 113470 }, { - "epoch": 0.51, - "learning_rate": 2.479193758127438e-05, - "loss": 0.1872, + "epoch": 0.25, + "learning_rate": 3.7424106843247357e-05, + "loss": 0.1883, "step": 113480 }, { - "epoch": 0.51, - "learning_rate": 2.478969552934846e-05, - "loss": 0.1899, + "epoch": 0.25, + "learning_rate": 3.742298830003803e-05, + "loss": 0.1966, "step": 113490 }, { - "epoch": 0.51, - "learning_rate": 2.4787453477422536e-05, - "loss": 0.1848, + "epoch": 0.25, + "learning_rate": 3.742186975682871e-05, + "loss": 0.187, "step": 113500 }, { - "epoch": 0.51, - "learning_rate": 2.4785211425496614e-05, - "loss": 0.1846, + "epoch": 0.25, + "learning_rate": 3.7420751213619384e-05, + "loss": 0.1886, "step": 113510 }, { - "epoch": 0.51, - "learning_rate": 2.4782969373570693e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.741963267041006e-05, + "loss": 0.1912, "step": 113520 }, { - "epoch": 0.51, - "learning_rate": 2.478072732164477e-05, - "loss": 0.193, + "epoch": 0.25, + "learning_rate": 3.741851412720074e-05, + "loss": 0.1939, "step": 113530 }, { - "epoch": 0.51, - "learning_rate": 2.4778485269718847e-05, - "loss": 0.1886, + "epoch": 0.25, + "learning_rate": 3.741739558399141e-05, + "loss": 0.1903, "step": 113540 }, { - "epoch": 0.51, - "learning_rate": 2.4776243217792926e-05, - "loss": 0.1943, + "epoch": 0.25, + "learning_rate": 3.741627704078209e-05, + "loss": 0.1957, "step": 113550 }, { - "epoch": 0.51, - "learning_rate": 2.4774001165867004e-05, - "loss": 0.19, + "epoch": 0.25, + "learning_rate": 3.741515849757276e-05, + "loss": 0.1884, "step": 113560 }, { - "epoch": 0.51, - "learning_rate": 2.477175911394108e-05, - "loss": 0.1921, + "epoch": 0.25, + "learning_rate": 3.741403995436344e-05, + "loss": 0.192, "step": 113570 }, { - "epoch": 0.51, - "learning_rate": 2.476951706201516e-05, - "loss": 0.1901, + "epoch": 0.25, + "learning_rate": 3.7412921411154115e-05, + "loss": 0.188, "step": 113580 }, { - "epoch": 0.51, - "learning_rate": 2.4767275010089237e-05, - "loss": 0.1941, + "epoch": 0.25, + "learning_rate": 3.741180286794479e-05, + "loss": 0.1913, "step": 113590 }, { - "epoch": 0.51, - "learning_rate": 2.4765032958163313e-05, - "loss": 0.1859, + "epoch": 0.25, + "learning_rate": 3.7410684324735465e-05, + "loss": 0.1944, "step": 113600 }, { - "epoch": 0.51, - "learning_rate": 2.476279090623739e-05, - "loss": 0.1876, + "epoch": 0.25, + "learning_rate": 3.740956578152614e-05, + "loss": 0.1879, "step": 113610 }, { - "epoch": 0.51, - "learning_rate": 2.4760548854311467e-05, - "loss": 0.1896, + "epoch": 0.25, + "learning_rate": 3.740844723831682e-05, + "loss": 0.1905, "step": 113620 }, { - "epoch": 0.51, - "learning_rate": 2.4758306802385545e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.74073286951075e-05, + "loss": 0.1915, "step": 113630 }, { - "epoch": 0.51, - "learning_rate": 2.475606475045962e-05, - "loss": 0.1858, + "epoch": 0.25, + "learning_rate": 3.740621015189817e-05, + "loss": 0.1845, "step": 113640 }, { - "epoch": 0.51, - "learning_rate": 2.47538226985337e-05, - "loss": 0.186, + "epoch": 0.25, + "learning_rate": 3.740509160868885e-05, + "loss": 0.1923, "step": 113650 }, { - "epoch": 0.51, - "learning_rate": 2.4751580646607778e-05, - "loss": 0.1876, + "epoch": 0.25, + "learning_rate": 3.740397306547952e-05, + "loss": 0.1917, "step": 113660 }, { - "epoch": 0.51, - "learning_rate": 2.4749338594681853e-05, - "loss": 0.1889, + "epoch": 0.25, + "learning_rate": 3.7402854522270197e-05, + "loss": 0.1885, "step": 113670 }, { - "epoch": 0.51, - "learning_rate": 2.4747096542755932e-05, - "loss": 0.1932, + "epoch": 0.25, + "learning_rate": 3.7401847833381805e-05, + "loss": 0.1915, "step": 113680 }, { - "epoch": 0.51, - "learning_rate": 2.4744854490830007e-05, - "loss": 0.1837, + "epoch": 0.25, + "learning_rate": 3.740072929017248e-05, + "loss": 0.1974, "step": 113690 }, { - "epoch": 0.51, - "learning_rate": 2.4742612438904086e-05, - "loss": 0.1836, + "epoch": 0.25, + "learning_rate": 3.739961074696316e-05, + "loss": 0.1911, "step": 113700 }, { - "epoch": 0.51, - "learning_rate": 2.474037038697816e-05, - "loss": 0.1916, + "epoch": 0.25, + "learning_rate": 3.739849220375383e-05, + "loss": 0.1965, "step": 113710 }, { - "epoch": 0.51, - "learning_rate": 2.473812833505224e-05, - "loss": 0.1857, + "epoch": 0.25, + "learning_rate": 3.739737366054451e-05, + "loss": 0.1988, "step": 113720 }, { - "epoch": 0.51, - "learning_rate": 2.473588628312632e-05, - "loss": 0.1857, + "epoch": 0.25, + "learning_rate": 3.739625511733518e-05, + "loss": 0.1909, "step": 113730 }, { - "epoch": 0.51, - "learning_rate": 2.4733644231200394e-05, - "loss": 0.1867, + "epoch": 0.25, + "learning_rate": 3.739513657412586e-05, + "loss": 0.1912, "step": 113740 }, { - "epoch": 0.51, - "learning_rate": 2.4731402179274473e-05, - "loss": 0.1855, + "epoch": 0.25, + "learning_rate": 3.739401803091653e-05, + "loss": 0.1877, "step": 113750 }, { - "epoch": 0.51, - "learning_rate": 2.472916012734855e-05, - "loss": 0.1839, + "epoch": 0.25, + "learning_rate": 3.739289948770721e-05, + "loss": 0.1936, "step": 113760 }, { - "epoch": 0.51, - "learning_rate": 2.4726918075422627e-05, - "loss": 0.1915, + "epoch": 0.25, + "learning_rate": 3.7391780944497886e-05, + "loss": 0.1942, "step": 113770 }, { - "epoch": 0.51, - "learning_rate": 2.4724676023496706e-05, - "loss": 0.1896, + "epoch": 0.25, + "learning_rate": 3.7390662401288564e-05, + "loss": 0.19, "step": 113780 }, { - "epoch": 0.51, - "learning_rate": 2.472243397157078e-05, - "loss": 0.1888, + "epoch": 0.25, + "learning_rate": 3.738954385807924e-05, + "loss": 0.1882, "step": 113790 }, { - "epoch": 0.51, - "learning_rate": 2.472019191964486e-05, - "loss": 0.1903, + "epoch": 0.25, + "learning_rate": 3.738842531486991e-05, + "loss": 0.1859, "step": 113800 }, { - "epoch": 0.51, - "learning_rate": 2.471794986771894e-05, + "epoch": 0.25, + "learning_rate": 3.738730677166059e-05, "loss": 0.1893, "step": 113810 }, { - "epoch": 0.51, - "learning_rate": 2.4715707815793014e-05, - "loss": 0.1819, + "epoch": 0.25, + "learning_rate": 3.738618822845127e-05, + "loss": 0.1885, "step": 113820 }, { - "epoch": 0.51, - "learning_rate": 2.4713465763867093e-05, - "loss": 0.1854, + "epoch": 0.25, + "learning_rate": 3.738506968524194e-05, + "loss": 0.1969, "step": 113830 }, { - "epoch": 0.51, - "learning_rate": 2.471122371194117e-05, - "loss": 0.1869, + "epoch": 0.25, + "learning_rate": 3.738395114203262e-05, + "loss": 0.1906, "step": 113840 }, { - "epoch": 0.51, - "learning_rate": 2.470898166001525e-05, - "loss": 0.1886, + "epoch": 0.25, + "learning_rate": 3.738283259882329e-05, + "loss": 0.1906, "step": 113850 }, { - "epoch": 0.51, - "learning_rate": 2.4706739608089325e-05, - "loss": 0.1916, + "epoch": 0.25, + "learning_rate": 3.738171405561397e-05, + "loss": 0.1905, "step": 113860 }, { - "epoch": 0.51, - "learning_rate": 2.4704497556163404e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.7380595512404645e-05, + "loss": 0.1916, "step": 113870 }, { - "epoch": 0.51, - "learning_rate": 2.470225550423748e-05, - "loss": 0.1873, + "epoch": 0.25, + "learning_rate": 3.737947696919532e-05, + "loss": 0.1883, "step": 113880 }, { - "epoch": 0.51, - "learning_rate": 2.4700013452311558e-05, - "loss": 0.1855, + "epoch": 0.25, + "learning_rate": 3.7378358425986e-05, + "loss": 0.1886, "step": 113890 }, { - "epoch": 0.51, - "learning_rate": 2.4697771400385633e-05, - "loss": 0.1832, + "epoch": 0.25, + "learning_rate": 3.737723988277667e-05, + "loss": 0.1926, "step": 113900 }, { - "epoch": 0.51, - "learning_rate": 2.4695529348459712e-05, - "loss": 0.1856, + "epoch": 0.25, + "learning_rate": 3.737612133956735e-05, + "loss": 0.1931, "step": 113910 }, { - "epoch": 0.51, - "learning_rate": 2.469328729653379e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.737500279635803e-05, + "loss": 0.1906, "step": 113920 }, { - "epoch": 0.51, - "learning_rate": 2.4691045244607866e-05, - "loss": 0.1885, + "epoch": 0.25, + "learning_rate": 3.73738842531487e-05, + "loss": 0.1894, "step": 113930 }, { - "epoch": 0.51, - "learning_rate": 2.4688803192681945e-05, - "loss": 0.1924, + "epoch": 0.25, + "learning_rate": 3.737276570993938e-05, + "loss": 0.1867, "step": 113940 }, { - "epoch": 0.51, - "learning_rate": 2.468656114075602e-05, - "loss": 0.1861, + "epoch": 0.25, + "learning_rate": 3.737164716673005e-05, + "loss": 0.1908, "step": 113950 }, { - "epoch": 0.51, - "learning_rate": 2.46843190888301e-05, - "loss": 0.1831, + "epoch": 0.25, + "learning_rate": 3.7370528623520726e-05, + "loss": 0.1952, "step": 113960 }, { - "epoch": 0.51, - "learning_rate": 2.4682077036904174e-05, - "loss": 0.1837, + "epoch": 0.25, + "learning_rate": 3.7369410080311404e-05, + "loss": 0.1882, "step": 113970 }, { - "epoch": 0.51, - "learning_rate": 2.4679834984978253e-05, - "loss": 0.1871, + "epoch": 0.25, + "learning_rate": 3.736829153710208e-05, + "loss": 0.1885, "step": 113980 }, { - "epoch": 0.51, - "learning_rate": 2.4677592933052332e-05, - "loss": 0.1857, + "epoch": 0.25, + "learning_rate": 3.736717299389276e-05, + "loss": 0.1921, "step": 113990 }, { - "epoch": 0.51, - "learning_rate": 2.4675350881126407e-05, - "loss": 0.1862, + "epoch": 0.25, + "learning_rate": 3.736605445068343e-05, + "loss": 0.1877, "step": 114000 }, { - "epoch": 0.51, - "learning_rate": 2.4673108829200486e-05, - "loss": 0.188, + "epoch": 0.25, + "learning_rate": 3.736493590747411e-05, + "loss": 0.1879, "step": 114010 }, { - "epoch": 0.51, - "learning_rate": 2.467086677727456e-05, - "loss": 0.1889, + "epoch": 0.25, + "learning_rate": 3.736381736426479e-05, + "loss": 0.1921, "step": 114020 }, { - "epoch": 0.51, - "learning_rate": 2.466862472534864e-05, - "loss": 0.1808, + "epoch": 0.25, + "learning_rate": 3.736269882105546e-05, + "loss": 0.188, "step": 114030 }, { - "epoch": 0.51, - "learning_rate": 2.4666382673422715e-05, - "loss": 0.1893, + "epoch": 0.25, + "learning_rate": 3.7361580277846136e-05, + "loss": 0.1921, "step": 114040 }, { - "epoch": 0.51, - "learning_rate": 2.4664140621496794e-05, - "loss": 0.187, + "epoch": 0.25, + "learning_rate": 3.736046173463681e-05, + "loss": 0.1898, "step": 114050 }, { - "epoch": 0.51, - "learning_rate": 2.4661898569570873e-05, - "loss": 0.1898, + "epoch": 0.25, + "learning_rate": 3.7359343191427485e-05, + "loss": 0.1914, "step": 114060 }, { - "epoch": 0.51, - "learning_rate": 2.4659656517644948e-05, - "loss": 0.1872, + "epoch": 0.25, + "learning_rate": 3.7358224648218156e-05, + "loss": 0.1918, "step": 114070 }, { - "epoch": 0.51, - "learning_rate": 2.4657414465719027e-05, - "loss": 0.1843, + "epoch": 0.25, + "learning_rate": 3.735710610500884e-05, + "loss": 0.1899, "step": 114080 }, { - "epoch": 0.51, - "learning_rate": 2.4655172413793105e-05, - "loss": 0.1865, + "epoch": 0.25, + "learning_rate": 3.735598756179952e-05, + "loss": 0.1926, "step": 114090 }, { - "epoch": 0.51, - "learning_rate": 2.4652930361867184e-05, - "loss": 0.1879, + "epoch": 0.25, + "learning_rate": 3.735486901859019e-05, + "loss": 0.1896, "step": 114100 }, { - "epoch": 0.51, - "learning_rate": 2.465068830994126e-05, - "loss": 0.1866, + "epoch": 0.25, + "learning_rate": 3.735375047538087e-05, + "loss": 0.1939, "step": 114110 }, { - "epoch": 0.51, - "learning_rate": 2.4648446258015338e-05, - "loss": 0.1889, + "epoch": 0.25, + "learning_rate": 3.735263193217154e-05, + "loss": 0.1901, "step": 114120 }, { - "epoch": 0.51, - "learning_rate": 2.4646204206089417e-05, - "loss": 0.1851, + "epoch": 0.25, + "learning_rate": 3.735151338896222e-05, + "loss": 0.193, "step": 114130 }, { - "epoch": 0.51, - "learning_rate": 2.4643962154163492e-05, - "loss": 0.1817, + "epoch": 0.25, + "learning_rate": 3.7350394845752895e-05, + "loss": 0.1949, "step": 114140 }, { - "epoch": 0.51, - "learning_rate": 2.464172010223757e-05, - "loss": 0.1885, + "epoch": 0.25, + "learning_rate": 3.7349276302543566e-05, + "loss": 0.1934, "step": 114150 }, { - "epoch": 0.51, - "learning_rate": 2.4639478050311646e-05, - "loss": 0.1869, + "epoch": 0.25, + "learning_rate": 3.7348157759334244e-05, + "loss": 0.1962, "step": 114160 }, { - "epoch": 0.51, - "learning_rate": 2.4637235998385725e-05, - "loss": 0.1917, + "epoch": 0.25, + "learning_rate": 3.7347039216124915e-05, + "loss": 0.1924, "step": 114170 }, { - "epoch": 0.51, - "learning_rate": 2.46349939464598e-05, - "loss": 0.1787, + "epoch": 0.25, + "learning_rate": 3.734592067291559e-05, + "loss": 0.1905, "step": 114180 }, { - "epoch": 0.51, - "learning_rate": 2.463275189453388e-05, - "loss": 0.1861, + "epoch": 0.25, + "learning_rate": 3.734480212970627e-05, + "loss": 0.1916, "step": 114190 }, { - "epoch": 0.51, - "learning_rate": 2.4630509842607958e-05, - "loss": 0.1858, + "epoch": 0.25, + "learning_rate": 3.734368358649695e-05, + "loss": 0.1921, "step": 114200 }, { - "epoch": 0.51, - "learning_rate": 2.4628267790682033e-05, - "loss": 0.181, + "epoch": 0.25, + "learning_rate": 3.734256504328763e-05, + "loss": 0.1879, "step": 114210 }, { - "epoch": 0.51, - "learning_rate": 2.4626025738756112e-05, - "loss": 0.1934, + "epoch": 0.25, + "learning_rate": 3.73414465000783e-05, + "loss": 0.1914, "step": 114220 }, { - "epoch": 0.51, - "learning_rate": 2.4623783686830187e-05, - "loss": 0.19, + "epoch": 0.25, + "learning_rate": 3.7340327956868976e-05, + "loss": 0.1897, "step": 114230 }, { - "epoch": 0.51, - "learning_rate": 2.4621541634904266e-05, - "loss": 0.187, + "epoch": 0.25, + "learning_rate": 3.7339209413659654e-05, + "loss": 0.1856, "step": 114240 }, { - "epoch": 0.51, - "learning_rate": 2.461929958297834e-05, - "loss": 0.1916, + "epoch": 0.26, + "learning_rate": 3.7338090870450325e-05, + "loss": 0.1904, "step": 114250 }, { - "epoch": 0.51, - "learning_rate": 2.461705753105242e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.7336972327241e-05, + "loss": 0.1928, "step": 114260 }, { - "epoch": 0.51, - "learning_rate": 2.46148154791265e-05, - "loss": 0.1939, + "epoch": 0.26, + "learning_rate": 3.7335853784031674e-05, + "loss": 0.1889, "step": 114270 }, { - "epoch": 0.51, - "learning_rate": 2.4612573427200574e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.733473524082235e-05, + "loss": 0.1964, "step": 114280 }, { - "epoch": 0.51, - "learning_rate": 2.4610331375274653e-05, - "loss": 0.189, + "epoch": 0.26, + "learning_rate": 3.733361669761303e-05, + "loss": 0.19, "step": 114290 }, { - "epoch": 0.51, - "learning_rate": 2.4608089323348728e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.733249815440371e-05, + "loss": 0.1934, "step": 114300 }, { - "epoch": 0.51, - "learning_rate": 2.4605847271422807e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.7331379611194386e-05, + "loss": 0.1942, "step": 114310 }, { - "epoch": 0.51, - "learning_rate": 2.4603605219496882e-05, - "loss": 0.192, + "epoch": 0.26, + "learning_rate": 3.733026106798506e-05, + "loss": 0.1895, "step": 114320 }, { - "epoch": 0.51, - "learning_rate": 2.460136316757096e-05, - "loss": 0.1833, + "epoch": 0.26, + "learning_rate": 3.7329142524775735e-05, + "loss": 0.1915, "step": 114330 }, { - "epoch": 0.51, - "learning_rate": 2.459912111564504e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.732802398156641e-05, + "loss": 0.1935, "step": 114340 }, { - "epoch": 0.51, - "learning_rate": 2.4596879063719118e-05, - "loss": 0.1916, + "epoch": 0.26, + "learning_rate": 3.7326905438357084e-05, + "loss": 0.189, "step": 114350 }, { - "epoch": 0.51, - "learning_rate": 2.4594637011793193e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.732578689514776e-05, + "loss": 0.1892, "step": 114360 }, { - "epoch": 0.51, - "learning_rate": 2.4592394959867272e-05, - "loss": 0.1889, + "epoch": 0.26, + "learning_rate": 3.732466835193843e-05, + "loss": 0.1937, "step": 114370 }, { - "epoch": 0.51, - "learning_rate": 2.459015290794135e-05, - "loss": 0.1859, + "epoch": 0.26, + "learning_rate": 3.732354980872911e-05, + "loss": 0.1903, "step": 114380 }, { - "epoch": 0.51, - "learning_rate": 2.4587910856015426e-05, - "loss": 0.1827, + "epoch": 0.26, + "learning_rate": 3.732243126551979e-05, + "loss": 0.1891, "step": 114390 }, { - "epoch": 0.51, - "learning_rate": 2.4585668804089505e-05, - "loss": 0.1901, + "epoch": 0.26, + "learning_rate": 3.732131272231047e-05, + "loss": 0.1941, "step": 114400 }, { - "epoch": 0.51, - "learning_rate": 2.4583426752163584e-05, - "loss": 0.1873, + "epoch": 0.26, + "learning_rate": 3.7320194179101145e-05, + "loss": 0.1935, "step": 114410 }, { - "epoch": 0.51, - "learning_rate": 2.458118470023766e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.7319075635891816e-05, + "loss": 0.1973, "step": 114420 }, { - "epoch": 0.51, - "learning_rate": 2.4578942648311738e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.7317957092682494e-05, + "loss": 0.1842, "step": 114430 }, { - "epoch": 0.51, - "learning_rate": 2.4576700596385813e-05, - "loss": 0.1877, + "epoch": 0.26, + "learning_rate": 3.7316838549473165e-05, + "loss": 0.1902, "step": 114440 }, { - "epoch": 0.51, - "learning_rate": 2.4574458544459892e-05, - "loss": 0.1874, + "epoch": 0.26, + "learning_rate": 3.731572000626384e-05, + "loss": 0.1904, "step": 114450 }, { - "epoch": 0.51, - "learning_rate": 2.4572216492533967e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.731460146305452e-05, + "loss": 0.1907, "step": 114460 }, { - "epoch": 0.51, - "learning_rate": 2.4569974440608046e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.731348291984519e-05, + "loss": 0.193, "step": 114470 }, { - "epoch": 0.51, - "learning_rate": 2.4567732388682125e-05, - "loss": 0.1888, + "epoch": 0.26, + "learning_rate": 3.731236437663587e-05, + "loss": 0.1904, "step": 114480 }, { - "epoch": 0.51, - "learning_rate": 2.45654903367562e-05, - "loss": 0.1872, + "epoch": 0.26, + "learning_rate": 3.731124583342655e-05, + "loss": 0.1896, "step": 114490 }, { - "epoch": 0.51, - "learning_rate": 2.456324828483028e-05, - "loss": 0.1857, + "epoch": 0.26, + "learning_rate": 3.7310127290217226e-05, + "loss": 0.1922, "step": 114500 }, { - "epoch": 0.51, - "learning_rate": 2.4561006232904354e-05, - "loss": 0.1832, + "epoch": 0.26, + "learning_rate": 3.7309008747007904e-05, + "loss": 0.1897, "step": 114510 }, { - "epoch": 0.51, - "learning_rate": 2.4558764180978433e-05, - "loss": 0.185, + "epoch": 0.26, + "learning_rate": 3.7307890203798575e-05, + "loss": 0.1935, "step": 114520 }, { - "epoch": 0.51, - "learning_rate": 2.4556522129052508e-05, - "loss": 0.1861, + "epoch": 0.26, + "learning_rate": 3.730677166058925e-05, + "loss": 0.1876, "step": 114530 }, { - "epoch": 0.51, - "learning_rate": 2.4554280077126587e-05, - "loss": 0.1879, + "epoch": 0.26, + "learning_rate": 3.7305653117379924e-05, + "loss": 0.1944, "step": 114540 }, { - "epoch": 0.51, - "learning_rate": 2.4552038025200665e-05, - "loss": 0.181, + "epoch": 0.26, + "learning_rate": 3.73045345741706e-05, + "loss": 0.1921, "step": 114550 }, { - "epoch": 0.51, - "learning_rate": 2.454979597327474e-05, - "loss": 0.1881, + "epoch": 0.26, + "learning_rate": 3.730341603096128e-05, + "loss": 0.1937, "step": 114560 }, { - "epoch": 0.51, - "learning_rate": 2.454755392134882e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.730229748775195e-05, + "loss": 0.1935, "step": 114570 }, { - "epoch": 0.51, - "learning_rate": 2.4545311869422895e-05, - "loss": 0.1863, + "epoch": 0.26, + "learning_rate": 3.730117894454263e-05, + "loss": 0.1934, "step": 114580 }, { - "epoch": 0.51, - "learning_rate": 2.4543069817496974e-05, - "loss": 0.1826, + "epoch": 0.26, + "learning_rate": 3.73000604013333e-05, + "loss": 0.1865, "step": 114590 }, { - "epoch": 0.51, - "learning_rate": 2.4540827765571052e-05, - "loss": 0.1909, + "epoch": 0.26, + "learning_rate": 3.729894185812398e-05, + "loss": 0.1905, "step": 114600 }, { - "epoch": 0.51, - "learning_rate": 2.4538585713645128e-05, - "loss": 0.1799, + "epoch": 0.26, + "learning_rate": 3.7297823314914656e-05, + "loss": 0.1843, "step": 114610 }, { - "epoch": 0.51, - "learning_rate": 2.4536343661719206e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.7296704771705334e-05, + "loss": 0.1939, "step": 114620 }, { - "epoch": 0.51, - "learning_rate": 2.4534101609793285e-05, - "loss": 0.181, + "epoch": 0.26, + "learning_rate": 3.729558622849601e-05, + "loss": 0.1905, "step": 114630 }, { - "epoch": 0.51, - "learning_rate": 2.4531859557867364e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.729446768528668e-05, + "loss": 0.1919, "step": 114640 }, { - "epoch": 0.51, - "learning_rate": 2.452961750594144e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.729334914207736e-05, + "loss": 0.1936, "step": 114650 }, { - "epoch": 0.51, - "learning_rate": 2.4527375454015518e-05, - "loss": 0.1796, + "epoch": 0.26, + "learning_rate": 3.729223059886804e-05, + "loss": 0.1881, "step": 114660 }, { - "epoch": 0.51, - "learning_rate": 2.4525133402089593e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.729111205565871e-05, + "loss": 0.1937, "step": 114670 }, { - "epoch": 0.51, - "learning_rate": 2.4522891350163672e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.728999351244939e-05, + "loss": 0.1955, "step": 114680 }, { - "epoch": 0.51, - "learning_rate": 2.452064929823775e-05, - "loss": 0.1896, + "epoch": 0.26, + "learning_rate": 3.728887496924006e-05, + "loss": 0.1946, "step": 114690 }, { - "epoch": 0.51, - "learning_rate": 2.4518407246311826e-05, - "loss": 0.1871, + "epoch": 0.26, + "learning_rate": 3.728775642603074e-05, + "loss": 0.192, "step": 114700 }, { - "epoch": 0.51, - "learning_rate": 2.4516165194385905e-05, - "loss": 0.1871, + "epoch": 0.26, + "learning_rate": 3.7286637882821415e-05, + "loss": 0.1907, "step": 114710 }, { - "epoch": 0.51, - "learning_rate": 2.451392314245998e-05, - "loss": 0.189, + "epoch": 0.26, + "learning_rate": 3.728551933961209e-05, + "loss": 0.1923, "step": 114720 }, { - "epoch": 0.51, - "learning_rate": 2.451168109053406e-05, - "loss": 0.1873, + "epoch": 0.26, + "learning_rate": 3.728440079640277e-05, + "loss": 0.1928, "step": 114730 }, { - "epoch": 0.51, - "learning_rate": 2.4509439038608134e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.728328225319344e-05, + "loss": 0.1888, "step": 114740 }, { - "epoch": 0.51, - "learning_rate": 2.4507196986682213e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.728216370998412e-05, + "loss": 0.1953, "step": 114750 }, { - "epoch": 0.51, - "learning_rate": 2.450495493475629e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.728104516677479e-05, + "loss": 0.1845, "step": 114760 }, { - "epoch": 0.51, - "learning_rate": 2.4502712882830367e-05, - "loss": 0.1872, + "epoch": 0.26, + "learning_rate": 3.727992662356547e-05, + "loss": 0.1878, "step": 114770 }, { - "epoch": 0.51, - "learning_rate": 2.4500470830904445e-05, - "loss": 0.1929, + "epoch": 0.26, + "learning_rate": 3.727880808035615e-05, + "loss": 0.1937, "step": 114780 }, { - "epoch": 0.51, - "learning_rate": 2.449822877897852e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.727768953714682e-05, + "loss": 0.1965, "step": 114790 }, { - "epoch": 0.51, - "learning_rate": 2.44959867270526e-05, - "loss": 0.1828, + "epoch": 0.26, + "learning_rate": 3.7276570993937496e-05, + "loss": 0.193, "step": 114800 }, { - "epoch": 0.51, - "learning_rate": 2.4493744675126675e-05, - "loss": 0.1906, + "epoch": 0.26, + "learning_rate": 3.7275452450728174e-05, + "loss": 0.1929, "step": 114810 }, { - "epoch": 0.51, - "learning_rate": 2.4491502623200754e-05, - "loss": 0.1894, + "epoch": 0.26, + "learning_rate": 3.727433390751885e-05, + "loss": 0.1882, "step": 114820 }, { - "epoch": 0.51, - "learning_rate": 2.4489260571274832e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.727321536430953e-05, + "loss": 0.1862, "step": 114830 }, { - "epoch": 0.51, - "learning_rate": 2.4487018519348908e-05, - "loss": 0.185, + "epoch": 0.26, + "learning_rate": 3.72720968211002e-05, + "loss": 0.1874, "step": 114840 }, { - "epoch": 0.51, - "learning_rate": 2.4484776467422986e-05, - "loss": 0.1822, + "epoch": 0.26, + "learning_rate": 3.727097827789088e-05, + "loss": 0.1901, "step": 114850 }, { - "epoch": 0.51, - "learning_rate": 2.448253441549706e-05, - "loss": 0.1901, + "epoch": 0.26, + "learning_rate": 3.726985973468155e-05, + "loss": 0.1938, "step": 114860 }, { - "epoch": 0.51, - "learning_rate": 2.448029236357114e-05, - "loss": 0.1955, + "epoch": 0.26, + "learning_rate": 3.726874119147223e-05, + "loss": 0.1911, "step": 114870 }, { - "epoch": 0.51, - "learning_rate": 2.447805031164522e-05, - "loss": 0.1848, + "epoch": 0.26, + "learning_rate": 3.7267622648262906e-05, + "loss": 0.195, "step": 114880 }, { - "epoch": 0.51, - "learning_rate": 2.4475808259719298e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.726650410505358e-05, + "loss": 0.1929, "step": 114890 }, { - "epoch": 0.51, - "learning_rate": 2.4473566207793373e-05, - "loss": 0.189, + "epoch": 0.26, + "learning_rate": 3.7265385561844255e-05, + "loss": 0.1939, "step": 114900 }, { - "epoch": 0.51, - "learning_rate": 2.4471324155867452e-05, - "loss": 0.1828, + "epoch": 0.26, + "learning_rate": 3.726426701863493e-05, + "loss": 0.1896, "step": 114910 }, { - "epoch": 0.51, - "learning_rate": 2.446908210394153e-05, - "loss": 0.1861, + "epoch": 0.26, + "learning_rate": 3.726314847542561e-05, + "loss": 0.186, "step": 114920 }, { - "epoch": 0.51, - "learning_rate": 2.4466840052015606e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.726202993221629e-05, + "loss": 0.1891, "step": 114930 }, { - "epoch": 0.51, - "learning_rate": 2.4464598000089685e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.726091138900696e-05, + "loss": 0.1919, "step": 114940 }, { - "epoch": 0.51, - "learning_rate": 2.446235594816376e-05, - "loss": 0.1943, + "epoch": 0.26, + "learning_rate": 3.725979284579764e-05, + "loss": 0.1964, "step": 114950 }, { - "epoch": 0.51, - "learning_rate": 2.446011389623784e-05, - "loss": 0.1911, + "epoch": 0.26, + "learning_rate": 3.725867430258831e-05, + "loss": 0.1922, "step": 114960 }, { - "epoch": 0.51, - "learning_rate": 2.4457871844311917e-05, - "loss": 0.1874, + "epoch": 0.26, + "learning_rate": 3.725755575937899e-05, + "loss": 0.191, "step": 114970 }, { - "epoch": 0.51, - "learning_rate": 2.4455629792385993e-05, - "loss": 0.1822, + "epoch": 0.26, + "learning_rate": 3.7256437216169665e-05, + "loss": 0.19, "step": 114980 }, { - "epoch": 0.51, - "learning_rate": 2.445338774046007e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.7255318672960336e-05, + "loss": 0.1873, "step": 114990 }, { - "epoch": 0.51, - "learning_rate": 2.4451145688534147e-05, - "loss": 0.1853, + "epoch": 0.26, + "learning_rate": 3.7254200129751014e-05, + "loss": 0.1882, "step": 115000 }, { - "epoch": 0.51, - "learning_rate": 2.4448903636608225e-05, - "loss": 0.1895, + "epoch": 0.26, + "learning_rate": 3.7253081586541685e-05, + "loss": 0.1969, "step": 115010 }, { - "epoch": 0.51, - "learning_rate": 2.44466615846823e-05, - "loss": 0.1914, + "epoch": 0.26, + "learning_rate": 3.725196304333236e-05, + "loss": 0.1925, "step": 115020 }, { - "epoch": 0.51, - "learning_rate": 2.444441953275638e-05, - "loss": 0.1837, + "epoch": 0.26, + "learning_rate": 3.725084450012304e-05, + "loss": 0.1938, "step": 115030 }, { - "epoch": 0.51, - "learning_rate": 2.4442177480830458e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.724972595691372e-05, + "loss": 0.1904, "step": 115040 }, { - "epoch": 0.51, - "learning_rate": 2.4439935428904534e-05, - "loss": 0.19, + "epoch": 0.26, + "learning_rate": 3.72486074137044e-05, + "loss": 0.1891, "step": 115050 }, { - "epoch": 0.51, - "learning_rate": 2.4437693376978612e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.724748887049507e-05, + "loss": 0.1878, "step": 115060 }, { - "epoch": 0.51, - "learning_rate": 2.4435451325052688e-05, - "loss": 0.1827, + "epoch": 0.26, + "learning_rate": 3.7246370327285746e-05, + "loss": 0.1895, "step": 115070 }, { - "epoch": 0.51, - "learning_rate": 2.4433209273126766e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.724525178407642e-05, + "loss": 0.1918, "step": 115080 }, { - "epoch": 0.51, - "learning_rate": 2.443096722120084e-05, - "loss": 0.1949, + "epoch": 0.26, + "learning_rate": 3.7244133240867095e-05, + "loss": 0.1917, "step": 115090 }, { - "epoch": 0.51, - "learning_rate": 2.442872516927492e-05, - "loss": 0.1902, + "epoch": 0.26, + "learning_rate": 3.724301469765777e-05, + "loss": 0.1904, "step": 115100 }, { - "epoch": 0.51, - "learning_rate": 2.4426483117349e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.7241896154448444e-05, + "loss": 0.193, "step": 115110 }, { - "epoch": 0.51, - "learning_rate": 2.4424241065423074e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.724077761123912e-05, + "loss": 0.1927, "step": 115120 }, { - "epoch": 0.51, - "learning_rate": 2.4421999013497153e-05, + "epoch": 0.26, + "learning_rate": 3.72396590680298e-05, "loss": 0.1859, "step": 115130 }, { - "epoch": 0.51, - "learning_rate": 2.4419756961571232e-05, - "loss": 0.1805, + "epoch": 0.26, + "learning_rate": 3.723854052482048e-05, + "loss": 0.1917, "step": 115140 }, { - "epoch": 0.51, - "learning_rate": 2.4417514909645307e-05, - "loss": 0.188, + "epoch": 0.26, + "learning_rate": 3.7237421981611156e-05, + "loss": 0.1943, "step": 115150 }, { - "epoch": 0.51, - "learning_rate": 2.4415272857719386e-05, - "loss": 0.1852, + "epoch": 0.26, + "learning_rate": 3.723630343840183e-05, + "loss": 0.1912, "step": 115160 }, { - "epoch": 0.51, - "learning_rate": 2.4413030805793465e-05, - "loss": 0.1863, + "epoch": 0.26, + "learning_rate": 3.7235184895192505e-05, + "loss": 0.1901, "step": 115170 }, { - "epoch": 0.51, - "learning_rate": 2.4410788753867543e-05, - "loss": 0.1888, + "epoch": 0.26, + "learning_rate": 3.7234066351983176e-05, + "loss": 0.189, "step": 115180 }, { - "epoch": 0.51, - "learning_rate": 2.440854670194162e-05, - "loss": 0.1864, + "epoch": 0.26, + "learning_rate": 3.7232947808773854e-05, + "loss": 0.1912, "step": 115190 }, { - "epoch": 0.51, - "learning_rate": 2.4406304650015697e-05, - "loss": 0.1886, + "epoch": 0.26, + "learning_rate": 3.723182926556453e-05, + "loss": 0.1878, "step": 115200 }, { - "epoch": 0.51, - "learning_rate": 2.4404062598089773e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.72307107223552e-05, + "loss": 0.1916, "step": 115210 }, { - "epoch": 0.51, - "learning_rate": 2.440182054616385e-05, - "loss": 0.1872, + "epoch": 0.26, + "learning_rate": 3.722959217914588e-05, + "loss": 0.1902, "step": 115220 }, { - "epoch": 0.51, - "learning_rate": 2.439957849423793e-05, - "loss": 0.1866, + "epoch": 0.26, + "learning_rate": 3.722847363593656e-05, + "loss": 0.1908, "step": 115230 }, { - "epoch": 0.51, - "learning_rate": 2.4397336442312005e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.722735509272724e-05, + "loss": 0.1894, "step": 115240 }, { - "epoch": 0.51, - "learning_rate": 2.4395094390386084e-05, - "loss": 0.1894, + "epoch": 0.26, + "learning_rate": 3.7226236549517915e-05, + "loss": 0.1893, "step": 115250 }, { - "epoch": 0.51, - "learning_rate": 2.439285233846016e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.7225118006308586e-05, + "loss": 0.1877, "step": 115260 }, { - "epoch": 0.51, - "learning_rate": 2.4390610286534238e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.7223999463099264e-05, + "loss": 0.1889, "step": 115270 }, { - "epoch": 0.51, - "learning_rate": 2.4388368234608314e-05, - "loss": 0.1869, + "epoch": 0.26, + "learning_rate": 3.7222880919889935e-05, + "loss": 0.1951, "step": 115280 }, { - "epoch": 0.51, - "learning_rate": 2.4386126182682392e-05, - "loss": 0.1866, + "epoch": 0.26, + "learning_rate": 3.722176237668061e-05, + "loss": 0.1891, "step": 115290 }, { - "epoch": 0.51, - "learning_rate": 2.438388413075647e-05, - "loss": 0.185, + "epoch": 0.26, + "learning_rate": 3.722064383347129e-05, + "loss": 0.1885, "step": 115300 }, { - "epoch": 0.51, - "learning_rate": 2.4381642078830546e-05, - "loss": 0.1863, + "epoch": 0.26, + "learning_rate": 3.721952529026196e-05, + "loss": 0.1889, "step": 115310 }, { - "epoch": 0.51, - "learning_rate": 2.4379400026904625e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.721840674705264e-05, + "loss": 0.1881, "step": 115320 }, { - "epoch": 0.51, - "learning_rate": 2.43771579749787e-05, - "loss": 0.183, + "epoch": 0.26, + "learning_rate": 3.721728820384332e-05, + "loss": 0.1897, "step": 115330 }, { - "epoch": 0.51, - "learning_rate": 2.437491592305278e-05, - "loss": 0.1807, + "epoch": 0.26, + "learning_rate": 3.7216169660633996e-05, + "loss": 0.1917, "step": 115340 }, { - "epoch": 0.51, - "learning_rate": 2.4372673871126854e-05, - "loss": 0.1807, + "epoch": 0.26, + "learning_rate": 3.721505111742467e-05, + "loss": 0.1912, "step": 115350 }, { - "epoch": 0.51, - "learning_rate": 2.4370431819200933e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.7213932574215345e-05, + "loss": 0.1884, "step": 115360 }, { - "epoch": 0.52, - "learning_rate": 2.4368189767275012e-05, - "loss": 0.1852, + "epoch": 0.26, + "learning_rate": 3.721281403100602e-05, + "loss": 0.1916, "step": 115370 }, { - "epoch": 0.52, - "learning_rate": 2.4365947715349087e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.7211695487796694e-05, + "loss": 0.1864, "step": 115380 }, { - "epoch": 0.52, - "learning_rate": 2.4363705663423166e-05, - "loss": 0.1841, + "epoch": 0.26, + "learning_rate": 3.721057694458737e-05, + "loss": 0.1909, "step": 115390 }, { - "epoch": 0.52, - "learning_rate": 2.436146361149724e-05, - "loss": 0.183, + "epoch": 0.26, + "learning_rate": 3.720945840137804e-05, + "loss": 0.193, "step": 115400 }, { - "epoch": 0.52, - "learning_rate": 2.435922155957132e-05, - "loss": 0.18, + "epoch": 0.26, + "learning_rate": 3.720833985816872e-05, + "loss": 0.1919, "step": 115410 }, { - "epoch": 0.52, - "learning_rate": 2.43569795076454e-05, - "loss": 0.1865, + "epoch": 0.26, + "learning_rate": 3.72072213149594e-05, + "loss": 0.1855, "step": 115420 }, { - "epoch": 0.52, - "learning_rate": 2.4354737455719477e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.720610277175007e-05, + "loss": 0.191, "step": 115430 }, { - "epoch": 0.52, - "learning_rate": 2.4352495403793553e-05, - "loss": 0.1859, + "epoch": 0.26, + "learning_rate": 3.7204984228540755e-05, + "loss": 0.1902, "step": 115440 }, { - "epoch": 0.52, - "learning_rate": 2.435025335186763e-05, - "loss": 0.188, + "epoch": 0.26, + "learning_rate": 3.7203865685331426e-05, + "loss": 0.1872, "step": 115450 }, { - "epoch": 0.52, - "learning_rate": 2.434801129994171e-05, - "loss": 0.1854, + "epoch": 0.26, + "learning_rate": 3.7202747142122104e-05, + "loss": 0.1897, "step": 115460 }, { - "epoch": 0.52, - "learning_rate": 2.4345769248015785e-05, - "loss": 0.1902, + "epoch": 0.26, + "learning_rate": 3.720162859891278e-05, + "loss": 0.187, "step": 115470 }, { - "epoch": 0.52, - "learning_rate": 2.4343527196089864e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.720051005570345e-05, + "loss": 0.1924, "step": 115480 }, { - "epoch": 0.52, - "learning_rate": 2.434128514416394e-05, - "loss": 0.182, + "epoch": 0.26, + "learning_rate": 3.719939151249413e-05, + "loss": 0.1933, "step": 115490 }, { - "epoch": 0.52, - "learning_rate": 2.4339043092238018e-05, - "loss": 0.1884, + "epoch": 0.26, + "learning_rate": 3.71982729692848e-05, + "loss": 0.1929, "step": 115500 }, { - "epoch": 0.52, - "learning_rate": 2.4336801040312097e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.719715442607548e-05, + "loss": 0.1905, "step": 115510 }, { - "epoch": 0.52, - "learning_rate": 2.4334558988386172e-05, - "loss": 0.1832, + "epoch": 0.26, + "learning_rate": 3.719603588286616e-05, + "loss": 0.1934, "step": 115520 }, { - "epoch": 0.52, - "learning_rate": 2.433231693646025e-05, - "loss": 0.1846, + "epoch": 0.26, + "learning_rate": 3.719491733965683e-05, + "loss": 0.1935, "step": 115530 }, { - "epoch": 0.52, - "learning_rate": 2.4330074884534326e-05, - "loss": 0.1891, + "epoch": 0.26, + "learning_rate": 3.719379879644751e-05, + "loss": 0.192, "step": 115540 }, { - "epoch": 0.52, - "learning_rate": 2.4327832832608405e-05, - "loss": 0.1882, + "epoch": 0.26, + "learning_rate": 3.7192680253238185e-05, + "loss": 0.1879, "step": 115550 }, { - "epoch": 0.52, - "learning_rate": 2.432559078068248e-05, - "loss": 0.1848, + "epoch": 0.26, + "learning_rate": 3.719156171002886e-05, + "loss": 0.1909, "step": 115560 }, { - "epoch": 0.52, - "learning_rate": 2.432334872875656e-05, - "loss": 0.1818, + "epoch": 0.26, + "learning_rate": 3.719044316681954e-05, + "loss": 0.1903, "step": 115570 }, { - "epoch": 0.52, - "learning_rate": 2.4321106676830638e-05, - "loss": 0.1877, + "epoch": 0.26, + "learning_rate": 3.718932462361021e-05, + "loss": 0.1904, "step": 115580 }, { - "epoch": 0.52, - "learning_rate": 2.4318864624904713e-05, - "loss": 0.1814, + "epoch": 0.26, + "learning_rate": 3.718820608040089e-05, + "loss": 0.1853, "step": 115590 }, { - "epoch": 0.52, - "learning_rate": 2.4316622572978792e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.718708753719156e-05, + "loss": 0.1866, "step": 115600 }, { - "epoch": 0.52, - "learning_rate": 2.4314380521052867e-05, - "loss": 0.1868, + "epoch": 0.26, + "learning_rate": 3.718596899398224e-05, + "loss": 0.19, "step": 115610 }, { - "epoch": 0.52, - "learning_rate": 2.4312138469126946e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.718485045077292e-05, + "loss": 0.1939, "step": 115620 }, { - "epoch": 0.52, - "learning_rate": 2.430989641720102e-05, - "loss": 0.1882, + "epoch": 0.26, + "learning_rate": 3.718373190756359e-05, + "loss": 0.1954, "step": 115630 }, { - "epoch": 0.52, - "learning_rate": 2.43076543652751e-05, - "loss": 0.1851, + "epoch": 0.26, + "learning_rate": 3.7182613364354266e-05, + "loss": 0.1871, "step": 115640 }, { - "epoch": 0.52, - "learning_rate": 2.430541231334918e-05, - "loss": 0.191, + "epoch": 0.26, + "learning_rate": 3.7181494821144944e-05, + "loss": 0.1857, "step": 115650 }, { - "epoch": 0.52, - "learning_rate": 2.4303170261423254e-05, - "loss": 0.1804, + "epoch": 0.26, + "learning_rate": 3.718037627793562e-05, + "loss": 0.1978, "step": 115660 }, { - "epoch": 0.52, - "learning_rate": 2.4300928209497333e-05, - "loss": 0.1879, + "epoch": 0.26, + "learning_rate": 3.717925773472629e-05, + "loss": 0.185, "step": 115670 }, { - "epoch": 0.52, - "learning_rate": 2.429868615757141e-05, - "loss": 0.1842, + "epoch": 0.26, + "learning_rate": 3.717813919151697e-05, + "loss": 0.1937, "step": 115680 }, { - "epoch": 0.52, - "learning_rate": 2.4296444105645487e-05, - "loss": 0.1855, + "epoch": 0.26, + "learning_rate": 3.717702064830765e-05, + "loss": 0.1922, "step": 115690 }, { - "epoch": 0.52, - "learning_rate": 2.4294202053719565e-05, - "loss": 0.1895, + "epoch": 0.26, + "learning_rate": 3.717590210509832e-05, + "loss": 0.1871, "step": 115700 }, { - "epoch": 0.52, - "learning_rate": 2.4291960001793644e-05, - "loss": 0.1809, + "epoch": 0.26, + "learning_rate": 3.717489541620993e-05, + "loss": 0.1845, "step": 115710 }, { - "epoch": 0.52, - "learning_rate": 2.4289717949867723e-05, - "loss": 0.1855, + "epoch": 0.26, + "learning_rate": 3.7173776873000606e-05, + "loss": 0.1939, "step": 115720 }, { - "epoch": 0.52, - "learning_rate": 2.4287475897941798e-05, - "loss": 0.1825, + "epoch": 0.26, + "learning_rate": 3.7172658329791284e-05, + "loss": 0.1877, "step": 115730 }, { - "epoch": 0.52, - "learning_rate": 2.4285233846015877e-05, - "loss": 0.1905, + "epoch": 0.26, + "learning_rate": 3.7171539786581956e-05, + "loss": 0.1874, "step": 115740 }, { - "epoch": 0.52, - "learning_rate": 2.4282991794089952e-05, - "loss": 0.1834, + "epoch": 0.26, + "learning_rate": 3.7170421243372633e-05, + "loss": 0.1909, "step": 115750 }, { - "epoch": 0.52, - "learning_rate": 2.428074974216403e-05, - "loss": 0.1898, + "epoch": 0.26, + "learning_rate": 3.716930270016331e-05, + "loss": 0.1924, "step": 115760 }, { - "epoch": 0.52, - "learning_rate": 2.4278507690238106e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.716818415695398e-05, + "loss": 0.1912, "step": 115770 }, { - "epoch": 0.52, - "learning_rate": 2.4276265638312185e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.716706561374466e-05, + "loss": 0.1887, "step": 115780 }, { - "epoch": 0.52, - "learning_rate": 2.4274023586386264e-05, - "loss": 0.1916, + "epoch": 0.26, + "learning_rate": 3.716594707053533e-05, + "loss": 0.1929, "step": 115790 }, { - "epoch": 0.52, - "learning_rate": 2.427178153446034e-05, - "loss": 0.1789, + "epoch": 0.26, + "learning_rate": 3.716482852732601e-05, + "loss": 0.1954, "step": 115800 }, { - "epoch": 0.52, - "learning_rate": 2.4269539482534418e-05, - "loss": 0.1962, + "epoch": 0.26, + "learning_rate": 3.716370998411669e-05, + "loss": 0.1873, "step": 115810 }, { - "epoch": 0.52, - "learning_rate": 2.4267297430608493e-05, - "loss": 0.1873, + "epoch": 0.26, + "learning_rate": 3.7162591440907365e-05, + "loss": 0.1909, "step": 115820 }, { - "epoch": 0.52, - "learning_rate": 2.4265055378682572e-05, - "loss": 0.1891, + "epoch": 0.26, + "learning_rate": 3.716147289769804e-05, + "loss": 0.1893, "step": 115830 }, { - "epoch": 0.52, - "learning_rate": 2.4262813326756647e-05, - "loss": 0.1874, + "epoch": 0.26, + "learning_rate": 3.7160354354488715e-05, + "loss": 0.1899, "step": 115840 }, { - "epoch": 0.52, - "learning_rate": 2.4260571274830726e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.715923581127939e-05, + "loss": 0.1906, "step": 115850 }, { - "epoch": 0.52, - "learning_rate": 2.4258329222904805e-05, - "loss": 0.1889, + "epoch": 0.26, + "learning_rate": 3.715811726807007e-05, + "loss": 0.1876, "step": 115860 }, { - "epoch": 0.52, - "learning_rate": 2.425608717097888e-05, - "loss": 0.1877, + "epoch": 0.26, + "learning_rate": 3.715699872486074e-05, + "loss": 0.1883, "step": 115870 }, { - "epoch": 0.52, - "learning_rate": 2.425384511905296e-05, - "loss": 0.1924, + "epoch": 0.26, + "learning_rate": 3.715588018165142e-05, + "loss": 0.1882, "step": 115880 }, { - "epoch": 0.52, - "learning_rate": 2.4251603067127034e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.715476163844209e-05, + "loss": 0.1965, "step": 115890 }, { - "epoch": 0.52, - "learning_rate": 2.4249361015201113e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.715364309523277e-05, + "loss": 0.187, "step": 115900 }, { - "epoch": 0.52, - "learning_rate": 2.4247118963275188e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.7152524552023446e-05, + "loss": 0.1891, "step": 115910 }, { - "epoch": 0.52, - "learning_rate": 2.4244876911349267e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.7151406008814124e-05, + "loss": 0.1908, "step": 115920 }, { - "epoch": 0.52, - "learning_rate": 2.4242634859423345e-05, - "loss": 0.1806, + "epoch": 0.26, + "learning_rate": 3.71502874656048e-05, + "loss": 0.1922, "step": 115930 }, { - "epoch": 0.52, - "learning_rate": 2.424039280749742e-05, - "loss": 0.1956, + "epoch": 0.26, + "learning_rate": 3.7149168922395473e-05, + "loss": 0.1925, "step": 115940 }, { - "epoch": 0.52, - "learning_rate": 2.42381507555715e-05, - "loss": 0.1851, + "epoch": 0.26, + "learning_rate": 3.714805037918615e-05, + "loss": 0.1887, "step": 115950 }, { - "epoch": 0.52, - "learning_rate": 2.4235908703645578e-05, - "loss": 0.1881, + "epoch": 0.26, + "learning_rate": 3.714693183597683e-05, + "loss": 0.19, "step": 115960 }, { - "epoch": 0.52, - "learning_rate": 2.4233666651719657e-05, - "loss": 0.1825, + "epoch": 0.26, + "learning_rate": 3.71458132927675e-05, + "loss": 0.1915, "step": 115970 }, { - "epoch": 0.52, - "learning_rate": 2.4231424599793732e-05, - "loss": 0.1829, + "epoch": 0.26, + "learning_rate": 3.714469474955818e-05, + "loss": 0.1897, "step": 115980 }, { - "epoch": 0.52, - "learning_rate": 2.422918254786781e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.714357620634885e-05, + "loss": 0.1875, "step": 115990 }, { - "epoch": 0.52, - "learning_rate": 2.422694049594189e-05, - "loss": 0.1816, + "epoch": 0.26, + "learning_rate": 3.714245766313953e-05, + "loss": 0.1955, "step": 116000 }, { - "epoch": 0.52, - "learning_rate": 2.4224698444015965e-05, - "loss": 0.1826, + "epoch": 0.26, + "learning_rate": 3.7141339119930205e-05, + "loss": 0.1947, "step": 116010 }, { - "epoch": 0.52, - "learning_rate": 2.4222456392090044e-05, - "loss": 0.1863, + "epoch": 0.26, + "learning_rate": 3.714022057672088e-05, + "loss": 0.1944, "step": 116020 }, { - "epoch": 0.52, - "learning_rate": 2.422021434016412e-05, + "epoch": 0.26, + "learning_rate": 3.713910203351156e-05, "loss": 0.1867, "step": 116030 }, { - "epoch": 0.52, - "learning_rate": 2.4217972288238198e-05, - "loss": 0.1871, + "epoch": 0.26, + "learning_rate": 3.713798349030223e-05, + "loss": 0.1893, "step": 116040 }, { - "epoch": 0.52, - "learning_rate": 2.4215730236312273e-05, - "loss": 0.1892, + "epoch": 0.26, + "learning_rate": 3.713686494709291e-05, + "loss": 0.1964, "step": 116050 }, { - "epoch": 0.52, - "learning_rate": 2.4213488184386352e-05, - "loss": 0.1846, + "epoch": 0.26, + "learning_rate": 3.713574640388358e-05, + "loss": 0.1891, "step": 116060 }, { - "epoch": 0.52, - "learning_rate": 2.421124613246043e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.713462786067426e-05, + "loss": 0.191, "step": 116070 }, { - "epoch": 0.52, - "learning_rate": 2.4209004080534506e-05, - "loss": 0.1859, + "epoch": 0.26, + "learning_rate": 3.713350931746494e-05, + "loss": 0.1943, "step": 116080 }, { - "epoch": 0.52, - "learning_rate": 2.4206762028608585e-05, - "loss": 0.1906, + "epoch": 0.26, + "learning_rate": 3.713239077425561e-05, + "loss": 0.1924, "step": 116090 }, { - "epoch": 0.52, - "learning_rate": 2.420451997668266e-05, - "loss": 0.1859, + "epoch": 0.26, + "learning_rate": 3.7131272231046286e-05, + "loss": 0.1851, "step": 116100 }, { - "epoch": 0.52, - "learning_rate": 2.420227792475674e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.713015368783696e-05, + "loss": 0.1859, "step": 116110 }, { - "epoch": 0.52, - "learning_rate": 2.4200035872830814e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.7129035144627636e-05, + "loss": 0.1866, "step": 116120 }, { - "epoch": 0.52, - "learning_rate": 2.4197793820904893e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.7127916601418313e-05, + "loss": 0.1919, "step": 116130 }, { - "epoch": 0.52, - "learning_rate": 2.419555176897897e-05, - "loss": 0.1932, + "epoch": 0.26, + "learning_rate": 3.712679805820899e-05, + "loss": 0.1889, "step": 116140 }, { - "epoch": 0.52, - "learning_rate": 2.4193309717053047e-05, - "loss": 0.1855, + "epoch": 0.26, + "learning_rate": 3.712567951499967e-05, + "loss": 0.1856, "step": 116150 }, { - "epoch": 0.52, - "learning_rate": 2.4191067665127126e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.712456097179034e-05, + "loss": 0.1904, "step": 116160 }, { - "epoch": 0.52, - "learning_rate": 2.41888256132012e-05, - "loss": 0.1798, + "epoch": 0.26, + "learning_rate": 3.712344242858102e-05, + "loss": 0.1911, "step": 116170 }, { - "epoch": 0.52, - "learning_rate": 2.418658356127528e-05, - "loss": 0.1903, + "epoch": 0.26, + "learning_rate": 3.7122323885371696e-05, + "loss": 0.1923, "step": 116180 }, { - "epoch": 0.52, - "learning_rate": 2.4184341509349355e-05, - "loss": 0.1833, + "epoch": 0.26, + "learning_rate": 3.712120534216237e-05, + "loss": 0.1952, "step": 116190 }, { - "epoch": 0.52, - "learning_rate": 2.4182099457423434e-05, - "loss": 0.1817, + "epoch": 0.26, + "learning_rate": 3.7120086798953045e-05, + "loss": 0.1899, "step": 116200 }, { - "epoch": 0.52, - "learning_rate": 2.4179857405497512e-05, - "loss": 0.1846, + "epoch": 0.26, + "learning_rate": 3.7118968255743717e-05, + "loss": 0.191, "step": 116210 }, { - "epoch": 0.52, - "learning_rate": 2.417761535357159e-05, - "loss": 0.19, + "epoch": 0.26, + "learning_rate": 3.7117849712534394e-05, + "loss": 0.1934, "step": 116220 }, { - "epoch": 0.52, - "learning_rate": 2.4175373301645666e-05, - "loss": 0.1826, + "epoch": 0.26, + "learning_rate": 3.711673116932507e-05, + "loss": 0.1877, "step": 116230 }, { - "epoch": 0.52, - "learning_rate": 2.4173131249719745e-05, - "loss": 0.1874, + "epoch": 0.26, + "learning_rate": 3.711561262611575e-05, + "loss": 0.1901, "step": 116240 }, { - "epoch": 0.52, - "learning_rate": 2.4170889197793824e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.711449408290643e-05, + "loss": 0.1889, "step": 116250 }, { - "epoch": 0.52, - "learning_rate": 2.41686471458679e-05, - "loss": 0.1787, + "epoch": 0.26, + "learning_rate": 3.71133755396971e-05, + "loss": 0.1891, "step": 116260 }, { - "epoch": 0.52, - "learning_rate": 2.4166405093941978e-05, - "loss": 0.1895, + "epoch": 0.26, + "learning_rate": 3.711225699648778e-05, + "loss": 0.185, "step": 116270 }, { - "epoch": 0.52, - "learning_rate": 2.4164163042016057e-05, - "loss": 0.1891, + "epoch": 0.26, + "learning_rate": 3.7111138453278455e-05, + "loss": 0.1892, "step": 116280 }, { - "epoch": 0.52, - "learning_rate": 2.4161920990090132e-05, - "loss": 0.1824, + "epoch": 0.26, + "learning_rate": 3.7110019910069126e-05, + "loss": 0.1945, "step": 116290 }, { - "epoch": 0.52, - "learning_rate": 2.415967893816421e-05, - "loss": 0.1919, + "epoch": 0.26, + "learning_rate": 3.7108901366859804e-05, + "loss": 0.1901, "step": 116300 }, { - "epoch": 0.52, - "learning_rate": 2.4157436886238286e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.7107782823650475e-05, + "loss": 0.19, "step": 116310 }, { - "epoch": 0.52, - "learning_rate": 2.4155194834312365e-05, - "loss": 0.1832, + "epoch": 0.26, + "learning_rate": 3.7106664280441153e-05, + "loss": 0.1915, "step": 116320 }, { - "epoch": 0.52, - "learning_rate": 2.415295278238644e-05, - "loss": 0.1785, + "epoch": 0.26, + "learning_rate": 3.710554573723183e-05, + "loss": 0.1885, "step": 116330 }, { - "epoch": 0.52, - "learning_rate": 2.415071073046052e-05, - "loss": 0.1869, + "epoch": 0.26, + "learning_rate": 3.710442719402251e-05, + "loss": 0.1933, "step": 116340 }, { - "epoch": 0.52, - "learning_rate": 2.4148468678534597e-05, - "loss": 0.1869, + "epoch": 0.26, + "learning_rate": 3.710330865081319e-05, + "loss": 0.1902, "step": 116350 }, { - "epoch": 0.52, - "learning_rate": 2.4146226626608673e-05, - "loss": 0.1834, + "epoch": 0.26, + "learning_rate": 3.710219010760386e-05, + "loss": 0.191, "step": 116360 }, { - "epoch": 0.52, - "learning_rate": 2.414398457468275e-05, - "loss": 0.1872, + "epoch": 0.26, + "learning_rate": 3.7101071564394536e-05, + "loss": 0.1924, "step": 116370 }, { - "epoch": 0.52, - "learning_rate": 2.4141742522756827e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.709995302118521e-05, + "loss": 0.1888, "step": 116380 }, { - "epoch": 0.52, - "learning_rate": 2.4139500470830906e-05, - "loss": 0.1833, + "epoch": 0.26, + "learning_rate": 3.7098834477975885e-05, + "loss": 0.1892, "step": 116390 }, { - "epoch": 0.52, - "learning_rate": 2.413725841890498e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.709771593476656e-05, + "loss": 0.1882, "step": 116400 }, { - "epoch": 0.52, - "learning_rate": 2.413501636697906e-05, - "loss": 0.1834, + "epoch": 0.26, + "learning_rate": 3.7096597391557234e-05, + "loss": 0.1901, "step": 116410 }, { - "epoch": 0.52, - "learning_rate": 2.4132774315053138e-05, - "loss": 0.1842, + "epoch": 0.26, + "learning_rate": 3.709547884834791e-05, + "loss": 0.1896, "step": 116420 }, { - "epoch": 0.52, - "learning_rate": 2.4130532263127214e-05, - "loss": 0.1915, + "epoch": 0.26, + "learning_rate": 3.7094360305138584e-05, + "loss": 0.1874, "step": 116430 }, { - "epoch": 0.52, - "learning_rate": 2.4128290211201292e-05, - "loss": 0.1842, + "epoch": 0.26, + "learning_rate": 3.709324176192927e-05, + "loss": 0.192, "step": 116440 }, { - "epoch": 0.52, - "learning_rate": 2.4126048159275368e-05, - "loss": 0.1879, + "epoch": 0.26, + "learning_rate": 3.7092123218719946e-05, + "loss": 0.1951, "step": 116450 }, { - "epoch": 0.52, - "learning_rate": 2.4123806107349446e-05, - "loss": 0.1873, + "epoch": 0.26, + "learning_rate": 3.709100467551062e-05, + "loss": 0.1929, "step": 116460 }, { - "epoch": 0.52, - "learning_rate": 2.4121564055423522e-05, - "loss": 0.1854, + "epoch": 0.26, + "learning_rate": 3.7089886132301295e-05, + "loss": 0.1909, "step": 116470 }, { - "epoch": 0.52, - "learning_rate": 2.41193220034976e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.7088767589091966e-05, + "loss": 0.1936, "step": 116480 }, { - "epoch": 0.52, - "learning_rate": 2.411707995157168e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.7087649045882644e-05, + "loss": 0.1882, "step": 116490 }, { - "epoch": 0.52, - "learning_rate": 2.4114837899645758e-05, - "loss": 0.1776, + "epoch": 0.26, + "learning_rate": 3.708653050267332e-05, + "loss": 0.1982, "step": 116500 }, { - "epoch": 0.52, - "learning_rate": 2.4112595847719837e-05, - "loss": 0.1908, + "epoch": 0.26, + "learning_rate": 3.708541195946399e-05, + "loss": 0.1947, "step": 116510 }, { - "epoch": 0.52, - "learning_rate": 2.4110353795793912e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.708429341625467e-05, + "loss": 0.1874, "step": 116520 }, { - "epoch": 0.52, - "learning_rate": 2.410811174386799e-05, - "loss": 0.1821, + "epoch": 0.26, + "learning_rate": 3.708317487304534e-05, + "loss": 0.192, "step": 116530 }, { - "epoch": 0.52, - "learning_rate": 2.410586969194207e-05, - "loss": 0.1805, + "epoch": 0.26, + "learning_rate": 3.708205632983602e-05, + "loss": 0.1899, "step": 116540 }, { - "epoch": 0.52, - "learning_rate": 2.4103627640016145e-05, - "loss": 0.1878, + "epoch": 0.26, + "learning_rate": 3.70809377866267e-05, + "loss": 0.1946, "step": 116550 }, { - "epoch": 0.52, - "learning_rate": 2.4101385588090223e-05, - "loss": 0.1888, + "epoch": 0.26, + "learning_rate": 3.7079819243417376e-05, + "loss": 0.1873, "step": 116560 }, { - "epoch": 0.52, - "learning_rate": 2.40991435361643e-05, - "loss": 0.1853, + "epoch": 0.26, + "learning_rate": 3.7078700700208054e-05, + "loss": 0.1915, "step": 116570 }, { - "epoch": 0.52, - "learning_rate": 2.4096901484238377e-05, - "loss": 0.1912, + "epoch": 0.26, + "learning_rate": 3.7077582156998725e-05, + "loss": 0.1899, "step": 116580 }, { - "epoch": 0.52, - "learning_rate": 2.4094659432312453e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.70764636137894e-05, + "loss": 0.1878, "step": 116590 }, { - "epoch": 0.52, - "learning_rate": 2.409241738038653e-05, - "loss": 0.1832, + "epoch": 0.26, + "learning_rate": 3.707534507058008e-05, + "loss": 0.1917, "step": 116600 }, { - "epoch": 0.52, - "learning_rate": 2.409017532846061e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.707422652737075e-05, + "loss": 0.1888, "step": 116610 }, { - "epoch": 0.52, - "learning_rate": 2.4087933276534686e-05, - "loss": 0.1857, + "epoch": 0.26, + "learning_rate": 3.707310798416143e-05, + "loss": 0.1888, "step": 116620 }, { - "epoch": 0.52, - "learning_rate": 2.4085691224608764e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.70719894409521e-05, + "loss": 0.1912, "step": 116630 }, { - "epoch": 0.52, - "learning_rate": 2.408344917268284e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.707087089774278e-05, + "loss": 0.1921, "step": 116640 }, { - "epoch": 0.52, - "learning_rate": 2.408120712075692e-05, - "loss": 0.1876, + "epoch": 0.26, + "learning_rate": 3.706975235453346e-05, + "loss": 0.1984, "step": 116650 }, { - "epoch": 0.52, - "learning_rate": 2.4078965068830994e-05, - "loss": 0.1824, + "epoch": 0.26, + "learning_rate": 3.7068633811324135e-05, + "loss": 0.1881, "step": 116660 }, { - "epoch": 0.52, - "learning_rate": 2.4076723016905072e-05, - "loss": 0.1828, + "epoch": 0.26, + "learning_rate": 3.706751526811481e-05, + "loss": 0.1853, "step": 116670 }, { - "epoch": 0.52, - "learning_rate": 2.407448096497915e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.7066396724905484e-05, + "loss": 0.1923, "step": 116680 }, { - "epoch": 0.52, - "learning_rate": 2.4072238913053226e-05, - "loss": 0.1844, + "epoch": 0.26, + "learning_rate": 3.706527818169616e-05, + "loss": 0.1882, "step": 116690 }, { - "epoch": 0.52, - "learning_rate": 2.4069996861127305e-05, - "loss": 0.1825, + "epoch": 0.26, + "learning_rate": 3.706415963848683e-05, + "loss": 0.1865, "step": 116700 }, { - "epoch": 0.52, - "learning_rate": 2.406775480920138e-05, - "loss": 0.1877, + "epoch": 0.26, + "learning_rate": 3.706304109527751e-05, + "loss": 0.188, "step": 116710 }, { - "epoch": 0.52, - "learning_rate": 2.406551275727546e-05, - "loss": 0.1854, + "epoch": 0.26, + "learning_rate": 3.706192255206819e-05, + "loss": 0.1937, "step": 116720 }, { - "epoch": 0.52, - "learning_rate": 2.4063270705349534e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.706080400885886e-05, + "loss": 0.193, "step": 116730 }, { - "epoch": 0.52, - "learning_rate": 2.4061028653423613e-05, - "loss": 0.1867, + "epoch": 0.26, + "learning_rate": 3.705968546564954e-05, + "loss": 0.1941, "step": 116740 }, { - "epoch": 0.52, - "learning_rate": 2.4058786601497692e-05, - "loss": 0.1795, + "epoch": 0.26, + "learning_rate": 3.7058566922440216e-05, + "loss": 0.1921, "step": 116750 }, { - "epoch": 0.52, - "learning_rate": 2.4056544549571767e-05, - "loss": 0.1808, + "epoch": 0.26, + "learning_rate": 3.7057448379230894e-05, + "loss": 0.1881, "step": 116760 }, { - "epoch": 0.52, - "learning_rate": 2.4054302497645846e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.705632983602157e-05, + "loss": 0.1907, "step": 116770 }, { - "epoch": 0.52, - "learning_rate": 2.4052060445719925e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.705521129281224e-05, + "loss": 0.1891, "step": 116780 }, { - "epoch": 0.52, - "learning_rate": 2.4049818393794003e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.705409274960292e-05, + "loss": 0.1955, "step": 116790 }, { - "epoch": 0.52, - "learning_rate": 2.404757634186808e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.705297420639359e-05, + "loss": 0.1876, "step": 116800 }, { - "epoch": 0.52, - "learning_rate": 2.4045334289942157e-05, - "loss": 0.193, + "epoch": 0.26, + "learning_rate": 3.705185566318427e-05, + "loss": 0.1888, "step": 116810 }, { - "epoch": 0.52, - "learning_rate": 2.4043092238016236e-05, - "loss": 0.1888, + "epoch": 0.26, + "learning_rate": 3.705073711997495e-05, + "loss": 0.1864, "step": 116820 }, { - "epoch": 0.52, - "learning_rate": 2.404085018609031e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.704961857676562e-05, + "loss": 0.1877, "step": 116830 }, { - "epoch": 0.52, - "learning_rate": 2.403860813416439e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.70485000335563e-05, + "loss": 0.191, "step": 116840 }, { - "epoch": 0.52, - "learning_rate": 2.4036366082238466e-05, - "loss": 0.1891, + "epoch": 0.26, + "learning_rate": 3.7047381490346975e-05, + "loss": 0.1894, "step": 116850 }, { - "epoch": 0.52, - "learning_rate": 2.4034124030312544e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.704626294713765e-05, + "loss": 0.189, "step": 116860 }, { - "epoch": 0.52, - "learning_rate": 2.403188197838662e-05, - "loss": 0.1837, + "epoch": 0.26, + "learning_rate": 3.704514440392833e-05, + "loss": 0.1893, "step": 116870 }, { - "epoch": 0.52, - "learning_rate": 2.40296399264607e-05, - "loss": 0.1783, + "epoch": 0.26, + "learning_rate": 3.7044025860719e-05, + "loss": 0.1969, "step": 116880 }, { - "epoch": 0.52, - "learning_rate": 2.4027397874534777e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.704290731750968e-05, + "loss": 0.1875, "step": 116890 }, { - "epoch": 0.52, - "learning_rate": 2.4025155822608852e-05, - "loss": 0.189, + "epoch": 0.26, + "learning_rate": 3.704178877430035e-05, + "loss": 0.1903, "step": 116900 }, { - "epoch": 0.52, - "learning_rate": 2.402291377068293e-05, - "loss": 0.181, + "epoch": 0.26, + "learning_rate": 3.704067023109103e-05, + "loss": 0.192, "step": 116910 }, { - "epoch": 0.52, - "learning_rate": 2.4020671718757006e-05, - "loss": 0.1902, + "epoch": 0.26, + "learning_rate": 3.703955168788171e-05, + "loss": 0.1923, "step": 116920 }, { - "epoch": 0.52, - "learning_rate": 2.4018429666831085e-05, - "loss": 0.1827, + "epoch": 0.26, + "learning_rate": 3.703843314467238e-05, + "loss": 0.1888, "step": 116930 }, { - "epoch": 0.52, - "learning_rate": 2.401618761490516e-05, - "loss": 0.1821, + "epoch": 0.26, + "learning_rate": 3.7037314601463056e-05, + "loss": 0.1924, "step": 116940 }, { - "epoch": 0.52, - "learning_rate": 2.401394556297924e-05, - "loss": 0.1902, + "epoch": 0.26, + "learning_rate": 3.703619605825373e-05, + "loss": 0.1899, "step": 116950 }, { - "epoch": 0.52, - "learning_rate": 2.4011703511053318e-05, - "loss": 0.1846, + "epoch": 0.26, + "learning_rate": 3.7035077515044405e-05, + "loss": 0.192, "step": 116960 }, { - "epoch": 0.52, - "learning_rate": 2.4009461459127393e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.703395897183508e-05, + "loss": 0.1887, "step": 116970 }, { - "epoch": 0.52, - "learning_rate": 2.4007219407201472e-05, - "loss": 0.1829, + "epoch": 0.26, + "learning_rate": 3.703284042862576e-05, + "loss": 0.19, "step": 116980 }, { - "epoch": 0.52, - "learning_rate": 2.4004977355275547e-05, - "loss": 0.1899, + "epoch": 0.26, + "learning_rate": 3.703172188541644e-05, + "loss": 0.1944, "step": 116990 }, { - "epoch": 0.52, - "learning_rate": 2.4002735303349626e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.703060334220711e-05, + "loss": 0.1922, "step": 117000 }, { - "epoch": 0.52, - "learning_rate": 2.40004932514237e-05, - "loss": 0.1852, + "epoch": 0.26, + "learning_rate": 3.702948479899779e-05, + "loss": 0.1819, "step": 117010 }, { - "epoch": 0.52, - "learning_rate": 2.399825119949778e-05, - "loss": 0.1829, + "epoch": 0.26, + "learning_rate": 3.702836625578846e-05, + "loss": 0.1922, "step": 117020 }, { - "epoch": 0.52, - "learning_rate": 2.399600914757186e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.702724771257914e-05, + "loss": 0.1964, "step": 117030 }, { - "epoch": 0.52, - "learning_rate": 2.3993767095645937e-05, - "loss": 0.1811, + "epoch": 0.26, + "learning_rate": 3.7026129169369815e-05, + "loss": 0.1856, "step": 117040 }, { - "epoch": 0.52, - "learning_rate": 2.3991525043720016e-05, - "loss": 0.1868, + "epoch": 0.26, + "learning_rate": 3.7025010626160486e-05, + "loss": 0.1879, "step": 117050 }, { - "epoch": 0.52, - "learning_rate": 2.398928299179409e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.7023892082951164e-05, + "loss": 0.1932, "step": 117060 }, { - "epoch": 0.52, - "learning_rate": 2.398704093986817e-05, - "loss": 0.1781, + "epoch": 0.26, + "learning_rate": 3.702277353974184e-05, + "loss": 0.1932, "step": 117070 }, { - "epoch": 0.52, - "learning_rate": 2.3984798887942246e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.702165499653252e-05, + "loss": 0.1881, "step": 117080 }, { - "epoch": 0.52, - "learning_rate": 2.3982556836016324e-05, - "loss": 0.191, + "epoch": 0.26, + "learning_rate": 3.70205364533232e-05, + "loss": 0.193, "step": 117090 }, { - "epoch": 0.52, - "learning_rate": 2.3980314784090403e-05, - "loss": 0.176, + "epoch": 0.26, + "learning_rate": 3.701941791011387e-05, + "loss": 0.1888, "step": 117100 }, { - "epoch": 0.52, - "learning_rate": 2.397807273216448e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.701829936690455e-05, + "loss": 0.1896, "step": 117110 }, { - "epoch": 0.52, - "learning_rate": 2.3975830680238557e-05, - "loss": 0.1776, + "epoch": 0.26, + "learning_rate": 3.701718082369522e-05, + "loss": 0.1834, "step": 117120 }, { - "epoch": 0.52, - "learning_rate": 2.3973588628312632e-05, - "loss": 0.1838, + "epoch": 0.26, + "learning_rate": 3.7016062280485896e-05, + "loss": 0.1944, "step": 117130 }, { - "epoch": 0.52, - "learning_rate": 2.397134657638671e-05, - "loss": 0.1907, + "epoch": 0.26, + "learning_rate": 3.7014943737276574e-05, + "loss": 0.1936, "step": 117140 }, { - "epoch": 0.52, - "learning_rate": 2.3969104524460786e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.7013825194067245e-05, + "loss": 0.1905, "step": 117150 }, { - "epoch": 0.52, - "learning_rate": 2.3966862472534865e-05, - "loss": 0.1923, + "epoch": 0.26, + "learning_rate": 3.701270665085792e-05, + "loss": 0.1944, "step": 117160 }, { - "epoch": 0.52, - "learning_rate": 2.3964620420608944e-05, - "loss": 0.1833, + "epoch": 0.26, + "learning_rate": 3.70115881076486e-05, + "loss": 0.1922, "step": 117170 }, { - "epoch": 0.52, - "learning_rate": 2.396237836868302e-05, - "loss": 0.1811, + "epoch": 0.26, + "learning_rate": 3.701046956443928e-05, + "loss": 0.1946, "step": 117180 }, { - "epoch": 0.52, - "learning_rate": 2.3960136316757098e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.700935102122996e-05, + "loss": 0.1876, "step": 117190 }, { - "epoch": 0.52, - "learning_rate": 2.3957894264831173e-05, - "loss": 0.1879, + "epoch": 0.26, + "learning_rate": 3.700823247802063e-05, + "loss": 0.1925, "step": 117200 }, { - "epoch": 0.52, - "learning_rate": 2.3955652212905252e-05, - "loss": 0.186, + "epoch": 0.26, + "learning_rate": 3.7007113934811306e-05, + "loss": 0.1921, "step": 117210 }, { - "epoch": 0.52, - "learning_rate": 2.3953410160979327e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.700599539160198e-05, + "loss": 0.1885, "step": 117220 }, { - "epoch": 0.52, - "learning_rate": 2.3951168109053406e-05, - "loss": 0.1828, + "epoch": 0.26, + "learning_rate": 3.7004876848392655e-05, + "loss": 0.1872, "step": 117230 }, { - "epoch": 0.52, - "learning_rate": 2.3948926057127485e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.700375830518333e-05, + "loss": 0.1889, "step": 117240 }, { - "epoch": 0.52, - "learning_rate": 2.394668400520156e-05, - "loss": 0.1824, + "epoch": 0.26, + "learning_rate": 3.7002639761974004e-05, + "loss": 0.2006, "step": 117250 }, { - "epoch": 0.52, - "learning_rate": 2.394444195327564e-05, - "loss": 0.1827, + "epoch": 0.26, + "learning_rate": 3.700152121876468e-05, + "loss": 0.1898, "step": 117260 }, { - "epoch": 0.52, - "learning_rate": 2.3942199901349714e-05, - "loss": 0.183, + "epoch": 0.26, + "learning_rate": 3.700040267555536e-05, + "loss": 0.1894, "step": 117270 }, { - "epoch": 0.52, - "learning_rate": 2.3939957849423793e-05, - "loss": 0.181, + "epoch": 0.26, + "learning_rate": 3.699928413234604e-05, + "loss": 0.1898, "step": 117280 }, { - "epoch": 0.52, - "learning_rate": 2.393771579749787e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.699816558913671e-05, + "loss": 0.1923, "step": 117290 }, { - "epoch": 0.52, - "learning_rate": 2.3935473745571947e-05, - "loss": 0.1883, + "epoch": 0.26, + "learning_rate": 3.699704704592739e-05, + "loss": 0.1853, "step": 117300 }, { - "epoch": 0.52, - "learning_rate": 2.3933231693646026e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.6995928502718065e-05, + "loss": 0.1931, "step": 117310 }, { - "epoch": 0.52, - "learning_rate": 2.3930989641720104e-05, - "loss": 0.1841, + "epoch": 0.26, + "learning_rate": 3.6994809959508736e-05, + "loss": 0.1901, "step": 117320 }, { - "epoch": 0.52, - "learning_rate": 2.3928747589794183e-05, - "loss": 0.1831, + "epoch": 0.26, + "learning_rate": 3.6993691416299414e-05, + "loss": 0.189, "step": 117330 }, { - "epoch": 0.52, - "learning_rate": 2.392650553786826e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.6992572873090085e-05, + "loss": 0.1872, "step": 117340 }, { - "epoch": 0.52, - "learning_rate": 2.3924263485942337e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.699145432988076e-05, + "loss": 0.1911, "step": 117350 }, { - "epoch": 0.52, - "learning_rate": 2.3922021434016412e-05, - "loss": 0.1805, + "epoch": 0.26, + "learning_rate": 3.699033578667144e-05, + "loss": 0.1897, "step": 117360 }, { - "epoch": 0.52, - "learning_rate": 2.391977938209049e-05, - "loss": 0.1805, + "epoch": 0.26, + "learning_rate": 3.698921724346211e-05, + "loss": 0.188, "step": 117370 }, { - "epoch": 0.52, - "learning_rate": 2.391753733016457e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.698809870025279e-05, + "loss": 0.1855, "step": 117380 }, { - "epoch": 0.52, - "learning_rate": 2.3915295278238645e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.698698015704347e-05, + "loss": 0.197, "step": 117390 }, { - "epoch": 0.52, - "learning_rate": 2.3913053226312724e-05, - "loss": 0.1869, + "epoch": 0.26, + "learning_rate": 3.6985861613834146e-05, + "loss": 0.19, "step": 117400 }, { - "epoch": 0.52, - "learning_rate": 2.39108111743868e-05, - "loss": 0.1895, + "epoch": 0.26, + "learning_rate": 3.6984743070624824e-05, + "loss": 0.19, "step": 117410 }, { - "epoch": 0.52, - "learning_rate": 2.3908569122460878e-05, - "loss": 0.1811, + "epoch": 0.26, + "learning_rate": 3.6983624527415495e-05, + "loss": 0.1868, "step": 117420 }, { - "epoch": 0.52, - "learning_rate": 2.3906327070534953e-05, - "loss": 0.1841, + "epoch": 0.26, + "learning_rate": 3.698250598420617e-05, + "loss": 0.1895, "step": 117430 }, { - "epoch": 0.52, - "learning_rate": 2.3904085018609032e-05, - "loss": 0.1788, + "epoch": 0.26, + "learning_rate": 3.6981387440996844e-05, + "loss": 0.1897, "step": 117440 }, { - "epoch": 0.52, - "learning_rate": 2.390184296668311e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.698026889778752e-05, + "loss": 0.1875, "step": 117450 }, { - "epoch": 0.52, - "learning_rate": 2.3899600914757186e-05, - "loss": 0.1852, + "epoch": 0.26, + "learning_rate": 3.69791503545782e-05, + "loss": 0.1885, "step": 117460 }, { - "epoch": 0.52, - "learning_rate": 2.3897358862831265e-05, - "loss": 0.1803, + "epoch": 0.26, + "learning_rate": 3.697803181136887e-05, + "loss": 0.1911, "step": 117470 }, { - "epoch": 0.52, - "learning_rate": 2.389511681090534e-05, - "loss": 0.192, + "epoch": 0.26, + "learning_rate": 3.697691326815955e-05, + "loss": 0.1951, "step": 117480 }, { - "epoch": 0.52, - "learning_rate": 2.389287475897942e-05, - "loss": 0.1848, + "epoch": 0.26, + "learning_rate": 3.697579472495023e-05, + "loss": 0.1905, "step": 117490 }, { - "epoch": 0.52, - "learning_rate": 2.3890632707053494e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.6974676181740905e-05, + "loss": 0.1902, "step": 117500 }, { - "epoch": 0.52, - "learning_rate": 2.3888390655127573e-05, - "loss": 0.1871, + "epoch": 0.26, + "learning_rate": 3.697355763853158e-05, + "loss": 0.185, "step": 117510 }, { - "epoch": 0.52, - "learning_rate": 2.388614860320165e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.6972439095322254e-05, + "loss": 0.1882, "step": 117520 }, { - "epoch": 0.52, - "learning_rate": 2.3883906551275727e-05, - "loss": 0.18, + "epoch": 0.26, + "learning_rate": 3.697132055211293e-05, + "loss": 0.1869, "step": 117530 }, { - "epoch": 0.52, - "learning_rate": 2.3881664499349806e-05, - "loss": 0.1824, + "epoch": 0.26, + "learning_rate": 3.69702020089036e-05, + "loss": 0.1907, "step": 117540 }, { - "epoch": 0.52, - "learning_rate": 2.387942244742388e-05, - "loss": 0.1901, + "epoch": 0.26, + "learning_rate": 3.696908346569428e-05, + "loss": 0.1879, "step": 117550 }, { - "epoch": 0.52, - "learning_rate": 2.387718039549796e-05, - "loss": 0.1789, + "epoch": 0.26, + "learning_rate": 3.696796492248496e-05, + "loss": 0.1866, "step": 117560 }, { - "epoch": 0.52, - "learning_rate": 2.387493834357204e-05, - "loss": 0.1822, + "epoch": 0.26, + "learning_rate": 3.696684637927563e-05, + "loss": 0.1925, "step": 117570 }, { - "epoch": 0.52, - "learning_rate": 2.3872696291646117e-05, - "loss": 0.1815, + "epoch": 0.26, + "learning_rate": 3.696572783606631e-05, + "loss": 0.1879, "step": 117580 }, { - "epoch": 0.52, - "learning_rate": 2.3870454239720196e-05, - "loss": 0.1845, + "epoch": 0.26, + "learning_rate": 3.6964609292856986e-05, + "loss": 0.1883, "step": 117590 }, { - "epoch": 0.52, - "learning_rate": 2.386821218779427e-05, - "loss": 0.1793, + "epoch": 0.26, + "learning_rate": 3.6963490749647664e-05, + "loss": 0.1901, "step": 117600 }, { - "epoch": 0.53, - "learning_rate": 2.386597013586835e-05, - "loss": 0.1861, + "epoch": 0.26, + "learning_rate": 3.6962372206438335e-05, + "loss": 0.1891, "step": 117610 }, { - "epoch": 0.53, - "learning_rate": 2.3863728083942425e-05, - "loss": 0.1886, + "epoch": 0.26, + "learning_rate": 3.696125366322901e-05, + "loss": 0.1889, "step": 117620 }, { - "epoch": 0.53, - "learning_rate": 2.3861486032016504e-05, - "loss": 0.1796, + "epoch": 0.26, + "learning_rate": 3.696013512001969e-05, + "loss": 0.1882, "step": 117630 }, { - "epoch": 0.53, - "learning_rate": 2.385924398009058e-05, - "loss": 0.1834, + "epoch": 0.26, + "learning_rate": 3.695901657681036e-05, + "loss": 0.1953, "step": 117640 }, { - "epoch": 0.53, - "learning_rate": 2.3857001928164658e-05, - "loss": 0.1855, + "epoch": 0.26, + "learning_rate": 3.695789803360104e-05, + "loss": 0.191, "step": 117650 }, { - "epoch": 0.53, - "learning_rate": 2.3854759876238737e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.695677949039171e-05, + "loss": 0.1886, "step": 117660 }, { - "epoch": 0.53, - "learning_rate": 2.3852517824312812e-05, - "loss": 0.1882, + "epoch": 0.26, + "learning_rate": 3.695566094718239e-05, + "loss": 0.1847, "step": 117670 }, { - "epoch": 0.53, - "learning_rate": 2.385027577238689e-05, - "loss": 0.1893, + "epoch": 0.26, + "learning_rate": 3.695454240397307e-05, + "loss": 0.1906, "step": 117680 }, { - "epoch": 0.53, - "learning_rate": 2.3848033720460966e-05, - "loss": 0.1797, + "epoch": 0.26, + "learning_rate": 3.6953423860763745e-05, + "loss": 0.1941, "step": 117690 }, { - "epoch": 0.53, - "learning_rate": 2.3845791668535045e-05, - "loss": 0.1853, + "epoch": 0.26, + "learning_rate": 3.695230531755442e-05, + "loss": 0.1909, "step": 117700 }, { - "epoch": 0.53, - "learning_rate": 2.384354961660912e-05, - "loss": 0.1857, + "epoch": 0.26, + "learning_rate": 3.6951186774345094e-05, + "loss": 0.1878, "step": 117710 }, { - "epoch": 0.53, - "learning_rate": 2.38413075646832e-05, - "loss": 0.1885, + "epoch": 0.26, + "learning_rate": 3.695006823113577e-05, + "loss": 0.1864, "step": 117720 }, { - "epoch": 0.53, - "learning_rate": 2.3839065512757278e-05, - "loss": 0.1854, + "epoch": 0.26, + "learning_rate": 3.694894968792645e-05, + "loss": 0.1924, "step": 117730 }, { - "epoch": 0.53, - "learning_rate": 2.3836823460831353e-05, - "loss": 0.1817, + "epoch": 0.26, + "learning_rate": 3.694783114471712e-05, + "loss": 0.1943, "step": 117740 }, { - "epoch": 0.53, - "learning_rate": 2.383458140890543e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.69467126015078e-05, + "loss": 0.1918, "step": 117750 }, { - "epoch": 0.53, - "learning_rate": 2.3832339356979507e-05, - "loss": 0.1809, + "epoch": 0.26, + "learning_rate": 3.694559405829847e-05, + "loss": 0.1888, "step": 117760 }, { - "epoch": 0.53, - "learning_rate": 2.3830097305053586e-05, - "loss": 0.1797, + "epoch": 0.26, + "learning_rate": 3.694447551508915e-05, + "loss": 0.1946, "step": 117770 }, { - "epoch": 0.53, - "learning_rate": 2.382785525312766e-05, - "loss": 0.1903, + "epoch": 0.26, + "learning_rate": 3.6943356971879826e-05, + "loss": 0.1867, "step": 117780 }, { - "epoch": 0.53, - "learning_rate": 2.382561320120174e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.69422384286705e-05, + "loss": 0.1845, "step": 117790 }, { - "epoch": 0.53, - "learning_rate": 2.382337114927582e-05, - "loss": 0.1799, + "epoch": 0.26, + "learning_rate": 3.694111988546118e-05, + "loss": 0.1872, "step": 117800 }, { - "epoch": 0.53, - "learning_rate": 2.3821129097349894e-05, - "loss": 0.1833, + "epoch": 0.26, + "learning_rate": 3.6940113196572784e-05, + "loss": 0.1933, "step": 117810 }, { - "epoch": 0.53, - "learning_rate": 2.3818887045423972e-05, - "loss": 0.182, + "epoch": 0.26, + "learning_rate": 3.693899465336346e-05, + "loss": 0.1885, "step": 117820 }, { - "epoch": 0.53, - "learning_rate": 2.381664499349805e-05, - "loss": 0.1813, + "epoch": 0.26, + "learning_rate": 3.693787611015413e-05, + "loss": 0.1931, "step": 117830 }, { - "epoch": 0.53, - "learning_rate": 2.3814402941572126e-05, - "loss": 0.1849, + "epoch": 0.26, + "learning_rate": 3.693675756694481e-05, + "loss": 0.1887, "step": 117840 }, { - "epoch": 0.53, - "learning_rate": 2.3812160889646205e-05, - "loss": 0.183, + "epoch": 0.26, + "learning_rate": 3.693563902373549e-05, + "loss": 0.1849, "step": 117850 }, { - "epoch": 0.53, - "learning_rate": 2.3809918837720284e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.693452048052617e-05, + "loss": 0.1886, "step": 117860 }, { - "epoch": 0.53, - "learning_rate": 2.3807676785794363e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.6933401937316845e-05, + "loss": 0.1896, "step": 117870 }, { - "epoch": 0.53, - "learning_rate": 2.3805434733868438e-05, - "loss": 0.1801, + "epoch": 0.26, + "learning_rate": 3.6932283394107516e-05, + "loss": 0.1906, "step": 117880 }, { - "epoch": 0.53, - "learning_rate": 2.3803192681942517e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.6931164850898194e-05, + "loss": 0.1899, "step": 117890 }, { - "epoch": 0.53, - "learning_rate": 2.3800950630016592e-05, - "loss": 0.1874, + "epoch": 0.26, + "learning_rate": 3.693004630768887e-05, + "loss": 0.1929, "step": 117900 }, { - "epoch": 0.53, - "learning_rate": 2.379870857809067e-05, - "loss": 0.1843, + "epoch": 0.26, + "learning_rate": 3.692892776447954e-05, + "loss": 0.1936, "step": 117910 }, { - "epoch": 0.53, - "learning_rate": 2.379646652616475e-05, - "loss": 0.1857, + "epoch": 0.26, + "learning_rate": 3.692780922127022e-05, + "loss": 0.1919, "step": 117920 }, { - "epoch": 0.53, - "learning_rate": 2.3794224474238825e-05, - "loss": 0.1854, + "epoch": 0.26, + "learning_rate": 3.692669067806089e-05, + "loss": 0.1927, "step": 117930 }, { - "epoch": 0.53, - "learning_rate": 2.3791982422312903e-05, - "loss": 0.1808, + "epoch": 0.26, + "learning_rate": 3.692557213485157e-05, + "loss": 0.1868, "step": 117940 }, { - "epoch": 0.53, - "learning_rate": 2.378974037038698e-05, - "loss": 0.1881, + "epoch": 0.26, + "learning_rate": 3.692445359164225e-05, + "loss": 0.1921, "step": 117950 }, { - "epoch": 0.53, - "learning_rate": 2.3787498318461058e-05, - "loss": 0.1869, + "epoch": 0.26, + "learning_rate": 3.692333504843292e-05, + "loss": 0.1914, "step": 117960 }, { - "epoch": 0.53, - "learning_rate": 2.3785256266535133e-05, - "loss": 0.18, + "epoch": 0.26, + "learning_rate": 3.6922216505223604e-05, + "loss": 0.1818, "step": 117970 }, { - "epoch": 0.53, - "learning_rate": 2.378301421460921e-05, - "loss": 0.1781, + "epoch": 0.26, + "learning_rate": 3.6921097962014275e-05, + "loss": 0.1833, "step": 117980 }, { - "epoch": 0.53, - "learning_rate": 2.378077216268329e-05, - "loss": 0.1852, + "epoch": 0.26, + "learning_rate": 3.691997941880495e-05, + "loss": 0.1891, "step": 117990 }, { - "epoch": 0.53, - "learning_rate": 2.3778530110757366e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.6918860875595624e-05, + "loss": 0.1874, "step": 118000 }, { - "epoch": 0.53, - "learning_rate": 2.3776288058831444e-05, - "loss": 0.1819, + "epoch": 0.26, + "learning_rate": 3.69177423323863e-05, + "loss": 0.1895, "step": 118010 }, { - "epoch": 0.53, - "learning_rate": 2.377404600690552e-05, - "loss": 0.1807, + "epoch": 0.26, + "learning_rate": 3.691662378917698e-05, + "loss": 0.1924, "step": 118020 }, { - "epoch": 0.53, - "learning_rate": 2.37718039549796e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.691550524596765e-05, + "loss": 0.1879, "step": 118030 }, { - "epoch": 0.53, - "learning_rate": 2.3769561903053674e-05, - "loss": 0.1875, + "epoch": 0.26, + "learning_rate": 3.691438670275833e-05, + "loss": 0.1911, "step": 118040 }, { - "epoch": 0.53, - "learning_rate": 2.3767319851127752e-05, - "loss": 0.1908, + "epoch": 0.26, + "learning_rate": 3.6913268159549e-05, + "loss": 0.1901, "step": 118050 }, { - "epoch": 0.53, - "learning_rate": 2.376507779920183e-05, - "loss": 0.1876, + "epoch": 0.26, + "learning_rate": 3.691214961633968e-05, + "loss": 0.1881, "step": 118060 }, { - "epoch": 0.53, - "learning_rate": 2.3762835747275906e-05, - "loss": 0.1816, + "epoch": 0.26, + "learning_rate": 3.6911031073130356e-05, + "loss": 0.1871, "step": 118070 }, { - "epoch": 0.53, - "learning_rate": 2.3760593695349985e-05, - "loss": 0.18, + "epoch": 0.26, + "learning_rate": 3.6909912529921034e-05, + "loss": 0.1856, "step": 118080 }, { - "epoch": 0.53, - "learning_rate": 2.375835164342406e-05, - "loss": 0.1864, + "epoch": 0.26, + "learning_rate": 3.690879398671171e-05, + "loss": 0.1912, "step": 118090 }, { - "epoch": 0.53, - "learning_rate": 2.375610959149814e-05, - "loss": 0.1848, + "epoch": 0.26, + "learning_rate": 3.690767544350238e-05, + "loss": 0.1887, "step": 118100 }, { - "epoch": 0.53, - "learning_rate": 2.3753867539572218e-05, - "loss": 0.1858, + "epoch": 0.26, + "learning_rate": 3.690655690029306e-05, + "loss": 0.1901, "step": 118110 }, { - "epoch": 0.53, - "learning_rate": 2.3751625487646297e-05, - "loss": 0.1845, + "epoch": 0.26, + "learning_rate": 3.690543835708374e-05, + "loss": 0.1891, "step": 118120 }, { - "epoch": 0.53, - "learning_rate": 2.3749383435720375e-05, - "loss": 0.1776, + "epoch": 0.26, + "learning_rate": 3.690431981387441e-05, + "loss": 0.1869, "step": 118130 }, { - "epoch": 0.53, - "learning_rate": 2.374714138379445e-05, - "loss": 0.1785, + "epoch": 0.26, + "learning_rate": 3.690320127066509e-05, + "loss": 0.1835, "step": 118140 }, { - "epoch": 0.53, - "learning_rate": 2.374489933186853e-05, - "loss": 0.184, + "epoch": 0.26, + "learning_rate": 3.690208272745576e-05, + "loss": 0.1885, "step": 118150 }, { - "epoch": 0.53, - "learning_rate": 2.3742657279942605e-05, - "loss": 0.1838, + "epoch": 0.26, + "learning_rate": 3.690096418424644e-05, + "loss": 0.1881, "step": 118160 }, { - "epoch": 0.53, - "learning_rate": 2.3740415228016684e-05, - "loss": 0.1826, + "epoch": 0.26, + "learning_rate": 3.6899845641037115e-05, + "loss": 0.1918, "step": 118170 }, { - "epoch": 0.53, - "learning_rate": 2.373817317609076e-05, - "loss": 0.187, + "epoch": 0.26, + "learning_rate": 3.689872709782779e-05, + "loss": 0.1915, "step": 118180 }, { - "epoch": 0.53, - "learning_rate": 2.3735931124164838e-05, - "loss": 0.1845, + "epoch": 0.26, + "learning_rate": 3.689760855461847e-05, + "loss": 0.1979, "step": 118190 }, { - "epoch": 0.53, - "learning_rate": 2.3733689072238916e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.689649001140914e-05, + "loss": 0.1913, "step": 118200 }, { - "epoch": 0.53, - "learning_rate": 2.373144702031299e-05, - "loss": 0.182, + "epoch": 0.26, + "learning_rate": 3.689537146819982e-05, + "loss": 0.1902, "step": 118210 }, { - "epoch": 0.53, - "learning_rate": 2.372920496838707e-05, - "loss": 0.1901, + "epoch": 0.26, + "learning_rate": 3.68942529249905e-05, + "loss": 0.19, "step": 118220 }, { - "epoch": 0.53, - "learning_rate": 2.3726962916461146e-05, - "loss": 0.1886, + "epoch": 0.26, + "learning_rate": 3.689313438178117e-05, + "loss": 0.1962, "step": 118230 }, { - "epoch": 0.53, - "learning_rate": 2.3724720864535224e-05, - "loss": 0.1862, + "epoch": 0.26, + "learning_rate": 3.6892015838571847e-05, + "loss": 0.188, "step": 118240 }, { - "epoch": 0.53, - "learning_rate": 2.37224788126093e-05, - "loss": 0.1845, + "epoch": 0.26, + "learning_rate": 3.689089729536252e-05, + "loss": 0.1928, "step": 118250 }, { - "epoch": 0.53, - "learning_rate": 2.372023676068338e-05, - "loss": 0.1853, + "epoch": 0.26, + "learning_rate": 3.6889778752153196e-05, + "loss": 0.1906, "step": 118260 }, { - "epoch": 0.53, - "learning_rate": 2.3717994708757457e-05, - "loss": 0.1813, + "epoch": 0.26, + "learning_rate": 3.6888660208943874e-05, + "loss": 0.191, "step": 118270 }, { - "epoch": 0.53, - "learning_rate": 2.3715752656831532e-05, - "loss": 0.1802, + "epoch": 0.26, + "learning_rate": 3.688754166573455e-05, + "loss": 0.1922, "step": 118280 }, { - "epoch": 0.53, - "learning_rate": 2.371351060490561e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.688642312252523e-05, + "loss": 0.1887, "step": 118290 }, { - "epoch": 0.53, - "learning_rate": 2.3711268552979687e-05, - "loss": 0.1786, + "epoch": 0.26, + "learning_rate": 3.68853045793159e-05, + "loss": 0.1908, "step": 118300 }, { - "epoch": 0.53, - "learning_rate": 2.3709026501053765e-05, - "loss": 0.1894, + "epoch": 0.26, + "learning_rate": 3.688418603610658e-05, + "loss": 0.1947, "step": 118310 }, { - "epoch": 0.53, - "learning_rate": 2.370678444912784e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.688306749289725e-05, + "loss": 0.1942, "step": 118320 }, { - "epoch": 0.53, - "learning_rate": 2.370454239720192e-05, - "loss": 0.1807, + "epoch": 0.26, + "learning_rate": 3.688194894968793e-05, + "loss": 0.1831, "step": 118330 }, { - "epoch": 0.53, - "learning_rate": 2.3702300345275998e-05, - "loss": 0.1877, + "epoch": 0.26, + "learning_rate": 3.6880830406478606e-05, + "loss": 0.1878, "step": 118340 }, { - "epoch": 0.53, - "learning_rate": 2.3700058293350073e-05, - "loss": 0.1813, + "epoch": 0.26, + "learning_rate": 3.687971186326928e-05, + "loss": 0.1902, "step": 118350 }, { - "epoch": 0.53, - "learning_rate": 2.3697816241424152e-05, - "loss": 0.1873, + "epoch": 0.26, + "learning_rate": 3.6878593320059955e-05, + "loss": 0.1898, "step": 118360 }, { - "epoch": 0.53, - "learning_rate": 2.369557418949823e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.6877474776850626e-05, + "loss": 0.1911, "step": 118370 }, { - "epoch": 0.53, - "learning_rate": 2.3693332137572306e-05, - "loss": 0.1824, + "epoch": 0.26, + "learning_rate": 3.687635623364131e-05, + "loss": 0.1941, "step": 118380 }, { - "epoch": 0.53, - "learning_rate": 2.3691090085646385e-05, - "loss": 0.1875, + "epoch": 0.26, + "learning_rate": 3.687523769043199e-05, + "loss": 0.1879, "step": 118390 }, { - "epoch": 0.53, - "learning_rate": 2.3688848033720464e-05, - "loss": 0.1796, + "epoch": 0.26, + "learning_rate": 3.687411914722266e-05, + "loss": 0.1848, "step": 118400 }, { - "epoch": 0.53, - "learning_rate": 2.3686605981794542e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.687300060401334e-05, + "loss": 0.1854, "step": 118410 }, { - "epoch": 0.53, - "learning_rate": 2.3684363929868618e-05, - "loss": 0.1846, + "epoch": 0.26, + "learning_rate": 3.687188206080401e-05, + "loss": 0.1882, "step": 118420 }, { - "epoch": 0.53, - "learning_rate": 2.3682121877942696e-05, - "loss": 0.1839, + "epoch": 0.26, + "learning_rate": 3.6870763517594687e-05, + "loss": 0.1849, "step": 118430 }, { - "epoch": 0.53, - "learning_rate": 2.367987982601677e-05, - "loss": 0.1872, - "step": 118440 + "epoch": 0.26, + "learning_rate": 3.6869644974385364e-05, + "loss": 0.1897, + "step": 118440 }, { - "epoch": 0.53, - "learning_rate": 2.367763777409085e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.6868526431176036e-05, + "loss": 0.1819, "step": 118450 }, { - "epoch": 0.53, - "learning_rate": 2.3675395722164926e-05, - "loss": 0.1816, + "epoch": 0.26, + "learning_rate": 3.6867407887966714e-05, + "loss": 0.1888, "step": 118460 }, { - "epoch": 0.53, - "learning_rate": 2.3673153670239004e-05, - "loss": 0.1842, + "epoch": 0.26, + "learning_rate": 3.6866289344757385e-05, + "loss": 0.185, "step": 118470 }, { - "epoch": 0.53, - "learning_rate": 2.3670911618313083e-05, - "loss": 0.1902, + "epoch": 0.26, + "learning_rate": 3.686517080154806e-05, + "loss": 0.1885, "step": 118480 }, { - "epoch": 0.53, - "learning_rate": 2.366866956638716e-05, - "loss": 0.1775, + "epoch": 0.26, + "learning_rate": 3.686405225833874e-05, + "loss": 0.196, "step": 118490 }, { - "epoch": 0.53, - "learning_rate": 2.3666427514461237e-05, - "loss": 0.1799, + "epoch": 0.26, + "learning_rate": 3.686293371512942e-05, + "loss": 0.1908, "step": 118500 }, { - "epoch": 0.53, - "learning_rate": 2.3664185462535312e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.6861815171920096e-05, + "loss": 0.1859, "step": 118510 }, { - "epoch": 0.53, - "learning_rate": 2.366194341060939e-05, - "loss": 0.1794, + "epoch": 0.26, + "learning_rate": 3.686069662871077e-05, + "loss": 0.1855, "step": 118520 }, { - "epoch": 0.53, - "learning_rate": 2.3659701358683467e-05, - "loss": 0.1855, + "epoch": 0.26, + "learning_rate": 3.6859578085501445e-05, + "loss": 0.1879, "step": 118530 }, { - "epoch": 0.53, - "learning_rate": 2.3657459306757545e-05, - "loss": 0.1847, + "epoch": 0.26, + "learning_rate": 3.6858459542292123e-05, + "loss": 0.1911, "step": 118540 }, { - "epoch": 0.53, - "learning_rate": 2.3655217254831624e-05, - "loss": 0.1863, + "epoch": 0.26, + "learning_rate": 3.6857340999082795e-05, + "loss": 0.1854, "step": 118550 }, { - "epoch": 0.53, - "learning_rate": 2.36529752029057e-05, - "loss": 0.1822, + "epoch": 0.26, + "learning_rate": 3.685622245587347e-05, + "loss": 0.1837, "step": 118560 }, { - "epoch": 0.53, - "learning_rate": 2.3650733150979778e-05, - "loss": 0.185, + "epoch": 0.26, + "learning_rate": 3.6855103912664144e-05, + "loss": 0.1874, "step": 118570 }, { - "epoch": 0.53, - "learning_rate": 2.3648491099053853e-05, - "loss": 0.1884, + "epoch": 0.26, + "learning_rate": 3.685398536945482e-05, + "loss": 0.1865, "step": 118580 }, { - "epoch": 0.53, - "learning_rate": 2.3646249047127932e-05, - "loss": 0.1851, + "epoch": 0.26, + "learning_rate": 3.68528668262455e-05, + "loss": 0.1909, "step": 118590 }, { - "epoch": 0.53, - "learning_rate": 2.3644006995202007e-05, - "loss": 0.1812, + "epoch": 0.26, + "learning_rate": 3.685174828303618e-05, + "loss": 0.1842, "step": 118600 }, { - "epoch": 0.53, - "learning_rate": 2.3641764943276086e-05, - "loss": 0.1835, + "epoch": 0.26, + "learning_rate": 3.6850629739826855e-05, + "loss": 0.1833, "step": 118610 }, { - "epoch": 0.53, - "learning_rate": 2.3639522891350165e-05, - "loss": 0.1842, + "epoch": 0.26, + "learning_rate": 3.6849511196617527e-05, + "loss": 0.1887, "step": 118620 }, { - "epoch": 0.53, - "learning_rate": 2.363728083942424e-05, - "loss": 0.1821, + "epoch": 0.26, + "learning_rate": 3.6848392653408204e-05, + "loss": 0.1868, "step": 118630 }, { - "epoch": 0.53, - "learning_rate": 2.363503878749832e-05, - "loss": 0.1798, + "epoch": 0.26, + "learning_rate": 3.6847274110198876e-05, + "loss": 0.1898, "step": 118640 }, { - "epoch": 0.53, - "learning_rate": 2.3632796735572398e-05, - "loss": 0.1836, + "epoch": 0.26, + "learning_rate": 3.6846155566989554e-05, + "loss": 0.1907, "step": 118650 }, { - "epoch": 0.53, - "learning_rate": 2.3630554683646476e-05, - "loss": 0.1818, + "epoch": 0.26, + "learning_rate": 3.684503702378023e-05, + "loss": 0.1891, "step": 118660 }, { - "epoch": 0.53, - "learning_rate": 2.362831263172055e-05, - "loss": 0.1856, + "epoch": 0.26, + "learning_rate": 3.68439184805709e-05, + "loss": 0.1866, "step": 118670 }, { - "epoch": 0.53, - "learning_rate": 2.362607057979463e-05, - "loss": 0.1866, + "epoch": 0.26, + "learning_rate": 3.684279993736158e-05, + "loss": 0.1891, "step": 118680 }, { - "epoch": 0.53, - "learning_rate": 2.362382852786871e-05, - "loss": 0.1865, + "epoch": 0.26, + "learning_rate": 3.684168139415226e-05, + "loss": 0.1878, "step": 118690 }, { - "epoch": 0.53, - "learning_rate": 2.3621586475942784e-05, - "loss": 0.1825, + "epoch": 0.26, + "learning_rate": 3.6840562850942936e-05, + "loss": 0.1871, "step": 118700 }, { - "epoch": 0.53, - "learning_rate": 2.3619344424016863e-05, - "loss": 0.1823, + "epoch": 0.26, + "learning_rate": 3.6839444307733614e-05, + "loss": 0.1868, "step": 118710 }, { - "epoch": 0.53, - "learning_rate": 2.361710237209094e-05, - "loss": 0.1841, + "epoch": 0.26, + "learning_rate": 3.6838325764524285e-05, + "loss": 0.1886, "step": 118720 }, { - "epoch": 0.53, - "learning_rate": 2.3614860320165017e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.683720722131496e-05, + "loss": 0.1865, "step": 118730 }, { - "epoch": 0.53, - "learning_rate": 2.3612618268239092e-05, - "loss": 0.1793, + "epoch": 0.27, + "learning_rate": 3.6836088678105635e-05, + "loss": 0.1903, "step": 118740 }, { - "epoch": 0.53, - "learning_rate": 2.361037621631317e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.683497013489631e-05, + "loss": 0.1925, "step": 118750 }, { - "epoch": 0.53, - "learning_rate": 2.360813416438725e-05, - "loss": 0.1872, + "epoch": 0.27, + "learning_rate": 3.683385159168699e-05, + "loss": 0.1826, "step": 118760 }, { - "epoch": 0.53, - "learning_rate": 2.3605892112461325e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.683273304847766e-05, + "loss": 0.1865, "step": 118770 }, { - "epoch": 0.53, - "learning_rate": 2.3603650060535404e-05, - "loss": 0.1841, + "epoch": 0.27, + "learning_rate": 3.683161450526834e-05, + "loss": 0.1964, "step": 118780 }, { - "epoch": 0.53, - "learning_rate": 2.360140800860948e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.683049596205901e-05, + "loss": 0.1892, "step": 118790 }, { - "epoch": 0.53, - "learning_rate": 2.3599165956683558e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.6829377418849695e-05, + "loss": 0.1839, "step": 118800 }, { - "epoch": 0.53, - "learning_rate": 2.3596923904757633e-05, - "loss": 0.1862, + "epoch": 0.27, + "learning_rate": 3.682825887564037e-05, + "loss": 0.1911, "step": 118810 }, { - "epoch": 0.53, - "learning_rate": 2.3594681852831712e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.6827140332431044e-05, + "loss": 0.1897, "step": 118820 }, { - "epoch": 0.53, - "learning_rate": 2.359243980090579e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.682602178922172e-05, + "loss": 0.191, "step": 118830 }, { - "epoch": 0.53, - "learning_rate": 2.3590197748979866e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.6824903246012393e-05, + "loss": 0.1843, "step": 118840 }, { - "epoch": 0.53, - "learning_rate": 2.3587955697053945e-05, - "loss": 0.1889, + "epoch": 0.27, + "learning_rate": 3.682378470280307e-05, + "loss": 0.1876, "step": 118850 }, { - "epoch": 0.53, - "learning_rate": 2.358571364512802e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.682266615959375e-05, + "loss": 0.1931, "step": 118860 }, { - "epoch": 0.53, - "learning_rate": 2.35834715932021e-05, - "loss": 0.188, + "epoch": 0.27, + "learning_rate": 3.682154761638442e-05, + "loss": 0.1902, "step": 118870 }, { - "epoch": 0.53, - "learning_rate": 2.3581229541276174e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.68204290731751e-05, + "loss": 0.186, "step": 118880 }, { - "epoch": 0.53, - "learning_rate": 2.3578987489350253e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.681931052996577e-05, + "loss": 0.1884, "step": 118890 }, { - "epoch": 0.53, - "learning_rate": 2.357674543742433e-05, - "loss": 0.1819, + "epoch": 0.27, + "learning_rate": 3.681819198675645e-05, + "loss": 0.1846, "step": 118900 }, { - "epoch": 0.53, - "learning_rate": 2.357450338549841e-05, - "loss": 0.1877, + "epoch": 0.27, + "learning_rate": 3.6817073443547125e-05, + "loss": 0.1876, "step": 118910 }, { - "epoch": 0.53, - "learning_rate": 2.3572261333572486e-05, - "loss": 0.1914, + "epoch": 0.27, + "learning_rate": 3.68159549003378e-05, + "loss": 0.1884, "step": 118920 }, { - "epoch": 0.53, - "learning_rate": 2.3570019281646564e-05, - "loss": 0.1841, + "epoch": 0.27, + "learning_rate": 3.681483635712848e-05, + "loss": 0.186, "step": 118930 }, { - "epoch": 0.53, - "learning_rate": 2.3567777229720643e-05, - "loss": 0.1883, + "epoch": 0.27, + "learning_rate": 3.681371781391915e-05, + "loss": 0.1894, "step": 118940 }, { - "epoch": 0.53, - "learning_rate": 2.356553517779472e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.681259927070983e-05, + "loss": 0.1868, "step": 118950 }, { - "epoch": 0.53, - "learning_rate": 2.3563293125868797e-05, - "loss": 0.1791, + "epoch": 0.27, + "learning_rate": 3.68114807275005e-05, + "loss": 0.1882, "step": 118960 }, { - "epoch": 0.53, - "learning_rate": 2.3561051073942876e-05, - "loss": 0.1848, + "epoch": 0.27, + "learning_rate": 3.681036218429118e-05, + "loss": 0.1895, "step": 118970 }, { - "epoch": 0.53, - "learning_rate": 2.355880902201695e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.680924364108186e-05, + "loss": 0.1904, "step": 118980 }, { - "epoch": 0.53, - "learning_rate": 2.355656697009103e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.680812509787253e-05, + "loss": 0.1893, "step": 118990 }, { - "epoch": 0.53, - "learning_rate": 2.3554324918165105e-05, - "loss": 0.1875, + "epoch": 0.27, + "learning_rate": 3.6807006554663206e-05, + "loss": 0.1884, "step": 119000 }, { - "epoch": 0.53, - "learning_rate": 2.3552082866239184e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.6805888011453884e-05, + "loss": 0.1906, "step": 119010 }, { - "epoch": 0.53, - "learning_rate": 2.354984081431326e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.680476946824456e-05, + "loss": 0.196, "step": 119020 }, { - "epoch": 0.53, - "learning_rate": 2.3547598762387338e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.680365092503524e-05, + "loss": 0.1871, "step": 119030 }, { - "epoch": 0.53, - "learning_rate": 2.3545356710461417e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.680253238182591e-05, + "loss": 0.1835, "step": 119040 }, { - "epoch": 0.53, - "learning_rate": 2.3543114658535492e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.680141383861659e-05, + "loss": 0.1891, "step": 119050 }, { - "epoch": 0.53, - "learning_rate": 2.354087260660957e-05, - "loss": 0.1814, + "epoch": 0.27, + "learning_rate": 3.680029529540726e-05, + "loss": 0.1898, "step": 119060 }, { - "epoch": 0.53, - "learning_rate": 2.3538630554683646e-05, - "loss": 0.1837, + "epoch": 0.27, + "learning_rate": 3.679917675219794e-05, + "loss": 0.1907, "step": 119070 }, { - "epoch": 0.53, - "learning_rate": 2.3536388502757725e-05, - "loss": 0.1872, + "epoch": 0.27, + "learning_rate": 3.6798058208988616e-05, + "loss": 0.1931, "step": 119080 }, { - "epoch": 0.53, - "learning_rate": 2.35341464508318e-05, - "loss": 0.1871, + "epoch": 0.27, + "learning_rate": 3.679693966577929e-05, + "loss": 0.1865, "step": 119090 }, { - "epoch": 0.53, - "learning_rate": 2.353190439890588e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.6795821122569965e-05, + "loss": 0.1942, "step": 119100 }, { - "epoch": 0.53, - "learning_rate": 2.3529662346979958e-05, - "loss": 0.1741, + "epoch": 0.27, + "learning_rate": 3.679470257936064e-05, + "loss": 0.1914, "step": 119110 }, { - "epoch": 0.53, - "learning_rate": 2.3527420295054033e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.679358403615132e-05, + "loss": 0.194, "step": 119120 }, { - "epoch": 0.53, - "learning_rate": 2.352517824312811e-05, - "loss": 0.1803, + "epoch": 0.27, + "learning_rate": 3.6792465492942e-05, + "loss": 0.1885, "step": 119130 }, { - "epoch": 0.53, - "learning_rate": 2.3522936191202187e-05, - "loss": 0.1886, + "epoch": 0.27, + "learning_rate": 3.679134694973267e-05, + "loss": 0.1877, "step": 119140 }, { - "epoch": 0.53, - "learning_rate": 2.3520694139276266e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.679022840652335e-05, + "loss": 0.1882, "step": 119150 }, { - "epoch": 0.53, - "learning_rate": 2.3518452087350344e-05, - "loss": 0.1814, + "epoch": 0.27, + "learning_rate": 3.678910986331402e-05, + "loss": 0.1881, "step": 119160 }, { - "epoch": 0.53, - "learning_rate": 2.351621003542442e-05, - "loss": 0.1784, + "epoch": 0.27, + "learning_rate": 3.67879913201047e-05, + "loss": 0.1884, "step": 119170 }, { - "epoch": 0.53, - "learning_rate": 2.35139679834985e-05, - "loss": 0.1842, + "epoch": 0.27, + "learning_rate": 3.6786872776895375e-05, + "loss": 0.1886, "step": 119180 }, { - "epoch": 0.53, - "learning_rate": 2.3511725931572577e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.6785754233686046e-05, + "loss": 0.1924, "step": 119190 }, { - "epoch": 0.53, - "learning_rate": 2.3509483879646656e-05, - "loss": 0.1782, + "epoch": 0.27, + "learning_rate": 3.6784635690476724e-05, + "loss": 0.1899, "step": 119200 }, { - "epoch": 0.53, - "learning_rate": 2.350724182772073e-05, - "loss": 0.1832, + "epoch": 0.27, + "learning_rate": 3.67835171472674e-05, + "loss": 0.1929, "step": 119210 }, { - "epoch": 0.53, - "learning_rate": 2.350499977579481e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.678239860405808e-05, + "loss": 0.1869, "step": 119220 }, { - "epoch": 0.53, - "learning_rate": 2.350275772386889e-05, - "loss": 0.1883, + "epoch": 0.27, + "learning_rate": 3.678128006084876e-05, + "loss": 0.1924, "step": 119230 }, { - "epoch": 0.53, - "learning_rate": 2.3500515671942964e-05, - "loss": 0.1883, + "epoch": 0.27, + "learning_rate": 3.678016151763943e-05, + "loss": 0.1843, "step": 119240 }, { - "epoch": 0.53, - "learning_rate": 2.3498273620017043e-05, - "loss": 0.1852, + "epoch": 0.27, + "learning_rate": 3.677904297443011e-05, + "loss": 0.1892, "step": 119250 }, { - "epoch": 0.53, - "learning_rate": 2.3496031568091118e-05, - "loss": 0.1777, + "epoch": 0.27, + "learning_rate": 3.677792443122078e-05, + "loss": 0.1854, "step": 119260 }, { - "epoch": 0.53, - "learning_rate": 2.3493789516165197e-05, - "loss": 0.1848, + "epoch": 0.27, + "learning_rate": 3.6776805888011456e-05, + "loss": 0.1861, "step": 119270 }, { - "epoch": 0.53, - "learning_rate": 2.3491547464239272e-05, - "loss": 0.1868, + "epoch": 0.27, + "learning_rate": 3.677568734480213e-05, + "loss": 0.1909, "step": 119280 }, { - "epoch": 0.53, - "learning_rate": 2.348930541231335e-05, - "loss": 0.1813, + "epoch": 0.27, + "learning_rate": 3.6774568801592805e-05, + "loss": 0.19, "step": 119290 }, { - "epoch": 0.53, - "learning_rate": 2.348706336038743e-05, - "loss": 0.1847, + "epoch": 0.27, + "learning_rate": 3.677345025838348e-05, + "loss": 0.1839, "step": 119300 }, { - "epoch": 0.53, - "learning_rate": 2.3484821308461505e-05, - "loss": 0.191, + "epoch": 0.27, + "learning_rate": 3.6772331715174154e-05, + "loss": 0.1876, "step": 119310 }, { - "epoch": 0.53, - "learning_rate": 2.3482579256535584e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.677121317196483e-05, + "loss": 0.1909, "step": 119320 }, { - "epoch": 0.53, - "learning_rate": 2.348033720460966e-05, - "loss": 0.1801, + "epoch": 0.27, + "learning_rate": 3.677009462875551e-05, + "loss": 0.1871, "step": 119330 }, { - "epoch": 0.53, - "learning_rate": 2.3478095152683738e-05, + "epoch": 0.27, + "learning_rate": 3.676897608554619e-05, "loss": 0.1867, "step": 119340 }, { - "epoch": 0.53, - "learning_rate": 2.3475853100757813e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.6767857542336866e-05, + "loss": 0.1926, "step": 119350 }, { - "epoch": 0.53, - "learning_rate": 2.347361104883189e-05, - "loss": 0.1901, + "epoch": 0.27, + "learning_rate": 3.676673899912754e-05, + "loss": 0.1871, "step": 119360 }, { - "epoch": 0.53, - "learning_rate": 2.347136899690597e-05, - "loss": 0.1791, + "epoch": 0.27, + "learning_rate": 3.6765620455918215e-05, + "loss": 0.189, "step": 119370 }, { - "epoch": 0.53, - "learning_rate": 2.3469126944980046e-05, - "loss": 0.1884, + "epoch": 0.27, + "learning_rate": 3.6764501912708886e-05, + "loss": 0.1868, "step": 119380 }, { - "epoch": 0.53, - "learning_rate": 2.3466884893054124e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.6763383369499564e-05, + "loss": 0.187, "step": 119390 }, { - "epoch": 0.53, - "learning_rate": 2.34646428411282e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.676226482629024e-05, + "loss": 0.1834, "step": 119400 }, { - "epoch": 0.53, - "learning_rate": 2.346240078920228e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.6761146283080913e-05, + "loss": 0.184, "step": 119410 }, { - "epoch": 0.53, - "learning_rate": 2.3460158737276354e-05, - "loss": 0.1835, + "epoch": 0.27, + "learning_rate": 3.676002773987159e-05, + "loss": 0.1898, "step": 119420 }, { - "epoch": 0.53, - "learning_rate": 2.3457916685350433e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.675890919666227e-05, + "loss": 0.1884, "step": 119430 }, { - "epoch": 0.53, - "learning_rate": 2.345567463342451e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.675779065345295e-05, + "loss": 0.1897, "step": 119440 }, { - "epoch": 0.53, - "learning_rate": 2.345343258149859e-05, - "loss": 0.1833, + "epoch": 0.27, + "learning_rate": 3.6756672110243625e-05, + "loss": 0.1879, "step": 119450 }, { - "epoch": 0.53, - "learning_rate": 2.3451190529572665e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.6755553567034296e-05, + "loss": 0.1872, "step": 119460 }, { - "epoch": 0.53, - "learning_rate": 2.3448948477646744e-05, - "loss": 0.1855, + "epoch": 0.27, + "learning_rate": 3.6754435023824974e-05, + "loss": 0.1903, "step": 119470 }, { - "epoch": 0.53, - "learning_rate": 2.3446706425720823e-05, - "loss": 0.1768, + "epoch": 0.27, + "learning_rate": 3.6753316480615645e-05, + "loss": 0.1903, "step": 119480 }, { - "epoch": 0.53, - "learning_rate": 2.3444464373794898e-05, - "loss": 0.1829, + "epoch": 0.27, + "learning_rate": 3.675219793740632e-05, + "loss": 0.1936, "step": 119490 }, { - "epoch": 0.53, - "learning_rate": 2.3442222321868977e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.6751079394197e-05, + "loss": 0.1872, "step": 119500 }, { - "epoch": 0.53, - "learning_rate": 2.3439980269943056e-05, - "loss": 0.1795, + "epoch": 0.27, + "learning_rate": 3.674996085098767e-05, + "loss": 0.1877, "step": 119510 }, { - "epoch": 0.53, - "learning_rate": 2.343773821801713e-05, - "loss": 0.1865, + "epoch": 0.27, + "learning_rate": 3.674884230777835e-05, + "loss": 0.1869, "step": 119520 }, { - "epoch": 0.53, - "learning_rate": 2.343549616609121e-05, - "loss": 0.1822, + "epoch": 0.27, + "learning_rate": 3.674772376456903e-05, + "loss": 0.1884, "step": 119530 }, { - "epoch": 0.53, - "learning_rate": 2.3433254114165285e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.6746605221359706e-05, + "loss": 0.1897, "step": 119540 }, { - "epoch": 0.53, - "learning_rate": 2.3431012062239364e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.6745486678150384e-05, + "loss": 0.1917, "step": 119550 }, { - "epoch": 0.53, - "learning_rate": 2.342877001031344e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.6744368134941055e-05, + "loss": 0.1875, "step": 119560 }, { - "epoch": 0.53, - "learning_rate": 2.3426527958387518e-05, - "loss": 0.1857, + "epoch": 0.27, + "learning_rate": 3.674324959173173e-05, + "loss": 0.1876, "step": 119570 }, { - "epoch": 0.53, - "learning_rate": 2.3424285906461596e-05, - "loss": 0.1869, + "epoch": 0.27, + "learning_rate": 3.6742131048522404e-05, + "loss": 0.1847, "step": 119580 }, { - "epoch": 0.53, - "learning_rate": 2.342204385453567e-05, - "loss": 0.1849, + "epoch": 0.27, + "learning_rate": 3.674101250531308e-05, + "loss": 0.1839, "step": 119590 }, { - "epoch": 0.53, - "learning_rate": 2.341980180260975e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.673989396210375e-05, + "loss": 0.1917, "step": 119600 }, { - "epoch": 0.53, - "learning_rate": 2.3417559750683826e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.673877541889443e-05, + "loss": 0.1889, "step": 119610 }, { - "epoch": 0.53, - "learning_rate": 2.3415317698757904e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.673765687568511e-05, + "loss": 0.1827, "step": 119620 }, { - "epoch": 0.53, - "learning_rate": 2.341307564683198e-05, - "loss": 0.1809, + "epoch": 0.27, + "learning_rate": 3.673653833247579e-05, + "loss": 0.1846, "step": 119630 }, { - "epoch": 0.53, - "learning_rate": 2.341083359490606e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.6735419789266465e-05, + "loss": 0.1885, "step": 119640 }, { - "epoch": 0.53, - "learning_rate": 2.3408591542980137e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.6734301246057136e-05, + "loss": 0.1837, "step": 119650 }, { - "epoch": 0.53, - "learning_rate": 2.3406349491054213e-05, - "loss": 0.1787, + "epoch": 0.27, + "learning_rate": 3.6733182702847814e-05, + "loss": 0.1897, "step": 119660 }, { - "epoch": 0.53, - "learning_rate": 2.340410743912829e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.673206415963849e-05, + "loss": 0.1826, "step": 119670 }, { - "epoch": 0.53, - "learning_rate": 2.3401865387202367e-05, - "loss": 0.1779, + "epoch": 0.27, + "learning_rate": 3.673094561642916e-05, + "loss": 0.1863, "step": 119680 }, { - "epoch": 0.53, - "learning_rate": 2.3399623335276445e-05, - "loss": 0.1847, + "epoch": 0.27, + "learning_rate": 3.672982707321984e-05, + "loss": 0.1887, "step": 119690 }, { - "epoch": 0.53, - "learning_rate": 2.3397381283350524e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.672870853001051e-05, + "loss": 0.195, "step": 119700 }, { - "epoch": 0.53, - "learning_rate": 2.33951392314246e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.672758998680119e-05, + "loss": 0.1797, "step": 119710 }, { - "epoch": 0.53, - "learning_rate": 2.3392897179498678e-05, - "loss": 0.1858, + "epoch": 0.27, + "learning_rate": 3.672647144359187e-05, + "loss": 0.1927, "step": 119720 }, { - "epoch": 0.53, - "learning_rate": 2.3390655127572757e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.672535290038254e-05, + "loss": 0.1857, "step": 119730 }, { - "epoch": 0.53, - "learning_rate": 2.3388413075646836e-05, - "loss": 0.1871, + "epoch": 0.27, + "learning_rate": 3.672423435717322e-05, + "loss": 0.1921, "step": 119740 }, { - "epoch": 0.53, - "learning_rate": 2.338617102372091e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.6723115813963895e-05, + "loss": 0.1949, "step": 119750 }, { - "epoch": 0.53, - "learning_rate": 2.338392897179499e-05, - "loss": 0.1829, + "epoch": 0.27, + "learning_rate": 3.672199727075457e-05, + "loss": 0.1913, "step": 119760 }, { - "epoch": 0.53, - "learning_rate": 2.3381686919869065e-05, - "loss": 0.1852, + "epoch": 0.27, + "learning_rate": 3.672087872754525e-05, + "loss": 0.1858, "step": 119770 }, { - "epoch": 0.53, - "learning_rate": 2.3379444867943144e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.671976018433592e-05, + "loss": 0.1891, "step": 119780 }, { - "epoch": 0.53, - "learning_rate": 2.3377202816017222e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.67186416411266e-05, + "loss": 0.1842, "step": 119790 }, { - "epoch": 0.53, - "learning_rate": 2.3374960764091298e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.671752309791727e-05, + "loss": 0.1888, "step": 119800 }, { - "epoch": 0.53, - "learning_rate": 2.3372718712165376e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.671640455470795e-05, + "loss": 0.1862, "step": 119810 }, { - "epoch": 0.53, - "learning_rate": 2.3370476660239452e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.671528601149863e-05, + "loss": 0.1885, "step": 119820 }, { - "epoch": 0.53, - "learning_rate": 2.336823460831353e-05, - "loss": 0.1837, + "epoch": 0.27, + "learning_rate": 3.6714279322610236e-05, + "loss": 0.1818, "step": 119830 }, { - "epoch": 0.53, - "learning_rate": 2.3365992556387606e-05, - "loss": 0.1837, + "epoch": 0.27, + "learning_rate": 3.6713160779400914e-05, + "loss": 0.1854, "step": 119840 }, { - "epoch": 0.54, - "learning_rate": 2.3363750504461684e-05, - "loss": 0.1786, + "epoch": 0.27, + "learning_rate": 3.6712042236191585e-05, + "loss": 0.1839, "step": 119850 }, { - "epoch": 0.54, - "learning_rate": 2.3361508452535763e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.671092369298226e-05, + "loss": 0.1909, "step": 119860 }, { - "epoch": 0.54, - "learning_rate": 2.335926640060984e-05, - "loss": 0.1764, + "epoch": 0.27, + "learning_rate": 3.6709805149772934e-05, + "loss": 0.188, "step": 119870 }, { - "epoch": 0.54, - "learning_rate": 2.3357024348683917e-05, - "loss": 0.176, + "epoch": 0.27, + "learning_rate": 3.670868660656361e-05, + "loss": 0.1926, "step": 119880 }, { - "epoch": 0.54, - "learning_rate": 2.3354782296757993e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.670756806335429e-05, + "loss": 0.1892, "step": 119890 }, { - "epoch": 0.54, - "learning_rate": 2.335254024483207e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.670644952014496e-05, + "loss": 0.1923, "step": 119900 }, { - "epoch": 0.54, - "learning_rate": 2.3350298192906147e-05, - "loss": 0.1781, + "epoch": 0.27, + "learning_rate": 3.6705330976935646e-05, + "loss": 0.1883, "step": 119910 }, { - "epoch": 0.54, - "learning_rate": 2.3348056140980225e-05, - "loss": 0.1848, + "epoch": 0.27, + "learning_rate": 3.670421243372632e-05, + "loss": 0.1851, "step": 119920 }, { - "epoch": 0.54, - "learning_rate": 2.3345814089054304e-05, - "loss": 0.1848, + "epoch": 0.27, + "learning_rate": 3.6703093890516995e-05, + "loss": 0.1868, "step": 119930 }, { - "epoch": 0.54, - "learning_rate": 2.334357203712838e-05, - "loss": 0.1801, + "epoch": 0.27, + "learning_rate": 3.6701975347307666e-05, + "loss": 0.1882, "step": 119940 }, { - "epoch": 0.54, - "learning_rate": 2.3341329985202458e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.6700856804098344e-05, + "loss": 0.1917, "step": 119950 }, { - "epoch": 0.54, - "learning_rate": 2.3339087933276533e-05, - "loss": 0.1769, + "epoch": 0.27, + "learning_rate": 3.669973826088902e-05, + "loss": 0.1864, "step": 119960 }, { - "epoch": 0.54, - "learning_rate": 2.3336845881350612e-05, - "loss": 0.1857, + "epoch": 0.27, + "learning_rate": 3.669861971767969e-05, + "loss": 0.1901, "step": 119970 }, { - "epoch": 0.54, - "learning_rate": 2.333460382942469e-05, - "loss": 0.1759, + "epoch": 0.27, + "learning_rate": 3.669750117447037e-05, + "loss": 0.1881, "step": 119980 }, { - "epoch": 0.54, - "learning_rate": 2.333236177749877e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.669638263126104e-05, + "loss": 0.1919, "step": 119990 }, { - "epoch": 0.54, - "learning_rate": 2.3330119725572845e-05, - "loss": 0.1862, + "epoch": 0.27, + "learning_rate": 3.669526408805172e-05, + "loss": 0.1818, "step": 120000 }, { - "epoch": 0.54, - "learning_rate": 2.3327877673646924e-05, - "loss": 0.1819, + "epoch": 0.27, + "learning_rate": 3.66941455448424e-05, + "loss": 0.1917, "step": 120010 }, { - "epoch": 0.54, - "learning_rate": 2.3325635621721002e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.6693027001633076e-05, + "loss": 0.1914, "step": 120020 }, { - "epoch": 0.54, - "learning_rate": 2.3323393569795078e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.6691908458423754e-05, + "loss": 0.189, "step": 120030 }, { - "epoch": 0.54, - "learning_rate": 2.3321151517869156e-05, - "loss": 0.1835, + "epoch": 0.27, + "learning_rate": 3.6690789915214425e-05, + "loss": 0.1958, "step": 120040 }, { - "epoch": 0.54, - "learning_rate": 2.3318909465943232e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.66896713720051e-05, + "loss": 0.1899, "step": 120050 }, { - "epoch": 0.54, - "learning_rate": 2.331666741401731e-05, - "loss": 0.1832, + "epoch": 0.27, + "learning_rate": 3.668855282879578e-05, + "loss": 0.1811, "step": 120060 }, { - "epoch": 0.54, - "learning_rate": 2.331442536209139e-05, - "loss": 0.1849, + "epoch": 0.27, + "learning_rate": 3.668743428558645e-05, + "loss": 0.1876, "step": 120070 }, { - "epoch": 0.54, - "learning_rate": 2.3312183310165464e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.668631574237713e-05, + "loss": 0.1891, "step": 120080 }, { - "epoch": 0.54, - "learning_rate": 2.3309941258239543e-05, - "loss": 0.1866, + "epoch": 0.27, + "learning_rate": 3.66851971991678e-05, + "loss": 0.1901, "step": 120090 }, { - "epoch": 0.54, - "learning_rate": 2.330769920631362e-05, - "loss": 0.1832, + "epoch": 0.27, + "learning_rate": 3.668407865595848e-05, + "loss": 0.1888, "step": 120100 }, { - "epoch": 0.54, - "learning_rate": 2.3305457154387697e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.668296011274916e-05, + "loss": 0.192, "step": 120110 }, { - "epoch": 0.54, - "learning_rate": 2.3303215102461773e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.6681841569539835e-05, + "loss": 0.1901, "step": 120120 }, { - "epoch": 0.54, - "learning_rate": 2.330097305053585e-05, - "loss": 0.1793, + "epoch": 0.27, + "learning_rate": 3.668072302633051e-05, + "loss": 0.194, "step": 120130 }, { - "epoch": 0.54, - "learning_rate": 2.329873099860993e-05, - "loss": 0.1798, + "epoch": 0.27, + "learning_rate": 3.6679604483121184e-05, + "loss": 0.19, "step": 120140 }, { - "epoch": 0.54, - "learning_rate": 2.3296488946684005e-05, - "loss": 0.1871, + "epoch": 0.27, + "learning_rate": 3.667848593991186e-05, + "loss": 0.1877, "step": 120150 }, { - "epoch": 0.54, - "learning_rate": 2.3294246894758084e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.667736739670254e-05, + "loss": 0.1867, "step": 120160 }, { - "epoch": 0.54, - "learning_rate": 2.329200484283216e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.667624885349321e-05, + "loss": 0.1864, "step": 120170 }, { - "epoch": 0.54, - "learning_rate": 2.3289762790906238e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.667513031028389e-05, + "loss": 0.1896, "step": 120180 }, { - "epoch": 0.54, - "learning_rate": 2.3287520738980313e-05, - "loss": 0.1785, + "epoch": 0.27, + "learning_rate": 3.667401176707456e-05, + "loss": 0.1903, "step": 120190 }, { - "epoch": 0.54, - "learning_rate": 2.3285278687054392e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.667289322386524e-05, + "loss": 0.1857, "step": 120200 }, { - "epoch": 0.54, - "learning_rate": 2.328303663512847e-05, - "loss": 0.189, + "epoch": 0.27, + "learning_rate": 3.6671774680655916e-05, + "loss": 0.1901, "step": 120210 }, { - "epoch": 0.54, - "learning_rate": 2.3280794583202546e-05, - "loss": 0.173, + "epoch": 0.27, + "learning_rate": 3.6670656137446594e-05, + "loss": 0.1868, "step": 120220 }, { - "epoch": 0.54, - "learning_rate": 2.3278552531276625e-05, - "loss": 0.1802, + "epoch": 0.27, + "learning_rate": 3.666953759423727e-05, + "loss": 0.1855, "step": 120230 }, { - "epoch": 0.54, - "learning_rate": 2.3276310479350704e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.666841905102794e-05, + "loss": 0.1894, "step": 120240 }, { - "epoch": 0.54, - "learning_rate": 2.327406842742478e-05, - "loss": 0.1818, + "epoch": 0.27, + "learning_rate": 3.666730050781862e-05, + "loss": 0.1876, "step": 120250 }, { - "epoch": 0.54, - "learning_rate": 2.3271826375498858e-05, - "loss": 0.1811, + "epoch": 0.27, + "learning_rate": 3.666618196460929e-05, + "loss": 0.1896, "step": 120260 }, { - "epoch": 0.54, - "learning_rate": 2.3269584323572936e-05, - "loss": 0.1777, + "epoch": 0.27, + "learning_rate": 3.666506342139997e-05, + "loss": 0.1853, "step": 120270 }, { - "epoch": 0.54, - "learning_rate": 2.3267342271647015e-05, - "loss": 0.1811, + "epoch": 0.27, + "learning_rate": 3.666394487819065e-05, + "loss": 0.1849, "step": 120280 }, { - "epoch": 0.54, - "learning_rate": 2.326510021972109e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.666282633498132e-05, + "loss": 0.1849, "step": 120290 }, { - "epoch": 0.54, - "learning_rate": 2.326285816779517e-05, - "loss": 0.1801, + "epoch": 0.27, + "learning_rate": 3.6661707791772e-05, + "loss": 0.1872, "step": 120300 }, { - "epoch": 0.54, - "learning_rate": 2.3260616115869245e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.666058924856267e-05, + "loss": 0.1889, "step": 120310 }, { - "epoch": 0.54, - "learning_rate": 2.3258374063943323e-05, - "loss": 0.1836, + "epoch": 0.27, + "learning_rate": 3.6659470705353346e-05, + "loss": 0.188, "step": 120320 }, { - "epoch": 0.54, - "learning_rate": 2.32561320120174e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.665835216214403e-05, + "loss": 0.1832, "step": 120330 }, { - "epoch": 0.54, - "learning_rate": 2.3253889960091477e-05, - "loss": 0.1883, + "epoch": 0.27, + "learning_rate": 3.66572336189347e-05, + "loss": 0.1947, "step": 120340 }, { - "epoch": 0.54, - "learning_rate": 2.3251647908165556e-05, - "loss": 0.1796, + "epoch": 0.27, + "learning_rate": 3.665611507572538e-05, + "loss": 0.1885, "step": 120350 }, { - "epoch": 0.54, - "learning_rate": 2.324940585623963e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.665499653251605e-05, + "loss": 0.1854, "step": 120360 }, { - "epoch": 0.54, - "learning_rate": 2.324716380431371e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.665387798930673e-05, + "loss": 0.1863, "step": 120370 }, { - "epoch": 0.54, - "learning_rate": 2.3244921752387785e-05, - "loss": 0.1868, + "epoch": 0.27, + "learning_rate": 3.665275944609741e-05, + "loss": 0.1861, "step": 120380 }, { - "epoch": 0.54, - "learning_rate": 2.3242679700461864e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.665164090288808e-05, + "loss": 0.1835, "step": 120390 }, { - "epoch": 0.54, - "learning_rate": 2.324043764853594e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.6650522359678756e-05, + "loss": 0.1882, "step": 120400 }, { - "epoch": 0.54, - "learning_rate": 2.3238195596610018e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.664940381646943e-05, + "loss": 0.1894, "step": 120410 }, { - "epoch": 0.54, - "learning_rate": 2.3235953544684097e-05, - "loss": 0.1813, + "epoch": 0.27, + "learning_rate": 3.6648285273260105e-05, + "loss": 0.188, "step": 120420 }, { - "epoch": 0.54, - "learning_rate": 2.3233711492758172e-05, - "loss": 0.1882, + "epoch": 0.27, + "learning_rate": 3.664716673005078e-05, + "loss": 0.1873, "step": 120430 }, { - "epoch": 0.54, - "learning_rate": 2.323146944083225e-05, - "loss": 0.1763, + "epoch": 0.27, + "learning_rate": 3.664604818684146e-05, + "loss": 0.1896, "step": 120440 }, { - "epoch": 0.54, - "learning_rate": 2.3229227388906326e-05, - "loss": 0.1869, + "epoch": 0.27, + "learning_rate": 3.664492964363214e-05, + "loss": 0.1864, "step": 120450 }, { - "epoch": 0.54, - "learning_rate": 2.3226985336980405e-05, - "loss": 0.1832, + "epoch": 0.27, + "learning_rate": 3.664381110042281e-05, + "loss": 0.1871, "step": 120460 }, { - "epoch": 0.54, - "learning_rate": 2.322474328505448e-05, - "loss": 0.1841, + "epoch": 0.27, + "learning_rate": 3.664269255721349e-05, + "loss": 0.189, "step": 120470 }, { - "epoch": 0.54, - "learning_rate": 2.322250123312856e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.6641574014004166e-05, + "loss": 0.1922, "step": 120480 }, { - "epoch": 0.54, - "learning_rate": 2.3220259181202638e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.664045547079484e-05, + "loss": 0.1903, "step": 120490 }, { - "epoch": 0.54, - "learning_rate": 2.3218017129276713e-05, - "loss": 0.1809, + "epoch": 0.27, + "learning_rate": 3.6639336927585515e-05, + "loss": 0.1852, "step": 120500 }, { - "epoch": 0.54, - "learning_rate": 2.3215775077350792e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.6638218384376186e-05, + "loss": 0.1874, "step": 120510 }, { - "epoch": 0.54, - "learning_rate": 2.321353302542487e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.6637099841166864e-05, + "loss": 0.1851, "step": 120520 }, { - "epoch": 0.54, - "learning_rate": 2.321129097349895e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.663598129795754e-05, + "loss": 0.1952, "step": 120530 }, { - "epoch": 0.54, - "learning_rate": 2.3209048921573025e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.663486275474822e-05, + "loss": 0.1871, "step": 120540 }, { - "epoch": 0.54, - "learning_rate": 2.3206806869647103e-05, - "loss": 0.1805, + "epoch": 0.27, + "learning_rate": 3.66337442115389e-05, + "loss": 0.1861, "step": 120550 }, { - "epoch": 0.54, - "learning_rate": 2.3204564817721182e-05, - "loss": 0.1819, + "epoch": 0.27, + "learning_rate": 3.663262566832957e-05, + "loss": 0.1897, "step": 120560 }, { - "epoch": 0.54, - "learning_rate": 2.3202322765795257e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.663150712512025e-05, + "loss": 0.1907, "step": 120570 }, { - "epoch": 0.54, - "learning_rate": 2.3200080713869336e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.663038858191092e-05, + "loss": 0.1846, "step": 120580 }, { - "epoch": 0.54, - "learning_rate": 2.319783866194341e-05, - "loss": 0.1775, + "epoch": 0.27, + "learning_rate": 3.6629270038701596e-05, + "loss": 0.1903, "step": 120590 }, { - "epoch": 0.54, - "learning_rate": 2.319559661001749e-05, - "loss": 0.1796, + "epoch": 0.27, + "learning_rate": 3.6628151495492274e-05, + "loss": 0.1918, "step": 120600 }, { - "epoch": 0.54, - "learning_rate": 2.319335455809157e-05, - "loss": 0.1873, + "epoch": 0.27, + "learning_rate": 3.6627032952282945e-05, + "loss": 0.1885, "step": 120610 }, { - "epoch": 0.54, - "learning_rate": 2.3191112506165644e-05, - "loss": 0.1785, + "epoch": 0.27, + "learning_rate": 3.662591440907362e-05, + "loss": 0.1837, "step": 120620 }, { - "epoch": 0.54, - "learning_rate": 2.3188870454239723e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.66247958658643e-05, + "loss": 0.1866, "step": 120630 }, { - "epoch": 0.54, - "learning_rate": 2.3186628402313798e-05, - "loss": 0.1892, + "epoch": 0.27, + "learning_rate": 3.662367732265498e-05, + "loss": 0.1891, "step": 120640 }, { - "epoch": 0.54, - "learning_rate": 2.3184386350387877e-05, - "loss": 0.1811, + "epoch": 0.27, + "learning_rate": 3.6622558779445657e-05, + "loss": 0.1886, "step": 120650 }, { - "epoch": 0.54, - "learning_rate": 2.3182144298461952e-05, + "epoch": 0.27, + "learning_rate": 3.662144023623633e-05, "loss": 0.1857, "step": 120660 }, { - "epoch": 0.54, - "learning_rate": 2.317990224653603e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.6620321693027006e-05, + "loss": 0.184, "step": 120670 }, { - "epoch": 0.54, - "learning_rate": 2.317766019461011e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.661920314981768e-05, + "loss": 0.185, "step": 120680 }, { - "epoch": 0.54, - "learning_rate": 2.3175418142684185e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.6618084606608355e-05, + "loss": 0.1853, "step": 120690 }, { - "epoch": 0.54, - "learning_rate": 2.3173176090758264e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.661696606339903e-05, + "loss": 0.1943, "step": 120700 }, { - "epoch": 0.54, - "learning_rate": 2.317093403883234e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.6615847520189704e-05, + "loss": 0.1854, "step": 120710 }, { - "epoch": 0.54, - "learning_rate": 2.3168691986906418e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.661472897698038e-05, + "loss": 0.1792, "step": 120720 }, { - "epoch": 0.54, - "learning_rate": 2.3166449934980493e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.661361043377105e-05, + "loss": 0.1837, "step": 120730 }, { - "epoch": 0.54, - "learning_rate": 2.3164207883054572e-05, - "loss": 0.1746, + "epoch": 0.27, + "learning_rate": 3.661249189056174e-05, + "loss": 0.1826, "step": 120740 }, { - "epoch": 0.54, - "learning_rate": 2.316196583112865e-05, - "loss": 0.1877, + "epoch": 0.27, + "learning_rate": 3.6611373347352416e-05, + "loss": 0.185, "step": 120750 }, { - "epoch": 0.54, - "learning_rate": 2.3159723779202726e-05, - "loss": 0.1799, + "epoch": 0.27, + "learning_rate": 3.661025480414309e-05, + "loss": 0.191, "step": 120760 }, { - "epoch": 0.54, - "learning_rate": 2.3157481727276805e-05, - "loss": 0.186, + "epoch": 0.27, + "learning_rate": 3.6609136260933765e-05, + "loss": 0.1917, "step": 120770 }, { - "epoch": 0.54, - "learning_rate": 2.3155239675350883e-05, - "loss": 0.1811, + "epoch": 0.27, + "learning_rate": 3.6608017717724436e-05, + "loss": 0.1837, "step": 120780 }, { - "epoch": 0.54, - "learning_rate": 2.315299762342496e-05, - "loss": 0.1809, + "epoch": 0.27, + "learning_rate": 3.6606899174515114e-05, + "loss": 0.1889, "step": 120790 }, { - "epoch": 0.54, - "learning_rate": 2.3150755571499037e-05, - "loss": 0.185, + "epoch": 0.27, + "learning_rate": 3.660578063130579e-05, + "loss": 0.1911, "step": 120800 }, { - "epoch": 0.54, - "learning_rate": 2.3148513519573116e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.660466208809646e-05, + "loss": 0.1878, "step": 120810 }, { - "epoch": 0.54, - "learning_rate": 2.3146271467647195e-05, + "epoch": 0.27, + "learning_rate": 3.660354354488714e-05, "loss": 0.1877, "step": 120820 }, { - "epoch": 0.54, - "learning_rate": 2.314402941572127e-05, - "loss": 0.1796, + "epoch": 0.27, + "learning_rate": 3.660242500167781e-05, + "loss": 0.1856, "step": 120830 }, { - "epoch": 0.54, - "learning_rate": 2.314178736379535e-05, - "loss": 0.1864, + "epoch": 0.27, + "learning_rate": 3.660130645846849e-05, + "loss": 0.1857, "step": 120840 }, { - "epoch": 0.54, - "learning_rate": 2.3139545311869424e-05, - "loss": 0.1782, + "epoch": 0.27, + "learning_rate": 3.660018791525917e-05, + "loss": 0.1849, "step": 120850 }, { - "epoch": 0.54, - "learning_rate": 2.3137303259943503e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.6599069372049846e-05, + "loss": 0.1875, "step": 120860 }, { - "epoch": 0.54, - "learning_rate": 2.3135061208017578e-05, - "loss": 0.1864, + "epoch": 0.27, + "learning_rate": 3.6597950828840524e-05, + "loss": 0.1883, "step": 120870 }, { - "epoch": 0.54, - "learning_rate": 2.3132819156091657e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.6596832285631195e-05, + "loss": 0.1911, "step": 120880 }, { - "epoch": 0.54, - "learning_rate": 2.3130577104165736e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.659571374242187e-05, + "loss": 0.1912, "step": 120890 }, { - "epoch": 0.54, - "learning_rate": 2.312833505223981e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.6594595199212544e-05, + "loss": 0.1815, "step": 120900 }, { - "epoch": 0.54, - "learning_rate": 2.312609300031389e-05, - "loss": 0.1827, + "epoch": 0.27, + "learning_rate": 3.659347665600322e-05, + "loss": 0.1889, "step": 120910 }, { - "epoch": 0.54, - "learning_rate": 2.3123850948387965e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.65923581127939e-05, + "loss": 0.1903, "step": 120920 }, { - "epoch": 0.54, - "learning_rate": 2.3121608896462044e-05, - "loss": 0.1852, + "epoch": 0.27, + "learning_rate": 3.659123956958457e-05, + "loss": 0.1912, "step": 120930 }, { - "epoch": 0.54, - "learning_rate": 2.311936684453612e-05, - "loss": 0.1733, + "epoch": 0.27, + "learning_rate": 3.659012102637525e-05, + "loss": 0.1878, "step": 120940 }, { - "epoch": 0.54, - "learning_rate": 2.3117124792610198e-05, - "loss": 0.1799, + "epoch": 0.27, + "learning_rate": 3.658900248316593e-05, + "loss": 0.1876, "step": 120950 }, { - "epoch": 0.54, - "learning_rate": 2.3114882740684276e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.6587883939956605e-05, + "loss": 0.1938, "step": 120960 }, { - "epoch": 0.54, - "learning_rate": 2.3112640688758352e-05, - "loss": 0.1862, + "epoch": 0.27, + "learning_rate": 3.658676539674728e-05, + "loss": 0.1848, "step": 120970 }, { - "epoch": 0.54, - "learning_rate": 2.311039863683243e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.6585646853537954e-05, + "loss": 0.1839, "step": 120980 }, { - "epoch": 0.54, - "learning_rate": 2.3108156584906506e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.658452831032863e-05, + "loss": 0.1814, "step": 120990 }, { - "epoch": 0.54, - "learning_rate": 2.3105914532980585e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.65834097671193e-05, + "loss": 0.1875, "step": 121000 }, { - "epoch": 0.54, - "learning_rate": 2.310367248105466e-05, - "loss": 0.1791, - "step": 121010 + "epoch": 0.27, + "learning_rate": 3.658229122390998e-05, + "loss": 0.1854, + "step": 121010 }, { - "epoch": 0.54, - "learning_rate": 2.310143042912874e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.658117268070066e-05, + "loss": 0.1872, "step": 121020 }, { - "epoch": 0.54, - "learning_rate": 2.3099188377202817e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.658005413749133e-05, + "loss": 0.1921, "step": 121030 }, { - "epoch": 0.54, - "learning_rate": 2.3096946325276893e-05, - "loss": 0.1877, + "epoch": 0.27, + "learning_rate": 3.657893559428201e-05, + "loss": 0.1925, "step": 121040 }, { - "epoch": 0.54, - "learning_rate": 2.309470427335097e-05, - "loss": 0.1888, + "epoch": 0.27, + "learning_rate": 3.6577817051072686e-05, + "loss": 0.1857, "step": 121050 }, { - "epoch": 0.54, - "learning_rate": 2.309246222142505e-05, - "loss": 0.1862, + "epoch": 0.27, + "learning_rate": 3.6576698507863363e-05, + "loss": 0.1875, "step": 121060 }, { - "epoch": 0.54, - "learning_rate": 2.309022016949913e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.657557996465404e-05, + "loss": 0.1886, "step": 121070 }, { - "epoch": 0.54, - "learning_rate": 2.3087978117573204e-05, - "loss": 0.188, + "epoch": 0.27, + "learning_rate": 3.657446142144471e-05, + "loss": 0.1918, "step": 121080 }, { - "epoch": 0.54, - "learning_rate": 2.3085736065647283e-05, - "loss": 0.1782, + "epoch": 0.27, + "learning_rate": 3.657334287823539e-05, + "loss": 0.1857, "step": 121090 }, { - "epoch": 0.54, - "learning_rate": 2.308349401372136e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.657222433502606e-05, + "loss": 0.1867, "step": 121100 }, { - "epoch": 0.54, - "learning_rate": 2.3081251961795437e-05, - "loss": 0.1809, + "epoch": 0.27, + "learning_rate": 3.657110579181674e-05, + "loss": 0.1846, "step": 121110 }, { - "epoch": 0.54, - "learning_rate": 2.3079009909869516e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.656998724860742e-05, + "loss": 0.1908, "step": 121120 }, { - "epoch": 0.54, - "learning_rate": 2.307676785794359e-05, - "loss": 0.1778, + "epoch": 0.27, + "learning_rate": 3.656886870539809e-05, + "loss": 0.1885, "step": 121130 }, { - "epoch": 0.54, - "learning_rate": 2.307452580601767e-05, - "loss": 0.1827, + "epoch": 0.27, + "learning_rate": 3.6567750162188767e-05, + "loss": 0.1939, "step": 121140 }, { - "epoch": 0.54, - "learning_rate": 2.3072283754091745e-05, - "loss": 0.1835, + "epoch": 0.27, + "learning_rate": 3.656663161897944e-05, + "loss": 0.1856, "step": 121150 }, { - "epoch": 0.54, - "learning_rate": 2.3070041702165824e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.656551307577012e-05, + "loss": 0.189, "step": 121160 }, { - "epoch": 0.54, - "learning_rate": 2.3067799650239902e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.65643945325608e-05, + "loss": 0.1908, "step": 121170 }, { - "epoch": 0.54, - "learning_rate": 2.3065557598313978e-05, - "loss": 0.1884, + "epoch": 0.27, + "learning_rate": 3.656327598935147e-05, + "loss": 0.1858, "step": 121180 }, { - "epoch": 0.54, - "learning_rate": 2.3063315546388056e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.656215744614215e-05, + "loss": 0.1846, "step": 121190 }, { - "epoch": 0.54, - "learning_rate": 2.3061073494462132e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.656103890293282e-05, + "loss": 0.1868, "step": 121200 }, { - "epoch": 0.54, - "learning_rate": 2.305883144253621e-05, - "loss": 0.1839, + "epoch": 0.27, + "learning_rate": 3.65599203597235e-05, + "loss": 0.1896, "step": 121210 }, { - "epoch": 0.54, - "learning_rate": 2.3056589390610286e-05, - "loss": 0.1873, + "epoch": 0.27, + "learning_rate": 3.655880181651417e-05, + "loss": 0.1851, "step": 121220 }, { - "epoch": 0.54, - "learning_rate": 2.3054347338684365e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.655768327330485e-05, + "loss": 0.1897, "step": 121230 }, { - "epoch": 0.54, - "learning_rate": 2.3052105286758443e-05, - "loss": 0.1806, + "epoch": 0.27, + "learning_rate": 3.6556564730095526e-05, + "loss": 0.1855, "step": 121240 }, { - "epoch": 0.54, - "learning_rate": 2.304986323483252e-05, - "loss": 0.1795, + "epoch": 0.27, + "learning_rate": 3.65554461868862e-05, + "loss": 0.1878, "step": 121250 }, { - "epoch": 0.54, - "learning_rate": 2.3047621182906597e-05, - "loss": 0.183, + "epoch": 0.27, + "learning_rate": 3.6554327643676875e-05, + "loss": 0.185, "step": 121260 }, { - "epoch": 0.54, - "learning_rate": 2.3045379130980673e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.655320910046755e-05, + "loss": 0.1879, "step": 121270 }, { - "epoch": 0.54, - "learning_rate": 2.304313707905475e-05, - "loss": 0.178, + "epoch": 0.27, + "learning_rate": 3.655209055725823e-05, + "loss": 0.1909, "step": 121280 }, { - "epoch": 0.54, - "learning_rate": 2.3040895027128827e-05, - "loss": 0.1857, + "epoch": 0.27, + "learning_rate": 3.655097201404891e-05, + "loss": 0.1919, "step": 121290 }, { - "epoch": 0.54, - "learning_rate": 2.3038652975202905e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.654985347083958e-05, + "loss": 0.1853, "step": 121300 }, { - "epoch": 0.54, - "learning_rate": 2.3036410923276984e-05, - "loss": 0.1854, + "epoch": 0.27, + "learning_rate": 3.654873492763026e-05, + "loss": 0.1871, "step": 121310 }, { - "epoch": 0.54, - "learning_rate": 2.3034168871351063e-05, - "loss": 0.1868, + "epoch": 0.27, + "learning_rate": 3.654761638442093e-05, + "loss": 0.189, "step": 121320 }, { - "epoch": 0.54, - "learning_rate": 2.3031926819425138e-05, - "loss": 0.1849, + "epoch": 0.27, + "learning_rate": 3.6546497841211607e-05, + "loss": 0.1894, "step": 121330 }, { - "epoch": 0.54, - "learning_rate": 2.3029684767499217e-05, + "epoch": 0.27, + "learning_rate": 3.6545379298002284e-05, "loss": 0.1857, "step": 121340 }, { - "epoch": 0.54, - "learning_rate": 2.3027442715573296e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.6544260754792956e-05, + "loss": 0.1829, "step": 121350 }, { - "epoch": 0.54, - "learning_rate": 2.302520066364737e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.6543142211583634e-05, + "loss": 0.1873, "step": 121360 }, { - "epoch": 0.54, - "learning_rate": 2.302295861172145e-05, - "loss": 0.1725, + "epoch": 0.27, + "learning_rate": 3.654202366837431e-05, + "loss": 0.1876, "step": 121370 }, { - "epoch": 0.54, - "learning_rate": 2.302071655979553e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.654090512516499e-05, + "loss": 0.1872, "step": 121380 }, { - "epoch": 0.54, - "learning_rate": 2.3018474507869604e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.653978658195567e-05, + "loss": 0.1864, "step": 121390 }, { - "epoch": 0.54, - "learning_rate": 2.3016232455943682e-05, - "loss": 0.1827, + "epoch": 0.27, + "learning_rate": 3.653866803874634e-05, + "loss": 0.1882, "step": 121400 }, { - "epoch": 0.54, - "learning_rate": 2.3013990404017758e-05, - "loss": 0.1799, + "epoch": 0.27, + "learning_rate": 3.6537549495537016e-05, + "loss": 0.1845, "step": 121410 }, { - "epoch": 0.54, - "learning_rate": 2.3011748352091836e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.653643095232769e-05, + "loss": 0.1919, "step": 121420 }, { - "epoch": 0.54, - "learning_rate": 2.3009506300165912e-05, - "loss": 0.1778, + "epoch": 0.27, + "learning_rate": 3.6535312409118366e-05, + "loss": 0.1881, "step": 121430 }, { - "epoch": 0.54, - "learning_rate": 2.300726424823999e-05, - "loss": 0.1841, + "epoch": 0.27, + "learning_rate": 3.6534193865909043e-05, + "loss": 0.194, "step": 121440 }, { - "epoch": 0.54, - "learning_rate": 2.300502219631407e-05, - "loss": 0.1879, + "epoch": 0.27, + "learning_rate": 3.6533075322699715e-05, + "loss": 0.1827, "step": 121450 }, { - "epoch": 0.54, - "learning_rate": 2.3002780144388145e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.653195677949039e-05, + "loss": 0.1841, "step": 121460 }, { - "epoch": 0.54, - "learning_rate": 2.3000538092462223e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.653083823628107e-05, + "loss": 0.1821, "step": 121470 }, { - "epoch": 0.54, - "learning_rate": 2.29982960405363e-05, - "loss": 0.1814, + "epoch": 0.27, + "learning_rate": 3.652971969307175e-05, + "loss": 0.1892, "step": 121480 }, { - "epoch": 0.54, - "learning_rate": 2.2996053988610377e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.6528601149862426e-05, + "loss": 0.1898, "step": 121490 }, { - "epoch": 0.54, - "learning_rate": 2.2993811936684453e-05, - "loss": 0.1785, + "epoch": 0.27, + "learning_rate": 3.65274826066531e-05, + "loss": 0.1913, "step": 121500 }, { - "epoch": 0.54, - "learning_rate": 2.299156988475853e-05, - "loss": 0.1787, + "epoch": 0.27, + "learning_rate": 3.6526364063443775e-05, + "loss": 0.185, "step": 121510 }, { - "epoch": 0.54, - "learning_rate": 2.298932783283261e-05, - "loss": 0.1877, + "epoch": 0.27, + "learning_rate": 3.6525245520234447e-05, + "loss": 0.1885, "step": 121520 }, { - "epoch": 0.54, - "learning_rate": 2.2987085780906685e-05, - "loss": 0.1847, + "epoch": 0.27, + "learning_rate": 3.6524126977025124e-05, + "loss": 0.1828, "step": 121530 }, { - "epoch": 0.54, - "learning_rate": 2.2984843728980764e-05, - "loss": 0.1784, + "epoch": 0.27, + "learning_rate": 3.6523008433815796e-05, + "loss": 0.1835, "step": 121540 }, { - "epoch": 0.54, - "learning_rate": 2.298260167705484e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.6521889890606474e-05, + "loss": 0.1849, "step": 121550 }, { - "epoch": 0.54, - "learning_rate": 2.2980359625128918e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.652077134739715e-05, + "loss": 0.1934, "step": 121560 }, { - "epoch": 0.54, - "learning_rate": 2.2978117573202994e-05, - "loss": 0.1747, + "epoch": 0.27, + "learning_rate": 3.651965280418783e-05, + "loss": 0.1823, "step": 121570 }, { - "epoch": 0.54, - "learning_rate": 2.2975875521277072e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.651853426097851e-05, + "loss": 0.189, "step": 121580 }, { - "epoch": 0.54, - "learning_rate": 2.297363346935115e-05, - "loss": 0.1802, + "epoch": 0.27, + "learning_rate": 3.651741571776918e-05, + "loss": 0.1913, "step": 121590 }, { - "epoch": 0.54, - "learning_rate": 2.297139141742523e-05, - "loss": 0.1788, + "epoch": 0.27, + "learning_rate": 3.6516297174559856e-05, + "loss": 0.1844, "step": 121600 }, { - "epoch": 0.54, - "learning_rate": 2.296914936549931e-05, - "loss": 0.1756, + "epoch": 0.27, + "learning_rate": 3.6515178631350534e-05, + "loss": 0.1864, "step": 121610 }, { - "epoch": 0.54, - "learning_rate": 2.2966907313573384e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.6514060088141205e-05, + "loss": 0.1889, "step": 121620 }, { - "epoch": 0.54, - "learning_rate": 2.2964665261647462e-05, - "loss": 0.1827, + "epoch": 0.27, + "learning_rate": 3.6512941544931883e-05, + "loss": 0.1856, "step": 121630 }, { - "epoch": 0.54, - "learning_rate": 2.2962423209721538e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.6511823001722555e-05, + "loss": 0.1848, "step": 121640 }, { - "epoch": 0.54, - "learning_rate": 2.2960181157795616e-05, - "loss": 0.1857, + "epoch": 0.27, + "learning_rate": 3.651070445851323e-05, + "loss": 0.1853, "step": 121650 }, { - "epoch": 0.54, - "learning_rate": 2.2957939105869695e-05, - "loss": 0.1773, + "epoch": 0.27, + "learning_rate": 3.650958591530391e-05, + "loss": 0.1907, "step": 121660 }, { - "epoch": 0.54, - "learning_rate": 2.295569705394377e-05, - "loss": 0.1816, + "epoch": 0.27, + "learning_rate": 3.650846737209458e-05, + "loss": 0.1876, "step": 121670 }, { - "epoch": 0.54, - "learning_rate": 2.295345500201785e-05, - "loss": 0.1863, + "epoch": 0.27, + "learning_rate": 3.650734882888526e-05, + "loss": 0.1897, "step": 121680 }, { - "epoch": 0.54, - "learning_rate": 2.2951212950091925e-05, - "loss": 0.1847, + "epoch": 0.27, + "learning_rate": 3.650623028567594e-05, + "loss": 0.1826, "step": 121690 }, { - "epoch": 0.54, - "learning_rate": 2.2948970898166003e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.6505111742466615e-05, + "loss": 0.1835, "step": 121700 }, { - "epoch": 0.54, - "learning_rate": 2.294672884624008e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.650399319925729e-05, + "loss": 0.181, "step": 121710 }, { - "epoch": 0.54, - "learning_rate": 2.2944486794314157e-05, - "loss": 0.1783, + "epoch": 0.27, + "learning_rate": 3.6502874656047964e-05, + "loss": 0.1837, "step": 121720 }, { - "epoch": 0.54, - "learning_rate": 2.2942244742388236e-05, - "loss": 0.1766, + "epoch": 0.27, + "learning_rate": 3.650175611283864e-05, + "loss": 0.1824, "step": 121730 }, { - "epoch": 0.54, - "learning_rate": 2.294000269046231e-05, - "loss": 0.1839, + "epoch": 0.27, + "learning_rate": 3.6500637569629314e-05, + "loss": 0.1884, "step": 121740 }, { - "epoch": 0.54, - "learning_rate": 2.293776063853639e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.649951902641999e-05, + "loss": 0.1893, "step": 121750 }, { - "epoch": 0.54, - "learning_rate": 2.2935518586610465e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.649840048321067e-05, + "loss": 0.1896, "step": 121760 }, { - "epoch": 0.54, - "learning_rate": 2.2933276534684544e-05, - "loss": 0.1846, + "epoch": 0.27, + "learning_rate": 3.649728194000134e-05, + "loss": 0.1875, "step": 121770 }, { - "epoch": 0.54, - "learning_rate": 2.293103448275862e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.649616339679202e-05, + "loss": 0.1902, "step": 121780 }, { - "epoch": 0.54, - "learning_rate": 2.2928792430832698e-05, - "loss": 0.1792, + "epoch": 0.27, + "learning_rate": 3.6495044853582696e-05, + "loss": 0.1898, "step": 121790 }, { - "epoch": 0.54, - "learning_rate": 2.2926550378906777e-05, - "loss": 0.1761, + "epoch": 0.27, + "learning_rate": 3.6493926310373374e-05, + "loss": 0.1913, "step": 121800 }, { - "epoch": 0.54, - "learning_rate": 2.2924308326980852e-05, - "loss": 0.1885, + "epoch": 0.27, + "learning_rate": 3.649280776716405e-05, + "loss": 0.1869, "step": 121810 }, { - "epoch": 0.54, - "learning_rate": 2.292206627505493e-05, - "loss": 0.1771, + "epoch": 0.27, + "learning_rate": 3.649168922395472e-05, + "loss": 0.1863, "step": 121820 }, { - "epoch": 0.54, - "learning_rate": 2.2919824223129006e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.64905706807454e-05, + "loss": 0.1929, "step": 121830 }, { - "epoch": 0.54, - "learning_rate": 2.2917582171203085e-05, - "loss": 0.1864, + "epoch": 0.27, + "learning_rate": 3.648945213753607e-05, + "loss": 0.1854, "step": 121840 }, { - "epoch": 0.54, - "learning_rate": 2.2915340119277164e-05, - "loss": 0.1806, + "epoch": 0.27, + "learning_rate": 3.648844544864768e-05, + "loss": 0.1842, "step": 121850 }, { - "epoch": 0.54, - "learning_rate": 2.291309806735124e-05, - "loss": 0.1785, + "epoch": 0.27, + "learning_rate": 3.648732690543836e-05, + "loss": 0.189, "step": 121860 }, { - "epoch": 0.54, - "learning_rate": 2.2910856015425318e-05, - "loss": 0.1783, + "epoch": 0.27, + "learning_rate": 3.648620836222904e-05, + "loss": 0.191, "step": 121870 }, { - "epoch": 0.54, - "learning_rate": 2.2908613963499397e-05, - "loss": 0.1786, + "epoch": 0.27, + "learning_rate": 3.6485089819019715e-05, + "loss": 0.1847, "step": 121880 }, { - "epoch": 0.54, - "learning_rate": 2.2906371911573475e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.6483971275810386e-05, + "loss": 0.1833, "step": 121890 }, { - "epoch": 0.54, - "learning_rate": 2.290412985964755e-05, - "loss": 0.1867, + "epoch": 0.27, + "learning_rate": 3.6482852732601064e-05, + "loss": 0.1837, "step": 121900 }, { - "epoch": 0.54, - "learning_rate": 2.290188780772163e-05, - "loss": 0.1787, + "epoch": 0.27, + "learning_rate": 3.6481734189391735e-05, + "loss": 0.1865, "step": 121910 }, { - "epoch": 0.54, - "learning_rate": 2.2899645755795708e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.648061564618241e-05, + "loss": 0.1836, "step": 121920 }, { - "epoch": 0.54, - "learning_rate": 2.2897403703869783e-05, - "loss": 0.1751, + "epoch": 0.27, + "learning_rate": 3.6479497102973084e-05, + "loss": 0.186, "step": 121930 }, { - "epoch": 0.54, - "learning_rate": 2.2895161651943862e-05, - "loss": 0.1805, + "epoch": 0.27, + "learning_rate": 3.647837855976376e-05, + "loss": 0.1916, "step": 121940 }, { - "epoch": 0.54, - "learning_rate": 2.2892919600017937e-05, - "loss": 0.1866, + "epoch": 0.27, + "learning_rate": 3.647726001655444e-05, + "loss": 0.1869, "step": 121950 }, { - "epoch": 0.54, - "learning_rate": 2.2890677548092016e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.647614147334512e-05, + "loss": 0.1851, "step": 121960 }, { - "epoch": 0.54, - "learning_rate": 2.288843549616609e-05, - "loss": 0.1819, + "epoch": 0.27, + "learning_rate": 3.6475022930135796e-05, + "loss": 0.1885, "step": 121970 }, { - "epoch": 0.54, - "learning_rate": 2.288619344424017e-05, - "loss": 0.1757, + "epoch": 0.27, + "learning_rate": 3.647390438692647e-05, + "loss": 0.1896, "step": 121980 }, { - "epoch": 0.54, - "learning_rate": 2.288395139231425e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.6472785843717145e-05, + "loss": 0.1907, "step": 121990 }, { - "epoch": 0.54, - "learning_rate": 2.2881709340388324e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.647166730050782e-05, + "loss": 0.1828, "step": 122000 }, { - "epoch": 0.54, - "learning_rate": 2.2879467288462403e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.6470548757298494e-05, + "loss": 0.1844, "step": 122010 }, { - "epoch": 0.54, - "learning_rate": 2.2877225236536478e-05, - "loss": 0.1868, + "epoch": 0.27, + "learning_rate": 3.646943021408917e-05, + "loss": 0.1905, "step": 122020 }, { - "epoch": 0.54, - "learning_rate": 2.2874983184610557e-05, - "loss": 0.187, + "epoch": 0.27, + "learning_rate": 3.646831167087984e-05, + "loss": 0.1895, "step": 122030 }, { - "epoch": 0.54, - "learning_rate": 2.2872741132684632e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.646719312767052e-05, + "loss": 0.1837, "step": 122040 }, { - "epoch": 0.54, - "learning_rate": 2.287049908075871e-05, - "loss": 0.1724, + "epoch": 0.27, + "learning_rate": 3.64660745844612e-05, + "loss": 0.1902, "step": 122050 }, { - "epoch": 0.54, - "learning_rate": 2.286825702883279e-05, - "loss": 0.179, + "epoch": 0.27, + "learning_rate": 3.646495604125188e-05, + "loss": 0.1871, "step": 122060 }, { - "epoch": 0.54, - "learning_rate": 2.2866014976906865e-05, - "loss": 0.1795, + "epoch": 0.27, + "learning_rate": 3.6463837498042555e-05, + "loss": 0.1837, "step": 122070 }, { - "epoch": 0.54, - "learning_rate": 2.2863772924980944e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.6462718954833226e-05, + "loss": 0.1877, "step": 122080 }, { - "epoch": 0.55, - "learning_rate": 2.286153087305502e-05, - "loss": 0.1814, + "epoch": 0.27, + "learning_rate": 3.6461600411623904e-05, + "loss": 0.1913, "step": 122090 }, { - "epoch": 0.55, - "learning_rate": 2.2859288821129098e-05, - "loss": 0.1835, + "epoch": 0.27, + "learning_rate": 3.646048186841458e-05, + "loss": 0.1872, "step": 122100 }, { - "epoch": 0.55, - "learning_rate": 2.2857046769203173e-05, - "loss": 0.177, + "epoch": 0.27, + "learning_rate": 3.645936332520525e-05, + "loss": 0.185, "step": 122110 }, { - "epoch": 0.55, - "learning_rate": 2.2854804717277252e-05, - "loss": 0.1798, + "epoch": 0.27, + "learning_rate": 3.645824478199593e-05, + "loss": 0.1871, "step": 122120 }, { - "epoch": 0.55, - "learning_rate": 2.285256266535133e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.64571262387866e-05, + "loss": 0.1878, "step": 122130 }, { - "epoch": 0.55, - "learning_rate": 2.285032061342541e-05, - "loss": 0.1799, + "epoch": 0.27, + "learning_rate": 3.645600769557728e-05, + "loss": 0.1899, "step": 122140 }, { - "epoch": 0.55, - "learning_rate": 2.2848078561499488e-05, - "loss": 0.181, + "epoch": 0.27, + "learning_rate": 3.645488915236796e-05, + "loss": 0.1874, "step": 122150 }, { - "epoch": 0.55, - "learning_rate": 2.2845836509573563e-05, - "loss": 0.1824, + "epoch": 0.27, + "learning_rate": 3.6453770609158636e-05, + "loss": 0.1865, "step": 122160 }, { - "epoch": 0.55, - "learning_rate": 2.2843594457647642e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.6452652065949314e-05, + "loss": 0.1926, "step": 122170 }, { - "epoch": 0.55, - "learning_rate": 2.2841352405721717e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.6451533522739985e-05, + "loss": 0.1899, "step": 122180 }, { - "epoch": 0.55, - "learning_rate": 2.2839110353795796e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.645041497953066e-05, + "loss": 0.1884, "step": 122190 }, { - "epoch": 0.55, - "learning_rate": 2.2836868301869875e-05, - "loss": 0.1863, + "epoch": 0.27, + "learning_rate": 3.644929643632134e-05, + "loss": 0.1859, "step": 122200 }, { - "epoch": 0.55, - "learning_rate": 2.283462624994395e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.644817789311201e-05, + "loss": 0.1841, "step": 122210 }, { - "epoch": 0.55, - "learning_rate": 2.283238419801803e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.644705934990269e-05, + "loss": 0.1829, "step": 122220 }, { - "epoch": 0.55, - "learning_rate": 2.2830142146092104e-05, - "loss": 0.1752, + "epoch": 0.27, + "learning_rate": 3.644594080669336e-05, + "loss": 0.1814, "step": 122230 }, { - "epoch": 0.55, - "learning_rate": 2.2827900094166183e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.644482226348404e-05, + "loss": 0.19, "step": 122240 }, { - "epoch": 0.55, - "learning_rate": 2.2825658042240258e-05, - "loss": 0.1795, + "epoch": 0.27, + "learning_rate": 3.644370372027471e-05, + "loss": 0.1887, "step": 122250 }, { - "epoch": 0.55, - "learning_rate": 2.2823415990314337e-05, - "loss": 0.1855, + "epoch": 0.27, + "learning_rate": 3.644258517706539e-05, + "loss": 0.1869, "step": 122260 }, { - "epoch": 0.55, - "learning_rate": 2.2821173938388416e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.644146663385607e-05, + "loss": 0.1895, "step": 122270 }, { - "epoch": 0.55, - "learning_rate": 2.281893188646249e-05, - "loss": 0.1852, + "epoch": 0.27, + "learning_rate": 3.6440348090646744e-05, + "loss": 0.1845, "step": 122280 }, { - "epoch": 0.55, - "learning_rate": 2.281668983453657e-05, - "loss": 0.1889, + "epoch": 0.27, + "learning_rate": 3.643922954743742e-05, + "loss": 0.1864, "step": 122290 }, { - "epoch": 0.55, - "learning_rate": 2.2814447782610645e-05, - "loss": 0.1826, + "epoch": 0.27, + "learning_rate": 3.643811100422809e-05, + "loss": 0.1836, "step": 122300 }, { - "epoch": 0.55, - "learning_rate": 2.2812205730684724e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.643699246101877e-05, + "loss": 0.1828, "step": 122310 }, { - "epoch": 0.55, - "learning_rate": 2.28099636787588e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.643587391780945e-05, + "loss": 0.1929, "step": 122320 }, { - "epoch": 0.55, - "learning_rate": 2.2807721626832878e-05, - "loss": 0.1806, + "epoch": 0.27, + "learning_rate": 3.643475537460012e-05, + "loss": 0.1952, "step": 122330 }, { - "epoch": 0.55, - "learning_rate": 2.2805479574906957e-05, - "loss": 0.1796, + "epoch": 0.27, + "learning_rate": 3.64336368313908e-05, + "loss": 0.1904, "step": 122340 }, { - "epoch": 0.55, - "learning_rate": 2.2803237522981032e-05, - "loss": 0.1854, + "epoch": 0.27, + "learning_rate": 3.643251828818147e-05, + "loss": 0.1857, "step": 122350 }, { - "epoch": 0.55, - "learning_rate": 2.280099547105511e-05, - "loss": 0.1844, + "epoch": 0.27, + "learning_rate": 3.643139974497215e-05, + "loss": 0.1895, "step": 122360 }, { - "epoch": 0.55, - "learning_rate": 2.2798753419129186e-05, - "loss": 0.1819, + "epoch": 0.27, + "learning_rate": 3.6430281201762825e-05, + "loss": 0.1813, "step": 122370 }, { - "epoch": 0.55, - "learning_rate": 2.2796511367203265e-05, - "loss": 0.182, + "epoch": 0.27, + "learning_rate": 3.64291626585535e-05, + "loss": 0.1869, "step": 122380 }, { - "epoch": 0.55, - "learning_rate": 2.2794269315277343e-05, - "loss": 0.1855, + "epoch": 0.27, + "learning_rate": 3.642804411534418e-05, + "loss": 0.1867, "step": 122390 }, { - "epoch": 0.55, - "learning_rate": 2.279202726335142e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.642692557213485e-05, + "loss": 0.1882, "step": 122400 }, { - "epoch": 0.55, - "learning_rate": 2.2789785211425497e-05, - "loss": 0.1839, + "epoch": 0.27, + "learning_rate": 3.642580702892553e-05, + "loss": 0.1845, "step": 122410 }, { - "epoch": 0.55, - "learning_rate": 2.2787543159499576e-05, - "loss": 0.1803, + "epoch": 0.27, + "learning_rate": 3.642468848571621e-05, + "loss": 0.1815, "step": 122420 }, { - "epoch": 0.55, - "learning_rate": 2.2785301107573655e-05, - "loss": 0.1816, + "epoch": 0.27, + "learning_rate": 3.642356994250688e-05, + "loss": 0.1871, "step": 122430 }, { - "epoch": 0.55, - "learning_rate": 2.278305905564773e-05, - "loss": 0.1842, + "epoch": 0.27, + "learning_rate": 3.642245139929756e-05, + "loss": 0.1838, "step": 122440 }, { - "epoch": 0.55, - "learning_rate": 2.278081700372181e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.642133285608823e-05, + "loss": 0.1847, "step": 122450 }, { - "epoch": 0.55, - "learning_rate": 2.2778574951795884e-05, + "epoch": 0.27, + "learning_rate": 3.6420214312878906e-05, "loss": 0.1906, "step": 122460 }, { - "epoch": 0.55, - "learning_rate": 2.2776332899869963e-05, - "loss": 0.1785, + "epoch": 0.27, + "learning_rate": 3.6419095769669584e-05, + "loss": 0.1923, "step": 122470 }, { - "epoch": 0.55, - "learning_rate": 2.277409084794404e-05, - "loss": 0.18, + "epoch": 0.27, + "learning_rate": 3.641797722646026e-05, + "loss": 0.1784, "step": 122480 }, { - "epoch": 0.55, - "learning_rate": 2.2771848796018117e-05, - "loss": 0.1871, + "epoch": 0.27, + "learning_rate": 3.641685868325094e-05, + "loss": 0.1867, "step": 122490 }, { - "epoch": 0.55, - "learning_rate": 2.2769606744092196e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.641574014004161e-05, + "loss": 0.1859, "step": 122500 }, { - "epoch": 0.55, - "learning_rate": 2.276736469216627e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.641462159683229e-05, + "loss": 0.1848, "step": 122510 }, { - "epoch": 0.55, - "learning_rate": 2.276512264024035e-05, - "loss": 0.1774, + "epoch": 0.27, + "learning_rate": 3.641350305362296e-05, + "loss": 0.1889, "step": 122520 }, { - "epoch": 0.55, - "learning_rate": 2.2762880588314425e-05, - "loss": 0.1856, + "epoch": 0.27, + "learning_rate": 3.641238451041364e-05, + "loss": 0.1899, "step": 122530 }, { - "epoch": 0.55, - "learning_rate": 2.2760638536388504e-05, - "loss": 0.1881, + "epoch": 0.27, + "learning_rate": 3.6411265967204316e-05, + "loss": 0.1878, "step": 122540 }, { - "epoch": 0.55, - "learning_rate": 2.2758620689655175e-05, - "loss": 0.1813, + "epoch": 0.27, + "learning_rate": 3.641014742399499e-05, + "loss": 0.1857, "step": 122550 }, { - "epoch": 0.55, - "learning_rate": 2.275637863772925e-05, - "loss": 0.1778, + "epoch": 0.27, + "learning_rate": 3.6409028880785665e-05, + "loss": 0.1858, "step": 122560 }, { - "epoch": 0.55, - "learning_rate": 2.275413658580333e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.640791033757634e-05, + "loss": 0.1844, "step": 122570 }, { - "epoch": 0.55, - "learning_rate": 2.2751894533877404e-05, - "loss": 0.1789, + "epoch": 0.27, + "learning_rate": 3.640679179436702e-05, + "loss": 0.1862, "step": 122580 }, { - "epoch": 0.55, - "learning_rate": 2.2749652481951483e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.64056732511577e-05, + "loss": 0.1891, "step": 122590 }, { - "epoch": 0.55, - "learning_rate": 2.274741043002556e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.640455470794837e-05, + "loss": 0.1865, "step": 122600 }, { - "epoch": 0.55, - "learning_rate": 2.2745168378099637e-05, - "loss": 0.1798, + "epoch": 0.27, + "learning_rate": 3.640343616473905e-05, + "loss": 0.1848, "step": 122610 }, { - "epoch": 0.55, - "learning_rate": 2.2742926326173716e-05, - "loss": 0.1834, + "epoch": 0.27, + "learning_rate": 3.640231762152972e-05, + "loss": 0.1882, "step": 122620 }, { - "epoch": 0.55, - "learning_rate": 2.274068427424779e-05, - "loss": 0.1836, + "epoch": 0.27, + "learning_rate": 3.64011990783204e-05, + "loss": 0.188, "step": 122630 }, { - "epoch": 0.55, - "learning_rate": 2.273844222232187e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.6400080535111075e-05, + "loss": 0.1834, "step": 122640 }, { - "epoch": 0.55, - "learning_rate": 2.2736200170395945e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.6398961991901746e-05, + "loss": 0.1848, "step": 122650 }, { - "epoch": 0.55, - "learning_rate": 2.2733958118470024e-05, - "loss": 0.1764, + "epoch": 0.27, + "learning_rate": 3.6397843448692424e-05, + "loss": 0.1868, "step": 122660 }, { - "epoch": 0.55, - "learning_rate": 2.27317160665441e-05, - "loss": 0.1795, + "epoch": 0.27, + "learning_rate": 3.6396724905483095e-05, + "loss": 0.185, "step": 122670 }, { - "epoch": 0.55, - "learning_rate": 2.2729474014618178e-05, - "loss": 0.1816, + "epoch": 0.27, + "learning_rate": 3.639560636227377e-05, + "loss": 0.1875, "step": 122680 }, { - "epoch": 0.55, - "learning_rate": 2.2727231962692257e-05, - "loss": 0.1808, + "epoch": 0.27, + "learning_rate": 3.639448781906446e-05, + "loss": 0.1816, "step": 122690 }, { - "epoch": 0.55, - "learning_rate": 2.2724989910766335e-05, - "loss": 0.1833, + "epoch": 0.27, + "learning_rate": 3.639336927585513e-05, + "loss": 0.1799, "step": 122700 }, { - "epoch": 0.55, - "learning_rate": 2.2722747858840414e-05, - "loss": 0.1823, + "epoch": 0.27, + "learning_rate": 3.639225073264581e-05, + "loss": 0.1903, "step": 122710 }, { - "epoch": 0.55, - "learning_rate": 2.272050580691449e-05, - "loss": 0.1892, + "epoch": 0.27, + "learning_rate": 3.639113218943648e-05, + "loss": 0.19, "step": 122720 }, { - "epoch": 0.55, - "learning_rate": 2.2718263754988568e-05, - "loss": 0.1772, + "epoch": 0.27, + "learning_rate": 3.6390013646227156e-05, + "loss": 0.1862, "step": 122730 }, { - "epoch": 0.55, - "learning_rate": 2.2716021703062644e-05, - "loss": 0.1767, + "epoch": 0.27, + "learning_rate": 3.6388895103017834e-05, + "loss": 0.1838, "step": 122740 }, { - "epoch": 0.55, - "learning_rate": 2.2713779651136722e-05, - "loss": 0.1817, + "epoch": 0.27, + "learning_rate": 3.6387776559808505e-05, + "loss": 0.1854, "step": 122750 }, { - "epoch": 0.55, - "learning_rate": 2.27115375992108e-05, - "loss": 0.1845, + "epoch": 0.27, + "learning_rate": 3.638665801659918e-05, + "loss": 0.1826, "step": 122760 }, { - "epoch": 0.55, - "learning_rate": 2.2709295547284876e-05, - "loss": 0.1838, + "epoch": 0.27, + "learning_rate": 3.6385539473389854e-05, + "loss": 0.1803, "step": 122770 }, { - "epoch": 0.55, - "learning_rate": 2.2707053495358955e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.638442093018053e-05, + "loss": 0.1824, "step": 122780 }, { - "epoch": 0.55, - "learning_rate": 2.270481144343303e-05, - "loss": 0.1794, + "epoch": 0.27, + "learning_rate": 3.638330238697121e-05, + "loss": 0.181, "step": 122790 }, { - "epoch": 0.55, - "learning_rate": 2.270256939150711e-05, - "loss": 0.1822, + "epoch": 0.27, + "learning_rate": 3.638218384376189e-05, + "loss": 0.1869, "step": 122800 }, { - "epoch": 0.55, - "learning_rate": 2.2700327339581184e-05, - "loss": 0.1805, + "epoch": 0.27, + "learning_rate": 3.6381065300552566e-05, + "loss": 0.1864, "step": 122810 }, { - "epoch": 0.55, - "learning_rate": 2.2698085287655263e-05, - "loss": 0.1816, + "epoch": 0.27, + "learning_rate": 3.637994675734324e-05, + "loss": 0.1855, "step": 122820 }, { - "epoch": 0.55, - "learning_rate": 2.2695843235729342e-05, - "loss": 0.1864, + "epoch": 0.27, + "learning_rate": 3.6378828214133915e-05, + "loss": 0.1905, "step": 122830 }, { - "epoch": 0.55, - "learning_rate": 2.2693601183803417e-05, - "loss": 0.1784, + "epoch": 0.27, + "learning_rate": 3.6377709670924586e-05, + "loss": 0.1818, "step": 122840 }, { - "epoch": 0.55, - "learning_rate": 2.2691359131877496e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.6376591127715264e-05, + "loss": 0.187, "step": 122850 }, { - "epoch": 0.55, - "learning_rate": 2.268911707995157e-05, - "loss": 0.1815, + "epoch": 0.27, + "learning_rate": 3.637547258450594e-05, + "loss": 0.1841, "step": 122860 }, { - "epoch": 0.55, - "learning_rate": 2.268687502802565e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.637435404129661e-05, + "loss": 0.1897, "step": 122870 }, { - "epoch": 0.55, - "learning_rate": 2.268463297609973e-05, - "loss": 0.1853, + "epoch": 0.27, + "learning_rate": 3.637323549808729e-05, + "loss": 0.1863, "step": 122880 }, { - "epoch": 0.55, - "learning_rate": 2.2682390924173804e-05, - "loss": 0.1807, + "epoch": 0.27, + "learning_rate": 3.637211695487797e-05, + "loss": 0.1842, "step": 122890 }, { - "epoch": 0.55, - "learning_rate": 2.2680148872247883e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.637099841166865e-05, + "loss": 0.1854, "step": 122900 }, { - "epoch": 0.55, - "learning_rate": 2.2677906820321958e-05, - "loss": 0.1768, + "epoch": 0.27, + "learning_rate": 3.6369879868459325e-05, + "loss": 0.1943, "step": 122910 }, { - "epoch": 0.55, - "learning_rate": 2.2675664768396037e-05, - "loss": 0.1822, + "epoch": 0.27, + "learning_rate": 3.6368761325249996e-05, + "loss": 0.1891, "step": 122920 }, { - "epoch": 0.55, - "learning_rate": 2.2673422716470112e-05, - "loss": 0.1805, + "epoch": 0.27, + "learning_rate": 3.6367642782040674e-05, + "loss": 0.192, "step": 122930 }, { - "epoch": 0.55, - "learning_rate": 2.267118066454419e-05, - "loss": 0.1818, + "epoch": 0.27, + "learning_rate": 3.6366524238831345e-05, + "loss": 0.1843, "step": 122940 }, { - "epoch": 0.55, - "learning_rate": 2.266893861261827e-05, - "loss": 0.1778, + "epoch": 0.27, + "learning_rate": 3.636540569562202e-05, + "loss": 0.1916, "step": 122950 }, { - "epoch": 0.55, - "learning_rate": 2.2666696560692345e-05, - "loss": 0.1797, + "epoch": 0.27, + "learning_rate": 3.63642871524127e-05, + "loss": 0.185, "step": 122960 }, { - "epoch": 0.55, - "learning_rate": 2.2664454508766424e-05, - "loss": 0.1862, + "epoch": 0.27, + "learning_rate": 3.636316860920337e-05, + "loss": 0.1891, "step": 122970 }, { - "epoch": 0.55, - "learning_rate": 2.2662212456840502e-05, - "loss": 0.1798, + "epoch": 0.27, + "learning_rate": 3.636205006599405e-05, + "loss": 0.1867, "step": 122980 }, { - "epoch": 0.55, - "learning_rate": 2.265997040491458e-05, - "loss": 0.1842, + "epoch": 0.27, + "learning_rate": 3.636093152278473e-05, + "loss": 0.1853, "step": 122990 }, { - "epoch": 0.55, - "learning_rate": 2.2657728352988656e-05, - "loss": 0.1805, + "epoch": 0.27, + "learning_rate": 3.6359812979575406e-05, + "loss": 0.1893, "step": 123000 }, { - "epoch": 0.55, - "learning_rate": 2.2655486301062735e-05, - "loss": 0.1828, + "epoch": 0.27, + "learning_rate": 3.6358694436366084e-05, + "loss": 0.187, "step": 123010 }, { - "epoch": 0.55, - "learning_rate": 2.2653244249136814e-05, - "loss": 0.1793, + "epoch": 0.27, + "learning_rate": 3.6357575893156755e-05, + "loss": 0.1821, "step": 123020 }, { - "epoch": 0.55, - "learning_rate": 2.265100219721089e-05, - "loss": 0.1728, + "epoch": 0.27, + "learning_rate": 3.635645734994743e-05, + "loss": 0.1892, "step": 123030 }, { - "epoch": 0.55, - "learning_rate": 2.2648760145284968e-05, - "loss": 0.184, + "epoch": 0.27, + "learning_rate": 3.6355338806738104e-05, + "loss": 0.1928, "step": 123040 }, { - "epoch": 0.55, - "learning_rate": 2.2646518093359043e-05, - "loss": 0.1821, + "epoch": 0.27, + "learning_rate": 3.635422026352878e-05, + "loss": 0.1893, "step": 123050 }, { - "epoch": 0.55, - "learning_rate": 2.2644276041433122e-05, - "loss": 0.1813, + "epoch": 0.27, + "learning_rate": 3.635310172031946e-05, + "loss": 0.1904, "step": 123060 }, { - "epoch": 0.55, - "learning_rate": 2.2642033989507197e-05, - "loss": 0.1811, + "epoch": 0.27, + "learning_rate": 3.635198317711013e-05, + "loss": 0.1878, "step": 123070 }, { - "epoch": 0.55, - "learning_rate": 2.2639791937581276e-05, - "loss": 0.1842, + "epoch": 0.27, + "learning_rate": 3.635086463390081e-05, + "loss": 0.1908, "step": 123080 }, { - "epoch": 0.55, - "learning_rate": 2.2637549885655355e-05, - "loss": 0.1831, + "epoch": 0.27, + "learning_rate": 3.634974609069148e-05, + "loss": 0.1844, "step": 123090 }, { - "epoch": 0.55, - "learning_rate": 2.263530783372943e-05, - "loss": 0.1829, + "epoch": 0.27, + "learning_rate": 3.6348627547482165e-05, + "loss": 0.1884, "step": 123100 }, { - "epoch": 0.55, - "learning_rate": 2.263306578180351e-05, - "loss": 0.1861, + "epoch": 0.27, + "learning_rate": 3.634750900427284e-05, + "loss": 0.1855, "step": 123110 }, { - "epoch": 0.55, - "learning_rate": 2.2630823729877584e-05, - "loss": 0.1816, + "epoch": 0.27, + "learning_rate": 3.6346390461063514e-05, + "loss": 0.1821, "step": 123120 }, { - "epoch": 0.55, - "learning_rate": 2.2628581677951663e-05, - "loss": 0.1804, + "epoch": 0.27, + "learning_rate": 3.634527191785419e-05, + "loss": 0.1856, "step": 123130 }, { - "epoch": 0.55, - "learning_rate": 2.2626339626025738e-05, - "loss": 0.1768, + "epoch": 0.27, + "learning_rate": 3.634415337464486e-05, + "loss": 0.19, "step": 123140 }, { - "epoch": 0.55, - "learning_rate": 2.2624097574099817e-05, - "loss": 0.1772, + "epoch": 0.27, + "learning_rate": 3.634303483143554e-05, + "loss": 0.1861, "step": 123150 }, { - "epoch": 0.55, - "learning_rate": 2.2621855522173895e-05, - "loss": 0.1802, + "epoch": 0.27, + "learning_rate": 3.634191628822621e-05, + "loss": 0.186, "step": 123160 }, { - "epoch": 0.55, - "learning_rate": 2.261961347024797e-05, - "loss": 0.1851, + "epoch": 0.27, + "learning_rate": 3.634079774501689e-05, + "loss": 0.1842, "step": 123170 }, { - "epoch": 0.55, - "learning_rate": 2.261737141832205e-05, - "loss": 0.1836, + "epoch": 0.27, + "learning_rate": 3.633967920180757e-05, + "loss": 0.1912, "step": 123180 }, { - "epoch": 0.55, - "learning_rate": 2.2615129366396125e-05, - "loss": 0.1825, + "epoch": 0.27, + "learning_rate": 3.633856065859824e-05, + "loss": 0.1952, "step": 123190 }, { - "epoch": 0.55, - "learning_rate": 2.2612887314470204e-05, - "loss": 0.182, + "epoch": 0.27, + "learning_rate": 3.633744211538892e-05, + "loss": 0.1793, "step": 123200 }, { - "epoch": 0.55, - "learning_rate": 2.261064526254428e-05, + "epoch": 0.28, + "learning_rate": 3.6336323572179595e-05, "loss": 0.1855, "step": 123210 }, { - "epoch": 0.55, - "learning_rate": 2.2608403210618358e-05, - "loss": 0.1766, + "epoch": 0.28, + "learning_rate": 3.633520502897027e-05, + "loss": 0.1848, "step": 123220 }, { - "epoch": 0.55, - "learning_rate": 2.2606161158692436e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.633408648576095e-05, + "loss": 0.1868, "step": 123230 }, { - "epoch": 0.55, - "learning_rate": 2.2603919106766515e-05, - "loss": 0.1785, + "epoch": 0.28, + "learning_rate": 3.633296794255162e-05, + "loss": 0.188, "step": 123240 }, { - "epoch": 0.55, - "learning_rate": 2.2601677054840594e-05, - "loss": 0.1765, + "epoch": 0.28, + "learning_rate": 3.63318493993423e-05, + "loss": 0.1821, "step": 123250 }, { - "epoch": 0.55, - "learning_rate": 2.259943500291467e-05, - "loss": 0.1757, + "epoch": 0.28, + "learning_rate": 3.633073085613297e-05, + "loss": 0.1868, "step": 123260 }, { - "epoch": 0.55, - "learning_rate": 2.2597192950988748e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.632961231292365e-05, + "loss": 0.1862, "step": 123270 }, { - "epoch": 0.55, - "learning_rate": 2.2594950899062823e-05, - "loss": 0.1782, + "epoch": 0.28, + "learning_rate": 3.632849376971433e-05, + "loss": 0.1899, "step": 123280 }, { - "epoch": 0.55, - "learning_rate": 2.2592708847136902e-05, - "loss": 0.1841, + "epoch": 0.28, + "learning_rate": 3.6327375226505e-05, + "loss": 0.1898, "step": 123290 }, { - "epoch": 0.55, - "learning_rate": 2.259046679521098e-05, - "loss": 0.182, + "epoch": 0.28, + "learning_rate": 3.6326256683295676e-05, + "loss": 0.1841, "step": 123300 }, { - "epoch": 0.55, - "learning_rate": 2.2588224743285056e-05, - "loss": 0.1867, + "epoch": 0.28, + "learning_rate": 3.6325138140086354e-05, + "loss": 0.1903, "step": 123310 }, { - "epoch": 0.55, - "learning_rate": 2.2585982691359135e-05, - "loss": 0.182, + "epoch": 0.28, + "learning_rate": 3.632401959687703e-05, + "loss": 0.1847, "step": 123320 }, { - "epoch": 0.55, - "learning_rate": 2.258374063943321e-05, - "loss": 0.1879, + "epoch": 0.28, + "learning_rate": 3.632290105366771e-05, + "loss": 0.1907, "step": 123330 }, { - "epoch": 0.55, - "learning_rate": 2.258149858750729e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.632178251045838e-05, + "loss": 0.1866, "step": 123340 }, { - "epoch": 0.55, - "learning_rate": 2.2579256535581364e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.632066396724906e-05, + "loss": 0.187, "step": 123350 }, { - "epoch": 0.55, - "learning_rate": 2.2577014483655443e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.631954542403973e-05, + "loss": 0.1808, "step": 123360 }, { - "epoch": 0.55, - "learning_rate": 2.257477243172952e-05, - "loss": 0.1828, + "epoch": 0.28, + "learning_rate": 3.631842688083041e-05, + "loss": 0.1819, "step": 123370 }, { - "epoch": 0.55, - "learning_rate": 2.2572530379803597e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.6317308337621086e-05, + "loss": 0.1878, "step": 123380 }, { - "epoch": 0.55, - "learning_rate": 2.2570288327877675e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.631618979441176e-05, + "loss": 0.191, "step": 123390 }, { - "epoch": 0.55, - "learning_rate": 2.256804627595175e-05, - "loss": 0.1817, + "epoch": 0.28, + "learning_rate": 3.6315071251202435e-05, + "loss": 0.1861, "step": 123400 }, { - "epoch": 0.55, - "learning_rate": 2.256580422402583e-05, - "loss": 0.1784, + "epoch": 0.28, + "learning_rate": 3.631395270799311e-05, + "loss": 0.1866, "step": 123410 }, { - "epoch": 0.55, - "learning_rate": 2.2563562172099905e-05, - "loss": 0.1837, + "epoch": 0.28, + "learning_rate": 3.631283416478379e-05, + "loss": 0.1884, "step": 123420 }, { - "epoch": 0.55, - "learning_rate": 2.2561320120173984e-05, - "loss": 0.1788, + "epoch": 0.28, + "learning_rate": 3.631171562157447e-05, + "loss": 0.1851, "step": 123430 }, { - "epoch": 0.55, - "learning_rate": 2.2559078068248062e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.631059707836514e-05, + "loss": 0.1897, "step": 123440 }, { - "epoch": 0.55, - "learning_rate": 2.2556836016322138e-05, - "loss": 0.1821, + "epoch": 0.28, + "learning_rate": 3.630947853515582e-05, + "loss": 0.1938, "step": 123450 }, { - "epoch": 0.55, - "learning_rate": 2.2554593964396216e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.630835999194649e-05, + "loss": 0.1877, "step": 123460 }, { - "epoch": 0.55, - "learning_rate": 2.255235191247029e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.630724144873717e-05, + "loss": 0.1877, "step": 123470 }, { - "epoch": 0.55, - "learning_rate": 2.255010986054437e-05, - "loss": 0.1857, + "epoch": 0.28, + "learning_rate": 3.630612290552784e-05, + "loss": 0.1849, "step": 123480 }, { - "epoch": 0.55, - "learning_rate": 2.254786780861845e-05, - "loss": 0.1856, + "epoch": 0.28, + "learning_rate": 3.6305004362318516e-05, + "loss": 0.186, "step": 123490 }, { - "epoch": 0.55, - "learning_rate": 2.2545625756692524e-05, - "loss": 0.1786, + "epoch": 0.28, + "learning_rate": 3.6303885819109194e-05, + "loss": 0.1863, "step": 123500 }, { - "epoch": 0.55, - "learning_rate": 2.2543383704766603e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.630276727589987e-05, + "loss": 0.1873, "step": 123510 }, { - "epoch": 0.55, - "learning_rate": 2.2541141652840682e-05, + "epoch": 0.28, + "learning_rate": 3.630164873269055e-05, "loss": 0.1835, "step": 123520 }, { - "epoch": 0.55, - "learning_rate": 2.253889960091476e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.630053018948122e-05, + "loss": 0.1901, "step": 123530 }, { - "epoch": 0.55, - "learning_rate": 2.2536657548988836e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.62994116462719e-05, + "loss": 0.1851, "step": 123540 }, { - "epoch": 0.55, - "learning_rate": 2.2534415497062915e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.6298293103062577e-05, + "loss": 0.1902, "step": 123550 }, { - "epoch": 0.55, - "learning_rate": 2.253217344513699e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.629717455985325e-05, + "loss": 0.1893, "step": 123560 }, { - "epoch": 0.55, - "learning_rate": 2.252993139321107e-05, - "loss": 0.1824, + "epoch": 0.28, + "learning_rate": 3.6296056016643926e-05, + "loss": 0.1872, "step": 123570 }, { - "epoch": 0.55, - "learning_rate": 2.2527689341285147e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.62949374734346e-05, + "loss": 0.1836, "step": 123580 }, { - "epoch": 0.55, - "learning_rate": 2.2525447289359223e-05, - "loss": 0.1827, + "epoch": 0.28, + "learning_rate": 3.6293818930225275e-05, + "loss": 0.1911, "step": 123590 }, { - "epoch": 0.55, - "learning_rate": 2.25232052374333e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.629270038701595e-05, + "loss": 0.1834, "step": 123600 }, { - "epoch": 0.55, - "learning_rate": 2.2520963185507377e-05, - "loss": 0.1854, + "epoch": 0.28, + "learning_rate": 3.6291581843806624e-05, + "loss": 0.1856, "step": 123610 }, { - "epoch": 0.55, - "learning_rate": 2.2518721133581455e-05, - "loss": 0.1817, + "epoch": 0.28, + "learning_rate": 3.62904633005973e-05, + "loss": 0.1894, "step": 123620 }, { - "epoch": 0.55, - "learning_rate": 2.251647908165553e-05, - "loss": 0.183, + "epoch": 0.28, + "learning_rate": 3.628934475738798e-05, + "loss": 0.186, "step": 123630 }, { - "epoch": 0.55, - "learning_rate": 2.251423702972961e-05, - "loss": 0.1776, + "epoch": 0.28, + "learning_rate": 3.628822621417866e-05, + "loss": 0.1918, "step": 123640 }, { - "epoch": 0.55, - "learning_rate": 2.2511994977803688e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.6287107670969336e-05, + "loss": 0.1877, "step": 123650 }, { - "epoch": 0.55, - "learning_rate": 2.2509752925877764e-05, - "loss": 0.1787, + "epoch": 0.28, + "learning_rate": 3.628598912776001e-05, + "loss": 0.1936, "step": 123660 }, { - "epoch": 0.55, - "learning_rate": 2.2507510873951842e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.6284870584550685e-05, + "loss": 0.1886, "step": 123670 }, { - "epoch": 0.55, - "learning_rate": 2.2505268822025918e-05, - "loss": 0.1805, + "epoch": 0.28, + "learning_rate": 3.6283752041341356e-05, + "loss": 0.1821, "step": 123680 }, { - "epoch": 0.55, - "learning_rate": 2.2503026770099996e-05, - "loss": 0.184, + "epoch": 0.28, + "learning_rate": 3.6282633498132034e-05, + "loss": 0.1861, "step": 123690 }, { - "epoch": 0.55, - "learning_rate": 2.250078471817407e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.628151495492271e-05, + "loss": 0.1868, "step": 123700 }, { - "epoch": 0.55, - "learning_rate": 2.249854266624815e-05, - "loss": 0.1864, + "epoch": 0.28, + "learning_rate": 3.628039641171338e-05, + "loss": 0.1855, "step": 123710 }, { - "epoch": 0.55, - "learning_rate": 2.249630061432223e-05, - "loss": 0.1839, + "epoch": 0.28, + "learning_rate": 3.627927786850406e-05, + "loss": 0.1792, "step": 123720 }, { - "epoch": 0.55, - "learning_rate": 2.2494058562396304e-05, - "loss": 0.1746, + "epoch": 0.28, + "learning_rate": 3.627815932529474e-05, + "loss": 0.1837, "step": 123730 }, { - "epoch": 0.55, - "learning_rate": 2.2491816510470383e-05, - "loss": 0.1782, + "epoch": 0.28, + "learning_rate": 3.6277040782085417e-05, + "loss": 0.1839, "step": 123740 }, { - "epoch": 0.55, - "learning_rate": 2.248957445854446e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.6275922238876094e-05, + "loss": 0.1879, "step": 123750 }, { - "epoch": 0.55, - "learning_rate": 2.2487332406618537e-05, - "loss": 0.1833, + "epoch": 0.28, + "learning_rate": 3.6274803695666766e-05, + "loss": 0.1829, "step": 123760 }, { - "epoch": 0.55, - "learning_rate": 2.2485090354692616e-05, - "loss": 0.1759, + "epoch": 0.28, + "learning_rate": 3.6273685152457444e-05, + "loss": 0.1849, "step": 123770 }, { - "epoch": 0.55, - "learning_rate": 2.2482848302766695e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.6272566609248115e-05, + "loss": 0.185, "step": 123780 }, { - "epoch": 0.55, - "learning_rate": 2.2480606250840773e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.627144806603879e-05, + "loss": 0.1881, "step": 123790 }, { - "epoch": 0.55, - "learning_rate": 2.247836419891485e-05, - "loss": 0.1804, + "epoch": 0.28, + "learning_rate": 3.6270329522829464e-05, + "loss": 0.1901, "step": 123800 }, { - "epoch": 0.55, - "learning_rate": 2.2476122146988927e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.626921097962014e-05, + "loss": 0.1873, "step": 123810 }, { - "epoch": 0.55, - "learning_rate": 2.2473880095063003e-05, - "loss": 0.1765, + "epoch": 0.28, + "learning_rate": 3.626809243641082e-05, + "loss": 0.1825, "step": 123820 }, { - "epoch": 0.55, - "learning_rate": 2.247163804313708e-05, - "loss": 0.1767, + "epoch": 0.28, + "learning_rate": 3.62669738932015e-05, + "loss": 0.1853, "step": 123830 }, { - "epoch": 0.55, - "learning_rate": 2.2469395991211157e-05, - "loss": 0.1778, + "epoch": 0.28, + "learning_rate": 3.6265855349992175e-05, + "loss": 0.1894, "step": 123840 }, { - "epoch": 0.55, - "learning_rate": 2.2467153939285235e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.626473680678285e-05, + "loss": 0.1883, "step": 123850 }, { - "epoch": 0.55, - "learning_rate": 2.2464911887359314e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.6263618263573525e-05, + "loss": 0.1913, "step": 123860 }, { - "epoch": 0.55, - "learning_rate": 2.246266983543339e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.62624997203642e-05, + "loss": 0.191, "step": 123870 }, { - "epoch": 0.55, - "learning_rate": 2.2460427783507468e-05, - "loss": 0.1769, + "epoch": 0.28, + "learning_rate": 3.6261381177154874e-05, + "loss": 0.1883, "step": 123880 }, { - "epoch": 0.55, - "learning_rate": 2.2458185731581544e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.626026263394555e-05, + "loss": 0.1853, "step": 123890 }, { - "epoch": 0.55, - "learning_rate": 2.2455943679655622e-05, - "loss": 0.1861, + "epoch": 0.28, + "learning_rate": 3.625914409073622e-05, + "loss": 0.1813, "step": 123900 }, { - "epoch": 0.55, - "learning_rate": 2.2453701627729698e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.62580255475269e-05, + "loss": 0.1907, "step": 123910 }, { - "epoch": 0.55, - "learning_rate": 2.2451459575803776e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.625690700431758e-05, + "loss": 0.1804, "step": 123920 }, { - "epoch": 0.55, - "learning_rate": 2.2449217523877855e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.6255788461108257e-05, + "loss": 0.1853, "step": 123930 }, { - "epoch": 0.55, - "learning_rate": 2.244697547195193e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.6254781772219865e-05, + "loss": 0.1872, "step": 123940 }, { - "epoch": 0.55, - "learning_rate": 2.244473342002601e-05, - "loss": 0.1831, + "epoch": 0.28, + "learning_rate": 3.6253663229010536e-05, + "loss": 0.1821, "step": 123950 }, { - "epoch": 0.55, - "learning_rate": 2.2442491368100084e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.6252544685801214e-05, + "loss": 0.1848, "step": 123960 }, { - "epoch": 0.55, - "learning_rate": 2.2440249316174163e-05, - "loss": 0.1831, + "epoch": 0.28, + "learning_rate": 3.6251426142591886e-05, + "loss": 0.1891, "step": 123970 }, { - "epoch": 0.55, - "learning_rate": 2.243800726424824e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.6250307599382563e-05, + "loss": 0.1873, "step": 123980 }, { - "epoch": 0.55, - "learning_rate": 2.2435765212322317e-05, - "loss": 0.1826, + "epoch": 0.28, + "learning_rate": 3.624918905617324e-05, + "loss": 0.1856, "step": 123990 }, { - "epoch": 0.55, - "learning_rate": 2.2433523160396396e-05, - "loss": 0.1796, + "epoch": 0.28, + "learning_rate": 3.624807051296392e-05, + "loss": 0.1837, "step": 124000 }, { - "epoch": 0.55, - "learning_rate": 2.243128110847047e-05, - "loss": 0.1772, + "epoch": 0.28, + "learning_rate": 3.62469519697546e-05, + "loss": 0.1885, "step": 124010 }, { - "epoch": 0.55, - "learning_rate": 2.242903905654455e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.624583342654527e-05, + "loss": 0.1931, "step": 124020 }, { - "epoch": 0.55, - "learning_rate": 2.242679700461863e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.6244714883335946e-05, + "loss": 0.1806, "step": 124030 }, { - "epoch": 0.55, - "learning_rate": 2.2424554952692704e-05, - "loss": 0.177, + "epoch": 0.28, + "learning_rate": 3.6243596340126624e-05, + "loss": 0.1855, "step": 124040 }, { - "epoch": 0.55, - "learning_rate": 2.2422312900766783e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.6242477796917295e-05, + "loss": 0.1842, "step": 124050 }, { - "epoch": 0.55, - "learning_rate": 2.242007084884086e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.624135925370797e-05, + "loss": 0.1905, "step": 124060 }, { - "epoch": 0.55, - "learning_rate": 2.241782879691494e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.6240240710498644e-05, + "loss": 0.1846, "step": 124070 }, { - "epoch": 0.55, - "learning_rate": 2.2415586744989016e-05, - "loss": 0.1787, + "epoch": 0.28, + "learning_rate": 3.623912216728932e-05, + "loss": 0.1859, "step": 124080 }, { - "epoch": 0.55, - "learning_rate": 2.2413344693063094e-05, - "loss": 0.1815, + "epoch": 0.28, + "learning_rate": 3.623800362408e-05, + "loss": 0.1898, "step": 124090 }, { - "epoch": 0.55, - "learning_rate": 2.241110264113717e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.623688508087068e-05, + "loss": 0.1847, "step": 124100 }, { - "epoch": 0.55, - "learning_rate": 2.2408860589211248e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.6235766537661356e-05, + "loss": 0.1812, "step": 124110 }, { - "epoch": 0.55, - "learning_rate": 2.2406618537285324e-05, - "loss": 0.1756, + "epoch": 0.28, + "learning_rate": 3.623464799445203e-05, + "loss": 0.1843, "step": 124120 }, { - "epoch": 0.55, - "learning_rate": 2.2404376485359402e-05, - "loss": 0.1895, + "epoch": 0.28, + "learning_rate": 3.6233529451242705e-05, + "loss": 0.1813, "step": 124130 }, { - "epoch": 0.55, - "learning_rate": 2.240213443343348e-05, - "loss": 0.1752, + "epoch": 0.28, + "learning_rate": 3.623241090803338e-05, + "loss": 0.1859, "step": 124140 }, { - "epoch": 0.55, - "learning_rate": 2.2399892381507556e-05, - "loss": 0.1858, + "epoch": 0.28, + "learning_rate": 3.6231292364824054e-05, + "loss": 0.1821, "step": 124150 }, { - "epoch": 0.55, - "learning_rate": 2.2397650329581635e-05, - "loss": 0.185, + "epoch": 0.28, + "learning_rate": 3.623017382161473e-05, + "loss": 0.1874, "step": 124160 }, { - "epoch": 0.55, - "learning_rate": 2.239540827765571e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.6229055278405403e-05, + "loss": 0.1846, "step": 124170 }, { - "epoch": 0.55, - "learning_rate": 2.239316622572979e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.622793673519608e-05, + "loss": 0.1872, "step": 124180 }, { - "epoch": 0.55, - "learning_rate": 2.2390924173803868e-05, - "loss": 0.1761, + "epoch": 0.28, + "learning_rate": 3.622681819198675e-05, + "loss": 0.1844, "step": 124190 }, { - "epoch": 0.55, - "learning_rate": 2.2388682121877943e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.622569964877743e-05, + "loss": 0.1884, "step": 124200 }, { - "epoch": 0.55, - "learning_rate": 2.2386440069952022e-05, - "loss": 0.1749, + "epoch": 0.28, + "learning_rate": 3.622458110556811e-05, + "loss": 0.1931, "step": 124210 }, { - "epoch": 0.55, - "learning_rate": 2.2384198018026097e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.6223462562358786e-05, + "loss": 0.1839, "step": 124220 }, { - "epoch": 0.55, - "learning_rate": 2.2381955966100176e-05, - "loss": 0.1859, + "epoch": 0.28, + "learning_rate": 3.6222344019149464e-05, + "loss": 0.1827, "step": 124230 }, { - "epoch": 0.55, - "learning_rate": 2.237971391417425e-05, - "loss": 0.1771, + "epoch": 0.28, + "learning_rate": 3.6221225475940135e-05, + "loss": 0.1854, "step": 124240 }, { - "epoch": 0.55, - "learning_rate": 2.237747186224833e-05, - "loss": 0.1846, + "epoch": 0.28, + "learning_rate": 3.622010693273081e-05, + "loss": 0.1885, "step": 124250 }, { - "epoch": 0.55, - "learning_rate": 2.237522981032241e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.621898838952149e-05, + "loss": 0.1903, "step": 124260 }, { - "epoch": 0.55, - "learning_rate": 2.2372987758396484e-05, - "loss": 0.1827, + "epoch": 0.28, + "learning_rate": 3.621786984631216e-05, + "loss": 0.1887, "step": 124270 }, { - "epoch": 0.55, - "learning_rate": 2.2370745706470563e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.621675130310284e-05, + "loss": 0.1856, "step": 124280 }, { - "epoch": 0.55, - "learning_rate": 2.2368503654544638e-05, - "loss": 0.1759, + "epoch": 0.28, + "learning_rate": 3.621563275989351e-05, + "loss": 0.1903, "step": 124290 }, { - "epoch": 0.55, - "learning_rate": 2.2366261602618717e-05, - "loss": 0.1776, + "epoch": 0.28, + "learning_rate": 3.621451421668419e-05, + "loss": 0.1832, "step": 124300 }, { - "epoch": 0.55, - "learning_rate": 2.2364019550692796e-05, - "loss": 0.1796, + "epoch": 0.28, + "learning_rate": 3.621339567347487e-05, + "loss": 0.1906, "step": 124310 }, { - "epoch": 0.55, - "learning_rate": 2.2361777498766874e-05, - "loss": 0.1818, + "epoch": 0.28, + "learning_rate": 3.6212277130265545e-05, + "loss": 0.1786, "step": 124320 }, { - "epoch": 0.56, - "learning_rate": 2.235953544684095e-05, - "loss": 0.1764, + "epoch": 0.28, + "learning_rate": 3.621115858705622e-05, + "loss": 0.1843, "step": 124330 }, { - "epoch": 0.56, - "learning_rate": 2.2357293394915028e-05, - "loss": 0.1762, + "epoch": 0.28, + "learning_rate": 3.6210040043846894e-05, + "loss": 0.1876, "step": 124340 }, { - "epoch": 0.56, - "learning_rate": 2.2355051342989107e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.620892150063757e-05, + "loss": 0.191, "step": 124350 }, { - "epoch": 0.56, - "learning_rate": 2.2352809291063182e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.620780295742825e-05, + "loss": 0.1855, "step": 124360 }, { - "epoch": 0.56, - "learning_rate": 2.235056723913726e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.620668441421892e-05, + "loss": 0.1844, "step": 124370 }, { - "epoch": 0.56, - "learning_rate": 2.2348325187211336e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.62055658710096e-05, + "loss": 0.1836, "step": 124380 }, { - "epoch": 0.56, - "learning_rate": 2.2346083135285415e-05, - "loss": 0.1783, + "epoch": 0.28, + "learning_rate": 3.620444732780027e-05, + "loss": 0.1844, "step": 124390 }, { - "epoch": 0.56, - "learning_rate": 2.2343841083359494e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.620332878459095e-05, + "loss": 0.1821, "step": 124400 }, { - "epoch": 0.56, - "learning_rate": 2.234159903143357e-05, - "loss": 0.1762, + "epoch": 0.28, + "learning_rate": 3.6202210241381626e-05, + "loss": 0.1897, "step": 124410 }, { - "epoch": 0.56, - "learning_rate": 2.2339356979507648e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.6201091698172304e-05, + "loss": 0.1838, "step": 124420 }, { - "epoch": 0.56, - "learning_rate": 2.2337114927581723e-05, - "loss": 0.1811, + "epoch": 0.28, + "learning_rate": 3.619997315496298e-05, + "loss": 0.1897, "step": 124430 }, { - "epoch": 0.56, - "learning_rate": 2.2334872875655802e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.6198966466074584e-05, + "loss": 0.1844, "step": 124440 }, { - "epoch": 0.56, - "learning_rate": 2.2332630823729877e-05, - "loss": 0.1816, + "epoch": 0.28, + "learning_rate": 3.619784792286526e-05, + "loss": 0.1819, "step": 124450 }, { - "epoch": 0.56, - "learning_rate": 2.2330388771803956e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.619672937965593e-05, + "loss": 0.1847, "step": 124460 }, { - "epoch": 0.56, - "learning_rate": 2.2328146719878035e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.619561083644661e-05, + "loss": 0.1854, "step": 124470 }, { - "epoch": 0.56, - "learning_rate": 2.232590466795211e-05, - "loss": 0.183, + "epoch": 0.28, + "learning_rate": 3.619449229323729e-05, + "loss": 0.1849, "step": 124480 }, { - "epoch": 0.56, - "learning_rate": 2.232366261602619e-05, - "loss": 0.1772, + "epoch": 0.28, + "learning_rate": 3.619337375002797e-05, + "loss": 0.1863, "step": 124490 }, { - "epoch": 0.56, - "learning_rate": 2.2321420564100264e-05, - "loss": 0.1757, + "epoch": 0.28, + "learning_rate": 3.6192255206818645e-05, + "loss": 0.1828, "step": 124500 }, { - "epoch": 0.56, - "learning_rate": 2.2319178512174343e-05, - "loss": 0.1848, + "epoch": 0.28, + "learning_rate": 3.6191136663609316e-05, + "loss": 0.1812, "step": 124510 }, { - "epoch": 0.56, - "learning_rate": 2.2316936460248418e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.6190018120399994e-05, + "loss": 0.1909, "step": 124520 }, { - "epoch": 0.56, - "learning_rate": 2.2314694408322497e-05, - "loss": 0.1764, + "epoch": 0.28, + "learning_rate": 3.618889957719067e-05, + "loss": 0.1799, "step": 124530 }, { - "epoch": 0.56, - "learning_rate": 2.2312452356396576e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.618778103398134e-05, + "loss": 0.1835, "step": 124540 }, { - "epoch": 0.56, - "learning_rate": 2.231021030447065e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.618666249077202e-05, + "loss": 0.1895, "step": 124550 }, { - "epoch": 0.56, - "learning_rate": 2.230796825254473e-05, - "loss": 0.1791, + "epoch": 0.28, + "learning_rate": 3.618554394756269e-05, + "loss": 0.1808, "step": 124560 }, { - "epoch": 0.56, - "learning_rate": 2.2305726200618808e-05, - "loss": 0.177, + "epoch": 0.28, + "learning_rate": 3.618442540435337e-05, + "loss": 0.1844, "step": 124570 }, { - "epoch": 0.56, - "learning_rate": 2.2303484148692884e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.618330686114405e-05, + "loss": 0.1836, "step": 124580 }, { - "epoch": 0.56, - "learning_rate": 2.2301242096766962e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.6182188317934726e-05, + "loss": 0.1856, "step": 124590 }, { - "epoch": 0.56, - "learning_rate": 2.229900004484104e-05, - "loss": 0.1833, + "epoch": 0.28, + "learning_rate": 3.6181069774725404e-05, + "loss": 0.1825, "step": 124600 }, { - "epoch": 0.56, - "learning_rate": 2.229675799291512e-05, - "loss": 0.1829, + "epoch": 0.28, + "learning_rate": 3.6179951231516075e-05, + "loss": 0.1812, "step": 124610 }, { - "epoch": 0.56, - "learning_rate": 2.2294515940989195e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.617883268830675e-05, + "loss": 0.1868, "step": 124620 }, { - "epoch": 0.56, - "learning_rate": 2.2292273889063274e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.6177714145097424e-05, + "loss": 0.188, "step": 124630 }, { - "epoch": 0.56, - "learning_rate": 2.229003183713735e-05, + "epoch": 0.28, + "learning_rate": 3.61765956018881e-05, "loss": 0.1843, "step": 124640 }, { - "epoch": 0.56, - "learning_rate": 2.2287789785211428e-05, - "loss": 0.183, + "epoch": 0.28, + "learning_rate": 3.617547705867878e-05, + "loss": 0.1875, "step": 124650 }, { - "epoch": 0.56, - "learning_rate": 2.2285547733285503e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.617435851546945e-05, + "loss": 0.1826, "step": 124660 }, { - "epoch": 0.56, - "learning_rate": 2.2283305681359582e-05, + "epoch": 0.28, + "learning_rate": 3.617323997226013e-05, "loss": 0.1847, "step": 124670 }, { - "epoch": 0.56, - "learning_rate": 2.228106362943366e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.617212142905081e-05, + "loss": 0.184, "step": 124680 }, { - "epoch": 0.56, - "learning_rate": 2.2278821577507736e-05, - "loss": 0.1827, + "epoch": 0.28, + "learning_rate": 3.6171002885841485e-05, + "loss": 0.1859, "step": 124690 }, { - "epoch": 0.56, - "learning_rate": 2.2276579525581815e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.616988434263216e-05, + "loss": 0.1847, "step": 124700 }, { - "epoch": 0.56, - "learning_rate": 2.227433747365589e-05, - "loss": 0.1889, + "epoch": 0.28, + "learning_rate": 3.6168765799422834e-05, + "loss": 0.1874, "step": 124710 }, { - "epoch": 0.56, - "learning_rate": 2.227209542172997e-05, - "loss": 0.1815, + "epoch": 0.28, + "learning_rate": 3.616764725621351e-05, + "loss": 0.1827, "step": 124720 }, { - "epoch": 0.56, - "learning_rate": 2.2269853369804044e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.616652871300418e-05, + "loss": 0.1815, "step": 124730 }, { - "epoch": 0.56, - "learning_rate": 2.2267611317878123e-05, - "loss": 0.1739, + "epoch": 0.28, + "learning_rate": 3.616541016979486e-05, + "loss": 0.1863, "step": 124740 }, { - "epoch": 0.56, - "learning_rate": 2.22653692659522e-05, - "loss": 0.176, + "epoch": 0.28, + "learning_rate": 3.616429162658554e-05, + "loss": 0.1838, "step": 124750 }, { - "epoch": 0.56, - "learning_rate": 2.2263127214026277e-05, - "loss": 0.1746, + "epoch": 0.28, + "learning_rate": 3.616317308337621e-05, + "loss": 0.18, "step": 124760 }, { - "epoch": 0.56, - "learning_rate": 2.2260885162100356e-05, - "loss": 0.1777, + "epoch": 0.28, + "learning_rate": 3.616205454016689e-05, + "loss": 0.1909, "step": 124770 }, { - "epoch": 0.56, - "learning_rate": 2.225864311017443e-05, - "loss": 0.1824, + "epoch": 0.28, + "learning_rate": 3.616093599695756e-05, + "loss": 0.1829, "step": 124780 }, { - "epoch": 0.56, - "learning_rate": 2.225640105824851e-05, - "loss": 0.1826, + "epoch": 0.28, + "learning_rate": 3.615981745374824e-05, + "loss": 0.1849, "step": 124790 }, { - "epoch": 0.56, - "learning_rate": 2.2254159006322585e-05, - "loss": 0.1828, + "epoch": 0.28, + "learning_rate": 3.615869891053892e-05, + "loss": 0.1918, "step": 124800 }, { - "epoch": 0.56, - "learning_rate": 2.2251916954396664e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.615758036732959e-05, + "loss": 0.1835, "step": 124810 }, { - "epoch": 0.56, - "learning_rate": 2.2249674902470742e-05, - "loss": 0.176, + "epoch": 0.28, + "learning_rate": 3.615646182412027e-05, + "loss": 0.1857, "step": 124820 }, { - "epoch": 0.56, - "learning_rate": 2.2247432850544818e-05, - "loss": 0.18, + "epoch": 0.28, + "learning_rate": 3.615534328091094e-05, + "loss": 0.1925, "step": 124830 }, { - "epoch": 0.56, - "learning_rate": 2.2245190798618896e-05, - "loss": 0.188, + "epoch": 0.28, + "learning_rate": 3.615422473770162e-05, + "loss": 0.1838, "step": 124840 }, { - "epoch": 0.56, - "learning_rate": 2.2242948746692975e-05, - "loss": 0.1864, + "epoch": 0.28, + "learning_rate": 3.61531061944923e-05, + "loss": 0.1922, "step": 124850 }, { - "epoch": 0.56, - "learning_rate": 2.2240706694767054e-05, - "loss": 0.1836, + "epoch": 0.28, + "learning_rate": 3.615198765128297e-05, + "loss": 0.1857, "step": 124860 }, { - "epoch": 0.56, - "learning_rate": 2.223846464284113e-05, - "loss": 0.1754, + "epoch": 0.28, + "learning_rate": 3.615086910807365e-05, + "loss": 0.1851, "step": 124870 }, { - "epoch": 0.56, - "learning_rate": 2.2236222590915208e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.614975056486432e-05, + "loss": 0.1792, "step": 124880 }, { - "epoch": 0.56, - "learning_rate": 2.2233980538989287e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.6148632021654996e-05, + "loss": 0.1878, "step": 124890 }, { - "epoch": 0.56, - "learning_rate": 2.2231738487063362e-05, - "loss": 0.1777, + "epoch": 0.28, + "learning_rate": 3.6147513478445674e-05, + "loss": 0.1806, "step": 124900 }, { - "epoch": 0.56, - "learning_rate": 2.222949643513744e-05, - "loss": 0.1754, + "epoch": 0.28, + "learning_rate": 3.614639493523635e-05, + "loss": 0.1896, "step": 124910 }, { - "epoch": 0.56, - "learning_rate": 2.2227254383211516e-05, - "loss": 0.1787, + "epoch": 0.28, + "learning_rate": 3.614527639202703e-05, + "loss": 0.1811, "step": 124920 }, { - "epoch": 0.56, - "learning_rate": 2.2225012331285595e-05, - "loss": 0.1839, + "epoch": 0.28, + "learning_rate": 3.61441578488177e-05, + "loss": 0.1837, "step": 124930 }, { - "epoch": 0.56, - "learning_rate": 2.222277027935967e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.614303930560838e-05, + "loss": 0.1825, "step": 124940 }, { - "epoch": 0.56, - "learning_rate": 2.222052822743375e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.614192076239905e-05, + "loss": 0.1905, "step": 124950 }, { - "epoch": 0.56, - "learning_rate": 2.2218286175507827e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.614080221918973e-05, + "loss": 0.1849, "step": 124960 }, { - "epoch": 0.56, - "learning_rate": 2.2216044123581903e-05, - "loss": 0.1811, + "epoch": 0.28, + "learning_rate": 3.6139683675980406e-05, + "loss": 0.1853, "step": 124970 }, { - "epoch": 0.56, - "learning_rate": 2.221380207165598e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.613856513277108e-05, + "loss": 0.1854, "step": 124980 }, { - "epoch": 0.56, - "learning_rate": 2.2211560019730057e-05, - "loss": 0.1804, + "epoch": 0.28, + "learning_rate": 3.6137446589561755e-05, + "loss": 0.1875, "step": 124990 }, { - "epoch": 0.56, - "learning_rate": 2.2209317967804136e-05, - "loss": 0.1775, + "epoch": 0.28, + "learning_rate": 3.613632804635243e-05, + "loss": 0.1757, "step": 125000 }, { - "epoch": 0.56, - "learning_rate": 2.220707591587821e-05, - "loss": 0.1848, + "epoch": 0.28, + "learning_rate": 3.613520950314311e-05, + "loss": 0.1834, "step": 125010 }, { - "epoch": 0.56, - "learning_rate": 2.220483386395229e-05, - "loss": 0.1734, + "epoch": 0.28, + "learning_rate": 3.613409095993379e-05, + "loss": 0.1893, "step": 125020 }, { - "epoch": 0.56, - "learning_rate": 2.220259181202637e-05, - "loss": 0.176, + "epoch": 0.28, + "learning_rate": 3.613297241672446e-05, + "loss": 0.1836, "step": 125030 }, { - "epoch": 0.56, - "learning_rate": 2.2200349760100444e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.613185387351514e-05, + "loss": 0.1833, "step": 125040 }, { - "epoch": 0.56, - "learning_rate": 2.2198107708174522e-05, - "loss": 0.1747, + "epoch": 0.28, + "learning_rate": 3.613073533030581e-05, + "loss": 0.1858, "step": 125050 }, { - "epoch": 0.56, - "learning_rate": 2.2195865656248598e-05, - "loss": 0.175, + "epoch": 0.28, + "learning_rate": 3.612961678709649e-05, + "loss": 0.1845, "step": 125060 }, { - "epoch": 0.56, - "learning_rate": 2.2193623604322676e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.6128498243887165e-05, + "loss": 0.1859, "step": 125070 }, { - "epoch": 0.56, - "learning_rate": 2.2191381552396752e-05, - "loss": 0.1865, + "epoch": 0.28, + "learning_rate": 3.6127379700677836e-05, + "loss": 0.1861, "step": 125080 }, { - "epoch": 0.56, - "learning_rate": 2.218913950047083e-05, - "loss": 0.1831, + "epoch": 0.28, + "learning_rate": 3.6126261157468514e-05, + "loss": 0.1836, "step": 125090 }, { - "epoch": 0.56, - "learning_rate": 2.218689744854491e-05, - "loss": 0.1829, + "epoch": 0.28, + "learning_rate": 3.612514261425919e-05, + "loss": 0.1748, "step": 125100 }, { - "epoch": 0.56, - "learning_rate": 2.2184655396618988e-05, - "loss": 0.1717, + "epoch": 0.28, + "learning_rate": 3.612402407104987e-05, + "loss": 0.1846, "step": 125110 }, { - "epoch": 0.56, - "learning_rate": 2.2182413344693063e-05, - "loss": 0.1827, + "epoch": 0.28, + "learning_rate": 3.612290552784055e-05, + "loss": 0.1823, "step": 125120 }, { - "epoch": 0.56, - "learning_rate": 2.2180171292767142e-05, - "loss": 0.1805, + "epoch": 0.28, + "learning_rate": 3.612178698463122e-05, + "loss": 0.1819, "step": 125130 }, { - "epoch": 0.56, - "learning_rate": 2.217792924084122e-05, - "loss": 0.1717, + "epoch": 0.28, + "learning_rate": 3.61206684414219e-05, + "loss": 0.1868, "step": 125140 }, { - "epoch": 0.56, - "learning_rate": 2.2175687188915296e-05, - "loss": 0.1819, + "epoch": 0.28, + "learning_rate": 3.611954989821257e-05, + "loss": 0.1824, "step": 125150 }, { - "epoch": 0.56, - "learning_rate": 2.2173445136989375e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.6118431355003246e-05, + "loss": 0.1834, "step": 125160 }, { - "epoch": 0.56, - "learning_rate": 2.2171203085063453e-05, - "loss": 0.1845, + "epoch": 0.28, + "learning_rate": 3.611731281179392e-05, + "loss": 0.1829, "step": 125170 }, { - "epoch": 0.56, - "learning_rate": 2.216896103313753e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.6116194268584595e-05, + "loss": 0.1874, "step": 125180 }, { - "epoch": 0.56, - "learning_rate": 2.2166718981211607e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.611507572537527e-05, + "loss": 0.1842, "step": 125190 }, { - "epoch": 0.56, - "learning_rate": 2.2164476929285683e-05, - "loss": 0.1711, + "epoch": 0.28, + "learning_rate": 3.6113957182165944e-05, + "loss": 0.1888, "step": 125200 }, { - "epoch": 0.56, - "learning_rate": 2.216223487735976e-05, - "loss": 0.1844, + "epoch": 0.28, + "learning_rate": 3.611283863895663e-05, + "loss": 0.1826, "step": 125210 }, { - "epoch": 0.56, - "learning_rate": 2.2159992825433837e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.61117200957473e-05, + "loss": 0.1853, "step": 125220 }, { - "epoch": 0.56, - "learning_rate": 2.2157750773507916e-05, - "loss": 0.1796, + "epoch": 0.28, + "learning_rate": 3.611060155253798e-05, + "loss": 0.1816, "step": 125230 }, { - "epoch": 0.56, - "learning_rate": 2.2155508721581994e-05, - "loss": 0.184, + "epoch": 0.28, + "learning_rate": 3.6109483009328656e-05, + "loss": 0.1835, "step": 125240 }, { - "epoch": 0.56, - "learning_rate": 2.215326666965607e-05, - "loss": 0.1818, + "epoch": 0.28, + "learning_rate": 3.610836446611933e-05, + "loss": 0.1861, "step": 125250 }, { - "epoch": 0.56, - "learning_rate": 2.215102461773015e-05, - "loss": 0.1772, + "epoch": 0.28, + "learning_rate": 3.6107245922910005e-05, + "loss": 0.1838, "step": 125260 }, { - "epoch": 0.56, - "learning_rate": 2.2148782565804224e-05, - "loss": 0.1737, + "epoch": 0.28, + "learning_rate": 3.6106127379700676e-05, + "loss": 0.1875, "step": 125270 }, { - "epoch": 0.56, - "learning_rate": 2.2146540513878302e-05, - "loss": 0.1815, + "epoch": 0.28, + "learning_rate": 3.6105008836491354e-05, + "loss": 0.1864, "step": 125280 }, { - "epoch": 0.56, - "learning_rate": 2.2144298461952378e-05, - "loss": 0.1788, + "epoch": 0.28, + "learning_rate": 3.610389029328203e-05, + "loss": 0.1835, "step": 125290 }, { - "epoch": 0.56, - "learning_rate": 2.2142056410026456e-05, - "loss": 0.1864, + "epoch": 0.28, + "learning_rate": 3.61027717500727e-05, + "loss": 0.1846, "step": 125300 }, { - "epoch": 0.56, - "learning_rate": 2.2139814358100535e-05, - "loss": 0.1782, + "epoch": 0.28, + "learning_rate": 3.610165320686338e-05, + "loss": 0.1859, "step": 125310 }, { - "epoch": 0.56, - "learning_rate": 2.213757230617461e-05, - "loss": 0.1792, + "epoch": 0.28, + "learning_rate": 3.610053466365406e-05, + "loss": 0.1841, "step": 125320 }, { - "epoch": 0.56, - "learning_rate": 2.213533025424869e-05, - "loss": 0.1834, + "epoch": 0.28, + "learning_rate": 3.609941612044474e-05, + "loss": 0.1837, "step": 125330 }, { - "epoch": 0.56, - "learning_rate": 2.2133088202322765e-05, - "loss": 0.1726, + "epoch": 0.28, + "learning_rate": 3.6098297577235415e-05, + "loss": 0.1841, "step": 125340 }, { - "epoch": 0.56, - "learning_rate": 2.2130846150396843e-05, - "loss": 0.1785, + "epoch": 0.28, + "learning_rate": 3.6097179034026086e-05, + "loss": 0.191, "step": 125350 }, { - "epoch": 0.56, - "learning_rate": 2.2128604098470922e-05, - "loss": 0.1739, + "epoch": 0.28, + "learning_rate": 3.6096060490816764e-05, + "loss": 0.1816, "step": 125360 }, { - "epoch": 0.56, - "learning_rate": 2.2126362046544997e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.6094941947607435e-05, + "loss": 0.181, "step": 125370 }, { - "epoch": 0.56, - "learning_rate": 2.2124119994619076e-05, - "loss": 0.1748, + "epoch": 0.28, + "learning_rate": 3.609382340439811e-05, + "loss": 0.1857, "step": 125380 }, { - "epoch": 0.56, - "learning_rate": 2.2121877942693155e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.609270486118879e-05, + "loss": 0.1885, "step": 125390 }, { - "epoch": 0.56, - "learning_rate": 2.2119635890767233e-05, - "loss": 0.1737, + "epoch": 0.28, + "learning_rate": 3.609158631797946e-05, + "loss": 0.1839, "step": 125400 }, { - "epoch": 0.56, - "learning_rate": 2.211739383884131e-05, - "loss": 0.1841, + "epoch": 0.28, + "learning_rate": 3.609046777477014e-05, + "loss": 0.1803, "step": 125410 }, { - "epoch": 0.56, - "learning_rate": 2.2115151786915387e-05, - "loss": 0.1827, + "epoch": 0.28, + "learning_rate": 3.608934923156082e-05, + "loss": 0.1855, "step": 125420 }, { - "epoch": 0.56, - "learning_rate": 2.2112909734989463e-05, - "loss": 0.1845, + "epoch": 0.28, + "learning_rate": 3.6088230688351496e-05, + "loss": 0.1814, "step": 125430 }, { - "epoch": 0.56, - "learning_rate": 2.211066768306354e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.6087112145142174e-05, + "loss": 0.1824, "step": 125440 }, { - "epoch": 0.56, - "learning_rate": 2.210842563113762e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.6085993601932845e-05, + "loss": 0.1888, "step": 125450 }, { - "epoch": 0.56, - "learning_rate": 2.2106183579211696e-05, - "loss": 0.1798, + "epoch": 0.28, + "learning_rate": 3.608487505872352e-05, + "loss": 0.1837, "step": 125460 }, { - "epoch": 0.56, - "learning_rate": 2.2103941527285774e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.6083756515514194e-05, + "loss": 0.1892, "step": 125470 }, { - "epoch": 0.56, - "learning_rate": 2.210169947535985e-05, - "loss": 0.1792, + "epoch": 0.28, + "learning_rate": 3.608263797230487e-05, + "loss": 0.1842, "step": 125480 }, { - "epoch": 0.56, - "learning_rate": 2.209945742343393e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.608151942909554e-05, + "loss": 0.1835, "step": 125490 }, { - "epoch": 0.56, - "learning_rate": 2.2097215371508004e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.608040088588622e-05, + "loss": 0.1896, "step": 125500 }, { - "epoch": 0.56, - "learning_rate": 2.2094973319582082e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.60792823426769e-05, + "loss": 0.1936, "step": 125510 }, { - "epoch": 0.56, - "learning_rate": 2.209273126765616e-05, - "loss": 0.1769, + "epoch": 0.28, + "learning_rate": 3.607816379946758e-05, + "loss": 0.1778, "step": 125520 }, { - "epoch": 0.56, - "learning_rate": 2.2090489215730236e-05, - "loss": 0.1785, + "epoch": 0.28, + "learning_rate": 3.6077045256258255e-05, + "loss": 0.1834, "step": 125530 }, { - "epoch": 0.56, - "learning_rate": 2.2088247163804315e-05, - "loss": 0.18, + "epoch": 0.28, + "learning_rate": 3.6075926713048926e-05, + "loss": 0.1768, "step": 125540 }, { - "epoch": 0.56, - "learning_rate": 2.208600511187839e-05, - "loss": 0.1842, + "epoch": 0.28, + "learning_rate": 3.6074808169839604e-05, + "loss": 0.1847, "step": 125550 }, { - "epoch": 0.56, - "learning_rate": 2.208376305995247e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.607368962663028e-05, + "loss": 0.1854, "step": 125560 }, { - "epoch": 0.56, - "learning_rate": 2.2081521008026548e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.607257108342095e-05, + "loss": 0.1822, "step": 125570 }, { - "epoch": 0.56, - "learning_rate": 2.2079278956100623e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.607145254021163e-05, + "loss": 0.1864, "step": 125580 }, { - "epoch": 0.56, - "learning_rate": 2.2077036904174702e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.60703339970023e-05, + "loss": 0.1904, "step": 125590 }, { - "epoch": 0.56, - "learning_rate": 2.2074794852248777e-05, - "loss": 0.1826, + "epoch": 0.28, + "learning_rate": 3.606921545379298e-05, + "loss": 0.1893, "step": 125600 }, { - "epoch": 0.56, - "learning_rate": 2.2072552800322856e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.606809691058366e-05, + "loss": 0.1845, "step": 125610 }, { - "epoch": 0.56, - "learning_rate": 2.207031074839693e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.606697836737433e-05, + "loss": 0.1919, "step": 125620 }, { - "epoch": 0.56, - "learning_rate": 2.206806869647101e-05, - "loss": 0.1869, + "epoch": 0.28, + "learning_rate": 3.6065859824165014e-05, + "loss": 0.1878, "step": 125630 }, { - "epoch": 0.56, - "learning_rate": 2.206582664454509e-05, - "loss": 0.1853, + "epoch": 0.28, + "learning_rate": 3.6064741280955685e-05, + "loss": 0.1854, "step": 125640 }, { - "epoch": 0.56, - "learning_rate": 2.2063584592619168e-05, - "loss": 0.1829, + "epoch": 0.28, + "learning_rate": 3.606362273774636e-05, + "loss": 0.1887, "step": 125650 }, { - "epoch": 0.56, - "learning_rate": 2.2061342540693243e-05, - "loss": 0.1753, + "epoch": 0.28, + "learning_rate": 3.606250419453704e-05, + "loss": 0.1808, "step": 125660 }, { - "epoch": 0.56, - "learning_rate": 2.205910048876732e-05, - "loss": 0.1788, + "epoch": 0.28, + "learning_rate": 3.606138565132771e-05, + "loss": 0.1849, "step": 125670 }, { - "epoch": 0.56, - "learning_rate": 2.20568584368414e-05, - "loss": 0.1851, + "epoch": 0.28, + "learning_rate": 3.606026710811839e-05, + "loss": 0.1793, "step": 125680 }, { - "epoch": 0.56, - "learning_rate": 2.2054616384915476e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.605914856490906e-05, + "loss": 0.1864, "step": 125690 }, { - "epoch": 0.56, - "learning_rate": 2.2052374332989554e-05, - "loss": 0.1796, + "epoch": 0.28, + "learning_rate": 3.605803002169974e-05, + "loss": 0.1799, "step": 125700 }, { - "epoch": 0.56, - "learning_rate": 2.2050132281063633e-05, - "loss": 0.1819, + "epoch": 0.28, + "learning_rate": 3.605691147849042e-05, + "loss": 0.1847, "step": 125710 }, { - "epoch": 0.56, - "learning_rate": 2.204789022913771e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.605579293528109e-05, + "loss": 0.1875, "step": 125720 }, { - "epoch": 0.56, - "learning_rate": 2.2045648177211787e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.6054674392071766e-05, + "loss": 0.1841, "step": 125730 }, { - "epoch": 0.56, - "learning_rate": 2.2043406125285862e-05, - "loss": 0.1786, + "epoch": 0.28, + "learning_rate": 3.6053555848862444e-05, + "loss": 0.1875, "step": 125740 }, { - "epoch": 0.56, - "learning_rate": 2.204116407335994e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.605243730565312e-05, + "loss": 0.1815, "step": 125750 }, { - "epoch": 0.56, - "learning_rate": 2.2038922021434016e-05, - "loss": 0.183, + "epoch": 0.28, + "learning_rate": 3.60513187624438e-05, + "loss": 0.1907, "step": 125760 }, { - "epoch": 0.56, - "learning_rate": 2.2036679969508095e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.605020021923447e-05, + "loss": 0.1866, "step": 125770 }, { - "epoch": 0.56, - "learning_rate": 2.2034437917582174e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.604908167602515e-05, + "loss": 0.1841, "step": 125780 }, { - "epoch": 0.56, - "learning_rate": 2.203219586565625e-05, - "loss": 0.1804, + "epoch": 0.28, + "learning_rate": 3.604796313281582e-05, + "loss": 0.1906, "step": 125790 }, { - "epoch": 0.56, - "learning_rate": 2.2029953813730328e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.60468445896065e-05, + "loss": 0.184, "step": 125800 }, { - "epoch": 0.56, - "learning_rate": 2.2027711761804403e-05, - "loss": 0.1854, + "epoch": 0.28, + "learning_rate": 3.604572604639717e-05, + "loss": 0.1834, "step": 125810 }, { - "epoch": 0.56, - "learning_rate": 2.2025469709878482e-05, - "loss": 0.1783, + "epoch": 0.28, + "learning_rate": 3.604460750318785e-05, + "loss": 0.1841, "step": 125820 }, { - "epoch": 0.56, - "learning_rate": 2.2023227657952557e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.6043488959978525e-05, + "loss": 0.1859, "step": 125830 }, { - "epoch": 0.56, - "learning_rate": 2.2020985606026636e-05, - "loss": 0.1819, + "epoch": 0.28, + "learning_rate": 3.60423704167692e-05, + "loss": 0.1773, "step": 125840 }, { - "epoch": 0.56, - "learning_rate": 2.2018743554100715e-05, - "loss": 0.178, + "epoch": 0.28, + "learning_rate": 3.604125187355988e-05, + "loss": 0.1866, "step": 125850 }, { - "epoch": 0.56, - "learning_rate": 2.201650150217479e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.604013333035055e-05, + "loss": 0.1779, "step": 125860 }, { - "epoch": 0.56, - "learning_rate": 2.201425945024887e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.603901478714123e-05, + "loss": 0.1884, "step": 125870 }, { - "epoch": 0.56, - "learning_rate": 2.2012017398322944e-05, - "loss": 0.1788, + "epoch": 0.28, + "learning_rate": 3.603789624393191e-05, + "loss": 0.1841, "step": 125880 }, { - "epoch": 0.56, - "learning_rate": 2.2009775346397023e-05, - "loss": 0.1821, + "epoch": 0.28, + "learning_rate": 3.603677770072258e-05, + "loss": 0.1801, "step": 125890 }, { - "epoch": 0.56, - "learning_rate": 2.20075332944711e-05, - "loss": 0.1755, + "epoch": 0.28, + "learning_rate": 3.6035659157513257e-05, + "loss": 0.1853, "step": 125900 }, { - "epoch": 0.56, - "learning_rate": 2.2005291242545177e-05, - "loss": 0.1792, + "epoch": 0.28, + "learning_rate": 3.603454061430393e-05, + "loss": 0.1909, "step": 125910 }, { - "epoch": 0.56, - "learning_rate": 2.2003049190619256e-05, - "loss": 0.1733, + "epoch": 0.28, + "learning_rate": 3.6033422071094606e-05, + "loss": 0.1866, "step": 125920 }, { - "epoch": 0.56, - "learning_rate": 2.2000807138693334e-05, + "epoch": 0.28, + "learning_rate": 3.6032303527885284e-05, "loss": 0.1796, "step": 125930 }, { - "epoch": 0.56, - "learning_rate": 2.1998565086767413e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.603118498467596e-05, + "loss": 0.1904, "step": 125940 }, { - "epoch": 0.56, - "learning_rate": 2.199632303484149e-05, - "loss": 0.1761, + "epoch": 0.28, + "learning_rate": 3.603006644146664e-05, + "loss": 0.1816, "step": 125950 }, { - "epoch": 0.56, - "learning_rate": 2.1994080982915567e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.602894789825731e-05, + "loss": 0.1846, "step": 125960 }, { - "epoch": 0.56, - "learning_rate": 2.1992063136182235e-05, - "loss": 0.1852, + "epoch": 0.28, + "learning_rate": 3.602782935504799e-05, + "loss": 0.1862, "step": 125970 }, { - "epoch": 0.56, - "learning_rate": 2.1989821084256314e-05, - "loss": 0.1846, + "epoch": 0.28, + "learning_rate": 3.6026710811838666e-05, + "loss": 0.1865, "step": 125980 }, { - "epoch": 0.56, - "learning_rate": 2.1987579032330392e-05, - "loss": 0.1785, + "epoch": 0.28, + "learning_rate": 3.602559226862934e-05, + "loss": 0.187, "step": 125990 }, { - "epoch": 0.56, - "learning_rate": 2.1985336980404468e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.6024473725420016e-05, + "loss": 0.1881, "step": 126000 }, { - "epoch": 0.56, - "learning_rate": 2.1983094928478546e-05, - "loss": 0.1833, + "epoch": 0.28, + "learning_rate": 3.602335518221069e-05, + "loss": 0.1831, "step": 126010 }, { - "epoch": 0.56, - "learning_rate": 2.1980852876552622e-05, - "loss": 0.1798, + "epoch": 0.28, + "learning_rate": 3.6022236639001365e-05, + "loss": 0.1832, "step": 126020 }, { - "epoch": 0.56, - "learning_rate": 2.19786108246267e-05, - "loss": 0.1831, + "epoch": 0.28, + "learning_rate": 3.602111809579204e-05, + "loss": 0.186, "step": 126030 }, { - "epoch": 0.56, - "learning_rate": 2.1976368772700776e-05, - "loss": 0.1762, + "epoch": 0.28, + "learning_rate": 3.601999955258272e-05, + "loss": 0.1868, "step": 126040 }, { - "epoch": 0.56, - "learning_rate": 2.1974126720774854e-05, - "loss": 0.1771, + "epoch": 0.28, + "learning_rate": 3.60188810093734e-05, + "loss": 0.1889, "step": 126050 }, { - "epoch": 0.56, - "learning_rate": 2.1971884668848933e-05, - "loss": 0.176, + "epoch": 0.28, + "learning_rate": 3.601776246616407e-05, + "loss": 0.1865, "step": 126060 }, { - "epoch": 0.56, - "learning_rate": 2.196964261692301e-05, - "loss": 0.1839, + "epoch": 0.28, + "learning_rate": 3.601664392295475e-05, + "loss": 0.1794, "step": 126070 }, { - "epoch": 0.56, - "learning_rate": 2.1967400564997087e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.6015525379745425e-05, + "loss": 0.1811, "step": 126080 }, { - "epoch": 0.56, - "learning_rate": 2.1965158513071163e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.6014406836536097e-05, + "loss": 0.1884, "step": 126090 }, { - "epoch": 0.56, - "learning_rate": 2.196291646114524e-05, - "loss": 0.188, + "epoch": 0.28, + "learning_rate": 3.6013288293326775e-05, + "loss": 0.1854, "step": 126100 }, { - "epoch": 0.56, - "learning_rate": 2.1960674409219317e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.6012169750117446e-05, + "loss": 0.1867, "step": 126110 }, { - "epoch": 0.56, - "learning_rate": 2.1958432357293395e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.6011051206908124e-05, + "loss": 0.1817, "step": 126120 }, { - "epoch": 0.56, - "learning_rate": 2.1956190305367474e-05, - "loss": 0.1771, + "epoch": 0.28, + "learning_rate": 3.6009932663698795e-05, + "loss": 0.1819, "step": 126130 }, { - "epoch": 0.56, - "learning_rate": 2.195394825344155e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.600881412048947e-05, + "loss": 0.1867, "step": 126140 }, { - "epoch": 0.56, - "learning_rate": 2.1951706201515628e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.600769557728015e-05, + "loss": 0.1937, "step": 126150 }, { - "epoch": 0.56, - "learning_rate": 2.1949464149589703e-05, - "loss": 0.1779, - "step": 126160 + "epoch": 0.28, + "learning_rate": 3.600657703407083e-05, + "loss": 0.185, + "step": 126160 }, { - "epoch": 0.56, - "learning_rate": 2.1947222097663782e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.6005458490861506e-05, + "loss": 0.1775, "step": 126170 }, { - "epoch": 0.56, - "learning_rate": 2.1944980045737857e-05, - "loss": 0.187, + "epoch": 0.28, + "learning_rate": 3.600433994765218e-05, + "loss": 0.1854, "step": 126180 }, { - "epoch": 0.56, - "learning_rate": 2.1942737993811936e-05, - "loss": 0.1809, + "epoch": 0.28, + "learning_rate": 3.6003221404442856e-05, + "loss": 0.1867, "step": 126190 }, { - "epoch": 0.56, - "learning_rate": 2.1940495941886015e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.6002102861233533e-05, + "loss": 0.1781, "step": 126200 }, { - "epoch": 0.56, - "learning_rate": 2.1938253889960094e-05, - "loss": 0.1759, + "epoch": 0.28, + "learning_rate": 3.6000984318024205e-05, + "loss": 0.188, "step": 126210 }, { - "epoch": 0.56, - "learning_rate": 2.193601183803417e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.599986577481488e-05, + "loss": 0.1879, "step": 126220 }, { - "epoch": 0.56, - "learning_rate": 2.1933769786108248e-05, - "loss": 0.1792, + "epoch": 0.28, + "learning_rate": 3.5998747231605554e-05, + "loss": 0.1785, "step": 126230 }, { - "epoch": 0.56, - "learning_rate": 2.1931527734182326e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.599762868839623e-05, + "loss": 0.1877, "step": 126240 }, { - "epoch": 0.56, - "learning_rate": 2.1929285682256402e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.599651014518691e-05, + "loss": 0.1853, "step": 126250 }, { - "epoch": 0.56, - "learning_rate": 2.192704363033048e-05, - "loss": 0.1849, + "epoch": 0.28, + "learning_rate": 3.599539160197759e-05, + "loss": 0.1879, "step": 126260 }, { - "epoch": 0.56, - "learning_rate": 2.192480157840456e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.5994273058768265e-05, + "loss": 0.1908, "step": 126270 }, { - "epoch": 0.56, - "learning_rate": 2.1922559526478634e-05, - "loss": 0.1832, + "epoch": 0.28, + "learning_rate": 3.5993154515558937e-05, + "loss": 0.1814, "step": 126280 }, { - "epoch": 0.56, - "learning_rate": 2.1920317474552713e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.5992035972349614e-05, + "loss": 0.1852, "step": 126290 }, { - "epoch": 0.56, - "learning_rate": 2.191807542262679e-05, - "loss": 0.1681, + "epoch": 0.28, + "learning_rate": 3.599091742914029e-05, + "loss": 0.1833, "step": 126300 }, { - "epoch": 0.56, - "learning_rate": 2.1915833370700867e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.5989798885930964e-05, + "loss": 0.1798, "step": 126310 }, { - "epoch": 0.56, - "learning_rate": 2.1913591318774943e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.598868034272164e-05, + "loss": 0.1857, "step": 126320 }, { - "epoch": 0.56, - "learning_rate": 2.191134926684902e-05, - "loss": 0.1729, + "epoch": 0.28, + "learning_rate": 3.598756179951231e-05, + "loss": 0.1825, "step": 126330 }, { - "epoch": 0.56, - "learning_rate": 2.19091072149231e-05, - "loss": 0.1817, + "epoch": 0.28, + "learning_rate": 3.598644325630299e-05, + "loss": 0.1819, "step": 126340 }, { - "epoch": 0.56, - "learning_rate": 2.1906865162997175e-05, - "loss": 0.1805, + "epoch": 0.28, + "learning_rate": 3.598532471309367e-05, + "loss": 0.1875, "step": 126350 }, { - "epoch": 0.56, - "learning_rate": 2.1904623111071254e-05, - "loss": 0.1749, + "epoch": 0.28, + "learning_rate": 3.5984206169884346e-05, + "loss": 0.1852, "step": 126360 }, { - "epoch": 0.56, - "learning_rate": 2.190238105914533e-05, - "loss": 0.1752, + "epoch": 0.28, + "learning_rate": 3.5983087626675024e-05, + "loss": 0.1852, "step": 126370 }, { - "epoch": 0.56, - "learning_rate": 2.1900139007219408e-05, - "loss": 0.1854, + "epoch": 0.28, + "learning_rate": 3.5981969083465695e-05, + "loss": 0.1831, "step": 126380 }, { - "epoch": 0.56, - "learning_rate": 2.1897896955293483e-05, - "loss": 0.1828, + "epoch": 0.28, + "learning_rate": 3.5980850540256373e-05, + "loss": 0.1864, "step": 126390 }, { - "epoch": 0.56, - "learning_rate": 2.1895654903367562e-05, - "loss": 0.189, + "epoch": 0.28, + "learning_rate": 3.597973199704705e-05, + "loss": 0.1858, "step": 126400 }, { - "epoch": 0.56, - "learning_rate": 2.189341285144164e-05, - "loss": 0.1841, + "epoch": 0.28, + "learning_rate": 3.597861345383772e-05, + "loss": 0.1872, "step": 126410 }, { - "epoch": 0.56, - "learning_rate": 2.1891170799515716e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.59774949106284e-05, + "loss": 0.1863, "step": 126420 }, { - "epoch": 0.56, - "learning_rate": 2.1888928747589795e-05, - "loss": 0.1838, + "epoch": 0.28, + "learning_rate": 3.597637636741907e-05, + "loss": 0.1852, "step": 126430 }, { - "epoch": 0.56, - "learning_rate": 2.188668669566387e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.597525782420975e-05, + "loss": 0.1846, "step": 126440 }, { - "epoch": 0.56, - "learning_rate": 2.188444464373795e-05, - "loss": 0.1857, + "epoch": 0.28, + "learning_rate": 3.597413928100043e-05, + "loss": 0.1843, "step": 126450 }, { - "epoch": 0.56, - "learning_rate": 2.1882202591812028e-05, - "loss": 0.1765, + "epoch": 0.28, + "learning_rate": 3.5973020737791105e-05, + "loss": 0.1792, "step": 126460 }, { - "epoch": 0.56, - "learning_rate": 2.1879960539886103e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.597190219458178e-05, + "loss": 0.1856, "step": 126470 }, { - "epoch": 0.56, - "learning_rate": 2.1877718487960182e-05, - "loss": 0.1793, + "epoch": 0.28, + "learning_rate": 3.5970783651372454e-05, + "loss": 0.1855, "step": 126480 }, { - "epoch": 0.56, - "learning_rate": 2.187547643603426e-05, - "loss": 0.1836, + "epoch": 0.28, + "learning_rate": 3.596966510816313e-05, + "loss": 0.1871, "step": 126490 }, { - "epoch": 0.56, - "learning_rate": 2.187323438410834e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.5968546564953804e-05, + "loss": 0.1825, "step": 126500 }, { - "epoch": 0.56, - "learning_rate": 2.1870992332182415e-05, - "loss": 0.1734, + "epoch": 0.28, + "learning_rate": 3.596742802174448e-05, + "loss": 0.1788, "step": 126510 }, { - "epoch": 0.56, - "learning_rate": 2.1868750280256493e-05, - "loss": 0.1752, + "epoch": 0.28, + "learning_rate": 3.596630947853516e-05, + "loss": 0.1841, "step": 126520 }, { - "epoch": 0.56, - "learning_rate": 2.1866508228330572e-05, - "loss": 0.174, + "epoch": 0.28, + "learning_rate": 3.596519093532583e-05, + "loss": 0.1784, "step": 126530 }, { - "epoch": 0.56, - "learning_rate": 2.1864266176404647e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.596407239211651e-05, + "loss": 0.1885, "step": 126540 }, { - "epoch": 0.56, - "learning_rate": 2.1862024124478726e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.596295384890718e-05, + "loss": 0.1807, "step": 126550 }, { - "epoch": 0.56, - "learning_rate": 2.18597820725528e-05, - "loss": 0.1804, + "epoch": 0.28, + "learning_rate": 3.596183530569786e-05, + "loss": 0.1826, "step": 126560 }, { - "epoch": 0.57, - "learning_rate": 2.185754002062688e-05, - "loss": 0.1811, + "epoch": 0.28, + "learning_rate": 3.5960716762488535e-05, + "loss": 0.181, "step": 126570 }, { - "epoch": 0.57, - "learning_rate": 2.1855297968700955e-05, - "loss": 0.1756, + "epoch": 0.28, + "learning_rate": 3.5959598219279213e-05, + "loss": 0.1846, "step": 126580 }, { - "epoch": 0.57, - "learning_rate": 2.1853055916775034e-05, - "loss": 0.1812, + "epoch": 0.28, + "learning_rate": 3.595847967606989e-05, + "loss": 0.1819, "step": 126590 }, { - "epoch": 0.57, - "learning_rate": 2.1850813864849113e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.595736113286056e-05, + "loss": 0.1834, "step": 126600 }, { - "epoch": 0.57, - "learning_rate": 2.1848571812923188e-05, - "loss": 0.1836, + "epoch": 0.28, + "learning_rate": 3.595624258965124e-05, + "loss": 0.1835, "step": 126610 }, { - "epoch": 0.57, - "learning_rate": 2.1846329760997267e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.595512404644192e-05, + "loss": 0.182, "step": 126620 }, { - "epoch": 0.57, - "learning_rate": 2.1844087709071342e-05, - "loss": 0.1778, + "epoch": 0.28, + "learning_rate": 3.595400550323259e-05, + "loss": 0.1837, "step": 126630 }, { - "epoch": 0.57, - "learning_rate": 2.184184565714542e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.595288696002327e-05, + "loss": 0.1826, "step": 126640 }, { - "epoch": 0.57, - "learning_rate": 2.1839603605219496e-05, - "loss": 0.1789, + "epoch": 0.28, + "learning_rate": 3.595176841681394e-05, + "loss": 0.1838, "step": 126650 }, { - "epoch": 0.57, - "learning_rate": 2.1837361553293575e-05, - "loss": 0.1817, + "epoch": 0.28, + "learning_rate": 3.5950649873604616e-05, + "loss": 0.1844, "step": 126660 }, { - "epoch": 0.57, - "learning_rate": 2.1835119501367654e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.5949531330395294e-05, + "loss": 0.1828, "step": 126670 }, { - "epoch": 0.57, - "learning_rate": 2.183287744944173e-05, - "loss": 0.1776, + "epoch": 0.28, + "learning_rate": 3.594841278718597e-05, + "loss": 0.1838, "step": 126680 }, { - "epoch": 0.57, - "learning_rate": 2.1830635397515808e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.594729424397665e-05, + "loss": 0.1874, "step": 126690 }, { - "epoch": 0.57, - "learning_rate": 2.1828393345589883e-05, - "loss": 0.1839, + "epoch": 0.28, + "learning_rate": 3.594617570076732e-05, + "loss": 0.1886, "step": 126700 }, { - "epoch": 0.57, - "learning_rate": 2.1826151293663962e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.5945057157558e-05, + "loss": 0.183, "step": 126710 }, { - "epoch": 0.57, - "learning_rate": 2.1823909241738037e-05, - "loss": 0.1772, + "epoch": 0.28, + "learning_rate": 3.594393861434868e-05, + "loss": 0.1847, "step": 126720 }, { - "epoch": 0.57, - "learning_rate": 2.1821667189812116e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.594282007113935e-05, + "loss": 0.1912, "step": 126730 }, { - "epoch": 0.57, - "learning_rate": 2.1819425137886195e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.5941701527930026e-05, + "loss": 0.1859, "step": 126740 }, { - "epoch": 0.57, - "learning_rate": 2.1817183085960273e-05, - "loss": 0.1778, + "epoch": 0.28, + "learning_rate": 3.59405829847207e-05, + "loss": 0.1861, "step": 126750 }, { - "epoch": 0.57, - "learning_rate": 2.181494103403435e-05, - "loss": 0.1765, + "epoch": 0.28, + "learning_rate": 3.5939464441511375e-05, + "loss": 0.1824, "step": 126760 }, { - "epoch": 0.57, - "learning_rate": 2.1812698982108427e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.593834589830205e-05, + "loss": 0.1752, "step": 126770 }, { - "epoch": 0.57, - "learning_rate": 2.1810456930182506e-05, - "loss": 0.1779, + "epoch": 0.28, + "learning_rate": 3.593722735509273e-05, + "loss": 0.1801, "step": 126780 }, { - "epoch": 0.57, - "learning_rate": 2.180821487825658e-05, - "loss": 0.1825, + "epoch": 0.28, + "learning_rate": 3.593610881188341e-05, + "loss": 0.1839, "step": 126790 }, { - "epoch": 0.57, - "learning_rate": 2.180597282633066e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.593499026867408e-05, + "loss": 0.1804, "step": 126800 }, { - "epoch": 0.57, - "learning_rate": 2.180373077440474e-05, - "loss": 0.1763, + "epoch": 0.28, + "learning_rate": 3.593387172546476e-05, + "loss": 0.1862, "step": 126810 }, { - "epoch": 0.57, - "learning_rate": 2.1801488722478814e-05, - "loss": 0.1872, + "epoch": 0.28, + "learning_rate": 3.593275318225543e-05, + "loss": 0.184, "step": 126820 }, { - "epoch": 0.57, - "learning_rate": 2.1799246670552893e-05, - "loss": 0.1763, + "epoch": 0.28, + "learning_rate": 3.593163463904611e-05, + "loss": 0.1856, "step": 126830 }, { - "epoch": 0.57, - "learning_rate": 2.1797004618626968e-05, - "loss": 0.1837, + "epoch": 0.28, + "learning_rate": 3.5930516095836785e-05, + "loss": 0.1797, "step": 126840 }, { - "epoch": 0.57, - "learning_rate": 2.1794762566701047e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.5929397552627456e-05, + "loss": 0.1814, "step": 126850 }, { - "epoch": 0.57, - "learning_rate": 2.1792520514775122e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.5928279009418134e-05, + "loss": 0.1845, "step": 126860 }, { - "epoch": 0.57, - "learning_rate": 2.17902784628492e-05, - "loss": 0.1784, + "epoch": 0.28, + "learning_rate": 3.592716046620881e-05, + "loss": 0.1846, "step": 126870 }, { - "epoch": 0.57, - "learning_rate": 2.178803641092328e-05, - "loss": 0.1826, + "epoch": 0.28, + "learning_rate": 3.592604192299949e-05, + "loss": 0.1861, "step": 126880 }, { - "epoch": 0.57, - "learning_rate": 2.1785794358997355e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.592492337979017e-05, + "loss": 0.1838, "step": 126890 }, { - "epoch": 0.57, - "learning_rate": 2.1783552307071434e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.592380483658084e-05, + "loss": 0.1831, "step": 126900 }, { - "epoch": 0.57, - "learning_rate": 2.178131025514551e-05, - "loss": 0.1772, + "epoch": 0.28, + "learning_rate": 3.592268629337152e-05, + "loss": 0.182, "step": 126910 }, { - "epoch": 0.57, - "learning_rate": 2.1779068203219588e-05, - "loss": 0.1801, + "epoch": 0.28, + "learning_rate": 3.592156775016219e-05, + "loss": 0.1837, "step": 126920 }, { - "epoch": 0.57, - "learning_rate": 2.1776826151293663e-05, - "loss": 0.1788, + "epoch": 0.28, + "learning_rate": 3.5920449206952866e-05, + "loss": 0.1848, "step": 126930 }, { - "epoch": 0.57, - "learning_rate": 2.1774584099367742e-05, - "loss": 0.1781, + "epoch": 0.28, + "learning_rate": 3.5919330663743544e-05, + "loss": 0.1834, "step": 126940 }, { - "epoch": 0.57, - "learning_rate": 2.177234204744182e-05, - "loss": 0.1818, + "epoch": 0.28, + "learning_rate": 3.5918212120534215e-05, + "loss": 0.186, "step": 126950 }, { - "epoch": 0.57, - "learning_rate": 2.1770099995515896e-05, - "loss": 0.18, + "epoch": 0.28, + "learning_rate": 3.591709357732489e-05, + "loss": 0.1856, "step": 126960 }, { - "epoch": 0.57, - "learning_rate": 2.1767857943589975e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.5915975034115564e-05, + "loss": 0.1841, "step": 126970 }, { - "epoch": 0.57, - "learning_rate": 2.176561589166405e-05, - "loss": 0.1753, + "epoch": 0.28, + "learning_rate": 3.591485649090624e-05, + "loss": 0.1804, "step": 126980 }, { - "epoch": 0.57, - "learning_rate": 2.176337383973813e-05, - "loss": 0.18, + "epoch": 0.28, + "learning_rate": 3.591373794769693e-05, + "loss": 0.182, "step": 126990 }, { - "epoch": 0.57, - "learning_rate": 2.1761131787812207e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.59126194044876e-05, + "loss": 0.186, "step": 127000 }, { - "epoch": 0.57, - "learning_rate": 2.1758889735886283e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.5911500861278276e-05, + "loss": 0.1831, "step": 127010 }, { - "epoch": 0.57, - "learning_rate": 2.175664768396036e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.591038231806895e-05, + "loss": 0.1824, "step": 127020 }, { - "epoch": 0.57, - "learning_rate": 2.175440563203444e-05, - "loss": 0.1778, + "epoch": 0.28, + "learning_rate": 3.5909263774859625e-05, + "loss": 0.184, "step": 127030 }, { - "epoch": 0.57, - "learning_rate": 2.175216358010852e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.59081452316503e-05, + "loss": 0.1883, "step": 127040 }, { - "epoch": 0.57, - "learning_rate": 2.1749921528182594e-05, - "loss": 0.178, + "epoch": 0.28, + "learning_rate": 3.5907026688440974e-05, + "loss": 0.1781, "step": 127050 }, { - "epoch": 0.57, - "learning_rate": 2.1747679476256673e-05, - "loss": 0.1787, + "epoch": 0.28, + "learning_rate": 3.590590814523165e-05, + "loss": 0.1853, "step": 127060 }, { - "epoch": 0.57, - "learning_rate": 2.1745437424330748e-05, - "loss": 0.1744, + "epoch": 0.28, + "learning_rate": 3.5904789602022323e-05, + "loss": 0.1804, "step": 127070 }, { - "epoch": 0.57, - "learning_rate": 2.1743195372404827e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.5903671058813e-05, + "loss": 0.1799, "step": 127080 }, { - "epoch": 0.57, - "learning_rate": 2.1740953320478906e-05, - "loss": 0.173, + "epoch": 0.28, + "learning_rate": 3.590255251560368e-05, + "loss": 0.1852, "step": 127090 }, { - "epoch": 0.57, - "learning_rate": 2.173871126855298e-05, - "loss": 0.1758, + "epoch": 0.28, + "learning_rate": 3.590143397239436e-05, + "loss": 0.1869, "step": 127100 }, { - "epoch": 0.57, - "learning_rate": 2.173646921662706e-05, - "loss": 0.1783, + "epoch": 0.28, + "learning_rate": 3.5900315429185035e-05, + "loss": 0.1799, "step": 127110 }, { - "epoch": 0.57, - "learning_rate": 2.1734227164701135e-05, - "loss": 0.1803, + "epoch": 0.28, + "learning_rate": 3.5899196885975706e-05, + "loss": 0.1818, "step": 127120 }, { - "epoch": 0.57, - "learning_rate": 2.1731985112775214e-05, - "loss": 0.1769, + "epoch": 0.28, + "learning_rate": 3.5898078342766384e-05, + "loss": 0.1847, "step": 127130 }, { - "epoch": 0.57, - "learning_rate": 2.172974306084929e-05, - "loss": 0.1799, + "epoch": 0.28, + "learning_rate": 3.5896959799557055e-05, + "loss": 0.1877, "step": 127140 }, { - "epoch": 0.57, - "learning_rate": 2.1727501008923368e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.589584125634773e-05, + "loss": 0.1863, "step": 127150 }, { - "epoch": 0.57, - "learning_rate": 2.1725258956997446e-05, - "loss": 0.1828, + "epoch": 0.28, + "learning_rate": 3.589472271313841e-05, + "loss": 0.1827, "step": 127160 }, { - "epoch": 0.57, - "learning_rate": 2.1723016905071522e-05, - "loss": 0.1854, + "epoch": 0.28, + "learning_rate": 3.589360416992908e-05, + "loss": 0.1905, "step": 127170 }, { - "epoch": 0.57, - "learning_rate": 2.17207748531456e-05, - "loss": 0.1759, + "epoch": 0.28, + "learning_rate": 3.589248562671976e-05, + "loss": 0.1792, "step": 127180 }, { - "epoch": 0.57, - "learning_rate": 2.1718532801219676e-05, - "loss": 0.1815, + "epoch": 0.28, + "learning_rate": 3.589136708351044e-05, + "loss": 0.1864, "step": 127190 }, { - "epoch": 0.57, - "learning_rate": 2.1716290749293755e-05, - "loss": 0.1752, + "epoch": 0.28, + "learning_rate": 3.5890248540301116e-05, + "loss": 0.1874, "step": 127200 }, { - "epoch": 0.57, - "learning_rate": 2.171404869736783e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.5889129997091794e-05, + "loss": 0.1823, "step": 127210 }, { - "epoch": 0.57, - "learning_rate": 2.171180664544191e-05, - "loss": 0.1857, + "epoch": 0.28, + "learning_rate": 3.5888011453882465e-05, + "loss": 0.1829, "step": 127220 }, { - "epoch": 0.57, - "learning_rate": 2.1709564593515987e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.588689291067314e-05, + "loss": 0.1811, "step": 127230 }, { - "epoch": 0.57, - "learning_rate": 2.1707322541590063e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.5885774367463814e-05, + "loss": 0.1836, "step": 127240 }, { - "epoch": 0.57, - "learning_rate": 2.170508048966414e-05, - "loss": 0.1773, + "epoch": 0.28, + "learning_rate": 3.588465582425449e-05, + "loss": 0.1863, "step": 127250 }, { - "epoch": 0.57, - "learning_rate": 2.1702838437738217e-05, - "loss": 0.181, + "epoch": 0.28, + "learning_rate": 3.588353728104517e-05, + "loss": 0.1816, "step": 127260 }, { - "epoch": 0.57, - "learning_rate": 2.1700596385812295e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.588241873783584e-05, + "loss": 0.1768, "step": 127270 }, { - "epoch": 0.57, - "learning_rate": 2.1698354333886374e-05, - "loss": 0.1826, + "epoch": 0.28, + "learning_rate": 3.588130019462652e-05, + "loss": 0.186, "step": 127280 }, { - "epoch": 0.57, - "learning_rate": 2.1696112281960453e-05, - "loss": 0.1776, + "epoch": 0.28, + "learning_rate": 3.58801816514172e-05, + "loss": 0.184, "step": 127290 }, { - "epoch": 0.57, - "learning_rate": 2.1693870230034528e-05, - "loss": 0.1763, + "epoch": 0.28, + "learning_rate": 3.5879063108207875e-05, + "loss": 0.1836, "step": 127300 }, { - "epoch": 0.57, - "learning_rate": 2.1691628178108607e-05, - "loss": 0.1711, + "epoch": 0.28, + "learning_rate": 3.587794456499855e-05, + "loss": 0.1834, "step": 127310 }, { - "epoch": 0.57, - "learning_rate": 2.1689386126182686e-05, - "loss": 0.1795, + "epoch": 0.28, + "learning_rate": 3.5876826021789224e-05, + "loss": 0.1842, "step": 127320 }, { - "epoch": 0.57, - "learning_rate": 2.168714407425676e-05, - "loss": 0.1806, + "epoch": 0.28, + "learning_rate": 3.58757074785799e-05, + "loss": 0.1858, "step": 127330 }, { - "epoch": 0.57, - "learning_rate": 2.168490202233084e-05, - "loss": 0.1808, + "epoch": 0.28, + "learning_rate": 3.587458893537057e-05, + "loss": 0.1828, "step": 127340 }, { - "epoch": 0.57, - "learning_rate": 2.1682659970404915e-05, - "loss": 0.18, + "epoch": 0.28, + "learning_rate": 3.587347039216125e-05, + "loss": 0.1813, "step": 127350 }, { - "epoch": 0.57, - "learning_rate": 2.1680417918478994e-05, - "loss": 0.1753, + "epoch": 0.28, + "learning_rate": 3.587235184895193e-05, + "loss": 0.1819, "step": 127360 }, { - "epoch": 0.57, - "learning_rate": 2.1678175866553072e-05, - "loss": 0.1802, + "epoch": 0.28, + "learning_rate": 3.58712333057426e-05, + "loss": 0.1819, "step": 127370 }, { - "epoch": 0.57, - "learning_rate": 2.1675933814627148e-05, + "epoch": 0.28, + "learning_rate": 3.587011476253328e-05, "loss": 0.1823, "step": 127380 }, { - "epoch": 0.57, - "learning_rate": 2.1673691762701226e-05, - "loss": 0.1776, + "epoch": 0.28, + "learning_rate": 3.586899621932395e-05, + "loss": 0.1824, "step": 127390 }, { - "epoch": 0.57, - "learning_rate": 2.1671449710775302e-05, - "loss": 0.1755, + "epoch": 0.28, + "learning_rate": 3.5867877676114634e-05, + "loss": 0.1829, "step": 127400 }, { - "epoch": 0.57, - "learning_rate": 2.166920765884938e-05, - "loss": 0.176, + "epoch": 0.28, + "learning_rate": 3.5866759132905305e-05, + "loss": 0.1807, "step": 127410 }, { - "epoch": 0.57, - "learning_rate": 2.1666965606923456e-05, - "loss": 0.1823, + "epoch": 0.28, + "learning_rate": 3.586564058969598e-05, + "loss": 0.1839, "step": 127420 }, { - "epoch": 0.57, - "learning_rate": 2.1664723554997535e-05, - "loss": 0.1767, + "epoch": 0.28, + "learning_rate": 3.586452204648666e-05, + "loss": 0.1774, "step": 127430 }, { - "epoch": 0.57, - "learning_rate": 2.1662481503071613e-05, - "loss": 0.1814, + "epoch": 0.28, + "learning_rate": 3.586340350327733e-05, + "loss": 0.1827, "step": 127440 }, { - "epoch": 0.57, - "learning_rate": 2.166023945114569e-05, - "loss": 0.1764, + "epoch": 0.28, + "learning_rate": 3.586228496006801e-05, + "loss": 0.1762, "step": 127450 }, { - "epoch": 0.57, - "learning_rate": 2.1657997399219767e-05, - "loss": 0.183, + "epoch": 0.28, + "learning_rate": 3.586116641685868e-05, + "loss": 0.1901, "step": 127460 }, { - "epoch": 0.57, - "learning_rate": 2.1655755347293843e-05, - "loss": 0.1797, + "epoch": 0.28, + "learning_rate": 3.586004787364936e-05, + "loss": 0.1787, "step": 127470 }, { - "epoch": 0.57, - "learning_rate": 2.165351329536792e-05, - "loss": 0.1805, + "epoch": 0.28, + "learning_rate": 3.585892933044004e-05, + "loss": 0.1887, "step": 127480 }, { - "epoch": 0.57, - "learning_rate": 2.1651271243441997e-05, - "loss": 0.1816, + "epoch": 0.28, + "learning_rate": 3.585781078723071e-05, + "loss": 0.1826, "step": 127490 }, { - "epoch": 0.57, - "learning_rate": 2.1649029191516075e-05, - "loss": 0.1778, + "epoch": 0.28, + "learning_rate": 3.5856692244021386e-05, + "loss": 0.1814, "step": 127500 }, { - "epoch": 0.57, - "learning_rate": 2.1646787139590154e-05, - "loss": 0.1784, + "epoch": 0.28, + "learning_rate": 3.5855573700812064e-05, + "loss": 0.19, "step": 127510 }, { - "epoch": 0.57, - "learning_rate": 2.164454508766423e-05, - "loss": 0.1787, + "epoch": 0.28, + "learning_rate": 3.585445515760274e-05, + "loss": 0.1813, "step": 127520 }, { - "epoch": 0.57, - "learning_rate": 2.1642303035738308e-05, - "loss": 0.1767, + "epoch": 0.28, + "learning_rate": 3.585333661439342e-05, + "loss": 0.1863, "step": 127530 }, { - "epoch": 0.57, - "learning_rate": 2.1640060983812387e-05, - "loss": 0.1813, + "epoch": 0.28, + "learning_rate": 3.585221807118409e-05, + "loss": 0.1808, "step": 127540 }, { - "epoch": 0.57, - "learning_rate": 2.1637818931886462e-05, - "loss": 0.1831, + "epoch": 0.28, + "learning_rate": 3.585109952797477e-05, + "loss": 0.1804, "step": 127550 }, { - "epoch": 0.57, - "learning_rate": 2.163557687996054e-05, - "loss": 0.186, + "epoch": 0.28, + "learning_rate": 3.584998098476544e-05, + "loss": 0.1781, "step": 127560 }, { - "epoch": 0.57, - "learning_rate": 2.163333482803462e-05, - "loss": 0.1784, + "epoch": 0.28, + "learning_rate": 3.584886244155612e-05, + "loss": 0.1782, "step": 127570 }, { - "epoch": 0.57, - "learning_rate": 2.16310927761087e-05, - "loss": 0.1737, + "epoch": 0.28, + "learning_rate": 3.5847743898346796e-05, + "loss": 0.1851, "step": 127580 }, { - "epoch": 0.57, - "learning_rate": 2.1628850724182774e-05, - "loss": 0.1807, + "epoch": 0.28, + "learning_rate": 3.584662535513747e-05, + "loss": 0.1837, "step": 127590 }, { - "epoch": 0.57, - "learning_rate": 2.1626608672256852e-05, - "loss": 0.1774, + "epoch": 0.28, + "learning_rate": 3.5845506811928145e-05, + "loss": 0.179, "step": 127600 }, { - "epoch": 0.57, - "learning_rate": 2.1624366620330928e-05, - "loss": 0.1749, + "epoch": 0.28, + "learning_rate": 3.584438826871882e-05, + "loss": 0.1822, "step": 127610 }, { - "epoch": 0.57, - "learning_rate": 2.1622124568405006e-05, - "loss": 0.1777, + "epoch": 0.28, + "learning_rate": 3.58432697255095e-05, + "loss": 0.1876, "step": 127620 }, { - "epoch": 0.57, - "learning_rate": 2.1619882516479082e-05, - "loss": 0.1817, + "epoch": 0.28, + "learning_rate": 3.584215118230018e-05, + "loss": 0.184, "step": 127630 }, { - "epoch": 0.57, - "learning_rate": 2.161764046455316e-05, - "loss": 0.1783, + "epoch": 0.28, + "learning_rate": 3.584103263909085e-05, + "loss": 0.1799, "step": 127640 }, { - "epoch": 0.57, - "learning_rate": 2.161539841262724e-05, - "loss": 0.1782, + "epoch": 0.28, + "learning_rate": 3.583991409588153e-05, + "loss": 0.1816, "step": 127650 }, { - "epoch": 0.57, - "learning_rate": 2.1613156360701315e-05, - "loss": 0.1794, + "epoch": 0.28, + "learning_rate": 3.58387955526722e-05, + "loss": 0.1779, "step": 127660 }, { - "epoch": 0.57, - "learning_rate": 2.1610914308775393e-05, - "loss": 0.179, + "epoch": 0.28, + "learning_rate": 3.583767700946288e-05, + "loss": 0.1772, "step": 127670 }, { - "epoch": 0.57, - "learning_rate": 2.160867225684947e-05, - "loss": 0.1828, + "epoch": 0.28, + "learning_rate": 3.5836558466253555e-05, + "loss": 0.1885, "step": 127680 }, { - "epoch": 0.57, - "learning_rate": 2.1606430204923547e-05, - "loss": 0.1813, + "epoch": 0.29, + "learning_rate": 3.5835439923044226e-05, + "loss": 0.1821, "step": 127690 }, { - "epoch": 0.57, - "learning_rate": 2.1604188152997623e-05, - "loss": 0.1836, + "epoch": 0.29, + "learning_rate": 3.5834321379834904e-05, + "loss": 0.1835, "step": 127700 }, { - "epoch": 0.57, - "learning_rate": 2.16019461010717e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.583320283662558e-05, + "loss": 0.1822, "step": 127710 }, { - "epoch": 0.57, - "learning_rate": 2.159970404914578e-05, - "loss": 0.1773, + "epoch": 0.29, + "learning_rate": 3.583208429341626e-05, + "loss": 0.1857, "step": 127720 }, { - "epoch": 0.57, - "learning_rate": 2.1597461997219855e-05, - "loss": 0.1794, + "epoch": 0.29, + "learning_rate": 3.583096575020693e-05, + "loss": 0.1869, "step": 127730 }, { - "epoch": 0.57, - "learning_rate": 2.1595219945293934e-05, - "loss": 0.1837, + "epoch": 0.29, + "learning_rate": 3.582984720699761e-05, + "loss": 0.1865, "step": 127740 }, { - "epoch": 0.57, - "learning_rate": 2.159297789336801e-05, - "loss": 0.1809, + "epoch": 0.29, + "learning_rate": 3.582872866378829e-05, + "loss": 0.1812, "step": 127750 }, { - "epoch": 0.57, - "learning_rate": 2.1590735841442088e-05, - "loss": 0.1728, + "epoch": 0.29, + "learning_rate": 3.582761012057896e-05, + "loss": 0.1822, "step": 127760 }, { - "epoch": 0.57, - "learning_rate": 2.1588493789516164e-05, - "loss": 0.1761, + "epoch": 0.29, + "learning_rate": 3.5826491577369636e-05, + "loss": 0.1878, "step": 127770 }, { - "epoch": 0.57, - "learning_rate": 2.1586251737590242e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.582537303416031e-05, + "loss": 0.1858, "step": 127780 }, { - "epoch": 0.57, - "learning_rate": 2.158400968566432e-05, - "loss": 0.1766, + "epoch": 0.29, + "learning_rate": 3.5824254490950985e-05, + "loss": 0.1806, "step": 127790 }, { - "epoch": 0.57, - "learning_rate": 2.1581767633738396e-05, + "epoch": 0.29, + "learning_rate": 3.582313594774166e-05, "loss": 0.1839, "step": 127800 }, { - "epoch": 0.57, - "learning_rate": 2.1579525581812475e-05, - "loss": 0.1785, + "epoch": 0.29, + "learning_rate": 3.5822017404532334e-05, + "loss": 0.1767, "step": 127810 }, { - "epoch": 0.57, - "learning_rate": 2.1577283529886554e-05, - "loss": 0.1796, + "epoch": 0.29, + "learning_rate": 3.582089886132302e-05, + "loss": 0.1831, "step": 127820 }, { - "epoch": 0.57, - "learning_rate": 2.1575041477960632e-05, - "loss": 0.1796, + "epoch": 0.29, + "learning_rate": 3.581978031811369e-05, + "loss": 0.1842, "step": 127830 }, { - "epoch": 0.57, - "learning_rate": 2.1572799426034708e-05, - "loss": 0.1739, + "epoch": 0.29, + "learning_rate": 3.581866177490437e-05, + "loss": 0.1828, "step": 127840 }, { - "epoch": 0.57, - "learning_rate": 2.1570557374108787e-05, - "loss": 0.1786, + "epoch": 0.29, + "learning_rate": 3.5817543231695046e-05, + "loss": 0.1824, "step": 127850 }, { - "epoch": 0.57, - "learning_rate": 2.1568315322182865e-05, - "loss": 0.1784, + "epoch": 0.29, + "learning_rate": 3.581642468848572e-05, + "loss": 0.1813, "step": 127860 }, { - "epoch": 0.57, - "learning_rate": 2.156607327025694e-05, - "loss": 0.179, + "epoch": 0.29, + "learning_rate": 3.5815306145276395e-05, + "loss": 0.1844, "step": 127870 }, { - "epoch": 0.57, - "learning_rate": 2.156383121833102e-05, - "loss": 0.1833, + "epoch": 0.29, + "learning_rate": 3.5814187602067066e-05, + "loss": 0.1777, "step": 127880 }, { - "epoch": 0.57, - "learning_rate": 2.1561589166405095e-05, - "loss": 0.1795, + "epoch": 0.29, + "learning_rate": 3.5813069058857744e-05, + "loss": 0.1785, "step": 127890 }, { - "epoch": 0.57, - "learning_rate": 2.1559347114479173e-05, - "loss": 0.1841, + "epoch": 0.29, + "learning_rate": 3.581195051564842e-05, + "loss": 0.1825, "step": 127900 }, { - "epoch": 0.57, - "learning_rate": 2.1557105062553252e-05, - "loss": 0.1832, + "epoch": 0.29, + "learning_rate": 3.581083197243909e-05, + "loss": 0.1845, "step": 127910 }, { - "epoch": 0.57, - "learning_rate": 2.1554863010627327e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.580971342922977e-05, + "loss": 0.1819, "step": 127920 }, { - "epoch": 0.57, - "learning_rate": 2.1552620958701406e-05, - "loss": 0.1792, + "epoch": 0.29, + "learning_rate": 3.580859488602045e-05, + "loss": 0.1833, "step": 127930 }, { - "epoch": 0.57, - "learning_rate": 2.155037890677548e-05, - "loss": 0.1802, + "epoch": 0.29, + "learning_rate": 3.580747634281113e-05, + "loss": 0.1859, "step": 127940 }, { - "epoch": 0.57, - "learning_rate": 2.154813685484956e-05, - "loss": 0.1784, + "epoch": 0.29, + "learning_rate": 3.5806357799601805e-05, + "loss": 0.1874, "step": 127950 }, { - "epoch": 0.57, - "learning_rate": 2.1545894802923635e-05, - "loss": 0.1714, + "epoch": 0.29, + "learning_rate": 3.5805239256392476e-05, + "loss": 0.1854, "step": 127960 }, { - "epoch": 0.57, - "learning_rate": 2.1543652750997714e-05, - "loss": 0.1775, + "epoch": 0.29, + "learning_rate": 3.5804120713183154e-05, + "loss": 0.1839, "step": 127970 }, { - "epoch": 0.57, - "learning_rate": 2.1541410699071793e-05, - "loss": 0.1759, + "epoch": 0.29, + "learning_rate": 3.5803002169973825e-05, + "loss": 0.1817, "step": 127980 }, { - "epoch": 0.57, - "learning_rate": 2.1539168647145868e-05, - "loss": 0.182, + "epoch": 0.29, + "learning_rate": 3.58018836267645e-05, + "loss": 0.1815, "step": 127990 }, { - "epoch": 0.57, - "learning_rate": 2.1536926595219947e-05, - "loss": 0.1842, + "epoch": 0.29, + "learning_rate": 3.580076508355518e-05, + "loss": 0.1827, "step": 128000 }, { - "epoch": 0.57, - "eval_NEIMS_canon_smiles": 0.9442, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.060533333333333335, - "eval_NEIMS_daylight_tanimoto_simil": 0.46074801317645475, - "eval_NEIMS_exact_mols": 0.060316666666666664, - "eval_NEIMS_exact_smiles": 0.05846666666666667, - "eval_NEIMS_loss": 0.21823979914188385, - "eval_NEIMS_matched_formulas": 0.5509166666666667, - "eval_NEIMS_morgan_tanimoto_simil": 0.3658473136765312, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.06065, - "eval_NEIMS_runtime": 716.0986, - "eval_NEIMS_samples_per_second": 83.787, - "eval_NEIMS_steps_per_second": 1.31, + "epoch": 0.29, + "eval_NEIMS_canon_smiles": 0.9481833333333334, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.08701666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.4940359259320148, + "eval_NEIMS_exact_mols": 0.0868, + "eval_NEIMS_exact_smiles": 0.08456666666666666, + "eval_NEIMS_loss": 0.19371925294399261, + "eval_NEIMS_matched_formulas": 0.6091833333333333, + "eval_NEIMS_morgan_tanimoto_simil": 0.40232716460663215, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.08713333333333333, + "eval_NEIMS_runtime": 723.4995, + "eval_NEIMS_samples_per_second": 82.93, + "eval_NEIMS_steps_per_second": 1.296, "step": 128000 }, { - "epoch": 0.57, - "eval_RASSP_canon_smiles": 0.9369385915116706, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.14238487995458643, - "eval_RASSP_daylight_tanimoto_simil": 0.5888624426564175, - "eval_RASSP_exact_mols": 0.14191738738437906, - "eval_RASSP_exact_smiles": 0.13750960029385248, - "eval_RASSP_loss": 0.15661999583244324, - "eval_RASSP_matched_formulas": 0.7334791464921361, - "eval_RASSP_morgan_tanimoto_simil": 0.46166409815266424, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.1420509566901526, - "eval_RASSP_runtime": 817.8885, - "eval_RASSP_samples_per_second": 73.23, - "eval_RASSP_steps_per_second": 1.144, + "epoch": 0.29, + "eval_RASSP_canon_smiles": 0.9460380004674925, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.12740842154472903, + "eval_RASSP_daylight_tanimoto_simil": 0.581246476855378, + "eval_RASSP_exact_mols": 0.12692423281129997, + "eval_RASSP_exact_smiles": 0.12286706514842889, + "eval_RASSP_loss": 0.15924470126628876, + "eval_RASSP_matched_formulas": 0.7646341870638127, + "eval_RASSP_morgan_tanimoto_simil": 0.44838309612918026, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.12709119444351688, + "eval_RASSP_runtime": 826.5366, + "eval_RASSP_samples_per_second": 72.464, + "eval_RASSP_steps_per_second": 1.132, "step": 128000 }, { - "epoch": 0.57, - "eval_NIST_canon_smiles": 0.8755722752599638, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.011960109309010895, - "eval_NIST_daylight_tanimoto_simil": 0.2668137700125038, - "eval_NIST_exact_mols": 0.01153423004578202, - "eval_NIST_exact_smiles": 0.010859921212336303, - "eval_NIST_loss": 1.8035073280334473, - "eval_NIST_matched_formulas": 0.08265606700500408, - "eval_NIST_morgan_tanimoto_simil": 0.21989801486693322, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01192461937040849, - "eval_NIST_runtime": 535.9421, - "eval_NIST_samples_per_second": 52.575, - "eval_NIST_steps_per_second": 0.823, + "epoch": 0.29, + "eval_NEIMS_old_canon_smiles": 0.9495666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.08583333333333333, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.49136076841095405, + "eval_NEIMS_old_exact_mols": 0.08566666666666667, + "eval_NEIMS_old_exact_smiles": 0.083, + "eval_NEIMS_old_loss": 0.1934109628200531, + "eval_NEIMS_old_matched_formulas": 0.6061666666666666, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.40081758933050365, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.08616666666666667, + "eval_NEIMS_old_runtime": 366.1568, + "eval_NEIMS_old_samples_per_second": 81.932, + "eval_NEIMS_old_steps_per_second": 1.281, "step": 128000 }, { - "epoch": 0.57, - "learning_rate": 2.1534684543294022e-05, - "loss": 0.1771, + "epoch": 0.29, + "eval_RASSP_old_canon_smiles": 0.942870490873294, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.14259018253412087, + "eval_RASSP_old_daylight_tanimoto_simil": 0.5951672001403203, + "eval_RASSP_old_exact_mols": 0.14218974204958787, + "eval_RASSP_old_exact_smiles": 0.13745119631594754, + "eval_RASSP_old_loss": 0.15243235230445862, + "eval_RASSP_old_matched_formulas": 0.7752861480962392, + "eval_RASSP_old_morgan_tanimoto_simil": 0.46526866784495496, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.14238996229185438, + "eval_RASSP_old_runtime": 412.566, + "eval_RASSP_old_samples_per_second": 72.636, + "eval_RASSP_old_steps_per_second": 1.137, + "step": 128000 + }, + { + "epoch": 0.29, + "eval_NIST_canon_smiles": 0.8693970259431452, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.018241828441636795, + "eval_NIST_daylight_tanimoto_simil": 0.281109068198515, + "eval_NIST_exact_mols": 0.017106150406359797, + "eval_NIST_exact_smiles": 0.016254391879902047, + "eval_NIST_loss": 1.7484208345413208, + "eval_NIST_matched_formulas": 0.099336338148135, + "eval_NIST_morgan_tanimoto_simil": 0.23717129634392867, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.018099868687227173, + "eval_NIST_runtime": 561.4081, + "eval_NIST_samples_per_second": 50.19, + "eval_NIST_steps_per_second": 0.786, + "step": 128000 + }, + { + "epoch": 0.29, + "learning_rate": 3.579964654034585e-05, + "loss": 0.1831, "step": 128010 }, { - "epoch": 0.57, - "learning_rate": 2.15324424913681e-05, - "loss": 0.1828, + "epoch": 0.29, + "learning_rate": 3.579852799713653e-05, + "loss": 0.1851, "step": 128020 }, { - "epoch": 0.57, - "learning_rate": 2.1530200439442176e-05, - "loss": 0.1791, + "epoch": 0.29, + "learning_rate": 3.579740945392721e-05, + "loss": 0.1813, "step": 128030 }, { - "epoch": 0.57, - "learning_rate": 2.1527958387516255e-05, - "loss": 0.1745, + "epoch": 0.29, + "learning_rate": 3.5796290910717886e-05, + "loss": 0.1833, "step": 128040 }, { - "epoch": 0.57, - "learning_rate": 2.1525716335590334e-05, - "loss": 0.1826, + "epoch": 0.29, + "learning_rate": 3.579517236750856e-05, + "loss": 0.1846, "step": 128050 }, { - "epoch": 0.57, - "learning_rate": 2.152347428366441e-05, - "loss": 0.1768, + "epoch": 0.29, + "learning_rate": 3.5794053824299235e-05, + "loss": 0.1834, "step": 128060 }, { - "epoch": 0.57, - "learning_rate": 2.1521232231738488e-05, - "loss": 0.1771, + "epoch": 0.29, + "learning_rate": 3.579293528108991e-05, + "loss": 0.1791, "step": 128070 }, { - "epoch": 0.57, - "learning_rate": 2.1518990179812563e-05, - "loss": 0.1816, + "epoch": 0.29, + "learning_rate": 3.5791816737880584e-05, + "loss": 0.1847, "step": 128080 }, { - "epoch": 0.57, - "learning_rate": 2.1516748127886642e-05, - "loss": 0.1811, + "epoch": 0.29, + "learning_rate": 3.579069819467126e-05, + "loss": 0.1838, "step": 128090 }, { - "epoch": 0.57, - "learning_rate": 2.151450607596072e-05, - "loss": 0.1751, + "epoch": 0.29, + "learning_rate": 3.578957965146193e-05, + "loss": 0.1815, "step": 128100 }, { - "epoch": 0.57, - "learning_rate": 2.15122640240348e-05, - "loss": 0.1735, + "epoch": 0.29, + "learning_rate": 3.578846110825261e-05, + "loss": 0.1853, "step": 128110 }, { - "epoch": 0.57, - "learning_rate": 2.1510021972108878e-05, - "loss": 0.1804, + "epoch": 0.29, + "learning_rate": 3.578734256504329e-05, + "loss": 0.1825, "step": 128120 }, { - "epoch": 0.57, - "learning_rate": 2.1507779920182953e-05, - "loss": 0.1796, + "epoch": 0.29, + "learning_rate": 3.578622402183397e-05, + "loss": 0.1808, "step": 128130 }, { - "epoch": 0.57, - "learning_rate": 2.1505537868257032e-05, - "loss": 0.1776, + "epoch": 0.29, + "learning_rate": 3.5785105478624645e-05, + "loss": 0.1823, "step": 128140 }, { - "epoch": 0.57, - "learning_rate": 2.1503295816331107e-05, - "loss": 0.1762, + "epoch": 0.29, + "learning_rate": 3.5783986935415316e-05, + "loss": 0.1825, "step": 128150 }, { - "epoch": 0.57, - "learning_rate": 2.1501053764405186e-05, - "loss": 0.174, + "epoch": 0.29, + "learning_rate": 3.5782868392205994e-05, + "loss": 0.1789, "step": 128160 }, { - "epoch": 0.57, - "learning_rate": 2.149881171247926e-05, + "epoch": 0.29, + "learning_rate": 3.578174984899667e-05, "loss": 0.1793, "step": 128170 }, { - "epoch": 0.57, - "learning_rate": 2.149656966055334e-05, - "loss": 0.1771, + "epoch": 0.29, + "learning_rate": 3.578063130578734e-05, + "loss": 0.1845, "step": 128180 }, { - "epoch": 0.57, - "learning_rate": 2.149432760862742e-05, - "loss": 0.1841, + "epoch": 0.29, + "learning_rate": 3.577951276257802e-05, + "loss": 0.1823, "step": 128190 }, { - "epoch": 0.57, - "learning_rate": 2.1492085556701494e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.577839421936869e-05, + "loss": 0.1828, "step": 128200 }, { - "epoch": 0.57, - "learning_rate": 2.1489843504775573e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.577727567615937e-05, + "loss": 0.1822, "step": 128210 }, { - "epoch": 0.57, - "learning_rate": 2.1487601452849648e-05, - "loss": 0.1805, + "epoch": 0.29, + "learning_rate": 3.577615713295005e-05, + "loss": 0.1822, "step": 128220 }, { - "epoch": 0.57, - "learning_rate": 2.1485359400923727e-05, - "loss": 0.1798, + "epoch": 0.29, + "learning_rate": 3.5775038589740726e-05, + "loss": 0.181, "step": 128230 }, { - "epoch": 0.57, - "learning_rate": 2.1483117348997802e-05, - "loss": 0.1835, + "epoch": 0.29, + "learning_rate": 3.5773920046531404e-05, + "loss": 0.1816, "step": 128240 }, { - "epoch": 0.57, - "learning_rate": 2.148087529707188e-05, - "loss": 0.1765, + "epoch": 0.29, + "learning_rate": 3.5772801503322075e-05, + "loss": 0.1848, "step": 128250 }, { - "epoch": 0.57, - "learning_rate": 2.147863324514596e-05, - "loss": 0.1823, + "epoch": 0.29, + "learning_rate": 3.577168296011275e-05, + "loss": 0.1806, "step": 128260 }, { - "epoch": 0.57, - "learning_rate": 2.1476391193220035e-05, - "loss": 0.1779, + "epoch": 0.29, + "learning_rate": 3.577056441690343e-05, + "loss": 0.1843, "step": 128270 }, { - "epoch": 0.57, - "learning_rate": 2.1474149141294114e-05, - "loss": 0.1847, + "epoch": 0.29, + "learning_rate": 3.57694458736941e-05, + "loss": 0.1802, "step": 128280 }, { - "epoch": 0.57, - "learning_rate": 2.147190708936819e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.576832733048478e-05, + "loss": 0.1807, "step": 128290 }, { - "epoch": 0.57, - "learning_rate": 2.1469665037442268e-05, - "loss": 0.1733, + "epoch": 0.29, + "learning_rate": 3.576720878727545e-05, + "loss": 0.1795, "step": 128300 }, { - "epoch": 0.57, - "learning_rate": 2.1467422985516343e-05, - "loss": 0.1779, + "epoch": 0.29, + "learning_rate": 3.576609024406613e-05, + "loss": 0.1858, "step": 128310 }, { - "epoch": 0.57, - "learning_rate": 2.1465180933590422e-05, - "loss": 0.184, + "epoch": 0.29, + "learning_rate": 3.57649717008568e-05, + "loss": 0.1839, "step": 128320 }, { - "epoch": 0.57, - "learning_rate": 2.14629388816645e-05, - "loss": 0.177, + "epoch": 0.29, + "learning_rate": 3.576385315764748e-05, + "loss": 0.1868, "step": 128330 }, { - "epoch": 0.57, - "learning_rate": 2.1460696829738576e-05, - "loss": 0.1734, + "epoch": 0.29, + "learning_rate": 3.5762734614438156e-05, + "loss": 0.1848, "step": 128340 }, { - "epoch": 0.57, - "learning_rate": 2.1458454777812655e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.5761616071228834e-05, + "loss": 0.1839, "step": 128350 }, { - "epoch": 0.57, - "learning_rate": 2.1456212725886733e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.576060938234044e-05, + "loss": 0.1926, "step": 128360 }, { - "epoch": 0.57, - "learning_rate": 2.1453970673960812e-05, - "loss": 0.1785, + "epoch": 0.29, + "learning_rate": 3.5759490839131114e-05, + "loss": 0.1816, "step": 128370 }, { - "epoch": 0.57, - "learning_rate": 2.1451728622034887e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.575837229592179e-05, + "loss": 0.1831, "step": 128380 }, { - "epoch": 0.57, - "learning_rate": 2.1449486570108966e-05, - "loss": 0.182, + "epoch": 0.29, + "learning_rate": 3.575725375271246e-05, + "loss": 0.1861, "step": 128390 }, { - "epoch": 0.57, - "learning_rate": 2.1447244518183045e-05, - "loss": 0.1797, + "epoch": 0.29, + "learning_rate": 3.575613520950315e-05, + "loss": 0.1894, "step": 128400 }, { - "epoch": 0.57, - "learning_rate": 2.144500246625712e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.5755016666293826e-05, + "loss": 0.1797, "step": 128410 }, { - "epoch": 0.57, - "learning_rate": 2.14427604143312e-05, - "loss": 0.1826, + "epoch": 0.29, + "learning_rate": 3.57538981230845e-05, + "loss": 0.1809, "step": 128420 }, { - "epoch": 0.57, - "learning_rate": 2.1440518362405274e-05, - "loss": 0.1813, + "epoch": 0.29, + "learning_rate": 3.5752779579875175e-05, + "loss": 0.1873, "step": 128430 }, { - "epoch": 0.57, - "learning_rate": 2.1438276310479353e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.5751661036665846e-05, + "loss": 0.1762, "step": 128440 }, { - "epoch": 0.57, - "learning_rate": 2.1436034258553428e-05, - "loss": 0.1749, + "epoch": 0.29, + "learning_rate": 3.5750542493456524e-05, + "loss": 0.1764, "step": 128450 }, { - "epoch": 0.57, - "learning_rate": 2.1433792206627507e-05, - "loss": 0.1795, + "epoch": 0.29, + "learning_rate": 3.57494239502472e-05, + "loss": 0.1813, "step": 128460 }, { - "epoch": 0.57, - "learning_rate": 2.1431550154701586e-05, - "loss": 0.1743, + "epoch": 0.29, + "learning_rate": 3.574830540703787e-05, + "loss": 0.1795, "step": 128470 }, { - "epoch": 0.57, - "learning_rate": 2.142930810277566e-05, - "loss": 0.1802, + "epoch": 0.29, + "learning_rate": 3.574718686382855e-05, + "loss": 0.1891, "step": 128480 }, { - "epoch": 0.57, - "learning_rate": 2.142706605084974e-05, - "loss": 0.1753, + "epoch": 0.29, + "learning_rate": 3.574606832061922e-05, + "loss": 0.1806, "step": 128490 }, { - "epoch": 0.57, - "learning_rate": 2.1424823998923815e-05, - "loss": 0.1804, + "epoch": 0.29, + "learning_rate": 3.57449497774099e-05, + "loss": 0.1803, "step": 128500 }, { - "epoch": 0.57, - "learning_rate": 2.1422581946997894e-05, - "loss": 0.1829, + "epoch": 0.29, + "learning_rate": 3.574383123420058e-05, + "loss": 0.18, "step": 128510 }, { - "epoch": 0.57, - "learning_rate": 2.142033989507197e-05, - "loss": 0.1788, + "epoch": 0.29, + "learning_rate": 3.5742712690991256e-05, + "loss": 0.1823, "step": 128520 }, { - "epoch": 0.57, - "learning_rate": 2.1418097843146048e-05, - "loss": 0.1764, + "epoch": 0.29, + "learning_rate": 3.5741594147781934e-05, + "loss": 0.1851, "step": 128530 }, { - "epoch": 0.57, - "learning_rate": 2.1415855791220127e-05, - "loss": 0.1768, + "epoch": 0.29, + "learning_rate": 3.5740475604572605e-05, + "loss": 0.1802, "step": 128540 }, { - "epoch": 0.57, - "learning_rate": 2.1413613739294202e-05, - "loss": 0.1746, + "epoch": 0.29, + "learning_rate": 3.573935706136328e-05, + "loss": 0.1819, "step": 128550 }, { - "epoch": 0.57, - "learning_rate": 2.141137168736828e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.573823851815396e-05, + "loss": 0.1822, "step": 128560 }, { - "epoch": 0.57, - "learning_rate": 2.1409129635442356e-05, - "loss": 0.1769, + "epoch": 0.29, + "learning_rate": 3.573711997494463e-05, + "loss": 0.18, "step": 128570 }, { - "epoch": 0.57, - "learning_rate": 2.1406887583516435e-05, - "loss": 0.1776, + "epoch": 0.29, + "learning_rate": 3.573600143173531e-05, + "loss": 0.1801, "step": 128580 }, { - "epoch": 0.57, - "learning_rate": 2.140464553159051e-05, - "loss": 0.1677, + "epoch": 0.29, + "learning_rate": 3.573488288852598e-05, + "loss": 0.184, "step": 128590 }, { - "epoch": 0.57, - "learning_rate": 2.140240347966459e-05, - "loss": 0.1761, + "epoch": 0.29, + "learning_rate": 3.573376434531666e-05, + "loss": 0.1835, "step": 128600 }, { - "epoch": 0.57, - "learning_rate": 2.1400161427738667e-05, - "loss": 0.1793, + "epoch": 0.29, + "learning_rate": 3.573264580210734e-05, + "loss": 0.1822, "step": 128610 }, { - "epoch": 0.57, - "learning_rate": 2.1397919375812743e-05, - "loss": 0.1739, + "epoch": 0.29, + "learning_rate": 3.5731527258898015e-05, + "loss": 0.1835, "step": 128620 }, { - "epoch": 0.57, - "learning_rate": 2.139567732388682e-05, - "loss": 0.1792, + "epoch": 0.29, + "learning_rate": 3.573040871568869e-05, + "loss": 0.1874, "step": 128630 }, { - "epoch": 0.57, - "learning_rate": 2.13934352719609e-05, - "loss": 0.1778, + "epoch": 0.29, + "learning_rate": 3.5729290172479364e-05, + "loss": 0.1773, "step": 128640 }, { - "epoch": 0.57, - "learning_rate": 2.139119322003498e-05, - "loss": 0.1813, + "epoch": 0.29, + "learning_rate": 3.572817162927004e-05, + "loss": 0.178, "step": 128650 }, { - "epoch": 0.57, - "learning_rate": 2.1388951168109054e-05, - "loss": 0.1762, + "epoch": 0.29, + "learning_rate": 3.572705308606072e-05, + "loss": 0.1821, "step": 128660 }, { - "epoch": 0.57, - "learning_rate": 2.1386709116183133e-05, - "loss": 0.1746, + "epoch": 0.29, + "learning_rate": 3.572593454285139e-05, + "loss": 0.1812, "step": 128670 }, { - "epoch": 0.57, - "learning_rate": 2.138446706425721e-05, - "loss": 0.1763, + "epoch": 0.29, + "learning_rate": 3.572481599964207e-05, + "loss": 0.1789, "step": 128680 }, { - "epoch": 0.57, - "learning_rate": 2.1382225012331287e-05, - "loss": 0.1811, - "step": 128690 + "epoch": 0.29, + "learning_rate": 3.572369745643274e-05, + "loss": 0.1795, + "step": 128690 }, { - "epoch": 0.57, - "learning_rate": 2.1379982960405366e-05, - "loss": 0.184, + "epoch": 0.29, + "learning_rate": 3.572257891322342e-05, + "loss": 0.1837, "step": 128700 }, { - "epoch": 0.57, - "learning_rate": 2.137774090847944e-05, - "loss": 0.181, + "epoch": 0.29, + "learning_rate": 3.5721460370014096e-05, + "loss": 0.1798, "step": 128710 }, { - "epoch": 0.57, - "learning_rate": 2.137549885655352e-05, - "loss": 0.1805, + "epoch": 0.29, + "learning_rate": 3.5720341826804774e-05, + "loss": 0.178, "step": 128720 }, { - "epoch": 0.57, - "learning_rate": 2.1373256804627595e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.571922328359545e-05, + "loss": 0.1822, "step": 128730 }, { - "epoch": 0.57, - "learning_rate": 2.1371014752701674e-05, - "loss": 0.1834, + "epoch": 0.29, + "learning_rate": 3.571810474038612e-05, + "loss": 0.1803, "step": 128740 }, { - "epoch": 0.57, - "learning_rate": 2.1368772700775753e-05, - "loss": 0.1818, + "epoch": 0.29, + "learning_rate": 3.57169861971768e-05, + "loss": 0.1866, "step": 128750 }, { - "epoch": 0.57, - "learning_rate": 2.1366530648849828e-05, - "loss": 0.1763, + "epoch": 0.29, + "learning_rate": 3.571586765396747e-05, + "loss": 0.1826, "step": 128760 }, { - "epoch": 0.57, - "learning_rate": 2.1364288596923907e-05, - "loss": 0.1794, + "epoch": 0.29, + "learning_rate": 3.571474911075815e-05, + "loss": 0.1853, "step": 128770 }, { - "epoch": 0.57, - "learning_rate": 2.1362046544997982e-05, - "loss": 0.1828, + "epoch": 0.29, + "learning_rate": 3.571363056754883e-05, + "loss": 0.1792, "step": 128780 }, { - "epoch": 0.57, - "learning_rate": 2.135980449307206e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.57125120243395e-05, + "loss": 0.1859, "step": 128790 }, { - "epoch": 0.57, - "learning_rate": 2.1357562441146136e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.571139348113018e-05, + "loss": 0.1799, "step": 128800 }, { - "epoch": 0.58, - "learning_rate": 2.1355320389220215e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.5710274937920855e-05, + "loss": 0.1799, "step": 128810 }, { - "epoch": 0.58, - "learning_rate": 2.1353078337294293e-05, - "loss": 0.176, + "epoch": 0.29, + "learning_rate": 3.570915639471153e-05, + "loss": 0.183, "step": 128820 }, { - "epoch": 0.58, - "learning_rate": 2.135083628536837e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.570803785150221e-05, + "loss": 0.1775, "step": 128830 }, { - "epoch": 0.58, - "learning_rate": 2.1348594233442447e-05, - "loss": 0.1814, + "epoch": 0.29, + "learning_rate": 3.570691930829288e-05, + "loss": 0.1846, "step": 128840 }, { - "epoch": 0.58, - "learning_rate": 2.1346352181516523e-05, - "loss": 0.1792, + "epoch": 0.29, + "learning_rate": 3.570580076508356e-05, + "loss": 0.1777, "step": 128850 }, { - "epoch": 0.58, - "learning_rate": 2.13441101295906e-05, - "loss": 0.1742, + "epoch": 0.29, + "learning_rate": 3.570468222187423e-05, + "loss": 0.1833, "step": 128860 }, { - "epoch": 0.58, - "learning_rate": 2.1341868077664677e-05, - "loss": 0.1814, + "epoch": 0.29, + "learning_rate": 3.570356367866491e-05, + "loss": 0.1831, "step": 128870 }, { - "epoch": 0.58, - "learning_rate": 2.1339626025738756e-05, - "loss": 0.1825, + "epoch": 0.29, + "learning_rate": 3.5702445135455586e-05, + "loss": 0.1821, "step": 128880 }, { - "epoch": 0.58, - "learning_rate": 2.1337383973812834e-05, - "loss": 0.1827, + "epoch": 0.29, + "learning_rate": 3.570132659224626e-05, + "loss": 0.1863, "step": 128890 }, { - "epoch": 0.58, - "learning_rate": 2.1335141921886913e-05, - "loss": 0.1782, + "epoch": 0.29, + "learning_rate": 3.5700208049036936e-05, + "loss": 0.1808, "step": 128900 }, { - "epoch": 0.58, - "learning_rate": 2.133289986996099e-05, - "loss": 0.1788, + "epoch": 0.29, + "learning_rate": 3.569908950582761e-05, + "loss": 0.1862, "step": 128910 }, { - "epoch": 0.58, - "learning_rate": 2.1330657818035067e-05, - "loss": 0.1758, + "epoch": 0.29, + "learning_rate": 3.5697970962618285e-05, + "loss": 0.1802, "step": 128920 }, { - "epoch": 0.58, - "learning_rate": 2.1328415766109146e-05, - "loss": 0.1759, + "epoch": 0.29, + "learning_rate": 3.569685241940896e-05, + "loss": 0.1817, "step": 128930 }, { - "epoch": 0.58, - "learning_rate": 2.132617371418322e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.569573387619964e-05, + "loss": 0.1855, "step": 128940 }, { - "epoch": 0.58, - "learning_rate": 2.13239316622573e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.569461533299032e-05, + "loss": 0.1842, "step": 128950 }, { - "epoch": 0.58, - "learning_rate": 2.132168961033138e-05, - "loss": 0.1763, + "epoch": 0.29, + "learning_rate": 3.569349678978099e-05, + "loss": 0.1791, "step": 128960 }, { - "epoch": 0.58, - "learning_rate": 2.1319447558405454e-05, - "loss": 0.1749, + "epoch": 0.29, + "learning_rate": 3.569237824657167e-05, + "loss": 0.1852, "step": 128970 }, { - "epoch": 0.58, - "learning_rate": 2.1317205506479533e-05, - "loss": 0.1753, + "epoch": 0.29, + "learning_rate": 3.5691259703362345e-05, + "loss": 0.1834, "step": 128980 }, { - "epoch": 0.58, - "learning_rate": 2.1314963454553608e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.5690141160153017e-05, + "loss": 0.1827, "step": 128990 }, { - "epoch": 0.58, - "learning_rate": 2.1312721402627687e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.5689022616943695e-05, + "loss": 0.1786, "step": 129000 }, { - "epoch": 0.58, - "learning_rate": 2.1310479350701762e-05, - "loss": 0.1754, + "epoch": 0.29, + "learning_rate": 3.5687904073734366e-05, + "loss": 0.1839, "step": 129010 }, { - "epoch": 0.58, - "learning_rate": 2.130823729877584e-05, - "loss": 0.1786, + "epoch": 0.29, + "learning_rate": 3.5686785530525044e-05, + "loss": 0.1826, "step": 129020 }, { - "epoch": 0.58, - "learning_rate": 2.130599524684992e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.568566698731572e-05, + "loss": 0.1795, "step": 129030 }, { - "epoch": 0.58, - "learning_rate": 2.1303753194923995e-05, - "loss": 0.1789, + "epoch": 0.29, + "learning_rate": 3.56845484441064e-05, + "loss": 0.1795, "step": 129040 }, { - "epoch": 0.58, - "learning_rate": 2.1301511142998073e-05, - "loss": 0.1818, + "epoch": 0.29, + "learning_rate": 3.568342990089708e-05, + "loss": 0.1824, "step": 129050 }, { - "epoch": 0.58, - "learning_rate": 2.129926909107215e-05, - "loss": 0.1775, + "epoch": 0.29, + "learning_rate": 3.568231135768775e-05, + "loss": 0.1824, "step": 129060 }, { - "epoch": 0.58, - "learning_rate": 2.1297027039146227e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.5681192814478426e-05, + "loss": 0.1818, "step": 129070 }, { - "epoch": 0.58, - "learning_rate": 2.1294784987220303e-05, - "loss": 0.1797, + "epoch": 0.29, + "learning_rate": 3.56800742712691e-05, + "loss": 0.1867, "step": 129080 }, { - "epoch": 0.58, - "learning_rate": 2.129254293529438e-05, - "loss": 0.1808, + "epoch": 0.29, + "learning_rate": 3.5678955728059776e-05, + "loss": 0.1828, "step": 129090 }, { - "epoch": 0.58, - "learning_rate": 2.129030088336846e-05, - "loss": 0.1789, + "epoch": 0.29, + "learning_rate": 3.5677837184850453e-05, + "loss": 0.1799, "step": 129100 }, { - "epoch": 0.58, - "learning_rate": 2.1288058831442536e-05, - "loss": 0.1822, + "epoch": 0.29, + "learning_rate": 3.5676718641641125e-05, + "loss": 0.1849, "step": 129110 }, { - "epoch": 0.58, - "learning_rate": 2.1285816779516614e-05, - "loss": 0.1764, + "epoch": 0.29, + "learning_rate": 3.56756000984318e-05, + "loss": 0.1827, "step": 129120 }, { - "epoch": 0.58, - "learning_rate": 2.128357472759069e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.567448155522248e-05, + "loss": 0.1817, "step": 129130 }, { - "epoch": 0.58, - "learning_rate": 2.128155688085736e-05, - "loss": 0.1802, + "epoch": 0.29, + "learning_rate": 3.567336301201316e-05, + "loss": 0.172, "step": 129140 }, { - "epoch": 0.58, - "learning_rate": 2.127931482893144e-05, - "loss": 0.179, + "epoch": 0.29, + "learning_rate": 3.5672244468803836e-05, + "loss": 0.1829, "step": 129150 }, { - "epoch": 0.58, - "learning_rate": 2.1277072777005515e-05, - "loss": 0.1738, + "epoch": 0.29, + "learning_rate": 3.567112592559451e-05, + "loss": 0.1842, "step": 129160 }, { - "epoch": 0.58, - "learning_rate": 2.1274830725079594e-05, - "loss": 0.1818, + "epoch": 0.29, + "learning_rate": 3.5670007382385185e-05, + "loss": 0.1816, "step": 129170 }, { - "epoch": 0.58, - "learning_rate": 2.127258867315367e-05, - "loss": 0.1787, + "epoch": 0.29, + "learning_rate": 3.5668888839175857e-05, + "loss": 0.1834, "step": 129180 }, { - "epoch": 0.58, - "learning_rate": 2.1270346621227748e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.5667770295966534e-05, + "loss": 0.1843, "step": 129190 }, { - "epoch": 0.58, - "learning_rate": 2.1268104569301826e-05, - "loss": 0.1801, + "epoch": 0.29, + "learning_rate": 3.566665175275721e-05, + "loss": 0.1791, "step": 129200 }, { - "epoch": 0.58, - "learning_rate": 2.1265862517375905e-05, - "loss": 0.1769, + "epoch": 0.29, + "learning_rate": 3.5665533209547884e-05, + "loss": 0.186, "step": 129210 }, { - "epoch": 0.58, - "learning_rate": 2.1263620465449984e-05, - "loss": 0.1797, + "epoch": 0.29, + "learning_rate": 3.566441466633856e-05, + "loss": 0.1863, "step": 129220 }, { - "epoch": 0.58, - "learning_rate": 2.126137841352406e-05, - "loss": 0.1772, + "epoch": 0.29, + "learning_rate": 3.566329612312924e-05, + "loss": 0.1825, "step": 129230 }, { - "epoch": 0.58, - "learning_rate": 2.1259136361598138e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.566217757991992e-05, + "loss": 0.1772, "step": 129240 }, { - "epoch": 0.58, - "learning_rate": 2.1256894309672213e-05, - "loss": 0.1787, + "epoch": 0.29, + "learning_rate": 3.5661059036710595e-05, + "loss": 0.1872, "step": 129250 }, { - "epoch": 0.58, - "learning_rate": 2.1254652257746292e-05, - "loss": 0.1788, + "epoch": 0.29, + "learning_rate": 3.5659940493501266e-05, + "loss": 0.1863, "step": 129260 }, { - "epoch": 0.58, - "learning_rate": 2.1252410205820367e-05, - "loss": 0.1701, + "epoch": 0.29, + "learning_rate": 3.5658821950291944e-05, + "loss": 0.1865, "step": 129270 }, { - "epoch": 0.58, - "learning_rate": 2.1250168153894446e-05, - "loss": 0.1786, + "epoch": 0.29, + "learning_rate": 3.5657703407082616e-05, + "loss": 0.1787, "step": 129280 }, { - "epoch": 0.58, - "learning_rate": 2.1247926101968525e-05, - "loss": 0.1746, + "epoch": 0.29, + "learning_rate": 3.5656584863873293e-05, + "loss": 0.1794, "step": 129290 }, { - "epoch": 0.58, - "learning_rate": 2.12456840500426e-05, - "loss": 0.1841, + "epoch": 0.29, + "learning_rate": 3.565546632066397e-05, + "loss": 0.186, "step": 129300 }, { - "epoch": 0.58, - "learning_rate": 2.124344199811668e-05, + "epoch": 0.29, + "learning_rate": 3.565434777745464e-05, "loss": 0.1824, "step": 129310 }, { - "epoch": 0.58, - "learning_rate": 2.1241199946190754e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.565322923424532e-05, + "loss": 0.1836, "step": 129320 }, { - "epoch": 0.58, - "learning_rate": 2.1238957894264833e-05, - "loss": 0.1824, + "epoch": 0.29, + "learning_rate": 3.565211069103599e-05, + "loss": 0.1822, "step": 129330 }, { - "epoch": 0.58, - "learning_rate": 2.1236715842338908e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.565099214782667e-05, + "loss": 0.1811, "step": 129340 }, { - "epoch": 0.58, - "learning_rate": 2.1234473790412987e-05, - "loss": 0.177, + "epoch": 0.29, + "learning_rate": 3.564987360461735e-05, + "loss": 0.1764, "step": 129350 }, { - "epoch": 0.58, - "learning_rate": 2.1232231738487065e-05, - "loss": 0.1794, + "epoch": 0.29, + "learning_rate": 3.5648755061408025e-05, + "loss": 0.1771, "step": 129360 }, { - "epoch": 0.58, - "learning_rate": 2.122998968656114e-05, - "loss": 0.1808, + "epoch": 0.29, + "learning_rate": 3.56476365181987e-05, + "loss": 0.1785, "step": 129370 }, { - "epoch": 0.58, - "learning_rate": 2.122774763463522e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.5646517974989374e-05, + "loss": 0.1846, "step": 129380 }, { - "epoch": 0.58, - "learning_rate": 2.1225505582709295e-05, - "loss": 0.1795, + "epoch": 0.29, + "learning_rate": 3.564539943178005e-05, + "loss": 0.1844, "step": 129390 }, { - "epoch": 0.58, - "learning_rate": 2.1223263530783374e-05, - "loss": 0.1771, + "epoch": 0.29, + "learning_rate": 3.5644280888570724e-05, + "loss": 0.1788, "step": 129400 }, { - "epoch": 0.58, - "learning_rate": 2.122102147885745e-05, - "loss": 0.1828, + "epoch": 0.29, + "learning_rate": 3.56431623453614e-05, + "loss": 0.1819, "step": 129410 }, { - "epoch": 0.58, - "learning_rate": 2.1218779426931528e-05, - "loss": 0.1813, + "epoch": 0.29, + "learning_rate": 3.564204380215208e-05, + "loss": 0.1814, "step": 129420 }, { - "epoch": 0.58, - "learning_rate": 2.1216537375005606e-05, - "loss": 0.1776, + "epoch": 0.29, + "learning_rate": 3.564092525894275e-05, + "loss": 0.1852, "step": 129430 }, { - "epoch": 0.58, - "learning_rate": 2.121429532307968e-05, - "loss": 0.1693, + "epoch": 0.29, + "learning_rate": 3.563980671573343e-05, + "loss": 0.1812, "step": 129440 }, { - "epoch": 0.58, - "learning_rate": 2.121205327115376e-05, - "loss": 0.1778, + "epoch": 0.29, + "learning_rate": 3.5638688172524106e-05, + "loss": 0.1774, "step": 129450 }, { - "epoch": 0.58, - "learning_rate": 2.120981121922784e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.5637569629314784e-05, + "loss": 0.1829, "step": 129460 }, { - "epoch": 0.58, - "learning_rate": 2.1207569167301918e-05, - "loss": 0.1772, + "epoch": 0.29, + "learning_rate": 3.563645108610546e-05, + "loss": 0.1856, "step": 129470 }, { - "epoch": 0.58, - "learning_rate": 2.1205327115375993e-05, - "loss": 0.1794, + "epoch": 0.29, + "learning_rate": 3.5635332542896133e-05, + "loss": 0.1804, "step": 129480 }, { - "epoch": 0.58, - "learning_rate": 2.1203085063450072e-05, - "loss": 0.1799, + "epoch": 0.29, + "learning_rate": 3.563421399968681e-05, + "loss": 0.1778, "step": 129490 }, { - "epoch": 0.58, - "learning_rate": 2.120084301152415e-05, - "loss": 0.184, + "epoch": 0.29, + "learning_rate": 3.563309545647748e-05, + "loss": 0.182, "step": 129500 }, { - "epoch": 0.58, - "learning_rate": 2.1198600959598226e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.563197691326816e-05, + "loss": 0.1828, "step": 129510 }, { - "epoch": 0.58, - "learning_rate": 2.1196358907672305e-05, - "loss": 0.1798, + "epoch": 0.29, + "learning_rate": 3.563085837005884e-05, + "loss": 0.1834, "step": 129520 }, { - "epoch": 0.58, - "learning_rate": 2.119411685574638e-05, - "loss": 0.1774, + "epoch": 0.29, + "learning_rate": 3.562973982684951e-05, + "loss": 0.1858, "step": 129530 }, { - "epoch": 0.58, - "learning_rate": 2.119187480382046e-05, - "loss": 0.1787, + "epoch": 0.29, + "learning_rate": 3.562862128364019e-05, + "loss": 0.1766, "step": 129540 }, { - "epoch": 0.58, - "learning_rate": 2.1189632751894534e-05, - "loss": 0.1718, + "epoch": 0.29, + "learning_rate": 3.5627502740430865e-05, + "loss": 0.1837, "step": 129550 }, { - "epoch": 0.58, - "learning_rate": 2.1187390699968613e-05, - "loss": 0.1797, + "epoch": 0.29, + "learning_rate": 3.562638419722154e-05, + "loss": 0.1875, "step": 129560 }, { - "epoch": 0.58, - "learning_rate": 2.118514864804269e-05, - "loss": 0.1785, + "epoch": 0.29, + "learning_rate": 3.562526565401222e-05, + "loss": 0.1836, "step": 129570 }, { - "epoch": 0.58, - "learning_rate": 2.1182906596116767e-05, - "loss": 0.1842, + "epoch": 0.29, + "learning_rate": 3.562414711080289e-05, + "loss": 0.1825, "step": 129580 }, { - "epoch": 0.58, - "learning_rate": 2.1180664544190845e-05, - "loss": 0.1743, + "epoch": 0.29, + "learning_rate": 3.562302856759357e-05, + "loss": 0.1815, "step": 129590 }, { - "epoch": 0.58, - "learning_rate": 2.117842249226492e-05, - "loss": 0.1737, + "epoch": 0.29, + "learning_rate": 3.562191002438424e-05, + "loss": 0.1865, "step": 129600 }, { - "epoch": 0.58, - "learning_rate": 2.1176180440339e-05, - "loss": 0.1801, + "epoch": 0.29, + "learning_rate": 3.562079148117492e-05, + "loss": 0.1761, "step": 129610 }, { - "epoch": 0.58, - "learning_rate": 2.1173938388413075e-05, - "loss": 0.1774, + "epoch": 0.29, + "learning_rate": 3.56196729379656e-05, + "loss": 0.1858, "step": 129620 }, { - "epoch": 0.58, - "learning_rate": 2.1171696336487154e-05, - "loss": 0.1784, + "epoch": 0.29, + "learning_rate": 3.561855439475627e-05, + "loss": 0.1842, "step": 129630 }, { - "epoch": 0.58, - "learning_rate": 2.1169454284561232e-05, - "loss": 0.1744, + "epoch": 0.29, + "learning_rate": 3.5617435851546946e-05, + "loss": 0.1836, "step": 129640 }, { - "epoch": 0.58, - "learning_rate": 2.1167212232635308e-05, - "loss": 0.1813, + "epoch": 0.29, + "learning_rate": 3.5616317308337624e-05, + "loss": 0.1841, "step": 129650 }, { - "epoch": 0.58, - "learning_rate": 2.1164970180709386e-05, - "loss": 0.173, + "epoch": 0.29, + "learning_rate": 3.56151987651283e-05, + "loss": 0.1819, "step": 129660 }, { - "epoch": 0.58, - "learning_rate": 2.116272812878346e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.561408022191897e-05, + "loss": 0.1815, "step": 129670 }, { - "epoch": 0.58, - "learning_rate": 2.116048607685754e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.561296167870965e-05, + "loss": 0.1839, "step": 129680 }, { - "epoch": 0.58, - "learning_rate": 2.1158244024931616e-05, - "loss": 0.179, + "epoch": 0.29, + "learning_rate": 3.561184313550033e-05, + "loss": 0.1816, "step": 129690 }, { - "epoch": 0.58, - "learning_rate": 2.1156001973005694e-05, - "loss": 0.1732, + "epoch": 0.29, + "learning_rate": 3.5610724592291e-05, + "loss": 0.1774, "step": 129700 }, { - "epoch": 0.58, - "learning_rate": 2.1153759921079773e-05, - "loss": 0.1806, + "epoch": 0.29, + "learning_rate": 3.560960604908168e-05, + "loss": 0.1777, "step": 129710 }, { - "epoch": 0.58, - "learning_rate": 2.115151786915385e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.560848750587235e-05, + "loss": 0.1812, "step": 129720 }, { - "epoch": 0.58, - "learning_rate": 2.1149275817227927e-05, - "loss": 0.1756, + "epoch": 0.29, + "learning_rate": 3.560736896266303e-05, + "loss": 0.1773, "step": 129730 }, { - "epoch": 0.58, - "learning_rate": 2.1147033765302006e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.5606250419453705e-05, + "loss": 0.1799, "step": 129740 }, { - "epoch": 0.58, - "learning_rate": 2.1144791713376085e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.5605131876244376e-05, + "loss": 0.1837, "step": 129750 }, { - "epoch": 0.58, - "learning_rate": 2.114254966145016e-05, - "loss": 0.1747, + "epoch": 0.29, + "learning_rate": 3.560401333303506e-05, + "loss": 0.1805, "step": 129760 }, { - "epoch": 0.58, - "learning_rate": 2.114030760952424e-05, - "loss": 0.176, + "epoch": 0.29, + "learning_rate": 3.560289478982573e-05, + "loss": 0.1808, "step": 129770 }, { - "epoch": 0.58, - "learning_rate": 2.1138065557598317e-05, - "loss": 0.1755, + "epoch": 0.29, + "learning_rate": 3.560177624661641e-05, + "loss": 0.1842, "step": 129780 }, { - "epoch": 0.58, - "learning_rate": 2.1135823505672393e-05, - "loss": 0.18, + "epoch": 0.29, + "learning_rate": 3.560065770340709e-05, + "loss": 0.178, "step": 129790 }, { - "epoch": 0.58, - "learning_rate": 2.113358145374647e-05, - "loss": 0.1793, + "epoch": 0.29, + "learning_rate": 3.559953916019776e-05, + "loss": 0.1842, "step": 129800 }, { - "epoch": 0.58, - "learning_rate": 2.1131339401820547e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.559842061698844e-05, + "loss": 0.1757, "step": 129810 }, { - "epoch": 0.58, - "learning_rate": 2.1129097349894625e-05, - "loss": 0.1744, + "epoch": 0.29, + "learning_rate": 3.559730207377911e-05, + "loss": 0.1822, "step": 129820 }, { - "epoch": 0.58, - "learning_rate": 2.11268552979687e-05, - "loss": 0.1834, + "epoch": 0.29, + "learning_rate": 3.5596183530569786e-05, + "loss": 0.1857, "step": 129830 }, { - "epoch": 0.58, - "learning_rate": 2.112461324604278e-05, - "loss": 0.1795, + "epoch": 0.29, + "learning_rate": 3.5595064987360464e-05, + "loss": 0.1844, "step": 129840 }, { - "epoch": 0.58, - "learning_rate": 2.1122371194116858e-05, - "loss": 0.1734, + "epoch": 0.29, + "learning_rate": 3.5593946444151135e-05, + "loss": 0.1807, "step": 129850 }, { - "epoch": 0.58, - "learning_rate": 2.1120129142190934e-05, - "loss": 0.1731, + "epoch": 0.29, + "learning_rate": 3.559282790094181e-05, + "loss": 0.1843, "step": 129860 }, { - "epoch": 0.58, - "learning_rate": 2.1117887090265012e-05, - "loss": 0.1764, + "epoch": 0.29, + "learning_rate": 3.559170935773249e-05, + "loss": 0.1845, "step": 129870 }, { - "epoch": 0.58, - "learning_rate": 2.1115645038339088e-05, - "loss": 0.1755, + "epoch": 0.29, + "learning_rate": 3.559059081452317e-05, + "loss": 0.1895, "step": 129880 }, { - "epoch": 0.58, - "learning_rate": 2.1113402986413166e-05, - "loss": 0.1766, + "epoch": 0.29, + "learning_rate": 3.558947227131385e-05, + "loss": 0.1829, "step": 129890 }, { - "epoch": 0.58, - "learning_rate": 2.111116093448724e-05, - "loss": 0.1815, + "epoch": 0.29, + "learning_rate": 3.558835372810452e-05, + "loss": 0.1845, "step": 129900 }, { - "epoch": 0.58, - "learning_rate": 2.110891888256132e-05, - "loss": 0.1751, + "epoch": 0.29, + "learning_rate": 3.5587235184895196e-05, + "loss": 0.1811, "step": 129910 }, { - "epoch": 0.58, - "learning_rate": 2.11066768306354e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.558611664168587e-05, + "loss": 0.1801, "step": 129920 }, { - "epoch": 0.58, - "learning_rate": 2.1104434778709474e-05, - "loss": 0.1804, + "epoch": 0.29, + "learning_rate": 3.5584998098476545e-05, + "loss": 0.1785, "step": 129930 }, { - "epoch": 0.58, - "learning_rate": 2.1102192726783553e-05, - "loss": 0.1776, + "epoch": 0.29, + "learning_rate": 3.558387955526722e-05, + "loss": 0.1803, "step": 129940 }, { - "epoch": 0.58, - "learning_rate": 2.109995067485763e-05, - "loss": 0.1809, + "epoch": 0.29, + "learning_rate": 3.5582761012057894e-05, + "loss": 0.1787, "step": 129950 }, { - "epoch": 0.58, - "learning_rate": 2.1097708622931707e-05, - "loss": 0.173, + "epoch": 0.29, + "learning_rate": 3.558164246884857e-05, + "loss": 0.1797, "step": 129960 }, { - "epoch": 0.58, - "learning_rate": 2.1095466571005783e-05, - "loss": 0.1802, + "epoch": 0.29, + "learning_rate": 3.558052392563925e-05, + "loss": 0.1823, "step": 129970 }, { - "epoch": 0.58, - "learning_rate": 2.109322451907986e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.557940538242993e-05, + "loss": 0.1879, "step": 129980 }, { - "epoch": 0.58, - "learning_rate": 2.109098246715394e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.55782868392206e-05, + "loss": 0.1837, "step": 129990 }, { - "epoch": 0.58, - "learning_rate": 2.108874041522802e-05, - "loss": 0.1741, + "epoch": 0.29, + "learning_rate": 3.557716829601128e-05, + "loss": 0.18, "step": 130000 }, { - "epoch": 0.58, - "learning_rate": 2.1086498363302097e-05, - "loss": 0.1742, + "epoch": 0.29, + "learning_rate": 3.5576049752801955e-05, + "loss": 0.1847, "step": 130010 }, { - "epoch": 0.58, - "learning_rate": 2.1084256311376173e-05, - "loss": 0.1749, + "epoch": 0.29, + "learning_rate": 3.5574931209592626e-05, + "loss": 0.1813, "step": 130020 }, { - "epoch": 0.58, - "learning_rate": 2.108201425945025e-05, - "loss": 0.1786, + "epoch": 0.29, + "learning_rate": 3.5573812666383304e-05, + "loss": 0.1836, "step": 130030 }, { - "epoch": 0.58, - "learning_rate": 2.1079772207524327e-05, - "loss": 0.1796, + "epoch": 0.29, + "learning_rate": 3.5572694123173975e-05, + "loss": 0.184, "step": 130040 }, { - "epoch": 0.58, - "learning_rate": 2.1077530155598405e-05, - "loss": 0.1721, + "epoch": 0.29, + "learning_rate": 3.557157557996465e-05, + "loss": 0.1797, "step": 130050 }, { - "epoch": 0.58, - "learning_rate": 2.1075288103672484e-05, - "loss": 0.1705, + "epoch": 0.29, + "learning_rate": 3.557045703675533e-05, + "loss": 0.1809, "step": 130060 }, { - "epoch": 0.58, - "learning_rate": 2.107304605174656e-05, - "loss": 0.1758, + "epoch": 0.29, + "learning_rate": 3.556933849354601e-05, + "loss": 0.1804, "step": 130070 }, { - "epoch": 0.58, - "learning_rate": 2.1070803999820638e-05, - "loss": 0.1783, + "epoch": 0.29, + "learning_rate": 3.556821995033669e-05, + "loss": 0.1789, "step": 130080 }, { - "epoch": 0.58, - "learning_rate": 2.1068561947894714e-05, - "loss": 0.1769, + "epoch": 0.29, + "learning_rate": 3.556710140712736e-05, + "loss": 0.1852, "step": 130090 }, { - "epoch": 0.58, - "learning_rate": 2.1066319895968792e-05, - "loss": 0.1785, + "epoch": 0.29, + "learning_rate": 3.5565982863918036e-05, + "loss": 0.175, "step": 130100 }, { - "epoch": 0.58, - "learning_rate": 2.1064077844042868e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.5564864320708714e-05, + "loss": 0.1865, "step": 130110 }, { - "epoch": 0.58, - "learning_rate": 2.1061835792116946e-05, - "loss": 0.1729, + "epoch": 0.29, + "learning_rate": 3.5563745777499385e-05, + "loss": 0.1815, "step": 130120 }, { - "epoch": 0.58, - "learning_rate": 2.1059593740191025e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.556262723429006e-05, + "loss": 0.1823, "step": 130130 }, { - "epoch": 0.58, - "learning_rate": 2.10573516882651e-05, - "loss": 0.1787, + "epoch": 0.29, + "learning_rate": 3.5561508691080734e-05, + "loss": 0.1857, "step": 130140 }, { - "epoch": 0.58, - "learning_rate": 2.105510963633918e-05, - "loss": 0.1804, + "epoch": 0.29, + "learning_rate": 3.556039014787141e-05, + "loss": 0.1787, "step": 130150 }, { - "epoch": 0.58, - "learning_rate": 2.1052867584413254e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.555927160466209e-05, + "loss": 0.1757, "step": 130160 }, { - "epoch": 0.58, - "learning_rate": 2.1050625532487333e-05, - "loss": 0.1733, + "epoch": 0.29, + "learning_rate": 3.555815306145276e-05, + "loss": 0.1737, "step": 130170 }, { - "epoch": 0.58, - "learning_rate": 2.1048383480561412e-05, - "loss": 0.1741, + "epoch": 0.29, + "learning_rate": 3.5557034518243446e-05, + "loss": 0.1797, "step": 130180 }, { - "epoch": 0.58, - "learning_rate": 2.1046141428635487e-05, - "loss": 0.1764, + "epoch": 0.29, + "learning_rate": 3.555591597503412e-05, + "loss": 0.1767, "step": 130190 }, { - "epoch": 0.58, - "learning_rate": 2.1043899376709566e-05, - "loss": 0.1751, + "epoch": 0.29, + "learning_rate": 3.5554797431824795e-05, + "loss": 0.1813, "step": 130200 }, { - "epoch": 0.58, - "learning_rate": 2.104165732478364e-05, - "loss": 0.1788, + "epoch": 0.29, + "learning_rate": 3.555367888861547e-05, + "loss": 0.1759, "step": 130210 }, { - "epoch": 0.58, - "learning_rate": 2.103941527285772e-05, - "loss": 0.176, + "epoch": 0.29, + "learning_rate": 3.5552560345406144e-05, + "loss": 0.179, "step": 130220 }, { - "epoch": 0.58, - "learning_rate": 2.1037173220931795e-05, - "loss": 0.1748, + "epoch": 0.29, + "learning_rate": 3.555144180219682e-05, + "loss": 0.1849, "step": 130230 }, { - "epoch": 0.58, - "learning_rate": 2.1034931169005874e-05, - "loss": 0.175, + "epoch": 0.29, + "learning_rate": 3.555032325898749e-05, + "loss": 0.182, "step": 130240 }, { - "epoch": 0.58, - "learning_rate": 2.1032689117079953e-05, - "loss": 0.1741, + "epoch": 0.29, + "learning_rate": 3.554920471577817e-05, + "loss": 0.1901, "step": 130250 }, { - "epoch": 0.58, - "learning_rate": 2.1030447065154028e-05, - "loss": 0.1763, + "epoch": 0.29, + "learning_rate": 3.554808617256885e-05, + "loss": 0.1825, "step": 130260 }, { - "epoch": 0.58, - "learning_rate": 2.1028205013228107e-05, - "loss": 0.1773, + "epoch": 0.29, + "learning_rate": 3.554696762935952e-05, + "loss": 0.1786, "step": 130270 }, { - "epoch": 0.58, - "learning_rate": 2.1025962961302186e-05, - "loss": 0.1702, + "epoch": 0.29, + "learning_rate": 3.55458490861502e-05, + "loss": 0.1813, "step": 130280 }, { - "epoch": 0.58, - "learning_rate": 2.1023720909376264e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.5544730542940876e-05, + "loss": 0.1856, "step": 130290 }, { - "epoch": 0.58, - "learning_rate": 2.102147885745034e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.5543611999731554e-05, + "loss": 0.1861, "step": 130300 }, { - "epoch": 0.58, - "learning_rate": 2.1019236805524418e-05, - "loss": 0.1696, + "epoch": 0.29, + "learning_rate": 3.5542493456522225e-05, + "loss": 0.1869, "step": 130310 }, { - "epoch": 0.58, - "learning_rate": 2.1016994753598497e-05, - "loss": 0.1708, + "epoch": 0.29, + "learning_rate": 3.55413749133129e-05, + "loss": 0.1816, "step": 130320 }, { - "epoch": 0.58, - "learning_rate": 2.1014752701672572e-05, - "loss": 0.1768, + "epoch": 0.29, + "learning_rate": 3.554025637010358e-05, + "loss": 0.184, "step": 130330 }, { - "epoch": 0.58, - "learning_rate": 2.101251064974665e-05, - "loss": 0.1775, + "epoch": 0.29, + "learning_rate": 3.553913782689425e-05, + "loss": 0.186, "step": 130340 }, { - "epoch": 0.58, - "learning_rate": 2.1010268597820726e-05, - "loss": 0.1744, + "epoch": 0.29, + "learning_rate": 3.553801928368493e-05, + "loss": 0.1819, "step": 130350 }, { - "epoch": 0.58, - "learning_rate": 2.1008026545894805e-05, - "loss": 0.1774, + "epoch": 0.29, + "learning_rate": 3.55369007404756e-05, + "loss": 0.1879, "step": 130360 }, { - "epoch": 0.58, - "learning_rate": 2.100578449396888e-05, - "loss": 0.178, + "epoch": 0.29, + "learning_rate": 3.553578219726628e-05, + "loss": 0.1828, "step": 130370 }, { - "epoch": 0.58, - "learning_rate": 2.100354244204296e-05, - "loss": 0.1734, + "epoch": 0.29, + "learning_rate": 3.553466365405696e-05, + "loss": 0.1795, "step": 130380 }, { - "epoch": 0.58, - "learning_rate": 2.1001300390117038e-05, - "loss": 0.1811, + "epoch": 0.29, + "learning_rate": 3.5533545110847635e-05, + "loss": 0.1875, "step": 130390 }, { - "epoch": 0.58, - "learning_rate": 2.0999058338191113e-05, - "loss": 0.1696, + "epoch": 0.29, + "learning_rate": 3.553242656763831e-05, + "loss": 0.1774, "step": 130400 }, { - "epoch": 0.58, - "learning_rate": 2.0996816286265192e-05, - "loss": 0.172, + "epoch": 0.29, + "learning_rate": 3.5531308024428984e-05, + "loss": 0.1776, "step": 130410 }, { - "epoch": 0.58, - "learning_rate": 2.0994574234339267e-05, - "loss": 0.1719, + "epoch": 0.29, + "learning_rate": 3.553018948121966e-05, + "loss": 0.1839, "step": 130420 }, { - "epoch": 0.58, - "learning_rate": 2.0992332182413346e-05, - "loss": 0.174, + "epoch": 0.29, + "learning_rate": 3.552907093801034e-05, + "loss": 0.1847, "step": 130430 }, { - "epoch": 0.58, - "learning_rate": 2.099009013048742e-05, - "loss": 0.1713, + "epoch": 0.29, + "learning_rate": 3.552795239480101e-05, + "loss": 0.1805, "step": 130440 }, { - "epoch": 0.58, - "learning_rate": 2.09878480785615e-05, - "loss": 0.1752, + "epoch": 0.29, + "learning_rate": 3.552683385159169e-05, + "loss": 0.1825, "step": 130450 }, { - "epoch": 0.58, - "learning_rate": 2.098560602663558e-05, - "loss": 0.1709, + "epoch": 0.29, + "learning_rate": 3.552571530838236e-05, + "loss": 0.1798, "step": 130460 }, { - "epoch": 0.58, - "learning_rate": 2.0983363974709654e-05, - "loss": 0.1717, + "epoch": 0.29, + "learning_rate": 3.552459676517304e-05, + "loss": 0.1811, "step": 130470 }, { - "epoch": 0.58, - "learning_rate": 2.0981121922783733e-05, - "loss": 0.1718, + "epoch": 0.29, + "learning_rate": 3.5523478221963716e-05, + "loss": 0.1792, "step": 130480 }, { - "epoch": 0.58, - "learning_rate": 2.0978879870857808e-05, - "loss": 0.1726, + "epoch": 0.29, + "learning_rate": 3.5522359678754394e-05, + "loss": 0.1794, "step": 130490 }, { - "epoch": 0.58, - "learning_rate": 2.0976637818931887e-05, - "loss": 0.1766, + "epoch": 0.29, + "learning_rate": 3.552124113554507e-05, + "loss": 0.1823, "step": 130500 }, { - "epoch": 0.58, - "learning_rate": 2.0974395767005962e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.552012259233574e-05, + "loss": 0.1796, "step": 130510 }, { - "epoch": 0.58, - "learning_rate": 2.097215371508004e-05, - "loss": 0.1807, + "epoch": 0.29, + "learning_rate": 3.551900404912642e-05, + "loss": 0.1794, "step": 130520 }, { - "epoch": 0.58, - "learning_rate": 2.096991166315412e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.55178855059171e-05, + "loss": 0.1779, "step": 130530 }, { - "epoch": 0.58, - "learning_rate": 2.0967669611228198e-05, - "loss": 0.1737, + "epoch": 0.29, + "learning_rate": 3.551676696270777e-05, + "loss": 0.1816, "step": 130540 }, { - "epoch": 0.58, - "learning_rate": 2.0965427559302274e-05, - "loss": 0.1782, + "epoch": 0.29, + "learning_rate": 3.551564841949845e-05, + "loss": 0.1852, "step": 130550 }, { - "epoch": 0.58, - "learning_rate": 2.0963185507376352e-05, - "loss": 0.1767, + "epoch": 0.29, + "learning_rate": 3.551452987628912e-05, + "loss": 0.1827, "step": 130560 }, { - "epoch": 0.58, - "learning_rate": 2.096094345545043e-05, - "loss": 0.1772, + "epoch": 0.29, + "learning_rate": 3.55134113330798e-05, + "loss": 0.1799, "step": 130570 }, { - "epoch": 0.58, - "learning_rate": 2.0958701403524506e-05, - "loss": 0.1718, + "epoch": 0.29, + "learning_rate": 3.5512292789870475e-05, + "loss": 0.1838, "step": 130580 }, { - "epoch": 0.58, - "learning_rate": 2.0956459351598585e-05, - "loss": 0.1727, + "epoch": 0.29, + "learning_rate": 3.551117424666115e-05, + "loss": 0.1816, "step": 130590 }, { - "epoch": 0.58, - "learning_rate": 2.0954217299672664e-05, - "loss": 0.1707, + "epoch": 0.29, + "learning_rate": 3.551005570345183e-05, + "loss": 0.1815, "step": 130600 }, { - "epoch": 0.58, - "learning_rate": 2.095197524774674e-05, - "loss": 0.1701, + "epoch": 0.29, + "learning_rate": 3.55089371602425e-05, + "loss": 0.187, "step": 130610 }, { - "epoch": 0.58, - "learning_rate": 2.0949733195820818e-05, - "loss": 0.168, + "epoch": 0.29, + "learning_rate": 3.550781861703318e-05, + "loss": 0.1882, "step": 130620 }, { - "epoch": 0.58, - "learning_rate": 2.0947491143894893e-05, - "loss": 0.175, + "epoch": 0.29, + "learning_rate": 3.550670007382385e-05, + "loss": 0.1825, "step": 130630 }, { - "epoch": 0.58, - "learning_rate": 2.0945249091968972e-05, - "loss": 0.1753, + "epoch": 0.29, + "learning_rate": 3.550558153061453e-05, + "loss": 0.1842, "step": 130640 }, { - "epoch": 0.58, - "learning_rate": 2.0943007040043047e-05, - "loss": 0.1824, + "epoch": 0.29, + "learning_rate": 3.550446298740521e-05, + "loss": 0.183, "step": 130650 }, { - "epoch": 0.58, - "learning_rate": 2.0940764988117126e-05, - "loss": 0.1736, + "epoch": 0.29, + "learning_rate": 3.550334444419588e-05, + "loss": 0.1778, "step": 130660 }, { - "epoch": 0.58, - "learning_rate": 2.0938522936191205e-05, - "loss": 0.1749, + "epoch": 0.29, + "learning_rate": 3.5502225900986556e-05, + "loss": 0.1824, "step": 130670 }, { - "epoch": 0.58, - "learning_rate": 2.093628088426528e-05, - "loss": 0.1724, + "epoch": 0.29, + "learning_rate": 3.550110735777723e-05, + "loss": 0.1801, "step": 130680 }, { - "epoch": 0.58, - "learning_rate": 2.093403883233936e-05, - "loss": 0.1738, + "epoch": 0.29, + "learning_rate": 3.5499988814567905e-05, + "loss": 0.1815, "step": 130690 }, { - "epoch": 0.58, - "learning_rate": 2.0931796780413434e-05, - "loss": 0.1766, + "epoch": 0.29, + "learning_rate": 3.549887027135858e-05, + "loss": 0.1824, "step": 130700 }, { - "epoch": 0.58, - "learning_rate": 2.0929554728487513e-05, - "loss": 0.1718, + "epoch": 0.29, + "learning_rate": 3.549775172814926e-05, + "loss": 0.1899, "step": 130710 }, { - "epoch": 0.58, - "learning_rate": 2.0927312676561588e-05, - "loss": 0.1745, + "epoch": 0.29, + "learning_rate": 3.549663318493994e-05, + "loss": 0.1823, "step": 130720 }, { - "epoch": 0.58, - "learning_rate": 2.0925070624635667e-05, - "loss": 0.1795, + "epoch": 0.29, + "learning_rate": 3.549551464173061e-05, + "loss": 0.1855, "step": 130730 }, { - "epoch": 0.58, - "learning_rate": 2.0922828572709746e-05, - "loss": 0.1689, + "epoch": 0.29, + "learning_rate": 3.549439609852129e-05, + "loss": 0.1829, "step": 130740 }, { - "epoch": 0.58, - "learning_rate": 2.092058652078382e-05, - "loss": 0.1707, + "epoch": 0.29, + "learning_rate": 3.5493277555311966e-05, + "loss": 0.1811, "step": 130750 }, { - "epoch": 0.58, - "learning_rate": 2.09183444688579e-05, - "loss": 0.1713, + "epoch": 0.29, + "learning_rate": 3.549215901210264e-05, + "loss": 0.1811, "step": 130760 }, { - "epoch": 0.58, - "learning_rate": 2.0916102416931975e-05, - "loss": 0.169, + "epoch": 0.29, + "learning_rate": 3.5491040468893315e-05, + "loss": 0.1809, "step": 130770 }, { - "epoch": 0.58, - "learning_rate": 2.0913860365006054e-05, - "loss": 0.1733, + "epoch": 0.29, + "learning_rate": 3.5489921925683986e-05, + "loss": 0.1791, "step": 130780 }, { - "epoch": 0.58, - "learning_rate": 2.0911618313080132e-05, - "loss": 0.1702, + "epoch": 0.29, + "learning_rate": 3.5488803382474664e-05, + "loss": 0.1833, "step": 130790 }, { - "epoch": 0.58, - "learning_rate": 2.0909376261154208e-05, - "loss": 0.175, + "epoch": 0.29, + "learning_rate": 3.548768483926534e-05, + "loss": 0.1797, "step": 130800 }, { - "epoch": 0.58, - "learning_rate": 2.0907134209228286e-05, - "loss": 0.1754, + "epoch": 0.29, + "learning_rate": 3.548656629605602e-05, + "loss": 0.1812, "step": 130810 }, { - "epoch": 0.58, - "learning_rate": 2.0904892157302365e-05, - "loss": 0.1782, + "epoch": 0.29, + "learning_rate": 3.54854477528467e-05, + "loss": 0.1807, "step": 130820 }, { - "epoch": 0.58, - "learning_rate": 2.0902650105376444e-05, - "loss": 0.1781, + "epoch": 0.29, + "learning_rate": 3.548432920963737e-05, + "loss": 0.1865, "step": 130830 }, { - "epoch": 0.58, - "learning_rate": 2.090040805345052e-05, - "loss": 0.1724, + "epoch": 0.29, + "learning_rate": 3.548321066642805e-05, + "loss": 0.1771, "step": 130840 }, { - "epoch": 0.58, - "learning_rate": 2.0898166001524598e-05, - "loss": 0.1682, + "epoch": 0.29, + "learning_rate": 3.5482092123218725e-05, + "loss": 0.1782, "step": 130850 }, { - "epoch": 0.58, - "learning_rate": 2.0895923949598673e-05, - "loss": 0.1746, + "epoch": 0.29, + "learning_rate": 3.5480973580009396e-05, + "loss": 0.1782, "step": 130860 }, { - "epoch": 0.58, - "learning_rate": 2.0893681897672752e-05, - "loss": 0.1722, + "epoch": 0.29, + "learning_rate": 3.5479855036800074e-05, + "loss": 0.1861, "step": 130870 }, { - "epoch": 0.58, - "learning_rate": 2.089143984574683e-05, - "loss": 0.1734, + "epoch": 0.29, + "learning_rate": 3.5478736493590745e-05, + "loss": 0.1852, "step": 130880 }, { - "epoch": 0.58, - "learning_rate": 2.0889197793820906e-05, - "loss": 0.1686, + "epoch": 0.29, + "learning_rate": 3.547761795038142e-05, + "loss": 0.1838, "step": 130890 }, { - "epoch": 0.58, - "learning_rate": 2.0886955741894985e-05, - "loss": 0.1657, + "epoch": 0.29, + "learning_rate": 3.54764994071721e-05, + "loss": 0.1846, "step": 130900 }, { - "epoch": 0.58, - "learning_rate": 2.088471368996906e-05, - "loss": 0.1695, + "epoch": 0.29, + "learning_rate": 3.547538086396278e-05, + "loss": 0.1719, "step": 130910 }, { - "epoch": 0.58, - "learning_rate": 2.088247163804314e-05, - "loss": 0.1723, + "epoch": 0.29, + "learning_rate": 3.547426232075346e-05, + "loss": 0.1836, "step": 130920 }, { - "epoch": 0.58, - "learning_rate": 2.0880229586117214e-05, - "loss": 0.1701, + "epoch": 0.29, + "learning_rate": 3.547314377754413e-05, + "loss": 0.1842, "step": 130930 }, { - "epoch": 0.58, - "learning_rate": 2.0877987534191293e-05, - "loss": 0.1739, + "epoch": 0.29, + "learning_rate": 3.5472025234334806e-05, + "loss": 0.1749, "step": 130940 }, { - "epoch": 0.58, - "learning_rate": 2.087574548226537e-05, - "loss": 0.1724, + "epoch": 0.29, + "learning_rate": 3.547090669112548e-05, + "loss": 0.1801, "step": 130950 }, { - "epoch": 0.58, - "learning_rate": 2.0873503430339447e-05, - "loss": 0.1742, + "epoch": 0.29, + "learning_rate": 3.5469788147916155e-05, + "loss": 0.1825, "step": 130960 }, { - "epoch": 0.58, - "learning_rate": 2.0871261378413526e-05, - "loss": 0.1705, + "epoch": 0.29, + "learning_rate": 3.546866960470683e-05, + "loss": 0.1785, "step": 130970 }, { - "epoch": 0.58, - "learning_rate": 2.08690193264876e-05, - "loss": 0.1733, + "epoch": 0.29, + "learning_rate": 3.5467551061497504e-05, + "loss": 0.1799, "step": 130980 }, { - "epoch": 0.58, - "learning_rate": 2.086677727456168e-05, - "loss": 0.1671, + "epoch": 0.29, + "learning_rate": 3.546643251828818e-05, + "loss": 0.1825, "step": 130990 }, { - "epoch": 0.58, - "learning_rate": 2.0864535222635755e-05, - "loss": 0.1704, + "epoch": 0.29, + "learning_rate": 3.546531397507886e-05, + "loss": 0.1794, "step": 131000 }, { - "epoch": 0.58, - "learning_rate": 2.0862293170709834e-05, - "loss": 0.1702, + "epoch": 0.29, + "learning_rate": 3.546419543186954e-05, + "loss": 0.1851, "step": 131010 }, { - "epoch": 0.58, - "learning_rate": 2.0860051118783912e-05, - "loss": 0.1737, + "epoch": 0.29, + "learning_rate": 3.5463076888660216e-05, + "loss": 0.1865, "step": 131020 }, { - "epoch": 0.58, - "learning_rate": 2.0857809066857988e-05, - "loss": 0.1702, + "epoch": 0.29, + "learning_rate": 3.546195834545089e-05, + "loss": 0.1813, "step": 131030 }, { - "epoch": 0.58, - "learning_rate": 2.0855567014932066e-05, - "loss": 0.1814, + "epoch": 0.29, + "learning_rate": 3.5460839802241565e-05, + "loss": 0.1806, "step": 131040 }, { - "epoch": 0.59, - "learning_rate": 2.0853324963006142e-05, - "loss": 0.1681, + "epoch": 0.29, + "learning_rate": 3.5459721259032236e-05, + "loss": 0.1797, "step": 131050 }, { - "epoch": 0.59, - "learning_rate": 2.085108291108022e-05, - "loss": 0.1683, + "epoch": 0.29, + "learning_rate": 3.5458602715822914e-05, + "loss": 0.1822, "step": 131060 }, { - "epoch": 0.59, - "learning_rate": 2.08488408591543e-05, - "loss": 0.1717, + "epoch": 0.29, + "learning_rate": 3.545748417261359e-05, + "loss": 0.1813, "step": 131070 }, { - "epoch": 0.59, - "learning_rate": 2.0846598807228378e-05, - "loss": 0.166, + "epoch": 0.29, + "learning_rate": 3.545636562940426e-05, + "loss": 0.1836, "step": 131080 }, { - "epoch": 0.59, - "learning_rate": 2.0844356755302453e-05, - "loss": 0.1671, + "epoch": 0.29, + "learning_rate": 3.545524708619494e-05, + "loss": 0.1876, "step": 131090 }, { - "epoch": 0.59, - "learning_rate": 2.0842114703376532e-05, - "loss": 0.1717, + "epoch": 0.29, + "learning_rate": 3.545412854298561e-05, + "loss": 0.182, "step": 131100 }, { - "epoch": 0.59, - "learning_rate": 2.083987265145061e-05, - "loss": 0.1696, + "epoch": 0.29, + "learning_rate": 3.545300999977629e-05, + "loss": 0.1783, "step": 131110 }, { - "epoch": 0.59, - "learning_rate": 2.0837630599524686e-05, - "loss": 0.1664, + "epoch": 0.29, + "learning_rate": 3.545189145656697e-05, + "loss": 0.1766, "step": 131120 }, { - "epoch": 0.59, - "learning_rate": 2.0835388547598765e-05, - "loss": 0.1662, + "epoch": 0.29, + "learning_rate": 3.5450772913357646e-05, + "loss": 0.1845, "step": 131130 }, { - "epoch": 0.59, - "learning_rate": 2.083314649567284e-05, - "loss": 0.1681, + "epoch": 0.29, + "learning_rate": 3.5449654370148324e-05, + "loss": 0.1798, "step": 131140 }, { - "epoch": 0.59, - "learning_rate": 2.083090444374692e-05, - "loss": 0.171, + "epoch": 0.29, + "learning_rate": 3.5448535826938995e-05, + "loss": 0.1828, "step": 131150 }, { - "epoch": 0.59, - "learning_rate": 2.0828662391820997e-05, - "loss": 0.1714, + "epoch": 0.29, + "learning_rate": 3.544741728372967e-05, + "loss": 0.1797, "step": 131160 }, { - "epoch": 0.59, - "learning_rate": 2.0826420339895073e-05, - "loss": 0.167, + "epoch": 0.29, + "learning_rate": 3.544629874052035e-05, + "loss": 0.1816, "step": 131170 }, { - "epoch": 0.59, - "learning_rate": 2.082417828796915e-05, - "loss": 0.1662, + "epoch": 0.29, + "learning_rate": 3.544518019731102e-05, + "loss": 0.1755, "step": 131180 }, { - "epoch": 0.59, - "learning_rate": 2.0821936236043227e-05, - "loss": 0.1646, + "epoch": 0.29, + "learning_rate": 3.54440616541017e-05, + "loss": 0.1795, "step": 131190 }, { - "epoch": 0.59, - "learning_rate": 2.0819694184117306e-05, - "loss": 0.1672, + "epoch": 0.29, + "learning_rate": 3.544294311089237e-05, + "loss": 0.1791, "step": 131200 }, { - "epoch": 0.59, - "learning_rate": 2.081745213219138e-05, - "loss": 0.1703, + "epoch": 0.29, + "learning_rate": 3.544182456768305e-05, + "loss": 0.1811, "step": 131210 }, { - "epoch": 0.59, - "learning_rate": 2.081521008026546e-05, - "loss": 0.1619, + "epoch": 0.29, + "learning_rate": 3.544070602447373e-05, + "loss": 0.1794, "step": 131220 }, { - "epoch": 0.59, - "learning_rate": 2.081296802833954e-05, - "loss": 0.1762, + "epoch": 0.29, + "learning_rate": 3.5439587481264405e-05, + "loss": 0.1797, "step": 131230 }, { - "epoch": 0.59, - "learning_rate": 2.0810725976413614e-05, - "loss": 0.1633, + "epoch": 0.29, + "learning_rate": 3.543846893805508e-05, + "loss": 0.1861, "step": 131240 }, { - "epoch": 0.59, - "learning_rate": 2.0808483924487692e-05, - "loss": 0.1642, - "step": 131250 + "epoch": 0.29, + "learning_rate": 3.5437350394845754e-05, + "loss": 0.1844, + "step": 131250 }, { - "epoch": 0.59, - "learning_rate": 2.0806241872561768e-05, - "loss": 0.1743, + "epoch": 0.29, + "learning_rate": 3.543623185163643e-05, + "loss": 0.1825, "step": 131260 }, { - "epoch": 0.59, - "learning_rate": 2.0803999820635846e-05, - "loss": 0.1682, + "epoch": 0.29, + "learning_rate": 3.54351133084271e-05, + "loss": 0.1809, "step": 131270 }, { - "epoch": 0.59, - "learning_rate": 2.0801757768709922e-05, - "loss": 0.174, + "epoch": 0.29, + "learning_rate": 3.543399476521778e-05, + "loss": 0.1789, "step": 131280 }, { - "epoch": 0.59, - "learning_rate": 2.0799515716784e-05, - "loss": 0.1706, + "epoch": 0.29, + "learning_rate": 3.543287622200846e-05, + "loss": 0.1788, "step": 131290 }, { - "epoch": 0.59, - "learning_rate": 2.079727366485808e-05, - "loss": 0.1692, + "epoch": 0.29, + "learning_rate": 3.543175767879913e-05, + "loss": 0.1772, "step": 131300 }, { - "epoch": 0.59, - "learning_rate": 2.0795031612932155e-05, - "loss": 0.1685, + "epoch": 0.29, + "learning_rate": 3.543063913558981e-05, + "loss": 0.1806, "step": 131310 }, { - "epoch": 0.59, - "learning_rate": 2.0792789561006233e-05, - "loss": 0.1716, + "epoch": 0.29, + "learning_rate": 3.5429520592380486e-05, + "loss": 0.181, "step": 131320 }, { - "epoch": 0.59, - "learning_rate": 2.0790547509080312e-05, - "loss": 0.1682, + "epoch": 0.29, + "learning_rate": 3.5428402049171164e-05, + "loss": 0.1834, "step": 131330 }, { - "epoch": 0.59, - "learning_rate": 2.0788305457154387e-05, - "loss": 0.164, + "epoch": 0.29, + "learning_rate": 3.542728350596184e-05, + "loss": 0.1792, "step": 131340 }, { - "epoch": 0.59, - "learning_rate": 2.0786063405228466e-05, - "loss": 0.1694, + "epoch": 0.29, + "learning_rate": 3.542616496275251e-05, + "loss": 0.1862, "step": 131350 }, { - "epoch": 0.59, - "learning_rate": 2.0783821353302545e-05, - "loss": 0.169, + "epoch": 0.29, + "learning_rate": 3.542504641954319e-05, + "loss": 0.1844, "step": 131360 }, { - "epoch": 0.59, - "learning_rate": 2.0781579301376623e-05, - "loss": 0.1648, + "epoch": 0.29, + "learning_rate": 3.542392787633386e-05, + "loss": 0.1803, "step": 131370 }, { - "epoch": 0.59, - "learning_rate": 2.07793372494507e-05, - "loss": 0.168, + "epoch": 0.29, + "learning_rate": 3.542280933312454e-05, + "loss": 0.1811, "step": 131380 }, { - "epoch": 0.59, - "learning_rate": 2.0777095197524777e-05, - "loss": 0.1698, + "epoch": 0.29, + "learning_rate": 3.542169078991522e-05, + "loss": 0.1763, "step": 131390 }, { - "epoch": 0.59, - "learning_rate": 2.0774853145598853e-05, - "loss": 0.1681, + "epoch": 0.29, + "learning_rate": 3.542057224670589e-05, + "loss": 0.1745, "step": 131400 }, { - "epoch": 0.59, - "learning_rate": 2.077261109367293e-05, - "loss": 0.1712, + "epoch": 0.29, + "learning_rate": 3.541945370349657e-05, + "loss": 0.1807, "step": 131410 }, { - "epoch": 0.59, - "learning_rate": 2.0770369041747007e-05, - "loss": 0.1661, + "epoch": 0.29, + "learning_rate": 3.5418335160287245e-05, + "loss": 0.1828, "step": 131420 }, { - "epoch": 0.59, - "learning_rate": 2.0768126989821086e-05, - "loss": 0.1715, + "epoch": 0.29, + "learning_rate": 3.541721661707792e-05, + "loss": 0.1813, "step": 131430 }, { - "epoch": 0.59, - "learning_rate": 2.0765884937895164e-05, - "loss": 0.1661, + "epoch": 0.29, + "learning_rate": 3.54160980738686e-05, + "loss": 0.182, "step": 131440 }, { - "epoch": 0.59, - "learning_rate": 2.076364288596924e-05, - "loss": 0.1681, + "epoch": 0.29, + "learning_rate": 3.541497953065927e-05, + "loss": 0.1821, "step": 131450 }, { - "epoch": 0.59, - "learning_rate": 2.076140083404332e-05, - "loss": 0.1691, + "epoch": 0.29, + "learning_rate": 3.541386098744995e-05, + "loss": 0.1788, "step": 131460 }, { - "epoch": 0.59, - "learning_rate": 2.0759158782117394e-05, - "loss": 0.1624, + "epoch": 0.29, + "learning_rate": 3.541274244424062e-05, + "loss": 0.1795, "step": 131470 }, { - "epoch": 0.59, - "learning_rate": 2.0756916730191472e-05, - "loss": 0.1666, + "epoch": 0.29, + "learning_rate": 3.54116239010313e-05, + "loss": 0.1811, "step": 131480 }, { - "epoch": 0.59, - "learning_rate": 2.075467467826555e-05, - "loss": 0.1671, + "epoch": 0.29, + "learning_rate": 3.541050535782198e-05, + "loss": 0.1775, "step": 131490 }, { - "epoch": 0.59, - "learning_rate": 2.0752432626339626e-05, - "loss": 0.1683, + "epoch": 0.29, + "learning_rate": 3.540938681461265e-05, + "loss": 0.1827, "step": 131500 }, { - "epoch": 0.59, - "learning_rate": 2.0750190574413705e-05, - "loss": 0.1633, + "epoch": 0.29, + "learning_rate": 3.5408268271403326e-05, + "loss": 0.1826, "step": 131510 }, { - "epoch": 0.59, - "learning_rate": 2.074794852248778e-05, - "loss": 0.1666, + "epoch": 0.29, + "learning_rate": 3.5407149728194e-05, + "loss": 0.1811, "step": 131520 }, { - "epoch": 0.59, - "learning_rate": 2.074570647056186e-05, - "loss": 0.1616, + "epoch": 0.29, + "learning_rate": 3.5406031184984675e-05, + "loss": 0.1781, "step": 131530 }, { - "epoch": 0.59, - "learning_rate": 2.0743464418635935e-05, - "loss": 0.1723, + "epoch": 0.29, + "learning_rate": 3.540491264177535e-05, + "loss": 0.1801, "step": 131540 }, { - "epoch": 0.59, - "learning_rate": 2.0741222366710013e-05, - "loss": 0.176, + "epoch": 0.29, + "learning_rate": 3.540379409856603e-05, + "loss": 0.1801, "step": 131550 }, { - "epoch": 0.59, - "learning_rate": 2.0738980314784092e-05, - "loss": 0.1779, + "epoch": 0.29, + "learning_rate": 3.540267555535671e-05, + "loss": 0.1813, "step": 131560 }, { - "epoch": 0.59, - "learning_rate": 2.0736738262858167e-05, - "loss": 0.1761, + "epoch": 0.29, + "learning_rate": 3.540155701214738e-05, + "loss": 0.1859, "step": 131570 }, { - "epoch": 0.59, - "learning_rate": 2.0734496210932246e-05, - "loss": 0.1787, + "epoch": 0.29, + "learning_rate": 3.540043846893806e-05, + "loss": 0.1834, "step": 131580 }, { - "epoch": 0.59, - "learning_rate": 2.073225415900632e-05, - "loss": 0.1766, + "epoch": 0.29, + "learning_rate": 3.539931992572873e-05, + "loss": 0.182, "step": 131590 }, { - "epoch": 0.59, - "learning_rate": 2.07300121070804e-05, - "loss": 0.1733, + "epoch": 0.29, + "learning_rate": 3.539820138251941e-05, + "loss": 0.178, "step": 131600 }, { - "epoch": 0.59, - "learning_rate": 2.072777005515448e-05, - "loss": 0.1785, + "epoch": 0.29, + "learning_rate": 3.5397082839310085e-05, + "loss": 0.1835, "step": 131610 }, { - "epoch": 0.59, - "learning_rate": 2.0725528003228558e-05, - "loss": 0.1775, + "epoch": 0.29, + "learning_rate": 3.5395964296100756e-05, + "loss": 0.1807, "step": 131620 }, { - "epoch": 0.59, - "learning_rate": 2.0723285951302633e-05, - "loss": 0.1815, + "epoch": 0.29, + "learning_rate": 3.5394845752891434e-05, + "loss": 0.1804, "step": 131630 }, { - "epoch": 0.59, - "learning_rate": 2.072104389937671e-05, - "loss": 0.176, + "epoch": 0.29, + "learning_rate": 3.539372720968211e-05, + "loss": 0.1825, "step": 131640 }, { - "epoch": 0.59, - "learning_rate": 2.071880184745079e-05, - "loss": 0.1792, + "epoch": 0.29, + "learning_rate": 3.539260866647279e-05, + "loss": 0.1756, "step": 131650 }, { - "epoch": 0.59, - "learning_rate": 2.0716559795524866e-05, - "loss": 0.173, + "epoch": 0.29, + "learning_rate": 3.539149012326347e-05, + "loss": 0.1862, "step": 131660 }, { - "epoch": 0.59, - "learning_rate": 2.0714317743598944e-05, - "loss": 0.1763, + "epoch": 0.29, + "learning_rate": 3.539037158005414e-05, + "loss": 0.1789, "step": 131670 }, { - "epoch": 0.59, - "learning_rate": 2.071207569167302e-05, - "loss": 0.1761, + "epoch": 0.29, + "learning_rate": 3.538925303684482e-05, + "loss": 0.1779, "step": 131680 }, { - "epoch": 0.59, - "learning_rate": 2.07098336397471e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.538813449363549e-05, + "loss": 0.1804, "step": 131690 }, { - "epoch": 0.59, - "learning_rate": 2.0707591587821177e-05, - "loss": 0.1913, + "epoch": 0.29, + "learning_rate": 3.5387015950426166e-05, + "loss": 0.1761, "step": 131700 }, { - "epoch": 0.59, - "learning_rate": 2.0705349535895252e-05, - "loss": 0.1834, + "epoch": 0.29, + "learning_rate": 3.5385897407216844e-05, + "loss": 0.1777, "step": 131710 }, { - "epoch": 0.59, - "learning_rate": 2.070310748396933e-05, - "loss": 0.1907, + "epoch": 0.29, + "learning_rate": 3.5384778864007515e-05, + "loss": 0.1777, "step": 131720 }, { - "epoch": 0.59, - "learning_rate": 2.0700865432043406e-05, - "loss": 0.1889, + "epoch": 0.29, + "learning_rate": 3.538366032079819e-05, + "loss": 0.1852, "step": 131730 }, { - "epoch": 0.59, - "learning_rate": 2.0698623380117485e-05, - "loss": 0.1868, + "epoch": 0.29, + "learning_rate": 3.538254177758887e-05, + "loss": 0.1828, "step": 131740 }, { - "epoch": 0.59, - "learning_rate": 2.069638132819156e-05, - "loss": 0.1913, + "epoch": 0.29, + "learning_rate": 3.538142323437955e-05, + "loss": 0.1816, "step": 131750 }, { - "epoch": 0.59, - "learning_rate": 2.069413927626564e-05, - "loss": 0.1865, + "epoch": 0.29, + "learning_rate": 3.5380304691170227e-05, + "loss": 0.1757, "step": 131760 }, { - "epoch": 0.59, - "learning_rate": 2.0691897224339718e-05, - "loss": 0.1835, + "epoch": 0.29, + "learning_rate": 3.53791861479609e-05, + "loss": 0.1787, "step": 131770 }, { - "epoch": 0.59, - "learning_rate": 2.0689655172413793e-05, - "loss": 0.1855, + "epoch": 0.29, + "learning_rate": 3.5378067604751576e-05, + "loss": 0.1841, "step": 131780 }, { - "epoch": 0.59, - "learning_rate": 2.0687413120487872e-05, - "loss": 0.1823, + "epoch": 0.29, + "learning_rate": 3.537694906154225e-05, + "loss": 0.1816, "step": 131790 }, { - "epoch": 0.59, - "learning_rate": 2.0685171068561947e-05, - "loss": 0.1854, + "epoch": 0.29, + "learning_rate": 3.5375830518332925e-05, + "loss": 0.186, "step": 131800 }, { - "epoch": 0.59, - "learning_rate": 2.0682929016636026e-05, - "loss": 0.1864, + "epoch": 0.29, + "learning_rate": 3.53747119751236e-05, + "loss": 0.1779, "step": 131810 }, { - "epoch": 0.59, - "learning_rate": 2.06806869647101e-05, - "loss": 0.1851, + "epoch": 0.29, + "learning_rate": 3.5373593431914274e-05, + "loss": 0.1803, "step": 131820 }, { - "epoch": 0.59, - "learning_rate": 2.067844491278418e-05, - "loss": 0.1817, + "epoch": 0.29, + "learning_rate": 3.537247488870495e-05, + "loss": 0.1797, "step": 131830 }, { - "epoch": 0.59, - "learning_rate": 2.067620286085826e-05, - "loss": 0.1873, + "epoch": 0.29, + "learning_rate": 3.537135634549563e-05, + "loss": 0.1765, "step": 131840 }, { - "epoch": 0.59, - "learning_rate": 2.0673960808932334e-05, - "loss": 0.1879, + "epoch": 0.29, + "learning_rate": 3.537023780228631e-05, + "loss": 0.1765, "step": 131850 }, { - "epoch": 0.59, - "learning_rate": 2.0671718757006413e-05, - "loss": 0.1897, + "epoch": 0.29, + "learning_rate": 3.536911925907698e-05, + "loss": 0.1856, "step": 131860 }, { - "epoch": 0.59, - "learning_rate": 2.066970091027308e-05, - "loss": 0.1871, + "epoch": 0.29, + "learning_rate": 3.536800071586766e-05, + "loss": 0.1757, "step": 131870 }, { - "epoch": 0.59, - "learning_rate": 2.066745885834716e-05, - "loss": 0.1843, + "epoch": 0.29, + "learning_rate": 3.5366882172658335e-05, + "loss": 0.1766, "step": 131880 }, { - "epoch": 0.59, - "learning_rate": 2.0665216806421238e-05, - "loss": 0.1829, + "epoch": 0.29, + "learning_rate": 3.5365763629449006e-05, + "loss": 0.1782, "step": 131890 }, { - "epoch": 0.59, - "learning_rate": 2.0662974754495313e-05, - "loss": 0.1873, + "epoch": 0.29, + "learning_rate": 3.5364645086239684e-05, + "loss": 0.1805, "step": 131900 }, { - "epoch": 0.59, - "learning_rate": 2.0660732702569392e-05, - "loss": 0.1866, + "epoch": 0.29, + "learning_rate": 3.5363526543030355e-05, + "loss": 0.1766, "step": 131910 }, { - "epoch": 0.59, - "learning_rate": 2.065849065064347e-05, - "loss": 0.184, + "epoch": 0.29, + "learning_rate": 3.536240799982103e-05, + "loss": 0.1816, "step": 131920 }, { - "epoch": 0.59, - "learning_rate": 2.065624859871755e-05, - "loss": 0.189, + "epoch": 0.29, + "learning_rate": 3.536128945661171e-05, + "loss": 0.1875, "step": 131930 }, { - "epoch": 0.59, - "learning_rate": 2.0654006546791625e-05, - "loss": 0.1897, + "epoch": 0.29, + "learning_rate": 3.536017091340238e-05, + "loss": 0.1827, "step": 131940 }, { - "epoch": 0.59, - "learning_rate": 2.0651764494865704e-05, - "loss": 0.1815, + "epoch": 0.29, + "learning_rate": 3.535905237019306e-05, + "loss": 0.1804, "step": 131950 }, { - "epoch": 0.59, - "learning_rate": 2.064952244293978e-05, - "loss": 0.1843, + "epoch": 0.29, + "learning_rate": 3.535793382698374e-05, + "loss": 0.178, "step": 131960 }, { - "epoch": 0.59, - "learning_rate": 2.0647280391013858e-05, - "loss": 0.182, + "epoch": 0.29, + "learning_rate": 3.5356815283774416e-05, + "loss": 0.1812, "step": 131970 }, { - "epoch": 0.59, - "learning_rate": 2.0645038339087936e-05, - "loss": 0.182, + "epoch": 0.29, + "learning_rate": 3.5355696740565094e-05, + "loss": 0.1843, "step": 131980 }, { - "epoch": 0.59, - "learning_rate": 2.0642796287162012e-05, - "loss": 0.1843, + "epoch": 0.29, + "learning_rate": 3.5354578197355765e-05, + "loss": 0.1852, "step": 131990 }, { - "epoch": 0.59, - "learning_rate": 2.064055423523609e-05, - "loss": 0.1896, + "epoch": 0.29, + "learning_rate": 3.535345965414644e-05, + "loss": 0.1726, "step": 132000 }, { - "epoch": 0.59, - "learning_rate": 2.0638312183310166e-05, - "loss": 0.1804, + "epoch": 0.29, + "learning_rate": 3.5352341110937114e-05, + "loss": 0.1789, "step": 132010 }, { - "epoch": 0.59, - "learning_rate": 2.0636070131384244e-05, - "loss": 0.1839, + "epoch": 0.29, + "learning_rate": 3.535122256772779e-05, + "loss": 0.1768, "step": 132020 }, { - "epoch": 0.59, - "learning_rate": 2.063382807945832e-05, - "loss": 0.1837, + "epoch": 0.29, + "learning_rate": 3.535010402451847e-05, + "loss": 0.1782, "step": 132030 }, { - "epoch": 0.59, - "learning_rate": 2.06315860275324e-05, - "loss": 0.1834, + "epoch": 0.29, + "learning_rate": 3.534898548130914e-05, + "loss": 0.1801, "step": 132040 }, { - "epoch": 0.59, - "learning_rate": 2.0629343975606477e-05, - "loss": 0.1756, + "epoch": 0.29, + "learning_rate": 3.534786693809982e-05, + "loss": 0.1778, "step": 132050 }, { - "epoch": 0.59, - "learning_rate": 2.0627101923680553e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.53467483948905e-05, + "loss": 0.1785, "step": 132060 }, { - "epoch": 0.59, - "learning_rate": 2.062485987175463e-05, - "loss": 0.1818, + "epoch": 0.29, + "learning_rate": 3.5345629851681175e-05, + "loss": 0.1815, "step": 132070 }, { - "epoch": 0.59, - "learning_rate": 2.0622617819828707e-05, - "loss": 0.1764, + "epoch": 0.29, + "learning_rate": 3.534451130847185e-05, + "loss": 0.1778, "step": 132080 }, { - "epoch": 0.59, - "learning_rate": 2.0620375767902785e-05, - "loss": 0.1838, + "epoch": 0.29, + "learning_rate": 3.5343392765262524e-05, + "loss": 0.1777, "step": 132090 }, { - "epoch": 0.59, - "learning_rate": 2.061813371597686e-05, - "loss": 0.1777, + "epoch": 0.29, + "learning_rate": 3.53422742220532e-05, + "loss": 0.1801, "step": 132100 }, { - "epoch": 0.59, - "learning_rate": 2.061589166405094e-05, - "loss": 0.1836, + "epoch": 0.29, + "learning_rate": 3.534115567884387e-05, + "loss": 0.1816, "step": 132110 }, { - "epoch": 0.59, - "learning_rate": 2.0613649612125018e-05, - "loss": 0.181, + "epoch": 0.29, + "learning_rate": 3.534003713563455e-05, + "loss": 0.1766, "step": 132120 }, { - "epoch": 0.59, - "learning_rate": 2.0611407560199093e-05, - "loss": 0.1803, + "epoch": 0.29, + "learning_rate": 3.533891859242523e-05, + "loss": 0.1782, "step": 132130 }, { - "epoch": 0.59, - "learning_rate": 2.0609165508273172e-05, - "loss": 0.181, + "epoch": 0.29, + "learning_rate": 3.53378000492159e-05, + "loss": 0.1761, "step": 132140 }, { - "epoch": 0.59, - "learning_rate": 2.0606923456347247e-05, - "loss": 0.1811, + "epoch": 0.29, + "learning_rate": 3.533668150600658e-05, + "loss": 0.171, "step": 132150 }, { - "epoch": 0.59, - "learning_rate": 2.0604681404421326e-05, - "loss": 0.1796, + "epoch": 0.29, + "learning_rate": 3.5335562962797256e-05, + "loss": 0.175, "step": 132160 }, { - "epoch": 0.59, - "learning_rate": 2.0602439352495405e-05, - "loss": 0.1831, + "epoch": 0.3, + "learning_rate": 3.5334444419587934e-05, + "loss": 0.1797, "step": 132170 }, { - "epoch": 0.59, - "learning_rate": 2.0600197300569484e-05, - "loss": 0.1854, + "epoch": 0.3, + "learning_rate": 3.5333325876378605e-05, + "loss": 0.1786, "step": 132180 }, { - "epoch": 0.59, - "learning_rate": 2.059795524864356e-05, - "loss": 0.1798, + "epoch": 0.3, + "learning_rate": 3.533220733316928e-05, + "loss": 0.1802, "step": 132190 }, { - "epoch": 0.59, - "learning_rate": 2.0595713196717638e-05, - "loss": 0.18, + "epoch": 0.3, + "learning_rate": 3.533108878995996e-05, + "loss": 0.1795, "step": 132200 }, { - "epoch": 0.59, - "learning_rate": 2.0593471144791716e-05, - "loss": 0.1817, + "epoch": 0.3, + "learning_rate": 3.532997024675063e-05, + "loss": 0.1759, "step": 132210 }, { - "epoch": 0.59, - "learning_rate": 2.0591229092865792e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.532885170354131e-05, + "loss": 0.1777, "step": 132220 }, { - "epoch": 0.59, - "learning_rate": 2.058898704093987e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.532773316033198e-05, + "loss": 0.1702, "step": 132230 }, { - "epoch": 0.59, - "learning_rate": 2.0586744989013946e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.532661461712266e-05, + "loss": 0.1756, "step": 132240 }, { - "epoch": 0.59, - "learning_rate": 2.0584502937088024e-05, - "loss": 0.1847, + "epoch": 0.3, + "learning_rate": 3.532549607391334e-05, + "loss": 0.1757, "step": 132250 }, { - "epoch": 0.59, - "learning_rate": 2.0582260885162103e-05, - "loss": 0.1817, + "epoch": 0.3, + "learning_rate": 3.5324377530704015e-05, + "loss": 0.1799, "step": 132260 }, { - "epoch": 0.59, - "learning_rate": 2.058001883323618e-05, - "loss": 0.1824, + "epoch": 0.3, + "learning_rate": 3.532325898749469e-05, + "loss": 0.1736, "step": 132270 }, { - "epoch": 0.59, - "learning_rate": 2.0577776781310257e-05, - "loss": 0.179, + "epoch": 0.3, + "learning_rate": 3.5322140444285364e-05, + "loss": 0.1801, "step": 132280 }, { - "epoch": 0.59, - "learning_rate": 2.0575534729384333e-05, - "loss": 0.1719, + "epoch": 0.3, + "learning_rate": 3.532102190107604e-05, + "loss": 0.181, "step": 132290 }, { - "epoch": 0.59, - "learning_rate": 2.057329267745841e-05, - "loss": 0.1794, + "epoch": 0.3, + "learning_rate": 3.531990335786672e-05, + "loss": 0.1784, "step": 132300 }, { - "epoch": 0.59, - "learning_rate": 2.0571050625532487e-05, - "loss": 0.1867, + "epoch": 0.3, + "learning_rate": 3.531878481465739e-05, + "loss": 0.1759, "step": 132310 }, { - "epoch": 0.59, - "learning_rate": 2.0568808573606565e-05, - "loss": 0.1805, + "epoch": 0.3, + "learning_rate": 3.531766627144807e-05, + "loss": 0.1804, "step": 132320 }, { - "epoch": 0.59, - "learning_rate": 2.0566566521680644e-05, - "loss": 0.1817, + "epoch": 0.3, + "learning_rate": 3.531654772823874e-05, + "loss": 0.1771, "step": 132330 }, { - "epoch": 0.59, - "learning_rate": 2.056432446975472e-05, - "loss": 0.1808, + "epoch": 0.3, + "learning_rate": 3.531542918502942e-05, + "loss": 0.1763, "step": 132340 }, { - "epoch": 0.59, - "learning_rate": 2.0562082417828798e-05, - "loss": 0.1817, + "epoch": 0.3, + "learning_rate": 3.5314310641820096e-05, + "loss": 0.1723, "step": 132350 }, { - "epoch": 0.59, - "learning_rate": 2.0559840365902873e-05, - "loss": 0.1763, + "epoch": 0.3, + "learning_rate": 3.531319209861077e-05, + "loss": 0.1797, "step": 132360 }, { - "epoch": 0.59, - "learning_rate": 2.0557598313976952e-05, - "loss": 0.1859, + "epoch": 0.3, + "learning_rate": 3.531207355540145e-05, + "loss": 0.1704, "step": 132370 }, { - "epoch": 0.59, - "learning_rate": 2.0555356262051027e-05, - "loss": 0.1805, + "epoch": 0.3, + "learning_rate": 3.531095501219212e-05, + "loss": 0.1801, "step": 132380 }, { - "epoch": 0.59, - "learning_rate": 2.0553114210125106e-05, - "loss": 0.1784, + "epoch": 0.3, + "learning_rate": 3.530994832330373e-05, + "loss": 0.1753, "step": 132390 }, { - "epoch": 0.59, - "learning_rate": 2.0550872158199185e-05, - "loss": 0.1773, + "epoch": 0.3, + "learning_rate": 3.53088297800944e-05, + "loss": 0.174, "step": 132400 }, { - "epoch": 0.59, - "learning_rate": 2.054863010627326e-05, - "loss": 0.1831, + "epoch": 0.3, + "learning_rate": 3.530771123688508e-05, + "loss": 0.1786, "step": 132410 }, { - "epoch": 0.59, - "learning_rate": 2.054638805434734e-05, - "loss": 0.1852, + "epoch": 0.3, + "learning_rate": 3.530659269367576e-05, + "loss": 0.1793, "step": 132420 }, { - "epoch": 0.59, - "learning_rate": 2.0544146002421418e-05, - "loss": 0.1728, + "epoch": 0.3, + "learning_rate": 3.5305474150466436e-05, + "loss": 0.1764, "step": 132430 }, { - "epoch": 0.59, - "learning_rate": 2.0541903950495493e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.5304355607257114e-05, + "loss": 0.1732, "step": 132440 }, { - "epoch": 0.59, - "learning_rate": 2.0539661898569572e-05, - "loss": 0.1819, + "epoch": 0.3, + "learning_rate": 3.5303237064047785e-05, + "loss": 0.1751, "step": 132450 }, { - "epoch": 0.59, - "learning_rate": 2.053741984664365e-05, - "loss": 0.1799, + "epoch": 0.3, + "learning_rate": 3.530211852083846e-05, + "loss": 0.18, "step": 132460 }, { - "epoch": 0.59, - "learning_rate": 2.053517779471773e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.530099997762914e-05, + "loss": 0.174, "step": 132470 }, { - "epoch": 0.59, - "learning_rate": 2.0532935742791805e-05, - "loss": 0.1788, + "epoch": 0.3, + "learning_rate": 3.529988143441981e-05, + "loss": 0.172, "step": 132480 }, { - "epoch": 0.59, - "learning_rate": 2.0530693690865883e-05, - "loss": 0.183, + "epoch": 0.3, + "learning_rate": 3.529876289121049e-05, + "loss": 0.1775, "step": 132490 }, { - "epoch": 0.59, - "learning_rate": 2.052845163893996e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.529764434800116e-05, + "loss": 0.1736, "step": 132500 }, { - "epoch": 0.59, - "learning_rate": 2.0526209587014037e-05, - "loss": 0.1816, + "epoch": 0.3, + "learning_rate": 3.529652580479184e-05, + "loss": 0.1729, "step": 132510 }, { - "epoch": 0.59, - "learning_rate": 2.0523967535088116e-05, - "loss": 0.1863, + "epoch": 0.3, + "learning_rate": 3.529540726158252e-05, + "loss": 0.1818, "step": 132520 }, { - "epoch": 0.59, - "learning_rate": 2.052172548316219e-05, + "epoch": 0.3, + "learning_rate": 3.529428871837319e-05, "loss": 0.1757, "step": 132530 }, { - "epoch": 0.59, - "learning_rate": 2.051948343123627e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.529317017516387e-05, + "loss": 0.1796, "step": 132540 }, { - "epoch": 0.59, - "learning_rate": 2.0517241379310345e-05, - "loss": 0.1764, + "epoch": 0.3, + "learning_rate": 3.5292051631954544e-05, + "loss": 0.1758, "step": 132550 }, { - "epoch": 0.59, - "learning_rate": 2.0514999327384424e-05, - "loss": 0.1801, + "epoch": 0.3, + "learning_rate": 3.529093308874522e-05, + "loss": 0.1761, "step": 132560 }, { - "epoch": 0.59, - "learning_rate": 2.05127572754585e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.5289814545535893e-05, + "loss": 0.1755, "step": 132570 }, { - "epoch": 0.59, - "learning_rate": 2.0510515223532578e-05, - "loss": 0.1777, + "epoch": 0.3, + "learning_rate": 3.528869600232657e-05, + "loss": 0.1747, "step": 132580 }, { - "epoch": 0.59, - "learning_rate": 2.0508273171606657e-05, - "loss": 0.1774, + "epoch": 0.3, + "learning_rate": 3.528757745911725e-05, + "loss": 0.1785, "step": 132590 }, { - "epoch": 0.59, - "learning_rate": 2.0506031119680732e-05, - "loss": 0.178, + "epoch": 0.3, + "learning_rate": 3.528645891590792e-05, + "loss": 0.1786, "step": 132600 }, { - "epoch": 0.59, - "learning_rate": 2.050378906775481e-05, - "loss": 0.1831, + "epoch": 0.3, + "learning_rate": 3.52853403726986e-05, + "loss": 0.1784, "step": 132610 }, { - "epoch": 0.59, - "learning_rate": 2.0501547015828886e-05, - "loss": 0.1792, + "epoch": 0.3, + "learning_rate": 3.528422182948927e-05, + "loss": 0.1769, "step": 132620 }, { - "epoch": 0.59, - "learning_rate": 2.0499304963902965e-05, - "loss": 0.1786, + "epoch": 0.3, + "learning_rate": 3.528310328627995e-05, + "loss": 0.1747, "step": 132630 }, { - "epoch": 0.59, - "learning_rate": 2.049706291197704e-05, - "loss": 0.1786, + "epoch": 0.3, + "learning_rate": 3.5281984743070625e-05, + "loss": 0.1764, "step": 132640 }, { - "epoch": 0.59, - "learning_rate": 2.049482086005112e-05, - "loss": 0.1771, + "epoch": 0.3, + "learning_rate": 3.52808661998613e-05, + "loss": 0.1737, "step": 132650 }, { - "epoch": 0.59, - "learning_rate": 2.0492578808125198e-05, - "loss": 0.1831, + "epoch": 0.3, + "learning_rate": 3.527974765665198e-05, + "loss": 0.1701, "step": 132660 }, { - "epoch": 0.59, - "learning_rate": 2.0490336756199273e-05, - "loss": 0.1763, + "epoch": 0.3, + "learning_rate": 3.527862911344265e-05, + "loss": 0.1832, "step": 132670 }, { - "epoch": 0.59, - "learning_rate": 2.0488094704273352e-05, - "loss": 0.1789, + "epoch": 0.3, + "learning_rate": 3.527751057023333e-05, + "loss": 0.1813, "step": 132680 }, { - "epoch": 0.59, - "learning_rate": 2.0485852652347427e-05, - "loss": 0.1795, + "epoch": 0.3, + "learning_rate": 3.527639202702401e-05, + "loss": 0.1748, "step": 132690 }, { - "epoch": 0.59, - "learning_rate": 2.0483610600421506e-05, - "loss": 0.1821, + "epoch": 0.3, + "learning_rate": 3.527527348381468e-05, + "loss": 0.1777, "step": 132700 }, { - "epoch": 0.59, - "learning_rate": 2.0481368548495585e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.527415494060536e-05, + "loss": 0.1823, "step": 132710 }, { - "epoch": 0.59, - "learning_rate": 2.0479126496569663e-05, - "loss": 0.1774, + "epoch": 0.3, + "learning_rate": 3.527303639739603e-05, + "loss": 0.1768, "step": 132720 }, { - "epoch": 0.59, - "learning_rate": 2.047688444464374e-05, - "loss": 0.1796, + "epoch": 0.3, + "learning_rate": 3.5271917854186706e-05, + "loss": 0.1786, "step": 132730 }, { - "epoch": 0.59, - "learning_rate": 2.0474642392717817e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.5270799310977384e-05, + "loss": 0.1737, "step": 132740 }, { - "epoch": 0.59, - "learning_rate": 2.0472400340791896e-05, - "loss": 0.1769, + "epoch": 0.3, + "learning_rate": 3.526968076776806e-05, + "loss": 0.1763, "step": 132750 }, { - "epoch": 0.59, - "learning_rate": 2.047015828886597e-05, - "loss": 0.1798, + "epoch": 0.3, + "learning_rate": 3.526856222455874e-05, + "loss": 0.176, "step": 132760 }, { - "epoch": 0.59, - "learning_rate": 2.046791623694005e-05, - "loss": 0.1784, + "epoch": 0.3, + "learning_rate": 3.526744368134941e-05, + "loss": 0.1719, "step": 132770 }, { - "epoch": 0.59, - "learning_rate": 2.0465674185014125e-05, - "loss": 0.1841, + "epoch": 0.3, + "learning_rate": 3.526632513814009e-05, + "loss": 0.1715, "step": 132780 }, { - "epoch": 0.59, - "learning_rate": 2.0463432133088204e-05, - "loss": 0.1756, + "epoch": 0.3, + "learning_rate": 3.526520659493077e-05, + "loss": 0.1758, "step": 132790 }, { - "epoch": 0.59, - "learning_rate": 2.0461190081162283e-05, - "loss": 0.1823, + "epoch": 0.3, + "learning_rate": 3.526408805172144e-05, + "loss": 0.1746, "step": 132800 }, { - "epoch": 0.59, - "learning_rate": 2.0458948029236358e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.5262969508512116e-05, + "loss": 0.1722, "step": 132810 }, { - "epoch": 0.59, - "learning_rate": 2.0456705977310437e-05, - "loss": 0.1758, + "epoch": 0.3, + "learning_rate": 3.526185096530279e-05, + "loss": 0.1777, "step": 132820 }, { - "epoch": 0.59, - "learning_rate": 2.0454463925384512e-05, - "loss": 0.1735, + "epoch": 0.3, + "learning_rate": 3.5260732422093465e-05, + "loss": 0.1777, "step": 132830 }, { - "epoch": 0.59, - "learning_rate": 2.045222187345859e-05, - "loss": 0.1713, + "epoch": 0.3, + "learning_rate": 3.525961387888414e-05, + "loss": 0.1776, "step": 132840 }, { - "epoch": 0.59, - "learning_rate": 2.0449979821532666e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.525849533567482e-05, + "loss": 0.1794, "step": 132850 }, { - "epoch": 0.59, - "learning_rate": 2.0447737769606745e-05, - "loss": 0.1776, + "epoch": 0.3, + "learning_rate": 3.52573767924655e-05, + "loss": 0.1716, "step": 132860 }, { - "epoch": 0.59, - "learning_rate": 2.0445495717680824e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.525625824925617e-05, + "loss": 0.1763, "step": 132870 }, { - "epoch": 0.59, - "learning_rate": 2.04432536657549e-05, - "loss": 0.1734, + "epoch": 0.3, + "learning_rate": 3.525513970604685e-05, + "loss": 0.1718, "step": 132880 }, { - "epoch": 0.59, - "learning_rate": 2.0441011613828978e-05, - "loss": 0.1765, + "epoch": 0.3, + "learning_rate": 3.525402116283752e-05, + "loss": 0.1806, "step": 132890 }, { - "epoch": 0.59, - "learning_rate": 2.0438769561903053e-05, - "loss": 0.1795, + "epoch": 0.3, + "learning_rate": 3.52529026196282e-05, + "loss": 0.1705, "step": 132900 }, { - "epoch": 0.59, - "learning_rate": 2.0436527509977132e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.5251784076418875e-05, + "loss": 0.1752, "step": 132910 }, { - "epoch": 0.59, - "learning_rate": 2.0434285458051207e-05, - "loss": 0.1816, + "epoch": 0.3, + "learning_rate": 3.5250665533209546e-05, + "loss": 0.1741, "step": 132920 }, { - "epoch": 0.59, - "learning_rate": 2.0432043406125286e-05, - "loss": 0.18, + "epoch": 0.3, + "learning_rate": 3.5249546990000224e-05, + "loss": 0.1729, "step": 132930 }, { - "epoch": 0.59, - "learning_rate": 2.0429801354199365e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.5248428446790895e-05, + "loss": 0.1749, "step": 132940 }, { - "epoch": 0.59, - "learning_rate": 2.042755930227344e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.524730990358158e-05, + "loss": 0.1757, "step": 132950 }, { - "epoch": 0.59, - "learning_rate": 2.042531725034752e-05, - "loss": 0.1814, + "epoch": 0.3, + "learning_rate": 3.524619136037226e-05, + "loss": 0.1758, "step": 132960 }, { - "epoch": 0.59, - "learning_rate": 2.0423075198421597e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.524507281716293e-05, + "loss": 0.173, "step": 132970 }, { - "epoch": 0.59, - "learning_rate": 2.0420833146495673e-05, - "loss": 0.1772, + "epoch": 0.3, + "learning_rate": 3.524395427395361e-05, + "loss": 0.1805, "step": 132980 }, { - "epoch": 0.59, - "learning_rate": 2.041859109456975e-05, - "loss": 0.1732, + "epoch": 0.3, + "learning_rate": 3.524283573074428e-05, + "loss": 0.1711, "step": 132990 }, { - "epoch": 0.59, - "learning_rate": 2.041634904264383e-05, - "loss": 0.1744, + "epoch": 0.3, + "learning_rate": 3.5241717187534956e-05, + "loss": 0.1737, "step": 133000 }, { - "epoch": 0.59, - "learning_rate": 2.041410699071791e-05, - "loss": 0.1795, + "epoch": 0.3, + "learning_rate": 3.5240598644325634e-05, + "loss": 0.1694, "step": 133010 }, { - "epoch": 0.59, - "learning_rate": 2.0411864938791984e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.5239480101116305e-05, + "loss": 0.1743, "step": 133020 }, { - "epoch": 0.59, - "learning_rate": 2.0409622886866063e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.523836155790698e-05, + "loss": 0.1743, "step": 133030 }, { - "epoch": 0.59, - "learning_rate": 2.0407380834940138e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.5237243014697654e-05, + "loss": 0.1784, "step": 133040 }, { - "epoch": 0.59, - "learning_rate": 2.0405138783014217e-05, - "loss": 0.186, + "epoch": 0.3, + "learning_rate": 3.523612447148833e-05, + "loss": 0.1735, "step": 133050 }, { - "epoch": 0.59, - "learning_rate": 2.0402896731088292e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.523500592827901e-05, + "loss": 0.1708, "step": 133060 }, { - "epoch": 0.59, - "learning_rate": 2.040065467916237e-05, - "loss": 0.1809, + "epoch": 0.3, + "learning_rate": 3.523388738506969e-05, + "loss": 0.1789, "step": 133070 }, { - "epoch": 0.59, - "learning_rate": 2.039841262723645e-05, - "loss": 0.1779, + "epoch": 0.3, + "learning_rate": 3.5232768841860366e-05, + "loss": 0.177, "step": 133080 }, { - "epoch": 0.59, - "learning_rate": 2.0396170575310525e-05, - "loss": 0.1789, + "epoch": 0.3, + "learning_rate": 3.523165029865104e-05, + "loss": 0.1772, "step": 133090 }, { - "epoch": 0.59, - "learning_rate": 2.0393928523384604e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.5230531755441715e-05, + "loss": 0.1748, "step": 133100 }, { - "epoch": 0.59, - "learning_rate": 2.039168647145868e-05, - "loss": 0.179, + "epoch": 0.3, + "learning_rate": 3.522941321223239e-05, + "loss": 0.1713, "step": 133110 }, { - "epoch": 0.59, - "learning_rate": 2.0389444419532758e-05, - "loss": 0.1775, + "epoch": 0.3, + "learning_rate": 3.5228294669023064e-05, + "loss": 0.1759, "step": 133120 }, { - "epoch": 0.59, - "learning_rate": 2.0387202367606833e-05, - "loss": 0.1794, + "epoch": 0.3, + "learning_rate": 3.522717612581374e-05, + "loss": 0.1754, "step": 133130 }, { - "epoch": 0.59, - "learning_rate": 2.0384960315680912e-05, - "loss": 0.1803, + "epoch": 0.3, + "learning_rate": 3.522605758260441e-05, + "loss": 0.1781, "step": 133140 }, { - "epoch": 0.59, - "learning_rate": 2.038271826375499e-05, - "loss": 0.1781, + "epoch": 0.3, + "learning_rate": 3.522493903939509e-05, + "loss": 0.1716, "step": 133150 }, { - "epoch": 0.59, - "learning_rate": 2.0380476211829066e-05, - "loss": 0.1817, + "epoch": 0.3, + "learning_rate": 3.522382049618577e-05, + "loss": 0.1753, "step": 133160 }, { - "epoch": 0.59, - "learning_rate": 2.0378234159903145e-05, - "loss": 0.1736, + "epoch": 0.3, + "learning_rate": 3.522270195297645e-05, + "loss": 0.1757, "step": 133170 }, { - "epoch": 0.59, - "learning_rate": 2.037599210797722e-05, - "loss": 0.1756, + "epoch": 0.3, + "learning_rate": 3.5221583409767125e-05, + "loss": 0.1749, "step": 133180 }, { - "epoch": 0.59, - "learning_rate": 2.03737500560513e-05, - "loss": 0.1846, + "epoch": 0.3, + "learning_rate": 3.5220464866557796e-05, + "loss": 0.1709, "step": 133190 }, { - "epoch": 0.59, - "learning_rate": 2.0371508004125374e-05, - "loss": 0.1806, + "epoch": 0.3, + "learning_rate": 3.5219346323348474e-05, + "loss": 0.1738, "step": 133200 }, { - "epoch": 0.59, - "learning_rate": 2.0369265952199453e-05, - "loss": 0.1794, + "epoch": 0.3, + "learning_rate": 3.5218227780139145e-05, + "loss": 0.1729, "step": 133210 }, { - "epoch": 0.59, - "learning_rate": 2.036702390027353e-05, - "loss": 0.1791, + "epoch": 0.3, + "learning_rate": 3.521710923692982e-05, + "loss": 0.1743, "step": 133220 }, { - "epoch": 0.59, - "learning_rate": 2.0364781848347607e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.52159906937205e-05, + "loss": 0.1747, "step": 133230 }, { - "epoch": 0.59, - "learning_rate": 2.0362539796421685e-05, - "loss": 0.1756, + "epoch": 0.3, + "learning_rate": 3.521487215051117e-05, + "loss": 0.1719, "step": 133240 }, { - "epoch": 0.59, - "learning_rate": 2.0360297744495764e-05, - "loss": 0.1821, + "epoch": 0.3, + "learning_rate": 3.521375360730185e-05, + "loss": 0.1716, "step": 133250 }, { - "epoch": 0.59, - "learning_rate": 2.0358055692569843e-05, - "loss": 0.1786, + "epoch": 0.3, + "learning_rate": 3.521263506409253e-05, + "loss": 0.174, "step": 133260 }, { - "epoch": 0.59, - "learning_rate": 2.0355813640643918e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.5211516520883206e-05, + "loss": 0.1752, "step": 133270 }, { - "epoch": 0.59, - "learning_rate": 2.0353571588717997e-05, - "loss": 0.1787, + "epoch": 0.3, + "learning_rate": 3.5210397977673884e-05, + "loss": 0.1694, "step": 133280 }, { - "epoch": 0.6, - "learning_rate": 2.0351329536792076e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.5209279434464555e-05, + "loss": 0.1766, "step": 133290 }, { - "epoch": 0.6, - "learning_rate": 2.034908748486615e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.520816089125523e-05, + "loss": 0.1734, "step": 133300 }, { - "epoch": 0.6, - "learning_rate": 2.034684543294023e-05, - "loss": 0.1782, + "epoch": 0.3, + "learning_rate": 3.5207042348045904e-05, + "loss": 0.1748, "step": 133310 }, { - "epoch": 0.6, - "learning_rate": 2.0344603381014305e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.520592380483658e-05, + "loss": 0.1704, "step": 133320 }, { - "epoch": 0.6, - "learning_rate": 2.0342361329088384e-05, - "loss": 0.1744, + "epoch": 0.3, + "learning_rate": 3.520480526162726e-05, + "loss": 0.1757, "step": 133330 }, { - "epoch": 0.6, - "learning_rate": 2.034011927716246e-05, - "loss": 0.1692, + "epoch": 0.3, + "learning_rate": 3.520368671841793e-05, + "loss": 0.1729, "step": 133340 }, { - "epoch": 0.6, - "learning_rate": 2.0337877225236538e-05, - "loss": 0.1804, + "epoch": 0.3, + "learning_rate": 3.520256817520861e-05, + "loss": 0.1727, "step": 133350 }, { - "epoch": 0.6, - "learning_rate": 2.0335635173310616e-05, - "loss": 0.1715, + "epoch": 0.3, + "learning_rate": 3.520144963199929e-05, + "loss": 0.1645, "step": 133360 }, { - "epoch": 0.6, - "learning_rate": 2.0333393121384692e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.5200331088789965e-05, + "loss": 0.1713, "step": 133370 }, { - "epoch": 0.6, - "learning_rate": 2.033115106945877e-05, - "loss": 0.18, + "epoch": 0.3, + "learning_rate": 3.519921254558064e-05, + "loss": 0.1699, "step": 133380 }, { - "epoch": 0.6, - "learning_rate": 2.0328909017532846e-05, - "loss": 0.175, + "epoch": 0.3, + "learning_rate": 3.5198094002371314e-05, + "loss": 0.179, "step": 133390 }, { - "epoch": 0.6, - "learning_rate": 2.0326666965606925e-05, - "loss": 0.1775, + "epoch": 0.3, + "learning_rate": 3.519697545916199e-05, + "loss": 0.1736, "step": 133400 }, { - "epoch": 0.6, - "learning_rate": 2.0324424913681e-05, - "loss": 0.1797, + "epoch": 0.3, + "learning_rate": 3.519585691595266e-05, + "loss": 0.1751, "step": 133410 }, { - "epoch": 0.6, - "learning_rate": 2.032218286175508e-05, - "loss": 0.1756, + "epoch": 0.3, + "learning_rate": 3.519473837274334e-05, + "loss": 0.1795, "step": 133420 }, { - "epoch": 0.6, - "learning_rate": 2.0319940809829157e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.519361982953402e-05, + "loss": 0.1699, "step": 133430 }, { - "epoch": 0.6, - "learning_rate": 2.0317698757903233e-05, - "loss": 0.1793, + "epoch": 0.3, + "learning_rate": 3.519250128632469e-05, + "loss": 0.1788, "step": 133440 }, { - "epoch": 0.6, - "learning_rate": 2.031545670597731e-05, - "loss": 0.1694, + "epoch": 0.3, + "learning_rate": 3.519138274311537e-05, + "loss": 0.1739, "step": 133450 }, { - "epoch": 0.6, - "learning_rate": 2.0313214654051387e-05, - "loss": 0.1725, + "epoch": 0.3, + "learning_rate": 3.519026419990604e-05, + "loss": 0.175, "step": 133460 }, { - "epoch": 0.6, - "learning_rate": 2.0310972602125465e-05, - "loss": 0.1734, + "epoch": 0.3, + "learning_rate": 3.518914565669672e-05, + "loss": 0.1698, "step": 133470 }, { - "epoch": 0.6, - "learning_rate": 2.030873055019954e-05, - "loss": 0.1779, + "epoch": 0.3, + "learning_rate": 3.5188027113487395e-05, + "loss": 0.182, "step": 133480 }, { - "epoch": 0.6, - "learning_rate": 2.030648849827362e-05, - "loss": 0.1837, + "epoch": 0.3, + "learning_rate": 3.518690857027807e-05, + "loss": 0.1733, "step": 133490 }, { - "epoch": 0.6, - "learning_rate": 2.0304246446347698e-05, - "loss": 0.1709, + "epoch": 0.3, + "learning_rate": 3.518579002706875e-05, + "loss": 0.1786, "step": 133500 }, { - "epoch": 0.6, - "learning_rate": 2.0302004394421777e-05, - "loss": 0.1718, + "epoch": 0.3, + "learning_rate": 3.518467148385942e-05, + "loss": 0.1738, "step": 133510 }, { - "epoch": 0.6, - "learning_rate": 2.0299762342495852e-05, - "loss": 0.1722, + "epoch": 0.3, + "learning_rate": 3.51835529406501e-05, + "loss": 0.1804, "step": 133520 }, { - "epoch": 0.6, - "learning_rate": 2.029752029056993e-05, - "loss": 0.1732, + "epoch": 0.3, + "learning_rate": 3.518243439744077e-05, + "loss": 0.1755, "step": 133530 }, { - "epoch": 0.6, - "learning_rate": 2.029527823864401e-05, - "loss": 0.1719, + "epoch": 0.3, + "learning_rate": 3.518131585423145e-05, + "loss": 0.1751, "step": 133540 }, { - "epoch": 0.6, - "learning_rate": 2.0293036186718085e-05, - "loss": 0.178, + "epoch": 0.3, + "learning_rate": 3.518019731102213e-05, + "loss": 0.1711, "step": 133550 }, { - "epoch": 0.6, - "learning_rate": 2.0290794134792164e-05, - "loss": 0.1711, + "epoch": 0.3, + "learning_rate": 3.51790787678128e-05, + "loss": 0.1758, "step": 133560 }, { - "epoch": 0.6, - "learning_rate": 2.0288552082866242e-05, - "loss": 0.1794, + "epoch": 0.3, + "learning_rate": 3.5177960224603476e-05, + "loss": 0.1814, "step": 133570 }, { - "epoch": 0.6, - "learning_rate": 2.0286310030940318e-05, - "loss": 0.1733, + "epoch": 0.3, + "learning_rate": 3.5176841681394154e-05, + "loss": 0.1782, "step": 133580 }, { - "epoch": 0.6, - "learning_rate": 2.0284067979014396e-05, - "loss": 0.1875, + "epoch": 0.3, + "learning_rate": 3.517572313818483e-05, + "loss": 0.1728, "step": 133590 }, { - "epoch": 0.6, - "learning_rate": 2.0281825927088472e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.517460459497551e-05, + "loss": 0.1752, "step": 133600 }, { - "epoch": 0.6, - "learning_rate": 2.027958387516255e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.517348605176618e-05, + "loss": 0.1753, "step": 133610 }, { - "epoch": 0.6, - "learning_rate": 2.0277341823236626e-05, - "loss": 0.1746, + "epoch": 0.3, + "learning_rate": 3.517236750855686e-05, + "loss": 0.1721, "step": 133620 }, { - "epoch": 0.6, - "learning_rate": 2.0275099771310705e-05, - "loss": 0.1812, + "epoch": 0.3, + "learning_rate": 3.517124896534753e-05, + "loss": 0.1742, "step": 133630 }, { - "epoch": 0.6, - "learning_rate": 2.0272857719384783e-05, - "loss": 0.1766, + "epoch": 0.3, + "learning_rate": 3.517013042213821e-05, + "loss": 0.1717, "step": 133640 }, { - "epoch": 0.6, - "learning_rate": 2.027061566745886e-05, - "loss": 0.175, + "epoch": 0.3, + "learning_rate": 3.5169011878928886e-05, + "loss": 0.1779, "step": 133650 }, { - "epoch": 0.6, - "learning_rate": 2.0268373615532937e-05, - "loss": 0.1812, + "epoch": 0.3, + "learning_rate": 3.516789333571956e-05, + "loss": 0.1723, "step": 133660 }, { - "epoch": 0.6, - "learning_rate": 2.0266131563607013e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.5166774792510235e-05, + "loss": 0.174, "step": 133670 }, { - "epoch": 0.6, - "learning_rate": 2.026388951168109e-05, - "loss": 0.1786, + "epoch": 0.3, + "learning_rate": 3.516565624930091e-05, + "loss": 0.1777, "step": 133680 }, { - "epoch": 0.6, - "learning_rate": 2.0261647459755167e-05, - "loss": 0.1803, + "epoch": 0.3, + "learning_rate": 3.516453770609159e-05, + "loss": 0.1756, "step": 133690 }, { - "epoch": 0.6, - "learning_rate": 2.0259405407829245e-05, - "loss": 0.1739, + "epoch": 0.3, + "learning_rate": 3.516341916288227e-05, + "loss": 0.1753, "step": 133700 }, { - "epoch": 0.6, - "learning_rate": 2.0257163355903324e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.516230061967294e-05, + "loss": 0.1791, "step": 133710 }, { - "epoch": 0.6, - "learning_rate": 2.02549213039774e-05, - "loss": 0.1749, + "epoch": 0.3, + "learning_rate": 3.516118207646362e-05, + "loss": 0.1733, "step": 133720 }, { - "epoch": 0.6, - "learning_rate": 2.0252679252051478e-05, - "loss": 0.1712, + "epoch": 0.3, + "learning_rate": 3.516006353325429e-05, + "loss": 0.1797, "step": 133730 }, { - "epoch": 0.6, - "learning_rate": 2.0250437200125554e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.515894499004497e-05, + "loss": 0.1725, "step": 133740 }, { - "epoch": 0.6, - "learning_rate": 2.0248195148199632e-05, - "loss": 0.1754, + "epoch": 0.3, + "learning_rate": 3.5157826446835645e-05, + "loss": 0.1751, "step": 133750 }, { - "epoch": 0.6, - "learning_rate": 2.024595309627371e-05, - "loss": 0.1773, + "epoch": 0.3, + "learning_rate": 3.5156707903626316e-05, + "loss": 0.1727, "step": 133760 }, { - "epoch": 0.6, - "learning_rate": 2.0243711044347786e-05, - "loss": 0.1714, + "epoch": 0.3, + "learning_rate": 3.5155589360416994e-05, + "loss": 0.1755, "step": 133770 }, { - "epoch": 0.6, - "learning_rate": 2.0241468992421865e-05, - "loss": 0.1749, + "epoch": 0.3, + "learning_rate": 3.515447081720767e-05, + "loss": 0.1742, "step": 133780 }, { - "epoch": 0.6, - "learning_rate": 2.0239226940495944e-05, - "loss": 0.1759, + "epoch": 0.3, + "learning_rate": 3.515335227399835e-05, + "loss": 0.1702, "step": 133790 }, { - "epoch": 0.6, - "learning_rate": 2.0236984888570022e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.515223373078903e-05, + "loss": 0.1789, "step": 133800 }, { - "epoch": 0.6, - "learning_rate": 2.0234742836644098e-05, - "loss": 0.1737, - "step": 133810 + "epoch": 0.3, + "learning_rate": 3.51511151875797e-05, + "loss": 0.171, + "step": 133810 }, { - "epoch": 0.6, - "learning_rate": 2.0232500784718177e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.514999664437038e-05, + "loss": 0.1726, "step": 133820 }, { - "epoch": 0.6, - "learning_rate": 2.0230258732792255e-05, - "loss": 0.1777, + "epoch": 0.3, + "learning_rate": 3.514887810116105e-05, + "loss": 0.1741, "step": 133830 }, { - "epoch": 0.6, - "learning_rate": 2.022801668086633e-05, - "loss": 0.181, + "epoch": 0.3, + "learning_rate": 3.5147759557951726e-05, + "loss": 0.17, "step": 133840 }, { - "epoch": 0.6, - "learning_rate": 2.022577462894041e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.51466410147424e-05, + "loss": 0.1707, "step": 133850 }, { - "epoch": 0.6, - "learning_rate": 2.0223532577014485e-05, - "loss": 0.1775, + "epoch": 0.3, + "learning_rate": 3.5145522471533075e-05, + "loss": 0.1774, "step": 133860 }, { - "epoch": 0.6, - "learning_rate": 2.0221290525088563e-05, - "loss": 0.1845, + "epoch": 0.3, + "learning_rate": 3.514440392832375e-05, + "loss": 0.1755, "step": 133870 }, { - "epoch": 0.6, - "learning_rate": 2.021904847316264e-05, - "loss": 0.1845, + "epoch": 0.3, + "learning_rate": 3.5143285385114424e-05, + "loss": 0.1757, "step": 133880 }, { - "epoch": 0.6, - "learning_rate": 2.0216806421236717e-05, - "loss": 0.1774, + "epoch": 0.3, + "learning_rate": 3.51421668419051e-05, + "loss": 0.1773, "step": 133890 }, { - "epoch": 0.6, - "learning_rate": 2.0214564369310796e-05, - "loss": 0.1798, + "epoch": 0.3, + "learning_rate": 3.514104829869578e-05, + "loss": 0.1683, "step": 133900 }, { - "epoch": 0.6, - "learning_rate": 2.021232231738487e-05, - "loss": 0.1759, + "epoch": 0.3, + "learning_rate": 3.513992975548646e-05, + "loss": 0.1741, "step": 133910 }, { - "epoch": 0.6, - "learning_rate": 2.021008026545895e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.5138811212277136e-05, + "loss": 0.1713, "step": 133920 }, { - "epoch": 0.6, - "learning_rate": 2.0207838213533025e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.513769266906781e-05, + "loss": 0.1735, "step": 133930 }, { - "epoch": 0.6, - "learning_rate": 2.0205596161607104e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.5136574125858485e-05, + "loss": 0.172, "step": 133940 }, { - "epoch": 0.6, - "learning_rate": 2.020335410968118e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.5135455582649156e-05, + "loss": 0.1765, "step": 133950 }, { - "epoch": 0.6, - "learning_rate": 2.0201112057755258e-05, - "loss": 0.1775, + "epoch": 0.3, + "learning_rate": 3.5134337039439834e-05, + "loss": 0.1756, "step": 133960 }, { - "epoch": 0.6, - "learning_rate": 2.0198870005829337e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.513321849623051e-05, + "loss": 0.1749, "step": 133970 }, { - "epoch": 0.6, - "learning_rate": 2.0196627953903412e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.513209995302118e-05, + "loss": 0.1754, "step": 133980 }, { - "epoch": 0.6, - "learning_rate": 2.019438590197749e-05, - "loss": 0.1697, + "epoch": 0.3, + "learning_rate": 3.513098140981186e-05, + "loss": 0.1754, "step": 133990 }, { - "epoch": 0.6, - "learning_rate": 2.0192143850051566e-05, - "loss": 0.1739, + "epoch": 0.3, + "learning_rate": 3.512986286660254e-05, + "loss": 0.1736, "step": 134000 }, { - "epoch": 0.6, - "learning_rate": 2.0189901798125645e-05, - "loss": 0.1735, + "epoch": 0.3, + "learning_rate": 3.512874432339322e-05, + "loss": 0.1705, "step": 134010 }, { - "epoch": 0.6, - "learning_rate": 2.018765974619972e-05, - "loss": 0.1665, + "epoch": 0.3, + "learning_rate": 3.5127625780183895e-05, + "loss": 0.1711, "step": 134020 }, { - "epoch": 0.6, - "learning_rate": 2.01854176942738e-05, - "loss": 0.1709, + "epoch": 0.3, + "learning_rate": 3.5126507236974566e-05, + "loss": 0.1694, "step": 134030 }, { - "epoch": 0.6, - "learning_rate": 2.0183175642347878e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.5125388693765244e-05, + "loss": 0.1679, "step": 134040 }, { - "epoch": 0.6, - "learning_rate": 2.0180933590421957e-05, - "loss": 0.1699, + "epoch": 0.3, + "learning_rate": 3.5124270150555915e-05, + "loss": 0.1743, "step": 134050 }, { - "epoch": 0.6, - "learning_rate": 2.0178691538496032e-05, - "loss": 0.1789, + "epoch": 0.3, + "learning_rate": 3.512315160734659e-05, + "loss": 0.1724, "step": 134060 }, { - "epoch": 0.6, - "learning_rate": 2.0176673691762703e-05, - "loss": 0.1793, + "epoch": 0.3, + "learning_rate": 3.512203306413727e-05, + "loss": 0.1724, "step": 134070 }, { - "epoch": 0.6, - "learning_rate": 2.017443163983678e-05, - "loss": 0.172, + "epoch": 0.3, + "learning_rate": 3.512091452092794e-05, + "loss": 0.1727, "step": 134080 }, { - "epoch": 0.6, - "learning_rate": 2.0172189587910857e-05, - "loss": 0.1749, + "epoch": 0.3, + "learning_rate": 3.511979597771862e-05, + "loss": 0.1762, "step": 134090 }, { - "epoch": 0.6, - "learning_rate": 2.0169947535984936e-05, - "loss": 0.1772, + "epoch": 0.3, + "learning_rate": 3.51186774345093e-05, + "loss": 0.1715, "step": 134100 }, { - "epoch": 0.6, - "learning_rate": 2.0167705484059015e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.5117558891299976e-05, + "loss": 0.1771, "step": 134110 }, { - "epoch": 0.6, - "learning_rate": 2.016546343213309e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.5116440348090654e-05, + "loss": 0.1747, "step": 134120 }, { - "epoch": 0.6, - "learning_rate": 2.016322138020717e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.5115321804881325e-05, + "loss": 0.1787, "step": 134130 }, { - "epoch": 0.6, - "learning_rate": 2.0160979328281244e-05, - "loss": 0.1736, + "epoch": 0.3, + "learning_rate": 3.5114203261672e-05, + "loss": 0.1768, "step": 134140 }, { - "epoch": 0.6, - "learning_rate": 2.0158737276355323e-05, - "loss": 0.1802, + "epoch": 0.3, + "learning_rate": 3.5113084718462674e-05, + "loss": 0.1714, "step": 134150 }, { - "epoch": 0.6, - "learning_rate": 2.0156495224429398e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.511196617525335e-05, + "loss": 0.1795, "step": 134160 }, { - "epoch": 0.6, - "learning_rate": 2.0154253172503477e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.511084763204402e-05, + "loss": 0.1722, "step": 134170 }, { - "epoch": 0.6, - "learning_rate": 2.0152011120577555e-05, - "loss": 0.1717, + "epoch": 0.3, + "learning_rate": 3.51097290888347e-05, + "loss": 0.176, "step": 134180 }, { - "epoch": 0.6, - "learning_rate": 2.014976906865163e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.510861054562538e-05, + "loss": 0.1747, "step": 134190 }, { - "epoch": 0.6, - "learning_rate": 2.014752701672571e-05, - "loss": 0.181, + "epoch": 0.3, + "learning_rate": 3.510749200241606e-05, + "loss": 0.1765, "step": 134200 }, { - "epoch": 0.6, - "learning_rate": 2.0145284964799785e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.5106373459206735e-05, + "loss": 0.1743, "step": 134210 }, { - "epoch": 0.6, - "learning_rate": 2.0143042912873863e-05, - "loss": 0.178, + "epoch": 0.3, + "learning_rate": 3.5105254915997406e-05, + "loss": 0.1752, "step": 134220 }, { - "epoch": 0.6, - "learning_rate": 2.014080086094794e-05, - "loss": 0.1769, + "epoch": 0.3, + "learning_rate": 3.5104136372788084e-05, + "loss": 0.1794, "step": 134230 }, { - "epoch": 0.6, - "learning_rate": 2.0138558809022018e-05, - "loss": 0.1725, + "epoch": 0.3, + "learning_rate": 3.510301782957876e-05, + "loss": 0.1779, "step": 134240 }, { - "epoch": 0.6, - "learning_rate": 2.0136316757096096e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.510189928636943e-05, + "loss": 0.1733, "step": 134250 }, { - "epoch": 0.6, - "learning_rate": 2.013407470517017e-05, - "loss": 0.1746, + "epoch": 0.3, + "learning_rate": 3.510078074316011e-05, + "loss": 0.1747, "step": 134260 }, { - "epoch": 0.6, - "learning_rate": 2.013183265324425e-05, - "loss": 0.1788, + "epoch": 0.3, + "learning_rate": 3.509966219995078e-05, + "loss": 0.1723, "step": 134270 }, { - "epoch": 0.6, - "learning_rate": 2.0129590601318326e-05, - "loss": 0.183, + "epoch": 0.3, + "learning_rate": 3.509854365674146e-05, + "loss": 0.1711, "step": 134280 }, { - "epoch": 0.6, - "learning_rate": 2.0127348549392404e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.509742511353214e-05, + "loss": 0.1738, "step": 134290 }, { - "epoch": 0.6, - "learning_rate": 2.012510649746648e-05, - "loss": 0.1706, + "epoch": 0.3, + "learning_rate": 3.509630657032281e-05, + "loss": 0.1729, "step": 134300 }, { - "epoch": 0.6, - "learning_rate": 2.012286444554056e-05, - "loss": 0.1787, + "epoch": 0.3, + "learning_rate": 3.5095188027113494e-05, + "loss": 0.1758, "step": 134310 }, { - "epoch": 0.6, - "learning_rate": 2.0120622393614637e-05, - "loss": 0.1763, + "epoch": 0.3, + "learning_rate": 3.5094069483904165e-05, + "loss": 0.1687, "step": 134320 }, { - "epoch": 0.6, - "learning_rate": 2.0118380341688712e-05, + "epoch": 0.3, + "learning_rate": 3.509295094069484e-05, "loss": 0.1749, "step": 134330 }, { - "epoch": 0.6, - "learning_rate": 2.011613828976279e-05, - "loss": 0.1738, + "epoch": 0.3, + "learning_rate": 3.509183239748552e-05, + "loss": 0.1741, "step": 134340 }, { - "epoch": 0.6, - "learning_rate": 2.011389623783687e-05, - "loss": 0.1735, + "epoch": 0.3, + "learning_rate": 3.509071385427619e-05, + "loss": 0.1746, "step": 134350 }, { - "epoch": 0.6, - "learning_rate": 2.011165418591095e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.508959531106687e-05, + "loss": 0.1737, "step": 134360 }, { - "epoch": 0.6, - "learning_rate": 2.0109412133985024e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.508847676785754e-05, + "loss": 0.1691, "step": 134370 }, { - "epoch": 0.6, - "learning_rate": 2.0107170082059103e-05, - "loss": 0.1758, + "epoch": 0.3, + "learning_rate": 3.508735822464822e-05, + "loss": 0.1748, "step": 134380 }, { - "epoch": 0.6, - "learning_rate": 2.010492803013318e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.508635153575983e-05, + "loss": 0.1731, "step": 134390 }, { - "epoch": 0.6, - "learning_rate": 2.0102685978207257e-05, - "loss": 0.1703, + "epoch": 0.3, + "learning_rate": 3.5085232992550506e-05, + "loss": 0.1714, "step": 134400 }, { - "epoch": 0.6, - "learning_rate": 2.0100443926281335e-05, - "loss": 0.1665, + "epoch": 0.3, + "learning_rate": 3.5084114449341183e-05, + "loss": 0.1756, "step": 134410 }, { - "epoch": 0.6, - "learning_rate": 2.009820187435541e-05, - "loss": 0.1713, + "epoch": 0.3, + "learning_rate": 3.5082995906131855e-05, + "loss": 0.1772, "step": 134420 }, { - "epoch": 0.6, - "learning_rate": 2.009595982242949e-05, - "loss": 0.1744, + "epoch": 0.3, + "learning_rate": 3.508187736292253e-05, + "loss": 0.171, "step": 134430 }, { - "epoch": 0.6, - "learning_rate": 2.0093717770503565e-05, - "loss": 0.1706, + "epoch": 0.3, + "learning_rate": 3.5080758819713204e-05, + "loss": 0.1742, "step": 134440 }, { - "epoch": 0.6, - "learning_rate": 2.0091475718577643e-05, - "loss": 0.1761, + "epoch": 0.3, + "learning_rate": 3.507964027650388e-05, + "loss": 0.1689, "step": 134450 }, { - "epoch": 0.6, - "learning_rate": 2.0089233666651722e-05, - "loss": 0.1774, + "epoch": 0.3, + "learning_rate": 3.507852173329456e-05, + "loss": 0.1728, "step": 134460 }, { - "epoch": 0.6, - "learning_rate": 2.0086991614725798e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.507740319008523e-05, + "loss": 0.175, "step": 134470 }, { - "epoch": 0.6, - "learning_rate": 2.0084749562799876e-05, - "loss": 0.1754, + "epoch": 0.3, + "learning_rate": 3.5076284646875915e-05, + "loss": 0.1728, "step": 134480 }, { - "epoch": 0.6, - "learning_rate": 2.008250751087395e-05, - "loss": 0.1763, + "epoch": 0.3, + "learning_rate": 3.5075166103666587e-05, + "loss": 0.1724, "step": 134490 }, { - "epoch": 0.6, - "learning_rate": 2.008026545894803e-05, - "loss": 0.1809, + "epoch": 0.3, + "learning_rate": 3.5074047560457264e-05, + "loss": 0.1741, "step": 134500 }, { - "epoch": 0.6, - "learning_rate": 2.0078023407022106e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.5072929017247936e-05, + "loss": 0.1701, "step": 134510 }, { - "epoch": 0.6, - "learning_rate": 2.0075781355096184e-05, - "loss": 0.178, + "epoch": 0.3, + "learning_rate": 3.5071810474038614e-05, + "loss": 0.17, "step": 134520 }, { - "epoch": 0.6, - "learning_rate": 2.0073539303170263e-05, - "loss": 0.1724, + "epoch": 0.3, + "learning_rate": 3.507069193082929e-05, + "loss": 0.1723, "step": 134530 }, { - "epoch": 0.6, - "learning_rate": 2.007129725124434e-05, - "loss": 0.1784, + "epoch": 0.3, + "learning_rate": 3.506957338761996e-05, + "loss": 0.1694, "step": 134540 }, { - "epoch": 0.6, - "learning_rate": 2.0069055199318417e-05, - "loss": 0.18, + "epoch": 0.3, + "learning_rate": 3.506845484441064e-05, + "loss": 0.1716, "step": 134550 }, { - "epoch": 0.6, - "learning_rate": 2.0066813147392492e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.506733630120131e-05, + "loss": 0.1722, "step": 134560 }, { - "epoch": 0.6, - "learning_rate": 2.006457109546657e-05, - "loss": 0.1761, + "epoch": 0.3, + "learning_rate": 3.506621775799199e-05, + "loss": 0.1729, "step": 134570 }, { - "epoch": 0.6, - "learning_rate": 2.0062329043540646e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.506509921478267e-05, + "loss": 0.1717, "step": 134580 }, { - "epoch": 0.6, - "learning_rate": 2.0060086991614725e-05, - "loss": 0.1689, + "epoch": 0.3, + "learning_rate": 3.5063980671573346e-05, + "loss": 0.1748, "step": 134590 }, { - "epoch": 0.6, - "learning_rate": 2.0057844939688804e-05, - "loss": 0.167, + "epoch": 0.3, + "learning_rate": 3.5062862128364023e-05, + "loss": 0.1689, "step": 134600 }, { - "epoch": 0.6, - "learning_rate": 2.0055602887762883e-05, - "loss": 0.1723, + "epoch": 0.3, + "learning_rate": 3.5061743585154695e-05, + "loss": 0.1753, "step": 134610 }, { - "epoch": 0.6, - "learning_rate": 2.0053360835836958e-05, - "loss": 0.1718, + "epoch": 0.3, + "learning_rate": 3.506062504194537e-05, + "loss": 0.1764, "step": 134620 }, { - "epoch": 0.6, - "learning_rate": 2.0051118783911037e-05, - "loss": 0.1816, + "epoch": 0.3, + "learning_rate": 3.505950649873605e-05, + "loss": 0.1716, "step": 134630 }, { - "epoch": 0.6, - "learning_rate": 2.0048876731985115e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.505838795552672e-05, + "loss": 0.1765, "step": 134640 }, { - "epoch": 0.6, - "learning_rate": 2.004663468005919e-05, - "loss": 0.1802, + "epoch": 0.3, + "learning_rate": 3.50572694123174e-05, + "loss": 0.1734, "step": 134650 }, { - "epoch": 0.6, - "learning_rate": 2.004439262813327e-05, - "loss": 0.1782, + "epoch": 0.3, + "learning_rate": 3.505615086910807e-05, + "loss": 0.1705, "step": 134660 }, { - "epoch": 0.6, - "learning_rate": 2.0042150576207348e-05, - "loss": 0.1763, + "epoch": 0.3, + "learning_rate": 3.505503232589875e-05, + "loss": 0.1699, "step": 134670 }, { - "epoch": 0.6, - "learning_rate": 2.0039908524281423e-05, - "loss": 0.1787, + "epoch": 0.3, + "learning_rate": 3.5053913782689427e-05, + "loss": 0.1774, "step": 134680 }, { - "epoch": 0.6, - "learning_rate": 2.0037666472355502e-05, - "loss": 0.1807, + "epoch": 0.3, + "learning_rate": 3.5052795239480104e-05, + "loss": 0.1746, "step": 134690 }, { - "epoch": 0.6, - "learning_rate": 2.0035424420429578e-05, - "loss": 0.1807, + "epoch": 0.3, + "learning_rate": 3.505167669627078e-05, + "loss": 0.1727, "step": 134700 }, { - "epoch": 0.6, - "learning_rate": 2.0033182368503656e-05, - "loss": 0.1784, + "epoch": 0.3, + "learning_rate": 3.5050558153061454e-05, + "loss": 0.1738, "step": 134710 }, { - "epoch": 0.6, - "learning_rate": 2.003094031657773e-05, - "loss": 0.1781, + "epoch": 0.3, + "learning_rate": 3.504943960985213e-05, + "loss": 0.1737, "step": 134720 }, { - "epoch": 0.6, - "learning_rate": 2.002869826465181e-05, - "loss": 0.1726, + "epoch": 0.3, + "learning_rate": 3.504832106664281e-05, + "loss": 0.1682, "step": 134730 }, { - "epoch": 0.6, - "learning_rate": 2.002645621272589e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.504720252343348e-05, + "loss": 0.1739, "step": 134740 }, { - "epoch": 0.6, - "learning_rate": 2.0024214160799964e-05, - "loss": 0.1744, + "epoch": 0.3, + "learning_rate": 3.504608398022416e-05, + "loss": 0.1734, "step": 134750 }, { - "epoch": 0.6, - "learning_rate": 2.0021972108874043e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.504496543701483e-05, + "loss": 0.1741, "step": 134760 }, { - "epoch": 0.6, - "learning_rate": 2.001973005694812e-05, - "loss": 0.183, + "epoch": 0.3, + "learning_rate": 3.504384689380551e-05, + "loss": 0.1726, "step": 134770 }, { - "epoch": 0.6, - "learning_rate": 2.0017488005022197e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.5042728350596185e-05, + "loss": 0.17, "step": 134780 }, { - "epoch": 0.6, - "learning_rate": 2.0015245953096276e-05, - "loss": 0.1782, + "epoch": 0.3, + "learning_rate": 3.5041609807386863e-05, + "loss": 0.1801, "step": 134790 }, { - "epoch": 0.6, - "learning_rate": 2.001300390117035e-05, - "loss": 0.1704, + "epoch": 0.3, + "learning_rate": 3.504049126417754e-05, + "loss": 0.177, "step": 134800 }, { - "epoch": 0.6, - "learning_rate": 2.001076184924443e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.503937272096821e-05, + "loss": 0.1739, "step": 134810 }, { - "epoch": 0.6, - "learning_rate": 2.0008519797318505e-05, - "loss": 0.1726, + "epoch": 0.3, + "learning_rate": 3.503825417775889e-05, + "loss": 0.1784, "step": 134820 }, { - "epoch": 0.6, - "learning_rate": 2.0006277745392584e-05, - "loss": 0.172, + "epoch": 0.3, + "learning_rate": 3.503713563454956e-05, + "loss": 0.1719, "step": 134830 }, { - "epoch": 0.6, - "learning_rate": 2.000403569346666e-05, - "loss": 0.1788, + "epoch": 0.3, + "learning_rate": 3.503601709134024e-05, + "loss": 0.1735, "step": 134840 }, { - "epoch": 0.6, - "learning_rate": 2.0001793641540738e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.503489854813092e-05, + "loss": 0.1768, "step": 134850 }, { - "epoch": 0.6, - "learning_rate": 1.9999551589614817e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.503378000492159e-05, + "loss": 0.1736, "step": 134860 }, { - "epoch": 0.6, - "learning_rate": 1.9997309537688892e-05, - "loss": 0.1746, + "epoch": 0.3, + "learning_rate": 3.5032661461712266e-05, + "loss": 0.1715, "step": 134870 }, { - "epoch": 0.6, - "learning_rate": 1.999506748576297e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.503154291850294e-05, + "loss": 0.1721, "step": 134880 }, { - "epoch": 0.6, - "learning_rate": 1.999282543383705e-05, - "loss": 0.1789, + "epoch": 0.3, + "learning_rate": 3.503042437529362e-05, + "loss": 0.1727, "step": 134890 }, { - "epoch": 0.6, - "learning_rate": 1.9990583381911128e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.50293058320843e-05, + "loss": 0.1737, "step": 134900 }, { - "epoch": 0.6, - "learning_rate": 1.9988341329985204e-05, - "loss": 0.1738, + "epoch": 0.3, + "learning_rate": 3.502818728887497e-05, + "loss": 0.1714, "step": 134910 }, { - "epoch": 0.6, - "learning_rate": 1.9986099278059282e-05, - "loss": 0.1813, + "epoch": 0.3, + "learning_rate": 3.502706874566565e-05, + "loss": 0.1717, "step": 134920 }, { - "epoch": 0.6, - "learning_rate": 1.998385722613336e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.502595020245632e-05, + "loss": 0.1733, "step": 134930 }, { - "epoch": 0.6, - "learning_rate": 1.9981615174207436e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.5024831659247e-05, + "loss": 0.173, "step": 134940 }, { - "epoch": 0.6, - "learning_rate": 1.9979373122281515e-05, - "loss": 0.1775, + "epoch": 0.3, + "learning_rate": 3.5023713116037676e-05, + "loss": 0.1681, "step": 134950 }, { - "epoch": 0.6, - "learning_rate": 1.997713107035559e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.502259457282835e-05, + "loss": 0.177, "step": 134960 }, { - "epoch": 0.6, - "learning_rate": 1.997488901842967e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.5021476029619025e-05, + "loss": 0.1791, "step": 134970 }, { - "epoch": 0.6, - "learning_rate": 1.9972646966503744e-05, - "loss": 0.1802, + "epoch": 0.3, + "learning_rate": 3.5020357486409697e-05, + "loss": 0.1735, "step": 134980 }, { - "epoch": 0.6, - "learning_rate": 1.9970404914577823e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.5019238943200375e-05, + "loss": 0.1716, "step": 134990 }, { - "epoch": 0.6, - "learning_rate": 1.9968162862651902e-05, - "loss": 0.1735, + "epoch": 0.3, + "learning_rate": 3.501812039999105e-05, + "loss": 0.1732, "step": 135000 }, { - "epoch": 0.6, - "learning_rate": 1.9965920810725977e-05, - "loss": 0.1734, + "epoch": 0.3, + "learning_rate": 3.501700185678173e-05, + "loss": 0.1687, "step": 135010 }, { - "epoch": 0.6, - "learning_rate": 1.9963678758800056e-05, - "loss": 0.1711, + "epoch": 0.3, + "learning_rate": 3.501588331357241e-05, + "loss": 0.1718, "step": 135020 }, { - "epoch": 0.6, - "learning_rate": 1.996143670687413e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.501476477036308e-05, + "loss": 0.1696, "step": 135030 }, { - "epoch": 0.6, - "learning_rate": 1.995919465494821e-05, - "loss": 0.1807, + "epoch": 0.3, + "learning_rate": 3.501364622715376e-05, + "loss": 0.1703, "step": 135040 }, { - "epoch": 0.6, - "learning_rate": 1.9956952603022285e-05, - "loss": 0.1761, + "epoch": 0.3, + "learning_rate": 3.5012527683944435e-05, + "loss": 0.1698, "step": 135050 }, { - "epoch": 0.6, - "learning_rate": 1.9954710551096364e-05, - "loss": 0.1747, + "epoch": 0.3, + "learning_rate": 3.5011409140735106e-05, + "loss": 0.1731, "step": 135060 }, { - "epoch": 0.6, - "learning_rate": 1.9952468499170443e-05, - "loss": 0.172, + "epoch": 0.3, + "learning_rate": 3.5010290597525784e-05, + "loss": 0.1702, "step": 135070 }, { - "epoch": 0.6, - "learning_rate": 1.9950226447244518e-05, - "loss": 0.1777, + "epoch": 0.3, + "learning_rate": 3.5009172054316456e-05, + "loss": 0.1697, "step": 135080 }, { - "epoch": 0.6, - "learning_rate": 1.9947984395318597e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.5008053511107133e-05, + "loss": 0.173, "step": 135090 }, { - "epoch": 0.6, - "learning_rate": 1.9945742343392672e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.500693496789781e-05, + "loss": 0.1725, "step": 135100 }, { - "epoch": 0.6, - "learning_rate": 1.994350029146675e-05, - "loss": 0.1736, + "epoch": 0.3, + "learning_rate": 3.500581642468849e-05, + "loss": 0.1678, "step": 135110 }, { - "epoch": 0.6, - "learning_rate": 1.9941258239540826e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.500469788147917e-05, + "loss": 0.1704, "step": 135120 }, { - "epoch": 0.6, - "learning_rate": 1.9939016187614905e-05, - "loss": 0.1766, + "epoch": 0.3, + "learning_rate": 3.500357933826984e-05, + "loss": 0.1703, "step": 135130 }, { - "epoch": 0.6, - "learning_rate": 1.9936774135688984e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.5002460795060516e-05, + "loss": 0.1762, "step": 135140 }, { - "epoch": 0.6, - "learning_rate": 1.9934532083763062e-05, - "loss": 0.1734, + "epoch": 0.3, + "learning_rate": 3.500134225185119e-05, + "loss": 0.1745, "step": 135150 }, { - "epoch": 0.6, - "learning_rate": 1.9932290031837138e-05, - "loss": 0.168, + "epoch": 0.3, + "learning_rate": 3.5000223708641865e-05, + "loss": 0.1727, "step": 135160 }, { - "epoch": 0.6, - "learning_rate": 1.9930047979911216e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.499910516543254e-05, + "loss": 0.1782, "step": 135170 }, { - "epoch": 0.6, - "learning_rate": 1.9927805927985295e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.4997986622223214e-05, + "loss": 0.1674, "step": 135180 }, { - "epoch": 0.6, - "learning_rate": 1.992556387605937e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.499686807901389e-05, + "loss": 0.171, "step": 135190 }, { - "epoch": 0.6, - "learning_rate": 1.992332182413345e-05, - "loss": 0.1754, + "epoch": 0.3, + "learning_rate": 3.499574953580457e-05, + "loss": 0.1712, "step": 135200 }, { - "epoch": 0.6, - "learning_rate": 1.9921079772207528e-05, - "loss": 0.1727, + "epoch": 0.3, + "learning_rate": 3.499463099259525e-05, + "loss": 0.172, "step": 135210 }, { - "epoch": 0.6, - "learning_rate": 1.9918837720281603e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.4993512449385926e-05, + "loss": 0.1727, "step": 135220 }, { - "epoch": 0.6, - "learning_rate": 1.9916595668355682e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.49923939061766e-05, + "loss": 0.169, "step": 135230 }, { - "epoch": 0.6, - "learning_rate": 1.9914353616429757e-05, - "loss": 0.1758, + "epoch": 0.3, + "learning_rate": 3.4991275362967275e-05, + "loss": 0.1717, "step": 135240 }, { - "epoch": 0.6, - "learning_rate": 1.9912111564503836e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.4990156819757946e-05, + "loss": 0.1731, "step": 135250 }, { - "epoch": 0.6, - "learning_rate": 1.990986951257791e-05, - "loss": 0.1717, + "epoch": 0.3, + "learning_rate": 3.4989038276548624e-05, + "loss": 0.1715, "step": 135260 }, { - "epoch": 0.6, - "learning_rate": 1.990762746065199e-05, - "loss": 0.1785, + "epoch": 0.3, + "learning_rate": 3.49879197333393e-05, + "loss": 0.1709, "step": 135270 }, { - "epoch": 0.6, - "learning_rate": 1.990538540872607e-05, - "loss": 0.1708, + "epoch": 0.3, + "learning_rate": 3.4986801190129973e-05, + "loss": 0.176, "step": 135280 }, { - "epoch": 0.6, - "learning_rate": 1.9903143356800144e-05, - "loss": 0.1723, + "epoch": 0.3, + "learning_rate": 3.498568264692065e-05, + "loss": 0.1686, "step": 135290 }, { - "epoch": 0.6, - "learning_rate": 1.9900901304874223e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.498456410371132e-05, + "loss": 0.1709, "step": 135300 }, { - "epoch": 0.6, - "learning_rate": 1.9898659252948298e-05, - "loss": 0.1723, + "epoch": 0.3, + "learning_rate": 3.498344556050201e-05, + "loss": 0.1763, "step": 135310 }, { - "epoch": 0.6, - "learning_rate": 1.9896417201022377e-05, - "loss": 0.1744, + "epoch": 0.3, + "learning_rate": 3.4982327017292685e-05, + "loss": 0.174, "step": 135320 }, { - "epoch": 0.6, - "learning_rate": 1.9894175149096452e-05, - "loss": 0.1687, + "epoch": 0.3, + "learning_rate": 3.4981208474083356e-05, + "loss": 0.1787, "step": 135330 }, { - "epoch": 0.6, - "learning_rate": 1.989193309717053e-05, - "loss": 0.1773, + "epoch": 0.3, + "learning_rate": 3.4980089930874034e-05, + "loss": 0.1735, "step": 135340 }, { - "epoch": 0.6, - "learning_rate": 1.988969104524461e-05, - "loss": 0.168, + "epoch": 0.3, + "learning_rate": 3.4978971387664705e-05, + "loss": 0.1759, "step": 135350 }, { - "epoch": 0.6, - "learning_rate": 1.9887448993318685e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.497785284445538e-05, + "loss": 0.1757, "step": 135360 }, { - "epoch": 0.6, - "learning_rate": 1.9885206941392764e-05, - "loss": 0.179, + "epoch": 0.3, + "learning_rate": 3.497673430124606e-05, + "loss": 0.1785, "step": 135370 }, { - "epoch": 0.6, - "learning_rate": 1.988296488946684e-05, - "loss": 0.1773, + "epoch": 0.3, + "learning_rate": 3.497561575803673e-05, + "loss": 0.1712, "step": 135380 }, { - "epoch": 0.6, - "learning_rate": 1.9880722837540918e-05, - "loss": 0.1704, + "epoch": 0.3, + "learning_rate": 3.497449721482741e-05, + "loss": 0.1744, "step": 135390 }, { - "epoch": 0.6, - "learning_rate": 1.9878480785614993e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.497337867161808e-05, + "loss": 0.1707, "step": 135400 }, { - "epoch": 0.6, - "learning_rate": 1.987623873368907e-05, - "loss": 0.175, + "epoch": 0.3, + "learning_rate": 3.497226012840876e-05, + "loss": 0.1681, "step": 135410 }, { - "epoch": 0.6, - "learning_rate": 1.987399668176315e-05, - "loss": 0.1705, + "epoch": 0.3, + "learning_rate": 3.497114158519944e-05, + "loss": 0.1708, "step": 135420 }, { - "epoch": 0.6, - "learning_rate": 1.987175462983723e-05, - "loss": 0.1728, + "epoch": 0.3, + "learning_rate": 3.4970023041990115e-05, + "loss": 0.1786, "step": 135430 }, { - "epoch": 0.6, - "learning_rate": 1.9869512577911308e-05, - "loss": 0.1733, + "epoch": 0.3, + "learning_rate": 3.496890449878079e-05, + "loss": 0.1791, "step": 135440 }, { - "epoch": 0.6, - "learning_rate": 1.9867270525985383e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.4967785955571464e-05, + "loss": 0.1693, "step": 135450 }, { - "epoch": 0.6, - "learning_rate": 1.9865028474059462e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.496666741236214e-05, + "loss": 0.1662, "step": 135460 }, { - "epoch": 0.6, - "learning_rate": 1.9862786422133537e-05, - "loss": 0.1724, + "epoch": 0.3, + "learning_rate": 3.4965548869152813e-05, + "loss": 0.1689, "step": 135470 }, { - "epoch": 0.6, - "learning_rate": 1.9860544370207616e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.496443032594349e-05, + "loss": 0.1761, "step": 135480 }, { - "epoch": 0.6, - "learning_rate": 1.9858302318281695e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.496331178273417e-05, + "loss": 0.1751, "step": 135490 }, { - "epoch": 0.6, - "learning_rate": 1.985606026635577e-05, - "loss": 0.1801, + "epoch": 0.3, + "learning_rate": 3.496219323952484e-05, + "loss": 0.1757, "step": 135500 }, { - "epoch": 0.6, - "learning_rate": 1.985381821442985e-05, - "loss": 0.1712, + "epoch": 0.3, + "learning_rate": 3.496107469631552e-05, + "loss": 0.1732, "step": 135510 }, { - "epoch": 0.6, - "learning_rate": 1.9851576162503924e-05, - "loss": 0.173, + "epoch": 0.3, + "learning_rate": 3.4959956153106196e-05, + "loss": 0.1756, "step": 135520 }, { - "epoch": 0.61, - "learning_rate": 1.9849334110578003e-05, - "loss": 0.1681, + "epoch": 0.3, + "learning_rate": 3.4958837609896874e-05, + "loss": 0.1717, "step": 135530 }, { - "epoch": 0.61, - "learning_rate": 1.9847092058652078e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.495771906668755e-05, + "loss": 0.1716, "step": 135540 }, { - "epoch": 0.61, - "learning_rate": 1.9844850006726157e-05, - "loss": 0.1716, + "epoch": 0.3, + "learning_rate": 3.495660052347822e-05, + "loss": 0.1734, "step": 135550 }, { - "epoch": 0.61, - "learning_rate": 1.9842607954800235e-05, - "loss": 0.1822, + "epoch": 0.3, + "learning_rate": 3.49554819802689e-05, + "loss": 0.1784, "step": 135560 }, { - "epoch": 0.61, - "learning_rate": 1.984036590287431e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.495436343705957e-05, + "loss": 0.1698, "step": 135570 }, { - "epoch": 0.61, - "learning_rate": 1.983812385094839e-05, - "loss": 0.1801, + "epoch": 0.3, + "learning_rate": 3.495324489385025e-05, + "loss": 0.1697, "step": 135580 }, { - "epoch": 0.61, - "learning_rate": 1.9835881799022465e-05, - "loss": 0.1719, + "epoch": 0.3, + "learning_rate": 3.495212635064093e-05, + "loss": 0.1715, "step": 135590 }, { - "epoch": 0.61, - "learning_rate": 1.9833639747096544e-05, - "loss": 0.1723, + "epoch": 0.3, + "learning_rate": 3.49510078074316e-05, + "loss": 0.174, "step": 135600 }, { - "epoch": 0.61, - "learning_rate": 1.983139769517062e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.494988926422228e-05, + "loss": 0.1703, "step": 135610 }, { - "epoch": 0.61, - "learning_rate": 1.9829155643244698e-05, - "loss": 0.1779, + "epoch": 0.3, + "learning_rate": 3.4948770721012955e-05, + "loss": 0.172, "step": 135620 }, { - "epoch": 0.61, - "learning_rate": 1.9826913591318776e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.494765217780363e-05, + "loss": 0.1713, "step": 135630 }, { - "epoch": 0.61, - "learning_rate": 1.982467153939285e-05, - "loss": 0.1733, + "epoch": 0.3, + "learning_rate": 3.494653363459431e-05, + "loss": 0.1704, "step": 135640 }, { - "epoch": 0.61, - "learning_rate": 1.982242948746693e-05, - "loss": 0.1713, + "epoch": 0.3, + "learning_rate": 3.494541509138498e-05, + "loss": 0.1709, "step": 135650 }, { - "epoch": 0.61, - "learning_rate": 1.9820187435541006e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.494429654817566e-05, + "loss": 0.1697, "step": 135660 }, { - "epoch": 0.61, - "learning_rate": 1.9817945383615084e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.494317800496633e-05, + "loss": 0.1758, "step": 135670 }, { - "epoch": 0.61, - "learning_rate": 1.9815703331689163e-05, - "loss": 0.1706, + "epoch": 0.3, + "learning_rate": 3.494205946175701e-05, + "loss": 0.1715, "step": 135680 }, { - "epoch": 0.61, - "learning_rate": 1.9813461279763242e-05, - "loss": 0.1761, + "epoch": 0.3, + "learning_rate": 3.494094091854769e-05, + "loss": 0.1733, "step": 135690 }, { - "epoch": 0.61, - "learning_rate": 1.9811219227837317e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.493982237533836e-05, + "loss": 0.169, "step": 135700 }, { - "epoch": 0.61, - "learning_rate": 1.9808977175911396e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.4938703832129036e-05, + "loss": 0.1747, "step": 135710 }, { - "epoch": 0.61, - "learning_rate": 1.9806735123985475e-05, - "loss": 0.1726, + "epoch": 0.3, + "learning_rate": 3.4937585288919714e-05, + "loss": 0.1694, "step": 135720 }, { - "epoch": 0.61, - "learning_rate": 1.980449307205955e-05, - "loss": 0.1767, + "epoch": 0.3, + "learning_rate": 3.493646674571039e-05, + "loss": 0.1775, "step": 135730 }, { - "epoch": 0.61, - "learning_rate": 1.980225102013363e-05, - "loss": 0.1812, + "epoch": 0.3, + "learning_rate": 3.493534820250107e-05, + "loss": 0.1723, "step": 135740 }, { - "epoch": 0.61, - "learning_rate": 1.9800008968207704e-05, - "loss": 0.1838, + "epoch": 0.3, + "learning_rate": 3.493422965929174e-05, + "loss": 0.1692, "step": 135750 }, { - "epoch": 0.61, - "learning_rate": 1.9797766916281783e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.493311111608242e-05, + "loss": 0.1711, "step": 135760 }, { - "epoch": 0.61, - "learning_rate": 1.979552486435586e-05, - "loss": 0.1733, + "epoch": 0.3, + "learning_rate": 3.493199257287309e-05, + "loss": 0.1757, "step": 135770 }, { - "epoch": 0.61, - "learning_rate": 1.9793282812429937e-05, - "loss": 0.1796, + "epoch": 0.3, + "learning_rate": 3.493087402966377e-05, + "loss": 0.1714, "step": 135780 }, { - "epoch": 0.61, - "learning_rate": 1.9791040760504015e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.492975548645444e-05, + "loss": 0.169, "step": 135790 }, { - "epoch": 0.61, - "learning_rate": 1.978879870857809e-05, - "loss": 0.1724, + "epoch": 0.3, + "learning_rate": 3.492863694324512e-05, + "loss": 0.1751, "step": 135800 }, { - "epoch": 0.61, - "learning_rate": 1.978655665665217e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.4927518400035795e-05, + "loss": 0.1722, "step": 135810 }, { - "epoch": 0.61, - "learning_rate": 1.9784314604726245e-05, - "loss": 0.1716, + "epoch": 0.3, + "learning_rate": 3.4926399856826466e-05, + "loss": 0.1711, "step": 135820 }, { - "epoch": 0.61, - "learning_rate": 1.9782072552800324e-05, - "loss": 0.1768, + "epoch": 0.3, + "learning_rate": 3.4925281313617144e-05, + "loss": 0.1806, "step": 135830 }, { - "epoch": 0.61, - "learning_rate": 1.9779830500874402e-05, - "loss": 0.1716, + "epoch": 0.3, + "learning_rate": 3.492416277040782e-05, + "loss": 0.1763, "step": 135840 }, { - "epoch": 0.61, - "learning_rate": 1.9777588448948478e-05, - "loss": 0.176, + "epoch": 0.3, + "learning_rate": 3.49230442271985e-05, + "loss": 0.1671, "step": 135850 }, { - "epoch": 0.61, - "learning_rate": 1.9775346397022556e-05, - "loss": 0.1782, + "epoch": 0.3, + "learning_rate": 3.492192568398918e-05, + "loss": 0.1737, "step": 135860 }, { - "epoch": 0.61, - "learning_rate": 1.977310434509663e-05, - "loss": 0.1742, + "epoch": 0.3, + "learning_rate": 3.492080714077985e-05, + "loss": 0.1757, "step": 135870 }, { - "epoch": 0.61, - "learning_rate": 1.977086229317071e-05, - "loss": 0.1676, + "epoch": 0.3, + "learning_rate": 3.491968859757053e-05, + "loss": 0.1697, "step": 135880 }, { - "epoch": 0.61, - "learning_rate": 1.9768620241244786e-05, - "loss": 0.1782, + "epoch": 0.3, + "learning_rate": 3.49185700543612e-05, + "loss": 0.172, "step": 135890 }, { - "epoch": 0.61, - "learning_rate": 1.9766378189318864e-05, - "loss": 0.1708, + "epoch": 0.3, + "learning_rate": 3.4917451511151876e-05, + "loss": 0.1673, "step": 135900 }, { - "epoch": 0.61, - "learning_rate": 1.9764136137392943e-05, - "loss": 0.1686, + "epoch": 0.3, + "learning_rate": 3.4916332967942554e-05, + "loss": 0.1718, "step": 135910 }, { - "epoch": 0.61, - "learning_rate": 1.976189408546702e-05, - "loss": 0.1725, + "epoch": 0.3, + "learning_rate": 3.4915214424733225e-05, + "loss": 0.1704, "step": 135920 }, { - "epoch": 0.61, - "learning_rate": 1.9759652033541097e-05, - "loss": 0.1747, + "epoch": 0.3, + "learning_rate": 3.49140958815239e-05, + "loss": 0.1698, "step": 135930 }, { - "epoch": 0.61, - "learning_rate": 1.9757409981615173e-05, - "loss": 0.1764, + "epoch": 0.3, + "learning_rate": 3.491297733831458e-05, + "loss": 0.1715, "step": 135940 }, { - "epoch": 0.61, - "learning_rate": 1.975516792968925e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.491185879510526e-05, + "loss": 0.1756, "step": 135950 }, { - "epoch": 0.61, - "learning_rate": 1.975292587776333e-05, - "loss": 0.1705, + "epoch": 0.3, + "learning_rate": 3.491074025189594e-05, + "loss": 0.1776, "step": 135960 }, { - "epoch": 0.61, - "learning_rate": 1.975068382583741e-05, - "loss": 0.1667, + "epoch": 0.3, + "learning_rate": 3.490962170868661e-05, + "loss": 0.1716, "step": 135970 }, { - "epoch": 0.61, - "learning_rate": 1.9748441773911487e-05, - "loss": 0.1751, + "epoch": 0.3, + "learning_rate": 3.4908503165477286e-05, + "loss": 0.1714, "step": 135980 }, { - "epoch": 0.61, - "learning_rate": 1.9746199721985563e-05, - "loss": 0.1705, + "epoch": 0.3, + "learning_rate": 3.490738462226796e-05, + "loss": 0.176, "step": 135990 }, { - "epoch": 0.61, - "learning_rate": 1.974395767005964e-05, - "loss": 0.1735, + "epoch": 0.3, + "learning_rate": 3.4906266079058635e-05, + "loss": 0.1739, "step": 136000 }, { - "epoch": 0.61, - "learning_rate": 1.9741715618133717e-05, - "loss": 0.1776, + "epoch": 0.3, + "learning_rate": 3.490514753584931e-05, + "loss": 0.1771, "step": 136010 }, { - "epoch": 0.61, - "learning_rate": 1.9739473566207795e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.4904028992639984e-05, + "loss": 0.173, "step": 136020 }, { - "epoch": 0.61, - "learning_rate": 1.973723151428187e-05, - "loss": 0.1716, + "epoch": 0.3, + "learning_rate": 3.490291044943066e-05, + "loss": 0.1725, "step": 136030 }, { - "epoch": 0.61, - "learning_rate": 1.973498946235595e-05, - "loss": 0.1762, + "epoch": 0.3, + "learning_rate": 3.490179190622134e-05, + "loss": 0.1727, "step": 136040 }, { - "epoch": 0.61, - "learning_rate": 1.9732747410430028e-05, - "loss": 0.1758, + "epoch": 0.3, + "learning_rate": 3.490067336301202e-05, + "loss": 0.1697, "step": 136050 }, { - "epoch": 0.61, - "learning_rate": 1.9730505358504104e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.4899554819802696e-05, + "loss": 0.1719, "step": 136060 }, { - "epoch": 0.61, - "learning_rate": 1.9728263306578182e-05, - "loss": 0.175, + "epoch": 0.3, + "learning_rate": 3.489843627659337e-05, + "loss": 0.1758, "step": 136070 }, { - "epoch": 0.61, - "learning_rate": 1.9726021254652258e-05, - "loss": 0.1705, + "epoch": 0.3, + "learning_rate": 3.4897317733384045e-05, + "loss": 0.1726, "step": 136080 }, { - "epoch": 0.61, - "learning_rate": 1.972400340791893e-05, - "loss": 0.1716, + "epoch": 0.3, + "learning_rate": 3.4896199190174716e-05, + "loss": 0.1719, "step": 136090 }, { - "epoch": 0.61, - "learning_rate": 1.9721761355993008e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.4895080646965394e-05, + "loss": 0.166, "step": 136100 }, { - "epoch": 0.61, - "learning_rate": 1.9719519304067083e-05, - "loss": 0.1785, + "epoch": 0.3, + "learning_rate": 3.4893962103756065e-05, + "loss": 0.1699, "step": 136110 }, { - "epoch": 0.61, - "learning_rate": 1.971727725214116e-05, - "loss": 0.1712, + "epoch": 0.3, + "learning_rate": 3.489284356054674e-05, + "loss": 0.1742, "step": 136120 }, { - "epoch": 0.61, - "learning_rate": 1.9715035200215237e-05, + "epoch": 0.3, + "learning_rate": 3.489172501733742e-05, "loss": 0.1752, "step": 136130 }, { - "epoch": 0.61, - "learning_rate": 1.9712793148289316e-05, - "loss": 0.1726, + "epoch": 0.3, + "learning_rate": 3.48906064741281e-05, + "loss": 0.1739, "step": 136140 }, { - "epoch": 0.61, - "learning_rate": 1.971055109636339e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.488948793091878e-05, + "loss": 0.1756, "step": 136150 }, { - "epoch": 0.61, - "learning_rate": 1.970830904443747e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.488836938770945e-05, + "loss": 0.1711, "step": 136160 }, { - "epoch": 0.61, - "learning_rate": 1.970606699251155e-05, - "loss": 0.1734, + "epoch": 0.3, + "learning_rate": 3.4887250844500126e-05, + "loss": 0.1722, "step": 136170 }, { - "epoch": 0.61, - "learning_rate": 1.9703824940585624e-05, - "loss": 0.17, + "epoch": 0.3, + "learning_rate": 3.4886132301290804e-05, + "loss": 0.1662, "step": 136180 }, { - "epoch": 0.61, - "learning_rate": 1.9701582888659702e-05, - "loss": 0.1776, + "epoch": 0.3, + "learning_rate": 3.4885013758081475e-05, + "loss": 0.171, "step": 136190 }, { - "epoch": 0.61, - "learning_rate": 1.9699340836733778e-05, - "loss": 0.1795, + "epoch": 0.3, + "learning_rate": 3.488389521487215e-05, + "loss": 0.1732, "step": 136200 }, { - "epoch": 0.61, - "learning_rate": 1.9697098784807856e-05, - "loss": 0.1712, + "epoch": 0.3, + "learning_rate": 3.4882776671662824e-05, + "loss": 0.1738, "step": 136210 }, { - "epoch": 0.61, - "learning_rate": 1.9694856732881932e-05, - "loss": 0.1739, + "epoch": 0.3, + "learning_rate": 3.48816581284535e-05, + "loss": 0.173, "step": 136220 }, { - "epoch": 0.61, - "learning_rate": 1.969261468095601e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.488053958524418e-05, + "loss": 0.1723, "step": 136230 }, { - "epoch": 0.61, - "learning_rate": 1.969037262903009e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.487942104203485e-05, + "loss": 0.1685, "step": 136240 }, { - "epoch": 0.61, - "learning_rate": 1.9688130577104168e-05, - "loss": 0.1729, + "epoch": 0.3, + "learning_rate": 3.487830249882553e-05, + "loss": 0.172, "step": 136250 }, { - "epoch": 0.61, - "learning_rate": 1.9685888525178243e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.487718395561621e-05, + "loss": 0.1724, "step": 136260 }, { - "epoch": 0.61, - "learning_rate": 1.9683646473252322e-05, - "loss": 0.1773, + "epoch": 0.3, + "learning_rate": 3.4876065412406885e-05, + "loss": 0.1755, "step": 136270 }, { - "epoch": 0.61, - "learning_rate": 1.96814044213264e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.487494686919756e-05, + "loss": 0.1708, "step": 136280 }, { - "epoch": 0.61, - "learning_rate": 1.9679162369400476e-05, - "loss": 0.1749, + "epoch": 0.3, + "learning_rate": 3.4873828325988234e-05, + "loss": 0.1718, "step": 136290 }, { - "epoch": 0.61, - "learning_rate": 1.9676920317474555e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.487270978277891e-05, + "loss": 0.1702, "step": 136300 }, { - "epoch": 0.61, - "learning_rate": 1.9674678265548634e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.487159123956958e-05, + "loss": 0.178, "step": 136310 }, { - "epoch": 0.61, - "learning_rate": 1.967243621362271e-05, - "loss": 0.1793, + "epoch": 0.3, + "learning_rate": 3.487047269636026e-05, + "loss": 0.1738, "step": 136320 }, { - "epoch": 0.61, - "learning_rate": 1.9670194161696788e-05, - "loss": 0.1793, + "epoch": 0.3, + "learning_rate": 3.486935415315094e-05, + "loss": 0.1658, "step": 136330 }, { - "epoch": 0.61, - "learning_rate": 1.9667952109770863e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.486823560994161e-05, + "loss": 0.177, "step": 136340 }, { - "epoch": 0.61, - "learning_rate": 1.966571005784494e-05, - "loss": 0.1739, + "epoch": 0.3, + "learning_rate": 3.486711706673229e-05, + "loss": 0.1743, "step": 136350 }, { - "epoch": 0.61, - "learning_rate": 1.9663468005919017e-05, - "loss": 0.1757, + "epoch": 0.3, + "learning_rate": 3.4865998523522966e-05, + "loss": 0.1737, "step": 136360 }, { - "epoch": 0.61, - "learning_rate": 1.9661225953993096e-05, - "loss": 0.1743, + "epoch": 0.3, + "learning_rate": 3.4864879980313644e-05, + "loss": 0.1716, "step": 136370 }, { - "epoch": 0.61, - "learning_rate": 1.9658983902067174e-05, - "loss": 0.1741, + "epoch": 0.3, + "learning_rate": 3.486376143710432e-05, + "loss": 0.1708, "step": 136380 }, { - "epoch": 0.61, - "learning_rate": 1.965674185014125e-05, - "loss": 0.1752, + "epoch": 0.3, + "learning_rate": 3.486264289389499e-05, + "loss": 0.1676, "step": 136390 }, { - "epoch": 0.61, - "learning_rate": 1.965449979821533e-05, - "loss": 0.1755, + "epoch": 0.3, + "learning_rate": 3.48616362050066e-05, + "loss": 0.1745, "step": 136400 }, { - "epoch": 0.61, - "learning_rate": 1.9652257746289404e-05, - "loss": 0.1737, + "epoch": 0.3, + "learning_rate": 3.486051766179727e-05, + "loss": 0.1722, "step": 136410 }, { - "epoch": 0.61, - "learning_rate": 1.9650015694363482e-05, - "loss": 0.1753, + "epoch": 0.3, + "learning_rate": 3.485939911858795e-05, + "loss": 0.1806, "step": 136420 }, { - "epoch": 0.61, - "learning_rate": 1.9647773642437558e-05, - "loss": 0.1758, + "epoch": 0.3, + "learning_rate": 3.485828057537863e-05, + "loss": 0.1676, "step": 136430 }, { - "epoch": 0.61, - "learning_rate": 1.9645531590511637e-05, - "loss": 0.1738, + "epoch": 0.3, + "learning_rate": 3.485716203216931e-05, + "loss": 0.1711, "step": 136440 }, { - "epoch": 0.61, - "learning_rate": 1.9643289538585715e-05, - "loss": 0.1672, + "epoch": 0.3, + "learning_rate": 3.4856043488959985e-05, + "loss": 0.1815, "step": 136450 }, { - "epoch": 0.61, - "learning_rate": 1.964104748665979e-05, - "loss": 0.169, + "epoch": 0.3, + "learning_rate": 3.4854924945750656e-05, + "loss": 0.1791, "step": 136460 }, { - "epoch": 0.61, - "learning_rate": 1.963880543473387e-05, - "loss": 0.1778, + "epoch": 0.3, + "learning_rate": 3.4853806402541334e-05, + "loss": 0.17, "step": 136470 }, { - "epoch": 0.61, - "learning_rate": 1.9636563382807945e-05, - "loss": 0.1761, + "epoch": 0.3, + "learning_rate": 3.4852687859332005e-05, + "loss": 0.1707, "step": 136480 }, { - "epoch": 0.61, - "learning_rate": 1.9634321330882023e-05, - "loss": 0.173, + "epoch": 0.3, + "learning_rate": 3.485156931612268e-05, + "loss": 0.1748, "step": 136490 }, { - "epoch": 0.61, - "learning_rate": 1.96320792789561e-05, - "loss": 0.1738, + "epoch": 0.3, + "learning_rate": 3.4850450772913354e-05, + "loss": 0.1744, "step": 136500 }, { - "epoch": 0.61, - "learning_rate": 1.9629837227030177e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.484933222970403e-05, + "loss": 0.1752, "step": 136510 }, { - "epoch": 0.61, - "learning_rate": 1.9627595175104256e-05, - "loss": 0.1731, + "epoch": 0.3, + "learning_rate": 3.484821368649471e-05, + "loss": 0.1727, "step": 136520 }, { - "epoch": 0.61, - "learning_rate": 1.9625353123178335e-05, - "loss": 0.1748, + "epoch": 0.3, + "learning_rate": 3.484709514328539e-05, + "loss": 0.1699, "step": 136530 }, { - "epoch": 0.61, - "learning_rate": 1.9623111071252414e-05, - "loss": 0.1788, + "epoch": 0.3, + "learning_rate": 3.4845976600076066e-05, + "loss": 0.1708, "step": 136540 }, { - "epoch": 0.61, - "learning_rate": 1.962086901932649e-05, - "loss": 0.179, + "epoch": 0.3, + "learning_rate": 3.484485805686674e-05, + "loss": 0.1745, "step": 136550 }, { - "epoch": 0.61, - "learning_rate": 1.9618626967400568e-05, - "loss": 0.1717, + "epoch": 0.3, + "learning_rate": 3.4843739513657415e-05, + "loss": 0.1714, "step": 136560 }, { - "epoch": 0.61, - "learning_rate": 1.9616384915474643e-05, - "loss": 0.175, + "epoch": 0.3, + "learning_rate": 3.484262097044809e-05, + "loss": 0.1661, "step": 136570 }, { - "epoch": 0.61, - "learning_rate": 1.961414286354872e-05, - "loss": 0.1733, + "epoch": 0.3, + "learning_rate": 3.4841502427238764e-05, + "loss": 0.1674, "step": 136580 }, { - "epoch": 0.61, - "learning_rate": 1.96119008116228e-05, - "loss": 0.1745, + "epoch": 0.3, + "learning_rate": 3.484038388402944e-05, + "loss": 0.173, "step": 136590 }, { - "epoch": 0.61, - "learning_rate": 1.9609658759696876e-05, - "loss": 0.1698, + "epoch": 0.3, + "learning_rate": 3.483926534082011e-05, + "loss": 0.1671, "step": 136600 }, { - "epoch": 0.61, - "learning_rate": 1.9607416707770954e-05, - "loss": 0.1756, + "epoch": 0.3, + "learning_rate": 3.483814679761079e-05, + "loss": 0.1741, "step": 136610 }, { - "epoch": 0.61, - "learning_rate": 1.960517465584503e-05, - "loss": 0.1718, + "epoch": 0.3, + "learning_rate": 3.483702825440147e-05, + "loss": 0.1727, "step": 136620 }, { - "epoch": 0.61, - "learning_rate": 1.960293260391911e-05, - "loss": 0.1721, + "epoch": 0.3, + "learning_rate": 3.483590971119215e-05, + "loss": 0.1686, "step": 136630 }, { - "epoch": 0.61, - "learning_rate": 1.9600690551993184e-05, - "loss": 0.174, + "epoch": 0.3, + "learning_rate": 3.4834791167982825e-05, + "loss": 0.1743, "step": 136640 }, { - "epoch": 0.61, - "learning_rate": 1.9598448500067262e-05, - "loss": 0.1687, + "epoch": 0.31, + "learning_rate": 3.4833672624773496e-05, + "loss": 0.1755, "step": 136650 }, { - "epoch": 0.61, - "learning_rate": 1.959620644814134e-05, - "loss": 0.1768, + "epoch": 0.31, + "learning_rate": 3.4832554081564174e-05, + "loss": 0.1674, "step": 136660 }, { - "epoch": 0.61, - "learning_rate": 1.9593964396215417e-05, - "loss": 0.1687, + "epoch": 0.31, + "learning_rate": 3.483143553835485e-05, + "loss": 0.1778, "step": 136670 }, { - "epoch": 0.61, - "learning_rate": 1.9591722344289495e-05, - "loss": 0.1702, + "epoch": 0.31, + "learning_rate": 3.483031699514552e-05, + "loss": 0.1695, "step": 136680 }, { - "epoch": 0.61, - "learning_rate": 1.958948029236357e-05, - "loss": 0.1665, + "epoch": 0.31, + "learning_rate": 3.48291984519362e-05, + "loss": 0.1746, "step": 136690 }, { - "epoch": 0.61, - "learning_rate": 1.958723824043765e-05, - "loss": 0.1721, + "epoch": 0.31, + "learning_rate": 3.482807990872687e-05, + "loss": 0.1742, "step": 136700 }, { - "epoch": 0.61, - "learning_rate": 1.9584996188511725e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.482696136551755e-05, + "loss": 0.1698, "step": 136710 }, { - "epoch": 0.61, - "learning_rate": 1.9582754136585803e-05, - "loss": 0.1832, + "epoch": 0.31, + "learning_rate": 3.482584282230823e-05, + "loss": 0.1697, "step": 136720 }, { - "epoch": 0.61, - "learning_rate": 1.9580512084659882e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.4824724279098906e-05, + "loss": 0.1707, "step": 136730 }, { - "epoch": 0.61, - "learning_rate": 1.9578270032733957e-05, - "loss": 0.1778, + "epoch": 0.31, + "learning_rate": 3.4823605735889584e-05, + "loss": 0.1752, "step": 136740 }, { - "epoch": 0.61, - "learning_rate": 1.9576027980808036e-05, - "loss": 0.1719, + "epoch": 0.31, + "learning_rate": 3.4822487192680255e-05, + "loss": 0.1704, "step": 136750 }, { - "epoch": 0.61, - "learning_rate": 1.957378592888211e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.482136864947093e-05, + "loss": 0.1712, "step": 136760 }, { - "epoch": 0.61, - "learning_rate": 1.957154387695619e-05, - "loss": 0.1708, + "epoch": 0.31, + "learning_rate": 3.482025010626161e-05, + "loss": 0.172, "step": 136770 }, { - "epoch": 0.61, - "learning_rate": 1.956930182503027e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.481913156305228e-05, + "loss": 0.1686, "step": 136780 }, { - "epoch": 0.61, - "learning_rate": 1.9567059773104348e-05, - "loss": 0.1759, + "epoch": 0.31, + "learning_rate": 3.481801301984296e-05, + "loss": 0.1665, "step": 136790 }, { - "epoch": 0.61, - "learning_rate": 1.9564817721178423e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.481689447663363e-05, + "loss": 0.1748, "step": 136800 }, { - "epoch": 0.61, - "learning_rate": 1.95625756692525e-05, - "loss": 0.1779, + "epoch": 0.31, + "learning_rate": 3.481577593342431e-05, + "loss": 0.1706, "step": 136810 }, { - "epoch": 0.61, - "learning_rate": 1.956033361732658e-05, - "loss": 0.1815, + "epoch": 0.31, + "learning_rate": 3.481465739021498e-05, + "loss": 0.1734, "step": 136820 }, { - "epoch": 0.61, - "learning_rate": 1.9558091565400656e-05, - "loss": 0.1665, + "epoch": 0.31, + "learning_rate": 3.481353884700566e-05, + "loss": 0.1737, "step": 136830 }, { - "epoch": 0.61, - "learning_rate": 1.9555849513474734e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.481242030379634e-05, + "loss": 0.1688, "step": 136840 }, { - "epoch": 0.61, - "learning_rate": 1.955360746154881e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4811301760587014e-05, + "loss": 0.167, "step": 136850 }, { - "epoch": 0.61, - "learning_rate": 1.955136540962289e-05, - "loss": 0.1767, + "epoch": 0.31, + "learning_rate": 3.481018321737769e-05, + "loss": 0.1694, "step": 136860 }, { - "epoch": 0.61, - "learning_rate": 1.9549123357696967e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.480906467416836e-05, + "loss": 0.1723, "step": 136870 }, { - "epoch": 0.61, - "learning_rate": 1.9546881305771042e-05, - "loss": 0.1772, + "epoch": 0.31, + "learning_rate": 3.480794613095904e-05, + "loss": 0.1678, "step": 136880 }, { - "epoch": 0.61, - "learning_rate": 1.954463925384512e-05, - "loss": 0.1712, + "epoch": 0.31, + "learning_rate": 3.480682758774972e-05, + "loss": 0.1722, "step": 136890 }, { - "epoch": 0.61, - "learning_rate": 1.9542397201919197e-05, - "loss": 0.177, + "epoch": 0.31, + "learning_rate": 3.480570904454039e-05, + "loss": 0.169, "step": 136900 }, { - "epoch": 0.61, - "learning_rate": 1.9540155149993275e-05, - "loss": 0.1775, + "epoch": 0.31, + "learning_rate": 3.480459050133107e-05, + "loss": 0.1684, "step": 136910 }, { - "epoch": 0.61, - "learning_rate": 1.953791309806735e-05, - "loss": 0.178, + "epoch": 0.31, + "learning_rate": 3.480347195812174e-05, + "loss": 0.1623, "step": 136920 }, { - "epoch": 0.61, - "learning_rate": 1.953567104614143e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.480235341491242e-05, + "loss": 0.174, "step": 136930 }, { - "epoch": 0.61, - "learning_rate": 1.9533428994215508e-05, - "loss": 0.1729, + "epoch": 0.31, + "learning_rate": 3.4801234871703095e-05, + "loss": 0.1705, "step": 136940 }, { - "epoch": 0.61, - "learning_rate": 1.9531186942289583e-05, - "loss": 0.1697, + "epoch": 0.31, + "learning_rate": 3.480011632849377e-05, + "loss": 0.1718, "step": 136950 }, { - "epoch": 0.61, - "learning_rate": 1.9528944890363662e-05, - "loss": 0.1767, + "epoch": 0.31, + "learning_rate": 3.479899778528445e-05, + "loss": 0.178, "step": 136960 }, { - "epoch": 0.61, - "learning_rate": 1.9526702838437737e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.479787924207512e-05, + "loss": 0.164, "step": 136970 }, { - "epoch": 0.61, - "learning_rate": 1.9524460786511816e-05, - "loss": 0.1706, + "epoch": 0.31, + "learning_rate": 3.47967606988658e-05, + "loss": 0.1701, "step": 136980 }, { - "epoch": 0.61, - "learning_rate": 1.952221873458589e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.479564215565648e-05, + "loss": 0.1644, "step": 136990 }, { - "epoch": 0.61, - "learning_rate": 1.951997668265997e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.479452361244715e-05, + "loss": 0.1714, "step": 137000 }, { - "epoch": 0.61, - "learning_rate": 1.951773463073405e-05, - "loss": 0.1715, + "epoch": 0.31, + "learning_rate": 3.479340506923783e-05, + "loss": 0.1685, "step": 137010 }, { - "epoch": 0.61, - "learning_rate": 1.9515492578808124e-05, - "loss": 0.1686, + "epoch": 0.31, + "learning_rate": 3.47922865260285e-05, + "loss": 0.1703, "step": 137020 }, { - "epoch": 0.61, - "learning_rate": 1.9513250526882203e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.4791167982819176e-05, + "loss": 0.1717, "step": 137030 }, { - "epoch": 0.61, - "learning_rate": 1.9511008474956278e-05, - "loss": 0.1782, + "epoch": 0.31, + "learning_rate": 3.4790049439609854e-05, + "loss": 0.1683, "step": 137040 }, { - "epoch": 0.61, - "learning_rate": 1.9508766423030357e-05, - "loss": 0.1755, + "epoch": 0.31, + "learning_rate": 3.478893089640053e-05, + "loss": 0.1661, "step": 137050 }, { - "epoch": 0.61, - "learning_rate": 1.9506524371104436e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.478781235319121e-05, + "loss": 0.1693, "step": 137060 }, { - "epoch": 0.61, - "learning_rate": 1.9504282319178514e-05, - "loss": 0.1752, + "epoch": 0.31, + "learning_rate": 3.478669380998188e-05, + "loss": 0.1687, "step": 137070 }, { - "epoch": 0.61, - "learning_rate": 1.9502040267252593e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.478557526677256e-05, + "loss": 0.1731, "step": 137080 }, { - "epoch": 0.61, - "learning_rate": 1.949979821532667e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.478445672356323e-05, + "loss": 0.1734, "step": 137090 }, { - "epoch": 0.61, - "learning_rate": 1.9497556163400747e-05, - "loss": 0.1698, + "epoch": 0.31, + "learning_rate": 3.478333818035391e-05, + "loss": 0.1719, "step": 137100 }, { - "epoch": 0.61, - "learning_rate": 1.9495314111474823e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.4782219637144586e-05, + "loss": 0.1692, "step": 137110 }, { - "epoch": 0.61, - "learning_rate": 1.94930720595489e-05, - "loss": 0.1752, + "epoch": 0.31, + "learning_rate": 3.478110109393526e-05, + "loss": 0.1671, "step": 137120 }, { - "epoch": 0.61, - "learning_rate": 1.949083000762298e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.4779982550725935e-05, + "loss": 0.1728, "step": 137130 }, { - "epoch": 0.61, - "learning_rate": 1.9488587955697055e-05, - "loss": 0.182, + "epoch": 0.31, + "learning_rate": 3.477886400751661e-05, + "loss": 0.1639, "step": 137140 }, { - "epoch": 0.61, - "learning_rate": 1.9486345903771134e-05, - "loss": 0.1721, + "epoch": 0.31, + "learning_rate": 3.477774546430729e-05, + "loss": 0.1692, "step": 137150 }, { - "epoch": 0.61, - "learning_rate": 1.948410385184521e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.477662692109797e-05, + "loss": 0.174, "step": 137160 }, { - "epoch": 0.61, - "learning_rate": 1.9481861799919288e-05, - "loss": 0.1779, + "epoch": 0.31, + "learning_rate": 3.477550837788864e-05, + "loss": 0.1652, "step": 137170 }, { - "epoch": 0.61, - "learning_rate": 1.9479619747993363e-05, - "loss": 0.1768, + "epoch": 0.31, + "learning_rate": 3.477438983467932e-05, + "loss": 0.1674, "step": 137180 }, { - "epoch": 0.61, - "learning_rate": 1.9477377696067442e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.477327129146999e-05, + "loss": 0.1711, "step": 137190 }, { - "epoch": 0.61, - "learning_rate": 1.947513564414152e-05, - "loss": 0.1718, + "epoch": 0.31, + "learning_rate": 3.4772152748260667e-05, + "loss": 0.1605, "step": 137200 }, { - "epoch": 0.61, - "learning_rate": 1.9472893592215596e-05, - "loss": 0.1676, + "epoch": 0.31, + "learning_rate": 3.4771034205051345e-05, + "loss": 0.1695, "step": 137210 }, { - "epoch": 0.61, - "learning_rate": 1.9470651540289675e-05, - "loss": 0.1703, + "epoch": 0.31, + "learning_rate": 3.4769915661842016e-05, + "loss": 0.1649, "step": 137220 }, { - "epoch": 0.61, - "learning_rate": 1.946840948836375e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.4768797118632694e-05, + "loss": 0.1732, "step": 137230 }, { - "epoch": 0.61, - "learning_rate": 1.946616743643783e-05, - "loss": 0.1744, + "epoch": 0.31, + "learning_rate": 3.4767678575423365e-05, + "loss": 0.1728, "step": 137240 }, { - "epoch": 0.61, - "learning_rate": 1.9463925384511904e-05, - "loss": 0.172, + "epoch": 0.31, + "learning_rate": 3.476656003221405e-05, + "loss": 0.174, "step": 137250 }, { - "epoch": 0.61, - "learning_rate": 1.9461683332585983e-05, - "loss": 0.1765, + "epoch": 0.31, + "learning_rate": 3.476544148900473e-05, + "loss": 0.1713, "step": 137260 }, { - "epoch": 0.61, - "learning_rate": 1.945944128066006e-05, - "loss": 0.1702, + "epoch": 0.31, + "learning_rate": 3.47643229457954e-05, + "loss": 0.1665, "step": 137270 }, { - "epoch": 0.61, - "learning_rate": 1.9457199228734137e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.4763204402586076e-05, + "loss": 0.1675, "step": 137280 }, { - "epoch": 0.61, - "learning_rate": 1.9454957176808216e-05, - "loss": 0.1746, + "epoch": 0.31, + "learning_rate": 3.476208585937675e-05, + "loss": 0.1683, "step": 137290 }, { - "epoch": 0.61, - "learning_rate": 1.945271512488229e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.4760967316167426e-05, + "loss": 0.1707, "step": 137300 }, { - "epoch": 0.61, - "learning_rate": 1.945047307295637e-05, - "loss": 0.1756, + "epoch": 0.31, + "learning_rate": 3.4759848772958103e-05, + "loss": 0.1709, "step": 137310 }, { - "epoch": 0.61, - "learning_rate": 1.944823102103045e-05, - "loss": 0.1724, + "epoch": 0.31, + "learning_rate": 3.4758730229748775e-05, + "loss": 0.1679, "step": 137320 }, { - "epoch": 0.61, - "learning_rate": 1.9445988969104527e-05, - "loss": 0.172, + "epoch": 0.31, + "learning_rate": 3.475761168653945e-05, + "loss": 0.1682, "step": 137330 }, { - "epoch": 0.61, - "learning_rate": 1.9443746917178603e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.4756493143330124e-05, + "loss": 0.1679, "step": 137340 }, { - "epoch": 0.61, - "learning_rate": 1.944150486525268e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.47553746001208e-05, + "loss": 0.1685, "step": 137350 }, { - "epoch": 0.61, - "learning_rate": 1.943926281332676e-05, - "loss": 0.1782, + "epoch": 0.31, + "learning_rate": 3.475425605691148e-05, + "loss": 0.1734, "step": 137360 }, { - "epoch": 0.61, - "learning_rate": 1.9437020761400835e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.475313751370216e-05, + "loss": 0.1697, "step": 137370 }, { - "epoch": 0.61, - "learning_rate": 1.9434778709474914e-05, - "loss": 0.1733, + "epoch": 0.31, + "learning_rate": 3.4752018970492835e-05, + "loss": 0.1694, "step": 137380 }, { - "epoch": 0.61, - "learning_rate": 1.943253665754899e-05, - "loss": 0.1762, + "epoch": 0.31, + "learning_rate": 3.4750900427283507e-05, + "loss": 0.1675, "step": 137390 }, { - "epoch": 0.61, - "learning_rate": 1.9430294605623068e-05, - "loss": 0.1703, + "epoch": 0.31, + "learning_rate": 3.4749781884074185e-05, + "loss": 0.1722, "step": 137400 }, { - "epoch": 0.61, - "learning_rate": 1.9428052553697147e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.4748663340864856e-05, + "loss": 0.1676, "step": 137410 }, { - "epoch": 0.61, - "learning_rate": 1.9425810501771222e-05, - "loss": 0.1692, + "epoch": 0.31, + "learning_rate": 3.4747544797655534e-05, + "loss": 0.1639, "step": 137420 }, { - "epoch": 0.61, - "learning_rate": 1.94235684498453e-05, - "loss": 0.1762, + "epoch": 0.31, + "learning_rate": 3.474642625444621e-05, + "loss": 0.1672, "step": 137430 }, { - "epoch": 0.61, - "learning_rate": 1.9421326397919376e-05, - "loss": 0.1786, + "epoch": 0.31, + "learning_rate": 3.474530771123688e-05, + "loss": 0.1695, "step": 137440 }, { - "epoch": 0.61, - "learning_rate": 1.9419084345993455e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.474418916802756e-05, + "loss": 0.1695, "step": 137450 }, { - "epoch": 0.61, - "learning_rate": 1.941684229406753e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.474307062481824e-05, + "loss": 0.1712, "step": 137460 }, { - "epoch": 0.61, - "learning_rate": 1.941460024214161e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.4741952081608916e-05, + "loss": 0.1663, "step": 137470 }, { - "epoch": 0.61, - "learning_rate": 1.9412358190215688e-05, - "loss": 0.175, + "epoch": 0.31, + "learning_rate": 3.4740833538399594e-05, + "loss": 0.1676, "step": 137480 }, { - "epoch": 0.61, - "learning_rate": 1.9410116138289763e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.4739714995190266e-05, + "loss": 0.1668, "step": 137490 }, { - "epoch": 0.61, - "learning_rate": 1.940787408636384e-05, - "loss": 0.1777, + "epoch": 0.31, + "learning_rate": 3.4738596451980943e-05, + "loss": 0.1712, "step": 137500 }, { - "epoch": 0.61, - "learning_rate": 1.9405632034437917e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.4737477908771615e-05, + "loss": 0.1619, "step": 137510 }, { - "epoch": 0.61, - "learning_rate": 1.9403389982511996e-05, - "loss": 0.1728, + "epoch": 0.31, + "learning_rate": 3.473635936556229e-05, + "loss": 0.1686, "step": 137520 }, { - "epoch": 0.61, - "learning_rate": 1.940114793058607e-05, - "loss": 0.1675, + "epoch": 0.31, + "learning_rate": 3.473524082235297e-05, + "loss": 0.1688, "step": 137530 }, { - "epoch": 0.61, - "learning_rate": 1.939890587866015e-05, - "loss": 0.181, + "epoch": 0.31, + "learning_rate": 3.473412227914364e-05, + "loss": 0.1692, "step": 137540 }, { - "epoch": 0.61, - "learning_rate": 1.939666382673423e-05, - "loss": 0.1768, + "epoch": 0.31, + "learning_rate": 3.473300373593432e-05, + "loss": 0.1684, "step": 137550 }, { - "epoch": 0.61, - "learning_rate": 1.9394421774808304e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.4731885192725e-05, + "loss": 0.1702, "step": 137560 }, { - "epoch": 0.61, - "learning_rate": 1.9392179722882383e-05, - "loss": 0.1769, + "epoch": 0.31, + "learning_rate": 3.4730766649515675e-05, + "loss": 0.169, "step": 137570 }, { - "epoch": 0.61, - "learning_rate": 1.9389937670956458e-05, - "loss": 0.1777, + "epoch": 0.31, + "learning_rate": 3.472964810630635e-05, + "loss": 0.1685, "step": 137580 }, { - "epoch": 0.61, - "learning_rate": 1.9387695619030537e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.4728529563097024e-05, + "loss": 0.1575, "step": 137590 }, { - "epoch": 0.61, - "learning_rate": 1.9385453567104615e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.47274110198877e-05, + "loss": 0.1682, "step": 137600 }, { - "epoch": 0.61, - "learning_rate": 1.9383211515178694e-05, - "loss": 0.1773, + "epoch": 0.31, + "learning_rate": 3.4726292476678374e-05, + "loss": 0.1667, "step": 137610 }, { - "epoch": 0.61, - "learning_rate": 1.9380969463252773e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.472517393346905e-05, + "loss": 0.1707, "step": 137620 }, { - "epoch": 0.61, - "learning_rate": 1.9378727411326848e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.472405539025973e-05, + "loss": 0.1652, "step": 137630 }, { - "epoch": 0.61, - "learning_rate": 1.9376485359400927e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.47229368470504e-05, + "loss": 0.164, "step": 137640 }, { - "epoch": 0.61, - "learning_rate": 1.9374243307475002e-05, - "loss": 0.1783, + "epoch": 0.31, + "learning_rate": 3.472181830384108e-05, + "loss": 0.1701, "step": 137650 }, { - "epoch": 0.61, - "learning_rate": 1.937200125554908e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.472069976063175e-05, + "loss": 0.1654, "step": 137660 }, { - "epoch": 0.61, - "learning_rate": 1.9369759203623156e-05, - "loss": 0.1752, + "epoch": 0.31, + "learning_rate": 3.4719581217422434e-05, + "loss": 0.1681, "step": 137670 }, { - "epoch": 0.61, - "learning_rate": 1.9367517151697235e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.471846267421311e-05, + "loss": 0.1611, "step": 137680 }, { - "epoch": 0.61, - "learning_rate": 1.9365275099771314e-05, - "loss": 0.1695, + "epoch": 0.31, + "learning_rate": 3.4717344131003783e-05, + "loss": 0.1683, "step": 137690 }, { - "epoch": 0.61, - "learning_rate": 1.936303304784539e-05, - "loss": 0.1726, + "epoch": 0.31, + "learning_rate": 3.471622558779446e-05, + "loss": 0.167, "step": 137700 }, { - "epoch": 0.61, - "learning_rate": 1.9360790995919468e-05, - "loss": 0.1704, + "epoch": 0.31, + "learning_rate": 3.471510704458513e-05, + "loss": 0.1697, "step": 137710 }, { - "epoch": 0.61, - "learning_rate": 1.9358548943993543e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.471398850137581e-05, + "loss": 0.1689, "step": 137720 }, { - "epoch": 0.61, - "learning_rate": 1.935630689206762e-05, - "loss": 0.1746, + "epoch": 0.31, + "learning_rate": 3.471286995816648e-05, + "loss": 0.1707, "step": 137730 }, { - "epoch": 0.61, - "learning_rate": 1.9354064840141697e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.471175141495716e-05, + "loss": 0.1688, "step": 137740 }, { - "epoch": 0.61, - "learning_rate": 1.9351822788215776e-05, - "loss": 0.1756, + "epoch": 0.31, + "learning_rate": 3.471063287174784e-05, + "loss": 0.1674, "step": 137750 }, { - "epoch": 0.61, - "learning_rate": 1.9349580736289854e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.470951432853851e-05, + "loss": 0.1691, "step": 137760 }, { - "epoch": 0.62, - "learning_rate": 1.934733868436393e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.4708395785329187e-05, + "loss": 0.1619, "step": 137770 }, { - "epoch": 0.62, - "learning_rate": 1.934509663243801e-05, - "loss": 0.1718, + "epoch": 0.31, + "learning_rate": 3.4707277242119864e-05, + "loss": 0.1653, "step": 137780 }, { - "epoch": 0.62, - "learning_rate": 1.9342854580512084e-05, - "loss": 0.1772, + "epoch": 0.31, + "learning_rate": 3.470615869891054e-05, + "loss": 0.1649, "step": 137790 }, { - "epoch": 0.62, - "learning_rate": 1.9340612528586163e-05, - "loss": 0.1647, + "epoch": 0.31, + "learning_rate": 3.470504015570122e-05, + "loss": 0.1671, "step": 137800 }, { - "epoch": 0.62, - "learning_rate": 1.9338370476660238e-05, - "loss": 0.1764, + "epoch": 0.31, + "learning_rate": 3.470392161249189e-05, + "loss": 0.1684, "step": 137810 }, { - "epoch": 0.62, - "learning_rate": 1.9336128424734317e-05, - "loss": 0.1774, + "epoch": 0.31, + "learning_rate": 3.470280306928257e-05, + "loss": 0.1643, "step": 137820 }, { - "epoch": 0.62, - "learning_rate": 1.9333886372808395e-05, - "loss": 0.1707, + "epoch": 0.31, + "learning_rate": 3.470168452607324e-05, + "loss": 0.1717, "step": 137830 }, { - "epoch": 0.62, - "learning_rate": 1.933164432088247e-05, - "loss": 0.1729, + "epoch": 0.31, + "learning_rate": 3.470056598286392e-05, + "loss": 0.1663, "step": 137840 }, { - "epoch": 0.62, - "learning_rate": 1.932940226895655e-05, - "loss": 0.1767, + "epoch": 0.31, + "learning_rate": 3.4699447439654596e-05, + "loss": 0.1675, "step": 137850 }, { - "epoch": 0.62, - "learning_rate": 1.9327160217030628e-05, - "loss": 0.1747, + "epoch": 0.31, + "learning_rate": 3.469832889644527e-05, + "loss": 0.1723, "step": 137860 }, { - "epoch": 0.62, - "learning_rate": 1.9324918165104703e-05, - "loss": 0.1735, + "epoch": 0.31, + "learning_rate": 3.4697210353235945e-05, + "loss": 0.1639, "step": 137870 }, { - "epoch": 0.62, - "learning_rate": 1.9322676113178782e-05, - "loss": 0.1747, + "epoch": 0.31, + "learning_rate": 3.4696091810026623e-05, + "loss": 0.1732, "step": 137880 }, { - "epoch": 0.62, - "learning_rate": 1.932043406125286e-05, - "loss": 0.1694, + "epoch": 0.31, + "learning_rate": 3.46949732668173e-05, + "loss": 0.1674, "step": 137890 }, { - "epoch": 0.62, - "learning_rate": 1.931819200932694e-05, - "loss": 0.1776, + "epoch": 0.31, + "learning_rate": 3.469385472360798e-05, + "loss": 0.1677, "step": 137900 }, { - "epoch": 0.62, - "learning_rate": 1.9315949957401015e-05, - "loss": 0.1806, + "epoch": 0.31, + "learning_rate": 3.469273618039865e-05, + "loss": 0.1694, "step": 137910 }, { - "epoch": 0.62, - "learning_rate": 1.9313707905475094e-05, - "loss": 0.1701, + "epoch": 0.31, + "learning_rate": 3.469161763718933e-05, + "loss": 0.1711, "step": 137920 }, { - "epoch": 0.62, - "learning_rate": 1.931146585354917e-05, - "loss": 0.1761, + "epoch": 0.31, + "learning_rate": 3.469049909398e-05, + "loss": 0.1659, "step": 137930 }, { - "epoch": 0.62, - "learning_rate": 1.9309223801623248e-05, - "loss": 0.1665, + "epoch": 0.31, + "learning_rate": 3.468938055077068e-05, + "loss": 0.1661, "step": 137940 }, { - "epoch": 0.62, - "learning_rate": 1.9306981749697323e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.4688262007561355e-05, + "loss": 0.1675, "step": 137950 }, { - "epoch": 0.62, - "learning_rate": 1.9304739697771402e-05, - "loss": 0.1783, + "epoch": 0.31, + "learning_rate": 3.4687143464352026e-05, + "loss": 0.1701, "step": 137960 }, { - "epoch": 0.62, - "learning_rate": 1.930249764584548e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.4686024921142704e-05, + "loss": 0.17, "step": 137970 }, { - "epoch": 0.62, - "learning_rate": 1.9300255593919556e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.468490637793338e-05, + "loss": 0.1673, "step": 137980 }, { - "epoch": 0.62, - "learning_rate": 1.9298013541993634e-05, - "loss": 0.1757, + "epoch": 0.31, + "learning_rate": 3.468378783472406e-05, + "loss": 0.1711, "step": 137990 }, { - "epoch": 0.62, - "learning_rate": 1.929577149006771e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.468266929151474e-05, + "loss": 0.1709, "step": 138000 }, { - "epoch": 0.62, - "learning_rate": 1.929352943814179e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.468155074830541e-05, + "loss": 0.168, "step": 138010 }, { - "epoch": 0.62, - "learning_rate": 1.9291287386215864e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.468043220509609e-05, + "loss": 0.1652, "step": 138020 }, { - "epoch": 0.62, - "learning_rate": 1.9289045334289943e-05, - "loss": 0.1693, + "epoch": 0.31, + "learning_rate": 3.467931366188676e-05, + "loss": 0.1708, "step": 138030 }, { - "epoch": 0.62, - "learning_rate": 1.928680328236402e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.4678195118677436e-05, + "loss": 0.1682, "step": 138040 }, { - "epoch": 0.62, - "learning_rate": 1.9284561230438097e-05, - "loss": 0.1696, + "epoch": 0.31, + "learning_rate": 3.467707657546811e-05, + "loss": 0.1664, "step": 138050 }, { - "epoch": 0.62, - "learning_rate": 1.9282319178512175e-05, - "loss": 0.1782, + "epoch": 0.31, + "learning_rate": 3.4675958032258785e-05, + "loss": 0.1699, "step": 138060 }, { - "epoch": 0.62, - "learning_rate": 1.928007712658625e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.467483948904946e-05, + "loss": 0.1704, "step": 138070 }, { - "epoch": 0.62, - "learning_rate": 1.927783507466033e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.467372094584014e-05, + "loss": 0.165, "step": 138080 }, { - "epoch": 0.62, - "learning_rate": 1.9275593022734405e-05, - "loss": 0.1715, + "epoch": 0.31, + "learning_rate": 3.467260240263082e-05, + "loss": 0.1743, "step": 138090 }, { - "epoch": 0.62, - "learning_rate": 1.9273350970808483e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.467148385942149e-05, + "loss": 0.1684, "step": 138100 }, { - "epoch": 0.62, - "learning_rate": 1.9271108918882562e-05, - "loss": 0.1703, + "epoch": 0.31, + "learning_rate": 3.467036531621217e-05, + "loss": 0.1661, "step": 138110 }, { - "epoch": 0.62, - "learning_rate": 1.9268866866956637e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.4669246773002846e-05, + "loss": 0.1631, "step": 138120 }, { - "epoch": 0.62, - "learning_rate": 1.9266624815030716e-05, - "loss": 0.1697, + "epoch": 0.31, + "learning_rate": 3.466812822979352e-05, + "loss": 0.1652, "step": 138130 }, { - "epoch": 0.62, - "learning_rate": 1.9264382763104795e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.4667009686584195e-05, + "loss": 0.1633, "step": 138140 }, { - "epoch": 0.62, - "learning_rate": 1.9262140711178874e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.4665891143374866e-05, + "loss": 0.1669, "step": 138150 }, { - "epoch": 0.62, - "learning_rate": 1.925989865925295e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.4664772600165544e-05, + "loss": 0.1663, "step": 138160 }, { - "epoch": 0.62, - "learning_rate": 1.9257656607327028e-05, - "loss": 0.1702, + "epoch": 0.31, + "learning_rate": 3.466365405695622e-05, + "loss": 0.1687, "step": 138170 }, { - "epoch": 0.62, - "learning_rate": 1.9255414555401106e-05, - "loss": 0.1702, + "epoch": 0.31, + "learning_rate": 3.4662535513746893e-05, + "loss": 0.1672, "step": 138180 }, { - "epoch": 0.62, - "learning_rate": 1.9253172503475182e-05, - "loss": 0.1706, + "epoch": 0.31, + "learning_rate": 3.466141697053757e-05, + "loss": 0.1632, "step": 138190 }, { - "epoch": 0.62, - "learning_rate": 1.925093045154926e-05, - "loss": 0.1762, + "epoch": 0.31, + "learning_rate": 3.466029842732825e-05, + "loss": 0.1705, "step": 138200 }, { - "epoch": 0.62, - "learning_rate": 1.9248688399623336e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.465917988411893e-05, + "loss": 0.1672, "step": 138210 }, { - "epoch": 0.62, - "learning_rate": 1.9246670552890007e-05, - "loss": 0.1721, + "epoch": 0.31, + "learning_rate": 3.4658061340909605e-05, + "loss": 0.165, "step": 138220 }, { - "epoch": 0.62, - "learning_rate": 1.9244428500964086e-05, - "loss": 0.1662, + "epoch": 0.31, + "learning_rate": 3.4656942797700276e-05, + "loss": 0.1692, "step": 138230 }, { - "epoch": 0.62, - "learning_rate": 1.924218644903816e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.4655824254490954e-05, + "loss": 0.1716, "step": 138240 }, { - "epoch": 0.62, - "learning_rate": 1.923994439711224e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4654705711281625e-05, + "loss": 0.1637, "step": 138250 }, { - "epoch": 0.62, - "learning_rate": 1.9237702345186315e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.46535871680723e-05, + "loss": 0.1625, "step": 138260 }, { - "epoch": 0.62, - "learning_rate": 1.9235460293260394e-05, - "loss": 0.1663, + "epoch": 0.31, + "learning_rate": 3.465246862486298e-05, + "loss": 0.1641, "step": 138270 }, { - "epoch": 0.62, - "learning_rate": 1.923321824133447e-05, - "loss": 0.1765, + "epoch": 0.31, + "learning_rate": 3.465135008165365e-05, + "loss": 0.1634, "step": 138280 }, { - "epoch": 0.62, - "learning_rate": 1.9230976189408548e-05, - "loss": 0.1759, + "epoch": 0.31, + "learning_rate": 3.465023153844433e-05, + "loss": 0.1644, "step": 138290 }, { - "epoch": 0.62, - "learning_rate": 1.9228734137482627e-05, - "loss": 0.1677, + "epoch": 0.31, + "learning_rate": 3.464911299523501e-05, + "loss": 0.1687, "step": 138300 }, { - "epoch": 0.62, - "learning_rate": 1.9226492085556702e-05, - "loss": 0.1742, + "epoch": 0.31, + "learning_rate": 3.4647994452025686e-05, + "loss": 0.163, "step": 138310 }, { - "epoch": 0.62, - "learning_rate": 1.922425003363078e-05, - "loss": 0.1719, + "epoch": 0.31, + "learning_rate": 3.4646875908816364e-05, + "loss": 0.1673, "step": 138320 }, { - "epoch": 0.62, - "learning_rate": 1.9222007981704856e-05, - "loss": 0.1766, + "epoch": 0.31, + "learning_rate": 3.4645757365607035e-05, + "loss": 0.1677, "step": 138330 }, { - "epoch": 0.62, - "learning_rate": 1.9219765929778935e-05, - "loss": 0.1706, + "epoch": 0.31, + "learning_rate": 3.464463882239771e-05, + "loss": 0.1671, "step": 138340 }, { - "epoch": 0.62, - "learning_rate": 1.921752387785301e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.4643520279188384e-05, + "loss": 0.1674, "step": 138350 }, { - "epoch": 0.62, - "learning_rate": 1.921528182592709e-05, - "loss": 0.1699, + "epoch": 0.31, + "learning_rate": 3.464240173597906e-05, + "loss": 0.1696, "step": 138360 }, { - "epoch": 0.62, - "learning_rate": 1.9213039774001167e-05, - "loss": 0.1708, + "epoch": 0.31, + "learning_rate": 3.4641283192769733e-05, + "loss": 0.1721, "step": 138370 }, { - "epoch": 0.62, - "learning_rate": 1.9210797722075243e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.464016464956041e-05, + "loss": 0.1634, "step": 138380 }, { - "epoch": 0.62, - "learning_rate": 1.920855567014932e-05, - "loss": 0.1685, + "epoch": 0.31, + "learning_rate": 3.463904610635109e-05, + "loss": 0.1653, "step": 138390 }, { - "epoch": 0.62, - "learning_rate": 1.9206313618223397e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.463792756314177e-05, + "loss": 0.1644, "step": 138400 }, { - "epoch": 0.62, - "learning_rate": 1.9204071566297475e-05, - "loss": 0.176, + "epoch": 0.31, + "learning_rate": 3.4636809019932445e-05, + "loss": 0.1642, "step": 138410 }, { - "epoch": 0.62, - "learning_rate": 1.9201829514371554e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.463580233104405e-05, + "loss": 0.1664, "step": 138420 }, { - "epoch": 0.62, - "learning_rate": 1.919958746244563e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.4634683787834725e-05, + "loss": 0.1653, "step": 138430 }, { - "epoch": 0.62, - "learning_rate": 1.9197345410519708e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.4633565244625396e-05, + "loss": 0.166, "step": 138440 }, { - "epoch": 0.62, - "learning_rate": 1.9195103358593787e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.4632446701416074e-05, + "loss": 0.1652, "step": 138450 }, { - "epoch": 0.62, - "learning_rate": 1.9192861306667866e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.463132815820675e-05, + "loss": 0.1703, "step": 138460 }, { - "epoch": 0.62, - "learning_rate": 1.919061925474194e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.463020961499743e-05, + "loss": 0.1707, "step": 138470 }, { - "epoch": 0.62, - "learning_rate": 1.918837720281602e-05, - "loss": 0.1724, + "epoch": 0.31, + "learning_rate": 3.462909107178811e-05, + "loss": 0.1683, "step": 138480 }, { - "epoch": 0.62, - "learning_rate": 1.9186135150890095e-05, - "loss": 0.17, + "epoch": 0.31, + "learning_rate": 3.462797252857878e-05, + "loss": 0.1637, "step": 138490 }, { - "epoch": 0.62, - "learning_rate": 1.9183893098964174e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.462685398536946e-05, + "loss": 0.1649, "step": 138500 }, { - "epoch": 0.62, - "learning_rate": 1.9181651047038252e-05, - "loss": 0.1718, + "epoch": 0.31, + "learning_rate": 3.4625735442160135e-05, + "loss": 0.1627, "step": 138510 }, { - "epoch": 0.62, - "learning_rate": 1.9179408995112328e-05, - "loss": 0.173, + "epoch": 0.31, + "learning_rate": 3.4624616898950806e-05, + "loss": 0.1652, "step": 138520 }, { - "epoch": 0.62, - "learning_rate": 1.9177166943186407e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.4623498355741484e-05, + "loss": 0.1677, "step": 138530 }, { - "epoch": 0.62, - "learning_rate": 1.9174924891260482e-05, - "loss": 0.1744, + "epoch": 0.31, + "learning_rate": 3.4622379812532155e-05, + "loss": 0.1642, "step": 138540 }, { - "epoch": 0.62, - "learning_rate": 1.917268283933456e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.462126126932283e-05, + "loss": 0.1687, "step": 138550 }, { - "epoch": 0.62, - "learning_rate": 1.9170440787408636e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.462014272611351e-05, + "loss": 0.1655, "step": 138560 }, { - "epoch": 0.62, - "learning_rate": 1.9168198735482715e-05, - "loss": 0.1708, + "epoch": 0.31, + "learning_rate": 3.461902418290419e-05, + "loss": 0.1627, "step": 138570 }, { - "epoch": 0.62, - "learning_rate": 1.9165956683556793e-05, - "loss": 0.1756, + "epoch": 0.31, + "learning_rate": 3.461790563969487e-05, + "loss": 0.1605, "step": 138580 }, { - "epoch": 0.62, - "learning_rate": 1.916371463163087e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.461678709648554e-05, + "loss": 0.1676, "step": 138590 }, { - "epoch": 0.62, - "learning_rate": 1.9161472579704947e-05, + "epoch": 0.31, + "learning_rate": 3.4615668553276216e-05, "loss": 0.1687, "step": 138600 }, { - "epoch": 0.62, - "learning_rate": 1.9159230527779023e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.4614550010066894e-05, + "loss": 0.1679, "step": 138610 }, { - "epoch": 0.62, - "learning_rate": 1.91569884758531e-05, - "loss": 0.1799, + "epoch": 0.31, + "learning_rate": 3.4613431466857565e-05, + "loss": 0.1702, "step": 138620 }, { - "epoch": 0.62, - "learning_rate": 1.9154746423927177e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.461231292364824e-05, + "loss": 0.1699, "step": 138630 }, { - "epoch": 0.62, - "learning_rate": 1.9152504372001256e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.4611194380438914e-05, + "loss": 0.1672, "step": 138640 }, { - "epoch": 0.62, - "learning_rate": 1.9150262320075334e-05, - "loss": 0.1745, + "epoch": 0.31, + "learning_rate": 3.461007583722959e-05, + "loss": 0.1664, "step": 138650 }, { - "epoch": 0.62, - "learning_rate": 1.914802026814941e-05, - "loss": 0.1744, + "epoch": 0.31, + "learning_rate": 3.460895729402027e-05, + "loss": 0.1629, "step": 138660 }, { - "epoch": 0.62, - "learning_rate": 1.9145778216223488e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.460783875081095e-05, + "loss": 0.1655, "step": 138670 }, { - "epoch": 0.62, - "learning_rate": 1.9143536164297564e-05, - "loss": 0.1745, + "epoch": 0.31, + "learning_rate": 3.4606720207601626e-05, + "loss": 0.1734, "step": 138680 }, { - "epoch": 0.62, - "learning_rate": 1.9141294112371642e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.46056016643923e-05, + "loss": 0.1682, "step": 138690 }, { - "epoch": 0.62, - "learning_rate": 1.913905206044572e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.4604483121182975e-05, + "loss": 0.1641, "step": 138700 }, { - "epoch": 0.62, - "learning_rate": 1.91368100085198e-05, - "loss": 0.173, + "epoch": 0.31, + "learning_rate": 3.460336457797365e-05, + "loss": 0.166, "step": 138710 }, { - "epoch": 0.62, - "learning_rate": 1.913456795659388e-05, - "loss": 0.1719, + "epoch": 0.31, + "learning_rate": 3.4602246034764324e-05, + "loss": 0.1709, "step": 138720 }, { - "epoch": 0.62, - "learning_rate": 1.9132325904667954e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.4601127491555e-05, + "loss": 0.1659, "step": 138730 }, { - "epoch": 0.62, - "learning_rate": 1.9130083852742033e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.460000894834567e-05, + "loss": 0.1638, "step": 138740 }, { - "epoch": 0.62, - "learning_rate": 1.9127841800816108e-05, - "loss": 0.1668, + "epoch": 0.31, + "learning_rate": 3.459889040513635e-05, + "loss": 0.1663, "step": 138750 }, { - "epoch": 0.62, - "learning_rate": 1.9125599748890187e-05, - "loss": 0.1758, + "epoch": 0.31, + "learning_rate": 3.459777186192702e-05, + "loss": 0.1679, "step": 138760 }, { - "epoch": 0.62, - "learning_rate": 1.9123357696964262e-05, - "loss": 0.173, + "epoch": 0.31, + "learning_rate": 3.45966533187177e-05, + "loss": 0.167, "step": 138770 }, { - "epoch": 0.62, - "learning_rate": 1.912111564503834e-05, - "loss": 0.1784, + "epoch": 0.31, + "learning_rate": 3.4595534775508385e-05, + "loss": 0.1637, "step": 138780 }, { - "epoch": 0.62, - "learning_rate": 1.911887359311242e-05, - "loss": 0.1796, + "epoch": 0.31, + "learning_rate": 3.4594416232299056e-05, + "loss": 0.1662, "step": 138790 }, { - "epoch": 0.62, - "learning_rate": 1.9116631541186495e-05, - "loss": 0.1689, + "epoch": 0.31, + "learning_rate": 3.4593297689089734e-05, + "loss": 0.1697, "step": 138800 }, { - "epoch": 0.62, - "learning_rate": 1.9114389489260573e-05, - "loss": 0.1765, + "epoch": 0.31, + "learning_rate": 3.4592179145880405e-05, + "loss": 0.1643, "step": 138810 }, { - "epoch": 0.62, - "learning_rate": 1.911214743733465e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.459106060267108e-05, + "loss": 0.1659, "step": 138820 }, { - "epoch": 0.62, - "learning_rate": 1.9109905385408727e-05, - "loss": 0.1705, + "epoch": 0.31, + "learning_rate": 3.458994205946176e-05, + "loss": 0.1651, "step": 138830 }, { - "epoch": 0.62, - "learning_rate": 1.9107663333482803e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.458882351625243e-05, + "loss": 0.1673, "step": 138840 }, { - "epoch": 0.62, - "learning_rate": 1.910542128155688e-05, - "loss": 0.1667, + "epoch": 0.31, + "learning_rate": 3.458770497304311e-05, + "loss": 0.1696, "step": 138850 }, { - "epoch": 0.62, - "learning_rate": 1.910317922963096e-05, - "loss": 0.1681, + "epoch": 0.31, + "learning_rate": 3.458658642983378e-05, + "loss": 0.163, "step": 138860 }, { - "epoch": 0.62, - "learning_rate": 1.9100937177705036e-05, - "loss": 0.1758, + "epoch": 0.31, + "learning_rate": 3.458546788662446e-05, + "loss": 0.1608, "step": 138870 }, { - "epoch": 0.62, - "learning_rate": 1.9098695125779114e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.458434934341514e-05, + "loss": 0.1616, "step": 138880 }, { - "epoch": 0.62, - "learning_rate": 1.909645307385319e-05, - "loss": 0.1697, + "epoch": 0.31, + "learning_rate": 3.4583230800205815e-05, + "loss": 0.1632, "step": 138890 }, { - "epoch": 0.62, - "learning_rate": 1.9094211021927268e-05, - "loss": 0.1677, + "epoch": 0.31, + "learning_rate": 3.458211225699649e-05, + "loss": 0.1649, "step": 138900 }, { - "epoch": 0.62, - "learning_rate": 1.9091968970001344e-05, - "loss": 0.1724, + "epoch": 0.31, + "learning_rate": 3.4580993713787164e-05, + "loss": 0.1638, "step": 138910 }, { - "epoch": 0.62, - "learning_rate": 1.9089726918075422e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.457987517057784e-05, + "loss": 0.1684, "step": 138920 }, { - "epoch": 0.62, - "learning_rate": 1.90874848661495e-05, - "loss": 0.1706, + "epoch": 0.31, + "learning_rate": 3.457875662736852e-05, + "loss": 0.1667, "step": 138930 }, { - "epoch": 0.62, - "learning_rate": 1.9085242814223576e-05, - "loss": 0.1756, - "step": 138940 + "epoch": 0.31, + "learning_rate": 3.457763808415919e-05, + "loss": 0.1661, + "step": 138940 }, { - "epoch": 0.62, - "learning_rate": 1.9083000762297655e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.457651954094987e-05, + "loss": 0.1651, "step": 138950 }, { - "epoch": 0.62, - "learning_rate": 1.9080758710371734e-05, - "loss": 0.1761, + "epoch": 0.31, + "learning_rate": 3.457540099774054e-05, + "loss": 0.1664, "step": 138960 }, { - "epoch": 0.62, - "learning_rate": 1.907851665844581e-05, - "loss": 0.1713, + "epoch": 0.31, + "learning_rate": 3.457428245453122e-05, + "loss": 0.1621, "step": 138970 }, { - "epoch": 0.62, - "learning_rate": 1.9076274606519888e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.4573163911321896e-05, + "loss": 0.1691, "step": 138980 }, { - "epoch": 0.62, - "learning_rate": 1.9074032554593967e-05, - "loss": 0.1769, + "epoch": 0.31, + "learning_rate": 3.4572045368112574e-05, + "loss": 0.1667, "step": 138990 }, { - "epoch": 0.62, - "learning_rate": 1.9071790502668045e-05, - "loss": 0.1756, + "epoch": 0.31, + "learning_rate": 3.457092682490325e-05, + "loss": 0.1635, "step": 139000 }, { - "epoch": 0.62, - "learning_rate": 1.906954845074212e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.456980828169392e-05, + "loss": 0.1686, "step": 139010 }, { - "epoch": 0.62, - "learning_rate": 1.90673063988162e-05, - "loss": 0.1701, + "epoch": 0.31, + "learning_rate": 3.45686897384846e-05, + "loss": 0.1656, "step": 139020 }, { - "epoch": 0.62, - "learning_rate": 1.9065064346890275e-05, - "loss": 0.1705, + "epoch": 0.31, + "learning_rate": 3.456757119527528e-05, + "loss": 0.1638, "step": 139030 }, { - "epoch": 0.62, - "learning_rate": 1.9062822294964353e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.456645265206595e-05, + "loss": 0.1706, "step": 139040 }, { - "epoch": 0.62, - "learning_rate": 1.906058024303843e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.456533410885663e-05, + "loss": 0.1711, "step": 139050 }, { - "epoch": 0.62, - "learning_rate": 1.9058338191112507e-05, - "loss": 0.1746, + "epoch": 0.31, + "learning_rate": 3.45642155656473e-05, + "loss": 0.1684, "step": 139060 }, { - "epoch": 0.62, - "learning_rate": 1.9056096139186586e-05, - "loss": 0.177, + "epoch": 0.31, + "learning_rate": 3.456309702243798e-05, + "loss": 0.1662, "step": 139070 }, { - "epoch": 0.62, - "learning_rate": 1.905385408726066e-05, - "loss": 0.1717, + "epoch": 0.31, + "learning_rate": 3.4561978479228655e-05, + "loss": 0.1645, "step": 139080 }, { - "epoch": 0.62, - "learning_rate": 1.905161203533474e-05, - "loss": 0.1678, + "epoch": 0.31, + "learning_rate": 3.456085993601933e-05, + "loss": 0.1657, "step": 139090 }, { - "epoch": 0.62, - "learning_rate": 1.9049369983408816e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.455974139281001e-05, + "loss": 0.162, "step": 139100 }, { - "epoch": 0.62, - "learning_rate": 1.9047127931482894e-05, - "loss": 0.1769, + "epoch": 0.31, + "learning_rate": 3.455862284960068e-05, + "loss": 0.1598, "step": 139110 }, { - "epoch": 0.62, - "learning_rate": 1.904488587955697e-05, - "loss": 0.1679, + "epoch": 0.31, + "learning_rate": 3.455750430639136e-05, + "loss": 0.166, "step": 139120 }, { - "epoch": 0.62, - "learning_rate": 1.9042643827631048e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.455638576318203e-05, + "loss": 0.1674, "step": 139130 }, { - "epoch": 0.62, - "learning_rate": 1.9040401775705127e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.455526721997271e-05, + "loss": 0.1664, "step": 139140 }, { - "epoch": 0.62, - "learning_rate": 1.9038159723779202e-05, - "loss": 0.1707, + "epoch": 0.31, + "learning_rate": 3.455414867676339e-05, + "loss": 0.1698, "step": 139150 }, { - "epoch": 0.62, - "learning_rate": 1.903591767185328e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.455303013355406e-05, + "loss": 0.1655, "step": 139160 }, { - "epoch": 0.62, - "learning_rate": 1.9033675619927356e-05, - "loss": 0.1781, + "epoch": 0.31, + "learning_rate": 3.4551911590344736e-05, + "loss": 0.1651, "step": 139170 }, { - "epoch": 0.62, - "learning_rate": 1.9031433568001435e-05, - "loss": 0.1692, + "epoch": 0.31, + "learning_rate": 3.455079304713541e-05, + "loss": 0.1606, "step": 139180 }, { - "epoch": 0.62, - "learning_rate": 1.902919151607551e-05, - "loss": 0.1694, + "epoch": 0.31, + "learning_rate": 3.4549674503926085e-05, + "loss": 0.1716, "step": 139190 }, { - "epoch": 0.62, - "learning_rate": 1.902694946414959e-05, - "loss": 0.1745, + "epoch": 0.31, + "learning_rate": 3.454855596071677e-05, + "loss": 0.165, "step": 139200 }, { - "epoch": 0.62, - "learning_rate": 1.9024707412223668e-05, - "loss": 0.1747, + "epoch": 0.31, + "learning_rate": 3.454743741750744e-05, + "loss": 0.1602, "step": 139210 }, { - "epoch": 0.62, - "learning_rate": 1.9022465360297743e-05, - "loss": 0.1785, + "epoch": 0.31, + "learning_rate": 3.454631887429812e-05, + "loss": 0.169, "step": 139220 }, { - "epoch": 0.62, - "learning_rate": 1.9020223308371822e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.454520033108879e-05, + "loss": 0.1688, "step": 139230 }, { - "epoch": 0.62, - "learning_rate": 1.90179812564459e-05, - "loss": 0.1729, + "epoch": 0.31, + "learning_rate": 3.454408178787947e-05, + "loss": 0.1683, "step": 139240 }, { - "epoch": 0.62, - "learning_rate": 1.901573920451998e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4542963244670146e-05, + "loss": 0.167, "step": 139250 }, { - "epoch": 0.62, - "learning_rate": 1.9013497152594055e-05, - "loss": 0.1747, + "epoch": 0.31, + "learning_rate": 3.454184470146082e-05, + "loss": 0.1662, "step": 139260 }, { - "epoch": 0.62, - "learning_rate": 1.9011255100668133e-05, - "loss": 0.1776, + "epoch": 0.31, + "learning_rate": 3.4540726158251495e-05, + "loss": 0.1663, "step": 139270 }, { - "epoch": 0.62, - "learning_rate": 1.9009013048742212e-05, - "loss": 0.1667, + "epoch": 0.31, + "learning_rate": 3.4539607615042166e-05, + "loss": 0.1698, "step": 139280 }, { - "epoch": 0.62, - "learning_rate": 1.9006770996816287e-05, - "loss": 0.1733, + "epoch": 0.31, + "learning_rate": 3.4538489071832844e-05, + "loss": 0.1676, "step": 139290 }, { - "epoch": 0.62, - "learning_rate": 1.9004528944890366e-05, - "loss": 0.1748, + "epoch": 0.31, + "learning_rate": 3.453737052862352e-05, + "loss": 0.1661, "step": 139300 }, { - "epoch": 0.62, - "learning_rate": 1.900228689296444e-05, - "loss": 0.1768, + "epoch": 0.31, + "learning_rate": 3.45362519854142e-05, + "loss": 0.1646, "step": 139310 }, { - "epoch": 0.62, - "learning_rate": 1.900004484103852e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.453513344220488e-05, + "loss": 0.1656, "step": 139320 }, { - "epoch": 0.62, - "learning_rate": 1.89978027891126e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.453401489899555e-05, + "loss": 0.1615, "step": 139330 }, { - "epoch": 0.62, - "learning_rate": 1.8995560737186674e-05, - "loss": 0.1718, + "epoch": 0.31, + "learning_rate": 3.453289635578623e-05, + "loss": 0.1712, "step": 139340 }, { - "epoch": 0.62, - "learning_rate": 1.8993318685260753e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.4531777812576905e-05, + "loss": 0.1676, "step": 139350 }, { - "epoch": 0.62, - "learning_rate": 1.899107663333483e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.4530659269367576e-05, + "loss": 0.1669, "step": 139360 }, { - "epoch": 0.62, - "learning_rate": 1.8988834581408907e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4529540726158254e-05, + "loss": 0.1627, "step": 139370 }, { - "epoch": 0.62, - "learning_rate": 1.8986592529482982e-05, - "loss": 0.1712, + "epoch": 0.31, + "learning_rate": 3.4528422182948925e-05, + "loss": 0.1644, "step": 139380 }, { - "epoch": 0.62, - "learning_rate": 1.898435047755706e-05, - "loss": 0.1681, + "epoch": 0.31, + "learning_rate": 3.45273036397396e-05, + "loss": 0.1635, "step": 139390 }, { - "epoch": 0.62, - "learning_rate": 1.898210842563114e-05, - "loss": 0.1687, + "epoch": 0.31, + "learning_rate": 3.452618509653028e-05, + "loss": 0.1661, "step": 139400 }, { - "epoch": 0.62, - "learning_rate": 1.8979866373705215e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.452506655332096e-05, + "loss": 0.1627, "step": 139410 }, { - "epoch": 0.62, - "learning_rate": 1.8977624321779294e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.452394801011164e-05, + "loss": 0.1634, "step": 139420 }, { - "epoch": 0.62, - "learning_rate": 1.897538226985337e-05, - "loss": 0.1701, + "epoch": 0.31, + "learning_rate": 3.452282946690231e-05, + "loss": 0.1682, "step": 139430 }, { - "epoch": 0.62, - "learning_rate": 1.8973140217927448e-05, - "loss": 0.1695, + "epoch": 0.31, + "learning_rate": 3.4521710923692986e-05, + "loss": 0.164, "step": 139440 }, { - "epoch": 0.62, - "learning_rate": 1.8970898166001523e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.452059238048366e-05, + "loss": 0.1617, "step": 139450 }, { - "epoch": 0.62, - "learning_rate": 1.8968656114075602e-05, - "loss": 0.1695, + "epoch": 0.31, + "learning_rate": 3.4519473837274335e-05, + "loss": 0.1665, "step": 139460 }, { - "epoch": 0.62, - "learning_rate": 1.896641406214968e-05, - "loss": 0.1751, + "epoch": 0.31, + "learning_rate": 3.451835529406501e-05, + "loss": 0.159, "step": 139470 }, { - "epoch": 0.62, - "learning_rate": 1.8964172010223756e-05, - "loss": 0.1679, + "epoch": 0.31, + "learning_rate": 3.4517236750855684e-05, + "loss": 0.168, "step": 139480 }, { - "epoch": 0.62, - "learning_rate": 1.8961929958297835e-05, - "loss": 0.1702, + "epoch": 0.31, + "learning_rate": 3.451611820764636e-05, + "loss": 0.1666, "step": 139490 }, { - "epoch": 0.62, - "learning_rate": 1.8959687906371913e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.451499966443704e-05, + "loss": 0.1645, "step": 139500 }, { - "epoch": 0.62, - "learning_rate": 1.895744585444599e-05, - "loss": 0.1735, + "epoch": 0.31, + "learning_rate": 3.451388112122772e-05, + "loss": 0.1632, "step": 139510 }, { - "epoch": 0.62, - "learning_rate": 1.8955203802520067e-05, - "loss": 0.1665, + "epoch": 0.31, + "learning_rate": 3.4512762578018396e-05, + "loss": 0.165, "step": 139520 }, { - "epoch": 0.62, - "learning_rate": 1.8952961750594146e-05, - "loss": 0.1686, + "epoch": 0.31, + "learning_rate": 3.451164403480907e-05, + "loss": 0.1607, "step": 139530 }, { - "epoch": 0.62, - "learning_rate": 1.8950719698668225e-05, - "loss": 0.1703, + "epoch": 0.31, + "learning_rate": 3.4510525491599745e-05, + "loss": 0.1678, "step": 139540 }, { - "epoch": 0.62, - "learning_rate": 1.89484776467423e-05, - "loss": 0.1746, + "epoch": 0.31, + "learning_rate": 3.4509406948390416e-05, + "loss": 0.1679, "step": 139550 }, { - "epoch": 0.62, - "learning_rate": 1.894623559481638e-05, - "loss": 0.1721, + "epoch": 0.31, + "learning_rate": 3.4508288405181094e-05, + "loss": 0.1647, "step": 139560 }, { - "epoch": 0.62, - "learning_rate": 1.8943993542890454e-05, - "loss": 0.1753, + "epoch": 0.31, + "learning_rate": 3.450716986197177e-05, + "loss": 0.1698, "step": 139570 }, { - "epoch": 0.62, - "learning_rate": 1.8941751490964533e-05, - "loss": 0.1776, + "epoch": 0.31, + "learning_rate": 3.450605131876244e-05, + "loss": 0.1682, "step": 139580 }, { - "epoch": 0.62, - "learning_rate": 1.893950943903861e-05, - "loss": 0.1708, + "epoch": 0.31, + "learning_rate": 3.450493277555312e-05, + "loss": 0.1665, "step": 139590 }, { - "epoch": 0.62, - "learning_rate": 1.8937267387112687e-05, - "loss": 0.1751, + "epoch": 0.31, + "learning_rate": 3.450381423234379e-05, + "loss": 0.1665, "step": 139600 }, { - "epoch": 0.62, - "learning_rate": 1.8935025335186766e-05, - "loss": 0.1735, + "epoch": 0.31, + "learning_rate": 3.4502695689134477e-05, + "loss": 0.1661, "step": 139610 }, { - "epoch": 0.62, - "learning_rate": 1.893278328326084e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4501577145925155e-05, + "loss": 0.1618, "step": 139620 }, { - "epoch": 0.62, - "learning_rate": 1.893054123133492e-05, - "loss": 0.1757, + "epoch": 0.31, + "learning_rate": 3.4500458602715826e-05, + "loss": 0.1653, "step": 139630 }, { - "epoch": 0.62, - "learning_rate": 1.8928299179408995e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.4499340059506504e-05, + "loss": 0.1655, "step": 139640 }, { - "epoch": 0.62, - "learning_rate": 1.8926057127483074e-05, - "loss": 0.1694, + "epoch": 0.31, + "learning_rate": 3.4498221516297175e-05, + "loss": 0.1643, "step": 139650 }, { - "epoch": 0.62, - "learning_rate": 1.892381507555715e-05, - "loss": 0.1691, + "epoch": 0.31, + "learning_rate": 3.449710297308785e-05, + "loss": 0.1672, "step": 139660 }, { - "epoch": 0.62, - "learning_rate": 1.8921573023631228e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.449598442987853e-05, + "loss": 0.172, "step": 139670 }, { - "epoch": 0.62, - "learning_rate": 1.8919330971705307e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.44948658866692e-05, + "loss": 0.1675, "step": 139680 }, { - "epoch": 0.62, - "learning_rate": 1.8917088919779382e-05, - "loss": 0.1701, + "epoch": 0.31, + "learning_rate": 3.449374734345988e-05, + "loss": 0.1602, "step": 139690 }, { - "epoch": 0.62, - "learning_rate": 1.891484686785346e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.449262880025055e-05, + "loss": 0.1677, "step": 139700 }, { - "epoch": 0.62, - "learning_rate": 1.8912604815927536e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.449151025704123e-05, + "loss": 0.1614, "step": 139710 }, { - "epoch": 0.62, - "learning_rate": 1.8910362764001615e-05, - "loss": 0.1698, + "epoch": 0.31, + "learning_rate": 3.449039171383191e-05, + "loss": 0.1689, "step": 139720 }, { - "epoch": 0.62, - "learning_rate": 1.890812071207569e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.4489273170622585e-05, + "loss": 0.1622, "step": 139730 }, { - "epoch": 0.62, - "learning_rate": 1.890587866014977e-05, - "loss": 0.176, + "epoch": 0.31, + "learning_rate": 3.448815462741326e-05, + "loss": 0.1653, "step": 139740 }, { - "epoch": 0.62, - "learning_rate": 1.8903636608223847e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.4487036084203934e-05, + "loss": 0.1668, "step": 139750 }, { - "epoch": 0.62, - "learning_rate": 1.8901394556297923e-05, - "loss": 0.1693, + "epoch": 0.31, + "learning_rate": 3.448591754099461e-05, + "loss": 0.1612, "step": 139760 }, { - "epoch": 0.62, - "learning_rate": 1.8899152504372e-05, - "loss": 0.1707, + "epoch": 0.31, + "learning_rate": 3.448479899778528e-05, + "loss": 0.167, "step": 139770 }, { - "epoch": 0.62, - "learning_rate": 1.889691045244608e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.448368045457596e-05, + "loss": 0.1677, "step": 139780 }, { - "epoch": 0.62, - "learning_rate": 1.889466840052016e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.448256191136664e-05, + "loss": 0.165, "step": 139790 }, { - "epoch": 0.62, - "learning_rate": 1.8892426348594234e-05, - "loss": 0.1705, + "epoch": 0.31, + "learning_rate": 3.448144336815731e-05, + "loss": 0.166, "step": 139800 }, { - "epoch": 0.62, - "learning_rate": 1.8890184296668313e-05, - "loss": 0.173, + "epoch": 0.31, + "learning_rate": 3.448032482494799e-05, + "loss": 0.1627, "step": 139810 }, { - "epoch": 0.62, - "learning_rate": 1.8887942244742392e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.4479206281738666e-05, + "loss": 0.164, "step": 139820 }, { - "epoch": 0.62, - "learning_rate": 1.8885700192816467e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.4478087738529344e-05, + "loss": 0.1709, "step": 139830 }, { - "epoch": 0.62, - "learning_rate": 1.8883458140890546e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.447696919532002e-05, + "loss": 0.1645, "step": 139840 }, { - "epoch": 0.62, - "learning_rate": 1.888121608896462e-05, - "loss": 0.1758, + "epoch": 0.31, + "learning_rate": 3.447585065211069e-05, + "loss": 0.1641, "step": 139850 }, { - "epoch": 0.62, - "learning_rate": 1.88789740370387e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.447473210890137e-05, + "loss": 0.1656, "step": 139860 }, { - "epoch": 0.62, - "learning_rate": 1.8876731985112775e-05, - "loss": 0.1746, + "epoch": 0.31, + "learning_rate": 3.447361356569204e-05, + "loss": 0.1678, "step": 139870 }, { - "epoch": 0.62, - "learning_rate": 1.8874489933186854e-05, - "loss": 0.172, + "epoch": 0.31, + "learning_rate": 3.447249502248272e-05, + "loss": 0.1679, "step": 139880 }, { - "epoch": 0.62, - "learning_rate": 1.8872247881260933e-05, - "loss": 0.1769, + "epoch": 0.31, + "learning_rate": 3.44713764792734e-05, + "loss": 0.1621, "step": 139890 }, { - "epoch": 0.62, - "learning_rate": 1.8870005829335008e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.447025793606407e-05, + "loss": 0.1656, "step": 139900 }, { - "epoch": 0.62, - "learning_rate": 1.8867763777409087e-05, - "loss": 0.1698, + "epoch": 0.31, + "learning_rate": 3.446913939285475e-05, + "loss": 0.1645, "step": 139910 }, { - "epoch": 0.62, - "learning_rate": 1.8865521725483162e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.4468020849645425e-05, + "loss": 0.1674, "step": 139920 }, { - "epoch": 0.62, - "learning_rate": 1.886327967355724e-05, - "loss": 0.1669, + "epoch": 0.31, + "learning_rate": 3.44669023064361e-05, + "loss": 0.1645, "step": 139930 }, { - "epoch": 0.62, - "learning_rate": 1.8861037621631316e-05, - "loss": 0.1695, + "epoch": 0.31, + "learning_rate": 3.446578376322678e-05, + "loss": 0.1659, "step": 139940 }, { - "epoch": 0.62, - "learning_rate": 1.8858795569705395e-05, - "loss": 0.1784, + "epoch": 0.31, + "learning_rate": 3.446466522001745e-05, + "loss": 0.1712, "step": 139950 }, { - "epoch": 0.62, - "learning_rate": 1.8856553517779473e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.446354667680813e-05, + "loss": 0.168, "step": 139960 }, { - "epoch": 0.62, - "learning_rate": 1.885431146585355e-05, - "loss": 0.1738, + "epoch": 0.31, + "learning_rate": 3.44624281335988e-05, + "loss": 0.1681, "step": 139970 }, { - "epoch": 0.62, - "learning_rate": 1.8852069413927627e-05, - "loss": 0.1724, + "epoch": 0.31, + "learning_rate": 3.446130959038948e-05, + "loss": 0.1652, "step": 139980 }, { - "epoch": 0.62, - "learning_rate": 1.8849827362001703e-05, - "loss": 0.1735, + "epoch": 0.31, + "learning_rate": 3.446019104718015e-05, + "loss": 0.1662, "step": 139990 }, { - "epoch": 0.62, - "learning_rate": 1.884758531007578e-05, - "loss": 0.1776, + "epoch": 0.31, + "learning_rate": 3.445907250397083e-05, + "loss": 0.1643, "step": 140000 }, { - "epoch": 0.63, - "learning_rate": 1.8845343258149857e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.4457953960761506e-05, + "loss": 0.1626, "step": 140010 }, { - "epoch": 0.63, - "learning_rate": 1.8843101206223936e-05, - "loss": 0.1715, + "epoch": 0.31, + "learning_rate": 3.445683541755218e-05, + "loss": 0.1668, "step": 140020 }, { - "epoch": 0.63, - "learning_rate": 1.8840859154298014e-05, - "loss": 0.1704, + "epoch": 0.31, + "learning_rate": 3.445571687434286e-05, + "loss": 0.1657, "step": 140030 }, { - "epoch": 0.63, - "learning_rate": 1.8838617102372093e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.445459833113353e-05, + "loss": 0.1643, "step": 140040 }, { - "epoch": 0.63, - "learning_rate": 1.883637505044617e-05, - "loss": 0.1679, + "epoch": 0.31, + "learning_rate": 3.445347978792421e-05, + "loss": 0.1623, "step": 140050 }, { - "epoch": 0.63, - "learning_rate": 1.8834132998520247e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.445236124471489e-05, + "loss": 0.1638, "step": 140060 }, { - "epoch": 0.63, - "learning_rate": 1.8831890946594326e-05, - "loss": 0.1679, + "epoch": 0.31, + "learning_rate": 3.445124270150556e-05, + "loss": 0.1693, "step": 140070 }, { - "epoch": 0.63, - "learning_rate": 1.88296488946684e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.445012415829624e-05, + "loss": 0.1678, "step": 140080 }, { - "epoch": 0.63, - "learning_rate": 1.882740684274248e-05, - "loss": 0.17, + "epoch": 0.31, + "learning_rate": 3.444900561508691e-05, + "loss": 0.1669, "step": 140090 }, { - "epoch": 0.63, - "learning_rate": 1.882516479081656e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.444788707187759e-05, + "loss": 0.1667, "step": 140100 }, { - "epoch": 0.63, - "learning_rate": 1.8822922738890634e-05, - "loss": 0.1758, + "epoch": 0.31, + "learning_rate": 3.4446768528668265e-05, + "loss": 0.1679, "step": 140110 }, { - "epoch": 0.63, - "learning_rate": 1.8820680686964713e-05, - "loss": 0.1705, + "epoch": 0.31, + "learning_rate": 3.4445649985458936e-05, + "loss": 0.162, "step": 140120 }, { - "epoch": 0.63, - "learning_rate": 1.8818438635038788e-05, - "loss": 0.1699, + "epoch": 0.31, + "learning_rate": 3.4444531442249614e-05, + "loss": 0.1613, "step": 140130 }, { - "epoch": 0.63, - "learning_rate": 1.8816196583112867e-05, - "loss": 0.1742, + "epoch": 0.31, + "learning_rate": 3.444341289904029e-05, + "loss": 0.1669, "step": 140140 }, { - "epoch": 0.63, - "learning_rate": 1.8813954531186942e-05, - "loss": 0.1733, + "epoch": 0.31, + "learning_rate": 3.444229435583097e-05, + "loss": 0.1636, "step": 140150 }, { - "epoch": 0.63, - "learning_rate": 1.881171247926102e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.444117581262165e-05, + "loss": 0.1616, "step": 140160 }, { - "epoch": 0.63, - "learning_rate": 1.88094704273351e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.444005726941232e-05, + "loss": 0.1651, "step": 140170 }, { - "epoch": 0.63, - "learning_rate": 1.8807228375409175e-05, - "loss": 0.1727, + "epoch": 0.31, + "learning_rate": 3.4438938726202996e-05, + "loss": 0.1632, "step": 140180 }, { - "epoch": 0.63, - "learning_rate": 1.8804986323483253e-05, - "loss": 0.1751, + "epoch": 0.31, + "learning_rate": 3.443782018299367e-05, + "loss": 0.1683, "step": 140190 }, { - "epoch": 0.63, - "learning_rate": 1.880274427155733e-05, - "loss": 0.1712, + "epoch": 0.31, + "learning_rate": 3.4436701639784346e-05, + "loss": 0.1682, "step": 140200 }, { - "epoch": 0.63, - "learning_rate": 1.8800502219631408e-05, - "loss": 0.1714, + "epoch": 0.31, + "learning_rate": 3.4435583096575024e-05, + "loss": 0.1607, "step": 140210 }, { - "epoch": 0.63, - "learning_rate": 1.8798260167705483e-05, - "loss": 0.1649, + "epoch": 0.31, + "learning_rate": 3.4434464553365695e-05, + "loss": 0.1648, "step": 140220 }, { - "epoch": 0.63, - "learning_rate": 1.879601811577956e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.443334601015637e-05, + "loss": 0.1602, "step": 140230 }, { - "epoch": 0.63, - "learning_rate": 1.879377606385364e-05, - "loss": 0.1743, + "epoch": 0.31, + "learning_rate": 3.443222746694705e-05, + "loss": 0.161, "step": 140240 }, { - "epoch": 0.63, - "learning_rate": 1.8791534011927716e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.443110892373773e-05, + "loss": 0.1603, "step": 140250 }, { - "epoch": 0.63, - "learning_rate": 1.8789291960001794e-05, - "loss": 0.1675, + "epoch": 0.31, + "learning_rate": 3.4429990380528406e-05, + "loss": 0.167, "step": 140260 }, { - "epoch": 0.63, - "learning_rate": 1.878704990807587e-05, - "loss": 0.1698, + "epoch": 0.31, + "learning_rate": 3.442887183731908e-05, + "loss": 0.1632, "step": 140270 }, { - "epoch": 0.63, - "learning_rate": 1.878480785614995e-05, - "loss": 0.1626, + "epoch": 0.31, + "learning_rate": 3.4427753294109755e-05, + "loss": 0.1663, "step": 140280 }, { - "epoch": 0.63, - "learning_rate": 1.8782565804224027e-05, - "loss": 0.1631, + "epoch": 0.31, + "learning_rate": 3.4426634750900427e-05, + "loss": 0.1644, "step": 140290 }, { - "epoch": 0.63, - "learning_rate": 1.8780323752298102e-05, - "loss": 0.1753, + "epoch": 0.31, + "learning_rate": 3.4425516207691105e-05, + "loss": 0.1674, "step": 140300 }, { - "epoch": 0.63, - "learning_rate": 1.877808170037218e-05, - "loss": 0.1691, + "epoch": 0.31, + "learning_rate": 3.4424397664481776e-05, + "loss": 0.1632, "step": 140310 }, { - "epoch": 0.63, - "learning_rate": 1.877583964844626e-05, - "loss": 0.1752, + "epoch": 0.31, + "learning_rate": 3.4423279121272454e-05, + "loss": 0.1572, "step": 140320 }, { - "epoch": 0.63, - "learning_rate": 1.877359759652034e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.442216057806313e-05, + "loss": 0.1654, "step": 140330 }, { - "epoch": 0.63, - "learning_rate": 1.8771355544594414e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.442104203485381e-05, + "loss": 0.1661, "step": 140340 }, { - "epoch": 0.63, - "learning_rate": 1.8769113492668493e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.441992349164449e-05, + "loss": 0.1643, "step": 140350 }, { - "epoch": 0.63, - "learning_rate": 1.8766871440742568e-05, - "loss": 0.1684, + "epoch": 0.31, + "learning_rate": 3.441880494843516e-05, + "loss": 0.1683, "step": 140360 }, { - "epoch": 0.63, - "learning_rate": 1.8764629388816647e-05, - "loss": 0.167, + "epoch": 0.31, + "learning_rate": 3.4417686405225836e-05, + "loss": 0.1627, "step": 140370 }, { - "epoch": 0.63, - "learning_rate": 1.8762387336890725e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.4416567862016514e-05, + "loss": 0.1632, "step": 140380 }, { - "epoch": 0.63, - "learning_rate": 1.87601452849648e-05, - "loss": 0.1749, + "epoch": 0.31, + "learning_rate": 3.4415449318807186e-05, + "loss": 0.1657, "step": 140390 }, { - "epoch": 0.63, - "learning_rate": 1.875790323303888e-05, - "loss": 0.171, + "epoch": 0.31, + "learning_rate": 3.4414330775597863e-05, + "loss": 0.1583, "step": 140400 }, { - "epoch": 0.63, - "learning_rate": 1.8755661181112955e-05, - "loss": 0.1729, + "epoch": 0.31, + "learning_rate": 3.4413212232388535e-05, + "loss": 0.1629, "step": 140410 }, { - "epoch": 0.63, - "learning_rate": 1.8753419129187033e-05, - "loss": 0.1739, + "epoch": 0.31, + "learning_rate": 3.441209368917921e-05, + "loss": 0.1675, "step": 140420 }, { - "epoch": 0.63, - "learning_rate": 1.875117707726111e-05, - "loss": 0.1691, + "epoch": 0.31, + "learning_rate": 3.441097514596989e-05, + "loss": 0.1658, "step": 140430 }, { - "epoch": 0.63, - "learning_rate": 1.8748935025335188e-05, - "loss": 0.17, + "epoch": 0.31, + "learning_rate": 3.440985660276057e-05, + "loss": 0.1666, "step": 140440 }, { - "epoch": 0.63, - "learning_rate": 1.8746692973409266e-05, - "loss": 0.1731, + "epoch": 0.31, + "learning_rate": 3.4408738059551246e-05, + "loss": 0.1634, "step": 140450 }, { - "epoch": 0.63, - "learning_rate": 1.874445092148334e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.440761951634192e-05, + "loss": 0.1656, "step": 140460 }, { - "epoch": 0.63, - "learning_rate": 1.874220886955742e-05, - "loss": 0.1705, + "epoch": 0.31, + "learning_rate": 3.4406500973132595e-05, + "loss": 0.1599, "step": 140470 }, { - "epoch": 0.63, - "learning_rate": 1.8739966817631496e-05, - "loss": 0.1744, + "epoch": 0.31, + "learning_rate": 3.440538242992327e-05, + "loss": 0.1636, "step": 140480 }, { - "epoch": 0.63, - "learning_rate": 1.8737724765705574e-05, - "loss": 0.1733, + "epoch": 0.31, + "learning_rate": 3.4404375741034875e-05, + "loss": 0.1646, "step": 140490 }, { - "epoch": 0.63, - "learning_rate": 1.873548271377965e-05, - "loss": 0.1758, + "epoch": 0.31, + "learning_rate": 3.440325719782555e-05, + "loss": 0.1632, "step": 140500 }, { - "epoch": 0.63, - "learning_rate": 1.873324066185373e-05, - "loss": 0.1699, + "epoch": 0.31, + "learning_rate": 3.440213865461623e-05, + "loss": 0.1637, "step": 140510 }, { - "epoch": 0.63, - "learning_rate": 1.8730998609927807e-05, - "loss": 0.1715, + "epoch": 0.31, + "learning_rate": 3.440102011140691e-05, + "loss": 0.1675, "step": 140520 }, { - "epoch": 0.63, - "learning_rate": 1.8728756558001882e-05, - "loss": 0.1698, + "epoch": 0.31, + "learning_rate": 3.439990156819758e-05, + "loss": 0.1659, "step": 140530 }, { - "epoch": 0.63, - "learning_rate": 1.872651450607596e-05, - "loss": 0.174, + "epoch": 0.31, + "learning_rate": 3.439878302498826e-05, + "loss": 0.1633, "step": 140540 }, { - "epoch": 0.63, - "learning_rate": 1.8724272454150036e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.4397664481778936e-05, + "loss": 0.1609, "step": 140550 }, { - "epoch": 0.63, - "learning_rate": 1.8722030402224115e-05, - "loss": 0.1735, + "epoch": 0.31, + "learning_rate": 3.439654593856961e-05, + "loss": 0.1615, "step": 140560 }, { - "epoch": 0.63, - "learning_rate": 1.8719788350298194e-05, - "loss": 0.1753, + "epoch": 0.31, + "learning_rate": 3.4395427395360285e-05, + "loss": 0.165, "step": 140570 }, { - "epoch": 0.63, - "learning_rate": 1.8717546298372273e-05, - "loss": 0.1728, + "epoch": 0.31, + "learning_rate": 3.4394308852150956e-05, + "loss": 0.1639, "step": 140580 }, { - "epoch": 0.63, - "learning_rate": 1.8715304246446348e-05, - "loss": 0.168, + "epoch": 0.31, + "learning_rate": 3.4393190308941634e-05, + "loss": 0.1612, "step": 140590 }, { - "epoch": 0.63, - "learning_rate": 1.8713062194520427e-05, - "loss": 0.1752, + "epoch": 0.31, + "learning_rate": 3.439207176573231e-05, + "loss": 0.1663, "step": 140600 }, { - "epoch": 0.63, - "learning_rate": 1.8710820142594505e-05, - "loss": 0.1734, + "epoch": 0.31, + "learning_rate": 3.439095322252299e-05, + "loss": 0.1665, "step": 140610 }, { - "epoch": 0.63, - "learning_rate": 1.870857809066858e-05, - "loss": 0.1755, + "epoch": 0.31, + "learning_rate": 3.438983467931367e-05, + "loss": 0.167, "step": 140620 }, { - "epoch": 0.63, - "learning_rate": 1.870633603874266e-05, - "loss": 0.1732, + "epoch": 0.31, + "learning_rate": 3.438871613610434e-05, + "loss": 0.1623, "step": 140630 }, { - "epoch": 0.63, - "learning_rate": 1.8704093986816735e-05, - "loss": 0.1771, + "epoch": 0.31, + "learning_rate": 3.438759759289502e-05, + "loss": 0.1704, "step": 140640 }, { - "epoch": 0.63, - "learning_rate": 1.8701851934890813e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.4386479049685695e-05, + "loss": 0.1674, "step": 140650 }, { - "epoch": 0.63, - "learning_rate": 1.8699609882964892e-05, - "loss": 0.167, + "epoch": 0.31, + "learning_rate": 3.4385360506476366e-05, + "loss": 0.166, "step": 140660 }, { - "epoch": 0.63, - "learning_rate": 1.8697367831038968e-05, - "loss": 0.1648, + "epoch": 0.31, + "learning_rate": 3.4384241963267044e-05, + "loss": 0.1621, "step": 140670 }, { - "epoch": 0.63, - "learning_rate": 1.8695125779113046e-05, - "loss": 0.166, + "epoch": 0.31, + "learning_rate": 3.4383123420057715e-05, + "loss": 0.1694, "step": 140680 }, { - "epoch": 0.63, - "learning_rate": 1.869288372718712e-05, - "loss": 0.1722, + "epoch": 0.31, + "learning_rate": 3.438200487684839e-05, + "loss": 0.1644, "step": 140690 }, { - "epoch": 0.63, - "learning_rate": 1.86906416752612e-05, - "loss": 0.1682, + "epoch": 0.31, + "learning_rate": 3.4380886333639064e-05, + "loss": 0.1614, "step": 140700 }, { - "epoch": 0.63, - "learning_rate": 1.868839962333528e-05, - "loss": 0.167, + "epoch": 0.31, + "learning_rate": 3.437976779042974e-05, + "loss": 0.1646, "step": 140710 }, { - "epoch": 0.63, - "learning_rate": 1.8686157571409354e-05, - "loss": 0.1646, + "epoch": 0.31, + "learning_rate": 3.437864924722042e-05, + "loss": 0.1623, "step": 140720 }, { - "epoch": 0.63, - "learning_rate": 1.8683915519483433e-05, - "loss": 0.1678, + "epoch": 0.31, + "learning_rate": 3.43775307040111e-05, + "loss": 0.1668, "step": 140730 }, { - "epoch": 0.63, - "learning_rate": 1.868167346755751e-05, - "loss": 0.1745, + "epoch": 0.31, + "learning_rate": 3.4376412160801776e-05, + "loss": 0.164, "step": 140740 }, { - "epoch": 0.63, - "learning_rate": 1.8679431415631587e-05, - "loss": 0.1697, + "epoch": 0.31, + "learning_rate": 3.437529361759245e-05, + "loss": 0.1576, "step": 140750 }, { - "epoch": 0.63, - "learning_rate": 1.8677189363705662e-05, - "loss": 0.1713, + "epoch": 0.31, + "learning_rate": 3.4374175074383125e-05, + "loss": 0.1635, "step": 140760 }, { - "epoch": 0.63, - "learning_rate": 1.867494731177974e-05, - "loss": 0.1753, + "epoch": 0.31, + "learning_rate": 3.43730565311738e-05, + "loss": 0.1698, "step": 140770 }, { - "epoch": 0.63, - "learning_rate": 1.867270525985382e-05, - "loss": 0.1711, + "epoch": 0.31, + "learning_rate": 3.4371937987964474e-05, + "loss": 0.1655, "step": 140780 }, { - "epoch": 0.63, - "learning_rate": 1.8670463207927895e-05, - "loss": 0.1736, + "epoch": 0.31, + "learning_rate": 3.437081944475515e-05, + "loss": 0.1609, "step": 140790 }, { - "epoch": 0.63, - "learning_rate": 1.8668221156001974e-05, - "loss": 0.1664, + "epoch": 0.31, + "learning_rate": 3.436970090154582e-05, + "loss": 0.1618, "step": 140800 }, { - "epoch": 0.63, - "learning_rate": 1.866597910407605e-05, - "loss": 0.1696, + "epoch": 0.31, + "learning_rate": 3.43685823583365e-05, + "loss": 0.1615, "step": 140810 }, { - "epoch": 0.63, - "learning_rate": 1.8663737052150128e-05, - "loss": 0.1747, + "epoch": 0.31, + "learning_rate": 3.436746381512718e-05, + "loss": 0.162, "step": 140820 }, { - "epoch": 0.63, - "learning_rate": 1.8661495000224207e-05, - "loss": 0.1716, + "epoch": 0.31, + "learning_rate": 3.436634527191786e-05, + "loss": 0.1612, "step": 140830 }, { - "epoch": 0.63, - "learning_rate": 1.8659252948298282e-05, - "loss": 0.1703, + "epoch": 0.31, + "learning_rate": 3.4365226728708535e-05, + "loss": 0.1622, "step": 140840 }, { - "epoch": 0.63, - "learning_rate": 1.865701089637236e-05, - "loss": 0.1704, + "epoch": 0.31, + "learning_rate": 3.4364108185499206e-05, + "loss": 0.1673, "step": 140850 }, { - "epoch": 0.63, - "learning_rate": 1.865476884444644e-05, - "loss": 0.1671, + "epoch": 0.31, + "learning_rate": 3.4362989642289884e-05, + "loss": 0.1635, "step": 140860 }, { - "epoch": 0.63, - "learning_rate": 1.8652526792520518e-05, - "loss": 0.173, + "epoch": 0.31, + "learning_rate": 3.436187109908056e-05, + "loss": 0.1658, "step": 140870 }, { - "epoch": 0.63, - "learning_rate": 1.8650284740594594e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.436075255587123e-05, + "loss": 0.1646, "step": 140880 }, { - "epoch": 0.63, - "learning_rate": 1.8648042688668672e-05, - "loss": 0.1671, + "epoch": 0.31, + "learning_rate": 3.435963401266191e-05, + "loss": 0.17, "step": 140890 }, { - "epoch": 0.63, - "learning_rate": 1.8645800636742748e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.435851546945258e-05, + "loss": 0.1642, "step": 140900 }, { - "epoch": 0.63, - "learning_rate": 1.8643558584816826e-05, - "loss": 0.1729, + "epoch": 0.31, + "learning_rate": 3.435739692624326e-05, + "loss": 0.1651, "step": 140910 }, { - "epoch": 0.63, - "learning_rate": 1.8641316532890905e-05, - "loss": 0.18, + "epoch": 0.31, + "learning_rate": 3.435627838303394e-05, + "loss": 0.1631, "step": 140920 }, { - "epoch": 0.63, - "learning_rate": 1.863907448096498e-05, - "loss": 0.1778, + "epoch": 0.31, + "learning_rate": 3.4355159839824616e-05, + "loss": 0.1651, "step": 140930 }, { - "epoch": 0.63, - "learning_rate": 1.863683242903906e-05, - "loss": 0.1741, + "epoch": 0.31, + "learning_rate": 3.4354041296615294e-05, + "loss": 0.1651, "step": 140940 }, { - "epoch": 0.63, - "learning_rate": 1.8634590377113134e-05, - "loss": 0.1768, + "epoch": 0.31, + "learning_rate": 3.4352922753405965e-05, + "loss": 0.1642, "step": 140950 }, { - "epoch": 0.63, - "learning_rate": 1.8632348325187213e-05, - "loss": 0.1737, + "epoch": 0.31, + "learning_rate": 3.435180421019664e-05, + "loss": 0.1644, "step": 140960 }, { - "epoch": 0.63, - "learning_rate": 1.863010627326129e-05, - "loss": 0.1691, + "epoch": 0.31, + "learning_rate": 3.435068566698732e-05, + "loss": 0.1651, "step": 140970 }, { - "epoch": 0.63, - "learning_rate": 1.8627864221335367e-05, - "loss": 0.1617, + "epoch": 0.31, + "learning_rate": 3.434956712377799e-05, + "loss": 0.1613, "step": 140980 }, { - "epoch": 0.63, - "learning_rate": 1.8625622169409446e-05, - "loss": 0.1754, + "epoch": 0.31, + "learning_rate": 3.434844858056867e-05, + "loss": 0.165, "step": 140990 }, { - "epoch": 0.63, - "learning_rate": 1.862338011748352e-05, - "loss": 0.1688, + "epoch": 0.31, + "learning_rate": 3.434733003735934e-05, + "loss": 0.1643, "step": 141000 }, { - "epoch": 0.63, - "learning_rate": 1.86211380655576e-05, - "loss": 0.1674, + "epoch": 0.31, + "learning_rate": 3.434621149415002e-05, + "loss": 0.1636, "step": 141010 }, { - "epoch": 0.63, - "learning_rate": 1.8618896013631675e-05, - "loss": 0.1697, + "epoch": 0.31, + "learning_rate": 3.43450929509407e-05, + "loss": 0.1618, "step": 141020 }, { - "epoch": 0.63, - "learning_rate": 1.8616653961705754e-05, - "loss": 0.1674, + "epoch": 0.31, + "learning_rate": 3.4343974407731375e-05, + "loss": 0.1642, "step": 141030 }, { - "epoch": 0.63, - "learning_rate": 1.861441190977983e-05, - "loss": 0.1715, + "epoch": 0.31, + "learning_rate": 3.434285586452205e-05, + "loss": 0.168, "step": 141040 }, { - "epoch": 0.63, - "learning_rate": 1.8612169857853908e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.4341737321312724e-05, + "loss": 0.1654, "step": 141050 }, { - "epoch": 0.63, - "learning_rate": 1.8609927805927987e-05, - "loss": 0.1723, + "epoch": 0.31, + "learning_rate": 3.43406187781034e-05, + "loss": 0.1696, "step": 141060 }, { - "epoch": 0.63, - "learning_rate": 1.8607685754002062e-05, - "loss": 0.1691, + "epoch": 0.31, + "learning_rate": 3.433950023489407e-05, + "loss": 0.1638, "step": 141070 }, { - "epoch": 0.63, - "learning_rate": 1.860544370207614e-05, - "loss": 0.1658, + "epoch": 0.31, + "learning_rate": 3.433838169168475e-05, + "loss": 0.1612, "step": 141080 }, { - "epoch": 0.63, - "learning_rate": 1.8603201650150216e-05, - "loss": 0.1694, + "epoch": 0.31, + "learning_rate": 3.433726314847543e-05, + "loss": 0.1657, "step": 141090 }, { - "epoch": 0.63, - "learning_rate": 1.8600959598224295e-05, - "loss": 0.1709, + "epoch": 0.31, + "learning_rate": 3.43361446052661e-05, + "loss": 0.1631, "step": 141100 }, { - "epoch": 0.63, - "learning_rate": 1.8598717546298374e-05, - "loss": 0.1725, + "epoch": 0.31, + "learning_rate": 3.433502606205678e-05, + "loss": 0.1622, "step": 141110 }, { - "epoch": 0.63, - "learning_rate": 1.8596475494372452e-05, - "loss": 0.1745, + "epoch": 0.31, + "learning_rate": 3.433390751884745e-05, + "loss": 0.1619, "step": 141120 }, { - "epoch": 0.63, - "learning_rate": 1.8594233442446528e-05, - "loss": 0.1762, + "epoch": 0.32, + "learning_rate": 3.433278897563813e-05, + "loss": 0.168, "step": 141130 }, { - "epoch": 0.63, - "learning_rate": 1.8591991390520606e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.433167043242881e-05, + "loss": 0.1624, "step": 141140 }, { - "epoch": 0.63, - "learning_rate": 1.8589749338594685e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.433055188921948e-05, + "loss": 0.1663, "step": 141150 }, { - "epoch": 0.63, - "learning_rate": 1.8587731491861353e-05, - "loss": 0.1782, + "epoch": 0.32, + "learning_rate": 3.432943334601016e-05, + "loss": 0.1703, "step": 141160 }, { - "epoch": 0.63, - "learning_rate": 1.858548943993543e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.432831480280083e-05, + "loss": 0.1638, "step": 141170 }, { - "epoch": 0.63, - "learning_rate": 1.8583247388009507e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.432719625959151e-05, + "loss": 0.1685, "step": 141180 }, { - "epoch": 0.63, - "learning_rate": 1.8581005336083586e-05, - "loss": 0.1696, + "epoch": 0.32, + "learning_rate": 3.432607771638219e-05, + "loss": 0.166, "step": 141190 }, { - "epoch": 0.63, - "learning_rate": 1.8578763284157664e-05, - "loss": 0.172, + "epoch": 0.32, + "learning_rate": 3.432495917317286e-05, + "loss": 0.1661, "step": 141200 }, { - "epoch": 0.63, - "learning_rate": 1.857652123223174e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.432384062996354e-05, + "loss": 0.164, "step": 141210 }, { - "epoch": 0.63, - "learning_rate": 1.857427918030582e-05, - "loss": 0.1719, + "epoch": 0.32, + "learning_rate": 3.432272208675421e-05, + "loss": 0.1684, "step": 141220 }, { - "epoch": 0.63, - "learning_rate": 1.8572037128379894e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.4321603543544886e-05, + "loss": 0.1647, "step": 141230 }, { - "epoch": 0.63, - "learning_rate": 1.8569795076453972e-05, - "loss": 0.1767, + "epoch": 0.32, + "learning_rate": 3.4320485000335564e-05, + "loss": 0.1624, "step": 141240 }, { - "epoch": 0.63, - "learning_rate": 1.8567553024528048e-05, - "loss": 0.1721, + "epoch": 0.32, + "learning_rate": 3.431936645712624e-05, + "loss": 0.1605, "step": 141250 }, { - "epoch": 0.63, - "learning_rate": 1.8565310972602126e-05, - "loss": 0.1759, + "epoch": 0.32, + "learning_rate": 3.431824791391692e-05, + "loss": 0.1634, "step": 141260 }, { - "epoch": 0.63, - "learning_rate": 1.8563068920676205e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.431712937070759e-05, + "loss": 0.1669, "step": 141270 }, { - "epoch": 0.63, - "learning_rate": 1.856082686875028e-05, - "loss": 0.1739, + "epoch": 0.32, + "learning_rate": 3.431601082749827e-05, + "loss": 0.1619, "step": 141280 }, { - "epoch": 0.63, - "learning_rate": 1.855858481682436e-05, - "loss": 0.1716, + "epoch": 0.32, + "learning_rate": 3.431489228428895e-05, + "loss": 0.1653, "step": 141290 }, { - "epoch": 0.63, - "learning_rate": 1.8556342764898435e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.431377374107962e-05, + "loss": 0.162, "step": 141300 }, { - "epoch": 0.63, - "learning_rate": 1.8554100712972513e-05, - "loss": 0.1754, + "epoch": 0.32, + "learning_rate": 3.4312655197870296e-05, + "loss": 0.167, "step": 141310 }, { - "epoch": 0.63, - "learning_rate": 1.855185866104659e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.431153665466097e-05, + "loss": 0.1623, "step": 141320 }, { - "epoch": 0.63, - "learning_rate": 1.8549616609120667e-05, - "loss": 0.163, + "epoch": 0.32, + "learning_rate": 3.4310418111451645e-05, + "loss": 0.1625, "step": 141330 }, { - "epoch": 0.63, - "learning_rate": 1.8547374557194746e-05, - "loss": 0.1786, + "epoch": 0.32, + "learning_rate": 3.430929956824232e-05, + "loss": 0.1607, "step": 141340 }, { - "epoch": 0.63, - "learning_rate": 1.854513250526882e-05, - "loss": 0.1781, + "epoch": 0.32, + "learning_rate": 3.4308181025033e-05, + "loss": 0.1653, "step": 141350 }, { - "epoch": 0.63, - "learning_rate": 1.85428904533429e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.430706248182368e-05, + "loss": 0.1625, "step": 141360 }, { - "epoch": 0.63, - "learning_rate": 1.8540648401416975e-05, - "loss": 0.1766, + "epoch": 0.32, + "learning_rate": 3.430594393861435e-05, + "loss": 0.1687, "step": 141370 }, { - "epoch": 0.63, - "learning_rate": 1.8538406349491054e-05, - "loss": 0.1726, + "epoch": 0.32, + "learning_rate": 3.430482539540503e-05, + "loss": 0.1675, "step": 141380 }, { - "epoch": 0.63, - "learning_rate": 1.8536164297565133e-05, - "loss": 0.1679, + "epoch": 0.32, + "learning_rate": 3.43037068521957e-05, + "loss": 0.1621, "step": 141390 }, { - "epoch": 0.63, - "learning_rate": 1.8533922245639208e-05, - "loss": 0.171, + "epoch": 0.32, + "learning_rate": 3.430258830898638e-05, + "loss": 0.1645, "step": 141400 }, { - "epoch": 0.63, - "learning_rate": 1.8531680193713287e-05, - "loss": 0.174, + "epoch": 0.32, + "learning_rate": 3.4301469765777055e-05, + "loss": 0.1633, "step": 141410 }, { - "epoch": 0.63, - "learning_rate": 1.8529438141787366e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.4300351222567726e-05, + "loss": 0.1658, "step": 141420 }, { - "epoch": 0.63, - "learning_rate": 1.8527196089861444e-05, - "loss": 0.1691, + "epoch": 0.32, + "learning_rate": 3.4299232679358404e-05, + "loss": 0.1696, "step": 141430 }, { - "epoch": 0.63, - "learning_rate": 1.852495403793552e-05, - "loss": 0.172, + "epoch": 0.32, + "learning_rate": 3.429811413614908e-05, + "loss": 0.161, "step": 141440 }, { - "epoch": 0.63, - "learning_rate": 1.85227119860096e-05, - "loss": 0.1695, + "epoch": 0.32, + "learning_rate": 3.429699559293976e-05, + "loss": 0.1696, "step": 141450 }, { - "epoch": 0.63, - "learning_rate": 1.8520469934083674e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.429587704973044e-05, + "loss": 0.1667, "step": 141460 }, { - "epoch": 0.63, - "learning_rate": 1.8518227882157752e-05, - "loss": 0.1714, + "epoch": 0.32, + "learning_rate": 3.429475850652111e-05, + "loss": 0.1662, "step": 141470 }, { - "epoch": 0.63, - "learning_rate": 1.851598583023183e-05, - "loss": 0.1771, + "epoch": 0.32, + "learning_rate": 3.429363996331179e-05, + "loss": 0.1681, "step": 141480 }, { - "epoch": 0.63, - "learning_rate": 1.8513743778305906e-05, + "epoch": 0.32, + "learning_rate": 3.429252142010246e-05, "loss": 0.1674, "step": 141490 }, { - "epoch": 0.63, - "learning_rate": 1.8511501726379985e-05, - "loss": 0.1715, - "step": 141500 + "epoch": 0.32, + "learning_rate": 3.4291402876893136e-05, + "loss": 0.1606, + "step": 141500 }, { - "epoch": 0.63, - "learning_rate": 1.850925967445406e-05, - "loss": 0.1668, + "epoch": 0.32, + "learning_rate": 3.4290284333683814e-05, + "loss": 0.1663, "step": 141510 }, { - "epoch": 0.63, - "learning_rate": 1.850701762252814e-05, - "loss": 0.1683, + "epoch": 0.32, + "learning_rate": 3.4289165790474485e-05, + "loss": 0.1604, "step": 141520 }, { - "epoch": 0.63, - "learning_rate": 1.8504775570602215e-05, - "loss": 0.1738, + "epoch": 0.32, + "learning_rate": 3.428804724726516e-05, + "loss": 0.1686, "step": 141530 }, { - "epoch": 0.63, - "learning_rate": 1.8502533518676293e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.4286928704055834e-05, + "loss": 0.1639, "step": 141540 }, { - "epoch": 0.63, - "learning_rate": 1.8500291466750372e-05, - "loss": 0.1703, + "epoch": 0.32, + "learning_rate": 3.428581016084651e-05, + "loss": 0.1625, "step": 141550 }, { - "epoch": 0.63, - "learning_rate": 1.8498049414824447e-05, - "loss": 0.1776, + "epoch": 0.32, + "learning_rate": 3.42846916176372e-05, + "loss": 0.1631, "step": 141560 }, { - "epoch": 0.63, - "learning_rate": 1.8495807362898526e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.428357307442787e-05, + "loss": 0.1674, "step": 141570 }, { - "epoch": 0.63, - "learning_rate": 1.84935653109726e-05, + "epoch": 0.32, + "learning_rate": 3.4282454531218546e-05, "loss": 0.1685, "step": 141580 }, { - "epoch": 0.63, - "learning_rate": 1.849132325904668e-05, - "loss": 0.1634, + "epoch": 0.32, + "learning_rate": 3.428133598800922e-05, + "loss": 0.1647, "step": 141590 }, { - "epoch": 0.63, - "learning_rate": 1.8489081207120755e-05, - "loss": 0.1735, + "epoch": 0.32, + "learning_rate": 3.4280217444799895e-05, + "loss": 0.1621, "step": 141600 }, { - "epoch": 0.63, - "learning_rate": 1.8486839155194834e-05, - "loss": 0.1735, + "epoch": 0.32, + "learning_rate": 3.427909890159057e-05, + "loss": 0.1603, "step": 141610 }, { - "epoch": 0.63, - "learning_rate": 1.8484597103268913e-05, - "loss": 0.1744, + "epoch": 0.32, + "learning_rate": 3.4277980358381244e-05, + "loss": 0.159, "step": 141620 }, { - "epoch": 0.63, - "learning_rate": 1.8482355051342988e-05, - "loss": 0.1662, + "epoch": 0.32, + "learning_rate": 3.427686181517192e-05, + "loss": 0.1628, "step": 141630 }, { - "epoch": 0.63, - "learning_rate": 1.8480112999417067e-05, - "loss": 0.1743, + "epoch": 0.32, + "learning_rate": 3.427574327196259e-05, + "loss": 0.1629, "step": 141640 }, { - "epoch": 0.63, - "learning_rate": 1.8477870947491142e-05, - "loss": 0.1678, + "epoch": 0.32, + "learning_rate": 3.427462472875327e-05, + "loss": 0.1602, "step": 141650 }, { - "epoch": 0.63, - "learning_rate": 1.847562889556522e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.427350618554395e-05, + "loss": 0.1697, "step": 141660 }, { - "epoch": 0.63, - "learning_rate": 1.84733868436393e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.427238764233463e-05, + "loss": 0.1642, "step": 141670 }, { - "epoch": 0.63, - "learning_rate": 1.847114479171338e-05, - "loss": 0.1771, + "epoch": 0.32, + "learning_rate": 3.4271269099125305e-05, + "loss": 0.1655, "step": 141680 }, { - "epoch": 0.63, - "learning_rate": 1.8468902739787454e-05, - "loss": 0.1743, + "epoch": 0.32, + "learning_rate": 3.4270150555915976e-05, + "loss": 0.1611, "step": 141690 }, { - "epoch": 0.63, - "learning_rate": 1.8466660687861532e-05, - "loss": 0.1775, + "epoch": 0.32, + "learning_rate": 3.4269032012706654e-05, + "loss": 0.1608, "step": 141700 }, { - "epoch": 0.63, - "learning_rate": 1.846441863593561e-05, - "loss": 0.1735, + "epoch": 0.32, + "learning_rate": 3.4267913469497325e-05, + "loss": 0.1619, "step": 141710 }, { - "epoch": 0.63, - "learning_rate": 1.8462176584009686e-05, - "loss": 0.1722, + "epoch": 0.32, + "learning_rate": 3.4266794926288e-05, + "loss": 0.1674, "step": 141720 }, { - "epoch": 0.63, - "learning_rate": 1.8459934532083765e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.426567638307868e-05, + "loss": 0.1652, "step": 141730 }, { - "epoch": 0.63, - "learning_rate": 1.8457692480157844e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.426455783986935e-05, + "loss": 0.1616, "step": 141740 }, { - "epoch": 0.63, - "learning_rate": 1.845545042823192e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.426343929666003e-05, + "loss": 0.1629, "step": 141750 }, { - "epoch": 0.63, - "learning_rate": 1.8453208376305998e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.426232075345071e-05, + "loss": 0.1639, "step": 141760 }, { - "epoch": 0.63, - "learning_rate": 1.8450966324380073e-05, - "loss": 0.1733, + "epoch": 0.32, + "learning_rate": 3.4261202210241386e-05, + "loss": 0.1673, "step": 141770 }, { - "epoch": 0.63, - "learning_rate": 1.8448724272454152e-05, - "loss": 0.1652, + "epoch": 0.32, + "learning_rate": 3.4260083667032064e-05, + "loss": 0.1634, "step": 141780 }, { - "epoch": 0.63, - "learning_rate": 1.8446482220528227e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.4258965123822735e-05, + "loss": 0.1657, "step": 141790 }, { - "epoch": 0.63, - "learning_rate": 1.8444240168602306e-05, - "loss": 0.1675, + "epoch": 0.32, + "learning_rate": 3.425784658061341e-05, + "loss": 0.1634, "step": 141800 }, { - "epoch": 0.63, - "learning_rate": 1.8441998116676385e-05, - "loss": 0.1713, + "epoch": 0.32, + "learning_rate": 3.4256728037404084e-05, + "loss": 0.1613, "step": 141810 }, { - "epoch": 0.63, - "learning_rate": 1.843975606475046e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.425560949419476e-05, + "loss": 0.1638, "step": 141820 }, { - "epoch": 0.63, - "learning_rate": 1.843751401282454e-05, - "loss": 0.1753, + "epoch": 0.32, + "learning_rate": 3.425449095098544e-05, + "loss": 0.1604, "step": 141830 }, { - "epoch": 0.63, - "learning_rate": 1.8435271960898614e-05, - "loss": 0.1614, + "epoch": 0.32, + "learning_rate": 3.425337240777611e-05, + "loss": 0.1692, "step": 141840 }, { - "epoch": 0.63, - "learning_rate": 1.8433029908972693e-05, - "loss": 0.1755, + "epoch": 0.32, + "learning_rate": 3.425225386456679e-05, + "loss": 0.1612, "step": 141850 }, { - "epoch": 0.63, - "learning_rate": 1.8430787857046768e-05, - "loss": 0.1777, + "epoch": 0.32, + "learning_rate": 3.425113532135747e-05, + "loss": 0.1696, "step": 141860 }, { - "epoch": 0.63, - "learning_rate": 1.8428545805120847e-05, - "loss": 0.1724, + "epoch": 0.32, + "learning_rate": 3.4250016778148145e-05, + "loss": 0.1678, "step": 141870 }, { - "epoch": 0.63, - "learning_rate": 1.8426303753194926e-05, - "loss": 0.1625, + "epoch": 0.32, + "learning_rate": 3.424889823493882e-05, + "loss": 0.1637, "step": 141880 }, { - "epoch": 0.63, - "learning_rate": 1.8424061701269e-05, - "loss": 0.1734, + "epoch": 0.32, + "learning_rate": 3.4247779691729494e-05, + "loss": 0.1678, "step": 141890 }, { - "epoch": 0.63, - "learning_rate": 1.842181964934308e-05, - "loss": 0.1711, + "epoch": 0.32, + "learning_rate": 3.424666114852017e-05, + "loss": 0.1669, "step": 141900 }, { - "epoch": 0.63, - "learning_rate": 1.8419577597417155e-05, - "loss": 0.1737, + "epoch": 0.32, + "learning_rate": 3.424554260531084e-05, + "loss": 0.1644, "step": 141910 }, { - "epoch": 0.63, - "learning_rate": 1.8417335545491234e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.424442406210152e-05, + "loss": 0.1613, "step": 141920 }, { - "epoch": 0.63, - "learning_rate": 1.8415093493565312e-05, - "loss": 0.1694, + "epoch": 0.32, + "learning_rate": 3.42433055188922e-05, + "loss": 0.1654, "step": 141930 }, { - "epoch": 0.63, - "learning_rate": 1.8412851441639388e-05, - "loss": 0.1672, + "epoch": 0.32, + "learning_rate": 3.424218697568287e-05, + "loss": 0.1636, "step": 141940 }, { - "epoch": 0.63, - "learning_rate": 1.8410609389713466e-05, - "loss": 0.1713, + "epoch": 0.32, + "learning_rate": 3.424106843247355e-05, + "loss": 0.1603, "step": 141950 }, { - "epoch": 0.63, - "learning_rate": 1.8408367337787545e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.423994988926422e-05, + "loss": 0.1651, "step": 141960 }, { - "epoch": 0.63, - "learning_rate": 1.8406125285861624e-05, - "loss": 0.1734, + "epoch": 0.32, + "learning_rate": 3.4238831346054904e-05, + "loss": 0.1602, "step": 141970 }, { - "epoch": 0.63, - "learning_rate": 1.84038832339357e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.4237712802845575e-05, + "loss": 0.1637, "step": 141980 }, { - "epoch": 0.63, - "learning_rate": 1.8401641182009778e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.423659425963625e-05, + "loss": 0.1647, "step": 141990 }, { - "epoch": 0.63, - "learning_rate": 1.8399399130083853e-05, - "loss": 0.1656, + "epoch": 0.32, + "learning_rate": 3.423547571642693e-05, + "loss": 0.162, "step": 142000 }, { - "epoch": 0.63, - "learning_rate": 1.8397157078157932e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.42343571732176e-05, + "loss": 0.1671, "step": 142010 }, { - "epoch": 0.63, - "learning_rate": 1.839491502623201e-05, - "loss": 0.1667, + "epoch": 0.32, + "learning_rate": 3.423323863000828e-05, + "loss": 0.1688, "step": 142020 }, { - "epoch": 0.63, - "learning_rate": 1.8392672974306086e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.423212008679895e-05, + "loss": 0.1595, "step": 142030 }, { - "epoch": 0.63, - "learning_rate": 1.8390430922380165e-05, - "loss": 0.1677, + "epoch": 0.32, + "learning_rate": 3.423100154358963e-05, + "loss": 0.1623, "step": 142040 }, { - "epoch": 0.63, - "learning_rate": 1.838818887045424e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.422988300038031e-05, + "loss": 0.1553, "step": 142050 }, { - "epoch": 0.63, - "learning_rate": 1.838594681852832e-05, - "loss": 0.1694, + "epoch": 0.32, + "learning_rate": 3.422876445717098e-05, + "loss": 0.1636, "step": 142060 }, { - "epoch": 0.63, - "learning_rate": 1.8383704766602394e-05, - "loss": 0.1685, + "epoch": 0.32, + "learning_rate": 3.4227645913961656e-05, + "loss": 0.169, "step": 142070 }, { - "epoch": 0.63, - "learning_rate": 1.8381462714676473e-05, - "loss": 0.1747, + "epoch": 0.32, + "learning_rate": 3.4226527370752334e-05, + "loss": 0.1657, "step": 142080 }, { - "epoch": 0.63, - "learning_rate": 1.837922066275055e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.422540882754301e-05, + "loss": 0.1677, "step": 142090 }, { - "epoch": 0.63, - "learning_rate": 1.8376978610824627e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.422429028433369e-05, + "loss": 0.166, "step": 142100 }, { - "epoch": 0.63, - "learning_rate": 1.8374736558898706e-05, - "loss": 0.168, + "epoch": 0.32, + "learning_rate": 3.422317174112436e-05, + "loss": 0.1632, "step": 142110 }, { - "epoch": 0.63, - "learning_rate": 1.837249450697278e-05, - "loss": 0.1741, + "epoch": 0.32, + "learning_rate": 3.422205319791504e-05, + "loss": 0.1651, "step": 142120 }, { - "epoch": 0.63, - "learning_rate": 1.837025245504686e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.422093465470571e-05, + "loss": 0.1662, "step": 142130 }, { - "epoch": 0.63, - "learning_rate": 1.8368010403120935e-05, - "loss": 0.1758, + "epoch": 0.32, + "learning_rate": 3.421981611149639e-05, + "loss": 0.1645, "step": 142140 }, { - "epoch": 0.63, - "learning_rate": 1.8365768351195014e-05, - "loss": 0.1757, + "epoch": 0.32, + "learning_rate": 3.4218697568287066e-05, + "loss": 0.1654, "step": 142150 }, { - "epoch": 0.63, - "learning_rate": 1.8363526299269092e-05, - "loss": 0.1664, + "epoch": 0.32, + "learning_rate": 3.421757902507774e-05, + "loss": 0.1624, "step": 142160 }, { - "epoch": 0.63, - "learning_rate": 1.8361284247343168e-05, - "loss": 0.1718, + "epoch": 0.32, + "learning_rate": 3.4216460481868415e-05, + "loss": 0.1595, "step": 142170 }, { - "epoch": 0.63, - "learning_rate": 1.8359042195417246e-05, - "loss": 0.1683, + "epoch": 0.32, + "learning_rate": 3.421534193865909e-05, + "loss": 0.1585, "step": 142180 }, { - "epoch": 0.63, - "learning_rate": 1.8356800143491322e-05, - "loss": 0.1616, + "epoch": 0.32, + "learning_rate": 3.421422339544977e-05, + "loss": 0.1636, "step": 142190 }, { - "epoch": 0.63, - "learning_rate": 1.83545580915654e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.421310485224045e-05, + "loss": 0.1654, "step": 142200 }, { - "epoch": 0.63, - "learning_rate": 1.835231603963948e-05, - "loss": 0.1724, + "epoch": 0.32, + "learning_rate": 3.421198630903112e-05, + "loss": 0.1595, "step": 142210 }, { - "epoch": 0.63, - "learning_rate": 1.8350073987713558e-05, - "loss": 0.1707, + "epoch": 0.32, + "learning_rate": 3.42108677658218e-05, + "loss": 0.1635, "step": 142220 }, { - "epoch": 0.63, - "learning_rate": 1.8347831935787633e-05, - "loss": 0.1746, + "epoch": 0.32, + "learning_rate": 3.420974922261247e-05, + "loss": 0.1608, "step": 142230 }, { - "epoch": 0.63, - "learning_rate": 1.8345589883861712e-05, - "loss": 0.1685, + "epoch": 0.32, + "learning_rate": 3.420863067940315e-05, + "loss": 0.1608, "step": 142240 }, { - "epoch": 0.64, - "learning_rate": 1.834334783193579e-05, - "loss": 0.1744, + "epoch": 0.32, + "learning_rate": 3.4207512136193825e-05, + "loss": 0.1661, "step": 142250 }, { - "epoch": 0.64, - "learning_rate": 1.8341105780009866e-05, - "loss": 0.1739, + "epoch": 0.32, + "learning_rate": 3.4206393592984496e-05, + "loss": 0.1617, "step": 142260 }, { - "epoch": 0.64, - "learning_rate": 1.8338863728083945e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.4205275049775174e-05, + "loss": 0.1616, "step": 142270 }, { - "epoch": 0.64, - "learning_rate": 1.833662167615802e-05, - "loss": 0.1737, + "epoch": 0.32, + "learning_rate": 3.420415650656585e-05, + "loss": 0.1631, "step": 142280 }, { - "epoch": 0.64, - "learning_rate": 1.83343796242321e-05, - "loss": 0.1743, + "epoch": 0.32, + "learning_rate": 3.420303796335653e-05, + "loss": 0.1657, "step": 142290 }, { - "epoch": 0.64, - "learning_rate": 1.8332137572306178e-05, - "loss": 0.1623, + "epoch": 0.32, + "learning_rate": 3.42019194201472e-05, + "loss": 0.1649, "step": 142300 }, { - "epoch": 0.64, - "learning_rate": 1.8329895520380253e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.420080087693788e-05, + "loss": 0.166, "step": 142310 }, { - "epoch": 0.64, - "learning_rate": 1.832765346845433e-05, - "loss": 0.1681, + "epoch": 0.32, + "learning_rate": 3.419968233372856e-05, + "loss": 0.1608, "step": 142320 }, { - "epoch": 0.64, - "learning_rate": 1.8325411416528407e-05, - "loss": 0.1672, + "epoch": 0.32, + "learning_rate": 3.419856379051923e-05, + "loss": 0.1668, "step": 142330 }, { - "epoch": 0.64, - "learning_rate": 1.8323169364602486e-05, - "loss": 0.1713, + "epoch": 0.32, + "learning_rate": 3.4197445247309906e-05, + "loss": 0.1654, "step": 142340 }, { - "epoch": 0.64, - "learning_rate": 1.832092731267656e-05, - "loss": 0.1638, + "epoch": 0.32, + "learning_rate": 3.419632670410058e-05, + "loss": 0.1701, "step": 142350 }, { - "epoch": 0.64, - "learning_rate": 1.831868526075064e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.4195208160891255e-05, + "loss": 0.163, "step": 142360 }, { - "epoch": 0.64, - "learning_rate": 1.831644320882472e-05, - "loss": 0.1734, + "epoch": 0.32, + "learning_rate": 3.419408961768193e-05, + "loss": 0.1632, "step": 142370 }, { - "epoch": 0.64, - "learning_rate": 1.8314201156898794e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.419297107447261e-05, + "loss": 0.1696, "step": 142380 }, { - "epoch": 0.64, - "learning_rate": 1.8311959104972872e-05, - "loss": 0.1649, + "epoch": 0.32, + "learning_rate": 3.419185253126329e-05, + "loss": 0.1623, "step": 142390 }, { - "epoch": 0.64, - "learning_rate": 1.8309717053046948e-05, - "loss": 0.1672, + "epoch": 0.32, + "learning_rate": 3.419073398805396e-05, + "loss": 0.1604, "step": 142400 }, { - "epoch": 0.64, - "learning_rate": 1.8307475001121027e-05, - "loss": 0.1639, + "epoch": 0.32, + "learning_rate": 3.418961544484464e-05, + "loss": 0.1612, "step": 142410 }, { - "epoch": 0.64, - "learning_rate": 1.8305232949195102e-05, - "loss": 0.1722, + "epoch": 0.32, + "learning_rate": 3.4188496901635316e-05, + "loss": 0.1649, "step": 142420 }, { - "epoch": 0.64, - "learning_rate": 1.830299089726918e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.418737835842599e-05, + "loss": 0.1581, "step": 142430 }, { - "epoch": 0.64, - "learning_rate": 1.830074884534326e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.4186259815216665e-05, + "loss": 0.1659, "step": 142440 }, { - "epoch": 0.64, - "learning_rate": 1.8298506793417335e-05, - "loss": 0.1648, + "epoch": 0.32, + "learning_rate": 3.4185141272007336e-05, + "loss": 0.1653, "step": 142450 }, { - "epoch": 0.64, - "learning_rate": 1.8296264741491413e-05, - "loss": 0.1684, + "epoch": 0.32, + "learning_rate": 3.4184022728798014e-05, + "loss": 0.1587, "step": 142460 }, { - "epoch": 0.64, - "learning_rate": 1.8294022689565492e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.418290418558869e-05, + "loss": 0.1642, "step": 142470 }, { - "epoch": 0.64, - "learning_rate": 1.8291780637639567e-05, - "loss": 0.1709, + "epoch": 0.32, + "learning_rate": 3.418178564237936e-05, + "loss": 0.1633, "step": 142480 }, { - "epoch": 0.64, - "learning_rate": 1.8289538585713646e-05, - "loss": 0.168, + "epoch": 0.32, + "learning_rate": 3.418066709917004e-05, + "loss": 0.1662, "step": 142490 }, { - "epoch": 0.64, - "learning_rate": 1.8287296533787725e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.417954855596072e-05, + "loss": 0.1614, "step": 142500 }, { - "epoch": 0.64, - "learning_rate": 1.8285054481861804e-05, - "loss": 0.1691, + "epoch": 0.32, + "learning_rate": 3.4178430012751397e-05, + "loss": 0.1639, "step": 142510 }, { - "epoch": 0.64, - "learning_rate": 1.828281242993588e-05, - "loss": 0.174, + "epoch": 0.32, + "learning_rate": 3.4177311469542075e-05, + "loss": 0.164, "step": 142520 }, { - "epoch": 0.64, - "learning_rate": 1.8280570378009958e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.4176192926332746e-05, + "loss": 0.1658, "step": 142530 }, { - "epoch": 0.64, - "learning_rate": 1.8278328326084033e-05, - "loss": 0.1666, + "epoch": 0.32, + "learning_rate": 3.4175074383123424e-05, + "loss": 0.1652, "step": 142540 }, { - "epoch": 0.64, - "learning_rate": 1.827608627415811e-05, - "loss": 0.1709, + "epoch": 0.32, + "learning_rate": 3.4173955839914095e-05, + "loss": 0.1635, "step": 142550 }, { - "epoch": 0.64, - "learning_rate": 1.8273844222232187e-05, - "loss": 0.1754, + "epoch": 0.32, + "learning_rate": 3.417283729670477e-05, + "loss": 0.1621, "step": 142560 }, { - "epoch": 0.64, - "learning_rate": 1.8271602170306266e-05, - "loss": 0.1734, + "epoch": 0.32, + "learning_rate": 3.417171875349545e-05, + "loss": 0.1652, "step": 142570 }, { - "epoch": 0.64, - "learning_rate": 1.8269360118380344e-05, - "loss": 0.1799, + "epoch": 0.32, + "learning_rate": 3.417060021028612e-05, + "loss": 0.1678, "step": 142580 }, { - "epoch": 0.64, - "learning_rate": 1.826711806645442e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.416959352139774e-05, + "loss": 0.1653, "step": 142590 }, { - "epoch": 0.64, - "learning_rate": 1.82648760145285e-05, - "loss": 0.176, + "epoch": 0.32, + "learning_rate": 3.416847497818841e-05, + "loss": 0.1644, "step": 142600 }, { - "epoch": 0.64, - "learning_rate": 1.8262633962602574e-05, - "loss": 0.1751, + "epoch": 0.32, + "learning_rate": 3.4167356434979086e-05, + "loss": 0.1683, "step": 142610 }, { - "epoch": 0.64, - "learning_rate": 1.8260391910676652e-05, - "loss": 0.1734, + "epoch": 0.32, + "learning_rate": 3.416623789176976e-05, + "loss": 0.1611, "step": 142620 }, { - "epoch": 0.64, - "learning_rate": 1.8258149858750728e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.4165119348560435e-05, + "loss": 0.1642, "step": 142630 }, { - "epoch": 0.64, - "learning_rate": 1.8255907806824807e-05, - "loss": 0.1728, + "epoch": 0.32, + "learning_rate": 3.416400080535111e-05, + "loss": 0.1646, "step": 142640 }, { - "epoch": 0.64, - "learning_rate": 1.8253665754898885e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.4162882262141785e-05, + "loss": 0.1677, "step": 142650 }, { - "epoch": 0.64, - "learning_rate": 1.825142370297296e-05, - "loss": 0.1638, + "epoch": 0.32, + "learning_rate": 3.416176371893246e-05, + "loss": 0.1678, "step": 142660 }, { - "epoch": 0.64, - "learning_rate": 1.824918165104704e-05, - "loss": 0.1748, + "epoch": 0.32, + "learning_rate": 3.416064517572314e-05, + "loss": 0.1646, "step": 142670 }, { - "epoch": 0.64, - "learning_rate": 1.8246939599121115e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.415952663251382e-05, + "loss": 0.1622, "step": 142680 }, { - "epoch": 0.64, - "learning_rate": 1.8244697547195193e-05, - "loss": 0.176, + "epoch": 0.32, + "learning_rate": 3.415840808930449e-05, + "loss": 0.173, "step": 142690 }, { - "epoch": 0.64, - "learning_rate": 1.824245549526927e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.415728954609517e-05, + "loss": 0.1629, "step": 142700 }, { - "epoch": 0.64, - "learning_rate": 1.8240213443343347e-05, - "loss": 0.1693, + "epoch": 0.32, + "learning_rate": 3.4156171002885845e-05, + "loss": 0.1583, "step": 142710 }, { - "epoch": 0.64, - "learning_rate": 1.8237971391417426e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.4155052459676517e-05, + "loss": 0.1637, "step": 142720 }, { - "epoch": 0.64, - "learning_rate": 1.82357293394915e-05, - "loss": 0.1709, + "epoch": 0.32, + "learning_rate": 3.4153933916467194e-05, + "loss": 0.1642, "step": 142730 }, { - "epoch": 0.64, - "learning_rate": 1.823348728756558e-05, - "loss": 0.172, + "epoch": 0.32, + "learning_rate": 3.4152815373257866e-05, + "loss": 0.1649, "step": 142740 }, { - "epoch": 0.64, - "learning_rate": 1.823124523563966e-05, - "loss": 0.1718, + "epoch": 0.32, + "learning_rate": 3.4151696830048544e-05, + "loss": 0.1627, "step": 142750 }, { - "epoch": 0.64, - "learning_rate": 1.8229003183713738e-05, - "loss": 0.1686, + "epoch": 0.32, + "learning_rate": 3.415057828683922e-05, + "loss": 0.1651, "step": 142760 }, { - "epoch": 0.64, - "learning_rate": 1.8226761131787813e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.41494597436299e-05, + "loss": 0.1651, "step": 142770 }, { - "epoch": 0.64, - "learning_rate": 1.822451907986189e-05, - "loss": 0.1711, + "epoch": 0.32, + "learning_rate": 3.414834120042058e-05, + "loss": 0.164, "step": 142780 }, { - "epoch": 0.64, - "learning_rate": 1.822227702793597e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.414722265721125e-05, + "loss": 0.1694, "step": 142790 }, { - "epoch": 0.64, - "learning_rate": 1.8220034976010046e-05, - "loss": 0.1728, + "epoch": 0.32, + "learning_rate": 3.4146104114001926e-05, + "loss": 0.1692, "step": 142800 }, { - "epoch": 0.64, - "learning_rate": 1.8217792924084124e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.4144985570792604e-05, + "loss": 0.1744, "step": 142810 }, { - "epoch": 0.64, - "learning_rate": 1.82155508721582e-05, - "loss": 0.1714, + "epoch": 0.32, + "learning_rate": 3.4143867027583275e-05, + "loss": 0.1554, "step": 142820 }, { - "epoch": 0.64, - "learning_rate": 1.821330882023228e-05, - "loss": 0.1707, + "epoch": 0.32, + "learning_rate": 3.414274848437395e-05, + "loss": 0.1613, "step": 142830 }, { - "epoch": 0.64, - "learning_rate": 1.8211066768306354e-05, - "loss": 0.1753, + "epoch": 0.32, + "learning_rate": 3.4141629941164625e-05, + "loss": 0.1648, "step": 142840 }, { - "epoch": 0.64, - "learning_rate": 1.8208824716380432e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.41405113979553e-05, + "loss": 0.1645, "step": 142850 }, { - "epoch": 0.64, - "learning_rate": 1.820658266445451e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.413939285474598e-05, + "loss": 0.1608, "step": 142860 }, { - "epoch": 0.64, - "learning_rate": 1.8204340612528587e-05, - "loss": 0.1683, + "epoch": 0.32, + "learning_rate": 3.413827431153666e-05, + "loss": 0.1615, "step": 142870 }, { - "epoch": 0.64, - "learning_rate": 1.8202098560602665e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.4137155768327336e-05, + "loss": 0.1673, "step": 142880 }, { - "epoch": 0.64, - "learning_rate": 1.819985650867674e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.413603722511801e-05, + "loss": 0.1673, "step": 142890 }, { - "epoch": 0.64, - "learning_rate": 1.819761445675082e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.4134918681908685e-05, + "loss": 0.1674, "step": 142900 }, { - "epoch": 0.64, - "learning_rate": 1.8195372404824895e-05, - "loss": 0.1663, + "epoch": 0.32, + "learning_rate": 3.413380013869936e-05, + "loss": 0.1626, "step": 142910 }, { - "epoch": 0.64, - "learning_rate": 1.8193130352898973e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.4132681595490034e-05, + "loss": 0.1633, "step": 142920 }, { - "epoch": 0.64, - "learning_rate": 1.8190888300973052e-05, - "loss": 0.1641, + "epoch": 0.32, + "learning_rate": 3.413156305228071e-05, + "loss": 0.1611, "step": 142930 }, { - "epoch": 0.64, - "learning_rate": 1.8188646249047127e-05, - "loss": 0.1716, + "epoch": 0.32, + "learning_rate": 3.4130444509071383e-05, + "loss": 0.1701, "step": 142940 }, { - "epoch": 0.64, - "learning_rate": 1.8186404197121206e-05, - "loss": 0.1669, + "epoch": 0.32, + "learning_rate": 3.412932596586206e-05, + "loss": 0.1696, "step": 142950 }, { - "epoch": 0.64, - "learning_rate": 1.818416214519528e-05, - "loss": 0.1675, + "epoch": 0.32, + "learning_rate": 3.412820742265274e-05, + "loss": 0.1621, "step": 142960 }, { - "epoch": 0.64, - "learning_rate": 1.818192009326936e-05, - "loss": 0.1718, + "epoch": 0.32, + "learning_rate": 3.412708887944342e-05, + "loss": 0.1609, "step": 142970 }, { - "epoch": 0.64, - "learning_rate": 1.817967804134344e-05, - "loss": 0.1749, + "epoch": 0.32, + "learning_rate": 3.4125970336234095e-05, + "loss": 0.1623, "step": 142980 }, { - "epoch": 0.64, - "learning_rate": 1.8177435989417514e-05, - "loss": 0.1677, + "epoch": 0.32, + "learning_rate": 3.4124851793024766e-05, + "loss": 0.1661, "step": 142990 }, { - "epoch": 0.64, - "learning_rate": 1.8175193937491593e-05, - "loss": 0.1703, + "epoch": 0.32, + "learning_rate": 3.4123733249815444e-05, + "loss": 0.1636, "step": 143000 }, { - "epoch": 0.64, - "learning_rate": 1.817295188556567e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.4122614706606115e-05, + "loss": 0.1642, "step": 143010 }, { - "epoch": 0.64, - "learning_rate": 1.8170709833639747e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.412149616339679e-05, + "loss": 0.165, "step": 143020 }, { - "epoch": 0.64, - "learning_rate": 1.8168467781713826e-05, - "loss": 0.1735, + "epoch": 0.32, + "learning_rate": 3.412037762018747e-05, + "loss": 0.1627, "step": 143030 }, { - "epoch": 0.64, - "learning_rate": 1.8166225729787904e-05, - "loss": 0.1728, + "epoch": 0.32, + "learning_rate": 3.411925907697814e-05, + "loss": 0.1658, "step": 143040 }, { - "epoch": 0.64, - "learning_rate": 1.8163983677861983e-05, - "loss": 0.1716, + "epoch": 0.32, + "learning_rate": 3.411814053376882e-05, + "loss": 0.1684, "step": 143050 }, { - "epoch": 0.64, - "learning_rate": 1.816174162593606e-05, - "loss": 0.175, + "epoch": 0.32, + "learning_rate": 3.411702199055949e-05, + "loss": 0.1654, "step": 143060 }, { - "epoch": 0.64, - "learning_rate": 1.8159499574010137e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.411590344735017e-05, + "loss": 0.1618, "step": 143070 }, { - "epoch": 0.64, - "learning_rate": 1.8157257522084213e-05, - "loss": 0.1706, + "epoch": 0.32, + "learning_rate": 3.411478490414085e-05, + "loss": 0.161, "step": 143080 }, { - "epoch": 0.64, - "learning_rate": 1.815501547015829e-05, - "loss": 0.178, + "epoch": 0.32, + "learning_rate": 3.4113666360931525e-05, + "loss": 0.1654, "step": 143090 }, { - "epoch": 0.64, - "learning_rate": 1.8152773418232367e-05, - "loss": 0.1771, + "epoch": 0.32, + "learning_rate": 3.41125478177222e-05, + "loss": 0.165, "step": 143100 }, { - "epoch": 0.64, - "learning_rate": 1.8150531366306445e-05, - "loss": 0.1672, + "epoch": 0.32, + "learning_rate": 3.4111429274512874e-05, + "loss": 0.1637, "step": 143110 }, { - "epoch": 0.64, - "learning_rate": 1.8148289314380524e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.411031073130355e-05, + "loss": 0.1648, "step": 143120 }, { - "epoch": 0.64, - "learning_rate": 1.81460472624546e-05, - "loss": 0.1694, + "epoch": 0.32, + "learning_rate": 3.410919218809423e-05, + "loss": 0.1605, "step": 143130 }, { - "epoch": 0.64, - "learning_rate": 1.8143805210528678e-05, - "loss": 0.1743, + "epoch": 0.32, + "learning_rate": 3.41080736448849e-05, + "loss": 0.1606, "step": 143140 }, { - "epoch": 0.64, - "learning_rate": 1.8141563158602753e-05, - "loss": 0.1721, + "epoch": 0.32, + "learning_rate": 3.410695510167558e-05, + "loss": 0.1635, "step": 143150 }, { - "epoch": 0.64, - "learning_rate": 1.8139321106676832e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.410583655846625e-05, + "loss": 0.1643, "step": 143160 }, { - "epoch": 0.64, - "learning_rate": 1.8137079054750907e-05, - "loss": 0.1728, + "epoch": 0.32, + "learning_rate": 3.410471801525693e-05, + "loss": 0.1633, "step": 143170 }, { - "epoch": 0.64, - "learning_rate": 1.8134837002824986e-05, - "loss": 0.1685, + "epoch": 0.32, + "learning_rate": 3.4103599472047606e-05, + "loss": 0.1567, "step": 143180 }, { - "epoch": 0.64, - "learning_rate": 1.8132594950899065e-05, - "loss": 0.177, + "epoch": 0.32, + "learning_rate": 3.4102480928838284e-05, + "loss": 0.1619, "step": 143190 }, { - "epoch": 0.64, - "learning_rate": 1.813035289897314e-05, - "loss": 0.1763, + "epoch": 0.32, + "learning_rate": 3.410136238562896e-05, + "loss": 0.1628, "step": 143200 }, { - "epoch": 0.64, - "learning_rate": 1.812811084704722e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.410024384241963e-05, + "loss": 0.16, "step": 143210 }, { - "epoch": 0.64, - "learning_rate": 1.8125868795121294e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.409912529921031e-05, + "loss": 0.1703, "step": 143220 }, { - "epoch": 0.64, - "learning_rate": 1.8123626743195373e-05, - "loss": 0.1706, + "epoch": 0.32, + "learning_rate": 3.409800675600099e-05, + "loss": 0.169, "step": 143230 }, { - "epoch": 0.64, - "learning_rate": 1.8121384691269448e-05, - "loss": 0.1631, + "epoch": 0.32, + "learning_rate": 3.409688821279166e-05, + "loss": 0.1668, "step": 143240 }, { - "epoch": 0.64, - "learning_rate": 1.8119142639343527e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.409576966958234e-05, + "loss": 0.1665, "step": 143250 }, { - "epoch": 0.64, - "learning_rate": 1.8116900587417606e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.409465112637301e-05, + "loss": 0.1644, "step": 143260 }, { - "epoch": 0.64, - "learning_rate": 1.811465853549168e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.409353258316369e-05, + "loss": 0.1645, "step": 143270 }, { - "epoch": 0.64, - "learning_rate": 1.811241648356576e-05, - "loss": 0.1724, + "epoch": 0.32, + "learning_rate": 3.4092414039954365e-05, + "loss": 0.166, "step": 143280 }, { - "epoch": 0.64, - "learning_rate": 1.811017443163984e-05, - "loss": 0.1756, + "epoch": 0.32, + "learning_rate": 3.409129549674504e-05, + "loss": 0.165, "step": 143290 }, { - "epoch": 0.64, - "learning_rate": 1.8107932379713917e-05, - "loss": 0.1768, + "epoch": 0.32, + "learning_rate": 3.409017695353572e-05, + "loss": 0.1669, "step": 143300 }, { - "epoch": 0.64, - "learning_rate": 1.8105690327787993e-05, - "loss": 0.1665, + "epoch": 0.32, + "learning_rate": 3.408905841032639e-05, + "loss": 0.1624, "step": 143310 }, { - "epoch": 0.64, - "learning_rate": 1.810344827586207e-05, - "loss": 0.1679, + "epoch": 0.32, + "learning_rate": 3.408793986711707e-05, + "loss": 0.164, "step": 143320 }, { - "epoch": 0.64, - "learning_rate": 1.810120622393615e-05, - "loss": 0.1718, + "epoch": 0.32, + "learning_rate": 3.408682132390774e-05, + "loss": 0.1655, "step": 143330 }, { - "epoch": 0.64, - "learning_rate": 1.8098964172010225e-05, - "loss": 0.1692, + "epoch": 0.32, + "learning_rate": 3.408570278069842e-05, + "loss": 0.1703, "step": 143340 }, { - "epoch": 0.64, - "learning_rate": 1.8096722120084304e-05, - "loss": 0.1675, + "epoch": 0.32, + "learning_rate": 3.40845842374891e-05, + "loss": 0.1635, "step": 143350 }, { - "epoch": 0.64, - "learning_rate": 1.809448006815838e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.408346569427977e-05, + "loss": 0.164, "step": 143360 }, { - "epoch": 0.64, - "learning_rate": 1.8092238016232458e-05, - "loss": 0.167, + "epoch": 0.32, + "learning_rate": 3.4082347151070446e-05, + "loss": 0.1655, "step": 143370 }, { - "epoch": 0.64, - "learning_rate": 1.8089995964306533e-05, - "loss": 0.1692, + "epoch": 0.32, + "learning_rate": 3.4081228607861124e-05, + "loss": 0.1641, "step": 143380 }, { - "epoch": 0.64, - "learning_rate": 1.8087753912380612e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.40801100646518e-05, + "loss": 0.1667, "step": 143390 }, { - "epoch": 0.64, - "learning_rate": 1.808551186045469e-05, - "loss": 0.1703, + "epoch": 0.32, + "learning_rate": 3.407899152144248e-05, + "loss": 0.1633, "step": 143400 }, { - "epoch": 0.64, - "learning_rate": 1.8083269808528766e-05, - "loss": 0.1674, + "epoch": 0.32, + "learning_rate": 3.407787297823315e-05, + "loss": 0.1617, "step": 143410 }, { - "epoch": 0.64, - "learning_rate": 1.8081027756602845e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.407675443502383e-05, + "loss": 0.1622, "step": 143420 }, { - "epoch": 0.64, - "learning_rate": 1.807878570467692e-05, - "loss": 0.172, + "epoch": 0.32, + "learning_rate": 3.40756358918145e-05, + "loss": 0.1625, "step": 143430 }, { - "epoch": 0.64, - "learning_rate": 1.8076543652751e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.407451734860518e-05, + "loss": 0.165, "step": 143440 }, { - "epoch": 0.64, - "learning_rate": 1.8074301600825074e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.4073398805395856e-05, + "loss": 0.1637, "step": 143450 }, { - "epoch": 0.64, - "learning_rate": 1.8072059548899153e-05, - "loss": 0.1666, + "epoch": 0.32, + "learning_rate": 3.407228026218653e-05, + "loss": 0.1571, "step": 143460 }, { - "epoch": 0.64, - "learning_rate": 1.806981749697323e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.4071161718977205e-05, + "loss": 0.1657, "step": 143470 }, { - "epoch": 0.64, - "learning_rate": 1.8067575445047307e-05, - "loss": 0.1705, + "epoch": 0.32, + "learning_rate": 3.4070043175767876e-05, + "loss": 0.1635, "step": 143480 }, { - "epoch": 0.64, - "learning_rate": 1.8065333393121386e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.4068924632558554e-05, + "loss": 0.1656, "step": 143490 }, { - "epoch": 0.64, - "learning_rate": 1.806309134119546e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.406780608934924e-05, + "loss": 0.1605, "step": 143500 }, { - "epoch": 0.64, - "learning_rate": 1.806084928926954e-05, - "loss": 0.1691, + "epoch": 0.32, + "learning_rate": 3.406668754613991e-05, + "loss": 0.1678, "step": 143510 }, { - "epoch": 0.64, - "learning_rate": 1.8058607237343615e-05, - "loss": 0.1681, + "epoch": 0.32, + "learning_rate": 3.406556900293059e-05, + "loss": 0.165, "step": 143520 }, { - "epoch": 0.64, - "learning_rate": 1.8056365185417694e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.406445045972126e-05, + "loss": 0.1615, "step": 143530 }, { - "epoch": 0.64, - "learning_rate": 1.8054123133491773e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.406333191651194e-05, + "loss": 0.1618, "step": 143540 }, { - "epoch": 0.64, - "learning_rate": 1.805188108156585e-05, - "loss": 0.1675, + "epoch": 0.32, + "learning_rate": 3.4062213373302615e-05, + "loss": 0.1641, "step": 143550 }, { - "epoch": 0.64, - "learning_rate": 1.8049639029639927e-05, - "loss": 0.1685, + "epoch": 0.32, + "learning_rate": 3.4061094830093286e-05, + "loss": 0.1581, "step": 143560 }, { - "epoch": 0.64, - "learning_rate": 1.8047396977714005e-05, - "loss": 0.1687, + "epoch": 0.32, + "learning_rate": 3.4059976286883964e-05, + "loss": 0.16, "step": 143570 }, { - "epoch": 0.64, - "learning_rate": 1.8045154925788084e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.4058857743674635e-05, + "loss": 0.1671, "step": 143580 }, { - "epoch": 0.64, - "learning_rate": 1.804291287386216e-05, - "loss": 0.1699, + "epoch": 0.32, + "learning_rate": 3.405773920046531e-05, + "loss": 0.1665, "step": 143590 }, { - "epoch": 0.64, - "learning_rate": 1.8040670821936238e-05, - "loss": 0.173, + "epoch": 0.32, + "learning_rate": 3.405662065725599e-05, + "loss": 0.1669, "step": 143600 }, { - "epoch": 0.64, - "learning_rate": 1.8038428770010317e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.405550211404667e-05, + "loss": 0.1643, "step": 143610 }, { - "epoch": 0.64, - "learning_rate": 1.8036186718084392e-05, - "loss": 0.1647, + "epoch": 0.32, + "learning_rate": 3.405438357083735e-05, + "loss": 0.1678, "step": 143620 }, { - "epoch": 0.64, - "learning_rate": 1.803394466615847e-05, - "loss": 0.1754, + "epoch": 0.32, + "learning_rate": 3.405326502762802e-05, + "loss": 0.1651, "step": 143630 }, { - "epoch": 0.64, - "learning_rate": 1.8031702614232546e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.4052146484418696e-05, + "loss": 0.165, "step": 143640 }, { - "epoch": 0.64, - "learning_rate": 1.8029684767499217e-05, - "loss": 0.1677, + "epoch": 0.32, + "learning_rate": 3.405102794120937e-05, + "loss": 0.163, "step": 143650 }, { - "epoch": 0.64, - "learning_rate": 1.8027442715573293e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.4049909398000045e-05, + "loss": 0.161, "step": 143660 }, { - "epoch": 0.64, - "learning_rate": 1.802520066364737e-05, - "loss": 0.1696, + "epoch": 0.32, + "learning_rate": 3.404879085479072e-05, + "loss": 0.1687, "step": 143670 }, { - "epoch": 0.64, - "learning_rate": 1.802295861172145e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.4047672311581394e-05, + "loss": 0.1685, "step": 143680 }, { - "epoch": 0.64, - "learning_rate": 1.8020716559795525e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.404655376837207e-05, + "loss": 0.1617, "step": 143690 }, { - "epoch": 0.64, - "learning_rate": 1.8018474507869604e-05, - "loss": 0.166, + "epoch": 0.32, + "learning_rate": 3.404543522516275e-05, + "loss": 0.165, "step": 143700 }, { - "epoch": 0.64, - "learning_rate": 1.801623245594368e-05, - "loss": 0.1635, + "epoch": 0.32, + "learning_rate": 3.404431668195343e-05, + "loss": 0.1636, "step": 143710 }, { - "epoch": 0.64, - "learning_rate": 1.8013990404017758e-05, - "loss": 0.1664, + "epoch": 0.32, + "learning_rate": 3.4043198138744106e-05, + "loss": 0.1629, "step": 143720 }, { - "epoch": 0.64, - "learning_rate": 1.8011748352091834e-05, - "loss": 0.1709, + "epoch": 0.32, + "learning_rate": 3.404207959553478e-05, + "loss": 0.1651, "step": 143730 }, { - "epoch": 0.64, - "learning_rate": 1.8009506300165912e-05, - "loss": 0.1703, + "epoch": 0.32, + "learning_rate": 3.4040961052325455e-05, + "loss": 0.1668, "step": 143740 }, { - "epoch": 0.64, - "learning_rate": 1.800726424823999e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.4039842509116126e-05, + "loss": 0.1613, "step": 143750 }, { - "epoch": 0.64, - "learning_rate": 1.8005022196314066e-05, - "loss": 0.1756, + "epoch": 0.32, + "learning_rate": 3.4038723965906804e-05, + "loss": 0.1627, "step": 143760 }, { - "epoch": 0.64, - "learning_rate": 1.8002780144388145e-05, - "loss": 0.1756, + "epoch": 0.32, + "learning_rate": 3.403760542269748e-05, + "loss": 0.1644, "step": 143770 }, { - "epoch": 0.64, - "learning_rate": 1.800053809246222e-05, - "loss": 0.1723, + "epoch": 0.32, + "learning_rate": 3.403648687948815e-05, + "loss": 0.1668, "step": 143780 }, { - "epoch": 0.64, - "learning_rate": 1.79982960405363e-05, - "loss": 0.1655, + "epoch": 0.32, + "learning_rate": 3.403536833627883e-05, + "loss": 0.1626, "step": 143790 }, { - "epoch": 0.64, - "learning_rate": 1.7996053988610374e-05, - "loss": 0.1726, + "epoch": 0.32, + "learning_rate": 3.403424979306951e-05, + "loss": 0.1585, "step": 143800 }, { - "epoch": 0.64, - "learning_rate": 1.7993811936684453e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.403313124986019e-05, + "loss": 0.1667, "step": 143810 }, { - "epoch": 0.64, - "learning_rate": 1.7991569884758532e-05, - "loss": 0.1679, + "epoch": 0.32, + "learning_rate": 3.4032012706650865e-05, + "loss": 0.1632, "step": 143820 }, { - "epoch": 0.64, - "learning_rate": 1.7989327832832607e-05, - "loss": 0.1755, + "epoch": 0.32, + "learning_rate": 3.4030894163441536e-05, + "loss": 0.1642, "step": 143830 }, { - "epoch": 0.64, - "learning_rate": 1.7987085780906686e-05, - "loss": 0.1687, + "epoch": 0.32, + "learning_rate": 3.4029775620232214e-05, + "loss": 0.1596, "step": 143840 }, { - "epoch": 0.64, - "learning_rate": 1.7984843728980765e-05, - "loss": 0.1702, + "epoch": 0.32, + "learning_rate": 3.4028657077022885e-05, + "loss": 0.1584, "step": 143850 }, { - "epoch": 0.64, - "learning_rate": 1.7982601677054843e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.402753853381356e-05, + "loss": 0.1639, "step": 143860 }, { - "epoch": 0.64, - "learning_rate": 1.798035962512892e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.402641999060424e-05, + "loss": 0.1652, "step": 143870 }, { - "epoch": 0.64, - "learning_rate": 1.7978117573202997e-05, - "loss": 0.1685, + "epoch": 0.32, + "learning_rate": 3.402530144739491e-05, + "loss": 0.1555, "step": 143880 }, { - "epoch": 0.64, - "learning_rate": 1.7975875521277076e-05, - "loss": 0.168, + "epoch": 0.32, + "learning_rate": 3.402418290418559e-05, + "loss": 0.1656, "step": 143890 }, { - "epoch": 0.64, - "learning_rate": 1.797363346935115e-05, - "loss": 0.1645, + "epoch": 0.32, + "learning_rate": 3.402306436097626e-05, + "loss": 0.1615, "step": 143900 }, { - "epoch": 0.64, - "learning_rate": 1.797139141742523e-05, - "loss": 0.1707, + "epoch": 0.32, + "learning_rate": 3.402194581776694e-05, + "loss": 0.1633, "step": 143910 }, { - "epoch": 0.64, - "learning_rate": 1.7969149365499305e-05, - "loss": 0.1752, + "epoch": 0.32, + "learning_rate": 3.402082727455762e-05, + "loss": 0.1646, "step": 143920 }, { - "epoch": 0.64, - "learning_rate": 1.7966907313573384e-05, - "loss": 0.1707, + "epoch": 0.32, + "learning_rate": 3.4019708731348295e-05, + "loss": 0.1669, "step": 143930 }, { - "epoch": 0.64, - "learning_rate": 1.7964665261647463e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.401859018813897e-05, + "loss": 0.1648, "step": 143940 }, { - "epoch": 0.64, - "learning_rate": 1.7962423209721538e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.4017471644929644e-05, + "loss": 0.1668, "step": 143950 }, { - "epoch": 0.64, - "learning_rate": 1.7960181157795617e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.401635310172032e-05, + "loss": 0.1657, "step": 143960 }, { - "epoch": 0.64, - "learning_rate": 1.7957939105869692e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.401523455851099e-05, + "loss": 0.1628, "step": 143970 }, { - "epoch": 0.64, - "learning_rate": 1.795569705394377e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.401411601530167e-05, + "loss": 0.16, "step": 143980 }, { - "epoch": 0.64, - "learning_rate": 1.7953455002017846e-05, - "loss": 0.1655, + "epoch": 0.32, + "learning_rate": 3.401299747209235e-05, + "loss": 0.1631, "step": 143990 }, { - "epoch": 0.64, - "learning_rate": 1.7951212950091925e-05, - "loss": 0.1744, + "epoch": 0.32, + "learning_rate": 3.401187892888302e-05, + "loss": 0.1611, "step": 144000 }, { - "epoch": 0.64, - "eval_NEIMS_canon_smiles": 0.9400666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.07141666666666667, - "eval_NEIMS_daylight_tanimoto_simil": 0.4733336833562701, - "eval_NEIMS_exact_mols": 0.07115, - "eval_NEIMS_exact_smiles": 0.0692, - "eval_NEIMS_loss": 0.20888929069042206, - "eval_NEIMS_matched_formulas": 0.5735333333333333, - "eval_NEIMS_morgan_tanimoto_simil": 0.37904262966664, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.07145, - "eval_NEIMS_runtime": 715.6344, - "eval_NEIMS_samples_per_second": 83.842, - "eval_NEIMS_steps_per_second": 1.311, + "epoch": 0.32, + "eval_NEIMS_canon_smiles": 0.9501166666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.10121666666666666, + "eval_NEIMS_daylight_tanimoto_simil": 0.5095042108676217, + "eval_NEIMS_exact_mols": 0.101, + "eval_NEIMS_exact_smiles": 0.09856666666666666, + "eval_NEIMS_loss": 0.1877143383026123, + "eval_NEIMS_matched_formulas": 0.6336666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.41693000068902464, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.10143333333333333, + "eval_NEIMS_runtime": 729.6638, + "eval_NEIMS_samples_per_second": 82.23, + "eval_NEIMS_steps_per_second": 1.286, "step": 144000 }, { - "epoch": 0.64, - "eval_RASSP_canon_smiles": 0.9318629578922764, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.16687815140080808, - "eval_RASSP_daylight_tanimoto_simil": 0.6079040598169455, - "eval_RASSP_exact_mols": 0.16634387417771396, - "eval_RASSP_exact_smiles": 0.16091762113066418, - "eval_RASSP_loss": 0.14781031012535095, - "eval_RASSP_matched_formulas": 0.7601763114836211, - "eval_RASSP_morgan_tanimoto_simil": 0.4826798272174804, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.16657762046281765, - "eval_RASSP_runtime": 820.8546, - "eval_RASSP_samples_per_second": 72.965, - "eval_RASSP_steps_per_second": 1.14, + "epoch": 0.32, + "eval_RASSP_canon_smiles": 0.944552041940762, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.14530670851838248, + "eval_RASSP_daylight_tanimoto_simil": 0.5984818893870436, + "eval_RASSP_exact_mols": 0.14472234280562327, + "eval_RASSP_exact_smiles": 0.14078204828530402, + "eval_RASSP_loss": 0.1538674533367157, + "eval_RASSP_matched_formulas": 0.7861555414565733, + "eval_RASSP_morgan_tanimoto_simil": 0.46568628422166214, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.14487260827461848, + "eval_RASSP_runtime": 830.9733, + "eval_RASSP_samples_per_second": 72.077, + "eval_RASSP_steps_per_second": 1.126, "step": 144000 }, { - "epoch": 0.64, - "eval_NIST_canon_smiles": 0.8558398693970259, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.011818149554601271, - "eval_NIST_daylight_tanimoto_simil": 0.26327297585527626, - "eval_NIST_exact_mols": 0.011569719984384427, - "eval_NIST_exact_smiles": 0.010576001703517053, - "eval_NIST_loss": 1.8349838256835938, - "eval_NIST_matched_formulas": 0.0833303758384498, - "eval_NIST_morgan_tanimoto_simil": 0.2154380983344991, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.011853639493203677, - "eval_NIST_runtime": 498.1444, - "eval_NIST_samples_per_second": 56.564, - "eval_NIST_steps_per_second": 0.885, + "epoch": 0.32, + "eval_NEIMS_old_canon_smiles": 0.9481333333333334, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.10193333333333333, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5097666678808961, + "eval_NEIMS_old_exact_mols": 0.10166666666666667, + "eval_NEIMS_old_exact_smiles": 0.09916666666666667, + "eval_NEIMS_old_loss": 0.187037393450737, + "eval_NEIMS_old_matched_formulas": 0.6304666666666666, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4190511237733919, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1021, + "eval_NEIMS_old_runtime": 365.7582, + "eval_NEIMS_old_samples_per_second": 82.021, + "eval_NEIMS_old_steps_per_second": 1.282, "step": 144000 }, { - "epoch": 0.64, - "learning_rate": 1.7948970898166004e-05, - "loss": 0.169, - "step": 144010 + "epoch": 0.32, + "eval_RASSP_old_canon_smiles": 0.9455734641438917, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.16297927720492542, + "eval_RASSP_old_daylight_tanimoto_simil": 0.613839324141489, + "eval_RASSP_old_exact_mols": 0.16264557680114794, + "eval_RASSP_old_exact_smiles": 0.1582407314712851, + "eval_RASSP_old_loss": 0.14649610221385956, + "eval_RASSP_old_matched_formulas": 0.7991457269663297, + "eval_RASSP_old_morgan_tanimoto_simil": 0.48432851439833885, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.16284579704341443, + "eval_RASSP_old_runtime": 413.6781, + "eval_RASSP_old_samples_per_second": 72.44, + "eval_RASSP_old_steps_per_second": 1.134, + "step": 144000 }, { - "epoch": 0.64, - "learning_rate": 1.794672884624008e-05, - "loss": 0.1702, - "step": 144020 + "epoch": 0.32, + "eval_NIST_canon_smiles": 0.8819604642083969, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.018170848564431984, + "eval_NIST_daylight_tanimoto_simil": 0.28058060558634684, + "eval_NIST_exact_mols": 0.017425559853781452, + "eval_NIST_exact_smiles": 0.016289881818504454, + "eval_NIST_loss": 1.8420897722244263, + "eval_NIST_matched_formulas": 0.10228200305213472, + "eval_NIST_morgan_tanimoto_simil": 0.2339703402124791, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01792241899421514, + "eval_NIST_runtime": 502.693, + "eval_NIST_samples_per_second": 56.052, + "eval_NIST_steps_per_second": 0.877, + "step": 144000 }, { - "epoch": 0.64, - "learning_rate": 1.7944486794314158e-05, - "loss": 0.1756, - "step": 144030 + "epoch": 0.32, + "learning_rate": 3.40107603856737e-05, + "loss": 0.1676, + "step": 144010 }, { - "epoch": 0.64, - "learning_rate": 1.7942244742388233e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.4009641842464376e-05, + "loss": 0.165, + "step": 144020 + }, + { + "epoch": 0.32, + "learning_rate": 3.4008523299255054e-05, + "loss": 0.1628, + "step": 144030 + }, + { + "epoch": 0.32, + "learning_rate": 3.400740475604573e-05, + "loss": 0.1633, "step": 144040 }, { - "epoch": 0.64, - "learning_rate": 1.7940002690462312e-05, - "loss": 0.1715, + "epoch": 0.32, + "learning_rate": 3.40062862128364e-05, + "loss": 0.1678, "step": 144050 }, { - "epoch": 0.64, - "learning_rate": 1.7937760638536387e-05, - "loss": 0.1677, + "epoch": 0.32, + "learning_rate": 3.400516766962708e-05, + "loss": 0.1643, "step": 144060 }, { - "epoch": 0.64, - "learning_rate": 1.7935518586610466e-05, - "loss": 0.1749, + "epoch": 0.32, + "learning_rate": 3.400404912641775e-05, + "loss": 0.1633, "step": 144070 }, { - "epoch": 0.64, - "learning_rate": 1.7933276534684545e-05, - "loss": 0.1718, + "epoch": 0.32, + "learning_rate": 3.400293058320843e-05, + "loss": 0.1573, "step": 144080 }, { - "epoch": 0.64, - "learning_rate": 1.793103448275862e-05, - "loss": 0.1639, + "epoch": 0.32, + "learning_rate": 3.400181203999911e-05, + "loss": 0.1615, "step": 144090 }, { - "epoch": 0.64, - "learning_rate": 1.79287924308327e-05, - "loss": 0.1737, + "epoch": 0.32, + "learning_rate": 3.400069349678978e-05, + "loss": 0.1647, "step": 144100 }, { - "epoch": 0.64, - "learning_rate": 1.7926550378906777e-05, - "loss": 0.1792, + "epoch": 0.32, + "learning_rate": 3.399957495358046e-05, + "loss": 0.1666, "step": 144110 }, { - "epoch": 0.64, - "learning_rate": 1.7924308326980853e-05, - "loss": 0.1682, + "epoch": 0.32, + "learning_rate": 3.3998456410371135e-05, + "loss": 0.1714, "step": 144120 }, { - "epoch": 0.64, - "learning_rate": 1.792206627505493e-05, - "loss": 0.1662, + "epoch": 0.32, + "learning_rate": 3.399733786716181e-05, + "loss": 0.1603, "step": 144130 }, { - "epoch": 0.64, - "learning_rate": 1.791982422312901e-05, - "loss": 0.1642, + "epoch": 0.32, + "learning_rate": 3.399621932395249e-05, + "loss": 0.1652, "step": 144140 }, { - "epoch": 0.64, - "learning_rate": 1.791758217120309e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.399510078074316e-05, + "loss": 0.1603, "step": 144150 }, { - "epoch": 0.64, - "learning_rate": 1.7915340119277164e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.399398223753384e-05, + "loss": 0.167, "step": 144160 }, { - "epoch": 0.64, - "learning_rate": 1.7913098067351243e-05, - "loss": 0.1678, + "epoch": 0.32, + "learning_rate": 3.399286369432451e-05, + "loss": 0.1641, "step": 144170 }, { - "epoch": 0.64, - "learning_rate": 1.7910856015425318e-05, - "loss": 0.1726, + "epoch": 0.32, + "learning_rate": 3.399174515111519e-05, + "loss": 0.1655, "step": 144180 }, { - "epoch": 0.64, - "learning_rate": 1.7908613963499397e-05, - "loss": 0.1661, + "epoch": 0.32, + "learning_rate": 3.399062660790587e-05, + "loss": 0.1599, "step": 144190 }, { - "epoch": 0.64, - "learning_rate": 1.7906371911573472e-05, - "loss": 0.1692, + "epoch": 0.32, + "learning_rate": 3.398950806469654e-05, + "loss": 0.1676, "step": 144200 }, { - "epoch": 0.64, - "learning_rate": 1.790412985964755e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.3988389521487216e-05, + "loss": 0.1686, "step": 144210 }, { - "epoch": 0.64, - "learning_rate": 1.790188780772163e-05, - "loss": 0.1727, + "epoch": 0.32, + "learning_rate": 3.3987270978277894e-05, + "loss": 0.1614, "step": 144220 }, { - "epoch": 0.64, - "learning_rate": 1.7899645755795705e-05, - "loss": 0.1711, + "epoch": 0.32, + "learning_rate": 3.398615243506857e-05, + "loss": 0.1678, "step": 144230 }, { - "epoch": 0.64, - "learning_rate": 1.7897403703869784e-05, - "loss": 0.1691, + "epoch": 0.32, + "learning_rate": 3.398503389185924e-05, + "loss": 0.1667, "step": 144240 }, { - "epoch": 0.64, - "learning_rate": 1.789516165194386e-05, - "loss": 0.1651, + "epoch": 0.32, + "learning_rate": 3.398391534864992e-05, + "loss": 0.164, "step": 144250 }, { - "epoch": 0.64, - "learning_rate": 1.7892919600017938e-05, - "loss": 0.1667, + "epoch": 0.32, + "learning_rate": 3.39827968054406e-05, + "loss": 0.1628, "step": 144260 }, { - "epoch": 0.64, - "learning_rate": 1.7890677548092013e-05, - "loss": 0.1719, + "epoch": 0.32, + "learning_rate": 3.398167826223127e-05, + "loss": 0.1641, "step": 144270 }, { - "epoch": 0.64, - "learning_rate": 1.7888435496166092e-05, - "loss": 0.1658, + "epoch": 0.32, + "learning_rate": 3.398055971902195e-05, + "loss": 0.1629, "step": 144280 }, { - "epoch": 0.64, - "learning_rate": 1.788619344424017e-05, - "loss": 0.1656, + "epoch": 0.32, + "learning_rate": 3.397944117581262e-05, + "loss": 0.1644, "step": 144290 }, { - "epoch": 0.64, - "learning_rate": 1.7883951392314246e-05, - "loss": 0.165, + "epoch": 0.32, + "learning_rate": 3.39783226326033e-05, + "loss": 0.164, "step": 144300 }, { - "epoch": 0.64, - "learning_rate": 1.7881709340388325e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.3977204089393975e-05, + "loss": 0.1646, "step": 144310 }, { - "epoch": 0.64, - "learning_rate": 1.78794672884624e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.3976085546184646e-05, + "loss": 0.1617, "step": 144320 }, { - "epoch": 0.64, - "learning_rate": 1.787722523653648e-05, - "loss": 0.1732, + "epoch": 0.32, + "learning_rate": 3.397496700297533e-05, + "loss": 0.1643, "step": 144330 }, { - "epoch": 0.64, - "learning_rate": 1.7874983184610554e-05, - "loss": 0.1668, + "epoch": 0.32, + "learning_rate": 3.3973848459766e-05, + "loss": 0.1641, "step": 144340 }, { - "epoch": 0.64, - "learning_rate": 1.7872741132684633e-05, - "loss": 0.1706, + "epoch": 0.32, + "learning_rate": 3.397272991655668e-05, + "loss": 0.1681, "step": 144350 }, { - "epoch": 0.64, - "learning_rate": 1.787049908075871e-05, - "loss": 0.1668, + "epoch": 0.32, + "learning_rate": 3.397161137334736e-05, + "loss": 0.1629, "step": 144360 }, { - "epoch": 0.64, - "learning_rate": 1.7868257028832787e-05, - "loss": 0.1693, + "epoch": 0.32, + "learning_rate": 3.397049283013803e-05, + "loss": 0.1652, "step": 144370 }, { - "epoch": 0.64, - "learning_rate": 1.7866014976906865e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.396937428692871e-05, + "loss": 0.1597, "step": 144380 }, { - "epoch": 0.64, - "learning_rate": 1.7863772924980944e-05, - "loss": 0.1684, + "epoch": 0.32, + "learning_rate": 3.396825574371938e-05, + "loss": 0.1615, "step": 144390 }, { - "epoch": 0.64, - "learning_rate": 1.7861530873055023e-05, - "loss": 0.1642, + "epoch": 0.32, + "learning_rate": 3.3967137200510056e-05, + "loss": 0.1589, "step": 144400 }, { - "epoch": 0.64, - "learning_rate": 1.7859288821129098e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.3966018657300734e-05, + "loss": 0.163, "step": 144410 }, { - "epoch": 0.64, - "learning_rate": 1.7857046769203177e-05, - "loss": 0.1744, + "epoch": 0.32, + "learning_rate": 3.3964900114091405e-05, + "loss": 0.165, "step": 144420 }, { - "epoch": 0.64, - "learning_rate": 1.7854804717277256e-05, - "loss": 0.1713, + "epoch": 0.32, + "learning_rate": 3.396378157088208e-05, + "loss": 0.1662, "step": 144430 }, { - "epoch": 0.64, - "learning_rate": 1.785256266535133e-05, - "loss": 0.1714, + "epoch": 0.32, + "learning_rate": 3.396266302767276e-05, + "loss": 0.1653, "step": 144440 }, { - "epoch": 0.64, - "learning_rate": 1.785032061342541e-05, - "loss": 0.178, + "epoch": 0.32, + "learning_rate": 3.396154448446344e-05, + "loss": 0.1621, "step": 144450 }, { - "epoch": 0.64, - "learning_rate": 1.7848078561499485e-05, - "loss": 0.1731, + "epoch": 0.32, + "learning_rate": 3.396042594125412e-05, + "loss": 0.1625, "step": 144460 }, { - "epoch": 0.64, - "learning_rate": 1.7845836509573564e-05, - "loss": 0.1738, + "epoch": 0.32, + "learning_rate": 3.395930739804479e-05, + "loss": 0.1576, "step": 144470 }, { - "epoch": 0.64, - "learning_rate": 1.784359445764764e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.3958188854835466e-05, + "loss": 0.1596, "step": 144480 }, { - "epoch": 0.65, - "learning_rate": 1.7841352405721718e-05, - "loss": 0.173, + "epoch": 0.32, + "learning_rate": 3.395707031162614e-05, + "loss": 0.1588, "step": 144490 }, { - "epoch": 0.65, - "learning_rate": 1.7839110353795797e-05, - "loss": 0.1692, + "epoch": 0.32, + "learning_rate": 3.3955951768416815e-05, + "loss": 0.1641, "step": 144500 }, { - "epoch": 0.65, - "learning_rate": 1.7836868301869872e-05, - "loss": 0.1719, + "epoch": 0.32, + "learning_rate": 3.395483322520749e-05, + "loss": 0.1679, "step": 144510 }, { - "epoch": 0.65, - "learning_rate": 1.783462624994395e-05, - "loss": 0.1663, + "epoch": 0.32, + "learning_rate": 3.3953714681998164e-05, + "loss": 0.1644, "step": 144520 }, { - "epoch": 0.65, - "learning_rate": 1.7832384198018026e-05, - "loss": 0.166, + "epoch": 0.32, + "learning_rate": 3.395259613878884e-05, + "loss": 0.1617, "step": 144530 }, { - "epoch": 0.65, - "learning_rate": 1.7830142146092105e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.395147759557952e-05, + "loss": 0.1602, "step": 144540 }, { - "epoch": 0.65, - "learning_rate": 1.782790009416618e-05, - "loss": 0.1696, + "epoch": 0.32, + "learning_rate": 3.39503590523702e-05, + "loss": 0.1619, "step": 144550 }, { - "epoch": 0.65, - "learning_rate": 1.782565804224026e-05, - "loss": 0.1716, + "epoch": 0.32, + "learning_rate": 3.394924050916087e-05, + "loss": 0.1608, "step": 144560 }, { - "epoch": 0.65, - "learning_rate": 1.7823415990314337e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.394812196595155e-05, + "loss": 0.1706, "step": 144570 }, { - "epoch": 0.65, - "learning_rate": 1.7821173938388413e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.3947003422742225e-05, + "loss": 0.1622, "step": 144580 }, { - "epoch": 0.65, - "learning_rate": 1.781893188646249e-05, - "loss": 0.1709, + "epoch": 0.32, + "learning_rate": 3.3945884879532896e-05, + "loss": 0.1668, "step": 144590 }, { - "epoch": 0.65, - "learning_rate": 1.7816689834536567e-05, - "loss": 0.1669, + "epoch": 0.32, + "learning_rate": 3.3944766336323574e-05, + "loss": 0.1594, "step": 144600 }, { - "epoch": 0.65, - "learning_rate": 1.7814447782610645e-05, - "loss": 0.1657, + "epoch": 0.32, + "learning_rate": 3.3943647793114245e-05, + "loss": 0.1591, "step": 144610 }, { - "epoch": 0.65, - "learning_rate": 1.781220573068472e-05, - "loss": 0.1714, + "epoch": 0.32, + "learning_rate": 3.394252924990492e-05, + "loss": 0.166, "step": 144620 }, { - "epoch": 0.65, - "learning_rate": 1.78099636787588e-05, - "loss": 0.1687, + "epoch": 0.32, + "learning_rate": 3.39414107066956e-05, + "loss": 0.1662, "step": 144630 }, { - "epoch": 0.65, - "learning_rate": 1.7807721626832878e-05, - "loss": 0.1686, + "epoch": 0.32, + "learning_rate": 3.394029216348628e-05, + "loss": 0.1653, "step": 144640 }, { - "epoch": 0.65, - "learning_rate": 1.7805479574906954e-05, - "loss": 0.1643, + "epoch": 0.32, + "learning_rate": 3.393917362027696e-05, + "loss": 0.164, "step": 144650 }, { - "epoch": 0.65, - "learning_rate": 1.7803237522981032e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.393805507706763e-05, + "loss": 0.1621, "step": 144660 }, { - "epoch": 0.65, - "learning_rate": 1.780099547105511e-05, - "loss": 0.1641, + "epoch": 0.32, + "learning_rate": 3.3936936533858306e-05, + "loss": 0.1645, "step": 144670 }, { - "epoch": 0.65, - "learning_rate": 1.779875341912919e-05, - "loss": 0.1747, + "epoch": 0.32, + "learning_rate": 3.3935817990648984e-05, + "loss": 0.1629, "step": 144680 }, { - "epoch": 0.65, - "learning_rate": 1.7796511367203265e-05, - "loss": 0.1716, + "epoch": 0.32, + "learning_rate": 3.3934699447439655e-05, + "loss": 0.1662, "step": 144690 }, { - "epoch": 0.65, - "learning_rate": 1.7794269315277344e-05, - "loss": 0.163, + "epoch": 0.32, + "learning_rate": 3.393358090423033e-05, + "loss": 0.1622, "step": 144700 }, { - "epoch": 0.65, - "learning_rate": 1.7792027263351423e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.3932462361021004e-05, + "loss": 0.1596, "step": 144710 }, { - "epoch": 0.65, - "learning_rate": 1.7789785211425498e-05, - "loss": 0.1671, + "epoch": 0.32, + "learning_rate": 3.393134381781168e-05, + "loss": 0.1621, "step": 144720 }, { - "epoch": 0.65, - "learning_rate": 1.7787543159499577e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.393022527460236e-05, + "loss": 0.162, "step": 144730 }, { - "epoch": 0.65, - "learning_rate": 1.7785301107573652e-05, - "loss": 0.1724, + "epoch": 0.32, + "learning_rate": 3.392910673139304e-05, + "loss": 0.1576, "step": 144740 }, { - "epoch": 0.65, - "learning_rate": 1.778305905564773e-05, - "loss": 0.1689, + "epoch": 0.32, + "learning_rate": 3.3927988188183716e-05, + "loss": 0.1599, "step": 144750 }, { - "epoch": 0.65, - "learning_rate": 1.7780817003721806e-05, - "loss": 0.1654, + "epoch": 0.32, + "learning_rate": 3.392686964497439e-05, + "loss": 0.1646, "step": 144760 }, { - "epoch": 0.65, - "learning_rate": 1.7778574951795885e-05, - "loss": 0.1634, + "epoch": 0.32, + "learning_rate": 3.3925751101765065e-05, + "loss": 0.1589, "step": 144770 }, { - "epoch": 0.65, - "learning_rate": 1.7776332899869963e-05, - "loss": 0.1644, + "epoch": 0.32, + "learning_rate": 3.392463255855574e-05, + "loss": 0.1657, "step": 144780 }, { - "epoch": 0.65, - "learning_rate": 1.777409084794404e-05, - "loss": 0.1666, + "epoch": 0.32, + "learning_rate": 3.3923514015346414e-05, + "loss": 0.1667, "step": 144790 }, { - "epoch": 0.65, - "learning_rate": 1.7771848796018117e-05, - "loss": 0.1643, + "epoch": 0.32, + "learning_rate": 3.392239547213709e-05, + "loss": 0.1621, "step": 144800 }, { - "epoch": 0.65, - "learning_rate": 1.7769606744092193e-05, - "loss": 0.164, + "epoch": 0.32, + "learning_rate": 3.392127692892776e-05, + "loss": 0.1638, "step": 144810 }, { - "epoch": 0.65, - "learning_rate": 1.776736469216627e-05, - "loss": 0.1717, + "epoch": 0.32, + "learning_rate": 3.392015838571844e-05, + "loss": 0.1664, "step": 144820 }, { - "epoch": 0.65, - "learning_rate": 1.7765122640240347e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.391903984250912e-05, + "loss": 0.1634, "step": 144830 }, { - "epoch": 0.65, - "learning_rate": 1.7762880588314426e-05, - "loss": 0.1662, + "epoch": 0.32, + "learning_rate": 3.391792129929979e-05, + "loss": 0.1671, "step": 144840 }, { - "epoch": 0.65, - "learning_rate": 1.7760638536388504e-05, - "loss": 0.1613, + "epoch": 0.32, + "learning_rate": 3.391680275609047e-05, + "loss": 0.163, "step": 144850 }, { - "epoch": 0.65, - "learning_rate": 1.775839648446258e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.3915684212881146e-05, + "loss": 0.1601, "step": 144860 }, { - "epoch": 0.65, - "learning_rate": 1.7756154432536658e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.3914565669671824e-05, + "loss": 0.1641, "step": 144870 }, { - "epoch": 0.65, - "learning_rate": 1.7753912380610734e-05, - "loss": 0.1722, + "epoch": 0.32, + "learning_rate": 3.3913447126462495e-05, + "loss": 0.1642, "step": 144880 }, { - "epoch": 0.65, - "learning_rate": 1.7751670328684812e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.391232858325317e-05, + "loss": 0.1665, "step": 144890 }, { - "epoch": 0.65, - "learning_rate": 1.7749428276758888e-05, - "loss": 0.1712, + "epoch": 0.32, + "learning_rate": 3.391121004004385e-05, + "loss": 0.1647, "step": 144900 }, { - "epoch": 0.65, - "learning_rate": 1.7747186224832966e-05, - "loss": 0.1739, + "epoch": 0.32, + "learning_rate": 3.391009149683452e-05, + "loss": 0.1627, "step": 144910 }, { - "epoch": 0.65, - "learning_rate": 1.7744944172907045e-05, - "loss": 0.1695, + "epoch": 0.32, + "learning_rate": 3.39089729536252e-05, + "loss": 0.1608, "step": 144920 }, { - "epoch": 0.65, - "learning_rate": 1.7742702120981124e-05, - "loss": 0.176, + "epoch": 0.32, + "learning_rate": 3.390785441041587e-05, + "loss": 0.1628, "step": 144930 }, { - "epoch": 0.65, - "learning_rate": 1.7740460069055203e-05, - "loss": 0.1674, + "epoch": 0.32, + "learning_rate": 3.390673586720655e-05, + "loss": 0.1602, "step": 144940 }, { - "epoch": 0.65, - "learning_rate": 1.7738218017129278e-05, - "loss": 0.1678, + "epoch": 0.32, + "learning_rate": 3.390561732399723e-05, + "loss": 0.1629, "step": 144950 }, { - "epoch": 0.65, - "learning_rate": 1.7735975965203357e-05, - "loss": 0.1725, + "epoch": 0.32, + "learning_rate": 3.3904498780787905e-05, + "loss": 0.1613, "step": 144960 }, { - "epoch": 0.65, - "learning_rate": 1.7733733913277432e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.390338023757858e-05, + "loss": 0.1697, "step": 144970 }, { - "epoch": 0.65, - "learning_rate": 1.773149186135151e-05, - "loss": 0.1676, + "epoch": 0.32, + "learning_rate": 3.3902261694369254e-05, + "loss": 0.1609, "step": 144980 }, { - "epoch": 0.65, - "learning_rate": 1.772924980942559e-05, - "loss": 0.172, + "epoch": 0.32, + "learning_rate": 3.390114315115993e-05, + "loss": 0.1651, "step": 144990 }, { - "epoch": 0.65, - "learning_rate": 1.7727007757499665e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.390002460795061e-05, + "loss": 0.1685, "step": 145000 }, { - "epoch": 0.65, - "learning_rate": 1.7724765705573743e-05, - "loss": 0.1684, + "epoch": 0.32, + "learning_rate": 3.389901791906221e-05, + "loss": 0.1634, "step": 145010 }, { - "epoch": 0.65, - "learning_rate": 1.772252365364782e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.389789937585289e-05, + "loss": 0.1632, "step": 145020 }, { - "epoch": 0.65, - "learning_rate": 1.7720281601721897e-05, - "loss": 0.1769, + "epoch": 0.32, + "learning_rate": 3.389678083264357e-05, + "loss": 0.1616, "step": 145030 }, { - "epoch": 0.65, - "learning_rate": 1.7718039549795973e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.3895662289434245e-05, + "loss": 0.1569, "step": 145040 }, { - "epoch": 0.65, - "learning_rate": 1.771579749787005e-05, - "loss": 0.1669, + "epoch": 0.32, + "learning_rate": 3.389454374622492e-05, + "loss": 0.1679, "step": 145050 }, { - "epoch": 0.65, - "learning_rate": 1.771355544594413e-05, - "loss": 0.1708, + "epoch": 0.32, + "learning_rate": 3.3893425203015595e-05, + "loss": 0.1676, "step": 145060 }, { - "epoch": 0.65, - "learning_rate": 1.7711313394018206e-05, - "loss": 0.1642, + "epoch": 0.32, + "learning_rate": 3.389230665980627e-05, + "loss": 0.1685, "step": 145070 }, { - "epoch": 0.65, - "learning_rate": 1.7709071342092284e-05, - "loss": 0.1648, + "epoch": 0.32, + "learning_rate": 3.3891188116596944e-05, + "loss": 0.1626, "step": 145080 }, { - "epoch": 0.65, - "learning_rate": 1.770682929016636e-05, - "loss": 0.1731, + "epoch": 0.32, + "learning_rate": 3.389006957338762e-05, + "loss": 0.1649, "step": 145090 }, { - "epoch": 0.65, - "learning_rate": 1.7704587238240438e-05, - "loss": 0.1635, + "epoch": 0.32, + "learning_rate": 3.388895103017829e-05, + "loss": 0.1668, "step": 145100 }, { - "epoch": 0.65, - "learning_rate": 1.7702345186314514e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.388783248696897e-05, + "loss": 0.1631, "step": 145110 }, { - "epoch": 0.65, - "learning_rate": 1.7700103134388592e-05, - "loss": 0.1736, + "epoch": 0.32, + "learning_rate": 3.388671394375965e-05, + "loss": 0.1617, "step": 145120 }, { - "epoch": 0.65, - "learning_rate": 1.769786108246267e-05, - "loss": 0.1686, + "epoch": 0.32, + "learning_rate": 3.3885595400550326e-05, + "loss": 0.1602, "step": 145130 }, { - "epoch": 0.65, - "learning_rate": 1.7695619030536746e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.3884476857341004e-05, + "loss": 0.1677, "step": 145140 }, { - "epoch": 0.65, - "learning_rate": 1.7693376978610825e-05, - "loss": 0.1687, + "epoch": 0.32, + "learning_rate": 3.3883358314131676e-05, + "loss": 0.163, "step": 145150 }, { - "epoch": 0.65, - "learning_rate": 1.76911349266849e-05, - "loss": 0.1697, + "epoch": 0.32, + "learning_rate": 3.3882239770922353e-05, + "loss": 0.1607, "step": 145160 }, { - "epoch": 0.65, - "learning_rate": 1.768889287475898e-05, - "loss": 0.1723, + "epoch": 0.32, + "learning_rate": 3.388112122771303e-05, + "loss": 0.1589, "step": 145170 }, { - "epoch": 0.65, - "learning_rate": 1.7686650822833058e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.38800026845037e-05, + "loss": 0.1627, "step": 145180 }, { - "epoch": 0.65, - "learning_rate": 1.7684408770907133e-05, - "loss": 0.1666, + "epoch": 0.32, + "learning_rate": 3.387888414129438e-05, + "loss": 0.1618, "step": 145190 }, { - "epoch": 0.65, - "learning_rate": 1.7682166718981212e-05, - "loss": 0.1662, + "epoch": 0.32, + "learning_rate": 3.387776559808505e-05, + "loss": 0.1628, "step": 145200 }, { - "epoch": 0.65, - "learning_rate": 1.767992466705529e-05, - "loss": 0.1644, + "epoch": 0.32, + "learning_rate": 3.387664705487573e-05, + "loss": 0.161, "step": 145210 }, { - "epoch": 0.65, - "learning_rate": 1.767768261512937e-05, - "loss": 0.1677, + "epoch": 0.32, + "learning_rate": 3.387552851166641e-05, + "loss": 0.1604, "step": 145220 }, { - "epoch": 0.65, - "learning_rate": 1.7675440563203445e-05, - "loss": 0.1642, + "epoch": 0.32, + "learning_rate": 3.3874409968457085e-05, + "loss": 0.165, "step": 145230 }, { - "epoch": 0.65, - "learning_rate": 1.7673198511277523e-05, - "loss": 0.175, + "epoch": 0.32, + "learning_rate": 3.387329142524776e-05, + "loss": 0.1595, "step": 145240 }, { - "epoch": 0.65, - "learning_rate": 1.76709564593516e-05, - "loss": 0.1698, + "epoch": 0.32, + "learning_rate": 3.3872172882038435e-05, + "loss": 0.1633, "step": 145250 }, { - "epoch": 0.65, - "learning_rate": 1.7668714407425677e-05, - "loss": 0.1648, + "epoch": 0.32, + "learning_rate": 3.387105433882911e-05, + "loss": 0.1618, "step": 145260 }, { - "epoch": 0.65, - "learning_rate": 1.7666472355499756e-05, - "loss": 0.1691, + "epoch": 0.32, + "learning_rate": 3.3869935795619784e-05, + "loss": 0.1604, "step": 145270 }, { - "epoch": 0.65, - "learning_rate": 1.766423030357383e-05, - "loss": 0.1728, + "epoch": 0.32, + "learning_rate": 3.386881725241046e-05, + "loss": 0.1623, "step": 145280 }, { - "epoch": 0.65, - "learning_rate": 1.766198825164791e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.386769870920114e-05, + "loss": 0.1676, "step": 145290 }, { - "epoch": 0.65, - "learning_rate": 1.7659746199721986e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.386669202031275e-05, + "loss": 0.1627, "step": 145300 }, { - "epoch": 0.65, - "learning_rate": 1.7657504147796064e-05, - "loss": 0.1683, + "epoch": 0.32, + "learning_rate": 3.3865573477103426e-05, + "loss": 0.1612, "step": 145310 }, { - "epoch": 0.65, - "learning_rate": 1.7655262095870143e-05, - "loss": 0.167, + "epoch": 0.32, + "learning_rate": 3.38644549338941e-05, + "loss": 0.1701, "step": 145320 }, { - "epoch": 0.65, - "learning_rate": 1.765302004394422e-05, - "loss": 0.1639, + "epoch": 0.32, + "learning_rate": 3.3863336390684775e-05, + "loss": 0.1615, "step": 145330 }, { - "epoch": 0.65, - "learning_rate": 1.7650777992018297e-05, - "loss": 0.1662, + "epoch": 0.32, + "learning_rate": 3.3862217847475446e-05, + "loss": 0.1652, "step": 145340 }, { - "epoch": 0.65, - "learning_rate": 1.7648535940092372e-05, - "loss": 0.1628, + "epoch": 0.32, + "learning_rate": 3.3861099304266124e-05, + "loss": 0.1583, "step": 145350 }, { - "epoch": 0.65, - "learning_rate": 1.764629388816645e-05, - "loss": 0.1688, + "epoch": 0.32, + "learning_rate": 3.38599807610568e-05, + "loss": 0.1617, "step": 145360 }, { - "epoch": 0.65, - "learning_rate": 1.7644051836240526e-05, - "loss": 0.1701, + "epoch": 0.32, + "learning_rate": 3.3858862217847473e-05, + "loss": 0.1597, "step": 145370 }, { - "epoch": 0.65, - "learning_rate": 1.7641809784314605e-05, - "loss": 0.1623, + "epoch": 0.32, + "learning_rate": 3.385774367463815e-05, + "loss": 0.1634, "step": 145380 }, { - "epoch": 0.65, - "learning_rate": 1.7639567732388684e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.385662513142883e-05, + "loss": 0.1665, "step": 145390 }, { - "epoch": 0.65, - "learning_rate": 1.763732568046276e-05, - "loss": 0.1667, + "epoch": 0.32, + "learning_rate": 3.385550658821951e-05, + "loss": 0.164, "step": 145400 }, { - "epoch": 0.65, - "learning_rate": 1.7635083628536838e-05, - "loss": 0.1658, + "epoch": 0.32, + "learning_rate": 3.3854388045010185e-05, + "loss": 0.1657, "step": 145410 }, { - "epoch": 0.65, - "learning_rate": 1.7632841576610913e-05, - "loss": 0.1652, + "epoch": 0.32, + "learning_rate": 3.3853269501800856e-05, + "loss": 0.158, "step": 145420 }, { - "epoch": 0.65, - "learning_rate": 1.7630599524684992e-05, - "loss": 0.1652, + "epoch": 0.32, + "learning_rate": 3.3852150958591534e-05, + "loss": 0.1696, "step": 145430 }, { - "epoch": 0.65, - "learning_rate": 1.7628357472759067e-05, - "loss": 0.1651, + "epoch": 0.32, + "learning_rate": 3.3851032415382205e-05, + "loss": 0.1585, "step": 145440 }, { - "epoch": 0.65, - "learning_rate": 1.7626115420833146e-05, - "loss": 0.167, + "epoch": 0.32, + "learning_rate": 3.384991387217288e-05, + "loss": 0.1632, "step": 145450 }, { - "epoch": 0.65, - "learning_rate": 1.7623873368907225e-05, - "loss": 0.1663, + "epoch": 0.32, + "learning_rate": 3.384879532896356e-05, + "loss": 0.1603, "step": 145460 }, { - "epoch": 0.65, - "learning_rate": 1.7621631316981303e-05, - "loss": 0.1722, + "epoch": 0.32, + "learning_rate": 3.384767678575423e-05, + "loss": 0.1547, "step": 145470 }, { - "epoch": 0.65, - "learning_rate": 1.7619389265055382e-05, - "loss": 0.167, + "epoch": 0.32, + "learning_rate": 3.384655824254491e-05, + "loss": 0.1674, "step": 145480 }, { - "epoch": 0.65, - "learning_rate": 1.7617147213129457e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.384543969933559e-05, + "loss": 0.1651, "step": 145490 }, { - "epoch": 0.65, - "learning_rate": 1.7614905161203536e-05, - "loss": 0.1663, + "epoch": 0.32, + "learning_rate": 3.3844321156126266e-05, + "loss": 0.1682, "step": 145500 }, { - "epoch": 0.65, - "learning_rate": 1.761266310927761e-05, - "loss": 0.1772, + "epoch": 0.32, + "learning_rate": 3.3843202612916944e-05, + "loss": 0.1638, "step": 145510 }, { - "epoch": 0.65, - "learning_rate": 1.761042105735169e-05, - "loss": 0.1633, + "epoch": 0.32, + "learning_rate": 3.3842084069707615e-05, + "loss": 0.1636, "step": 145520 }, { - "epoch": 0.65, - "learning_rate": 1.760817900542577e-05, - "loss": 0.168, + "epoch": 0.32, + "learning_rate": 3.384096552649829e-05, + "loss": 0.1627, "step": 145530 }, { - "epoch": 0.65, - "learning_rate": 1.7605936953499844e-05, - "loss": 0.1654, + "epoch": 0.32, + "learning_rate": 3.3839846983288964e-05, + "loss": 0.1616, "step": 145540 }, { - "epoch": 0.65, - "learning_rate": 1.7603694901573923e-05, - "loss": 0.17, + "epoch": 0.32, + "learning_rate": 3.383872844007964e-05, + "loss": 0.1601, "step": 145550 }, { - "epoch": 0.65, - "learning_rate": 1.7601452849648e-05, - "loss": 0.173, + "epoch": 0.32, + "learning_rate": 3.383760989687032e-05, + "loss": 0.1609, "step": 145560 }, { - "epoch": 0.65, - "learning_rate": 1.7599210797722077e-05, - "loss": 0.1704, + "epoch": 0.32, + "learning_rate": 3.383649135366099e-05, + "loss": 0.1599, "step": 145570 }, { - "epoch": 0.65, - "learning_rate": 1.7596968745796152e-05, - "loss": 0.169, + "epoch": 0.32, + "learning_rate": 3.383537281045167e-05, + "loss": 0.1619, "step": 145580 }, { - "epoch": 0.65, - "learning_rate": 1.759472669387023e-05, - "loss": 0.1601, + "epoch": 0.32, + "learning_rate": 3.383425426724234e-05, + "loss": 0.1586, "step": 145590 }, { - "epoch": 0.65, - "learning_rate": 1.759248464194431e-05, - "loss": 0.1633, + "epoch": 0.32, + "learning_rate": 3.383313572403302e-05, + "loss": 0.1627, "step": 145600 }, { - "epoch": 0.65, - "learning_rate": 1.7590242590018385e-05, - "loss": 0.1675, + "epoch": 0.33, + "learning_rate": 3.3832017180823696e-05, + "loss": 0.1598, "step": 145610 }, { - "epoch": 0.65, - "learning_rate": 1.7588000538092464e-05, - "loss": 0.1675, + "epoch": 0.33, + "learning_rate": 3.3830898637614374e-05, + "loss": 0.1588, "step": 145620 }, { - "epoch": 0.65, - "learning_rate": 1.758575848616654e-05, - "loss": 0.1701, + "epoch": 0.33, + "learning_rate": 3.382978009440505e-05, + "loss": 0.1575, "step": 145630 }, { - "epoch": 0.65, - "learning_rate": 1.7583516434240618e-05, - "loss": 0.1705, + "epoch": 0.33, + "learning_rate": 3.382866155119572e-05, + "loss": 0.1635, "step": 145640 }, { - "epoch": 0.65, - "learning_rate": 1.7581274382314693e-05, - "loss": 0.1705, + "epoch": 0.33, + "learning_rate": 3.38275430079864e-05, + "loss": 0.163, "step": 145650 }, { - "epoch": 0.65, - "learning_rate": 1.7579032330388772e-05, - "loss": 0.1726, + "epoch": 0.33, + "learning_rate": 3.382642446477707e-05, + "loss": 0.163, "step": 145660 }, { - "epoch": 0.65, - "learning_rate": 1.757679027846285e-05, - "loss": 0.1644, + "epoch": 0.33, + "learning_rate": 3.382530592156775e-05, + "loss": 0.1608, "step": 145670 }, { - "epoch": 0.65, - "learning_rate": 1.7574548226536926e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.382418737835843e-05, + "loss": 0.1583, "step": 145680 }, { - "epoch": 0.65, - "learning_rate": 1.7572306174611005e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.38230688351491e-05, + "loss": 0.1644, "step": 145690 }, { - "epoch": 0.65, - "learning_rate": 1.757006412268508e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.382195029193978e-05, + "loss": 0.1627, "step": 145700 }, { - "epoch": 0.65, - "learning_rate": 1.756782207075916e-05, - "loss": 0.1691, + "epoch": 0.33, + "learning_rate": 3.3820831748730455e-05, + "loss": 0.1679, "step": 145710 }, { - "epoch": 0.65, - "learning_rate": 1.7565580018833237e-05, - "loss": 0.1691, + "epoch": 0.33, + "learning_rate": 3.381971320552113e-05, + "loss": 0.1625, "step": 145720 }, { - "epoch": 0.65, - "learning_rate": 1.7563337966907313e-05, - "loss": 0.1708, + "epoch": 0.33, + "learning_rate": 3.381859466231181e-05, + "loss": 0.1639, "step": 145730 }, { - "epoch": 0.65, - "learning_rate": 1.756109591498139e-05, - "loss": 0.1739, + "epoch": 0.33, + "learning_rate": 3.381747611910248e-05, + "loss": 0.1627, "step": 145740 }, { - "epoch": 0.65, - "learning_rate": 1.755885386305547e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.381635757589316e-05, + "loss": 0.1635, "step": 145750 }, { - "epoch": 0.65, - "learning_rate": 1.755661181112955e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.381523903268383e-05, + "loss": 0.1645, "step": 145760 }, { - "epoch": 0.65, - "learning_rate": 1.7554369759203624e-05, - "loss": 0.1636, + "epoch": 0.33, + "learning_rate": 3.381412048947451e-05, + "loss": 0.1666, "step": 145770 }, { - "epoch": 0.65, - "learning_rate": 1.7552127707277703e-05, - "loss": 0.1693, + "epoch": 0.33, + "learning_rate": 3.381300194626519e-05, + "loss": 0.1649, "step": 145780 }, { - "epoch": 0.65, - "learning_rate": 1.755010986054437e-05, - "loss": 0.1661, + "epoch": 0.33, + "learning_rate": 3.381188340305586e-05, + "loss": 0.163, "step": 145790 }, { - "epoch": 0.65, - "learning_rate": 1.754786780861845e-05, - "loss": 0.1699, + "epoch": 0.33, + "learning_rate": 3.3810764859846536e-05, + "loss": 0.1625, "step": 145800 }, { - "epoch": 0.65, - "learning_rate": 1.7545625756692528e-05, - "loss": 0.1668, + "epoch": 0.33, + "learning_rate": 3.3809646316637214e-05, + "loss": 0.1613, "step": 145810 }, { - "epoch": 0.65, - "learning_rate": 1.7543383704766604e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.380852777342789e-05, + "loss": 0.1597, "step": 145820 }, { - "epoch": 0.65, - "learning_rate": 1.7541141652840682e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.380740923021857e-05, + "loss": 0.1612, "step": 145830 }, { - "epoch": 0.65, - "learning_rate": 1.7538899600914758e-05, - "loss": 0.1724, + "epoch": 0.33, + "learning_rate": 3.380629068700924e-05, + "loss": 0.168, "step": 145840 }, { - "epoch": 0.65, - "learning_rate": 1.7536657548988836e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.380517214379992e-05, + "loss": 0.1624, "step": 145850 }, { - "epoch": 0.65, - "learning_rate": 1.753441549706291e-05, - "loss": 0.169, + "epoch": 0.33, + "learning_rate": 3.380405360059059e-05, + "loss": 0.1638, "step": 145860 }, { - "epoch": 0.65, - "learning_rate": 1.753217344513699e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.380293505738127e-05, + "loss": 0.1604, "step": 145870 }, { - "epoch": 0.65, - "learning_rate": 1.752993139321107e-05, - "loss": 0.1723, + "epoch": 0.33, + "learning_rate": 3.3801816514171946e-05, + "loss": 0.1593, "step": 145880 }, { - "epoch": 0.65, - "learning_rate": 1.7527689341285144e-05, - "loss": 0.1732, + "epoch": 0.33, + "learning_rate": 3.380069797096262e-05, + "loss": 0.1629, "step": 145890 }, { - "epoch": 0.65, - "learning_rate": 1.7525447289359223e-05, - "loss": 0.1704, + "epoch": 0.33, + "learning_rate": 3.3799579427753295e-05, + "loss": 0.1652, "step": 145900 }, { - "epoch": 0.65, - "learning_rate": 1.75232052374333e-05, - "loss": 0.1661, + "epoch": 0.33, + "learning_rate": 3.379846088454397e-05, + "loss": 0.1614, "step": 145910 }, { - "epoch": 0.65, - "learning_rate": 1.7520963185507377e-05, - "loss": 0.1674, + "epoch": 0.33, + "learning_rate": 3.379734234133465e-05, + "loss": 0.1618, "step": 145920 }, { - "epoch": 0.65, - "learning_rate": 1.7518721133581453e-05, - "loss": 0.1708, + "epoch": 0.33, + "learning_rate": 3.379622379812532e-05, + "loss": 0.1598, "step": 145930 }, { - "epoch": 0.65, - "learning_rate": 1.751647908165553e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.3795105254916e-05, + "loss": 0.1618, "step": 145940 }, { - "epoch": 0.65, - "learning_rate": 1.751423702972961e-05, - "loss": 0.1716, + "epoch": 0.33, + "learning_rate": 3.379398671170668e-05, + "loss": 0.1668, "step": 145950 }, { - "epoch": 0.65, - "learning_rate": 1.7511994977803685e-05, - "loss": 0.1675, + "epoch": 0.33, + "learning_rate": 3.379286816849735e-05, + "loss": 0.1631, "step": 145960 }, { - "epoch": 0.65, - "learning_rate": 1.7509752925877764e-05, - "loss": 0.166, + "epoch": 0.33, + "learning_rate": 3.379174962528803e-05, + "loss": 0.1646, "step": 145970 }, { - "epoch": 0.65, - "learning_rate": 1.750751087395184e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.37906310820787e-05, + "loss": 0.1601, "step": 145980 }, { - "epoch": 0.65, - "learning_rate": 1.7505268822025918e-05, - "loss": 0.1745, + "epoch": 0.33, + "learning_rate": 3.3789512538869376e-05, + "loss": 0.1656, "step": 145990 }, { - "epoch": 0.65, - "learning_rate": 1.7503026770099993e-05, - "loss": 0.1661, + "epoch": 0.33, + "learning_rate": 3.3788393995660054e-05, + "loss": 0.1629, "step": 146000 }, { - "epoch": 0.65, - "learning_rate": 1.7500784718174072e-05, - "loss": 0.1624, + "epoch": 0.33, + "learning_rate": 3.3787275452450725e-05, + "loss": 0.1613, "step": 146010 }, { - "epoch": 0.65, - "learning_rate": 1.749854266624815e-05, - "loss": 0.174, + "epoch": 0.33, + "learning_rate": 3.37861569092414e-05, + "loss": 0.1627, "step": 146020 }, { - "epoch": 0.65, - "learning_rate": 1.749630061432223e-05, - "loss": 0.17, + "epoch": 0.33, + "learning_rate": 3.378503836603208e-05, + "loss": 0.1635, "step": 146030 }, { - "epoch": 0.65, - "learning_rate": 1.7494058562396308e-05, - "loss": 0.1737, + "epoch": 0.33, + "learning_rate": 3.378391982282276e-05, + "loss": 0.1588, "step": 146040 }, { - "epoch": 0.65, - "learning_rate": 1.7491816510470384e-05, - "loss": 0.1626, + "epoch": 0.33, + "learning_rate": 3.378280127961344e-05, + "loss": 0.1609, "step": 146050 }, { - "epoch": 0.65, - "learning_rate": 1.7489574458544462e-05, - "loss": 0.164, + "epoch": 0.33, + "learning_rate": 3.378168273640411e-05, + "loss": 0.1631, "step": 146060 }, { - "epoch": 0.65, - "learning_rate": 1.7487332406618538e-05, - "loss": 0.1653, + "epoch": 0.33, + "learning_rate": 3.3780564193194786e-05, + "loss": 0.1594, "step": 146070 }, { - "epoch": 0.65, - "learning_rate": 1.7485090354692616e-05, - "loss": 0.1699, + "epoch": 0.33, + "learning_rate": 3.377944564998546e-05, + "loss": 0.1584, "step": 146080 }, { - "epoch": 0.65, - "learning_rate": 1.7482848302766695e-05, - "loss": 0.1675, + "epoch": 0.33, + "learning_rate": 3.3778327106776135e-05, + "loss": 0.1622, "step": 146090 }, { - "epoch": 0.65, - "learning_rate": 1.748060625084077e-05, - "loss": 0.1743, + "epoch": 0.33, + "learning_rate": 3.377720856356681e-05, + "loss": 0.1591, "step": 146100 }, { - "epoch": 0.65, - "learning_rate": 1.747836419891485e-05, - "loss": 0.1734, + "epoch": 0.33, + "learning_rate": 3.3776090020357484e-05, + "loss": 0.1679, "step": 146110 }, { - "epoch": 0.65, - "learning_rate": 1.7476122146988924e-05, - "loss": 0.173, + "epoch": 0.33, + "learning_rate": 3.377497147714816e-05, + "loss": 0.1628, "step": 146120 }, { - "epoch": 0.65, - "learning_rate": 1.7473880095063003e-05, - "loss": 0.1658, + "epoch": 0.33, + "learning_rate": 3.377385293393884e-05, + "loss": 0.1619, "step": 146130 }, { - "epoch": 0.65, - "learning_rate": 1.747163804313708e-05, - "loss": 0.1665, + "epoch": 0.33, + "learning_rate": 3.377273439072952e-05, + "loss": 0.1634, "step": 146140 }, { - "epoch": 0.65, - "learning_rate": 1.7469395991211157e-05, - "loss": 0.1695, + "epoch": 0.33, + "learning_rate": 3.3771615847520196e-05, + "loss": 0.166, "step": 146150 }, { - "epoch": 0.65, - "learning_rate": 1.7467153939285236e-05, - "loss": 0.169, + "epoch": 0.33, + "learning_rate": 3.377049730431087e-05, + "loss": 0.1641, "step": 146160 }, { - "epoch": 0.65, - "learning_rate": 1.746491188735931e-05, - "loss": 0.1686, + "epoch": 0.33, + "learning_rate": 3.3769378761101545e-05, + "loss": 0.1573, "step": 146170 }, { - "epoch": 0.65, - "learning_rate": 1.746266983543339e-05, - "loss": 0.161, + "epoch": 0.33, + "learning_rate": 3.3768260217892216e-05, + "loss": 0.1598, "step": 146180 }, { - "epoch": 0.65, - "learning_rate": 1.7460427783507465e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.3767141674682894e-05, + "loss": 0.1642, "step": 146190 }, { - "epoch": 0.65, - "learning_rate": 1.7458185731581544e-05, - "loss": 0.1715, + "epoch": 0.33, + "learning_rate": 3.376602313147357e-05, + "loss": 0.1572, "step": 146200 }, { - "epoch": 0.65, - "learning_rate": 1.745594367965562e-05, - "loss": 0.17, + "epoch": 0.33, + "learning_rate": 3.376490458826424e-05, + "loss": 0.1629, "step": 146210 }, { - "epoch": 0.65, - "learning_rate": 1.7453701627729698e-05, - "loss": 0.1671, + "epoch": 0.33, + "learning_rate": 3.376378604505492e-05, + "loss": 0.1659, "step": 146220 }, { - "epoch": 0.65, - "learning_rate": 1.7451459575803777e-05, - "loss": 0.1661, + "epoch": 0.33, + "learning_rate": 3.37626675018456e-05, + "loss": 0.1579, "step": 146230 }, { - "epoch": 0.65, - "learning_rate": 1.7449217523877852e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.376154895863628e-05, + "loss": 0.1638, "step": 146240 }, { - "epoch": 0.65, - "learning_rate": 1.744697547195193e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.376043041542695e-05, + "loss": 0.1598, "step": 146250 }, { - "epoch": 0.65, - "learning_rate": 1.7444733420026006e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.3759311872217626e-05, + "loss": 0.1613, "step": 146260 }, { - "epoch": 0.65, - "learning_rate": 1.7442491368100085e-05, - "loss": 0.1624, + "epoch": 0.33, + "learning_rate": 3.3758193329008304e-05, + "loss": 0.1593, "step": 146270 }, { - "epoch": 0.65, - "learning_rate": 1.7440249316174164e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.3757074785798975e-05, + "loss": 0.166, "step": 146280 }, { - "epoch": 0.65, - "learning_rate": 1.743800726424824e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.375595624258965e-05, + "loss": 0.1606, "step": 146290 }, { - "epoch": 0.65, - "learning_rate": 1.7435765212322318e-05, - "loss": 0.1653, + "epoch": 0.33, + "learning_rate": 3.3754837699380324e-05, + "loss": 0.1649, "step": 146300 }, { - "epoch": 0.65, - "learning_rate": 1.7433523160396396e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3753719156171e-05, + "loss": 0.1613, "step": 146310 }, { - "epoch": 0.65, - "learning_rate": 1.7431281108470475e-05, - "loss": 0.1714, + "epoch": 0.33, + "learning_rate": 3.375260061296168e-05, + "loss": 0.1661, "step": 146320 }, { - "epoch": 0.65, - "learning_rate": 1.742903905654455e-05, - "loss": 0.1715, + "epoch": 0.33, + "learning_rate": 3.375148206975236e-05, + "loss": 0.1648, "step": 146330 }, { - "epoch": 0.65, - "learning_rate": 1.742679700461863e-05, - "loss": 0.1643, + "epoch": 0.33, + "learning_rate": 3.3750363526543036e-05, + "loss": 0.156, "step": 146340 }, { - "epoch": 0.65, - "learning_rate": 1.7424554952692708e-05, - "loss": 0.1716, + "epoch": 0.33, + "learning_rate": 3.374924498333371e-05, + "loss": 0.1659, "step": 146350 }, { - "epoch": 0.65, - "learning_rate": 1.7422312900766783e-05, - "loss": 0.1741, + "epoch": 0.33, + "learning_rate": 3.3748126440124385e-05, + "loss": 0.1653, "step": 146360 }, { - "epoch": 0.65, - "learning_rate": 1.7420070848840862e-05, - "loss": 0.1697, + "epoch": 0.33, + "learning_rate": 3.374700789691506e-05, + "loss": 0.1645, "step": 146370 }, { - "epoch": 0.65, - "learning_rate": 1.7417828796914937e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.3745889353705734e-05, + "loss": 0.1665, "step": 146380 }, { - "epoch": 0.65, - "learning_rate": 1.7415586744989016e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.374477081049641e-05, + "loss": 0.1619, "step": 146390 }, { - "epoch": 0.65, - "learning_rate": 1.741334469306309e-05, - "loss": 0.174, + "epoch": 0.33, + "learning_rate": 3.374365226728708e-05, + "loss": 0.1621, "step": 146400 }, { - "epoch": 0.65, - "learning_rate": 1.741110264113717e-05, - "loss": 0.1626, + "epoch": 0.33, + "learning_rate": 3.374253372407776e-05, + "loss": 0.1609, "step": 146410 }, { - "epoch": 0.65, - "learning_rate": 1.740886058921125e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.374141518086844e-05, + "loss": 0.162, "step": 146420 }, { - "epoch": 0.65, - "learning_rate": 1.7406618537285324e-05, - "loss": 0.1658, + "epoch": 0.33, + "learning_rate": 3.374029663765911e-05, + "loss": 0.165, "step": 146430 }, { - "epoch": 0.65, - "learning_rate": 1.7404376485359403e-05, - "loss": 0.1713, + "epoch": 0.33, + "learning_rate": 3.3739178094449795e-05, + "loss": 0.1588, "step": 146440 }, { - "epoch": 0.65, - "learning_rate": 1.7402134433433478e-05, - "loss": 0.1708, + "epoch": 0.33, + "learning_rate": 3.3738059551240466e-05, + "loss": 0.1661, "step": 146450 }, { - "epoch": 0.65, - "learning_rate": 1.7399892381507557e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.3736941008031144e-05, + "loss": 0.1569, "step": 146460 }, { - "epoch": 0.65, - "learning_rate": 1.7397650329581632e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.373582246482182e-05, + "loss": 0.1639, "step": 146470 }, { - "epoch": 0.65, - "learning_rate": 1.739540827765571e-05, - "loss": 0.1715, + "epoch": 0.33, + "learning_rate": 3.373470392161249e-05, + "loss": 0.1603, "step": 146480 }, { - "epoch": 0.65, - "learning_rate": 1.739316622572979e-05, - "loss": 0.17, + "epoch": 0.33, + "learning_rate": 3.373358537840317e-05, + "loss": 0.1639, "step": 146490 }, { - "epoch": 0.65, - "learning_rate": 1.7390924173803865e-05, - "loss": 0.165, + "epoch": 0.33, + "learning_rate": 3.373246683519384e-05, + "loss": 0.1615, "step": 146500 }, { - "epoch": 0.65, - "learning_rate": 1.7388682121877944e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.373134829198452e-05, + "loss": 0.1617, "step": 146510 }, { - "epoch": 0.65, - "learning_rate": 1.738644006995202e-05, - "loss": 0.1698, + "epoch": 0.33, + "learning_rate": 3.37302297487752e-05, + "loss": 0.1599, "step": 146520 }, { - "epoch": 0.65, - "learning_rate": 1.7384198018026098e-05, - "loss": 0.1715, + "epoch": 0.33, + "learning_rate": 3.372911120556587e-05, + "loss": 0.1614, "step": 146530 }, { - "epoch": 0.65, - "learning_rate": 1.7381955966100173e-05, - "loss": 0.1735, + "epoch": 0.33, + "learning_rate": 3.372799266235655e-05, + "loss": 0.163, "step": 146540 }, { - "epoch": 0.65, - "learning_rate": 1.7379713914174252e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.3726874119147225e-05, + "loss": 0.165, "step": 146550 }, { - "epoch": 0.65, - "learning_rate": 1.737747186224833e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.37257555759379e-05, + "loss": 0.161, "step": 146560 }, { - "epoch": 0.65, - "learning_rate": 1.737522981032241e-05, - "loss": 0.1671, - "step": 146570 + "epoch": 0.33, + "learning_rate": 3.3724637032728574e-05, + "loss": 0.1607, + "step": 146570 }, { - "epoch": 0.65, - "learning_rate": 1.7372987758396488e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.372351848951925e-05, + "loss": 0.162, "step": 146580 }, { - "epoch": 0.65, - "learning_rate": 1.7370745706470563e-05, - "loss": 0.1633, + "epoch": 0.33, + "learning_rate": 3.372239994630993e-05, + "loss": 0.1636, "step": 146590 }, { - "epoch": 0.65, - "learning_rate": 1.7368503654544642e-05, - "loss": 0.1721, + "epoch": 0.33, + "learning_rate": 3.37212814031006e-05, + "loss": 0.1645, "step": 146600 }, { - "epoch": 0.65, - "learning_rate": 1.7366261602618717e-05, - "loss": 0.1729, + "epoch": 0.33, + "learning_rate": 3.372016285989128e-05, + "loss": 0.1596, "step": 146610 }, { - "epoch": 0.65, - "learning_rate": 1.7364019550692796e-05, - "loss": 0.1695, + "epoch": 0.33, + "learning_rate": 3.371904431668195e-05, + "loss": 0.1632, "step": 146620 }, { - "epoch": 0.65, - "learning_rate": 1.7361777498766875e-05, - "loss": 0.1703, + "epoch": 0.33, + "learning_rate": 3.371792577347263e-05, + "loss": 0.1664, "step": 146630 }, { - "epoch": 0.65, - "learning_rate": 1.735953544684095e-05, - "loss": 0.1693, + "epoch": 0.33, + "learning_rate": 3.3716807230263306e-05, + "loss": 0.1643, "step": 146640 }, { - "epoch": 0.65, - "learning_rate": 1.735729339491503e-05, - "loss": 0.1701, + "epoch": 0.33, + "learning_rate": 3.3715688687053984e-05, + "loss": 0.163, "step": 146650 }, { - "epoch": 0.65, - "learning_rate": 1.7355051342989104e-05, - "loss": 0.1771, + "epoch": 0.33, + "learning_rate": 3.371457014384466e-05, + "loss": 0.1635, "step": 146660 }, { - "epoch": 0.65, - "learning_rate": 1.7352809291063183e-05, - "loss": 0.1698, + "epoch": 0.33, + "learning_rate": 3.371345160063533e-05, + "loss": 0.1636, "step": 146670 }, { - "epoch": 0.65, - "learning_rate": 1.7350567239137258e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.371233305742601e-05, + "loss": 0.1616, "step": 146680 }, { - "epoch": 0.65, - "learning_rate": 1.7348325187211337e-05, - "loss": 0.1682, + "epoch": 0.33, + "learning_rate": 3.371121451421669e-05, + "loss": 0.1601, "step": 146690 }, { - "epoch": 0.65, - "learning_rate": 1.7346083135285416e-05, - "loss": 0.1767, + "epoch": 0.33, + "learning_rate": 3.371009597100736e-05, + "loss": 0.1645, "step": 146700 }, { - "epoch": 0.65, - "learning_rate": 1.734384108335949e-05, - "loss": 0.1743, + "epoch": 0.33, + "learning_rate": 3.370897742779804e-05, + "loss": 0.1623, "step": 146710 }, { - "epoch": 0.65, - "learning_rate": 1.734159903143357e-05, - "loss": 0.1622, + "epoch": 0.33, + "learning_rate": 3.370785888458871e-05, + "loss": 0.1665, "step": 146720 }, { - "epoch": 0.66, - "learning_rate": 1.7339356979507645e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.370674034137939e-05, + "loss": 0.1605, "step": 146730 }, { - "epoch": 0.66, - "learning_rate": 1.7337114927581724e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3705621798170065e-05, + "loss": 0.1637, "step": 146740 }, { - "epoch": 0.66, - "learning_rate": 1.73348728756558e-05, - "loss": 0.1708, + "epoch": 0.33, + "learning_rate": 3.370450325496074e-05, + "loss": 0.1657, "step": 146750 }, { - "epoch": 0.66, - "learning_rate": 1.7332630823729878e-05, - "loss": 0.1658, + "epoch": 0.33, + "learning_rate": 3.370338471175142e-05, + "loss": 0.1587, "step": 146760 }, { - "epoch": 0.66, - "learning_rate": 1.7330388771803956e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.370226616854209e-05, + "loss": 0.1629, "step": 146770 }, { - "epoch": 0.66, - "learning_rate": 1.7328146719878032e-05, - "loss": 0.1659, + "epoch": 0.33, + "learning_rate": 3.370114762533277e-05, + "loss": 0.166, "step": 146780 }, { - "epoch": 0.66, - "learning_rate": 1.732590466795211e-05, - "loss": 0.1638, + "epoch": 0.33, + "learning_rate": 3.370002908212345e-05, + "loss": 0.1629, "step": 146790 }, { - "epoch": 0.66, - "learning_rate": 1.7323662616026186e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.369891053891412e-05, + "loss": 0.1629, "step": 146800 }, { - "epoch": 0.66, - "learning_rate": 1.7321420564100264e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.36977919957048e-05, + "loss": 0.1623, "step": 146810 }, { - "epoch": 0.66, - "learning_rate": 1.7319178512174343e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.369667345249547e-05, + "loss": 0.161, "step": 146820 }, { - "epoch": 0.66, - "learning_rate": 1.731693646024842e-05, - "loss": 0.1744, + "epoch": 0.33, + "learning_rate": 3.3695554909286146e-05, + "loss": 0.1651, "step": 146830 }, { - "epoch": 0.66, - "learning_rate": 1.7314694408322497e-05, - "loss": 0.1761, + "epoch": 0.33, + "learning_rate": 3.3694436366076824e-05, + "loss": 0.1616, "step": 146840 }, { - "epoch": 0.66, - "learning_rate": 1.7312452356396576e-05, - "loss": 0.1705, + "epoch": 0.33, + "learning_rate": 3.36933178228675e-05, + "loss": 0.165, "step": 146850 }, { - "epoch": 0.66, - "learning_rate": 1.7310210304470655e-05, - "loss": 0.1622, + "epoch": 0.33, + "learning_rate": 3.369219927965818e-05, + "loss": 0.1577, "step": 146860 }, { - "epoch": 0.66, - "learning_rate": 1.730796825254473e-05, - "loss": 0.1642, + "epoch": 0.33, + "learning_rate": 3.369108073644885e-05, + "loss": 0.1578, "step": 146870 }, { - "epoch": 0.66, - "learning_rate": 1.730572620061881e-05, - "loss": 0.1729, + "epoch": 0.33, + "learning_rate": 3.368996219323953e-05, + "loss": 0.1554, "step": 146880 }, { - "epoch": 0.66, - "learning_rate": 1.7303484148692884e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.36888436500302e-05, + "loss": 0.1627, "step": 146890 }, { - "epoch": 0.66, - "learning_rate": 1.7301242096766963e-05, - "loss": 0.1628, + "epoch": 0.33, + "learning_rate": 3.368772510682088e-05, + "loss": 0.164, "step": 146900 }, { - "epoch": 0.66, - "learning_rate": 1.729900004484104e-05, - "loss": 0.1636, + "epoch": 0.33, + "learning_rate": 3.3686606563611556e-05, + "loss": 0.1665, "step": 146910 }, { - "epoch": 0.66, - "learning_rate": 1.7296757992915117e-05, - "loss": 0.1646, + "epoch": 0.33, + "learning_rate": 3.368548802040223e-05, + "loss": 0.1629, "step": 146920 }, { - "epoch": 0.66, - "learning_rate": 1.7294515940989196e-05, - "loss": 0.1722, + "epoch": 0.33, + "learning_rate": 3.3684369477192905e-05, + "loss": 0.1636, "step": 146930 }, { - "epoch": 0.66, - "learning_rate": 1.729227388906327e-05, - "loss": 0.1717, + "epoch": 0.33, + "learning_rate": 3.3683250933983576e-05, + "loss": 0.164, "step": 146940 }, { - "epoch": 0.66, - "learning_rate": 1.729003183713735e-05, - "loss": 0.1674, + "epoch": 0.33, + "learning_rate": 3.3682132390774254e-05, + "loss": 0.1642, "step": 146950 }, { - "epoch": 0.66, - "learning_rate": 1.7287789785211425e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.368101384756493e-05, + "loss": 0.1634, "step": 146960 }, { - "epoch": 0.66, - "learning_rate": 1.7285547733285504e-05, - "loss": 0.1628, + "epoch": 0.33, + "learning_rate": 3.367989530435561e-05, + "loss": 0.1667, "step": 146970 }, { - "epoch": 0.66, - "learning_rate": 1.7283305681359582e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.367877676114629e-05, + "loss": 0.1627, "step": 146980 }, { - "epoch": 0.66, - "learning_rate": 1.7281063629433658e-05, - "loss": 0.1656, + "epoch": 0.33, + "learning_rate": 3.367765821793696e-05, + "loss": 0.1594, "step": 146990 }, { - "epoch": 0.66, - "learning_rate": 1.7278821577507736e-05, - "loss": 0.1695, + "epoch": 0.33, + "learning_rate": 3.367653967472764e-05, + "loss": 0.1626, "step": 147000 }, { - "epoch": 0.66, - "learning_rate": 1.7276579525581812e-05, - "loss": 0.1659, + "epoch": 0.33, + "learning_rate": 3.3675421131518315e-05, + "loss": 0.1639, "step": 147010 }, { - "epoch": 0.66, - "learning_rate": 1.727433747365589e-05, - "loss": 0.1654, + "epoch": 0.33, + "learning_rate": 3.3674302588308986e-05, + "loss": 0.1627, "step": 147020 }, { - "epoch": 0.66, - "learning_rate": 1.7272095421729966e-05, - "loss": 0.1698, + "epoch": 0.33, + "learning_rate": 3.3673184045099664e-05, + "loss": 0.1651, "step": 147030 }, { - "epoch": 0.66, - "learning_rate": 1.7269853369804045e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.3672065501890335e-05, + "loss": 0.1652, "step": 147040 }, { - "epoch": 0.66, - "learning_rate": 1.7267611317878123e-05, - "loss": 0.1711, + "epoch": 0.33, + "learning_rate": 3.367094695868101e-05, + "loss": 0.1623, "step": 147050 }, { - "epoch": 0.66, - "learning_rate": 1.72653692659522e-05, - "loss": 0.1701, + "epoch": 0.33, + "learning_rate": 3.366982841547169e-05, + "loss": 0.1614, "step": 147060 }, { - "epoch": 0.66, - "learning_rate": 1.7263127214026277e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.366870987226237e-05, + "loss": 0.1635, "step": 147070 }, { - "epoch": 0.66, - "learning_rate": 1.7260885162100353e-05, - "loss": 0.171, + "epoch": 0.33, + "learning_rate": 3.366759132905305e-05, + "loss": 0.1609, "step": 147080 }, { - "epoch": 0.66, - "learning_rate": 1.725864311017443e-05, - "loss": 0.1703, + "epoch": 0.33, + "learning_rate": 3.366647278584372e-05, + "loss": 0.1628, "step": 147090 }, { - "epoch": 0.66, - "learning_rate": 1.725640105824851e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.3665354242634396e-05, + "loss": 0.1643, "step": 147100 }, { - "epoch": 0.66, - "learning_rate": 1.725415900632259e-05, - "loss": 0.1731, + "epoch": 0.33, + "learning_rate": 3.3664235699425074e-05, + "loss": 0.1679, "step": 147110 }, { - "epoch": 0.66, - "learning_rate": 1.7251916954396667e-05, - "loss": 0.1705, + "epoch": 0.33, + "learning_rate": 3.3663117156215745e-05, + "loss": 0.1618, "step": 147120 }, { - "epoch": 0.66, - "learning_rate": 1.7249674902470743e-05, - "loss": 0.1726, + "epoch": 0.33, + "learning_rate": 3.366199861300642e-05, + "loss": 0.1646, "step": 147130 }, { - "epoch": 0.66, - "learning_rate": 1.724743285054482e-05, - "loss": 0.1671, + "epoch": 0.33, + "learning_rate": 3.3660880069797094e-05, + "loss": 0.1578, "step": 147140 }, { - "epoch": 0.66, - "learning_rate": 1.7245190798618897e-05, - "loss": 0.1701, + "epoch": 0.33, + "learning_rate": 3.365976152658777e-05, + "loss": 0.1614, "step": 147150 }, { - "epoch": 0.66, - "learning_rate": 1.7242948746692976e-05, - "loss": 0.1626, + "epoch": 0.33, + "learning_rate": 3.365864298337845e-05, + "loss": 0.1602, "step": 147160 }, { - "epoch": 0.66, - "learning_rate": 1.724070669476705e-05, - "loss": 0.1721, + "epoch": 0.33, + "learning_rate": 3.365752444016913e-05, + "loss": 0.1608, "step": 147170 }, { - "epoch": 0.66, - "learning_rate": 1.723846464284113e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.3656405896959806e-05, + "loss": 0.1588, "step": 147180 }, { - "epoch": 0.66, - "learning_rate": 1.723622259091521e-05, - "loss": 0.1761, + "epoch": 0.33, + "learning_rate": 3.365528735375048e-05, + "loss": 0.1589, "step": 147190 }, { - "epoch": 0.66, - "learning_rate": 1.7233980538989284e-05, - "loss": 0.1667, + "epoch": 0.33, + "learning_rate": 3.3654168810541155e-05, + "loss": 0.1623, "step": 147200 }, { - "epoch": 0.66, - "learning_rate": 1.7231738487063362e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.3653050267331826e-05, + "loss": 0.1603, "step": 147210 }, { - "epoch": 0.66, - "learning_rate": 1.7229496435137438e-05, - "loss": 0.1687, + "epoch": 0.33, + "learning_rate": 3.3651931724122504e-05, + "loss": 0.1631, "step": 147220 }, { - "epoch": 0.66, - "learning_rate": 1.7227254383211516e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.365081318091318e-05, + "loss": 0.1649, "step": 147230 }, { - "epoch": 0.66, - "learning_rate": 1.7225012331285592e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.364969463770385e-05, + "loss": 0.1629, "step": 147240 }, { - "epoch": 0.66, - "learning_rate": 1.722277027935967e-05, - "loss": 0.1652, + "epoch": 0.33, + "learning_rate": 3.364857609449453e-05, + "loss": 0.1628, "step": 147250 }, { - "epoch": 0.66, - "learning_rate": 1.722052822743375e-05, - "loss": 0.1653, + "epoch": 0.33, + "learning_rate": 3.36474575512852e-05, + "loss": 0.1593, "step": 147260 }, { - "epoch": 0.66, - "learning_rate": 1.7218286175507825e-05, - "loss": 0.172, + "epoch": 0.33, + "learning_rate": 3.364633900807589e-05, + "loss": 0.1609, "step": 147270 }, { - "epoch": 0.66, - "learning_rate": 1.7216044123581903e-05, - "loss": 0.1679, + "epoch": 0.33, + "learning_rate": 3.3645220464866565e-05, + "loss": 0.1591, "step": 147280 }, { - "epoch": 0.66, - "learning_rate": 1.721380207165598e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.3644101921657236e-05, + "loss": 0.1616, "step": 147290 }, { - "epoch": 0.66, - "learning_rate": 1.7211560019730057e-05, - "loss": 0.1775, + "epoch": 0.33, + "learning_rate": 3.3642983378447914e-05, + "loss": 0.1613, "step": 147300 }, { - "epoch": 0.66, - "learning_rate": 1.7209317967804133e-05, - "loss": 0.1711, + "epoch": 0.33, + "learning_rate": 3.3641864835238585e-05, + "loss": 0.1608, "step": 147310 }, { - "epoch": 0.66, - "learning_rate": 1.720707591587821e-05, - "loss": 0.1667, + "epoch": 0.33, + "learning_rate": 3.364074629202926e-05, + "loss": 0.1601, "step": 147320 }, { - "epoch": 0.66, - "learning_rate": 1.720483386395229e-05, - "loss": 0.1703, + "epoch": 0.33, + "learning_rate": 3.363962774881994e-05, + "loss": 0.1654, "step": 147330 }, { - "epoch": 0.66, - "learning_rate": 1.7202591812026365e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.363850920561061e-05, + "loss": 0.1669, "step": 147340 }, { - "epoch": 0.66, - "learning_rate": 1.7200349760100444e-05, - "loss": 0.1693, + "epoch": 0.33, + "learning_rate": 3.363739066240129e-05, + "loss": 0.1629, "step": 147350 }, { - "epoch": 0.66, - "learning_rate": 1.7198107708174523e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.363627211919196e-05, + "loss": 0.1631, "step": 147360 }, { - "epoch": 0.66, - "learning_rate": 1.7195865656248598e-05, - "loss": 0.1732, + "epoch": 0.33, + "learning_rate": 3.363515357598264e-05, + "loss": 0.163, "step": 147370 }, { - "epoch": 0.66, - "learning_rate": 1.7193623604322677e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.363403503277332e-05, + "loss": 0.1637, "step": 147380 }, { - "epoch": 0.66, - "learning_rate": 1.7191381552396756e-05, - "loss": 0.1672, + "epoch": 0.33, + "learning_rate": 3.3632916489563995e-05, + "loss": 0.1582, "step": 147390 }, { - "epoch": 0.66, - "learning_rate": 1.7189139500470834e-05, - "loss": 0.1676, + "epoch": 0.33, + "learning_rate": 3.363179794635467e-05, + "loss": 0.1588, "step": 147400 }, { - "epoch": 0.66, - "learning_rate": 1.718689744854491e-05, - "loss": 0.17, + "epoch": 0.33, + "learning_rate": 3.3630679403145344e-05, + "loss": 0.1627, "step": 147410 }, { - "epoch": 0.66, - "learning_rate": 1.718465539661899e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.362956085993602e-05, + "loss": 0.1682, "step": 147420 }, { - "epoch": 0.66, - "learning_rate": 1.7182413344693064e-05, - "loss": 0.1636, + "epoch": 0.33, + "learning_rate": 3.36284423167267e-05, + "loss": 0.1598, "step": 147430 }, { - "epoch": 0.66, - "learning_rate": 1.7180171292767142e-05, - "loss": 0.1606, + "epoch": 0.33, + "learning_rate": 3.362732377351737e-05, + "loss": 0.1639, "step": 147440 }, { - "epoch": 0.66, - "learning_rate": 1.7177929240841218e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.362620523030805e-05, + "loss": 0.1618, "step": 147450 }, { - "epoch": 0.66, - "learning_rate": 1.7175687188915296e-05, - "loss": 0.1627, + "epoch": 0.33, + "learning_rate": 3.362508668709872e-05, + "loss": 0.162, "step": 147460 }, { - "epoch": 0.66, - "learning_rate": 1.7173445136989375e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.36239681438894e-05, + "loss": 0.1637, "step": 147470 }, { - "epoch": 0.66, - "learning_rate": 1.717120308506345e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3622849600680076e-05, + "loss": 0.1583, "step": 147480 }, { - "epoch": 0.66, - "learning_rate": 1.716896103313753e-05, - "loss": 0.1714, + "epoch": 0.33, + "learning_rate": 3.3621731057470754e-05, + "loss": 0.1605, "step": 147490 }, { - "epoch": 0.66, - "learning_rate": 1.7166718981211605e-05, - "loss": 0.1757, + "epoch": 0.33, + "learning_rate": 3.362061251426143e-05, + "loss": 0.1636, "step": 147500 }, { - "epoch": 0.66, - "learning_rate": 1.7164476929285683e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.36194939710521e-05, + "loss": 0.1628, "step": 147510 }, { - "epoch": 0.66, - "learning_rate": 1.716223487735976e-05, - "loss": 0.1669, + "epoch": 0.33, + "learning_rate": 3.361837542784278e-05, + "loss": 0.1586, "step": 147520 }, { - "epoch": 0.66, - "learning_rate": 1.7159992825433837e-05, - "loss": 0.1707, + "epoch": 0.33, + "learning_rate": 3.361725688463345e-05, + "loss": 0.16, "step": 147530 }, { - "epoch": 0.66, - "learning_rate": 1.7157750773507916e-05, - "loss": 0.1655, + "epoch": 0.33, + "learning_rate": 3.361613834142413e-05, + "loss": 0.1611, "step": 147540 }, { - "epoch": 0.66, - "learning_rate": 1.715550872158199e-05, - "loss": 0.1629, + "epoch": 0.33, + "learning_rate": 3.361501979821481e-05, + "loss": 0.1572, "step": 147550 }, { - "epoch": 0.66, - "learning_rate": 1.715326666965607e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.361390125500548e-05, + "loss": 0.1584, "step": 147560 }, { - "epoch": 0.66, - "learning_rate": 1.7151024617730145e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.361278271179616e-05, + "loss": 0.164, "step": 147570 }, { - "epoch": 0.66, - "learning_rate": 1.7148782565804224e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3611664168586835e-05, + "loss": 0.1631, "step": 147580 }, { - "epoch": 0.66, - "learning_rate": 1.7146540513878303e-05, - "loss": 0.1684, + "epoch": 0.33, + "learning_rate": 3.361054562537751e-05, + "loss": 0.1591, "step": 147590 }, { - "epoch": 0.66, - "learning_rate": 1.7144298461952378e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.360942708216819e-05, + "loss": 0.1645, "step": 147600 }, { - "epoch": 0.66, - "learning_rate": 1.7142056410026457e-05, - "loss": 0.1614, + "epoch": 0.33, + "learning_rate": 3.360830853895886e-05, + "loss": 0.1657, "step": 147610 }, { - "epoch": 0.66, - "learning_rate": 1.7139814358100532e-05, - "loss": 0.1728, + "epoch": 0.33, + "learning_rate": 3.360718999574954e-05, + "loss": 0.1562, "step": 147620 }, { - "epoch": 0.66, - "learning_rate": 1.713757230617461e-05, - "loss": 0.1699, + "epoch": 0.33, + "learning_rate": 3.360607145254021e-05, + "loss": 0.1602, "step": 147630 }, { - "epoch": 0.66, - "learning_rate": 1.713533025424869e-05, - "loss": 0.1723, + "epoch": 0.33, + "learning_rate": 3.360495290933089e-05, + "loss": 0.1576, "step": 147640 }, { - "epoch": 0.66, - "learning_rate": 1.713308820232277e-05, - "loss": 0.1607, + "epoch": 0.33, + "learning_rate": 3.3603834366121567e-05, + "loss": 0.1623, "step": 147650 }, { - "epoch": 0.66, - "learning_rate": 1.7130846150396844e-05, - "loss": 0.1631, + "epoch": 0.33, + "learning_rate": 3.360271582291224e-05, + "loss": 0.162, "step": 147660 }, { - "epoch": 0.66, - "learning_rate": 1.7128604098470922e-05, - "loss": 0.1714, + "epoch": 0.33, + "learning_rate": 3.3601597279702916e-05, + "loss": 0.166, "step": 147670 }, { - "epoch": 0.66, - "learning_rate": 1.7126362046545e-05, - "loss": 0.17, + "epoch": 0.33, + "learning_rate": 3.3600478736493594e-05, + "loss": 0.1655, "step": 147680 }, { - "epoch": 0.66, - "learning_rate": 1.7124119994619076e-05, - "loss": 0.1659, + "epoch": 0.33, + "learning_rate": 3.359936019328427e-05, + "loss": 0.1608, "step": 147690 }, { - "epoch": 0.66, - "learning_rate": 1.7121877942693155e-05, - "loss": 0.1699, + "epoch": 0.33, + "learning_rate": 3.359824165007495e-05, + "loss": 0.1677, "step": 147700 }, { - "epoch": 0.66, - "learning_rate": 1.711963589076723e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.359712310686562e-05, + "loss": 0.1633, "step": 147710 }, { - "epoch": 0.66, - "learning_rate": 1.711739383884131e-05, - "loss": 0.1653, + "epoch": 0.33, + "learning_rate": 3.35960045636563e-05, + "loss": 0.1602, "step": 147720 }, { - "epoch": 0.66, - "learning_rate": 1.7115151786915388e-05, - "loss": 0.1732, + "epoch": 0.33, + "learning_rate": 3.359488602044697e-05, + "loss": 0.1595, "step": 147730 }, { - "epoch": 0.66, - "learning_rate": 1.7112909734989463e-05, - "loss": 0.1689, + "epoch": 0.33, + "learning_rate": 3.359376747723765e-05, + "loss": 0.1633, "step": 147740 }, { - "epoch": 0.66, - "learning_rate": 1.7110667683063542e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.3592648934028326e-05, + "loss": 0.1653, "step": 147750 }, { - "epoch": 0.66, - "learning_rate": 1.7108425631137617e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.3591530390819e-05, + "loss": 0.1608, "step": 147760 }, { - "epoch": 0.66, - "learning_rate": 1.7106183579211696e-05, - "loss": 0.1679, + "epoch": 0.33, + "learning_rate": 3.3590411847609675e-05, + "loss": 0.1631, "step": 147770 }, { - "epoch": 0.66, - "learning_rate": 1.710394152728577e-05, - "loss": 0.1622, + "epoch": 0.33, + "learning_rate": 3.3589293304400346e-05, + "loss": 0.1607, "step": 147780 }, { - "epoch": 0.66, - "learning_rate": 1.710169947535985e-05, - "loss": 0.167, + "epoch": 0.33, + "learning_rate": 3.3588174761191024e-05, + "loss": 0.1609, "step": 147790 }, { - "epoch": 0.66, - "learning_rate": 1.709945742343393e-05, - "loss": 0.171, + "epoch": 0.33, + "learning_rate": 3.35870562179817e-05, + "loss": 0.159, "step": 147800 }, { - "epoch": 0.66, - "learning_rate": 1.7097215371508004e-05, - "loss": 0.1626, + "epoch": 0.33, + "learning_rate": 3.358593767477238e-05, + "loss": 0.1581, "step": 147810 }, { - "epoch": 0.66, - "learning_rate": 1.7094973319582083e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.358481913156306e-05, + "loss": 0.1602, "step": 147820 }, { - "epoch": 0.66, - "learning_rate": 1.7092731267656158e-05, - "loss": 0.1631, + "epoch": 0.33, + "learning_rate": 3.358370058835373e-05, + "loss": 0.1608, "step": 147830 }, { - "epoch": 0.66, - "learning_rate": 1.7090489215730237e-05, - "loss": 0.1624, + "epoch": 0.33, + "learning_rate": 3.3582582045144407e-05, + "loss": 0.1656, "step": 147840 }, { - "epoch": 0.66, - "learning_rate": 1.7088247163804312e-05, - "loss": 0.1663, + "epoch": 0.33, + "learning_rate": 3.358146350193508e-05, + "loss": 0.1615, "step": 147850 }, { - "epoch": 0.66, - "learning_rate": 1.708600511187839e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3580344958725756e-05, + "loss": 0.1644, "step": 147860 }, { - "epoch": 0.66, - "learning_rate": 1.708376305995247e-05, - "loss": 0.1671, + "epoch": 0.33, + "learning_rate": 3.3579226415516434e-05, + "loss": 0.1595, "step": 147870 }, { - "epoch": 0.66, - "learning_rate": 1.7081745213219137e-05, - "loss": 0.1672, + "epoch": 0.33, + "learning_rate": 3.3578107872307105e-05, + "loss": 0.1596, "step": 147880 }, { - "epoch": 0.66, - "learning_rate": 1.7079503161293216e-05, - "loss": 0.1739, + "epoch": 0.33, + "learning_rate": 3.357698932909778e-05, + "loss": 0.1659, "step": 147890 }, { - "epoch": 0.66, - "learning_rate": 1.707726110936729e-05, - "loss": 0.167, + "epoch": 0.33, + "learning_rate": 3.357587078588846e-05, + "loss": 0.1632, "step": 147900 }, { - "epoch": 0.66, - "learning_rate": 1.707501905744137e-05, - "loss": 0.1722, + "epoch": 0.33, + "learning_rate": 3.357475224267914e-05, + "loss": 0.159, "step": 147910 }, { - "epoch": 0.66, - "learning_rate": 1.707277700551545e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.3573633699469816e-05, + "loss": 0.1578, "step": 147920 }, { - "epoch": 0.66, - "learning_rate": 1.7070534953589524e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.357251515626049e-05, + "loss": 0.1631, "step": 147930 }, { - "epoch": 0.66, - "learning_rate": 1.7068292901663603e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3571396613051165e-05, + "loss": 0.1624, "step": 147940 }, { - "epoch": 0.66, - "learning_rate": 1.7066050849737682e-05, - "loss": 0.1647, + "epoch": 0.33, + "learning_rate": 3.357027806984184e-05, + "loss": 0.1588, "step": 147950 }, { - "epoch": 0.66, - "learning_rate": 1.706380879781176e-05, - "loss": 0.1759, + "epoch": 0.33, + "learning_rate": 3.3569159526632515e-05, + "loss": 0.1616, "step": 147960 }, { - "epoch": 0.66, - "learning_rate": 1.7061566745885836e-05, - "loss": 0.1668, + "epoch": 0.33, + "learning_rate": 3.356804098342319e-05, + "loss": 0.1617, "step": 147970 }, { - "epoch": 0.66, - "learning_rate": 1.7059324693959914e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3566922440213864e-05, + "loss": 0.1577, "step": 147980 }, { - "epoch": 0.66, - "learning_rate": 1.705708264203399e-05, - "loss": 0.1606, + "epoch": 0.33, + "learning_rate": 3.356580389700454e-05, + "loss": 0.163, "step": 147990 }, { - "epoch": 0.66, - "learning_rate": 1.705484059010807e-05, - "loss": 0.1691, + "epoch": 0.33, + "learning_rate": 3.356468535379522e-05, + "loss": 0.1594, "step": 148000 }, { - "epoch": 0.66, - "learning_rate": 1.7052598538182147e-05, - "loss": 0.1704, + "epoch": 0.33, + "learning_rate": 3.35635668105859e-05, + "loss": 0.1587, "step": 148010 }, { - "epoch": 0.66, - "learning_rate": 1.7050356486256223e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.3562448267376575e-05, + "loss": 0.1578, "step": 148020 }, { - "epoch": 0.66, - "learning_rate": 1.70481144343303e-05, - "loss": 0.1726, + "epoch": 0.33, + "learning_rate": 3.3561329724167247e-05, + "loss": 0.1609, "step": 148030 }, { - "epoch": 0.66, - "learning_rate": 1.7045872382404377e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.3560211180957924e-05, + "loss": 0.1586, "step": 148040 }, { - "epoch": 0.66, - "learning_rate": 1.7043630330478455e-05, - "loss": 0.1712, + "epoch": 0.33, + "learning_rate": 3.3559092637748596e-05, + "loss": 0.1599, "step": 148050 }, { - "epoch": 0.66, - "learning_rate": 1.704138827855253e-05, - "loss": 0.163, + "epoch": 0.33, + "learning_rate": 3.3557974094539274e-05, + "loss": 0.1587, "step": 148060 }, { - "epoch": 0.66, - "learning_rate": 1.703914622662661e-05, - "loss": 0.1691, + "epoch": 0.33, + "learning_rate": 3.355685555132995e-05, + "loss": 0.1594, "step": 148070 }, { - "epoch": 0.66, - "learning_rate": 1.7036904174700688e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.355573700812062e-05, + "loss": 0.1639, "step": 148080 }, { - "epoch": 0.66, - "learning_rate": 1.7034662122774763e-05, - "loss": 0.1687, + "epoch": 0.33, + "learning_rate": 3.35546184649113e-05, + "loss": 0.16, "step": 148090 }, { - "epoch": 0.66, - "learning_rate": 1.7032420070848842e-05, - "loss": 0.1717, + "epoch": 0.33, + "learning_rate": 3.355349992170198e-05, + "loss": 0.1631, "step": 148100 }, { - "epoch": 0.66, - "learning_rate": 1.7030178018922917e-05, - "loss": 0.163, + "epoch": 0.33, + "learning_rate": 3.3552381378492656e-05, + "loss": 0.1655, "step": 148110 }, { - "epoch": 0.66, - "learning_rate": 1.7027935966996996e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.3551262835283334e-05, + "loss": 0.1615, "step": 148120 }, { - "epoch": 0.66, - "learning_rate": 1.702569391507107e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.3550144292074005e-05, + "loss": 0.1626, "step": 148130 }, { - "epoch": 0.66, - "learning_rate": 1.702345186314515e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.354902574886468e-05, + "loss": 0.1621, "step": 148140 }, { - "epoch": 0.66, - "learning_rate": 1.702120981121923e-05, - "loss": 0.1646, + "epoch": 0.33, + "learning_rate": 3.3547907205655355e-05, + "loss": 0.1639, "step": 148150 }, { - "epoch": 0.66, - "learning_rate": 1.7018967759293304e-05, - "loss": 0.1638, + "epoch": 0.33, + "learning_rate": 3.354678866244603e-05, + "loss": 0.1605, "step": 148160 }, { - "epoch": 0.66, - "learning_rate": 1.7016725707367383e-05, - "loss": 0.1753, + "epoch": 0.33, + "learning_rate": 3.3545670119236704e-05, + "loss": 0.1609, "step": 148170 }, { - "epoch": 0.66, - "learning_rate": 1.701448365544146e-05, - "loss": 0.1622, + "epoch": 0.33, + "learning_rate": 3.354455157602738e-05, + "loss": 0.1629, "step": 148180 }, { - "epoch": 0.66, - "learning_rate": 1.7012241603515537e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.354343303281806e-05, + "loss": 0.1596, "step": 148190 }, { - "epoch": 0.66, - "learning_rate": 1.7009999551589616e-05, - "loss": 0.1719, + "epoch": 0.33, + "learning_rate": 3.354231448960873e-05, + "loss": 0.1566, "step": 148200 }, { - "epoch": 0.66, - "learning_rate": 1.7007757499663694e-05, - "loss": 0.1754, + "epoch": 0.33, + "learning_rate": 3.354119594639941e-05, + "loss": 0.1553, "step": 148210 }, { - "epoch": 0.66, - "learning_rate": 1.700551544773777e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3540077403190086e-05, + "loss": 0.1626, "step": 148220 }, { - "epoch": 0.66, - "learning_rate": 1.700327339581185e-05, - "loss": 0.1629, + "epoch": 0.33, + "learning_rate": 3.3538958859980764e-05, + "loss": 0.1639, "step": 148230 }, { - "epoch": 0.66, - "learning_rate": 1.7001031343885927e-05, - "loss": 0.1725, + "epoch": 0.33, + "learning_rate": 3.353784031677144e-05, + "loss": 0.1555, "step": 148240 }, { - "epoch": 0.66, - "learning_rate": 1.6998789291960003e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.3536721773562113e-05, + "loss": 0.1588, "step": 148250 }, { - "epoch": 0.66, - "learning_rate": 1.699654724003408e-05, - "loss": 0.174, + "epoch": 0.33, + "learning_rate": 3.353560323035279e-05, + "loss": 0.1601, "step": 148260 }, { - "epoch": 0.66, - "learning_rate": 1.6994305188108157e-05, - "loss": 0.1648, + "epoch": 0.33, + "learning_rate": 3.353448468714346e-05, + "loss": 0.1591, "step": 148270 }, { - "epoch": 0.66, - "learning_rate": 1.6992063136182235e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.353336614393414e-05, + "loss": 0.1628, "step": 148280 }, { - "epoch": 0.66, - "learning_rate": 1.6989821084256314e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.353224760072482e-05, + "loss": 0.1609, "step": 148290 }, { - "epoch": 0.66, - "learning_rate": 1.698757903233039e-05, - "loss": 0.1663, + "epoch": 0.33, + "learning_rate": 3.353112905751549e-05, + "loss": 0.1601, "step": 148300 }, { - "epoch": 0.66, - "learning_rate": 1.6985336980404468e-05, - "loss": 0.1686, + "epoch": 0.33, + "learning_rate": 3.353001051430617e-05, + "loss": 0.1632, "step": 148310 }, { - "epoch": 0.66, - "learning_rate": 1.6983094928478543e-05, - "loss": 0.173, + "epoch": 0.33, + "learning_rate": 3.3528891971096845e-05, + "loss": 0.1617, "step": 148320 }, { - "epoch": 0.66, - "learning_rate": 1.6980852876552622e-05, - "loss": 0.1722, + "epoch": 0.33, + "learning_rate": 3.352777342788752e-05, + "loss": 0.1636, "step": 148330 }, { - "epoch": 0.66, - "learning_rate": 1.6978610824626697e-05, - "loss": 0.1709, + "epoch": 0.33, + "learning_rate": 3.35266548846782e-05, + "loss": 0.1632, "step": 148340 }, { - "epoch": 0.66, - "learning_rate": 1.6976368772700776e-05, - "loss": 0.1636, + "epoch": 0.33, + "learning_rate": 3.352553634146887e-05, + "loss": 0.1664, "step": 148350 }, { - "epoch": 0.66, - "learning_rate": 1.6974126720774855e-05, - "loss": 0.1724, + "epoch": 0.33, + "learning_rate": 3.352441779825955e-05, + "loss": 0.1671, "step": 148360 }, { - "epoch": 0.66, - "learning_rate": 1.697188466884893e-05, - "loss": 0.1655, + "epoch": 0.33, + "learning_rate": 3.352329925505022e-05, + "loss": 0.1592, "step": 148370 }, { - "epoch": 0.66, - "learning_rate": 1.696964261692301e-05, - "loss": 0.1658, + "epoch": 0.33, + "learning_rate": 3.35221807118409e-05, + "loss": 0.1667, "step": 148380 }, { - "epoch": 0.66, - "learning_rate": 1.6967400564997084e-05, - "loss": 0.166, + "epoch": 0.33, + "learning_rate": 3.352106216863158e-05, + "loss": 0.1633, "step": 148390 }, { - "epoch": 0.66, - "learning_rate": 1.6965158513071163e-05, - "loss": 0.1723, + "epoch": 0.33, + "learning_rate": 3.351994362542225e-05, + "loss": 0.1603, "step": 148400 }, { - "epoch": 0.66, - "learning_rate": 1.696291646114524e-05, - "loss": 0.1672, + "epoch": 0.33, + "learning_rate": 3.3518825082212926e-05, + "loss": 0.1607, "step": 148410 }, { - "epoch": 0.66, - "learning_rate": 1.6960674409219317e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.3517706539003604e-05, + "loss": 0.1567, "step": 148420 }, { - "epoch": 0.66, - "learning_rate": 1.6958432357293396e-05, - "loss": 0.1679, + "epoch": 0.33, + "learning_rate": 3.351658799579428e-05, + "loss": 0.1584, "step": 148430 }, { - "epoch": 0.66, - "learning_rate": 1.695619030536747e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.3515469452584953e-05, + "loss": 0.1636, "step": 148440 }, { - "epoch": 0.66, - "learning_rate": 1.695394825344155e-05, - "loss": 0.1679, + "epoch": 0.33, + "learning_rate": 3.351435090937563e-05, + "loss": 0.1598, "step": 148450 }, { - "epoch": 0.66, - "learning_rate": 1.695170620151563e-05, - "loss": 0.1622, + "epoch": 0.33, + "learning_rate": 3.351323236616631e-05, + "loss": 0.1623, "step": 148460 }, { - "epoch": 0.66, - "learning_rate": 1.6949464149589704e-05, - "loss": 0.1663, + "epoch": 0.33, + "learning_rate": 3.351211382295698e-05, + "loss": 0.1588, "step": 148470 }, { - "epoch": 0.66, - "learning_rate": 1.6947222097663783e-05, - "loss": 0.1647, + "epoch": 0.33, + "learning_rate": 3.351099527974766e-05, + "loss": 0.1637, "step": 148480 }, { - "epoch": 0.66, - "learning_rate": 1.694498004573786e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.350987673653833e-05, + "loss": 0.1597, "step": 148490 }, { - "epoch": 0.66, - "learning_rate": 1.694273799381194e-05, - "loss": 0.1703, + "epoch": 0.33, + "learning_rate": 3.350875819332901e-05, + "loss": 0.161, "step": 148500 }, { - "epoch": 0.66, - "learning_rate": 1.6940495941886015e-05, - "loss": 0.1716, + "epoch": 0.33, + "learning_rate": 3.3507639650119685e-05, + "loss": 0.1586, "step": 148510 }, { - "epoch": 0.66, - "learning_rate": 1.6938253889960094e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.350652110691036e-05, + "loss": 0.1545, "step": 148520 }, { - "epoch": 0.66, - "learning_rate": 1.693601183803417e-05, - "loss": 0.1674, + "epoch": 0.33, + "learning_rate": 3.350540256370104e-05, + "loss": 0.1598, "step": 148530 }, { - "epoch": 0.66, - "learning_rate": 1.6933769786108248e-05, - "loss": 0.1676, + "epoch": 0.33, + "learning_rate": 3.350428402049171e-05, + "loss": 0.1634, "step": 148540 }, { - "epoch": 0.66, - "learning_rate": 1.6931527734182327e-05, - "loss": 0.1716, + "epoch": 0.33, + "learning_rate": 3.350316547728239e-05, + "loss": 0.1588, "step": 148550 }, { - "epoch": 0.66, - "learning_rate": 1.6929285682256402e-05, - "loss": 0.1639, + "epoch": 0.33, + "learning_rate": 3.350204693407307e-05, + "loss": 0.1638, "step": 148560 }, { - "epoch": 0.66, - "learning_rate": 1.692704363033048e-05, - "loss": 0.1671, + "epoch": 0.33, + "learning_rate": 3.350092839086374e-05, + "loss": 0.1631, "step": 148570 }, { - "epoch": 0.66, - "learning_rate": 1.6924801578404556e-05, - "loss": 0.1723, + "epoch": 0.33, + "learning_rate": 3.349980984765442e-05, + "loss": 0.1587, "step": 148580 }, { - "epoch": 0.66, - "learning_rate": 1.6922559526478635e-05, - "loss": 0.1726, + "epoch": 0.33, + "learning_rate": 3.349869130444509e-05, + "loss": 0.1648, "step": 148590 }, { - "epoch": 0.66, - "learning_rate": 1.692031747455271e-05, - "loss": 0.1635, + "epoch": 0.33, + "learning_rate": 3.3497572761235766e-05, + "loss": 0.1629, "step": 148600 }, { - "epoch": 0.66, - "learning_rate": 1.691807542262679e-05, - "loss": 0.1665, + "epoch": 0.33, + "learning_rate": 3.3496454218026444e-05, + "loss": 0.1565, "step": 148610 }, { - "epoch": 0.66, - "learning_rate": 1.6915833370700868e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.3495335674817115e-05, + "loss": 0.1585, "step": 148620 }, { - "epoch": 0.66, - "learning_rate": 1.6913591318774943e-05, - "loss": 0.1687, + "epoch": 0.33, + "learning_rate": 3.34942171316078e-05, + "loss": 0.1626, "step": 148630 }, { - "epoch": 0.66, - "learning_rate": 1.6911349266849022e-05, - "loss": 0.1642, + "epoch": 0.33, + "learning_rate": 3.349309858839847e-05, + "loss": 0.1652, "step": 148640 }, { - "epoch": 0.66, - "learning_rate": 1.6909107214923097e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.349198004518915e-05, + "loss": 0.1603, "step": 148650 }, { - "epoch": 0.66, - "learning_rate": 1.6906865162997176e-05, - "loss": 0.1648, + "epoch": 0.33, + "learning_rate": 3.349086150197983e-05, + "loss": 0.1585, "step": 148660 }, { - "epoch": 0.66, - "learning_rate": 1.690462311107125e-05, - "loss": 0.1612, + "epoch": 0.33, + "learning_rate": 3.34897429587705e-05, + "loss": 0.1685, "step": 148670 }, { - "epoch": 0.66, - "learning_rate": 1.690238105914533e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3488624415561176e-05, + "loss": 0.1547, "step": 148680 }, { - "epoch": 0.66, - "learning_rate": 1.690013900721941e-05, - "loss": 0.1728, + "epoch": 0.33, + "learning_rate": 3.348750587235185e-05, + "loss": 0.1584, "step": 148690 }, { - "epoch": 0.66, - "learning_rate": 1.6897896955293484e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.3486387329142525e-05, + "loss": 0.1625, "step": 148700 }, { - "epoch": 0.66, - "learning_rate": 1.6895654903367563e-05, - "loss": 0.169, + "epoch": 0.33, + "learning_rate": 3.34852687859332e-05, + "loss": 0.1622, "step": 148710 }, { - "epoch": 0.66, - "learning_rate": 1.6893412851441638e-05, - "loss": 0.1642, + "epoch": 0.33, + "learning_rate": 3.3484150242723874e-05, + "loss": 0.162, "step": 148720 }, { - "epoch": 0.66, - "learning_rate": 1.6891170799515717e-05, - "loss": 0.1727, + "epoch": 0.33, + "learning_rate": 3.348303169951455e-05, + "loss": 0.1612, "step": 148730 }, { - "epoch": 0.66, - "learning_rate": 1.6888928747589795e-05, - "loss": 0.1711, + "epoch": 0.33, + "learning_rate": 3.348191315630523e-05, + "loss": 0.1669, "step": 148740 }, { - "epoch": 0.66, - "learning_rate": 1.6886686695663874e-05, - "loss": 0.1742, + "epoch": 0.33, + "learning_rate": 3.348079461309591e-05, + "loss": 0.1629, "step": 148750 }, { - "epoch": 0.66, - "learning_rate": 1.688444464373795e-05, - "loss": 0.1718, + "epoch": 0.33, + "learning_rate": 3.347967606988658e-05, + "loss": 0.16, "step": 148760 }, { - "epoch": 0.66, - "learning_rate": 1.6882202591812028e-05, - "loss": 0.1713, + "epoch": 0.33, + "learning_rate": 3.347855752667726e-05, + "loss": 0.1576, "step": 148770 }, { - "epoch": 0.66, - "learning_rate": 1.6879960539886107e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.3477438983467935e-05, + "loss": 0.1627, "step": 148780 }, { - "epoch": 0.66, - "learning_rate": 1.6877718487960182e-05, - "loss": 0.1714, + "epoch": 0.33, + "learning_rate": 3.3476320440258606e-05, + "loss": 0.1652, "step": 148790 }, { - "epoch": 0.66, - "learning_rate": 1.687547643603426e-05, - "loss": 0.1701, + "epoch": 0.33, + "learning_rate": 3.3475201897049284e-05, + "loss": 0.1612, "step": 148800 }, { - "epoch": 0.66, - "learning_rate": 1.6873234384108336e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3474083353839955e-05, + "loss": 0.1532, "step": 148810 }, { - "epoch": 0.66, - "learning_rate": 1.6870992332182415e-05, - "loss": 0.1738, + "epoch": 0.33, + "learning_rate": 3.347296481063063e-05, + "loss": 0.1592, "step": 148820 }, { - "epoch": 0.66, - "learning_rate": 1.6868750280256494e-05, - "loss": 0.1662, + "epoch": 0.33, + "learning_rate": 3.347184626742131e-05, + "loss": 0.1602, "step": 148830 }, { - "epoch": 0.66, - "learning_rate": 1.686650822833057e-05, - "loss": 0.1605, + "epoch": 0.33, + "learning_rate": 3.347072772421199e-05, + "loss": 0.1601, "step": 148840 }, { - "epoch": 0.66, - "learning_rate": 1.6864266176404648e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.346960918100267e-05, + "loss": 0.1584, "step": 148850 }, { - "epoch": 0.66, - "learning_rate": 1.6862024124478723e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.346849063779334e-05, + "loss": 0.1573, "step": 148860 }, { - "epoch": 0.66, - "learning_rate": 1.6859782072552802e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.3467372094584016e-05, + "loss": 0.1609, "step": 148870 }, { - "epoch": 0.66, - "learning_rate": 1.6857540020626877e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.3466253551374694e-05, + "loss": 0.1612, "step": 148880 }, { - "epoch": 0.66, - "learning_rate": 1.6855297968700956e-05, - "loss": 0.1651, + "epoch": 0.33, + "learning_rate": 3.3465135008165365e-05, + "loss": 0.16, "step": 148890 }, { - "epoch": 0.66, - "learning_rate": 1.6853055916775035e-05, - "loss": 0.1633, + "epoch": 0.33, + "learning_rate": 3.346401646495604e-05, + "loss": 0.1607, "step": 148900 }, { - "epoch": 0.66, - "learning_rate": 1.685081386484911e-05, - "loss": 0.1656, + "epoch": 0.33, + "learning_rate": 3.3462897921746714e-05, + "loss": 0.162, "step": 148910 }, { - "epoch": 0.66, - "learning_rate": 1.684857181292319e-05, - "loss": 0.163, + "epoch": 0.33, + "learning_rate": 3.346177937853739e-05, + "loss": 0.1659, "step": 148920 }, { - "epoch": 0.66, - "learning_rate": 1.6846329760997264e-05, - "loss": 0.166, + "epoch": 0.33, + "learning_rate": 3.346066083532807e-05, + "loss": 0.1611, "step": 148930 }, { - "epoch": 0.66, - "learning_rate": 1.6844087709071343e-05, - "loss": 0.1653, + "epoch": 0.33, + "learning_rate": 3.345954229211875e-05, + "loss": 0.1617, "step": 148940 }, { - "epoch": 0.66, - "learning_rate": 1.6841845657145418e-05, - "loss": 0.1702, + "epoch": 0.33, + "learning_rate": 3.3458423748909426e-05, + "loss": 0.162, "step": 148950 }, { - "epoch": 0.66, - "learning_rate": 1.6839603605219497e-05, - "loss": 0.1682, + "epoch": 0.33, + "learning_rate": 3.34573052057001e-05, + "loss": 0.1604, "step": 148960 }, { - "epoch": 0.67, - "learning_rate": 1.6837361553293575e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.3456186662490775e-05, + "loss": 0.159, "step": 148970 }, { - "epoch": 0.67, - "learning_rate": 1.683511950136765e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.345506811928145e-05, + "loss": 0.1588, "step": 148980 }, { - "epoch": 0.67, - "learning_rate": 1.683287744944173e-05, - "loss": 0.1619, + "epoch": 0.33, + "learning_rate": 3.3453949576072124e-05, + "loss": 0.1555, "step": 148990 }, { - "epoch": 0.67, - "learning_rate": 1.6830635397515808e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.34528310328628e-05, + "loss": 0.1588, "step": 149000 }, { - "epoch": 0.67, - "learning_rate": 1.6828393345589883e-05, - "loss": 0.1691, + "epoch": 0.33, + "learning_rate": 3.345171248965347e-05, + "loss": 0.1609, "step": 149010 }, { - "epoch": 0.67, - "learning_rate": 1.6826151293663962e-05, - "loss": 0.165, + "epoch": 0.33, + "learning_rate": 3.345059394644415e-05, + "loss": 0.1635, "step": 149020 }, { - "epoch": 0.67, - "learning_rate": 1.682390924173804e-05, - "loss": 0.165, + "epoch": 0.33, + "learning_rate": 3.344947540323483e-05, + "loss": 0.1622, "step": 149030 }, { - "epoch": 0.67, - "learning_rate": 1.682166718981212e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.34483568600255e-05, + "loss": 0.1589, "step": 149040 }, { - "epoch": 0.67, - "learning_rate": 1.6819425137886195e-05, - "loss": 0.1686, + "epoch": 0.33, + "learning_rate": 3.3447238316816185e-05, + "loss": 0.1613, "step": 149050 }, { - "epoch": 0.67, - "learning_rate": 1.6817183085960274e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.3446119773606856e-05, + "loss": 0.1576, "step": 149060 }, { - "epoch": 0.67, - "learning_rate": 1.681494103403435e-05, - "loss": 0.1585, + "epoch": 0.33, + "learning_rate": 3.3445001230397534e-05, + "loss": 0.1615, "step": 149070 }, { - "epoch": 0.67, - "learning_rate": 1.6812698982108428e-05, - "loss": 0.1692, + "epoch": 0.33, + "learning_rate": 3.3443882687188205e-05, + "loss": 0.1645, "step": 149080 }, { - "epoch": 0.67, - "learning_rate": 1.6810456930182503e-05, - "loss": 0.1669, + "epoch": 0.33, + "learning_rate": 3.344276414397888e-05, + "loss": 0.1604, "step": 149090 }, { - "epoch": 0.67, - "learning_rate": 1.6808214878256582e-05, - "loss": 0.1671, + "epoch": 0.33, + "learning_rate": 3.344164560076956e-05, + "loss": 0.1644, "step": 149100 }, { - "epoch": 0.67, - "learning_rate": 1.680597282633066e-05, - "loss": 0.1672, + "epoch": 0.33, + "learning_rate": 3.344052705756023e-05, + "loss": 0.1615, "step": 149110 }, { - "epoch": 0.67, - "learning_rate": 1.6803730774404736e-05, - "loss": 0.1673, + "epoch": 0.33, + "learning_rate": 3.343940851435091e-05, + "loss": 0.1605, "step": 149120 }, { - "epoch": 0.67, - "learning_rate": 1.6801488722478815e-05, - "loss": 0.1674, + "epoch": 0.33, + "learning_rate": 3.343828997114158e-05, + "loss": 0.16, "step": 149130 }, { - "epoch": 0.67, - "learning_rate": 1.679924667055289e-05, - "loss": 0.1684, + "epoch": 0.33, + "learning_rate": 3.343717142793226e-05, + "loss": 0.165, "step": 149140 }, { - "epoch": 0.67, - "learning_rate": 1.679700461862697e-05, - "loss": 0.1633, + "epoch": 0.33, + "learning_rate": 3.343605288472294e-05, + "loss": 0.1615, "step": 149150 }, { - "epoch": 0.67, - "learning_rate": 1.6794762566701044e-05, - "loss": 0.1692, + "epoch": 0.33, + "learning_rate": 3.3434934341513615e-05, + "loss": 0.1613, "step": 149160 }, { - "epoch": 0.67, - "learning_rate": 1.6792520514775123e-05, - "loss": 0.1703, + "epoch": 0.33, + "learning_rate": 3.343381579830429e-05, + "loss": 0.1634, "step": 149170 }, { - "epoch": 0.67, - "learning_rate": 1.67902784628492e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.3432697255094964e-05, + "loss": 0.1613, "step": 149180 }, { - "epoch": 0.67, - "learning_rate": 1.6788036410923277e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.343157871188564e-05, + "loss": 0.1635, "step": 149190 }, { - "epoch": 0.67, - "learning_rate": 1.6785794358997355e-05, - "loss": 0.1694, + "epoch": 0.33, + "learning_rate": 3.343046016867632e-05, + "loss": 0.1663, "step": 149200 }, { - "epoch": 0.67, - "learning_rate": 1.678355230707143e-05, - "loss": 0.1649, + "epoch": 0.33, + "learning_rate": 3.342934162546699e-05, + "loss": 0.1625, "step": 149210 }, { - "epoch": 0.67, - "learning_rate": 1.678131025514551e-05, - "loss": 0.1687, + "epoch": 0.33, + "learning_rate": 3.342822308225767e-05, + "loss": 0.1644, "step": 149220 }, { - "epoch": 0.67, - "learning_rate": 1.6779068203219585e-05, - "loss": 0.1705, + "epoch": 0.33, + "learning_rate": 3.342710453904834e-05, + "loss": 0.1618, "step": 149230 }, { - "epoch": 0.67, - "learning_rate": 1.6776826151293663e-05, - "loss": 0.1659, + "epoch": 0.33, + "learning_rate": 3.342598599583902e-05, + "loss": 0.1576, "step": 149240 }, { - "epoch": 0.67, - "learning_rate": 1.6774584099367742e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.3424867452629696e-05, + "loss": 0.166, "step": 149250 }, { - "epoch": 0.67, - "learning_rate": 1.6772342047441818e-05, - "loss": 0.1654, + "epoch": 0.33, + "learning_rate": 3.3423748909420374e-05, + "loss": 0.1528, "step": 149260 }, { - "epoch": 0.67, - "learning_rate": 1.6770099995515896e-05, - "loss": 0.1711, + "epoch": 0.33, + "learning_rate": 3.342263036621105e-05, + "loss": 0.1638, "step": 149270 }, { - "epoch": 0.67, - "learning_rate": 1.6767857943589975e-05, - "loss": 0.1696, + "epoch": 0.33, + "learning_rate": 3.342151182300172e-05, + "loss": 0.1613, "step": 149280 }, { - "epoch": 0.67, - "learning_rate": 1.6765615891664054e-05, - "loss": 0.1666, + "epoch": 0.33, + "learning_rate": 3.34203932797924e-05, + "loss": 0.1606, "step": 149290 }, { - "epoch": 0.67, - "learning_rate": 1.676337383973813e-05, - "loss": 0.1657, + "epoch": 0.33, + "learning_rate": 3.341927473658308e-05, + "loss": 0.16, "step": 149300 }, { - "epoch": 0.67, - "learning_rate": 1.6761131787812208e-05, - "loss": 0.1743, + "epoch": 0.33, + "learning_rate": 3.341815619337375e-05, + "loss": 0.166, "step": 149310 }, { - "epoch": 0.67, - "learning_rate": 1.6758889735886286e-05, + "epoch": 0.33, + "learning_rate": 3.341703765016443e-05, "loss": 0.167, "step": 149320 }, { - "epoch": 0.67, - "learning_rate": 1.6756647683960362e-05, - "loss": 0.1677, + "epoch": 0.33, + "learning_rate": 3.34159191069551e-05, + "loss": 0.1586, "step": 149330 }, { - "epoch": 0.67, - "learning_rate": 1.675440563203444e-05, - "loss": 0.1674, + "epoch": 0.33, + "learning_rate": 3.341480056374578e-05, + "loss": 0.1594, "step": 149340 }, { - "epoch": 0.67, - "learning_rate": 1.6752163580108516e-05, - "loss": 0.1641, + "epoch": 0.33, + "learning_rate": 3.3413682020536455e-05, + "loss": 0.1551, "step": 149350 }, { - "epoch": 0.67, - "learning_rate": 1.6749921528182595e-05, - "loss": 0.167, + "epoch": 0.33, + "learning_rate": 3.341256347732713e-05, + "loss": 0.1575, "step": 149360 }, { - "epoch": 0.67, - "learning_rate": 1.674767947625667e-05, - "loss": 0.1719, + "epoch": 0.33, + "learning_rate": 3.341144493411781e-05, + "loss": 0.1645, "step": 149370 }, { - "epoch": 0.67, - "learning_rate": 1.674543742433075e-05, - "loss": 0.1617, + "epoch": 0.33, + "learning_rate": 3.341032639090848e-05, + "loss": 0.1639, "step": 149380 }, { - "epoch": 0.67, - "learning_rate": 1.6743195372404827e-05, - "loss": 0.1647, + "epoch": 0.33, + "learning_rate": 3.340920784769916e-05, + "loss": 0.1609, "step": 149390 }, { - "epoch": 0.67, - "learning_rate": 1.6740953320478903e-05, - "loss": 0.1676, + "epoch": 0.33, + "learning_rate": 3.340808930448983e-05, + "loss": 0.1646, "step": 149400 }, { - "epoch": 0.67, - "learning_rate": 1.673871126855298e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.340697076128051e-05, + "loss": 0.1627, "step": 149410 }, { - "epoch": 0.67, - "learning_rate": 1.6736469216627057e-05, - "loss": 0.1699, + "epoch": 0.33, + "learning_rate": 3.340585221807119e-05, + "loss": 0.1644, "step": 149420 }, { - "epoch": 0.67, - "learning_rate": 1.6734227164701135e-05, - "loss": 0.1642, + "epoch": 0.33, + "learning_rate": 3.340473367486186e-05, + "loss": 0.1634, "step": 149430 }, { - "epoch": 0.67, - "learning_rate": 1.673198511277521e-05, - "loss": 0.1638, + "epoch": 0.33, + "learning_rate": 3.3403615131652536e-05, + "loss": 0.1566, "step": 149440 }, { - "epoch": 0.67, - "learning_rate": 1.672974306084929e-05, - "loss": 0.1688, + "epoch": 0.33, + "learning_rate": 3.340249658844321e-05, + "loss": 0.1624, "step": 149450 }, { - "epoch": 0.67, - "learning_rate": 1.6727501008923368e-05, - "loss": 0.1717, + "epoch": 0.33, + "learning_rate": 3.340137804523389e-05, + "loss": 0.1606, "step": 149460 }, { - "epoch": 0.67, - "learning_rate": 1.6725258956997444e-05, - "loss": 0.1708, + "epoch": 0.33, + "learning_rate": 3.340025950202457e-05, + "loss": 0.161, "step": 149470 }, { - "epoch": 0.67, - "learning_rate": 1.6723016905071522e-05, - "loss": 0.169, + "epoch": 0.33, + "learning_rate": 3.339914095881524e-05, + "loss": 0.1589, "step": 149480 }, { - "epoch": 0.67, - "learning_rate": 1.6720774853145598e-05, - "loss": 0.1659, + "epoch": 0.33, + "learning_rate": 3.339813426992685e-05, + "loss": 0.16, "step": 149490 }, { - "epoch": 0.67, - "learning_rate": 1.6718532801219676e-05, - "loss": 0.1665, + "epoch": 0.33, + "learning_rate": 3.339701572671752e-05, + "loss": 0.1602, "step": 149500 }, { - "epoch": 0.67, - "learning_rate": 1.671629074929375e-05, - "loss": 0.1665, + "epoch": 0.33, + "learning_rate": 3.33958971835082e-05, + "loss": 0.1664, "step": 149510 }, { - "epoch": 0.67, - "learning_rate": 1.671404869736783e-05, - "loss": 0.1647, + "epoch": 0.33, + "learning_rate": 3.339477864029888e-05, + "loss": 0.1619, "step": 149520 }, { - "epoch": 0.67, - "learning_rate": 1.671180664544191e-05, - "loss": 0.1689, + "epoch": 0.33, + "learning_rate": 3.3393660097089555e-05, + "loss": 0.1655, "step": 149530 }, { - "epoch": 0.67, - "learning_rate": 1.6709564593515988e-05, - "loss": 0.1731, + "epoch": 0.33, + "learning_rate": 3.339254155388023e-05, + "loss": 0.1574, "step": 149540 }, { - "epoch": 0.67, - "learning_rate": 1.6707322541590063e-05, - "loss": 0.1704, + "epoch": 0.33, + "learning_rate": 3.3391423010670904e-05, + "loss": 0.1596, "step": 149550 }, { - "epoch": 0.67, - "learning_rate": 1.6705080489664142e-05, - "loss": 0.1687, + "epoch": 0.33, + "learning_rate": 3.339030446746158e-05, + "loss": 0.1615, "step": 149560 }, { - "epoch": 0.67, - "learning_rate": 1.670283843773822e-05, - "loss": 0.1609, + "epoch": 0.33, + "learning_rate": 3.338918592425225e-05, + "loss": 0.1617, "step": 149570 }, { - "epoch": 0.67, - "learning_rate": 1.6700596385812296e-05, - "loss": 0.1626, + "epoch": 0.33, + "learning_rate": 3.338806738104293e-05, + "loss": 0.1575, "step": 149580 }, { - "epoch": 0.67, - "learning_rate": 1.6698354333886375e-05, - "loss": 0.1631, + "epoch": 0.33, + "learning_rate": 3.338694883783361e-05, + "loss": 0.1634, "step": 149590 }, { - "epoch": 0.67, - "learning_rate": 1.6696112281960453e-05, - "loss": 0.1669, + "epoch": 0.33, + "learning_rate": 3.338583029462428e-05, + "loss": 0.1625, "step": 149600 }, { - "epoch": 0.67, - "learning_rate": 1.669387023003453e-05, - "loss": 0.163, + "epoch": 0.33, + "learning_rate": 3.338471175141496e-05, + "loss": 0.1603, "step": 149610 }, { - "epoch": 0.67, - "learning_rate": 1.6691628178108607e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.338359320820563e-05, + "loss": 0.1595, "step": 149620 }, { - "epoch": 0.67, - "learning_rate": 1.6689386126182683e-05, - "loss": 0.1641, + "epoch": 0.33, + "learning_rate": 3.3382474664996314e-05, + "loss": 0.1565, "step": 149630 }, { - "epoch": 0.67, - "learning_rate": 1.668714407425676e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.338135612178699e-05, + "loss": 0.1616, "step": 149640 }, { - "epoch": 0.67, - "learning_rate": 1.6684902022330837e-05, - "loss": 0.1684, + "epoch": 0.33, + "learning_rate": 3.338023757857766e-05, + "loss": 0.1579, "step": 149650 }, { - "epoch": 0.67, - "learning_rate": 1.6682659970404915e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.337911903536834e-05, + "loss": 0.16, "step": 149660 }, { - "epoch": 0.67, - "learning_rate": 1.6680417918478994e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.337800049215901e-05, + "loss": 0.1587, "step": 149670 }, { - "epoch": 0.67, - "learning_rate": 1.667817586655307e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.337688194894969e-05, + "loss": 0.1638, "step": 149680 }, { - "epoch": 0.67, - "learning_rate": 1.6675933814627148e-05, - "loss": 0.1672, + "epoch": 0.33, + "learning_rate": 3.337576340574037e-05, + "loss": 0.1668, "step": 149690 }, { - "epoch": 0.67, - "learning_rate": 1.6673691762701224e-05, - "loss": 0.1611, + "epoch": 0.33, + "learning_rate": 3.337464486253104e-05, + "loss": 0.1609, "step": 149700 }, { - "epoch": 0.67, - "learning_rate": 1.6671449710775302e-05, - "loss": 0.1617, + "epoch": 0.33, + "learning_rate": 3.337352631932172e-05, + "loss": 0.1559, "step": 149710 }, { - "epoch": 0.67, - "learning_rate": 1.6669207658849378e-05, - "loss": 0.1644, + "epoch": 0.33, + "learning_rate": 3.337240777611239e-05, + "loss": 0.1604, "step": 149720 }, { - "epoch": 0.67, - "learning_rate": 1.6666965606923456e-05, - "loss": 0.1692, + "epoch": 0.33, + "learning_rate": 3.3371289232903066e-05, + "loss": 0.1652, "step": 149730 }, { - "epoch": 0.67, - "learning_rate": 1.6664723554997535e-05, - "loss": 0.1741, + "epoch": 0.33, + "learning_rate": 3.3370170689693744e-05, + "loss": 0.1606, "step": 149740 }, { - "epoch": 0.67, - "learning_rate": 1.666248150307161e-05, - "loss": 0.1641, + "epoch": 0.33, + "learning_rate": 3.336905214648442e-05, + "loss": 0.1578, "step": 149750 }, { - "epoch": 0.67, - "learning_rate": 1.666023945114569e-05, - "loss": 0.165, + "epoch": 0.33, + "learning_rate": 3.33679336032751e-05, + "loss": 0.1632, "step": 149760 }, { - "epoch": 0.67, - "learning_rate": 1.6657997399219764e-05, - "loss": 0.1706, + "epoch": 0.33, + "learning_rate": 3.336681506006577e-05, + "loss": 0.1633, "step": 149770 }, { - "epoch": 0.67, - "learning_rate": 1.6655755347293843e-05, - "loss": 0.1678, + "epoch": 0.33, + "learning_rate": 3.336569651685645e-05, + "loss": 0.1556, "step": 149780 }, { - "epoch": 0.67, - "learning_rate": 1.6653513295367922e-05, - "loss": 0.1715, + "epoch": 0.33, + "learning_rate": 3.336457797364712e-05, + "loss": 0.1635, "step": 149790 }, { - "epoch": 0.67, - "learning_rate": 1.6651271243441997e-05, - "loss": 0.1628, + "epoch": 0.33, + "learning_rate": 3.33634594304378e-05, + "loss": 0.1633, "step": 149800 }, { - "epoch": 0.67, - "learning_rate": 1.6649029191516076e-05, - "loss": 0.174, + "epoch": 0.33, + "learning_rate": 3.3362340887228476e-05, + "loss": 0.1654, "step": 149810 }, { - "epoch": 0.67, - "learning_rate": 1.6646787139590155e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.336122234401915e-05, + "loss": 0.1642, "step": 149820 }, { - "epoch": 0.67, - "learning_rate": 1.6644545087664233e-05, - "loss": 0.1685, + "epoch": 0.33, + "learning_rate": 3.3360103800809825e-05, + "loss": 0.163, "step": 149830 }, { - "epoch": 0.67, - "learning_rate": 1.664230303573831e-05, - "loss": 0.1713, + "epoch": 0.33, + "learning_rate": 3.33589852576005e-05, + "loss": 0.1649, "step": 149840 }, { - "epoch": 0.67, - "learning_rate": 1.6640060983812387e-05, - "loss": 0.1684, + "epoch": 0.33, + "learning_rate": 3.335786671439118e-05, + "loss": 0.1588, "step": 149850 }, { - "epoch": 0.67, - "learning_rate": 1.6637818931886463e-05, - "loss": 0.1679, + "epoch": 0.33, + "learning_rate": 3.335674817118186e-05, + "loss": 0.1602, "step": 149860 }, { - "epoch": 0.67, - "learning_rate": 1.663557687996054e-05, - "loss": 0.1723, + "epoch": 0.33, + "learning_rate": 3.335562962797253e-05, + "loss": 0.1662, "step": 149870 }, { - "epoch": 0.67, - "learning_rate": 1.663333482803462e-05, - "loss": 0.1681, + "epoch": 0.33, + "learning_rate": 3.335451108476321e-05, + "loss": 0.1648, "step": 149880 }, { - "epoch": 0.67, - "learning_rate": 1.6631092776108695e-05, - "loss": 0.1684, + "epoch": 0.33, + "learning_rate": 3.335339254155388e-05, + "loss": 0.1584, "step": 149890 }, { - "epoch": 0.67, - "learning_rate": 1.6628850724182774e-05, - "loss": 0.1676, + "epoch": 0.33, + "learning_rate": 3.335227399834456e-05, + "loss": 0.1643, "step": 149900 }, { - "epoch": 0.67, - "learning_rate": 1.662660867225685e-05, - "loss": 0.1656, + "epoch": 0.33, + "learning_rate": 3.3351155455135235e-05, + "loss": 0.1604, "step": 149910 }, { - "epoch": 0.67, - "learning_rate": 1.6624366620330928e-05, - "loss": 0.1664, + "epoch": 0.33, + "learning_rate": 3.3350036911925906e-05, + "loss": 0.162, "step": 149920 }, { - "epoch": 0.67, - "learning_rate": 1.6622124568405007e-05, - "loss": 0.1728, + "epoch": 0.33, + "learning_rate": 3.3348918368716584e-05, + "loss": 0.1613, "step": 149930 }, { - "epoch": 0.67, - "learning_rate": 1.6619882516479082e-05, - "loss": 0.1665, + "epoch": 0.33, + "learning_rate": 3.334779982550726e-05, + "loss": 0.1643, "step": 149940 }, { - "epoch": 0.67, - "learning_rate": 1.661764046455316e-05, - "loss": 0.1722, + "epoch": 0.33, + "learning_rate": 3.334668128229794e-05, + "loss": 0.164, "step": 149950 }, { - "epoch": 0.67, - "learning_rate": 1.6615398412627236e-05, - "loss": 0.1613, + "epoch": 0.33, + "learning_rate": 3.334556273908862e-05, + "loss": 0.1623, "step": 149960 }, { - "epoch": 0.67, - "learning_rate": 1.6613156360701315e-05, - "loss": 0.1637, + "epoch": 0.33, + "learning_rate": 3.334444419587929e-05, + "loss": 0.1615, "step": 149970 }, { - "epoch": 0.67, - "learning_rate": 1.661091430877539e-05, - "loss": 0.168, + "epoch": 0.33, + "learning_rate": 3.334332565266997e-05, + "loss": 0.1632, "step": 149980 }, { - "epoch": 0.67, - "learning_rate": 1.660867225684947e-05, - "loss": 0.1695, + "epoch": 0.33, + "learning_rate": 3.334220710946064e-05, + "loss": 0.1582, "step": 149990 }, { - "epoch": 0.67, - "learning_rate": 1.6606430204923548e-05, - "loss": 0.1683, + "epoch": 0.33, + "learning_rate": 3.3341088566251316e-05, + "loss": 0.1645, "step": 150000 }, { - "epoch": 0.67, - "learning_rate": 1.6604188152997623e-05, - "loss": 0.1644, + "epoch": 0.33, + "learning_rate": 3.3339970023041994e-05, + "loss": 0.1621, "step": 150010 }, { - "epoch": 0.67, - "learning_rate": 1.6601946101071702e-05, - "loss": 0.1576, + "epoch": 0.33, + "learning_rate": 3.3338851479832665e-05, + "loss": 0.1633, "step": 150020 }, { - "epoch": 0.67, - "learning_rate": 1.6599704049145777e-05, - "loss": 0.1655, + "epoch": 0.33, + "learning_rate": 3.333773293662334e-05, + "loss": 0.1621, "step": 150030 }, { - "epoch": 0.67, - "learning_rate": 1.6597461997219856e-05, - "loss": 0.1654, + "epoch": 0.33, + "learning_rate": 3.333661439341402e-05, + "loss": 0.1604, "step": 150040 }, { - "epoch": 0.67, - "learning_rate": 1.659521994529393e-05, - "loss": 0.1719, + "epoch": 0.33, + "learning_rate": 3.33354958502047e-05, + "loss": 0.1622, "step": 150050 }, { - "epoch": 0.67, - "learning_rate": 1.659297789336801e-05, - "loss": 0.1607, + "epoch": 0.33, + "learning_rate": 3.3334377306995377e-05, + "loss": 0.1619, "step": 150060 }, { - "epoch": 0.67, - "learning_rate": 1.659073584144209e-05, - "loss": 0.1638, + "epoch": 0.33, + "learning_rate": 3.333325876378605e-05, + "loss": 0.1616, "step": 150070 }, { - "epoch": 0.67, - "learning_rate": 1.6588493789516167e-05, - "loss": 0.1692, + "epoch": 0.33, + "learning_rate": 3.3332140220576726e-05, + "loss": 0.1571, "step": 150080 }, { - "epoch": 0.67, - "learning_rate": 1.6586251737590243e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.33310216773674e-05, + "loss": 0.1576, "step": 150090 }, { - "epoch": 0.67, - "learning_rate": 1.658400968566432e-05, - "loss": 0.1626, + "epoch": 0.34, + "learning_rate": 3.3329903134158075e-05, + "loss": 0.16, "step": 150100 }, { - "epoch": 0.67, - "learning_rate": 1.65817676337384e-05, - "loss": 0.1708, + "epoch": 0.34, + "learning_rate": 3.3328784590948746e-05, + "loss": 0.1598, "step": 150110 }, { - "epoch": 0.67, - "learning_rate": 1.6579525581812475e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.3327666047739424e-05, + "loss": 0.1619, "step": 150120 }, { - "epoch": 0.67, - "learning_rate": 1.6577283529886554e-05, - "loss": 0.1679, + "epoch": 0.34, + "learning_rate": 3.33265475045301e-05, + "loss": 0.1604, "step": 150130 }, { - "epoch": 0.67, - "learning_rate": 1.6575265683153225e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.332542896132077e-05, + "loss": 0.162, "step": 150140 }, { - "epoch": 0.67, - "learning_rate": 1.65730236312273e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.332431041811145e-05, + "loss": 0.159, "step": 150150 }, { - "epoch": 0.67, - "learning_rate": 1.657078157930138e-05, - "loss": 0.1696, + "epoch": 0.34, + "learning_rate": 3.332319187490213e-05, + "loss": 0.1625, "step": 150160 }, { - "epoch": 0.67, - "learning_rate": 1.6568539527375455e-05, - "loss": 0.1624, + "epoch": 0.34, + "learning_rate": 3.332207333169281e-05, + "loss": 0.158, "step": 150170 }, { - "epoch": 0.67, - "learning_rate": 1.6566297475449533e-05, - "loss": 0.1692, + "epoch": 0.34, + "learning_rate": 3.3320954788483485e-05, + "loss": 0.1573, "step": 150180 }, { - "epoch": 0.67, - "learning_rate": 1.656405542352361e-05, - "loss": 0.1565, + "epoch": 0.34, + "learning_rate": 3.3319836245274156e-05, + "loss": 0.1591, "step": 150190 }, { - "epoch": 0.67, - "learning_rate": 1.6561813371597688e-05, - "loss": 0.1637, + "epoch": 0.34, + "learning_rate": 3.3318717702064834e-05, + "loss": 0.1632, "step": 150200 }, { - "epoch": 0.67, - "learning_rate": 1.6559571319671766e-05, - "loss": 0.1722, + "epoch": 0.34, + "learning_rate": 3.3317599158855505e-05, + "loss": 0.1576, "step": 150210 }, { - "epoch": 0.67, - "learning_rate": 1.655732926774584e-05, - "loss": 0.172, + "epoch": 0.34, + "learning_rate": 3.331648061564618e-05, + "loss": 0.1583, "step": 150220 }, { - "epoch": 0.67, - "learning_rate": 1.655508721581992e-05, - "loss": 0.1629, + "epoch": 0.34, + "learning_rate": 3.331536207243686e-05, + "loss": 0.1606, "step": 150230 }, { - "epoch": 0.67, - "learning_rate": 1.6552845163893996e-05, - "loss": 0.1706, + "epoch": 0.34, + "learning_rate": 3.331424352922753e-05, + "loss": 0.1576, "step": 150240 }, { - "epoch": 0.67, - "learning_rate": 1.6550603111968074e-05, - "loss": 0.1689, + "epoch": 0.34, + "learning_rate": 3.331312498601821e-05, + "loss": 0.1624, "step": 150250 }, { - "epoch": 0.67, - "learning_rate": 1.654836106004215e-05, - "loss": 0.1628, + "epoch": 0.34, + "learning_rate": 3.331200644280889e-05, + "loss": 0.1594, "step": 150260 }, { - "epoch": 0.67, - "learning_rate": 1.654611900811623e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.3310887899599566e-05, + "loss": 0.1656, "step": 150270 }, { - "epoch": 0.67, - "learning_rate": 1.6543876956190307e-05, - "loss": 0.1724, + "epoch": 0.34, + "learning_rate": 3.3309769356390244e-05, + "loss": 0.1608, "step": 150280 }, { - "epoch": 0.67, - "learning_rate": 1.6541634904264382e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.3308650813180915e-05, + "loss": 0.1608, "step": 150290 }, { - "epoch": 0.67, - "learning_rate": 1.653939285233846e-05, - "loss": 0.1685, + "epoch": 0.34, + "learning_rate": 3.330753226997159e-05, + "loss": 0.1594, "step": 150300 }, { - "epoch": 0.67, - "learning_rate": 1.6537150800412536e-05, - "loss": 0.1695, + "epoch": 0.34, + "learning_rate": 3.3306413726762264e-05, + "loss": 0.162, "step": 150310 }, { - "epoch": 0.67, - "learning_rate": 1.6534908748486615e-05, - "loss": 0.1599, + "epoch": 0.34, + "learning_rate": 3.330529518355294e-05, + "loss": 0.1555, "step": 150320 }, { - "epoch": 0.67, - "learning_rate": 1.653266669656069e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.330417664034362e-05, + "loss": 0.1662, "step": 150330 }, { - "epoch": 0.67, - "learning_rate": 1.653042464463477e-05, - "loss": 0.1648, + "epoch": 0.34, + "learning_rate": 3.330305809713429e-05, + "loss": 0.153, "step": 150340 }, { - "epoch": 0.67, - "learning_rate": 1.6528182592708848e-05, - "loss": 0.1599, + "epoch": 0.34, + "learning_rate": 3.330193955392497e-05, + "loss": 0.1584, "step": 150350 }, { - "epoch": 0.67, - "learning_rate": 1.6525940540782923e-05, - "loss": 0.1623, + "epoch": 0.34, + "learning_rate": 3.330082101071565e-05, + "loss": 0.1593, "step": 150360 }, { - "epoch": 0.67, - "learning_rate": 1.6523698488857002e-05, - "loss": 0.1734, + "epoch": 0.34, + "learning_rate": 3.3299702467506325e-05, + "loss": 0.157, "step": 150370 }, { - "epoch": 0.67, - "learning_rate": 1.652145643693108e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.3298583924297e-05, + "loss": 0.1618, "step": 150380 }, { - "epoch": 0.67, - "learning_rate": 1.651921438500516e-05, - "loss": 0.1691, + "epoch": 0.34, + "learning_rate": 3.3297465381087674e-05, + "loss": 0.1571, "step": 150390 }, { - "epoch": 0.67, - "learning_rate": 1.6516972333079235e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.329634683787835e-05, + "loss": 0.1603, "step": 150400 }, { - "epoch": 0.67, - "learning_rate": 1.6514730281153313e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.329522829466902e-05, + "loss": 0.1618, "step": 150410 }, { - "epoch": 0.67, - "learning_rate": 1.6512488229227392e-05, + "epoch": 0.34, + "learning_rate": 3.32941097514597e-05, "loss": 0.1622, "step": 150420 }, { - "epoch": 0.67, - "learning_rate": 1.6510246177301468e-05, - "loss": 0.1667, + "epoch": 0.34, + "learning_rate": 3.329299120825037e-05, + "loss": 0.1594, "step": 150430 }, { - "epoch": 0.67, - "learning_rate": 1.6508004125375546e-05, - "loss": 0.163, + "epoch": 0.34, + "learning_rate": 3.329187266504105e-05, + "loss": 0.1574, "step": 150440 }, { - "epoch": 0.67, - "learning_rate": 1.650576207344962e-05, - "loss": 0.1701, + "epoch": 0.34, + "learning_rate": 3.329075412183173e-05, + "loss": 0.1655, "step": 150450 }, { - "epoch": 0.67, - "learning_rate": 1.65035200215237e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.3289635578622406e-05, + "loss": 0.1666, "step": 150460 }, { - "epoch": 0.67, - "learning_rate": 1.6501277969597776e-05, - "loss": 0.1671, + "epoch": 0.34, + "learning_rate": 3.3288517035413083e-05, + "loss": 0.1643, "step": 150470 }, { - "epoch": 0.67, - "learning_rate": 1.6499035917671854e-05, - "loss": 0.1676, + "epoch": 0.34, + "learning_rate": 3.3287398492203755e-05, + "loss": 0.1662, "step": 150480 }, { - "epoch": 0.67, - "learning_rate": 1.6496793865745933e-05, - "loss": 0.1729, + "epoch": 0.34, + "learning_rate": 3.328627994899443e-05, + "loss": 0.162, "step": 150490 }, { - "epoch": 0.67, - "learning_rate": 1.649455181382001e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.328516140578511e-05, + "loss": 0.1606, "step": 150500 }, { - "epoch": 0.67, - "learning_rate": 1.6492309761894087e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.328404286257578e-05, + "loss": 0.1606, "step": 150510 }, { - "epoch": 0.67, - "learning_rate": 1.6490067709968162e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.328292431936646e-05, + "loss": 0.1579, "step": 150520 }, { - "epoch": 0.67, - "learning_rate": 1.648782565804224e-05, - "loss": 0.1701, + "epoch": 0.34, + "learning_rate": 3.328180577615713e-05, + "loss": 0.1621, "step": 150530 }, { - "epoch": 0.67, - "learning_rate": 1.6485583606116316e-05, - "loss": 0.1607, + "epoch": 0.34, + "learning_rate": 3.328068723294781e-05, + "loss": 0.159, "step": 150540 }, { - "epoch": 0.67, - "learning_rate": 1.6483341554190395e-05, - "loss": 0.1654, + "epoch": 0.34, + "learning_rate": 3.3279568689738487e-05, + "loss": 0.1585, "step": 150550 }, { - "epoch": 0.67, - "learning_rate": 1.6481099502264474e-05, - "loss": 0.1596, + "epoch": 0.34, + "learning_rate": 3.327845014652916e-05, + "loss": 0.1603, "step": 150560 }, { - "epoch": 0.67, - "learning_rate": 1.647885745033855e-05, - "loss": 0.1624, + "epoch": 0.34, + "learning_rate": 3.3277331603319836e-05, + "loss": 0.1605, "step": 150570 }, { - "epoch": 0.67, - "learning_rate": 1.6476615398412628e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.3276213060110514e-05, + "loss": 0.1627, "step": 150580 }, { - "epoch": 0.67, - "learning_rate": 1.6474373346486703e-05, - "loss": 0.1639, + "epoch": 0.34, + "learning_rate": 3.327509451690119e-05, + "loss": 0.1632, "step": 150590 }, { - "epoch": 0.67, - "learning_rate": 1.6472131294560782e-05, - "loss": 0.1699, + "epoch": 0.34, + "learning_rate": 3.327397597369187e-05, + "loss": 0.1575, "step": 150600 }, { - "epoch": 0.67, - "learning_rate": 1.6469889242634857e-05, - "loss": 0.1678, + "epoch": 0.34, + "learning_rate": 3.327285743048254e-05, + "loss": 0.1619, "step": 150610 }, { - "epoch": 0.67, - "learning_rate": 1.6467647190708936e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.327173888727322e-05, + "loss": 0.1616, "step": 150620 }, { - "epoch": 0.67, - "learning_rate": 1.6465405138783015e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.327062034406389e-05, + "loss": 0.1582, "step": 150630 }, { - "epoch": 0.67, - "learning_rate": 1.6463163086857093e-05, - "loss": 0.1643, + "epoch": 0.34, + "learning_rate": 3.326950180085457e-05, + "loss": 0.1612, "step": 150640 }, { - "epoch": 0.67, - "learning_rate": 1.646092103493117e-05, - "loss": 0.1686, + "epoch": 0.34, + "learning_rate": 3.3268383257645246e-05, + "loss": 0.1614, "step": 150650 }, { - "epoch": 0.67, - "learning_rate": 1.6458678983005248e-05, - "loss": 0.1586, + "epoch": 0.34, + "learning_rate": 3.326726471443592e-05, + "loss": 0.1605, "step": 150660 }, { - "epoch": 0.67, - "learning_rate": 1.6456436931079326e-05, - "loss": 0.1683, + "epoch": 0.34, + "learning_rate": 3.3266146171226595e-05, + "loss": 0.1607, "step": 150670 }, { - "epoch": 0.67, - "learning_rate": 1.64541948791534e-05, - "loss": 0.1641, + "epoch": 0.34, + "learning_rate": 3.326502762801727e-05, + "loss": 0.1557, "step": 150680 }, { - "epoch": 0.67, - "learning_rate": 1.645195282722748e-05, - "loss": 0.1717, + "epoch": 0.34, + "learning_rate": 3.326390908480795e-05, + "loss": 0.1576, "step": 150690 }, { - "epoch": 0.67, - "learning_rate": 1.644971077530156e-05, - "loss": 0.1652, + "epoch": 0.34, + "learning_rate": 3.326279054159863e-05, + "loss": 0.164, "step": 150700 }, { - "epoch": 0.67, - "learning_rate": 1.6447468723375634e-05, - "loss": 0.163, + "epoch": 0.34, + "learning_rate": 3.32616719983893e-05, + "loss": 0.1598, "step": 150710 }, { - "epoch": 0.67, - "learning_rate": 1.6445226671449713e-05, - "loss": 0.172, + "epoch": 0.34, + "learning_rate": 3.326055345517998e-05, + "loss": 0.1641, "step": 150720 }, { - "epoch": 0.67, - "learning_rate": 1.644298461952379e-05, - "loss": 0.1676, + "epoch": 0.34, + "learning_rate": 3.325943491197065e-05, + "loss": 0.1618, "step": 150730 }, { - "epoch": 0.67, - "learning_rate": 1.6440742567597867e-05, - "loss": 0.1718, + "epoch": 0.34, + "learning_rate": 3.3258316368761327e-05, + "loss": 0.1618, "step": 150740 }, { - "epoch": 0.67, - "learning_rate": 1.6438500515671942e-05, - "loss": 0.1624, + "epoch": 0.34, + "learning_rate": 3.3257197825552e-05, + "loss": 0.1571, "step": 150750 }, { - "epoch": 0.67, - "learning_rate": 1.643625846374602e-05, - "loss": 0.1637, + "epoch": 0.34, + "learning_rate": 3.3256079282342676e-05, + "loss": 0.1597, "step": 150760 }, { - "epoch": 0.67, - "learning_rate": 1.64340164118201e-05, - "loss": 0.1697, + "epoch": 0.34, + "learning_rate": 3.3254960739133354e-05, + "loss": 0.1651, "step": 150770 }, { - "epoch": 0.67, - "learning_rate": 1.6431774359894175e-05, - "loss": 0.1643, + "epoch": 0.34, + "learning_rate": 3.325384219592403e-05, + "loss": 0.1595, "step": 150780 }, { - "epoch": 0.67, - "learning_rate": 1.6429532307968254e-05, - "loss": 0.164, + "epoch": 0.34, + "learning_rate": 3.325272365271471e-05, + "loss": 0.1625, "step": 150790 }, { - "epoch": 0.67, - "learning_rate": 1.642729025604233e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.325160510950538e-05, + "loss": 0.1643, "step": 150800 }, { - "epoch": 0.67, - "learning_rate": 1.6425048204116408e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.325048656629606e-05, + "loss": 0.163, "step": 150810 }, { - "epoch": 0.67, - "learning_rate": 1.6422806152190487e-05, - "loss": 0.1619, + "epoch": 0.34, + "learning_rate": 3.3249368023086736e-05, + "loss": 0.1627, "step": 150820 }, { - "epoch": 0.67, - "learning_rate": 1.6420564100264562e-05, - "loss": 0.1691, + "epoch": 0.34, + "learning_rate": 3.324824947987741e-05, + "loss": 0.1593, "step": 150830 }, { - "epoch": 0.67, - "learning_rate": 1.641832204833864e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.3247130936668085e-05, + "loss": 0.1595, "step": 150840 }, { - "epoch": 0.67, - "learning_rate": 1.6416079996412716e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.324601239345876e-05, + "loss": 0.1587, "step": 150850 }, { - "epoch": 0.67, - "learning_rate": 1.6413837944486795e-05, - "loss": 0.1678, + "epoch": 0.34, + "learning_rate": 3.3244893850249435e-05, + "loss": 0.162, "step": 150860 }, { - "epoch": 0.67, - "learning_rate": 1.641159589256087e-05, - "loss": 0.1697, + "epoch": 0.34, + "learning_rate": 3.324377530704011e-05, + "loss": 0.1589, "step": 150870 }, { - "epoch": 0.67, - "learning_rate": 1.640935384063495e-05, - "loss": 0.1673, + "epoch": 0.34, + "learning_rate": 3.324265676383079e-05, + "loss": 0.165, "step": 150880 }, { - "epoch": 0.67, - "learning_rate": 1.6407111788709028e-05, - "loss": 0.1633, + "epoch": 0.34, + "learning_rate": 3.324153822062147e-05, + "loss": 0.1619, "step": 150890 }, { - "epoch": 0.67, - "learning_rate": 1.6404869736783103e-05, - "loss": 0.164, + "epoch": 0.34, + "learning_rate": 3.324041967741214e-05, + "loss": 0.1581, "step": 150900 }, { - "epoch": 0.67, - "learning_rate": 1.640262768485718e-05, - "loss": 0.1609, + "epoch": 0.34, + "learning_rate": 3.323930113420282e-05, + "loss": 0.1632, "step": 150910 }, { - "epoch": 0.67, - "learning_rate": 1.640038563293126e-05, - "loss": 0.1699, + "epoch": 0.34, + "learning_rate": 3.3238182590993495e-05, + "loss": 0.1594, "step": 150920 }, { - "epoch": 0.67, - "learning_rate": 1.639814358100534e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.3237064047784167e-05, + "loss": 0.1608, "step": 150930 }, { - "epoch": 0.67, - "learning_rate": 1.6395901529079414e-05, - "loss": 0.1669, + "epoch": 0.34, + "learning_rate": 3.3235945504574844e-05, + "loss": 0.1651, "step": 150940 }, { - "epoch": 0.67, - "learning_rate": 1.6393659477153493e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.3234826961365516e-05, + "loss": 0.1616, "step": 150950 }, { - "epoch": 0.67, - "learning_rate": 1.6391417425227572e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.3233708418156194e-05, + "loss": 0.1614, "step": 150960 }, { - "epoch": 0.67, - "learning_rate": 1.6389175373301647e-05, - "loss": 0.1695, + "epoch": 0.34, + "learning_rate": 3.323258987494687e-05, + "loss": 0.16, "step": 150970 }, { - "epoch": 0.67, - "learning_rate": 1.6386933321375726e-05, - "loss": 0.1657, + "epoch": 0.34, + "learning_rate": 3.323147133173754e-05, + "loss": 0.163, "step": 150980 }, { - "epoch": 0.67, - "learning_rate": 1.63846912694498e-05, - "loss": 0.1719, + "epoch": 0.34, + "learning_rate": 3.323035278852823e-05, + "loss": 0.1634, "step": 150990 }, { - "epoch": 0.67, - "learning_rate": 1.638244921752388e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.32292342453189e-05, + "loss": 0.1598, "step": 151000 }, { - "epoch": 0.67, - "learning_rate": 1.6380207165597955e-05, + "epoch": 0.34, + "learning_rate": 3.3228115702109576e-05, "loss": 0.1639, "step": 151010 }, { - "epoch": 0.67, - "learning_rate": 1.6377965113672034e-05, - "loss": 0.1693, + "epoch": 0.34, + "learning_rate": 3.3226997158900254e-05, + "loss": 0.1624, "step": 151020 }, { - "epoch": 0.67, - "learning_rate": 1.6375723061746113e-05, - "loss": 0.1661, + "epoch": 0.34, + "learning_rate": 3.3225878615690925e-05, + "loss": 0.1591, "step": 151030 }, { - "epoch": 0.67, - "learning_rate": 1.6373481009820188e-05, - "loss": 0.169, + "epoch": 0.34, + "learning_rate": 3.3224760072481603e-05, + "loss": 0.1649, "step": 151040 }, { - "epoch": 0.67, - "learning_rate": 1.6371238957894267e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.3223641529272275e-05, + "loss": 0.1618, "step": 151050 }, { - "epoch": 0.67, - "learning_rate": 1.6368996905968342e-05, - "loss": 0.1667, + "epoch": 0.34, + "learning_rate": 3.322252298606295e-05, + "loss": 0.1597, "step": 151060 }, { - "epoch": 0.67, - "learning_rate": 1.636675485404242e-05, - "loss": 0.1659, + "epoch": 0.34, + "learning_rate": 3.3221404442853624e-05, + "loss": 0.157, "step": 151070 }, { - "epoch": 0.67, - "learning_rate": 1.6364512802116496e-05, - "loss": 0.1667, + "epoch": 0.34, + "learning_rate": 3.32202858996443e-05, + "loss": 0.1592, "step": 151080 }, { - "epoch": 0.67, - "learning_rate": 1.6362270750190575e-05, - "loss": 0.1677, + "epoch": 0.34, + "learning_rate": 3.321916735643498e-05, + "loss": 0.16, "step": 151090 }, { - "epoch": 0.67, - "learning_rate": 1.6360028698264654e-05, - "loss": 0.1623, + "epoch": 0.34, + "learning_rate": 3.321804881322566e-05, + "loss": 0.1628, "step": 151100 }, { - "epoch": 0.67, - "learning_rate": 1.635778664633873e-05, - "loss": 0.164, + "epoch": 0.34, + "learning_rate": 3.3216930270016335e-05, + "loss": 0.1601, "step": 151110 }, { - "epoch": 0.67, - "learning_rate": 1.6355544594412808e-05, - "loss": 0.1669, + "epoch": 0.34, + "learning_rate": 3.3215811726807006e-05, + "loss": 0.1585, "step": 151120 }, { - "epoch": 0.67, - "learning_rate": 1.6353302542486883e-05, - "loss": 0.1626, + "epoch": 0.34, + "learning_rate": 3.3214693183597684e-05, + "loss": 0.1624, "step": 151130 }, { - "epoch": 0.67, - "learning_rate": 1.635106049056096e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.321357464038836e-05, + "loss": 0.1547, "step": 151140 }, { - "epoch": 0.67, - "learning_rate": 1.6348818438635037e-05, - "loss": 0.1734, + "epoch": 0.34, + "learning_rate": 3.3212456097179033e-05, + "loss": 0.1601, "step": 151150 }, { - "epoch": 0.67, - "learning_rate": 1.6346576386709116e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.321133755396971e-05, + "loss": 0.1565, "step": 151160 }, { - "epoch": 0.67, - "learning_rate": 1.6344334334783194e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.321021901076038e-05, + "loss": 0.1652, "step": 151170 }, { - "epoch": 0.67, - "learning_rate": 1.6342092282857273e-05, - "loss": 0.1638, + "epoch": 0.34, + "learning_rate": 3.320910046755106e-05, + "loss": 0.1621, "step": 151180 }, { - "epoch": 0.67, - "learning_rate": 1.633985023093135e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.320798192434174e-05, + "loss": 0.1621, "step": 151190 }, { - "epoch": 0.67, - "learning_rate": 1.6337608179005427e-05, - "loss": 0.1671, + "epoch": 0.34, + "learning_rate": 3.3206863381132416e-05, + "loss": 0.1606, "step": 151200 }, { - "epoch": 0.68, - "learning_rate": 1.6335366127079506e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.3205744837923094e-05, + "loss": 0.1547, "step": 151210 }, { - "epoch": 0.68, - "learning_rate": 1.633312407515358e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.3204626294713765e-05, + "loss": 0.1592, "step": 151220 }, { - "epoch": 0.68, - "learning_rate": 1.633088202322766e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.320350775150444e-05, + "loss": 0.1657, "step": 151230 }, { - "epoch": 0.68, - "learning_rate": 1.632863997130174e-05, - "loss": 0.1661, + "epoch": 0.34, + "learning_rate": 3.320238920829512e-05, + "loss": 0.1582, "step": 151240 }, { - "epoch": 0.68, - "learning_rate": 1.6326397919375814e-05, - "loss": 0.1685, + "epoch": 0.34, + "learning_rate": 3.320127066508579e-05, + "loss": 0.1591, "step": 151250 }, { - "epoch": 0.68, - "learning_rate": 1.6324155867449893e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.320015212187647e-05, + "loss": 0.1616, "step": 151260 }, { - "epoch": 0.68, - "learning_rate": 1.6321913815523968e-05, - "loss": 0.1698, + "epoch": 0.34, + "learning_rate": 3.319903357866714e-05, + "loss": 0.1609, "step": 151270 }, { - "epoch": 0.68, - "learning_rate": 1.6319671763598047e-05, - "loss": 0.1618, + "epoch": 0.34, + "learning_rate": 3.319791503545782e-05, + "loss": 0.1663, "step": 151280 }, { - "epoch": 0.68, - "learning_rate": 1.6317429711672122e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.31967964922485e-05, + "loss": 0.1567, "step": 151290 }, { - "epoch": 0.68, - "learning_rate": 1.63151876597462e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.3195677949039175e-05, + "loss": 0.1615, "step": 151300 }, { - "epoch": 0.68, - "learning_rate": 1.631294560782028e-05, - "loss": 0.1661, + "epoch": 0.34, + "learning_rate": 3.319455940582985e-05, + "loss": 0.16, "step": 151310 }, { - "epoch": 0.68, - "learning_rate": 1.6310703555894355e-05, - "loss": 0.1676, + "epoch": 0.34, + "learning_rate": 3.3193440862620524e-05, + "loss": 0.1645, "step": 151320 }, { - "epoch": 0.68, - "learning_rate": 1.6308461503968434e-05, - "loss": 0.1692, + "epoch": 0.34, + "learning_rate": 3.31923223194112e-05, + "loss": 0.1583, "step": 151330 }, { - "epoch": 0.68, - "learning_rate": 1.630621945204251e-05, - "loss": 0.1687, + "epoch": 0.34, + "learning_rate": 3.319120377620188e-05, + "loss": 0.1601, "step": 151340 }, { - "epoch": 0.68, - "learning_rate": 1.6303977400116588e-05, - "loss": 0.1598, + "epoch": 0.34, + "learning_rate": 3.319008523299255e-05, + "loss": 0.1558, "step": 151350 }, { - "epoch": 0.68, - "learning_rate": 1.6301735348190663e-05, - "loss": 0.1666, + "epoch": 0.34, + "learning_rate": 3.318896668978323e-05, + "loss": 0.1595, "step": 151360 }, { - "epoch": 0.68, - "learning_rate": 1.629949329626474e-05, - "loss": 0.1706, + "epoch": 0.34, + "learning_rate": 3.31878481465739e-05, + "loss": 0.1674, "step": 151370 }, { - "epoch": 0.68, - "learning_rate": 1.629725124433882e-05, - "loss": 0.1619, + "epoch": 0.34, + "learning_rate": 3.318672960336458e-05, + "loss": 0.1621, "step": 151380 }, { - "epoch": 0.68, - "learning_rate": 1.6295009192412896e-05, - "loss": 0.1646, + "epoch": 0.34, + "learning_rate": 3.318561106015525e-05, + "loss": 0.1595, "step": 151390 }, { - "epoch": 0.68, - "learning_rate": 1.6292767140486974e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.3184492516945934e-05, + "loss": 0.1685, "step": 151400 }, { - "epoch": 0.68, - "learning_rate": 1.629052508856105e-05, - "loss": 0.1681, + "epoch": 0.34, + "learning_rate": 3.318337397373661e-05, + "loss": 0.1668, "step": 151410 }, { - "epoch": 0.68, - "learning_rate": 1.628828303663513e-05, - "loss": 0.172, + "epoch": 0.34, + "learning_rate": 3.318225543052728e-05, + "loss": 0.1624, "step": 151420 }, { - "epoch": 0.68, - "learning_rate": 1.6286040984709207e-05, - "loss": 0.1593, + "epoch": 0.34, + "learning_rate": 3.318113688731796e-05, + "loss": 0.1582, "step": 151430 }, { - "epoch": 0.68, - "learning_rate": 1.6283798932783282e-05, - "loss": 0.1698, + "epoch": 0.34, + "learning_rate": 3.318001834410863e-05, + "loss": 0.1608, "step": 151440 }, { - "epoch": 0.68, - "learning_rate": 1.628155688085736e-05, - "loss": 0.1704, + "epoch": 0.34, + "learning_rate": 3.317889980089931e-05, + "loss": 0.1619, "step": 151450 }, { - "epoch": 0.68, - "learning_rate": 1.627931482893144e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.317778125768999e-05, + "loss": 0.1648, "step": 151460 }, { - "epoch": 0.68, - "learning_rate": 1.627707277700552e-05, - "loss": 0.1633, + "epoch": 0.34, + "learning_rate": 3.317666271448066e-05, + "loss": 0.1615, "step": 151470 }, { - "epoch": 0.68, - "learning_rate": 1.6274830725079594e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.317554417127134e-05, + "loss": 0.162, "step": 151480 }, { - "epoch": 0.68, - "learning_rate": 1.6272588673153673e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.317442562806201e-05, + "loss": 0.1644, "step": 151490 }, { - "epoch": 0.68, - "learning_rate": 1.6270346621227748e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.3173307084852686e-05, + "loss": 0.1627, "step": 151500 }, { - "epoch": 0.68, - "learning_rate": 1.6268104569301827e-05, - "loss": 0.1684, + "epoch": 0.34, + "learning_rate": 3.3172188541643364e-05, + "loss": 0.1602, "step": 151510 }, { - "epoch": 0.68, - "learning_rate": 1.6265862517375905e-05, - "loss": 0.1746, + "epoch": 0.34, + "learning_rate": 3.317106999843404e-05, + "loss": 0.1564, "step": 151520 }, { - "epoch": 0.68, - "learning_rate": 1.626362046544998e-05, - "loss": 0.1657, + "epoch": 0.34, + "learning_rate": 3.316995145522472e-05, + "loss": 0.158, "step": 151530 }, { - "epoch": 0.68, - "learning_rate": 1.626137841352406e-05, - "loss": 0.1701, + "epoch": 0.34, + "learning_rate": 3.316883291201539e-05, + "loss": 0.152, "step": 151540 }, { - "epoch": 0.68, - "learning_rate": 1.6259136361598135e-05, - "loss": 0.1741, + "epoch": 0.34, + "learning_rate": 3.316771436880607e-05, + "loss": 0.161, "step": 151550 }, { - "epoch": 0.68, - "learning_rate": 1.6256894309672214e-05, - "loss": 0.1701, + "epoch": 0.34, + "learning_rate": 3.316659582559675e-05, + "loss": 0.1676, "step": 151560 }, { - "epoch": 0.68, - "learning_rate": 1.625465225774629e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.316547728238742e-05, + "loss": 0.1594, "step": 151570 }, { - "epoch": 0.68, - "learning_rate": 1.6252410205820368e-05, - "loss": 0.1654, + "epoch": 0.34, + "learning_rate": 3.3164358739178096e-05, + "loss": 0.1569, "step": 151580 }, { - "epoch": 0.68, - "learning_rate": 1.6250168153894446e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.316324019596877e-05, + "loss": 0.1613, "step": 151590 }, { - "epoch": 0.68, - "learning_rate": 1.624792610196852e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.3162121652759445e-05, + "loss": 0.1623, "step": 151600 }, { - "epoch": 0.68, - "learning_rate": 1.62456840500426e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.316100310955012e-05, + "loss": 0.1617, "step": 151610 }, { - "epoch": 0.68, - "learning_rate": 1.6243441998116676e-05, - "loss": 0.1648, + "epoch": 0.34, + "learning_rate": 3.31598845663408e-05, + "loss": 0.162, "step": 151620 }, { - "epoch": 0.68, - "learning_rate": 1.6241199946190754e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.315876602313148e-05, + "loss": 0.1588, "step": 151630 }, { - "epoch": 0.68, - "learning_rate": 1.623895789426483e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.315764747992215e-05, + "loss": 0.1631, "step": 151640 }, { - "epoch": 0.68, - "learning_rate": 1.623671584233891e-05, - "loss": 0.161, + "epoch": 0.34, + "learning_rate": 3.315652893671283e-05, + "loss": 0.1579, "step": 151650 }, { - "epoch": 0.68, - "learning_rate": 1.6234473790412987e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.31554103935035e-05, + "loss": 0.1578, "step": 151660 }, { - "epoch": 0.68, - "learning_rate": 1.6232231738487063e-05, - "loss": 0.1689, + "epoch": 0.34, + "learning_rate": 3.315429185029418e-05, + "loss": 0.1609, "step": 151670 }, { - "epoch": 0.68, - "learning_rate": 1.622998968656114e-05, - "loss": 0.1616, + "epoch": 0.34, + "learning_rate": 3.3153173307084855e-05, + "loss": 0.1591, "step": 151680 }, { - "epoch": 0.68, - "learning_rate": 1.6227747634635217e-05, - "loss": 0.1715, + "epoch": 0.34, + "learning_rate": 3.3152054763875526e-05, + "loss": 0.1588, "step": 151690 }, { - "epoch": 0.68, - "learning_rate": 1.6225505582709295e-05, - "loss": 0.1629, - "step": 151700 + "epoch": 0.34, + "learning_rate": 3.3150936220666204e-05, + "loss": 0.1596, + "step": 151700 }, { - "epoch": 0.68, - "learning_rate": 1.6223263530783374e-05, - "loss": 0.1652, + "epoch": 0.34, + "learning_rate": 3.314981767745688e-05, + "loss": 0.16, "step": 151710 }, { - "epoch": 0.68, - "learning_rate": 1.6221021478857453e-05, - "loss": 0.1727, + "epoch": 0.34, + "learning_rate": 3.314869913424756e-05, + "loss": 0.1592, "step": 151720 }, { - "epoch": 0.68, - "learning_rate": 1.6218779426931528e-05, + "epoch": 0.34, + "learning_rate": 3.314758059103824e-05, "loss": 0.1656, "step": 151730 }, { - "epoch": 0.68, - "learning_rate": 1.6216537375005607e-05, - "loss": 0.1625, + "epoch": 0.34, + "learning_rate": 3.314646204782891e-05, + "loss": 0.1641, "step": 151740 }, { - "epoch": 0.68, - "learning_rate": 1.6214295323079685e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.314534350461959e-05, + "loss": 0.1593, "step": 151750 }, { - "epoch": 0.68, - "learning_rate": 1.621205327115376e-05, - "loss": 0.1576, + "epoch": 0.34, + "learning_rate": 3.314422496141026e-05, + "loss": 0.1566, "step": 151760 }, { - "epoch": 0.68, - "learning_rate": 1.620981121922784e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.3143106418200936e-05, + "loss": 0.1557, "step": 151770 }, { - "epoch": 0.68, - "learning_rate": 1.6207569167301915e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.3141987874991614e-05, + "loss": 0.1643, "step": 151780 }, { - "epoch": 0.68, - "learning_rate": 1.6205327115375994e-05, - "loss": 0.1687, + "epoch": 0.34, + "learning_rate": 3.3140869331782285e-05, + "loss": 0.1641, "step": 151790 }, { - "epoch": 0.68, - "learning_rate": 1.6203085063450072e-05, - "loss": 0.1665, + "epoch": 0.34, + "learning_rate": 3.313975078857296e-05, + "loss": 0.1673, "step": 151800 }, { - "epoch": 0.68, - "learning_rate": 1.6200843011524148e-05, - "loss": 0.1697, + "epoch": 0.34, + "learning_rate": 3.3138632245363634e-05, + "loss": 0.1598, "step": 151810 }, { - "epoch": 0.68, - "learning_rate": 1.6198600959598226e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.313751370215432e-05, + "loss": 0.1598, "step": 151820 }, { - "epoch": 0.68, - "learning_rate": 1.61963589076723e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.3136395158945e-05, + "loss": 0.1575, "step": 151830 }, { - "epoch": 0.68, - "learning_rate": 1.619411685574638e-05, - "loss": 0.1602, + "epoch": 0.34, + "learning_rate": 3.313527661573567e-05, + "loss": 0.1613, "step": 151840 }, { - "epoch": 0.68, - "learning_rate": 1.6191874803820456e-05, - "loss": 0.1625, + "epoch": 0.34, + "learning_rate": 3.3134158072526346e-05, + "loss": 0.1619, "step": 151850 }, { - "epoch": 0.68, - "learning_rate": 1.6189632751894534e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.313303952931702e-05, + "loss": 0.156, "step": 151860 }, { - "epoch": 0.68, - "learning_rate": 1.6187390699968613e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.3131920986107695e-05, + "loss": 0.161, "step": 151870 }, { - "epoch": 0.68, - "learning_rate": 1.618514864804269e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.313080244289837e-05, + "loss": 0.167, "step": 151880 }, { - "epoch": 0.68, - "learning_rate": 1.6182906596116767e-05, - "loss": 0.1692, + "epoch": 0.34, + "learning_rate": 3.3129683899689044e-05, + "loss": 0.16, "step": 151890 }, { - "epoch": 0.68, - "learning_rate": 1.6180664544190843e-05, - "loss": 0.1682, + "epoch": 0.34, + "learning_rate": 3.312856535647972e-05, + "loss": 0.1596, "step": 151900 }, { - "epoch": 0.68, - "learning_rate": 1.617842249226492e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.312744681327039e-05, + "loss": 0.1597, "step": 151910 }, { - "epoch": 0.68, - "learning_rate": 1.6176180440338997e-05, - "loss": 0.1691, + "epoch": 0.34, + "learning_rate": 3.312632827006107e-05, + "loss": 0.1644, "step": 151920 }, { - "epoch": 0.68, - "learning_rate": 1.6173938388413075e-05, - "loss": 0.1628, + "epoch": 0.34, + "learning_rate": 3.312520972685175e-05, + "loss": 0.1584, "step": 151930 }, { - "epoch": 0.68, - "learning_rate": 1.6171696336487154e-05, - "loss": 0.1652, + "epoch": 0.34, + "learning_rate": 3.312409118364243e-05, + "loss": 0.1633, "step": 151940 }, { - "epoch": 0.68, - "learning_rate": 1.616945428456123e-05, - "loss": 0.1673, + "epoch": 0.34, + "learning_rate": 3.3122972640433105e-05, + "loss": 0.1639, "step": 151950 }, { - "epoch": 0.68, - "learning_rate": 1.6167212232635308e-05, - "loss": 0.1689, + "epoch": 0.34, + "learning_rate": 3.3121854097223776e-05, + "loss": 0.1604, "step": 151960 }, { - "epoch": 0.68, - "learning_rate": 1.6164970180709383e-05, - "loss": 0.1677, + "epoch": 0.34, + "learning_rate": 3.3120735554014454e-05, + "loss": 0.1638, "step": 151970 }, { - "epoch": 0.68, - "learning_rate": 1.6162728128783462e-05, - "loss": 0.1619, + "epoch": 0.34, + "learning_rate": 3.3119617010805125e-05, + "loss": 0.1639, "step": 151980 }, { - "epoch": 0.68, - "learning_rate": 1.616048607685754e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.31184984675958e-05, + "loss": 0.1649, "step": 151990 }, { - "epoch": 0.68, - "learning_rate": 1.615824402493162e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.311737992438648e-05, + "loss": 0.1575, "step": 152000 }, { - "epoch": 0.68, - "learning_rate": 1.6156001973005698e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.311626138117715e-05, + "loss": 0.1615, "step": 152010 }, { - "epoch": 0.68, - "learning_rate": 1.6153759921079774e-05, - "loss": 0.1742, + "epoch": 0.34, + "learning_rate": 3.311514283796783e-05, + "loss": 0.1621, "step": 152020 }, { - "epoch": 0.68, - "learning_rate": 1.6151517869153852e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.311402429475851e-05, + "loss": 0.1584, "step": 152030 }, { - "epoch": 0.68, - "learning_rate": 1.6149275817227928e-05, - "loss": 0.1616, + "epoch": 0.34, + "learning_rate": 3.311301760587012e-05, + "loss": 0.1599, "step": 152040 }, { - "epoch": 0.68, - "learning_rate": 1.6147033765302006e-05, - "loss": 0.1639, + "epoch": 0.34, + "learning_rate": 3.311189906266079e-05, + "loss": 0.1626, "step": 152050 }, { - "epoch": 0.68, - "learning_rate": 1.614479171337608e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.3110780519451466e-05, + "loss": 0.1621, "step": 152060 }, { - "epoch": 0.68, - "learning_rate": 1.614254966145016e-05, - "loss": 0.17, + "epoch": 0.34, + "learning_rate": 3.3109661976242144e-05, + "loss": 0.1573, "step": 152070 }, { - "epoch": 0.68, - "learning_rate": 1.614030760952424e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.3108543433032815e-05, + "loss": 0.1652, "step": 152080 }, { - "epoch": 0.68, - "learning_rate": 1.6138065557598314e-05, - "loss": 0.1633, + "epoch": 0.34, + "learning_rate": 3.310742488982349e-05, + "loss": 0.1622, "step": 152090 }, { - "epoch": 0.68, - "learning_rate": 1.6135823505672393e-05, - "loss": 0.1701, + "epoch": 0.34, + "learning_rate": 3.310630634661417e-05, + "loss": 0.1595, "step": 152100 }, { - "epoch": 0.68, - "learning_rate": 1.613358145374647e-05, - "loss": 0.163, + "epoch": 0.34, + "learning_rate": 3.310518780340485e-05, + "loss": 0.1624, "step": 152110 }, { - "epoch": 0.68, - "learning_rate": 1.6131339401820547e-05, - "loss": 0.1714, + "epoch": 0.34, + "learning_rate": 3.310406926019553e-05, + "loss": 0.1609, "step": 152120 }, { - "epoch": 0.68, - "learning_rate": 1.6129097349894623e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.31029507169862e-05, + "loss": 0.1597, "step": 152130 }, { - "epoch": 0.68, - "learning_rate": 1.61268552979687e-05, - "loss": 0.1678, + "epoch": 0.34, + "learning_rate": 3.3101832173776876e-05, + "loss": 0.1567, "step": 152140 }, { - "epoch": 0.68, - "learning_rate": 1.612461324604278e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.310071363056755e-05, + "loss": 0.1576, "step": 152150 }, { - "epoch": 0.68, - "learning_rate": 1.6122371194116855e-05, - "loss": 0.1643, + "epoch": 0.34, + "learning_rate": 3.3099595087358225e-05, + "loss": 0.1629, "step": 152160 }, { - "epoch": 0.68, - "learning_rate": 1.6120129142190934e-05, - "loss": 0.1621, + "epoch": 0.34, + "learning_rate": 3.30984765441489e-05, + "loss": 0.1549, "step": 152170 }, { - "epoch": 0.68, - "learning_rate": 1.611788709026501e-05, - "loss": 0.1694, + "epoch": 0.34, + "learning_rate": 3.3097358000939574e-05, + "loss": 0.1543, "step": 152180 }, { - "epoch": 0.68, - "learning_rate": 1.6115645038339088e-05, - "loss": 0.1709, + "epoch": 0.34, + "learning_rate": 3.309623945773025e-05, + "loss": 0.1622, "step": 152190 }, { - "epoch": 0.68, - "learning_rate": 1.6113402986413167e-05, - "loss": 0.1616, + "epoch": 0.34, + "learning_rate": 3.309512091452093e-05, + "loss": 0.1628, "step": 152200 }, { - "epoch": 0.68, - "learning_rate": 1.6111160934487242e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.309400237131161e-05, + "loss": 0.1606, "step": 152210 }, { - "epoch": 0.68, - "learning_rate": 1.610891888256132e-05, - "loss": 0.1632, + "epoch": 0.34, + "learning_rate": 3.3092883828102286e-05, + "loss": 0.1626, "step": 152220 }, { - "epoch": 0.68, - "learning_rate": 1.6106676830635396e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.309176528489296e-05, + "loss": 0.1609, "step": 152230 }, { - "epoch": 0.68, - "learning_rate": 1.6104434778709475e-05, - "loss": 0.1687, + "epoch": 0.34, + "learning_rate": 3.3090646741683635e-05, + "loss": 0.1634, "step": 152240 }, { - "epoch": 0.68, - "learning_rate": 1.6102192726783554e-05, - "loss": 0.1641, + "epoch": 0.34, + "learning_rate": 3.3089528198474306e-05, + "loss": 0.1586, "step": 152250 }, { - "epoch": 0.68, - "learning_rate": 1.6099950674857632e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.3088409655264984e-05, + "loss": 0.162, "step": 152260 }, { - "epoch": 0.68, - "learning_rate": 1.6097708622931708e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.308729111205566e-05, + "loss": 0.1587, "step": 152270 }, { - "epoch": 0.68, - "learning_rate": 1.6095466571005786e-05, - "loss": 0.1761, + "epoch": 0.34, + "learning_rate": 3.308617256884633e-05, + "loss": 0.1565, "step": 152280 }, { - "epoch": 0.68, - "learning_rate": 1.6093224519079865e-05, - "loss": 0.1627, + "epoch": 0.34, + "learning_rate": 3.308505402563701e-05, + "loss": 0.1649, "step": 152290 }, { - "epoch": 0.68, - "learning_rate": 1.609098246715394e-05, - "loss": 0.1653, + "epoch": 0.34, + "learning_rate": 3.308393548242769e-05, + "loss": 0.1602, "step": 152300 }, { - "epoch": 0.68, - "learning_rate": 1.608874041522802e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.308281693921837e-05, + "loss": 0.1588, "step": 152310 }, { - "epoch": 0.68, - "learning_rate": 1.6086498363302094e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.3081698396009045e-05, + "loss": 0.1577, "step": 152320 }, { - "epoch": 0.68, - "learning_rate": 1.6084256311376173e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.3080579852799716e-05, + "loss": 0.1622, "step": 152330 }, { - "epoch": 0.68, - "learning_rate": 1.6082014259450252e-05, - "loss": 0.1639, + "epoch": 0.34, + "learning_rate": 3.3079461309590394e-05, + "loss": 0.1611, "step": 152340 }, { - "epoch": 0.68, - "learning_rate": 1.6079772207524327e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.3078342766381065e-05, + "loss": 0.1646, "step": 152350 }, { - "epoch": 0.68, - "learning_rate": 1.6077530155598406e-05, - "loss": 0.1655, + "epoch": 0.34, + "learning_rate": 3.307722422317174e-05, + "loss": 0.1567, "step": 152360 }, { - "epoch": 0.68, - "learning_rate": 1.6075512308865074e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.3076105679962414e-05, + "loss": 0.1572, "step": 152370 }, { - "epoch": 0.68, - "learning_rate": 1.6073270256939152e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.307498713675309e-05, + "loss": 0.1677, "step": 152380 }, { - "epoch": 0.68, - "learning_rate": 1.6071028205013228e-05, - "loss": 0.1586, + "epoch": 0.34, + "learning_rate": 3.307386859354377e-05, + "loss": 0.1571, "step": 152390 }, { - "epoch": 0.68, - "learning_rate": 1.6068786153087306e-05, - "loss": 0.1637, + "epoch": 0.34, + "learning_rate": 3.307275005033445e-05, + "loss": 0.1584, "step": 152400 }, { - "epoch": 0.68, - "learning_rate": 1.6066544101161385e-05, - "loss": 0.1606, + "epoch": 0.34, + "learning_rate": 3.3071631507125126e-05, + "loss": 0.1582, "step": 152410 }, { - "epoch": 0.68, - "learning_rate": 1.606430204923546e-05, - "loss": 0.1649, + "epoch": 0.34, + "learning_rate": 3.30705129639158e-05, + "loss": 0.1561, "step": 152420 }, { - "epoch": 0.68, - "learning_rate": 1.606205999730954e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.3069394420706475e-05, + "loss": 0.1595, "step": 152430 }, { - "epoch": 0.68, - "learning_rate": 1.6059817945383615e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.306827587749715e-05, + "loss": 0.1586, "step": 152440 }, { - "epoch": 0.68, - "learning_rate": 1.6057575893457693e-05, - "loss": 0.1588, + "epoch": 0.34, + "learning_rate": 3.3067157334287824e-05, + "loss": 0.1604, "step": 152450 }, { - "epoch": 0.68, - "learning_rate": 1.605533384153177e-05, - "loss": 0.1697, + "epoch": 0.34, + "learning_rate": 3.30660387910785e-05, + "loss": 0.1587, "step": 152460 }, { - "epoch": 0.68, - "learning_rate": 1.6053091789605847e-05, - "loss": 0.1641, + "epoch": 0.34, + "learning_rate": 3.306492024786917e-05, + "loss": 0.1561, "step": 152470 }, { - "epoch": 0.68, - "learning_rate": 1.6050849737679926e-05, - "loss": 0.1693, + "epoch": 0.34, + "learning_rate": 3.306380170465985e-05, + "loss": 0.1601, "step": 152480 }, { - "epoch": 0.68, - "learning_rate": 1.6048607685754e-05, - "loss": 0.164, + "epoch": 0.34, + "learning_rate": 3.306268316145053e-05, + "loss": 0.1606, "step": 152490 }, { - "epoch": 0.68, - "learning_rate": 1.604636563382808e-05, - "loss": 0.1698, + "epoch": 0.34, + "learning_rate": 3.30615646182412e-05, + "loss": 0.1656, "step": 152500 }, { - "epoch": 0.68, - "learning_rate": 1.6044123581902155e-05, - "loss": 0.1624, + "epoch": 0.34, + "learning_rate": 3.306044607503188e-05, + "loss": 0.159, "step": 152510 }, { - "epoch": 0.68, - "learning_rate": 1.6041881529976234e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.3059327531822556e-05, + "loss": 0.162, "step": 152520 }, { - "epoch": 0.68, - "learning_rate": 1.6039639478050313e-05, - "loss": 0.1699, + "epoch": 0.34, + "learning_rate": 3.3058208988613234e-05, + "loss": 0.1572, "step": 152530 }, { - "epoch": 0.68, - "learning_rate": 1.6037397426124388e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.305709044540391e-05, + "loss": 0.1598, "step": 152540 }, { - "epoch": 0.68, - "learning_rate": 1.6035155374198467e-05, - "loss": 0.1683, + "epoch": 0.34, + "learning_rate": 3.305597190219458e-05, + "loss": 0.1632, "step": 152550 }, { - "epoch": 0.68, - "learning_rate": 1.6032913322272546e-05, - "loss": 0.1665, + "epoch": 0.34, + "learning_rate": 3.305485335898526e-05, + "loss": 0.1578, "step": 152560 }, { - "epoch": 0.68, - "learning_rate": 1.6030671270346624e-05, - "loss": 0.171, + "epoch": 0.34, + "learning_rate": 3.305373481577593e-05, + "loss": 0.1586, "step": 152570 }, { - "epoch": 0.68, - "learning_rate": 1.60284292184207e-05, - "loss": 0.1687, + "epoch": 0.34, + "learning_rate": 3.305261627256661e-05, + "loss": 0.1614, "step": 152580 }, { - "epoch": 0.68, - "learning_rate": 1.602618716649478e-05, - "loss": 0.1582, + "epoch": 0.34, + "learning_rate": 3.305149772935729e-05, + "loss": 0.1608, "step": 152590 }, { - "epoch": 0.68, - "learning_rate": 1.6023945114568854e-05, - "loss": 0.1582, + "epoch": 0.34, + "learning_rate": 3.305037918614796e-05, + "loss": 0.1597, "step": 152600 }, { - "epoch": 0.68, - "learning_rate": 1.6021703062642932e-05, - "loss": 0.1623, + "epoch": 0.34, + "learning_rate": 3.304926064293864e-05, + "loss": 0.1585, "step": 152610 }, { - "epoch": 0.68, - "learning_rate": 1.601946101071701e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.3048142099729315e-05, + "loss": 0.1586, "step": 152620 }, { - "epoch": 0.68, - "learning_rate": 1.6017218958791087e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.304702355651999e-05, + "loss": 0.1576, "step": 152630 }, { - "epoch": 0.68, - "learning_rate": 1.6014976906865165e-05, - "loss": 0.1671, + "epoch": 0.34, + "learning_rate": 3.304590501331067e-05, + "loss": 0.1602, "step": 152640 }, { - "epoch": 0.68, - "learning_rate": 1.601273485493924e-05, - "loss": 0.1657, + "epoch": 0.34, + "learning_rate": 3.304478647010134e-05, + "loss": 0.1618, "step": 152650 }, { - "epoch": 0.68, - "learning_rate": 1.601049280301332e-05, - "loss": 0.1689, + "epoch": 0.34, + "learning_rate": 3.304366792689202e-05, + "loss": 0.1645, "step": 152660 }, { - "epoch": 0.68, - "learning_rate": 1.6008250751087395e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.304254938368269e-05, + "loss": 0.163, "step": 152670 }, { - "epoch": 0.68, - "learning_rate": 1.6006008699161473e-05, - "loss": 0.1609, + "epoch": 0.34, + "learning_rate": 3.304143084047337e-05, + "loss": 0.1658, "step": 152680 }, { - "epoch": 0.68, - "learning_rate": 1.6003766647235552e-05, - "loss": 0.1603, + "epoch": 0.34, + "learning_rate": 3.304031229726404e-05, + "loss": 0.1564, "step": 152690 }, { - "epoch": 0.68, - "learning_rate": 1.6001524595309627e-05, - "loss": 0.1648, + "epoch": 0.34, + "learning_rate": 3.303919375405472e-05, + "loss": 0.1593, "step": 152700 }, { - "epoch": 0.68, - "learning_rate": 1.5999282543383706e-05, - "loss": 0.1655, + "epoch": 0.34, + "learning_rate": 3.3038075210845396e-05, + "loss": 0.1677, "step": 152710 }, { - "epoch": 0.68, - "learning_rate": 1.599704049145778e-05, - "loss": 0.1681, + "epoch": 0.34, + "learning_rate": 3.3036956667636074e-05, + "loss": 0.157, "step": 152720 }, { - "epoch": 0.68, - "learning_rate": 1.599479843953186e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.303583812442675e-05, + "loss": 0.1601, "step": 152730 }, { - "epoch": 0.68, - "learning_rate": 1.5992556387605935e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.303471958121742e-05, + "loss": 0.1627, "step": 152740 }, { - "epoch": 0.68, - "learning_rate": 1.5990314335680014e-05, - "loss": 0.1614, + "epoch": 0.34, + "learning_rate": 3.30336010380081e-05, + "loss": 0.1623, "step": 152750 }, { - "epoch": 0.68, - "learning_rate": 1.5988072283754093e-05, - "loss": 0.1691, + "epoch": 0.34, + "learning_rate": 3.303248249479878e-05, + "loss": 0.1664, "step": 152760 }, { - "epoch": 0.68, - "learning_rate": 1.5985830231828168e-05, - "loss": 0.1722, + "epoch": 0.34, + "learning_rate": 3.303136395158945e-05, + "loss": 0.1662, "step": 152770 }, { - "epoch": 0.68, - "learning_rate": 1.5983588179902247e-05, - "loss": 0.1641, + "epoch": 0.34, + "learning_rate": 3.303024540838013e-05, + "loss": 0.1546, "step": 152780 }, { - "epoch": 0.68, - "learning_rate": 1.5981346127976322e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.30291268651708e-05, + "loss": 0.1571, "step": 152790 }, { - "epoch": 0.68, - "learning_rate": 1.59791040760504e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.302800832196148e-05, + "loss": 0.1535, "step": 152800 }, { - "epoch": 0.68, - "learning_rate": 1.597686202412448e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.3026889778752155e-05, + "loss": 0.1583, "step": 152810 }, { - "epoch": 0.68, - "learning_rate": 1.597461997219856e-05, - "loss": 0.1704, + "epoch": 0.34, + "learning_rate": 3.302577123554283e-05, + "loss": 0.1599, "step": 152820 }, { - "epoch": 0.68, - "learning_rate": 1.5972377920272634e-05, - "loss": 0.1699, + "epoch": 0.34, + "learning_rate": 3.302465269233351e-05, + "loss": 0.1591, "step": 152830 }, { - "epoch": 0.68, - "learning_rate": 1.5970135868346712e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.302353414912418e-05, + "loss": 0.1603, "step": 152840 }, { - "epoch": 0.68, - "learning_rate": 1.596789381642079e-05, - "loss": 0.1677, + "epoch": 0.34, + "learning_rate": 3.302241560591486e-05, + "loss": 0.1653, "step": 152850 }, { - "epoch": 0.68, - "learning_rate": 1.5965651764494867e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.302129706270554e-05, + "loss": 0.1637, "step": 152860 }, { - "epoch": 0.68, - "learning_rate": 1.5963409712568945e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.302017851949621e-05, + "loss": 0.1608, "step": 152870 }, { - "epoch": 0.68, - "learning_rate": 1.596116766064302e-05, - "loss": 0.1657, + "epoch": 0.34, + "learning_rate": 3.301905997628689e-05, + "loss": 0.1626, "step": 152880 }, { - "epoch": 0.68, - "learning_rate": 1.59589256087171e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.301794143307756e-05, + "loss": 0.1576, "step": 152890 }, { - "epoch": 0.68, - "learning_rate": 1.5956683556791178e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.3016822889868236e-05, + "loss": 0.157, "step": 152900 }, { - "epoch": 0.68, - "learning_rate": 1.5954441504865253e-05, - "loss": 0.163, + "epoch": 0.34, + "learning_rate": 3.3015704346658914e-05, + "loss": 0.1644, "step": 152910 }, { - "epoch": 0.68, - "learning_rate": 1.5952199452939332e-05, - "loss": 0.1694, + "epoch": 0.34, + "learning_rate": 3.3014585803449585e-05, + "loss": 0.1602, "step": 152920 }, { - "epoch": 0.68, - "learning_rate": 1.5949957401013407e-05, - "loss": 0.1613, + "epoch": 0.34, + "learning_rate": 3.301346726024026e-05, + "loss": 0.1604, "step": 152930 }, { - "epoch": 0.68, - "learning_rate": 1.5947715349087486e-05, - "loss": 0.1662, + "epoch": 0.34, + "learning_rate": 3.301234871703094e-05, + "loss": 0.1609, "step": 152940 }, { - "epoch": 0.68, - "learning_rate": 1.594547329716156e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.301123017382162e-05, + "loss": 0.1589, "step": 152950 }, { - "epoch": 0.68, - "learning_rate": 1.594323124523564e-05, - "loss": 0.1638, + "epoch": 0.34, + "learning_rate": 3.3010111630612297e-05, + "loss": 0.1576, "step": 152960 }, { - "epoch": 0.68, - "learning_rate": 1.594098919330972e-05, - "loss": 0.1711, + "epoch": 0.34, + "learning_rate": 3.300899308740297e-05, + "loss": 0.1602, "step": 152970 }, { - "epoch": 0.68, - "learning_rate": 1.5938747141383794e-05, - "loss": 0.1682, + "epoch": 0.34, + "learning_rate": 3.3007874544193646e-05, + "loss": 0.1552, "step": 152980 }, { - "epoch": 0.68, - "learning_rate": 1.5936505089457873e-05, - "loss": 0.1599, + "epoch": 0.34, + "learning_rate": 3.300675600098432e-05, + "loss": 0.1595, "step": 152990 }, { - "epoch": 0.68, - "learning_rate": 1.5934263037531948e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.3005637457774995e-05, + "loss": 0.158, "step": 153000 }, { - "epoch": 0.68, - "learning_rate": 1.5932020985606027e-05, - "loss": 0.1621, + "epoch": 0.34, + "learning_rate": 3.3004518914565666e-05, + "loss": 0.1554, "step": 153010 }, { - "epoch": 0.68, - "learning_rate": 1.5929778933680102e-05, - "loss": 0.1609, + "epoch": 0.34, + "learning_rate": 3.3003400371356344e-05, + "loss": 0.156, "step": 153020 }, { - "epoch": 0.68, - "learning_rate": 1.592753688175418e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.300228182814702e-05, + "loss": 0.1642, "step": 153030 }, { - "epoch": 0.68, - "learning_rate": 1.592529482982826e-05, - "loss": 0.1668, + "epoch": 0.34, + "learning_rate": 3.30011632849377e-05, + "loss": 0.1557, "step": 153040 }, { - "epoch": 0.68, - "learning_rate": 1.5923052777902335e-05, - "loss": 0.1661, + "epoch": 0.34, + "learning_rate": 3.300004474172838e-05, + "loss": 0.1671, "step": 153050 }, { - "epoch": 0.68, - "learning_rate": 1.5920810725976414e-05, - "loss": 0.1651, + "epoch": 0.34, + "learning_rate": 3.299892619851905e-05, + "loss": 0.1618, "step": 153060 }, { - "epoch": 0.68, - "learning_rate": 1.591856867405049e-05, - "loss": 0.1579, + "epoch": 0.34, + "learning_rate": 3.299780765530973e-05, + "loss": 0.1607, "step": 153070 }, { - "epoch": 0.68, - "learning_rate": 1.5916326622124568e-05, - "loss": 0.1628, + "epoch": 0.34, + "learning_rate": 3.2996689112100405e-05, + "loss": 0.1611, "step": 153080 }, { - "epoch": 0.68, - "learning_rate": 1.5914084570198647e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.2995570568891076e-05, + "loss": 0.161, "step": 153090 }, { - "epoch": 0.68, - "learning_rate": 1.5911842518272725e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.2994452025681754e-05, + "loss": 0.1619, "step": 153100 }, { - "epoch": 0.68, - "learning_rate": 1.5909600466346804e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.2993333482472425e-05, + "loss": 0.1589, "step": 153110 }, { - "epoch": 0.68, - "learning_rate": 1.590735841442088e-05, - "loss": 0.1659, + "epoch": 0.34, + "learning_rate": 3.29922149392631e-05, + "loss": 0.1608, "step": 153120 }, { - "epoch": 0.68, - "learning_rate": 1.5905116362494958e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.299109639605378e-05, + "loss": 0.1537, "step": 153130 }, { - "epoch": 0.68, - "learning_rate": 1.5902874310569033e-05, - "loss": 0.1661, + "epoch": 0.34, + "learning_rate": 3.298997785284446e-05, + "loss": 0.1639, "step": 153140 }, { - "epoch": 0.68, - "learning_rate": 1.5900632258643112e-05, - "loss": 0.1639, + "epoch": 0.34, + "learning_rate": 3.2988859309635137e-05, + "loss": 0.1585, "step": 153150 }, { - "epoch": 0.68, - "learning_rate": 1.589839020671719e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.298774076642581e-05, + "loss": 0.1608, "step": 153160 }, { - "epoch": 0.68, - "learning_rate": 1.5896148154791266e-05, - "loss": 0.1652, + "epoch": 0.34, + "learning_rate": 3.2986622223216486e-05, + "loss": 0.1602, "step": 153170 }, { - "epoch": 0.68, - "learning_rate": 1.5893906102865345e-05, - "loss": 0.1621, + "epoch": 0.34, + "learning_rate": 3.2985503680007164e-05, + "loss": 0.163, "step": 153180 }, { - "epoch": 0.68, - "learning_rate": 1.589166405093942e-05, - "loss": 0.1698, + "epoch": 0.34, + "learning_rate": 3.2984385136797835e-05, + "loss": 0.165, "step": 153190 }, { - "epoch": 0.68, - "learning_rate": 1.58894219990135e-05, - "loss": 0.1667, + "epoch": 0.34, + "learning_rate": 3.298326659358851e-05, + "loss": 0.1626, "step": 153200 }, { - "epoch": 0.68, - "learning_rate": 1.5887179947087574e-05, - "loss": 0.1635, + "epoch": 0.34, + "learning_rate": 3.2982148050379184e-05, + "loss": 0.162, "step": 153210 }, { - "epoch": 0.68, - "learning_rate": 1.5884937895161653e-05, - "loss": 0.1695, + "epoch": 0.34, + "learning_rate": 3.298102950716986e-05, + "loss": 0.1575, "step": 153220 }, { - "epoch": 0.68, - "learning_rate": 1.588269584323573e-05, - "loss": 0.1612, + "epoch": 0.34, + "learning_rate": 3.297991096396054e-05, + "loss": 0.1609, "step": 153230 }, { - "epoch": 0.68, - "learning_rate": 1.5880453791309807e-05, - "loss": 0.1658, + "epoch": 0.34, + "learning_rate": 3.297879242075122e-05, + "loss": 0.1606, "step": 153240 }, { - "epoch": 0.68, - "learning_rate": 1.5878211739383886e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.2977673877541895e-05, + "loss": 0.1637, "step": 153250 }, { - "epoch": 0.68, - "learning_rate": 1.587596968745796e-05, - "loss": 0.1706, + "epoch": 0.34, + "learning_rate": 3.297655533433257e-05, + "loss": 0.1635, "step": 153260 }, { - "epoch": 0.68, - "learning_rate": 1.587372763553204e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.2975436791123245e-05, + "loss": 0.1602, "step": 153270 }, { - "epoch": 0.68, - "learning_rate": 1.5871485583606115e-05, - "loss": 0.1665, + "epoch": 0.34, + "learning_rate": 3.297431824791392e-05, + "loss": 0.1566, "step": 153280 }, { - "epoch": 0.68, - "learning_rate": 1.5869243531680194e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.2973199704704594e-05, + "loss": 0.1611, "step": 153290 }, { - "epoch": 0.68, - "learning_rate": 1.5867001479754273e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.297208116149527e-05, + "loss": 0.1569, "step": 153300 }, { - "epoch": 0.68, - "learning_rate": 1.5864759427828348e-05, - "loss": 0.1679, + "epoch": 0.34, + "learning_rate": 3.297096261828594e-05, + "loss": 0.1594, "step": 153310 }, { - "epoch": 0.68, - "learning_rate": 1.5862517375902427e-05, - "loss": 0.1682, + "epoch": 0.34, + "learning_rate": 3.296984407507662e-05, + "loss": 0.1549, "step": 153320 }, { - "epoch": 0.68, - "learning_rate": 1.5860275323976502e-05, - "loss": 0.1685, + "epoch": 0.34, + "learning_rate": 3.296872553186729e-05, + "loss": 0.1568, "step": 153330 }, { - "epoch": 0.68, - "learning_rate": 1.585803327205058e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.296760698865797e-05, + "loss": 0.1635, "step": 153340 }, { - "epoch": 0.68, - "learning_rate": 1.585579122012466e-05, - "loss": 0.1648, + "epoch": 0.34, + "learning_rate": 3.2966488445448654e-05, + "loss": 0.1638, "step": 153350 }, { - "epoch": 0.68, - "learning_rate": 1.5853549168198738e-05, - "loss": 0.1605, + "epoch": 0.34, + "learning_rate": 3.2965369902239326e-05, + "loss": 0.1591, "step": 153360 }, { - "epoch": 0.68, - "learning_rate": 1.5851307116272813e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.2964251359030004e-05, + "loss": 0.1658, "step": 153370 }, { - "epoch": 0.68, - "learning_rate": 1.5849065064346892e-05, - "loss": 0.1738, + "epoch": 0.34, + "learning_rate": 3.2963132815820675e-05, + "loss": 0.1598, "step": 153380 }, { - "epoch": 0.68, - "learning_rate": 1.584682301242097e-05, - "loss": 0.1681, + "epoch": 0.34, + "learning_rate": 3.296201427261135e-05, + "loss": 0.1541, "step": 153390 }, { - "epoch": 0.68, - "learning_rate": 1.5844580960495046e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.296089572940203e-05, + "loss": 0.1616, "step": 153400 }, { - "epoch": 0.68, - "learning_rate": 1.5842338908569125e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.29597771861927e-05, + "loss": 0.1589, "step": 153410 }, { - "epoch": 0.68, - "learning_rate": 1.58400968566432e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.295865864298338e-05, + "loss": 0.162, "step": 153420 }, { - "epoch": 0.68, - "learning_rate": 1.583785480471728e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.295754009977405e-05, + "loss": 0.1605, "step": 153430 }, { - "epoch": 0.68, - "learning_rate": 1.5835612752791358e-05, - "loss": 0.1709, + "epoch": 0.34, + "learning_rate": 3.295642155656473e-05, + "loss": 0.1628, "step": 153440 }, { - "epoch": 0.69, - "learning_rate": 1.5833370700865433e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.2955303013355407e-05, + "loss": 0.1559, "step": 153450 }, { - "epoch": 0.69, - "learning_rate": 1.583112864893951e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.2954184470146085e-05, + "loss": 0.1614, "step": 153460 }, { - "epoch": 0.69, - "learning_rate": 1.5828886597013587e-05, - "loss": 0.1683, + "epoch": 0.34, + "learning_rate": 3.295306592693676e-05, + "loss": 0.1639, "step": 153470 }, { - "epoch": 0.69, - "learning_rate": 1.5826644545087666e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.2951947383727434e-05, + "loss": 0.1561, "step": 153480 }, { - "epoch": 0.69, - "learning_rate": 1.582440249316174e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.295082884051811e-05, + "loss": 0.159, "step": 153490 }, { - "epoch": 0.69, - "learning_rate": 1.582216044123582e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.294971029730879e-05, + "loss": 0.159, "step": 153500 }, { - "epoch": 0.69, - "learning_rate": 1.58199183893099e-05, - "loss": 0.161, + "epoch": 0.34, + "learning_rate": 3.294859175409946e-05, + "loss": 0.1608, "step": 153510 }, { - "epoch": 0.69, - "learning_rate": 1.5817676337383974e-05, - "loss": 0.1695, + "epoch": 0.34, + "learning_rate": 3.294747321089014e-05, + "loss": 0.1635, "step": 153520 }, { - "epoch": 0.69, - "learning_rate": 1.5815434285458053e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.294635466768081e-05, + "loss": 0.1644, "step": 153530 }, { - "epoch": 0.69, - "learning_rate": 1.5813192233532128e-05, - "loss": 0.171, + "epoch": 0.34, + "learning_rate": 3.294523612447149e-05, + "loss": 0.1613, "step": 153540 }, { - "epoch": 0.69, - "learning_rate": 1.5810950181606207e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.2944117581262166e-05, + "loss": 0.1596, "step": 153550 }, { - "epoch": 0.69, - "learning_rate": 1.5808708129680282e-05, - "loss": 0.1718, + "epoch": 0.34, + "learning_rate": 3.2942999038052843e-05, + "loss": 0.1585, "step": 153560 }, { - "epoch": 0.69, - "learning_rate": 1.580646607775436e-05, - "loss": 0.1703, + "epoch": 0.34, + "learning_rate": 3.294188049484352e-05, + "loss": 0.1588, "step": 153570 }, { - "epoch": 0.69, - "learning_rate": 1.580422402582844e-05, - "loss": 0.1594, + "epoch": 0.34, + "learning_rate": 3.294076195163419e-05, + "loss": 0.1528, "step": 153580 }, { - "epoch": 0.69, - "learning_rate": 1.5801981973902515e-05, - "loss": 0.1652, + "epoch": 0.34, + "learning_rate": 3.293964340842487e-05, + "loss": 0.1551, "step": 153590 }, { - "epoch": 0.69, - "learning_rate": 1.5799739921976593e-05, - "loss": 0.1612, + "epoch": 0.34, + "learning_rate": 3.293852486521555e-05, + "loss": 0.1584, "step": 153600 }, { - "epoch": 0.69, - "learning_rate": 1.579749787005067e-05, - "loss": 0.1709, + "epoch": 0.34, + "learning_rate": 3.293740632200622e-05, + "loss": 0.1562, "step": 153610 }, { - "epoch": 0.69, - "learning_rate": 1.5795255818124747e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.29362877787969e-05, + "loss": 0.1603, "step": 153620 }, { - "epoch": 0.69, - "learning_rate": 1.5793013766198826e-05, - "loss": 0.1627, + "epoch": 0.34, + "learning_rate": 3.293516923558757e-05, + "loss": 0.1597, "step": 153630 }, { - "epoch": 0.69, - "learning_rate": 1.5790771714272905e-05, - "loss": 0.1619, + "epoch": 0.34, + "learning_rate": 3.2934050692378247e-05, + "loss": 0.1599, "step": 153640 }, { - "epoch": 0.69, - "learning_rate": 1.5788529662346984e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.2932932149168924e-05, + "loss": 0.1634, "step": 153650 }, { - "epoch": 0.69, - "learning_rate": 1.578628761042106e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.29318136059596e-05, + "loss": 0.1548, "step": 153660 }, { - "epoch": 0.69, - "learning_rate": 1.5784045558495138e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.293069506275028e-05, + "loss": 0.1594, "step": 153670 }, { - "epoch": 0.69, - "learning_rate": 1.5781803506569213e-05, - "loss": 0.1678, + "epoch": 0.34, + "learning_rate": 3.292957651954095e-05, + "loss": 0.1552, "step": 153680 }, { - "epoch": 0.69, - "learning_rate": 1.577956145464329e-05, - "loss": 0.1669, + "epoch": 0.34, + "learning_rate": 3.292845797633163e-05, + "loss": 0.1601, "step": 153690 }, { - "epoch": 0.69, - "learning_rate": 1.5777319402717367e-05, - "loss": 0.1713, + "epoch": 0.34, + "learning_rate": 3.29273394331223e-05, + "loss": 0.1613, "step": 153700 }, { - "epoch": 0.69, - "learning_rate": 1.5775077350791446e-05, - "loss": 0.1625, + "epoch": 0.34, + "learning_rate": 3.292622088991298e-05, + "loss": 0.1616, "step": 153710 }, { - "epoch": 0.69, - "learning_rate": 1.5772835298865524e-05, - "loss": 0.1657, + "epoch": 0.34, + "learning_rate": 3.2925102346703656e-05, + "loss": 0.1576, "step": 153720 }, { - "epoch": 0.69, - "learning_rate": 1.57705932469396e-05, - "loss": 0.1635, + "epoch": 0.34, + "learning_rate": 3.292398380349433e-05, + "loss": 0.1566, "step": 153730 }, { - "epoch": 0.69, - "learning_rate": 1.576835119501368e-05, - "loss": 0.1599, + "epoch": 0.34, + "learning_rate": 3.2922865260285006e-05, + "loss": 0.1631, "step": 153740 }, { - "epoch": 0.69, - "learning_rate": 1.5766109143087754e-05, - "loss": 0.1628, + "epoch": 0.34, + "learning_rate": 3.292174671707568e-05, + "loss": 0.154, "step": 153750 }, { - "epoch": 0.69, - "learning_rate": 1.5763867091161833e-05, - "loss": 0.1623, + "epoch": 0.34, + "learning_rate": 3.292062817386636e-05, + "loss": 0.1634, "step": 153760 }, { - "epoch": 0.69, - "learning_rate": 1.5761625039235908e-05, - "loss": 0.1663, + "epoch": 0.34, + "learning_rate": 3.291950963065704e-05, + "loss": 0.1583, "step": 153770 }, { - "epoch": 0.69, - "learning_rate": 1.5759382987309987e-05, - "loss": 0.1674, + "epoch": 0.34, + "learning_rate": 3.291839108744771e-05, + "loss": 0.1593, "step": 153780 }, { - "epoch": 0.69, - "learning_rate": 1.5757140935384065e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.291727254423839e-05, + "loss": 0.1618, "step": 153790 }, { - "epoch": 0.69, - "learning_rate": 1.575489888345814e-05, - "loss": 0.1666, + "epoch": 0.34, + "learning_rate": 3.291615400102906e-05, + "loss": 0.1586, "step": 153800 }, { - "epoch": 0.69, - "learning_rate": 1.575265683153222e-05, - "loss": 0.1671, + "epoch": 0.34, + "learning_rate": 3.291503545781974e-05, + "loss": 0.1529, "step": 153810 }, { - "epoch": 0.69, - "learning_rate": 1.5750414779606295e-05, - "loss": 0.1673, + "epoch": 0.34, + "learning_rate": 3.2913916914610415e-05, + "loss": 0.1591, "step": 153820 }, { - "epoch": 0.69, - "learning_rate": 1.5748172727680373e-05, - "loss": 0.1651, + "epoch": 0.34, + "learning_rate": 3.2912798371401087e-05, + "loss": 0.1606, "step": 153830 }, { - "epoch": 0.69, - "learning_rate": 1.574593067575445e-05, - "loss": 0.1637, + "epoch": 0.34, + "learning_rate": 3.2911679828191764e-05, + "loss": 0.1577, "step": 153840 }, { - "epoch": 0.69, - "learning_rate": 1.5743688623828527e-05, - "loss": 0.1664, + "epoch": 0.34, + "learning_rate": 3.2910561284982436e-05, + "loss": 0.1579, "step": 153850 }, { - "epoch": 0.69, - "learning_rate": 1.5741446571902606e-05, - "loss": 0.1615, + "epoch": 0.34, + "learning_rate": 3.2909442741773114e-05, + "loss": 0.1647, "step": 153860 }, { - "epoch": 0.69, - "learning_rate": 1.573920451997668e-05, - "loss": 0.1607, + "epoch": 0.34, + "learning_rate": 3.290832419856379e-05, + "loss": 0.1654, "step": 153870 }, { - "epoch": 0.69, - "learning_rate": 1.573696246805076e-05, - "loss": 0.1671, + "epoch": 0.34, + "learning_rate": 3.290720565535447e-05, + "loss": 0.1625, "step": 153880 }, { - "epoch": 0.69, - "learning_rate": 1.573472041612484e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.290608711214515e-05, + "loss": 0.1708, "step": 153890 }, { - "epoch": 0.69, - "learning_rate": 1.5732478364198918e-05, - "loss": 0.1628, + "epoch": 0.34, + "learning_rate": 3.290496856893582e-05, + "loss": 0.1533, "step": 153900 }, { - "epoch": 0.69, - "learning_rate": 1.5730236312272993e-05, - "loss": 0.1705, + "epoch": 0.34, + "learning_rate": 3.2903850025726496e-05, + "loss": 0.1549, "step": 153910 }, { - "epoch": 0.69, - "learning_rate": 1.5727994260347072e-05, - "loss": 0.166, + "epoch": 0.34, + "learning_rate": 3.2902731482517174e-05, + "loss": 0.1529, "step": 153920 }, { - "epoch": 0.69, - "learning_rate": 1.572575220842115e-05, - "loss": 0.168, + "epoch": 0.34, + "learning_rate": 3.2901612939307845e-05, + "loss": 0.1559, "step": 153930 }, { - "epoch": 0.69, - "learning_rate": 1.5723510156495226e-05, - "loss": 0.1604, + "epoch": 0.34, + "learning_rate": 3.2900494396098523e-05, + "loss": 0.1587, "step": 153940 }, { - "epoch": 0.69, - "learning_rate": 1.5721268104569304e-05, - "loss": 0.1629, + "epoch": 0.34, + "learning_rate": 3.2899375852889195e-05, + "loss": 0.1619, "step": 153950 }, { - "epoch": 0.69, - "learning_rate": 1.571902605264338e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.289825730967987e-05, + "loss": 0.1636, "step": 153960 }, { - "epoch": 0.69, - "learning_rate": 1.571678400071746e-05, - "loss": 0.1722, + "epoch": 0.34, + "learning_rate": 3.289713876647055e-05, + "loss": 0.1625, "step": 153970 }, { - "epoch": 0.69, - "learning_rate": 1.5714541948791534e-05, - "loss": 0.1648, + "epoch": 0.34, + "learning_rate": 3.289602022326123e-05, + "loss": 0.1626, "step": 153980 }, { - "epoch": 0.69, - "learning_rate": 1.5712299896865613e-05, - "loss": 0.1677, + "epoch": 0.34, + "learning_rate": 3.2894901680051906e-05, + "loss": 0.1655, "step": 153990 }, { - "epoch": 0.69, - "learning_rate": 1.571005784493969e-05, - "loss": 0.1673, + "epoch": 0.34, + "learning_rate": 3.289378313684258e-05, + "loss": 0.156, "step": 154000 }, { - "epoch": 0.69, - "learning_rate": 1.5707815793013767e-05, - "loss": 0.1603, + "epoch": 0.34, + "learning_rate": 3.2892664593633255e-05, + "loss": 0.161, "step": 154010 }, { - "epoch": 0.69, - "learning_rate": 1.5705573741087845e-05, - "loss": 0.1622, + "epoch": 0.34, + "learning_rate": 3.2891546050423927e-05, + "loss": 0.1591, "step": 154020 }, { - "epoch": 0.69, - "learning_rate": 1.570333168916192e-05, - "loss": 0.1654, + "epoch": 0.34, + "learning_rate": 3.2890427507214604e-05, + "loss": 0.1571, "step": 154030 }, { - "epoch": 0.69, - "learning_rate": 1.5701089637236e-05, - "loss": 0.1691, + "epoch": 0.34, + "learning_rate": 3.288930896400528e-05, + "loss": 0.164, "step": 154040 }, { - "epoch": 0.69, - "learning_rate": 1.5698847585310075e-05, - "loss": 0.1612, + "epoch": 0.34, + "learning_rate": 3.2888190420795954e-05, + "loss": 0.1582, "step": 154050 }, { - "epoch": 0.69, - "learning_rate": 1.5696605533384153e-05, - "loss": 0.1717, + "epoch": 0.34, + "learning_rate": 3.288707187758663e-05, + "loss": 0.1641, "step": 154060 }, { - "epoch": 0.69, - "learning_rate": 1.5694363481458232e-05, - "loss": 0.1717, + "epoch": 0.34, + "learning_rate": 3.288595333437731e-05, + "loss": 0.1551, "step": 154070 }, { - "epoch": 0.69, - "learning_rate": 1.5692121429532307e-05, - "loss": 0.1656, + "epoch": 0.34, + "learning_rate": 3.288483479116799e-05, + "loss": 0.1583, "step": 154080 }, { - "epoch": 0.69, - "learning_rate": 1.5689879377606386e-05, - "loss": 0.1678, + "epoch": 0.34, + "learning_rate": 3.2883716247958665e-05, + "loss": 0.1601, "step": 154090 }, { - "epoch": 0.69, - "learning_rate": 1.568763732568046e-05, - "loss": 0.1577, + "epoch": 0.34, + "learning_rate": 3.2882597704749336e-05, + "loss": 0.1584, "step": 154100 }, { - "epoch": 0.69, - "learning_rate": 1.568539527375454e-05, - "loss": 0.1595, + "epoch": 0.34, + "learning_rate": 3.2881479161540014e-05, + "loss": 0.1615, "step": 154110 }, { - "epoch": 0.69, - "learning_rate": 1.5683153221828616e-05, - "loss": 0.1676, + "epoch": 0.34, + "learning_rate": 3.2880472472651616e-05, + "loss": 0.1664, "step": 154120 }, { - "epoch": 0.69, - "learning_rate": 1.5680911169902694e-05, - "loss": 0.1729, + "epoch": 0.34, + "learning_rate": 3.2879353929442294e-05, + "loss": 0.1571, "step": 154130 }, { - "epoch": 0.69, - "learning_rate": 1.5678669117976773e-05, - "loss": 0.1646, + "epoch": 0.34, + "learning_rate": 3.287823538623297e-05, + "loss": 0.1588, "step": 154140 }, { - "epoch": 0.69, - "learning_rate": 1.567642706605085e-05, - "loss": 0.1727, + "epoch": 0.34, + "learning_rate": 3.287711684302365e-05, + "loss": 0.1657, "step": 154150 }, { - "epoch": 0.69, - "learning_rate": 1.5674185014124927e-05, - "loss": 0.1681, + "epoch": 0.34, + "learning_rate": 3.287599829981433e-05, + "loss": 0.1593, "step": 154160 }, { - "epoch": 0.69, - "learning_rate": 1.5671942962199006e-05, - "loss": 0.1653, + "epoch": 0.34, + "learning_rate": 3.2874879756605e-05, + "loss": 0.1563, "step": 154170 }, { - "epoch": 0.69, - "learning_rate": 1.5669700910273084e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.287376121339568e-05, + "loss": 0.1594, "step": 154180 }, { - "epoch": 0.69, - "learning_rate": 1.566745885834716e-05, - "loss": 0.1632, + "epoch": 0.34, + "learning_rate": 3.287264267018635e-05, + "loss": 0.1579, "step": 154190 }, { - "epoch": 0.69, - "learning_rate": 1.566521680642124e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.2871524126977026e-05, + "loss": 0.1601, "step": 154200 }, { - "epoch": 0.69, - "learning_rate": 1.5662974754495317e-05, - "loss": 0.1675, + "epoch": 0.34, + "learning_rate": 3.2870405583767704e-05, + "loss": 0.1634, "step": 154210 }, { - "epoch": 0.69, - "learning_rate": 1.5660732702569393e-05, - "loss": 0.1646, + "epoch": 0.34, + "learning_rate": 3.2869287040558375e-05, + "loss": 0.1561, "step": 154220 }, { - "epoch": 0.69, - "learning_rate": 1.565849065064347e-05, - "loss": 0.1599, + "epoch": 0.34, + "learning_rate": 3.286816849734905e-05, + "loss": 0.1591, "step": 154230 }, { - "epoch": 0.69, - "learning_rate": 1.5656248598717547e-05, - "loss": 0.1627, + "epoch": 0.34, + "learning_rate": 3.286704995413973e-05, + "loss": 0.1547, "step": 154240 }, { - "epoch": 0.69, - "learning_rate": 1.5654006546791625e-05, - "loss": 0.1647, + "epoch": 0.34, + "learning_rate": 3.286593141093041e-05, + "loss": 0.1549, "step": 154250 }, { - "epoch": 0.69, - "learning_rate": 1.56517644948657e-05, - "loss": 0.1632, - "step": 154260 + "epoch": 0.34, + "learning_rate": 3.286481286772109e-05, + "loss": 0.1501, + "step": 154260 }, { - "epoch": 0.69, - "learning_rate": 1.564952244293978e-05, - "loss": 0.1617, + "epoch": 0.34, + "learning_rate": 3.286369432451176e-05, + "loss": 0.1601, "step": 154270 }, { - "epoch": 0.69, - "learning_rate": 1.5647280391013858e-05, - "loss": 0.1642, + "epoch": 0.34, + "learning_rate": 3.2862575781302436e-05, + "loss": 0.1551, "step": 154280 }, { - "epoch": 0.69, - "learning_rate": 1.5645038339087933e-05, - "loss": 0.1654, + "epoch": 0.34, + "learning_rate": 3.286145723809311e-05, + "loss": 0.1637, "step": 154290 }, { - "epoch": 0.69, - "learning_rate": 1.5642796287162012e-05, - "loss": 0.1666, + "epoch": 0.34, + "learning_rate": 3.2860338694883785e-05, + "loss": 0.1607, "step": 154300 }, { - "epoch": 0.69, - "learning_rate": 1.5640554235236087e-05, - "loss": 0.1669, + "epoch": 0.34, + "learning_rate": 3.2859220151674456e-05, + "loss": 0.166, "step": 154310 }, { - "epoch": 0.69, - "learning_rate": 1.5638312183310166e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.2858101608465134e-05, + "loss": 0.1598, "step": 154320 }, { - "epoch": 0.69, - "learning_rate": 1.563607013138424e-05, - "loss": 0.1637, + "epoch": 0.34, + "learning_rate": 3.285698306525581e-05, + "loss": 0.1635, "step": 154330 }, { - "epoch": 0.69, - "learning_rate": 1.563382807945832e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.285586452204649e-05, + "loss": 0.1591, "step": 154340 }, { - "epoch": 0.69, - "learning_rate": 1.56315860275324e-05, - "loss": 0.1659, + "epoch": 0.34, + "learning_rate": 3.285474597883717e-05, + "loss": 0.1575, "step": 154350 }, { - "epoch": 0.69, - "learning_rate": 1.5629343975606474e-05, - "loss": 0.1684, + "epoch": 0.34, + "learning_rate": 3.285362743562784e-05, + "loss": 0.159, "step": 154360 }, { - "epoch": 0.69, - "learning_rate": 1.5627101923680553e-05, - "loss": 0.1639, + "epoch": 0.34, + "learning_rate": 3.285250889241852e-05, + "loss": 0.1613, "step": 154370 }, { - "epoch": 0.69, - "learning_rate": 1.562508407694722e-05, - "loss": 0.1625, + "epoch": 0.34, + "learning_rate": 3.2851390349209195e-05, + "loss": 0.1607, "step": 154380 }, { - "epoch": 0.69, - "learning_rate": 1.56228420250213e-05, - "loss": 0.1636, + "epoch": 0.34, + "learning_rate": 3.2850271805999866e-05, + "loss": 0.1566, "step": 154390 }, { - "epoch": 0.69, - "learning_rate": 1.5620599973095378e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.2849153262790544e-05, + "loss": 0.163, "step": 154400 }, { - "epoch": 0.69, - "learning_rate": 1.5618357921169454e-05, - "loss": 0.1621, + "epoch": 0.34, + "learning_rate": 3.2848034719581215e-05, + "loss": 0.1613, "step": 154410 }, { - "epoch": 0.69, - "learning_rate": 1.5616115869243532e-05, - "loss": 0.1616, + "epoch": 0.34, + "learning_rate": 3.284691617637189e-05, + "loss": 0.1636, "step": 154420 }, { - "epoch": 0.69, - "learning_rate": 1.5613873817317608e-05, - "loss": 0.1654, + "epoch": 0.34, + "learning_rate": 3.284579763316257e-05, + "loss": 0.1603, "step": 154430 }, { - "epoch": 0.69, - "learning_rate": 1.5611631765391686e-05, - "loss": 0.1631, + "epoch": 0.34, + "learning_rate": 3.284467908995324e-05, + "loss": 0.1578, "step": 154440 }, { - "epoch": 0.69, - "learning_rate": 1.5609389713465765e-05, - "loss": 0.1621, + "epoch": 0.34, + "learning_rate": 3.284356054674392e-05, + "loss": 0.1569, "step": 154450 }, { - "epoch": 0.69, - "learning_rate": 1.5607147661539844e-05, - "loss": 0.1614, + "epoch": 0.34, + "learning_rate": 3.28424420035346e-05, + "loss": 0.157, "step": 154460 }, { - "epoch": 0.69, - "learning_rate": 1.560490560961392e-05, - "loss": 0.1608, + "epoch": 0.34, + "learning_rate": 3.2841323460325276e-05, + "loss": 0.1563, "step": 154470 }, { - "epoch": 0.69, - "learning_rate": 1.5602663557687998e-05, - "loss": 0.165, + "epoch": 0.34, + "learning_rate": 3.2840204917115954e-05, + "loss": 0.1617, "step": 154480 }, { - "epoch": 0.69, - "learning_rate": 1.5600421505762077e-05, - "loss": 0.1645, + "epoch": 0.34, + "learning_rate": 3.2839086373906625e-05, + "loss": 0.1596, "step": 154490 }, { - "epoch": 0.69, - "learning_rate": 1.5598179453836152e-05, - "loss": 0.167, + "epoch": 0.34, + "learning_rate": 3.28379678306973e-05, + "loss": 0.1555, "step": 154500 }, { - "epoch": 0.69, - "learning_rate": 1.559593740191023e-05, - "loss": 0.1649, + "epoch": 0.34, + "learning_rate": 3.2836849287487974e-05, + "loss": 0.1644, "step": 154510 }, { - "epoch": 0.69, - "learning_rate": 1.5593695349984306e-05, - "loss": 0.1688, + "epoch": 0.34, + "learning_rate": 3.283573074427865e-05, + "loss": 0.1629, "step": 154520 }, { - "epoch": 0.69, - "learning_rate": 1.5591453298058385e-05, - "loss": 0.1584, + "epoch": 0.34, + "learning_rate": 3.283461220106933e-05, + "loss": 0.1633, "step": 154530 }, { - "epoch": 0.69, - "learning_rate": 1.5589211246132463e-05, - "loss": 0.1592, + "epoch": 0.34, + "learning_rate": 3.283349365786e-05, + "loss": 0.1575, "step": 154540 }, { - "epoch": 0.69, - "learning_rate": 1.558696919420654e-05, - "loss": 0.1633, + "epoch": 0.34, + "learning_rate": 3.283237511465068e-05, + "loss": 0.1584, "step": 154550 }, { - "epoch": 0.69, - "learning_rate": 1.5584727142280617e-05, - "loss": 0.1672, + "epoch": 0.34, + "learning_rate": 3.283125657144136e-05, + "loss": 0.1616, "step": 154560 }, { - "epoch": 0.69, - "learning_rate": 1.5582485090354693e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.2830138028232035e-05, + "loss": 0.1593, "step": 154570 }, { - "epoch": 0.69, - "learning_rate": 1.558024303842877e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.282901948502271e-05, + "loss": 0.1618, "step": 154580 }, { - "epoch": 0.69, - "learning_rate": 1.5578000986502847e-05, - "loss": 0.1648, + "epoch": 0.35, + "learning_rate": 3.2827900941813384e-05, + "loss": 0.1635, "step": 154590 }, { - "epoch": 0.69, - "learning_rate": 1.5575758934576925e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.282678239860406e-05, + "loss": 0.1609, "step": 154600 }, { - "epoch": 0.69, - "learning_rate": 1.5573516882651004e-05, - "loss": 0.1653, + "epoch": 0.35, + "learning_rate": 3.282566385539473e-05, + "loss": 0.161, "step": 154610 }, { - "epoch": 0.69, - "learning_rate": 1.557127483072508e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.282454531218541e-05, + "loss": 0.1551, "step": 154620 }, { - "epoch": 0.69, - "learning_rate": 1.5569032778799158e-05, - "loss": 0.165, + "epoch": 0.35, + "learning_rate": 3.282342676897608e-05, + "loss": 0.1643, "step": 154630 }, { - "epoch": 0.69, - "learning_rate": 1.5566790726873234e-05, - "loss": 0.1596, + "epoch": 0.35, + "learning_rate": 3.282230822576676e-05, + "loss": 0.1578, "step": 154640 }, { - "epoch": 0.69, - "learning_rate": 1.5564548674947312e-05, - "loss": 0.1677, + "epoch": 0.35, + "learning_rate": 3.282118968255744e-05, + "loss": 0.1587, "step": 154650 }, { - "epoch": 0.69, - "learning_rate": 1.5562306623021388e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.2820071139348116e-05, + "loss": 0.1571, "step": 154660 }, { - "epoch": 0.69, - "learning_rate": 1.5560064571095466e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.2818952596138794e-05, + "loss": 0.1584, "step": 154670 }, { - "epoch": 0.69, - "learning_rate": 1.5557822519169545e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.2817834052929465e-05, + "loss": 0.162, "step": 154680 }, { - "epoch": 0.69, - "learning_rate": 1.555558046724362e-05, - "loss": 0.165, + "epoch": 0.35, + "learning_rate": 3.281671550972014e-05, + "loss": 0.1645, "step": 154690 }, { - "epoch": 0.69, - "learning_rate": 1.55533384153177e-05, - "loss": 0.1604, + "epoch": 0.35, + "learning_rate": 3.281559696651082e-05, + "loss": 0.1558, "step": 154700 }, { - "epoch": 0.69, - "learning_rate": 1.5551096363391774e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.281447842330149e-05, + "loss": 0.1555, "step": 154710 }, { - "epoch": 0.69, - "learning_rate": 1.5548854311465853e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.281335988009217e-05, + "loss": 0.1585, "step": 154720 }, { - "epoch": 0.69, - "learning_rate": 1.5546612259539932e-05, - "loss": 0.1578, + "epoch": 0.35, + "learning_rate": 3.281224133688284e-05, + "loss": 0.156, "step": 154730 }, { - "epoch": 0.69, - "learning_rate": 1.554437020761401e-05, - "loss": 0.1694, + "epoch": 0.35, + "learning_rate": 3.281112279367352e-05, + "loss": 0.1584, "step": 154740 }, { - "epoch": 0.69, - "learning_rate": 1.554212815568809e-05, - "loss": 0.1659, + "epoch": 0.35, + "learning_rate": 3.28100042504642e-05, + "loss": 0.1597, "step": 154750 }, { - "epoch": 0.69, - "learning_rate": 1.5539886103762165e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.2808885707254875e-05, + "loss": 0.16, "step": 154760 }, { - "epoch": 0.69, - "learning_rate": 1.5537644051836243e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.280776716404555e-05, + "loss": 0.1589, "step": 154770 }, { - "epoch": 0.69, - "learning_rate": 1.553540199991032e-05, - "loss": 0.1594, + "epoch": 0.35, + "learning_rate": 3.2806648620836224e-05, + "loss": 0.1586, "step": 154780 }, { - "epoch": 0.69, - "learning_rate": 1.5533159947984397e-05, - "loss": 0.1692, + "epoch": 0.35, + "learning_rate": 3.28055300776269e-05, + "loss": 0.1601, "step": 154790 }, { - "epoch": 0.69, - "learning_rate": 1.5530917896058473e-05, - "loss": 0.16, + "epoch": 0.35, + "learning_rate": 3.280441153441758e-05, + "loss": 0.1559, "step": 154800 }, { - "epoch": 0.69, - "learning_rate": 1.552867584413255e-05, - "loss": 0.1612, + "epoch": 0.35, + "learning_rate": 3.280329299120825e-05, + "loss": 0.1651, "step": 154810 }, { - "epoch": 0.69, - "learning_rate": 1.552643379220663e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.280217444799893e-05, + "loss": 0.1618, "step": 154820 }, { - "epoch": 0.69, - "learning_rate": 1.5524191740280706e-05, - "loss": 0.1666, + "epoch": 0.35, + "learning_rate": 3.28010559047896e-05, + "loss": 0.1577, "step": 154830 }, { - "epoch": 0.69, - "learning_rate": 1.5521949688354784e-05, - "loss": 0.1657, + "epoch": 0.35, + "learning_rate": 3.279993736158028e-05, + "loss": 0.1546, "step": 154840 }, { - "epoch": 0.69, - "learning_rate": 1.551970763642886e-05, - "loss": 0.1607, + "epoch": 0.35, + "learning_rate": 3.2798818818370956e-05, + "loss": 0.1608, "step": 154850 }, { - "epoch": 0.69, - "learning_rate": 1.5517465584502938e-05, - "loss": 0.1685, + "epoch": 0.35, + "learning_rate": 3.279770027516163e-05, + "loss": 0.163, "step": 154860 }, { - "epoch": 0.69, - "learning_rate": 1.5515223532577014e-05, - "loss": 0.1594, + "epoch": 0.35, + "learning_rate": 3.2796581731952305e-05, + "loss": 0.1546, "step": 154870 }, { - "epoch": 0.69, - "learning_rate": 1.5512981480651092e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.279546318874298e-05, + "loss": 0.1578, "step": 154880 }, { - "epoch": 0.69, - "learning_rate": 1.551073942872517e-05, - "loss": 0.1679, + "epoch": 0.35, + "learning_rate": 3.279434464553366e-05, + "loss": 0.1601, "step": 154890 }, { - "epoch": 0.69, - "learning_rate": 1.5508497376799246e-05, - "loss": 0.161, + "epoch": 0.35, + "learning_rate": 3.279322610232434e-05, + "loss": 0.1584, "step": 154900 }, { - "epoch": 0.69, - "learning_rate": 1.5506255324873325e-05, - "loss": 0.1593, + "epoch": 0.35, + "learning_rate": 3.279210755911501e-05, + "loss": 0.1611, "step": 154910 }, { - "epoch": 0.69, - "learning_rate": 1.55040132729474e-05, - "loss": 0.1633, + "epoch": 0.35, + "learning_rate": 3.279098901590569e-05, + "loss": 0.1533, "step": 154920 }, { - "epoch": 0.69, - "learning_rate": 1.550177122102148e-05, - "loss": 0.1605, + "epoch": 0.35, + "learning_rate": 3.278987047269636e-05, + "loss": 0.1598, "step": 154930 }, { - "epoch": 0.69, - "learning_rate": 1.5499529169095554e-05, - "loss": 0.1655, + "epoch": 0.35, + "learning_rate": 3.278875192948704e-05, + "loss": 0.1616, "step": 154940 }, { - "epoch": 0.69, - "learning_rate": 1.5497287117169633e-05, - "loss": 0.1666, + "epoch": 0.35, + "learning_rate": 3.278763338627771e-05, + "loss": 0.1601, "step": 154950 }, { - "epoch": 0.69, - "learning_rate": 1.5495045065243712e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.2786514843068386e-05, + "loss": 0.1573, "step": 154960 }, { - "epoch": 0.69, - "learning_rate": 1.5492803013317787e-05, - "loss": 0.167, + "epoch": 0.35, + "learning_rate": 3.2785396299859064e-05, + "loss": 0.1602, "step": 154970 }, { - "epoch": 0.69, - "learning_rate": 1.5490560961391866e-05, - "loss": 0.1611, + "epoch": 0.35, + "learning_rate": 3.278427775664974e-05, + "loss": 0.1567, "step": 154980 }, { - "epoch": 0.69, - "learning_rate": 1.5488318909465945e-05, - "loss": 0.157, + "epoch": 0.35, + "learning_rate": 3.278315921344042e-05, + "loss": 0.1621, "step": 154990 }, { - "epoch": 0.69, - "learning_rate": 1.5486076857540023e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.278204067023109e-05, + "loss": 0.1512, "step": 155000 }, { - "epoch": 0.69, - "learning_rate": 1.54838348056141e-05, - "loss": 0.1612, + "epoch": 0.35, + "learning_rate": 3.278092212702177e-05, + "loss": 0.1579, "step": 155010 }, { - "epoch": 0.69, - "learning_rate": 1.5481592753688177e-05, - "loss": 0.1604, + "epoch": 0.35, + "learning_rate": 3.277980358381245e-05, + "loss": 0.1596, "step": 155020 }, { - "epoch": 0.69, - "learning_rate": 1.5479350701762256e-05, - "loss": 0.1623, + "epoch": 0.35, + "learning_rate": 3.277868504060312e-05, + "loss": 0.1609, "step": 155030 }, { - "epoch": 0.69, - "learning_rate": 1.547710864983633e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.2777566497393796e-05, + "loss": 0.1609, "step": 155040 }, { - "epoch": 0.69, - "learning_rate": 1.547486659791041e-05, - "loss": 0.1617, + "epoch": 0.35, + "learning_rate": 3.277644795418447e-05, + "loss": 0.1548, "step": 155050 }, { - "epoch": 0.69, - "learning_rate": 1.5472624545984486e-05, - "loss": 0.165, + "epoch": 0.35, + "learning_rate": 3.2775329410975145e-05, + "loss": 0.1587, "step": 155060 }, { - "epoch": 0.69, - "learning_rate": 1.5470382494058564e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.277421086776582e-05, + "loss": 0.1563, "step": 155070 }, { - "epoch": 0.69, - "learning_rate": 1.546814044213264e-05, - "loss": 0.1625, + "epoch": 0.35, + "learning_rate": 3.27730923245565e-05, + "loss": 0.1602, "step": 155080 }, { - "epoch": 0.69, - "learning_rate": 1.5465898390206718e-05, - "loss": 0.1687, + "epoch": 0.35, + "learning_rate": 3.277197378134718e-05, + "loss": 0.155, "step": 155090 }, { - "epoch": 0.69, - "learning_rate": 1.5463656338280797e-05, - "loss": 0.1672, + "epoch": 0.35, + "learning_rate": 3.277085523813785e-05, + "loss": 0.1634, "step": 155100 }, { - "epoch": 0.69, - "learning_rate": 1.5461414286354872e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.276973669492853e-05, + "loss": 0.1584, "step": 155110 }, { - "epoch": 0.69, - "learning_rate": 1.545917223442895e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.2768618151719206e-05, + "loss": 0.1598, "step": 155120 }, { - "epoch": 0.69, - "learning_rate": 1.5456930182503026e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.276749960850988e-05, + "loss": 0.1617, "step": 155130 }, { - "epoch": 0.69, - "learning_rate": 1.5454688130577105e-05, - "loss": 0.1723, + "epoch": 0.35, + "learning_rate": 3.2766381065300555e-05, + "loss": 0.1599, "step": 155140 }, { - "epoch": 0.69, - "learning_rate": 1.545244607865118e-05, - "loss": 0.1646, + "epoch": 0.35, + "learning_rate": 3.2765262522091226e-05, + "loss": 0.1595, "step": 155150 }, { - "epoch": 0.69, - "learning_rate": 1.545020402672526e-05, - "loss": 0.1564, + "epoch": 0.35, + "learning_rate": 3.2764143978881904e-05, + "loss": 0.1602, "step": 155160 }, { - "epoch": 0.69, - "learning_rate": 1.5447961974799338e-05, - "loss": 0.1621, + "epoch": 0.35, + "learning_rate": 3.276302543567258e-05, + "loss": 0.1566, "step": 155170 }, { - "epoch": 0.69, - "learning_rate": 1.5445719922873413e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.276190689246326e-05, + "loss": 0.1541, "step": 155180 }, { - "epoch": 0.69, - "learning_rate": 1.5443477870947492e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.276078834925394e-05, + "loss": 0.1513, "step": 155190 }, { - "epoch": 0.69, - "learning_rate": 1.5441235819021567e-05, - "loss": 0.1606, + "epoch": 0.35, + "learning_rate": 3.275966980604461e-05, + "loss": 0.1508, "step": 155200 }, { - "epoch": 0.69, - "learning_rate": 1.5438993767095646e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.275855126283529e-05, + "loss": 0.1574, "step": 155210 }, { - "epoch": 0.69, - "learning_rate": 1.543675171516972e-05, - "loss": 0.1638, + "epoch": 0.35, + "learning_rate": 3.2757432719625965e-05, + "loss": 0.1581, "step": 155220 }, { - "epoch": 0.69, - "learning_rate": 1.54345096632438e-05, - "loss": 0.1695, + "epoch": 0.35, + "learning_rate": 3.2756314176416636e-05, + "loss": 0.1595, "step": 155230 }, { - "epoch": 0.69, - "learning_rate": 1.543226761131788e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.2755195633207314e-05, + "loss": 0.1652, "step": 155240 }, { - "epoch": 0.69, - "learning_rate": 1.5430025559391954e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.2754077089997985e-05, + "loss": 0.1624, "step": 155250 }, { - "epoch": 0.69, - "learning_rate": 1.5427783507466033e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.275295854678866e-05, + "loss": 0.1588, "step": 155260 }, { - "epoch": 0.69, - "learning_rate": 1.542554145554011e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.2751840003579334e-05, + "loss": 0.1607, "step": 155270 }, { - "epoch": 0.69, - "learning_rate": 1.542329940361419e-05, - "loss": 0.1602, + "epoch": 0.35, + "learning_rate": 3.275072146037001e-05, + "loss": 0.1553, "step": 155280 }, { - "epoch": 0.69, - "learning_rate": 1.5421057351688266e-05, - "loss": 0.1621, + "epoch": 0.35, + "learning_rate": 3.27496029171607e-05, + "loss": 0.1551, "step": 155290 }, { - "epoch": 0.69, - "learning_rate": 1.5418815299762344e-05, - "loss": 0.1669, + "epoch": 0.35, + "learning_rate": 3.274848437395137e-05, + "loss": 0.153, "step": 155300 }, { - "epoch": 0.69, - "learning_rate": 1.5416573247836423e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.2747365830742046e-05, + "loss": 0.1575, "step": 155310 }, { - "epoch": 0.69, - "learning_rate": 1.5414331195910498e-05, - "loss": 0.1676, + "epoch": 0.35, + "learning_rate": 3.274624728753272e-05, + "loss": 0.1588, "step": 155320 }, { - "epoch": 0.69, - "learning_rate": 1.5412089143984577e-05, - "loss": 0.1658, + "epoch": 0.35, + "learning_rate": 3.2745128744323395e-05, + "loss": 0.1627, "step": 155330 }, { - "epoch": 0.69, - "learning_rate": 1.5409847092058652e-05, - "loss": 0.1699, + "epoch": 0.35, + "learning_rate": 3.274401020111407e-05, + "loss": 0.1616, "step": 155340 }, { - "epoch": 0.69, - "learning_rate": 1.540760504013273e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.2742891657904744e-05, + "loss": 0.164, "step": 155350 }, { - "epoch": 0.69, - "learning_rate": 1.5405362988206806e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.274177311469542e-05, + "loss": 0.1578, "step": 155360 }, { - "epoch": 0.69, - "learning_rate": 1.5403120936280885e-05, - "loss": 0.1659, + "epoch": 0.35, + "learning_rate": 3.274065457148609e-05, + "loss": 0.1616, "step": 155370 }, { - "epoch": 0.69, - "learning_rate": 1.5400878884354964e-05, - "loss": 0.1678, + "epoch": 0.35, + "learning_rate": 3.273953602827677e-05, + "loss": 0.1553, "step": 155380 }, { - "epoch": 0.69, - "learning_rate": 1.539863683242904e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.273841748506745e-05, + "loss": 0.1588, "step": 155390 }, { - "epoch": 0.69, - "learning_rate": 1.5396394780503118e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.273729894185813e-05, + "loss": 0.1576, "step": 155400 }, { - "epoch": 0.69, - "learning_rate": 1.5394152728577193e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.2736180398648805e-05, + "loss": 0.1573, "step": 155410 }, { - "epoch": 0.69, - "learning_rate": 1.5391910676651272e-05, - "loss": 0.1614, + "epoch": 0.35, + "learning_rate": 3.2735061855439476e-05, + "loss": 0.1594, "step": 155420 }, { - "epoch": 0.69, - "learning_rate": 1.538966862472535e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.2733943312230154e-05, + "loss": 0.1514, "step": 155430 }, { - "epoch": 0.69, - "learning_rate": 1.5387426572799426e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.273282476902083e-05, + "loss": 0.1587, "step": 155440 }, { - "epoch": 0.69, - "learning_rate": 1.5385184520873505e-05, - "loss": 0.1663, + "epoch": 0.35, + "learning_rate": 3.27317062258115e-05, + "loss": 0.1606, "step": 155450 }, { - "epoch": 0.69, - "learning_rate": 1.538294246894758e-05, - "loss": 0.1642, + "epoch": 0.35, + "learning_rate": 3.273058768260218e-05, + "loss": 0.1529, "step": 155460 }, { - "epoch": 0.69, - "learning_rate": 1.538070041702166e-05, - "loss": 0.1655, + "epoch": 0.35, + "learning_rate": 3.272946913939285e-05, + "loss": 0.1606, "step": 155470 }, { - "epoch": 0.69, - "learning_rate": 1.5378458365095734e-05, - "loss": 0.1625, + "epoch": 0.35, + "learning_rate": 3.272835059618353e-05, + "loss": 0.1596, "step": 155480 }, { - "epoch": 0.69, - "learning_rate": 1.5376216313169813e-05, - "loss": 0.1671, + "epoch": 0.35, + "learning_rate": 3.272723205297421e-05, + "loss": 0.1557, "step": 155490 }, { - "epoch": 0.69, - "learning_rate": 1.537397426124389e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.2726113509764886e-05, + "loss": 0.1616, "step": 155500 }, { - "epoch": 0.69, - "learning_rate": 1.5371732209317967e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.2724994966555564e-05, + "loss": 0.1628, "step": 155510 }, { - "epoch": 0.69, - "learning_rate": 1.5369490157392046e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.2723876423346235e-05, + "loss": 0.157, "step": 155520 }, { - "epoch": 0.69, - "learning_rate": 1.5367248105466124e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.272275788013691e-05, + "loss": 0.1564, "step": 155530 }, { - "epoch": 0.69, - "learning_rate": 1.53650060535402e-05, - "loss": 0.1689, + "epoch": 0.35, + "learning_rate": 3.272163933692759e-05, + "loss": 0.1556, "step": 155540 }, { - "epoch": 0.69, - "learning_rate": 1.536276400161428e-05, - "loss": 0.1686, + "epoch": 0.35, + "learning_rate": 3.272052079371826e-05, + "loss": 0.165, "step": 155550 }, { - "epoch": 0.69, - "learning_rate": 1.5360521949688357e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.271940225050894e-05, + "loss": 0.1596, "step": 155560 }, { - "epoch": 0.69, - "learning_rate": 1.5358279897762436e-05, - "loss": 0.1556, + "epoch": 0.35, + "learning_rate": 3.271828370729961e-05, + "loss": 0.1546, "step": 155570 }, { - "epoch": 0.69, - "learning_rate": 1.535603784583651e-05, - "loss": 0.1646, + "epoch": 0.35, + "learning_rate": 3.271716516409029e-05, + "loss": 0.1595, "step": 155580 }, { - "epoch": 0.69, - "learning_rate": 1.535379579391059e-05, - "loss": 0.168, + "epoch": 0.35, + "learning_rate": 3.271604662088097e-05, + "loss": 0.1636, "step": 155590 }, { - "epoch": 0.69, - "learning_rate": 1.5351553741984665e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.2714928077671645e-05, + "loss": 0.1558, "step": 155600 }, { - "epoch": 0.69, - "learning_rate": 1.5349311690058744e-05, - "loss": 0.1586, + "epoch": 0.35, + "learning_rate": 3.271380953446232e-05, + "loss": 0.1597, "step": 155610 }, { - "epoch": 0.69, - "learning_rate": 1.534706963813282e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.2712690991252994e-05, + "loss": 0.154, "step": 155620 }, { - "epoch": 0.69, - "learning_rate": 1.5344827586206898e-05, - "loss": 0.1584, + "epoch": 0.35, + "learning_rate": 3.271157244804367e-05, + "loss": 0.1577, "step": 155630 }, { - "epoch": 0.69, - "learning_rate": 1.5342585534280977e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.271045390483434e-05, + "loss": 0.1572, "step": 155640 }, { - "epoch": 0.69, - "learning_rate": 1.5340343482355052e-05, - "loss": 0.1681, + "epoch": 0.35, + "learning_rate": 3.270933536162502e-05, + "loss": 0.1556, "step": 155650 }, { - "epoch": 0.69, - "learning_rate": 1.533810143042913e-05, - "loss": 0.1651, + "epoch": 0.35, + "learning_rate": 3.27082168184157e-05, + "loss": 0.1578, "step": 155660 }, { - "epoch": 0.69, - "learning_rate": 1.5335859378503206e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.270709827520637e-05, + "loss": 0.1612, "step": 155670 }, { - "epoch": 0.69, - "learning_rate": 1.5333617326577285e-05, - "loss": 0.1605, + "epoch": 0.35, + "learning_rate": 3.270597973199705e-05, + "loss": 0.1625, "step": 155680 }, { - "epoch": 0.7, - "learning_rate": 1.533137527465136e-05, - "loss": 0.1621, + "epoch": 0.35, + "learning_rate": 3.270486118878772e-05, + "loss": 0.1591, "step": 155690 }, { - "epoch": 0.7, - "learning_rate": 1.532913322272544e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.27037426455784e-05, + "loss": 0.1562, "step": 155700 }, { - "epoch": 0.7, - "learning_rate": 1.5326891170799517e-05, - "loss": 0.1617, + "epoch": 0.35, + "learning_rate": 3.270262410236908e-05, + "loss": 0.1594, "step": 155710 }, { - "epoch": 0.7, - "learning_rate": 1.5324649118873593e-05, - "loss": 0.161, + "epoch": 0.35, + "learning_rate": 3.270150555915975e-05, + "loss": 0.1584, "step": 155720 }, { - "epoch": 0.7, - "learning_rate": 1.532240706694767e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.270038701595043e-05, + "loss": 0.1547, "step": 155730 }, { - "epoch": 0.7, - "learning_rate": 1.5320165015021747e-05, - "loss": 0.1669, + "epoch": 0.35, + "learning_rate": 3.26992684727411e-05, + "loss": 0.162, "step": 155740 }, { - "epoch": 0.7, - "learning_rate": 1.5317922963095826e-05, - "loss": 0.1639, + "epoch": 0.35, + "learning_rate": 3.269814992953178e-05, + "loss": 0.1563, "step": 155750 }, { - "epoch": 0.7, - "learning_rate": 1.53156809111699e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.269703138632246e-05, + "loss": 0.158, "step": 155760 }, { - "epoch": 0.7, - "learning_rate": 1.531343885924398e-05, - "loss": 0.1698, + "epoch": 0.35, + "learning_rate": 3.269591284311313e-05, + "loss": 0.1569, "step": 155770 }, { - "epoch": 0.7, - "learning_rate": 1.531119680731806e-05, - "loss": 0.1607, + "epoch": 0.35, + "learning_rate": 3.269479429990381e-05, + "loss": 0.1629, "step": 155780 }, { - "epoch": 0.7, - "learning_rate": 1.5308954755392134e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.269367575669448e-05, + "loss": 0.1649, "step": 155790 }, { - "epoch": 0.7, - "learning_rate": 1.5306712703466212e-05, - "loss": 0.1613, + "epoch": 0.35, + "learning_rate": 3.2692557213485156e-05, + "loss": 0.1563, "step": 155800 }, { - "epoch": 0.7, - "learning_rate": 1.530447065154029e-05, - "loss": 0.1587, + "epoch": 0.35, + "learning_rate": 3.2691438670275834e-05, + "loss": 0.1609, "step": 155810 }, { - "epoch": 0.7, - "learning_rate": 1.530222859961437e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.269032012706651e-05, + "loss": 0.161, "step": 155820 }, { - "epoch": 0.7, - "learning_rate": 1.5299986547688445e-05, - "loss": 0.1701, + "epoch": 0.35, + "learning_rate": 3.268920158385719e-05, + "loss": 0.1566, "step": 155830 }, { - "epoch": 0.7, - "learning_rate": 1.5297744495762524e-05, - "loss": 0.1619, + "epoch": 0.35, + "learning_rate": 3.268808304064786e-05, + "loss": 0.158, "step": 155840 }, { - "epoch": 0.7, - "learning_rate": 1.5295502443836603e-05, - "loss": 0.1679, + "epoch": 0.35, + "learning_rate": 3.268696449743854e-05, + "loss": 0.1591, "step": 155850 }, { - "epoch": 0.7, - "learning_rate": 1.5293260391910678e-05, - "loss": 0.1614, + "epoch": 0.35, + "learning_rate": 3.2685845954229217e-05, + "loss": 0.1637, "step": 155860 }, { - "epoch": 0.7, - "learning_rate": 1.5291018339984757e-05, - "loss": 0.1617, + "epoch": 0.35, + "learning_rate": 3.268472741101989e-05, + "loss": 0.1577, "step": 155870 }, { - "epoch": 0.7, - "learning_rate": 1.5288776288058832e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.2683608867810566e-05, + "loss": 0.1559, "step": 155880 }, { - "epoch": 0.7, - "learning_rate": 1.528653423613291e-05, - "loss": 0.1662, + "epoch": 0.35, + "learning_rate": 3.268249032460124e-05, + "loss": 0.1582, "step": 155890 }, { - "epoch": 0.7, - "learning_rate": 1.5284292184206986e-05, - "loss": 0.1692, + "epoch": 0.35, + "learning_rate": 3.2681371781391915e-05, + "loss": 0.1605, "step": 155900 }, { - "epoch": 0.7, - "learning_rate": 1.5282050132281065e-05, - "loss": 0.1643, + "epoch": 0.35, + "learning_rate": 3.268025323818259e-05, + "loss": 0.1553, "step": 155910 }, { - "epoch": 0.7, - "learning_rate": 1.5279808080355143e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.267913469497327e-05, + "loss": 0.1619, "step": 155920 }, { - "epoch": 0.7, - "learning_rate": 1.527756602842922e-05, - "loss": 0.1706, + "epoch": 0.35, + "learning_rate": 3.267801615176395e-05, + "loss": 0.161, "step": 155930 }, { - "epoch": 0.7, - "learning_rate": 1.5275323976503297e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.267689760855462e-05, + "loss": 0.1578, "step": 155940 }, { - "epoch": 0.7, - "learning_rate": 1.5273081924577373e-05, - "loss": 0.1648, + "epoch": 0.35, + "learning_rate": 3.26757790653453e-05, + "loss": 0.163, "step": 155950 }, { - "epoch": 0.7, - "learning_rate": 1.527083987265145e-05, - "loss": 0.1667, + "epoch": 0.35, + "learning_rate": 3.267466052213597e-05, + "loss": 0.1629, "step": 155960 }, { - "epoch": 0.7, - "learning_rate": 1.5268597820725527e-05, - "loss": 0.1663, + "epoch": 0.35, + "learning_rate": 3.267354197892665e-05, + "loss": 0.1589, "step": 155970 }, { - "epoch": 0.7, - "learning_rate": 1.5266355768799606e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.2672423435717325e-05, + "loss": 0.1574, "step": 155980 }, { - "epoch": 0.7, - "learning_rate": 1.5264113716873684e-05, - "loss": 0.1621, + "epoch": 0.35, + "learning_rate": 3.2671304892507996e-05, + "loss": 0.1601, "step": 155990 }, { - "epoch": 0.7, - "learning_rate": 1.526187166494776e-05, - "loss": 0.1644, + "epoch": 0.35, + "learning_rate": 3.2670186349298674e-05, + "loss": 0.1576, "step": 156000 }, { - "epoch": 0.7, - "learning_rate": 1.525962961302184e-05, - "loss": 0.1692, + "epoch": 0.35, + "learning_rate": 3.266906780608935e-05, + "loss": 0.1651, "step": 156010 }, { - "epoch": 0.7, - "learning_rate": 1.5257387561095915e-05, - "loss": 0.1682, + "epoch": 0.35, + "learning_rate": 3.266794926288003e-05, + "loss": 0.159, "step": 156020 }, { - "epoch": 0.7, - "learning_rate": 1.5255145509169994e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.266683071967071e-05, + "loss": 0.1524, "step": 156030 }, { - "epoch": 0.7, - "learning_rate": 1.525290345724407e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.266571217646138e-05, + "loss": 0.1652, "step": 156040 }, { - "epoch": 0.7, - "learning_rate": 1.5250661405318148e-05, - "loss": 0.1646, + "epoch": 0.35, + "learning_rate": 3.2664593633252057e-05, + "loss": 0.1594, "step": 156050 }, { - "epoch": 0.7, - "learning_rate": 1.5248419353392227e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.266347509004273e-05, + "loss": 0.1601, "step": 156060 }, { - "epoch": 0.7, - "learning_rate": 1.5246177301466302e-05, - "loss": 0.1618, + "epoch": 0.35, + "learning_rate": 3.2662356546833406e-05, + "loss": 0.1576, "step": 156070 }, { - "epoch": 0.7, - "learning_rate": 1.5243935249540381e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.2661238003624084e-05, + "loss": 0.1547, "step": 156080 }, { - "epoch": 0.7, - "learning_rate": 1.5241693197614456e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.2660119460414755e-05, + "loss": 0.158, "step": 156090 }, { - "epoch": 0.7, - "learning_rate": 1.5239451145688535e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.265900091720543e-05, + "loss": 0.1594, "step": 156100 }, { - "epoch": 0.7, - "learning_rate": 1.523720909376261e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.2657882373996104e-05, + "loss": 0.1578, "step": 156110 }, { - "epoch": 0.7, - "learning_rate": 1.5234967041836689e-05, - "loss": 0.1633, + "epoch": 0.35, + "learning_rate": 3.265676383078679e-05, + "loss": 0.1604, "step": 156120 }, { - "epoch": 0.7, - "learning_rate": 1.5232724989910768e-05, - "loss": 0.1705, + "epoch": 0.35, + "learning_rate": 3.2655645287577466e-05, + "loss": 0.1548, "step": 156130 }, { - "epoch": 0.7, - "learning_rate": 1.5230482937984845e-05, - "loss": 0.1633, + "epoch": 0.35, + "learning_rate": 3.265452674436814e-05, + "loss": 0.1618, "step": 156140 }, { - "epoch": 0.7, - "learning_rate": 1.5228240886058923e-05, - "loss": 0.1684, + "epoch": 0.35, + "learning_rate": 3.2653408201158815e-05, + "loss": 0.1599, "step": 156150 }, { - "epoch": 0.7, - "learning_rate": 1.5225998834132999e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.265228965794949e-05, + "loss": 0.1602, "step": 156160 }, { - "epoch": 0.7, - "learning_rate": 1.5223756782207078e-05, - "loss": 0.1599, + "epoch": 0.35, + "learning_rate": 3.2651171114740165e-05, + "loss": 0.1641, "step": 156170 }, { - "epoch": 0.7, - "learning_rate": 1.5221514730281153e-05, - "loss": 0.1639, + "epoch": 0.35, + "learning_rate": 3.265005257153084e-05, + "loss": 0.1533, "step": 156180 }, { - "epoch": 0.7, - "learning_rate": 1.5219272678355232e-05, - "loss": 0.1616, + "epoch": 0.35, + "learning_rate": 3.2648934028321514e-05, + "loss": 0.16, "step": 156190 }, { - "epoch": 0.7, - "learning_rate": 1.521703062642931e-05, - "loss": 0.1614, + "epoch": 0.35, + "learning_rate": 3.264781548511219e-05, + "loss": 0.1622, "step": 156200 }, { - "epoch": 0.7, - "learning_rate": 1.5214788574503386e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.264669694190286e-05, + "loss": 0.1585, "step": 156210 }, { - "epoch": 0.7, - "learning_rate": 1.5212546522577464e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.264557839869354e-05, + "loss": 0.1601, "step": 156220 }, { - "epoch": 0.7, - "learning_rate": 1.521030447065154e-05, - "loss": 0.1623, + "epoch": 0.35, + "learning_rate": 3.264445985548422e-05, + "loss": 0.1597, "step": 156230 }, { - "epoch": 0.7, - "learning_rate": 1.5208062418725618e-05, - "loss": 0.1587, + "epoch": 0.35, + "learning_rate": 3.2643341312274897e-05, + "loss": 0.1561, "step": 156240 }, { - "epoch": 0.7, - "learning_rate": 1.5205820366799695e-05, - "loss": 0.16, + "epoch": 0.35, + "learning_rate": 3.2642222769065574e-05, + "loss": 0.1601, "step": 156250 }, { - "epoch": 0.7, - "learning_rate": 1.5203578314873772e-05, - "loss": 0.1684, + "epoch": 0.35, + "learning_rate": 3.2641104225856246e-05, + "loss": 0.16, "step": 156260 }, { - "epoch": 0.7, - "learning_rate": 1.5201336262947851e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.2639985682646924e-05, + "loss": 0.158, "step": 156270 }, { - "epoch": 0.7, - "learning_rate": 1.5199094211021928e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.2638867139437595e-05, + "loss": 0.1636, "step": 156280 }, { - "epoch": 0.7, - "learning_rate": 1.5196852159096007e-05, - "loss": 0.1659, + "epoch": 0.35, + "learning_rate": 3.263774859622827e-05, + "loss": 0.1517, "step": 156290 }, { - "epoch": 0.7, - "learning_rate": 1.5194610107170082e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.263663005301895e-05, + "loss": 0.1551, "step": 156300 }, { - "epoch": 0.7, - "learning_rate": 1.5192368055244161e-05, - "loss": 0.1721, + "epoch": 0.35, + "learning_rate": 3.263551150980962e-05, + "loss": 0.1568, "step": 156310 }, { - "epoch": 0.7, - "learning_rate": 1.5190126003318236e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.26343929666003e-05, + "loss": 0.1607, "step": 156320 }, { - "epoch": 0.7, - "learning_rate": 1.5187883951392315e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.263327442339098e-05, + "loss": 0.1598, "step": 156330 }, { - "epoch": 0.7, - "learning_rate": 1.5185641899466394e-05, - "loss": 0.1676, + "epoch": 0.35, + "learning_rate": 3.2632155880181655e-05, + "loss": 0.157, "step": 156340 }, { - "epoch": 0.7, - "learning_rate": 1.5183399847540469e-05, - "loss": 0.159, + "epoch": 0.35, + "learning_rate": 3.2631037336972333e-05, + "loss": 0.1563, "step": 156350 }, { - "epoch": 0.7, - "learning_rate": 1.5181157795614548e-05, - "loss": 0.1583, + "epoch": 0.35, + "learning_rate": 3.2629918793763005e-05, + "loss": 0.1617, "step": 156360 }, { - "epoch": 0.7, - "learning_rate": 1.5178915743688623e-05, - "loss": 0.1675, + "epoch": 0.35, + "learning_rate": 3.262880025055368e-05, + "loss": 0.1558, "step": 156370 }, { - "epoch": 0.7, - "learning_rate": 1.5176673691762702e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.2627681707344354e-05, + "loss": 0.1623, "step": 156380 }, { - "epoch": 0.7, - "learning_rate": 1.5174431639836779e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.262656316413503e-05, + "loss": 0.1569, "step": 156390 }, { - "epoch": 0.7, - "learning_rate": 1.5172189587910856e-05, - "loss": 0.1652, + "epoch": 0.35, + "learning_rate": 3.262544462092571e-05, + "loss": 0.1655, "step": 156400 }, { - "epoch": 0.7, - "learning_rate": 1.5169947535984935e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.262432607771638e-05, + "loss": 0.1598, "step": 156410 }, { - "epoch": 0.7, - "learning_rate": 1.5167705484059012e-05, - "loss": 0.1603, + "epoch": 0.35, + "learning_rate": 3.262320753450706e-05, + "loss": 0.1571, "step": 156420 }, { - "epoch": 0.7, - "learning_rate": 1.516546343213309e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.2622088991297736e-05, + "loss": 0.1583, "step": 156430 }, { - "epoch": 0.7, - "learning_rate": 1.5163221380207166e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.2620970448088414e-05, + "loss": 0.1618, "step": 156440 }, { - "epoch": 0.7, - "learning_rate": 1.5160979328281244e-05, - "loss": 0.1706, + "epoch": 0.35, + "learning_rate": 3.261985190487909e-05, + "loss": 0.1542, "step": 156450 }, { - "epoch": 0.7, - "learning_rate": 1.515873727635532e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.2618733361669763e-05, + "loss": 0.1597, "step": 156460 }, { - "epoch": 0.7, - "learning_rate": 1.5156495224429398e-05, - "loss": 0.1676, + "epoch": 0.35, + "learning_rate": 3.261761481846044e-05, + "loss": 0.1598, "step": 156470 }, { - "epoch": 0.7, - "learning_rate": 1.5154253172503477e-05, - "loss": 0.1644, + "epoch": 0.35, + "learning_rate": 3.261649627525111e-05, + "loss": 0.154, "step": 156480 }, { - "epoch": 0.7, - "learning_rate": 1.5152011120577552e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.261537773204179e-05, + "loss": 0.1591, "step": 156490 }, { - "epoch": 0.7, - "learning_rate": 1.5149769068651631e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.261425918883247e-05, + "loss": 0.1604, "step": 156500 }, { - "epoch": 0.7, - "learning_rate": 1.5147527016725706e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.261325249994408e-05, + "loss": 0.1565, "step": 156510 }, { - "epoch": 0.7, - "learning_rate": 1.5145284964799785e-05, - "loss": 0.1614, + "epoch": 0.35, + "learning_rate": 3.2612133956734755e-05, + "loss": 0.1555, "step": 156520 }, { - "epoch": 0.7, - "learning_rate": 1.5143042912873862e-05, - "loss": 0.1622, + "epoch": 0.35, + "learning_rate": 3.2611015413525426e-05, + "loss": 0.1608, "step": 156530 }, { - "epoch": 0.7, - "learning_rate": 1.5140800860947941e-05, - "loss": 0.1694, + "epoch": 0.35, + "learning_rate": 3.2609896870316104e-05, + "loss": 0.1543, "step": 156540 }, { - "epoch": 0.7, - "learning_rate": 1.5138558809022018e-05, - "loss": 0.1568, + "epoch": 0.35, + "learning_rate": 3.2608778327106775e-05, + "loss": 0.1559, "step": 156550 }, { - "epoch": 0.7, - "learning_rate": 1.5136316757096095e-05, - "loss": 0.1618, + "epoch": 0.35, + "learning_rate": 3.260765978389745e-05, + "loss": 0.1609, "step": 156560 }, { - "epoch": 0.7, - "learning_rate": 1.5134074705170174e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.260654124068813e-05, + "loss": 0.1597, "step": 156570 }, { - "epoch": 0.7, - "learning_rate": 1.5131832653244249e-05, - "loss": 0.1631, + "epoch": 0.35, + "learning_rate": 3.26054226974788e-05, + "loss": 0.1531, "step": 156580 }, { - "epoch": 0.7, - "learning_rate": 1.5129590601318328e-05, - "loss": 0.1594, + "epoch": 0.35, + "learning_rate": 3.260430415426948e-05, + "loss": 0.1561, "step": 156590 }, { - "epoch": 0.7, - "learning_rate": 1.5127348549392403e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.260318561106016e-05, + "loss": 0.1568, "step": 156600 }, { - "epoch": 0.7, - "learning_rate": 1.5125106497466482e-05, - "loss": 0.1604, + "epoch": 0.35, + "learning_rate": 3.2602067067850836e-05, + "loss": 0.1593, "step": 156610 }, { - "epoch": 0.7, - "learning_rate": 1.512286444554056e-05, - "loss": 0.1652, + "epoch": 0.35, + "learning_rate": 3.260094852464151e-05, + "loss": 0.1599, "step": 156620 }, { - "epoch": 0.7, - "learning_rate": 1.5120622393614636e-05, - "loss": 0.1623, + "epoch": 0.35, + "learning_rate": 3.2599829981432185e-05, + "loss": 0.1548, "step": 156630 }, { - "epoch": 0.7, - "learning_rate": 1.5118380341688715e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.259871143822286e-05, + "loss": 0.1592, "step": 156640 }, { - "epoch": 0.7, - "learning_rate": 1.511613828976279e-05, - "loss": 0.1673, + "epoch": 0.35, + "learning_rate": 3.2597592895013534e-05, + "loss": 0.1615, "step": 156650 }, { - "epoch": 0.7, - "learning_rate": 1.5113896237836869e-05, - "loss": 0.1724, + "epoch": 0.35, + "learning_rate": 3.259647435180421e-05, + "loss": 0.1606, "step": 156660 }, { - "epoch": 0.7, - "learning_rate": 1.5111654185910946e-05, - "loss": 0.1638, + "epoch": 0.35, + "learning_rate": 3.2595355808594883e-05, + "loss": 0.1618, "step": 156670 }, { - "epoch": 0.7, - "learning_rate": 1.5109412133985024e-05, - "loss": 0.1708, + "epoch": 0.35, + "learning_rate": 3.259423726538556e-05, + "loss": 0.155, "step": 156680 }, { - "epoch": 0.7, - "learning_rate": 1.5107170082059103e-05, - "loss": 0.1675, + "epoch": 0.35, + "learning_rate": 3.259311872217624e-05, + "loss": 0.1539, "step": 156690 }, { - "epoch": 0.7, - "learning_rate": 1.5104928030133178e-05, - "loss": 0.1593, + "epoch": 0.35, + "learning_rate": 3.259200017896692e-05, + "loss": 0.1574, "step": 156700 }, { - "epoch": 0.7, - "learning_rate": 1.5102685978207257e-05, - "loss": 0.1586, + "epoch": 0.35, + "learning_rate": 3.2590881635757595e-05, + "loss": 0.1608, "step": 156710 }, { - "epoch": 0.7, - "learning_rate": 1.5100443926281332e-05, - "loss": 0.1639, + "epoch": 0.35, + "learning_rate": 3.2589763092548266e-05, + "loss": 0.156, "step": 156720 }, { - "epoch": 0.7, - "learning_rate": 1.5098201874355411e-05, - "loss": 0.1628, + "epoch": 0.35, + "learning_rate": 3.2588644549338944e-05, + "loss": 0.158, "step": 156730 }, { - "epoch": 0.7, - "learning_rate": 1.5095959822429486e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.258752600612962e-05, + "loss": 0.1611, "step": 156740 }, { - "epoch": 0.7, - "learning_rate": 1.5093717770503565e-05, - "loss": 0.1649, + "epoch": 0.35, + "learning_rate": 3.258640746292029e-05, + "loss": 0.1606, "step": 156750 }, { - "epoch": 0.7, - "learning_rate": 1.5091475718577644e-05, - "loss": 0.1704, + "epoch": 0.35, + "learning_rate": 3.258528891971097e-05, + "loss": 0.1561, "step": 156760 }, { - "epoch": 0.7, - "learning_rate": 1.508923366665172e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.258417037650164e-05, + "loss": 0.1609, "step": 156770 }, { - "epoch": 0.7, - "learning_rate": 1.5086991614725798e-05, - "loss": 0.1665, + "epoch": 0.35, + "learning_rate": 3.258305183329232e-05, + "loss": 0.1564, "step": 156780 }, { - "epoch": 0.7, - "learning_rate": 1.5084749562799875e-05, - "loss": 0.1579, + "epoch": 0.35, + "learning_rate": 3.2581933290083e-05, + "loss": 0.1591, "step": 156790 }, { - "epoch": 0.7, - "learning_rate": 1.5082507510873952e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.258081474687367e-05, + "loss": 0.1566, "step": 156800 }, { - "epoch": 0.7, - "learning_rate": 1.508026545894803e-05, - "loss": 0.1593, + "epoch": 0.35, + "learning_rate": 3.257969620366435e-05, + "loss": 0.1577, "step": 156810 }, { - "epoch": 0.7, - "learning_rate": 1.5078023407022108e-05, - "loss": 0.1663, + "epoch": 0.35, + "learning_rate": 3.2578577660455025e-05, + "loss": 0.154, "step": 156820 }, { - "epoch": 0.7, - "learning_rate": 1.5075781355096186e-05, - "loss": 0.167, + "epoch": 0.35, + "learning_rate": 3.25774591172457e-05, + "loss": 0.1628, "step": 156830 }, { - "epoch": 0.7, - "learning_rate": 1.5073539303170262e-05, - "loss": 0.1654, + "epoch": 0.35, + "learning_rate": 3.257634057403638e-05, + "loss": 0.161, "step": 156840 }, { - "epoch": 0.7, - "learning_rate": 1.507129725124434e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.257522203082705e-05, + "loss": 0.155, "step": 156850 }, { - "epoch": 0.7, - "learning_rate": 1.5069055199318416e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.257410348761773e-05, + "loss": 0.1575, "step": 156860 }, { - "epoch": 0.7, - "learning_rate": 1.5066813147392495e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.25729849444084e-05, + "loss": 0.1544, "step": 156870 }, { - "epoch": 0.7, - "learning_rate": 1.5064571095466573e-05, - "loss": 0.1597, + "epoch": 0.35, + "learning_rate": 3.257186640119908e-05, + "loss": 0.1577, "step": 156880 }, { - "epoch": 0.7, - "learning_rate": 1.5062329043540649e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.257074785798976e-05, + "loss": 0.1581, "step": 156890 }, { - "epoch": 0.7, - "learning_rate": 1.5060086991614727e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.256962931478043e-05, + "loss": 0.1605, "step": 156900 }, { - "epoch": 0.7, - "learning_rate": 1.5057844939688803e-05, - "loss": 0.1681, + "epoch": 0.35, + "learning_rate": 3.2568510771571106e-05, + "loss": 0.1572, "step": 156910 }, { - "epoch": 0.7, - "learning_rate": 1.5055602887762881e-05, - "loss": 0.1712, + "epoch": 0.35, + "learning_rate": 3.2567392228361784e-05, + "loss": 0.1569, "step": 156920 }, { - "epoch": 0.7, - "learning_rate": 1.505358504102955e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.256627368515246e-05, + "loss": 0.1584, "step": 156930 }, { - "epoch": 0.7, - "learning_rate": 1.5051342989103628e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.256515514194313e-05, + "loss": 0.1597, "step": 156940 }, { - "epoch": 0.7, - "learning_rate": 1.5049100937177707e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.256403659873381e-05, + "loss": 0.1572, "step": 156950 }, { - "epoch": 0.7, - "learning_rate": 1.5046858885251782e-05, - "loss": 0.1657, + "epoch": 0.35, + "learning_rate": 3.256291805552449e-05, + "loss": 0.162, "step": 156960 }, { - "epoch": 0.7, - "learning_rate": 1.504461683332586e-05, - "loss": 0.1584, + "epoch": 0.35, + "learning_rate": 3.256179951231516e-05, + "loss": 0.1586, "step": 156970 }, { - "epoch": 0.7, - "learning_rate": 1.5042374781399938e-05, - "loss": 0.1658, + "epoch": 0.35, + "learning_rate": 3.256068096910584e-05, + "loss": 0.1615, "step": 156980 }, { - "epoch": 0.7, - "learning_rate": 1.5040132729474016e-05, - "loss": 0.1679, + "epoch": 0.35, + "learning_rate": 3.255956242589651e-05, + "loss": 0.1593, "step": 156990 }, { - "epoch": 0.7, - "learning_rate": 1.5037890677548092e-05, - "loss": 0.1628, + "epoch": 0.35, + "learning_rate": 3.255844388268719e-05, + "loss": 0.16, "step": 157000 }, { - "epoch": 0.7, - "learning_rate": 1.503564862562217e-05, - "loss": 0.1618, + "epoch": 0.35, + "learning_rate": 3.2557325339477865e-05, + "loss": 0.157, "step": 157010 }, { - "epoch": 0.7, - "learning_rate": 1.503340657369625e-05, - "loss": 0.1599, + "epoch": 0.35, + "learning_rate": 3.255620679626854e-05, + "loss": 0.1589, "step": 157020 }, { - "epoch": 0.7, - "learning_rate": 1.5031164521770324e-05, - "loss": 0.1648, + "epoch": 0.35, + "learning_rate": 3.255508825305922e-05, + "loss": 0.1568, "step": 157030 }, { - "epoch": 0.7, - "learning_rate": 1.5028922469844403e-05, - "loss": 0.1608, + "epoch": 0.35, + "learning_rate": 3.255396970984989e-05, + "loss": 0.1625, "step": 157040 }, { - "epoch": 0.7, - "learning_rate": 1.5026680417918479e-05, - "loss": 0.1655, + "epoch": 0.35, + "learning_rate": 3.255285116664057e-05, + "loss": 0.1502, "step": 157050 }, { - "epoch": 0.7, - "learning_rate": 1.5024438365992557e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.255173262343125e-05, + "loss": 0.1552, "step": 157060 }, { - "epoch": 0.7, - "learning_rate": 1.5022196314066633e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.255061408022192e-05, + "loss": 0.1551, "step": 157070 }, { - "epoch": 0.7, - "learning_rate": 1.5019954262140711e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.25494955370126e-05, + "loss": 0.1599, "step": 157080 }, { - "epoch": 0.7, - "learning_rate": 1.501771221021479e-05, - "loss": 0.1586, + "epoch": 0.35, + "learning_rate": 3.254837699380327e-05, + "loss": 0.1565, "step": 157090 }, { - "epoch": 0.7, - "learning_rate": 1.5015470158288867e-05, - "loss": 0.1646, + "epoch": 0.35, + "learning_rate": 3.2547258450593946e-05, + "loss": 0.1581, "step": 157100 }, { - "epoch": 0.7, - "learning_rate": 1.5013228106362944e-05, - "loss": 0.1623, + "epoch": 0.35, + "learning_rate": 3.2546139907384624e-05, + "loss": 0.16, "step": 157110 }, { - "epoch": 0.7, - "learning_rate": 1.5010986054437021e-05, - "loss": 0.1632, + "epoch": 0.35, + "learning_rate": 3.25450213641753e-05, + "loss": 0.1559, "step": 157120 }, { - "epoch": 0.7, - "learning_rate": 1.50087440025111e-05, - "loss": 0.1648, + "epoch": 0.35, + "learning_rate": 3.254390282096598e-05, + "loss": 0.1597, "step": 157130 }, { - "epoch": 0.7, - "learning_rate": 1.5006501950585175e-05, - "loss": 0.1639, + "epoch": 0.35, + "learning_rate": 3.254278427775665e-05, + "loss": 0.1581, "step": 157140 }, { - "epoch": 0.7, - "learning_rate": 1.5004259898659254e-05, - "loss": 0.1612, + "epoch": 0.35, + "learning_rate": 3.254166573454733e-05, + "loss": 0.1626, "step": 157150 }, { - "epoch": 0.7, - "learning_rate": 1.5002017846733333e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.254054719133801e-05, + "loss": 0.1645, "step": 157160 }, { - "epoch": 0.7, - "learning_rate": 1.4999775794807408e-05, - "loss": 0.1632, + "epoch": 0.35, + "learning_rate": 3.253942864812868e-05, + "loss": 0.1619, "step": 157170 }, { - "epoch": 0.7, - "learning_rate": 1.4997533742881487e-05, - "loss": 0.1588, + "epoch": 0.35, + "learning_rate": 3.2538310104919356e-05, + "loss": 0.1598, "step": 157180 }, { - "epoch": 0.7, - "learning_rate": 1.4995291690955562e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.253719156171003e-05, + "loss": 0.1533, "step": 157190 }, { - "epoch": 0.7, - "learning_rate": 1.499304963902964e-05, - "loss": 0.1593, + "epoch": 0.35, + "learning_rate": 3.2536073018500705e-05, + "loss": 0.1541, "step": 157200 }, { - "epoch": 0.7, - "learning_rate": 1.4990807587103716e-05, - "loss": 0.1655, + "epoch": 0.35, + "learning_rate": 3.2534954475291376e-05, + "loss": 0.1568, "step": 157210 }, { - "epoch": 0.7, - "learning_rate": 1.4988565535177795e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.2533835932082054e-05, + "loss": 0.1624, "step": 157220 }, { - "epoch": 0.7, - "learning_rate": 1.4986323483251873e-05, - "loss": 0.1659, + "epoch": 0.35, + "learning_rate": 3.253271738887273e-05, + "loss": 0.1644, "step": 157230 }, { - "epoch": 0.7, - "learning_rate": 1.498408143132595e-05, - "loss": 0.1546, + "epoch": 0.35, + "learning_rate": 3.253159884566341e-05, + "loss": 0.1555, "step": 157240 }, { - "epoch": 0.7, - "learning_rate": 1.498183937940003e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.253048030245409e-05, + "loss": 0.1588, "step": 157250 }, { - "epoch": 0.7, - "learning_rate": 1.4979597327474105e-05, - "loss": 0.1588, + "epoch": 0.35, + "learning_rate": 3.252936175924476e-05, + "loss": 0.1525, "step": 157260 }, { - "epoch": 0.7, - "learning_rate": 1.4977355275548183e-05, - "loss": 0.1686, + "epoch": 0.35, + "learning_rate": 3.252824321603544e-05, + "loss": 0.1569, "step": 157270 }, { - "epoch": 0.7, - "learning_rate": 1.4975113223622259e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.2527124672826115e-05, + "loss": 0.1594, "step": 157280 }, { - "epoch": 0.7, - "learning_rate": 1.4972871171696337e-05, - "loss": 0.1648, + "epoch": 0.35, + "learning_rate": 3.2526006129616786e-05, + "loss": 0.1621, "step": 157290 }, { - "epoch": 0.7, - "learning_rate": 1.4970629119770416e-05, - "loss": 0.1599, + "epoch": 0.35, + "learning_rate": 3.2524887586407464e-05, + "loss": 0.1572, "step": 157300 }, { - "epoch": 0.7, - "learning_rate": 1.4968387067844491e-05, - "loss": 0.1597, + "epoch": 0.35, + "learning_rate": 3.2523769043198135e-05, + "loss": 0.1586, "step": 157310 }, { - "epoch": 0.7, - "learning_rate": 1.496614501591857e-05, - "loss": 0.168, + "epoch": 0.35, + "learning_rate": 3.252265049998881e-05, + "loss": 0.1532, "step": 157320 }, { - "epoch": 0.7, - "learning_rate": 1.4963902963992645e-05, - "loss": 0.1594, + "epoch": 0.35, + "learning_rate": 3.252153195677949e-05, + "loss": 0.1566, "step": 157330 }, { - "epoch": 0.7, - "learning_rate": 1.4961660912066724e-05, - "loss": 0.159, + "epoch": 0.35, + "learning_rate": 3.252041341357017e-05, + "loss": 0.1534, "step": 157340 }, { - "epoch": 0.7, - "learning_rate": 1.4959418860140801e-05, - "loss": 0.1596, + "epoch": 0.35, + "learning_rate": 3.251929487036085e-05, + "loss": 0.1608, "step": 157350 }, { - "epoch": 0.7, - "learning_rate": 1.4957176808214878e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.251817632715152e-05, + "loss": 0.155, "step": 157360 }, { - "epoch": 0.7, - "learning_rate": 1.4954934756288957e-05, - "loss": 0.1638, + "epoch": 0.35, + "learning_rate": 3.2517057783942196e-05, + "loss": 0.1575, "step": 157370 }, { - "epoch": 0.7, - "learning_rate": 1.4952692704363034e-05, - "loss": 0.1617, + "epoch": 0.35, + "learning_rate": 3.2515939240732874e-05, + "loss": 0.1549, "step": 157380 }, { - "epoch": 0.7, - "learning_rate": 1.4950450652437113e-05, - "loss": 0.1594, + "epoch": 0.35, + "learning_rate": 3.2514820697523545e-05, + "loss": 0.1561, "step": 157390 }, { - "epoch": 0.7, - "learning_rate": 1.4948208600511188e-05, - "loss": 0.1578, + "epoch": 0.35, + "learning_rate": 3.251370215431422e-05, + "loss": 0.1584, "step": 157400 }, { - "epoch": 0.7, - "learning_rate": 1.4945966548585267e-05, - "loss": 0.1667, + "epoch": 0.35, + "learning_rate": 3.2512583611104894e-05, + "loss": 0.1568, "step": 157410 }, { - "epoch": 0.7, - "learning_rate": 1.4943724496659342e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.251146506789557e-05, + "loss": 0.1578, "step": 157420 }, { - "epoch": 0.7, - "learning_rate": 1.494148244473342e-05, - "loss": 0.1677, + "epoch": 0.35, + "learning_rate": 3.251034652468625e-05, + "loss": 0.1578, "step": 157430 }, { - "epoch": 0.7, - "learning_rate": 1.49392403928075e-05, - "loss": 0.1601, + "epoch": 0.35, + "learning_rate": 3.250922798147693e-05, + "loss": 0.1613, "step": 157440 }, { - "epoch": 0.7, - "learning_rate": 1.4936998340881575e-05, - "loss": 0.1584, + "epoch": 0.35, + "learning_rate": 3.2508109438267606e-05, + "loss": 0.1612, "step": 157450 }, { - "epoch": 0.7, - "learning_rate": 1.4934756288955653e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.250699089505828e-05, + "loss": 0.1586, "step": 157460 }, { - "epoch": 0.7, - "learning_rate": 1.4932514237029729e-05, - "loss": 0.1597, + "epoch": 0.35, + "learning_rate": 3.2505872351848955e-05, + "loss": 0.1601, "step": 157470 }, { - "epoch": 0.7, - "learning_rate": 1.4930272185103808e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.250475380863963e-05, + "loss": 0.1562, "step": 157480 }, { - "epoch": 0.7, - "learning_rate": 1.4928030133177885e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.2503635265430304e-05, + "loss": 0.1587, "step": 157490 }, { - "epoch": 0.7, - "learning_rate": 1.4925788081251962e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.250251672222098e-05, + "loss": 0.16, "step": 157500 }, { - "epoch": 0.7, - "learning_rate": 1.492354602932604e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.250139817901165e-05, + "loss": 0.1618, "step": 157510 }, { - "epoch": 0.7, - "learning_rate": 1.4921303977400117e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.250027963580233e-05, + "loss": 0.1554, "step": 157520 }, { - "epoch": 0.7, - "learning_rate": 1.4919061925474196e-05, - "loss": 0.1638, + "epoch": 0.35, + "learning_rate": 3.249916109259301e-05, + "loss": 0.1547, "step": 157530 }, { - "epoch": 0.7, - "learning_rate": 1.4916819873548271e-05, - "loss": 0.1603, + "epoch": 0.35, + "learning_rate": 3.249804254938369e-05, + "loss": 0.1594, "step": 157540 }, { - "epoch": 0.7, - "learning_rate": 1.491457782162235e-05, - "loss": 0.1616, + "epoch": 0.35, + "learning_rate": 3.2496924006174365e-05, + "loss": 0.1513, "step": 157550 }, { - "epoch": 0.7, - "learning_rate": 1.4912335769696425e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.2495805462965036e-05, + "loss": 0.1588, "step": 157560 }, { - "epoch": 0.7, - "learning_rate": 1.4910093717770504e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.2494686919755714e-05, + "loss": 0.155, "step": 157570 }, { - "epoch": 0.7, - "learning_rate": 1.4907851665844583e-05, - "loss": 0.1689, + "epoch": 0.35, + "learning_rate": 3.2493568376546385e-05, + "loss": 0.1581, "step": 157580 }, { - "epoch": 0.7, - "learning_rate": 1.4905609613918658e-05, - "loss": 0.1647, + "epoch": 0.35, + "learning_rate": 3.249244983333706e-05, + "loss": 0.1511, "step": 157590 }, { - "epoch": 0.7, - "learning_rate": 1.4903367561992737e-05, - "loss": 0.1602, + "epoch": 0.35, + "learning_rate": 3.249133129012774e-05, + "loss": 0.1642, "step": 157600 }, { - "epoch": 0.7, - "learning_rate": 1.4901125510066812e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.249021274691841e-05, + "loss": 0.1579, "step": 157610 }, { - "epoch": 0.7, - "learning_rate": 1.4898883458140891e-05, - "loss": 0.1652, + "epoch": 0.35, + "learning_rate": 3.248909420370909e-05, + "loss": 0.1603, "step": 157620 }, { - "epoch": 0.7, - "learning_rate": 1.4896641406214968e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.248797566049976e-05, + "loss": 0.1577, "step": 157630 }, { - "epoch": 0.7, - "learning_rate": 1.4894399354289047e-05, - "loss": 0.1625, + "epoch": 0.35, + "learning_rate": 3.248685711729044e-05, + "loss": 0.154, "step": 157640 }, { - "epoch": 0.7, - "learning_rate": 1.4892157302363124e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.2485738574081124e-05, + "loss": 0.1582, "step": 157650 }, { - "epoch": 0.7, - "learning_rate": 1.48899152504372e-05, - "loss": 0.1614, + "epoch": 0.35, + "learning_rate": 3.2484620030871795e-05, + "loss": 0.1606, "step": 157660 }, { - "epoch": 0.7, - "learning_rate": 1.488767319851128e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.248350148766247e-05, + "loss": 0.1596, "step": 157670 }, { - "epoch": 0.7, - "learning_rate": 1.4885431146585355e-05, - "loss": 0.1572, + "epoch": 0.35, + "learning_rate": 3.2482382944453144e-05, + "loss": 0.1562, "step": 157680 }, { - "epoch": 0.7, - "learning_rate": 1.4883189094659433e-05, - "loss": 0.1682, + "epoch": 0.35, + "learning_rate": 3.248126440124382e-05, + "loss": 0.1551, "step": 157690 }, { - "epoch": 0.7, - "learning_rate": 1.4880947042733509e-05, - "loss": 0.1617, + "epoch": 0.35, + "learning_rate": 3.24801458580345e-05, + "loss": 0.1559, "step": 157700 }, { - "epoch": 0.7, - "learning_rate": 1.4878704990807588e-05, - "loss": 0.1622, + "epoch": 0.35, + "learning_rate": 3.247902731482517e-05, + "loss": 0.1534, "step": 157710 }, { - "epoch": 0.7, - "learning_rate": 1.4876462938881666e-05, - "loss": 0.1607, + "epoch": 0.35, + "learning_rate": 3.247790877161585e-05, + "loss": 0.1542, "step": 157720 }, { - "epoch": 0.7, - "learning_rate": 1.4874220886955742e-05, - "loss": 0.1578, + "epoch": 0.35, + "learning_rate": 3.247679022840652e-05, + "loss": 0.1551, "step": 157730 }, { - "epoch": 0.7, - "learning_rate": 1.487197883502982e-05, - "loss": 0.159, + "epoch": 0.35, + "learning_rate": 3.24756716851972e-05, + "loss": 0.1586, "step": 157740 }, { - "epoch": 0.7, - "learning_rate": 1.4869736783103896e-05, - "loss": 0.1606, + "epoch": 0.35, + "learning_rate": 3.2474553141987876e-05, + "loss": 0.1612, "step": 157750 }, { - "epoch": 0.7, - "learning_rate": 1.4867494731177974e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.2473434598778554e-05, + "loss": 0.1616, "step": 157760 }, { - "epoch": 0.7, - "learning_rate": 1.4865252679252053e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.247231605556923e-05, + "loss": 0.1572, "step": 157770 }, { - "epoch": 0.7, - "learning_rate": 1.486301062732613e-05, - "loss": 0.1658, + "epoch": 0.35, + "learning_rate": 3.24711975123599e-05, + "loss": 0.1564, "step": 157780 }, { - "epoch": 0.7, - "learning_rate": 1.4860768575400209e-05, - "loss": 0.1612, + "epoch": 0.35, + "learning_rate": 3.247007896915058e-05, + "loss": 0.1585, "step": 157790 }, { - "epoch": 0.7, - "learning_rate": 1.4858526523474284e-05, - "loss": 0.1694, + "epoch": 0.35, + "learning_rate": 3.246896042594126e-05, + "loss": 0.1586, "step": 157800 }, { - "epoch": 0.7, - "learning_rate": 1.4856284471548363e-05, - "loss": 0.1703, + "epoch": 0.35, + "learning_rate": 3.246784188273193e-05, + "loss": 0.1513, "step": 157810 }, { - "epoch": 0.7, - "learning_rate": 1.4854042419622438e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.246672333952261e-05, + "loss": 0.1482, "step": 157820 }, { - "epoch": 0.7, - "learning_rate": 1.4851800367696517e-05, - "loss": 0.1684, + "epoch": 0.35, + "learning_rate": 3.246560479631328e-05, + "loss": 0.1579, "step": 157830 }, { - "epoch": 0.7, - "learning_rate": 1.4849558315770596e-05, - "loss": 0.158, + "epoch": 0.35, + "learning_rate": 3.246448625310396e-05, + "loss": 0.1598, "step": 157840 }, { - "epoch": 0.7, - "learning_rate": 1.4847316263844671e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.2463367709894635e-05, + "loss": 0.1606, "step": 157850 }, { - "epoch": 0.7, - "learning_rate": 1.484507421191875e-05, - "loss": 0.1683, + "epoch": 0.35, + "learning_rate": 3.246224916668531e-05, + "loss": 0.1588, "step": 157860 }, { - "epoch": 0.7, - "learning_rate": 1.4842832159992825e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.246113062347599e-05, + "loss": 0.1571, "step": 157870 }, { - "epoch": 0.7, - "learning_rate": 1.4840590108066904e-05, - "loss": 0.1671, + "epoch": 0.35, + "learning_rate": 3.246001208026666e-05, + "loss": 0.1568, "step": 157880 }, { - "epoch": 0.7, - "learning_rate": 1.483834805614098e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.245889353705734e-05, + "loss": 0.1537, "step": 157890 }, { - "epoch": 0.7, - "learning_rate": 1.4836106004215058e-05, - "loss": 0.1625, + "epoch": 0.35, + "learning_rate": 3.245777499384801e-05, + "loss": 0.1563, "step": 157900 }, { - "epoch": 0.7, - "learning_rate": 1.4833863952289136e-05, - "loss": 0.1656, + "epoch": 0.35, + "learning_rate": 3.245665645063869e-05, + "loss": 0.156, "step": 157910 }, { - "epoch": 0.7, - "learning_rate": 1.4831621900363213e-05, - "loss": 0.1588, + "epoch": 0.35, + "learning_rate": 3.245553790742937e-05, + "loss": 0.1529, "step": 157920 }, { - "epoch": 0.71, - "learning_rate": 1.4829379848437292e-05, - "loss": 0.1652, + "epoch": 0.35, + "learning_rate": 3.245441936422004e-05, + "loss": 0.1584, "step": 157930 }, { - "epoch": 0.71, - "learning_rate": 1.4827137796511368e-05, - "loss": 0.1612, + "epoch": 0.35, + "learning_rate": 3.2453300821010716e-05, + "loss": 0.1564, "step": 157940 }, { - "epoch": 0.71, - "learning_rate": 1.4824895744585446e-05, - "loss": 0.1555, + "epoch": 0.35, + "learning_rate": 3.2452182277801394e-05, + "loss": 0.1595, "step": 157950 }, { - "epoch": 0.71, - "learning_rate": 1.4822653692659522e-05, - "loss": 0.1623, + "epoch": 0.35, + "learning_rate": 3.245106373459207e-05, + "loss": 0.153, "step": 157960 }, { - "epoch": 0.71, - "learning_rate": 1.48204116407336e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.244994519138275e-05, + "loss": 0.1638, "step": 157970 }, { - "epoch": 0.71, - "learning_rate": 1.4818169588807679e-05, - "loss": 0.167, + "epoch": 0.35, + "learning_rate": 3.244882664817342e-05, + "loss": 0.1613, "step": 157980 }, { - "epoch": 0.71, - "learning_rate": 1.4815927536881754e-05, - "loss": 0.1652, + "epoch": 0.35, + "learning_rate": 3.24477081049641e-05, + "loss": 0.1549, "step": 157990 }, { - "epoch": 0.71, - "learning_rate": 1.4813685484955833e-05, - "loss": 0.1627, + "epoch": 0.35, + "learning_rate": 3.244658956175477e-05, + "loss": 0.1597, "step": 158000 }, { - "epoch": 0.71, - "learning_rate": 1.4811443433029908e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.244547101854545e-05, + "loss": 0.1588, "step": 158010 }, { - "epoch": 0.71, - "learning_rate": 1.4809201381103987e-05, - "loss": 0.1698, + "epoch": 0.35, + "learning_rate": 3.2444352475336126e-05, + "loss": 0.1593, "step": 158020 }, { - "epoch": 0.71, - "learning_rate": 1.4806959329178064e-05, - "loss": 0.1601, + "epoch": 0.35, + "learning_rate": 3.24432339321268e-05, + "loss": 0.1553, "step": 158030 }, { - "epoch": 0.71, - "learning_rate": 1.4804717277252141e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.2442115388917475e-05, + "loss": 0.1568, "step": 158040 }, { - "epoch": 0.71, - "learning_rate": 1.480247522532622e-05, - "loss": 0.1628, + "epoch": 0.35, + "learning_rate": 3.2440996845708146e-05, + "loss": 0.1559, "step": 158050 }, { - "epoch": 0.71, - "learning_rate": 1.4800233173400297e-05, - "loss": 0.1643, + "epoch": 0.35, + "learning_rate": 3.2439878302498824e-05, + "loss": 0.159, "step": 158060 }, { - "epoch": 0.71, - "learning_rate": 1.4797991121474376e-05, - "loss": 0.1632, + "epoch": 0.35, + "learning_rate": 3.243875975928951e-05, + "loss": 0.1578, "step": 158070 }, { - "epoch": 0.71, - "learning_rate": 1.4795749069548451e-05, - "loss": 0.1682, + "epoch": 0.35, + "learning_rate": 3.243764121608018e-05, + "loss": 0.161, "step": 158080 }, { - "epoch": 0.71, - "learning_rate": 1.479350701762253e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.243652267287086e-05, + "loss": 0.1541, "step": 158090 }, { - "epoch": 0.71, - "learning_rate": 1.4791264965696605e-05, - "loss": 0.1595, + "epoch": 0.35, + "learning_rate": 3.243540412966153e-05, + "loss": 0.1537, "step": 158100 }, { - "epoch": 0.71, - "learning_rate": 1.4789022913770684e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.243428558645221e-05, + "loss": 0.1572, "step": 158110 }, { - "epoch": 0.71, - "learning_rate": 1.4786780861844762e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.2433167043242885e-05, + "loss": 0.1632, "step": 158120 }, { - "epoch": 0.71, - "learning_rate": 1.4784538809918838e-05, - "loss": 0.166, + "epoch": 0.35, + "learning_rate": 3.2432048500033556e-05, + "loss": 0.1591, "step": 158130 }, { - "epoch": 0.71, - "learning_rate": 1.4782296757992916e-05, - "loss": 0.1589, + "epoch": 0.35, + "learning_rate": 3.2430929956824234e-05, + "loss": 0.1593, "step": 158140 }, { - "epoch": 0.71, - "learning_rate": 1.4780054706066992e-05, - "loss": 0.1658, + "epoch": 0.35, + "learning_rate": 3.2429811413614905e-05, + "loss": 0.1607, "step": 158150 }, { - "epoch": 0.71, - "learning_rate": 1.477781265414107e-05, - "loss": 0.1615, + "epoch": 0.35, + "learning_rate": 3.242869287040558e-05, + "loss": 0.1645, "step": 158160 }, { - "epoch": 0.71, - "learning_rate": 1.4775570602215148e-05, - "loss": 0.1624, + "epoch": 0.35, + "learning_rate": 3.242757432719626e-05, + "loss": 0.1588, "step": 158170 }, { - "epoch": 0.71, - "learning_rate": 1.4773328550289226e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.242645578398694e-05, + "loss": 0.1553, "step": 158180 }, { - "epoch": 0.71, - "learning_rate": 1.4771086498363303e-05, - "loss": 0.1628, + "epoch": 0.35, + "learning_rate": 3.242533724077762e-05, + "loss": 0.1602, "step": 158190 }, { - "epoch": 0.71, - "learning_rate": 1.476884444643738e-05, - "loss": 0.1581, + "epoch": 0.35, + "learning_rate": 3.242421869756829e-05, + "loss": 0.1547, "step": 158200 }, { - "epoch": 0.71, - "learning_rate": 1.4766602394511459e-05, - "loss": 0.1707, + "epoch": 0.35, + "learning_rate": 3.2423100154358966e-05, + "loss": 0.1643, "step": 158210 }, { - "epoch": 0.71, - "learning_rate": 1.4764360342585534e-05, - "loss": 0.1651, + "epoch": 0.35, + "learning_rate": 3.242198161114964e-05, + "loss": 0.1508, "step": 158220 }, { - "epoch": 0.71, - "learning_rate": 1.4762118290659613e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.2420863067940315e-05, + "loss": 0.1568, "step": 158230 }, { - "epoch": 0.71, - "learning_rate": 1.4759876238733688e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.241974452473099e-05, + "loss": 0.1621, "step": 158240 }, { - "epoch": 0.71, - "learning_rate": 1.4757634186807767e-05, - "loss": 0.1616, + "epoch": 0.35, + "learning_rate": 3.2418625981521664e-05, + "loss": 0.1587, "step": 158250 }, { - "epoch": 0.71, - "learning_rate": 1.4755392134881846e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.241750743831234e-05, + "loss": 0.1562, "step": 158260 }, { - "epoch": 0.71, - "learning_rate": 1.4753150082955921e-05, - "loss": 0.167, + "epoch": 0.35, + "learning_rate": 3.241638889510302e-05, + "loss": 0.1588, "step": 158270 }, { - "epoch": 0.71, - "learning_rate": 1.475090803103e-05, - "loss": 0.1558, + "epoch": 0.35, + "learning_rate": 3.24152703518937e-05, + "loss": 0.1588, "step": 158280 }, { - "epoch": 0.71, - "learning_rate": 1.4748665979104075e-05, - "loss": 0.1616, + "epoch": 0.35, + "learning_rate": 3.2414151808684376e-05, + "loss": 0.1535, "step": 158290 }, { - "epoch": 0.71, - "learning_rate": 1.4746423927178154e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.241303326547505e-05, + "loss": 0.1577, "step": 158300 }, { - "epoch": 0.71, - "learning_rate": 1.4744181875252231e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.2411914722265725e-05, + "loss": 0.1568, "step": 158310 }, { - "epoch": 0.71, - "learning_rate": 1.474193982332631e-05, - "loss": 0.1663, + "epoch": 0.35, + "learning_rate": 3.2410796179056396e-05, + "loss": 0.1612, "step": 158320 }, { - "epoch": 0.71, - "learning_rate": 1.4739697771400387e-05, - "loss": 0.161, + "epoch": 0.35, + "learning_rate": 3.2409677635847074e-05, + "loss": 0.1573, "step": 158330 }, { - "epoch": 0.71, - "learning_rate": 1.4737455719474464e-05, - "loss": 0.163, + "epoch": 0.35, + "learning_rate": 3.240855909263775e-05, + "loss": 0.1561, "step": 158340 }, { - "epoch": 0.71, - "learning_rate": 1.4735213667548542e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.240744054942842e-05, + "loss": 0.1587, "step": 158350 }, { - "epoch": 0.71, - "learning_rate": 1.4732971615622618e-05, - "loss": 0.1633, + "epoch": 0.35, + "learning_rate": 3.24063220062191e-05, + "loss": 0.1571, "step": 158360 }, { - "epoch": 0.71, - "learning_rate": 1.4730729563696696e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.240520346300978e-05, + "loss": 0.1566, "step": 158370 }, { - "epoch": 0.71, - "learning_rate": 1.4728487511770772e-05, - "loss": 0.1606, + "epoch": 0.35, + "learning_rate": 3.240408491980046e-05, + "loss": 0.1496, "step": 158380 }, { - "epoch": 0.71, - "learning_rate": 1.472624545984485e-05, - "loss": 0.1599, + "epoch": 0.35, + "learning_rate": 3.2402966376591135e-05, + "loss": 0.1582, "step": 158390 }, { - "epoch": 0.71, - "learning_rate": 1.472400340791893e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.2401847833381806e-05, + "loss": 0.1528, "step": 158400 }, { - "epoch": 0.71, - "learning_rate": 1.4721761355993005e-05, - "loss": 0.1632, + "epoch": 0.35, + "learning_rate": 3.2400729290172484e-05, + "loss": 0.1605, "step": 158410 }, { - "epoch": 0.71, - "learning_rate": 1.4719519304067083e-05, - "loss": 0.1632, + "epoch": 0.35, + "learning_rate": 3.2399610746963155e-05, + "loss": 0.1561, "step": 158420 }, { - "epoch": 0.71, - "learning_rate": 1.471727725214116e-05, - "loss": 0.1674, + "epoch": 0.35, + "learning_rate": 3.239849220375383e-05, + "loss": 0.1554, "step": 158430 }, { - "epoch": 0.71, - "learning_rate": 1.4715035200215237e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.239737366054451e-05, + "loss": 0.1589, "step": 158440 }, { - "epoch": 0.71, - "learning_rate": 1.4712793148289314e-05, - "loss": 0.167, + "epoch": 0.35, + "learning_rate": 3.239625511733518e-05, + "loss": 0.1599, "step": 158450 }, { - "epoch": 0.71, - "learning_rate": 1.4710551096363393e-05, - "loss": 0.1598, + "epoch": 0.35, + "learning_rate": 3.239513657412586e-05, + "loss": 0.1576, "step": 158460 }, { - "epoch": 0.71, - "learning_rate": 1.4708309044437472e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.239401803091653e-05, + "loss": 0.1623, "step": 158470 }, { - "epoch": 0.71, - "learning_rate": 1.4706066992511547e-05, - "loss": 0.1622, + "epoch": 0.35, + "learning_rate": 3.2392899487707216e-05, + "loss": 0.1605, "step": 158480 }, { - "epoch": 0.71, - "learning_rate": 1.4703824940585626e-05, - "loss": 0.1675, + "epoch": 0.35, + "learning_rate": 3.239178094449789e-05, + "loss": 0.1613, "step": 158490 }, { - "epoch": 0.71, - "learning_rate": 1.4701582888659701e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.2390662401288565e-05, + "loss": 0.1586, "step": 158500 }, { - "epoch": 0.71, - "learning_rate": 1.469934083673378e-05, - "loss": 0.164, + "epoch": 0.35, + "learning_rate": 3.238954385807924e-05, + "loss": 0.1594, "step": 158510 }, { - "epoch": 0.71, - "learning_rate": 1.4697098784807855e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.2388425314869914e-05, + "loss": 0.1614, "step": 158520 }, { - "epoch": 0.71, - "learning_rate": 1.4694856732881934e-05, - "loss": 0.165, + "epoch": 0.35, + "learning_rate": 3.238730677166059e-05, + "loss": 0.1594, "step": 158530 }, { - "epoch": 0.71, - "learning_rate": 1.4692614680956013e-05, - "loss": 0.16, + "epoch": 0.35, + "learning_rate": 3.238618822845126e-05, + "loss": 0.155, "step": 158540 }, { - "epoch": 0.71, - "learning_rate": 1.4690372629030088e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.238506968524194e-05, + "loss": 0.1545, "step": 158550 }, { - "epoch": 0.71, - "learning_rate": 1.4688130577104167e-05, - "loss": 0.158, + "epoch": 0.35, + "learning_rate": 3.238395114203262e-05, + "loss": 0.1541, "step": 158560 }, { - "epoch": 0.71, - "learning_rate": 1.4685888525178244e-05, - "loss": 0.158, + "epoch": 0.35, + "learning_rate": 3.238283259882329e-05, + "loss": 0.1564, "step": 158570 }, { - "epoch": 0.71, - "learning_rate": 1.468364647325232e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.238171405561397e-05, + "loss": 0.1589, "step": 158580 }, { - "epoch": 0.71, - "learning_rate": 1.4681404421326398e-05, - "loss": 0.1628, + "epoch": 0.35, + "learning_rate": 3.2380595512404646e-05, + "loss": 0.1563, "step": 158590 }, { - "epoch": 0.71, - "learning_rate": 1.4679162369400477e-05, - "loss": 0.1646, + "epoch": 0.35, + "learning_rate": 3.2379476969195324e-05, + "loss": 0.1585, "step": 158600 }, { - "epoch": 0.71, - "learning_rate": 1.4676920317474555e-05, - "loss": 0.1598, + "epoch": 0.35, + "learning_rate": 3.2378358425986e-05, + "loss": 0.1609, "step": 158610 }, { - "epoch": 0.71, - "learning_rate": 1.467467826554863e-05, - "loss": 0.1577, + "epoch": 0.35, + "learning_rate": 3.237723988277667e-05, + "loss": 0.1597, "step": 158620 }, { - "epoch": 0.71, - "learning_rate": 1.467243621362271e-05, - "loss": 0.1577, + "epoch": 0.35, + "learning_rate": 3.237612133956735e-05, + "loss": 0.1585, "step": 158630 }, { - "epoch": 0.71, - "learning_rate": 1.4670194161696785e-05, - "loss": 0.1596, + "epoch": 0.35, + "learning_rate": 3.237500279635802e-05, + "loss": 0.1581, "step": 158640 }, { - "epoch": 0.71, - "learning_rate": 1.4667952109770863e-05, - "loss": 0.1607, + "epoch": 0.35, + "learning_rate": 3.23738842531487e-05, + "loss": 0.1586, "step": 158650 }, { - "epoch": 0.71, - "learning_rate": 1.4665710057844939e-05, - "loss": 0.162, + "epoch": 0.35, + "learning_rate": 3.237276570993938e-05, + "loss": 0.1641, "step": 158660 }, { - "epoch": 0.71, - "learning_rate": 1.4663468005919017e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.237164716673005e-05, + "loss": 0.1566, "step": 158670 }, { - "epoch": 0.71, - "learning_rate": 1.4661225953993096e-05, - "loss": 0.1641, + "epoch": 0.35, + "learning_rate": 3.237052862352073e-05, + "loss": 0.1568, "step": 158680 }, { - "epoch": 0.71, - "learning_rate": 1.4658983902067171e-05, - "loss": 0.1557, + "epoch": 0.35, + "learning_rate": 3.2369410080311405e-05, + "loss": 0.1618, "step": 158690 }, { - "epoch": 0.71, - "learning_rate": 1.465674185014125e-05, - "loss": 0.1629, + "epoch": 0.35, + "learning_rate": 3.236829153710208e-05, + "loss": 0.1556, "step": 158700 }, { - "epoch": 0.71, - "learning_rate": 1.4654499798215327e-05, - "loss": 0.1591, + "epoch": 0.35, + "learning_rate": 3.236717299389276e-05, + "loss": 0.155, "step": 158710 }, { - "epoch": 0.71, - "learning_rate": 1.4652257746289406e-05, - "loss": 0.1659, + "epoch": 0.35, + "learning_rate": 3.236605445068343e-05, + "loss": 0.1554, "step": 158720 }, { - "epoch": 0.71, - "learning_rate": 1.4650015694363481e-05, - "loss": 0.1618, + "epoch": 0.35, + "learning_rate": 3.236493590747411e-05, + "loss": 0.1625, "step": 158730 }, { - "epoch": 0.71, - "learning_rate": 1.464777364243756e-05, - "loss": 0.1645, + "epoch": 0.35, + "learning_rate": 3.236381736426478e-05, + "loss": 0.1565, "step": 158740 }, { - "epoch": 0.71, - "learning_rate": 1.4645531590511639e-05, - "loss": 0.1668, + "epoch": 0.35, + "learning_rate": 3.236269882105546e-05, + "loss": 0.1621, "step": 158750 }, { - "epoch": 0.71, - "learning_rate": 1.4643289538585714e-05, - "loss": 0.1637, + "epoch": 0.35, + "learning_rate": 3.2361580277846137e-05, + "loss": 0.1575, "step": 158760 }, { - "epoch": 0.71, - "learning_rate": 1.4641047486659793e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.236046173463681e-05, + "loss": 0.1529, "step": 158770 }, { - "epoch": 0.71, - "learning_rate": 1.4638805434733868e-05, - "loss": 0.1662, + "epoch": 0.35, + "learning_rate": 3.2359343191427486e-05, + "loss": 0.1592, "step": 158780 }, { - "epoch": 0.71, - "learning_rate": 1.4636563382807947e-05, - "loss": 0.1664, + "epoch": 0.35, + "learning_rate": 3.2358224648218164e-05, + "loss": 0.1588, "step": 158790 }, { - "epoch": 0.71, - "learning_rate": 1.4634321330882022e-05, + "epoch": 0.35, + "learning_rate": 3.235710610500884e-05, "loss": 0.159, "step": 158800 }, { - "epoch": 0.71, - "learning_rate": 1.46320792789561e-05, - "loss": 0.1709, + "epoch": 0.35, + "learning_rate": 3.235598756179951e-05, + "loss": 0.1583, "step": 158810 }, { - "epoch": 0.71, - "learning_rate": 1.462983722703018e-05, - "loss": 0.1636, + "epoch": 0.35, + "learning_rate": 3.235486901859019e-05, + "loss": 0.158, "step": 158820 }, { - "epoch": 0.71, - "learning_rate": 1.4627595175104255e-05, - "loss": 0.1599, + "epoch": 0.35, + "learning_rate": 3.235375047538087e-05, + "loss": 0.1584, "step": 158830 }, { - "epoch": 0.71, - "learning_rate": 1.4625353123178334e-05, - "loss": 0.1622, + "epoch": 0.35, + "learning_rate": 3.235263193217154e-05, + "loss": 0.1602, "step": 158840 }, { - "epoch": 0.71, - "learning_rate": 1.462311107125241e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.235162524328315e-05, + "loss": 0.1589, "step": 158850 }, { - "epoch": 0.71, - "learning_rate": 1.462086901932649e-05, - "loss": 0.1626, + "epoch": 0.35, + "learning_rate": 3.2350506700073826e-05, + "loss": 0.1585, "step": 158860 }, { - "epoch": 0.71, - "learning_rate": 1.4618626967400565e-05, - "loss": 0.1673, + "epoch": 0.35, + "learning_rate": 3.2349388156864504e-05, + "loss": 0.1621, "step": 158870 }, { - "epoch": 0.71, - "learning_rate": 1.4616384915474643e-05, - "loss": 0.1609, + "epoch": 0.35, + "learning_rate": 3.2348269613655175e-05, + "loss": 0.1555, "step": 158880 }, { - "epoch": 0.71, - "learning_rate": 1.4614142863548722e-05, - "loss": 0.1573, + "epoch": 0.35, + "learning_rate": 3.2347151070445853e-05, + "loss": 0.1541, "step": 158890 }, { - "epoch": 0.71, - "learning_rate": 1.4611900811622797e-05, - "loss": 0.1683, + "epoch": 0.35, + "learning_rate": 3.234603252723653e-05, + "loss": 0.1576, "step": 158900 }, { - "epoch": 0.71, - "learning_rate": 1.4609658759696876e-05, - "loss": 0.1635, + "epoch": 0.35, + "learning_rate": 3.23449139840272e-05, + "loss": 0.1583, "step": 158910 }, { - "epoch": 0.71, - "learning_rate": 1.4607416707770951e-05, - "loss": 0.1611, + "epoch": 0.35, + "learning_rate": 3.234379544081788e-05, + "loss": 0.1526, "step": 158920 }, { - "epoch": 0.71, - "learning_rate": 1.460517465584503e-05, - "loss": 0.1572, + "epoch": 0.35, + "learning_rate": 3.234267689760855e-05, + "loss": 0.1558, "step": 158930 }, { - "epoch": 0.71, - "learning_rate": 1.4602932603919105e-05, - "loss": 0.1665, + "epoch": 0.35, + "learning_rate": 3.234155835439923e-05, + "loss": 0.154, "step": 158940 }, { - "epoch": 0.71, - "learning_rate": 1.4600690551993184e-05, - "loss": 0.159, + "epoch": 0.35, + "learning_rate": 3.234043981118991e-05, + "loss": 0.1571, "step": 158950 }, { - "epoch": 0.71, - "learning_rate": 1.4598448500067263e-05, - "loss": 0.1661, + "epoch": 0.35, + "learning_rate": 3.2339321267980585e-05, + "loss": 0.1578, "step": 158960 }, { - "epoch": 0.71, - "learning_rate": 1.4596206448141338e-05, - "loss": 0.1585, + "epoch": 0.35, + "learning_rate": 3.233820272477126e-05, + "loss": 0.1583, "step": 158970 }, { - "epoch": 0.71, - "learning_rate": 1.4593964396215417e-05, - "loss": 0.1554, + "epoch": 0.35, + "learning_rate": 3.2337084181561934e-05, + "loss": 0.1582, "step": 158980 }, { - "epoch": 0.71, - "learning_rate": 1.4591722344289494e-05, - "loss": 0.1585, + "epoch": 0.35, + "learning_rate": 3.233596563835261e-05, + "loss": 0.1562, "step": 158990 }, { - "epoch": 0.71, - "learning_rate": 1.4589480292363573e-05, - "loss": 0.1596, + "epoch": 0.35, + "learning_rate": 3.233484709514329e-05, + "loss": 0.1615, "step": 159000 }, { - "epoch": 0.71, - "learning_rate": 1.4587238240437648e-05, - "loss": 0.1633, + "epoch": 0.35, + "learning_rate": 3.233372855193396e-05, + "loss": 0.1557, "step": 159010 }, { - "epoch": 0.71, - "learning_rate": 1.4584996188511727e-05, - "loss": 0.1634, + "epoch": 0.35, + "learning_rate": 3.233261000872464e-05, + "loss": 0.1607, "step": 159020 }, { - "epoch": 0.71, - "learning_rate": 1.4582754136585805e-05, - "loss": 0.1631, + "epoch": 0.35, + "learning_rate": 3.233149146551531e-05, + "loss": 0.1611, "step": 159030 }, { - "epoch": 0.71, - "learning_rate": 1.458051208465988e-05, - "loss": 0.1619, + "epoch": 0.35, + "learning_rate": 3.233037292230599e-05, + "loss": 0.1558, "step": 159040 }, { - "epoch": 0.71, - "learning_rate": 1.457827003273396e-05, - "loss": 0.1582, + "epoch": 0.36, + "learning_rate": 3.2329254379096666e-05, + "loss": 0.1523, "step": 159050 }, { - "epoch": 0.71, - "learning_rate": 1.4576027980808035e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.2328135835887344e-05, + "loss": 0.1584, "step": 159060 }, { - "epoch": 0.71, - "learning_rate": 1.4573785928882114e-05, - "loss": 0.1643, + "epoch": 0.36, + "learning_rate": 3.232701729267802e-05, + "loss": 0.1568, "step": 159070 }, { - "epoch": 0.71, - "learning_rate": 1.4571543876956192e-05, - "loss": 0.1586, + "epoch": 0.36, + "learning_rate": 3.232589874946869e-05, + "loss": 0.1552, "step": 159080 }, { - "epoch": 0.71, - "learning_rate": 1.4569301825030268e-05, - "loss": 0.1661, + "epoch": 0.36, + "learning_rate": 3.232478020625937e-05, + "loss": 0.1558, "step": 159090 }, { - "epoch": 0.71, - "learning_rate": 1.4567059773104346e-05, - "loss": 0.1673, + "epoch": 0.36, + "learning_rate": 3.232366166305005e-05, + "loss": 0.1582, "step": 159100 }, { - "epoch": 0.71, - "learning_rate": 1.4564817721178423e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.232254311984072e-05, + "loss": 0.1593, "step": 159110 }, { - "epoch": 0.71, - "learning_rate": 1.45625756692525e-05, - "loss": 0.1645, + "epoch": 0.36, + "learning_rate": 3.23214245766314e-05, + "loss": 0.1595, "step": 159120 }, { - "epoch": 0.71, - "learning_rate": 1.4560333617326577e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.232030603342207e-05, + "loss": 0.1551, "step": 159130 }, { - "epoch": 0.71, - "learning_rate": 1.4558091565400656e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.231918749021275e-05, + "loss": 0.1627, "step": 159140 }, { - "epoch": 0.71, - "learning_rate": 1.4555849513474735e-05, - "loss": 0.1621, + "epoch": 0.36, + "learning_rate": 3.2318068947003425e-05, + "loss": 0.1596, "step": 159150 }, { - "epoch": 0.71, - "learning_rate": 1.455360746154881e-05, - "loss": 0.1626, + "epoch": 0.36, + "learning_rate": 3.2316950403794096e-05, + "loss": 0.1597, "step": 159160 }, { - "epoch": 0.71, - "learning_rate": 1.4551365409622889e-05, - "loss": 0.1656, + "epoch": 0.36, + "learning_rate": 3.2315831860584774e-05, + "loss": 0.1589, "step": 159170 }, { - "epoch": 0.71, - "learning_rate": 1.4549123357696964e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.231471331737545e-05, + "loss": 0.1552, "step": 159180 }, { - "epoch": 0.71, - "learning_rate": 1.4546881305771043e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.231359477416613e-05, + "loss": 0.159, "step": 159190 }, { - "epoch": 0.71, - "learning_rate": 1.4544639253845118e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.23124762309568e-05, + "loss": 0.1603, "step": 159200 }, { - "epoch": 0.71, - "learning_rate": 1.4542397201919197e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.231135768774748e-05, + "loss": 0.1567, "step": 159210 }, { - "epoch": 0.71, - "learning_rate": 1.4540155149993276e-05, - "loss": 0.1649, + "epoch": 0.36, + "learning_rate": 3.231023914453816e-05, + "loss": 0.1555, "step": 159220 }, { - "epoch": 0.71, - "learning_rate": 1.4537913098067351e-05, - "loss": 0.1641, + "epoch": 0.36, + "learning_rate": 3.230912060132883e-05, + "loss": 0.1626, "step": 159230 }, { - "epoch": 0.71, - "learning_rate": 1.453567104614143e-05, - "loss": 0.1565, + "epoch": 0.36, + "learning_rate": 3.2308002058119506e-05, + "loss": 0.1633, "step": 159240 }, { - "epoch": 0.71, - "learning_rate": 1.4533428994215507e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.230688351491018e-05, + "loss": 0.1541, "step": 159250 }, { - "epoch": 0.71, - "learning_rate": 1.4531186942289585e-05, - "loss": 0.1579, + "epoch": 0.36, + "learning_rate": 3.2305764971700855e-05, + "loss": 0.1542, "step": 159260 }, { - "epoch": 0.71, - "learning_rate": 1.452894489036366e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.230464642849153e-05, + "loss": 0.1532, "step": 159270 }, { - "epoch": 0.71, - "learning_rate": 1.452670283843774e-05, - "loss": 0.1549, + "epoch": 0.36, + "learning_rate": 3.230352788528221e-05, + "loss": 0.1599, "step": 159280 }, { - "epoch": 0.71, - "learning_rate": 1.4524460786511818e-05, - "loss": 0.1655, + "epoch": 0.36, + "learning_rate": 3.230240934207289e-05, + "loss": 0.1588, "step": 159290 }, { - "epoch": 0.71, - "learning_rate": 1.4522218734585894e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.230129079886356e-05, + "loss": 0.1607, "step": 159300 }, { - "epoch": 0.71, - "learning_rate": 1.4519976682659972e-05, - "loss": 0.1604, + "epoch": 0.36, + "learning_rate": 3.230017225565424e-05, + "loss": 0.1534, "step": 159310 }, { - "epoch": 0.71, - "learning_rate": 1.451795883592664e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.2299053712444916e-05, + "loss": 0.1507, "step": 159320 }, { - "epoch": 0.71, - "learning_rate": 1.4515716784000719e-05, - "loss": 0.1645, + "epoch": 0.36, + "learning_rate": 3.229793516923559e-05, + "loss": 0.1567, "step": 159330 }, { - "epoch": 0.71, - "learning_rate": 1.4513474732074794e-05, - "loss": 0.1667, + "epoch": 0.36, + "learning_rate": 3.2296816626026265e-05, + "loss": 0.1567, "step": 159340 }, { - "epoch": 0.71, - "learning_rate": 1.4511232680148873e-05, - "loss": 0.1646, + "epoch": 0.36, + "learning_rate": 3.2295698082816936e-05, + "loss": 0.1635, "step": 159350 }, { - "epoch": 0.71, - "learning_rate": 1.4508990628222952e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.2294579539607614e-05, + "loss": 0.1607, "step": 159360 }, { - "epoch": 0.71, - "learning_rate": 1.4506748576297027e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.229346099639829e-05, + "loss": 0.1577, "step": 159370 }, { - "epoch": 0.71, - "learning_rate": 1.4504506524371106e-05, - "loss": 0.165, - "step": 159380 + "epoch": 0.36, + "learning_rate": 3.229234245318897e-05, + "loss": 0.1558, + "step": 159380 }, { - "epoch": 0.71, - "learning_rate": 1.4502264472445181e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.229122390997965e-05, + "loss": 0.1537, "step": 159390 }, { - "epoch": 0.71, - "learning_rate": 1.450002242051926e-05, - "loss": 0.1655, + "epoch": 0.36, + "learning_rate": 3.229010536677032e-05, + "loss": 0.1549, "step": 159400 }, { - "epoch": 0.71, - "learning_rate": 1.4497780368593337e-05, - "loss": 0.1635, + "epoch": 0.36, + "learning_rate": 3.2288986823561e-05, + "loss": 0.1607, "step": 159410 }, { - "epoch": 0.71, - "learning_rate": 1.4495538316667415e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.2287868280351675e-05, + "loss": 0.1597, "step": 159420 }, { - "epoch": 0.71, - "learning_rate": 1.4493296264741492e-05, - "loss": 0.1641, + "epoch": 0.36, + "learning_rate": 3.2286749737142346e-05, + "loss": 0.1601, "step": 159430 }, { - "epoch": 0.71, - "learning_rate": 1.449105421281557e-05, - "loss": 0.167, + "epoch": 0.36, + "learning_rate": 3.2285631193933024e-05, + "loss": 0.1577, "step": 159440 }, { - "epoch": 0.71, - "learning_rate": 1.4488812160889648e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.2284512650723695e-05, + "loss": 0.1563, "step": 159450 }, { - "epoch": 0.71, - "learning_rate": 1.4486570108963724e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.228339410751437e-05, + "loss": 0.1579, "step": 159460 }, { - "epoch": 0.71, - "learning_rate": 1.4484328057037802e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.228227556430505e-05, + "loss": 0.16, "step": 159470 }, { - "epoch": 0.71, - "learning_rate": 1.4482086005111878e-05, - "loss": 0.1629, + "epoch": 0.36, + "learning_rate": 3.228115702109573e-05, + "loss": 0.1561, "step": 159480 }, { - "epoch": 0.71, - "learning_rate": 1.4479843953185956e-05, - "loss": 0.1577, + "epoch": 0.36, + "learning_rate": 3.228003847788641e-05, + "loss": 0.1553, "step": 159490 }, { - "epoch": 0.71, - "learning_rate": 1.4477601901260035e-05, - "loss": 0.1651, + "epoch": 0.36, + "learning_rate": 3.227891993467708e-05, + "loss": 0.1602, "step": 159500 }, { - "epoch": 0.71, - "learning_rate": 1.447535984933411e-05, - "loss": 0.167, + "epoch": 0.36, + "learning_rate": 3.2277801391467756e-05, + "loss": 0.1531, "step": 159510 }, { - "epoch": 0.71, - "learning_rate": 1.4473117797408189e-05, - "loss": 0.1639, + "epoch": 0.36, + "learning_rate": 3.227668284825843e-05, + "loss": 0.1636, "step": 159520 }, { - "epoch": 0.71, - "learning_rate": 1.4470875745482264e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.2275564305049105e-05, + "loss": 0.1561, "step": 159530 }, { - "epoch": 0.71, - "learning_rate": 1.4468633693556343e-05, - "loss": 0.1571, + "epoch": 0.36, + "learning_rate": 3.227444576183978e-05, + "loss": 0.1519, "step": 159540 }, { - "epoch": 0.71, - "learning_rate": 1.446639164163042e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.2273327218630454e-05, + "loss": 0.1615, "step": 159550 }, { - "epoch": 0.71, - "learning_rate": 1.4464149589704499e-05, - "loss": 0.1604, + "epoch": 0.36, + "learning_rate": 3.227220867542113e-05, + "loss": 0.1578, "step": 159560 }, { - "epoch": 0.71, - "learning_rate": 1.4461907537778578e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.2271090132211803e-05, + "loss": 0.1511, "step": 159570 }, { - "epoch": 0.71, - "learning_rate": 1.4459665485852653e-05, - "loss": 0.1635, + "epoch": 0.36, + "learning_rate": 3.226997158900248e-05, + "loss": 0.1613, "step": 159580 }, { - "epoch": 0.71, - "learning_rate": 1.4457423433926732e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.226885304579316e-05, + "loss": 0.1587, "step": 159590 }, { - "epoch": 0.71, - "learning_rate": 1.4455181382000807e-05, - "loss": 0.1641, + "epoch": 0.36, + "learning_rate": 3.226773450258384e-05, + "loss": 0.164, "step": 159600 }, { - "epoch": 0.71, - "learning_rate": 1.4452939330074886e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.2266615959374515e-05, + "loss": 0.1588, "step": 159610 }, { - "epoch": 0.71, - "learning_rate": 1.4450697278148961e-05, - "loss": 0.1628, + "epoch": 0.36, + "learning_rate": 3.2265497416165186e-05, + "loss": 0.157, "step": 159620 }, { - "epoch": 0.71, - "learning_rate": 1.444845522622304e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.2264378872955864e-05, + "loss": 0.1585, "step": 159630 }, { - "epoch": 0.71, - "learning_rate": 1.4446213174297118e-05, - "loss": 0.1654, + "epoch": 0.36, + "learning_rate": 3.226326032974654e-05, + "loss": 0.1587, "step": 159640 }, { - "epoch": 0.71, - "learning_rate": 1.4443971122371194e-05, - "loss": 0.1629, + "epoch": 0.36, + "learning_rate": 3.226214178653721e-05, + "loss": 0.1635, "step": 159650 }, { - "epoch": 0.71, - "learning_rate": 1.4441729070445272e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.226102324332789e-05, + "loss": 0.1561, "step": 159660 }, { - "epoch": 0.71, - "learning_rate": 1.443948701851935e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.225990470011856e-05, + "loss": 0.1505, "step": 159670 }, { - "epoch": 0.71, - "learning_rate": 1.4437244966593426e-05, - "loss": 0.1586, + "epoch": 0.36, + "learning_rate": 3.225878615690924e-05, + "loss": 0.1522, "step": 159680 }, { - "epoch": 0.71, - "learning_rate": 1.4435002914667504e-05, - "loss": 0.1668, + "epoch": 0.36, + "learning_rate": 3.225766761369992e-05, + "loss": 0.1551, "step": 159690 }, { - "epoch": 0.71, - "learning_rate": 1.4432760862741582e-05, - "loss": 0.1625, + "epoch": 0.36, + "learning_rate": 3.2256549070490596e-05, + "loss": 0.1575, "step": 159700 }, { - "epoch": 0.71, - "learning_rate": 1.4430518810815661e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.2255430527281274e-05, + "loss": 0.1539, "step": 159710 }, { - "epoch": 0.71, - "learning_rate": 1.4428276758889736e-05, - "loss": 0.1647, + "epoch": 0.36, + "learning_rate": 3.2254311984071945e-05, + "loss": 0.1552, "step": 159720 }, { - "epoch": 0.71, - "learning_rate": 1.4426034706963815e-05, - "loss": 0.1625, + "epoch": 0.36, + "learning_rate": 3.225319344086262e-05, + "loss": 0.1568, "step": 159730 }, { - "epoch": 0.71, - "learning_rate": 1.442379265503789e-05, - "loss": 0.1659, + "epoch": 0.36, + "learning_rate": 3.22520748976533e-05, + "loss": 0.1587, "step": 159740 }, { - "epoch": 0.71, - "learning_rate": 1.4421550603111969e-05, - "loss": 0.1566, + "epoch": 0.36, + "learning_rate": 3.225095635444397e-05, + "loss": 0.1595, "step": 159750 }, { - "epoch": 0.71, - "learning_rate": 1.4419308551186044e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.224983781123465e-05, + "loss": 0.152, "step": 159760 }, { - "epoch": 0.71, - "learning_rate": 1.4417066499260123e-05, - "loss": 0.1616, + "epoch": 0.36, + "learning_rate": 3.224871926802532e-05, + "loss": 0.1556, "step": 159770 }, { - "epoch": 0.71, - "learning_rate": 1.4414824447334202e-05, - "loss": 0.1598, + "epoch": 0.36, + "learning_rate": 3.2247600724816e-05, + "loss": 0.1583, "step": 159780 }, { - "epoch": 0.71, - "learning_rate": 1.4412582395408277e-05, - "loss": 0.1669, + "epoch": 0.36, + "learning_rate": 3.224648218160668e-05, + "loss": 0.1587, "step": 159790 }, { - "epoch": 0.71, - "learning_rate": 1.4410340343482356e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.2245363638397355e-05, + "loss": 0.1568, "step": 159800 }, { - "epoch": 0.71, - "learning_rate": 1.4408098291556433e-05, - "loss": 0.1586, + "epoch": 0.36, + "learning_rate": 3.224424509518803e-05, + "loss": 0.1596, "step": 159810 }, { - "epoch": 0.71, - "learning_rate": 1.4405856239630512e-05, - "loss": 0.1628, + "epoch": 0.36, + "learning_rate": 3.2243126551978704e-05, + "loss": 0.1587, "step": 159820 }, { - "epoch": 0.71, - "learning_rate": 1.4403614187704587e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.224200800876938e-05, + "loss": 0.1593, "step": 159830 }, { - "epoch": 0.71, - "learning_rate": 1.4401372135778666e-05, - "loss": 0.1648, + "epoch": 0.36, + "learning_rate": 3.224088946556005e-05, + "loss": 0.1523, "step": 159840 }, { - "epoch": 0.71, - "learning_rate": 1.4399130083852744e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.223977092235073e-05, + "loss": 0.161, "step": 159850 }, { - "epoch": 0.71, - "learning_rate": 1.439688803192682e-05, - "loss": 0.1646, + "epoch": 0.36, + "learning_rate": 3.223865237914141e-05, + "loss": 0.1582, "step": 159860 }, { - "epoch": 0.71, - "learning_rate": 1.4394645980000898e-05, - "loss": 0.1579, + "epoch": 0.36, + "learning_rate": 3.223753383593208e-05, + "loss": 0.1564, "step": 159870 }, { - "epoch": 0.71, - "learning_rate": 1.4392403928074974e-05, - "loss": 0.1568, + "epoch": 0.36, + "learning_rate": 3.223641529272276e-05, + "loss": 0.1617, "step": 159880 }, { - "epoch": 0.71, - "learning_rate": 1.4390161876149052e-05, - "loss": 0.1588, + "epoch": 0.36, + "learning_rate": 3.2235296749513436e-05, + "loss": 0.1563, "step": 159890 }, { - "epoch": 0.71, - "learning_rate": 1.4387919824223128e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.2234178206304114e-05, + "loss": 0.1582, "step": 159900 }, { - "epoch": 0.71, - "learning_rate": 1.4385677772297207e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.223305966309479e-05, + "loss": 0.1571, "step": 159910 }, { - "epoch": 0.71, - "learning_rate": 1.4383435720371285e-05, - "loss": 0.164, + "epoch": 0.36, + "learning_rate": 3.223194111988546e-05, + "loss": 0.1613, "step": 159920 }, { - "epoch": 0.71, - "learning_rate": 1.438119366844536e-05, - "loss": 0.1646, + "epoch": 0.36, + "learning_rate": 3.223082257667614e-05, + "loss": 0.16, "step": 159930 }, { - "epoch": 0.71, - "learning_rate": 1.437895161651944e-05, - "loss": 0.1658, + "epoch": 0.36, + "learning_rate": 3.222970403346681e-05, + "loss": 0.1593, "step": 159940 }, { - "epoch": 0.71, - "learning_rate": 1.4376709564593516e-05, - "loss": 0.1664, + "epoch": 0.36, + "learning_rate": 3.222858549025749e-05, + "loss": 0.155, "step": 159950 }, { - "epoch": 0.71, - "learning_rate": 1.4374467512667595e-05, - "loss": 0.1611, + "epoch": 0.36, + "learning_rate": 3.222746694704817e-05, + "loss": 0.156, "step": 159960 }, { - "epoch": 0.71, - "learning_rate": 1.437222546074167e-05, - "loss": 0.1603, + "epoch": 0.36, + "learning_rate": 3.222634840383884e-05, + "loss": 0.1533, "step": 159970 }, { - "epoch": 0.71, - "learning_rate": 1.4369983408815749e-05, - "loss": 0.1598, + "epoch": 0.36, + "learning_rate": 3.222522986062952e-05, + "loss": 0.1551, "step": 159980 }, { - "epoch": 0.71, - "learning_rate": 1.4367741356889828e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.222411131742019e-05, + "loss": 0.1637, "step": 159990 }, { - "epoch": 0.71, - "learning_rate": 1.4365499304963903e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.2222992774210866e-05, + "loss": 0.1566, "step": 160000 }, { - "epoch": 0.71, - "eval_NEIMS_canon_smiles": 0.9451666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.08185, - "eval_NEIMS_daylight_tanimoto_simil": 0.4856654689384945, - "eval_NEIMS_exact_mols": 0.08156666666666666, - "eval_NEIMS_exact_smiles": 0.07951666666666667, - "eval_NEIMS_loss": 0.19957083463668823, - "eval_NEIMS_matched_formulas": 0.5902833333333334, - "eval_NEIMS_morgan_tanimoto_simil": 0.39239375453426634, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.08201666666666667, - "eval_NEIMS_runtime": 714.7921, - "eval_NEIMS_samples_per_second": 83.94, - "eval_NEIMS_steps_per_second": 1.312, + "epoch": 0.36, + "eval_NEIMS_canon_smiles": 0.9509, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.10896666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.5152181678176679, + "eval_NEIMS_exact_mols": 0.10868333333333334, + "eval_NEIMS_exact_smiles": 0.10593333333333334, + "eval_NEIMS_loss": 0.182097926735878, + "eval_NEIMS_matched_formulas": 0.6366166666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.4252234049041588, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.1091, + "eval_NEIMS_runtime": 737.7842, + "eval_NEIMS_samples_per_second": 81.325, + "eval_NEIMS_steps_per_second": 1.271, "step": 160000 }, { - "epoch": 0.71, - "eval_RASSP_canon_smiles": 0.938975523424717, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.18973519885130397, - "eval_RASSP_daylight_tanimoto_simil": 0.627314988259476, - "eval_RASSP_exact_mols": 0.18903395999599293, - "eval_RASSP_exact_smiles": 0.1828897719304104, - "eval_RASSP_loss": 0.1380533128976822, - "eval_RASSP_matched_formulas": 0.767706281096604, - "eval_RASSP_morgan_tanimoto_simil": 0.504474684110161, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.1892677062810966, - "eval_RASSP_runtime": 815.587, - "eval_RASSP_samples_per_second": 73.437, - "eval_RASSP_steps_per_second": 1.148, + "epoch": 0.36, + "eval_RASSP_canon_smiles": 0.9464887968744783, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.15595886065382175, + "eval_RASSP_daylight_tanimoto_simil": 0.6065111838627886, + "eval_RASSP_exact_mols": 0.15540788726750593, + "eval_RASSP_exact_smiles": 0.15111697331953117, + "eval_RASSP_loss": 0.14842118322849274, + "eval_RASSP_matched_formulas": 0.7917654522990617, + "eval_RASSP_morgan_tanimoto_simil": 0.4769554675439158, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.15554145657327947, + "eval_RASSP_runtime": 839.0587, + "eval_RASSP_samples_per_second": 71.382, + "eval_RASSP_steps_per_second": 1.116, "step": 160000 }, { - "epoch": 0.71, - "eval_NIST_canon_smiles": 0.8837704510771196, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.013663626361926393, - "eval_NIST_daylight_tanimoto_simil": 0.27592106839424707, - "eval_NIST_exact_mols": 0.0131312772828903, - "eval_NIST_exact_smiles": 0.012066579124818113, - "eval_NIST_loss": 1.8635547161102295, - "eval_NIST_matched_formulas": 0.08971856478688292, - "eval_NIST_morgan_tanimoto_simil": 0.22686512865065844, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.013663626361926393, - "eval_NIST_runtime": 464.2492, - "eval_NIST_samples_per_second": 60.694, - "eval_NIST_steps_per_second": 0.95, + "epoch": 0.36, + "eval_NEIMS_old_canon_smiles": 0.9517666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.1086, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5129941726803703, + "eval_NEIMS_old_exact_mols": 0.10836666666666667, + "eval_NEIMS_old_exact_smiles": 0.10586666666666666, + "eval_NEIMS_old_loss": 0.18200337886810303, + "eval_NEIMS_old_matched_formulas": 0.6340666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.42498359344697073, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.10886666666666667, + "eval_NEIMS_old_runtime": 373.9573, + "eval_NEIMS_old_samples_per_second": 80.223, + "eval_NEIMS_old_steps_per_second": 1.254, "step": 160000 }, { - "epoch": 0.71, - "learning_rate": 1.4363257253037982e-05, - "loss": 0.1618, + "epoch": 0.36, + "eval_RASSP_old_canon_smiles": 0.9431708212366937, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.17722828444622418, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6247385275861159, + "eval_RASSP_old_exact_mols": 0.1769613241232022, + "eval_RASSP_old_exact_smiles": 0.17138852738011812, + "eval_RASSP_old_loss": 0.14052924513816833, + "eval_RASSP_old_matched_formulas": 0.8088564087162545, + "eval_RASSP_old_morgan_tanimoto_simil": 0.499600053328365, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.17719491440584642, + "eval_RASSP_old_runtime": 416.4375, + "eval_RASSP_old_samples_per_second": 71.96, + "eval_RASSP_old_steps_per_second": 1.126, + "step": 160000 + }, + { + "epoch": 0.36, + "eval_NIST_canon_smiles": 0.8644284345388082, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.0194129964155162, + "eval_NIST_daylight_tanimoto_simil": 0.2819906570862649, + "eval_NIST_exact_mols": 0.01849025801185364, + "eval_NIST_exact_smiles": 0.017425559853781452, + "eval_NIST_loss": 1.8024065494537354, + "eval_NIST_matched_formulas": 0.10100436526244809, + "eval_NIST_morgan_tanimoto_simil": 0.23543333058956517, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.019271036661106578, + "eval_NIST_runtime": 516.2165, + "eval_NIST_samples_per_second": 54.584, + "eval_NIST_steps_per_second": 0.854, + "step": 160000 + }, + { + "epoch": 0.36, + "learning_rate": 3.222187423100155e-05, + "loss": 0.158, "step": 160010 }, { - "epoch": 0.71, - "learning_rate": 1.4361015201112057e-05, - "loss": 0.1555, + "epoch": 0.36, + "learning_rate": 3.222075568779222e-05, + "loss": 0.1577, "step": 160020 }, { - "epoch": 0.71, - "learning_rate": 1.4358773149186136e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.22196371445829e-05, + "loss": 0.161, "step": 160030 }, { - "epoch": 0.71, - "learning_rate": 1.4356531097260215e-05, - "loss": 0.1633, + "epoch": 0.36, + "learning_rate": 3.221851860137357e-05, + "loss": 0.1609, "step": 160040 }, { - "epoch": 0.71, - "learning_rate": 1.435428904533429e-05, - "loss": 0.1618, + "epoch": 0.36, + "learning_rate": 3.221740005816425e-05, + "loss": 0.159, "step": 160050 }, { - "epoch": 0.71, - "learning_rate": 1.4352046993408369e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.221628151495493e-05, + "loss": 0.1563, "step": 160060 }, { - "epoch": 0.71, - "learning_rate": 1.4349804941482444e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.22151629717456e-05, + "loss": 0.1529, "step": 160070 }, { - "epoch": 0.71, - "learning_rate": 1.4347562889556523e-05, - "loss": 0.1586, + "epoch": 0.36, + "learning_rate": 3.2214044428536276e-05, + "loss": 0.156, "step": 160080 }, { - "epoch": 0.71, - "learning_rate": 1.43453208376306e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.221292588532695e-05, + "loss": 0.1563, "step": 160090 }, { - "epoch": 0.71, - "learning_rate": 1.4343078785704678e-05, - "loss": 0.1637, + "epoch": 0.36, + "learning_rate": 3.2211807342117625e-05, + "loss": 0.1532, "step": 160100 }, { - "epoch": 0.71, - "learning_rate": 1.4340836733778757e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.22106887989083e-05, + "loss": 0.1592, "step": 160110 }, { - "epoch": 0.71, - "learning_rate": 1.4338594681852832e-05, - "loss": 0.1649, + "epoch": 0.36, + "learning_rate": 3.220957025569898e-05, + "loss": 0.1565, "step": 160120 }, { - "epoch": 0.71, - "learning_rate": 1.4336352629926911e-05, - "loss": 0.1546, + "epoch": 0.36, + "learning_rate": 3.220845171248966e-05, + "loss": 0.1554, "step": 160130 }, { - "epoch": 0.71, - "learning_rate": 1.4334110578000987e-05, - "loss": 0.1662, + "epoch": 0.36, + "learning_rate": 3.220733316928033e-05, + "loss": 0.1534, "step": 160140 }, { - "epoch": 0.71, - "learning_rate": 1.4331868526075065e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.220621462607101e-05, + "loss": 0.1593, "step": 160150 }, { - "epoch": 0.71, - "learning_rate": 1.432962647414914e-05, - "loss": 0.1635, + "epoch": 0.36, + "learning_rate": 3.220509608286168e-05, + "loss": 0.1557, "step": 160160 }, { - "epoch": 0.72, - "learning_rate": 1.432738442222322e-05, - "loss": 0.1629, + "epoch": 0.36, + "learning_rate": 3.220397753965236e-05, + "loss": 0.1545, "step": 160170 }, { - "epoch": 0.72, - "learning_rate": 1.4325142370297298e-05, - "loss": 0.1675, + "epoch": 0.36, + "learning_rate": 3.2202858996443035e-05, + "loss": 0.1567, "step": 160180 }, { - "epoch": 0.72, - "learning_rate": 1.4322900318371373e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.2201740453233706e-05, + "loss": 0.1596, "step": 160190 }, { - "epoch": 0.72, - "learning_rate": 1.4320658266445452e-05, - "loss": 0.159, + "epoch": 0.36, + "learning_rate": 3.2200621910024384e-05, + "loss": 0.1532, "step": 160200 }, { - "epoch": 0.72, - "learning_rate": 1.4318416214519529e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.219950336681506e-05, + "loss": 0.1567, "step": 160210 }, { - "epoch": 0.72, - "learning_rate": 1.4316174162593606e-05, - "loss": 0.16, + "epoch": 0.36, + "learning_rate": 3.219838482360574e-05, + "loss": 0.1625, "step": 160220 }, { - "epoch": 0.72, - "learning_rate": 1.4313932110667683e-05, - "loss": 0.1583, + "epoch": 0.36, + "learning_rate": 3.219726628039642e-05, + "loss": 0.1536, "step": 160230 }, { - "epoch": 0.72, - "learning_rate": 1.4311690058741762e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.219614773718709e-05, + "loss": 0.1541, "step": 160240 }, { - "epoch": 0.72, - "learning_rate": 1.430944800681584e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.219502919397777e-05, + "loss": 0.1542, "step": 160250 }, { - "epoch": 0.72, - "learning_rate": 1.4307205954889916e-05, - "loss": 0.1621, + "epoch": 0.36, + "learning_rate": 3.219391065076844e-05, + "loss": 0.1562, "step": 160260 }, { - "epoch": 0.72, - "learning_rate": 1.4304963902963995e-05, - "loss": 0.1643, + "epoch": 0.36, + "learning_rate": 3.2192792107559116e-05, + "loss": 0.1565, "step": 160270 }, { - "epoch": 0.72, - "learning_rate": 1.430272185103807e-05, - "loss": 0.1671, + "epoch": 0.36, + "learning_rate": 3.2191673564349794e-05, + "loss": 0.1553, "step": 160280 }, { - "epoch": 0.72, - "learning_rate": 1.4300479799112149e-05, - "loss": 0.1551, + "epoch": 0.36, + "learning_rate": 3.2190555021140465e-05, + "loss": 0.1567, "step": 160290 }, { - "epoch": 0.72, - "learning_rate": 1.4298237747186224e-05, - "loss": 0.1607, + "epoch": 0.36, + "learning_rate": 3.218943647793114e-05, + "loss": 0.1529, "step": 160300 }, { - "epoch": 0.72, - "learning_rate": 1.4295995695260303e-05, - "loss": 0.1573, + "epoch": 0.36, + "learning_rate": 3.218831793472182e-05, + "loss": 0.1535, "step": 160310 }, { - "epoch": 0.72, - "learning_rate": 1.4293753643334381e-05, - "loss": 0.1606, + "epoch": 0.36, + "learning_rate": 3.21871993915125e-05, + "loss": 0.1569, "step": 160320 }, { - "epoch": 0.72, - "learning_rate": 1.4291511591408457e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.218608084830318e-05, + "loss": 0.1589, "step": 160330 }, { - "epoch": 0.72, - "learning_rate": 1.4289269539482535e-05, - "loss": 0.1641, + "epoch": 0.36, + "learning_rate": 3.218496230509385e-05, + "loss": 0.1532, "step": 160340 }, { - "epoch": 0.72, - "learning_rate": 1.4287027487556612e-05, - "loss": 0.1664, + "epoch": 0.36, + "learning_rate": 3.2183843761884526e-05, + "loss": 0.16, "step": 160350 }, { - "epoch": 0.72, - "learning_rate": 1.4284785435630691e-05, - "loss": 0.1651, + "epoch": 0.36, + "learning_rate": 3.21827252186752e-05, + "loss": 0.1531, "step": 160360 }, { - "epoch": 0.72, - "learning_rate": 1.4282543383704767e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.2181606675465875e-05, + "loss": 0.1571, "step": 160370 }, { - "epoch": 0.72, - "learning_rate": 1.4280301331778845e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.218048813225655e-05, + "loss": 0.1531, "step": 160380 }, { - "epoch": 0.72, - "learning_rate": 1.4278059279852924e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.2179369589047224e-05, + "loss": 0.1549, "step": 160390 }, { - "epoch": 0.72, - "learning_rate": 1.4275817227927e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.21782510458379e-05, + "loss": 0.1571, "step": 160400 }, { - "epoch": 0.72, - "learning_rate": 1.4273575176001078e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.217713250262857e-05, + "loss": 0.1531, "step": 160410 }, { - "epoch": 0.72, - "learning_rate": 1.4271333124075153e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.217601395941925e-05, + "loss": 0.16, "step": 160420 }, { - "epoch": 0.72, - "learning_rate": 1.4269091072149232e-05, - "loss": 0.1626, + "epoch": 0.36, + "learning_rate": 3.217489541620993e-05, + "loss": 0.1552, "step": 160430 }, { - "epoch": 0.72, - "learning_rate": 1.4266849020223307e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.217377687300061e-05, + "loss": 0.1555, "step": 160440 }, { - "epoch": 0.72, - "learning_rate": 1.4264606968297386e-05, - "loss": 0.1666, + "epoch": 0.36, + "learning_rate": 3.2172658329791285e-05, + "loss": 0.1553, "step": 160450 }, { - "epoch": 0.72, - "learning_rate": 1.4262364916371465e-05, - "loss": 0.163, + "epoch": 0.36, + "learning_rate": 3.2171539786581956e-05, + "loss": 0.1513, "step": 160460 }, { - "epoch": 0.72, - "learning_rate": 1.426012286444554e-05, - "loss": 0.1571, + "epoch": 0.36, + "learning_rate": 3.2170421243372634e-05, + "loss": 0.1608, "step": 160470 }, { - "epoch": 0.72, - "learning_rate": 1.4257880812519619e-05, - "loss": 0.1583, + "epoch": 0.36, + "learning_rate": 3.2169302700163305e-05, + "loss": 0.1574, "step": 160480 }, { - "epoch": 0.72, - "learning_rate": 1.4255638760593696e-05, - "loss": 0.1635, + "epoch": 0.36, + "learning_rate": 3.216818415695398e-05, + "loss": 0.1562, "step": 160490 }, { - "epoch": 0.72, - "learning_rate": 1.4253396708667775e-05, - "loss": 0.1588, + "epoch": 0.36, + "learning_rate": 3.216706561374466e-05, + "loss": 0.1564, "step": 160500 }, { - "epoch": 0.72, - "learning_rate": 1.425115465674185e-05, - "loss": 0.1701, + "epoch": 0.36, + "learning_rate": 3.216594707053533e-05, + "loss": 0.1546, "step": 160510 }, { - "epoch": 0.72, - "learning_rate": 1.4248912604815929e-05, - "loss": 0.1629, + "epoch": 0.36, + "learning_rate": 3.216482852732601e-05, + "loss": 0.1526, "step": 160520 }, { - "epoch": 0.72, - "learning_rate": 1.4246670552890007e-05, - "loss": 0.1621, + "epoch": 0.36, + "learning_rate": 3.216370998411669e-05, + "loss": 0.1519, "step": 160530 }, { - "epoch": 0.72, - "learning_rate": 1.4244428500964083e-05, - "loss": 0.1666, + "epoch": 0.36, + "learning_rate": 3.2162591440907366e-05, + "loss": 0.1625, "step": 160540 }, { - "epoch": 0.72, - "learning_rate": 1.4242186449038161e-05, - "loss": 0.1625, + "epoch": 0.36, + "learning_rate": 3.2161472897698044e-05, + "loss": 0.1584, "step": 160550 }, { - "epoch": 0.72, - "learning_rate": 1.4239944397112237e-05, - "loss": 0.1644, + "epoch": 0.36, + "learning_rate": 3.2160354354488715e-05, + "loss": 0.158, "step": 160560 }, { - "epoch": 0.72, - "learning_rate": 1.4237702345186315e-05, - "loss": 0.1672, + "epoch": 0.36, + "learning_rate": 3.215923581127939e-05, + "loss": 0.1602, "step": 160570 }, { - "epoch": 0.72, - "learning_rate": 1.423546029326039e-05, - "loss": 0.1637, + "epoch": 0.36, + "learning_rate": 3.2158117268070064e-05, + "loss": 0.1544, "step": 160580 }, { - "epoch": 0.72, - "learning_rate": 1.423321824133447e-05, - "loss": 0.1684, + "epoch": 0.36, + "learning_rate": 3.215699872486074e-05, + "loss": 0.1604, "step": 160590 }, { - "epoch": 0.72, - "learning_rate": 1.4230976189408548e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.215588018165142e-05, + "loss": 0.1575, "step": 160600 }, { - "epoch": 0.72, - "learning_rate": 1.4228734137482624e-05, - "loss": 0.1649, + "epoch": 0.36, + "learning_rate": 3.215476163844209e-05, + "loss": 0.1536, "step": 160610 }, { - "epoch": 0.72, - "learning_rate": 1.4226492085556702e-05, - "loss": 0.1573, + "epoch": 0.36, + "learning_rate": 3.215364309523277e-05, + "loss": 0.1593, "step": 160620 }, { - "epoch": 0.72, - "learning_rate": 1.422425003363078e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.215252455202345e-05, + "loss": 0.1554, "step": 160630 }, { - "epoch": 0.72, - "learning_rate": 1.4222007981704858e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.2151406008814125e-05, + "loss": 0.1628, "step": 160640 }, { - "epoch": 0.72, - "learning_rate": 1.4219765929778933e-05, - "loss": 0.1553, + "epoch": 0.36, + "learning_rate": 3.21502874656048e-05, + "loss": 0.1575, "step": 160650 }, { - "epoch": 0.72, - "learning_rate": 1.4217523877853012e-05, - "loss": 0.1596, + "epoch": 0.36, + "learning_rate": 3.2149168922395474e-05, + "loss": 0.1549, "step": 160660 }, { - "epoch": 0.72, - "learning_rate": 1.421528182592709e-05, - "loss": 0.1698, + "epoch": 0.36, + "learning_rate": 3.214805037918615e-05, + "loss": 0.1579, "step": 160670 }, { - "epoch": 0.72, - "learning_rate": 1.4213039774001166e-05, - "loss": 0.1607, + "epoch": 0.36, + "learning_rate": 3.214693183597682e-05, + "loss": 0.158, "step": 160680 }, { - "epoch": 0.72, - "learning_rate": 1.4210797722075245e-05, - "loss": 0.1568, + "epoch": 0.36, + "learning_rate": 3.21458132927675e-05, + "loss": 0.156, "step": 160690 }, { - "epoch": 0.72, - "learning_rate": 1.420855567014932e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.214469474955818e-05, + "loss": 0.1552, "step": 160700 }, { - "epoch": 0.72, - "learning_rate": 1.4206313618223399e-05, - "loss": 0.1675, + "epoch": 0.36, + "learning_rate": 3.214357620634885e-05, + "loss": 0.1517, "step": 160710 }, { - "epoch": 0.72, - "learning_rate": 1.4204071566297474e-05, - "loss": 0.1583, + "epoch": 0.36, + "learning_rate": 3.214245766313953e-05, + "loss": 0.1642, "step": 160720 }, { - "epoch": 0.72, - "learning_rate": 1.4201829514371553e-05, - "loss": 0.1668, + "epoch": 0.36, + "learning_rate": 3.2141339119930206e-05, + "loss": 0.1552, "step": 160730 }, { - "epoch": 0.72, - "learning_rate": 1.4199587462445632e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.2140220576720884e-05, + "loss": 0.1547, "step": 160740 }, { - "epoch": 0.72, - "learning_rate": 1.4197345410519709e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.2139102033511555e-05, + "loss": 0.1526, "step": 160750 }, { - "epoch": 0.72, - "learning_rate": 1.4195103358593786e-05, - "loss": 0.165, + "epoch": 0.36, + "learning_rate": 3.213798349030223e-05, + "loss": 0.1558, "step": 160760 }, { - "epoch": 0.72, - "learning_rate": 1.4192861306667863e-05, - "loss": 0.1669, + "epoch": 0.36, + "learning_rate": 3.213686494709291e-05, + "loss": 0.1574, "step": 160770 }, { - "epoch": 0.72, - "learning_rate": 1.4190619254741941e-05, - "loss": 0.1618, + "epoch": 0.36, + "learning_rate": 3.213574640388358e-05, + "loss": 0.1559, "step": 160780 }, { - "epoch": 0.72, - "learning_rate": 1.4188377202816017e-05, - "loss": 0.1574, + "epoch": 0.36, + "learning_rate": 3.213462786067426e-05, + "loss": 0.1542, "step": 160790 }, { - "epoch": 0.72, - "learning_rate": 1.4186135150890096e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.213350931746493e-05, + "loss": 0.1593, "step": 160800 }, { - "epoch": 0.72, - "learning_rate": 1.4183893098964174e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.213239077425561e-05, + "loss": 0.1574, "step": 160810 }, { - "epoch": 0.72, - "learning_rate": 1.418165104703825e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.213127223104629e-05, + "loss": 0.1603, "step": 160820 }, { - "epoch": 0.72, - "learning_rate": 1.4179408995112328e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.213015368783696e-05, + "loss": 0.1543, "step": 160830 }, { - "epoch": 0.72, - "learning_rate": 1.4177166943186404e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.212903514462764e-05, + "loss": 0.155, "step": 160840 }, { - "epoch": 0.72, - "learning_rate": 1.4174924891260482e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.2127916601418314e-05, + "loss": 0.1565, "step": 160850 }, { - "epoch": 0.72, - "learning_rate": 1.4172682839334558e-05, - "loss": 0.1633, + "epoch": 0.36, + "learning_rate": 3.212679805820899e-05, + "loss": 0.1607, "step": 160860 }, { - "epoch": 0.72, - "learning_rate": 1.4170440787408636e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.212567951499967e-05, + "loss": 0.1615, "step": 160870 }, { - "epoch": 0.72, - "learning_rate": 1.4168198735482715e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.212456097179034e-05, + "loss": 0.1575, "step": 160880 }, { - "epoch": 0.72, - "learning_rate": 1.4165956683556792e-05, - "loss": 0.1647, + "epoch": 0.36, + "learning_rate": 3.212344242858102e-05, + "loss": 0.1545, "step": 160890 }, { - "epoch": 0.72, - "learning_rate": 1.416371463163087e-05, - "loss": 0.1621, + "epoch": 0.36, + "learning_rate": 3.212243573969263e-05, + "loss": 0.158, "step": 160900 }, { - "epoch": 0.72, - "learning_rate": 1.4161472579704946e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.2121317196483306e-05, + "loss": 0.1512, "step": 160910 }, { - "epoch": 0.72, - "learning_rate": 1.4159230527779025e-05, - "loss": 0.1632, + "epoch": 0.36, + "learning_rate": 3.212019865327398e-05, + "loss": 0.1536, "step": 160920 }, { - "epoch": 0.72, - "learning_rate": 1.41569884758531e-05, - "loss": 0.1656, + "epoch": 0.36, + "learning_rate": 3.2119080110064655e-05, + "loss": 0.1558, "step": 160930 }, { - "epoch": 0.72, - "learning_rate": 1.4154746423927179e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.211796156685533e-05, + "loss": 0.1597, "step": 160940 }, { - "epoch": 0.72, - "learning_rate": 1.4152504372001258e-05, - "loss": 0.1595, + "epoch": 0.36, + "learning_rate": 3.2116843023646004e-05, + "loss": 0.1575, "step": 160950 }, { - "epoch": 0.72, - "learning_rate": 1.4150262320075333e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.211572448043668e-05, + "loss": 0.1576, "step": 160960 }, { - "epoch": 0.72, - "learning_rate": 1.4148020268149412e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.211460593722735e-05, + "loss": 0.1561, "step": 160970 }, { - "epoch": 0.72, - "learning_rate": 1.4145778216223487e-05, - "loss": 0.1656, + "epoch": 0.36, + "learning_rate": 3.211348739401803e-05, + "loss": 0.1544, "step": 160980 }, { - "epoch": 0.72, - "learning_rate": 1.4143536164297566e-05, - "loss": 0.1595, + "epoch": 0.36, + "learning_rate": 3.211236885080871e-05, + "loss": 0.1556, "step": 160990 }, { - "epoch": 0.72, - "learning_rate": 1.4141294112371643e-05, - "loss": 0.1548, + "epoch": 0.36, + "learning_rate": 3.211125030759938e-05, + "loss": 0.1504, "step": 161000 }, { - "epoch": 0.72, - "learning_rate": 1.413905206044572e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.2110131764390064e-05, + "loss": 0.1546, "step": 161010 }, { - "epoch": 0.72, - "learning_rate": 1.4136810008519798e-05, - "loss": 0.1624, + "epoch": 0.36, + "learning_rate": 3.2109013221180736e-05, + "loss": 0.1611, "step": 161020 }, { - "epoch": 0.72, - "learning_rate": 1.4134567956593876e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.2107894677971414e-05, + "loss": 0.1553, "step": 161030 }, { - "epoch": 0.72, - "learning_rate": 1.4132325904667954e-05, - "loss": 0.1632, + "epoch": 0.36, + "learning_rate": 3.210677613476209e-05, + "loss": 0.1539, "step": 161040 }, { - "epoch": 0.72, - "learning_rate": 1.413008385274203e-05, - "loss": 0.159, + "epoch": 0.36, + "learning_rate": 3.210565759155276e-05, + "loss": 0.1544, "step": 161050 }, { - "epoch": 0.72, - "learning_rate": 1.4127841800816108e-05, - "loss": 0.1673, + "epoch": 0.36, + "learning_rate": 3.210453904834344e-05, + "loss": 0.1551, "step": 161060 }, { - "epoch": 0.72, - "learning_rate": 1.4125599748890184e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.210342050513411e-05, + "loss": 0.1576, "step": 161070 }, { - "epoch": 0.72, - "learning_rate": 1.4123357696964262e-05, - "loss": 0.1573, + "epoch": 0.36, + "learning_rate": 3.210230196192479e-05, + "loss": 0.158, "step": 161080 }, { - "epoch": 0.72, - "learning_rate": 1.4121115645038341e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.210118341871547e-05, + "loss": 0.1592, "step": 161090 }, { - "epoch": 0.72, - "learning_rate": 1.4118873593112416e-05, - "loss": 0.1582, + "epoch": 0.36, + "learning_rate": 3.210006487550614e-05, + "loss": 0.158, "step": 161100 }, { - "epoch": 0.72, - "learning_rate": 1.4116631541186495e-05, - "loss": 0.166, + "epoch": 0.36, + "learning_rate": 3.209894633229682e-05, + "loss": 0.1539, "step": 161110 }, { - "epoch": 0.72, - "learning_rate": 1.411438948926057e-05, - "loss": 0.1655, + "epoch": 0.36, + "learning_rate": 3.2097827789087495e-05, + "loss": 0.1564, "step": 161120 }, { - "epoch": 0.72, - "learning_rate": 1.4112147437334649e-05, - "loss": 0.1611, + "epoch": 0.36, + "learning_rate": 3.209670924587817e-05, + "loss": 0.1577, "step": 161130 }, { - "epoch": 0.72, - "learning_rate": 1.4109905385408726e-05, - "loss": 0.1633, + "epoch": 0.36, + "learning_rate": 3.2095590702668844e-05, + "loss": 0.1567, "step": 161140 }, { - "epoch": 0.72, - "learning_rate": 1.4107663333482803e-05, - "loss": 0.1651, + "epoch": 0.36, + "learning_rate": 3.209447215945952e-05, + "loss": 0.1577, "step": 161150 }, { - "epoch": 0.72, - "learning_rate": 1.4105421281556882e-05, - "loss": 0.1621, + "epoch": 0.36, + "learning_rate": 3.20933536162502e-05, + "loss": 0.1507, "step": 161160 }, { - "epoch": 0.72, - "learning_rate": 1.4103179229630959e-05, - "loss": 0.1644, + "epoch": 0.36, + "learning_rate": 3.209223507304087e-05, + "loss": 0.1577, "step": 161170 }, { - "epoch": 0.72, - "learning_rate": 1.4100937177705038e-05, - "loss": 0.1655, + "epoch": 0.36, + "learning_rate": 3.209111652983155e-05, + "loss": 0.1546, "step": 161180 }, { - "epoch": 0.72, - "learning_rate": 1.4098695125779113e-05, - "loss": 0.1624, + "epoch": 0.36, + "learning_rate": 3.208999798662222e-05, + "loss": 0.1583, "step": 161190 }, { - "epoch": 0.72, - "learning_rate": 1.4096453073853192e-05, - "loss": 0.1644, + "epoch": 0.36, + "learning_rate": 3.20888794434129e-05, + "loss": 0.1541, "step": 161200 }, { - "epoch": 0.72, - "learning_rate": 1.4094211021927267e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.2087760900203576e-05, + "loss": 0.1585, "step": 161210 }, { - "epoch": 0.72, - "learning_rate": 1.4091968970001346e-05, - "loss": 0.1644, + "epoch": 0.36, + "learning_rate": 3.2086642356994254e-05, + "loss": 0.154, "step": 161220 }, { - "epoch": 0.72, - "learning_rate": 1.4089726918075424e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.208552381378493e-05, + "loss": 0.1527, "step": 161230 }, { - "epoch": 0.72, - "learning_rate": 1.40874848661495e-05, - "loss": 0.1609, + "epoch": 0.36, + "learning_rate": 3.20844052705756e-05, + "loss": 0.1573, "step": 161240 }, { - "epoch": 0.72, - "learning_rate": 1.4085242814223579e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.208328672736628e-05, + "loss": 0.1567, "step": 161250 }, { - "epoch": 0.72, - "learning_rate": 1.4083000762297654e-05, - "loss": 0.1609, + "epoch": 0.36, + "learning_rate": 3.208216818415696e-05, + "loss": 0.1544, "step": 161260 }, { - "epoch": 0.72, - "learning_rate": 1.4080758710371733e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.208104964094763e-05, + "loss": 0.1573, "step": 161270 }, { - "epoch": 0.72, - "learning_rate": 1.407851665844581e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.207993109773831e-05, + "loss": 0.1579, "step": 161280 }, { - "epoch": 0.72, - "learning_rate": 1.4076274606519888e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.207881255452898e-05, + "loss": 0.1543, "step": 161290 }, { - "epoch": 0.72, - "learning_rate": 1.4074032554593965e-05, - "loss": 0.1521, + "epoch": 0.36, + "learning_rate": 3.2077694011319657e-05, + "loss": 0.1532, "step": 161300 }, { - "epoch": 0.72, - "learning_rate": 1.4071790502668042e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.2076575468110335e-05, + "loss": 0.1576, "step": 161310 }, { - "epoch": 0.72, - "learning_rate": 1.4069548450742121e-05, - "loss": 0.1595, + "epoch": 0.36, + "learning_rate": 3.207545692490101e-05, + "loss": 0.1581, "step": 161320 }, { - "epoch": 0.72, - "learning_rate": 1.4067306398816196e-05, - "loss": 0.1607, + "epoch": 0.36, + "learning_rate": 3.207433838169169e-05, + "loss": 0.1612, "step": 161330 }, { - "epoch": 0.72, - "learning_rate": 1.4065064346890275e-05, - "loss": 0.1588, + "epoch": 0.36, + "learning_rate": 3.207321983848236e-05, + "loss": 0.1572, "step": 161340 }, { - "epoch": 0.72, - "learning_rate": 1.406282229496435e-05, - "loss": 0.1596, + "epoch": 0.36, + "learning_rate": 3.207210129527304e-05, + "loss": 0.1543, "step": 161350 }, { - "epoch": 0.72, - "learning_rate": 1.406058024303843e-05, - "loss": 0.1631, + "epoch": 0.36, + "learning_rate": 3.207098275206372e-05, + "loss": 0.1544, "step": 161360 }, { - "epoch": 0.72, - "learning_rate": 1.4058338191112508e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.206986420885439e-05, + "loss": 0.1573, "step": 161370 }, { - "epoch": 0.72, - "learning_rate": 1.4056096139186583e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.2068745665645066e-05, + "loss": 0.1593, "step": 161380 }, { - "epoch": 0.72, - "learning_rate": 1.4053854087260662e-05, - "loss": 0.1536, + "epoch": 0.36, + "learning_rate": 3.206762712243574e-05, + "loss": 0.1521, "step": 161390 }, { - "epoch": 0.72, - "learning_rate": 1.4051612035334737e-05, - "loss": 0.1579, + "epoch": 0.36, + "learning_rate": 3.2066508579226416e-05, + "loss": 0.1587, "step": 161400 }, { - "epoch": 0.72, - "learning_rate": 1.4049369983408816e-05, - "loss": 0.1592, + "epoch": 0.36, + "learning_rate": 3.2065390036017093e-05, + "loss": 0.1577, "step": 161410 }, { - "epoch": 0.72, - "learning_rate": 1.4047127931482895e-05, - "loss": 0.1555, + "epoch": 0.36, + "learning_rate": 3.206427149280777e-05, + "loss": 0.1518, "step": 161420 }, { - "epoch": 0.72, - "learning_rate": 1.4044885879556972e-05, - "loss": 0.1686, + "epoch": 0.36, + "learning_rate": 3.206315294959845e-05, + "loss": 0.1599, "step": 161430 }, { - "epoch": 0.72, - "learning_rate": 1.4042643827631049e-05, - "loss": 0.1662, + "epoch": 0.36, + "learning_rate": 3.206203440638912e-05, + "loss": 0.1537, "step": 161440 }, { - "epoch": 0.72, - "learning_rate": 1.4040401775705126e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.20609158631798e-05, + "loss": 0.1609, "step": 161450 }, { - "epoch": 0.72, - "learning_rate": 1.4038159723779204e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.205979731997047e-05, + "loss": 0.1569, "step": 161460 }, { - "epoch": 0.72, - "learning_rate": 1.403591767185328e-05, - "loss": 0.1675, + "epoch": 0.36, + "learning_rate": 3.205867877676115e-05, + "loss": 0.1582, "step": 161470 }, { - "epoch": 0.72, - "learning_rate": 1.4033675619927359e-05, - "loss": 0.1564, + "epoch": 0.36, + "learning_rate": 3.2057560233551825e-05, + "loss": 0.1595, "step": 161480 }, { - "epoch": 0.72, - "learning_rate": 1.4031433568001437e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.2056441690342497e-05, + "loss": 0.1544, "step": 161490 }, { - "epoch": 0.72, - "learning_rate": 1.4029191516075513e-05, - "loss": 0.1606, + "epoch": 0.36, + "learning_rate": 3.2055323147133175e-05, + "loss": 0.1564, "step": 161500 }, { - "epoch": 0.72, - "learning_rate": 1.4026949464149591e-05, - "loss": 0.1662, + "epoch": 0.36, + "learning_rate": 3.2054204603923846e-05, + "loss": 0.1514, "step": 161510 }, { - "epoch": 0.72, - "learning_rate": 1.4024707412223667e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.2053086060714524e-05, + "loss": 0.1546, "step": 161520 }, { - "epoch": 0.72, - "learning_rate": 1.4022465360297745e-05, - "loss": 0.1631, + "epoch": 0.36, + "learning_rate": 3.20519675175052e-05, + "loss": 0.1617, "step": 161530 }, { - "epoch": 0.72, - "learning_rate": 1.4020223308371822e-05, - "loss": 0.166, + "epoch": 0.36, + "learning_rate": 3.205084897429588e-05, + "loss": 0.158, "step": 161540 }, { - "epoch": 0.72, - "learning_rate": 1.40179812564459e-05, - "loss": 0.1639, + "epoch": 0.36, + "learning_rate": 3.204973043108656e-05, + "loss": 0.156, "step": 161550 }, { - "epoch": 0.72, - "learning_rate": 1.4015739204519978e-05, - "loss": 0.1587, + "epoch": 0.36, + "learning_rate": 3.204861188787723e-05, + "loss": 0.1532, "step": 161560 }, { - "epoch": 0.72, - "learning_rate": 1.4013497152594055e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.2047493344667906e-05, + "loss": 0.1579, "step": 161570 }, { - "epoch": 0.72, - "learning_rate": 1.4011255100668134e-05, - "loss": 0.1604, + "epoch": 0.36, + "learning_rate": 3.2046374801458584e-05, + "loss": 0.1594, "step": 161580 }, { - "epoch": 0.72, - "learning_rate": 1.400901304874221e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.2045256258249256e-05, + "loss": 0.1558, "step": 161590 }, { - "epoch": 0.72, - "learning_rate": 1.4006770996816288e-05, - "loss": 0.163, + "epoch": 0.36, + "learning_rate": 3.2044137715039933e-05, + "loss": 0.155, "step": 161600 }, { - "epoch": 0.72, - "learning_rate": 1.4004528944890363e-05, - "loss": 0.1655, + "epoch": 0.36, + "learning_rate": 3.2043019171830605e-05, + "loss": 0.1577, "step": 161610 }, { - "epoch": 0.72, - "learning_rate": 1.4002286892964442e-05, - "loss": 0.165, + "epoch": 0.36, + "learning_rate": 3.204190062862128e-05, + "loss": 0.1555, "step": 161620 }, { - "epoch": 0.72, - "learning_rate": 1.400004484103852e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.204078208541196e-05, + "loss": 0.1609, "step": 161630 }, { - "epoch": 0.72, - "learning_rate": 1.3997802789112596e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.203966354220264e-05, + "loss": 0.1582, "step": 161640 }, { - "epoch": 0.72, - "learning_rate": 1.3995560737186675e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.2038544998993316e-05, + "loss": 0.1569, "step": 161650 }, { - "epoch": 0.72, - "learning_rate": 1.399331868526075e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.203742645578399e-05, + "loss": 0.1535, "step": 161660 }, { - "epoch": 0.72, - "learning_rate": 1.3991076633334829e-05, - "loss": 0.1592, + "epoch": 0.36, + "learning_rate": 3.2036307912574665e-05, + "loss": 0.1604, "step": 161670 }, { - "epoch": 0.72, - "learning_rate": 1.3988834581408906e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.203518936936534e-05, + "loss": 0.155, "step": 161680 }, { - "epoch": 0.72, - "learning_rate": 1.3986592529482983e-05, - "loss": 0.1628, + "epoch": 0.36, + "learning_rate": 3.2034070826156014e-05, + "loss": 0.1554, "step": 161690 }, { - "epoch": 0.72, - "learning_rate": 1.3984350477557062e-05, - "loss": 0.1592, + "epoch": 0.36, + "learning_rate": 3.203295228294669e-05, + "loss": 0.1552, "step": 161700 }, { - "epoch": 0.72, - "learning_rate": 1.3982108425631139e-05, - "loss": 0.1647, + "epoch": 0.36, + "learning_rate": 3.2031833739737364e-05, + "loss": 0.152, "step": 161710 }, { - "epoch": 0.72, - "learning_rate": 1.3979866373705217e-05, - "loss": 0.1556, + "epoch": 0.36, + "learning_rate": 3.203071519652804e-05, + "loss": 0.1563, "step": 161720 }, { - "epoch": 0.72, - "learning_rate": 1.3977624321779293e-05, - "loss": 0.1592, + "epoch": 0.36, + "learning_rate": 3.202959665331872e-05, + "loss": 0.1605, "step": 161730 }, { - "epoch": 0.72, - "learning_rate": 1.3975382269853371e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.20284781101094e-05, + "loss": 0.1528, "step": 161740 }, { - "epoch": 0.72, - "learning_rate": 1.3973140217927447e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.2027359566900075e-05, + "loss": 0.1588, "step": 161750 }, { - "epoch": 0.72, - "learning_rate": 1.3970898166001525e-05, - "loss": 0.1626, + "epoch": 0.36, + "learning_rate": 3.2026241023690746e-05, + "loss": 0.1577, "step": 161760 }, { - "epoch": 0.72, - "learning_rate": 1.3968656114075604e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.2025122480481424e-05, + "loss": 0.1568, "step": 161770 }, { - "epoch": 0.72, - "learning_rate": 1.396641406214968e-05, - "loss": 0.1616, + "epoch": 0.36, + "learning_rate": 3.2024003937272095e-05, + "loss": 0.157, "step": 161780 }, { - "epoch": 0.72, - "learning_rate": 1.3964172010223758e-05, - "loss": 0.1667, + "epoch": 0.36, + "learning_rate": 3.2022885394062773e-05, + "loss": 0.1553, "step": 161790 }, { - "epoch": 0.72, - "learning_rate": 1.3961929958297833e-05, - "loss": 0.1598, + "epoch": 0.36, + "learning_rate": 3.202176685085345e-05, + "loss": 0.1545, "step": 161800 }, { - "epoch": 0.72, - "learning_rate": 1.3959687906371912e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.202064830764412e-05, + "loss": 0.1583, "step": 161810 }, { - "epoch": 0.72, - "learning_rate": 1.395744585444599e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.20195297644348e-05, + "loss": 0.1597, "step": 161820 }, { - "epoch": 0.72, - "learning_rate": 1.3955203802520068e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.201841122122548e-05, + "loss": 0.1584, "step": 161830 }, { - "epoch": 0.72, - "learning_rate": 1.3952961750594145e-05, - "loss": 0.1553, + "epoch": 0.36, + "learning_rate": 3.2017292678016156e-05, + "loss": 0.158, "step": 161840 }, { - "epoch": 0.72, - "learning_rate": 1.3950719698668222e-05, - "loss": 0.1581, + "epoch": 0.36, + "learning_rate": 3.2016174134806834e-05, + "loss": 0.1537, "step": 161850 }, { - "epoch": 0.72, - "learning_rate": 1.39484776467423e-05, - "loss": 0.1565, + "epoch": 0.36, + "learning_rate": 3.2015055591597505e-05, + "loss": 0.1548, "step": 161860 }, { - "epoch": 0.72, - "learning_rate": 1.3946235594816376e-05, - "loss": 0.1693, + "epoch": 0.36, + "learning_rate": 3.201393704838818e-05, + "loss": 0.1606, "step": 161870 }, { - "epoch": 0.72, - "learning_rate": 1.3944217748083047e-05, - "loss": 0.17, + "epoch": 0.36, + "learning_rate": 3.2012818505178854e-05, + "loss": 0.1589, "step": 161880 }, { - "epoch": 0.72, - "learning_rate": 1.3941975696157123e-05, - "loss": 0.1648, + "epoch": 0.36, + "learning_rate": 3.201169996196953e-05, + "loss": 0.1573, "step": 161890 }, { - "epoch": 0.72, - "learning_rate": 1.3939733644231201e-05, - "loss": 0.155, + "epoch": 0.36, + "learning_rate": 3.201058141876021e-05, + "loss": 0.1603, "step": 161900 }, { - "epoch": 0.72, - "learning_rate": 1.393749159230528e-05, - "loss": 0.1604, + "epoch": 0.36, + "learning_rate": 3.200946287555088e-05, + "loss": 0.1507, "step": 161910 }, { - "epoch": 0.72, - "learning_rate": 1.3935249540379355e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.200834433234156e-05, + "loss": 0.1556, "step": 161920 }, { - "epoch": 0.72, - "learning_rate": 1.3933007488453434e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.200722578913223e-05, + "loss": 0.1576, "step": 161930 }, { - "epoch": 0.72, - "learning_rate": 1.393076543652751e-05, - "loss": 0.1623, + "epoch": 0.36, + "learning_rate": 3.200610724592291e-05, + "loss": 0.1561, "step": 161940 }, { - "epoch": 0.72, - "learning_rate": 1.3928523384601588e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.2004988702713586e-05, + "loss": 0.1576, "step": 161950 }, { - "epoch": 0.72, - "learning_rate": 1.3926281332675663e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.2003870159504264e-05, + "loss": 0.1558, "step": 161960 }, { - "epoch": 0.72, - "learning_rate": 1.3924039280749742e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.200275161629494e-05, + "loss": 0.1547, "step": 161970 }, { - "epoch": 0.72, - "learning_rate": 1.392179722882382e-05, - "loss": 0.1619, + "epoch": 0.36, + "learning_rate": 3.200163307308561e-05, + "loss": 0.1469, "step": 161980 }, { - "epoch": 0.72, - "learning_rate": 1.3919555176897898e-05, - "loss": 0.1604, + "epoch": 0.36, + "learning_rate": 3.200051452987629e-05, + "loss": 0.1581, "step": 161990 }, { - "epoch": 0.72, - "learning_rate": 1.3917313124971975e-05, - "loss": 0.1583, + "epoch": 0.36, + "learning_rate": 3.199939598666697e-05, + "loss": 0.1641, "step": 162000 }, { - "epoch": 0.72, - "learning_rate": 1.3915071073046052e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.199827744345764e-05, + "loss": 0.1597, "step": 162010 }, { - "epoch": 0.72, - "learning_rate": 1.391282902112013e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.199715890024832e-05, + "loss": 0.1559, "step": 162020 }, { - "epoch": 0.72, - "learning_rate": 1.3910586969194206e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.199604035703899e-05, + "loss": 0.1562, "step": 162030 }, { - "epoch": 0.72, - "learning_rate": 1.3908344917268285e-05, - "loss": 0.1568, + "epoch": 0.36, + "learning_rate": 3.199492181382967e-05, + "loss": 0.1579, "step": 162040 }, { - "epoch": 0.72, - "learning_rate": 1.3906102865342363e-05, - "loss": 0.1595, + "epoch": 0.36, + "learning_rate": 3.1993803270620345e-05, + "loss": 0.1533, "step": 162050 }, { - "epoch": 0.72, - "learning_rate": 1.3903860813416439e-05, - "loss": 0.1584, + "epoch": 0.36, + "learning_rate": 3.199268472741102e-05, + "loss": 0.1598, "step": 162060 }, { - "epoch": 0.72, - "learning_rate": 1.3901618761490517e-05, - "loss": 0.1593, + "epoch": 0.36, + "learning_rate": 3.19915661842017e-05, + "loss": 0.1561, "step": 162070 }, { - "epoch": 0.72, - "learning_rate": 1.3899376709564593e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.199044764099237e-05, + "loss": 0.1641, "step": 162080 }, { - "epoch": 0.72, - "learning_rate": 1.3897134657638671e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.198932909778305e-05, + "loss": 0.1615, "step": 162090 }, { - "epoch": 0.72, - "learning_rate": 1.3894892605712748e-05, - "loss": 0.1574, + "epoch": 0.36, + "learning_rate": 3.198821055457372e-05, + "loss": 0.1556, "step": 162100 }, { - "epoch": 0.72, - "learning_rate": 1.3892650553786826e-05, - "loss": 0.1596, + "epoch": 0.36, + "learning_rate": 3.19870920113644e-05, + "loss": 0.15, "step": 162110 }, { - "epoch": 0.72, - "learning_rate": 1.3890408501860904e-05, - "loss": 0.1596, + "epoch": 0.36, + "learning_rate": 3.198597346815508e-05, + "loss": 0.1491, "step": 162120 }, { - "epoch": 0.72, - "learning_rate": 1.3888166449934981e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.198485492494575e-05, + "loss": 0.1565, "step": 162130 }, { - "epoch": 0.72, - "learning_rate": 1.388592439800906e-05, - "loss": 0.1595, + "epoch": 0.36, + "learning_rate": 3.1983736381736426e-05, + "loss": 0.1527, "step": 162140 }, { - "epoch": 0.72, - "learning_rate": 1.3883682346083135e-05, - "loss": 0.1572, + "epoch": 0.36, + "learning_rate": 3.1982617838527104e-05, + "loss": 0.1516, "step": 162150 }, { - "epoch": 0.72, - "learning_rate": 1.3881440294157214e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.198149929531778e-05, + "loss": 0.1534, "step": 162160 }, { - "epoch": 0.72, - "learning_rate": 1.387919824223129e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.198038075210846e-05, + "loss": 0.1583, "step": 162170 }, { - "epoch": 0.72, - "learning_rate": 1.3876956190305368e-05, - "loss": 0.1665, + "epoch": 0.36, + "learning_rate": 3.197926220889913e-05, + "loss": 0.1528, "step": 162180 }, { - "epoch": 0.72, - "learning_rate": 1.3874714138379447e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.197814366568981e-05, + "loss": 0.1561, "step": 162190 }, { - "epoch": 0.72, - "learning_rate": 1.3872472086453522e-05, - "loss": 0.1574, + "epoch": 0.36, + "learning_rate": 3.197702512248048e-05, + "loss": 0.1486, "step": 162200 }, { - "epoch": 0.72, - "learning_rate": 1.38702300345276e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.197590657927116e-05, + "loss": 0.1528, "step": 162210 }, { - "epoch": 0.72, - "learning_rate": 1.3867987982601676e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.1974788036061836e-05, + "loss": 0.155, "step": 162220 }, { - "epoch": 0.72, - "learning_rate": 1.3865745930675755e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.197366949285251e-05, + "loss": 0.1558, "step": 162230 }, { - "epoch": 0.72, - "learning_rate": 1.3863503878749832e-05, - "loss": 0.158, + "epoch": 0.36, + "learning_rate": 3.1972550949643185e-05, + "loss": 0.1509, "step": 162240 }, { - "epoch": 0.72, - "learning_rate": 1.3861261826823909e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.197143240643386e-05, + "loss": 0.1568, "step": 162250 }, { - "epoch": 0.72, - "learning_rate": 1.3859019774897988e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.197031386322454e-05, + "loss": 0.1546, "step": 162260 }, { - "epoch": 0.72, - "learning_rate": 1.3856777722972065e-05, - "loss": 0.1505, + "epoch": 0.36, + "learning_rate": 3.196919532001522e-05, + "loss": 0.158, "step": 162270 }, { - "epoch": 0.72, - "learning_rate": 1.3854535671046143e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.196807677680589e-05, + "loss": 0.1569, "step": 162280 }, { - "epoch": 0.72, - "learning_rate": 1.3852293619120219e-05, - "loss": 0.157, + "epoch": 0.36, + "learning_rate": 3.196695823359657e-05, + "loss": 0.1549, "step": 162290 }, { - "epoch": 0.72, - "learning_rate": 1.3850051567194297e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.196583969038724e-05, + "loss": 0.1583, "step": 162300 }, { - "epoch": 0.72, - "learning_rate": 1.3847809515268376e-05, - "loss": 0.1567, + "epoch": 0.36, + "learning_rate": 3.196472114717792e-05, + "loss": 0.1576, "step": 162310 }, { - "epoch": 0.72, - "learning_rate": 1.3845567463342451e-05, - "loss": 0.1572, + "epoch": 0.36, + "learning_rate": 3.1963602603968595e-05, + "loss": 0.1535, "step": 162320 }, { - "epoch": 0.72, - "learning_rate": 1.384332541141653e-05, - "loss": 0.1576, + "epoch": 0.36, + "learning_rate": 3.1962484060759266e-05, + "loss": 0.1543, "step": 162330 }, { - "epoch": 0.72, - "learning_rate": 1.3841083359490606e-05, - "loss": 0.1671, + "epoch": 0.36, + "learning_rate": 3.1961365517549944e-05, + "loss": 0.1583, "step": 162340 }, { - "epoch": 0.72, - "learning_rate": 1.3838841307564684e-05, - "loss": 0.1609, + "epoch": 0.36, + "learning_rate": 3.1960246974340615e-05, + "loss": 0.1559, "step": 162350 }, { - "epoch": 0.72, - "learning_rate": 1.383659925563876e-05, - "loss": 0.1598, + "epoch": 0.36, + "learning_rate": 3.195912843113129e-05, + "loss": 0.1518, "step": 162360 }, { - "epoch": 0.72, - "learning_rate": 1.3834357203712838e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.195800988792198e-05, + "loss": 0.1608, "step": 162370 }, { - "epoch": 0.72, - "learning_rate": 1.3832115151786917e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.195689134471265e-05, + "loss": 0.1529, "step": 162380 }, { - "epoch": 0.72, - "learning_rate": 1.3829873099860994e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.195577280150333e-05, + "loss": 0.1602, "step": 162390 }, { - "epoch": 0.72, - "learning_rate": 1.3827631047935071e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.1954654258294e-05, + "loss": 0.1591, "step": 162400 }, { - "epoch": 0.73, - "learning_rate": 1.3825388996009148e-05, - "loss": 0.1539, + "epoch": 0.36, + "learning_rate": 3.1953535715084676e-05, + "loss": 0.1569, "step": 162410 }, { - "epoch": 0.73, - "learning_rate": 1.3823146944083227e-05, - "loss": 0.165, + "epoch": 0.36, + "learning_rate": 3.195241717187535e-05, + "loss": 0.1573, "step": 162420 }, { - "epoch": 0.73, - "learning_rate": 1.3820904892157302e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.1951298628666025e-05, + "loss": 0.1595, "step": 162430 }, { - "epoch": 0.73, - "learning_rate": 1.381866284023138e-05, - "loss": 0.1676, + "epoch": 0.36, + "learning_rate": 3.19501800854567e-05, + "loss": 0.1605, "step": 162440 }, { - "epoch": 0.73, - "learning_rate": 1.381642078830546e-05, - "loss": 0.1646, + "epoch": 0.36, + "learning_rate": 3.1949061542247374e-05, + "loss": 0.1554, "step": 162450 }, { - "epoch": 0.73, - "learning_rate": 1.3814178736379535e-05, - "loss": 0.1656, + "epoch": 0.36, + "learning_rate": 3.194794299903805e-05, + "loss": 0.1578, "step": 162460 }, { - "epoch": 0.73, - "learning_rate": 1.3811936684453614e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.194682445582873e-05, + "loss": 0.1566, "step": 162470 }, { - "epoch": 0.73, - "learning_rate": 1.3809694632527689e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.194570591261941e-05, + "loss": 0.1578, "step": 162480 }, { - "epoch": 0.73, - "learning_rate": 1.3807452580601768e-05, - "loss": 0.1614, + "epoch": 0.36, + "learning_rate": 3.1944587369410086e-05, + "loss": 0.1536, "step": 162490 }, { - "epoch": 0.73, - "learning_rate": 1.3805210528675843e-05, - "loss": 0.1639, + "epoch": 0.36, + "learning_rate": 3.194346882620076e-05, + "loss": 0.1564, "step": 162500 }, { - "epoch": 0.73, - "learning_rate": 1.3802968476749922e-05, - "loss": 0.1591, + "epoch": 0.36, + "learning_rate": 3.1942350282991435e-05, + "loss": 0.155, "step": 162510 }, { - "epoch": 0.73, - "learning_rate": 1.3800726424824e-05, - "loss": 0.1633, + "epoch": 0.36, + "learning_rate": 3.1941231739782106e-05, + "loss": 0.1654, "step": 162520 }, { - "epoch": 0.73, - "learning_rate": 1.3798484372898077e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.1940113196572784e-05, + "loss": 0.1533, "step": 162530 }, { - "epoch": 0.73, - "learning_rate": 1.3796242320972154e-05, - "loss": 0.163, + "epoch": 0.36, + "learning_rate": 3.193899465336346e-05, + "loss": 0.1528, "step": 162540 }, { - "epoch": 0.73, - "learning_rate": 1.3794000269046231e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.193787611015413e-05, + "loss": 0.159, "step": 162550 }, { - "epoch": 0.73, - "learning_rate": 1.379175821712031e-05, - "loss": 0.1606, + "epoch": 0.36, + "learning_rate": 3.193675756694481e-05, + "loss": 0.1531, "step": 162560 }, { - "epoch": 0.73, - "learning_rate": 1.3789516165194386e-05, - "loss": 0.1587, + "epoch": 0.36, + "learning_rate": 3.193563902373549e-05, + "loss": 0.1561, "step": 162570 }, { - "epoch": 0.73, - "learning_rate": 1.3787274113268464e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.193452048052617e-05, + "loss": 0.1556, "step": 162580 }, { - "epoch": 0.73, - "learning_rate": 1.3785032061342543e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.1933401937316845e-05, + "loss": 0.1568, "step": 162590 }, { - "epoch": 0.73, - "learning_rate": 1.3782790009416618e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.1932283394107516e-05, + "loss": 0.1522, "step": 162600 }, { - "epoch": 0.73, - "learning_rate": 1.3780547957490697e-05, - "loss": 0.1637, + "epoch": 0.36, + "learning_rate": 3.1931164850898194e-05, + "loss": 0.1599, "step": 162610 }, { - "epoch": 0.73, - "learning_rate": 1.3778305905564772e-05, - "loss": 0.1647, + "epoch": 0.36, + "learning_rate": 3.1930046307688865e-05, + "loss": 0.1547, "step": 162620 }, { - "epoch": 0.73, - "learning_rate": 1.3776063853638851e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.192892776447954e-05, + "loss": 0.1543, "step": 162630 }, { - "epoch": 0.73, - "learning_rate": 1.3773821801712928e-05, - "loss": 0.1558, + "epoch": 0.36, + "learning_rate": 3.192780922127022e-05, + "loss": 0.1607, "step": 162640 }, { - "epoch": 0.73, - "learning_rate": 1.3771579749787005e-05, - "loss": 0.1569, + "epoch": 0.36, + "learning_rate": 3.192669067806089e-05, + "loss": 0.1572, "step": 162650 }, { - "epoch": 0.73, - "learning_rate": 1.3769337697861084e-05, - "loss": 0.1592, + "epoch": 0.36, + "learning_rate": 3.192557213485157e-05, + "loss": 0.1594, "step": 162660 }, { - "epoch": 0.73, - "learning_rate": 1.3767095645935161e-05, - "loss": 0.1588, + "epoch": 0.36, + "learning_rate": 3.192445359164225e-05, + "loss": 0.1648, "step": 162670 }, { - "epoch": 0.73, - "learning_rate": 1.376485359400924e-05, - "loss": 0.1559, + "epoch": 0.36, + "learning_rate": 3.1923335048432926e-05, + "loss": 0.1577, "step": 162680 }, { - "epoch": 0.73, - "learning_rate": 1.3762611542083315e-05, - "loss": 0.1653, + "epoch": 0.36, + "learning_rate": 3.1922216505223604e-05, + "loss": 0.155, "step": 162690 }, { - "epoch": 0.73, - "learning_rate": 1.3760369490157394e-05, - "loss": 0.1609, + "epoch": 0.36, + "learning_rate": 3.1921097962014275e-05, + "loss": 0.1499, "step": 162700 }, { - "epoch": 0.73, - "learning_rate": 1.3758127438231469e-05, - "loss": 0.161, + "epoch": 0.36, + "learning_rate": 3.191997941880495e-05, + "loss": 0.1557, "step": 162710 }, { - "epoch": 0.73, - "learning_rate": 1.3755885386305548e-05, - "loss": 0.1524, + "epoch": 0.36, + "learning_rate": 3.1918860875595624e-05, + "loss": 0.1544, "step": 162720 }, { - "epoch": 0.73, - "learning_rate": 1.3753643334379626e-05, - "loss": 0.1607, + "epoch": 0.36, + "learning_rate": 3.19177423323863e-05, + "loss": 0.1605, "step": 162730 }, { - "epoch": 0.73, - "learning_rate": 1.3751401282453702e-05, - "loss": 0.158, + "epoch": 0.36, + "learning_rate": 3.191662378917697e-05, + "loss": 0.1582, "step": 162740 }, { - "epoch": 0.73, - "learning_rate": 1.374915923052778e-05, - "loss": 0.1659, + "epoch": 0.36, + "learning_rate": 3.191550524596765e-05, + "loss": 0.1517, "step": 162750 }, { - "epoch": 0.73, - "learning_rate": 1.3746917178601856e-05, - "loss": 0.1625, + "epoch": 0.36, + "learning_rate": 3.191438670275833e-05, + "loss": 0.1593, "step": 162760 }, { - "epoch": 0.73, - "learning_rate": 1.3744675126675934e-05, - "loss": 0.165, + "epoch": 0.36, + "learning_rate": 3.1913268159549e-05, + "loss": 0.1559, "step": 162770 }, { - "epoch": 0.73, - "learning_rate": 1.3742433074750012e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.1912149616339685e-05, + "loss": 0.1664, "step": 162780 }, { - "epoch": 0.73, - "learning_rate": 1.3740191022824089e-05, - "loss": 0.1597, + "epoch": 0.36, + "learning_rate": 3.1911031073130356e-05, + "loss": 0.1555, "step": 162790 }, { - "epoch": 0.73, - "learning_rate": 1.3737948970898167e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.1909912529921034e-05, + "loss": 0.1556, "step": 162800 }, { - "epoch": 0.73, - "learning_rate": 1.3735706918972244e-05, - "loss": 0.1589, + "epoch": 0.36, + "learning_rate": 3.190879398671171e-05, + "loss": 0.1559, "step": 162810 }, { - "epoch": 0.73, - "learning_rate": 1.3733464867046323e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.190767544350238e-05, + "loss": 0.1507, "step": 162820 }, { - "epoch": 0.73, - "learning_rate": 1.3731222815120398e-05, - "loss": 0.1591, + "epoch": 0.36, + "learning_rate": 3.190655690029306e-05, + "loss": 0.1575, "step": 162830 }, { - "epoch": 0.73, - "learning_rate": 1.3728980763194477e-05, - "loss": 0.1555, + "epoch": 0.36, + "learning_rate": 3.190543835708373e-05, + "loss": 0.1544, "step": 162840 }, { - "epoch": 0.73, - "learning_rate": 1.3726738711268552e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.190431981387441e-05, + "loss": 0.1508, "step": 162850 }, { - "epoch": 0.73, - "learning_rate": 1.3724496659342631e-05, - "loss": 0.1609, + "epoch": 0.36, + "learning_rate": 3.190320127066509e-05, + "loss": 0.1554, "step": 162860 }, { - "epoch": 0.73, - "learning_rate": 1.372225460741671e-05, - "loss": 0.1658, + "epoch": 0.36, + "learning_rate": 3.190208272745576e-05, + "loss": 0.16, "step": 162870 }, { - "epoch": 0.73, - "learning_rate": 1.3720012555490785e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.190096418424644e-05, + "loss": 0.1523, "step": 162880 }, { - "epoch": 0.73, - "learning_rate": 1.3717770503564864e-05, - "loss": 0.1533, + "epoch": 0.36, + "learning_rate": 3.1899845641037115e-05, + "loss": 0.1582, "step": 162890 }, { - "epoch": 0.73, - "learning_rate": 1.371552845163894e-05, - "loss": 0.1591, + "epoch": 0.36, + "learning_rate": 3.189872709782779e-05, + "loss": 0.1524, "step": 162900 }, { - "epoch": 0.73, - "learning_rate": 1.3713286399713018e-05, - "loss": 0.1603, + "epoch": 0.36, + "learning_rate": 3.189760855461847e-05, + "loss": 0.1487, "step": 162910 }, { - "epoch": 0.73, - "learning_rate": 1.3711044347787095e-05, - "loss": 0.1608, + "epoch": 0.36, + "learning_rate": 3.189649001140914e-05, + "loss": 0.1546, "step": 162920 }, { - "epoch": 0.73, - "learning_rate": 1.3708802295861174e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.189537146819982e-05, + "loss": 0.1565, "step": 162930 }, { - "epoch": 0.73, - "learning_rate": 1.370656024393525e-05, - "loss": 0.1558, + "epoch": 0.36, + "learning_rate": 3.189425292499049e-05, + "loss": 0.1546, "step": 162940 }, { - "epoch": 0.73, - "learning_rate": 1.3704318192009328e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.189313438178117e-05, + "loss": 0.154, "step": 162950 }, { - "epoch": 0.73, - "learning_rate": 1.3702076140083406e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.189212769289278e-05, + "loss": 0.156, "step": 162960 }, { - "epoch": 0.73, - "learning_rate": 1.3699834088157482e-05, - "loss": 0.1594, + "epoch": 0.36, + "learning_rate": 3.1891009149683456e-05, + "loss": 0.1526, "step": 162970 }, { - "epoch": 0.73, - "learning_rate": 1.369759203623156e-05, - "loss": 0.1626, + "epoch": 0.36, + "learning_rate": 3.1889890606474134e-05, + "loss": 0.1566, "step": 162980 }, { - "epoch": 0.73, - "learning_rate": 1.3695349984305636e-05, - "loss": 0.1601, + "epoch": 0.36, + "learning_rate": 3.1888772063264805e-05, + "loss": 0.1529, "step": 162990 }, { - "epoch": 0.73, - "learning_rate": 1.3693107932379714e-05, - "loss": 0.1641, + "epoch": 0.36, + "learning_rate": 3.188765352005548e-05, + "loss": 0.1603, "step": 163000 }, { - "epoch": 0.73, - "learning_rate": 1.3690865880453793e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.1886534976846154e-05, + "loss": 0.1535, "step": 163010 }, { - "epoch": 0.73, - "learning_rate": 1.3688623828527869e-05, - "loss": 0.1627, + "epoch": 0.36, + "learning_rate": 3.188541643363683e-05, + "loss": 0.1532, "step": 163020 }, { - "epoch": 0.73, - "learning_rate": 1.3686381776601947e-05, - "loss": 0.1629, + "epoch": 0.36, + "learning_rate": 3.188429789042751e-05, + "loss": 0.1553, "step": 163030 }, { - "epoch": 0.73, - "learning_rate": 1.3684139724676023e-05, - "loss": 0.1573, + "epoch": 0.36, + "learning_rate": 3.188317934721818e-05, + "loss": 0.1532, "step": 163040 }, { - "epoch": 0.73, - "learning_rate": 1.3681897672750101e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.188206080400886e-05, + "loss": 0.159, "step": 163050 }, { - "epoch": 0.73, - "learning_rate": 1.3679655620824178e-05, - "loss": 0.1524, + "epoch": 0.36, + "learning_rate": 3.188094226079954e-05, + "loss": 0.1546, "step": 163060 }, { - "epoch": 0.73, - "learning_rate": 1.3677413568898257e-05, - "loss": 0.1659, + "epoch": 0.36, + "learning_rate": 3.1879823717590215e-05, + "loss": 0.157, "step": 163070 }, { - "epoch": 0.73, - "learning_rate": 1.3675171516972334e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.1878705174380886e-05, + "loss": 0.1521, "step": 163080 }, { - "epoch": 0.73, - "learning_rate": 1.3672929465046411e-05, - "loss": 0.1571, + "epoch": 0.36, + "learning_rate": 3.1877586631171564e-05, + "loss": 0.1553, "step": 163090 }, { - "epoch": 0.73, - "learning_rate": 1.367068741312049e-05, - "loss": 0.1606, + "epoch": 0.36, + "learning_rate": 3.187646808796224e-05, + "loss": 0.1583, "step": 163100 }, { - "epoch": 0.73, - "learning_rate": 1.3668445361194565e-05, - "loss": 0.163, + "epoch": 0.36, + "learning_rate": 3.187534954475291e-05, + "loss": 0.1563, "step": 163110 }, { - "epoch": 0.73, - "learning_rate": 1.3666203309268644e-05, - "loss": 0.1605, + "epoch": 0.36, + "learning_rate": 3.187423100154359e-05, + "loss": 0.1527, "step": 163120 }, { - "epoch": 0.73, - "learning_rate": 1.366396125734272e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.187311245833426e-05, + "loss": 0.157, "step": 163130 }, { - "epoch": 0.73, - "learning_rate": 1.3661719205416798e-05, - "loss": 0.1694, + "epoch": 0.36, + "learning_rate": 3.187199391512494e-05, + "loss": 0.155, "step": 163140 }, { - "epoch": 0.73, - "learning_rate": 1.3659477153490877e-05, - "loss": 0.1584, + "epoch": 0.36, + "learning_rate": 3.187087537191562e-05, + "loss": 0.1545, "step": 163150 }, { - "epoch": 0.73, - "learning_rate": 1.3657235101564952e-05, - "loss": 0.1644, + "epoch": 0.36, + "learning_rate": 3.1869756828706296e-05, + "loss": 0.1533, "step": 163160 }, { - "epoch": 0.73, - "learning_rate": 1.365499304963903e-05, - "loss": 0.1612, + "epoch": 0.36, + "learning_rate": 3.1868638285496974e-05, + "loss": 0.1553, "step": 163170 }, { - "epoch": 0.73, - "learning_rate": 1.3652750997713106e-05, - "loss": 0.1591, + "epoch": 0.36, + "learning_rate": 3.1867519742287645e-05, + "loss": 0.1599, "step": 163180 }, { - "epoch": 0.73, - "learning_rate": 1.3650508945787185e-05, - "loss": 0.1558, + "epoch": 0.36, + "learning_rate": 3.186640119907832e-05, + "loss": 0.1536, "step": 163190 }, { - "epoch": 0.73, - "learning_rate": 1.3648266893861262e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.1865282655869e-05, + "loss": 0.1516, "step": 163200 }, { - "epoch": 0.73, - "learning_rate": 1.364602484193534e-05, - "loss": 0.1619, + "epoch": 0.36, + "learning_rate": 3.186416411265967e-05, + "loss": 0.1509, "step": 163210 }, { - "epoch": 0.73, - "learning_rate": 1.364378279000942e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.186304556945035e-05, + "loss": 0.1537, "step": 163220 }, { - "epoch": 0.73, - "learning_rate": 1.3641540738083495e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.186192702624102e-05, + "loss": 0.1594, "step": 163230 }, { - "epoch": 0.73, - "learning_rate": 1.3639298686157573e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.18608084830317e-05, + "loss": 0.1556, "step": 163240 }, { - "epoch": 0.73, - "learning_rate": 1.3637056634231649e-05, - "loss": 0.1617, + "epoch": 0.36, + "learning_rate": 3.185968993982238e-05, + "loss": 0.155, "step": 163250 }, { - "epoch": 0.73, - "learning_rate": 1.3634814582305727e-05, - "loss": 0.1584, + "epoch": 0.36, + "learning_rate": 3.1858571396613055e-05, + "loss": 0.1578, "step": 163260 }, { - "epoch": 0.73, - "learning_rate": 1.3632572530379803e-05, - "loss": 0.1571, + "epoch": 0.36, + "learning_rate": 3.185745285340373e-05, + "loss": 0.1545, "step": 163270 }, { - "epoch": 0.73, - "learning_rate": 1.3630330478453881e-05, - "loss": 0.163, + "epoch": 0.36, + "learning_rate": 3.1856334310194404e-05, + "loss": 0.155, "step": 163280 }, { - "epoch": 0.73, - "learning_rate": 1.362808842652796e-05, - "loss": 0.1606, + "epoch": 0.36, + "learning_rate": 3.185521576698508e-05, + "loss": 0.1529, "step": 163290 }, { - "epoch": 0.73, - "learning_rate": 1.3625846374602035e-05, - "loss": 0.1616, + "epoch": 0.36, + "learning_rate": 3.185409722377576e-05, + "loss": 0.1528, "step": 163300 }, { - "epoch": 0.73, - "learning_rate": 1.3623604322676114e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.185297868056643e-05, + "loss": 0.15, "step": 163310 }, { - "epoch": 0.73, - "learning_rate": 1.3621362270750191e-05, - "loss": 0.1588, + "epoch": 0.36, + "learning_rate": 3.185186013735711e-05, + "loss": 0.1539, "step": 163320 }, { - "epoch": 0.73, - "learning_rate": 1.3619120218824268e-05, - "loss": 0.1574, + "epoch": 0.36, + "learning_rate": 3.185074159414778e-05, + "loss": 0.1564, "step": 163330 }, { - "epoch": 0.73, - "learning_rate": 1.3616878166898345e-05, - "loss": 0.1578, + "epoch": 0.36, + "learning_rate": 3.184962305093846e-05, + "loss": 0.1548, "step": 163340 }, { - "epoch": 0.73, - "learning_rate": 1.3614636114972424e-05, - "loss": 0.1636, + "epoch": 0.36, + "learning_rate": 3.1848504507729136e-05, + "loss": 0.155, "step": 163350 }, { - "epoch": 0.73, - "learning_rate": 1.3612394063046503e-05, - "loss": 0.1575, + "epoch": 0.36, + "learning_rate": 3.1847385964519814e-05, + "loss": 0.1488, "step": 163360 }, { - "epoch": 0.73, - "learning_rate": 1.3610152011120578e-05, - "loss": 0.162, + "epoch": 0.36, + "learning_rate": 3.184626742131049e-05, + "loss": 0.1579, "step": 163370 }, { - "epoch": 0.73, - "learning_rate": 1.3607909959194657e-05, - "loss": 0.1599, + "epoch": 0.36, + "learning_rate": 3.184514887810116e-05, + "loss": 0.1597, "step": 163380 }, { - "epoch": 0.73, - "learning_rate": 1.3605667907268732e-05, - "loss": 0.1602, + "epoch": 0.36, + "learning_rate": 3.184403033489184e-05, + "loss": 0.1585, "step": 163390 }, { - "epoch": 0.73, - "learning_rate": 1.360342585534281e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.184291179168251e-05, + "loss": 0.1588, "step": 163400 }, { - "epoch": 0.73, - "learning_rate": 1.3601183803416886e-05, - "loss": 0.1635, + "epoch": 0.36, + "learning_rate": 3.184179324847319e-05, + "loss": 0.1542, "step": 163410 }, { - "epoch": 0.73, - "learning_rate": 1.3598941751490965e-05, - "loss": 0.1563, + "epoch": 0.36, + "learning_rate": 3.184067470526387e-05, + "loss": 0.1529, "step": 163420 }, { - "epoch": 0.73, - "learning_rate": 1.3596699699565043e-05, - "loss": 0.1587, + "epoch": 0.36, + "learning_rate": 3.183955616205454e-05, + "loss": 0.1574, "step": 163430 }, { - "epoch": 0.73, - "learning_rate": 1.3594457647639119e-05, - "loss": 0.1565, + "epoch": 0.36, + "learning_rate": 3.183843761884522e-05, + "loss": 0.1614, "step": 163440 }, { - "epoch": 0.73, - "learning_rate": 1.3592215595713198e-05, - "loss": 0.1613, + "epoch": 0.36, + "learning_rate": 3.183731907563589e-05, + "loss": 0.1595, "step": 163450 }, { - "epoch": 0.73, - "learning_rate": 1.3589973543787275e-05, - "loss": 0.1634, + "epoch": 0.36, + "learning_rate": 3.1836200532426566e-05, + "loss": 0.1525, "step": 163460 }, { - "epoch": 0.73, - "learning_rate": 1.3587731491861353e-05, - "loss": 0.1624, + "epoch": 0.36, + "learning_rate": 3.1835081989217244e-05, + "loss": 0.1565, "step": 163470 }, { - "epoch": 0.73, - "learning_rate": 1.3585489439935429e-05, - "loss": 0.1585, + "epoch": 0.36, + "learning_rate": 3.183396344600792e-05, + "loss": 0.1561, "step": 163480 }, { - "epoch": 0.73, - "learning_rate": 1.3583247388009507e-05, - "loss": 0.1642, + "epoch": 0.36, + "learning_rate": 3.18328449027986e-05, + "loss": 0.157, "step": 163490 }, { - "epoch": 0.73, - "learning_rate": 1.3581005336083586e-05, - "loss": 0.1615, + "epoch": 0.36, + "learning_rate": 3.183172635958927e-05, + "loss": 0.1561, "step": 163500 }, { - "epoch": 0.73, - "learning_rate": 1.3578763284157661e-05, - "loss": 0.1567, + "epoch": 0.36, + "learning_rate": 3.183060781637995e-05, + "loss": 0.1614, "step": 163510 }, { - "epoch": 0.73, - "learning_rate": 1.357652123223174e-05, - "loss": 0.1622, + "epoch": 0.36, + "learning_rate": 3.182948927317063e-05, + "loss": 0.1592, "step": 163520 }, { - "epoch": 0.73, - "learning_rate": 1.3574279180305815e-05, - "loss": 0.1569, + "epoch": 0.37, + "learning_rate": 3.18283707299613e-05, + "loss": 0.1489, "step": 163530 }, { - "epoch": 0.73, - "learning_rate": 1.3572037128379894e-05, - "loss": 0.1639, + "epoch": 0.37, + "learning_rate": 3.1827252186751976e-05, + "loss": 0.1532, "step": 163540 }, { - "epoch": 0.73, - "learning_rate": 1.356979507645397e-05, - "loss": 0.157, + "epoch": 0.37, + "learning_rate": 3.182613364354265e-05, + "loss": 0.1583, "step": 163550 }, { - "epoch": 0.73, - "learning_rate": 1.3567553024528048e-05, - "loss": 0.1627, + "epoch": 0.37, + "learning_rate": 3.1825015100333325e-05, + "loss": 0.1592, "step": 163560 }, { - "epoch": 0.73, - "learning_rate": 1.3565310972602127e-05, - "loss": 0.1646, + "epoch": 0.37, + "learning_rate": 3.1823896557124e-05, + "loss": 0.151, "step": 163570 }, { - "epoch": 0.73, - "learning_rate": 1.3563068920676202e-05, - "loss": 0.164, + "epoch": 0.37, + "learning_rate": 3.182277801391468e-05, + "loss": 0.1595, "step": 163580 }, { - "epoch": 0.73, - "learning_rate": 1.3560826868750281e-05, - "loss": 0.1587, + "epoch": 0.37, + "learning_rate": 3.182165947070536e-05, + "loss": 0.1526, "step": 163590 }, { - "epoch": 0.73, - "learning_rate": 1.3558584816824358e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.182054092749603e-05, + "loss": 0.1548, "step": 163600 }, { - "epoch": 0.73, - "learning_rate": 1.3556342764898437e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.181942238428671e-05, + "loss": 0.158, "step": 163610 }, { - "epoch": 0.73, - "learning_rate": 1.3554100712972512e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.1818303841077386e-05, + "loss": 0.158, "step": 163620 }, { - "epoch": 0.73, - "learning_rate": 1.355185866104659e-05, - "loss": 0.1659, + "epoch": 0.37, + "learning_rate": 3.181718529786806e-05, + "loss": 0.1553, "step": 163630 }, { - "epoch": 0.73, - "learning_rate": 1.354961660912067e-05, - "loss": 0.1599, + "epoch": 0.37, + "learning_rate": 3.1816066754658735e-05, + "loss": 0.156, "step": 163640 }, { - "epoch": 0.73, - "learning_rate": 1.3547374557194745e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.1814948211449406e-05, + "loss": 0.1576, "step": 163650 }, { - "epoch": 0.73, - "learning_rate": 1.3545132505268823e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.1813829668240084e-05, + "loss": 0.1538, "step": 163660 }, { - "epoch": 0.73, - "learning_rate": 1.3542890453342899e-05, - "loss": 0.1584, + "epoch": 0.37, + "learning_rate": 3.181271112503076e-05, + "loss": 0.1496, "step": 163670 }, { - "epoch": 0.73, - "learning_rate": 1.3540648401416978e-05, - "loss": 0.1595, + "epoch": 0.37, + "learning_rate": 3.181159258182144e-05, + "loss": 0.1569, "step": 163680 }, { - "epoch": 0.73, - "learning_rate": 1.3538406349491056e-05, - "loss": 0.1607, + "epoch": 0.37, + "learning_rate": 3.181047403861212e-05, + "loss": 0.1526, "step": 163690 }, { - "epoch": 0.73, - "learning_rate": 1.3536164297565132e-05, - "loss": 0.1588, + "epoch": 0.37, + "learning_rate": 3.180935549540279e-05, + "loss": 0.1502, "step": 163700 }, { - "epoch": 0.73, - "learning_rate": 1.353392224563921e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.1808236952193467e-05, + "loss": 0.1543, "step": 163710 }, { - "epoch": 0.73, - "learning_rate": 1.3531680193713286e-05, - "loss": 0.1626, + "epoch": 0.37, + "learning_rate": 3.180711840898414e-05, + "loss": 0.1621, "step": 163720 }, { - "epoch": 0.73, - "learning_rate": 1.3529438141787364e-05, - "loss": 0.1604, + "epoch": 0.37, + "learning_rate": 3.1805999865774816e-05, + "loss": 0.159, "step": 163730 }, { - "epoch": 0.73, - "learning_rate": 1.3527196089861441e-05, - "loss": 0.1606, + "epoch": 0.37, + "learning_rate": 3.1804881322565494e-05, + "loss": 0.1552, "step": 163740 }, { - "epoch": 0.73, - "learning_rate": 1.352495403793552e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.1803762779356165e-05, + "loss": 0.156, "step": 163750 }, { - "epoch": 0.73, - "learning_rate": 1.3522711986009599e-05, - "loss": 0.1635, + "epoch": 0.37, + "learning_rate": 3.180264423614684e-05, + "loss": 0.1521, "step": 163760 }, { - "epoch": 0.73, - "learning_rate": 1.3520469934083674e-05, - "loss": 0.1577, + "epoch": 0.37, + "learning_rate": 3.1801525692937514e-05, + "loss": 0.153, "step": 163770 }, { - "epoch": 0.73, - "learning_rate": 1.3518227882157753e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.18004071497282e-05, + "loss": 0.153, "step": 163780 }, { - "epoch": 0.73, - "learning_rate": 1.3515985830231828e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.1799288606518876e-05, + "loss": 0.1546, "step": 163790 }, { - "epoch": 0.73, - "learning_rate": 1.3513743778305907e-05, - "loss": 0.1657, + "epoch": 0.37, + "learning_rate": 3.179817006330955e-05, + "loss": 0.1499, "step": 163800 }, { - "epoch": 0.73, - "learning_rate": 1.3511501726379982e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.1797051520100226e-05, + "loss": 0.1586, "step": 163810 }, { - "epoch": 0.73, - "learning_rate": 1.3509259674454061e-05, - "loss": 0.1666, + "epoch": 0.37, + "learning_rate": 3.17959329768909e-05, + "loss": 0.1492, "step": 163820 }, { - "epoch": 0.73, - "learning_rate": 1.350701762252814e-05, - "loss": 0.1619, + "epoch": 0.37, + "learning_rate": 3.1794814433681575e-05, + "loss": 0.1556, "step": 163830 }, { - "epoch": 0.73, - "learning_rate": 1.3504775570602215e-05, - "loss": 0.1698, + "epoch": 0.37, + "learning_rate": 3.179369589047225e-05, + "loss": 0.1563, "step": 163840 }, { - "epoch": 0.73, - "learning_rate": 1.3502533518676294e-05, - "loss": 0.1626, + "epoch": 0.37, + "learning_rate": 3.1792577347262924e-05, + "loss": 0.1552, "step": 163850 }, { - "epoch": 0.73, - "learning_rate": 1.350029146675037e-05, - "loss": 0.1595, + "epoch": 0.37, + "learning_rate": 3.17914588040536e-05, + "loss": 0.1542, "step": 163860 }, { - "epoch": 0.73, - "learning_rate": 1.3498049414824448e-05, - "loss": 0.1673, + "epoch": 0.37, + "learning_rate": 3.179034026084427e-05, + "loss": 0.1554, "step": 163870 }, { - "epoch": 0.73, - "learning_rate": 1.3495807362898525e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.178922171763495e-05, + "loss": 0.1542, "step": 163880 }, { - "epoch": 0.73, - "learning_rate": 1.3493565310972603e-05, - "loss": 0.1629, + "epoch": 0.37, + "learning_rate": 3.178810317442563e-05, + "loss": 0.1547, "step": 163890 }, { - "epoch": 0.73, - "learning_rate": 1.3491323259046682e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.1786984631216307e-05, + "loss": 0.1537, "step": 163900 }, { - "epoch": 0.73, - "learning_rate": 1.3489081207120758e-05, - "loss": 0.1531, + "epoch": 0.37, + "learning_rate": 3.1785866088006984e-05, + "loss": 0.1558, "step": 163910 }, { - "epoch": 0.73, - "learning_rate": 1.3486839155194836e-05, - "loss": 0.1655, + "epoch": 0.37, + "learning_rate": 3.1784747544797656e-05, + "loss": 0.1511, "step": 163920 }, { - "epoch": 0.73, - "learning_rate": 1.3484597103268912e-05, - "loss": 0.1523, + "epoch": 0.37, + "learning_rate": 3.1783629001588334e-05, + "loss": 0.1546, "step": 163930 }, { - "epoch": 0.73, - "learning_rate": 1.348235505134299e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.178251045837901e-05, + "loss": 0.1569, "step": 163940 }, { - "epoch": 0.73, - "learning_rate": 1.3480112999417066e-05, - "loss": 0.163, + "epoch": 0.37, + "learning_rate": 3.178139191516968e-05, + "loss": 0.1524, "step": 163950 }, { - "epoch": 0.73, - "learning_rate": 1.3477870947491144e-05, - "loss": 0.164, + "epoch": 0.37, + "learning_rate": 3.178027337196036e-05, + "loss": 0.1595, "step": 163960 }, { - "epoch": 0.73, - "learning_rate": 1.3475628895565223e-05, - "loss": 0.1626, + "epoch": 0.37, + "learning_rate": 3.177915482875103e-05, + "loss": 0.1509, "step": 163970 }, { - "epoch": 0.73, - "learning_rate": 1.3473386843639298e-05, - "loss": 0.1556, + "epoch": 0.37, + "learning_rate": 3.177803628554171e-05, + "loss": 0.1596, "step": 163980 }, { - "epoch": 0.73, - "learning_rate": 1.3471144791713377e-05, - "loss": 0.1572, + "epoch": 0.37, + "learning_rate": 3.177691774233239e-05, + "loss": 0.1527, "step": 163990 }, { - "epoch": 0.73, - "learning_rate": 1.3468902739787454e-05, - "loss": 0.1569, + "epoch": 0.37, + "learning_rate": 3.1775799199123066e-05, + "loss": 0.1573, "step": 164000 }, { - "epoch": 0.73, - "learning_rate": 1.3466660687861533e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.1774680655913743e-05, + "loss": 0.1518, "step": 164010 }, { - "epoch": 0.73, - "learning_rate": 1.3464418635935608e-05, - "loss": 0.1606, + "epoch": 0.37, + "learning_rate": 3.1773562112704415e-05, + "loss": 0.1521, "step": 164020 }, { - "epoch": 0.73, - "learning_rate": 1.3462176584009687e-05, - "loss": 0.1614, + "epoch": 0.37, + "learning_rate": 3.177244356949509e-05, + "loss": 0.1532, "step": 164030 }, { - "epoch": 0.73, - "learning_rate": 1.3459934532083766e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.1771325026285764e-05, + "loss": 0.1526, "step": 164040 }, { - "epoch": 0.73, - "learning_rate": 1.3457692480157841e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.177020648307644e-05, + "loss": 0.1602, "step": 164050 }, { - "epoch": 0.73, - "learning_rate": 1.345545042823192e-05, - "loss": 0.1679, + "epoch": 0.37, + "learning_rate": 3.176908793986712e-05, + "loss": 0.1566, "step": 164060 }, { - "epoch": 0.73, - "learning_rate": 1.3453208376305995e-05, - "loss": 0.1599, + "epoch": 0.37, + "learning_rate": 3.176796939665779e-05, + "loss": 0.1557, "step": 164070 }, { - "epoch": 0.73, - "learning_rate": 1.3450966324380074e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.176685085344847e-05, + "loss": 0.1523, "step": 164080 }, { - "epoch": 0.73, - "learning_rate": 1.3448724272454149e-05, - "loss": 0.1666, + "epoch": 0.37, + "learning_rate": 3.1765732310239147e-05, + "loss": 0.1536, "step": 164090 }, { - "epoch": 0.73, - "learning_rate": 1.3446482220528228e-05, - "loss": 0.1633, + "epoch": 0.37, + "learning_rate": 3.1764613767029824e-05, + "loss": 0.1543, "step": 164100 }, { - "epoch": 0.73, - "learning_rate": 1.3444240168602306e-05, - "loss": 0.1673, + "epoch": 0.37, + "learning_rate": 3.17634952238205e-05, + "loss": 0.1539, "step": 164110 }, { - "epoch": 0.73, - "learning_rate": 1.3441998116676382e-05, - "loss": 0.1556, + "epoch": 0.37, + "learning_rate": 3.1762376680611174e-05, + "loss": 0.1577, "step": 164120 }, { - "epoch": 0.73, - "learning_rate": 1.343975606475046e-05, - "loss": 0.1604, + "epoch": 0.37, + "learning_rate": 3.176125813740185e-05, + "loss": 0.1558, "step": 164130 }, { - "epoch": 0.73, - "learning_rate": 1.3437514012824538e-05, - "loss": 0.1624, + "epoch": 0.37, + "learning_rate": 3.176013959419252e-05, + "loss": 0.1557, "step": 164140 }, { - "epoch": 0.73, - "learning_rate": 1.3435271960898616e-05, - "loss": 0.1667, + "epoch": 0.37, + "learning_rate": 3.17590210509832e-05, + "loss": 0.1523, "step": 164150 }, { - "epoch": 0.73, - "learning_rate": 1.3433029908972692e-05, - "loss": 0.1588, + "epoch": 0.37, + "learning_rate": 3.175790250777388e-05, + "loss": 0.1517, "step": 164160 }, { - "epoch": 0.73, - "learning_rate": 1.343078785704677e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.175678396456455e-05, + "loss": 0.1541, "step": 164170 }, { - "epoch": 0.73, - "learning_rate": 1.3428545805120849e-05, - "loss": 0.157, + "epoch": 0.37, + "learning_rate": 3.175566542135523e-05, + "loss": 0.1532, "step": 164180 }, { - "epoch": 0.73, - "learning_rate": 1.3426303753194924e-05, - "loss": 0.1611, + "epoch": 0.37, + "learning_rate": 3.1754546878145905e-05, + "loss": 0.1577, "step": 164190 }, { - "epoch": 0.73, - "learning_rate": 1.3424061701269003e-05, - "loss": 0.1588, + "epoch": 0.37, + "learning_rate": 3.1753428334936583e-05, + "loss": 0.1573, "step": 164200 }, { - "epoch": 0.73, - "learning_rate": 1.3421819649343078e-05, - "loss": 0.1641, + "epoch": 0.37, + "learning_rate": 3.175230979172726e-05, + "loss": 0.1539, "step": 164210 }, { - "epoch": 0.73, - "learning_rate": 1.3419577597417157e-05, - "loss": 0.1609, + "epoch": 0.37, + "learning_rate": 3.175119124851793e-05, + "loss": 0.1552, "step": 164220 }, { - "epoch": 0.73, - "learning_rate": 1.3417335545491232e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.175007270530861e-05, + "loss": 0.1511, "step": 164230 }, { - "epoch": 0.73, - "learning_rate": 1.3415093493565311e-05, - "loss": 0.1582, + "epoch": 0.37, + "learning_rate": 3.174895416209928e-05, + "loss": 0.1538, "step": 164240 }, { - "epoch": 0.73, - "learning_rate": 1.341285144163939e-05, - "loss": 0.1597, + "epoch": 0.37, + "learning_rate": 3.174783561888996e-05, + "loss": 0.1551, "step": 164250 }, { - "epoch": 0.73, - "learning_rate": 1.3410609389713465e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.174671707568064e-05, + "loss": 0.1547, "step": 164260 }, { - "epoch": 0.73, - "learning_rate": 1.3408367337787544e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.174559853247131e-05, + "loss": 0.1539, "step": 164270 }, { - "epoch": 0.73, - "learning_rate": 1.3406125285861621e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.1744479989261986e-05, + "loss": 0.1503, "step": 164280 }, { - "epoch": 0.73, - "learning_rate": 1.34038832339357e-05, - "loss": 0.1593, + "epoch": 0.37, + "learning_rate": 3.174336144605266e-05, + "loss": 0.1557, "step": 164290 }, { - "epoch": 0.73, - "learning_rate": 1.3401641182009775e-05, - "loss": 0.1663, + "epoch": 0.37, + "learning_rate": 3.1742242902843336e-05, + "loss": 0.1499, "step": 164300 }, { - "epoch": 0.73, - "learning_rate": 1.3399399130083854e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.1741124359634013e-05, + "loss": 0.1535, "step": 164310 }, { - "epoch": 0.73, - "learning_rate": 1.3397157078157932e-05, - "loss": 0.1636, + "epoch": 0.37, + "learning_rate": 3.174000581642469e-05, + "loss": 0.1557, "step": 164320 }, { - "epoch": 0.73, - "learning_rate": 1.3394915026232008e-05, - "loss": 0.1569, + "epoch": 0.37, + "learning_rate": 3.173888727321537e-05, + "loss": 0.1561, "step": 164330 }, { - "epoch": 0.73, - "learning_rate": 1.3392672974306086e-05, - "loss": 0.1632, + "epoch": 0.37, + "learning_rate": 3.173776873000604e-05, + "loss": 0.1566, "step": 164340 }, { - "epoch": 0.73, - "learning_rate": 1.3390430922380162e-05, - "loss": 0.1649, + "epoch": 0.37, + "learning_rate": 3.173665018679672e-05, + "loss": 0.1546, "step": 164350 }, { - "epoch": 0.73, - "learning_rate": 1.338818887045424e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.173553164358739e-05, + "loss": 0.1557, "step": 164360 }, { - "epoch": 0.73, - "learning_rate": 1.3385946818528316e-05, - "loss": 0.1652, + "epoch": 0.37, + "learning_rate": 3.173441310037807e-05, + "loss": 0.1595, "step": 164370 }, { - "epoch": 0.73, - "learning_rate": 1.3383704766602395e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.1733294557168745e-05, + "loss": 0.1582, "step": 164380 }, { - "epoch": 0.73, - "learning_rate": 1.3381462714676473e-05, - "loss": 0.1615, + "epoch": 0.37, + "learning_rate": 3.1732176013959417e-05, + "loss": 0.1555, "step": 164390 }, { - "epoch": 0.73, - "learning_rate": 1.337922066275055e-05, - "loss": 0.1556, + "epoch": 0.37, + "learning_rate": 3.1731057470750095e-05, + "loss": 0.1581, "step": 164400 }, { - "epoch": 0.73, - "learning_rate": 1.3376978610824627e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.172993892754077e-05, + "loss": 0.1558, "step": 164410 }, { - "epoch": 0.73, - "learning_rate": 1.3374736558898704e-05, - "loss": 0.1644, + "epoch": 0.37, + "learning_rate": 3.172882038433145e-05, + "loss": 0.1511, "step": 164420 }, { - "epoch": 0.73, - "learning_rate": 1.3372494506972783e-05, - "loss": 0.1691, + "epoch": 0.37, + "learning_rate": 3.172770184112213e-05, + "loss": 0.1574, "step": 164430 }, { - "epoch": 0.73, - "learning_rate": 1.3370252455046858e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.17265832979128e-05, + "loss": 0.156, "step": 164440 }, { - "epoch": 0.73, - "learning_rate": 1.3368010403120937e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.172546475470348e-05, + "loss": 0.1562, "step": 164450 }, { - "epoch": 0.73, - "learning_rate": 1.3365768351195016e-05, - "loss": 0.157, + "epoch": 0.37, + "learning_rate": 3.172434621149415e-05, + "loss": 0.1569, "step": 164460 }, { - "epoch": 0.73, - "learning_rate": 1.3363526299269091e-05, - "loss": 0.1555, + "epoch": 0.37, + "learning_rate": 3.1723227668284826e-05, + "loss": 0.1542, "step": 164470 }, { - "epoch": 0.73, - "learning_rate": 1.336128424734317e-05, - "loss": 0.1582, + "epoch": 0.37, + "learning_rate": 3.1722109125075504e-05, + "loss": 0.1545, "step": 164480 }, { - "epoch": 0.73, - "learning_rate": 1.3359266400609838e-05, - "loss": 0.1649, + "epoch": 0.37, + "learning_rate": 3.1720990581866176e-05, + "loss": 0.1543, "step": 164490 }, { - "epoch": 0.73, - "learning_rate": 1.3357024348683916e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.1719872038656853e-05, + "loss": 0.1565, "step": 164500 }, { - "epoch": 0.73, - "learning_rate": 1.3354782296757992e-05, - "loss": 0.1651, + "epoch": 0.37, + "learning_rate": 3.171875349544753e-05, + "loss": 0.1569, "step": 164510 }, { - "epoch": 0.73, - "learning_rate": 1.335254024483207e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.171763495223821e-05, + "loss": 0.1559, "step": 164520 }, { - "epoch": 0.73, - "learning_rate": 1.335029819290615e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.171651640902889e-05, + "loss": 0.1592, "step": 164530 }, { - "epoch": 0.73, - "learning_rate": 1.3348056140980225e-05, - "loss": 0.1581, + "epoch": 0.37, + "learning_rate": 3.171539786581956e-05, + "loss": 0.1521, "step": 164540 }, { - "epoch": 0.73, - "learning_rate": 1.3345814089054303e-05, - "loss": 0.158, + "epoch": 0.37, + "learning_rate": 3.1714279322610236e-05, + "loss": 0.1584, "step": 164550 }, { - "epoch": 0.73, - "learning_rate": 1.334357203712838e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.171316077940091e-05, + "loss": 0.1495, "step": 164560 }, { - "epoch": 0.73, - "learning_rate": 1.3341329985202459e-05, - "loss": 0.1514, + "epoch": 0.37, + "learning_rate": 3.1712042236191585e-05, + "loss": 0.1551, "step": 164570 }, { - "epoch": 0.73, - "learning_rate": 1.3339087933276534e-05, - "loss": 0.1557, + "epoch": 0.37, + "learning_rate": 3.171092369298226e-05, + "loss": 0.1576, "step": 164580 }, { - "epoch": 0.73, - "learning_rate": 1.3336845881350613e-05, - "loss": 0.1501, + "epoch": 0.37, + "learning_rate": 3.1709805149772934e-05, + "loss": 0.1498, "step": 164590 }, { - "epoch": 0.73, - "learning_rate": 1.3334603829424692e-05, - "loss": 0.1559, + "epoch": 0.37, + "learning_rate": 3.170868660656361e-05, + "loss": 0.1526, "step": 164600 }, { - "epoch": 0.73, - "learning_rate": 1.3332361777498767e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.170756806335429e-05, + "loss": 0.1523, "step": 164610 }, { - "epoch": 0.73, - "learning_rate": 1.3330119725572846e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.170644952014497e-05, + "loss": 0.1534, "step": 164620 }, { - "epoch": 0.73, - "learning_rate": 1.3327877673646921e-05, - "loss": 0.1607, + "epoch": 0.37, + "learning_rate": 3.1705330976935646e-05, + "loss": 0.1575, "step": 164630 }, { - "epoch": 0.73, - "learning_rate": 1.3325635621721e-05, - "loss": 0.1632, + "epoch": 0.37, + "learning_rate": 3.170421243372632e-05, + "loss": 0.1544, "step": 164640 }, { - "epoch": 0.74, - "learning_rate": 1.3323393569795079e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.1703093890516995e-05, + "loss": 0.1546, "step": 164650 }, { - "epoch": 0.74, - "learning_rate": 1.3321151517869154e-05, - "loss": 0.161, + "epoch": 0.37, + "learning_rate": 3.1701975347307666e-05, + "loss": 0.1582, "step": 164660 }, { - "epoch": 0.74, - "learning_rate": 1.3318909465943233e-05, - "loss": 0.1591, + "epoch": 0.37, + "learning_rate": 3.1700856804098344e-05, + "loss": 0.157, "step": 164670 }, { - "epoch": 0.74, - "learning_rate": 1.3316667414017308e-05, - "loss": 0.1657, + "epoch": 0.37, + "learning_rate": 3.1699738260889016e-05, + "loss": 0.1558, "step": 164680 }, { - "epoch": 0.74, - "learning_rate": 1.3314425362091387e-05, - "loss": 0.1649, + "epoch": 0.37, + "learning_rate": 3.1698619717679693e-05, + "loss": 0.1593, "step": 164690 }, { - "epoch": 0.74, - "learning_rate": 1.3312183310165464e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.169750117447037e-05, + "loss": 0.1503, "step": 164700 }, { - "epoch": 0.74, - "learning_rate": 1.3309941258239542e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.169638263126104e-05, + "loss": 0.1547, "step": 164710 }, { - "epoch": 0.74, - "learning_rate": 1.330769920631362e-05, - "loss": 0.1581, + "epoch": 0.37, + "learning_rate": 3.169526408805172e-05, + "loss": 0.1502, "step": 164720 }, { - "epoch": 0.74, - "learning_rate": 1.3305457154387696e-05, - "loss": 0.163, + "epoch": 0.37, + "learning_rate": 3.16941455448424e-05, + "loss": 0.1541, "step": 164730 }, { - "epoch": 0.74, - "learning_rate": 1.3303215102461775e-05, - "loss": 0.1552, + "epoch": 0.37, + "learning_rate": 3.1693027001633076e-05, + "loss": 0.1576, "step": 164740 }, { - "epoch": 0.74, - "learning_rate": 1.330097305053585e-05, - "loss": 0.1615, + "epoch": 0.37, + "learning_rate": 3.1691908458423754e-05, + "loss": 0.1495, "step": 164750 }, { - "epoch": 0.74, - "learning_rate": 1.329873099860993e-05, - "loss": 0.1643, + "epoch": 0.37, + "learning_rate": 3.1690789915214425e-05, + "loss": 0.1564, "step": 164760 }, { - "epoch": 0.74, - "learning_rate": 1.3296488946684005e-05, - "loss": 0.1595, + "epoch": 0.37, + "learning_rate": 3.16896713720051e-05, + "loss": 0.1515, "step": 164770 }, { - "epoch": 0.74, - "learning_rate": 1.3294246894758083e-05, - "loss": 0.161, + "epoch": 0.37, + "learning_rate": 3.1688552828795774e-05, + "loss": 0.1552, "step": 164780 }, { - "epoch": 0.74, - "learning_rate": 1.3292004842832162e-05, - "loss": 0.1643, + "epoch": 0.37, + "learning_rate": 3.168743428558645e-05, + "loss": 0.1554, "step": 164790 }, { - "epoch": 0.74, - "learning_rate": 1.3289762790906237e-05, - "loss": 0.1631, + "epoch": 0.37, + "learning_rate": 3.168631574237713e-05, + "loss": 0.1552, "step": 164800 }, { - "epoch": 0.74, - "learning_rate": 1.3287520738980316e-05, - "loss": 0.1674, + "epoch": 0.37, + "learning_rate": 3.16851971991678e-05, + "loss": 0.1548, "step": 164810 }, { - "epoch": 0.74, - "learning_rate": 1.3285278687054391e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.168407865595848e-05, + "loss": 0.1509, "step": 164820 }, { - "epoch": 0.74, - "learning_rate": 1.328303663512847e-05, - "loss": 0.158, + "epoch": 0.37, + "learning_rate": 3.168296011274916e-05, + "loss": 0.1544, "step": 164830 }, { - "epoch": 0.74, - "learning_rate": 1.3280794583202547e-05, - "loss": 0.1635, + "epoch": 0.37, + "learning_rate": 3.1681841569539835e-05, + "loss": 0.1496, "step": 164840 }, { - "epoch": 0.74, - "learning_rate": 1.3278552531276626e-05, - "loss": 0.1621, + "epoch": 0.37, + "learning_rate": 3.168072302633051e-05, + "loss": 0.1504, "step": 164850 }, { - "epoch": 0.74, - "learning_rate": 1.3276310479350705e-05, - "loss": 0.1625, + "epoch": 0.37, + "learning_rate": 3.1679604483121184e-05, + "loss": 0.1572, "step": 164860 }, { - "epoch": 0.74, - "learning_rate": 1.327406842742478e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.167848593991186e-05, + "loss": 0.1529, "step": 164870 }, { - "epoch": 0.74, - "learning_rate": 1.3271826375498859e-05, - "loss": 0.1607, + "epoch": 0.37, + "learning_rate": 3.1677367396702533e-05, + "loss": 0.1536, "step": 164880 }, { - "epoch": 0.74, - "learning_rate": 1.3269584323572934e-05, - "loss": 0.1652, + "epoch": 0.37, + "learning_rate": 3.167624885349321e-05, + "loss": 0.1548, "step": 164890 }, { - "epoch": 0.74, - "learning_rate": 1.3267342271647013e-05, - "loss": 0.1598, + "epoch": 0.37, + "learning_rate": 3.167513031028389e-05, + "loss": 0.157, "step": 164900 }, { - "epoch": 0.74, - "learning_rate": 1.3265100219721088e-05, - "loss": 0.1596, + "epoch": 0.37, + "learning_rate": 3.167401176707456e-05, + "loss": 0.1559, "step": 164910 }, { - "epoch": 0.74, - "learning_rate": 1.3262858167795167e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.167289322386524e-05, + "loss": 0.1539, "step": 164920 }, { - "epoch": 0.74, - "learning_rate": 1.3260616115869245e-05, - "loss": 0.1554, + "epoch": 0.37, + "learning_rate": 3.1671774680655916e-05, + "loss": 0.1528, "step": 164930 }, { - "epoch": 0.74, - "learning_rate": 1.325837406394332e-05, - "loss": 0.162, + "epoch": 0.37, + "learning_rate": 3.1670656137446594e-05, + "loss": 0.1557, "step": 164940 }, { - "epoch": 0.74, - "learning_rate": 1.32561320120174e-05, - "loss": 0.163, + "epoch": 0.37, + "learning_rate": 3.166953759423727e-05, + "loss": 0.1571, "step": 164950 }, { - "epoch": 0.74, - "learning_rate": 1.3253889960091476e-05, - "loss": 0.1611, + "epoch": 0.37, + "learning_rate": 3.166841905102794e-05, + "loss": 0.1508, "step": 164960 }, { - "epoch": 0.74, - "learning_rate": 1.3251647908165553e-05, - "loss": 0.1624, + "epoch": 0.37, + "learning_rate": 3.166730050781862e-05, + "loss": 0.1569, "step": 164970 }, { - "epoch": 0.74, - "learning_rate": 1.324940585623963e-05, - "loss": 0.1644, + "epoch": 0.37, + "learning_rate": 3.166618196460929e-05, + "loss": 0.1533, "step": 164980 }, { - "epoch": 0.74, - "learning_rate": 1.324716380431371e-05, - "loss": 0.1542, + "epoch": 0.37, + "learning_rate": 3.166506342139997e-05, + "loss": 0.1595, "step": 164990 }, { - "epoch": 0.74, - "learning_rate": 1.3244921752387788e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.166394487819064e-05, + "loss": 0.1522, "step": 165000 }, { - "epoch": 0.74, - "learning_rate": 1.3242679700461863e-05, - "loss": 0.163, + "epoch": 0.37, + "learning_rate": 3.166282633498132e-05, + "loss": 0.1553, "step": 165010 }, { - "epoch": 0.74, - "learning_rate": 1.3240437648535942e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.1661707791772e-05, + "loss": 0.1517, "step": 165020 }, { - "epoch": 0.74, - "learning_rate": 1.3238195596610017e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.1660589248562675e-05, + "loss": 0.1536, "step": 165030 }, { - "epoch": 0.74, - "learning_rate": 1.3235953544684096e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.165947070535335e-05, + "loss": 0.1488, "step": 165040 }, { - "epoch": 0.74, - "learning_rate": 1.3233711492758171e-05, - "loss": 0.1621, + "epoch": 0.37, + "learning_rate": 3.1658352162144024e-05, + "loss": 0.1527, "step": 165050 }, { - "epoch": 0.74, - "learning_rate": 1.323146944083225e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.16572336189347e-05, + "loss": 0.1518, "step": 165060 }, { - "epoch": 0.74, - "learning_rate": 1.3229227388906329e-05, - "loss": 0.1636, + "epoch": 0.37, + "learning_rate": 3.165611507572538e-05, + "loss": 0.1562, "step": 165070 }, { - "epoch": 0.74, - "learning_rate": 1.3226985336980404e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.165499653251605e-05, + "loss": 0.1573, "step": 165080 }, { - "epoch": 0.74, - "learning_rate": 1.3224743285054483e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.165387798930673e-05, + "loss": 0.1559, "step": 165090 }, { - "epoch": 0.74, - "learning_rate": 1.322250123312856e-05, - "loss": 0.1494, + "epoch": 0.37, + "learning_rate": 3.16527594460974e-05, + "loss": 0.155, "step": 165100 }, { - "epoch": 0.74, - "learning_rate": 1.3220259181202639e-05, - "loss": 0.1559, + "epoch": 0.37, + "learning_rate": 3.165164090288808e-05, + "loss": 0.1576, "step": 165110 }, { - "epoch": 0.74, - "learning_rate": 1.3218017129276714e-05, - "loss": 0.1634, + "epoch": 0.37, + "learning_rate": 3.1650522359678756e-05, + "loss": 0.1554, "step": 165120 }, { - "epoch": 0.74, - "learning_rate": 1.3215775077350793e-05, - "loss": 0.1627, + "epoch": 0.37, + "learning_rate": 3.164940381646943e-05, + "loss": 0.153, "step": 165130 }, { - "epoch": 0.74, - "learning_rate": 1.3213533025424871e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.164828527326011e-05, + "loss": 0.1493, "step": 165140 }, { - "epoch": 0.74, - "learning_rate": 1.3211290973498947e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.164716673005078e-05, + "loss": 0.1501, "step": 165150 }, { - "epoch": 0.74, - "learning_rate": 1.3209048921573025e-05, - "loss": 0.1582, + "epoch": 0.37, + "learning_rate": 3.164604818684146e-05, + "loss": 0.1519, "step": 165160 }, { - "epoch": 0.74, - "learning_rate": 1.32068068696471e-05, - "loss": 0.1568, + "epoch": 0.37, + "learning_rate": 3.164492964363214e-05, + "loss": 0.1507, "step": 165170 }, { - "epoch": 0.74, - "learning_rate": 1.320456481772118e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.164381110042281e-05, + "loss": 0.1615, "step": 165180 }, { - "epoch": 0.74, - "learning_rate": 1.3202322765795255e-05, - "loss": 0.1601, + "epoch": 0.37, + "learning_rate": 3.164269255721349e-05, + "loss": 0.1599, "step": 165190 }, { - "epoch": 0.74, - "learning_rate": 1.3200080713869333e-05, - "loss": 0.1644, + "epoch": 0.37, + "learning_rate": 3.164157401400416e-05, + "loss": 0.1531, "step": 165200 }, { - "epoch": 0.74, - "learning_rate": 1.3197838661943412e-05, - "loss": 0.1642, + "epoch": 0.37, + "learning_rate": 3.164045547079484e-05, + "loss": 0.1563, "step": 165210 }, { - "epoch": 0.74, - "learning_rate": 1.3195596610017488e-05, - "loss": 0.1624, + "epoch": 0.37, + "learning_rate": 3.1639336927585515e-05, + "loss": 0.1552, "step": 165220 }, { - "epoch": 0.74, - "learning_rate": 1.3193354558091566e-05, - "loss": 0.1667, + "epoch": 0.37, + "learning_rate": 3.1638218384376186e-05, + "loss": 0.1533, "step": 165230 }, { - "epoch": 0.74, - "learning_rate": 1.3191112506165643e-05, - "loss": 0.1617, + "epoch": 0.37, + "learning_rate": 3.1637099841166864e-05, + "loss": 0.1546, "step": 165240 }, { - "epoch": 0.74, - "learning_rate": 1.3188870454239722e-05, - "loss": 0.161, + "epoch": 0.37, + "learning_rate": 3.163598129795754e-05, + "loss": 0.1551, "step": 165250 }, { - "epoch": 0.74, - "learning_rate": 1.3186628402313797e-05, - "loss": 0.1591, + "epoch": 0.37, + "learning_rate": 3.163486275474822e-05, + "loss": 0.1579, "step": 165260 }, { - "epoch": 0.74, - "learning_rate": 1.3184386350387876e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.16337442115389e-05, + "loss": 0.1517, "step": 165270 }, { - "epoch": 0.74, - "learning_rate": 1.3182144298461955e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.163262566832957e-05, + "loss": 0.1554, "step": 165280 }, { - "epoch": 0.74, - "learning_rate": 1.317990224653603e-05, - "loss": 0.1582, + "epoch": 0.37, + "learning_rate": 3.163150712512025e-05, + "loss": 0.1544, "step": 165290 }, { - "epoch": 0.74, - "learning_rate": 1.3177660194610109e-05, - "loss": 0.1637, + "epoch": 0.37, + "learning_rate": 3.163038858191092e-05, + "loss": 0.1538, "step": 165300 }, { - "epoch": 0.74, - "learning_rate": 1.3175418142684184e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.1629270038701596e-05, + "loss": 0.1548, "step": 165310 }, { - "epoch": 0.74, - "learning_rate": 1.3173176090758263e-05, - "loss": 0.1595, + "epoch": 0.37, + "learning_rate": 3.162815149549227e-05, + "loss": 0.151, "step": 165320 }, { - "epoch": 0.74, - "learning_rate": 1.3170934038832338e-05, - "loss": 0.1626, + "epoch": 0.37, + "learning_rate": 3.1627032952282945e-05, + "loss": 0.1552, "step": 165330 }, { - "epoch": 0.74, - "learning_rate": 1.3168691986906417e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.162591440907362e-05, + "loss": 0.1568, "step": 165340 }, { - "epoch": 0.74, - "learning_rate": 1.3166449934980496e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.16247958658643e-05, + "loss": 0.1558, "step": 165350 }, { - "epoch": 0.74, - "learning_rate": 1.3164207883054571e-05, - "loss": 0.1539, + "epoch": 0.37, + "learning_rate": 3.162367732265498e-05, + "loss": 0.1541, "step": 165360 }, { - "epoch": 0.74, - "learning_rate": 1.316196583112865e-05, - "loss": 0.1598, + "epoch": 0.37, + "learning_rate": 3.162255877944565e-05, + "loss": 0.1527, "step": 165370 }, { - "epoch": 0.74, - "learning_rate": 1.3159723779202727e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.162144023623633e-05, + "loss": 0.1542, "step": 165380 }, { - "epoch": 0.74, - "learning_rate": 1.3157481727276805e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.1620321693027006e-05, + "loss": 0.1549, "step": 165390 }, { - "epoch": 0.74, - "learning_rate": 1.315523967535088e-05, - "loss": 0.1624, + "epoch": 0.37, + "learning_rate": 3.161920314981768e-05, + "loss": 0.1565, "step": 165400 }, { - "epoch": 0.74, - "learning_rate": 1.315299762342496e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.1618084606608355e-05, + "loss": 0.1515, "step": 165410 }, { - "epoch": 0.74, - "learning_rate": 1.3150755571499038e-05, - "loss": 0.1536, + "epoch": 0.37, + "learning_rate": 3.1616966063399026e-05, + "loss": 0.1546, "step": 165420 }, { - "epoch": 0.74, - "learning_rate": 1.3148513519573114e-05, - "loss": 0.1558, + "epoch": 0.37, + "learning_rate": 3.1615847520189704e-05, + "loss": 0.1526, "step": 165430 }, { - "epoch": 0.74, - "learning_rate": 1.3146271467647192e-05, - "loss": 0.161, + "epoch": 0.37, + "learning_rate": 3.161472897698038e-05, + "loss": 0.1509, "step": 165440 }, { - "epoch": 0.74, - "learning_rate": 1.3144029415721268e-05, - "loss": 0.1648, + "epoch": 0.37, + "learning_rate": 3.161361043377106e-05, + "loss": 0.1563, "step": 165450 }, { - "epoch": 0.74, - "learning_rate": 1.3141787363795346e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.161249189056174e-05, + "loss": 0.1542, "step": 165460 }, { - "epoch": 0.74, - "learning_rate": 1.3139545311869422e-05, - "loss": 0.1647, + "epoch": 0.37, + "learning_rate": 3.161137334735241e-05, + "loss": 0.1545, "step": 165470 }, { - "epoch": 0.74, - "learning_rate": 1.31373032599435e-05, - "loss": 0.1533, + "epoch": 0.37, + "learning_rate": 3.161025480414309e-05, + "loss": 0.1568, "step": 165480 }, { - "epoch": 0.74, - "learning_rate": 1.3135061208017579e-05, - "loss": 0.1606, + "epoch": 0.37, + "learning_rate": 3.160924811525469e-05, + "loss": 0.1552, "step": 165490 }, { - "epoch": 0.74, - "learning_rate": 1.3132819156091656e-05, - "loss": 0.1513, + "epoch": 0.37, + "learning_rate": 3.160812957204537e-05, + "loss": 0.1569, "step": 165500 }, { - "epoch": 0.74, - "learning_rate": 1.3130577104165733e-05, - "loss": 0.1671, + "epoch": 0.37, + "learning_rate": 3.1607011028836045e-05, + "loss": 0.1605, "step": 165510 }, { - "epoch": 0.74, - "learning_rate": 1.312833505223981e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.160589248562672e-05, + "loss": 0.1568, "step": 165520 }, { - "epoch": 0.74, - "learning_rate": 1.3126093000313889e-05, - "loss": 0.1621, + "epoch": 0.37, + "learning_rate": 3.16047739424174e-05, + "loss": 0.1537, "step": 165530 }, { - "epoch": 0.74, - "learning_rate": 1.3123850948387964e-05, - "loss": 0.1629, + "epoch": 0.37, + "learning_rate": 3.160365539920807e-05, + "loss": 0.1549, "step": 165540 }, { - "epoch": 0.74, - "learning_rate": 1.3121608896462043e-05, - "loss": 0.1614, + "epoch": 0.37, + "learning_rate": 3.160253685599875e-05, + "loss": 0.1521, "step": 165550 }, { - "epoch": 0.74, - "learning_rate": 1.3119366844536122e-05, - "loss": 0.1536, + "epoch": 0.37, + "learning_rate": 3.160141831278943e-05, + "loss": 0.1523, "step": 165560 }, { - "epoch": 0.74, - "learning_rate": 1.3117124792610197e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.16002997695801e-05, + "loss": 0.1536, "step": 165570 }, { - "epoch": 0.74, - "learning_rate": 1.3114882740684276e-05, - "loss": 0.1617, + "epoch": 0.37, + "learning_rate": 3.159918122637078e-05, + "loss": 0.1544, "step": 165580 }, { - "epoch": 0.74, - "learning_rate": 1.3112640688758351e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.159806268316145e-05, + "loss": 0.1513, "step": 165590 }, { - "epoch": 0.74, - "learning_rate": 1.311039863683243e-05, - "loss": 0.1567, + "epoch": 0.37, + "learning_rate": 3.1596944139952126e-05, + "loss": 0.1549, "step": 165600 }, { - "epoch": 0.74, - "learning_rate": 1.3108156584906505e-05, - "loss": 0.1601, + "epoch": 0.37, + "learning_rate": 3.1595825596742804e-05, + "loss": 0.1558, "step": 165610 }, { - "epoch": 0.74, - "learning_rate": 1.3105914532980584e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.159470705353348e-05, + "loss": 0.1562, "step": 165620 }, { - "epoch": 0.74, - "learning_rate": 1.3103672481054662e-05, - "loss": 0.1604, + "epoch": 0.37, + "learning_rate": 3.159358851032416e-05, + "loss": 0.156, "step": 165630 }, { - "epoch": 0.74, - "learning_rate": 1.310143042912874e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.159246996711483e-05, + "loss": 0.1553, "step": 165640 }, { - "epoch": 0.74, - "learning_rate": 1.3099188377202816e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.159135142390551e-05, + "loss": 0.1521, "step": 165650 }, { - "epoch": 0.74, - "learning_rate": 1.3096946325276894e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.159023288069618e-05, + "loss": 0.1532, "step": 165660 }, { - "epoch": 0.74, - "learning_rate": 1.3094704273350972e-05, - "loss": 0.1551, + "epoch": 0.37, + "learning_rate": 3.158911433748686e-05, + "loss": 0.1526, "step": 165670 }, { - "epoch": 0.74, - "learning_rate": 1.3092462221425048e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.1587995794277536e-05, + "loss": 0.1554, "step": 165680 }, { - "epoch": 0.74, - "learning_rate": 1.3090220169499126e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.158687725106821e-05, + "loss": 0.1586, "step": 165690 }, { - "epoch": 0.74, - "learning_rate": 1.3087978117573205e-05, - "loss": 0.1558, + "epoch": 0.37, + "learning_rate": 3.1585758707858885e-05, + "loss": 0.1563, "step": 165700 }, { - "epoch": 0.74, - "learning_rate": 1.308573606564728e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.1584640164649556e-05, + "loss": 0.154, "step": 165710 }, { - "epoch": 0.74, - "learning_rate": 1.3083494013721359e-05, - "loss": 0.1545, + "epoch": 0.37, + "learning_rate": 3.158352162144024e-05, + "loss": 0.1537, "step": 165720 }, { - "epoch": 0.74, - "learning_rate": 1.3081251961795434e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.158240307823092e-05, + "loss": 0.1496, "step": 165730 }, { - "epoch": 0.74, - "learning_rate": 1.3079009909869513e-05, - "loss": 0.164, + "epoch": 0.37, + "learning_rate": 3.158128453502159e-05, + "loss": 0.1523, "step": 165740 }, { - "epoch": 0.74, - "learning_rate": 1.307676785794359e-05, - "loss": 0.1609, + "epoch": 0.37, + "learning_rate": 3.158016599181227e-05, + "loss": 0.1577, "step": 165750 }, { - "epoch": 0.74, - "learning_rate": 1.3074525806017667e-05, - "loss": 0.1676, + "epoch": 0.37, + "learning_rate": 3.157904744860294e-05, + "loss": 0.1542, "step": 165760 }, { - "epoch": 0.74, - "learning_rate": 1.3072283754091746e-05, - "loss": 0.1658, + "epoch": 0.37, + "learning_rate": 3.157792890539362e-05, + "loss": 0.155, "step": 165770 }, { - "epoch": 0.74, - "learning_rate": 1.3070041702165823e-05, - "loss": 0.1632, + "epoch": 0.37, + "learning_rate": 3.1576810362184295e-05, + "loss": 0.1592, "step": 165780 }, { - "epoch": 0.74, - "learning_rate": 1.3067799650239902e-05, - "loss": 0.1619, + "epoch": 0.37, + "learning_rate": 3.1575691818974966e-05, + "loss": 0.1504, "step": 165790 }, { - "epoch": 0.74, - "learning_rate": 1.3065557598313977e-05, - "loss": 0.1617, + "epoch": 0.37, + "learning_rate": 3.1574573275765644e-05, + "loss": 0.1571, "step": 165800 }, { - "epoch": 0.74, - "learning_rate": 1.3063315546388056e-05, - "loss": 0.1559, + "epoch": 0.37, + "learning_rate": 3.1573454732556315e-05, + "loss": 0.155, "step": 165810 }, { - "epoch": 0.74, - "learning_rate": 1.3061073494462131e-05, - "loss": 0.1568, + "epoch": 0.37, + "learning_rate": 3.157233618934699e-05, + "loss": 0.1629, "step": 165820 }, { - "epoch": 0.74, - "learning_rate": 1.305883144253621e-05, - "loss": 0.1635, + "epoch": 0.37, + "learning_rate": 3.157121764613767e-05, + "loss": 0.158, "step": 165830 }, { - "epoch": 0.74, - "learning_rate": 1.3056589390610288e-05, - "loss": 0.1615, + "epoch": 0.37, + "learning_rate": 3.157009910292835e-05, + "loss": 0.1524, "step": 165840 }, { - "epoch": 0.74, - "learning_rate": 1.3054347338684364e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.156898055971903e-05, + "loss": 0.1553, "step": 165850 }, { - "epoch": 0.74, - "learning_rate": 1.3052105286758442e-05, - "loss": 0.1629, + "epoch": 0.37, + "learning_rate": 3.15678620165097e-05, + "loss": 0.1525, "step": 165860 }, { - "epoch": 0.74, - "learning_rate": 1.3049863234832518e-05, - "loss": 0.1655, + "epoch": 0.37, + "learning_rate": 3.1566743473300376e-05, + "loss": 0.1514, "step": 165870 }, { - "epoch": 0.74, - "learning_rate": 1.3047621182906597e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.1565624930091054e-05, + "loss": 0.1568, "step": 165880 }, { - "epoch": 0.74, - "learning_rate": 1.3045379130980674e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.1564506386881725e-05, + "loss": 0.1561, "step": 165890 }, { - "epoch": 0.74, - "learning_rate": 1.304313707905475e-05, - "loss": 0.1652, + "epoch": 0.37, + "learning_rate": 3.15633878436724e-05, + "loss": 0.1582, "step": 165900 }, { - "epoch": 0.74, - "learning_rate": 1.304089502712883e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.1562269300463074e-05, + "loss": 0.153, "step": 165910 }, { - "epoch": 0.74, - "learning_rate": 1.3038652975202906e-05, - "loss": 0.1596, + "epoch": 0.37, + "learning_rate": 3.156115075725375e-05, + "loss": 0.1521, "step": 165920 }, { - "epoch": 0.74, - "learning_rate": 1.3036410923276985e-05, - "loss": 0.1638, + "epoch": 0.37, + "learning_rate": 3.156003221404443e-05, + "loss": 0.1576, "step": 165930 }, { - "epoch": 0.74, - "learning_rate": 1.303416887135106e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.155891367083511e-05, + "loss": 0.1566, "step": 165940 }, { - "epoch": 0.74, - "learning_rate": 1.3031926819425139e-05, - "loss": 0.1658, + "epoch": 0.37, + "learning_rate": 3.1557795127625786e-05, + "loss": 0.1551, "step": 165950 }, { - "epoch": 0.74, - "learning_rate": 1.3029684767499218e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.155667658441646e-05, + "loss": 0.1544, "step": 165960 }, { - "epoch": 0.74, - "learning_rate": 1.3027442715573293e-05, - "loss": 0.1554, + "epoch": 0.37, + "learning_rate": 3.1555558041207135e-05, + "loss": 0.155, "step": 165970 }, { - "epoch": 0.74, - "learning_rate": 1.3025200663647372e-05, - "loss": 0.1627, + "epoch": 0.37, + "learning_rate": 3.1554439497997806e-05, + "loss": 0.1517, "step": 165980 }, { - "epoch": 0.74, - "learning_rate": 1.3022958611721447e-05, - "loss": 0.1595, + "epoch": 0.37, + "learning_rate": 3.1553320954788484e-05, + "loss": 0.1506, "step": 165990 }, { - "epoch": 0.74, - "learning_rate": 1.3020716559795526e-05, - "loss": 0.1619, + "epoch": 0.37, + "learning_rate": 3.155220241157916e-05, + "loss": 0.155, "step": 166000 }, { - "epoch": 0.74, - "learning_rate": 1.3018474507869601e-05, - "loss": 0.1585, + "epoch": 0.37, + "learning_rate": 3.155108386836983e-05, + "loss": 0.1574, "step": 166010 }, { - "epoch": 0.74, - "learning_rate": 1.301623245594368e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.154996532516051e-05, + "loss": 0.1566, "step": 166020 }, { - "epoch": 0.74, - "learning_rate": 1.3013990404017759e-05, - "loss": 0.1653, + "epoch": 0.37, + "learning_rate": 3.154884678195119e-05, + "loss": 0.1533, "step": 166030 }, { - "epoch": 0.74, - "learning_rate": 1.3011748352091836e-05, - "loss": 0.1563, + "epoch": 0.37, + "learning_rate": 3.154772823874187e-05, + "loss": 0.1556, "step": 166040 }, { - "epoch": 0.74, - "learning_rate": 1.3009506300165913e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.1546609695532545e-05, + "loss": 0.1517, "step": 166050 }, { - "epoch": 0.74, - "learning_rate": 1.300726424823999e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.1545491152323216e-05, + "loss": 0.156, "step": 166060 }, { - "epoch": 0.74, - "learning_rate": 1.3005022196314068e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.1544372609113894e-05, + "loss": 0.1549, "step": 166070 }, { - "epoch": 0.74, - "learning_rate": 1.3002780144388144e-05, - "loss": 0.159, + "epoch": 0.37, + "learning_rate": 3.1543254065904565e-05, + "loss": 0.1549, "step": 166080 }, { - "epoch": 0.74, - "learning_rate": 1.3000538092462222e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.154213552269524e-05, + "loss": 0.1551, "step": 166090 }, { - "epoch": 0.74, - "learning_rate": 1.2998296040536301e-05, - "loss": 0.1548, + "epoch": 0.37, + "learning_rate": 3.154101697948592e-05, + "loss": 0.1561, "step": 166100 }, { - "epoch": 0.74, - "learning_rate": 1.2996053988610377e-05, - "loss": 0.1601, + "epoch": 0.37, + "learning_rate": 3.153989843627659e-05, + "loss": 0.1473, "step": 166110 }, { - "epoch": 0.74, - "learning_rate": 1.2993811936684455e-05, - "loss": 0.1516, + "epoch": 0.37, + "learning_rate": 3.153877989306727e-05, + "loss": 0.1576, "step": 166120 }, { - "epoch": 0.74, - "learning_rate": 1.299156988475853e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.153766134985794e-05, + "loss": 0.157, "step": 166130 }, { - "epoch": 0.74, - "learning_rate": 1.298932783283261e-05, - "loss": 0.1581, + "epoch": 0.37, + "learning_rate": 3.1536542806648626e-05, + "loss": 0.1536, "step": 166140 }, { - "epoch": 0.74, - "learning_rate": 1.2987085780906685e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.1535424263439304e-05, + "loss": 0.1558, "step": 166150 }, { - "epoch": 0.74, - "learning_rate": 1.2984843728980763e-05, - "loss": 0.164, + "epoch": 0.37, + "learning_rate": 3.1534305720229975e-05, + "loss": 0.1554, "step": 166160 }, { - "epoch": 0.74, - "learning_rate": 1.2982601677054842e-05, - "loss": 0.1572, + "epoch": 0.37, + "learning_rate": 3.153318717702065e-05, + "loss": 0.1565, "step": 166170 }, { - "epoch": 0.74, - "learning_rate": 1.2980359625128919e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.1532068633811324e-05, + "loss": 0.158, "step": 166180 }, { - "epoch": 0.74, - "learning_rate": 1.2978117573202996e-05, - "loss": 0.1566, + "epoch": 0.37, + "learning_rate": 3.1530950090602e-05, + "loss": 0.159, "step": 166190 }, { - "epoch": 0.74, - "learning_rate": 1.2975875521277073e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.152983154739268e-05, + "loss": 0.1502, "step": 166200 }, { - "epoch": 0.74, - "learning_rate": 1.2973633469351152e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.152871300418335e-05, + "loss": 0.1534, "step": 166210 }, { - "epoch": 0.74, - "learning_rate": 1.2971391417425227e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.152759446097403e-05, + "loss": 0.1573, "step": 166220 }, { - "epoch": 0.74, - "learning_rate": 1.2969149365499306e-05, - "loss": 0.1621, + "epoch": 0.37, + "learning_rate": 3.15264759177647e-05, + "loss": 0.1543, "step": 166230 }, { - "epoch": 0.74, - "learning_rate": 1.2966907313573385e-05, - "loss": 0.1575, + "epoch": 0.37, + "learning_rate": 3.152535737455538e-05, + "loss": 0.1565, "step": 166240 }, { - "epoch": 0.74, - "learning_rate": 1.296466526164746e-05, - "loss": 0.1618, + "epoch": 0.37, + "learning_rate": 3.1524238831346056e-05, + "loss": 0.1583, "step": 166250 }, { - "epoch": 0.74, - "learning_rate": 1.2962423209721539e-05, - "loss": 0.1596, + "epoch": 0.37, + "learning_rate": 3.1523120288136734e-05, + "loss": 0.1513, "step": 166260 }, { - "epoch": 0.74, - "learning_rate": 1.2960181157795614e-05, - "loss": 0.1683, + "epoch": 0.37, + "learning_rate": 3.152200174492741e-05, + "loss": 0.1549, "step": 166270 }, { - "epoch": 0.74, - "learning_rate": 1.2957939105869693e-05, - "loss": 0.1615, + "epoch": 0.37, + "learning_rate": 3.152088320171808e-05, + "loss": 0.1523, "step": 166280 }, { - "epoch": 0.74, - "learning_rate": 1.2955697053943768e-05, - "loss": 0.1617, + "epoch": 0.37, + "learning_rate": 3.151976465850876e-05, + "loss": 0.1503, "step": 166290 }, { - "epoch": 0.74, - "learning_rate": 1.2953455002017847e-05, - "loss": 0.1648, + "epoch": 0.37, + "learning_rate": 3.151864611529943e-05, + "loss": 0.1598, "step": 166300 }, { - "epoch": 0.74, - "learning_rate": 1.2951212950091925e-05, - "loss": 0.1588, + "epoch": 0.37, + "learning_rate": 3.151752757209011e-05, + "loss": 0.1529, "step": 166310 }, { - "epoch": 0.74, - "learning_rate": 1.2948970898166002e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.151640902888079e-05, + "loss": 0.1567, "step": 166320 }, { - "epoch": 0.74, - "learning_rate": 1.2946728846240081e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.151529048567146e-05, + "loss": 0.1556, "step": 166330 }, { - "epoch": 0.74, - "learning_rate": 1.2944486794314157e-05, - "loss": 0.1604, + "epoch": 0.37, + "learning_rate": 3.151417194246214e-05, + "loss": 0.1563, "step": 166340 }, { - "epoch": 0.74, - "learning_rate": 1.2942244742388235e-05, - "loss": 0.1593, + "epoch": 0.37, + "learning_rate": 3.1513053399252815e-05, + "loss": 0.1571, "step": 166350 }, { - "epoch": 0.74, - "learning_rate": 1.294000269046231e-05, - "loss": 0.1557, + "epoch": 0.37, + "learning_rate": 3.151193485604349e-05, + "loss": 0.1519, "step": 166360 }, { - "epoch": 0.74, - "learning_rate": 1.293776063853639e-05, - "loss": 0.1574, + "epoch": 0.37, + "learning_rate": 3.151081631283417e-05, + "loss": 0.1505, "step": 166370 }, { - "epoch": 0.74, - "learning_rate": 1.2935518586610468e-05, - "loss": 0.1598, + "epoch": 0.37, + "learning_rate": 3.150969776962484e-05, + "loss": 0.1627, "step": 166380 }, { - "epoch": 0.74, - "learning_rate": 1.2933276534684543e-05, - "loss": 0.1567, + "epoch": 0.37, + "learning_rate": 3.150857922641552e-05, + "loss": 0.1538, "step": 166390 }, { - "epoch": 0.74, - "learning_rate": 1.2931034482758622e-05, - "loss": 0.156, + "epoch": 0.37, + "learning_rate": 3.150746068320619e-05, + "loss": 0.1543, "step": 166400 }, { - "epoch": 0.74, - "learning_rate": 1.2928792430832697e-05, - "loss": 0.1614, + "epoch": 0.37, + "learning_rate": 3.150634213999687e-05, + "loss": 0.1567, "step": 166410 }, { - "epoch": 0.74, - "learning_rate": 1.2926550378906776e-05, - "loss": 0.1562, + "epoch": 0.37, + "learning_rate": 3.150522359678755e-05, + "loss": 0.1552, "step": 166420 }, { - "epoch": 0.74, - "learning_rate": 1.2924308326980853e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.150410505357822e-05, + "loss": 0.1519, "step": 166430 }, { - "epoch": 0.74, - "learning_rate": 1.292206627505493e-05, - "loss": 0.1555, + "epoch": 0.37, + "learning_rate": 3.1502986510368896e-05, + "loss": 0.1513, "step": 166440 }, { - "epoch": 0.74, - "learning_rate": 1.2919824223129009e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.1501867967159574e-05, + "loss": 0.1555, "step": 166450 }, { - "epoch": 0.74, - "learning_rate": 1.2917582171203086e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.150074942395025e-05, + "loss": 0.1534, "step": 166460 }, { - "epoch": 0.74, - "learning_rate": 1.2915340119277165e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.149963088074093e-05, + "loss": 0.1545, "step": 166470 }, { - "epoch": 0.74, - "learning_rate": 1.291309806735124e-05, - "loss": 0.1529, + "epoch": 0.37, + "learning_rate": 3.14985123375316e-05, + "loss": 0.151, "step": 166480 }, { - "epoch": 0.74, - "learning_rate": 1.2910856015425319e-05, - "loss": 0.1547, + "epoch": 0.37, + "learning_rate": 3.149739379432228e-05, + "loss": 0.1602, "step": 166490 }, { - "epoch": 0.74, - "learning_rate": 1.2908613963499394e-05, - "loss": 0.1611, + "epoch": 0.37, + "learning_rate": 3.149627525111295e-05, + "loss": 0.1519, "step": 166500 }, { - "epoch": 0.74, - "learning_rate": 1.2906371911573473e-05, - "loss": 0.1671, + "epoch": 0.37, + "learning_rate": 3.149515670790363e-05, + "loss": 0.15, "step": 166510 }, { - "epoch": 0.74, - "learning_rate": 1.2904129859647551e-05, - "loss": 0.1626, + "epoch": 0.37, + "learning_rate": 3.1494038164694306e-05, + "loss": 0.1572, "step": 166520 }, { - "epoch": 0.74, - "learning_rate": 1.2901887807721627e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.149291962148498e-05, + "loss": 0.1541, "step": 166530 }, { - "epoch": 0.74, - "learning_rate": 1.2899645755795705e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.1491801078275655e-05, + "loss": 0.1522, "step": 166540 }, { - "epoch": 0.74, - "learning_rate": 1.289740370386978e-05, - "loss": 0.1545, + "epoch": 0.37, + "learning_rate": 3.149068253506633e-05, + "loss": 0.1572, "step": 166550 }, { - "epoch": 0.74, - "learning_rate": 1.289516165194386e-05, - "loss": 0.1628, + "epoch": 0.37, + "learning_rate": 3.148956399185701e-05, + "loss": 0.1497, "step": 166560 }, { - "epoch": 0.74, - "learning_rate": 1.2892919600017937e-05, - "loss": 0.1571, + "epoch": 0.37, + "learning_rate": 3.148844544864769e-05, + "loss": 0.1565, "step": 166570 }, { - "epoch": 0.74, - "learning_rate": 1.2890677548092015e-05, - "loss": 0.1604, + "epoch": 0.37, + "learning_rate": 3.148732690543836e-05, + "loss": 0.1523, "step": 166580 }, { - "epoch": 0.74, - "learning_rate": 1.2888435496166092e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.148620836222904e-05, + "loss": 0.1537, "step": 166590 }, { - "epoch": 0.74, - "learning_rate": 1.288619344424017e-05, - "loss": 0.1561, + "epoch": 0.37, + "learning_rate": 3.148508981901971e-05, + "loss": 0.1537, "step": 166600 }, { - "epoch": 0.74, - "learning_rate": 1.2883951392314248e-05, - "loss": 0.159, + "epoch": 0.37, + "learning_rate": 3.1483971275810387e-05, + "loss": 0.152, "step": 166610 }, { - "epoch": 0.74, - "learning_rate": 1.2881709340388323e-05, - "loss": 0.1632, + "epoch": 0.37, + "learning_rate": 3.148285273260106e-05, + "loss": 0.1532, "step": 166620 }, { - "epoch": 0.74, - "learning_rate": 1.2879467288462402e-05, - "loss": 0.1584, + "epoch": 0.37, + "learning_rate": 3.1481734189391736e-05, + "loss": 0.153, "step": 166630 }, { - "epoch": 0.74, - "learning_rate": 1.2877225236536477e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.1480615646182414e-05, + "loss": 0.1533, "step": 166640 }, { - "epoch": 0.74, - "learning_rate": 1.2874983184610556e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.1479497102973085e-05, + "loss": 0.1546, "step": 166650 }, { - "epoch": 0.74, - "learning_rate": 1.2872741132684635e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.147837855976376e-05, + "loss": 0.1562, "step": 166660 }, { - "epoch": 0.74, - "learning_rate": 1.287049908075871e-05, - "loss": 0.1555, + "epoch": 0.37, + "learning_rate": 3.147726001655444e-05, + "loss": 0.1605, "step": 166670 }, { - "epoch": 0.74, - "learning_rate": 1.2868257028832789e-05, - "loss": 0.1653, + "epoch": 0.37, + "learning_rate": 3.147614147334512e-05, + "loss": 0.1603, "step": 166680 }, { - "epoch": 0.74, - "learning_rate": 1.2866014976906864e-05, - "loss": 0.1609, + "epoch": 0.37, + "learning_rate": 3.1475022930135796e-05, + "loss": 0.1518, "step": 166690 }, { - "epoch": 0.74, - "learning_rate": 1.2863772924980943e-05, - "loss": 0.1587, + "epoch": 0.37, + "learning_rate": 3.147390438692647e-05, + "loss": 0.1547, "step": 166700 }, { - "epoch": 0.74, - "learning_rate": 1.286153087305502e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.1472785843717146e-05, + "loss": 0.1571, "step": 166710 }, { - "epoch": 0.74, - "learning_rate": 1.2859288821129099e-05, - "loss": 0.1618, + "epoch": 0.37, + "learning_rate": 3.147166730050782e-05, + "loss": 0.1558, "step": 166720 }, { - "epoch": 0.74, - "learning_rate": 1.2857046769203176e-05, - "loss": 0.159, + "epoch": 0.37, + "learning_rate": 3.1470548757298495e-05, + "loss": 0.1521, "step": 166730 }, { - "epoch": 0.74, - "learning_rate": 1.2854804717277253e-05, - "loss": 0.1561, + "epoch": 0.37, + "learning_rate": 3.146943021408917e-05, + "loss": 0.1539, "step": 166740 }, { - "epoch": 0.74, - "learning_rate": 1.2852562665351331e-05, - "loss": 0.1496, + "epoch": 0.37, + "learning_rate": 3.1468311670879844e-05, + "loss": 0.1483, "step": 166750 }, { - "epoch": 0.74, - "learning_rate": 1.2850320613425407e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.146719312767052e-05, + "loss": 0.1562, "step": 166760 }, { - "epoch": 0.74, - "learning_rate": 1.2848078561499485e-05, - "loss": 0.1631, + "epoch": 0.37, + "learning_rate": 3.14660745844612e-05, + "loss": 0.1521, "step": 166770 }, { - "epoch": 0.74, - "learning_rate": 1.284583650957356e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.146495604125188e-05, + "loss": 0.1551, "step": 166780 }, { - "epoch": 0.74, - "learning_rate": 1.284359445764764e-05, - "loss": 0.1638, + "epoch": 0.37, + "learning_rate": 3.1463837498042555e-05, + "loss": 0.1518, "step": 166790 }, { - "epoch": 0.74, - "learning_rate": 1.2841352405721718e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.1462718954833227e-05, + "loss": 0.1595, "step": 166800 }, { - "epoch": 0.74, - "learning_rate": 1.2839110353795794e-05, - "loss": 0.162, + "epoch": 0.37, + "learning_rate": 3.1461600411623904e-05, + "loss": 0.1473, "step": 166810 }, { - "epoch": 0.74, - "learning_rate": 1.2836868301869872e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.1460481868414576e-05, + "loss": 0.1553, "step": 166820 }, { - "epoch": 0.74, - "learning_rate": 1.2834626249943948e-05, - "loss": 0.1577, + "epoch": 0.37, + "learning_rate": 3.1459363325205254e-05, + "loss": 0.1504, "step": 166830 }, { - "epoch": 0.74, - "learning_rate": 1.2832384198018026e-05, - "loss": 0.1558, + "epoch": 0.37, + "learning_rate": 3.145824478199593e-05, + "loss": 0.1493, "step": 166840 }, { - "epoch": 0.74, - "learning_rate": 1.2830142146092103e-05, - "loss": 0.1584, + "epoch": 0.37, + "learning_rate": 3.14571262387866e-05, + "loss": 0.154, "step": 166850 }, { - "epoch": 0.74, - "learning_rate": 1.2827900094166182e-05, - "loss": 0.1587, + "epoch": 0.37, + "learning_rate": 3.145600769557728e-05, + "loss": 0.156, "step": 166860 }, { - "epoch": 0.74, - "learning_rate": 1.282565804224026e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.145488915236796e-05, + "loss": 0.1528, "step": 166870 }, { - "epoch": 0.74, - "learning_rate": 1.2823415990314336e-05, - "loss": 0.1566, + "epoch": 0.37, + "learning_rate": 3.1453770609158636e-05, + "loss": 0.1574, "step": 166880 }, { - "epoch": 0.75, - "learning_rate": 1.2821173938388415e-05, - "loss": 0.1599, + "epoch": 0.37, + "learning_rate": 3.1452652065949314e-05, + "loss": 0.1528, "step": 166890 }, { - "epoch": 0.75, - "learning_rate": 1.281893188646249e-05, - "loss": 0.1542, + "epoch": 0.37, + "learning_rate": 3.1451533522739986e-05, + "loss": 0.1611, "step": 166900 }, { - "epoch": 0.75, - "learning_rate": 1.2816689834536569e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.1450414979530663e-05, + "loss": 0.1502, "step": 166910 }, { - "epoch": 0.75, - "learning_rate": 1.2814447782610644e-05, - "loss": 0.1593, + "epoch": 0.37, + "learning_rate": 3.1449296436321335e-05, + "loss": 0.1534, "step": 166920 }, { - "epoch": 0.75, - "learning_rate": 1.2812205730684723e-05, - "loss": 0.1539, + "epoch": 0.37, + "learning_rate": 3.144817789311201e-05, + "loss": 0.1471, "step": 166930 }, { - "epoch": 0.75, - "learning_rate": 1.2809963678758802e-05, - "loss": 0.1633, + "epoch": 0.37, + "learning_rate": 3.1447059349902684e-05, + "loss": 0.1526, "step": 166940 }, { - "epoch": 0.75, - "learning_rate": 1.2807721626832877e-05, - "loss": 0.1581, + "epoch": 0.37, + "learning_rate": 3.144594080669336e-05, + "loss": 0.1551, "step": 166950 }, { - "epoch": 0.75, - "learning_rate": 1.2805479574906956e-05, - "loss": 0.1661, + "epoch": 0.37, + "learning_rate": 3.144482226348404e-05, + "loss": 0.1618, "step": 166960 }, { - "epoch": 0.75, - "learning_rate": 1.2803237522981033e-05, - "loss": 0.1584, + "epoch": 0.37, + "learning_rate": 3.144370372027472e-05, + "loss": 0.1574, "step": 166970 }, { - "epoch": 0.75, - "learning_rate": 1.280099547105511e-05, - "loss": 0.1625, + "epoch": 0.37, + "learning_rate": 3.1442585177065395e-05, + "loss": 0.15, "step": 166980 }, { - "epoch": 0.75, - "learning_rate": 1.2798753419129187e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.1441466633856067e-05, + "loss": 0.1533, "step": 166990 }, { - "epoch": 0.75, - "learning_rate": 1.2796511367203266e-05, - "loss": 0.1543, + "epoch": 0.37, + "learning_rate": 3.1440348090646744e-05, + "loss": 0.1597, "step": 167000 }, { - "epoch": 0.75, - "learning_rate": 1.2794269315277344e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.143922954743742e-05, + "loss": 0.1545, "step": 167010 }, { - "epoch": 0.75, - "learning_rate": 1.279202726335142e-05, - "loss": 0.1593, + "epoch": 0.37, + "learning_rate": 3.1438111004228094e-05, + "loss": 0.1528, "step": 167020 }, { - "epoch": 0.75, - "learning_rate": 1.2789785211425498e-05, - "loss": 0.1572, + "epoch": 0.37, + "learning_rate": 3.143699246101877e-05, + "loss": 0.1526, "step": 167030 }, { - "epoch": 0.75, - "learning_rate": 1.2787543159499574e-05, - "loss": 0.1565, + "epoch": 0.37, + "learning_rate": 3.143587391780944e-05, + "loss": 0.1538, "step": 167040 }, { - "epoch": 0.75, - "learning_rate": 1.2785301107573652e-05, - "loss": 0.1613, + "epoch": 0.37, + "learning_rate": 3.143475537460012e-05, + "loss": 0.1509, "step": 167050 }, { - "epoch": 0.75, - "learning_rate": 1.2783059055647728e-05, - "loss": 0.1587, + "epoch": 0.37, + "learning_rate": 3.14336368313908e-05, + "loss": 0.1487, "step": 167060 }, { - "epoch": 0.75, - "learning_rate": 1.2780817003721806e-05, - "loss": 0.1645, + "epoch": 0.37, + "learning_rate": 3.143251828818147e-05, + "loss": 0.1515, "step": 167070 }, { - "epoch": 0.75, - "learning_rate": 1.2778574951795885e-05, - "loss": 0.1562, + "epoch": 0.37, + "learning_rate": 3.143139974497215e-05, + "loss": 0.1529, "step": 167080 }, { - "epoch": 0.75, - "learning_rate": 1.277633289986996e-05, - "loss": 0.1533, + "epoch": 0.37, + "learning_rate": 3.1430281201762825e-05, + "loss": 0.1491, "step": 167090 }, { - "epoch": 0.75, - "learning_rate": 1.2774090847944039e-05, - "loss": 0.1554, + "epoch": 0.37, + "learning_rate": 3.1429162658553503e-05, + "loss": 0.1538, "step": 167100 }, { - "epoch": 0.75, - "learning_rate": 1.2771848796018116e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.142804411534418e-05, + "loss": 0.1537, "step": 167110 }, { - "epoch": 0.75, - "learning_rate": 1.2769606744092195e-05, - "loss": 0.1628, + "epoch": 0.37, + "learning_rate": 3.142692557213485e-05, + "loss": 0.1538, "step": 167120 }, { - "epoch": 0.75, - "learning_rate": 1.276736469216627e-05, - "loss": 0.1637, + "epoch": 0.37, + "learning_rate": 3.142580702892553e-05, + "loss": 0.1545, "step": 167130 }, { - "epoch": 0.75, - "learning_rate": 1.2765122640240349e-05, - "loss": 0.16, + "epoch": 0.37, + "learning_rate": 3.14246884857162e-05, + "loss": 0.1549, "step": 167140 }, { - "epoch": 0.75, - "learning_rate": 1.2762880588314428e-05, - "loss": 0.1559, + "epoch": 0.37, + "learning_rate": 3.142356994250688e-05, + "loss": 0.1506, "step": 167150 }, { - "epoch": 0.75, - "learning_rate": 1.2760638536388503e-05, - "loss": 0.1599, + "epoch": 0.37, + "learning_rate": 3.142245139929756e-05, + "loss": 0.1589, "step": 167160 }, { - "epoch": 0.75, - "learning_rate": 1.2758396484462582e-05, - "loss": 0.156, + "epoch": 0.37, + "learning_rate": 3.142133285608823e-05, + "loss": 0.1575, "step": 167170 }, { - "epoch": 0.75, - "learning_rate": 1.2756154432536657e-05, - "loss": 0.1614, + "epoch": 0.37, + "learning_rate": 3.1420214312878907e-05, + "loss": 0.1568, "step": 167180 }, { - "epoch": 0.75, - "learning_rate": 1.2753912380610736e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.1419095769669584e-05, + "loss": 0.1532, "step": 167190 }, { - "epoch": 0.75, - "learning_rate": 1.2751670328684811e-05, - "loss": 0.1607, + "epoch": 0.37, + "learning_rate": 3.141797722646026e-05, + "loss": 0.1608, "step": 167200 }, { - "epoch": 0.75, - "learning_rate": 1.274942827675889e-05, - "loss": 0.1605, + "epoch": 0.37, + "learning_rate": 3.141685868325094e-05, + "loss": 0.1543, "step": 167210 }, { - "epoch": 0.75, - "learning_rate": 1.2747186224832969e-05, - "loss": 0.1597, + "epoch": 0.37, + "learning_rate": 3.141574014004161e-05, + "loss": 0.1529, "step": 167220 }, { - "epoch": 0.75, - "learning_rate": 1.2744944172907044e-05, - "loss": 0.1598, + "epoch": 0.37, + "learning_rate": 3.141462159683229e-05, + "loss": 0.1597, "step": 167230 }, { - "epoch": 0.75, - "learning_rate": 1.2742702120981123e-05, - "loss": 0.1544, + "epoch": 0.37, + "learning_rate": 3.141350305362296e-05, + "loss": 0.153, "step": 167240 }, { - "epoch": 0.75, - "learning_rate": 1.27404600690552e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.141238451041364e-05, + "loss": 0.1485, "step": 167250 }, { - "epoch": 0.75, - "learning_rate": 1.2738218017129278e-05, - "loss": 0.1618, + "epoch": 0.37, + "learning_rate": 3.141126596720431e-05, + "loss": 0.1563, "step": 167260 }, { - "epoch": 0.75, - "learning_rate": 1.2735975965203354e-05, - "loss": 0.1553, + "epoch": 0.37, + "learning_rate": 3.141014742399499e-05, + "loss": 0.1538, "step": 167270 }, { - "epoch": 0.75, - "learning_rate": 1.2733733913277432e-05, - "loss": 0.1504, + "epoch": 0.37, + "learning_rate": 3.1409028880785665e-05, + "loss": 0.1497, "step": 167280 }, { - "epoch": 0.75, - "learning_rate": 1.2731491861351511e-05, - "loss": 0.1647, + "epoch": 0.37, + "learning_rate": 3.140791033757634e-05, + "loss": 0.1496, "step": 167290 }, { - "epoch": 0.75, - "learning_rate": 1.2729249809425586e-05, - "loss": 0.1603, + "epoch": 0.37, + "learning_rate": 3.140679179436702e-05, + "loss": 0.1534, "step": 167300 }, { - "epoch": 0.75, - "learning_rate": 1.2727231962692258e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.140567325115769e-05, + "loss": 0.1531, "step": 167310 }, { - "epoch": 0.75, - "learning_rate": 1.2724989910766333e-05, - "loss": 0.1573, + "epoch": 0.37, + "learning_rate": 3.140455470794837e-05, + "loss": 0.1506, "step": 167320 }, { - "epoch": 0.75, - "learning_rate": 1.2722747858840412e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.140343616473905e-05, + "loss": 0.1544, "step": 167330 }, { - "epoch": 0.75, - "learning_rate": 1.272050580691449e-05, - "loss": 0.1599, + "epoch": 0.37, + "learning_rate": 3.140231762152972e-05, + "loss": 0.1526, "step": 167340 }, { - "epoch": 0.75, - "learning_rate": 1.2718263754988566e-05, - "loss": 0.1544, + "epoch": 0.37, + "learning_rate": 3.14011990783204e-05, + "loss": 0.1546, "step": 167350 }, { - "epoch": 0.75, - "learning_rate": 1.2716021703062644e-05, + "epoch": 0.37, + "learning_rate": 3.140008053511107e-05, "loss": 0.1593, "step": 167360 }, { - "epoch": 0.75, - "learning_rate": 1.271377965113672e-05, - "loss": 0.1578, + "epoch": 0.37, + "learning_rate": 3.1398961991901746e-05, + "loss": 0.1561, "step": 167370 }, { - "epoch": 0.75, - "learning_rate": 1.2711537599210798e-05, - "loss": 0.1585, + "epoch": 0.37, + "learning_rate": 3.1397843448692424e-05, + "loss": 0.1544, "step": 167380 }, { - "epoch": 0.75, - "learning_rate": 1.2709295547284874e-05, - "loss": 0.1601, + "epoch": 0.37, + "learning_rate": 3.13967249054831e-05, + "loss": 0.1546, "step": 167390 }, { - "epoch": 0.75, - "learning_rate": 1.2707053495358952e-05, - "loss": 0.1629, + "epoch": 0.37, + "learning_rate": 3.139560636227378e-05, + "loss": 0.1604, "step": 167400 }, { - "epoch": 0.75, - "learning_rate": 1.2704811443433031e-05, - "loss": 0.1556, + "epoch": 0.37, + "learning_rate": 3.139448781906445e-05, + "loss": 0.152, "step": 167410 }, { - "epoch": 0.75, - "learning_rate": 1.2702569391507108e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.139336927585513e-05, + "loss": 0.1473, "step": 167420 }, { - "epoch": 0.75, - "learning_rate": 1.2700327339581187e-05, - "loss": 0.1555, + "epoch": 0.37, + "learning_rate": 3.139225073264581e-05, + "loss": 0.1549, "step": 167430 }, { - "epoch": 0.75, - "learning_rate": 1.2698085287655262e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.139113218943648e-05, + "loss": 0.151, "step": 167440 }, { - "epoch": 0.75, - "learning_rate": 1.2695843235729341e-05, - "loss": 0.1623, + "epoch": 0.37, + "learning_rate": 3.1390013646227156e-05, + "loss": 0.1487, "step": 167450 }, { - "epoch": 0.75, - "learning_rate": 1.2693601183803416e-05, - "loss": 0.1552, + "epoch": 0.37, + "learning_rate": 3.138889510301783e-05, + "loss": 0.1535, "step": 167460 }, { - "epoch": 0.75, - "learning_rate": 1.2691359131877495e-05, - "loss": 0.1536, + "epoch": 0.37, + "learning_rate": 3.1387776559808505e-05, + "loss": 0.1508, "step": 167470 }, { - "epoch": 0.75, - "learning_rate": 1.2689117079951574e-05, - "loss": 0.1583, + "epoch": 0.37, + "learning_rate": 3.138665801659918e-05, + "loss": 0.1576, "step": 167480 }, { - "epoch": 0.75, - "learning_rate": 1.2686875028025649e-05, - "loss": 0.1576, + "epoch": 0.37, + "learning_rate": 3.1385539473389855e-05, + "loss": 0.1553, "step": 167490 }, { - "epoch": 0.75, - "learning_rate": 1.2684632976099728e-05, - "loss": 0.1587, + "epoch": 0.37, + "learning_rate": 3.138442093018054e-05, + "loss": 0.1576, "step": 167500 }, { - "epoch": 0.75, - "learning_rate": 1.2682390924173803e-05, - "loss": 0.1594, + "epoch": 0.37, + "learning_rate": 3.138341424129214e-05, + "loss": 0.1528, "step": 167510 }, { - "epoch": 0.75, - "learning_rate": 1.2680148872247882e-05, - "loss": 0.1562, + "epoch": 0.37, + "learning_rate": 3.138229569808282e-05, + "loss": 0.1552, "step": 167520 }, { - "epoch": 0.75, - "learning_rate": 1.2677906820321959e-05, - "loss": 0.163, + "epoch": 0.37, + "learning_rate": 3.138117715487349e-05, + "loss": 0.1541, "step": 167530 }, { - "epoch": 0.75, - "learning_rate": 1.2675664768396036e-05, - "loss": 0.1584, + "epoch": 0.37, + "learning_rate": 3.138005861166417e-05, + "loss": 0.1534, "step": 167540 }, { - "epoch": 0.75, - "learning_rate": 1.2673422716470115e-05, - "loss": 0.1543, + "epoch": 0.37, + "learning_rate": 3.1378940068454846e-05, + "loss": 0.158, "step": 167550 }, { - "epoch": 0.75, - "learning_rate": 1.2671180664544192e-05, - "loss": 0.1546, + "epoch": 0.37, + "learning_rate": 3.1377821525245524e-05, + "loss": 0.1512, "step": 167560 }, { - "epoch": 0.75, - "learning_rate": 1.266893861261827e-05, - "loss": 0.1655, + "epoch": 0.37, + "learning_rate": 3.13767029820362e-05, + "loss": 0.1549, "step": 167570 }, { - "epoch": 0.75, - "learning_rate": 1.2666696560692346e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.137558443882687e-05, + "loss": 0.1504, "step": 167580 }, { - "epoch": 0.75, - "learning_rate": 1.2664454508766424e-05, - "loss": 0.152, + "epoch": 0.37, + "learning_rate": 3.137446589561755e-05, + "loss": 0.1496, "step": 167590 }, { - "epoch": 0.75, - "learning_rate": 1.26622124568405e-05, - "loss": 0.1564, + "epoch": 0.37, + "learning_rate": 3.137334735240823e-05, + "loss": 0.1579, "step": 167600 }, { - "epoch": 0.75, - "learning_rate": 1.2659970404914578e-05, - "loss": 0.1609, + "epoch": 0.37, + "learning_rate": 3.13722288091989e-05, + "loss": 0.1542, "step": 167610 }, { - "epoch": 0.75, - "learning_rate": 1.2657728352988657e-05, - "loss": 0.1589, + "epoch": 0.37, + "learning_rate": 3.137111026598958e-05, + "loss": 0.1549, "step": 167620 }, { - "epoch": 0.75, - "learning_rate": 1.2655486301062732e-05, - "loss": 0.1582, + "epoch": 0.37, + "learning_rate": 3.136999172278025e-05, + "loss": 0.1511, "step": 167630 }, { - "epoch": 0.75, - "learning_rate": 1.2653244249136811e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.136887317957093e-05, + "loss": 0.1588, "step": 167640 }, { - "epoch": 0.75, - "learning_rate": 1.2651002197210887e-05, - "loss": 0.156, + "epoch": 0.37, + "learning_rate": 3.13677546363616e-05, + "loss": 0.1541, "step": 167650 }, { - "epoch": 0.75, - "learning_rate": 1.2648760145284965e-05, - "loss": 0.1565, + "epoch": 0.37, + "learning_rate": 3.1366636093152276e-05, + "loss": 0.1556, "step": 167660 }, { - "epoch": 0.75, - "learning_rate": 1.2646518093359042e-05, - "loss": 0.1625, + "epoch": 0.37, + "learning_rate": 3.136551754994296e-05, + "loss": 0.1589, "step": 167670 }, { - "epoch": 0.75, - "learning_rate": 1.2644276041433121e-05, - "loss": 0.165, + "epoch": 0.37, + "learning_rate": 3.136439900673363e-05, + "loss": 0.1565, "step": 167680 }, { - "epoch": 0.75, - "learning_rate": 1.2642033989507198e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.136328046352431e-05, + "loss": 0.1574, "step": 167690 }, { - "epoch": 0.75, - "learning_rate": 1.2639791937581275e-05, - "loss": 0.1586, + "epoch": 0.37, + "learning_rate": 3.136216192031498e-05, + "loss": 0.1511, "step": 167700 }, { - "epoch": 0.75, - "learning_rate": 1.2637549885655354e-05, - "loss": 0.159, + "epoch": 0.37, + "learning_rate": 3.136104337710566e-05, + "loss": 0.1584, "step": 167710 }, { - "epoch": 0.75, - "learning_rate": 1.2635307833729429e-05, - "loss": 0.1592, + "epoch": 0.37, + "learning_rate": 3.135992483389634e-05, + "loss": 0.1531, "step": 167720 }, { - "epoch": 0.75, - "learning_rate": 1.2633065781803508e-05, - "loss": 0.1622, + "epoch": 0.37, + "learning_rate": 3.135880629068701e-05, + "loss": 0.1601, "step": 167730 }, { - "epoch": 0.75, - "learning_rate": 1.2630823729877583e-05, - "loss": 0.158, + "epoch": 0.37, + "learning_rate": 3.1357687747477686e-05, + "loss": 0.1495, "step": 167740 }, { - "epoch": 0.75, - "learning_rate": 1.2628581677951662e-05, - "loss": 0.1632, + "epoch": 0.37, + "learning_rate": 3.135656920426836e-05, + "loss": 0.1546, "step": 167750 }, { - "epoch": 0.75, - "learning_rate": 1.262633962602574e-05, - "loss": 0.1614, + "epoch": 0.37, + "learning_rate": 3.1355450661059035e-05, + "loss": 0.1485, "step": 167760 }, { - "epoch": 0.75, - "learning_rate": 1.2624097574099816e-05, - "loss": 0.1551, + "epoch": 0.37, + "learning_rate": 3.135433211784971e-05, + "loss": 0.1556, "step": 167770 }, { - "epoch": 0.75, - "learning_rate": 1.2621855522173895e-05, - "loss": 0.1566, + "epoch": 0.37, + "learning_rate": 3.135321357464039e-05, + "loss": 0.1481, "step": 167780 }, { - "epoch": 0.75, - "learning_rate": 1.261961347024797e-05, - "loss": 0.1577, + "epoch": 0.37, + "learning_rate": 3.135209503143107e-05, + "loss": 0.155, "step": 167790 }, { - "epoch": 0.75, - "learning_rate": 1.2617371418322049e-05, - "loss": 0.1616, + "epoch": 0.37, + "learning_rate": 3.135097648822174e-05, + "loss": 0.1537, "step": 167800 }, { - "epoch": 0.75, - "learning_rate": 1.2615129366396126e-05, - "loss": 0.159, + "epoch": 0.37, + "learning_rate": 3.134985794501242e-05, + "loss": 0.1543, "step": 167810 }, { - "epoch": 0.75, - "learning_rate": 1.2612887314470204e-05, - "loss": 0.1543, + "epoch": 0.37, + "learning_rate": 3.1348739401803096e-05, + "loss": 0.1509, "step": 167820 }, { - "epoch": 0.75, - "learning_rate": 1.2610645262544281e-05, - "loss": 0.1639, + "epoch": 0.37, + "learning_rate": 3.134762085859377e-05, + "loss": 0.1497, "step": 167830 }, { - "epoch": 0.75, - "learning_rate": 1.2608403210618358e-05, + "epoch": 0.37, + "learning_rate": 3.1346502315384445e-05, "loss": 0.1571, "step": 167840 }, { - "epoch": 0.75, - "learning_rate": 1.2606161158692437e-05, - "loss": 0.1579, + "epoch": 0.37, + "learning_rate": 3.1345383772175116e-05, + "loss": 0.1521, "step": 167850 }, { - "epoch": 0.75, - "learning_rate": 1.2603919106766513e-05, - "loss": 0.1597, + "epoch": 0.37, + "learning_rate": 3.1344265228965794e-05, + "loss": 0.1555, "step": 167860 }, { - "epoch": 0.75, - "learning_rate": 1.2601677054840591e-05, - "loss": 0.1539, + "epoch": 0.37, + "learning_rate": 3.134314668575647e-05, + "loss": 0.1581, "step": 167870 }, { - "epoch": 0.75, - "learning_rate": 1.2599435002914667e-05, - "loss": 0.1606, + "epoch": 0.37, + "learning_rate": 3.134202814254715e-05, + "loss": 0.1574, "step": 167880 }, { - "epoch": 0.75, - "learning_rate": 1.2597192950988745e-05, - "loss": 0.1619, + "epoch": 0.37, + "learning_rate": 3.134090959933783e-05, + "loss": 0.1558, "step": 167890 }, { - "epoch": 0.75, - "learning_rate": 1.2594950899062824e-05, - "loss": 0.1551, + "epoch": 0.37, + "learning_rate": 3.13397910561285e-05, + "loss": 0.1545, "step": 167900 }, { - "epoch": 0.75, - "learning_rate": 1.25927088471369e-05, - "loss": 0.1612, + "epoch": 0.37, + "learning_rate": 3.133867251291918e-05, + "loss": 0.1538, "step": 167910 }, { - "epoch": 0.75, - "learning_rate": 1.2590466795210978e-05, - "loss": 0.156, + "epoch": 0.37, + "learning_rate": 3.1337553969709855e-05, + "loss": 0.1552, "step": 167920 }, { - "epoch": 0.75, - "learning_rate": 1.2588224743285053e-05, - "loss": 0.1567, + "epoch": 0.37, + "learning_rate": 3.1336435426500526e-05, + "loss": 0.1554, "step": 167930 }, { - "epoch": 0.75, - "learning_rate": 1.2585982691359132e-05, - "loss": 0.1602, + "epoch": 0.37, + "learning_rate": 3.1335316883291204e-05, + "loss": 0.1588, "step": 167940 }, { - "epoch": 0.75, - "learning_rate": 1.2583740639433209e-05, - "loss": 0.1608, + "epoch": 0.37, + "learning_rate": 3.1334198340081875e-05, + "loss": 0.1585, "step": 167950 }, { - "epoch": 0.75, - "learning_rate": 1.2581498587507288e-05, - "loss": 0.1591, + "epoch": 0.37, + "learning_rate": 3.133307979687255e-05, + "loss": 0.1542, "step": 167960 }, { - "epoch": 0.75, - "learning_rate": 1.2579256535581367e-05, - "loss": 0.1597, + "epoch": 0.37, + "learning_rate": 3.133196125366323e-05, + "loss": 0.1484, "step": 167970 }, { - "epoch": 0.75, - "learning_rate": 1.2577014483655442e-05, - "loss": 0.1504, + "epoch": 0.37, + "learning_rate": 3.133084271045391e-05, + "loss": 0.1529, "step": 167980 }, { - "epoch": 0.75, - "learning_rate": 1.257477243172952e-05, - "loss": 0.1571, + "epoch": 0.37, + "learning_rate": 3.132972416724459e-05, + "loss": 0.1515, "step": 167990 }, { - "epoch": 0.75, - "learning_rate": 1.2572530379803596e-05, - "loss": 0.1638, + "epoch": 0.37, + "learning_rate": 3.132860562403526e-05, + "loss": 0.1476, "step": 168000 }, { - "epoch": 0.75, - "learning_rate": 1.2570288327877675e-05, - "loss": 0.1641, + "epoch": 0.38, + "learning_rate": 3.1327487080825936e-05, + "loss": 0.159, "step": 168010 }, { - "epoch": 0.75, - "learning_rate": 1.256804627595175e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.132636853761661e-05, + "loss": 0.1575, "step": 168020 }, { - "epoch": 0.75, - "learning_rate": 1.2565804224025829e-05, - "loss": 0.1604, + "epoch": 0.38, + "learning_rate": 3.1325249994407285e-05, + "loss": 0.1483, "step": 168030 }, { - "epoch": 0.75, - "learning_rate": 1.2563562172099907e-05, - "loss": 0.1558, + "epoch": 0.38, + "learning_rate": 3.132413145119796e-05, + "loss": 0.1528, "step": 168040 }, { - "epoch": 0.75, - "learning_rate": 1.2561320120173983e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.1323012907988634e-05, + "loss": 0.1536, "step": 168050 }, { - "epoch": 0.75, - "learning_rate": 1.2559078068248061e-05, - "loss": 0.1552, + "epoch": 0.38, + "learning_rate": 3.132189436477931e-05, + "loss": 0.156, "step": 168060 }, { - "epoch": 0.75, - "learning_rate": 1.2556836016322138e-05, - "loss": 0.1554, + "epoch": 0.38, + "learning_rate": 3.132077582156998e-05, + "loss": 0.1535, "step": 168070 }, { - "epoch": 0.75, - "learning_rate": 1.2554593964396216e-05, - "loss": 0.1578, + "epoch": 0.38, + "learning_rate": 3.131965727836067e-05, + "loss": 0.1486, "step": 168080 }, { - "epoch": 0.75, - "learning_rate": 1.2552351912470293e-05, - "loss": 0.1572, + "epoch": 0.38, + "learning_rate": 3.1318538735151346e-05, + "loss": 0.1501, "step": 168090 }, { - "epoch": 0.75, - "learning_rate": 1.2550109860544371e-05, - "loss": 0.162, + "epoch": 0.38, + "learning_rate": 3.131742019194202e-05, + "loss": 0.1526, "step": 168100 }, { - "epoch": 0.75, - "learning_rate": 1.254786780861845e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.1316301648732695e-05, + "loss": 0.1556, "step": 168110 }, { - "epoch": 0.75, - "learning_rate": 1.2545625756692525e-05, - "loss": 0.1577, + "epoch": 0.38, + "learning_rate": 3.1315183105523366e-05, + "loss": 0.1535, "step": 168120 }, { - "epoch": 0.75, - "learning_rate": 1.2543383704766604e-05, - "loss": 0.1606, + "epoch": 0.38, + "learning_rate": 3.1314064562314044e-05, + "loss": 0.1503, "step": 168130 }, { - "epoch": 0.75, - "learning_rate": 1.254114165284068e-05, - "loss": 0.1545, + "epoch": 0.38, + "learning_rate": 3.131294601910472e-05, + "loss": 0.1533, "step": 168140 }, { - "epoch": 0.75, - "learning_rate": 1.2538899600914758e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.131182747589539e-05, + "loss": 0.1584, "step": 168150 }, { - "epoch": 0.75, - "learning_rate": 1.2536657548988833e-05, - "loss": 0.1601, + "epoch": 0.38, + "learning_rate": 3.131070893268607e-05, + "loss": 0.1527, "step": 168160 }, { - "epoch": 0.75, - "learning_rate": 1.2534415497062912e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.130959038947674e-05, + "loss": 0.1592, "step": 168170 }, { - "epoch": 0.75, - "learning_rate": 1.253217344513699e-05, - "loss": 0.1589, + "epoch": 0.38, + "learning_rate": 3.130847184626742e-05, + "loss": 0.1502, "step": 168180 }, { - "epoch": 0.75, - "learning_rate": 1.2529931393211066e-05, - "loss": 0.1542, + "epoch": 0.38, + "learning_rate": 3.13073533030581e-05, + "loss": 0.1514, "step": 168190 }, { - "epoch": 0.75, - "learning_rate": 1.2527689341285145e-05, - "loss": 0.1614, + "epoch": 0.38, + "learning_rate": 3.1306234759848776e-05, + "loss": 0.1508, "step": 168200 }, { - "epoch": 0.75, - "learning_rate": 1.2525447289359222e-05, - "loss": 0.1559, + "epoch": 0.38, + "learning_rate": 3.1305116216639454e-05, + "loss": 0.1544, "step": 168210 }, { - "epoch": 0.75, - "learning_rate": 1.25232052374333e-05, - "loss": 0.1554, + "epoch": 0.38, + "learning_rate": 3.1303997673430125e-05, + "loss": 0.149, "step": 168220 }, { - "epoch": 0.75, - "learning_rate": 1.2520963185507376e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.13028791302208e-05, + "loss": 0.1548, "step": 168230 }, { - "epoch": 0.75, - "learning_rate": 1.2518721133581455e-05, - "loss": 0.1587, + "epoch": 0.38, + "learning_rate": 3.130176058701148e-05, + "loss": 0.1529, "step": 168240 }, { - "epoch": 0.75, - "learning_rate": 1.2516479081655533e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.130064204380215e-05, + "loss": 0.1533, "step": 168250 }, { - "epoch": 0.75, - "learning_rate": 1.2514237029729609e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.129952350059283e-05, + "loss": 0.1494, "step": 168260 }, { - "epoch": 0.75, - "learning_rate": 1.2511994977803687e-05, - "loss": 0.1539, + "epoch": 0.38, + "learning_rate": 3.12984049573835e-05, + "loss": 0.1505, "step": 168270 }, { - "epoch": 0.75, - "learning_rate": 1.2509752925877763e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.129728641417418e-05, + "loss": 0.15, "step": 168280 }, { - "epoch": 0.75, - "learning_rate": 1.2507510873951841e-05, - "loss": 0.1601, + "epoch": 0.38, + "learning_rate": 3.129616787096486e-05, + "loss": 0.1535, "step": 168290 }, { - "epoch": 0.75, - "learning_rate": 1.250526882202592e-05, - "loss": 0.1578, + "epoch": 0.38, + "learning_rate": 3.1295049327755535e-05, + "loss": 0.1526, "step": 168300 }, { - "epoch": 0.75, - "learning_rate": 1.2503026770099996e-05, - "loss": 0.157, + "epoch": 0.38, + "learning_rate": 3.129393078454621e-05, + "loss": 0.1507, "step": 168310 }, { - "epoch": 0.75, - "learning_rate": 1.2500784718174074e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.1292812241336884e-05, + "loss": 0.1562, "step": 168320 }, { - "epoch": 0.75, - "learning_rate": 1.249854266624815e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.129169369812756e-05, + "loss": 0.1537, "step": 168330 }, { - "epoch": 0.75, - "learning_rate": 1.2496300614322228e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.129057515491823e-05, + "loss": 0.1461, "step": 168340 }, { - "epoch": 0.75, - "learning_rate": 1.2494058562396305e-05, - "loss": 0.1626, + "epoch": 0.38, + "learning_rate": 3.128945661170891e-05, + "loss": 0.1531, "step": 168350 }, { - "epoch": 0.75, - "learning_rate": 1.2491816510470384e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.128833806849959e-05, + "loss": 0.1542, "step": 168360 }, { - "epoch": 0.75, - "learning_rate": 1.2489574458544461e-05, - "loss": 0.1536, + "epoch": 0.38, + "learning_rate": 3.128721952529026e-05, + "loss": 0.1555, "step": 168370 }, { - "epoch": 0.75, - "learning_rate": 1.2487332406618538e-05, - "loss": 0.1556, + "epoch": 0.38, + "learning_rate": 3.128610098208094e-05, + "loss": 0.1477, "step": 168380 }, { - "epoch": 0.75, - "learning_rate": 1.2485090354692615e-05, - "loss": 0.1564, + "epoch": 0.38, + "learning_rate": 3.128509429319255e-05, + "loss": 0.1522, "step": 168390 }, { - "epoch": 0.75, - "learning_rate": 1.2482848302766692e-05, - "loss": 0.1595, + "epoch": 0.38, + "learning_rate": 3.1283975749983225e-05, + "loss": 0.1548, "step": 168400 }, { - "epoch": 0.75, - "learning_rate": 1.248060625084077e-05, - "loss": 0.16, + "epoch": 0.38, + "learning_rate": 3.1282857206773896e-05, + "loss": 0.1555, "step": 168410 }, { - "epoch": 0.75, - "learning_rate": 1.2478364198914848e-05, - "loss": 0.161, + "epoch": 0.38, + "learning_rate": 3.1281738663564574e-05, + "loss": 0.1564, "step": 168420 }, { - "epoch": 0.75, - "learning_rate": 1.2476122146988925e-05, - "loss": 0.1582, + "epoch": 0.38, + "learning_rate": 3.128062012035525e-05, + "loss": 0.1509, "step": 168430 }, { - "epoch": 0.75, - "learning_rate": 1.2473880095063002e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.127950157714592e-05, + "loss": 0.1484, "step": 168440 }, { - "epoch": 0.75, - "learning_rate": 1.2471638043137079e-05, - "loss": 0.159, + "epoch": 0.38, + "learning_rate": 3.12783830339366e-05, + "loss": 0.1575, "step": 168450 }, { - "epoch": 0.75, - "learning_rate": 1.2469395991211156e-05, - "loss": 0.1637, + "epoch": 0.38, + "learning_rate": 3.127726449072728e-05, + "loss": 0.1528, "step": 168460 }, { - "epoch": 0.75, - "learning_rate": 1.2467153939285233e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.1276145947517957e-05, + "loss": 0.1488, "step": 168470 }, { - "epoch": 0.75, - "learning_rate": 1.2464911887359312e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.1275027404308635e-05, + "loss": 0.1557, "step": 168480 }, { - "epoch": 0.75, - "learning_rate": 1.2462669835433389e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.1273908861099306e-05, + "loss": 0.1515, "step": 168490 }, { - "epoch": 0.75, - "learning_rate": 1.2460427783507467e-05, - "loss": 0.161, + "epoch": 0.38, + "learning_rate": 3.1272790317889984e-05, + "loss": 0.1569, "step": 168500 }, { - "epoch": 0.75, - "learning_rate": 1.2458185731581544e-05, - "loss": 0.1587, + "epoch": 0.38, + "learning_rate": 3.1271671774680655e-05, + "loss": 0.1545, "step": 168510 }, { - "epoch": 0.75, - "learning_rate": 1.2455943679655621e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.127055323147133e-05, + "loss": 0.1562, "step": 168520 }, { - "epoch": 0.75, - "learning_rate": 1.2453701627729699e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.126943468826201e-05, + "loss": 0.1478, "step": 168530 }, { - "epoch": 0.75, - "learning_rate": 1.2451459575803776e-05, - "loss": 0.1484, + "epoch": 0.38, + "learning_rate": 3.126831614505268e-05, + "loss": 0.1572, "step": 168540 }, { - "epoch": 0.75, - "learning_rate": 1.2449217523877854e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.126719760184336e-05, + "loss": 0.1484, "step": 168550 }, { - "epoch": 0.75, - "learning_rate": 1.2446975471951931e-05, - "loss": 0.1545, + "epoch": 0.38, + "learning_rate": 3.126607905863404e-05, + "loss": 0.1503, "step": 168560 }, { - "epoch": 0.75, - "learning_rate": 1.2444733420026008e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.1264960515424716e-05, + "loss": 0.1475, "step": 168570 }, { - "epoch": 0.75, - "learning_rate": 1.2442491368100085e-05, - "loss": 0.1512, + "epoch": 0.38, + "learning_rate": 3.1263841972215393e-05, + "loss": 0.1553, "step": 168580 }, { - "epoch": 0.75, - "learning_rate": 1.2440249316174162e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.1262723429006065e-05, + "loss": 0.154, "step": 168590 }, { - "epoch": 0.75, - "learning_rate": 1.243800726424824e-05, - "loss": 0.1592, + "epoch": 0.38, + "learning_rate": 3.126160488579674e-05, + "loss": 0.1538, "step": 168600 }, { - "epoch": 0.75, - "learning_rate": 1.2435765212322318e-05, - "loss": 0.1536, + "epoch": 0.38, + "learning_rate": 3.1260486342587414e-05, + "loss": 0.1537, "step": 168610 }, { - "epoch": 0.75, - "learning_rate": 1.2433523160396395e-05, - "loss": 0.1663, + "epoch": 0.38, + "learning_rate": 3.125936779937809e-05, + "loss": 0.152, "step": 168620 }, { - "epoch": 0.75, - "learning_rate": 1.2431281108470474e-05, - "loss": 0.1647, + "epoch": 0.38, + "learning_rate": 3.125824925616876e-05, + "loss": 0.1537, "step": 168630 }, { - "epoch": 0.75, - "learning_rate": 1.2429039056544551e-05, - "loss": 0.1564, + "epoch": 0.38, + "learning_rate": 3.125713071295944e-05, + "loss": 0.1545, "step": 168640 }, { - "epoch": 0.75, - "learning_rate": 1.2426797004618628e-05, - "loss": 0.1597, + "epoch": 0.38, + "learning_rate": 3.125601216975012e-05, + "loss": 0.1517, "step": 168650 }, { - "epoch": 0.75, - "learning_rate": 1.2424554952692705e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.1254893626540797e-05, + "loss": 0.1562, "step": 168660 }, { - "epoch": 0.75, - "learning_rate": 1.2422312900766782e-05, - "loss": 0.1625, + "epoch": 0.38, + "learning_rate": 3.1253775083331475e-05, + "loss": 0.1566, "step": 168670 }, { - "epoch": 0.75, - "learning_rate": 1.242007084884086e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.1252656540122146e-05, + "loss": 0.1585, "step": 168680 }, { - "epoch": 0.75, - "learning_rate": 1.2417828796914938e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.1251537996912824e-05, + "loss": 0.1496, "step": 168690 }, { - "epoch": 0.75, - "learning_rate": 1.2415586744989015e-05, - "loss": 0.1544, + "epoch": 0.38, + "learning_rate": 3.12504194537035e-05, + "loss": 0.149, "step": 168700 }, { - "epoch": 0.75, - "learning_rate": 1.2413344693063092e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.124930091049417e-05, + "loss": 0.155, "step": 168710 }, { - "epoch": 0.75, - "learning_rate": 1.2411102641137169e-05, - "loss": 0.1615, + "epoch": 0.38, + "learning_rate": 3.124818236728485e-05, + "loss": 0.1559, "step": 168720 }, { - "epoch": 0.75, - "learning_rate": 1.2408860589211246e-05, - "loss": 0.1618, + "epoch": 0.38, + "learning_rate": 3.124706382407552e-05, + "loss": 0.1543, "step": 168730 }, { - "epoch": 0.75, - "learning_rate": 1.2406618537285323e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.12459452808662e-05, + "loss": 0.1537, "step": 168740 }, { - "epoch": 0.75, - "learning_rate": 1.2404376485359401e-05, - "loss": 0.153, + "epoch": 0.38, + "learning_rate": 3.124482673765688e-05, + "loss": 0.1541, "step": 168750 }, { - "epoch": 0.75, - "learning_rate": 1.2402134433433479e-05, - "loss": 0.1547, + "epoch": 0.38, + "learning_rate": 3.124370819444755e-05, + "loss": 0.1569, "step": 168760 }, { - "epoch": 0.75, - "learning_rate": 1.2399892381507557e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.124258965123823e-05, + "loss": 0.1563, "step": 168770 }, { - "epoch": 0.75, - "learning_rate": 1.2397650329581634e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.1241471108028905e-05, + "loss": 0.1518, "step": 168780 }, { - "epoch": 0.75, - "learning_rate": 1.2395408277655711e-05, - "loss": 0.1532, + "epoch": 0.38, + "learning_rate": 3.124035256481958e-05, + "loss": 0.1524, "step": 168790 }, { - "epoch": 0.75, - "learning_rate": 1.2393166225729788e-05, - "loss": 0.1549, + "epoch": 0.38, + "learning_rate": 3.123923402161026e-05, + "loss": 0.1558, "step": 168800 }, { - "epoch": 0.75, - "learning_rate": 1.2390924173803865e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.123811547840093e-05, + "loss": 0.1517, "step": 168810 }, { - "epoch": 0.75, - "learning_rate": 1.2388682121877944e-05, - "loss": 0.1538, + "epoch": 0.38, + "learning_rate": 3.123699693519161e-05, + "loss": 0.1517, "step": 168820 }, { - "epoch": 0.75, - "learning_rate": 1.2386440069952021e-05, - "loss": 0.1549, + "epoch": 0.38, + "learning_rate": 3.123587839198228e-05, + "loss": 0.1514, "step": 168830 }, { - "epoch": 0.75, - "learning_rate": 1.2384198018026098e-05, - "loss": 0.1564, + "epoch": 0.38, + "learning_rate": 3.123475984877296e-05, + "loss": 0.1485, "step": 168840 }, { - "epoch": 0.75, - "learning_rate": 1.2381955966100175e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.1233641305563637e-05, + "loss": 0.1523, "step": 168850 }, { - "epoch": 0.75, - "learning_rate": 1.2379713914174252e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.123252276235431e-05, + "loss": 0.1518, "step": 168860 }, { - "epoch": 0.75, - "learning_rate": 1.237747186224833e-05, - "loss": 0.1558, + "epoch": 0.38, + "learning_rate": 3.1231404219144986e-05, + "loss": 0.1562, "step": 168870 }, { - "epoch": 0.75, - "learning_rate": 1.2375229810322408e-05, - "loss": 0.1556, + "epoch": 0.38, + "learning_rate": 3.1230285675935664e-05, + "loss": 0.1546, "step": 168880 }, { - "epoch": 0.75, - "learning_rate": 1.2372987758396485e-05, - "loss": 0.1578, + "epoch": 0.38, + "learning_rate": 3.122916713272634e-05, + "loss": 0.1527, "step": 168890 }, { - "epoch": 0.75, - "learning_rate": 1.2370745706470564e-05, - "loss": 0.1608, + "epoch": 0.38, + "learning_rate": 3.122804858951702e-05, + "loss": 0.1526, "step": 168900 }, { - "epoch": 0.75, - "learning_rate": 1.236850365454464e-05, - "loss": 0.1541, + "epoch": 0.38, + "learning_rate": 3.122693004630769e-05, + "loss": 0.1548, "step": 168910 }, { - "epoch": 0.75, - "learning_rate": 1.2366261602618718e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.122581150309837e-05, + "loss": 0.1551, "step": 168920 }, { - "epoch": 0.75, - "learning_rate": 1.2364019550692795e-05, - "loss": 0.1564, + "epoch": 0.38, + "learning_rate": 3.122469295988904e-05, + "loss": 0.1527, "step": 168930 }, { - "epoch": 0.75, - "learning_rate": 1.2361777498766872e-05, - "loss": 0.16, + "epoch": 0.38, + "learning_rate": 3.122357441667972e-05, + "loss": 0.1558, "step": 168940 }, { - "epoch": 0.75, - "learning_rate": 1.2359535446840949e-05, - "loss": 0.1569, + "epoch": 0.38, + "learning_rate": 3.122245587347039e-05, + "loss": 0.1525, "step": 168950 }, { - "epoch": 0.75, - "learning_rate": 1.2357293394915027e-05, - "loss": 0.1523, + "epoch": 0.38, + "learning_rate": 3.122133733026107e-05, + "loss": 0.1509, "step": 168960 }, { - "epoch": 0.75, - "learning_rate": 1.2355051342989104e-05, - "loss": 0.1541, + "epoch": 0.38, + "learning_rate": 3.1220218787051745e-05, + "loss": 0.1566, "step": 168970 }, { - "epoch": 0.75, - "learning_rate": 1.2352809291063182e-05, - "loss": 0.1618, + "epoch": 0.38, + "learning_rate": 3.121910024384242e-05, + "loss": 0.1522, "step": 168980 }, { - "epoch": 0.75, - "learning_rate": 1.2350567239137259e-05, - "loss": 0.1525, + "epoch": 0.38, + "learning_rate": 3.12179817006331e-05, + "loss": 0.1564, "step": 168990 }, { - "epoch": 0.75, - "learning_rate": 1.2348325187211336e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.121686315742377e-05, + "loss": 0.1527, "step": 169000 }, { - "epoch": 0.75, - "learning_rate": 1.2346083135285413e-05, - "loss": 0.1587, + "epoch": 0.38, + "learning_rate": 3.121574461421445e-05, + "loss": 0.1523, "step": 169010 }, { - "epoch": 0.75, - "learning_rate": 1.2343841083359491e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.121462607100513e-05, + "loss": 0.1561, "step": 169020 }, { - "epoch": 0.75, - "learning_rate": 1.2341599031433568e-05, - "loss": 0.1535, + "epoch": 0.38, + "learning_rate": 3.12135075277958e-05, + "loss": 0.1509, "step": 169030 }, { - "epoch": 0.75, - "learning_rate": 1.2339356979507647e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.1212388984586477e-05, + "loss": 0.1572, "step": 169040 }, { - "epoch": 0.75, - "learning_rate": 1.2337114927581724e-05, - "loss": 0.1601, + "epoch": 0.38, + "learning_rate": 3.121127044137715e-05, + "loss": 0.1523, "step": 169050 }, { - "epoch": 0.75, - "learning_rate": 1.2334872875655801e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.1210151898167826e-05, + "loss": 0.1559, "step": 169060 }, { - "epoch": 0.75, - "learning_rate": 1.2332630823729878e-05, - "loss": 0.1609, + "epoch": 0.38, + "learning_rate": 3.1209033354958504e-05, + "loss": 0.15, "step": 169070 }, { - "epoch": 0.75, - "learning_rate": 1.2330388771803955e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.120791481174918e-05, + "loss": 0.1537, "step": 169080 }, { - "epoch": 0.75, - "learning_rate": 1.2328146719878032e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.120679626853986e-05, + "loss": 0.1513, "step": 169090 }, { - "epoch": 0.75, - "learning_rate": 1.2325904667952111e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.120567772533053e-05, + "loss": 0.1481, "step": 169100 }, { - "epoch": 0.75, - "learning_rate": 1.2323662616026188e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.120455918212121e-05, + "loss": 0.1544, "step": 169110 }, { - "epoch": 0.75, - "learning_rate": 1.2321420564100265e-05, - "loss": 0.1643, + "epoch": 0.38, + "learning_rate": 3.1203440638911886e-05, + "loss": 0.1499, "step": 169120 }, { - "epoch": 0.76, - "learning_rate": 1.2319178512174342e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.120232209570256e-05, + "loss": 0.154, "step": 169130 }, { - "epoch": 0.76, - "learning_rate": 1.2316936460248419e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.1201203552493235e-05, + "loss": 0.1545, "step": 169140 }, { - "epoch": 0.76, - "learning_rate": 1.2314694408322498e-05, - "loss": 0.1638, + "epoch": 0.38, + "learning_rate": 3.1200085009283907e-05, + "loss": 0.1502, "step": 169150 }, { - "epoch": 0.76, - "learning_rate": 1.2312452356396575e-05, - "loss": 0.161, + "epoch": 0.38, + "learning_rate": 3.1198966466074585e-05, + "loss": 0.1482, "step": 169160 }, { - "epoch": 0.76, - "learning_rate": 1.2310210304470653e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.119784792286526e-05, + "loss": 0.1539, "step": 169170 }, { - "epoch": 0.76, - "learning_rate": 1.230796825254473e-05, - "loss": 0.16, + "epoch": 0.38, + "learning_rate": 3.1196729379655934e-05, + "loss": 0.147, "step": 169180 }, { - "epoch": 0.76, - "learning_rate": 1.2305726200618807e-05, - "loss": 0.1608, + "epoch": 0.38, + "learning_rate": 3.119561083644661e-05, + "loss": 0.1514, "step": 169190 }, { - "epoch": 0.76, - "learning_rate": 1.2303484148692885e-05, - "loss": 0.1632, + "epoch": 0.38, + "learning_rate": 3.119449229323729e-05, + "loss": 0.1556, "step": 169200 }, { - "epoch": 0.76, - "learning_rate": 1.2301242096766962e-05, - "loss": 0.1577, + "epoch": 0.38, + "learning_rate": 3.119337375002797e-05, + "loss": 0.1489, "step": 169210 }, { - "epoch": 0.76, - "learning_rate": 1.2299000044841039e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.1192255206818645e-05, + "loss": 0.1521, "step": 169220 }, { - "epoch": 0.76, - "learning_rate": 1.2296757992915116e-05, - "loss": 0.1574, + "epoch": 0.38, + "learning_rate": 3.1191136663609316e-05, + "loss": 0.1523, "step": 169230 }, { - "epoch": 0.76, - "learning_rate": 1.2294515940989194e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.1190018120399994e-05, + "loss": 0.1522, "step": 169240 }, { - "epoch": 0.76, - "learning_rate": 1.2292273889063271e-05, - "loss": 0.1607, + "epoch": 0.38, + "learning_rate": 3.1188899577190666e-05, + "loss": 0.1502, "step": 169250 }, { - "epoch": 0.76, - "learning_rate": 1.2290031837137348e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.1187781033981343e-05, + "loss": 0.1516, "step": 169260 }, { - "epoch": 0.76, - "learning_rate": 1.2287789785211425e-05, - "loss": 0.1504, + "epoch": 0.38, + "learning_rate": 3.1186662490772015e-05, + "loss": 0.1533, "step": 169270 }, { - "epoch": 0.76, - "learning_rate": 1.2285547733285502e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.118554394756269e-05, + "loss": 0.1528, "step": 169280 }, { - "epoch": 0.76, - "learning_rate": 1.2283305681359581e-05, - "loss": 0.1604, + "epoch": 0.38, + "learning_rate": 3.118442540435337e-05, + "loss": 0.1531, "step": 169290 }, { - "epoch": 0.76, - "learning_rate": 1.2281063629433658e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.118330686114405e-05, + "loss": 0.154, "step": 169300 }, { - "epoch": 0.76, - "learning_rate": 1.2278821577507737e-05, - "loss": 0.1532, + "epoch": 0.38, + "learning_rate": 3.1182188317934726e-05, + "loss": 0.1527, "step": 169310 }, { - "epoch": 0.76, - "learning_rate": 1.2276579525581814e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.11810697747254e-05, + "loss": 0.1528, "step": 169320 }, { - "epoch": 0.76, - "learning_rate": 1.2274337473655891e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.1179951231516075e-05, + "loss": 0.1511, "step": 169330 }, { - "epoch": 0.76, - "learning_rate": 1.2272095421729968e-05, - "loss": 0.1574, + "epoch": 0.38, + "learning_rate": 3.117883268830675e-05, + "loss": 0.1525, "step": 169340 }, { - "epoch": 0.76, - "learning_rate": 1.2269853369804045e-05, - "loss": 0.1629, + "epoch": 0.38, + "learning_rate": 3.1177714145097425e-05, + "loss": 0.1609, "step": 169350 }, { - "epoch": 0.76, - "learning_rate": 1.2267611317878122e-05, - "loss": 0.1613, + "epoch": 0.38, + "learning_rate": 3.11765956018881e-05, + "loss": 0.1493, "step": 169360 }, { - "epoch": 0.76, - "learning_rate": 1.22653692659522e-05, - "loss": 0.1584, + "epoch": 0.38, + "learning_rate": 3.1175477058678774e-05, + "loss": 0.1534, "step": 169370 }, { - "epoch": 0.76, - "learning_rate": 1.2263127214026278e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.117435851546945e-05, + "loss": 0.1503, "step": 169380 }, { - "epoch": 0.76, - "learning_rate": 1.2260885162100355e-05, - "loss": 0.1607, + "epoch": 0.38, + "learning_rate": 3.117323997226013e-05, + "loss": 0.1506, "step": 169390 }, { - "epoch": 0.76, - "learning_rate": 1.2258643110174432e-05, - "loss": 0.1554, + "epoch": 0.38, + "learning_rate": 3.117212142905081e-05, + "loss": 0.1529, "step": 169400 }, { - "epoch": 0.76, - "learning_rate": 1.2256401058248509e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.1171002885841485e-05, + "loss": 0.1575, "step": 169410 }, { - "epoch": 0.76, - "learning_rate": 1.2254159006322587e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.1169884342632156e-05, + "loss": 0.1516, "step": 169420 }, { - "epoch": 0.76, - "learning_rate": 1.2251916954396665e-05, - "loss": 0.1562, + "epoch": 0.38, + "learning_rate": 3.1168765799422834e-05, + "loss": 0.1569, "step": 169430 }, { - "epoch": 0.76, - "learning_rate": 1.2249674902470743e-05, - "loss": 0.1573, + "epoch": 0.38, + "learning_rate": 3.116764725621351e-05, + "loss": 0.1578, "step": 169440 }, { - "epoch": 0.76, - "learning_rate": 1.224743285054482e-05, - "loss": 0.1572, + "epoch": 0.38, + "learning_rate": 3.1166528713004183e-05, + "loss": 0.1553, "step": 169450 }, { - "epoch": 0.76, - "learning_rate": 1.2245190798618897e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.116541016979486e-05, + "loss": 0.1557, "step": 169460 }, { - "epoch": 0.76, - "learning_rate": 1.2242948746692974e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.116429162658553e-05, + "loss": 0.1547, "step": 169470 }, { - "epoch": 0.76, - "learning_rate": 1.2240706694767051e-05, - "loss": 0.1616, + "epoch": 0.38, + "learning_rate": 3.116317308337621e-05, + "loss": 0.1533, "step": 169480 }, { - "epoch": 0.76, - "learning_rate": 1.2238464642841128e-05, - "loss": 0.1683, + "epoch": 0.38, + "learning_rate": 3.116205454016689e-05, + "loss": 0.1517, "step": 169490 }, { - "epoch": 0.76, - "learning_rate": 1.2236222590915205e-05, - "loss": 0.1614, + "epoch": 0.38, + "learning_rate": 3.1160935996957566e-05, + "loss": 0.1546, "step": 169500 }, { - "epoch": 0.76, - "learning_rate": 1.2233980538989284e-05, - "loss": 0.1542, + "epoch": 0.38, + "learning_rate": 3.1159817453748244e-05, + "loss": 0.1541, "step": 169510 }, { - "epoch": 0.76, - "learning_rate": 1.2231962692255954e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.1158698910538915e-05, + "loss": 0.1494, "step": 169520 }, { - "epoch": 0.76, - "learning_rate": 1.222972064033003e-05, - "loss": 0.1531, + "epoch": 0.38, + "learning_rate": 3.115758036732959e-05, + "loss": 0.1492, "step": 169530 }, { - "epoch": 0.76, - "learning_rate": 1.2227478588404108e-05, - "loss": 0.1598, + "epoch": 0.38, + "learning_rate": 3.115646182412027e-05, + "loss": 0.1546, "step": 169540 }, { - "epoch": 0.76, - "learning_rate": 1.2225236536478185e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.115534328091094e-05, + "loss": 0.1531, "step": 169550 }, { - "epoch": 0.76, - "learning_rate": 1.2222994484552262e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.115422473770162e-05, + "loss": 0.1549, "step": 169560 }, { - "epoch": 0.76, - "learning_rate": 1.222075243262634e-05, - "loss": 0.1592, + "epoch": 0.38, + "learning_rate": 3.115310619449229e-05, + "loss": 0.1563, "step": 169570 }, { - "epoch": 0.76, - "learning_rate": 1.2218510380700417e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.115198765128297e-05, + "loss": 0.1535, "step": 169580 }, { - "epoch": 0.76, - "learning_rate": 1.2216268328774494e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.115086910807364e-05, + "loss": 0.1597, "step": 169590 }, { - "epoch": 0.76, - "learning_rate": 1.2214026276848573e-05, - "loss": 0.1582, + "epoch": 0.38, + "learning_rate": 3.114975056486432e-05, + "loss": 0.1518, "step": 169600 }, { - "epoch": 0.76, - "learning_rate": 1.221178422492265e-05, - "loss": 0.1584, + "epoch": 0.38, + "learning_rate": 3.1148632021655e-05, + "loss": 0.1564, "step": 169610 }, { - "epoch": 0.76, - "learning_rate": 1.2209542172996727e-05, - "loss": 0.1541, + "epoch": 0.38, + "learning_rate": 3.1147513478445674e-05, + "loss": 0.1547, "step": 169620 }, { - "epoch": 0.76, - "learning_rate": 1.2207300121070804e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.114639493523635e-05, + "loss": 0.1481, "step": 169630 }, { - "epoch": 0.76, - "learning_rate": 1.2205058069144883e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.1145276392027023e-05, + "loss": 0.1517, "step": 169640 }, { - "epoch": 0.76, - "learning_rate": 1.220281601721896e-05, - "loss": 0.1572, + "epoch": 0.38, + "learning_rate": 3.11441578488177e-05, + "loss": 0.1538, "step": 169650 }, { - "epoch": 0.76, - "learning_rate": 1.2200573965293037e-05, - "loss": 0.1531, + "epoch": 0.38, + "learning_rate": 3.114303930560838e-05, + "loss": 0.1473, "step": 169660 }, { - "epoch": 0.76, - "learning_rate": 1.2198331913367114e-05, - "loss": 0.1534, + "epoch": 0.38, + "learning_rate": 3.114192076239905e-05, + "loss": 0.151, "step": 169670 }, { - "epoch": 0.76, - "learning_rate": 1.2196089861441191e-05, - "loss": 0.1517, + "epoch": 0.38, + "learning_rate": 3.114080221918973e-05, + "loss": 0.15, "step": 169680 }, { - "epoch": 0.76, - "learning_rate": 1.2193847809515268e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.11396836759804e-05, + "loss": 0.1523, "step": 169690 }, { - "epoch": 0.76, - "learning_rate": 1.2191605757589345e-05, - "loss": 0.158, + "epoch": 0.38, + "learning_rate": 3.113856513277108e-05, + "loss": 0.1477, "step": 169700 }, { - "epoch": 0.76, - "learning_rate": 1.2189363705663424e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.1137446589561755e-05, + "loss": 0.1536, "step": 169710 }, { - "epoch": 0.76, - "learning_rate": 1.21871216537375e-05, - "loss": 0.1521, + "epoch": 0.38, + "learning_rate": 3.113632804635243e-05, + "loss": 0.1546, "step": 169720 }, { - "epoch": 0.76, - "learning_rate": 1.218487960181158e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.113520950314311e-05, + "loss": 0.1586, "step": 169730 }, { - "epoch": 0.76, - "learning_rate": 1.2182637549885657e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.113409095993378e-05, + "loss": 0.1537, "step": 169740 }, { - "epoch": 0.76, - "learning_rate": 1.2180395497959734e-05, - "loss": 0.1587, + "epoch": 0.38, + "learning_rate": 3.113297241672446e-05, + "loss": 0.1572, "step": 169750 }, { - "epoch": 0.76, - "learning_rate": 1.217815344603381e-05, - "loss": 0.1601, + "epoch": 0.38, + "learning_rate": 3.113185387351514e-05, + "loss": 0.1484, "step": 169760 }, { - "epoch": 0.76, - "learning_rate": 1.2175911394107888e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.113073533030581e-05, + "loss": 0.1485, "step": 169770 }, { - "epoch": 0.76, - "learning_rate": 1.2173669342181966e-05, - "loss": 0.154, + "epoch": 0.38, + "learning_rate": 3.112961678709649e-05, + "loss": 0.1568, "step": 169780 }, { - "epoch": 0.76, - "learning_rate": 1.2171427290256043e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.112849824388716e-05, + "loss": 0.1526, "step": 169790 }, { - "epoch": 0.76, - "learning_rate": 1.216918523833012e-05, - "loss": 0.1561, + "epoch": 0.38, + "learning_rate": 3.1127379700677836e-05, + "loss": 0.1567, "step": 169800 }, { - "epoch": 0.76, - "learning_rate": 1.2166943186404197e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.1126261157468514e-05, + "loss": 0.152, "step": 169810 }, { - "epoch": 0.76, - "learning_rate": 1.2164701134478274e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.112514261425919e-05, + "loss": 0.1542, "step": 169820 }, { - "epoch": 0.76, - "learning_rate": 1.2162459082552351e-05, - "loss": 0.1562, + "epoch": 0.38, + "learning_rate": 3.112402407104987e-05, + "loss": 0.154, "step": 169830 }, { - "epoch": 0.76, - "learning_rate": 1.2160217030626429e-05, - "loss": 0.1528, + "epoch": 0.38, + "learning_rate": 3.112290552784054e-05, + "loss": 0.1531, "step": 169840 }, { - "epoch": 0.76, - "learning_rate": 1.2157974978700507e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.112178698463122e-05, + "loss": 0.1542, "step": 169850 }, { - "epoch": 0.76, - "learning_rate": 1.2155732926774584e-05, - "loss": 0.1576, + "epoch": 0.38, + "learning_rate": 3.11206684414219e-05, + "loss": 0.1502, "step": 169860 }, { - "epoch": 0.76, - "learning_rate": 1.2153490874848663e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.111954989821257e-05, + "loss": 0.1548, "step": 169870 }, { - "epoch": 0.76, - "learning_rate": 1.215124882292274e-05, - "loss": 0.1572, + "epoch": 0.38, + "learning_rate": 3.1118431355003246e-05, + "loss": 0.1514, "step": 169880 }, { - "epoch": 0.76, - "learning_rate": 1.2149006770996817e-05, - "loss": 0.1561, + "epoch": 0.38, + "learning_rate": 3.111731281179392e-05, + "loss": 0.1493, "step": 169890 }, { - "epoch": 0.76, - "learning_rate": 1.2146764719070894e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.1116194268584595e-05, + "loss": 0.1515, "step": 169900 }, { - "epoch": 0.76, - "learning_rate": 1.2144522667144971e-05, - "loss": 0.1562, + "epoch": 0.38, + "learning_rate": 3.111507572537527e-05, + "loss": 0.1537, "step": 169910 }, { - "epoch": 0.76, - "learning_rate": 1.214228061521905e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.111395718216595e-05, + "loss": 0.1594, "step": 169920 }, { - "epoch": 0.76, - "learning_rate": 1.2140038563293127e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.111283863895663e-05, + "loss": 0.1516, "step": 169930 }, { - "epoch": 0.76, - "learning_rate": 1.2137796511367204e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.11117200957473e-05, + "loss": 0.1487, "step": 169940 }, { - "epoch": 0.76, - "learning_rate": 1.2135554459441281e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.111060155253798e-05, + "loss": 0.1534, "step": 169950 }, { - "epoch": 0.76, - "learning_rate": 1.2133312407515358e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.110948300932865e-05, + "loss": 0.1497, "step": 169960 }, { - "epoch": 0.76, - "learning_rate": 1.2131070355589435e-05, - "loss": 0.157, + "epoch": 0.38, + "learning_rate": 3.110836446611933e-05, + "loss": 0.1555, "step": 169970 }, { - "epoch": 0.76, - "learning_rate": 1.2128828303663514e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.1107245922910005e-05, + "loss": 0.1524, "step": 169980 }, { - "epoch": 0.76, - "learning_rate": 1.212658625173759e-05, - "loss": 0.1596, + "epoch": 0.38, + "learning_rate": 3.1106127379700676e-05, + "loss": 0.1519, "step": 169990 }, { - "epoch": 0.76, - "learning_rate": 1.212434419981167e-05, - "loss": 0.1587, + "epoch": 0.38, + "learning_rate": 3.1105008836491354e-05, + "loss": 0.155, "step": 170000 }, { - "epoch": 0.76, - "learning_rate": 1.2122102147885746e-05, - "loss": 0.1657, + "epoch": 0.38, + "learning_rate": 3.1103890293282025e-05, + "loss": 0.1567, "step": 170010 }, { - "epoch": 0.76, - "learning_rate": 1.2119860095959823e-05, - "loss": 0.1617, + "epoch": 0.38, + "learning_rate": 3.11027717500727e-05, + "loss": 0.1515, "step": 170020 }, { - "epoch": 0.76, - "learning_rate": 1.21176180440339e-05, - "loss": 0.1573, + "epoch": 0.38, + "learning_rate": 3.110165320686339e-05, + "loss": 0.1541, "step": 170030 }, { - "epoch": 0.76, - "learning_rate": 1.2115375992107977e-05, - "loss": 0.1517, + "epoch": 0.38, + "learning_rate": 3.110053466365406e-05, + "loss": 0.155, "step": 170040 }, { - "epoch": 0.76, - "learning_rate": 1.2113133940182054e-05, - "loss": 0.1643, + "epoch": 0.38, + "learning_rate": 3.109941612044474e-05, + "loss": 0.1548, "step": 170050 }, { - "epoch": 0.76, - "learning_rate": 1.2110891888256133e-05, - "loss": 0.1644, + "epoch": 0.38, + "learning_rate": 3.109829757723541e-05, + "loss": 0.1512, "step": 170060 }, { - "epoch": 0.76, - "learning_rate": 1.210864983633021e-05, - "loss": 0.1613, + "epoch": 0.38, + "learning_rate": 3.1097179034026086e-05, + "loss": 0.1501, "step": 170070 }, { - "epoch": 0.76, - "learning_rate": 1.2106407784404287e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.1096060490816764e-05, + "loss": 0.1525, "step": 170080 }, { - "epoch": 0.76, - "learning_rate": 1.2104165732478364e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.1094941947607435e-05, + "loss": 0.149, "step": 170090 }, { - "epoch": 0.76, - "learning_rate": 1.2101923680552441e-05, - "loss": 0.1557, + "epoch": 0.38, + "learning_rate": 3.109382340439811e-05, + "loss": 0.1535, "step": 170100 }, { - "epoch": 0.76, - "learning_rate": 1.2099681628626518e-05, - "loss": 0.165, + "epoch": 0.38, + "learning_rate": 3.1092704861188784e-05, + "loss": 0.1528, "step": 170110 }, { - "epoch": 0.76, - "learning_rate": 1.2097439576700597e-05, - "loss": 0.16, + "epoch": 0.38, + "learning_rate": 3.109158631797946e-05, + "loss": 0.1494, "step": 170120 }, { - "epoch": 0.76, - "learning_rate": 1.2095197524774674e-05, - "loss": 0.1625, + "epoch": 0.38, + "learning_rate": 3.109046777477014e-05, + "loss": 0.1561, "step": 170130 }, { - "epoch": 0.76, - "learning_rate": 1.2092955472848753e-05, - "loss": 0.1542, + "epoch": 0.38, + "learning_rate": 3.108934923156082e-05, + "loss": 0.1534, "step": 170140 }, { - "epoch": 0.76, - "learning_rate": 1.209071342092283e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.1088230688351496e-05, + "loss": 0.1529, "step": 170150 }, { - "epoch": 0.76, - "learning_rate": 1.2088471368996907e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.108711214514217e-05, + "loss": 0.154, "step": 170160 }, { - "epoch": 0.76, - "learning_rate": 1.2086229317070984e-05, - "loss": 0.164, + "epoch": 0.38, + "learning_rate": 3.1085993601932845e-05, + "loss": 0.1535, "step": 170170 }, { - "epoch": 0.76, - "learning_rate": 1.2083987265145061e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.108487505872352e-05, + "loss": 0.1546, "step": 170180 }, { - "epoch": 0.76, - "learning_rate": 1.2081745213219138e-05, - "loss": 0.1538, + "epoch": 0.38, + "learning_rate": 3.1083756515514194e-05, + "loss": 0.1515, "step": 170190 }, { - "epoch": 0.76, - "learning_rate": 1.2079503161293217e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.108263797230487e-05, + "loss": 0.1569, "step": 170200 }, { - "epoch": 0.76, - "learning_rate": 1.2077261109367294e-05, - "loss": 0.1621, + "epoch": 0.38, + "learning_rate": 3.108151942909554e-05, + "loss": 0.1474, "step": 170210 }, { - "epoch": 0.76, - "learning_rate": 1.207501905744137e-05, - "loss": 0.1586, + "epoch": 0.38, + "learning_rate": 3.108040088588622e-05, + "loss": 0.1507, "step": 170220 }, { - "epoch": 0.76, - "learning_rate": 1.2072777005515448e-05, - "loss": 0.1559, + "epoch": 0.38, + "learning_rate": 3.10792823426769e-05, + "loss": 0.1485, "step": 170230 }, { - "epoch": 0.76, - "learning_rate": 1.2070534953589525e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.107816379946758e-05, + "loss": 0.1475, "step": 170240 }, { - "epoch": 0.76, - "learning_rate": 1.2068292901663603e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.1077045256258255e-05, + "loss": 0.1549, "step": 170250 }, { - "epoch": 0.76, - "learning_rate": 1.206605084973768e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.1075926713048926e-05, + "loss": 0.1559, "step": 170260 }, { - "epoch": 0.76, - "learning_rate": 1.206380879781176e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.1074808169839604e-05, + "loss": 0.1543, "step": 170270 }, { - "epoch": 0.76, - "learning_rate": 1.2061566745885836e-05, - "loss": 0.1644, + "epoch": 0.38, + "learning_rate": 3.1073689626630275e-05, + "loss": 0.1536, "step": 170280 }, { - "epoch": 0.76, - "learning_rate": 1.2059324693959913e-05, - "loss": 0.1623, + "epoch": 0.38, + "learning_rate": 3.107257108342095e-05, + "loss": 0.1489, "step": 170290 }, { - "epoch": 0.76, - "learning_rate": 1.205708264203399e-05, - "loss": 0.1573, + "epoch": 0.38, + "learning_rate": 3.107145254021163e-05, + "loss": 0.1526, "step": 170300 }, { - "epoch": 0.76, - "learning_rate": 1.2054840590108067e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.10703339970023e-05, + "loss": 0.1552, "step": 170310 }, { - "epoch": 0.76, - "learning_rate": 1.2052598538182144e-05, - "loss": 0.1654, + "epoch": 0.38, + "learning_rate": 3.106921545379298e-05, + "loss": 0.152, "step": 170320 }, { - "epoch": 0.76, - "learning_rate": 1.2050356486256223e-05, - "loss": 0.1644, + "epoch": 0.38, + "learning_rate": 3.106809691058366e-05, + "loss": 0.1455, "step": 170330 }, { - "epoch": 0.76, - "learning_rate": 1.20481144343303e-05, - "loss": 0.1625, + "epoch": 0.38, + "learning_rate": 3.1066978367374336e-05, + "loss": 0.1496, "step": 170340 }, { - "epoch": 0.76, - "learning_rate": 1.2045872382404377e-05, - "loss": 0.1517, + "epoch": 0.38, + "learning_rate": 3.1065859824165014e-05, + "loss": 0.1535, "step": 170350 }, { - "epoch": 0.76, - "learning_rate": 1.2043630330478454e-05, - "loss": 0.1576, + "epoch": 0.38, + "learning_rate": 3.1064741280955685e-05, + "loss": 0.151, "step": 170360 }, { - "epoch": 0.76, - "learning_rate": 1.2041388278552531e-05, - "loss": 0.1589, + "epoch": 0.38, + "learning_rate": 3.106362273774636e-05, + "loss": 0.1513, "step": 170370 }, { - "epoch": 0.76, - "learning_rate": 1.2039146226626608e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.1062504194537034e-05, + "loss": 0.1546, "step": 170380 }, { - "epoch": 0.76, - "learning_rate": 1.2036904174700687e-05, - "loss": 0.1622, + "epoch": 0.38, + "learning_rate": 3.106138565132771e-05, + "loss": 0.1573, "step": 170390 }, { - "epoch": 0.76, - "learning_rate": 1.2034662122774764e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.106026710811839e-05, + "loss": 0.1545, "step": 170400 }, { - "epoch": 0.76, - "learning_rate": 1.2032420070848843e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.105914856490906e-05, + "loss": 0.1497, "step": 170410 }, { - "epoch": 0.76, - "learning_rate": 1.203017801892292e-05, - "loss": 0.1556, + "epoch": 0.38, + "learning_rate": 3.105803002169974e-05, + "loss": 0.1522, "step": 170420 }, { - "epoch": 0.76, - "learning_rate": 1.2027935966996997e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.105691147849041e-05, + "loss": 0.1506, "step": 170430 }, { - "epoch": 0.76, - "learning_rate": 1.2025693915071074e-05, - "loss": 0.1633, + "epoch": 0.38, + "learning_rate": 3.1055792935281095e-05, + "loss": 0.151, "step": 170440 }, { - "epoch": 0.76, - "learning_rate": 1.202345186314515e-05, - "loss": 0.1622, + "epoch": 0.38, + "learning_rate": 3.105467439207177e-05, + "loss": 0.1494, "step": 170450 }, { - "epoch": 0.76, - "learning_rate": 1.2021209811219228e-05, - "loss": 0.1639, + "epoch": 0.38, + "learning_rate": 3.1053555848862444e-05, + "loss": 0.1509, "step": 170460 }, { - "epoch": 0.76, - "learning_rate": 1.2018967759293306e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.105243730565312e-05, + "loss": 0.1533, "step": 170470 }, { - "epoch": 0.76, - "learning_rate": 1.2016725707367383e-05, - "loss": 0.163, + "epoch": 0.38, + "learning_rate": 3.105131876244379e-05, + "loss": 0.1515, "step": 170480 }, { - "epoch": 0.76, - "learning_rate": 1.201448365544146e-05, - "loss": 0.1636, + "epoch": 0.38, + "learning_rate": 3.105020021923447e-05, + "loss": 0.1501, "step": 170490 }, { - "epoch": 0.76, - "learning_rate": 1.2012241603515537e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.104908167602515e-05, + "loss": 0.1544, "step": 170500 }, { - "epoch": 0.76, - "learning_rate": 1.2009999551589615e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.104796313281582e-05, + "loss": 0.1555, "step": 170510 }, { - "epoch": 0.76, - "learning_rate": 1.2007757499663693e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.10468445896065e-05, + "loss": 0.1535, "step": 170520 }, { - "epoch": 0.76, - "learning_rate": 1.200551544773777e-05, - "loss": 0.1603, + "epoch": 0.38, + "learning_rate": 3.104572604639717e-05, + "loss": 0.1497, "step": 170530 }, { - "epoch": 0.76, - "learning_rate": 1.2003273395811849e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.104460750318785e-05, + "loss": 0.1512, "step": 170540 }, { - "epoch": 0.76, - "learning_rate": 1.2001031343885926e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.1043488959978525e-05, + "loss": 0.1552, "step": 170550 }, { - "epoch": 0.76, - "learning_rate": 1.1998789291960003e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.10423704167692e-05, + "loss": 0.1504, "step": 170560 }, { - "epoch": 0.76, - "learning_rate": 1.199654724003408e-05, - "loss": 0.1619, + "epoch": 0.38, + "learning_rate": 3.104125187355988e-05, + "loss": 0.1562, "step": 170570 }, { - "epoch": 0.76, - "learning_rate": 1.1994305188108157e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.104013333035055e-05, + "loss": 0.1555, "step": 170580 }, { - "epoch": 0.76, - "learning_rate": 1.1992063136182234e-05, - "loss": 0.1557, + "epoch": 0.38, + "learning_rate": 3.103901478714123e-05, + "loss": 0.1591, "step": 170590 }, { - "epoch": 0.76, - "learning_rate": 1.1989821084256311e-05, - "loss": 0.1572, + "epoch": 0.38, + "learning_rate": 3.10378962439319e-05, + "loss": 0.1505, "step": 170600 }, { - "epoch": 0.76, - "learning_rate": 1.198757903233039e-05, - "loss": 0.1578, + "epoch": 0.38, + "learning_rate": 3.103677770072258e-05, + "loss": 0.1533, "step": 170610 }, { - "epoch": 0.76, - "learning_rate": 1.1985336980404467e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.103565915751326e-05, + "loss": 0.1499, "step": 170620 }, { - "epoch": 0.76, - "learning_rate": 1.1983094928478544e-05, - "loss": 0.163, + "epoch": 0.38, + "learning_rate": 3.103454061430393e-05, + "loss": 0.1512, "step": 170630 }, { - "epoch": 0.76, - "learning_rate": 1.1980852876552621e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.1033422071094606e-05, + "loss": 0.1551, "step": 170640 }, { - "epoch": 0.76, - "learning_rate": 1.1978610824626698e-05, - "loss": 0.1631, + "epoch": 0.38, + "learning_rate": 3.1032303527885284e-05, + "loss": 0.1492, "step": 170650 }, { - "epoch": 0.76, - "learning_rate": 1.1976368772700777e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.103118498467596e-05, + "loss": 0.1485, "step": 170660 }, { - "epoch": 0.76, - "learning_rate": 1.1974126720774854e-05, - "loss": 0.1507, + "epoch": 0.38, + "learning_rate": 3.103006644146664e-05, + "loss": 0.1557, "step": 170670 }, { - "epoch": 0.76, - "learning_rate": 1.1971884668848932e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.102894789825731e-05, + "loss": 0.1532, "step": 170680 }, { - "epoch": 0.76, - "learning_rate": 1.196964261692301e-05, - "loss": 0.1547, + "epoch": 0.38, + "learning_rate": 3.102782935504799e-05, + "loss": 0.1537, "step": 170690 }, { - "epoch": 0.76, - "learning_rate": 1.1967400564997086e-05, - "loss": 0.1558, + "epoch": 0.38, + "learning_rate": 3.102671081183866e-05, + "loss": 0.1559, "step": 170700 }, { - "epoch": 0.76, - "learning_rate": 1.1965158513071163e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.102559226862934e-05, + "loss": 0.1524, "step": 170710 }, { - "epoch": 0.76, - "learning_rate": 1.196291646114524e-05, - "loss": 0.1601, + "epoch": 0.38, + "learning_rate": 3.1024473725420016e-05, + "loss": 0.157, "step": 170720 }, { - "epoch": 0.76, - "learning_rate": 1.1960674409219317e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.102335518221069e-05, + "loss": 0.147, "step": 170730 }, { - "epoch": 0.76, - "learning_rate": 1.1958432357293395e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.1022236639001365e-05, + "loss": 0.1501, "step": 170740 }, { - "epoch": 0.76, - "learning_rate": 1.1956190305367473e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.102111809579204e-05, + "loss": 0.1512, "step": 170750 }, { - "epoch": 0.76, - "learning_rate": 1.195394825344155e-05, - "loss": 0.1558, + "epoch": 0.38, + "learning_rate": 3.101999955258272e-05, + "loss": 0.1571, "step": 170760 }, { - "epoch": 0.76, - "learning_rate": 1.1951706201515627e-05, - "loss": 0.1511, + "epoch": 0.38, + "learning_rate": 3.10188810093734e-05, + "loss": 0.1496, "step": 170770 }, { - "epoch": 0.76, - "learning_rate": 1.1949464149589704e-05, - "loss": 0.1555, + "epoch": 0.38, + "learning_rate": 3.101776246616407e-05, + "loss": 0.1531, "step": 170780 }, { - "epoch": 0.76, - "learning_rate": 1.1947222097663783e-05, - "loss": 0.1626, + "epoch": 0.38, + "learning_rate": 3.101664392295475e-05, + "loss": 0.1464, "step": 170790 }, { - "epoch": 0.76, - "learning_rate": 1.194498004573786e-05, - "loss": 0.1544, + "epoch": 0.38, + "learning_rate": 3.101552537974542e-05, + "loss": 0.1539, "step": 170800 }, { - "epoch": 0.76, - "learning_rate": 1.1942737993811937e-05, - "loss": 0.1595, + "epoch": 0.38, + "learning_rate": 3.10144068365361e-05, + "loss": 0.1538, "step": 170810 }, { - "epoch": 0.76, - "learning_rate": 1.1940495941886016e-05, - "loss": 0.1541, + "epoch": 0.38, + "learning_rate": 3.1013288293326775e-05, + "loss": 0.1477, "step": 170820 }, { - "epoch": 0.76, - "learning_rate": 1.1938253889960093e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.1012169750117446e-05, + "loss": 0.1543, "step": 170830 }, { - "epoch": 0.76, - "learning_rate": 1.193601183803417e-05, - "loss": 0.1534, + "epoch": 0.38, + "learning_rate": 3.1011051206908124e-05, + "loss": 0.1512, "step": 170840 }, { - "epoch": 0.76, - "learning_rate": 1.1933769786108247e-05, - "loss": 0.1556, + "epoch": 0.38, + "learning_rate": 3.10099326636988e-05, + "loss": 0.1507, "step": 170850 }, { - "epoch": 0.76, - "learning_rate": 1.1931527734182324e-05, - "loss": 0.1557, + "epoch": 0.38, + "learning_rate": 3.100881412048948e-05, + "loss": 0.1492, "step": 170860 }, { - "epoch": 0.76, - "learning_rate": 1.1929285682256401e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.100769557728015e-05, + "loss": 0.1535, "step": 170870 }, { - "epoch": 0.76, - "learning_rate": 1.1927043630330478e-05, - "loss": 0.1559, + "epoch": 0.38, + "learning_rate": 3.100657703407083e-05, + "loss": 0.1542, "step": 170880 }, { - "epoch": 0.76, - "learning_rate": 1.1924801578404557e-05, - "loss": 0.1497, + "epoch": 0.38, + "learning_rate": 3.100545849086151e-05, + "loss": 0.1467, "step": 170890 }, { - "epoch": 0.76, - "learning_rate": 1.1922559526478634e-05, - "loss": 0.1552, + "epoch": 0.38, + "learning_rate": 3.100433994765218e-05, + "loss": 0.155, "step": 170900 }, { - "epoch": 0.76, - "learning_rate": 1.192031747455271e-05, - "loss": 0.162, + "epoch": 0.38, + "learning_rate": 3.1003221404442856e-05, + "loss": 0.1518, "step": 170910 }, { - "epoch": 0.76, - "learning_rate": 1.1918075422626788e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.100210286123353e-05, + "loss": 0.1537, "step": 170920 }, { - "epoch": 0.76, - "learning_rate": 1.1915833370700866e-05, - "loss": 0.1616, + "epoch": 0.38, + "learning_rate": 3.1000984318024205e-05, + "loss": 0.1509, "step": 170930 }, { - "epoch": 0.76, - "learning_rate": 1.1913591318774943e-05, - "loss": 0.1596, + "epoch": 0.38, + "learning_rate": 3.099986577481488e-05, + "loss": 0.1535, "step": 170940 }, { - "epoch": 0.76, - "learning_rate": 1.1911349266849022e-05, - "loss": 0.1614, + "epoch": 0.38, + "learning_rate": 3.0998747231605554e-05, + "loss": 0.1516, "step": 170950 }, { - "epoch": 0.76, - "learning_rate": 1.19091072149231e-05, - "loss": 0.1552, + "epoch": 0.38, + "learning_rate": 3.099762868839623e-05, + "loss": 0.1514, "step": 170960 }, { - "epoch": 0.76, - "learning_rate": 1.1906865162997176e-05, - "loss": 0.1631, + "epoch": 0.38, + "learning_rate": 3.099651014518691e-05, + "loss": 0.1515, "step": 170970 }, { - "epoch": 0.76, - "learning_rate": 1.1904623111071253e-05, - "loss": 0.159, + "epoch": 0.38, + "learning_rate": 3.099539160197759e-05, + "loss": 0.1564, "step": 170980 }, { - "epoch": 0.76, - "learning_rate": 1.190238105914533e-05, - "loss": 0.1526, + "epoch": 0.38, + "learning_rate": 3.0994273058768266e-05, + "loss": 0.152, "step": 170990 }, { - "epoch": 0.76, - "learning_rate": 1.1900139007219407e-05, - "loss": 0.1629, + "epoch": 0.38, + "learning_rate": 3.099315451555894e-05, + "loss": 0.1532, "step": 171000 }, { - "epoch": 0.76, - "learning_rate": 1.1897896955293484e-05, - "loss": 0.1629, + "epoch": 0.38, + "learning_rate": 3.0992035972349615e-05, + "loss": 0.1551, "step": 171010 }, { - "epoch": 0.76, - "learning_rate": 1.1895654903367563e-05, - "loss": 0.16, + "epoch": 0.38, + "learning_rate": 3.0990917429140286e-05, + "loss": 0.1529, "step": 171020 }, { - "epoch": 0.76, - "learning_rate": 1.189341285144164e-05, - "loss": 0.1529, + "epoch": 0.38, + "learning_rate": 3.0989798885930964e-05, + "loss": 0.1502, "step": 171030 }, { - "epoch": 0.76, - "learning_rate": 1.1891170799515717e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.098868034272164e-05, + "loss": 0.1503, "step": 171040 }, { - "epoch": 0.76, - "learning_rate": 1.1888928747589794e-05, - "loss": 0.1596, + "epoch": 0.38, + "learning_rate": 3.098756179951231e-05, + "loss": 0.1497, "step": 171050 }, { - "epoch": 0.76, - "learning_rate": 1.1886686695663873e-05, - "loss": 0.1653, + "epoch": 0.38, + "learning_rate": 3.098644325630299e-05, + "loss": 0.1488, "step": 171060 }, { - "epoch": 0.76, - "learning_rate": 1.188444464373795e-05, - "loss": 0.1596, + "epoch": 0.38, + "learning_rate": 3.098532471309367e-05, + "loss": 0.1565, "step": 171070 }, { - "epoch": 0.76, - "learning_rate": 1.1882202591812027e-05, - "loss": 0.1539, + "epoch": 0.38, + "learning_rate": 3.098420616988435e-05, + "loss": 0.1498, "step": 171080 }, { - "epoch": 0.76, - "learning_rate": 1.1879960539886106e-05, - "loss": 0.1529, + "epoch": 0.38, + "learning_rate": 3.0983087626675025e-05, + "loss": 0.1513, "step": 171090 }, { - "epoch": 0.76, - "learning_rate": 1.1877718487960183e-05, - "loss": 0.1622, + "epoch": 0.38, + "learning_rate": 3.0981969083465696e-05, + "loss": 0.1508, "step": 171100 }, { - "epoch": 0.76, - "learning_rate": 1.187547643603426e-05, - "loss": 0.1541, + "epoch": 0.38, + "learning_rate": 3.0980850540256374e-05, + "loss": 0.1488, "step": 171110 }, { - "epoch": 0.76, - "learning_rate": 1.1873234384108337e-05, - "loss": 0.1547, + "epoch": 0.38, + "learning_rate": 3.0979731997047045e-05, + "loss": 0.1515, "step": 171120 }, { - "epoch": 0.76, - "learning_rate": 1.1870992332182414e-05, - "loss": 0.1552, + "epoch": 0.38, + "learning_rate": 3.097861345383772e-05, + "loss": 0.1478, "step": 171130 }, { - "epoch": 0.76, - "learning_rate": 1.186875028025649e-05, - "loss": 0.1559, + "epoch": 0.38, + "learning_rate": 3.09774949106284e-05, + "loss": 0.1528, "step": 171140 }, { - "epoch": 0.76, - "learning_rate": 1.1866508228330568e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.097637636741907e-05, + "loss": 0.1508, "step": 171150 }, { - "epoch": 0.76, - "learning_rate": 1.1864266176404646e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.097525782420975e-05, + "loss": 0.1519, "step": 171160 }, { - "epoch": 0.76, - "learning_rate": 1.1862024124478723e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.097413928100043e-05, + "loss": 0.1543, "step": 171170 }, { - "epoch": 0.76, - "learning_rate": 1.18597820725528e-05, - "loss": 0.1569, + "epoch": 0.38, + "learning_rate": 3.0973020737791106e-05, + "loss": 0.151, "step": 171180 }, { - "epoch": 0.76, - "learning_rate": 1.1857540020626878e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.097190219458178e-05, + "loss": 0.1547, "step": 171190 }, { - "epoch": 0.76, - "learning_rate": 1.1855297968700956e-05, - "loss": 0.1554, + "epoch": 0.38, + "learning_rate": 3.0970783651372455e-05, + "loss": 0.1495, "step": 171200 }, { - "epoch": 0.76, - "learning_rate": 1.1853055916775033e-05, - "loss": 0.1529, + "epoch": 0.38, + "learning_rate": 3.096966510816313e-05, + "loss": 0.1541, "step": 171210 }, { - "epoch": 0.76, - "learning_rate": 1.185081386484911e-05, - "loss": 0.154, + "epoch": 0.38, + "learning_rate": 3.0968546564953804e-05, + "loss": 0.1504, "step": 171220 }, { - "epoch": 0.76, - "learning_rate": 1.1848571812923189e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.096742802174448e-05, + "loss": 0.15, "step": 171230 }, { - "epoch": 0.76, - "learning_rate": 1.1846329760997266e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.096630947853515e-05, + "loss": 0.1526, "step": 171240 }, { - "epoch": 0.76, - "learning_rate": 1.1844087709071343e-05, - "loss": 0.1532, + "epoch": 0.38, + "learning_rate": 3.096519093532583e-05, + "loss": 0.1534, "step": 171250 }, { - "epoch": 0.76, - "learning_rate": 1.184184565714542e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.096407239211651e-05, + "loss": 0.1521, "step": 171260 }, { - "epoch": 0.76, - "learning_rate": 1.1839603605219497e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.096295384890719e-05, + "loss": 0.1504, "step": 171270 }, { - "epoch": 0.76, - "learning_rate": 1.1837361553293574e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.0961835305697865e-05, + "loss": 0.1531, "step": 171280 }, { - "epoch": 0.76, - "learning_rate": 1.1835119501367651e-05, - "loss": 0.1576, + "epoch": 0.38, + "learning_rate": 3.0960716762488536e-05, + "loss": 0.1505, "step": 171290 }, { - "epoch": 0.76, - "learning_rate": 1.183287744944173e-05, - "loss": 0.1556, + "epoch": 0.38, + "learning_rate": 3.0959598219279214e-05, + "loss": 0.1523, "step": 171300 }, { - "epoch": 0.76, - "learning_rate": 1.1830635397515807e-05, - "loss": 0.1621, + "epoch": 0.38, + "learning_rate": 3.095847967606989e-05, + "loss": 0.1486, "step": 171310 }, { - "epoch": 0.76, - "learning_rate": 1.1828393345589884e-05, - "loss": 0.1576, + "epoch": 0.38, + "learning_rate": 3.095736113286056e-05, + "loss": 0.1502, "step": 171320 }, { - "epoch": 0.76, - "learning_rate": 1.1826151293663963e-05, - "loss": 0.1612, + "epoch": 0.38, + "learning_rate": 3.095624258965124e-05, + "loss": 0.1515, "step": 171330 }, { - "epoch": 0.76, - "learning_rate": 1.182390924173804e-05, - "loss": 0.1586, + "epoch": 0.38, + "learning_rate": 3.095512404644191e-05, + "loss": 0.1548, "step": 171340 }, { - "epoch": 0.76, - "learning_rate": 1.1821667189812117e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.095400550323259e-05, + "loss": 0.1506, "step": 171350 }, { - "epoch": 0.76, - "learning_rate": 1.1819425137886194e-05, - "loss": 0.1574, + "epoch": 0.38, + "learning_rate": 3.095288696002327e-05, + "loss": 0.1529, "step": 171360 }, { - "epoch": 0.77, - "learning_rate": 1.1817183085960272e-05, - "loss": 0.1545, + "epoch": 0.38, + "learning_rate": 3.095176841681394e-05, + "loss": 0.1532, "step": 171370 }, { - "epoch": 0.77, - "learning_rate": 1.181494103403435e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.095064987360462e-05, + "loss": 0.1509, "step": 171380 }, { - "epoch": 0.77, - "learning_rate": 1.1812698982108426e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.0949531330395295e-05, + "loss": 0.1568, "step": 171390 }, { - "epoch": 0.77, - "learning_rate": 1.1810456930182503e-05, - "loss": 0.167, + "epoch": 0.38, + "learning_rate": 3.094841278718597e-05, + "loss": 0.1534, "step": 171400 }, { - "epoch": 0.77, - "learning_rate": 1.180821487825658e-05, - "loss": 0.1551, + "epoch": 0.38, + "learning_rate": 3.094729424397665e-05, + "loss": 0.1476, "step": 171410 }, { - "epoch": 0.77, - "learning_rate": 1.1805972826330658e-05, - "loss": 0.1529, + "epoch": 0.38, + "learning_rate": 3.094617570076732e-05, + "loss": 0.1497, "step": 171420 }, { - "epoch": 0.77, - "learning_rate": 1.1803730774404735e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.0945057157558e-05, + "loss": 0.1468, "step": 171430 }, { - "epoch": 0.77, - "learning_rate": 1.1801488722478813e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.094393861434867e-05, + "loss": 0.1516, "step": 171440 }, { - "epoch": 0.77, - "learning_rate": 1.179924667055289e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.094282007113935e-05, + "loss": 0.1586, "step": 171450 }, { - "epoch": 0.77, - "learning_rate": 1.1797004618626967e-05, - "loss": 0.1577, + "epoch": 0.38, + "learning_rate": 3.094170152793003e-05, + "loss": 0.1507, "step": 171460 }, { - "epoch": 0.77, - "learning_rate": 1.1794762566701046e-05, - "loss": 0.1602, + "epoch": 0.38, + "learning_rate": 3.09405829847207e-05, + "loss": 0.1523, "step": 171470 }, { - "epoch": 0.77, - "learning_rate": 1.1792520514775123e-05, - "loss": 0.1559, + "epoch": 0.38, + "learning_rate": 3.0939464441511376e-05, + "loss": 0.1574, "step": 171480 }, { - "epoch": 0.77, - "learning_rate": 1.17902784628492e-05, - "loss": 0.1568, + "epoch": 0.38, + "learning_rate": 3.0938345898302054e-05, + "loss": 0.1462, "step": 171490 }, { - "epoch": 0.77, - "learning_rate": 1.1788036410923277e-05, - "loss": 0.1571, + "epoch": 0.38, + "learning_rate": 3.093722735509273e-05, + "loss": 0.1511, "step": 171500 }, { - "epoch": 0.77, - "learning_rate": 1.1785794358997356e-05, - "loss": 0.1475, + "epoch": 0.38, + "learning_rate": 3.09361088118834e-05, + "loss": 0.1488, "step": 171510 }, { - "epoch": 0.77, - "learning_rate": 1.1783552307071433e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.093499026867408e-05, + "loss": 0.1504, "step": 171520 }, { - "epoch": 0.77, - "learning_rate": 1.178131025514551e-05, - "loss": 0.1564, + "epoch": 0.38, + "learning_rate": 3.093387172546476e-05, + "loss": 0.153, "step": 171530 }, { - "epoch": 0.77, - "learning_rate": 1.1779068203219587e-05, - "loss": 0.1484, + "epoch": 0.38, + "learning_rate": 3.093275318225543e-05, + "loss": 0.1455, "step": 171540 }, { - "epoch": 0.77, - "learning_rate": 1.1776826151293664e-05, - "loss": 0.1625, + "epoch": 0.38, + "learning_rate": 3.093163463904611e-05, + "loss": 0.1543, "step": 171550 }, { - "epoch": 0.77, - "learning_rate": 1.1774584099367741e-05, - "loss": 0.1595, + "epoch": 0.38, + "learning_rate": 3.093051609583678e-05, + "loss": 0.1533, "step": 171560 }, { - "epoch": 0.77, - "learning_rate": 1.177234204744182e-05, - "loss": 0.1656, + "epoch": 0.38, + "learning_rate": 3.092939755262746e-05, + "loss": 0.1513, "step": 171570 }, { - "epoch": 0.77, - "learning_rate": 1.1770099995515897e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.0928279009418135e-05, + "loss": 0.1532, "step": 171580 }, { - "epoch": 0.77, - "learning_rate": 1.1767857943589974e-05, - "loss": 0.1562, + "epoch": 0.38, + "learning_rate": 3.092716046620881e-05, + "loss": 0.1494, "step": 171590 }, { - "epoch": 0.77, - "learning_rate": 1.176561589166405e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.092604192299949e-05, + "loss": 0.1536, "step": 171600 }, { - "epoch": 0.77, - "learning_rate": 1.176337383973813e-05, - "loss": 0.1622, + "epoch": 0.38, + "learning_rate": 3.092492337979016e-05, + "loss": 0.1487, "step": 171610 }, { - "epoch": 0.77, - "learning_rate": 1.1761131787812206e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.092380483658084e-05, + "loss": 0.1477, "step": 171620 }, { - "epoch": 0.77, - "learning_rate": 1.1758889735886284e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.092268629337152e-05, + "loss": 0.1515, "step": 171630 }, { - "epoch": 0.77, - "learning_rate": 1.1756647683960362e-05, - "loss": 0.1516, + "epoch": 0.38, + "learning_rate": 3.092156775016219e-05, + "loss": 0.1508, "step": 171640 }, { - "epoch": 0.77, - "learning_rate": 1.175440563203444e-05, - "loss": 0.1649, + "epoch": 0.38, + "learning_rate": 3.092044920695287e-05, + "loss": 0.1517, "step": 171650 }, { - "epoch": 0.77, - "learning_rate": 1.1752163580108516e-05, - "loss": 0.1534, + "epoch": 0.38, + "learning_rate": 3.091933066374354e-05, + "loss": 0.1543, "step": 171660 }, { - "epoch": 0.77, - "learning_rate": 1.1749921528182593e-05, - "loss": 0.1618, + "epoch": 0.38, + "learning_rate": 3.0918212120534216e-05, + "loss": 0.1516, "step": 171670 }, { - "epoch": 0.77, - "learning_rate": 1.174767947625667e-05, - "loss": 0.1579, + "epoch": 0.38, + "learning_rate": 3.0917093577324894e-05, + "loss": 0.1512, "step": 171680 }, { - "epoch": 0.77, - "learning_rate": 1.1745437424330747e-05, - "loss": 0.159, + "epoch": 0.38, + "learning_rate": 3.091597503411557e-05, + "loss": 0.1491, "step": 171690 }, { - "epoch": 0.77, - "learning_rate": 1.1743195372404824e-05, - "loss": 0.157, + "epoch": 0.38, + "learning_rate": 3.091485649090625e-05, + "loss": 0.1488, "step": 171700 }, { - "epoch": 0.77, - "learning_rate": 1.1740953320478903e-05, - "loss": 0.1627, + "epoch": 0.38, + "learning_rate": 3.091373794769692e-05, + "loss": 0.1563, "step": 171710 }, { - "epoch": 0.77, - "learning_rate": 1.173871126855298e-05, - "loss": 0.159, + "epoch": 0.38, + "learning_rate": 3.09126194044876e-05, + "loss": 0.1488, "step": 171720 }, { - "epoch": 0.77, - "learning_rate": 1.1736469216627057e-05, - "loss": 0.1615, + "epoch": 0.38, + "learning_rate": 3.091150086127828e-05, + "loss": 0.153, "step": 171730 }, { - "epoch": 0.77, - "learning_rate": 1.1734227164701136e-05, - "loss": 0.1641, + "epoch": 0.38, + "learning_rate": 3.091038231806895e-05, + "loss": 0.1551, "step": 171740 }, { - "epoch": 0.77, - "learning_rate": 1.1731985112775213e-05, - "loss": 0.1592, + "epoch": 0.38, + "learning_rate": 3.0909263774859626e-05, + "loss": 0.1478, "step": 171750 }, { - "epoch": 0.77, - "learning_rate": 1.172974306084929e-05, - "loss": 0.1607, + "epoch": 0.38, + "learning_rate": 3.09081452316503e-05, + "loss": 0.1518, "step": 171760 }, { - "epoch": 0.77, - "learning_rate": 1.1727501008923367e-05, - "loss": 0.1551, + "epoch": 0.38, + "learning_rate": 3.0907026688440975e-05, + "loss": 0.1516, "step": 171770 }, { - "epoch": 0.77, - "learning_rate": 1.1725258956997446e-05, - "loss": 0.1594, + "epoch": 0.38, + "learning_rate": 3.0905908145231646e-05, + "loss": 0.1494, "step": 171780 }, { - "epoch": 0.77, - "learning_rate": 1.1723016905071523e-05, - "loss": 0.1518, + "epoch": 0.38, + "learning_rate": 3.0904789602022324e-05, + "loss": 0.1526, "step": 171790 }, { - "epoch": 0.77, - "learning_rate": 1.17207748531456e-05, - "loss": 0.1611, + "epoch": 0.38, + "learning_rate": 3.0903671058813e-05, + "loss": 0.1529, "step": 171800 }, { - "epoch": 0.77, - "learning_rate": 1.1718532801219677e-05, - "loss": 0.158, + "epoch": 0.38, + "learning_rate": 3.090255251560368e-05, + "loss": 0.1541, "step": 171810 }, { - "epoch": 0.77, - "learning_rate": 1.1716290749293754e-05, - "loss": 0.156, + "epoch": 0.38, + "learning_rate": 3.090143397239436e-05, + "loss": 0.1525, "step": 171820 }, { - "epoch": 0.77, - "learning_rate": 1.171404869736783e-05, - "loss": 0.1551, + "epoch": 0.38, + "learning_rate": 3.090031542918503e-05, + "loss": 0.1502, "step": 171830 }, { - "epoch": 0.77, - "learning_rate": 1.1711806645441908e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.089919688597571e-05, + "loss": 0.1485, "step": 171840 }, { - "epoch": 0.77, - "learning_rate": 1.1709564593515987e-05, - "loss": 0.155, + "epoch": 0.38, + "learning_rate": 3.0898078342766385e-05, + "loss": 0.1524, "step": 171850 }, { - "epoch": 0.77, - "learning_rate": 1.1707322541590064e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.0896959799557056e-05, + "loss": 0.1512, "step": 171860 }, { - "epoch": 0.77, - "learning_rate": 1.170508048966414e-05, - "loss": 0.1604, + "epoch": 0.38, + "learning_rate": 3.0895841256347734e-05, + "loss": 0.148, "step": 171870 }, { - "epoch": 0.77, - "learning_rate": 1.170283843773822e-05, - "loss": 0.1577, + "epoch": 0.38, + "learning_rate": 3.0894722713138405e-05, + "loss": 0.1522, "step": 171880 }, { - "epoch": 0.77, - "learning_rate": 1.1700596385812296e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.089360416992908e-05, + "loss": 0.1483, "step": 171890 }, { - "epoch": 0.77, - "learning_rate": 1.1698354333886373e-05, - "loss": 0.1604, + "epoch": 0.38, + "learning_rate": 3.089248562671976e-05, + "loss": 0.1534, "step": 171900 }, { - "epoch": 0.77, - "learning_rate": 1.169611228196045e-05, - "loss": 0.1686, + "epoch": 0.38, + "learning_rate": 3.089136708351044e-05, + "loss": 0.1514, "step": 171910 }, { - "epoch": 0.77, - "learning_rate": 1.1693870230034529e-05, - "loss": 0.1578, + "epoch": 0.38, + "learning_rate": 3.0890248540301117e-05, + "loss": 0.1474, "step": 171920 }, { - "epoch": 0.77, - "learning_rate": 1.1691628178108606e-05, - "loss": 0.1562, + "epoch": 0.38, + "learning_rate": 3.088912999709179e-05, + "loss": 0.1509, "step": 171930 }, { - "epoch": 0.77, - "learning_rate": 1.1689386126182683e-05, - "loss": 0.1531, + "epoch": 0.38, + "learning_rate": 3.0888011453882466e-05, + "loss": 0.1529, "step": 171940 }, { - "epoch": 0.77, - "learning_rate": 1.168714407425676e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.0886892910673144e-05, + "loss": 0.1553, "step": 171950 }, { - "epoch": 0.77, - "learning_rate": 1.1684902022330837e-05, - "loss": 0.1527, + "epoch": 0.38, + "learning_rate": 3.0885774367463815e-05, + "loss": 0.1477, "step": 171960 }, { - "epoch": 0.77, - "learning_rate": 1.1682659970404914e-05, - "loss": 0.1523, + "epoch": 0.38, + "learning_rate": 3.088465582425449e-05, + "loss": 0.1467, "step": 171970 }, { - "epoch": 0.77, - "learning_rate": 1.1680417918478991e-05, - "loss": 0.1542, + "epoch": 0.38, + "learning_rate": 3.0883537281045164e-05, + "loss": 0.1551, "step": 171980 }, { - "epoch": 0.77, - "learning_rate": 1.167817586655307e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.088241873783584e-05, + "loss": 0.1522, "step": 171990 }, { - "epoch": 0.77, - "learning_rate": 1.1675933814627147e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.088130019462652e-05, + "loss": 0.1539, "step": 172000 }, { - "epoch": 0.77, - "learning_rate": 1.1673691762701226e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.08801816514172e-05, + "loss": 0.1499, "step": 172010 }, { - "epoch": 0.77, - "learning_rate": 1.1671449710775303e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.0879063108207876e-05, + "loss": 0.1577, "step": 172020 }, { - "epoch": 0.77, - "learning_rate": 1.166920765884938e-05, - "loss": 0.1583, + "epoch": 0.38, + "learning_rate": 3.087794456499855e-05, + "loss": 0.1536, "step": 172030 }, { - "epoch": 0.77, - "learning_rate": 1.1666965606923457e-05, - "loss": 0.1543, + "epoch": 0.38, + "learning_rate": 3.0876826021789225e-05, + "loss": 0.1478, "step": 172040 }, { - "epoch": 0.77, - "learning_rate": 1.1664723554997534e-05, - "loss": 0.1536, + "epoch": 0.38, + "learning_rate": 3.08757074785799e-05, + "loss": 0.1509, "step": 172050 }, { - "epoch": 0.77, - "learning_rate": 1.1662481503071612e-05, - "loss": 0.1567, + "epoch": 0.38, + "learning_rate": 3.0874588935370574e-05, + "loss": 0.1495, "step": 172060 }, { - "epoch": 0.77, - "learning_rate": 1.166023945114569e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.087347039216125e-05, + "loss": 0.1515, "step": 172070 }, { - "epoch": 0.77, - "learning_rate": 1.1657997399219767e-05, - "loss": 0.1642, + "epoch": 0.38, + "learning_rate": 3.087235184895192e-05, + "loss": 0.1531, "step": 172080 }, { - "epoch": 0.77, - "learning_rate": 1.1655755347293844e-05, - "loss": 0.1558, + "epoch": 0.38, + "learning_rate": 3.08712333057426e-05, + "loss": 0.1528, "step": 172090 }, { - "epoch": 0.77, - "learning_rate": 1.165351329536792e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.087011476253328e-05, + "loss": 0.15, "step": 172100 }, { - "epoch": 0.77, - "learning_rate": 1.1651271243441998e-05, - "loss": 0.1586, + "epoch": 0.38, + "learning_rate": 3.0868996219323957e-05, + "loss": 0.1557, "step": 172110 }, { - "epoch": 0.77, - "learning_rate": 1.1649029191516075e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.0867877676114634e-05, + "loss": 0.1551, "step": 172120 }, { - "epoch": 0.77, - "learning_rate": 1.1646787139590153e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.0866759132905306e-05, + "loss": 0.1492, "step": 172130 }, { - "epoch": 0.77, - "learning_rate": 1.164454508766423e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.0865640589695984e-05, + "loss": 0.1528, "step": 172140 }, { - "epoch": 0.77, - "learning_rate": 1.1642303035738309e-05, - "loss": 0.1641, + "epoch": 0.38, + "learning_rate": 3.0864522046486655e-05, + "loss": 0.1496, "step": 172150 }, { - "epoch": 0.77, - "learning_rate": 1.1640060983812386e-05, - "loss": 0.1575, + "epoch": 0.38, + "learning_rate": 3.086340350327733e-05, + "loss": 0.1486, "step": 172160 }, { - "epoch": 0.77, - "learning_rate": 1.1637818931886463e-05, - "loss": 0.1539, + "epoch": 0.38, + "learning_rate": 3.086228496006801e-05, + "loss": 0.1463, "step": 172170 }, { - "epoch": 0.77, - "learning_rate": 1.163557687996054e-05, - "loss": 0.1569, + "epoch": 0.38, + "learning_rate": 3.086116641685868e-05, + "loss": 0.1543, "step": 172180 }, { - "epoch": 0.77, - "learning_rate": 1.1633334828034617e-05, - "loss": 0.1593, + "epoch": 0.38, + "learning_rate": 3.086004787364936e-05, + "loss": 0.1554, "step": 172190 }, { - "epoch": 0.77, - "learning_rate": 1.1631092776108696e-05, - "loss": 0.1592, + "epoch": 0.38, + "learning_rate": 3.085892933044003e-05, + "loss": 0.1514, "step": 172200 }, { - "epoch": 0.77, - "learning_rate": 1.1628850724182773e-05, - "loss": 0.1591, + "epoch": 0.38, + "learning_rate": 3.085781078723071e-05, + "loss": 0.1535, "step": 172210 }, { - "epoch": 0.77, - "learning_rate": 1.162660867225685e-05, - "loss": 0.1568, + "epoch": 0.38, + "learning_rate": 3.0856692244021393e-05, + "loss": 0.1507, "step": 172220 }, { - "epoch": 0.77, - "learning_rate": 1.1624366620330927e-05, - "loss": 0.1511, + "epoch": 0.38, + "learning_rate": 3.0855573700812065e-05, + "loss": 0.146, "step": 172230 }, { - "epoch": 0.77, - "learning_rate": 1.1622124568405004e-05, - "loss": 0.1566, + "epoch": 0.38, + "learning_rate": 3.085445515760274e-05, + "loss": 0.1527, "step": 172240 }, { - "epoch": 0.77, - "learning_rate": 1.1619882516479081e-05, - "loss": 0.1585, + "epoch": 0.38, + "learning_rate": 3.0853336614393414e-05, + "loss": 0.1533, "step": 172250 }, { - "epoch": 0.77, - "learning_rate": 1.161764046455316e-05, - "loss": 0.1535, + "epoch": 0.38, + "learning_rate": 3.085221807118409e-05, + "loss": 0.1466, "step": 172260 }, { - "epoch": 0.77, - "learning_rate": 1.1615398412627237e-05, - "loss": 0.1614, + "epoch": 0.38, + "learning_rate": 3.085109952797477e-05, + "loss": 0.1519, "step": 172270 }, { - "epoch": 0.77, - "learning_rate": 1.1613156360701315e-05, - "loss": 0.1628, + "epoch": 0.38, + "learning_rate": 3.084998098476544e-05, + "loss": 0.1514, "step": 172280 }, { - "epoch": 0.77, - "learning_rate": 1.1610914308775392e-05, - "loss": 0.157, + "epoch": 0.38, + "learning_rate": 3.084886244155612e-05, + "loss": 0.1538, "step": 172290 }, { - "epoch": 0.77, - "learning_rate": 1.1608896462042062e-05, - "loss": 0.1534, + "epoch": 0.38, + "learning_rate": 3.084774389834679e-05, + "loss": 0.1576, "step": 172300 }, { - "epoch": 0.77, - "learning_rate": 1.1606654410116139e-05, - "loss": 0.1554, + "epoch": 0.38, + "learning_rate": 3.084662535513747e-05, + "loss": 0.1534, "step": 172310 }, { - "epoch": 0.77, - "learning_rate": 1.1604412358190216e-05, - "loss": 0.1627, + "epoch": 0.38, + "learning_rate": 3.0845506811928146e-05, + "loss": 0.1512, "step": 172320 }, { - "epoch": 0.77, - "learning_rate": 1.1602170306264295e-05, - "loss": 0.1543, + "epoch": 0.38, + "learning_rate": 3.0844388268718824e-05, + "loss": 0.1564, "step": 172330 }, { - "epoch": 0.77, - "learning_rate": 1.1599928254338372e-05, - "loss": 0.1596, + "epoch": 0.38, + "learning_rate": 3.08432697255095e-05, + "loss": 0.1523, "step": 172340 }, { - "epoch": 0.77, - "learning_rate": 1.1597686202412449e-05, - "loss": 0.1648, + "epoch": 0.38, + "learning_rate": 3.084215118230017e-05, + "loss": 0.1527, "step": 172350 }, { - "epoch": 0.77, - "learning_rate": 1.1595444150486526e-05, - "loss": 0.1547, + "epoch": 0.38, + "learning_rate": 3.084103263909085e-05, + "loss": 0.1486, "step": 172360 }, { - "epoch": 0.77, - "learning_rate": 1.1593202098560603e-05, - "loss": 0.1546, + "epoch": 0.38, + "learning_rate": 3.083991409588153e-05, + "loss": 0.1494, "step": 172370 }, { - "epoch": 0.77, - "learning_rate": 1.159096004663468e-05, - "loss": 0.1581, + "epoch": 0.38, + "learning_rate": 3.08387955526722e-05, + "loss": 0.1519, "step": 172380 }, { - "epoch": 0.77, - "learning_rate": 1.1588717994708757e-05, - "loss": 0.1588, + "epoch": 0.38, + "learning_rate": 3.083767700946288e-05, + "loss": 0.1473, "step": 172390 }, { - "epoch": 0.77, - "learning_rate": 1.1586475942782836e-05, - "loss": 0.1589, + "epoch": 0.38, + "learning_rate": 3.083655846625355e-05, + "loss": 0.1555, "step": 172400 }, { - "epoch": 0.77, - "learning_rate": 1.1584233890856913e-05, - "loss": 0.1565, + "epoch": 0.38, + "learning_rate": 3.083543992304423e-05, + "loss": 0.1485, "step": 172410 }, { - "epoch": 0.77, - "learning_rate": 1.158199183893099e-05, - "loss": 0.1599, + "epoch": 0.38, + "learning_rate": 3.0834321379834905e-05, + "loss": 0.1499, "step": 172420 }, { - "epoch": 0.77, - "learning_rate": 1.1579749787005067e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.083320283662558e-05, + "loss": 0.1538, "step": 172430 }, { - "epoch": 0.77, - "learning_rate": 1.1577507735079145e-05, - "loss": 0.1548, + "epoch": 0.38, + "learning_rate": 3.083208429341626e-05, + "loss": 0.1533, "step": 172440 }, { - "epoch": 0.77, - "learning_rate": 1.1575265683153222e-05, - "loss": 0.1584, + "epoch": 0.38, + "learning_rate": 3.083096575020693e-05, + "loss": 0.15, "step": 172450 }, { - "epoch": 0.77, - "learning_rate": 1.15730236312273e-05, - "loss": 0.1624, + "epoch": 0.38, + "learning_rate": 3.082984720699761e-05, + "loss": 0.1507, "step": 172460 }, { - "epoch": 0.77, - "learning_rate": 1.1570781579301378e-05, - "loss": 0.1553, + "epoch": 0.38, + "learning_rate": 3.082872866378828e-05, + "loss": 0.1508, "step": 172470 }, { - "epoch": 0.77, - "learning_rate": 1.1568539527375455e-05, - "loss": 0.1563, + "epoch": 0.38, + "learning_rate": 3.082761012057896e-05, + "loss": 0.1514, "step": 172480 }, { - "epoch": 0.77, - "learning_rate": 1.1566297475449532e-05, - "loss": 0.1565, + "epoch": 0.39, + "learning_rate": 3.0826491577369637e-05, + "loss": 0.1476, "step": 172490 }, { - "epoch": 0.77, - "learning_rate": 1.156405542352361e-05, - "loss": 0.1587, + "epoch": 0.39, + "learning_rate": 3.082537303416031e-05, + "loss": 0.1529, "step": 172500 }, { - "epoch": 0.77, - "learning_rate": 1.1561813371597686e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.0824254490950986e-05, + "loss": 0.148, "step": 172510 }, { - "epoch": 0.77, - "learning_rate": 1.1559571319671763e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.0823135947741664e-05, + "loss": 0.1459, "step": 172520 }, { - "epoch": 0.77, - "learning_rate": 1.1557329267745842e-05, - "loss": 0.1613, + "epoch": 0.39, + "learning_rate": 3.082201740453234e-05, + "loss": 0.1545, "step": 172530 }, { - "epoch": 0.77, - "learning_rate": 1.1555087215819919e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.082089886132302e-05, + "loss": 0.1531, "step": 172540 }, { - "epoch": 0.77, - "learning_rate": 1.1552845163893996e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.081989217243462e-05, + "loss": 0.1501, "step": 172550 }, { - "epoch": 0.77, - "learning_rate": 1.1550603111968073e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.08187736292253e-05, + "loss": 0.1483, "step": 172560 }, { - "epoch": 0.77, - "learning_rate": 1.1548361060042152e-05, - "loss": 0.1565, + "epoch": 0.39, + "learning_rate": 3.081765508601597e-05, + "loss": 0.1526, "step": 172570 }, { - "epoch": 0.77, - "learning_rate": 1.1546119008116229e-05, - "loss": 0.158, + "epoch": 0.39, + "learning_rate": 3.081653654280665e-05, + "loss": 0.1555, "step": 172580 }, { - "epoch": 0.77, - "learning_rate": 1.1543876956190306e-05, - "loss": 0.1571, + "epoch": 0.39, + "learning_rate": 3.0815417999597326e-05, + "loss": 0.1517, "step": 172590 }, { - "epoch": 0.77, - "learning_rate": 1.1541634904264385e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.0814299456388004e-05, + "loss": 0.1552, "step": 172600 }, { - "epoch": 0.77, - "learning_rate": 1.1539392852338462e-05, - "loss": 0.1635, + "epoch": 0.39, + "learning_rate": 3.081318091317868e-05, + "loss": 0.1514, "step": 172610 }, { - "epoch": 0.77, - "learning_rate": 1.1537150800412539e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.081206236996935e-05, + "loss": 0.1516, "step": 172620 }, { - "epoch": 0.77, - "learning_rate": 1.1534908748486616e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.081094382676003e-05, + "loss": 0.1487, "step": 172630 }, { - "epoch": 0.77, - "learning_rate": 1.1532666696560693e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.08098252835507e-05, + "loss": 0.1541, "step": 172640 }, { - "epoch": 0.77, - "learning_rate": 1.153042464463477e-05, - "loss": 0.1583, + "epoch": 0.39, + "learning_rate": 3.080870674034138e-05, + "loss": 0.1551, "step": 172650 }, { - "epoch": 0.77, - "learning_rate": 1.1528182592708847e-05, - "loss": 0.1531, + "epoch": 0.39, + "learning_rate": 3.080758819713206e-05, + "loss": 0.1486, "step": 172660 }, { - "epoch": 0.77, - "learning_rate": 1.1525940540782925e-05, - "loss": 0.155, + "epoch": 0.39, + "learning_rate": 3.080646965392273e-05, + "loss": 0.1496, "step": 172670 }, { - "epoch": 0.77, - "learning_rate": 1.1523698488857002e-05, - "loss": 0.1653, + "epoch": 0.39, + "learning_rate": 3.080535111071341e-05, + "loss": 0.1485, "step": 172680 }, { - "epoch": 0.77, - "learning_rate": 1.152145643693108e-05, - "loss": 0.1577, + "epoch": 0.39, + "learning_rate": 3.0804232567504085e-05, + "loss": 0.1467, "step": 172690 }, { - "epoch": 0.77, - "learning_rate": 1.1519214385005156e-05, - "loss": 0.1562, + "epoch": 0.39, + "learning_rate": 3.080311402429476e-05, + "loss": 0.1499, "step": 172700 }, { - "epoch": 0.77, - "learning_rate": 1.1516972333079235e-05, - "loss": 0.1634, + "epoch": 0.39, + "learning_rate": 3.080199548108544e-05, + "loss": 0.1546, "step": 172710 }, { - "epoch": 0.77, - "learning_rate": 1.1514730281153312e-05, - "loss": 0.1615, + "epoch": 0.39, + "learning_rate": 3.080087693787611e-05, + "loss": 0.1504, "step": 172720 }, { - "epoch": 0.77, - "learning_rate": 1.151248822922739e-05, - "loss": 0.1593, + "epoch": 0.39, + "learning_rate": 3.079975839466679e-05, + "loss": 0.1502, "step": 172730 }, { - "epoch": 0.77, - "learning_rate": 1.1510246177301468e-05, - "loss": 0.148, + "epoch": 0.39, + "learning_rate": 3.079863985145746e-05, + "loss": 0.149, "step": 172740 }, { - "epoch": 0.77, - "learning_rate": 1.1508004125375545e-05, - "loss": 0.1583, + "epoch": 0.39, + "learning_rate": 3.079752130824814e-05, + "loss": 0.1528, "step": 172750 }, { - "epoch": 0.77, - "learning_rate": 1.1505762073449622e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.079640276503882e-05, + "loss": 0.154, "step": 172760 }, { - "epoch": 0.77, - "learning_rate": 1.1503520021523699e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.079528422182949e-05, + "loss": 0.1512, "step": 172770 }, { - "epoch": 0.77, - "learning_rate": 1.1501277969597776e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.0794165678620166e-05, + "loss": 0.1493, "step": 172780 }, { - "epoch": 0.77, - "learning_rate": 1.1499035917671853e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.079304713541084e-05, + "loss": 0.1519, "step": 172790 }, { - "epoch": 0.77, - "learning_rate": 1.149679386574593e-05, - "loss": 0.1603, + "epoch": 0.39, + "learning_rate": 3.079192859220152e-05, + "loss": 0.1458, "step": 172800 }, { - "epoch": 0.77, - "learning_rate": 1.1494551813820009e-05, - "loss": 0.1549, + "epoch": 0.39, + "learning_rate": 3.079081004899219e-05, + "loss": 0.1464, "step": 172810 }, { - "epoch": 0.77, - "learning_rate": 1.1492309761894086e-05, - "loss": 0.1596, + "epoch": 0.39, + "learning_rate": 3.078969150578287e-05, + "loss": 0.1479, "step": 172820 }, { - "epoch": 0.77, - "learning_rate": 1.1490067709968163e-05, - "loss": 0.1547, + "epoch": 0.39, + "learning_rate": 3.078857296257355e-05, + "loss": 0.1502, "step": 172830 }, { - "epoch": 0.77, - "learning_rate": 1.1487825658042242e-05, - "loss": 0.1559, + "epoch": 0.39, + "learning_rate": 3.078745441936422e-05, + "loss": 0.1541, "step": 172840 }, { - "epoch": 0.77, - "learning_rate": 1.1485583606116319e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.07863358761549e-05, + "loss": 0.1494, "step": 172850 }, { - "epoch": 0.77, - "learning_rate": 1.1483341554190396e-05, - "loss": 0.162, + "epoch": 0.39, + "learning_rate": 3.078521733294557e-05, + "loss": 0.1492, "step": 172860 }, { - "epoch": 0.77, - "learning_rate": 1.1481099502264473e-05, - "loss": 0.1568, + "epoch": 0.39, + "learning_rate": 3.078409878973625e-05, + "loss": 0.1483, "step": 172870 }, { - "epoch": 0.77, - "learning_rate": 1.1478857450338551e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.0782980246526925e-05, + "loss": 0.153, "step": 172880 }, { - "epoch": 0.77, - "learning_rate": 1.1476615398412628e-05, - "loss": 0.1607, + "epoch": 0.39, + "learning_rate": 3.0781861703317596e-05, + "loss": 0.148, "step": 172890 }, { - "epoch": 0.77, - "learning_rate": 1.1474373346486705e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.0780743160108274e-05, + "loss": 0.1505, "step": 172900 }, { - "epoch": 0.77, - "learning_rate": 1.1472131294560782e-05, - "loss": 0.1575, + "epoch": 0.39, + "learning_rate": 3.077962461689895e-05, + "loss": 0.1455, "step": 172910 }, { - "epoch": 0.77, - "learning_rate": 1.146988924263486e-05, - "loss": 0.1533, + "epoch": 0.39, + "learning_rate": 3.077850607368963e-05, + "loss": 0.1507, "step": 172920 }, { - "epoch": 0.77, - "learning_rate": 1.1467647190708936e-05, - "loss": 0.1577, + "epoch": 0.39, + "learning_rate": 3.077738753048031e-05, + "loss": 0.1492, "step": 172930 }, { - "epoch": 0.77, - "learning_rate": 1.1465405138783014e-05, - "loss": 0.1516, + "epoch": 0.39, + "learning_rate": 3.077626898727098e-05, + "loss": 0.1498, "step": 172940 }, { - "epoch": 0.77, - "learning_rate": 1.1463163086857092e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.077515044406166e-05, + "loss": 0.1543, "step": 172950 }, { - "epoch": 0.77, - "learning_rate": 1.146092103493117e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.077403190085233e-05, + "loss": 0.149, "step": 172960 }, { - "epoch": 0.77, - "learning_rate": 1.1458678983005246e-05, - "loss": 0.1595, + "epoch": 0.39, + "learning_rate": 3.0772913357643006e-05, + "loss": 0.1514, "step": 172970 }, { - "epoch": 0.77, - "learning_rate": 1.1456436931079325e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.0771794814433684e-05, + "loss": 0.1556, "step": 172980 }, { - "epoch": 0.77, - "learning_rate": 1.1454194879153402e-05, - "loss": 0.1614, + "epoch": 0.39, + "learning_rate": 3.0770676271224355e-05, + "loss": 0.1513, "step": 172990 }, { - "epoch": 0.77, - "learning_rate": 1.1451952827227479e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.076955772801503e-05, + "loss": 0.1529, "step": 173000 }, { - "epoch": 0.77, - "learning_rate": 1.1449710775301556e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.076843918480571e-05, + "loss": 0.1529, "step": 173010 }, { - "epoch": 0.77, - "learning_rate": 1.1447468723375635e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.076732064159639e-05, + "loss": 0.1507, "step": 173020 }, { - "epoch": 0.77, - "learning_rate": 1.1445226671449712e-05, - "loss": 0.1621, + "epoch": 0.39, + "learning_rate": 3.076620209838707e-05, + "loss": 0.1468, "step": 173030 }, { - "epoch": 0.77, - "learning_rate": 1.1442984619523789e-05, - "loss": 0.1564, + "epoch": 0.39, + "learning_rate": 3.076508355517774e-05, + "loss": 0.151, "step": 173040 }, { - "epoch": 0.77, - "learning_rate": 1.1440742567597866e-05, - "loss": 0.1564, + "epoch": 0.39, + "learning_rate": 3.0763965011968416e-05, + "loss": 0.1518, "step": 173050 }, { - "epoch": 0.77, - "learning_rate": 1.1438500515671943e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.076284646875909e-05, + "loss": 0.1536, "step": 173060 }, { - "epoch": 0.77, - "learning_rate": 1.143625846374602e-05, - "loss": 0.1488, + "epoch": 0.39, + "learning_rate": 3.0761727925549765e-05, + "loss": 0.153, "step": 173070 }, { - "epoch": 0.77, - "learning_rate": 1.1434016411820097e-05, - "loss": 0.1592, + "epoch": 0.39, + "learning_rate": 3.076060938234044e-05, + "loss": 0.1492, "step": 173080 }, { - "epoch": 0.77, - "learning_rate": 1.1431774359894176e-05, - "loss": 0.157, + "epoch": 0.39, + "learning_rate": 3.0759490839131114e-05, + "loss": 0.149, "step": 173090 }, { - "epoch": 0.77, - "learning_rate": 1.1429532307968253e-05, - "loss": 0.1654, + "epoch": 0.39, + "learning_rate": 3.075837229592179e-05, + "loss": 0.1465, "step": 173100 }, { - "epoch": 0.77, - "learning_rate": 1.1427290256042331e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.075725375271247e-05, + "loss": 0.1497, "step": 173110 }, { - "epoch": 0.77, - "learning_rate": 1.1425048204116408e-05, - "loss": 0.1539, + "epoch": 0.39, + "learning_rate": 3.075613520950315e-05, + "loss": 0.1483, "step": 173120 }, { - "epoch": 0.77, - "learning_rate": 1.1422806152190485e-05, - "loss": 0.1559, + "epoch": 0.39, + "learning_rate": 3.075501666629382e-05, + "loss": 0.1517, "step": 173130 }, { - "epoch": 0.77, - "learning_rate": 1.1420564100264562e-05, - "loss": 0.1564, + "epoch": 0.39, + "learning_rate": 3.07538981230845e-05, + "loss": 0.1543, "step": 173140 }, { - "epoch": 0.77, - "learning_rate": 1.141832204833864e-05, - "loss": 0.1539, + "epoch": 0.39, + "learning_rate": 3.0752779579875175e-05, + "loss": 0.1479, "step": 173150 }, { - "epoch": 0.77, - "learning_rate": 1.1416079996412718e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.0751661036665846e-05, + "loss": 0.1486, "step": 173160 }, { - "epoch": 0.77, - "learning_rate": 1.1413837944486795e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.0750542493456524e-05, + "loss": 0.1469, "step": 173170 }, { - "epoch": 0.77, - "learning_rate": 1.1411595892560872e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.0749423950247195e-05, + "loss": 0.1537, "step": 173180 }, { - "epoch": 0.77, - "learning_rate": 1.140935384063495e-05, - "loss": 0.159, + "epoch": 0.39, + "learning_rate": 3.074830540703787e-05, + "loss": 0.1509, "step": 173190 }, { - "epoch": 0.77, - "learning_rate": 1.1407111788709026e-05, - "loss": 0.1637, + "epoch": 0.39, + "learning_rate": 3.074718686382855e-05, + "loss": 0.1525, "step": 173200 }, { - "epoch": 0.77, - "learning_rate": 1.1404869736783103e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.074606832061923e-05, + "loss": 0.1517, "step": 173210 }, { - "epoch": 0.77, - "learning_rate": 1.1402627684857182e-05, - "loss": 0.1593, + "epoch": 0.39, + "learning_rate": 3.074494977740991e-05, + "loss": 0.1486, "step": 173220 }, { - "epoch": 0.77, - "learning_rate": 1.1400385632931259e-05, - "loss": 0.1506, + "epoch": 0.39, + "learning_rate": 3.074383123420058e-05, + "loss": 0.1473, "step": 173230 }, { - "epoch": 0.77, - "learning_rate": 1.1398143581005336e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0742712690991256e-05, + "loss": 0.1507, "step": 173240 }, { - "epoch": 0.77, - "learning_rate": 1.1395901529079415e-05, - "loss": 0.1611, + "epoch": 0.39, + "learning_rate": 3.0741594147781934e-05, + "loss": 0.151, "step": 173250 }, { - "epoch": 0.77, - "learning_rate": 1.1393659477153492e-05, - "loss": 0.1613, + "epoch": 0.39, + "learning_rate": 3.0740475604572605e-05, + "loss": 0.1524, "step": 173260 }, { - "epoch": 0.77, - "learning_rate": 1.1391417425227569e-05, - "loss": 0.1524, + "epoch": 0.39, + "learning_rate": 3.073935706136328e-05, + "loss": 0.1447, "step": 173270 }, { - "epoch": 0.77, - "learning_rate": 1.1389175373301646e-05, - "loss": 0.161, + "epoch": 0.39, + "learning_rate": 3.0738238518153954e-05, + "loss": 0.152, "step": 173280 }, { - "epoch": 0.77, - "learning_rate": 1.1386933321375725e-05, - "loss": 0.1612, + "epoch": 0.39, + "learning_rate": 3.073711997494463e-05, + "loss": 0.1491, "step": 173290 }, { - "epoch": 0.77, - "learning_rate": 1.1384691269449802e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.073600143173531e-05, + "loss": 0.1535, "step": 173300 }, { - "epoch": 0.77, - "learning_rate": 1.1382449217523879e-05, - "loss": 0.1562, + "epoch": 0.39, + "learning_rate": 3.073488288852598e-05, + "loss": 0.1508, "step": 173310 }, { - "epoch": 0.77, - "learning_rate": 1.1380207165597956e-05, - "loss": 0.1559, + "epoch": 0.39, + "learning_rate": 3.073376434531666e-05, + "loss": 0.1557, "step": 173320 }, { - "epoch": 0.77, - "learning_rate": 1.1377965113672033e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.073264580210734e-05, + "loss": 0.1506, "step": 173330 }, { - "epoch": 0.77, - "learning_rate": 1.137572306174611e-05, - "loss": 0.1585, + "epoch": 0.39, + "learning_rate": 3.0731527258898015e-05, + "loss": 0.1499, "step": 173340 }, { - "epoch": 0.77, - "learning_rate": 1.1373481009820187e-05, - "loss": 0.1511, + "epoch": 0.39, + "learning_rate": 3.073040871568869e-05, + "loss": 0.1589, "step": 173350 }, { - "epoch": 0.77, - "learning_rate": 1.1371238957894265e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.0729290172479364e-05, + "loss": 0.1503, "step": 173360 }, { - "epoch": 0.77, - "learning_rate": 1.1368996905968342e-05, - "loss": 0.1579, + "epoch": 0.39, + "learning_rate": 3.072817162927004e-05, + "loss": 0.1454, "step": 173370 }, { - "epoch": 0.77, - "learning_rate": 1.1366754854042421e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.072705308606071e-05, + "loss": 0.1556, "step": 173380 }, { - "epoch": 0.77, - "learning_rate": 1.1364512802116498e-05, - "loss": 0.1626, + "epoch": 0.39, + "learning_rate": 3.072593454285139e-05, + "loss": 0.1518, "step": 173390 }, { - "epoch": 0.77, - "learning_rate": 1.1362270750190575e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.072481599964207e-05, + "loss": 0.1514, "step": 173400 }, { - "epoch": 0.77, - "learning_rate": 1.1360028698264652e-05, - "loss": 0.1519, + "epoch": 0.39, + "learning_rate": 3.072369745643274e-05, + "loss": 0.1505, "step": 173410 }, { - "epoch": 0.77, - "learning_rate": 1.135778664633873e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.072257891322342e-05, + "loss": 0.1524, "step": 173420 }, { - "epoch": 0.77, - "learning_rate": 1.1355544594412808e-05, - "loss": 0.1507, + "epoch": 0.39, + "learning_rate": 3.0721460370014096e-05, + "loss": 0.1529, "step": 173430 }, { - "epoch": 0.77, - "learning_rate": 1.1353302542486885e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.0720341826804774e-05, + "loss": 0.1523, "step": 173440 }, { - "epoch": 0.77, - "learning_rate": 1.1351060490560962e-05, - "loss": 0.1616, + "epoch": 0.39, + "learning_rate": 3.0719223283595445e-05, + "loss": 0.1516, "step": 173450 }, { - "epoch": 0.77, - "learning_rate": 1.1348818438635039e-05, - "loss": 0.1516, + "epoch": 0.39, + "learning_rate": 3.071810474038612e-05, + "loss": 0.1529, "step": 173460 }, { - "epoch": 0.77, - "learning_rate": 1.1346576386709116e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.07169861971768e-05, + "loss": 0.1518, "step": 173470 }, { - "epoch": 0.77, - "learning_rate": 1.1344334334783193e-05, - "loss": 0.1609, + "epoch": 0.39, + "learning_rate": 3.071586765396747e-05, + "loss": 0.1503, "step": 173480 }, { - "epoch": 0.77, - "learning_rate": 1.134209228285727e-05, - "loss": 0.1587, + "epoch": 0.39, + "learning_rate": 3.071474911075815e-05, + "loss": 0.1499, "step": 173490 }, { - "epoch": 0.77, - "learning_rate": 1.1339850230931349e-05, - "loss": 0.1509, + "epoch": 0.39, + "learning_rate": 3.071363056754882e-05, + "loss": 0.1524, "step": 173500 }, { - "epoch": 0.77, - "learning_rate": 1.1337608179005426e-05, + "epoch": 0.39, + "learning_rate": 3.07125120243395e-05, "loss": 0.1523, "step": 173510 }, { - "epoch": 0.77, - "learning_rate": 1.1335366127079505e-05, - "loss": 0.162, + "epoch": 0.39, + "learning_rate": 3.071139348113018e-05, + "loss": 0.1571, "step": 173520 }, { - "epoch": 0.77, - "learning_rate": 1.1333124075153582e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.0710274937920855e-05, + "loss": 0.152, "step": 173530 }, { - "epoch": 0.77, - "learning_rate": 1.1330882023227659e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.070915639471153e-05, + "loss": 0.1494, "step": 173540 }, { - "epoch": 0.77, - "learning_rate": 1.1328639971301736e-05, - "loss": 0.1598, + "epoch": 0.39, + "learning_rate": 3.0708037851502204e-05, + "loss": 0.1502, "step": 173550 }, { - "epoch": 0.77, - "learning_rate": 1.1326397919375813e-05, - "loss": 0.1638, + "epoch": 0.39, + "learning_rate": 3.070691930829288e-05, + "loss": 0.1492, "step": 173560 }, { - "epoch": 0.77, - "learning_rate": 1.1324155867449891e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.070580076508356e-05, + "loss": 0.1535, "step": 173570 }, { - "epoch": 0.77, - "learning_rate": 1.1321913815523968e-05, - "loss": 0.1579, + "epoch": 0.39, + "learning_rate": 3.070468222187423e-05, + "loss": 0.1537, "step": 173580 }, { - "epoch": 0.77, - "learning_rate": 1.1319671763598045e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.070356367866491e-05, + "loss": 0.1561, "step": 173590 }, { - "epoch": 0.77, - "learning_rate": 1.1317429711672122e-05, - "loss": 0.1522, + "epoch": 0.39, + "learning_rate": 3.070244513545558e-05, + "loss": 0.1502, "step": 173600 }, { - "epoch": 0.78, - "learning_rate": 1.13151876597462e-05, - "loss": 0.1623, + "epoch": 0.39, + "learning_rate": 3.070132659224626e-05, + "loss": 0.1495, "step": 173610 }, { - "epoch": 0.78, - "learning_rate": 1.1312945607820277e-05, - "loss": 0.1521, + "epoch": 0.39, + "learning_rate": 3.0700208049036936e-05, + "loss": 0.1526, "step": 173620 }, { - "epoch": 0.78, - "learning_rate": 1.1310703555894355e-05, - "loss": 0.1531, + "epoch": 0.39, + "learning_rate": 3.0699089505827614e-05, + "loss": 0.1516, "step": 173630 }, { - "epoch": 0.78, - "learning_rate": 1.1308461503968432e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.069797096261829e-05, + "loss": 0.1512, "step": 173640 }, { - "epoch": 0.78, - "learning_rate": 1.1306219452042511e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.069685241940896e-05, + "loss": 0.1498, "step": 173650 }, { - "epoch": 0.78, - "learning_rate": 1.1303977400116588e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.069573387619964e-05, + "loss": 0.1546, "step": 173660 }, { - "epoch": 0.78, - "learning_rate": 1.1301735348190665e-05, - "loss": 0.1573, + "epoch": 0.39, + "learning_rate": 3.069461533299032e-05, + "loss": 0.1499, "step": 173670 }, { - "epoch": 0.78, - "learning_rate": 1.1299493296264742e-05, - "loss": 0.1556, + "epoch": 0.39, + "learning_rate": 3.069349678978099e-05, + "loss": 0.1473, "step": 173680 }, { - "epoch": 0.78, - "learning_rate": 1.1297251244338819e-05, - "loss": 0.1628, + "epoch": 0.39, + "learning_rate": 3.069237824657167e-05, + "loss": 0.1522, "step": 173690 }, { - "epoch": 0.78, - "learning_rate": 1.1295009192412896e-05, - "loss": 0.1536, + "epoch": 0.39, + "learning_rate": 3.069125970336234e-05, + "loss": 0.1529, "step": 173700 }, { - "epoch": 0.78, - "learning_rate": 1.1292767140486975e-05, - "loss": 0.1581, + "epoch": 0.39, + "learning_rate": 3.069014116015302e-05, + "loss": 0.1493, "step": 173710 }, { - "epoch": 0.78, - "learning_rate": 1.1290525088561052e-05, - "loss": 0.1583, + "epoch": 0.39, + "learning_rate": 3.0689022616943695e-05, + "loss": 0.1492, "step": 173720 }, { - "epoch": 0.78, - "learning_rate": 1.1288283036635129e-05, - "loss": 0.1616, + "epoch": 0.39, + "learning_rate": 3.0687904073734366e-05, + "loss": 0.1525, "step": 173730 }, { - "epoch": 0.78, - "learning_rate": 1.1286040984709206e-05, - "loss": 0.1619, + "epoch": 0.39, + "learning_rate": 3.0686785530525044e-05, + "loss": 0.1546, "step": 173740 }, { - "epoch": 0.78, - "learning_rate": 1.1283798932783283e-05, - "loss": 0.1507, + "epoch": 0.39, + "learning_rate": 3.068566698731572e-05, + "loss": 0.1503, "step": 173750 }, { - "epoch": 0.78, - "learning_rate": 1.128155688085736e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.06845484441064e-05, + "loss": 0.1525, "step": 173760 }, { - "epoch": 0.78, - "learning_rate": 1.1279314828931439e-05, - "loss": 0.1606, + "epoch": 0.39, + "learning_rate": 3.068342990089707e-05, + "loss": 0.1532, "step": 173770 }, { - "epoch": 0.78, - "learning_rate": 1.1277072777005516e-05, - "loss": 0.1609, + "epoch": 0.39, + "learning_rate": 3.068231135768775e-05, + "loss": 0.1489, "step": 173780 }, { - "epoch": 0.78, - "learning_rate": 1.1274830725079594e-05, - "loss": 0.1603, + "epoch": 0.39, + "learning_rate": 3.068119281447843e-05, + "loss": 0.1498, "step": 173790 }, { - "epoch": 0.78, - "learning_rate": 1.1272588673153671e-05, - "loss": 0.154, + "epoch": 0.39, + "learning_rate": 3.06800742712691e-05, + "loss": 0.1546, "step": 173800 }, { - "epoch": 0.78, - "learning_rate": 1.1270346621227748e-05, - "loss": 0.1516, + "epoch": 0.39, + "learning_rate": 3.0678955728059776e-05, + "loss": 0.1484, "step": 173810 }, { - "epoch": 0.78, - "learning_rate": 1.1268104569301825e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.067783718485045e-05, + "loss": 0.1486, "step": 173820 }, { - "epoch": 0.78, - "learning_rate": 1.1265862517375903e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.0676718641641125e-05, + "loss": 0.1518, "step": 173830 }, { - "epoch": 0.78, - "learning_rate": 1.126362046544998e-05, - "loss": 0.1618, + "epoch": 0.39, + "learning_rate": 3.06756000984318e-05, + "loss": 0.1549, "step": 173840 }, { - "epoch": 0.78, - "learning_rate": 1.1261378413524058e-05, - "loss": 0.1524, + "epoch": 0.39, + "learning_rate": 3.067448155522248e-05, + "loss": 0.1494, "step": 173850 }, { - "epoch": 0.78, - "learning_rate": 1.1259136361598135e-05, - "loss": 0.1619, + "epoch": 0.39, + "learning_rate": 3.067336301201316e-05, + "loss": 0.1535, "step": 173860 }, { - "epoch": 0.78, - "learning_rate": 1.1256894309672212e-05, - "loss": 0.1568, + "epoch": 0.39, + "learning_rate": 3.067224446880383e-05, + "loss": 0.1518, "step": 173870 }, { - "epoch": 0.78, - "learning_rate": 1.125465225774629e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.067112592559451e-05, + "loss": 0.1473, "step": 173880 }, { - "epoch": 0.78, - "learning_rate": 1.1252410205820366e-05, - "loss": 0.1622, + "epoch": 0.39, + "learning_rate": 3.0670007382385186e-05, + "loss": 0.1582, "step": 173890 }, { - "epoch": 0.78, - "learning_rate": 1.1250168153894445e-05, - "loss": 0.152, + "epoch": 0.39, + "learning_rate": 3.066888883917586e-05, + "loss": 0.1524, "step": 173900 }, { - "epoch": 0.78, - "learning_rate": 1.1247926101968522e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0667770295966535e-05, + "loss": 0.149, "step": 173910 }, { - "epoch": 0.78, - "learning_rate": 1.12456840500426e-05, - "loss": 0.1526, + "epoch": 0.39, + "learning_rate": 3.0666651752757206e-05, + "loss": 0.15, "step": 173920 }, { - "epoch": 0.78, - "learning_rate": 1.1243441998116678e-05, - "loss": 0.1592, + "epoch": 0.39, + "learning_rate": 3.0665533209547884e-05, + "loss": 0.1552, "step": 173930 }, { - "epoch": 0.78, - "learning_rate": 1.1241199946190755e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.066441466633856e-05, + "loss": 0.1504, "step": 173940 }, { - "epoch": 0.78, - "learning_rate": 1.1238957894264832e-05, - "loss": 0.1567, + "epoch": 0.39, + "learning_rate": 3.066329612312924e-05, + "loss": 0.1499, "step": 173950 }, { - "epoch": 0.78, - "learning_rate": 1.1236715842338909e-05, - "loss": 0.1566, + "epoch": 0.39, + "learning_rate": 3.066217757991992e-05, + "loss": 0.1468, "step": 173960 }, { - "epoch": 0.78, - "learning_rate": 1.1234473790412986e-05, - "loss": 0.1568, + "epoch": 0.39, + "learning_rate": 3.066105903671059e-05, + "loss": 0.1506, "step": 173970 }, { - "epoch": 0.78, - "learning_rate": 1.1232231738487065e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.065994049350127e-05, + "loss": 0.1519, "step": 173980 }, { - "epoch": 0.78, - "learning_rate": 1.1229989686561142e-05, - "loss": 0.1529, + "epoch": 0.39, + "learning_rate": 3.0658821950291945e-05, + "loss": 0.1452, "step": 173990 }, { - "epoch": 0.78, - "learning_rate": 1.1227747634635219e-05, - "loss": 0.1627, + "epoch": 0.39, + "learning_rate": 3.0657703407082616e-05, + "loss": 0.155, "step": 174000 }, { - "epoch": 0.78, - "learning_rate": 1.1225505582709296e-05, - "loss": 0.1594, + "epoch": 0.39, + "learning_rate": 3.0656584863873294e-05, + "loss": 0.1505, "step": 174010 }, { - "epoch": 0.78, - "learning_rate": 1.1223263530783373e-05, - "loss": 0.158, + "epoch": 0.39, + "learning_rate": 3.0655466320663965e-05, + "loss": 0.1472, "step": 174020 }, { - "epoch": 0.78, - "learning_rate": 1.122102147885745e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.065434777745464e-05, + "loss": 0.1522, "step": 174030 }, { - "epoch": 0.78, - "learning_rate": 1.1218779426931528e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.065322923424532e-05, + "loss": 0.1497, "step": 174040 }, { - "epoch": 0.78, - "learning_rate": 1.1216537375005605e-05, - "loss": 0.1559, + "epoch": 0.39, + "learning_rate": 3.0652110691036e-05, + "loss": 0.1557, "step": 174050 }, { - "epoch": 0.78, - "learning_rate": 1.1214295323079684e-05, - "loss": 0.1604, + "epoch": 0.39, + "learning_rate": 3.065099214782668e-05, + "loss": 0.1516, "step": 174060 }, { - "epoch": 0.78, - "learning_rate": 1.1212053271153761e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.064987360461735e-05, + "loss": 0.1523, "step": 174070 }, { - "epoch": 0.78, - "learning_rate": 1.1209811219227838e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.0648755061408026e-05, + "loss": 0.1487, "step": 174080 }, { - "epoch": 0.78, - "learning_rate": 1.1207569167301915e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.06476365181987e-05, + "loss": 0.144, "step": 174090 }, { - "epoch": 0.78, - "learning_rate": 1.1205327115375992e-05, - "loss": 0.1536, + "epoch": 0.39, + "learning_rate": 3.0646517974989375e-05, + "loss": 0.147, "step": 174100 }, { - "epoch": 0.78, - "learning_rate": 1.120308506345007e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.064539943178005e-05, + "loss": 0.1494, "step": 174110 }, { - "epoch": 0.78, - "learning_rate": 1.1200843011524148e-05, - "loss": 0.1613, + "epoch": 0.39, + "learning_rate": 3.0644280888570724e-05, + "loss": 0.1514, "step": 174120 }, { - "epoch": 0.78, - "learning_rate": 1.1198600959598225e-05, - "loss": 0.1526, + "epoch": 0.39, + "learning_rate": 3.06431623453614e-05, + "loss": 0.1499, "step": 174130 }, { - "epoch": 0.78, - "learning_rate": 1.1196358907672302e-05, - "loss": 0.1577, + "epoch": 0.39, + "learning_rate": 3.064204380215207e-05, + "loss": 0.1566, "step": 174140 }, { - "epoch": 0.78, - "learning_rate": 1.1194116855746379e-05, - "loss": 0.1554, + "epoch": 0.39, + "learning_rate": 3.064092525894275e-05, + "loss": 0.1461, "step": 174150 }, { - "epoch": 0.78, - "learning_rate": 1.1191874803820456e-05, - "loss": 0.1609, + "epoch": 0.39, + "learning_rate": 3.0639806715733436e-05, + "loss": 0.1535, "step": 174160 }, { - "epoch": 0.78, - "learning_rate": 1.1189632751894535e-05, - "loss": 0.154, + "epoch": 0.39, + "learning_rate": 3.063868817252411e-05, + "loss": 0.1506, "step": 174170 }, { - "epoch": 0.78, - "learning_rate": 1.1187390699968612e-05, - "loss": 0.1584, + "epoch": 0.39, + "learning_rate": 3.0637569629314785e-05, + "loss": 0.1535, "step": 174180 }, { - "epoch": 0.78, - "learning_rate": 1.118514864804269e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.0636451086105456e-05, + "loss": 0.1492, "step": 174190 }, { - "epoch": 0.78, - "learning_rate": 1.1182906596116768e-05, - "loss": 0.1514, + "epoch": 0.39, + "learning_rate": 3.0635332542896134e-05, + "loss": 0.1525, "step": 174200 }, { - "epoch": 0.78, - "learning_rate": 1.1180664544190845e-05, - "loss": 0.1548, + "epoch": 0.39, + "learning_rate": 3.063421399968681e-05, + "loss": 0.146, "step": 174210 }, { - "epoch": 0.78, - "learning_rate": 1.1178422492264922e-05, - "loss": 0.1533, + "epoch": 0.39, + "learning_rate": 3.063309545647748e-05, + "loss": 0.1501, "step": 174220 }, { - "epoch": 0.78, - "learning_rate": 1.1176180440338999e-05, - "loss": 0.1585, + "epoch": 0.39, + "learning_rate": 3.063197691326816e-05, + "loss": 0.1514, "step": 174230 }, { - "epoch": 0.78, - "learning_rate": 1.1173938388413076e-05, - "loss": 0.1577, + "epoch": 0.39, + "learning_rate": 3.063085837005883e-05, + "loss": 0.1546, "step": 174240 }, { - "epoch": 0.78, - "learning_rate": 1.1171696336487153e-05, - "loss": 0.1581, + "epoch": 0.39, + "learning_rate": 3.062973982684951e-05, + "loss": 0.1523, "step": 174250 }, { - "epoch": 0.78, - "learning_rate": 1.1169454284561231e-05, - "loss": 0.1578, + "epoch": 0.39, + "learning_rate": 3.062862128364019e-05, + "loss": 0.1515, "step": 174260 }, { - "epoch": 0.78, - "learning_rate": 1.1167212232635308e-05, - "loss": 0.1559, + "epoch": 0.39, + "learning_rate": 3.0627502740430866e-05, + "loss": 0.1544, "step": 174270 }, { - "epoch": 0.78, - "learning_rate": 1.1164970180709386e-05, - "loss": 0.1496, + "epoch": 0.39, + "learning_rate": 3.0626384197221544e-05, + "loss": 0.1552, "step": 174280 }, { - "epoch": 0.78, - "learning_rate": 1.1162728128783463e-05, - "loss": 0.1638, + "epoch": 0.39, + "learning_rate": 3.0625265654012215e-05, + "loss": 0.1503, "step": 174290 }, { - "epoch": 0.78, - "learning_rate": 1.116048607685754e-05, - "loss": 0.1593, + "epoch": 0.39, + "learning_rate": 3.062414711080289e-05, + "loss": 0.1527, "step": 174300 }, { - "epoch": 0.78, - "learning_rate": 1.1158244024931618e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.062302856759357e-05, + "loss": 0.1528, "step": 174310 }, { - "epoch": 0.78, - "learning_rate": 1.1156001973005695e-05, - "loss": 0.1533, + "epoch": 0.39, + "learning_rate": 3.062191002438424e-05, + "loss": 0.152, "step": 174320 }, { - "epoch": 0.78, - "learning_rate": 1.1153759921079774e-05, - "loss": 0.1582, + "epoch": 0.39, + "learning_rate": 3.062079148117492e-05, + "loss": 0.151, "step": 174330 }, { - "epoch": 0.78, - "learning_rate": 1.1151517869153851e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.061967293796559e-05, + "loss": 0.1514, "step": 174340 }, { - "epoch": 0.78, - "learning_rate": 1.1149275817227928e-05, - "loss": 0.1511, + "epoch": 0.39, + "learning_rate": 3.061855439475627e-05, + "loss": 0.1478, "step": 174350 }, { - "epoch": 0.78, - "learning_rate": 1.1147033765302005e-05, + "epoch": 0.39, + "learning_rate": 3.061743585154695e-05, "loss": 0.1552, "step": 174360 }, { - "epoch": 0.78, - "learning_rate": 1.1144791713376082e-05, - "loss": 0.1519, + "epoch": 0.39, + "learning_rate": 3.0616317308337625e-05, + "loss": 0.1476, "step": 174370 }, { - "epoch": 0.78, - "learning_rate": 1.1142549661450159e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.06151987651283e-05, + "loss": 0.1525, "step": 174380 }, { - "epoch": 0.78, - "learning_rate": 1.1140307609524236e-05, - "loss": 0.1573, + "epoch": 0.39, + "learning_rate": 3.0614080221918974e-05, + "loss": 0.1513, "step": 174390 }, { - "epoch": 0.78, - "learning_rate": 1.1138065557598315e-05, - "loss": 0.1665, + "epoch": 0.39, + "learning_rate": 3.061296167870965e-05, + "loss": 0.1526, "step": 174400 }, { - "epoch": 0.78, - "learning_rate": 1.1135823505672392e-05, - "loss": 0.1547, + "epoch": 0.39, + "learning_rate": 3.061184313550032e-05, + "loss": 0.1517, "step": 174410 }, { - "epoch": 0.78, - "learning_rate": 1.1133581453746469e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.0610724592291e-05, + "loss": 0.1479, "step": 174420 }, { - "epoch": 0.78, - "learning_rate": 1.1131339401820546e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.060960604908168e-05, + "loss": 0.151, "step": 174430 }, { - "epoch": 0.78, - "learning_rate": 1.1129097349894625e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.060848750587235e-05, + "loss": 0.1482, "step": 174440 }, { - "epoch": 0.78, - "learning_rate": 1.1126855297968702e-05, - "loss": 0.1585, + "epoch": 0.39, + "learning_rate": 3.060736896266303e-05, + "loss": 0.1515, "step": 174450 }, { - "epoch": 0.78, - "learning_rate": 1.1124613246042779e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.0606250419453706e-05, + "loss": 0.152, "step": 174460 }, { - "epoch": 0.78, - "learning_rate": 1.1122371194116857e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.0605131876244384e-05, + "loss": 0.151, "step": 174470 }, { - "epoch": 0.78, - "learning_rate": 1.1120129142190934e-05, - "loss": 0.1564, + "epoch": 0.39, + "learning_rate": 3.060401333303506e-05, + "loss": 0.1531, "step": 174480 }, { - "epoch": 0.78, - "learning_rate": 1.1117887090265011e-05, - "loss": 0.1494, + "epoch": 0.39, + "learning_rate": 3.060289478982573e-05, + "loss": 0.1529, "step": 174490 }, { - "epoch": 0.78, - "learning_rate": 1.1115645038339089e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.060177624661641e-05, + "loss": 0.1461, "step": 174500 }, { - "epoch": 0.78, - "learning_rate": 1.1113402986413166e-05, - "loss": 0.1595, + "epoch": 0.39, + "learning_rate": 3.060065770340708e-05, + "loss": 0.1469, "step": 174510 }, { - "epoch": 0.78, - "learning_rate": 1.1111160934487243e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.059953916019776e-05, + "loss": 0.1498, "step": 174520 }, { - "epoch": 0.78, - "learning_rate": 1.110891888256132e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.059842061698844e-05, + "loss": 0.1496, "step": 174530 }, { - "epoch": 0.78, - "learning_rate": 1.1106676830635398e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.059730207377911e-05, + "loss": 0.1474, "step": 174540 }, { - "epoch": 0.78, - "learning_rate": 1.1104434778709475e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.059618353056979e-05, + "loss": 0.1505, "step": 174550 }, { - "epoch": 0.78, - "learning_rate": 1.1102192726783552e-05, - "loss": 0.1548, + "epoch": 0.39, + "learning_rate": 3.059506498736046e-05, + "loss": 0.1543, "step": 174560 }, { - "epoch": 0.78, - "learning_rate": 1.109995067485763e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.0593946444151136e-05, + "loss": 0.152, "step": 174570 }, { - "epoch": 0.78, - "learning_rate": 1.1097708622931708e-05, - "loss": 0.1508, + "epoch": 0.39, + "learning_rate": 3.059282790094182e-05, + "loss": 0.1523, "step": 174580 }, { - "epoch": 0.78, - "learning_rate": 1.1095466571005785e-05, - "loss": 0.1554, + "epoch": 0.39, + "learning_rate": 3.059170935773249e-05, + "loss": 0.153, "step": 174590 }, { - "epoch": 0.78, - "learning_rate": 1.1093224519079864e-05, - "loss": 0.1553, + "epoch": 0.39, + "learning_rate": 3.059059081452317e-05, + "loss": 0.1466, "step": 174600 }, { - "epoch": 0.78, - "learning_rate": 1.109098246715394e-05, - "loss": 0.1556, + "epoch": 0.39, + "learning_rate": 3.058947227131384e-05, + "loss": 0.1497, "step": 174610 }, { - "epoch": 0.78, - "learning_rate": 1.1088740415228018e-05, - "loss": 0.1566, + "epoch": 0.39, + "learning_rate": 3.058835372810452e-05, + "loss": 0.1515, "step": 174620 }, { - "epoch": 0.78, - "learning_rate": 1.1086722568494687e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.05872351848952e-05, + "loss": 0.1514, "step": 174630 }, { - "epoch": 0.78, - "learning_rate": 1.1084480516568764e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.058611664168587e-05, + "loss": 0.1485, "step": 174640 }, { - "epoch": 0.78, - "learning_rate": 1.1082238464642841e-05, - "loss": 0.1586, + "epoch": 0.39, + "learning_rate": 3.0584998098476546e-05, + "loss": 0.1501, "step": 174650 }, { - "epoch": 0.78, - "learning_rate": 1.1079996412716918e-05, - "loss": 0.1607, + "epoch": 0.39, + "learning_rate": 3.058387955526722e-05, + "loss": 0.1502, "step": 174660 }, { - "epoch": 0.78, - "learning_rate": 1.1077754360790997e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.0582761012057895e-05, + "loss": 0.1476, "step": 174670 }, { - "epoch": 0.78, - "learning_rate": 1.1075512308865074e-05, - "loss": 0.1556, + "epoch": 0.39, + "learning_rate": 3.058164246884857e-05, + "loss": 0.1528, "step": 174680 }, { - "epoch": 0.78, - "learning_rate": 1.1073270256939151e-05, - "loss": 0.151, + "epoch": 0.39, + "learning_rate": 3.058052392563925e-05, + "loss": 0.1477, "step": 174690 }, { - "epoch": 0.78, - "learning_rate": 1.1071028205013228e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.057940538242993e-05, + "loss": 0.1532, "step": 174700 }, { - "epoch": 0.78, - "learning_rate": 1.1068786153087305e-05, - "loss": 0.157, + "epoch": 0.39, + "learning_rate": 3.05782868392206e-05, + "loss": 0.1507, "step": 174710 }, { - "epoch": 0.78, - "learning_rate": 1.1066544101161382e-05, - "loss": 0.1579, + "epoch": 0.39, + "learning_rate": 3.057716829601128e-05, + "loss": 0.1483, "step": 174720 }, { - "epoch": 0.78, - "learning_rate": 1.1064302049235461e-05, - "loss": 0.1566, + "epoch": 0.39, + "learning_rate": 3.057604975280195e-05, + "loss": 0.152, "step": 174730 }, { - "epoch": 0.78, - "learning_rate": 1.1062059997309538e-05, - "loss": 0.1558, + "epoch": 0.39, + "learning_rate": 3.057493120959263e-05, + "loss": 0.1506, "step": 174740 }, { - "epoch": 0.78, - "learning_rate": 1.1059817945383617e-05, - "loss": 0.16, + "epoch": 0.39, + "learning_rate": 3.0573924520704236e-05, + "loss": 0.1486, "step": 174750 }, { - "epoch": 0.78, - "learning_rate": 1.1057575893457694e-05, - "loss": 0.154, + "epoch": 0.39, + "learning_rate": 3.0572805977494913e-05, + "loss": 0.1417, "step": 174760 }, { - "epoch": 0.78, - "learning_rate": 1.105533384153177e-05, - "loss": 0.156, + "epoch": 0.39, + "learning_rate": 3.057168743428559e-05, + "loss": 0.1507, "step": 174770 }, { - "epoch": 0.78, - "learning_rate": 1.1053091789605848e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.057056889107626e-05, + "loss": 0.1507, "step": 174780 }, { - "epoch": 0.78, - "learning_rate": 1.1050849737679925e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.056945034786694e-05, + "loss": 0.1524, "step": 174790 }, { - "epoch": 0.78, - "learning_rate": 1.1048607685754002e-05, - "loss": 0.1579, + "epoch": 0.39, + "learning_rate": 3.056833180465761e-05, + "loss": 0.1476, "step": 174800 }, { - "epoch": 0.78, - "learning_rate": 1.104636563382808e-05, - "loss": 0.155, + "epoch": 0.39, + "learning_rate": 3.056721326144829e-05, + "loss": 0.1487, "step": 174810 }, { - "epoch": 0.78, - "learning_rate": 1.1044123581902158e-05, - "loss": 0.1558, + "epoch": 0.39, + "learning_rate": 3.056609471823897e-05, + "loss": 0.1517, "step": 174820 }, { - "epoch": 0.78, - "learning_rate": 1.1041881529976235e-05, - "loss": 0.1603, + "epoch": 0.39, + "learning_rate": 3.056497617502964e-05, + "loss": 0.1496, "step": 174830 }, { - "epoch": 0.78, - "learning_rate": 1.1039639478050312e-05, - "loss": 0.152, + "epoch": 0.39, + "learning_rate": 3.0563857631820317e-05, + "loss": 0.1526, "step": 174840 }, { - "epoch": 0.78, - "learning_rate": 1.1037397426124389e-05, - "loss": 0.156, + "epoch": 0.39, + "learning_rate": 3.0562739088610994e-05, + "loss": 0.1453, "step": 174850 }, { - "epoch": 0.78, - "learning_rate": 1.1035155374198466e-05, - "loss": 0.154, + "epoch": 0.39, + "learning_rate": 3.056162054540167e-05, + "loss": 0.1515, "step": 174860 }, { - "epoch": 0.78, - "learning_rate": 1.1032913322272544e-05, - "loss": 0.1549, + "epoch": 0.39, + "learning_rate": 3.056050200219235e-05, + "loss": 0.1491, "step": 174870 }, { - "epoch": 0.78, - "learning_rate": 1.1030671270346621e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.055938345898302e-05, + "loss": 0.1557, "step": 174880 }, { - "epoch": 0.78, - "learning_rate": 1.10284292184207e-05, - "loss": 0.1524, + "epoch": 0.39, + "learning_rate": 3.05582649157737e-05, + "loss": 0.1518, "step": 174890 }, { - "epoch": 0.78, - "learning_rate": 1.1026187166494777e-05, - "loss": 0.1513, + "epoch": 0.39, + "learning_rate": 3.055714637256437e-05, + "loss": 0.1478, "step": 174900 }, { - "epoch": 0.78, - "learning_rate": 1.1023945114568854e-05, - "loss": 0.1645, + "epoch": 0.39, + "learning_rate": 3.055602782935505e-05, + "loss": 0.1481, "step": 174910 }, { - "epoch": 0.78, - "learning_rate": 1.1021703062642931e-05, - "loss": 0.1571, + "epoch": 0.39, + "learning_rate": 3.0554909286145726e-05, + "loss": 0.1507, "step": 174920 }, { - "epoch": 0.78, - "learning_rate": 1.1019461010717008e-05, - "loss": 0.1509, + "epoch": 0.39, + "learning_rate": 3.05537907429364e-05, + "loss": 0.1454, "step": 174930 }, { - "epoch": 0.78, - "learning_rate": 1.1017218958791087e-05, - "loss": 0.1624, + "epoch": 0.39, + "learning_rate": 3.0552672199727075e-05, + "loss": 0.1464, "step": 174940 }, { - "epoch": 0.78, - "learning_rate": 1.1014976906865164e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.0551553656517753e-05, + "loss": 0.1519, "step": 174950 }, { - "epoch": 0.78, - "learning_rate": 1.1012734854939241e-05, - "loss": 0.158, + "epoch": 0.39, + "learning_rate": 3.055043511330843e-05, + "loss": 0.1543, "step": 174960 }, { - "epoch": 0.78, - "learning_rate": 1.1010492803013318e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.054931657009911e-05, + "loss": 0.152, "step": 174970 }, { - "epoch": 0.78, - "learning_rate": 1.1008250751087395e-05, - "loss": 0.153, + "epoch": 0.39, + "learning_rate": 3.054819802688978e-05, + "loss": 0.147, "step": 174980 }, { - "epoch": 0.78, - "learning_rate": 1.1006008699161472e-05, - "loss": 0.1523, + "epoch": 0.39, + "learning_rate": 3.054707948368046e-05, + "loss": 0.1504, "step": 174990 }, { - "epoch": 0.78, - "learning_rate": 1.100376664723555e-05, - "loss": 0.156, + "epoch": 0.39, + "learning_rate": 3.054596094047113e-05, + "loss": 0.1471, "step": 175000 }, { - "epoch": 0.78, - "learning_rate": 1.1001524595309628e-05, - "loss": 0.159, + "epoch": 0.39, + "learning_rate": 3.054484239726181e-05, + "loss": 0.1493, "step": 175010 }, { - "epoch": 0.78, - "learning_rate": 1.0999282543383707e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.0543723854052485e-05, + "loss": 0.154, "step": 175020 }, { - "epoch": 0.78, - "learning_rate": 1.0997040491457784e-05, - "loss": 0.162, + "epoch": 0.39, + "learning_rate": 3.0542605310843157e-05, + "loss": 0.1517, "step": 175030 }, { - "epoch": 0.78, - "learning_rate": 1.099479843953186e-05, - "loss": 0.15, + "epoch": 0.39, + "learning_rate": 3.0541486767633834e-05, + "loss": 0.152, "step": 175040 }, { - "epoch": 0.78, - "learning_rate": 1.0992556387605938e-05, - "loss": 0.1568, + "epoch": 0.39, + "learning_rate": 3.054036822442451e-05, + "loss": 0.1551, "step": 175050 }, { - "epoch": 0.78, - "learning_rate": 1.0990314335680015e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.053924968121519e-05, + "loss": 0.148, "step": 175060 }, { - "epoch": 0.78, - "learning_rate": 1.0988072283754092e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.053813113800586e-05, + "loss": 0.1496, "step": 175070 }, { - "epoch": 0.78, - "learning_rate": 1.098583023182817e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.053701259479654e-05, + "loss": 0.1487, "step": 175080 }, { - "epoch": 0.78, - "learning_rate": 1.0983588179902247e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.053589405158722e-05, + "loss": 0.1492, "step": 175090 }, { - "epoch": 0.78, - "learning_rate": 1.0981346127976324e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.053477550837789e-05, + "loss": 0.1489, "step": 175100 }, { - "epoch": 0.78, - "learning_rate": 1.0979104076050401e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.0533656965168566e-05, + "loss": 0.1449, "step": 175110 }, { - "epoch": 0.78, - "learning_rate": 1.0976862024124478e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.053253842195924e-05, + "loss": 0.1489, "step": 175120 }, { - "epoch": 0.78, - "learning_rate": 1.0974619972198555e-05, - "loss": 0.1584, + "epoch": 0.39, + "learning_rate": 3.0531419878749915e-05, + "loss": 0.1497, "step": 175130 }, { - "epoch": 0.78, - "learning_rate": 1.0972377920272634e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.0530301335540593e-05, + "loss": 0.1528, "step": 175140 }, { - "epoch": 0.78, - "learning_rate": 1.0970135868346711e-05, - "loss": 0.1535, + "epoch": 0.39, + "learning_rate": 3.0529182792331265e-05, + "loss": 0.1456, "step": 175150 }, { - "epoch": 0.78, - "learning_rate": 1.096789381642079e-05, - "loss": 0.1575, + "epoch": 0.39, + "learning_rate": 3.052806424912195e-05, + "loss": 0.1492, "step": 175160 }, { - "epoch": 0.78, - "learning_rate": 1.0965651764494867e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.052694570591262e-05, + "loss": 0.149, "step": 175170 }, { - "epoch": 0.78, - "learning_rate": 1.0963409712568944e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.05258271627033e-05, + "loss": 0.1498, "step": 175180 }, { - "epoch": 0.78, - "learning_rate": 1.0961167660643021e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.0524708619493976e-05, + "loss": 0.1479, "step": 175190 }, { - "epoch": 0.78, - "learning_rate": 1.0958925608717098e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.052359007628465e-05, + "loss": 0.1526, "step": 175200 }, { - "epoch": 0.78, - "learning_rate": 1.0956683556791175e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.0522471533075325e-05, + "loss": 0.148, "step": 175210 }, { - "epoch": 0.78, - "learning_rate": 1.0954441504865254e-05, - "loss": 0.1567, + "epoch": 0.39, + "learning_rate": 3.0521352989865996e-05, + "loss": 0.1501, "step": 175220 }, { - "epoch": 0.78, - "learning_rate": 1.095219945293933e-05, - "loss": 0.1538, + "epoch": 0.39, + "learning_rate": 3.0520234446656674e-05, + "loss": 0.1473, "step": 175230 }, { - "epoch": 0.78, - "learning_rate": 1.0949957401013408e-05, - "loss": 0.1592, + "epoch": 0.39, + "learning_rate": 3.051911590344735e-05, + "loss": 0.1491, "step": 175240 }, { - "epoch": 0.78, - "learning_rate": 1.0947715349087485e-05, - "loss": 0.1566, + "epoch": 0.39, + "learning_rate": 3.0517997360238023e-05, + "loss": 0.155, "step": 175250 }, { - "epoch": 0.78, - "learning_rate": 1.0945473297161562e-05, - "loss": 0.1536, + "epoch": 0.39, + "learning_rate": 3.0516878817028705e-05, + "loss": 0.1507, "step": 175260 }, { - "epoch": 0.78, - "learning_rate": 1.094323124523564e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.0515760273819376e-05, + "loss": 0.1541, "step": 175270 }, { - "epoch": 0.78, - "learning_rate": 1.0940989193309718e-05, + "epoch": 0.39, + "learning_rate": 3.0514641730610054e-05, "loss": 0.1526, "step": 175280 }, { - "epoch": 0.78, - "learning_rate": 1.0938747141383796e-05, - "loss": 0.1623, + "epoch": 0.39, + "learning_rate": 3.0513523187400732e-05, + "loss": 0.1502, "step": 175290 }, { - "epoch": 0.78, - "learning_rate": 1.0936505089457873e-05, - "loss": 0.1584, + "epoch": 0.39, + "learning_rate": 3.0512404644191406e-05, + "loss": 0.1562, "step": 175300 }, { - "epoch": 0.78, - "learning_rate": 1.093426303753195e-05, - "loss": 0.1497, + "epoch": 0.39, + "learning_rate": 3.0511286100982084e-05, + "loss": 0.1539, "step": 175310 }, { - "epoch": 0.78, - "learning_rate": 1.0932020985606027e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.0510167557772755e-05, + "loss": 0.1469, "step": 175320 }, { - "epoch": 0.78, - "learning_rate": 1.0929778933680104e-05, - "loss": 0.1527, + "epoch": 0.39, + "learning_rate": 3.0509049014563433e-05, + "loss": 0.1482, "step": 175330 }, { - "epoch": 0.78, - "learning_rate": 1.0927536881754181e-05, - "loss": 0.1565, + "epoch": 0.39, + "learning_rate": 3.050793047135411e-05, + "loss": 0.148, "step": 175340 }, { - "epoch": 0.78, - "learning_rate": 1.0925294829828258e-05, - "loss": 0.1575, + "epoch": 0.39, + "learning_rate": 3.0506811928144786e-05, + "loss": 0.1531, "step": 175350 }, { - "epoch": 0.78, - "learning_rate": 1.0923052777902337e-05, - "loss": 0.1524, + "epoch": 0.39, + "learning_rate": 3.0505693384935464e-05, + "loss": 0.1445, "step": 175360 }, { - "epoch": 0.78, - "learning_rate": 1.0920810725976414e-05, - "loss": 0.153, + "epoch": 0.39, + "learning_rate": 3.0504574841726135e-05, + "loss": 0.1555, "step": 175370 }, { - "epoch": 0.78, - "learning_rate": 1.0918568674050491e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0503456298516813e-05, + "loss": 0.149, "step": 175380 }, { - "epoch": 0.78, - "learning_rate": 1.0916326622124568e-05, - "loss": 0.1556, + "epoch": 0.39, + "learning_rate": 3.0502337755307487e-05, + "loss": 0.1519, "step": 175390 }, { - "epoch": 0.78, - "learning_rate": 1.0914084570198645e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.0501219212098165e-05, + "loss": 0.1439, "step": 175400 }, { - "epoch": 0.78, - "learning_rate": 1.0911842518272724e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.0500100668888843e-05, + "loss": 0.1499, "step": 175410 }, { - "epoch": 0.78, - "learning_rate": 1.0909600466346801e-05, - "loss": 0.1565, + "epoch": 0.39, + "learning_rate": 3.0498982125679514e-05, + "loss": 0.1539, "step": 175420 }, { - "epoch": 0.78, - "learning_rate": 1.090735841442088e-05, - "loss": 0.1563, + "epoch": 0.39, + "learning_rate": 3.0497863582470192e-05, + "loss": 0.1542, "step": 175430 }, { - "epoch": 0.78, - "learning_rate": 1.0905116362494957e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0496745039260867e-05, + "loss": 0.1479, "step": 175440 }, { - "epoch": 0.78, - "learning_rate": 1.0902874310569034e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.0495626496051545e-05, + "loss": 0.1473, "step": 175450 }, { - "epoch": 0.78, - "learning_rate": 1.090063225864311e-05, - "loss": 0.1535, + "epoch": 0.39, + "learning_rate": 3.0494507952842223e-05, + "loss": 0.1517, "step": 175460 }, { - "epoch": 0.78, - "learning_rate": 1.0898390206717188e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.0493389409632894e-05, + "loss": 0.1494, "step": 175470 }, { - "epoch": 0.78, - "learning_rate": 1.0896148154791265e-05, - "loss": 0.1459, + "epoch": 0.39, + "learning_rate": 3.0492270866423572e-05, + "loss": 0.1566, "step": 175480 }, { - "epoch": 0.78, - "learning_rate": 1.0893906102865344e-05, - "loss": 0.1469, + "epoch": 0.39, + "learning_rate": 3.0491152323214246e-05, + "loss": 0.1498, "step": 175490 }, { - "epoch": 0.78, - "learning_rate": 1.089166405093942e-05, - "loss": 0.1509, + "epoch": 0.39, + "learning_rate": 3.0490033780004924e-05, + "loss": 0.1467, "step": 175500 }, { - "epoch": 0.78, - "learning_rate": 1.0889421999013498e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.0488915236795602e-05, + "loss": 0.1502, "step": 175510 }, { - "epoch": 0.78, - "learning_rate": 1.0887179947087575e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.0487796693586273e-05, + "loss": 0.1556, "step": 175520 }, { - "epoch": 0.78, - "learning_rate": 1.0884937895161652e-05, - "loss": 0.15, + "epoch": 0.39, + "learning_rate": 3.048667815037695e-05, + "loss": 0.1518, "step": 175530 }, { - "epoch": 0.78, - "learning_rate": 1.0882695843235729e-05, - "loss": 0.1523, + "epoch": 0.39, + "learning_rate": 3.0485559607167626e-05, + "loss": 0.1494, "step": 175540 }, { - "epoch": 0.78, - "learning_rate": 1.0880453791309807e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0484441063958304e-05, + "loss": 0.1465, "step": 175550 }, { - "epoch": 0.78, - "learning_rate": 1.0878211739383886e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.048332252074898e-05, + "loss": 0.1486, "step": 175560 }, { - "epoch": 0.78, - "learning_rate": 1.0875969687457963e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.0482203977539653e-05, + "loss": 0.1551, "step": 175570 }, { - "epoch": 0.78, - "learning_rate": 1.087372763553204e-05, - "loss": 0.1586, + "epoch": 0.39, + "learning_rate": 3.048108543433033e-05, + "loss": 0.1541, "step": 175580 }, { - "epoch": 0.78, - "learning_rate": 1.0871485583606117e-05, - "loss": 0.1599, + "epoch": 0.39, + "learning_rate": 3.0479966891121002e-05, + "loss": 0.1527, "step": 175590 }, { - "epoch": 0.78, - "learning_rate": 1.0869243531680194e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.0478848347911683e-05, + "loss": 0.1512, "step": 175600 }, { - "epoch": 0.78, - "learning_rate": 1.0867001479754271e-05, - "loss": 0.1566, + "epoch": 0.39, + "learning_rate": 3.047772980470236e-05, + "loss": 0.1518, "step": 175610 }, { - "epoch": 0.78, - "learning_rate": 1.0864759427828348e-05, - "loss": 0.1554, + "epoch": 0.39, + "learning_rate": 3.0476611261493032e-05, + "loss": 0.1491, "step": 175620 }, { - "epoch": 0.78, - "learning_rate": 1.0862517375902427e-05, - "loss": 0.1593, + "epoch": 0.39, + "learning_rate": 3.047549271828371e-05, + "loss": 0.1465, "step": 175630 }, { - "epoch": 0.78, - "learning_rate": 1.0860275323976504e-05, - "loss": 0.1595, + "epoch": 0.39, + "learning_rate": 3.047437417507438e-05, + "loss": 0.15, "step": 175640 }, { - "epoch": 0.78, - "learning_rate": 1.0858033272050581e-05, - "loss": 0.1539, + "epoch": 0.39, + "learning_rate": 3.047325563186506e-05, + "loss": 0.1519, "step": 175650 }, { - "epoch": 0.78, - "learning_rate": 1.0855791220124658e-05, - "loss": 0.1528, + "epoch": 0.39, + "learning_rate": 3.047213708865574e-05, + "loss": 0.1482, "step": 175660 }, { - "epoch": 0.78, - "learning_rate": 1.0853549168198735e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.0471018545446412e-05, + "loss": 0.1538, "step": 175670 }, { - "epoch": 0.78, - "learning_rate": 1.0851307116272814e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.046990000223709e-05, + "loss": 0.1469, "step": 175680 }, { - "epoch": 0.78, - "learning_rate": 1.084906506434689e-05, - "loss": 0.1553, + "epoch": 0.39, + "learning_rate": 3.046878145902776e-05, + "loss": 0.1485, "step": 175690 }, { - "epoch": 0.78, - "learning_rate": 1.084682301242097e-05, - "loss": 0.1608, + "epoch": 0.39, + "learning_rate": 3.046766291581844e-05, + "loss": 0.1529, "step": 175700 }, { - "epoch": 0.78, - "learning_rate": 1.0844580960495047e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0466544372609113e-05, + "loss": 0.1527, "step": 175710 }, { - "epoch": 0.78, - "learning_rate": 1.0842338908569124e-05, - "loss": 0.1533, + "epoch": 0.39, + "learning_rate": 3.046542582939979e-05, + "loss": 0.1484, "step": 175720 }, { - "epoch": 0.78, - "learning_rate": 1.08400968566432e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.046430728619047e-05, + "loss": 0.1555, "step": 175730 }, { - "epoch": 0.78, - "learning_rate": 1.0837854804717278e-05, - "loss": 0.1512, + "epoch": 0.39, + "learning_rate": 3.046318874298114e-05, + "loss": 0.1476, "step": 175740 }, { - "epoch": 0.78, - "learning_rate": 1.0835612752791355e-05, - "loss": 0.1572, + "epoch": 0.39, + "learning_rate": 3.0462070199771818e-05, + "loss": 0.1519, "step": 175750 }, { - "epoch": 0.78, - "learning_rate": 1.0833370700865432e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.0460951656562493e-05, + "loss": 0.1512, "step": 175760 }, { - "epoch": 0.78, - "learning_rate": 1.083112864893951e-05, - "loss": 0.1531, + "epoch": 0.39, + "learning_rate": 3.045983311335317e-05, + "loss": 0.1502, "step": 175770 }, { - "epoch": 0.78, - "learning_rate": 1.0828886597013587e-05, - "loss": 0.1532, + "epoch": 0.39, + "learning_rate": 3.045871457014385e-05, + "loss": 0.1471, "step": 175780 }, { - "epoch": 0.78, - "learning_rate": 1.0826644545087664e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.045759602693452e-05, + "loss": 0.1502, "step": 175790 }, { - "epoch": 0.78, - "learning_rate": 1.0824402493161741e-05, - "loss": 0.1588, + "epoch": 0.39, + "learning_rate": 3.0456477483725198e-05, + "loss": 0.1467, "step": 175800 }, { - "epoch": 0.78, - "learning_rate": 1.0822160441235819e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.0455358940515872e-05, + "loss": 0.1515, "step": 175810 }, { - "epoch": 0.78, - "learning_rate": 1.0819918389309897e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.045424039730655e-05, + "loss": 0.1516, "step": 175820 }, { - "epoch": 0.78, - "learning_rate": 1.0817676337383974e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.0453121854097228e-05, + "loss": 0.1507, "step": 175830 }, { - "epoch": 0.78, - "learning_rate": 1.0815434285458053e-05, - "loss": 0.1545, + "epoch": 0.39, + "learning_rate": 3.04520033108879e-05, + "loss": 0.1519, "step": 175840 }, { - "epoch": 0.79, - "learning_rate": 1.081319223353213e-05, - "loss": 0.1507, + "epoch": 0.39, + "learning_rate": 3.0450884767678577e-05, + "loss": 0.1521, "step": 175850 }, { - "epoch": 0.79, - "learning_rate": 1.0810950181606207e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.0449766224469252e-05, + "loss": 0.1517, "step": 175860 }, { - "epoch": 0.79, - "learning_rate": 1.0808708129680284e-05, - "loss": 0.1521, + "epoch": 0.39, + "learning_rate": 3.044864768125993e-05, + "loss": 0.1553, "step": 175870 }, { - "epoch": 0.79, - "learning_rate": 1.0806466077754361e-05, - "loss": 0.1615, + "epoch": 0.39, + "learning_rate": 3.0447529138050608e-05, + "loss": 0.1532, "step": 175880 }, { - "epoch": 0.79, - "learning_rate": 1.0804224025828438e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.044641059484128e-05, + "loss": 0.1538, "step": 175890 }, { - "epoch": 0.79, - "learning_rate": 1.0801981973902515e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.0445292051631957e-05, + "loss": 0.1498, "step": 175900 }, { - "epoch": 0.79, - "learning_rate": 1.0799739921976594e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.044417350842263e-05, + "loss": 0.1493, "step": 175910 }, { - "epoch": 0.79, - "learning_rate": 1.0797497870050671e-05, - "loss": 0.15, + "epoch": 0.39, + "learning_rate": 3.044305496521331e-05, + "loss": 0.149, "step": 175920 }, { - "epoch": 0.79, - "learning_rate": 1.0795255818124748e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.0441936422003987e-05, + "loss": 0.1519, "step": 175930 }, { - "epoch": 0.79, - "learning_rate": 1.0793013766198825e-05, - "loss": 0.1511, + "epoch": 0.39, + "learning_rate": 3.0440817878794658e-05, + "loss": 0.1539, "step": 175940 }, { - "epoch": 0.79, - "learning_rate": 1.0790771714272904e-05, - "loss": 0.1451, + "epoch": 0.39, + "learning_rate": 3.0439699335585336e-05, + "loss": 0.1497, "step": 175950 }, { - "epoch": 0.79, - "learning_rate": 1.078852966234698e-05, - "loss": 0.1567, + "epoch": 0.39, + "learning_rate": 3.043858079237601e-05, + "loss": 0.1454, "step": 175960 }, { - "epoch": 0.79, - "learning_rate": 1.0786287610421058e-05, - "loss": 0.1548, + "epoch": 0.39, + "learning_rate": 3.043746224916669e-05, + "loss": 0.15, "step": 175970 }, { - "epoch": 0.79, - "learning_rate": 1.0784045558495136e-05, - "loss": 0.1517, + "epoch": 0.39, + "learning_rate": 3.0436343705957367e-05, + "loss": 0.1482, "step": 175980 }, { - "epoch": 0.79, - "learning_rate": 1.0781803506569213e-05, - "loss": 0.1536, + "epoch": 0.39, + "learning_rate": 3.0435225162748038e-05, + "loss": 0.1548, "step": 175990 }, { - "epoch": 0.79, - "learning_rate": 1.077956145464329e-05, - "loss": 0.1501, + "epoch": 0.39, + "learning_rate": 3.0434106619538716e-05, + "loss": 0.1533, "step": 176000 }, { - "epoch": 0.79, - "eval_NEIMS_canon_smiles": 0.9436333333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.09533333333333334, - "eval_NEIMS_daylight_tanimoto_simil": 0.49817997067988024, - "eval_NEIMS_exact_mols": 0.09498333333333334, - "eval_NEIMS_exact_smiles": 0.09238333333333333, - "eval_NEIMS_loss": 0.19087590277194977, - "eval_NEIMS_matched_formulas": 0.6240333333333333, - "eval_NEIMS_morgan_tanimoto_simil": 0.40670017593076974, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.09548333333333334, - "eval_NEIMS_runtime": 712.1843, - "eval_NEIMS_samples_per_second": 84.248, - "eval_NEIMS_steps_per_second": 1.317, + "epoch": 0.39, + "eval_NEIMS_canon_smiles": 0.9499833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.1235, + "eval_NEIMS_daylight_tanimoto_simil": 0.5263809679518503, + "eval_NEIMS_exact_mols": 0.12326666666666666, + "eval_NEIMS_exact_smiles": 0.12005, + "eval_NEIMS_loss": 0.17554369568824768, + "eval_NEIMS_matched_formulas": 0.6571, + "eval_NEIMS_morgan_tanimoto_simil": 0.438047058614562, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.12381666666666667, + "eval_NEIMS_runtime": 737.7571, + "eval_NEIMS_samples_per_second": 81.328, + "eval_NEIMS_steps_per_second": 1.271, "step": 176000 }, { - "epoch": 0.79, - "eval_RASSP_canon_smiles": 0.9381741075900758, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.2163321868634588, - "eval_RASSP_daylight_tanimoto_simil": 0.6437398086932788, - "eval_RASSP_exact_mols": 0.21576451731392127, - "eval_RASSP_exact_smiles": 0.2090526596988012, - "eval_RASSP_loss": 0.1295212209224701, - "eval_RASSP_matched_formulas": 0.8016328847630815, - "eval_RASSP_morgan_tanimoto_simil": 0.5252261223042175, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.21589808661969478, - "eval_RASSP_runtime": 814.9341, - "eval_RASSP_samples_per_second": 73.496, - "eval_RASSP_steps_per_second": 1.149, + "epoch": 0.39, + "eval_RASSP_canon_smiles": 0.9487427789094066, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.1736567936688149, + "eval_RASSP_daylight_tanimoto_simil": 0.6197239753068624, + "eval_RASSP_exact_mols": 0.17318930109860753, + "eval_RASSP_exact_smiles": 0.16836410992753864, + "eval_RASSP_loss": 0.14111098647117615, + "eval_RASSP_matched_formulas": 0.8105820282499082, + "eval_RASSP_morgan_tanimoto_simil": 0.49142917336757186, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.17328947807793768, + "eval_RASSP_runtime": 840.7261, + "eval_RASSP_samples_per_second": 71.241, + "eval_RASSP_steps_per_second": 1.113, "step": 176000 }, { - "epoch": 0.79, - "eval_NIST_canon_smiles": 0.8716328920750968, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.016786740958938142, - "eval_NIST_daylight_tanimoto_simil": 0.2798117873592377, - "eval_NIST_exact_mols": 0.016076942186890018, - "eval_NIST_exact_smiles": 0.014763814458600987, - "eval_NIST_loss": 1.874320149421692, - "eval_NIST_matched_formulas": 0.09791674060403875, - "eval_NIST_morgan_tanimoto_simil": 0.23257471064607163, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.01660929126592611, - "eval_NIST_runtime": 472.9919, - "eval_NIST_samples_per_second": 59.572, - "eval_NIST_steps_per_second": 0.932, + "epoch": 0.39, + "eval_NEIMS_old_canon_smiles": 0.9504, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.1227, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5266931986294461, + "eval_NEIMS_old_exact_mols": 0.12236666666666667, + "eval_NEIMS_old_exact_smiles": 0.11926666666666667, + "eval_NEIMS_old_loss": 0.1752040535211563, + "eval_NEIMS_old_matched_formulas": 0.657, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4379438822121596, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.12303333333333333, + "eval_NEIMS_old_runtime": 367.8848, + "eval_NEIMS_old_samples_per_second": 81.547, + "eval_NEIMS_old_steps_per_second": 1.275, "step": 176000 }, { - "epoch": 0.79, - "learning_rate": 1.0777319402717367e-05, - "loss": 0.1522, + "epoch": 0.39, + "eval_RASSP_old_canon_smiles": 0.9472753362031568, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.1937130843928321, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6363740168286994, + "eval_RASSP_old_exact_mols": 0.19314579370641038, + "eval_RASSP_old_exact_smiles": 0.18787332732672607, + "eval_RASSP_old_loss": 0.1344922035932541, + "eval_RASSP_old_matched_formulas": 0.8231054159575533, + "eval_RASSP_old_morgan_tanimoto_simil": 0.511576860157094, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.19327927386792138, + "eval_RASSP_old_runtime": 412.0612, + "eval_RASSP_old_samples_per_second": 72.725, + "eval_RASSP_old_steps_per_second": 1.138, + "step": 176000 + }, + { + "epoch": 0.39, + "eval_NIST_canon_smiles": 0.8690066366185186, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02065514426660042, + "eval_NIST_daylight_tanimoto_simil": 0.2846762669774248, + "eval_NIST_exact_mols": 0.01962593604713064, + "eval_NIST_exact_smiles": 0.018809667459275297, + "eval_NIST_loss": 1.8544813394546509, + "eval_NIST_matched_formulas": 0.10568903715796572, + "eval_NIST_morgan_tanimoto_simil": 0.2367739252304438, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.020371224757781168, + "eval_NIST_runtime": 572.8226, + "eval_NIST_samples_per_second": 49.19, + "eval_NIST_steps_per_second": 0.77, + "step": 176000 + }, + { + "epoch": 0.39, + "learning_rate": 3.0432988076329387e-05, + "loss": 0.156, "step": 176010 }, { - "epoch": 0.79, - "learning_rate": 1.0775077350791444e-05, - "loss": 0.1591, + "epoch": 0.39, + "learning_rate": 3.0431869533120068e-05, + "loss": 0.1471, "step": 176020 }, { - "epoch": 0.79, - "learning_rate": 1.0772835298865521e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.043075098991074e-05, + "loss": 0.1472, "step": 176030 }, { - "epoch": 0.79, - "learning_rate": 1.0770593246939599e-05, - "loss": 0.1516, + "epoch": 0.39, + "learning_rate": 3.0429632446701417e-05, + "loss": 0.1475, "step": 176040 }, { - "epoch": 0.79, - "learning_rate": 1.0768351195013677e-05, - "loss": 0.1573, + "epoch": 0.39, + "learning_rate": 3.0428513903492095e-05, + "loss": 0.1498, "step": 176050 }, { - "epoch": 0.79, - "learning_rate": 1.0766109143087754e-05, - "loss": 0.1584, + "epoch": 0.39, + "learning_rate": 3.0427395360282766e-05, + "loss": 0.1539, "step": 176060 }, { - "epoch": 0.79, - "learning_rate": 1.0763867091161831e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.0426276817073444e-05, + "loss": 0.1522, "step": 176070 }, { - "epoch": 0.79, - "learning_rate": 1.0761625039235908e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.042515827386412e-05, + "loss": 0.152, "step": 176080 }, { - "epoch": 0.79, - "learning_rate": 1.0759382987309987e-05, - "loss": 0.1553, + "epoch": 0.39, + "learning_rate": 3.0424039730654797e-05, + "loss": 0.1493, "step": 176090 }, { - "epoch": 0.79, - "learning_rate": 1.0757140935384064e-05, - "loss": 0.1535, + "epoch": 0.39, + "learning_rate": 3.0422921187445475e-05, + "loss": 0.148, "step": 176100 }, { - "epoch": 0.79, - "learning_rate": 1.0754898883458141e-05, - "loss": 0.1575, + "epoch": 0.39, + "learning_rate": 3.0421802644236146e-05, + "loss": 0.1525, "step": 176110 }, { - "epoch": 0.79, - "learning_rate": 1.075265683153222e-05, - "loss": 0.151, + "epoch": 0.39, + "learning_rate": 3.0420684101026824e-05, + "loss": 0.1495, "step": 176120 }, { - "epoch": 0.79, - "learning_rate": 1.0750414779606297e-05, - "loss": 0.1564, + "epoch": 0.39, + "learning_rate": 3.0419565557817498e-05, + "loss": 0.1549, "step": 176130 }, { - "epoch": 0.79, - "learning_rate": 1.0748172727680374e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.0418447014608176e-05, + "loss": 0.1562, "step": 176140 }, { - "epoch": 0.79, - "learning_rate": 1.0745930675754451e-05, - "loss": 0.1568, + "epoch": 0.39, + "learning_rate": 3.0417328471398854e-05, + "loss": 0.1546, "step": 176150 }, { - "epoch": 0.79, - "learning_rate": 1.0743688623828528e-05, - "loss": 0.1555, + "epoch": 0.39, + "learning_rate": 3.0416209928189525e-05, + "loss": 0.1477, "step": 176160 }, { - "epoch": 0.79, - "learning_rate": 1.0741446571902605e-05, - "loss": 0.1529, + "epoch": 0.39, + "learning_rate": 3.0415091384980203e-05, + "loss": 0.149, "step": 176170 }, { - "epoch": 0.79, - "learning_rate": 1.0739204519976684e-05, - "loss": 0.153, + "epoch": 0.39, + "learning_rate": 3.0413972841770878e-05, + "loss": 0.1475, "step": 176180 }, { - "epoch": 0.79, - "learning_rate": 1.073696246805076e-05, - "loss": 0.1569, + "epoch": 0.39, + "learning_rate": 3.0412854298561556e-05, + "loss": 0.1494, "step": 176190 }, { - "epoch": 0.79, - "learning_rate": 1.0734720416124838e-05, - "loss": 0.1518, + "epoch": 0.39, + "learning_rate": 3.0411735755352233e-05, + "loss": 0.1534, "step": 176200 }, { - "epoch": 0.79, - "learning_rate": 1.0732478364198915e-05, - "loss": 0.1544, + "epoch": 0.39, + "learning_rate": 3.0410617212142905e-05, + "loss": 0.1528, "step": 176210 }, { - "epoch": 0.79, - "learning_rate": 1.0730236312272993e-05, - "loss": 0.1561, + "epoch": 0.39, + "learning_rate": 3.0409498668933583e-05, + "loss": 0.1499, "step": 176220 }, { - "epoch": 0.79, - "learning_rate": 1.072799426034707e-05, - "loss": 0.1606, + "epoch": 0.39, + "learning_rate": 3.0408380125724257e-05, + "loss": 0.1539, "step": 176230 }, { - "epoch": 0.79, - "learning_rate": 1.0725752208421147e-05, - "loss": 0.1526, + "epoch": 0.39, + "learning_rate": 3.0407261582514935e-05, + "loss": 0.1559, "step": 176240 }, { - "epoch": 0.79, - "learning_rate": 1.0723510156495226e-05, - "loss": 0.1534, + "epoch": 0.39, + "learning_rate": 3.0406143039305613e-05, + "loss": 0.1476, "step": 176250 }, { - "epoch": 0.79, - "learning_rate": 1.0721268104569303e-05, - "loss": 0.1523, + "epoch": 0.39, + "learning_rate": 3.0405024496096284e-05, + "loss": 0.1498, "step": 176260 }, { - "epoch": 0.79, - "learning_rate": 1.071902605264338e-05, - "loss": 0.1562, + "epoch": 0.39, + "learning_rate": 3.0403905952886962e-05, + "loss": 0.1518, "step": 176270 }, { - "epoch": 0.79, - "learning_rate": 1.0716784000717457e-05, - "loss": 0.1533, + "epoch": 0.39, + "learning_rate": 3.0402787409677637e-05, + "loss": 0.1454, "step": 176280 }, { - "epoch": 0.79, - "learning_rate": 1.0714541948791534e-05, - "loss": 0.1625, + "epoch": 0.39, + "learning_rate": 3.0401668866468315e-05, + "loss": 0.1464, "step": 176290 }, { - "epoch": 0.79, - "learning_rate": 1.0712299896865611e-05, - "loss": 0.1514, + "epoch": 0.39, + "learning_rate": 3.0400550323258992e-05, + "loss": 0.1516, "step": 176300 }, { - "epoch": 0.79, - "learning_rate": 1.0710057844939688e-05, - "loss": 0.1511, + "epoch": 0.39, + "learning_rate": 3.0399431780049664e-05, + "loss": 0.154, "step": 176310 }, { - "epoch": 0.79, - "learning_rate": 1.0707815793013767e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.039831323684034e-05, + "loss": 0.1485, "step": 176320 }, { - "epoch": 0.79, - "learning_rate": 1.0705573741087844e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.0397194693631016e-05, + "loss": 0.1459, "step": 176330 }, { - "epoch": 0.79, - "learning_rate": 1.0703331689161921e-05, - "loss": 0.1539, + "epoch": 0.39, + "learning_rate": 3.0396076150421694e-05, + "loss": 0.1472, "step": 176340 }, { - "epoch": 0.79, - "learning_rate": 1.0701089637235998e-05, - "loss": 0.1597, + "epoch": 0.39, + "learning_rate": 3.0394957607212365e-05, + "loss": 0.1496, "step": 176350 }, { - "epoch": 0.79, - "learning_rate": 1.0698847585310077e-05, - "loss": 0.151, + "epoch": 0.39, + "learning_rate": 3.0393839064003043e-05, + "loss": 0.1477, "step": 176360 }, { - "epoch": 0.79, - "learning_rate": 1.0696605533384154e-05, - "loss": 0.1551, + "epoch": 0.39, + "learning_rate": 3.039272052079372e-05, + "loss": 0.1523, "step": 176370 }, { - "epoch": 0.79, - "learning_rate": 1.0694363481458231e-05, - "loss": 0.1544, + "epoch": 0.39, + "learning_rate": 3.0391601977584396e-05, + "loss": 0.1486, "step": 176380 }, { - "epoch": 0.79, - "learning_rate": 1.069212142953231e-05, - "loss": 0.1557, + "epoch": 0.39, + "learning_rate": 3.0390483434375073e-05, + "loss": 0.1507, "step": 176390 }, { - "epoch": 0.79, - "learning_rate": 1.0689879377606387e-05, - "loss": 0.1536, + "epoch": 0.39, + "learning_rate": 3.0389364891165745e-05, + "loss": 0.1488, "step": 176400 }, { - "epoch": 0.79, - "learning_rate": 1.0687637325680464e-05, - "loss": 0.1526, + "epoch": 0.39, + "learning_rate": 3.0388246347956423e-05, + "loss": 0.1502, "step": 176410 }, { - "epoch": 0.79, - "learning_rate": 1.068539527375454e-05, - "loss": 0.1531, + "epoch": 0.39, + "learning_rate": 3.03871278047471e-05, + "loss": 0.1509, "step": 176420 }, { - "epoch": 0.79, - "learning_rate": 1.0683153221828618e-05, - "loss": 0.1518, + "epoch": 0.39, + "learning_rate": 3.0386009261537775e-05, + "loss": 0.1425, "step": 176430 }, { - "epoch": 0.79, - "learning_rate": 1.0680911169902695e-05, - "loss": 0.1535, + "epoch": 0.39, + "learning_rate": 3.0384890718328453e-05, + "loss": 0.1468, "step": 176440 }, { - "epoch": 0.79, - "learning_rate": 1.0678669117976772e-05, - "loss": 0.1541, + "epoch": 0.39, + "learning_rate": 3.0383772175119124e-05, + "loss": 0.148, "step": 176450 }, { - "epoch": 0.79, - "learning_rate": 1.067642706605085e-05, - "loss": 0.1606, + "epoch": 0.39, + "learning_rate": 3.0382653631909802e-05, + "loss": 0.1539, "step": 176460 }, { - "epoch": 0.79, - "learning_rate": 1.0674185014124927e-05, - "loss": 0.1598, + "epoch": 0.39, + "learning_rate": 3.038153508870048e-05, + "loss": 0.1492, "step": 176470 }, { - "epoch": 0.79, - "learning_rate": 1.0671942962199005e-05, - "loss": 0.154, + "epoch": 0.39, + "learning_rate": 3.038041654549115e-05, + "loss": 0.1509, "step": 176480 }, { - "epoch": 0.79, - "learning_rate": 1.0669700910273083e-05, - "loss": 0.1592, + "epoch": 0.39, + "learning_rate": 3.0379298002281832e-05, + "loss": 0.15, "step": 176490 }, { - "epoch": 0.79, - "learning_rate": 1.066745885834716e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.0378179459072504e-05, + "loss": 0.1494, "step": 176500 }, { - "epoch": 0.79, - "learning_rate": 1.0665216806421237e-05, - "loss": 0.1589, + "epoch": 0.39, + "learning_rate": 3.037706091586318e-05, + "loss": 0.1487, "step": 176510 }, { - "epoch": 0.79, - "learning_rate": 1.0662974754495314e-05, - "loss": 0.1602, + "epoch": 0.39, + "learning_rate": 3.037594237265386e-05, + "loss": 0.1479, "step": 176520 }, { - "epoch": 0.79, - "learning_rate": 1.0660732702569393e-05, - "loss": 0.1484, + "epoch": 0.39, + "learning_rate": 3.037482382944453e-05, + "loss": 0.149, "step": 176530 }, { - "epoch": 0.79, - "learning_rate": 1.065849065064347e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.037370528623521e-05, + "loss": 0.151, "step": 176540 }, { - "epoch": 0.79, - "learning_rate": 1.0656248598717547e-05, - "loss": 0.15, + "epoch": 0.39, + "learning_rate": 3.0372586743025883e-05, + "loss": 0.141, "step": 176550 }, { - "epoch": 0.79, - "learning_rate": 1.0654006546791624e-05, - "loss": 0.1577, + "epoch": 0.39, + "learning_rate": 3.037146819981656e-05, + "loss": 0.1512, "step": 176560 }, { - "epoch": 0.79, - "learning_rate": 1.0651764494865701e-05, - "loss": 0.1595, + "epoch": 0.39, + "learning_rate": 3.037034965660724e-05, + "loss": 0.1511, "step": 176570 }, { - "epoch": 0.79, - "learning_rate": 1.0649522442939778e-05, - "loss": 0.1525, + "epoch": 0.39, + "learning_rate": 3.036923111339791e-05, + "loss": 0.1552, "step": 176580 }, { - "epoch": 0.79, - "learning_rate": 1.0647280391013855e-05, - "loss": 0.1503, + "epoch": 0.39, + "learning_rate": 3.0368112570188588e-05, + "loss": 0.1468, "step": 176590 }, { - "epoch": 0.79, - "learning_rate": 1.0645038339087934e-05, - "loss": 0.1486, + "epoch": 0.39, + "learning_rate": 3.0366994026979263e-05, + "loss": 0.1494, "step": 176600 }, { - "epoch": 0.79, - "learning_rate": 1.0642796287162011e-05, - "loss": 0.1514, + "epoch": 0.39, + "learning_rate": 3.036587548376994e-05, + "loss": 0.1491, "step": 176610 }, { - "epoch": 0.79, - "learning_rate": 1.0640554235236088e-05, - "loss": 0.156, + "epoch": 0.39, + "learning_rate": 3.036475694056062e-05, + "loss": 0.1507, "step": 176620 }, { - "epoch": 0.79, - "learning_rate": 1.0638312183310167e-05, - "loss": 0.1574, + "epoch": 0.39, + "learning_rate": 3.036363839735129e-05, + "loss": 0.1533, "step": 176630 }, { - "epoch": 0.79, - "learning_rate": 1.0636070131384244e-05, - "loss": 0.1542, + "epoch": 0.39, + "learning_rate": 3.0362519854141967e-05, + "loss": 0.1511, "step": 176640 }, { - "epoch": 0.79, - "learning_rate": 1.063382807945832e-05, - "loss": 0.1578, + "epoch": 0.39, + "learning_rate": 3.0361401310932642e-05, + "loss": 0.1512, "step": 176650 }, { - "epoch": 0.79, - "learning_rate": 1.0631586027532398e-05, - "loss": 0.1455, + "epoch": 0.39, + "learning_rate": 3.036028276772332e-05, + "loss": 0.148, "step": 176660 }, { - "epoch": 0.79, - "learning_rate": 1.0629343975606476e-05, - "loss": 0.1526, + "epoch": 0.39, + "learning_rate": 3.035916422451399e-05, + "loss": 0.1451, "step": 176670 }, { - "epoch": 0.79, - "learning_rate": 1.0627101923680553e-05, - "loss": 0.1543, + "epoch": 0.39, + "learning_rate": 3.035804568130467e-05, + "loss": 0.1479, "step": 176680 }, { - "epoch": 0.79, - "learning_rate": 1.062485987175463e-05, - "loss": 0.152, + "epoch": 0.39, + "learning_rate": 3.0356927138095347e-05, + "loss": 0.1472, "step": 176690 }, { - "epoch": 0.79, - "learning_rate": 1.0622617819828707e-05, - "loss": 0.1632, + "epoch": 0.39, + "learning_rate": 3.035580859488602e-05, + "loss": 0.15, "step": 176700 }, { - "epoch": 0.79, - "learning_rate": 1.0620375767902785e-05, - "loss": 0.1519, + "epoch": 0.39, + "learning_rate": 3.03546900516767e-05, + "loss": 0.1492, "step": 176710 }, { - "epoch": 0.79, - "learning_rate": 1.0618133715976862e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.035357150846737e-05, + "loss": 0.1486, "step": 176720 }, { - "epoch": 0.79, - "learning_rate": 1.0615891664050939e-05, - "loss": 0.1523, + "epoch": 0.39, + "learning_rate": 3.035245296525805e-05, + "loss": 0.1486, "step": 176730 }, { - "epoch": 0.79, - "learning_rate": 1.0613649612125017e-05, - "loss": 0.153, + "epoch": 0.39, + "learning_rate": 3.0351334422048726e-05, + "loss": 0.145, "step": 176740 }, { - "epoch": 0.79, - "learning_rate": 1.0611407560199094e-05, - "loss": 0.1497, + "epoch": 0.39, + "learning_rate": 3.03502158788394e-05, + "loss": 0.1489, "step": 176750 }, { - "epoch": 0.79, - "learning_rate": 1.0609165508273173e-05, - "loss": 0.1576, + "epoch": 0.39, + "learning_rate": 3.034909733563008e-05, + "loss": 0.1498, "step": 176760 }, { - "epoch": 0.79, - "learning_rate": 1.060692345634725e-05, - "loss": 0.1581, + "epoch": 0.39, + "learning_rate": 3.034797879242075e-05, + "loss": 0.1512, "step": 176770 }, { - "epoch": 0.79, - "learning_rate": 1.0604681404421327e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.0346860249211428e-05, + "loss": 0.1509, "step": 176780 }, { - "epoch": 0.79, - "learning_rate": 1.0602439352495404e-05, - "loss": 0.1515, + "epoch": 0.39, + "learning_rate": 3.0345741706002106e-05, + "loss": 0.1527, "step": 176790 }, { - "epoch": 0.79, - "learning_rate": 1.0600197300569481e-05, - "loss": 0.153, + "epoch": 0.39, + "learning_rate": 3.034462316279278e-05, + "loss": 0.1501, "step": 176800 }, { - "epoch": 0.79, - "learning_rate": 1.059795524864356e-05, - "loss": 0.1583, + "epoch": 0.39, + "learning_rate": 3.034350461958346e-05, + "loss": 0.1504, "step": 176810 }, { - "epoch": 0.79, - "learning_rate": 1.0595713196717637e-05, - "loss": 0.1501, + "epoch": 0.39, + "learning_rate": 3.034238607637413e-05, + "loss": 0.157, "step": 176820 }, { - "epoch": 0.79, - "learning_rate": 1.0593471144791714e-05, - "loss": 0.1514, + "epoch": 0.39, + "learning_rate": 3.0341267533164807e-05, + "loss": 0.1459, "step": 176830 }, { - "epoch": 0.79, - "learning_rate": 1.0591229092865791e-05, - "loss": 0.1567, + "epoch": 0.39, + "learning_rate": 3.0340148989955485e-05, + "loss": 0.1562, "step": 176840 }, { - "epoch": 0.79, - "learning_rate": 1.0588987040939868e-05, - "loss": 0.1553, + "epoch": 0.39, + "learning_rate": 3.033903044674616e-05, + "loss": 0.1469, "step": 176850 }, { - "epoch": 0.79, - "learning_rate": 1.0586744989013945e-05, - "loss": 0.1553, + "epoch": 0.39, + "learning_rate": 3.0337911903536838e-05, + "loss": 0.1437, "step": 176860 }, { - "epoch": 0.79, - "learning_rate": 1.0584502937088024e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.033679336032751e-05, + "loss": 0.1495, "step": 176870 }, { - "epoch": 0.79, - "learning_rate": 1.05822608851621e-05, - "loss": 0.1517, + "epoch": 0.39, + "learning_rate": 3.0335674817118187e-05, + "loss": 0.1492, "step": 176880 }, { - "epoch": 0.79, - "learning_rate": 1.0580018833236178e-05, - "loss": 0.1546, + "epoch": 0.39, + "learning_rate": 3.0334556273908865e-05, + "loss": 0.1468, "step": 176890 }, { - "epoch": 0.79, - "learning_rate": 1.0577776781310256e-05, - "loss": 0.1491, + "epoch": 0.39, + "learning_rate": 3.0333437730699536e-05, + "loss": 0.1449, "step": 176900 }, { - "epoch": 0.79, - "learning_rate": 1.0575534729384333e-05, - "loss": 0.1485, + "epoch": 0.39, + "learning_rate": 3.0332319187490217e-05, + "loss": 0.1536, "step": 176910 }, { - "epoch": 0.79, - "learning_rate": 1.057329267745841e-05, - "loss": 0.1518, + "epoch": 0.39, + "learning_rate": 3.033120064428089e-05, + "loss": 0.1491, "step": 176920 }, { - "epoch": 0.79, - "learning_rate": 1.0571050625532488e-05, - "loss": 0.152, + "epoch": 0.39, + "learning_rate": 3.0330082101071566e-05, + "loss": 0.1466, "step": 176930 }, { - "epoch": 0.79, - "learning_rate": 1.0568808573606566e-05, - "loss": 0.1537, + "epoch": 0.39, + "learning_rate": 3.0328963557862244e-05, + "loss": 0.1529, "step": 176940 }, { - "epoch": 0.79, - "learning_rate": 1.0566566521680643e-05, - "loss": 0.1473, + "epoch": 0.39, + "learning_rate": 3.0327845014652915e-05, + "loss": 0.1491, "step": 176950 }, { - "epoch": 0.79, - "learning_rate": 1.056432446975472e-05, - "loss": 0.1552, + "epoch": 0.39, + "learning_rate": 3.0326726471443593e-05, + "loss": 0.1509, "step": 176960 }, { - "epoch": 0.79, - "learning_rate": 1.0562082417828797e-05, - "loss": 0.1531, + "epoch": 0.4, + "learning_rate": 3.0325607928234268e-05, + "loss": 0.152, "step": 176970 }, { - "epoch": 0.79, - "learning_rate": 1.0559840365902874e-05, - "loss": 0.1532, + "epoch": 0.4, + "learning_rate": 3.0324489385024946e-05, + "loss": 0.1495, "step": 176980 }, { - "epoch": 0.79, - "learning_rate": 1.0557598313976951e-05, - "loss": 0.1494, + "epoch": 0.4, + "learning_rate": 3.0323370841815617e-05, + "loss": 0.147, "step": 176990 }, { - "epoch": 0.79, - "learning_rate": 1.0555356262051028e-05, - "loss": 0.1564, + "epoch": 0.4, + "learning_rate": 3.0322252298606295e-05, + "loss": 0.1537, "step": 177000 }, { - "epoch": 0.79, - "learning_rate": 1.0553114210125107e-05, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 3.0321133755396973e-05, + "loss": 0.1451, "step": 177010 }, { - "epoch": 0.79, - "learning_rate": 1.0550872158199184e-05, - "loss": 0.1563, + "epoch": 0.4, + "learning_rate": 3.0320015212187647e-05, + "loss": 0.1466, "step": 177020 }, { - "epoch": 0.79, - "learning_rate": 1.0548630106273263e-05, - "loss": 0.1518, + "epoch": 0.4, + "learning_rate": 3.0318896668978325e-05, + "loss": 0.1488, "step": 177030 }, { - "epoch": 0.79, - "learning_rate": 1.054638805434734e-05, - "loss": 0.1568, + "epoch": 0.4, + "learning_rate": 3.0317778125768996e-05, + "loss": 0.1476, "step": 177040 }, { - "epoch": 0.79, - "learning_rate": 1.0544146002421417e-05, - "loss": 0.1525, + "epoch": 0.4, + "learning_rate": 3.0316659582559674e-05, + "loss": 0.1462, "step": 177050 }, { - "epoch": 0.79, - "learning_rate": 1.0541903950495494e-05, - "loss": 0.1472, + "epoch": 0.4, + "learning_rate": 3.0315541039350352e-05, + "loss": 0.148, "step": 177060 }, { - "epoch": 0.79, - "learning_rate": 1.0539661898569571e-05, - "loss": 0.1558, + "epoch": 0.4, + "learning_rate": 3.0314422496141027e-05, + "loss": 0.1451, "step": 177070 }, { - "epoch": 0.79, - "learning_rate": 1.053741984664365e-05, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 3.0313303952931705e-05, + "loss": 0.1476, "step": 177080 }, { - "epoch": 0.79, - "learning_rate": 1.0535177794717727e-05, - "loss": 0.1518, + "epoch": 0.4, + "learning_rate": 3.0312185409722376e-05, + "loss": 0.1497, "step": 177090 }, { - "epoch": 0.79, - "learning_rate": 1.0532935742791804e-05, - "loss": 0.1534, + "epoch": 0.4, + "learning_rate": 3.0311066866513054e-05, + "loss": 0.1419, "step": 177100 }, { - "epoch": 0.79, - "learning_rate": 1.053069369086588e-05, - "loss": 0.155, + "epoch": 0.4, + "learning_rate": 3.0309948323303732e-05, + "loss": 0.15, "step": 177110 }, { - "epoch": 0.79, - "learning_rate": 1.0528451638939958e-05, - "loss": 0.1591, + "epoch": 0.4, + "learning_rate": 3.0308829780094406e-05, + "loss": 0.148, "step": 177120 }, { - "epoch": 0.79, - "learning_rate": 1.0526209587014035e-05, - "loss": 0.1589, + "epoch": 0.4, + "learning_rate": 3.0307711236885084e-05, + "loss": 0.1507, "step": 177130 }, { - "epoch": 0.79, - "learning_rate": 1.0523967535088112e-05, - "loss": 0.1585, + "epoch": 0.4, + "learning_rate": 3.0306592693675755e-05, + "loss": 0.1458, "step": 177140 }, { - "epoch": 0.79, - "learning_rate": 1.052172548316219e-05, - "loss": 0.1495, + "epoch": 0.4, + "learning_rate": 3.0305474150466433e-05, + "loss": 0.1502, "step": 177150 }, { - "epoch": 0.79, - "learning_rate": 1.0519483431236268e-05, - "loss": 0.1503, + "epoch": 0.4, + "learning_rate": 3.030435560725711e-05, + "loss": 0.1532, "step": 177160 }, { - "epoch": 0.79, - "learning_rate": 1.0517241379310346e-05, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 3.0303237064047786e-05, + "loss": 0.1471, "step": 177170 }, { - "epoch": 0.79, - "learning_rate": 1.0514999327384423e-05, - "loss": 0.1519, + "epoch": 0.4, + "learning_rate": 3.0302118520838464e-05, + "loss": 0.1457, "step": 177180 }, { - "epoch": 0.79, - "learning_rate": 1.05127572754585e-05, - "loss": 0.1494, + "epoch": 0.4, + "learning_rate": 3.0300999977629135e-05, + "loss": 0.1421, "step": 177190 }, { - "epoch": 0.79, - "learning_rate": 1.0510515223532577e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.0299881434419813e-05, + "loss": 0.1468, "step": 177200 }, { - "epoch": 0.79, - "learning_rate": 1.0508273171606654e-05, - "loss": 0.1551, + "epoch": 0.4, + "learning_rate": 3.029876289121049e-05, + "loss": 0.1555, "step": 177210 }, { - "epoch": 0.79, - "learning_rate": 1.0506031119680733e-05, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 3.0297644348001165e-05, + "loss": 0.1476, "step": 177220 }, { - "epoch": 0.79, - "learning_rate": 1.050378906775481e-05, - "loss": 0.157, + "epoch": 0.4, + "learning_rate": 3.0296525804791843e-05, + "loss": 0.1496, "step": 177230 }, { - "epoch": 0.79, - "learning_rate": 1.0501547015828887e-05, - "loss": 0.1486, + "epoch": 0.4, + "learning_rate": 3.0295407261582514e-05, + "loss": 0.1491, "step": 177240 }, { - "epoch": 0.79, - "learning_rate": 1.0499304963902964e-05, - "loss": 0.1589, + "epoch": 0.4, + "learning_rate": 3.0294288718373192e-05, + "loss": 0.1498, "step": 177250 }, { - "epoch": 0.79, - "learning_rate": 1.0497062911977041e-05, - "loss": 0.1523, + "epoch": 0.4, + "learning_rate": 3.029317017516387e-05, + "loss": 0.1475, "step": 177260 }, { - "epoch": 0.79, - "learning_rate": 1.0494820860051118e-05, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 3.0292051631954545e-05, + "loss": 0.1508, "step": 177270 }, { - "epoch": 0.79, - "learning_rate": 1.0492578808125197e-05, - "loss": 0.1523, + "epoch": 0.4, + "learning_rate": 3.0290933088745223e-05, + "loss": 0.1488, "step": 177280 }, { - "epoch": 0.79, - "learning_rate": 1.0490336756199274e-05, - "loss": 0.1573, + "epoch": 0.4, + "learning_rate": 3.0289814545535894e-05, + "loss": 0.1518, "step": 177290 }, { - "epoch": 0.79, - "learning_rate": 1.0488094704273353e-05, - "loss": 0.1548, + "epoch": 0.4, + "learning_rate": 3.0288696002326572e-05, + "loss": 0.1439, "step": 177300 }, { - "epoch": 0.79, - "learning_rate": 1.048585265234743e-05, - "loss": 0.1562, + "epoch": 0.4, + "learning_rate": 3.0287577459117243e-05, + "loss": 0.1487, "step": 177310 }, { - "epoch": 0.79, - "learning_rate": 1.0483610600421507e-05, - "loss": 0.1498, + "epoch": 0.4, + "learning_rate": 3.0286458915907924e-05, + "loss": 0.15, "step": 177320 }, { - "epoch": 0.79, - "learning_rate": 1.0481368548495584e-05, - "loss": 0.1545, + "epoch": 0.4, + "learning_rate": 3.0285340372698602e-05, + "loss": 0.1511, "step": 177330 }, { - "epoch": 0.79, - "learning_rate": 1.047912649656966e-05, - "loss": 0.1536, + "epoch": 0.4, + "learning_rate": 3.0284221829489273e-05, + "loss": 0.1531, "step": 177340 }, { - "epoch": 0.79, - "learning_rate": 1.0476884444643738e-05, - "loss": 0.153, + "epoch": 0.4, + "learning_rate": 3.028310328627995e-05, + "loss": 0.1472, "step": 177350 }, { - "epoch": 0.79, - "learning_rate": 1.0474642392717816e-05, - "loss": 0.1508, + "epoch": 0.4, + "learning_rate": 3.0281984743070622e-05, + "loss": 0.1479, "step": 177360 }, { - "epoch": 0.79, - "learning_rate": 1.0472400340791893e-05, - "loss": 0.1552, + "epoch": 0.4, + "learning_rate": 3.02808661998613e-05, + "loss": 0.1525, "step": 177370 }, { - "epoch": 0.79, - "learning_rate": 1.047015828886597e-05, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 3.027974765665198e-05, + "loss": 0.1461, "step": 177380 }, { - "epoch": 0.79, - "learning_rate": 1.0467916236940048e-05, - "loss": 0.1526, + "epoch": 0.4, + "learning_rate": 3.0278629113442653e-05, + "loss": 0.1502, "step": 177390 }, { - "epoch": 0.79, - "learning_rate": 1.0465674185014125e-05, - "loss": 0.1533, + "epoch": 0.4, + "learning_rate": 3.027751057023333e-05, + "loss": 0.1508, "step": 177400 }, { - "epoch": 0.79, - "learning_rate": 1.0463432133088202e-05, - "loss": 0.158, + "epoch": 0.4, + "learning_rate": 3.0276392027024002e-05, + "loss": 0.1531, "step": 177410 }, { - "epoch": 0.79, - "learning_rate": 1.0461414286354873e-05, - "loss": 0.1537, + "epoch": 0.4, + "learning_rate": 3.027527348381468e-05, + "loss": 0.1483, "step": 177420 }, { - "epoch": 0.79, - "learning_rate": 1.045917223442895e-05, - "loss": 0.1537, + "epoch": 0.4, + "learning_rate": 3.0274154940605358e-05, + "loss": 0.15, "step": 177430 }, { - "epoch": 0.79, - "learning_rate": 1.0456930182503027e-05, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 3.0273036397396032e-05, + "loss": 0.1487, "step": 177440 }, { - "epoch": 0.79, - "learning_rate": 1.0454688130577104e-05, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 3.027191785418671e-05, + "loss": 0.1479, "step": 177450 }, { - "epoch": 0.79, - "learning_rate": 1.0452446078651183e-05, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 3.027079931097738e-05, + "loss": 0.1517, "step": 177460 }, { - "epoch": 0.79, - "learning_rate": 1.045020402672526e-05, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 3.026968076776806e-05, + "loss": 0.1541, "step": 177470 }, { - "epoch": 0.79, - "learning_rate": 1.0447961974799337e-05, - "loss": 0.1509, + "epoch": 0.4, + "learning_rate": 3.0268562224558737e-05, + "loss": 0.149, "step": 177480 }, { - "epoch": 0.79, - "learning_rate": 1.0445719922873415e-05, - "loss": 0.1453, + "epoch": 0.4, + "learning_rate": 3.0267443681349412e-05, + "loss": 0.148, "step": 177490 }, { - "epoch": 0.79, - "learning_rate": 1.0443477870947492e-05, - "loss": 0.1531, + "epoch": 0.4, + "learning_rate": 3.026632513814009e-05, + "loss": 0.1454, "step": 177500 }, { - "epoch": 0.79, - "learning_rate": 1.044123581902157e-05, - "loss": 0.1499, + "epoch": 0.4, + "learning_rate": 3.026520659493076e-05, + "loss": 0.1472, "step": 177510 }, { - "epoch": 0.79, - "learning_rate": 1.0438993767095646e-05, - "loss": 0.1459, + "epoch": 0.4, + "learning_rate": 3.026408805172144e-05, + "loss": 0.1434, "step": 177520 }, { - "epoch": 0.79, - "learning_rate": 1.0436751715169723e-05, - "loss": 0.1503, + "epoch": 0.4, + "learning_rate": 3.0262969508512117e-05, + "loss": 0.1482, "step": 177530 }, { - "epoch": 0.79, - "learning_rate": 1.04345096632438e-05, - "loss": 0.1588, + "epoch": 0.4, + "learning_rate": 3.026185096530279e-05, + "loss": 0.1497, "step": 177540 }, { - "epoch": 0.79, - "learning_rate": 1.0432267611317877e-05, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 3.0260844276414403e-05, + "loss": 0.15, "step": 177550 }, { - "epoch": 0.79, - "learning_rate": 1.0430025559391956e-05, - "loss": 0.1443, + "epoch": 0.4, + "learning_rate": 3.0259725733205075e-05, + "loss": 0.1506, "step": 177560 }, { - "epoch": 0.79, - "learning_rate": 1.0427783507466033e-05, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 3.0258607189995752e-05, + "loss": 0.1471, "step": 177570 }, { - "epoch": 0.79, - "learning_rate": 1.042554145554011e-05, - "loss": 0.1482, + "epoch": 0.4, + "learning_rate": 3.0257488646786424e-05, + "loss": 0.1434, "step": 177580 }, { - "epoch": 0.79, - "learning_rate": 1.0423299403614189e-05, - "loss": 0.1535, + "epoch": 0.4, + "learning_rate": 3.02563701035771e-05, + "loss": 0.1518, "step": 177590 }, { - "epoch": 0.79, - "learning_rate": 1.0421057351688266e-05, - "loss": 0.1531, + "epoch": 0.4, + "learning_rate": 3.025525156036778e-05, + "loss": 0.1542, "step": 177600 }, { - "epoch": 0.79, - "learning_rate": 1.0418815299762343e-05, - "loss": 0.1515, + "epoch": 0.4, + "learning_rate": 3.0254133017158454e-05, + "loss": 0.1484, "step": 177610 }, { - "epoch": 0.79, - "learning_rate": 1.041657324783642e-05, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 3.0253014473949132e-05, + "loss": 0.1526, "step": 177620 }, { - "epoch": 0.79, - "learning_rate": 1.0414331195910499e-05, - "loss": 0.1412, + "epoch": 0.4, + "learning_rate": 3.0251895930739803e-05, + "loss": 0.15, "step": 177630 }, { - "epoch": 0.79, - "learning_rate": 1.0412089143984576e-05, - "loss": 0.1456, + "epoch": 0.4, + "learning_rate": 3.025077738753048e-05, + "loss": 0.1484, "step": 177640 }, { - "epoch": 0.79, - "learning_rate": 1.0409847092058653e-05, - "loss": 0.1503, + "epoch": 0.4, + "learning_rate": 3.0249658844321156e-05, + "loss": 0.1512, "step": 177650 }, { - "epoch": 0.79, - "learning_rate": 1.040760504013273e-05, - "loss": 0.1507, + "epoch": 0.4, + "learning_rate": 3.0248540301111833e-05, + "loss": 0.1523, "step": 177660 }, { - "epoch": 0.79, - "learning_rate": 1.0405362988206807e-05, - "loss": 0.154, + "epoch": 0.4, + "learning_rate": 3.024742175790251e-05, + "loss": 0.1526, "step": 177670 }, { - "epoch": 0.79, - "learning_rate": 1.0403120936280884e-05, - "loss": 0.1562, + "epoch": 0.4, + "learning_rate": 3.0246303214693183e-05, + "loss": 0.1503, "step": 177680 }, { - "epoch": 0.79, - "learning_rate": 1.0400878884354961e-05, - "loss": 0.1493, + "epoch": 0.4, + "learning_rate": 3.024518467148386e-05, + "loss": 0.1532, "step": 177690 }, { - "epoch": 0.79, - "learning_rate": 1.039863683242904e-05, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 3.0244066128274535e-05, + "loss": 0.1469, "step": 177700 }, { - "epoch": 0.79, - "learning_rate": 1.0396394780503117e-05, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 3.0242947585065213e-05, + "loss": 0.1481, "step": 177710 }, { - "epoch": 0.79, - "learning_rate": 1.0394152728577194e-05, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 3.024182904185589e-05, + "loss": 0.1495, "step": 177720 }, { - "epoch": 0.79, - "learning_rate": 1.0391910676651272e-05, - "loss": 0.1499, + "epoch": 0.4, + "learning_rate": 3.0240710498646562e-05, + "loss": 0.1487, "step": 177730 }, { - "epoch": 0.79, - "learning_rate": 1.038966862472535e-05, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 3.023959195543724e-05, + "loss": 0.1502, "step": 177740 }, { - "epoch": 0.79, - "learning_rate": 1.0387426572799426e-05, - "loss": 0.1491, + "epoch": 0.4, + "learning_rate": 3.0238473412227914e-05, + "loss": 0.1517, "step": 177750 }, { - "epoch": 0.79, - "learning_rate": 1.0385184520873503e-05, - "loss": 0.1523, + "epoch": 0.4, + "learning_rate": 3.0237354869018592e-05, + "loss": 0.1511, "step": 177760 }, { - "epoch": 0.79, - "learning_rate": 1.0382942468947582e-05, - "loss": 0.1539, + "epoch": 0.4, + "learning_rate": 3.023623632580927e-05, + "loss": 0.1485, "step": 177770 }, { - "epoch": 0.79, - "learning_rate": 1.038070041702166e-05, - "loss": 0.1528, + "epoch": 0.4, + "learning_rate": 3.023511778259994e-05, + "loss": 0.1488, "step": 177780 }, { - "epoch": 0.79, - "learning_rate": 1.0378458365095736e-05, - "loss": 0.1456, + "epoch": 0.4, + "learning_rate": 3.023399923939062e-05, + "loss": 0.1547, "step": 177790 }, { - "epoch": 0.79, - "learning_rate": 1.0376216313169813e-05, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 3.0232880696181294e-05, + "loss": 0.151, "step": 177800 }, { - "epoch": 0.79, - "learning_rate": 1.037397426124389e-05, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 3.0231762152971972e-05, + "loss": 0.1481, "step": 177810 }, { - "epoch": 0.79, - "learning_rate": 1.0371732209317967e-05, - "loss": 0.1531, + "epoch": 0.4, + "learning_rate": 3.023064360976265e-05, + "loss": 0.153, "step": 177820 }, { - "epoch": 0.79, - "learning_rate": 1.0369490157392046e-05, - "loss": 0.1476, + "epoch": 0.4, + "learning_rate": 3.022952506655332e-05, + "loss": 0.1518, "step": 177830 }, { - "epoch": 0.79, - "learning_rate": 1.0367248105466123e-05, - "loss": 0.1539, + "epoch": 0.4, + "learning_rate": 3.0228406523344e-05, + "loss": 0.1478, "step": 177840 }, { - "epoch": 0.79, - "learning_rate": 1.03650060535402e-05, - "loss": 0.1543, + "epoch": 0.4, + "learning_rate": 3.0227287980134673e-05, + "loss": 0.1479, "step": 177850 }, { - "epoch": 0.79, - "learning_rate": 1.0362764001614279e-05, - "loss": 0.1535, + "epoch": 0.4, + "learning_rate": 3.022616943692535e-05, + "loss": 0.1548, "step": 177860 }, { - "epoch": 0.79, - "learning_rate": 1.0360521949688356e-05, - "loss": 0.1511, + "epoch": 0.4, + "learning_rate": 3.022505089371603e-05, + "loss": 0.1522, "step": 177870 }, { - "epoch": 0.79, - "learning_rate": 1.0358279897762433e-05, - "loss": 0.1523, + "epoch": 0.4, + "learning_rate": 3.02239323505067e-05, + "loss": 0.15, "step": 177880 }, { - "epoch": 0.79, - "learning_rate": 1.035603784583651e-05, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 3.022281380729738e-05, + "loss": 0.1498, "step": 177890 }, { - "epoch": 0.79, - "learning_rate": 1.0353795793910589e-05, - "loss": 0.1517, + "epoch": 0.4, + "learning_rate": 3.0221695264088053e-05, + "loss": 0.1457, "step": 177900 }, { - "epoch": 0.79, - "learning_rate": 1.0351553741984666e-05, - "loss": 0.147, + "epoch": 0.4, + "learning_rate": 3.022057672087873e-05, + "loss": 0.1516, "step": 177910 }, { - "epoch": 0.79, - "learning_rate": 1.0349311690058743e-05, - "loss": 0.1559, + "epoch": 0.4, + "learning_rate": 3.021945817766941e-05, + "loss": 0.1496, "step": 177920 }, { - "epoch": 0.79, - "learning_rate": 1.034706963813282e-05, - "loss": 0.1478, + "epoch": 0.4, + "learning_rate": 3.021833963446008e-05, + "loss": 0.1493, "step": 177930 }, { - "epoch": 0.79, - "learning_rate": 1.0344827586206897e-05, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 3.0217221091250758e-05, + "loss": 0.1532, "step": 177940 }, { - "epoch": 0.79, - "learning_rate": 1.0342585534280974e-05, - "loss": 0.1557, + "epoch": 0.4, + "learning_rate": 3.021610254804143e-05, + "loss": 0.1482, "step": 177950 }, { - "epoch": 0.79, - "learning_rate": 1.034034348235505e-05, - "loss": 0.1477, + "epoch": 0.4, + "learning_rate": 3.021498400483211e-05, + "loss": 0.1476, "step": 177960 }, { - "epoch": 0.79, - "learning_rate": 1.033810143042913e-05, - "loss": 0.1523, + "epoch": 0.4, + "learning_rate": 3.021386546162278e-05, + "loss": 0.1456, "step": 177970 }, { - "epoch": 0.79, - "learning_rate": 1.0335859378503206e-05, - "loss": 0.1534, + "epoch": 0.4, + "learning_rate": 3.021274691841346e-05, + "loss": 0.1497, "step": 177980 }, { - "epoch": 0.79, - "learning_rate": 1.0333617326577283e-05, - "loss": 0.1527, + "epoch": 0.4, + "learning_rate": 3.0211628375204137e-05, + "loss": 0.1464, "step": 177990 }, { - "epoch": 0.79, - "learning_rate": 1.0331375274651362e-05, - "loss": 0.1464, + "epoch": 0.4, + "learning_rate": 3.021050983199481e-05, + "loss": 0.1501, "step": 178000 }, { - "epoch": 0.79, - "learning_rate": 1.032913322272544e-05, - "loss": 0.1527, + "epoch": 0.4, + "learning_rate": 3.0209391288785486e-05, + "loss": 0.1535, "step": 178010 }, { - "epoch": 0.79, - "learning_rate": 1.0326891170799516e-05, - "loss": 0.1536, + "epoch": 0.4, + "learning_rate": 3.020827274557616e-05, + "loss": 0.149, "step": 178020 }, { - "epoch": 0.79, - "learning_rate": 1.0324649118873593e-05, - "loss": 0.1547, + "epoch": 0.4, + "learning_rate": 3.020715420236684e-05, + "loss": 0.1473, "step": 178030 }, { - "epoch": 0.79, - "learning_rate": 1.0322407066947672e-05, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 3.0206035659157517e-05, + "loss": 0.1553, "step": 178040 }, { - "epoch": 0.79, - "learning_rate": 1.0320165015021749e-05, - "loss": 0.1536, + "epoch": 0.4, + "learning_rate": 3.0204917115948188e-05, + "loss": 0.1482, "step": 178050 }, { - "epoch": 0.79, - "learning_rate": 1.0317922963095826e-05, - "loss": 0.1504, + "epoch": 0.4, + "learning_rate": 3.0203798572738866e-05, + "loss": 0.1497, "step": 178060 }, { - "epoch": 0.79, - "learning_rate": 1.0315680911169903e-05, - "loss": 0.1539, + "epoch": 0.4, + "learning_rate": 3.020268002952954e-05, + "loss": 0.1456, "step": 178070 }, { - "epoch": 0.79, - "learning_rate": 1.031343885924398e-05, - "loss": 0.15, + "epoch": 0.4, + "learning_rate": 3.020156148632022e-05, + "loss": 0.153, "step": 178080 }, { - "epoch": 0.8, - "learning_rate": 1.0311196807318057e-05, - "loss": 0.1448, + "epoch": 0.4, + "learning_rate": 3.0200442943110896e-05, + "loss": 0.1523, "step": 178090 }, { - "epoch": 0.8, - "learning_rate": 1.0308954755392134e-05, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 3.0199324399901567e-05, + "loss": 0.1518, "step": 178100 }, { - "epoch": 0.8, - "learning_rate": 1.0306712703466213e-05, - "loss": 0.145, + "epoch": 0.4, + "learning_rate": 3.0198205856692245e-05, + "loss": 0.1535, "step": 178110 }, { - "epoch": 0.8, - "learning_rate": 1.030447065154029e-05, - "loss": 0.1578, + "epoch": 0.4, + "learning_rate": 3.019708731348292e-05, + "loss": 0.1464, "step": 178120 }, { - "epoch": 0.8, - "learning_rate": 1.0302228599614369e-05, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 3.0195968770273598e-05, + "loss": 0.1508, "step": 178130 }, { - "epoch": 0.8, - "learning_rate": 1.0299986547688446e-05, - "loss": 0.1443, + "epoch": 0.4, + "learning_rate": 3.0194850227064276e-05, + "loss": 0.1444, "step": 178140 }, { - "epoch": 0.8, - "learning_rate": 1.0297744495762523e-05, - "loss": 0.1499, + "epoch": 0.4, + "learning_rate": 3.0193731683854947e-05, + "loss": 0.1431, "step": 178150 }, { - "epoch": 0.8, - "learning_rate": 1.02955024438366e-05, - "loss": 0.1487, + "epoch": 0.4, + "learning_rate": 3.0192613140645625e-05, + "loss": 0.1471, "step": 178160 }, { - "epoch": 0.8, - "learning_rate": 1.0293260391910677e-05, - "loss": 0.1509, + "epoch": 0.4, + "learning_rate": 3.01914945974363e-05, + "loss": 0.1491, "step": 178170 }, { - "epoch": 0.8, - "learning_rate": 1.0291018339984755e-05, - "loss": 0.1497, + "epoch": 0.4, + "learning_rate": 3.0190376054226977e-05, + "loss": 0.1531, "step": 178180 }, { - "epoch": 0.8, - "learning_rate": 1.0288776288058832e-05, - "loss": 0.1467, + "epoch": 0.4, + "learning_rate": 3.0189257511017655e-05, + "loss": 0.1553, "step": 178190 }, { - "epoch": 0.8, - "learning_rate": 1.028653423613291e-05, - "loss": 0.15, + "epoch": 0.4, + "learning_rate": 3.0188138967808326e-05, + "loss": 0.1518, "step": 178200 }, { - "epoch": 0.8, - "learning_rate": 1.0284292184206986e-05, - "loss": 0.1475, + "epoch": 0.4, + "learning_rate": 3.0187020424599004e-05, + "loss": 0.1506, "step": 178210 }, { - "epoch": 0.8, - "learning_rate": 1.0282050132281063e-05, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 3.018590188138968e-05, + "loss": 0.1476, "step": 178220 }, { - "epoch": 0.8, - "learning_rate": 1.027980808035514e-05, - "loss": 0.1485, + "epoch": 0.4, + "learning_rate": 3.0184783338180357e-05, + "loss": 0.1518, "step": 178230 }, { - "epoch": 0.8, - "learning_rate": 1.0277566028429218e-05, - "loss": 0.1464, + "epoch": 0.4, + "learning_rate": 3.0183664794971035e-05, + "loss": 0.153, "step": 178240 }, { - "epoch": 0.8, - "learning_rate": 1.0275323976503296e-05, - "loss": 0.1417, + "epoch": 0.4, + "learning_rate": 3.0182546251761706e-05, + "loss": 0.1483, "step": 178250 }, { - "epoch": 0.8, - "learning_rate": 1.0273081924577373e-05, - "loss": 0.151, + "epoch": 0.4, + "learning_rate": 3.0181427708552384e-05, + "loss": 0.1499, "step": 178260 }, { - "epoch": 0.8, - "learning_rate": 1.0270839872651452e-05, - "loss": 0.1577, + "epoch": 0.4, + "learning_rate": 3.018030916534306e-05, + "loss": 0.1533, "step": 178270 }, { - "epoch": 0.8, - "learning_rate": 1.0268597820725529e-05, - "loss": 0.1471, + "epoch": 0.4, + "learning_rate": 3.0179190622133736e-05, + "loss": 0.1454, "step": 178280 }, { - "epoch": 0.8, - "learning_rate": 1.0266355768799606e-05, - "loss": 0.1472, + "epoch": 0.4, + "learning_rate": 3.0178072078924407e-05, + "loss": 0.1522, "step": 178290 }, { - "epoch": 0.8, - "learning_rate": 1.0264113716873683e-05, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 3.0176953535715085e-05, + "loss": 0.1527, "step": 178300 }, { - "epoch": 0.8, - "learning_rate": 1.026187166494776e-05, - "loss": 0.1538, + "epoch": 0.4, + "learning_rate": 3.0175834992505763e-05, + "loss": 0.1496, "step": 178310 }, { - "epoch": 0.8, - "learning_rate": 1.0259629613021839e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.0174716449296438e-05, + "loss": 0.1475, "step": 178320 }, { - "epoch": 0.8, - "learning_rate": 1.0257387561095916e-05, - "loss": 0.1514, + "epoch": 0.4, + "learning_rate": 3.0173597906087116e-05, + "loss": 0.1506, "step": 178330 }, { - "epoch": 0.8, - "learning_rate": 1.0255145509169993e-05, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 3.0172479362877787e-05, + "loss": 0.149, "step": 178340 }, { - "epoch": 0.8, - "learning_rate": 1.025290345724407e-05, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 3.0171360819668465e-05, + "loss": 0.1514, "step": 178350 }, { - "epoch": 0.8, - "learning_rate": 1.0250661405318147e-05, - "loss": 0.1454, + "epoch": 0.4, + "learning_rate": 3.0170242276459143e-05, + "loss": 0.1507, "step": 178360 }, { - "epoch": 0.8, - "learning_rate": 1.0248419353392224e-05, - "loss": 0.148, + "epoch": 0.4, + "learning_rate": 3.0169123733249814e-05, + "loss": 0.1506, "step": 178370 }, { - "epoch": 0.8, - "learning_rate": 1.0246177301466303e-05, - "loss": 0.1472, + "epoch": 0.4, + "learning_rate": 3.0168005190040495e-05, + "loss": 0.1516, "step": 178380 }, { - "epoch": 0.8, - "learning_rate": 1.024393524954038e-05, - "loss": 0.1499, + "epoch": 0.4, + "learning_rate": 3.0166886646831166e-05, + "loss": 0.1477, "step": 178390 }, { - "epoch": 0.8, - "learning_rate": 1.0241693197614458e-05, - "loss": 0.15, + "epoch": 0.4, + "learning_rate": 3.0165768103621844e-05, + "loss": 0.1446, "step": 178400 }, { - "epoch": 0.8, - "learning_rate": 1.0239451145688535e-05, - "loss": 0.1561, + "epoch": 0.4, + "learning_rate": 3.0164649560412522e-05, + "loss": 0.1507, "step": 178410 }, { - "epoch": 0.8, - "learning_rate": 1.0237209093762612e-05, - "loss": 0.1435, + "epoch": 0.4, + "learning_rate": 3.0163531017203193e-05, + "loss": 0.1434, "step": 178420 }, { - "epoch": 0.8, - "learning_rate": 1.023496704183669e-05, - "loss": 0.1504, + "epoch": 0.4, + "learning_rate": 3.016241247399387e-05, + "loss": 0.1512, "step": 178430 }, { - "epoch": 0.8, - "learning_rate": 1.0232724989910766e-05, - "loss": 0.1493, + "epoch": 0.4, + "learning_rate": 3.0161293930784546e-05, + "loss": 0.1485, "step": 178440 }, { - "epoch": 0.8, - "learning_rate": 1.0230482937984843e-05, - "loss": 0.1489, + "epoch": 0.4, + "learning_rate": 3.0160175387575224e-05, + "loss": 0.1464, "step": 178450 }, { - "epoch": 0.8, - "learning_rate": 1.0228240886058922e-05, - "loss": 0.1469, + "epoch": 0.4, + "learning_rate": 3.01590568443659e-05, + "loss": 0.1491, "step": 178460 }, { - "epoch": 0.8, - "learning_rate": 1.0225998834133e-05, - "loss": 0.1514, + "epoch": 0.4, + "learning_rate": 3.0157938301156573e-05, + "loss": 0.1466, "step": 178470 }, { - "epoch": 0.8, - "learning_rate": 1.0223756782207076e-05, - "loss": 0.1435, + "epoch": 0.4, + "learning_rate": 3.015681975794725e-05, + "loss": 0.1476, "step": 178480 }, { - "epoch": 0.8, - "learning_rate": 1.0221514730281153e-05, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 3.0155701214737925e-05, + "loss": 0.1489, "step": 178490 }, { - "epoch": 0.8, - "learning_rate": 1.021927267835523e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.0154582671528603e-05, + "loss": 0.1494, "step": 178500 }, { - "epoch": 0.8, - "learning_rate": 1.0217030626429307e-05, - "loss": 0.1468, + "epoch": 0.4, + "learning_rate": 3.015346412831928e-05, + "loss": 0.146, "step": 178510 }, { - "epoch": 0.8, - "learning_rate": 1.0214788574503386e-05, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 3.0152345585109952e-05, + "loss": 0.1493, "step": 178520 }, { - "epoch": 0.8, - "learning_rate": 1.0212546522577463e-05, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 3.015122704190063e-05, + "loss": 0.1486, "step": 178530 }, { - "epoch": 0.8, - "learning_rate": 1.0210304470651542e-05, - "loss": 0.1489, + "epoch": 0.4, + "learning_rate": 3.0150108498691305e-05, + "loss": 0.1488, "step": 178540 }, { - "epoch": 0.8, - "learning_rate": 1.0208062418725619e-05, - "loss": 0.1534, + "epoch": 0.4, + "learning_rate": 3.0148989955481983e-05, + "loss": 0.1448, "step": 178550 }, { - "epoch": 0.8, - "learning_rate": 1.0205820366799696e-05, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 3.014787141227266e-05, + "loss": 0.1503, "step": 178560 }, { - "epoch": 0.8, - "learning_rate": 1.0203578314873773e-05, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 3.0146752869063332e-05, + "loss": 0.145, "step": 178570 }, { - "epoch": 0.8, - "learning_rate": 1.020133626294785e-05, - "loss": 0.1526, + "epoch": 0.4, + "learning_rate": 3.014563432585401e-05, + "loss": 0.1486, "step": 178580 }, { - "epoch": 0.8, - "learning_rate": 1.0199094211021929e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.0144515782644684e-05, + "loss": 0.1503, "step": 178590 }, { - "epoch": 0.8, - "learning_rate": 1.0196852159096006e-05, - "loss": 0.1484, + "epoch": 0.4, + "learning_rate": 3.0143397239435362e-05, + "loss": 0.15, "step": 178600 }, { - "epoch": 0.8, - "learning_rate": 1.0194610107170083e-05, - "loss": 0.1504, + "epoch": 0.4, + "learning_rate": 3.0142278696226033e-05, + "loss": 0.1449, "step": 178610 }, { - "epoch": 0.8, - "learning_rate": 1.019236805524416e-05, - "loss": 0.1497, + "epoch": 0.4, + "learning_rate": 3.014116015301671e-05, + "loss": 0.1462, "step": 178620 }, { - "epoch": 0.8, - "learning_rate": 1.0190126003318237e-05, - "loss": 0.1555, + "epoch": 0.4, + "learning_rate": 3.014004160980739e-05, + "loss": 0.1489, "step": 178630 }, { - "epoch": 0.8, - "learning_rate": 1.0187883951392314e-05, - "loss": 0.148, + "epoch": 0.4, + "learning_rate": 3.0138923066598064e-05, + "loss": 0.1461, "step": 178640 }, { - "epoch": 0.8, - "learning_rate": 1.0185641899466392e-05, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 3.013780452338874e-05, + "loss": 0.1459, "step": 178650 }, { - "epoch": 0.8, - "learning_rate": 1.018339984754047e-05, - "loss": 0.144, + "epoch": 0.4, + "learning_rate": 3.0136685980179413e-05, + "loss": 0.1511, "step": 178660 }, { - "epoch": 0.8, - "learning_rate": 1.0181157795614548e-05, - "loss": 0.1525, + "epoch": 0.4, + "learning_rate": 3.013556743697009e-05, + "loss": 0.148, "step": 178670 }, { - "epoch": 0.8, - "learning_rate": 1.0178915743688625e-05, - "loss": 0.1508, + "epoch": 0.4, + "learning_rate": 3.013444889376077e-05, + "loss": 0.1449, "step": 178680 }, { - "epoch": 0.8, - "learning_rate": 1.0176673691762702e-05, - "loss": 0.1522, + "epoch": 0.4, + "learning_rate": 3.0133330350551443e-05, + "loss": 0.1514, "step": 178690 }, { - "epoch": 0.8, - "learning_rate": 1.017443163983678e-05, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 3.013221180734212e-05, + "loss": 0.1467, "step": 178700 }, { - "epoch": 0.8, - "learning_rate": 1.0172189587910856e-05, - "loss": 0.1478, + "epoch": 0.4, + "learning_rate": 3.0131093264132792e-05, + "loss": 0.1472, "step": 178710 }, { - "epoch": 0.8, - "learning_rate": 1.0169947535984933e-05, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 3.012997472092347e-05, + "loss": 0.1528, "step": 178720 }, { - "epoch": 0.8, - "learning_rate": 1.0167705484059012e-05, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 3.0128856177714148e-05, + "loss": 0.1492, "step": 178730 }, { - "epoch": 0.8, - "learning_rate": 1.0165463432133089e-05, - "loss": 0.1463, + "epoch": 0.4, + "learning_rate": 3.0127737634504823e-05, + "loss": 0.1505, "step": 178740 }, { - "epoch": 0.8, - "learning_rate": 1.0163221380207166e-05, - "loss": 0.1432, + "epoch": 0.4, + "learning_rate": 3.01266190912955e-05, + "loss": 0.1509, "step": 178750 }, { - "epoch": 0.8, - "learning_rate": 1.0160979328281243e-05, - "loss": 0.1464, + "epoch": 0.4, + "learning_rate": 3.0125500548086172e-05, + "loss": 0.1498, "step": 178760 }, { - "epoch": 0.8, - "learning_rate": 1.015873727635532e-05, - "loss": 0.1533, + "epoch": 0.4, + "learning_rate": 3.012438200487685e-05, + "loss": 0.1467, "step": 178770 }, { - "epoch": 0.8, - "learning_rate": 1.0156495224429397e-05, - "loss": 0.1486, + "epoch": 0.4, + "learning_rate": 3.0123263461667528e-05, + "loss": 0.1466, "step": 178780 }, { - "epoch": 0.8, - "learning_rate": 1.0154253172503476e-05, - "loss": 0.1468, + "epoch": 0.4, + "learning_rate": 3.0122144918458202e-05, + "loss": 0.1498, "step": 178790 }, { - "epoch": 0.8, - "learning_rate": 1.0152011120577553e-05, - "loss": 0.1445, + "epoch": 0.4, + "learning_rate": 3.012102637524888e-05, + "loss": 0.1484, "step": 178800 }, { - "epoch": 0.8, - "learning_rate": 1.0149769068651632e-05, - "loss": 0.1529, + "epoch": 0.4, + "learning_rate": 3.011990783203955e-05, + "loss": 0.1475, "step": 178810 }, { - "epoch": 0.8, - "learning_rate": 1.0147527016725709e-05, - "loss": 0.1554, + "epoch": 0.4, + "learning_rate": 3.011878928883023e-05, + "loss": 0.147, "step": 178820 }, { - "epoch": 0.8, - "learning_rate": 1.0145284964799786e-05, - "loss": 0.1462, + "epoch": 0.4, + "learning_rate": 3.0117670745620907e-05, + "loss": 0.1555, "step": 178830 }, { - "epoch": 0.8, - "learning_rate": 1.0143042912873863e-05, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 3.0116552202411578e-05, + "loss": 0.1496, "step": 178840 }, { - "epoch": 0.8, - "learning_rate": 1.014080086094794e-05, - "loss": 0.1518, + "epoch": 0.4, + "learning_rate": 3.011543365920226e-05, + "loss": 0.1505, "step": 178850 }, { - "epoch": 0.8, - "learning_rate": 1.0138558809022017e-05, - "loss": 0.1452, + "epoch": 0.4, + "learning_rate": 3.011431511599293e-05, + "loss": 0.151, "step": 178860 }, { - "epoch": 0.8, - "learning_rate": 1.0136316757096095e-05, - "loss": 0.1465, + "epoch": 0.4, + "learning_rate": 3.011319657278361e-05, + "loss": 0.1544, "step": 178870 }, { - "epoch": 0.8, - "learning_rate": 1.0134074705170172e-05, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 3.0112078029574287e-05, + "loss": 0.1502, "step": 178880 }, { - "epoch": 0.8, - "learning_rate": 1.013183265324425e-05, - "loss": 0.1422, + "epoch": 0.4, + "learning_rate": 3.0110959486364958e-05, + "loss": 0.1481, "step": 178890 }, { - "epoch": 0.8, - "learning_rate": 1.0129590601318326e-05, - "loss": 0.1428, + "epoch": 0.4, + "learning_rate": 3.0109840943155636e-05, + "loss": 0.1528, "step": 178900 }, { - "epoch": 0.8, - "learning_rate": 1.0127348549392404e-05, + "epoch": 0.4, + "learning_rate": 3.010872239994631e-05, "loss": 0.1508, "step": 178910 }, { - "epoch": 0.8, - "learning_rate": 1.012510649746648e-05, - "loss": 0.1418, + "epoch": 0.4, + "learning_rate": 3.0107603856736988e-05, + "loss": 0.147, "step": 178920 }, { - "epoch": 0.8, - "learning_rate": 1.012286444554056e-05, - "loss": 0.147, + "epoch": 0.4, + "learning_rate": 3.010648531352766e-05, + "loss": 0.1463, "step": 178930 }, { - "epoch": 0.8, - "learning_rate": 1.0120622393614638e-05, - "loss": 0.148, + "epoch": 0.4, + "learning_rate": 3.0105366770318337e-05, + "loss": 0.1482, "step": 178940 }, { - "epoch": 0.8, - "learning_rate": 1.0118380341688715e-05, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 3.0104248227109015e-05, + "loss": 0.1444, "step": 178950 }, { - "epoch": 0.8, - "learning_rate": 1.0116138289762792e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.010312968389969e-05, + "loss": 0.1469, "step": 178960 }, { - "epoch": 0.8, - "learning_rate": 1.0113896237836869e-05, - "loss": 0.1491, + "epoch": 0.4, + "learning_rate": 3.0102011140690368e-05, + "loss": 0.1492, "step": 178970 }, { - "epoch": 0.8, - "learning_rate": 1.0111654185910946e-05, - "loss": 0.1527, + "epoch": 0.4, + "learning_rate": 3.010089259748104e-05, + "loss": 0.1518, "step": 178980 }, { - "epoch": 0.8, - "learning_rate": 1.0109412133985023e-05, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 3.0099774054271717e-05, + "loss": 0.1489, "step": 178990 }, { - "epoch": 0.8, - "learning_rate": 1.01071700820591e-05, - "loss": 0.1484, + "epoch": 0.4, + "learning_rate": 3.0098655511062395e-05, + "loss": 0.145, "step": 179000 }, { - "epoch": 0.8, - "learning_rate": 1.0104928030133179e-05, - "loss": 0.1478, + "epoch": 0.4, + "learning_rate": 3.009753696785307e-05, + "loss": 0.1487, "step": 179010 }, { - "epoch": 0.8, - "learning_rate": 1.0102685978207256e-05, - "loss": 0.1475, + "epoch": 0.4, + "learning_rate": 3.0096418424643747e-05, + "loss": 0.146, "step": 179020 }, { - "epoch": 0.8, - "learning_rate": 1.0100443926281333e-05, - "loss": 0.1468, + "epoch": 0.4, + "learning_rate": 3.0095299881434418e-05, + "loss": 0.1501, "step": 179030 }, { - "epoch": 0.8, - "learning_rate": 1.009820187435541e-05, - "loss": 0.1515, + "epoch": 0.4, + "learning_rate": 3.0094181338225096e-05, + "loss": 0.1467, "step": 179040 }, { - "epoch": 0.8, - "learning_rate": 1.0095959822429487e-05, - "loss": 0.1511, + "epoch": 0.4, + "learning_rate": 3.0093062795015774e-05, + "loss": 0.1479, "step": 179050 }, { - "epoch": 0.8, - "learning_rate": 1.0093717770503566e-05, - "loss": 0.1504, + "epoch": 0.4, + "learning_rate": 3.009194425180645e-05, + "loss": 0.1442, "step": 179060 }, { - "epoch": 0.8, - "learning_rate": 1.0091475718577643e-05, - "loss": 0.1487, + "epoch": 0.4, + "learning_rate": 3.0090825708597127e-05, + "loss": 0.1503, "step": 179070 }, { - "epoch": 0.8, - "learning_rate": 1.0089233666651721e-05, - "loss": 0.1443, + "epoch": 0.4, + "learning_rate": 3.0089707165387798e-05, + "loss": 0.151, "step": 179080 }, { - "epoch": 0.8, - "learning_rate": 1.0086991614725798e-05, - "loss": 0.1499, + "epoch": 0.4, + "learning_rate": 3.0088588622178476e-05, + "loss": 0.1504, "step": 179090 }, { - "epoch": 0.8, - "learning_rate": 1.0084749562799875e-05, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 3.0087470078969154e-05, + "loss": 0.1473, "step": 179100 }, { - "epoch": 0.8, - "learning_rate": 1.0082507510873952e-05, - "loss": 0.1462, + "epoch": 0.4, + "learning_rate": 3.0086351535759828e-05, + "loss": 0.1523, "step": 179110 }, { - "epoch": 0.8, - "learning_rate": 1.008026545894803e-05, - "loss": 0.1476, + "epoch": 0.4, + "learning_rate": 3.0085232992550506e-05, + "loss": 0.1467, "step": 179120 }, { - "epoch": 0.8, - "learning_rate": 1.0078023407022107e-05, - "loss": 0.1577, + "epoch": 0.4, + "learning_rate": 3.0084114449341177e-05, + "loss": 0.1516, "step": 179130 }, { - "epoch": 0.8, - "learning_rate": 1.0075781355096184e-05, - "loss": 0.1508, + "epoch": 0.4, + "learning_rate": 3.0082995906131855e-05, + "loss": 0.1465, "step": 179140 }, { - "epoch": 0.8, - "learning_rate": 1.0073539303170262e-05, - "loss": 0.1489, + "epoch": 0.4, + "learning_rate": 3.0081877362922533e-05, + "loss": 0.1497, "step": 179150 }, { - "epoch": 0.8, - "learning_rate": 1.007129725124434e-05, - "loss": 0.1435, + "epoch": 0.4, + "learning_rate": 3.0080758819713208e-05, + "loss": 0.1495, "step": 179160 }, { - "epoch": 0.8, - "learning_rate": 1.0069055199318416e-05, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 3.0079640276503885e-05, + "loss": 0.1478, "step": 179170 }, { - "epoch": 0.8, - "learning_rate": 1.0066813147392493e-05, - "loss": 0.1559, + "epoch": 0.4, + "learning_rate": 3.0078521733294557e-05, + "loss": 0.1472, "step": 179180 }, { - "epoch": 0.8, - "learning_rate": 1.006457109546657e-05, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 3.0077403190085235e-05, + "loss": 0.1511, "step": 179190 }, { - "epoch": 0.8, - "learning_rate": 1.0062329043540649e-05, - "loss": 0.1557, + "epoch": 0.4, + "learning_rate": 3.0076284646875912e-05, + "loss": 0.1475, "step": 179200 }, { - "epoch": 0.8, - "learning_rate": 1.0060086991614728e-05, - "loss": 0.1468, + "epoch": 0.4, + "learning_rate": 3.0075166103666587e-05, + "loss": 0.1482, "step": 179210 }, { - "epoch": 0.8, - "learning_rate": 1.0057844939688805e-05, - "loss": 0.1511, + "epoch": 0.4, + "learning_rate": 3.0074047560457265e-05, + "loss": 0.1516, "step": 179220 }, { - "epoch": 0.8, - "learning_rate": 1.0055602887762882e-05, - "loss": 0.1469, + "epoch": 0.4, + "learning_rate": 3.0072929017247936e-05, + "loss": 0.1449, "step": 179230 }, { - "epoch": 0.8, - "learning_rate": 1.0053360835836959e-05, - "loss": 0.1497, + "epoch": 0.4, + "learning_rate": 3.0071810474038614e-05, + "loss": 0.1468, "step": 179240 }, { - "epoch": 0.8, - "learning_rate": 1.0051118783911036e-05, - "loss": 0.1493, + "epoch": 0.4, + "learning_rate": 3.0070691930829285e-05, + "loss": 0.1494, "step": 179250 }, { - "epoch": 0.8, - "learning_rate": 1.0048876731985113e-05, - "loss": 0.1466, + "epoch": 0.4, + "learning_rate": 3.0069573387619966e-05, + "loss": 0.15, "step": 179260 }, { - "epoch": 0.8, - "learning_rate": 1.004663468005919e-05, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 3.0068454844410644e-05, + "loss": 0.1514, "step": 179270 }, { - "epoch": 0.8, - "learning_rate": 1.0044392628133269e-05, - "loss": 0.1471, + "epoch": 0.4, + "learning_rate": 3.0067336301201316e-05, + "loss": 0.1491, "step": 179280 }, { - "epoch": 0.8, - "learning_rate": 1.0042150576207346e-05, - "loss": 0.1528, + "epoch": 0.4, + "learning_rate": 3.0066217757991993e-05, + "loss": 0.1505, "step": 179290 }, { - "epoch": 0.8, - "learning_rate": 1.0039908524281423e-05, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 3.0065099214782665e-05, + "loss": 0.1525, "step": 179300 }, { - "epoch": 0.8, - "learning_rate": 1.00376664723555e-05, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 3.0063980671573343e-05, + "loss": 0.1528, "step": 179310 }, { - "epoch": 0.8, - "learning_rate": 1.0035424420429577e-05, - "loss": 0.1514, + "epoch": 0.4, + "learning_rate": 3.006286212836402e-05, + "loss": 0.1444, "step": 179320 }, { - "epoch": 0.8, - "learning_rate": 1.0033182368503655e-05, - "loss": 0.1451, + "epoch": 0.4, + "learning_rate": 3.0061743585154695e-05, + "loss": 0.1458, "step": 179330 }, { - "epoch": 0.8, - "learning_rate": 1.0030940316577732e-05, - "loss": 0.1413, + "epoch": 0.4, + "learning_rate": 3.0060625041945373e-05, + "loss": 0.1474, "step": 179340 }, { - "epoch": 0.8, - "learning_rate": 1.0028698264651811e-05, - "loss": 0.1489, + "epoch": 0.4, + "learning_rate": 3.0059506498736044e-05, + "loss": 0.1461, "step": 179350 }, { - "epoch": 0.8, - "learning_rate": 1.0026456212725888e-05, - "loss": 0.1526, + "epoch": 0.4, + "learning_rate": 3.0058387955526722e-05, + "loss": 0.1474, "step": 179360 }, { - "epoch": 0.8, - "learning_rate": 1.0024214160799965e-05, + "epoch": 0.4, + "learning_rate": 3.00572694123174e-05, "loss": 0.1493, "step": 179370 }, { - "epoch": 0.8, - "learning_rate": 1.0021972108874042e-05, - "loss": 0.1497, + "epoch": 0.4, + "learning_rate": 3.0056150869108075e-05, + "loss": 0.15, "step": 179380 }, { - "epoch": 0.8, - "learning_rate": 1.001973005694812e-05, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 3.0055032325898752e-05, + "loss": 0.151, "step": 179390 }, { - "epoch": 0.8, - "learning_rate": 1.0017488005022196e-05, - "loss": 0.1511, + "epoch": 0.4, + "learning_rate": 3.0053913782689424e-05, + "loss": 0.1465, "step": 179400 }, { - "epoch": 0.8, - "learning_rate": 1.0015245953096273e-05, - "loss": 0.1485, + "epoch": 0.4, + "learning_rate": 3.00527952394801e-05, + "loss": 0.1519, "step": 179410 }, { - "epoch": 0.8, - "learning_rate": 1.0013003901170352e-05, - "loss": 0.1517, + "epoch": 0.4, + "learning_rate": 3.005167669627078e-05, + "loss": 0.1493, "step": 179420 }, { - "epoch": 0.8, - "learning_rate": 1.0010761849244429e-05, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 3.0050558153061454e-05, + "loss": 0.1427, "step": 179430 }, { - "epoch": 0.8, - "learning_rate": 1.0008519797318506e-05, - "loss": 0.1452, + "epoch": 0.4, + "learning_rate": 3.0049439609852132e-05, + "loss": 0.1459, "step": 179440 }, { - "epoch": 0.8, - "learning_rate": 1.0006277745392583e-05, - "loss": 0.1431, + "epoch": 0.4, + "learning_rate": 3.0048321066642803e-05, + "loss": 0.1498, "step": 179450 }, { - "epoch": 0.8, - "learning_rate": 1.000403569346666e-05, - "loss": 0.1531, + "epoch": 0.4, + "learning_rate": 3.004720252343348e-05, + "loss": 0.1438, "step": 179460 }, { - "epoch": 0.8, - "learning_rate": 1.0001793641540739e-05, - "loss": 0.148, + "epoch": 0.4, + "learning_rate": 3.004608398022416e-05, + "loss": 0.1475, "step": 179470 }, { - "epoch": 0.8, - "learning_rate": 9.999551589614816e-06, - "loss": 0.1483, + "epoch": 0.4, + "learning_rate": 3.0044965437014833e-05, + "loss": 0.144, "step": 179480 }, { - "epoch": 0.8, - "learning_rate": 9.997309537688895e-06, - "loss": 0.1421, + "epoch": 0.4, + "learning_rate": 3.004384689380551e-05, + "loss": 0.1416, "step": 179490 }, { - "epoch": 0.8, - "learning_rate": 9.995067485762972e-06, - "loss": 0.1521, + "epoch": 0.4, + "learning_rate": 3.0042728350596183e-05, + "loss": 0.1468, "step": 179500 }, { - "epoch": 0.8, - "learning_rate": 9.992825433837049e-06, - "loss": 0.1457, + "epoch": 0.4, + "learning_rate": 3.004160980738686e-05, + "loss": 0.151, "step": 179510 }, { - "epoch": 0.8, - "learning_rate": 9.990583381911126e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 3.004049126417754e-05, + "loss": 0.1522, "step": 179520 }, { - "epoch": 0.8, - "learning_rate": 9.988341329985203e-06, - "loss": 0.1436, + "epoch": 0.4, + "learning_rate": 3.0039372720968213e-05, + "loss": 0.1465, "step": 179530 }, { - "epoch": 0.8, - "learning_rate": 9.98609927805928e-06, - "loss": 0.1439, + "epoch": 0.4, + "learning_rate": 3.003825417775889e-05, + "loss": 0.1491, "step": 179540 }, { - "epoch": 0.8, - "learning_rate": 9.983857226133357e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 3.0037135634549562e-05, + "loss": 0.1479, "step": 179550 }, { - "epoch": 0.8, - "learning_rate": 9.981615174207435e-06, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 3.003601709134024e-05, + "loss": 0.1467, "step": 179560 }, { - "epoch": 0.8, - "learning_rate": 9.979373122281512e-06, - "loss": 0.1462, + "epoch": 0.4, + "learning_rate": 3.0034898548130914e-05, + "loss": 0.1455, "step": 179570 }, { - "epoch": 0.8, - "learning_rate": 9.97713107035559e-06, - "loss": 0.1508, + "epoch": 0.4, + "learning_rate": 3.0033780004921592e-05, + "loss": 0.1479, "step": 179580 }, { - "epoch": 0.8, - "learning_rate": 9.974889018429667e-06, - "loss": 0.1505, + "epoch": 0.4, + "learning_rate": 3.003266146171227e-05, + "loss": 0.1494, "step": 179590 }, { - "epoch": 0.8, - "learning_rate": 9.972646966503745e-06, - "loss": 0.1509, + "epoch": 0.4, + "learning_rate": 3.003154291850294e-05, + "loss": 0.1472, "step": 179600 }, { - "epoch": 0.8, - "learning_rate": 9.970404914577822e-06, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 3.003042437529362e-05, + "loss": 0.1502, "step": 179610 }, { - "epoch": 0.8, - "learning_rate": 9.9681628626519e-06, - "loss": 0.1529, + "epoch": 0.4, + "learning_rate": 3.0029305832084294e-05, + "loss": 0.1525, "step": 179620 }, { - "epoch": 0.8, - "learning_rate": 9.965920810725978e-06, - "loss": 0.145, + "epoch": 0.4, + "learning_rate": 3.0028187288874972e-05, + "loss": 0.1469, "step": 179630 }, { - "epoch": 0.8, - "learning_rate": 9.963678758800055e-06, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 3.002706874566565e-05, + "loss": 0.149, "step": 179640 }, { - "epoch": 0.8, - "learning_rate": 9.961436706874132e-06, - "loss": 0.1438, + "epoch": 0.4, + "learning_rate": 3.002595020245632e-05, + "loss": 0.1505, "step": 179650 }, { - "epoch": 0.8, - "learning_rate": 9.959194654948209e-06, - "loss": 0.1497, + "epoch": 0.4, + "learning_rate": 3.0024831659247e-05, + "loss": 0.1461, "step": 179660 }, { - "epoch": 0.8, - "learning_rate": 9.956952603022286e-06, - "loss": 0.1427, + "epoch": 0.4, + "learning_rate": 3.002371311603767e-05, + "loss": 0.1483, "step": 179670 }, { - "epoch": 0.8, - "learning_rate": 9.954710551096363e-06, - "loss": 0.1456, + "epoch": 0.4, + "learning_rate": 3.002259457282835e-05, + "loss": 0.1442, "step": 179680 }, { - "epoch": 0.8, - "learning_rate": 9.95246849917044e-06, - "loss": 0.1517, + "epoch": 0.4, + "learning_rate": 3.002147602961903e-05, + "loss": 0.1483, "step": 179690 }, { - "epoch": 0.8, - "learning_rate": 9.950226447244519e-06, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 3.00203574864097e-05, + "loss": 0.1483, "step": 179700 }, { - "epoch": 0.8, - "learning_rate": 9.947984395318596e-06, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 3.001923894320038e-05, + "loss": 0.147, "step": 179710 }, { - "epoch": 0.8, - "learning_rate": 9.945742343392673e-06, - "loss": 0.1498, + "epoch": 0.4, + "learning_rate": 3.001812039999105e-05, + "loss": 0.1463, "step": 179720 }, { - "epoch": 0.8, - "learning_rate": 9.94350029146675e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 3.0017001856781727e-05, + "loss": 0.1524, "step": 179730 }, { - "epoch": 0.8, - "learning_rate": 9.941258239540829e-06, - "loss": 0.1528, + "epoch": 0.4, + "learning_rate": 3.001588331357241e-05, + "loss": 0.1471, "step": 179740 }, { - "epoch": 0.8, - "learning_rate": 9.939016187614906e-06, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 3.001476477036308e-05, + "loss": 0.1508, "step": 179750 }, { - "epoch": 0.8, - "learning_rate": 9.936774135688983e-06, - "loss": 0.1545, + "epoch": 0.4, + "learning_rate": 3.0013646227153758e-05, + "loss": 0.1523, "step": 179760 }, { - "epoch": 0.8, - "learning_rate": 9.934532083763061e-06, - "loss": 0.1459, + "epoch": 0.4, + "learning_rate": 3.001252768394443e-05, + "loss": 0.146, "step": 179770 }, { - "epoch": 0.8, - "learning_rate": 9.932290031837138e-06, - "loss": 0.1498, + "epoch": 0.4, + "learning_rate": 3.0011409140735107e-05, + "loss": 0.1452, "step": 179780 }, { - "epoch": 0.8, - "learning_rate": 9.930047979911215e-06, - "loss": 0.1521, + "epoch": 0.4, + "learning_rate": 3.0010290597525785e-05, + "loss": 0.1486, "step": 179790 }, { - "epoch": 0.8, - "learning_rate": 9.927805927985293e-06, - "loss": 0.1498, + "epoch": 0.4, + "learning_rate": 3.000917205431646e-05, + "loss": 0.1445, "step": 179800 }, { - "epoch": 0.8, - "learning_rate": 9.92556387605937e-06, - "loss": 0.1495, + "epoch": 0.4, + "learning_rate": 3.0008053511107137e-05, + "loss": 0.1467, "step": 179810 }, { - "epoch": 0.8, - "learning_rate": 9.923321824133447e-06, - "loss": 0.1527, + "epoch": 0.4, + "learning_rate": 3.000693496789781e-05, + "loss": 0.1448, "step": 179820 }, { - "epoch": 0.8, - "learning_rate": 9.921079772207525e-06, - "loss": 0.1505, + "epoch": 0.4, + "learning_rate": 3.0005816424688486e-05, + "loss": 0.148, "step": 179830 }, { - "epoch": 0.8, - "learning_rate": 9.918837720281602e-06, - "loss": 0.145, + "epoch": 0.4, + "learning_rate": 3.0004697881479164e-05, + "loss": 0.1494, "step": 179840 }, { - "epoch": 0.8, - "learning_rate": 9.91659566835568e-06, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 3.000357933826984e-05, + "loss": 0.1491, "step": 179850 }, { - "epoch": 0.8, - "learning_rate": 9.914353616429756e-06, - "loss": 0.1526, + "epoch": 0.4, + "learning_rate": 3.0002460795060517e-05, + "loss": 0.146, "step": 179860 }, { - "epoch": 0.8, - "learning_rate": 9.912111564503835e-06, - "loss": 0.1452, + "epoch": 0.4, + "learning_rate": 3.0001342251851188e-05, + "loss": 0.1465, "step": 179870 }, { - "epoch": 0.8, - "learning_rate": 9.909869512577912e-06, - "loss": 0.1475, + "epoch": 0.4, + "learning_rate": 3.0000223708641866e-05, + "loss": 0.1519, "step": 179880 }, { - "epoch": 0.8, - "learning_rate": 9.907627460651989e-06, - "loss": 0.155, + "epoch": 0.4, + "learning_rate": 2.999910516543254e-05, + "loss": 0.1476, "step": 179890 }, { - "epoch": 0.8, - "learning_rate": 9.905385408726068e-06, - "loss": 0.1447, + "epoch": 0.4, + "learning_rate": 2.999798662222322e-05, + "loss": 0.1482, "step": 179900 }, { - "epoch": 0.8, - "learning_rate": 9.903143356800145e-06, - "loss": 0.1429, + "epoch": 0.4, + "learning_rate": 2.9996868079013896e-05, + "loss": 0.1473, "step": 179910 }, { - "epoch": 0.8, - "learning_rate": 9.900901304874222e-06, - "loss": 0.143, + "epoch": 0.4, + "learning_rate": 2.9995749535804567e-05, + "loss": 0.1473, "step": 179920 }, { - "epoch": 0.8, - "learning_rate": 9.898659252948299e-06, - "loss": 0.1491, + "epoch": 0.4, + "learning_rate": 2.9994630992595245e-05, + "loss": 0.1532, "step": 179930 }, { - "epoch": 0.8, - "learning_rate": 9.896417201022376e-06, - "loss": 0.1437, + "epoch": 0.4, + "learning_rate": 2.999351244938592e-05, + "loss": 0.1502, "step": 179940 }, { - "epoch": 0.8, - "learning_rate": 9.894175149096453e-06, - "loss": 0.153, + "epoch": 0.4, + "learning_rate": 2.9992393906176598e-05, + "loss": 0.1498, "step": 179950 }, { - "epoch": 0.8, - "learning_rate": 9.89193309717053e-06, - "loss": 0.1467, + "epoch": 0.4, + "learning_rate": 2.9991275362967276e-05, + "loss": 0.1471, "step": 179960 }, { - "epoch": 0.8, - "learning_rate": 9.889691045244609e-06, - "loss": 0.1511, + "epoch": 0.4, + "learning_rate": 2.9990156819757947e-05, + "loss": 0.1498, "step": 179970 }, { - "epoch": 0.8, - "learning_rate": 9.887448993318686e-06, - "loss": 0.1507, + "epoch": 0.4, + "learning_rate": 2.9989038276548625e-05, + "loss": 0.1531, "step": 179980 }, { - "epoch": 0.8, - "learning_rate": 9.885206941392763e-06, - "loss": 0.1516, + "epoch": 0.4, + "learning_rate": 2.99879197333393e-05, + "loss": 0.1493, "step": 179990 }, { - "epoch": 0.8, - "learning_rate": 9.88296488946684e-06, - "loss": 0.1465, + "epoch": 0.4, + "learning_rate": 2.9986801190129977e-05, + "loss": 0.1424, "step": 180000 }, { - "epoch": 0.8, - "learning_rate": 9.880722837540918e-06, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 2.9985682646920655e-05, + "loss": 0.1496, "step": 180010 }, { - "epoch": 0.8, - "learning_rate": 9.878480785614995e-06, - "loss": 0.1466, + "epoch": 0.4, + "learning_rate": 2.9984564103711326e-05, + "loss": 0.1477, "step": 180020 }, { - "epoch": 0.8, - "learning_rate": 9.876238733689073e-06, - "loss": 0.1473, + "epoch": 0.4, + "learning_rate": 2.9983445560502004e-05, + "loss": 0.1494, "step": 180030 }, { - "epoch": 0.8, - "learning_rate": 9.873996681763151e-06, - "loss": 0.1451, + "epoch": 0.4, + "learning_rate": 2.998232701729268e-05, + "loss": 0.1455, "step": 180040 }, { - "epoch": 0.8, - "learning_rate": 9.871754629837228e-06, - "loss": 0.1455, + "epoch": 0.4, + "learning_rate": 2.9981208474083357e-05, + "loss": 0.1467, "step": 180050 }, { - "epoch": 0.8, - "learning_rate": 9.869512577911305e-06, - "loss": 0.1451, + "epoch": 0.4, + "learning_rate": 2.9980089930874035e-05, + "loss": 0.1511, "step": 180060 }, { - "epoch": 0.8, - "learning_rate": 9.867270525985382e-06, - "loss": 0.1508, + "epoch": 0.4, + "learning_rate": 2.9978971387664706e-05, + "loss": 0.1463, "step": 180070 }, { - "epoch": 0.8, - "learning_rate": 9.86502847405946e-06, - "loss": 0.1477, + "epoch": 0.4, + "learning_rate": 2.9977852844455384e-05, + "loss": 0.1479, "step": 180080 }, { - "epoch": 0.8, - "learning_rate": 9.862786422133536e-06, - "loss": 0.1432, + "epoch": 0.4, + "learning_rate": 2.9976734301246058e-05, + "loss": 0.1478, "step": 180090 }, { - "epoch": 0.8, - "learning_rate": 9.860544370207613e-06, - "loss": 0.1528, + "epoch": 0.4, + "learning_rate": 2.9975615758036736e-05, + "loss": 0.15, "step": 180100 }, { - "epoch": 0.8, - "learning_rate": 9.858302318281692e-06, - "loss": 0.1491, + "epoch": 0.4, + "learning_rate": 2.9974497214827414e-05, + "loss": 0.1503, "step": 180110 }, { - "epoch": 0.8, - "learning_rate": 9.856060266355769e-06, - "loss": 0.1455, + "epoch": 0.4, + "learning_rate": 2.9973378671618085e-05, + "loss": 0.1476, "step": 180120 }, { - "epoch": 0.8, - "learning_rate": 9.853818214429846e-06, - "loss": 0.1509, + "epoch": 0.4, + "learning_rate": 2.9972260128408763e-05, + "loss": 0.1474, "step": 180130 }, { - "epoch": 0.8, - "learning_rate": 9.851576162503925e-06, - "loss": 0.1445, + "epoch": 0.4, + "learning_rate": 2.9971141585199434e-05, + "loss": 0.1489, "step": 180140 }, { - "epoch": 0.8, - "learning_rate": 9.849334110578002e-06, + "epoch": 0.4, + "learning_rate": 2.9970023041990116e-05, "loss": 0.1489, "step": 180150 }, { - "epoch": 0.8, - "learning_rate": 9.847092058652079e-06, - "loss": 0.1477, + "epoch": 0.4, + "learning_rate": 2.9968904498780794e-05, + "loss": 0.1499, "step": 180160 }, { - "epoch": 0.8, - "learning_rate": 9.844850006726156e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.9967785955571465e-05, + "loss": 0.1471, "step": 180170 }, { - "epoch": 0.8, - "learning_rate": 9.842607954800235e-06, - "loss": 0.1513, + "epoch": 0.4, + "learning_rate": 2.9966667412362143e-05, + "loss": 0.1457, "step": 180180 }, { - "epoch": 0.8, - "learning_rate": 9.840365902874312e-06, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 2.9965548869152814e-05, + "loss": 0.1477, "step": 180190 }, { - "epoch": 0.8, - "learning_rate": 9.838123850948389e-06, - "loss": 0.1485, + "epoch": 0.4, + "learning_rate": 2.9964430325943492e-05, + "loss": 0.1409, "step": 180200 }, { - "epoch": 0.8, - "learning_rate": 9.835881799022466e-06, - "loss": 0.1477, + "epoch": 0.4, + "learning_rate": 2.9963311782734166e-05, + "loss": 0.1499, "step": 180210 }, { - "epoch": 0.8, - "learning_rate": 9.833639747096543e-06, - "loss": 0.1545, + "epoch": 0.4, + "learning_rate": 2.9962193239524844e-05, + "loss": 0.145, "step": 180220 }, { - "epoch": 0.8, - "learning_rate": 9.83139769517062e-06, - "loss": 0.1473, + "epoch": 0.4, + "learning_rate": 2.9961074696315522e-05, + "loss": 0.1466, "step": 180230 }, { - "epoch": 0.8, - "learning_rate": 9.829155643244697e-06, - "loss": 0.1493, + "epoch": 0.4, + "learning_rate": 2.9959956153106193e-05, + "loss": 0.152, "step": 180240 }, { - "epoch": 0.8, - "learning_rate": 9.826913591318776e-06, - "loss": 0.1441, + "epoch": 0.4, + "learning_rate": 2.995883760989687e-05, + "loss": 0.1447, "step": 180250 }, { - "epoch": 0.8, - "learning_rate": 9.824671539392853e-06, - "loss": 0.1414, + "epoch": 0.4, + "learning_rate": 2.9957719066687546e-05, + "loss": 0.1503, "step": 180260 }, { - "epoch": 0.8, - "learning_rate": 9.82242948746693e-06, - "loss": 0.142, + "epoch": 0.4, + "learning_rate": 2.9956600523478224e-05, + "loss": 0.1452, "step": 180270 }, { - "epoch": 0.8, - "learning_rate": 9.820187435541008e-06, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 2.99554819802689e-05, + "loss": 0.1455, "step": 180280 }, { - "epoch": 0.8, - "learning_rate": 9.817945383615085e-06, - "loss": 0.1488, + "epoch": 0.4, + "learning_rate": 2.9954363437059573e-05, + "loss": 0.1456, "step": 180290 }, { - "epoch": 0.8, - "learning_rate": 9.815703331689162e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.995324489385025e-05, + "loss": 0.1476, "step": 180300 }, { - "epoch": 0.8, - "learning_rate": 9.81346127976324e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.9952126350640925e-05, + "loss": 0.1469, "step": 180310 }, { - "epoch": 0.8, - "learning_rate": 9.811219227837318e-06, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 2.9951007807431603e-05, + "loss": 0.149, "step": 180320 }, { - "epoch": 0.81, - "learning_rate": 9.808977175911395e-06, - "loss": 0.1482, + "epoch": 0.4, + "learning_rate": 2.994988926422228e-05, + "loss": 0.143, "step": 180330 }, { - "epoch": 0.81, - "learning_rate": 9.806735123985472e-06, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 2.9948770721012952e-05, + "loss": 0.1482, "step": 180340 }, { - "epoch": 0.81, - "learning_rate": 9.804493072059549e-06, - "loss": 0.1453, + "epoch": 0.4, + "learning_rate": 2.994765217780363e-05, + "loss": 0.1493, "step": 180350 }, { - "epoch": 0.81, - "learning_rate": 9.802251020133626e-06, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 2.9946533634594305e-05, + "loss": 0.147, "step": 180360 }, { - "epoch": 0.81, - "learning_rate": 9.800008968207703e-06, - "loss": 0.1478, + "epoch": 0.4, + "learning_rate": 2.9945415091384983e-05, + "loss": 0.1521, "step": 180370 }, { - "epoch": 0.81, - "learning_rate": 9.79776691628178e-06, - "loss": 0.1407, + "epoch": 0.4, + "learning_rate": 2.994429654817566e-05, + "loss": 0.1478, "step": 180380 }, { - "epoch": 0.81, - "learning_rate": 9.795524864355859e-06, - "loss": 0.1493, + "epoch": 0.4, + "learning_rate": 2.9943178004966332e-05, + "loss": 0.1514, "step": 180390 }, { - "epoch": 0.81, - "learning_rate": 9.793282812429936e-06, - "loss": 0.1505, + "epoch": 0.4, + "learning_rate": 2.994205946175701e-05, + "loss": 0.1493, "step": 180400 }, { - "epoch": 0.81, - "learning_rate": 9.791040760504015e-06, - "loss": 0.1469, + "epoch": 0.4, + "learning_rate": 2.9940940918547684e-05, + "loss": 0.1498, "step": 180410 }, { - "epoch": 0.81, - "learning_rate": 9.788798708578092e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 2.9939822375338362e-05, + "loss": 0.1463, "step": 180420 }, { - "epoch": 0.81, - "learning_rate": 9.786556656652169e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.993870383212904e-05, + "loss": 0.1501, "step": 180430 }, { - "epoch": 0.81, - "learning_rate": 9.784314604726246e-06, + "epoch": 0.4, + "learning_rate": 2.993758528891971e-05, "loss": 0.1461, "step": 180440 }, { - "epoch": 0.81, - "learning_rate": 9.782072552800323e-06, - "loss": 0.1462, + "epoch": 0.4, + "learning_rate": 2.993646674571039e-05, + "loss": 0.1465, "step": 180450 }, { - "epoch": 0.81, - "learning_rate": 9.779830500874401e-06, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 2.9935348202501064e-05, + "loss": 0.1482, "step": 180460 }, { - "epoch": 0.81, - "learning_rate": 9.777588448948478e-06, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 2.993422965929174e-05, + "loss": 0.1481, "step": 180470 }, { - "epoch": 0.81, - "learning_rate": 9.775346397022556e-06, - "loss": 0.1533, + "epoch": 0.4, + "learning_rate": 2.993311111608242e-05, + "loss": 0.1455, "step": 180480 }, { - "epoch": 0.81, - "learning_rate": 9.773104345096633e-06, - "loss": 0.1501, + "epoch": 0.4, + "learning_rate": 2.993199257287309e-05, + "loss": 0.1488, "step": 180490 }, { - "epoch": 0.81, - "learning_rate": 9.77086229317071e-06, - "loss": 0.1507, + "epoch": 0.4, + "learning_rate": 2.993087402966377e-05, + "loss": 0.1472, "step": 180500 }, { - "epoch": 0.81, - "learning_rate": 9.768620241244787e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 2.9929755486454443e-05, + "loss": 0.1517, "step": 180510 }, { - "epoch": 0.81, - "learning_rate": 9.766378189318865e-06, - "loss": 0.1455, + "epoch": 0.4, + "learning_rate": 2.992863694324512e-05, + "loss": 0.1452, "step": 180520 }, { - "epoch": 0.81, - "learning_rate": 9.764136137392942e-06, - "loss": 0.1471, + "epoch": 0.4, + "learning_rate": 2.9927518400035792e-05, + "loss": 0.1535, "step": 180530 }, { - "epoch": 0.81, - "learning_rate": 9.76189408546702e-06, - "loss": 0.1484, + "epoch": 0.4, + "learning_rate": 2.992639985682647e-05, + "loss": 0.1439, "step": 180540 }, { - "epoch": 0.81, - "learning_rate": 9.759652033541098e-06, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 2.9925281313617148e-05, + "loss": 0.1479, "step": 180550 }, { - "epoch": 0.81, - "learning_rate": 9.757409981615175e-06, - "loss": 0.1524, + "epoch": 0.4, + "learning_rate": 2.992416277040782e-05, + "loss": 0.1496, "step": 180560 }, { - "epoch": 0.81, - "learning_rate": 9.755167929689252e-06, - "loss": 0.1472, + "epoch": 0.4, + "learning_rate": 2.99230442271985e-05, + "loss": 0.1453, "step": 180570 }, { - "epoch": 0.81, - "learning_rate": 9.752925877763329e-06, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 2.9921925683989172e-05, + "loss": 0.1504, "step": 180580 }, { - "epoch": 0.81, - "learning_rate": 9.750683825837408e-06, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 2.992080714077985e-05, + "loss": 0.1466, "step": 180590 }, { - "epoch": 0.81, - "learning_rate": 9.748441773911485e-06, - "loss": 0.1437, + "epoch": 0.4, + "learning_rate": 2.9919688597570528e-05, + "loss": 0.1454, "step": 180600 }, { - "epoch": 0.81, - "learning_rate": 9.746199721985562e-06, - "loss": 0.1509, + "epoch": 0.4, + "learning_rate": 2.99185700543612e-05, + "loss": 0.146, "step": 180610 }, { - "epoch": 0.81, - "learning_rate": 9.743957670059639e-06, - "loss": 0.1479, + "epoch": 0.4, + "learning_rate": 2.9917451511151877e-05, + "loss": 0.1496, "step": 180620 }, { - "epoch": 0.81, - "learning_rate": 9.741715618133716e-06, - "loss": 0.1414, + "epoch": 0.4, + "learning_rate": 2.991633296794255e-05, + "loss": 0.1504, "step": 180630 }, { - "epoch": 0.81, - "learning_rate": 9.739473566207793e-06, - "loss": 0.1467, + "epoch": 0.4, + "learning_rate": 2.991521442473323e-05, + "loss": 0.1447, "step": 180640 }, { - "epoch": 0.81, - "learning_rate": 9.73723151428187e-06, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 2.9914095881523907e-05, + "loss": 0.147, "step": 180650 }, { - "epoch": 0.81, - "learning_rate": 9.734989462355949e-06, - "loss": 0.1431, + "epoch": 0.4, + "learning_rate": 2.9912977338314578e-05, + "loss": 0.1494, "step": 180660 }, { - "epoch": 0.81, - "learning_rate": 9.732747410430026e-06, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 2.9911858795105256e-05, + "loss": 0.1463, "step": 180670 }, { - "epoch": 0.81, - "learning_rate": 9.730505358504104e-06, - "loss": 0.1522, + "epoch": 0.4, + "learning_rate": 2.991074025189593e-05, + "loss": 0.1465, "step": 180680 }, { - "epoch": 0.81, - "learning_rate": 9.728263306578181e-06, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 2.990962170868661e-05, + "loss": 0.151, "step": 180690 }, { - "epoch": 0.81, - "learning_rate": 9.726021254652259e-06, - "loss": 0.1454, + "epoch": 0.4, + "learning_rate": 2.9908503165477287e-05, + "loss": 0.15, "step": 180700 }, { - "epoch": 0.81, - "learning_rate": 9.723779202726336e-06, - "loss": 0.1443, + "epoch": 0.4, + "learning_rate": 2.9907384622267958e-05, + "loss": 0.15, "step": 180710 }, { - "epoch": 0.81, - "learning_rate": 9.721537150800413e-06, - "loss": 0.148, + "epoch": 0.4, + "learning_rate": 2.9906266079058636e-05, + "loss": 0.1481, "step": 180720 }, { - "epoch": 0.81, - "learning_rate": 9.719295098874491e-06, - "loss": 0.1469, + "epoch": 0.4, + "learning_rate": 2.990514753584931e-05, + "loss": 0.1547, "step": 180730 }, { - "epoch": 0.81, - "learning_rate": 9.717053046948568e-06, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 2.9904028992639988e-05, + "loss": 0.1451, "step": 180740 }, { - "epoch": 0.81, - "learning_rate": 9.714810995022645e-06, - "loss": 0.1452, + "epoch": 0.4, + "learning_rate": 2.9902910449430666e-05, + "loss": 0.1463, "step": 180750 }, { - "epoch": 0.81, - "learning_rate": 9.712568943096722e-06, - "loss": 0.1478, + "epoch": 0.4, + "learning_rate": 2.9901791906221337e-05, + "loss": 0.1539, "step": 180760 }, { - "epoch": 0.81, - "learning_rate": 9.7103268911708e-06, - "loss": 0.1467, + "epoch": 0.4, + "learning_rate": 2.9900673363012015e-05, + "loss": 0.1523, "step": 180770 }, { - "epoch": 0.81, - "learning_rate": 9.708084839244876e-06, - "loss": 0.1483, + "epoch": 0.4, + "learning_rate": 2.989955481980269e-05, + "loss": 0.1476, "step": 180780 }, { - "epoch": 0.81, - "learning_rate": 9.705842787318953e-06, - "loss": 0.1485, + "epoch": 0.4, + "learning_rate": 2.9898436276593368e-05, + "loss": 0.1483, "step": 180790 }, { - "epoch": 0.81, - "learning_rate": 9.703600735393032e-06, - "loss": 0.1475, + "epoch": 0.4, + "learning_rate": 2.989731773338404e-05, + "loss": 0.1477, "step": 180800 }, { - "epoch": 0.81, - "learning_rate": 9.70135868346711e-06, - "loss": 0.1444, + "epoch": 0.4, + "learning_rate": 2.9896199190174717e-05, + "loss": 0.1475, "step": 180810 }, { - "epoch": 0.81, - "learning_rate": 9.699116631541188e-06, - "loss": 0.147, + "epoch": 0.4, + "learning_rate": 2.9895080646965395e-05, + "loss": 0.145, "step": 180820 }, { - "epoch": 0.81, - "learning_rate": 9.696874579615265e-06, - "loss": 0.1432, + "epoch": 0.4, + "learning_rate": 2.989396210375607e-05, + "loss": 0.146, "step": 180830 }, { - "epoch": 0.81, - "learning_rate": 9.694632527689342e-06, - "loss": 0.144, + "epoch": 0.4, + "learning_rate": 2.9892843560546747e-05, + "loss": 0.1483, "step": 180840 }, { - "epoch": 0.81, - "learning_rate": 9.692390475763419e-06, - "loss": 0.1507, + "epoch": 0.4, + "learning_rate": 2.9891725017337418e-05, + "loss": 0.1463, "step": 180850 }, { - "epoch": 0.81, - "learning_rate": 9.690148423837496e-06, - "loss": 0.1459, + "epoch": 0.4, + "learning_rate": 2.9890606474128096e-05, + "loss": 0.1432, "step": 180860 }, { - "epoch": 0.81, - "learning_rate": 9.687906371911575e-06, - "loss": 0.143, + "epoch": 0.4, + "learning_rate": 2.9889487930918774e-05, + "loss": 0.1499, "step": 180870 }, { - "epoch": 0.81, - "learning_rate": 9.685664319985652e-06, - "loss": 0.1417, + "epoch": 0.4, + "learning_rate": 2.988836938770945e-05, + "loss": 0.1422, "step": 180880 }, { - "epoch": 0.81, - "learning_rate": 9.683422268059729e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.9887250844500126e-05, + "loss": 0.1504, "step": 180890 }, { - "epoch": 0.81, - "learning_rate": 9.681180216133806e-06, - "loss": 0.1458, + "epoch": 0.4, + "learning_rate": 2.9886132301290798e-05, + "loss": 0.1517, "step": 180900 }, { - "epoch": 0.81, - "learning_rate": 9.678938164207883e-06, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 2.9885013758081476e-05, + "loss": 0.1468, "step": 180910 }, { - "epoch": 0.81, - "learning_rate": 9.67669611228196e-06, - "loss": 0.1423, + "epoch": 0.4, + "learning_rate": 2.9883895214872153e-05, + "loss": 0.1455, "step": 180920 }, { - "epoch": 0.81, - "learning_rate": 9.674454060356039e-06, - "loss": 0.1391, + "epoch": 0.4, + "learning_rate": 2.9882776671662828e-05, + "loss": 0.1456, "step": 180930 }, { - "epoch": 0.81, - "learning_rate": 9.672212008430116e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.9881658128453506e-05, + "loss": 0.1425, "step": 180940 }, { - "epoch": 0.81, - "learning_rate": 9.669969956504194e-06, - "loss": 0.1398, + "epoch": 0.4, + "learning_rate": 2.9880539585244177e-05, + "loss": 0.1535, "step": 180950 }, { - "epoch": 0.81, - "learning_rate": 9.667727904578271e-06, - "loss": 0.1482, + "epoch": 0.4, + "learning_rate": 2.9879421042034855e-05, + "loss": 0.1459, "step": 180960 }, { - "epoch": 0.81, - "learning_rate": 9.665485852652348e-06, - "loss": 0.1502, + "epoch": 0.4, + "learning_rate": 2.9878302498825533e-05, + "loss": 0.1474, "step": 180970 }, { - "epoch": 0.81, - "learning_rate": 9.663243800726425e-06, - "loss": 0.147, + "epoch": 0.4, + "learning_rate": 2.9877183955616208e-05, + "loss": 0.1488, "step": 180980 }, { - "epoch": 0.81, - "learning_rate": 9.661001748800502e-06, - "loss": 0.1492, + "epoch": 0.4, + "learning_rate": 2.9876177266727816e-05, + "loss": 0.1494, "step": 180990 }, { - "epoch": 0.81, - "learning_rate": 9.65875969687458e-06, - "loss": 0.1505, + "epoch": 0.4, + "learning_rate": 2.987505872351849e-05, + "loss": 0.1424, "step": 181000 }, { - "epoch": 0.81, - "learning_rate": 9.656517644948658e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 2.987394018030917e-05, + "loss": 0.1492, "step": 181010 }, { - "epoch": 0.81, - "learning_rate": 9.654275593022735e-06, - "loss": 0.1518, + "epoch": 0.4, + "learning_rate": 2.987282163709984e-05, + "loss": 0.1515, "step": 181020 }, { - "epoch": 0.81, - "learning_rate": 9.652033541096812e-06, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 2.9871703093890518e-05, + "loss": 0.148, "step": 181030 }, { - "epoch": 0.81, - "learning_rate": 9.64979148917089e-06, - "loss": 0.1527, + "epoch": 0.4, + "learning_rate": 2.9870584550681196e-05, + "loss": 0.1489, "step": 181040 }, { - "epoch": 0.81, - "learning_rate": 9.647549437244966e-06, - "loss": 0.1428, + "epoch": 0.4, + "learning_rate": 2.986946600747187e-05, + "loss": 0.1485, "step": 181050 }, { - "epoch": 0.81, - "learning_rate": 9.645307385319043e-06, - "loss": 0.1416, + "epoch": 0.4, + "learning_rate": 2.9868347464262548e-05, + "loss": 0.1509, "step": 181060 }, { - "epoch": 0.81, - "learning_rate": 9.643065333393122e-06, - "loss": 0.1402, + "epoch": 0.4, + "learning_rate": 2.986722892105322e-05, + "loss": 0.1453, "step": 181070 }, { - "epoch": 0.81, - "learning_rate": 9.640823281467199e-06, - "loss": 0.1472, + "epoch": 0.4, + "learning_rate": 2.9866110377843897e-05, + "loss": 0.1423, "step": 181080 }, { - "epoch": 0.81, - "learning_rate": 9.638581229541278e-06, + "epoch": 0.4, + "learning_rate": 2.9864991834634575e-05, "loss": 0.1496, "step": 181090 }, { - "epoch": 0.81, - "learning_rate": 9.636339177615355e-06, - "loss": 0.1412, + "epoch": 0.4, + "learning_rate": 2.986387329142525e-05, + "loss": 0.1491, "step": 181100 }, { - "epoch": 0.81, - "learning_rate": 9.634097125689432e-06, - "loss": 0.1506, + "epoch": 0.4, + "learning_rate": 2.9862754748215928e-05, + "loss": 0.1564, "step": 181110 }, { - "epoch": 0.81, - "learning_rate": 9.631855073763509e-06, - "loss": 0.1496, + "epoch": 0.4, + "learning_rate": 2.98616362050066e-05, + "loss": 0.1546, "step": 181120 }, { - "epoch": 0.81, - "learning_rate": 9.629613021837586e-06, - "loss": 0.1474, + "epoch": 0.4, + "learning_rate": 2.9860517661797277e-05, + "loss": 0.1483, "step": 181130 }, { - "epoch": 0.81, - "learning_rate": 9.627370969911663e-06, - "loss": 0.1532, + "epoch": 0.4, + "learning_rate": 2.9859399118587955e-05, + "loss": 0.1485, "step": 181140 }, { - "epoch": 0.81, - "learning_rate": 9.625128917985742e-06, - "loss": 0.1428, + "epoch": 0.4, + "learning_rate": 2.985828057537863e-05, + "loss": 0.1441, "step": 181150 }, { - "epoch": 0.81, - "learning_rate": 9.622886866059819e-06, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 2.9857162032169307e-05, + "loss": 0.1487, "step": 181160 }, { - "epoch": 0.81, - "learning_rate": 9.620644814133896e-06, - "loss": 0.1456, + "epoch": 0.4, + "learning_rate": 2.985604348895998e-05, + "loss": 0.1439, "step": 181170 }, { - "epoch": 0.81, - "learning_rate": 9.618402762207973e-06, - "loss": 0.1466, + "epoch": 0.4, + "learning_rate": 2.9854924945750656e-05, + "loss": 0.1482, "step": 181180 }, { - "epoch": 0.81, - "learning_rate": 9.61616071028205e-06, - "loss": 0.1481, + "epoch": 0.4, + "learning_rate": 2.9853806402541327e-05, + "loss": 0.1422, "step": 181190 }, { - "epoch": 0.81, - "learning_rate": 9.613918658356127e-06, - "loss": 0.1461, + "epoch": 0.4, + "learning_rate": 2.9852687859332005e-05, + "loss": 0.1448, "step": 181200 }, { - "epoch": 0.81, - "learning_rate": 9.611676606430205e-06, - "loss": 0.1473, + "epoch": 0.4, + "learning_rate": 2.9851569316122687e-05, + "loss": 0.1517, "step": 181210 }, { - "epoch": 0.81, - "learning_rate": 9.609434554504284e-06, - "loss": 0.1458, + "epoch": 0.4, + "learning_rate": 2.9850450772913358e-05, + "loss": 0.1497, "step": 181220 }, { - "epoch": 0.81, - "learning_rate": 9.607192502578361e-06, - "loss": 0.1459, + "epoch": 0.4, + "learning_rate": 2.9849332229704036e-05, + "loss": 0.152, "step": 181230 }, { - "epoch": 0.81, - "learning_rate": 9.604950450652438e-06, - "loss": 0.1512, + "epoch": 0.4, + "learning_rate": 2.9848213686494707e-05, + "loss": 0.1505, "step": 181240 }, { - "epoch": 0.81, - "learning_rate": 9.602708398726515e-06, - "loss": 0.1387, + "epoch": 0.4, + "learning_rate": 2.9847095143285385e-05, + "loss": 0.1507, "step": 181250 }, { - "epoch": 0.81, - "learning_rate": 9.600466346800592e-06, - "loss": 0.1514, + "epoch": 0.4, + "learning_rate": 2.9845976600076063e-05, + "loss": 0.1427, "step": 181260 }, { - "epoch": 0.81, - "learning_rate": 9.59822429487467e-06, - "loss": 0.149, + "epoch": 0.4, + "learning_rate": 2.9844858056866737e-05, + "loss": 0.1511, "step": 181270 }, { - "epoch": 0.81, - "learning_rate": 9.595982242948748e-06, - "loss": 0.1445, + "epoch": 0.4, + "learning_rate": 2.9843739513657415e-05, + "loss": 0.1479, "step": 181280 }, { - "epoch": 0.81, - "learning_rate": 9.593740191022825e-06, - "loss": 0.1419, + "epoch": 0.4, + "learning_rate": 2.9842620970448086e-05, + "loss": 0.1479, "step": 181290 }, { - "epoch": 0.81, - "learning_rate": 9.591498139096902e-06, - "loss": 0.1494, + "epoch": 0.4, + "learning_rate": 2.9841502427238764e-05, + "loss": 0.1488, "step": 181300 }, { - "epoch": 0.81, - "learning_rate": 9.589256087170979e-06, - "loss": 0.1484, + "epoch": 0.4, + "learning_rate": 2.9840383884029442e-05, + "loss": 0.1467, "step": 181310 }, { - "epoch": 0.81, - "learning_rate": 9.587014035245056e-06, - "loss": 0.143, + "epoch": 0.4, + "learning_rate": 2.9839265340820117e-05, + "loss": 0.1493, "step": 181320 }, { - "epoch": 0.81, - "learning_rate": 9.584771983319133e-06, - "loss": 0.1423, + "epoch": 0.4, + "learning_rate": 2.9838146797610795e-05, + "loss": 0.1444, "step": 181330 }, { - "epoch": 0.81, - "learning_rate": 9.582529931393212e-06, - "loss": 0.152, + "epoch": 0.4, + "learning_rate": 2.9837028254401466e-05, + "loss": 0.1505, "step": 181340 }, { - "epoch": 0.81, - "learning_rate": 9.580287879467289e-06, - "loss": 0.1442, + "epoch": 0.4, + "learning_rate": 2.9835909711192144e-05, + "loss": 0.1474, "step": 181350 }, { - "epoch": 0.81, - "learning_rate": 9.578045827541367e-06, - "loss": 0.143, + "epoch": 0.4, + "learning_rate": 2.983479116798282e-05, + "loss": 0.1469, "step": 181360 }, { - "epoch": 0.81, - "learning_rate": 9.575803775615445e-06, - "loss": 0.1436, + "epoch": 0.4, + "learning_rate": 2.9833672624773496e-05, + "loss": 0.1474, "step": 181370 }, { - "epoch": 0.81, - "learning_rate": 9.573561723689522e-06, - "loss": 0.1483, + "epoch": 0.4, + "learning_rate": 2.9832554081564174e-05, + "loss": 0.1481, "step": 181380 }, { - "epoch": 0.81, - "learning_rate": 9.571319671763599e-06, - "loss": 0.15, + "epoch": 0.4, + "learning_rate": 2.9831435538354845e-05, + "loss": 0.149, "step": 181390 }, { - "epoch": 0.81, - "learning_rate": 9.569077619837676e-06, - "loss": 0.1482, + "epoch": 0.4, + "learning_rate": 2.9830316995145523e-05, + "loss": 0.15, "step": 181400 }, { - "epoch": 0.81, - "learning_rate": 9.566835567911753e-06, - "loss": 0.1475, + "epoch": 0.4, + "learning_rate": 2.98291984519362e-05, + "loss": 0.1489, "step": 181410 }, { - "epoch": 0.81, - "learning_rate": 9.564817721178424e-06, - "loss": 0.1467, + "epoch": 0.4, + "learning_rate": 2.9828079908726876e-05, + "loss": 0.1513, "step": 181420 }, { - "epoch": 0.81, - "learning_rate": 9.5625756692525e-06, - "loss": 0.1448, + "epoch": 0.4, + "learning_rate": 2.9826961365517554e-05, + "loss": 0.1534, "step": 181430 }, { - "epoch": 0.81, - "learning_rate": 9.560333617326578e-06, - "loss": 0.1484, + "epoch": 0.4, + "learning_rate": 2.9825842822308225e-05, + "loss": 0.1488, "step": 181440 }, { - "epoch": 0.81, - "learning_rate": 9.558091565400655e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.9824724279098903e-05, + "loss": 0.15, "step": 181450 }, { - "epoch": 0.81, - "learning_rate": 9.555849513474732e-06, - "loss": 0.1479, + "epoch": 0.41, + "learning_rate": 2.982360573588958e-05, + "loss": 0.152, "step": 181460 }, { - "epoch": 0.81, - "learning_rate": 9.553607461548809e-06, - "loss": 0.148, + "epoch": 0.41, + "learning_rate": 2.9822487192680255e-05, + "loss": 0.1476, "step": 181470 }, { - "epoch": 0.81, - "learning_rate": 9.551365409622888e-06, - "loss": 0.1402, + "epoch": 0.41, + "learning_rate": 2.9821368649470933e-05, + "loss": 0.1438, "step": 181480 }, { - "epoch": 0.81, - "learning_rate": 9.549123357696965e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9820250106261604e-05, + "loss": 0.1478, "step": 181490 }, { - "epoch": 0.81, - "learning_rate": 9.546881305771042e-06, - "loss": 0.149, + "epoch": 0.41, + "learning_rate": 2.9819131563052282e-05, + "loss": 0.1481, "step": 181500 }, { - "epoch": 0.81, - "learning_rate": 9.54463925384512e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.9818013019842957e-05, + "loss": 0.1464, "step": 181510 }, { - "epoch": 0.81, - "learning_rate": 9.542397201919197e-06, - "loss": 0.1527, + "epoch": 0.41, + "learning_rate": 2.9816894476633635e-05, + "loss": 0.1518, "step": 181520 }, { - "epoch": 0.81, - "learning_rate": 9.540155149993274e-06, - "loss": 0.1466, + "epoch": 0.41, + "learning_rate": 2.9815775933424313e-05, + "loss": 0.15, "step": 181530 }, { - "epoch": 0.81, - "learning_rate": 9.537913098067351e-06, - "loss": 0.1445, + "epoch": 0.41, + "learning_rate": 2.9814657390214984e-05, + "loss": 0.1457, "step": 181540 }, { - "epoch": 0.81, - "learning_rate": 9.53567104614143e-06, - "loss": 0.1462, + "epoch": 0.41, + "learning_rate": 2.981353884700566e-05, + "loss": 0.1443, "step": 181550 }, { - "epoch": 0.81, - "learning_rate": 9.533428994215507e-06, - "loss": 0.1494, + "epoch": 0.41, + "learning_rate": 2.9812420303796336e-05, + "loss": 0.1443, "step": 181560 }, { - "epoch": 0.81, - "learning_rate": 9.531186942289584e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.9811301760587014e-05, + "loss": 0.1503, "step": 181570 }, { - "epoch": 0.81, - "learning_rate": 9.528944890363661e-06, - "loss": 0.1426, + "epoch": 0.41, + "learning_rate": 2.9810183217377692e-05, + "loss": 0.1466, "step": 181580 }, { - "epoch": 0.81, - "learning_rate": 9.526702838437738e-06, - "loss": 0.1486, + "epoch": 0.41, + "learning_rate": 2.9809064674168363e-05, + "loss": 0.1445, "step": 181590 }, { - "epoch": 0.81, - "learning_rate": 9.524460786511815e-06, - "loss": 0.1462, + "epoch": 0.41, + "learning_rate": 2.980794613095904e-05, + "loss": 0.1494, "step": 181600 }, { - "epoch": 0.81, - "learning_rate": 9.522218734585892e-06, - "loss": 0.152, + "epoch": 0.41, + "learning_rate": 2.9806827587749712e-05, + "loss": 0.1526, "step": 181610 }, { - "epoch": 0.81, - "learning_rate": 9.519976682659971e-06, - "loss": 0.15, + "epoch": 0.41, + "learning_rate": 2.9805709044540394e-05, + "loss": 0.1485, "step": 181620 }, { - "epoch": 0.81, - "learning_rate": 9.517734630734048e-06, - "loss": 0.1425, + "epoch": 0.41, + "learning_rate": 2.980459050133107e-05, + "loss": 0.1504, "step": 181630 }, { - "epoch": 0.81, - "learning_rate": 9.515492578808125e-06, - "loss": 0.144, + "epoch": 0.41, + "learning_rate": 2.9803471958121743e-05, + "loss": 0.1499, "step": 181640 }, { - "epoch": 0.81, - "learning_rate": 9.513250526882204e-06, - "loss": 0.1432, + "epoch": 0.41, + "learning_rate": 2.980235341491242e-05, + "loss": 0.1508, "step": 181650 }, { - "epoch": 0.81, - "learning_rate": 9.51100847495628e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.9801234871703092e-05, + "loss": 0.1445, "step": 181660 }, { - "epoch": 0.81, - "learning_rate": 9.508766423030358e-06, - "loss": 0.1436, + "epoch": 0.41, + "learning_rate": 2.980011632849377e-05, + "loss": 0.1491, "step": 181670 }, { - "epoch": 0.81, - "learning_rate": 9.506524371104435e-06, - "loss": 0.1453, + "epoch": 0.41, + "learning_rate": 2.9798997785284448e-05, + "loss": 0.147, "step": 181680 }, { - "epoch": 0.81, - "learning_rate": 9.504282319178514e-06, - "loss": 0.1437, + "epoch": 0.41, + "learning_rate": 2.9797879242075122e-05, + "loss": 0.1487, "step": 181690 }, { - "epoch": 0.81, - "learning_rate": 9.50204026725259e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.97967606988658e-05, + "loss": 0.1499, "step": 181700 }, { - "epoch": 0.81, - "learning_rate": 9.499798215326668e-06, - "loss": 0.1501, + "epoch": 0.41, + "learning_rate": 2.979564215565647e-05, + "loss": 0.1463, "step": 181710 }, { - "epoch": 0.81, - "learning_rate": 9.497556163400745e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.979452361244715e-05, + "loss": 0.151, "step": 181720 }, { - "epoch": 0.81, - "learning_rate": 9.495314111474822e-06, - "loss": 0.1483, + "epoch": 0.41, + "learning_rate": 2.9793405069237827e-05, + "loss": 0.1439, "step": 181730 }, { - "epoch": 0.81, - "learning_rate": 9.493072059548899e-06, - "loss": 0.1501, + "epoch": 0.41, + "learning_rate": 2.97922865260285e-05, + "loss": 0.1479, "step": 181740 }, { - "epoch": 0.81, - "learning_rate": 9.490830007622976e-06, - "loss": 0.1479, + "epoch": 0.41, + "learning_rate": 2.979116798281918e-05, + "loss": 0.1444, "step": 181750 }, { - "epoch": 0.81, - "learning_rate": 9.488587955697054e-06, - "loss": 0.1468, + "epoch": 0.41, + "learning_rate": 2.979004943960985e-05, + "loss": 0.1473, "step": 181760 }, { - "epoch": 0.81, - "learning_rate": 9.486345903771131e-06, - "loss": 0.1468, + "epoch": 0.41, + "learning_rate": 2.978893089640053e-05, + "loss": 0.1502, "step": 181770 }, { - "epoch": 0.81, - "learning_rate": 9.48410385184521e-06, - "loss": 0.1472, + "epoch": 0.41, + "learning_rate": 2.9787812353191207e-05, + "loss": 0.1431, "step": 181780 }, { - "epoch": 0.81, - "learning_rate": 9.481861799919287e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.978669380998188e-05, + "loss": 0.1437, "step": 181790 }, { - "epoch": 0.81, - "learning_rate": 9.479619747993364e-06, - "loss": 0.1411, + "epoch": 0.41, + "learning_rate": 2.978557526677256e-05, + "loss": 0.1477, "step": 181800 }, { - "epoch": 0.81, - "learning_rate": 9.477377696067441e-06, - "loss": 0.1501, + "epoch": 0.41, + "learning_rate": 2.978445672356323e-05, + "loss": 0.145, "step": 181810 }, { - "epoch": 0.81, - "learning_rate": 9.475135644141518e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9783338180353908e-05, + "loss": 0.1477, "step": 181820 }, { - "epoch": 0.81, - "learning_rate": 9.472893592215597e-06, - "loss": 0.1494, + "epoch": 0.41, + "learning_rate": 2.9782219637144583e-05, + "loss": 0.1439, "step": 181830 }, { - "epoch": 0.81, - "learning_rate": 9.470651540289674e-06, - "loss": 0.1506, + "epoch": 0.41, + "learning_rate": 2.978110109393526e-05, + "loss": 0.1461, "step": 181840 }, { - "epoch": 0.81, - "learning_rate": 9.468409488363751e-06, - "loss": 0.1509, + "epoch": 0.41, + "learning_rate": 2.977998255072594e-05, + "loss": 0.1488, "step": 181850 }, { - "epoch": 0.81, - "learning_rate": 9.466167436437828e-06, - "loss": 0.1522, + "epoch": 0.41, + "learning_rate": 2.977886400751661e-05, + "loss": 0.1447, "step": 181860 }, { - "epoch": 0.81, - "learning_rate": 9.463925384511905e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9777745464307288e-05, + "loss": 0.1502, "step": 181870 }, { - "epoch": 0.81, - "learning_rate": 9.461683332585982e-06, - "loss": 0.1396, + "epoch": 0.41, + "learning_rate": 2.9776626921097962e-05, + "loss": 0.1444, "step": 181880 }, { - "epoch": 0.81, - "learning_rate": 9.459441280660059e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.977550837788864e-05, + "loss": 0.148, "step": 181890 }, { - "epoch": 0.81, - "learning_rate": 9.457199228734138e-06, - "loss": 0.1412, + "epoch": 0.41, + "learning_rate": 2.9774389834679318e-05, + "loss": 0.1519, "step": 181900 }, { - "epoch": 0.81, - "learning_rate": 9.454957176808215e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.977327129146999e-05, + "loss": 0.1505, "step": 181910 }, { - "epoch": 0.81, - "learning_rate": 9.452715124882294e-06, - "loss": 0.1384, + "epoch": 0.41, + "learning_rate": 2.9772152748260667e-05, + "loss": 0.1458, "step": 181920 }, { - "epoch": 0.81, - "learning_rate": 9.45047307295637e-06, - "loss": 0.1423, + "epoch": 0.41, + "learning_rate": 2.977103420505134e-05, + "loss": 0.1491, "step": 181930 }, { - "epoch": 0.81, - "learning_rate": 9.448231021030448e-06, - "loss": 0.1441, + "epoch": 0.41, + "learning_rate": 2.976991566184202e-05, + "loss": 0.1488, "step": 181940 }, { - "epoch": 0.81, - "learning_rate": 9.445988969104525e-06, - "loss": 0.1484, + "epoch": 0.41, + "learning_rate": 2.9768797118632697e-05, + "loss": 0.1514, "step": 181950 }, { - "epoch": 0.81, - "learning_rate": 9.443746917178602e-06, - "loss": 0.1468, + "epoch": 0.41, + "learning_rate": 2.976767857542337e-05, + "loss": 0.1527, "step": 181960 }, { - "epoch": 0.81, - "learning_rate": 9.44150486525268e-06, - "loss": 0.1421, + "epoch": 0.41, + "learning_rate": 2.9766560032214047e-05, + "loss": 0.1482, "step": 181970 }, { - "epoch": 0.81, - "learning_rate": 9.439262813326757e-06, - "loss": 0.148, + "epoch": 0.41, + "learning_rate": 2.976544148900472e-05, + "loss": 0.1438, "step": 181980 }, { - "epoch": 0.81, - "learning_rate": 9.437020761400834e-06, - "loss": 0.1503, + "epoch": 0.41, + "learning_rate": 2.97643229457954e-05, + "loss": 0.1482, "step": 181990 }, { - "epoch": 0.81, - "learning_rate": 9.434778709474911e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9763204402586077e-05, + "loss": 0.147, "step": 182000 }, { - "epoch": 0.81, - "learning_rate": 9.432536657548989e-06, - "loss": 0.1513, + "epoch": 0.41, + "learning_rate": 2.9762085859376748e-05, + "loss": 0.1454, "step": 182010 }, { - "epoch": 0.81, - "learning_rate": 9.430294605623066e-06, - "loss": 0.1507, + "epoch": 0.41, + "learning_rate": 2.9760967316167426e-05, + "loss": 0.1474, "step": 182020 }, { - "epoch": 0.81, - "learning_rate": 9.428052553697143e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.9759848772958097e-05, + "loss": 0.1449, "step": 182030 }, { - "epoch": 0.81, - "learning_rate": 9.425810501771221e-06, - "loss": 0.1462, + "epoch": 0.41, + "learning_rate": 2.975873022974878e-05, + "loss": 0.1491, "step": 182040 }, { - "epoch": 0.81, - "learning_rate": 9.4235684498453e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.9757611686539456e-05, + "loss": 0.1454, "step": 182050 }, { - "epoch": 0.81, - "learning_rate": 9.421326397919377e-06, - "loss": 0.1445, + "epoch": 0.41, + "learning_rate": 2.9756493143330128e-05, + "loss": 0.1433, "step": 182060 }, { - "epoch": 0.81, - "learning_rate": 9.419084345993454e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.9755374600120805e-05, + "loss": 0.1547, "step": 182070 }, { - "epoch": 0.81, - "learning_rate": 9.416842294067531e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.9754256056911477e-05, + "loss": 0.1476, "step": 182080 }, { - "epoch": 0.81, - "learning_rate": 9.414600242141608e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.9753137513702155e-05, + "loss": 0.1454, "step": 182090 }, { - "epoch": 0.81, - "learning_rate": 9.412358190215685e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9752018970492836e-05, + "loss": 0.1482, "step": 182100 }, { - "epoch": 0.81, - "learning_rate": 9.410116138289764e-06, - "loss": 0.1432, + "epoch": 0.41, + "learning_rate": 2.9750900427283507e-05, + "loss": 0.1501, "step": 182110 }, { - "epoch": 0.81, - "learning_rate": 9.407874086363841e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.9749781884074185e-05, + "loss": 0.1474, "step": 182120 }, { - "epoch": 0.81, - "learning_rate": 9.405632034437918e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9748663340864856e-05, + "loss": 0.1502, "step": 182130 }, { - "epoch": 0.81, - "learning_rate": 9.403389982511995e-06, - "loss": 0.151, + "epoch": 0.41, + "learning_rate": 2.9747544797655534e-05, + "loss": 0.1494, "step": 182140 }, { - "epoch": 0.81, - "learning_rate": 9.401147930586072e-06, - "loss": 0.1445, + "epoch": 0.41, + "learning_rate": 2.974642625444621e-05, + "loss": 0.1468, "step": 182150 }, { - "epoch": 0.81, - "learning_rate": 9.398905878660149e-06, - "loss": 0.148, + "epoch": 0.41, + "learning_rate": 2.9745307711236886e-05, + "loss": 0.1445, "step": 182160 }, { - "epoch": 0.81, - "learning_rate": 9.396663826734228e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.9744189168027564e-05, + "loss": 0.1484, "step": 182170 }, { - "epoch": 0.81, - "learning_rate": 9.394421774808305e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9743070624818236e-05, + "loss": 0.1492, "step": 182180 }, { - "epoch": 0.81, - "learning_rate": 9.392179722882383e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9741952081608913e-05, + "loss": 0.1461, "step": 182190 }, { - "epoch": 0.81, - "learning_rate": 9.38993767095646e-06, - "loss": 0.1487, + "epoch": 0.41, + "learning_rate": 2.9740833538399588e-05, + "loss": 0.1474, "step": 182200 }, { - "epoch": 0.81, - "learning_rate": 9.387695619030537e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9739714995190266e-05, + "loss": 0.1446, "step": 182210 }, { - "epoch": 0.81, - "learning_rate": 9.385453567104614e-06, - "loss": 0.1494, + "epoch": 0.41, + "learning_rate": 2.9738596451980944e-05, + "loss": 0.1522, "step": 182220 }, { - "epoch": 0.81, - "learning_rate": 9.383211515178692e-06, - "loss": 0.1492, + "epoch": 0.41, + "learning_rate": 2.9737477908771615e-05, + "loss": 0.1466, "step": 182230 }, { - "epoch": 0.81, - "learning_rate": 9.38096946325277e-06, - "loss": 0.1449, + "epoch": 0.41, + "learning_rate": 2.9736359365562293e-05, + "loss": 0.1479, "step": 182240 }, { - "epoch": 0.81, - "learning_rate": 9.378727411326847e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.9735240822352968e-05, + "loss": 0.148, "step": 182250 }, { - "epoch": 0.81, - "learning_rate": 9.376485359400924e-06, - "loss": 0.1524, + "epoch": 0.41, + "learning_rate": 2.9734122279143645e-05, + "loss": 0.1475, "step": 182260 }, { - "epoch": 0.81, - "learning_rate": 9.374243307475001e-06, - "loss": 0.1484, + "epoch": 0.41, + "learning_rate": 2.9733003735934323e-05, + "loss": 0.1483, "step": 182270 }, { - "epoch": 0.81, - "learning_rate": 9.372001255549078e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9731885192724995e-05, + "loss": 0.1462, "step": 182280 }, { - "epoch": 0.81, - "learning_rate": 9.369759203623155e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9730766649515672e-05, + "loss": 0.1491, "step": 182290 }, { - "epoch": 0.81, - "learning_rate": 9.367517151697232e-06, - "loss": 0.145, + "epoch": 0.41, + "learning_rate": 2.9729648106306347e-05, + "loss": 0.1548, "step": 182300 }, { - "epoch": 0.81, - "learning_rate": 9.365275099771311e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.9728529563097025e-05, + "loss": 0.1482, "step": 182310 }, { - "epoch": 0.81, - "learning_rate": 9.36303304784539e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.9727411019887703e-05, + "loss": 0.1502, "step": 182320 }, { - "epoch": 0.81, - "learning_rate": 9.360790995919467e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9726292476678374e-05, + "loss": 0.1461, "step": 182330 }, { - "epoch": 0.81, - "learning_rate": 9.358548943993544e-06, - "loss": 0.1472, + "epoch": 0.41, + "learning_rate": 2.9725173933469052e-05, + "loss": 0.1519, "step": 182340 }, { - "epoch": 0.81, - "learning_rate": 9.356306892067621e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9724055390259726e-05, + "loss": 0.1458, "step": 182350 }, { - "epoch": 0.81, - "learning_rate": 9.354064840141698e-06, - "loss": 0.1524, + "epoch": 0.41, + "learning_rate": 2.9722936847050404e-05, + "loss": 0.1478, "step": 182360 }, { - "epoch": 0.81, - "learning_rate": 9.351822788215775e-06, - "loss": 0.1494, + "epoch": 0.41, + "learning_rate": 2.9721818303841082e-05, + "loss": 0.1457, "step": 182370 }, { - "epoch": 0.81, - "learning_rate": 9.349580736289854e-06, - "loss": 0.1477, + "epoch": 0.41, + "learning_rate": 2.9720699760631753e-05, + "loss": 0.1537, "step": 182380 }, { - "epoch": 0.81, - "learning_rate": 9.34733868436393e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.971958121742243e-05, + "loss": 0.1501, "step": 182390 }, { - "epoch": 0.81, - "learning_rate": 9.345096632438008e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.9718462674213106e-05, + "loss": 0.1488, "step": 182400 }, { - "epoch": 0.81, - "learning_rate": 9.342854580512085e-06, - "loss": 0.1453, + "epoch": 0.41, + "learning_rate": 2.9717344131003784e-05, + "loss": 0.1431, "step": 182410 }, { - "epoch": 0.81, - "learning_rate": 9.340612528586162e-06, - "loss": 0.1417, + "epoch": 0.41, + "learning_rate": 2.9716225587794462e-05, + "loss": 0.1487, "step": 182420 }, { - "epoch": 0.81, - "learning_rate": 9.338370476660239e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.9715107044585133e-05, + "loss": 0.1503, "step": 182430 }, { - "epoch": 0.81, - "learning_rate": 9.336128424734317e-06, - "loss": 0.1447, + "epoch": 0.41, + "learning_rate": 2.971398850137581e-05, + "loss": 0.15, "step": 182440 }, { - "epoch": 0.81, - "learning_rate": 9.333886372808394e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.9712869958166485e-05, + "loss": 0.1431, "step": 182450 }, { - "epoch": 0.81, - "learning_rate": 9.331644320882473e-06, - "loss": 0.1433, + "epoch": 0.41, + "learning_rate": 2.9711751414957163e-05, + "loss": 0.147, "step": 182460 }, { - "epoch": 0.81, - "learning_rate": 9.32940226895655e-06, - "loss": 0.1454, + "epoch": 0.41, + "learning_rate": 2.9710632871747834e-05, + "loss": 0.1461, "step": 182470 }, { - "epoch": 0.81, - "learning_rate": 9.327160217030627e-06, - "loss": 0.1405, + "epoch": 0.41, + "learning_rate": 2.9709514328538512e-05, + "loss": 0.1475, "step": 182480 }, { - "epoch": 0.81, - "learning_rate": 9.324918165104704e-06, - "loss": 0.1432, + "epoch": 0.41, + "learning_rate": 2.970839578532919e-05, + "loss": 0.1517, "step": 182490 }, { - "epoch": 0.81, - "learning_rate": 9.322676113178781e-06, - "loss": 0.1492, + "epoch": 0.41, + "learning_rate": 2.970727724211986e-05, + "loss": 0.1535, "step": 182500 }, { - "epoch": 0.81, - "learning_rate": 9.320434061252858e-06, - "loss": 0.1449, + "epoch": 0.41, + "learning_rate": 2.9706158698910543e-05, + "loss": 0.1448, "step": 182510 }, { - "epoch": 0.81, - "learning_rate": 9.318192009326937e-06, - "loss": 0.147, + "epoch": 0.41, + "learning_rate": 2.9705040155701214e-05, + "loss": 0.1446, "step": 182520 }, { - "epoch": 0.81, - "learning_rate": 9.315949957401014e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9703921612491892e-05, + "loss": 0.1488, "step": 182530 }, { - "epoch": 0.81, - "learning_rate": 9.313707905475091e-06, - "loss": 0.1483, + "epoch": 0.41, + "learning_rate": 2.970280306928257e-05, + "loss": 0.1468, "step": 182540 }, { - "epoch": 0.81, - "learning_rate": 9.311465853549168e-06, - "loss": 0.1409, + "epoch": 0.41, + "learning_rate": 2.970168452607324e-05, + "loss": 0.1464, "step": 182550 }, { - "epoch": 0.81, - "learning_rate": 9.309223801623245e-06, - "loss": 0.1433, + "epoch": 0.41, + "learning_rate": 2.970056598286392e-05, + "loss": 0.1493, "step": 182560 }, { - "epoch": 0.82, - "learning_rate": 9.306981749697322e-06, - "loss": 0.1507, + "epoch": 0.41, + "learning_rate": 2.9699447439654593e-05, + "loss": 0.1441, "step": 182570 }, { - "epoch": 0.82, - "learning_rate": 9.304739697771401e-06, - "loss": 0.147, + "epoch": 0.41, + "learning_rate": 2.969832889644527e-05, + "loss": 0.1505, "step": 182580 }, { - "epoch": 0.82, - "learning_rate": 9.30249764584548e-06, - "loss": 0.1522, + "epoch": 0.41, + "learning_rate": 2.969721035323595e-05, + "loss": 0.1457, "step": 182590 }, { - "epoch": 0.82, - "learning_rate": 9.300255593919557e-06, - "loss": 0.1523, + "epoch": 0.41, + "learning_rate": 2.969609181002662e-05, + "loss": 0.1428, "step": 182600 }, { - "epoch": 0.82, - "learning_rate": 9.298013541993634e-06, - "loss": 0.1469, + "epoch": 0.41, + "learning_rate": 2.96949732668173e-05, + "loss": 0.1474, "step": 182610 }, { - "epoch": 0.82, - "learning_rate": 9.29577149006771e-06, - "loss": 0.1479, + "epoch": 0.41, + "learning_rate": 2.9693854723607973e-05, + "loss": 0.1469, "step": 182620 }, { - "epoch": 0.82, - "learning_rate": 9.293529438141788e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.969273618039865e-05, + "loss": 0.1478, "step": 182630 }, { - "epoch": 0.82, - "learning_rate": 9.291287386215865e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.969161763718933e-05, + "loss": 0.1443, "step": 182640 }, { - "epoch": 0.82, - "learning_rate": 9.289045334289942e-06, - "loss": 0.1405, + "epoch": 0.41, + "learning_rate": 2.969049909398e-05, + "loss": 0.1409, "step": 182650 }, { - "epoch": 0.82, - "learning_rate": 9.28680328236402e-06, - "loss": 0.1442, + "epoch": 0.41, + "learning_rate": 2.9689380550770678e-05, + "loss": 0.1394, "step": 182660 }, { - "epoch": 0.82, - "learning_rate": 9.284561230438097e-06, - "loss": 0.1499, + "epoch": 0.41, + "learning_rate": 2.9688262007561352e-05, + "loss": 0.1446, "step": 182670 }, { - "epoch": 0.82, - "learning_rate": 9.282319178512175e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.968714346435203e-05, + "loss": 0.1465, "step": 182680 }, { - "epoch": 0.82, - "learning_rate": 9.280077126586252e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9686024921142708e-05, + "loss": 0.1505, "step": 182690 }, { - "epoch": 0.82, - "learning_rate": 9.277835074660329e-06, - "loss": 0.149, + "epoch": 0.41, + "learning_rate": 2.968490637793338e-05, + "loss": 0.1483, "step": 182700 }, { - "epoch": 0.82, - "learning_rate": 9.275593022734407e-06, - "loss": 0.1451, + "epoch": 0.41, + "learning_rate": 2.9683787834724057e-05, + "loss": 0.1499, "step": 182710 }, { - "epoch": 0.82, - "learning_rate": 9.273350970808484e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.9682669291514732e-05, + "loss": 0.1465, "step": 182720 }, { - "epoch": 0.82, - "learning_rate": 9.271108918882563e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.968155074830541e-05, + "loss": 0.1461, "step": 182730 }, { - "epoch": 0.82, - "learning_rate": 9.26886686695664e-06, - "loss": 0.1403, + "epoch": 0.41, + "learning_rate": 2.9680432205096088e-05, + "loss": 0.1466, "step": 182740 }, { - "epoch": 0.82, - "learning_rate": 9.266624815030717e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.967931366188676e-05, + "loss": 0.1443, "step": 182750 }, { - "epoch": 0.82, - "learning_rate": 9.264382763104794e-06, + "epoch": 0.41, + "learning_rate": 2.9678195118677437e-05, "loss": 0.1492, "step": 182760 }, { - "epoch": 0.82, - "learning_rate": 9.262140711178871e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.967707657546811e-05, + "loss": 0.1459, "step": 182770 }, { - "epoch": 0.82, - "learning_rate": 9.259898659252948e-06, - "loss": 0.1494, + "epoch": 0.41, + "learning_rate": 2.967595803225879e-05, + "loss": 0.1475, "step": 182780 }, { - "epoch": 0.82, - "learning_rate": 9.257656607327025e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.967483948904946e-05, + "loss": 0.1484, "step": 182790 }, { - "epoch": 0.82, - "learning_rate": 9.255414555401104e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.967372094584014e-05, + "loss": 0.1484, "step": 182800 }, { - "epoch": 0.82, - "learning_rate": 9.253172503475181e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9672602402630816e-05, + "loss": 0.1492, "step": 182810 }, { - "epoch": 0.82, - "learning_rate": 9.250930451549258e-06, - "loss": 0.1413, + "epoch": 0.41, + "learning_rate": 2.967148385942149e-05, + "loss": 0.148, "step": 182820 }, { - "epoch": 0.82, - "learning_rate": 9.248688399623335e-06, - "loss": 0.1436, + "epoch": 0.41, + "learning_rate": 2.967036531621217e-05, + "loss": 0.1444, "step": 182830 }, { - "epoch": 0.82, - "learning_rate": 9.246446347697412e-06, - "loss": 0.1433, + "epoch": 0.41, + "learning_rate": 2.966924677300284e-05, + "loss": 0.1465, "step": 182840 }, { - "epoch": 0.82, - "learning_rate": 9.24420429577149e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9668128229793518e-05, + "loss": 0.1473, "step": 182850 }, { - "epoch": 0.82, - "learning_rate": 9.24196224384557e-06, - "loss": 0.1428, + "epoch": 0.41, + "learning_rate": 2.9667009686584196e-05, + "loss": 0.1484, "step": 182860 }, { - "epoch": 0.82, - "learning_rate": 9.239720191919646e-06, - "loss": 0.1484, + "epoch": 0.41, + "learning_rate": 2.966589114337487e-05, + "loss": 0.1418, "step": 182870 }, { - "epoch": 0.82, - "learning_rate": 9.237478139993723e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.9664772600165548e-05, + "loss": 0.144, "step": 182880 }, { - "epoch": 0.82, - "learning_rate": 9.2352360880678e-06, - "loss": 0.1499, + "epoch": 0.41, + "learning_rate": 2.966365405695622e-05, + "loss": 0.1461, "step": 182890 }, { - "epoch": 0.82, - "learning_rate": 9.232994036141878e-06, - "loss": 0.1483, + "epoch": 0.41, + "learning_rate": 2.9662535513746897e-05, + "loss": 0.1481, "step": 182900 }, { - "epoch": 0.82, - "learning_rate": 9.230751984215955e-06, - "loss": 0.1401, + "epoch": 0.41, + "learning_rate": 2.9661416970537575e-05, + "loss": 0.1414, "step": 182910 }, { - "epoch": 0.82, - "learning_rate": 9.228509932290032e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9660298427328246e-05, + "loss": 0.1425, "step": 182920 }, { - "epoch": 0.82, - "learning_rate": 9.22626788036411e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.9659179884118928e-05, + "loss": 0.145, "step": 182930 }, { - "epoch": 0.82, - "learning_rate": 9.224025828438187e-06, - "loss": 0.1491, + "epoch": 0.41, + "learning_rate": 2.96580613409096e-05, + "loss": 0.1501, "step": 182940 }, { - "epoch": 0.82, - "learning_rate": 9.221783776512264e-06, - "loss": 0.1475, + "epoch": 0.41, + "learning_rate": 2.9656942797700277e-05, + "loss": 0.1435, "step": 182950 }, { - "epoch": 0.82, - "learning_rate": 9.219541724586341e-06, - "loss": 0.1523, + "epoch": 0.41, + "learning_rate": 2.9655824254490955e-05, + "loss": 0.1473, "step": 182960 }, { - "epoch": 0.82, - "learning_rate": 9.217299672660418e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9654705711281626e-05, + "loss": 0.1426, "step": 182970 }, { - "epoch": 0.82, - "learning_rate": 9.215057620734497e-06, - "loss": 0.1492, + "epoch": 0.41, + "learning_rate": 2.9653587168072304e-05, + "loss": 0.1504, "step": 182980 }, { - "epoch": 0.82, - "learning_rate": 9.212815568808574e-06, - "loss": 0.1484, + "epoch": 0.41, + "learning_rate": 2.9652468624862978e-05, + "loss": 0.1453, "step": 182990 }, { - "epoch": 0.82, - "learning_rate": 9.210573516882653e-06, - "loss": 0.1435, + "epoch": 0.41, + "learning_rate": 2.9651350081653656e-05, + "loss": 0.1453, "step": 183000 }, { - "epoch": 0.82, - "learning_rate": 9.20833146495673e-06, - "loss": 0.1409, + "epoch": 0.41, + "learning_rate": 2.9650231538444334e-05, + "loss": 0.1506, "step": 183010 }, { - "epoch": 0.82, - "learning_rate": 9.206089413030807e-06, - "loss": 0.1416, + "epoch": 0.41, + "learning_rate": 2.9649112995235005e-05, + "loss": 0.142, "step": 183020 }, { - "epoch": 0.82, - "learning_rate": 9.203847361104884e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9647994452025683e-05, + "loss": 0.1481, "step": 183030 }, { - "epoch": 0.82, - "learning_rate": 9.201605309178961e-06, - "loss": 0.1452, + "epoch": 0.41, + "learning_rate": 2.9646875908816358e-05, + "loss": 0.1459, "step": 183040 }, { - "epoch": 0.82, - "learning_rate": 9.199363257253038e-06, - "loss": 0.1419, + "epoch": 0.41, + "learning_rate": 2.9645757365607036e-05, + "loss": 0.1531, "step": 183050 }, { - "epoch": 0.82, - "learning_rate": 9.197121205327115e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9644638822397714e-05, + "loss": 0.1455, "step": 183060 }, { - "epoch": 0.82, - "learning_rate": 9.194879153401194e-06, - "loss": 0.1455, + "epoch": 0.41, + "learning_rate": 2.9643520279188385e-05, + "loss": 0.1457, "step": 183070 }, { - "epoch": 0.82, - "learning_rate": 9.19263710147527e-06, - "loss": 0.1519, + "epoch": 0.41, + "learning_rate": 2.9642401735979063e-05, + "loss": 0.1452, "step": 183080 }, { - "epoch": 0.82, - "learning_rate": 9.190395049549348e-06, - "loss": 0.1508, + "epoch": 0.41, + "learning_rate": 2.9641283192769737e-05, + "loss": 0.1447, "step": 183090 }, { - "epoch": 0.82, - "learning_rate": 9.188152997623425e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9640164649560415e-05, + "loss": 0.1421, "step": 183100 }, { - "epoch": 0.82, - "learning_rate": 9.185910945697502e-06, - "loss": 0.1486, + "epoch": 0.41, + "learning_rate": 2.9639046106351086e-05, + "loss": 0.148, "step": 183110 }, { - "epoch": 0.82, - "learning_rate": 9.18366889377158e-06, - "loss": 0.1467, + "epoch": 0.41, + "learning_rate": 2.9637927563141764e-05, + "loss": 0.1438, "step": 183120 }, { - "epoch": 0.82, - "learning_rate": 9.181426841845658e-06, - "loss": 0.1477, + "epoch": 0.41, + "learning_rate": 2.9636809019932442e-05, + "loss": 0.1471, "step": 183130 }, { - "epoch": 0.82, - "learning_rate": 9.179184789919736e-06, - "loss": 0.1463, + "epoch": 0.41, + "learning_rate": 2.9635690476723117e-05, + "loss": 0.1513, "step": 183140 }, { - "epoch": 0.82, - "learning_rate": 9.176942737993813e-06, - "loss": 0.1403, + "epoch": 0.41, + "learning_rate": 2.9634571933513795e-05, + "loss": 0.1465, "step": 183150 }, { - "epoch": 0.82, - "learning_rate": 9.17470068606789e-06, - "loss": 0.1503, + "epoch": 0.41, + "learning_rate": 2.9633453390304466e-05, + "loss": 0.14, "step": 183160 }, { - "epoch": 0.82, - "learning_rate": 9.172458634141967e-06, - "loss": 0.141, + "epoch": 0.41, + "learning_rate": 2.9632334847095144e-05, + "loss": 0.1464, "step": 183170 }, { - "epoch": 0.82, - "learning_rate": 9.170216582216044e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.963121630388582e-05, + "loss": 0.1481, "step": 183180 }, { - "epoch": 0.82, - "learning_rate": 9.167974530290121e-06, - "loss": 0.1478, + "epoch": 0.41, + "learning_rate": 2.9630097760676496e-05, + "loss": 0.1474, "step": 183190 }, { - "epoch": 0.82, - "learning_rate": 9.165732478364198e-06, - "loss": 0.1418, + "epoch": 0.41, + "learning_rate": 2.9628979217467174e-05, + "loss": 0.1445, "step": 183200 }, { - "epoch": 0.82, - "learning_rate": 9.163490426438277e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9627860674257845e-05, + "loss": 0.1493, "step": 183210 }, { - "epoch": 0.82, - "learning_rate": 9.161248374512354e-06, - "loss": 0.1434, + "epoch": 0.41, + "learning_rate": 2.9626742131048523e-05, + "loss": 0.1444, "step": 183220 }, { - "epoch": 0.82, - "learning_rate": 9.159006322586431e-06, - "loss": 0.1508, + "epoch": 0.41, + "learning_rate": 2.96256235878392e-05, + "loss": 0.1461, "step": 183230 }, { - "epoch": 0.82, - "learning_rate": 9.156764270660508e-06, - "loss": 0.1467, + "epoch": 0.41, + "learning_rate": 2.9624505044629876e-05, + "loss": 0.1475, "step": 183240 }, { - "epoch": 0.82, - "learning_rate": 9.154522218734587e-06, - "loss": 0.1411, + "epoch": 0.41, + "learning_rate": 2.9623386501420554e-05, + "loss": 0.1432, "step": 183250 }, { - "epoch": 0.82, - "learning_rate": 9.152280166808664e-06, - "loss": 0.1407, + "epoch": 0.41, + "learning_rate": 2.9622267958211225e-05, + "loss": 0.1494, "step": 183260 }, { - "epoch": 0.82, - "learning_rate": 9.150038114882741e-06, - "loss": 0.1449, + "epoch": 0.41, + "learning_rate": 2.9621149415001903e-05, + "loss": 0.1482, "step": 183270 }, { - "epoch": 0.82, - "learning_rate": 9.14779606295682e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.9620142726113508e-05, + "loss": 0.1501, "step": 183280 }, { - "epoch": 0.82, - "learning_rate": 9.145554011030897e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.9619024182904186e-05, + "loss": 0.1442, "step": 183290 }, { - "epoch": 0.82, - "learning_rate": 9.143311959104974e-06, - "loss": 0.147, + "epoch": 0.41, + "learning_rate": 2.9617905639694864e-05, + "loss": 0.1479, "step": 183300 }, { - "epoch": 0.82, - "learning_rate": 9.14106990717905e-06, - "loss": 0.1409, + "epoch": 0.41, + "learning_rate": 2.961678709648554e-05, + "loss": 0.1473, "step": 183310 }, { - "epoch": 0.82, - "learning_rate": 9.138827855253128e-06, - "loss": 0.1442, + "epoch": 0.41, + "learning_rate": 2.9615668553276216e-05, + "loss": 0.1512, "step": 183320 }, { - "epoch": 0.82, - "learning_rate": 9.136585803327205e-06, - "loss": 0.1442, + "epoch": 0.41, + "learning_rate": 2.9614550010066888e-05, + "loss": 0.1481, "step": 183330 }, { - "epoch": 0.82, - "learning_rate": 9.134343751401282e-06, - "loss": 0.1456, + "epoch": 0.41, + "learning_rate": 2.9613431466857565e-05, + "loss": 0.1472, "step": 183340 }, { - "epoch": 0.82, - "learning_rate": 9.13210169947536e-06, - "loss": 0.1428, + "epoch": 0.41, + "learning_rate": 2.9612312923648243e-05, + "loss": 0.1433, "step": 183350 }, { - "epoch": 0.82, - "learning_rate": 9.129859647549438e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.9611194380438918e-05, + "loss": 0.1472, "step": 183360 }, { - "epoch": 0.82, - "learning_rate": 9.127617595623515e-06, - "loss": 0.1492, + "epoch": 0.41, + "learning_rate": 2.9610075837229596e-05, + "loss": 0.1459, "step": 183370 }, { - "epoch": 0.82, - "learning_rate": 9.125375543697592e-06, - "loss": 0.1427, + "epoch": 0.41, + "learning_rate": 2.9608957294020267e-05, + "loss": 0.1522, "step": 183380 }, { - "epoch": 0.82, - "learning_rate": 9.12313349177167e-06, - "loss": 0.1398, + "epoch": 0.41, + "learning_rate": 2.9607838750810945e-05, + "loss": 0.1498, "step": 183390 }, { - "epoch": 0.82, - "learning_rate": 9.120891439845747e-06, - "loss": 0.1421, + "epoch": 0.41, + "learning_rate": 2.9606720207601623e-05, + "loss": 0.1498, "step": 183400 }, { - "epoch": 0.82, - "learning_rate": 9.118649387919824e-06, - "loss": 0.1425, + "epoch": 0.41, + "learning_rate": 2.9605601664392297e-05, + "loss": 0.1501, "step": 183410 }, { - "epoch": 0.82, - "learning_rate": 9.116407335993903e-06, - "loss": 0.1408, + "epoch": 0.41, + "learning_rate": 2.9604483121182975e-05, + "loss": 0.1495, "step": 183420 }, { - "epoch": 0.82, - "learning_rate": 9.114389489260573e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.9603364577973646e-05, + "loss": 0.1461, "step": 183430 }, { - "epoch": 0.82, - "learning_rate": 9.11214743733465e-06, - "loss": 0.1455, + "epoch": 0.41, + "learning_rate": 2.9602246034764324e-05, + "loss": 0.1456, "step": 183440 }, { - "epoch": 0.82, - "learning_rate": 9.109905385408727e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9601127491555e-05, + "loss": 0.1452, "step": 183450 }, { - "epoch": 0.82, - "learning_rate": 9.107663333482804e-06, - "loss": 0.1435, + "epoch": 0.41, + "learning_rate": 2.9600008948345677e-05, + "loss": 0.1458, "step": 183460 }, { - "epoch": 0.82, - "learning_rate": 9.10542128155688e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9598890405136355e-05, + "loss": 0.1475, "step": 183470 }, { - "epoch": 0.82, - "learning_rate": 9.10317922963096e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9597771861927026e-05, + "loss": 0.1456, "step": 183480 }, { - "epoch": 0.82, - "learning_rate": 9.100937177705036e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9596653318717704e-05, + "loss": 0.1425, "step": 183490 }, { - "epoch": 0.82, - "learning_rate": 9.098695125779113e-06, - "loss": 0.1451, + "epoch": 0.41, + "learning_rate": 2.9595534775508375e-05, + "loss": 0.1434, "step": 183500 }, { - "epoch": 0.82, - "learning_rate": 9.09645307385319e-06, - "loss": 0.1431, + "epoch": 0.41, + "learning_rate": 2.9594416232299056e-05, + "loss": 0.1471, "step": 183510 }, { - "epoch": 0.82, - "learning_rate": 9.094211021927267e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9593297689089734e-05, + "loss": 0.1454, "step": 183520 }, { - "epoch": 0.82, - "learning_rate": 9.091968970001344e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.9592179145880405e-05, + "loss": 0.1461, "step": 183530 }, { - "epoch": 0.82, - "learning_rate": 9.089726918075423e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9591060602671083e-05, + "loss": 0.1445, "step": 183540 }, { - "epoch": 0.82, - "learning_rate": 9.0874848661495e-06, - "loss": 0.1449, + "epoch": 0.41, + "learning_rate": 2.9589942059461755e-05, + "loss": 0.1442, "step": 183550 }, { - "epoch": 0.82, - "learning_rate": 9.085242814223579e-06, - "loss": 0.1472, + "epoch": 0.41, + "learning_rate": 2.9588823516252432e-05, + "loss": 0.1444, "step": 183560 }, { - "epoch": 0.82, - "learning_rate": 9.083000762297656e-06, - "loss": 0.1485, + "epoch": 0.41, + "learning_rate": 2.9587704973043114e-05, + "loss": 0.1422, "step": 183570 }, { - "epoch": 0.82, - "learning_rate": 9.080758710371733e-06, - "loss": 0.1432, + "epoch": 0.41, + "learning_rate": 2.9586586429833785e-05, + "loss": 0.1453, "step": 183580 }, { - "epoch": 0.82, - "learning_rate": 9.07851665844581e-06, - "loss": 0.1487, + "epoch": 0.41, + "learning_rate": 2.9585467886624463e-05, + "loss": 0.1449, "step": 183590 }, { - "epoch": 0.82, - "learning_rate": 9.076274606519887e-06, - "loss": 0.1447, + "epoch": 0.41, + "learning_rate": 2.9584349343415134e-05, + "loss": 0.1478, "step": 183600 }, { - "epoch": 0.82, - "learning_rate": 9.074032554593964e-06, - "loss": 0.1379, + "epoch": 0.41, + "learning_rate": 2.9583230800205812e-05, + "loss": 0.147, "step": 183610 }, { - "epoch": 0.82, - "learning_rate": 9.071790502668043e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.958211225699649e-05, + "loss": 0.1441, "step": 183620 }, { - "epoch": 0.82, - "learning_rate": 9.06954845074212e-06, - "loss": 0.1468, + "epoch": 0.41, + "learning_rate": 2.9580993713787164e-05, + "loss": 0.1536, "step": 183630 }, { - "epoch": 0.82, - "learning_rate": 9.067306398816197e-06, - "loss": 0.1435, + "epoch": 0.41, + "learning_rate": 2.9579875170577842e-05, + "loss": 0.1434, "step": 183640 }, { - "epoch": 0.82, - "learning_rate": 9.065064346890274e-06, - "loss": 0.149, + "epoch": 0.41, + "learning_rate": 2.9578756627368513e-05, + "loss": 0.1512, "step": 183650 }, { - "epoch": 0.82, - "learning_rate": 9.062822294964351e-06, - "loss": 0.1459, + "epoch": 0.41, + "learning_rate": 2.957763808415919e-05, + "loss": 0.148, "step": 183660 }, { - "epoch": 0.82, - "learning_rate": 9.060580243038428e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.957651954094987e-05, + "loss": 0.149, "step": 183670 }, { - "epoch": 0.82, - "learning_rate": 9.058338191112507e-06, - "loss": 0.1499, + "epoch": 0.41, + "learning_rate": 2.9575400997740544e-05, + "loss": 0.1453, "step": 183680 }, { - "epoch": 0.82, - "learning_rate": 9.056096139186585e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9574282454531222e-05, + "loss": 0.1494, "step": 183690 }, { - "epoch": 0.82, - "learning_rate": 9.053854087260662e-06, - "loss": 0.1419, + "epoch": 0.41, + "learning_rate": 2.9573163911321893e-05, + "loss": 0.1449, "step": 183700 }, { - "epoch": 0.82, - "learning_rate": 9.05161203533474e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.957204536811257e-05, + "loss": 0.1478, "step": 183710 }, { - "epoch": 0.82, - "learning_rate": 9.049369983408816e-06, - "loss": 0.1399, + "epoch": 0.41, + "learning_rate": 2.957092682490325e-05, + "loss": 0.1482, "step": 183720 }, { - "epoch": 0.82, - "learning_rate": 9.047127931482893e-06, - "loss": 0.1409, + "epoch": 0.41, + "learning_rate": 2.9569808281693923e-05, + "loss": 0.1497, "step": 183730 }, { - "epoch": 0.82, - "learning_rate": 9.04488587955697e-06, - "loss": 0.1456, + "epoch": 0.41, + "learning_rate": 2.95686897384846e-05, + "loss": 0.1448, "step": 183740 }, { - "epoch": 0.82, - "learning_rate": 9.04264382763105e-06, - "loss": 0.1431, + "epoch": 0.41, + "learning_rate": 2.9567571195275272e-05, + "loss": 0.1503, "step": 183750 }, { - "epoch": 0.82, - "learning_rate": 9.040401775705126e-06, - "loss": 0.1401, + "epoch": 0.41, + "learning_rate": 2.956645265206595e-05, + "loss": 0.1452, "step": 183760 }, { - "epoch": 0.82, - "learning_rate": 9.038159723779203e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9565334108856625e-05, + "loss": 0.1481, "step": 183770 }, { - "epoch": 0.82, - "learning_rate": 9.03591767185328e-06, - "loss": 0.1508, + "epoch": 0.41, + "learning_rate": 2.9564215565647303e-05, + "loss": 0.1485, "step": 183780 }, { - "epoch": 0.82, - "learning_rate": 9.033675619927357e-06, - "loss": 0.1544, + "epoch": 0.41, + "learning_rate": 2.956309702243798e-05, + "loss": 0.1489, "step": 183790 }, { - "epoch": 0.82, - "learning_rate": 9.031433568001434e-06, - "loss": 0.1396, + "epoch": 0.41, + "learning_rate": 2.9561978479228652e-05, + "loss": 0.1447, "step": 183800 }, { - "epoch": 0.82, - "learning_rate": 9.029191516075513e-06, - "loss": 0.1466, + "epoch": 0.41, + "learning_rate": 2.956085993601933e-05, + "loss": 0.1498, "step": 183810 }, { - "epoch": 0.82, - "learning_rate": 9.02694946414959e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9559741392810004e-05, + "loss": 0.1485, "step": 183820 }, { - "epoch": 0.82, - "learning_rate": 9.024707412223669e-06, - "loss": 0.1483, + "epoch": 0.41, + "learning_rate": 2.9558622849600682e-05, + "loss": 0.1522, "step": 183830 }, { - "epoch": 0.82, - "learning_rate": 9.022465360297746e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.955750430639136e-05, + "loss": 0.149, "step": 183840 }, { - "epoch": 0.82, - "learning_rate": 9.020223308371823e-06, - "loss": 0.1469, + "epoch": 0.41, + "learning_rate": 2.955638576318203e-05, + "loss": 0.1473, "step": 183850 }, { - "epoch": 0.82, - "learning_rate": 9.0179812564459e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.955526721997271e-05, + "loss": 0.1427, "step": 183860 }, { - "epoch": 0.82, - "learning_rate": 9.015739204519977e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9554148676763384e-05, + "loss": 0.1428, "step": 183870 }, { - "epoch": 0.82, - "learning_rate": 9.013497152594054e-06, - "loss": 0.1437, + "epoch": 0.41, + "learning_rate": 2.9553030133554062e-05, + "loss": 0.1494, "step": 183880 }, { - "epoch": 0.82, - "learning_rate": 9.011255100668133e-06, - "loss": 0.145, + "epoch": 0.41, + "learning_rate": 2.955191159034474e-05, + "loss": 0.1486, "step": 183890 }, { - "epoch": 0.82, - "learning_rate": 9.00901304874221e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.955079304713541e-05, + "loss": 0.1498, "step": 183900 }, { - "epoch": 0.82, - "learning_rate": 9.006770996816287e-06, - "loss": 0.1445, + "epoch": 0.41, + "learning_rate": 2.954967450392609e-05, + "loss": 0.1476, "step": 183910 }, { - "epoch": 0.82, - "learning_rate": 9.004528944890364e-06, - "loss": 0.1484, + "epoch": 0.41, + "learning_rate": 2.9548555960716763e-05, + "loss": 0.1451, "step": 183920 }, { - "epoch": 0.82, - "learning_rate": 9.00228689296444e-06, - "loss": 0.1469, + "epoch": 0.41, + "learning_rate": 2.954743741750744e-05, + "loss": 0.1498, "step": 183930 }, { - "epoch": 0.82, - "learning_rate": 9.000044841038518e-06, - "loss": 0.144, + "epoch": 0.41, + "learning_rate": 2.954631887429812e-05, + "loss": 0.1484, "step": 183940 }, { - "epoch": 0.82, - "learning_rate": 8.997802789112596e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.954520033108879e-05, + "loss": 0.1509, "step": 183950 }, { - "epoch": 0.82, - "learning_rate": 8.995560737186675e-06, - "loss": 0.1453, + "epoch": 0.41, + "learning_rate": 2.9544081787879468e-05, + "loss": 0.1422, "step": 183960 }, { - "epoch": 0.82, - "learning_rate": 8.993318685260752e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.954296324467014e-05, + "loss": 0.1524, "step": 183970 }, { - "epoch": 0.82, - "learning_rate": 8.99107663333483e-06, - "loss": 0.1481, + "epoch": 0.41, + "learning_rate": 2.954184470146082e-05, + "loss": 0.1432, "step": 183980 }, { - "epoch": 0.82, - "learning_rate": 8.988834581408906e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.95407261582515e-05, + "loss": 0.1447, "step": 183990 }, { - "epoch": 0.82, - "learning_rate": 8.986592529482983e-06, - "loss": 0.1527, + "epoch": 0.41, + "learning_rate": 2.953960761504217e-05, + "loss": 0.142, "step": 184000 }, { - "epoch": 0.82, - "learning_rate": 8.98435047755706e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9538489071832848e-05, + "loss": 0.1511, "step": 184010 }, { - "epoch": 0.82, - "learning_rate": 8.982108425631137e-06, - "loss": 0.1487, + "epoch": 0.41, + "learning_rate": 2.953737052862352e-05, + "loss": 0.1473, "step": 184020 }, { - "epoch": 0.82, - "learning_rate": 8.979866373705216e-06, - "loss": 0.1433, + "epoch": 0.41, + "learning_rate": 2.9536251985414197e-05, + "loss": 0.1512, "step": 184030 }, { - "epoch": 0.82, - "learning_rate": 8.977624321779293e-06, - "loss": 0.1402, + "epoch": 0.41, + "learning_rate": 2.9535133442204878e-05, + "loss": 0.1432, "step": 184040 }, { - "epoch": 0.82, - "learning_rate": 8.97538226985337e-06, - "loss": 0.142, + "epoch": 0.41, + "learning_rate": 2.953401489899555e-05, + "loss": 0.1491, "step": 184050 }, { - "epoch": 0.82, - "learning_rate": 8.973140217927447e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9532896355786227e-05, + "loss": 0.1471, "step": 184060 }, { - "epoch": 0.82, - "learning_rate": 8.970898166001524e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.95317778125769e-05, + "loss": 0.1453, "step": 184070 }, { - "epoch": 0.82, - "learning_rate": 8.968656114075603e-06, - "loss": 0.1393, + "epoch": 0.41, + "learning_rate": 2.9530659269367576e-05, + "loss": 0.1505, "step": 184080 }, { - "epoch": 0.82, - "learning_rate": 8.96641406214968e-06, - "loss": 0.1441, + "epoch": 0.41, + "learning_rate": 2.952954072615825e-05, + "loss": 0.1457, "step": 184090 }, { - "epoch": 0.82, - "learning_rate": 8.964172010223759e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.952842218294893e-05, + "loss": 0.147, "step": 184100 }, { - "epoch": 0.82, - "learning_rate": 8.962154163490426e-06, - "loss": 0.1477, + "epoch": 0.41, + "learning_rate": 2.9527303639739607e-05, + "loss": 0.145, "step": 184110 }, { - "epoch": 0.82, - "learning_rate": 8.959912111564505e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9526185096530278e-05, + "loss": 0.1458, "step": 184120 }, { - "epoch": 0.82, - "learning_rate": 8.957670059638582e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9525066553320956e-05, + "loss": 0.1468, "step": 184130 }, { - "epoch": 0.82, - "learning_rate": 8.955428007712659e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.952394801011163e-05, + "loss": 0.1487, "step": 184140 }, { - "epoch": 0.82, - "learning_rate": 8.953185955786736e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9522829466902308e-05, + "loss": 0.1476, "step": 184150 }, { - "epoch": 0.82, - "learning_rate": 8.950943903860815e-06, - "loss": 0.143, + "epoch": 0.41, + "learning_rate": 2.9521710923692986e-05, + "loss": 0.1481, "step": 184160 }, { - "epoch": 0.82, - "learning_rate": 8.948701851934892e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.9520592380483657e-05, + "loss": 0.1484, "step": 184170 }, { - "epoch": 0.82, - "learning_rate": 8.946459800008969e-06, - "loss": 0.1454, + "epoch": 0.41, + "learning_rate": 2.9519473837274335e-05, + "loss": 0.1484, "step": 184180 }, { - "epoch": 0.82, - "learning_rate": 8.944217748083046e-06, - "loss": 0.1423, + "epoch": 0.41, + "learning_rate": 2.951835529406501e-05, + "loss": 0.152, "step": 184190 }, { - "epoch": 0.82, - "learning_rate": 8.941975696157123e-06, - "loss": 0.1479, + "epoch": 0.41, + "learning_rate": 2.9517236750855688e-05, + "loss": 0.145, "step": 184200 }, { - "epoch": 0.82, - "learning_rate": 8.9397336442312e-06, - "loss": 0.1498, + "epoch": 0.41, + "learning_rate": 2.9516118207646366e-05, + "loss": 0.1488, "step": 184210 }, { - "epoch": 0.82, - "learning_rate": 8.937491592305277e-06, - "loss": 0.1433, + "epoch": 0.41, + "learning_rate": 2.9514999664437037e-05, + "loss": 0.1444, "step": 184220 }, { - "epoch": 0.82, - "learning_rate": 8.935249540379356e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.9513881121227715e-05, + "loss": 0.1458, "step": 184230 }, { - "epoch": 0.82, - "learning_rate": 8.933007488453433e-06, - "loss": 0.1379, + "epoch": 0.41, + "learning_rate": 2.951276257801839e-05, + "loss": 0.1428, "step": 184240 }, { - "epoch": 0.82, - "learning_rate": 8.930765436527511e-06, - "loss": 0.1431, + "epoch": 0.41, + "learning_rate": 2.9511644034809067e-05, + "loss": 0.1515, "step": 184250 }, { - "epoch": 0.82, - "learning_rate": 8.928523384601588e-06, - "loss": 0.1396, + "epoch": 0.41, + "learning_rate": 2.9510525491599745e-05, + "loss": 0.1469, "step": 184260 }, { - "epoch": 0.82, - "learning_rate": 8.926281332675666e-06, - "loss": 0.1459, + "epoch": 0.41, + "learning_rate": 2.9509406948390416e-05, + "loss": 0.1498, "step": 184270 }, { - "epoch": 0.82, - "learning_rate": 8.924039280749743e-06, - "loss": 0.1447, + "epoch": 0.41, + "learning_rate": 2.9508288405181094e-05, + "loss": 0.1526, "step": 184280 }, { - "epoch": 0.82, - "learning_rate": 8.92179722882382e-06, - "loss": 0.1416, + "epoch": 0.41, + "learning_rate": 2.950716986197177e-05, + "loss": 0.1445, "step": 184290 }, { - "epoch": 0.82, - "learning_rate": 8.919555176897898e-06, - "loss": 0.1439, + "epoch": 0.41, + "learning_rate": 2.9506051318762447e-05, + "loss": 0.1478, "step": 184300 }, { - "epoch": 0.82, - "learning_rate": 8.917313124971975e-06, - "loss": 0.1485, + "epoch": 0.41, + "learning_rate": 2.9504932775553125e-05, + "loss": 0.144, "step": 184310 }, { - "epoch": 0.82, - "learning_rate": 8.915071073046052e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9503814232343796e-05, + "loss": 0.1447, "step": 184320 }, { - "epoch": 0.82, - "learning_rate": 8.91282902112013e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9502695689134474e-05, + "loss": 0.1499, "step": 184330 }, { - "epoch": 0.82, - "learning_rate": 8.910586969194206e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9501577145925148e-05, + "loss": 0.1462, "step": 184340 }, { - "epoch": 0.82, - "learning_rate": 8.908344917268283e-06, - "loss": 0.1409, + "epoch": 0.41, + "learning_rate": 2.9500458602715826e-05, + "loss": 0.145, "step": 184350 }, { - "epoch": 0.82, - "learning_rate": 8.90610286534236e-06, - "loss": 0.1414, + "epoch": 0.41, + "learning_rate": 2.9499340059506504e-05, + "loss": 0.1472, "step": 184360 }, { - "epoch": 0.82, - "learning_rate": 8.903860813416439e-06, - "loss": 0.1435, + "epoch": 0.41, + "learning_rate": 2.9498221516297175e-05, + "loss": 0.1448, "step": 184370 }, { - "epoch": 0.82, - "learning_rate": 8.901618761490516e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9497102973087853e-05, + "loss": 0.1507, "step": 184380 }, { - "epoch": 0.82, - "learning_rate": 8.899376709564595e-06, - "loss": 0.1453, + "epoch": 0.41, + "learning_rate": 2.9495984429878524e-05, + "loss": 0.1478, "step": 184390 }, { - "epoch": 0.82, - "learning_rate": 8.897134657638672e-06, - "loss": 0.1462, + "epoch": 0.41, + "learning_rate": 2.9494865886669206e-05, + "loss": 0.1486, "step": 184400 }, { - "epoch": 0.82, - "learning_rate": 8.894892605712749e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9493747343459877e-05, + "loss": 0.1446, "step": 184410 }, { - "epoch": 0.82, - "learning_rate": 8.892650553786826e-06, - "loss": 0.1455, + "epoch": 0.41, + "learning_rate": 2.9492628800250555e-05, + "loss": 0.1426, "step": 184420 }, { - "epoch": 0.82, - "learning_rate": 8.890408501860903e-06, - "loss": 0.1442, + "epoch": 0.41, + "learning_rate": 2.9491510257041233e-05, + "loss": 0.1492, "step": 184430 }, { - "epoch": 0.82, - "learning_rate": 8.888166449934982e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.9490391713831904e-05, + "loss": 0.1453, "step": 184440 }, { - "epoch": 0.82, - "learning_rate": 8.885924398009059e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.948927317062258e-05, + "loss": 0.1479, "step": 184450 }, { - "epoch": 0.82, - "learning_rate": 8.883682346083136e-06, - "loss": 0.1454, + "epoch": 0.41, + "learning_rate": 2.9488154627413256e-05, + "loss": 0.1519, "step": 184460 }, { - "epoch": 0.82, - "learning_rate": 8.881440294157213e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9487036084203934e-05, + "loss": 0.1484, "step": 184470 }, { - "epoch": 0.82, - "learning_rate": 8.87919824223129e-06, - "loss": 0.1428, + "epoch": 0.41, + "learning_rate": 2.9485917540994612e-05, + "loss": 0.147, "step": 184480 }, { - "epoch": 0.82, - "learning_rate": 8.876956190305367e-06, - "loss": 0.1399, + "epoch": 0.41, + "learning_rate": 2.9484798997785283e-05, + "loss": 0.147, "step": 184490 }, { - "epoch": 0.82, - "learning_rate": 8.874714138379444e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.948368045457596e-05, + "loss": 0.1467, "step": 184500 }, { - "epoch": 0.82, - "learning_rate": 8.872472086453523e-06, - "loss": 0.1419, + "epoch": 0.41, + "learning_rate": 2.9482561911366636e-05, + "loss": 0.1483, "step": 184510 }, { - "epoch": 0.82, - "learning_rate": 8.870230034527601e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9481443368157314e-05, + "loss": 0.1444, "step": 184520 }, { - "epoch": 0.82, - "learning_rate": 8.867987982601678e-06, - "loss": 0.1403, + "epoch": 0.41, + "learning_rate": 2.948032482494799e-05, + "loss": 0.1445, "step": 184530 }, { - "epoch": 0.82, - "learning_rate": 8.865745930675755e-06, - "loss": 0.148, + "epoch": 0.41, + "learning_rate": 2.9479206281738663e-05, + "loss": 0.1417, "step": 184540 }, { - "epoch": 0.82, - "learning_rate": 8.863503878749832e-06, - "loss": 0.1491, + "epoch": 0.41, + "learning_rate": 2.947808773852934e-05, + "loss": 0.1489, "step": 184550 }, { - "epoch": 0.82, - "learning_rate": 8.86126182682391e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.9476969195320015e-05, + "loss": 0.1472, "step": 184560 }, { - "epoch": 0.82, - "learning_rate": 8.859019774897986e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9475850652110693e-05, + "loss": 0.1481, "step": 184570 }, { - "epoch": 0.82, - "learning_rate": 8.856777722972065e-06, - "loss": 0.1404, + "epoch": 0.41, + "learning_rate": 2.947473210890137e-05, + "loss": 0.1454, "step": 184580 }, { - "epoch": 0.82, - "learning_rate": 8.854535671046142e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9473613565692042e-05, + "loss": 0.1468, "step": 184590 }, { - "epoch": 0.82, - "learning_rate": 8.852293619120219e-06, - "loss": 0.1391, + "epoch": 0.41, + "learning_rate": 2.947249502248272e-05, + "loss": 0.1491, "step": 184600 }, { - "epoch": 0.82, - "learning_rate": 8.850051567194296e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9471376479273395e-05, + "loss": 0.1486, "step": 184610 }, { - "epoch": 0.82, - "learning_rate": 8.847809515268373e-06, - "loss": 0.1487, + "epoch": 0.41, + "learning_rate": 2.9470257936064073e-05, + "loss": 0.1457, "step": 184620 }, { - "epoch": 0.82, - "learning_rate": 8.84556746334245e-06, - "loss": 0.1449, + "epoch": 0.41, + "learning_rate": 2.946913939285475e-05, + "loss": 0.1509, "step": 184630 }, { - "epoch": 0.82, - "learning_rate": 8.843325411416529e-06, - "loss": 0.1396, + "epoch": 0.41, + "learning_rate": 2.946802084964542e-05, + "loss": 0.1473, "step": 184640 }, { - "epoch": 0.82, - "learning_rate": 8.841083359490606e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.94669023064361e-05, + "loss": 0.146, "step": 184650 }, { - "epoch": 0.82, - "learning_rate": 8.838841307564685e-06, - "loss": 0.1427, + "epoch": 0.41, + "learning_rate": 2.9465783763226774e-05, + "loss": 0.1483, "step": 184660 }, { - "epoch": 0.82, - "learning_rate": 8.836599255638762e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9464665220017452e-05, + "loss": 0.1464, "step": 184670 }, { - "epoch": 0.82, - "learning_rate": 8.834357203712839e-06, - "loss": 0.1493, + "epoch": 0.41, + "learning_rate": 2.946354667680813e-05, + "loss": 0.145, "step": 184680 }, { - "epoch": 0.82, - "learning_rate": 8.832115151786916e-06, - "loss": 0.1415, + "epoch": 0.41, + "learning_rate": 2.94624281335988e-05, + "loss": 0.1477, "step": 184690 }, { - "epoch": 0.82, - "learning_rate": 8.829873099860993e-06, - "loss": 0.1445, + "epoch": 0.41, + "learning_rate": 2.946130959038948e-05, + "loss": 0.1435, "step": 184700 }, { - "epoch": 0.82, - "learning_rate": 8.827631047935071e-06, - "loss": 0.1427, + "epoch": 0.41, + "learning_rate": 2.9460191047180154e-05, + "loss": 0.1446, "step": 184710 }, { - "epoch": 0.82, - "learning_rate": 8.825388996009149e-06, - "loss": 0.1392, + "epoch": 0.41, + "learning_rate": 2.945907250397083e-05, + "loss": 0.1419, "step": 184720 }, { - "epoch": 0.82, - "learning_rate": 8.823146944083226e-06, - "loss": 0.1479, + "epoch": 0.41, + "learning_rate": 2.9457953960761503e-05, + "loss": 0.1508, "step": 184730 }, { - "epoch": 0.82, - "learning_rate": 8.820904892157303e-06, - "loss": 0.1475, + "epoch": 0.41, + "learning_rate": 2.945683541755218e-05, + "loss": 0.1474, "step": 184740 }, { - "epoch": 0.82, - "learning_rate": 8.81866284023138e-06, - "loss": 0.1478, + "epoch": 0.41, + "learning_rate": 2.945571687434286e-05, + "loss": 0.1476, "step": 184750 }, { - "epoch": 0.82, - "learning_rate": 8.816420788305457e-06, - "loss": 0.148, + "epoch": 0.41, + "learning_rate": 2.9454598331133533e-05, + "loss": 0.1495, "step": 184760 }, { - "epoch": 0.82, - "learning_rate": 8.814178736379534e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.945347978792421e-05, + "loss": 0.1496, "step": 184770 }, { - "epoch": 0.82, - "learning_rate": 8.811936684453612e-06, - "loss": 0.1435, + "epoch": 0.41, + "learning_rate": 2.9452361244714882e-05, + "loss": 0.146, "step": 184780 }, { - "epoch": 0.82, - "learning_rate": 8.809694632527691e-06, - "loss": 0.1415, + "epoch": 0.41, + "learning_rate": 2.945124270150556e-05, + "loss": 0.148, "step": 184790 }, { - "epoch": 0.82, - "learning_rate": 8.807452580601768e-06, - "loss": 0.1472, + "epoch": 0.41, + "learning_rate": 2.9450124158296238e-05, + "loss": 0.1468, "step": 184800 }, { - "epoch": 0.83, - "learning_rate": 8.805210528675845e-06, - "loss": 0.1425, + "epoch": 0.41, + "learning_rate": 2.9449005615086913e-05, + "loss": 0.1512, "step": 184810 }, { - "epoch": 0.83, - "learning_rate": 8.802968476749922e-06, - "loss": 0.1371, + "epoch": 0.41, + "learning_rate": 2.944788707187759e-05, + "loss": 0.1441, "step": 184820 }, { - "epoch": 0.83, - "learning_rate": 8.800726424824e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.944676852866826e-05, + "loss": 0.1467, "step": 184830 }, { - "epoch": 0.83, - "learning_rate": 8.798484372898076e-06, - "loss": 0.1428, + "epoch": 0.41, + "learning_rate": 2.944564998545894e-05, + "loss": 0.1406, "step": 184840 }, { - "epoch": 0.83, - "learning_rate": 8.796242320972155e-06, - "loss": 0.1397, + "epoch": 0.41, + "learning_rate": 2.9444531442249617e-05, + "loss": 0.1448, "step": 184850 }, { - "epoch": 0.83, - "learning_rate": 8.794000269046232e-06, - "loss": 0.1451, + "epoch": 0.41, + "learning_rate": 2.944341289904029e-05, + "loss": 0.1414, "step": 184860 }, { - "epoch": 0.83, - "learning_rate": 8.791758217120309e-06, - "loss": 0.1452, + "epoch": 0.41, + "learning_rate": 2.944229435583097e-05, + "loss": 0.1468, "step": 184870 }, { - "epoch": 0.83, - "learning_rate": 8.789516165194386e-06, - "loss": 0.1437, + "epoch": 0.41, + "learning_rate": 2.944117581262164e-05, + "loss": 0.1439, "step": 184880 }, { - "epoch": 0.83, - "learning_rate": 8.787274113268463e-06, - "loss": 0.1469, + "epoch": 0.41, + "learning_rate": 2.944005726941232e-05, + "loss": 0.1475, "step": 184890 }, { - "epoch": 0.83, - "learning_rate": 8.78503206134254e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.9438938726202997e-05, + "loss": 0.1476, "step": 184900 }, { - "epoch": 0.83, - "learning_rate": 8.782790009416619e-06, - "loss": 0.1459, + "epoch": 0.41, + "learning_rate": 2.9437820182993668e-05, + "loss": 0.144, "step": 184910 }, { - "epoch": 0.83, - "learning_rate": 8.780547957490696e-06, - "loss": 0.1459, + "epoch": 0.41, + "learning_rate": 2.9436701639784346e-05, + "loss": 0.1438, "step": 184920 }, { - "epoch": 0.83, - "learning_rate": 8.778305905564774e-06, - "loss": 0.1434, + "epoch": 0.41, + "learning_rate": 2.943558309657502e-05, + "loss": 0.1451, "step": 184930 }, { - "epoch": 0.83, - "learning_rate": 8.776063853638852e-06, - "loss": 0.1441, + "epoch": 0.41, + "learning_rate": 2.94344645533657e-05, + "loss": 0.1476, "step": 184940 }, { - "epoch": 0.83, - "learning_rate": 8.773821801712929e-06, - "loss": 0.1504, + "epoch": 0.41, + "learning_rate": 2.9433346010156376e-05, + "loss": 0.144, "step": 184950 }, { - "epoch": 0.83, - "learning_rate": 8.771579749787006e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.9432227466947048e-05, + "loss": 0.1452, "step": 184960 }, { - "epoch": 0.83, - "learning_rate": 8.769337697861083e-06, - "loss": 0.1454, + "epoch": 0.41, + "learning_rate": 2.9431108923737725e-05, + "loss": 0.148, "step": 184970 }, { - "epoch": 0.83, - "learning_rate": 8.76709564593516e-06, - "loss": 0.1505, + "epoch": 0.41, + "learning_rate": 2.94299903805284e-05, + "loss": 0.1467, "step": 184980 }, { - "epoch": 0.83, - "learning_rate": 8.764853594009238e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.9428871837319078e-05, + "loss": 0.1529, "step": 184990 }, { - "epoch": 0.83, - "learning_rate": 8.762611542083315e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9427753294109756e-05, + "loss": 0.1494, "step": 185000 }, { - "epoch": 0.83, - "learning_rate": 8.760369490157392e-06, - "loss": 0.1427, + "epoch": 0.41, + "learning_rate": 2.9426634750900427e-05, + "loss": 0.1479, "step": 185010 }, { - "epoch": 0.83, - "learning_rate": 8.75812743823147e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9425516207691105e-05, + "loss": 0.1456, "step": 185020 }, { - "epoch": 0.83, - "learning_rate": 8.755885386305546e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.942439766448178e-05, + "loss": 0.151, "step": 185030 }, { - "epoch": 0.83, - "learning_rate": 8.753643334379623e-06, - "loss": 0.1406, + "epoch": 0.41, + "learning_rate": 2.9423279121272457e-05, + "loss": 0.1437, "step": 185040 }, { - "epoch": 0.83, - "learning_rate": 8.751401282453702e-06, - "loss": 0.1427, + "epoch": 0.41, + "learning_rate": 2.942216057806313e-05, + "loss": 0.1473, "step": 185050 }, { - "epoch": 0.83, - "learning_rate": 8.749159230527781e-06, - "loss": 0.1452, + "epoch": 0.41, + "learning_rate": 2.9421042034853807e-05, + "loss": 0.1448, "step": 185060 }, { - "epoch": 0.83, - "learning_rate": 8.746917178601858e-06, - "loss": 0.1419, + "epoch": 0.41, + "learning_rate": 2.9419923491644484e-05, + "loss": 0.1451, "step": 185070 }, { - "epoch": 0.83, - "learning_rate": 8.744675126675935e-06, - "loss": 0.1472, + "epoch": 0.41, + "learning_rate": 2.941880494843516e-05, + "loss": 0.1485, "step": 185080 }, { - "epoch": 0.83, - "learning_rate": 8.742433074750012e-06, - "loss": 0.1477, + "epoch": 0.41, + "learning_rate": 2.9417686405225837e-05, + "loss": 0.1413, "step": 185090 }, { - "epoch": 0.83, - "learning_rate": 8.740191022824089e-06, - "loss": 0.1393, + "epoch": 0.41, + "learning_rate": 2.9416567862016508e-05, + "loss": 0.138, "step": 185100 }, { - "epoch": 0.83, - "learning_rate": 8.737948970898166e-06, - "loss": 0.15, + "epoch": 0.41, + "learning_rate": 2.9415449318807186e-05, + "loss": 0.1416, "step": 185110 }, { - "epoch": 0.83, - "learning_rate": 8.735706918972243e-06, - "loss": 0.1478, + "epoch": 0.41, + "learning_rate": 2.9414330775597864e-05, + "loss": 0.1537, "step": 185120 }, { - "epoch": 0.83, - "learning_rate": 8.733464867046322e-06, - "loss": 0.1424, + "epoch": 0.41, + "learning_rate": 2.941321223238854e-05, + "loss": 0.1455, "step": 185130 }, { - "epoch": 0.83, - "learning_rate": 8.731222815120399e-06, - "loss": 0.1424, + "epoch": 0.41, + "learning_rate": 2.9412093689179216e-05, + "loss": 0.1486, "step": 185140 }, { - "epoch": 0.83, - "learning_rate": 8.728980763194476e-06, - "loss": 0.1401, + "epoch": 0.41, + "learning_rate": 2.9410975145969888e-05, + "loss": 0.1425, "step": 185150 }, { - "epoch": 0.83, - "learning_rate": 8.726738711268553e-06, - "loss": 0.1443, + "epoch": 0.41, + "learning_rate": 2.9409856602760565e-05, + "loss": 0.1445, "step": 185160 }, { - "epoch": 0.83, - "learning_rate": 8.72449665934263e-06, - "loss": 0.1392, + "epoch": 0.41, + "learning_rate": 2.9408738059551243e-05, + "loss": 0.1476, "step": 185170 }, { - "epoch": 0.83, - "learning_rate": 8.722254607416709e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.9407619516341918e-05, + "loss": 0.1453, "step": 185180 }, { - "epoch": 0.83, - "learning_rate": 8.720012555490786e-06, - "loss": 0.1474, + "epoch": 0.41, + "learning_rate": 2.9406500973132596e-05, + "loss": 0.151, "step": 185190 }, { - "epoch": 0.83, - "learning_rate": 8.717770503564864e-06, - "loss": 0.1405, + "epoch": 0.41, + "learning_rate": 2.9405382429923267e-05, + "loss": 0.1472, "step": 185200 }, { - "epoch": 0.83, - "learning_rate": 8.715528451638941e-06, - "loss": 0.1447, + "epoch": 0.41, + "learning_rate": 2.9404263886713945e-05, + "loss": 0.1448, "step": 185210 }, { - "epoch": 0.83, - "learning_rate": 8.713286399713018e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.9403145343504623e-05, + "loss": 0.1427, "step": 185220 }, { - "epoch": 0.83, - "learning_rate": 8.711044347787095e-06, - "loss": 0.1456, + "epoch": 0.41, + "learning_rate": 2.9402026800295297e-05, + "loss": 0.1462, "step": 185230 }, { - "epoch": 0.83, - "learning_rate": 8.708802295861172e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9400908257085975e-05, + "loss": 0.1495, "step": 185240 }, { - "epoch": 0.83, - "learning_rate": 8.70656024393525e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.9399789713876646e-05, + "loss": 0.1398, "step": 185250 }, { - "epoch": 0.83, - "learning_rate": 8.704318192009326e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9398671170667324e-05, + "loss": 0.1495, "step": 185260 }, { - "epoch": 0.83, - "learning_rate": 8.702076140083405e-06, - "loss": 0.1473, + "epoch": 0.41, + "learning_rate": 2.9397552627458002e-05, + "loss": 0.1422, "step": 185270 }, { - "epoch": 0.83, - "learning_rate": 8.699834088157482e-06, - "loss": 0.1375, + "epoch": 0.41, + "learning_rate": 2.9396434084248677e-05, + "loss": 0.1466, "step": 185280 }, { - "epoch": 0.83, - "learning_rate": 8.69759203623156e-06, - "loss": 0.1414, + "epoch": 0.41, + "learning_rate": 2.9395315541039355e-05, + "loss": 0.1443, "step": 185290 }, { - "epoch": 0.83, - "learning_rate": 8.695349984305636e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9394196997830026e-05, + "loss": 0.1458, "step": 185300 }, { - "epoch": 0.83, - "learning_rate": 8.693107932379713e-06, - "loss": 0.1412, + "epoch": 0.41, + "learning_rate": 2.9393078454620704e-05, + "loss": 0.1439, "step": 185310 }, { - "epoch": 0.83, - "learning_rate": 8.690865880453792e-06, - "loss": 0.1469, + "epoch": 0.41, + "learning_rate": 2.9391959911411382e-05, + "loss": 0.1458, "step": 185320 }, { - "epoch": 0.83, - "learning_rate": 8.688623828527869e-06, - "loss": 0.1456, + "epoch": 0.41, + "learning_rate": 2.9390841368202053e-05, + "loss": 0.1443, "step": 185330 }, { - "epoch": 0.83, - "learning_rate": 8.686381776601948e-06, + "epoch": 0.41, + "learning_rate": 2.938972282499273e-05, "loss": 0.1447, "step": 185340 }, { - "epoch": 0.83, - "learning_rate": 8.684139724676025e-06, - "loss": 0.1411, + "epoch": 0.41, + "learning_rate": 2.9388604281783405e-05, + "loss": 0.1499, "step": 185350 }, { - "epoch": 0.83, - "learning_rate": 8.681897672750102e-06, - "loss": 0.1451, + "epoch": 0.41, + "learning_rate": 2.9387485738574083e-05, + "loss": 0.1476, "step": 185360 }, { - "epoch": 0.83, - "learning_rate": 8.679655620824179e-06, - "loss": 0.1426, + "epoch": 0.41, + "learning_rate": 2.9386367195364755e-05, + "loss": 0.1421, "step": 185370 }, { - "epoch": 0.83, - "learning_rate": 8.677413568898256e-06, - "loss": 0.1428, + "epoch": 0.41, + "learning_rate": 2.9385248652155432e-05, + "loss": 0.1512, "step": 185380 }, { - "epoch": 0.83, - "learning_rate": 8.675171516972333e-06, - "loss": 0.1497, + "epoch": 0.41, + "learning_rate": 2.938413010894611e-05, + "loss": 0.1466, "step": 185390 }, { - "epoch": 0.83, - "learning_rate": 8.672929465046412e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9383011565736785e-05, + "loss": 0.1421, "step": 185400 }, { - "epoch": 0.83, - "learning_rate": 8.670687413120489e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.9381893022527463e-05, + "loss": 0.1464, "step": 185410 }, { - "epoch": 0.83, - "learning_rate": 8.668445361194566e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9380774479318134e-05, + "loss": 0.1528, "step": 185420 }, { - "epoch": 0.83, - "learning_rate": 8.666203309268643e-06, - "loss": 0.1436, + "epoch": 0.41, + "learning_rate": 2.9379655936108812e-05, + "loss": 0.1451, "step": 185430 }, { - "epoch": 0.83, - "learning_rate": 8.66396125734272e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.937853739289949e-05, + "loss": 0.1455, "step": 185440 }, { - "epoch": 0.83, - "learning_rate": 8.661719205416798e-06, - "loss": 0.1421, + "epoch": 0.41, + "learning_rate": 2.9377418849690164e-05, + "loss": 0.1493, "step": 185450 }, { - "epoch": 0.83, - "learning_rate": 8.659477153490875e-06, - "loss": 0.1389, + "epoch": 0.41, + "learning_rate": 2.9376300306480842e-05, + "loss": 0.1446, "step": 185460 }, { - "epoch": 0.83, - "learning_rate": 8.657235101564954e-06, - "loss": 0.1416, + "epoch": 0.41, + "learning_rate": 2.9375181763271513e-05, + "loss": 0.1428, "step": 185470 }, { - "epoch": 0.83, - "learning_rate": 8.654993049639031e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.937406322006219e-05, + "loss": 0.1485, "step": 185480 }, { - "epoch": 0.83, - "learning_rate": 8.652750997713108e-06, - "loss": 0.1429, + "epoch": 0.41, + "learning_rate": 2.937294467685287e-05, + "loss": 0.1434, "step": 185490 }, { - "epoch": 0.83, - "learning_rate": 8.650508945787185e-06, - "loss": 0.1444, + "epoch": 0.41, + "learning_rate": 2.9371826133643544e-05, + "loss": 0.1475, "step": 185500 }, { - "epoch": 0.83, - "learning_rate": 8.648266893861262e-06, - "loss": 0.1398, + "epoch": 0.41, + "learning_rate": 2.9370707590434222e-05, + "loss": 0.1457, "step": 185510 }, { - "epoch": 0.83, - "learning_rate": 8.64602484193534e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9369589047224893e-05, + "loss": 0.1454, "step": 185520 }, { - "epoch": 0.83, - "learning_rate": 8.643782790009416e-06, - "loss": 0.139, + "epoch": 0.41, + "learning_rate": 2.936847050401557e-05, + "loss": 0.1445, "step": 185530 }, { - "epoch": 0.83, - "learning_rate": 8.641540738083495e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.936735196080625e-05, + "loss": 0.146, "step": 185540 }, { - "epoch": 0.83, - "learning_rate": 8.639298686157572e-06, - "loss": 0.1457, + "epoch": 0.41, + "learning_rate": 2.9366233417596923e-05, + "loss": 0.1468, "step": 185550 }, { - "epoch": 0.83, - "learning_rate": 8.637056634231649e-06, - "loss": 0.1402, + "epoch": 0.41, + "learning_rate": 2.93651148743876e-05, + "loss": 0.1445, "step": 185560 }, { - "epoch": 0.83, - "learning_rate": 8.634814582305726e-06, - "loss": 0.1448, + "epoch": 0.41, + "learning_rate": 2.9363996331178272e-05, + "loss": 0.1459, "step": 185570 }, { - "epoch": 0.83, - "learning_rate": 8.632572530379803e-06, - "loss": 0.1468, + "epoch": 0.41, + "learning_rate": 2.936287778796895e-05, + "loss": 0.1464, "step": 185580 }, { - "epoch": 0.83, - "learning_rate": 8.630330478453882e-06, - "loss": 0.1482, + "epoch": 0.41, + "learning_rate": 2.9361759244759628e-05, + "loss": 0.1438, "step": 185590 }, { - "epoch": 0.83, - "learning_rate": 8.628088426527959e-06, - "loss": 0.1431, + "epoch": 0.41, + "learning_rate": 2.9360640701550303e-05, + "loss": 0.142, "step": 185600 }, { - "epoch": 0.83, - "learning_rate": 8.625846374602038e-06, - "loss": 0.1442, + "epoch": 0.41, + "learning_rate": 2.935952215834098e-05, + "loss": 0.1433, "step": 185610 }, { - "epoch": 0.83, - "learning_rate": 8.623604322676115e-06, - "loss": 0.1451, + "epoch": 0.41, + "learning_rate": 2.9358403615131652e-05, + "loss": 0.1441, "step": 185620 }, { - "epoch": 0.83, - "learning_rate": 8.621362270750192e-06, - "loss": 0.1477, + "epoch": 0.41, + "learning_rate": 2.935728507192233e-05, + "loss": 0.145, "step": 185630 }, { - "epoch": 0.83, - "learning_rate": 8.619120218824269e-06, - "loss": 0.1476, + "epoch": 0.41, + "learning_rate": 2.9356166528713008e-05, + "loss": 0.1494, "step": 185640 }, { - "epoch": 0.83, - "learning_rate": 8.616878166898346e-06, - "loss": 0.1458, + "epoch": 0.41, + "learning_rate": 2.9355047985503682e-05, + "loss": 0.1427, "step": 185650 }, { - "epoch": 0.83, - "learning_rate": 8.614636114972423e-06, - "loss": 0.1414, + "epoch": 0.41, + "learning_rate": 2.935392944229436e-05, + "loss": 0.1484, "step": 185660 }, { - "epoch": 0.83, - "learning_rate": 8.6123940630465e-06, - "loss": 0.1461, + "epoch": 0.41, + "learning_rate": 2.935281089908503e-05, + "loss": 0.1404, "step": 185670 }, { - "epoch": 0.83, - "learning_rate": 8.610152011120578e-06, - "loss": 0.1422, + "epoch": 0.41, + "learning_rate": 2.9351804210196644e-05, + "loss": 0.1504, "step": 185680 }, { - "epoch": 0.83, - "learning_rate": 8.607909959194655e-06, - "loss": 0.1411, + "epoch": 0.41, + "learning_rate": 2.9350685666987315e-05, + "loss": 0.1432, "step": 185690 }, { - "epoch": 0.83, - "learning_rate": 8.605667907268732e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.9349567123777993e-05, + "loss": 0.152, "step": 185700 }, { - "epoch": 0.83, - "learning_rate": 8.60342585534281e-06, - "loss": 0.1452, + "epoch": 0.41, + "learning_rate": 2.934844858056867e-05, + "loss": 0.1467, "step": 185710 }, { - "epoch": 0.83, - "learning_rate": 8.601183803416888e-06, - "loss": 0.1491, + "epoch": 0.41, + "learning_rate": 2.9347330037359345e-05, + "loss": 0.1487, "step": 185720 }, { - "epoch": 0.83, - "learning_rate": 8.598941751490965e-06, - "loss": 0.1455, + "epoch": 0.41, + "learning_rate": 2.9346211494150023e-05, + "loss": 0.1442, "step": 185730 }, { - "epoch": 0.83, - "learning_rate": 8.596699699565042e-06, - "loss": 0.1454, + "epoch": 0.41, + "learning_rate": 2.9345092950940694e-05, + "loss": 0.1414, "step": 185740 }, { - "epoch": 0.83, - "learning_rate": 8.594457647639121e-06, - "loss": 0.1401, + "epoch": 0.41, + "learning_rate": 2.9343974407731372e-05, + "loss": 0.1448, "step": 185750 }, { - "epoch": 0.83, - "learning_rate": 8.592215595713198e-06, - "loss": 0.144, + "epoch": 0.41, + "learning_rate": 2.9342855864522047e-05, + "loss": 0.1439, "step": 185760 }, { - "epoch": 0.83, - "learning_rate": 8.589973543787275e-06, - "loss": 0.1489, + "epoch": 0.41, + "learning_rate": 2.9341737321312725e-05, + "loss": 0.1464, "step": 185770 }, { - "epoch": 0.83, - "learning_rate": 8.587731491861352e-06, - "loss": 0.1446, + "epoch": 0.41, + "learning_rate": 2.9340618778103402e-05, + "loss": 0.1471, "step": 185780 }, { - "epoch": 0.83, - "learning_rate": 8.585489439935429e-06, - "loss": 0.1447, + "epoch": 0.41, + "learning_rate": 2.9339500234894074e-05, + "loss": 0.1468, "step": 185790 }, { - "epoch": 0.83, - "learning_rate": 8.583247388009506e-06, - "loss": 0.146, + "epoch": 0.41, + "learning_rate": 2.933838169168475e-05, + "loss": 0.1404, "step": 185800 }, { - "epoch": 0.83, - "learning_rate": 8.581005336083583e-06, - "loss": 0.1464, + "epoch": 0.41, + "learning_rate": 2.9337263148475426e-05, + "loss": 0.1446, "step": 185810 }, { - "epoch": 0.83, - "learning_rate": 8.578763284157662e-06, - "loss": 0.1463, + "epoch": 0.41, + "learning_rate": 2.9336144605266104e-05, + "loss": 0.1423, "step": 185820 }, { - "epoch": 0.83, - "learning_rate": 8.576521232231739e-06, - "loss": 0.1436, + "epoch": 0.41, + "learning_rate": 2.9335026062056782e-05, + "loss": 0.1447, "step": 185830 }, { - "epoch": 0.83, - "learning_rate": 8.574279180305816e-06, - "loss": 0.1405, + "epoch": 0.41, + "learning_rate": 2.9333907518847453e-05, + "loss": 0.1464, "step": 185840 }, { - "epoch": 0.83, - "learning_rate": 8.572037128379893e-06, - "loss": 0.141, + "epoch": 0.41, + "learning_rate": 2.933278897563813e-05, + "loss": 0.1484, "step": 185850 }, { - "epoch": 0.83, - "learning_rate": 8.569795076453972e-06, - "loss": 0.1499, + "epoch": 0.41, + "learning_rate": 2.9331670432428802e-05, + "loss": 0.1535, "step": 185860 }, { - "epoch": 0.83, - "learning_rate": 8.567553024528049e-06, - "loss": 0.1438, + "epoch": 0.41, + "learning_rate": 2.9330551889219483e-05, + "loss": 0.1437, "step": 185870 }, { - "epoch": 0.83, - "learning_rate": 8.565310972602126e-06, - "loss": 0.1413, + "epoch": 0.41, + "learning_rate": 2.932943334601016e-05, + "loss": 0.1502, "step": 185880 }, { - "epoch": 0.83, - "learning_rate": 8.563068920676204e-06, - "loss": 0.14, + "epoch": 0.41, + "learning_rate": 2.9328314802800833e-05, + "loss": 0.1382, "step": 185890 }, { - "epoch": 0.83, - "learning_rate": 8.560826868750281e-06, - "loss": 0.1406, + "epoch": 0.41, + "learning_rate": 2.932719625959151e-05, + "loss": 0.1442, "step": 185900 }, { - "epoch": 0.83, - "learning_rate": 8.558584816824358e-06, - "loss": 0.145, + "epoch": 0.41, + "learning_rate": 2.932607771638218e-05, + "loss": 0.1485, "step": 185910 }, { - "epoch": 0.83, - "learning_rate": 8.556342764898435e-06, - "loss": 0.1465, + "epoch": 0.41, + "learning_rate": 2.932495917317286e-05, + "loss": 0.1541, "step": 185920 }, { - "epoch": 0.83, - "learning_rate": 8.554100712972512e-06, - "loss": 0.1448, + "epoch": 0.42, + "learning_rate": 2.932384062996354e-05, + "loss": 0.1513, "step": 185930 }, { - "epoch": 0.83, - "learning_rate": 8.55185866104659e-06, - "loss": 0.1481, + "epoch": 0.42, + "learning_rate": 2.9322722086754212e-05, + "loss": 0.1504, "step": 185940 }, { - "epoch": 0.83, - "learning_rate": 8.549616609120666e-06, - "loss": 0.1409, + "epoch": 0.42, + "learning_rate": 2.932160354354489e-05, + "loss": 0.1453, "step": 185950 }, { - "epoch": 0.83, - "learning_rate": 8.547374557194745e-06, - "loss": 0.142, + "epoch": 0.42, + "learning_rate": 2.9320596854656495e-05, + "loss": 0.1489, "step": 185960 }, { - "epoch": 0.83, - "learning_rate": 8.545132505268822e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.9319478311447173e-05, + "loss": 0.1419, "step": 185970 }, { - "epoch": 0.83, - "learning_rate": 8.5428904533429e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.9318359768237848e-05, + "loss": 0.1478, "step": 185980 }, { - "epoch": 0.83, - "learning_rate": 8.540648401416978e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.9317241225028526e-05, + "loss": 0.1465, "step": 185990 }, { - "epoch": 0.83, - "learning_rate": 8.538406349491055e-06, - "loss": 0.1469, + "epoch": 0.42, + "learning_rate": 2.9316122681819204e-05, + "loss": 0.1447, "step": 186000 }, { - "epoch": 0.83, - "learning_rate": 8.536164297565132e-06, - "loss": 0.144, + "epoch": 0.42, + "learning_rate": 2.9315004138609875e-05, + "loss": 0.1526, "step": 186010 }, { - "epoch": 0.83, - "learning_rate": 8.533922245639209e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.9313885595400553e-05, + "loss": 0.1447, "step": 186020 }, { - "epoch": 0.83, - "learning_rate": 8.531680193713288e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.9312767052191227e-05, + "loss": 0.1443, "step": 186030 }, { - "epoch": 0.83, - "learning_rate": 8.529438141787365e-06, - "loss": 0.1471, + "epoch": 0.42, + "learning_rate": 2.9311648508981905e-05, + "loss": 0.1401, "step": 186040 }, { - "epoch": 0.83, - "learning_rate": 8.527196089861442e-06, - "loss": 0.147, + "epoch": 0.42, + "learning_rate": 2.9310529965772583e-05, + "loss": 0.1452, "step": 186050 }, { - "epoch": 0.83, - "learning_rate": 8.524954037935519e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9309411422563254e-05, + "loss": 0.1454, "step": 186060 }, { - "epoch": 0.83, - "learning_rate": 8.522711986009596e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.9308292879353932e-05, + "loss": 0.1466, "step": 186070 }, { - "epoch": 0.83, - "learning_rate": 8.520469934083673e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.9307174336144603e-05, + "loss": 0.1501, "step": 186080 }, { - "epoch": 0.83, - "learning_rate": 8.518227882157752e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.9306055792935285e-05, + "loss": 0.1457, "step": 186090 }, { - "epoch": 0.83, - "learning_rate": 8.515985830231829e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.9304937249725956e-05, + "loss": 0.1459, "step": 186100 }, { - "epoch": 0.83, - "learning_rate": 8.513743778305906e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.9303818706516634e-05, + "loss": 0.1452, "step": 186110 }, { - "epoch": 0.83, - "learning_rate": 8.511501726379983e-06, - "loss": 0.142, + "epoch": 0.42, + "learning_rate": 2.9302700163307312e-05, + "loss": 0.1532, "step": 186120 }, { - "epoch": 0.83, - "learning_rate": 8.509259674454061e-06, - "loss": 0.1404, + "epoch": 0.42, + "learning_rate": 2.9301581620097983e-05, + "loss": 0.1473, "step": 186130 }, { - "epoch": 0.83, - "learning_rate": 8.507017622528138e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.930046307688866e-05, + "loss": 0.1472, "step": 186140 }, { - "epoch": 0.83, - "learning_rate": 8.504775570602215e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.9299344533679335e-05, + "loss": 0.1453, "step": 186150 }, { - "epoch": 0.83, - "learning_rate": 8.502533518676294e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.9298225990470013e-05, + "loss": 0.1452, "step": 186160 }, { - "epoch": 0.83, - "learning_rate": 8.500291466750371e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.929710744726069e-05, + "loss": 0.1416, "step": 186170 }, { - "epoch": 0.83, - "learning_rate": 8.498049414824448e-06, - "loss": 0.1374, + "epoch": 0.42, + "learning_rate": 2.9295988904051362e-05, + "loss": 0.1505, "step": 186180 }, { - "epoch": 0.83, - "learning_rate": 8.495807362898525e-06, - "loss": 0.1497, + "epoch": 0.42, + "learning_rate": 2.929487036084204e-05, + "loss": 0.1416, "step": 186190 }, { - "epoch": 0.83, - "learning_rate": 8.493565310972602e-06, - "loss": 0.1414, + "epoch": 0.42, + "learning_rate": 2.9293751817632715e-05, + "loss": 0.1455, "step": 186200 }, { - "epoch": 0.83, - "learning_rate": 8.49132325904668e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.9292633274423393e-05, + "loss": 0.1449, "step": 186210 }, { - "epoch": 0.83, - "learning_rate": 8.489081207120756e-06, - "loss": 0.1451, + "epoch": 0.42, + "learning_rate": 2.929151473121407e-05, + "loss": 0.1402, "step": 186220 }, { - "epoch": 0.83, - "learning_rate": 8.486839155194835e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9290396188004742e-05, + "loss": 0.1475, "step": 186230 }, { - "epoch": 0.83, - "learning_rate": 8.484597103268912e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.928927764479542e-05, + "loss": 0.1478, "step": 186240 }, { - "epoch": 0.83, - "learning_rate": 8.482355051342989e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9288159101586094e-05, + "loss": 0.148, "step": 186250 }, { - "epoch": 0.83, - "learning_rate": 8.480112999417068e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.9287040558376772e-05, + "loss": 0.1484, "step": 186260 }, { - "epoch": 0.83, - "learning_rate": 8.477870947491145e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.928592201516745e-05, + "loss": 0.1507, "step": 186270 }, { - "epoch": 0.83, - "learning_rate": 8.475628895565222e-06, - "loss": 0.1431, + "epoch": 0.42, + "learning_rate": 2.928480347195812e-05, + "loss": 0.1492, "step": 186280 }, { - "epoch": 0.83, - "learning_rate": 8.473386843639299e-06, - "loss": 0.1445, + "epoch": 0.42, + "learning_rate": 2.92836849287488e-05, + "loss": 0.1414, "step": 186290 }, { - "epoch": 0.83, - "learning_rate": 8.471144791713378e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.9282566385539474e-05, + "loss": 0.1513, "step": 186300 }, { - "epoch": 0.83, - "learning_rate": 8.468902739787455e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.928144784233015e-05, + "loss": 0.1413, "step": 186310 }, { - "epoch": 0.83, - "learning_rate": 8.466660687861532e-06, - "loss": 0.1388, + "epoch": 0.42, + "learning_rate": 2.928032929912083e-05, + "loss": 0.1407, "step": 186320 }, { - "epoch": 0.83, - "learning_rate": 8.464418635935609e-06, - "loss": 0.1427, + "epoch": 0.42, + "learning_rate": 2.92792107559115e-05, + "loss": 0.1459, "step": 186330 }, { - "epoch": 0.83, - "learning_rate": 8.462176584009686e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.927809221270218e-05, + "loss": 0.1476, "step": 186340 }, { - "epoch": 0.83, - "learning_rate": 8.459934532083763e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.9276973669492853e-05, + "loss": 0.1452, "step": 186350 }, { - "epoch": 0.83, - "learning_rate": 8.45769248015784e-06, - "loss": 0.1445, + "epoch": 0.42, + "learning_rate": 2.927585512628353e-05, + "loss": 0.1479, "step": 186360 }, { - "epoch": 0.83, - "learning_rate": 8.455450428231918e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.927473658307421e-05, + "loss": 0.1511, "step": 186370 }, { - "epoch": 0.83, - "learning_rate": 8.453208376305995e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.927361803986488e-05, + "loss": 0.1423, "step": 186380 }, { - "epoch": 0.83, - "learning_rate": 8.450966324380072e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.9272499496655558e-05, + "loss": 0.1422, "step": 186390 }, { - "epoch": 0.83, - "learning_rate": 8.448724272454151e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.9271380953446233e-05, + "loss": 0.1519, "step": 186400 }, { - "epoch": 0.83, - "learning_rate": 8.446482220528228e-06, - "loss": 0.1415, + "epoch": 0.42, + "learning_rate": 2.927026241023691e-05, + "loss": 0.1389, "step": 186410 }, { - "epoch": 0.83, - "learning_rate": 8.444240168602305e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.9269143867027582e-05, + "loss": 0.1458, "step": 186420 }, { - "epoch": 0.83, - "learning_rate": 8.441998116676382e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.926802532381826e-05, + "loss": 0.1429, "step": 186430 }, { - "epoch": 0.83, - "learning_rate": 8.439756064750461e-06, - "loss": 0.1448, + "epoch": 0.42, + "learning_rate": 2.9266906780608938e-05, + "loss": 0.1484, "step": 186440 }, { - "epoch": 0.83, - "learning_rate": 8.437514012824538e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.9265788237399612e-05, + "loss": 0.1466, "step": 186450 }, { - "epoch": 0.83, - "learning_rate": 8.435271960898615e-06, - "loss": 0.1378, + "epoch": 0.42, + "learning_rate": 2.926466969419029e-05, + "loss": 0.147, "step": 186460 }, { - "epoch": 0.83, - "learning_rate": 8.433029908972692e-06, - "loss": 0.1382, + "epoch": 0.42, + "learning_rate": 2.926355115098096e-05, + "loss": 0.1506, "step": 186470 }, { - "epoch": 0.83, - "learning_rate": 8.430787857046769e-06, - "loss": 0.1496, + "epoch": 0.42, + "learning_rate": 2.926243260777164e-05, + "loss": 0.1475, "step": 186480 }, { - "epoch": 0.83, - "learning_rate": 8.428545805120846e-06, - "loss": 0.1389, + "epoch": 0.42, + "learning_rate": 2.9261314064562317e-05, + "loss": 0.1436, "step": 186490 }, { - "epoch": 0.83, - "learning_rate": 8.426303753194923e-06, - "loss": 0.1384, + "epoch": 0.42, + "learning_rate": 2.9260195521352988e-05, + "loss": 0.1421, "step": 186500 }, { - "epoch": 0.83, - "learning_rate": 8.424061701269002e-06, - "loss": 0.1478, + "epoch": 0.42, + "learning_rate": 2.925907697814367e-05, + "loss": 0.1458, "step": 186510 }, { - "epoch": 0.83, - "learning_rate": 8.421819649343079e-06, - "loss": 0.1494, + "epoch": 0.42, + "learning_rate": 2.925795843493434e-05, + "loss": 0.1449, "step": 186520 }, { - "epoch": 0.83, - "learning_rate": 8.419577597417158e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.925683989172502e-05, + "loss": 0.1502, "step": 186530 }, { - "epoch": 0.83, - "learning_rate": 8.417335545491235e-06, - "loss": 0.1502, + "epoch": 0.42, + "learning_rate": 2.9255721348515697e-05, + "loss": 0.143, "step": 186540 }, { - "epoch": 0.83, - "learning_rate": 8.415093493565312e-06, - "loss": 0.1504, + "epoch": 0.42, + "learning_rate": 2.9254602805306368e-05, + "loss": 0.1545, "step": 186550 }, { - "epoch": 0.83, - "learning_rate": 8.412851441639389e-06, - "loss": 0.1487, + "epoch": 0.42, + "learning_rate": 2.9253484262097046e-05, + "loss": 0.1467, "step": 186560 }, { - "epoch": 0.83, - "learning_rate": 8.410609389713466e-06, - "loss": 0.1402, + "epoch": 0.42, + "learning_rate": 2.925236571888772e-05, + "loss": 0.1492, "step": 186570 }, { - "epoch": 0.83, - "learning_rate": 8.408367337787544e-06, - "loss": 0.1462, + "epoch": 0.42, + "learning_rate": 2.9251247175678398e-05, + "loss": 0.1443, "step": 186580 }, { - "epoch": 0.83, - "learning_rate": 8.406125285861621e-06, - "loss": 0.1415, + "epoch": 0.42, + "learning_rate": 2.9250128632469076e-05, + "loss": 0.1434, "step": 186590 }, { - "epoch": 0.83, - "learning_rate": 8.403883233935698e-06, - "loss": 0.1429, + "epoch": 0.42, + "learning_rate": 2.9249010089259747e-05, + "loss": 0.1468, "step": 186600 }, { - "epoch": 0.83, - "learning_rate": 8.401641182009775e-06, - "loss": 0.1427, + "epoch": 0.42, + "learning_rate": 2.9247891546050425e-05, + "loss": 0.1472, "step": 186610 }, { - "epoch": 0.83, - "learning_rate": 8.399399130083852e-06, - "loss": 0.1432, + "epoch": 0.42, + "learning_rate": 2.92467730028411e-05, + "loss": 0.1415, "step": 186620 }, { - "epoch": 0.83, - "learning_rate": 8.39715707815793e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.9245654459631778e-05, + "loss": 0.1418, "step": 186630 }, { - "epoch": 0.83, - "learning_rate": 8.394915026232007e-06, - "loss": 0.1398, + "epoch": 0.42, + "learning_rate": 2.9244535916422456e-05, + "loss": 0.1425, "step": 186640 }, { - "epoch": 0.83, - "learning_rate": 8.392672974306085e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.9243417373213127e-05, + "loss": 0.1391, "step": 186650 }, { - "epoch": 0.83, - "learning_rate": 8.390430922380162e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.9242298830003805e-05, + "loss": 0.147, "step": 186660 }, { - "epoch": 0.83, - "learning_rate": 8.388188870454241e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.924118028679448e-05, + "loss": 0.1455, "step": 186670 }, { - "epoch": 0.83, - "learning_rate": 8.385946818528318e-06, - "loss": 0.1418, + "epoch": 0.42, + "learning_rate": 2.9240061743585157e-05, + "loss": 0.1468, "step": 186680 }, { - "epoch": 0.83, - "learning_rate": 8.383704766602395e-06, - "loss": 0.1463, + "epoch": 0.42, + "learning_rate": 2.9238943200375835e-05, + "loss": 0.141, "step": 186690 }, { - "epoch": 0.83, - "learning_rate": 8.381462714676472e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.9237824657166506e-05, + "loss": 0.1501, "step": 186700 }, { - "epoch": 0.83, - "learning_rate": 8.379220662750549e-06, - "loss": 0.1386, + "epoch": 0.42, + "learning_rate": 2.9236706113957184e-05, + "loss": 0.1461, "step": 186710 }, { - "epoch": 0.83, - "learning_rate": 8.376978610824628e-06, - "loss": 0.1475, + "epoch": 0.42, + "learning_rate": 2.923558757074786e-05, + "loss": 0.1434, "step": 186720 }, { - "epoch": 0.83, - "learning_rate": 8.374736558898705e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.9234469027538537e-05, + "loss": 0.1475, "step": 186730 }, { - "epoch": 0.83, - "learning_rate": 8.372494506972782e-06, - "loss": 0.1462, + "epoch": 0.42, + "learning_rate": 2.9233350484329208e-05, + "loss": 0.1499, "step": 186740 }, { - "epoch": 0.83, - "learning_rate": 8.370252455046859e-06, - "loss": 0.1466, + "epoch": 0.42, + "learning_rate": 2.9232231941119886e-05, + "loss": 0.1436, "step": 186750 }, { - "epoch": 0.83, - "learning_rate": 8.368010403120936e-06, - "loss": 0.1454, + "epoch": 0.42, + "learning_rate": 2.9231113397910564e-05, + "loss": 0.1464, "step": 186760 }, { - "epoch": 0.83, - "learning_rate": 8.365768351195013e-06, - "loss": 0.1453, + "epoch": 0.42, + "learning_rate": 2.9229994854701238e-05, + "loss": 0.1455, "step": 186770 }, { - "epoch": 0.83, - "learning_rate": 8.363526299269092e-06, - "loss": 0.1436, + "epoch": 0.42, + "learning_rate": 2.9228876311491916e-05, + "loss": 0.1466, "step": 186780 }, { - "epoch": 0.83, - "learning_rate": 8.361284247343169e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.9227757768282587e-05, + "loss": 0.1501, "step": 186790 }, { - "epoch": 0.83, - "learning_rate": 8.359042195417247e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.9226639225073265e-05, + "loss": 0.1472, "step": 186800 }, { - "epoch": 0.83, - "learning_rate": 8.356800143491324e-06, - "loss": 0.1441, + "epoch": 0.42, + "learning_rate": 2.9225520681863943e-05, + "loss": 0.1451, "step": 186810 }, { - "epoch": 0.83, - "learning_rate": 8.354558091565401e-06, - "loss": 0.14, + "epoch": 0.42, + "learning_rate": 2.9224402138654618e-05, + "loss": 0.1433, "step": 186820 }, { - "epoch": 0.83, - "learning_rate": 8.352316039639478e-06, - "loss": 0.1486, + "epoch": 0.42, + "learning_rate": 2.9223283595445295e-05, + "loss": 0.1498, "step": 186830 }, { - "epoch": 0.83, - "learning_rate": 8.350073987713555e-06, - "loss": 0.1473, + "epoch": 0.42, + "learning_rate": 2.9222165052235967e-05, + "loss": 0.1449, "step": 186840 }, { - "epoch": 0.83, - "learning_rate": 8.347831935787634e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.9221046509026645e-05, + "loss": 0.1448, "step": 186850 }, { - "epoch": 0.83, - "learning_rate": 8.345589883861711e-06, - "loss": 0.1415, + "epoch": 0.42, + "learning_rate": 2.9219927965817322e-05, + "loss": 0.1469, "step": 186860 }, { - "epoch": 0.83, - "learning_rate": 8.343347831935788e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.9218809422607997e-05, + "loss": 0.1475, "step": 186870 }, { - "epoch": 0.83, - "learning_rate": 8.341105780009865e-06, - "loss": 0.1489, + "epoch": 0.42, + "learning_rate": 2.9217690879398675e-05, + "loss": 0.1443, "step": 186880 }, { - "epoch": 0.83, - "learning_rate": 8.338863728083942e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.9216572336189346e-05, + "loss": 0.1439, "step": 186890 }, { - "epoch": 0.83, - "learning_rate": 8.33662167615802e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.9215453792980024e-05, + "loss": 0.1401, "step": 186900 }, { - "epoch": 0.83, - "learning_rate": 8.334379624232096e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.9214335249770702e-05, + "loss": 0.1433, "step": 186910 }, { - "epoch": 0.83, - "learning_rate": 8.332137572306175e-06, - "loss": 0.1367, + "epoch": 0.42, + "learning_rate": 2.9213216706561377e-05, + "loss": 0.1409, "step": 186920 }, { - "epoch": 0.83, - "learning_rate": 8.329895520380252e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.9212098163352054e-05, + "loss": 0.1442, "step": 186930 }, { - "epoch": 0.83, - "learning_rate": 8.32765346845433e-06, - "loss": 0.1463, + "epoch": 0.42, + "learning_rate": 2.9210979620142726e-05, + "loss": 0.1438, "step": 186940 }, { - "epoch": 0.83, - "learning_rate": 8.325411416528408e-06, - "loss": 0.1394, + "epoch": 0.42, + "learning_rate": 2.9209861076933404e-05, + "loss": 0.1442, "step": 186950 }, { - "epoch": 0.83, - "learning_rate": 8.323169364602485e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.920874253372408e-05, + "loss": 0.1449, "step": 186960 }, { - "epoch": 0.83, - "learning_rate": 8.320927312676562e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.9207623990514753e-05, + "loss": 0.1433, "step": 186970 }, { - "epoch": 0.83, - "learning_rate": 8.318685260750639e-06, - "loss": 0.1389, + "epoch": 0.42, + "learning_rate": 2.9206505447305434e-05, + "loss": 0.1456, "step": 186980 }, { - "epoch": 0.83, - "learning_rate": 8.316443208824718e-06, - "loss": 0.1468, + "epoch": 0.42, + "learning_rate": 2.9205386904096105e-05, + "loss": 0.1419, "step": 186990 }, { - "epoch": 0.83, - "learning_rate": 8.314201156898795e-06, - "loss": 0.1453, + "epoch": 0.42, + "learning_rate": 2.9204268360886783e-05, + "loss": 0.1392, "step": 187000 }, { - "epoch": 0.83, - "learning_rate": 8.311959104972872e-06, - "loss": 0.146, + "epoch": 0.42, + "learning_rate": 2.920314981767746e-05, + "loss": 0.1485, "step": 187010 }, { - "epoch": 0.83, - "learning_rate": 8.309717053046949e-06, - "loss": 0.1397, + "epoch": 0.42, + "learning_rate": 2.9202031274468132e-05, + "loss": 0.1443, "step": 187020 }, { - "epoch": 0.83, - "learning_rate": 8.307475001121026e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.920091273125881e-05, + "loss": 0.1442, "step": 187030 }, { - "epoch": 0.83, - "learning_rate": 8.305232949195103e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.9199794188049485e-05, + "loss": 0.1477, "step": 187040 }, { - "epoch": 0.84, - "learning_rate": 8.30299089726918e-06, - "loss": 0.148, + "epoch": 0.42, + "learning_rate": 2.9198675644840162e-05, + "loss": 0.1451, "step": 187050 }, { - "epoch": 0.84, - "learning_rate": 8.300748845343258e-06, - "loss": 0.14, + "epoch": 0.42, + "learning_rate": 2.9197557101630834e-05, + "loss": 0.1439, "step": 187060 }, { - "epoch": 0.84, - "learning_rate": 8.298506793417337e-06, - "loss": 0.1365, + "epoch": 0.42, + "learning_rate": 2.919643855842151e-05, + "loss": 0.1492, "step": 187070 }, { - "epoch": 0.84, - "learning_rate": 8.296264741491414e-06, - "loss": 0.1493, + "epoch": 0.42, + "learning_rate": 2.919532001521219e-05, + "loss": 0.1463, "step": 187080 }, { - "epoch": 0.84, - "learning_rate": 8.294022689565491e-06, - "loss": 0.1395, + "epoch": 0.42, + "learning_rate": 2.9194201472002864e-05, + "loss": 0.1431, "step": 187090 }, { - "epoch": 0.84, - "learning_rate": 8.291780637639568e-06, - "loss": 0.1384, + "epoch": 0.42, + "learning_rate": 2.9193082928793542e-05, + "loss": 0.1498, "step": 187100 }, { - "epoch": 0.84, - "learning_rate": 8.289538585713645e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.9191964385584213e-05, + "loss": 0.1519, "step": 187110 }, { - "epoch": 0.84, - "learning_rate": 8.287296533787722e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.919084584237489e-05, + "loss": 0.147, "step": 187120 }, { - "epoch": 0.84, - "learning_rate": 8.285054481861801e-06, - "loss": 0.1478, + "epoch": 0.42, + "learning_rate": 2.918972729916557e-05, + "loss": 0.1508, "step": 187130 }, { - "epoch": 0.84, - "learning_rate": 8.282812429935878e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.9188608755956243e-05, + "loss": 0.1483, "step": 187140 }, { - "epoch": 0.84, - "learning_rate": 8.280570378009955e-06, - "loss": 0.1448, + "epoch": 0.42, + "learning_rate": 2.918749021274692e-05, + "loss": 0.1424, "step": 187150 }, { - "epoch": 0.84, - "learning_rate": 8.278328326084032e-06, - "loss": 0.1399, + "epoch": 0.42, + "learning_rate": 2.9186371669537593e-05, + "loss": 0.1452, "step": 187160 }, { - "epoch": 0.84, - "learning_rate": 8.276086274158109e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.918525312632827e-05, + "loss": 0.1473, "step": 187170 }, { - "epoch": 0.84, - "learning_rate": 8.273844222232186e-06, - "loss": 0.1512, + "epoch": 0.42, + "learning_rate": 2.918413458311895e-05, + "loss": 0.1479, "step": 187180 }, { - "epoch": 0.84, - "learning_rate": 8.271602170306265e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9183016039909623e-05, + "loss": 0.1458, "step": 187190 }, { - "epoch": 0.84, - "learning_rate": 8.269360118380342e-06, - "loss": 0.1437, + "epoch": 0.42, + "learning_rate": 2.91818974967003e-05, + "loss": 0.146, "step": 187200 }, { - "epoch": 0.84, - "learning_rate": 8.26711806645442e-06, - "loss": 0.1431, + "epoch": 0.42, + "learning_rate": 2.9180778953490972e-05, + "loss": 0.1499, "step": 187210 }, { - "epoch": 0.84, - "learning_rate": 8.264876014528498e-06, - "loss": 0.1411, + "epoch": 0.42, + "learning_rate": 2.917966041028165e-05, + "loss": 0.1436, "step": 187220 }, { - "epoch": 0.84, - "learning_rate": 8.262633962602575e-06, - "loss": 0.1402, + "epoch": 0.42, + "learning_rate": 2.9178541867072328e-05, + "loss": 0.149, "step": 187230 }, { - "epoch": 0.84, - "learning_rate": 8.260391910676652e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.9177423323863002e-05, + "loss": 0.1422, "step": 187240 }, { - "epoch": 0.84, - "learning_rate": 8.258149858750729e-06, - "loss": 0.1491, + "epoch": 0.42, + "learning_rate": 2.917630478065368e-05, + "loss": 0.1453, "step": 187250 }, { - "epoch": 0.84, - "learning_rate": 8.255907806824806e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.917518623744435e-05, + "loss": 0.144, "step": 187260 }, { - "epoch": 0.84, - "learning_rate": 8.253665754898884e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.917406769423503e-05, + "loss": 0.1471, "step": 187270 }, { - "epoch": 0.84, - "learning_rate": 8.251423702972961e-06, - "loss": 0.1367, + "epoch": 0.42, + "learning_rate": 2.9172949151025707e-05, + "loss": 0.1408, "step": 187280 }, { - "epoch": 0.84, - "learning_rate": 8.249181651047038e-06, - "loss": 0.1407, + "epoch": 0.42, + "learning_rate": 2.9171830607816382e-05, + "loss": 0.145, "step": 187290 }, { - "epoch": 0.84, - "learning_rate": 8.246939599121115e-06, - "loss": 0.142, + "epoch": 0.42, + "learning_rate": 2.917071206460706e-05, + "loss": 0.1515, "step": 187300 }, { - "epoch": 0.84, - "learning_rate": 8.244697547195193e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.916959352139773e-05, + "loss": 0.1483, "step": 187310 }, { - "epoch": 0.84, - "learning_rate": 8.24245549526927e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.916847497818841e-05, + "loss": 0.1395, "step": 187320 }, { - "epoch": 0.84, - "learning_rate": 8.240213443343348e-06, - "loss": 0.1472, + "epoch": 0.42, + "learning_rate": 2.9167356434979087e-05, + "loss": 0.1535, "step": 187330 }, { - "epoch": 0.84, - "learning_rate": 8.237971391417427e-06, - "loss": 0.1429, + "epoch": 0.42, + "learning_rate": 2.916623789176976e-05, + "loss": 0.1474, "step": 187340 }, { - "epoch": 0.84, - "learning_rate": 8.235729339491504e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.916511934856044e-05, + "loss": 0.1516, "step": 187350 }, { - "epoch": 0.84, - "learning_rate": 8.233487287565581e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.916400080535111e-05, + "loss": 0.144, "step": 187360 }, { - "epoch": 0.84, - "learning_rate": 8.231245235639658e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.916288226214179e-05, + "loss": 0.1453, "step": 187370 }, { - "epoch": 0.84, - "learning_rate": 8.229003183713735e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.916176371893246e-05, + "loss": 0.1409, "step": 187380 }, { - "epoch": 0.84, - "learning_rate": 8.226761131787812e-06, - "loss": 0.1394, + "epoch": 0.42, + "learning_rate": 2.9160645175723137e-05, + "loss": 0.1443, "step": 187390 }, { - "epoch": 0.84, - "learning_rate": 8.22451907986189e-06, - "loss": 0.1466, + "epoch": 0.42, + "learning_rate": 2.915952663251382e-05, + "loss": 0.1497, "step": 187400 }, { - "epoch": 0.84, - "learning_rate": 8.222277027935968e-06, - "loss": 0.1476, + "epoch": 0.42, + "learning_rate": 2.915840808930449e-05, + "loss": 0.1421, "step": 187410 }, { - "epoch": 0.84, - "learning_rate": 8.220034976010045e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9157289546095168e-05, + "loss": 0.1463, "step": 187420 }, { - "epoch": 0.84, - "learning_rate": 8.217792924084122e-06, - "loss": 0.1451, + "epoch": 0.42, + "learning_rate": 2.915617100288584e-05, + "loss": 0.1489, "step": 187430 }, { - "epoch": 0.84, - "learning_rate": 8.215550872158199e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.9155052459676517e-05, + "loss": 0.1505, "step": 187440 }, { - "epoch": 0.84, - "learning_rate": 8.213308820232276e-06, - "loss": 0.1373, + "epoch": 0.42, + "learning_rate": 2.9153933916467195e-05, + "loss": 0.1451, "step": 187450 }, { - "epoch": 0.84, - "learning_rate": 8.211066768306355e-06, - "loss": 0.1418, + "epoch": 0.42, + "learning_rate": 2.915281537325787e-05, + "loss": 0.1451, "step": 187460 }, { - "epoch": 0.84, - "learning_rate": 8.208824716380432e-06, - "loss": 0.1454, + "epoch": 0.42, + "learning_rate": 2.9151696830048547e-05, + "loss": 0.1469, "step": 187470 }, { - "epoch": 0.84, - "learning_rate": 8.20658266445451e-06, - "loss": 0.1459, + "epoch": 0.42, + "learning_rate": 2.915057828683922e-05, + "loss": 0.1496, "step": 187480 }, { - "epoch": 0.84, - "learning_rate": 8.204340612528587e-06, - "loss": 0.14, + "epoch": 0.42, + "learning_rate": 2.9149459743629896e-05, + "loss": 0.1463, "step": 187490 }, { - "epoch": 0.84, - "learning_rate": 8.202098560602664e-06, - "loss": 0.1427, + "epoch": 0.42, + "learning_rate": 2.9148341200420574e-05, + "loss": 0.1477, "step": 187500 }, { - "epoch": 0.84, - "learning_rate": 8.199856508676741e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.914722265721125e-05, + "loss": 0.1494, "step": 187510 }, { - "epoch": 0.84, - "learning_rate": 8.197614456750818e-06, - "loss": 0.146, + "epoch": 0.42, + "learning_rate": 2.9146104114001927e-05, + "loss": 0.1462, "step": 187520 }, { - "epoch": 0.84, - "learning_rate": 8.195372404824896e-06, - "loss": 0.1332, + "epoch": 0.42, + "learning_rate": 2.9144985570792598e-05, + "loss": 0.1438, "step": 187530 }, { - "epoch": 0.84, - "learning_rate": 8.193130352898974e-06, - "loss": 0.1489, + "epoch": 0.42, + "learning_rate": 2.9143867027583276e-05, + "loss": 0.1463, "step": 187540 }, { - "epoch": 0.84, - "learning_rate": 8.190888300973051e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.9142748484373954e-05, + "loss": 0.1422, "step": 187550 }, { - "epoch": 0.84, - "learning_rate": 8.188646249047128e-06, - "loss": 0.1471, + "epoch": 0.42, + "learning_rate": 2.914162994116463e-05, + "loss": 0.1447, "step": 187560 }, { - "epoch": 0.84, - "learning_rate": 8.186404197121205e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.9140511397955306e-05, + "loss": 0.1467, "step": 187570 }, { - "epoch": 0.84, - "learning_rate": 8.184162145195282e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.9139392854745977e-05, + "loss": 0.142, "step": 187580 }, { - "epoch": 0.84, - "learning_rate": 8.18192009326936e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.9138274311536655e-05, + "loss": 0.1424, "step": 187590 }, { - "epoch": 0.84, - "learning_rate": 8.179678041343438e-06, - "loss": 0.1406, + "epoch": 0.42, + "learning_rate": 2.9137155768327333e-05, + "loss": 0.146, "step": 187600 }, { - "epoch": 0.84, - "learning_rate": 8.177435989417517e-06, - "loss": 0.1401, + "epoch": 0.42, + "learning_rate": 2.9136037225118008e-05, + "loss": 0.1489, "step": 187610 }, { - "epoch": 0.84, - "learning_rate": 8.175193937491594e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.9134918681908686e-05, + "loss": 0.1443, "step": 187620 }, { - "epoch": 0.84, - "learning_rate": 8.17295188556567e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.9133800138699357e-05, + "loss": 0.1461, "step": 187630 }, { - "epoch": 0.84, - "learning_rate": 8.170709833639748e-06, - "loss": 0.1465, + "epoch": 0.42, + "learning_rate": 2.9132681595490035e-05, + "loss": 0.1466, "step": 187640 }, { - "epoch": 0.84, - "learning_rate": 8.168467781713825e-06, - "loss": 0.1468, + "epoch": 0.42, + "learning_rate": 2.9131563052280713e-05, + "loss": 0.1465, "step": 187650 }, { - "epoch": 0.84, - "learning_rate": 8.166225729787902e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.9130444509071387e-05, + "loss": 0.1462, "step": 187660 }, { - "epoch": 0.84, - "learning_rate": 8.163983677861979e-06, - "loss": 0.1441, + "epoch": 0.42, + "learning_rate": 2.9129325965862065e-05, + "loss": 0.1427, "step": 187670 }, { - "epoch": 0.84, - "learning_rate": 8.161741625936058e-06, - "loss": 0.1375, + "epoch": 0.42, + "learning_rate": 2.9128207422652736e-05, + "loss": 0.1477, "step": 187680 }, { - "epoch": 0.84, - "learning_rate": 8.159499574010135e-06, - "loss": 0.1481, + "epoch": 0.42, + "learning_rate": 2.9127088879443414e-05, + "loss": 0.1447, "step": 187690 }, { - "epoch": 0.84, - "learning_rate": 8.157257522084212e-06, - "loss": 0.1445, + "epoch": 0.42, + "learning_rate": 2.912597033623409e-05, + "loss": 0.1488, "step": 187700 }, { - "epoch": 0.84, - "learning_rate": 8.155015470158289e-06, - "loss": 0.1432, + "epoch": 0.42, + "learning_rate": 2.9124851793024767e-05, + "loss": 0.1425, "step": 187710 }, { - "epoch": 0.84, - "learning_rate": 8.152773418232366e-06, - "loss": 0.1375, + "epoch": 0.42, + "learning_rate": 2.9123733249815445e-05, + "loss": 0.1474, "step": 187720 }, { - "epoch": 0.84, - "learning_rate": 8.150531366306444e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.9122614706606116e-05, + "loss": 0.1473, "step": 187730 }, { - "epoch": 0.84, - "learning_rate": 8.148289314380521e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.9121496163396794e-05, + "loss": 0.1411, "step": 187740 }, { - "epoch": 0.84, - "learning_rate": 8.1460472624546e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.912037762018747e-05, + "loss": 0.1472, "step": 187750 }, { - "epoch": 0.84, - "learning_rate": 8.143805210528677e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.9119259076978146e-05, + "loss": 0.1488, "step": 187760 }, { - "epoch": 0.84, - "learning_rate": 8.141563158602754e-06, - "loss": 0.1421, + "epoch": 0.42, + "learning_rate": 2.9118140533768824e-05, + "loss": 0.1449, "step": 187770 }, { - "epoch": 0.84, - "learning_rate": 8.139321106676831e-06, - "loss": 0.1495, + "epoch": 0.42, + "learning_rate": 2.9117021990559495e-05, + "loss": 0.1421, "step": 187780 }, { - "epoch": 0.84, - "learning_rate": 8.137079054750908e-06, - "loss": 0.1427, + "epoch": 0.42, + "learning_rate": 2.9115903447350173e-05, + "loss": 0.1472, "step": 187790 }, { - "epoch": 0.84, - "learning_rate": 8.134837002824985e-06, - "loss": 0.1463, + "epoch": 0.42, + "learning_rate": 2.9114784904140844e-05, + "loss": 0.1428, "step": 187800 }, { - "epoch": 0.84, - "learning_rate": 8.132594950899062e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.9113666360931526e-05, + "loss": 0.1475, "step": 187810 }, { - "epoch": 0.84, - "learning_rate": 8.130352898973141e-06, - "loss": 0.1495, + "epoch": 0.42, + "learning_rate": 2.9112547817722204e-05, + "loss": 0.146, "step": 187820 }, { - "epoch": 0.84, - "learning_rate": 8.128110847047218e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.9111429274512875e-05, + "loss": 0.1487, "step": 187830 }, { - "epoch": 0.84, - "learning_rate": 8.125868795121295e-06, - "loss": 0.1435, + "epoch": 0.42, + "learning_rate": 2.9110310731303553e-05, + "loss": 0.1426, "step": 187840 }, { - "epoch": 0.84, - "learning_rate": 8.123626743195372e-06, - "loss": 0.1496, + "epoch": 0.42, + "learning_rate": 2.9109192188094224e-05, + "loss": 0.1462, "step": 187850 }, { - "epoch": 0.84, - "learning_rate": 8.121384691269449e-06, - "loss": 0.1497, + "epoch": 0.42, + "learning_rate": 2.9108073644884902e-05, + "loss": 0.1418, "step": 187860 }, { - "epoch": 0.84, - "learning_rate": 8.119142639343528e-06, - "loss": 0.1387, + "epoch": 0.42, + "learning_rate": 2.9106955101675583e-05, + "loss": 0.1535, "step": 187870 }, { - "epoch": 0.84, - "learning_rate": 8.116900587417605e-06, - "loss": 0.1383, + "epoch": 0.42, + "learning_rate": 2.9105836558466254e-05, + "loss": 0.1453, "step": 187880 }, { - "epoch": 0.84, - "learning_rate": 8.114658535491684e-06, - "loss": 0.1381, + "epoch": 0.42, + "learning_rate": 2.9104718015256932e-05, + "loss": 0.1446, "step": 187890 }, { - "epoch": 0.84, - "learning_rate": 8.11241648356576e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.9103599472047603e-05, + "loss": 0.1486, "step": 187900 }, { - "epoch": 0.84, - "learning_rate": 8.110174431639838e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.910248092883828e-05, + "loss": 0.1492, "step": 187910 }, { - "epoch": 0.84, - "learning_rate": 8.107932379713915e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.910136238562896e-05, + "loss": 0.1433, "step": 187920 }, { - "epoch": 0.84, - "learning_rate": 8.105690327787992e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.9100243842419634e-05, + "loss": 0.1504, "step": 187930 }, { - "epoch": 0.84, - "learning_rate": 8.103448275862069e-06, - "loss": 0.1406, + "epoch": 0.42, + "learning_rate": 2.909912529921031e-05, + "loss": 0.1473, "step": 187940 }, { - "epoch": 0.84, - "learning_rate": 8.101206223936146e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.9098006756000983e-05, + "loss": 0.1455, "step": 187950 }, { - "epoch": 0.84, - "learning_rate": 8.098964172010224e-06, - "loss": 0.1406, + "epoch": 0.42, + "learning_rate": 2.909688821279166e-05, + "loss": 0.1464, "step": 187960 }, { - "epoch": 0.84, - "learning_rate": 8.096722120084301e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.909576966958234e-05, + "loss": 0.1474, "step": 187970 }, { - "epoch": 0.84, - "learning_rate": 8.094480068158379e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.9094651126373013e-05, + "loss": 0.1383, "step": 187980 }, { - "epoch": 0.84, - "learning_rate": 8.092238016232456e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.909353258316369e-05, + "loss": 0.1447, "step": 187990 }, { - "epoch": 0.84, - "learning_rate": 8.089995964306534e-06, - "loss": 0.146, + "epoch": 0.42, + "learning_rate": 2.9092414039954362e-05, + "loss": 0.1493, "step": 188000 }, { - "epoch": 0.84, - "learning_rate": 8.087753912380611e-06, - "loss": 0.1464, + "epoch": 0.42, + "learning_rate": 2.909129549674504e-05, + "loss": 0.1472, "step": 188010 }, { - "epoch": 0.84, - "learning_rate": 8.085511860454688e-06, - "loss": 0.1465, + "epoch": 0.42, + "learning_rate": 2.9090176953535715e-05, + "loss": 0.1449, "step": 188020 }, { - "epoch": 0.84, - "learning_rate": 8.083269808528767e-06, - "loss": 0.1407, + "epoch": 0.42, + "learning_rate": 2.9089058410326393e-05, + "loss": 0.1467, "step": 188030 }, { - "epoch": 0.84, - "learning_rate": 8.081027756602844e-06, - "loss": 0.1404, + "epoch": 0.42, + "learning_rate": 2.908793986711707e-05, + "loss": 0.1463, "step": 188040 }, { - "epoch": 0.84, - "learning_rate": 8.078785704676921e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.9086821323907742e-05, + "loss": 0.1455, "step": 188050 }, { - "epoch": 0.84, - "learning_rate": 8.076543652750998e-06, - "loss": 0.1451, + "epoch": 0.42, + "learning_rate": 2.908570278069842e-05, + "loss": 0.1448, "step": 188060 }, { - "epoch": 0.84, - "learning_rate": 8.074301600825075e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.9084584237489094e-05, + "loss": 0.1486, "step": 188070 }, { - "epoch": 0.84, - "learning_rate": 8.072059548899152e-06, - "loss": 0.1398, + "epoch": 0.42, + "learning_rate": 2.9083465694279772e-05, + "loss": 0.1516, "step": 188080 }, { - "epoch": 0.84, - "learning_rate": 8.069817496973231e-06, - "loss": 0.1421, + "epoch": 0.42, + "learning_rate": 2.908234715107045e-05, + "loss": 0.1451, "step": 188090 }, { - "epoch": 0.84, - "learning_rate": 8.067575445047308e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.908122860786112e-05, + "loss": 0.146, "step": 188100 }, { - "epoch": 0.84, - "learning_rate": 8.065333393121385e-06, - "loss": 0.1414, + "epoch": 0.42, + "learning_rate": 2.90801100646518e-05, + "loss": 0.1461, "step": 188110 }, { - "epoch": 0.84, - "learning_rate": 8.063315546388054e-06, - "loss": 0.1405, + "epoch": 0.42, + "learning_rate": 2.9078991521442474e-05, + "loss": 0.145, "step": 188120 }, { - "epoch": 0.84, - "learning_rate": 8.061073494462131e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.907787297823315e-05, + "loss": 0.1455, "step": 188130 }, { - "epoch": 0.84, - "learning_rate": 8.058831442536208e-06, - "loss": 0.1354, + "epoch": 0.42, + "learning_rate": 2.907675443502383e-05, + "loss": 0.1452, "step": 188140 }, { - "epoch": 0.84, - "learning_rate": 8.056589390610285e-06, - "loss": 0.1388, + "epoch": 0.42, + "learning_rate": 2.90756358918145e-05, + "loss": 0.1478, "step": 188150 }, { - "epoch": 0.84, - "learning_rate": 8.054347338684364e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.907451734860518e-05, + "loss": 0.1448, "step": 188160 }, { - "epoch": 0.84, - "learning_rate": 8.052105286758443e-06, - "loss": 0.1377, + "epoch": 0.42, + "learning_rate": 2.9073398805395853e-05, + "loss": 0.147, "step": 188170 }, { - "epoch": 0.84, - "learning_rate": 8.04986323483252e-06, - "loss": 0.1391, + "epoch": 0.42, + "learning_rate": 2.907228026218653e-05, + "loss": 0.1457, "step": 188180 }, { - "epoch": 0.84, - "learning_rate": 8.047621182906597e-06, - "loss": 0.1413, + "epoch": 0.42, + "learning_rate": 2.907116171897721e-05, + "loss": 0.1415, "step": 188190 }, { - "epoch": 0.84, - "learning_rate": 8.045379130980674e-06, - "loss": 0.1375, + "epoch": 0.42, + "learning_rate": 2.907004317576788e-05, + "loss": 0.1505, "step": 188200 }, { - "epoch": 0.84, - "learning_rate": 8.043137079054751e-06, - "loss": 0.1401, + "epoch": 0.42, + "learning_rate": 2.9068924632558558e-05, + "loss": 0.1474, "step": 188210 }, { - "epoch": 0.84, - "learning_rate": 8.040895027128828e-06, - "loss": 0.1436, + "epoch": 0.42, + "learning_rate": 2.9067806089349233e-05, + "loss": 0.1453, "step": 188220 }, { - "epoch": 0.84, - "learning_rate": 8.038652975202907e-06, - "loss": 0.1495, + "epoch": 0.42, + "learning_rate": 2.906668754613991e-05, + "loss": 0.1419, "step": 188230 }, { - "epoch": 0.84, - "learning_rate": 8.036410923276984e-06, - "loss": 0.1493, + "epoch": 0.42, + "learning_rate": 2.906556900293059e-05, + "loss": 0.1439, "step": 188240 }, { - "epoch": 0.84, - "learning_rate": 8.03416887135106e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.906445045972126e-05, + "loss": 0.1496, "step": 188250 }, { - "epoch": 0.84, - "learning_rate": 8.031926819425138e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.9063331916511938e-05, + "loss": 0.1463, "step": 188260 }, { - "epoch": 0.84, - "learning_rate": 8.029684767499215e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.906221337330261e-05, + "loss": 0.1432, "step": 188270 }, { - "epoch": 0.84, - "learning_rate": 8.027442715573292e-06, - "loss": 0.1487, + "epoch": 0.42, + "learning_rate": 2.9061094830093287e-05, + "loss": 0.1436, "step": 188280 }, { - "epoch": 0.84, - "learning_rate": 8.02520066364737e-06, - "loss": 0.1375, + "epoch": 0.42, + "learning_rate": 2.9059976286883968e-05, + "loss": 0.1426, "step": 188290 }, { - "epoch": 0.84, - "learning_rate": 8.022958611721448e-06, - "loss": 0.1416, + "epoch": 0.42, + "learning_rate": 2.905885774367464e-05, + "loss": 0.1481, "step": 188300 }, { - "epoch": 0.84, - "learning_rate": 8.020716559795526e-06, - "loss": 0.1454, + "epoch": 0.42, + "learning_rate": 2.9057739200465317e-05, + "loss": 0.1427, "step": 188310 }, { - "epoch": 0.84, - "learning_rate": 8.018474507869603e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.9056620657255988e-05, + "loss": 0.1469, "step": 188320 }, { - "epoch": 0.84, - "learning_rate": 8.01623245594368e-06, - "loss": 0.1461, + "epoch": 0.42, + "learning_rate": 2.9055502114046666e-05, + "loss": 0.1441, "step": 188330 }, { - "epoch": 0.84, - "learning_rate": 8.013990404017757e-06, - "loss": 0.1404, + "epoch": 0.42, + "learning_rate": 2.905438357083734e-05, + "loss": 0.1393, "step": 188340 }, { - "epoch": 0.84, - "learning_rate": 8.011748352091834e-06, - "loss": 0.1387, + "epoch": 0.42, + "learning_rate": 2.905326502762802e-05, + "loss": 0.1479, "step": 188350 }, { - "epoch": 0.84, - "learning_rate": 8.009506300165913e-06, - "loss": 0.1467, + "epoch": 0.42, + "learning_rate": 2.9052146484418697e-05, + "loss": 0.1452, "step": 188360 }, { - "epoch": 0.84, - "learning_rate": 8.00726424823999e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.9051027941209368e-05, + "loss": 0.1425, "step": 188370 }, { - "epoch": 0.84, - "learning_rate": 8.005022196314067e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.9049909398000046e-05, + "loss": 0.1422, "step": 188380 }, { - "epoch": 0.84, - "learning_rate": 8.002780144388144e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.904879085479072e-05, + "loss": 0.142, "step": 188390 }, { - "epoch": 0.84, - "learning_rate": 8.000538092462221e-06, - "loss": 0.1408, + "epoch": 0.42, + "learning_rate": 2.9047672311581398e-05, + "loss": 0.1454, "step": 188400 }, { - "epoch": 0.84, - "learning_rate": 7.998296040536298e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.9046553768372076e-05, + "loss": 0.1467, "step": 188410 }, { - "epoch": 0.84, - "learning_rate": 7.996053988610375e-06, - "loss": 0.1484, + "epoch": 0.42, + "learning_rate": 2.9045435225162747e-05, + "loss": 0.1464, "step": 188420 }, { - "epoch": 0.84, - "learning_rate": 7.993811936684454e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.9044316681953425e-05, + "loss": 0.1388, "step": 188430 }, { - "epoch": 0.84, - "learning_rate": 7.991569884758531e-06, - "loss": 0.1409, + "epoch": 0.42, + "learning_rate": 2.90431981387441e-05, + "loss": 0.1488, "step": 188440 }, { - "epoch": 0.84, - "learning_rate": 7.98932783283261e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.9042079595534778e-05, + "loss": 0.1418, "step": 188450 }, { - "epoch": 0.84, - "learning_rate": 7.987085780906687e-06, - "loss": 0.1435, + "epoch": 0.42, + "learning_rate": 2.9040961052325456e-05, + "loss": 0.1451, "step": 188460 }, { - "epoch": 0.84, - "learning_rate": 7.984843728980764e-06, - "loss": 0.1468, + "epoch": 0.42, + "learning_rate": 2.9039842509116127e-05, + "loss": 0.1425, "step": 188470 }, { - "epoch": 0.84, - "learning_rate": 7.98260167705484e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.9038723965906805e-05, + "loss": 0.1447, "step": 188480 }, { - "epoch": 0.84, - "learning_rate": 7.980359625128918e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.903760542269748e-05, + "loss": 0.1496, "step": 188490 }, { - "epoch": 0.84, - "learning_rate": 7.978117573202997e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.9036486879488157e-05, + "loss": 0.1484, "step": 188500 }, { - "epoch": 0.84, - "learning_rate": 7.975875521277074e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.9035368336278835e-05, + "loss": 0.1518, "step": 188510 }, { - "epoch": 0.84, - "learning_rate": 7.97363346935115e-06, - "loss": 0.1467, + "epoch": 0.42, + "learning_rate": 2.9034249793069506e-05, + "loss": 0.1432, "step": 188520 }, { - "epoch": 0.84, - "learning_rate": 7.971391417425228e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.9033131249860184e-05, + "loss": 0.1424, "step": 188530 }, { - "epoch": 0.84, - "learning_rate": 7.969149365499305e-06, - "loss": 0.1421, + "epoch": 0.42, + "learning_rate": 2.903201270665086e-05, + "loss": 0.1495, "step": 188540 }, { - "epoch": 0.84, - "learning_rate": 7.966907313573382e-06, - "loss": 0.142, + "epoch": 0.42, + "learning_rate": 2.9030894163441537e-05, + "loss": 0.1433, "step": 188550 }, { - "epoch": 0.84, - "learning_rate": 7.96466526164746e-06, - "loss": 0.1348, + "epoch": 0.42, + "learning_rate": 2.9029775620232214e-05, + "loss": 0.1398, "step": 188560 }, { - "epoch": 0.84, - "learning_rate": 7.962423209721537e-06, - "loss": 0.1404, + "epoch": 0.42, + "learning_rate": 2.9028657077022886e-05, + "loss": 0.1429, "step": 188570 }, { - "epoch": 0.84, - "learning_rate": 7.960181157795616e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.9027538533813564e-05, + "loss": 0.1471, "step": 188580 }, { - "epoch": 0.84, - "learning_rate": 7.957939105869693e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9026419990604238e-05, + "loss": 0.1466, "step": 188590 }, { - "epoch": 0.84, - "learning_rate": 7.95569705394377e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.9025301447394916e-05, + "loss": 0.1463, "step": 188600 }, { - "epoch": 0.84, - "learning_rate": 7.953455002017847e-06, - "loss": 0.1432, + "epoch": 0.42, + "learning_rate": 2.9024182904185594e-05, + "loss": 0.1439, "step": 188610 }, { - "epoch": 0.84, - "learning_rate": 7.951212950091924e-06, - "loss": 0.139, + "epoch": 0.42, + "learning_rate": 2.9023064360976265e-05, + "loss": 0.1485, "step": 188620 }, { - "epoch": 0.84, - "learning_rate": 7.948970898166001e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.9021945817766943e-05, + "loss": 0.1462, "step": 188630 }, { - "epoch": 0.84, - "learning_rate": 7.94672884624008e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.9020827274557618e-05, + "loss": 0.1399, "step": 188640 }, { - "epoch": 0.84, - "learning_rate": 7.944486794314157e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.9019708731348295e-05, + "loss": 0.1452, "step": 188650 }, { - "epoch": 0.84, - "learning_rate": 7.942244742388234e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.9018590188138967e-05, + "loss": 0.1473, "step": 188660 }, { - "epoch": 0.84, - "learning_rate": 7.940002690462311e-06, - "loss": 0.1413, + "epoch": 0.42, + "learning_rate": 2.9017471644929645e-05, + "loss": 0.1423, "step": 188670 }, { - "epoch": 0.84, - "learning_rate": 7.937760638536388e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.9016353101720322e-05, + "loss": 0.1451, "step": 188680 }, { - "epoch": 0.84, - "learning_rate": 7.935518586610465e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.9015234558510994e-05, + "loss": 0.1431, "step": 188690 }, { - "epoch": 0.84, - "learning_rate": 7.933276534684544e-06, - "loss": 0.1468, + "epoch": 0.42, + "learning_rate": 2.9014116015301675e-05, + "loss": 0.1459, "step": 188700 }, { - "epoch": 0.84, - "learning_rate": 7.93103448275862e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.9012997472092346e-05, + "loss": 0.1519, "step": 188710 }, { - "epoch": 0.84, - "learning_rate": 7.9287924308327e-06, - "loss": 0.1462, + "epoch": 0.42, + "learning_rate": 2.9011878928883024e-05, + "loss": 0.146, "step": 188720 }, { - "epoch": 0.84, - "learning_rate": 7.926550378906777e-06, - "loss": 0.1496, + "epoch": 0.42, + "learning_rate": 2.9010760385673702e-05, + "loss": 0.1441, "step": 188730 }, { - "epoch": 0.84, - "learning_rate": 7.924308326980854e-06, - "loss": 0.1488, + "epoch": 0.42, + "learning_rate": 2.9009641842464373e-05, + "loss": 0.146, "step": 188740 }, { - "epoch": 0.84, - "learning_rate": 7.92206627505493e-06, - "loss": 0.1451, + "epoch": 0.42, + "learning_rate": 2.900852329925505e-05, + "loss": 0.1467, "step": 188750 }, { - "epoch": 0.84, - "learning_rate": 7.919824223129008e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.9007404756045726e-05, + "loss": 0.1466, "step": 188760 }, { - "epoch": 0.84, - "learning_rate": 7.917582171203085e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.9006286212836403e-05, + "loss": 0.1436, "step": 188770 }, { - "epoch": 0.84, - "learning_rate": 7.915340119277163e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.900516766962708e-05, + "loss": 0.1492, "step": 188780 }, { - "epoch": 0.84, - "learning_rate": 7.91309806735124e-06, - "loss": 0.1377, + "epoch": 0.42, + "learning_rate": 2.9004049126417753e-05, + "loss": 0.1479, "step": 188790 }, { - "epoch": 0.84, - "learning_rate": 7.910856015425317e-06, + "epoch": 0.42, + "learning_rate": 2.900293058320843e-05, "loss": 0.1456, "step": 188800 }, { - "epoch": 0.84, - "learning_rate": 7.908613963499394e-06, + "epoch": 0.42, + "learning_rate": 2.9001812039999105e-05, "loss": 0.1452, "step": 188810 }, { - "epoch": 0.84, - "learning_rate": 7.906371911573471e-06, - "loss": 0.1465, + "epoch": 0.42, + "learning_rate": 2.9000693496789783e-05, + "loss": 0.1427, "step": 188820 }, { - "epoch": 0.84, - "learning_rate": 7.90412985964755e-06, - "loss": 0.1362, + "epoch": 0.42, + "learning_rate": 2.899957495358046e-05, + "loss": 0.1469, "step": 188830 }, { - "epoch": 0.84, - "learning_rate": 7.901887807721627e-06, - "loss": 0.1429, + "epoch": 0.42, + "learning_rate": 2.8998456410371132e-05, + "loss": 0.14, "step": 188840 }, { - "epoch": 0.84, - "learning_rate": 7.899645755795706e-06, - "loss": 0.1458, + "epoch": 0.42, + "learning_rate": 2.899733786716181e-05, + "loss": 0.1466, "step": 188850 }, { - "epoch": 0.84, - "learning_rate": 7.897403703869783e-06, - "loss": 0.1414, + "epoch": 0.42, + "learning_rate": 2.8996219323952485e-05, + "loss": 0.1397, "step": 188860 }, { - "epoch": 0.84, - "learning_rate": 7.89516165194386e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.8995100780743162e-05, + "loss": 0.1438, "step": 188870 }, { - "epoch": 0.84, - "learning_rate": 7.892919600017937e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.899398223753384e-05, + "loss": 0.1461, "step": 188880 }, { - "epoch": 0.84, - "learning_rate": 7.890677548092014e-06, - "loss": 0.1485, + "epoch": 0.42, + "learning_rate": 2.899286369432451e-05, + "loss": 0.1515, "step": 188890 }, { - "epoch": 0.84, - "learning_rate": 7.888435496166091e-06, - "loss": 0.1408, + "epoch": 0.42, + "learning_rate": 2.899174515111519e-05, + "loss": 0.1454, "step": 188900 }, { - "epoch": 0.84, - "learning_rate": 7.886193444240168e-06, - "loss": 0.1487, + "epoch": 0.42, + "learning_rate": 2.8990626607905864e-05, + "loss": 0.1434, "step": 188910 }, { - "epoch": 0.84, - "learning_rate": 7.883951392314247e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.8989508064696542e-05, + "loss": 0.1427, "step": 188920 }, { - "epoch": 0.84, - "learning_rate": 7.881709340388324e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.898838952148722e-05, + "loss": 0.1462, "step": 188930 }, { - "epoch": 0.84, - "learning_rate": 7.8794672884624e-06, - "loss": 0.1485, + "epoch": 0.42, + "learning_rate": 2.898727097827789e-05, + "loss": 0.1448, "step": 188940 }, { - "epoch": 0.84, - "learning_rate": 7.877225236536478e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.898615243506857e-05, + "loss": 0.1475, "step": 188950 }, { - "epoch": 0.84, - "learning_rate": 7.874983184610555e-06, - "loss": 0.1454, + "epoch": 0.42, + "learning_rate": 2.8985033891859243e-05, + "loss": 0.1475, "step": 188960 }, { - "epoch": 0.84, - "learning_rate": 7.872741132684634e-06, - "loss": 0.1462, + "epoch": 0.42, + "learning_rate": 2.898391534864992e-05, + "loss": 0.1476, "step": 188970 }, { - "epoch": 0.84, - "learning_rate": 7.87049908075871e-06, - "loss": 0.1461, + "epoch": 0.42, + "learning_rate": 2.8982796805440593e-05, + "loss": 0.1485, "step": 188980 }, { - "epoch": 0.84, - "learning_rate": 7.86825702883279e-06, - "loss": 0.1409, + "epoch": 0.42, + "learning_rate": 2.898167826223127e-05, + "loss": 0.1454, "step": 188990 }, { - "epoch": 0.84, - "learning_rate": 7.866014976906866e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.898055971902195e-05, + "loss": 0.1522, "step": 189000 }, { - "epoch": 0.84, - "learning_rate": 7.863772924980943e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.8979441175812623e-05, + "loss": 0.1453, "step": 189010 }, { - "epoch": 0.84, - "learning_rate": 7.86153087305502e-06, - "loss": 0.1484, + "epoch": 0.42, + "learning_rate": 2.89783226326033e-05, + "loss": 0.143, "step": 189020 }, { - "epoch": 0.84, - "learning_rate": 7.859288821129097e-06, - "loss": 0.1437, + "epoch": 0.42, + "learning_rate": 2.8977204089393972e-05, + "loss": 0.1436, "step": 189030 }, { - "epoch": 0.84, - "learning_rate": 7.857046769203174e-06, - "loss": 0.136, + "epoch": 0.42, + "learning_rate": 2.897608554618465e-05, + "loss": 0.1476, "step": 189040 }, { - "epoch": 0.84, - "learning_rate": 7.854804717277253e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.8974967002975328e-05, + "loss": 0.1468, "step": 189050 }, { - "epoch": 0.84, - "learning_rate": 7.85256266535133e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.8973848459766002e-05, + "loss": 0.1489, "step": 189060 }, { - "epoch": 0.84, - "learning_rate": 7.850320613425407e-06, - "loss": 0.1369, + "epoch": 0.42, + "learning_rate": 2.897272991655668e-05, + "loss": 0.1434, "step": 189070 }, { - "epoch": 0.84, - "learning_rate": 7.848078561499484e-06, - "loss": 0.1401, + "epoch": 0.42, + "learning_rate": 2.897161137334735e-05, + "loss": 0.1441, "step": 189080 }, { - "epoch": 0.84, - "learning_rate": 7.845836509573561e-06, - "loss": 0.1414, + "epoch": 0.42, + "learning_rate": 2.897049283013803e-05, + "loss": 0.146, "step": 189090 }, { - "epoch": 0.84, - "learning_rate": 7.84359445764764e-06, - "loss": 0.1457, + "epoch": 0.42, + "learning_rate": 2.8969374286928707e-05, + "loss": 0.1428, "step": 189100 }, { - "epoch": 0.84, - "learning_rate": 7.841352405721717e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.8968255743719382e-05, + "loss": 0.1456, "step": 189110 }, { - "epoch": 0.84, - "learning_rate": 7.839110353795796e-06, - "loss": 0.1448, + "epoch": 0.42, + "learning_rate": 2.896713720051006e-05, + "loss": 0.1462, "step": 189120 }, { - "epoch": 0.84, - "learning_rate": 7.836868301869873e-06, - "loss": 0.1441, + "epoch": 0.42, + "learning_rate": 2.896601865730073e-05, + "loss": 0.1445, "step": 189130 }, { - "epoch": 0.84, - "learning_rate": 7.83462624994395e-06, - "loss": 0.1402, + "epoch": 0.42, + "learning_rate": 2.896490011409141e-05, + "loss": 0.1492, "step": 189140 }, { - "epoch": 0.84, - "learning_rate": 7.832384198018027e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.8963781570882087e-05, + "loss": 0.1472, "step": 189150 }, { - "epoch": 0.84, - "learning_rate": 7.830142146092104e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.8962663027672758e-05, + "loss": 0.147, "step": 189160 }, { - "epoch": 0.84, - "learning_rate": 7.82790009416618e-06, - "loss": 0.1387, + "epoch": 0.42, + "learning_rate": 2.896154448446344e-05, + "loss": 0.1436, "step": 189170 }, { - "epoch": 0.84, - "learning_rate": 7.825658042240258e-06, - "loss": 0.1425, + "epoch": 0.42, + "learning_rate": 2.896042594125411e-05, + "loss": 0.1471, "step": 189180 }, { - "epoch": 0.84, - "learning_rate": 7.823415990314337e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.895930739804479e-05, + "loss": 0.1421, "step": 189190 }, { - "epoch": 0.84, - "learning_rate": 7.821173938388414e-06, - "loss": 0.1431, + "epoch": 0.42, + "learning_rate": 2.8958188854835466e-05, + "loss": 0.1451, "step": 189200 }, { - "epoch": 0.84, - "learning_rate": 7.81893188646249e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.8957070311626137e-05, + "loss": 0.1469, "step": 189210 }, { - "epoch": 0.84, - "learning_rate": 7.816689834536568e-06, - "loss": 0.1415, + "epoch": 0.42, + "learning_rate": 2.8955951768416815e-05, + "loss": 0.1452, "step": 189220 }, { - "epoch": 0.84, - "learning_rate": 7.814447782610645e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.895483322520749e-05, + "loss": 0.1456, "step": 189230 }, { - "epoch": 0.84, - "learning_rate": 7.812205730684723e-06, - "loss": 0.1443, + "epoch": 0.42, + "learning_rate": 2.8953714681998168e-05, + "loss": 0.1429, "step": 189240 }, { - "epoch": 0.84, - "learning_rate": 7.8099636787588e-06, - "loss": 0.146, + "epoch": 0.42, + "learning_rate": 2.895259613878884e-05, + "loss": 0.1474, "step": 189250 }, { - "epoch": 0.84, - "learning_rate": 7.807721626832879e-06, - "loss": 0.1402, + "epoch": 0.42, + "learning_rate": 2.8951477595579517e-05, + "loss": 0.1453, "step": 189260 }, { - "epoch": 0.84, - "learning_rate": 7.805479574906956e-06, - "loss": 0.1399, + "epoch": 0.42, + "learning_rate": 2.8950359052370195e-05, + "loss": 0.1447, "step": 189270 }, { - "epoch": 0.84, - "learning_rate": 7.803237522981033e-06, - "loss": 0.1453, + "epoch": 0.42, + "learning_rate": 2.894924050916087e-05, + "loss": 0.1406, "step": 189280 }, { - "epoch": 0.85, - "learning_rate": 7.80099547105511e-06, - "loss": 0.1469, + "epoch": 0.42, + "learning_rate": 2.8948121965951547e-05, + "loss": 0.1479, "step": 189290 }, { - "epoch": 0.85, - "learning_rate": 7.798753419129187e-06, - "loss": 0.142, + "epoch": 0.42, + "learning_rate": 2.894700342274222e-05, + "loss": 0.1457, "step": 189300 }, { - "epoch": 0.85, - "learning_rate": 7.796511367203264e-06, - "loss": 0.1416, + "epoch": 0.42, + "learning_rate": 2.8945884879532896e-05, + "loss": 0.1452, "step": 189310 }, { - "epoch": 0.85, - "learning_rate": 7.794269315277341e-06, - "loss": 0.1475, + "epoch": 0.42, + "learning_rate": 2.8944766336323574e-05, + "loss": 0.1466, "step": 189320 }, { - "epoch": 0.85, - "learning_rate": 7.79202726335142e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.894364779311425e-05, + "loss": 0.1412, "step": 189330 }, { - "epoch": 0.85, - "learning_rate": 7.789785211425497e-06, - "loss": 0.1437, + "epoch": 0.42, + "learning_rate": 2.8942529249904927e-05, + "loss": 0.1526, "step": 189340 }, { - "epoch": 0.85, - "learning_rate": 7.787543159499574e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.8941410706695598e-05, + "loss": 0.1468, "step": 189350 }, { - "epoch": 0.85, - "learning_rate": 7.785301107573651e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.8940292163486276e-05, + "loss": 0.1467, "step": 189360 }, { - "epoch": 0.85, - "learning_rate": 7.78305905564773e-06, - "loss": 0.1482, + "epoch": 0.42, + "learning_rate": 2.8939173620276954e-05, + "loss": 0.1473, "step": 189370 }, { - "epoch": 0.85, - "learning_rate": 7.780817003721807e-06, - "loss": 0.1432, + "epoch": 0.42, + "learning_rate": 2.893805507706763e-05, + "loss": 0.1462, "step": 189380 }, { - "epoch": 0.85, - "learning_rate": 7.778574951795884e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.8936936533858306e-05, + "loss": 0.1383, "step": 189390 }, { - "epoch": 0.85, - "learning_rate": 7.776332899869963e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.8935817990648977e-05, + "loss": 0.1508, "step": 189400 }, { - "epoch": 0.85, - "learning_rate": 7.77409084794404e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.8934699447439655e-05, + "loss": 0.1461, "step": 189410 }, { - "epoch": 0.85, - "learning_rate": 7.771848796018117e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.8933580904230333e-05, + "loss": 0.1427, "step": 189420 }, { - "epoch": 0.85, - "learning_rate": 7.769606744092194e-06, - "loss": 0.1414, + "epoch": 0.42, + "learning_rate": 2.8932462361021008e-05, + "loss": 0.1455, "step": 189430 }, { - "epoch": 0.85, - "learning_rate": 7.76736469216627e-06, - "loss": 0.147, + "epoch": 0.42, + "learning_rate": 2.8931343817811686e-05, + "loss": 0.1508, "step": 189440 }, { - "epoch": 0.85, - "learning_rate": 7.765122640240348e-06, - "loss": 0.1395, + "epoch": 0.42, + "learning_rate": 2.8930225274602357e-05, + "loss": 0.1472, "step": 189450 }, { - "epoch": 0.85, - "learning_rate": 7.762880588314425e-06, - "loss": 0.1401, + "epoch": 0.42, + "learning_rate": 2.8929106731393035e-05, + "loss": 0.143, "step": 189460 }, { - "epoch": 0.85, - "learning_rate": 7.760638536388503e-06, - "loss": 0.1434, + "epoch": 0.42, + "learning_rate": 2.8927988188183713e-05, + "loss": 0.1453, "step": 189470 }, { - "epoch": 0.85, - "learning_rate": 7.75839648446258e-06, - "loss": 0.145, + "epoch": 0.42, + "learning_rate": 2.8926869644974387e-05, + "loss": 0.1406, "step": 189480 }, { - "epoch": 0.85, - "learning_rate": 7.756154432536657e-06, - "loss": 0.1406, + "epoch": 0.42, + "learning_rate": 2.8925751101765065e-05, + "loss": 0.1411, "step": 189490 }, { - "epoch": 0.85, - "learning_rate": 7.753912380610734e-06, - "loss": 0.1373, + "epoch": 0.42, + "learning_rate": 2.8924632558555736e-05, + "loss": 0.1443, "step": 189500 }, { - "epoch": 0.85, - "learning_rate": 7.751670328684813e-06, - "loss": 0.1371, + "epoch": 0.42, + "learning_rate": 2.8923514015346414e-05, + "loss": 0.1435, "step": 189510 }, { - "epoch": 0.85, - "learning_rate": 7.74942827675889e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.8922395472137092e-05, + "loss": 0.1464, "step": 189520 }, { - "epoch": 0.85, - "learning_rate": 7.747186224832967e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.8921276928927767e-05, + "loss": 0.1475, "step": 189530 }, { - "epoch": 0.85, - "learning_rate": 7.744944172907046e-06, - "loss": 0.1398, + "epoch": 0.42, + "learning_rate": 2.8920158385718445e-05, + "loss": 0.1433, "step": 189540 }, { - "epoch": 0.85, - "learning_rate": 7.742702120981123e-06, - "loss": 0.1381, + "epoch": 0.42, + "learning_rate": 2.8919039842509116e-05, + "loss": 0.1496, "step": 189550 }, { - "epoch": 0.85, - "learning_rate": 7.7404600690552e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.8917921299299794e-05, + "loss": 0.1437, "step": 189560 }, { - "epoch": 0.85, - "learning_rate": 7.738218017129277e-06, - "loss": 0.1417, + "epoch": 0.42, + "learning_rate": 2.8916802756090465e-05, + "loss": 0.1475, "step": 189570 }, { - "epoch": 0.85, - "learning_rate": 7.735975965203354e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.8915684212881143e-05, + "loss": 0.1489, "step": 189580 }, { - "epoch": 0.85, - "learning_rate": 7.733733913277431e-06, + "epoch": 0.42, + "learning_rate": 2.8914565669671824e-05, "loss": 0.1429, "step": 189590 }, { - "epoch": 0.85, - "learning_rate": 7.731491861351508e-06, - "loss": 0.1427, + "epoch": 0.42, + "learning_rate": 2.8913447126462495e-05, + "loss": 0.1474, "step": 189600 }, { - "epoch": 0.85, - "learning_rate": 7.729249809425587e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.8912328583253173e-05, + "loss": 0.1416, "step": 189610 }, { - "epoch": 0.85, - "learning_rate": 7.727007757499664e-06, - "loss": 0.1454, + "epoch": 0.42, + "learning_rate": 2.8911210040043844e-05, + "loss": 0.1462, "step": 189620 }, { - "epoch": 0.85, - "learning_rate": 7.724765705573741e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.8910091496834522e-05, + "loss": 0.1438, "step": 189630 }, { - "epoch": 0.85, - "learning_rate": 7.72252365364782e-06, - "loss": 0.1416, + "epoch": 0.42, + "learning_rate": 2.89089729536252e-05, + "loss": 0.1467, "step": 189640 }, { - "epoch": 0.85, - "learning_rate": 7.720281601721897e-06, - "loss": 0.144, + "epoch": 0.42, + "learning_rate": 2.8907854410415875e-05, + "loss": 0.1454, "step": 189650 }, { - "epoch": 0.85, - "learning_rate": 7.718039549795974e-06, - "loss": 0.1371, + "epoch": 0.42, + "learning_rate": 2.8906735867206553e-05, + "loss": 0.1447, "step": 189660 }, { - "epoch": 0.85, - "learning_rate": 7.71579749787005e-06, - "loss": 0.1411, + "epoch": 0.42, + "learning_rate": 2.8905617323997224e-05, + "loss": 0.1421, "step": 189670 }, { - "epoch": 0.85, - "learning_rate": 7.71355544594413e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.8904498780787902e-05, + "loss": 0.1417, "step": 189680 }, { - "epoch": 0.85, - "learning_rate": 7.711313394018206e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.890338023757858e-05, + "loss": 0.1452, "step": 189690 }, { - "epoch": 0.85, - "learning_rate": 7.709071342092283e-06, - "loss": 0.1391, + "epoch": 0.42, + "learning_rate": 2.8902261694369254e-05, + "loss": 0.1424, "step": 189700 }, { - "epoch": 0.85, - "learning_rate": 7.70682929016636e-06, - "loss": 0.1387, + "epoch": 0.42, + "learning_rate": 2.8901143151159932e-05, + "loss": 0.1439, "step": 189710 }, { - "epoch": 0.85, - "learning_rate": 7.704587238240437e-06, - "loss": 0.1465, + "epoch": 0.42, + "learning_rate": 2.8900024607950603e-05, + "loss": 0.14, "step": 189720 }, { - "epoch": 0.85, - "learning_rate": 7.702345186314514e-06, - "loss": 0.1438, + "epoch": 0.42, + "learning_rate": 2.889890606474128e-05, + "loss": 0.1417, "step": 189730 }, { - "epoch": 0.85, - "learning_rate": 7.700103134388593e-06, - "loss": 0.1435, + "epoch": 0.42, + "learning_rate": 2.889778752153196e-05, + "loss": 0.1425, "step": 189740 }, { - "epoch": 0.85, - "learning_rate": 7.69786108246267e-06, - "loss": 0.1429, + "epoch": 0.42, + "learning_rate": 2.8896668978322634e-05, + "loss": 0.1472, "step": 189750 }, { - "epoch": 0.85, - "learning_rate": 7.695619030536747e-06, - "loss": 0.1409, + "epoch": 0.42, + "learning_rate": 2.889555043511331e-05, + "loss": 0.1414, "step": 189760 }, { - "epoch": 0.85, - "learning_rate": 7.693376978610824e-06, - "loss": 0.1441, + "epoch": 0.42, + "learning_rate": 2.8894431891903983e-05, + "loss": 0.1416, "step": 189770 }, { - "epoch": 0.85, - "learning_rate": 7.691134926684903e-06, - "loss": 0.1406, + "epoch": 0.42, + "learning_rate": 2.889331334869466e-05, + "loss": 0.1507, "step": 189780 }, { - "epoch": 0.85, - "learning_rate": 7.68889287475898e-06, - "loss": 0.1448, + "epoch": 0.42, + "learning_rate": 2.889219480548534e-05, + "loss": 0.144, "step": 189790 }, { - "epoch": 0.85, - "learning_rate": 7.686650822833057e-06, - "loss": 0.1469, + "epoch": 0.42, + "learning_rate": 2.8891076262276013e-05, + "loss": 0.1439, "step": 189800 }, { - "epoch": 0.85, - "learning_rate": 7.684408770907136e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.888995771906669e-05, + "loss": 0.1482, "step": 189810 }, { - "epoch": 0.85, - "learning_rate": 7.682166718981213e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.8888839175857362e-05, + "loss": 0.146, "step": 189820 }, { - "epoch": 0.85, - "learning_rate": 7.67992466705529e-06, - "loss": 0.1411, + "epoch": 0.42, + "learning_rate": 2.888772063264804e-05, + "loss": 0.1497, "step": 189830 }, { - "epoch": 0.85, - "learning_rate": 7.677682615129367e-06, - "loss": 0.1446, + "epoch": 0.42, + "learning_rate": 2.8886602089438718e-05, + "loss": 0.1435, "step": 189840 }, { - "epoch": 0.85, - "learning_rate": 7.675440563203444e-06, - "loss": 0.1422, + "epoch": 0.42, + "learning_rate": 2.8885483546229393e-05, + "loss": 0.14, "step": 189850 }, { - "epoch": 0.85, - "learning_rate": 7.673198511277521e-06, - "loss": 0.1385, + "epoch": 0.42, + "learning_rate": 2.888436500302007e-05, + "loss": 0.1393, "step": 189860 }, { - "epoch": 0.85, - "learning_rate": 7.670956459351598e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.8883246459810742e-05, + "loss": 0.1446, "step": 189870 }, { - "epoch": 0.85, - "learning_rate": 7.668714407425677e-06, - "loss": 0.1442, + "epoch": 0.42, + "learning_rate": 2.888212791660142e-05, + "loss": 0.1465, "step": 189880 }, { - "epoch": 0.85, - "learning_rate": 7.666472355499754e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.8881009373392094e-05, + "loss": 0.1485, "step": 189890 }, { - "epoch": 0.85, - "learning_rate": 7.66423030357383e-06, - "loss": 0.1453, + "epoch": 0.42, + "learning_rate": 2.8879890830182772e-05, + "loss": 0.141, "step": 189900 }, { - "epoch": 0.85, - "learning_rate": 7.66198825164791e-06, - "loss": 0.1444, + "epoch": 0.42, + "learning_rate": 2.887877228697345e-05, + "loss": 0.1465, "step": 189910 }, { - "epoch": 0.85, - "learning_rate": 7.659746199721986e-06, - "loss": 0.1366, + "epoch": 0.42, + "learning_rate": 2.887765374376412e-05, + "loss": 0.149, "step": 189920 }, { - "epoch": 0.85, - "learning_rate": 7.657504147796063e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.88765352005548e-05, + "loss": 0.1398, "step": 189930 }, { - "epoch": 0.85, - "learning_rate": 7.65526209587014e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.8875416657345474e-05, + "loss": 0.1498, "step": 189940 }, { - "epoch": 0.85, - "learning_rate": 7.65302004394422e-06, - "loss": 0.1413, + "epoch": 0.42, + "learning_rate": 2.887429811413615e-05, + "loss": 0.1447, "step": 189950 }, { - "epoch": 0.85, - "learning_rate": 7.650777992018296e-06, - "loss": 0.1416, + "epoch": 0.42, + "learning_rate": 2.887317957092683e-05, + "loss": 0.1431, "step": 189960 }, { - "epoch": 0.85, - "learning_rate": 7.648535940092373e-06, - "loss": 0.1409, + "epoch": 0.42, + "learning_rate": 2.88720610277175e-05, + "loss": 0.1429, "step": 189970 }, { - "epoch": 0.85, - "learning_rate": 7.64629388816645e-06, - "loss": 0.1404, + "epoch": 0.42, + "learning_rate": 2.887094248450818e-05, + "loss": 0.1453, "step": 189980 }, { - "epoch": 0.85, - "learning_rate": 7.644051836240527e-06, - "loss": 0.1426, + "epoch": 0.42, + "learning_rate": 2.886982394129885e-05, + "loss": 0.1435, "step": 189990 }, { - "epoch": 0.85, - "learning_rate": 7.641809784314604e-06, - "loss": 0.1373, + "epoch": 0.42, + "learning_rate": 2.886870539808953e-05, + "loss": 0.1409, "step": 190000 }, { - "epoch": 0.85, - "learning_rate": 7.639567732388681e-06, - "loss": 0.1419, + "epoch": 0.42, + "learning_rate": 2.886758685488021e-05, + "loss": 0.1434, "step": 190010 }, { - "epoch": 0.85, - "learning_rate": 7.63732568046276e-06, - "loss": 0.1394, + "epoch": 0.42, + "learning_rate": 2.886646831167088e-05, + "loss": 0.1435, "step": 190020 }, { - "epoch": 0.85, - "learning_rate": 7.635083628536837e-06, - "loss": 0.1467, + "epoch": 0.42, + "learning_rate": 2.8865349768461558e-05, + "loss": 0.1471, "step": 190030 }, { - "epoch": 0.85, - "learning_rate": 7.632841576610914e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.886423122525223e-05, + "loss": 0.1461, "step": 190040 }, { - "epoch": 0.85, - "learning_rate": 7.630599524684993e-06, - "loss": 0.1433, + "epoch": 0.42, + "learning_rate": 2.8863112682042907e-05, + "loss": 0.1487, "step": 190050 }, { - "epoch": 0.85, - "learning_rate": 7.628357472759069e-06, - "loss": 0.1389, + "epoch": 0.42, + "learning_rate": 2.886199413883359e-05, + "loss": 0.1467, "step": 190060 }, { - "epoch": 0.85, - "learning_rate": 7.626115420833147e-06, - "loss": 0.1412, + "epoch": 0.42, + "learning_rate": 2.886087559562426e-05, + "loss": 0.1443, "step": 190070 }, { - "epoch": 0.85, - "learning_rate": 7.623873368907224e-06, - "loss": 0.1399, + "epoch": 0.42, + "learning_rate": 2.8859757052414938e-05, + "loss": 0.1403, "step": 190080 }, { - "epoch": 0.85, - "learning_rate": 7.621631316981303e-06, - "loss": 0.1428, + "epoch": 0.42, + "learning_rate": 2.885863850920561e-05, + "loss": 0.1502, "step": 190090 }, { - "epoch": 0.85, - "learning_rate": 7.61938926505538e-06, - "loss": 0.1395, + "epoch": 0.42, + "learning_rate": 2.8857519965996287e-05, + "loss": 0.1483, "step": 190100 }, { - "epoch": 0.85, - "learning_rate": 7.617147213129457e-06, - "loss": 0.1473, + "epoch": 0.42, + "learning_rate": 2.8856401422786965e-05, + "loss": 0.1425, "step": 190110 }, { - "epoch": 0.85, - "learning_rate": 7.614905161203534e-06, - "loss": 0.1436, + "epoch": 0.42, + "learning_rate": 2.8855394733898573e-05, + "loss": 0.1448, "step": 190120 }, { - "epoch": 0.85, - "learning_rate": 7.612663109277611e-06, - "loss": 0.1392, + "epoch": 0.42, + "learning_rate": 2.885427619068925e-05, + "loss": 0.1423, "step": 190130 }, { - "epoch": 0.85, - "learning_rate": 7.6104210573516886e-06, - "loss": 0.1407, + "epoch": 0.42, + "learning_rate": 2.8853157647479922e-05, + "loss": 0.1463, "step": 190140 }, { - "epoch": 0.85, - "learning_rate": 7.608179005425766e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.88520391042706e-05, + "loss": 0.147, "step": 190150 }, { - "epoch": 0.85, - "learning_rate": 7.605936953499844e-06, - "loss": 0.1466, + "epoch": 0.42, + "learning_rate": 2.885092056106127e-05, + "loss": 0.1449, "step": 190160 }, { - "epoch": 0.85, - "learning_rate": 7.603919106766513e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.8849802017851953e-05, + "loss": 0.1449, "step": 190170 }, { - "epoch": 0.85, - "learning_rate": 7.601677054840591e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.884868347464263e-05, + "loss": 0.1432, "step": 190180 }, { - "epoch": 0.85, - "learning_rate": 7.599435002914668e-06, - "loss": 0.1449, + "epoch": 0.42, + "learning_rate": 2.8847564931433302e-05, + "loss": 0.1425, "step": 190190 }, { - "epoch": 0.85, - "learning_rate": 7.597192950988745e-06, - "loss": 0.1456, + "epoch": 0.42, + "learning_rate": 2.884644638822398e-05, + "loss": 0.1466, "step": 190200 }, { - "epoch": 0.85, - "learning_rate": 7.594950899062822e-06, - "loss": 0.1378, + "epoch": 0.42, + "learning_rate": 2.884532784501465e-05, + "loss": 0.147, "step": 190210 }, { - "epoch": 0.85, - "learning_rate": 7.592708847136901e-06, - "loss": 0.1477, + "epoch": 0.42, + "learning_rate": 2.884420930180533e-05, + "loss": 0.1452, "step": 190220 }, { - "epoch": 0.85, - "learning_rate": 7.590466795210978e-06, - "loss": 0.1488, + "epoch": 0.42, + "learning_rate": 2.884309075859601e-05, + "loss": 0.148, "step": 190230 }, { - "epoch": 0.85, - "learning_rate": 7.588224743285055e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.884197221538668e-05, + "loss": 0.141, "step": 190240 }, { - "epoch": 0.85, - "learning_rate": 7.5859826913591325e-06, - "loss": 0.1423, + "epoch": 0.42, + "learning_rate": 2.884085367217736e-05, + "loss": 0.1445, "step": 190250 }, { - "epoch": 0.85, - "learning_rate": 7.5837406394332095e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.883973512896803e-05, + "loss": 0.1443, "step": 190260 }, { - "epoch": 0.85, - "learning_rate": 7.5814985875072866e-06, - "loss": 0.1436, + "epoch": 0.42, + "learning_rate": 2.883861658575871e-05, + "loss": 0.1456, "step": 190270 }, { - "epoch": 0.85, - "learning_rate": 7.579256535581364e-06, - "loss": 0.143, + "epoch": 0.42, + "learning_rate": 2.8837498042549383e-05, + "loss": 0.1449, "step": 190280 }, { - "epoch": 0.85, - "learning_rate": 7.577014483655442e-06, - "loss": 0.1461, + "epoch": 0.42, + "learning_rate": 2.883637949934006e-05, + "loss": 0.1482, "step": 190290 }, { - "epoch": 0.85, - "learning_rate": 7.574772431729519e-06, - "loss": 0.1483, + "epoch": 0.42, + "learning_rate": 2.883526095613074e-05, + "loss": 0.1431, "step": 190300 }, { - "epoch": 0.85, - "learning_rate": 7.572530379803597e-06, - "loss": 0.1408, + "epoch": 0.42, + "learning_rate": 2.883414241292141e-05, + "loss": 0.1419, "step": 190310 }, { - "epoch": 0.85, - "learning_rate": 7.570288327877674e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.8833023869712088e-05, + "loss": 0.1432, "step": 190320 }, { - "epoch": 0.85, - "learning_rate": 7.568046275951751e-06, - "loss": 0.1439, + "epoch": 0.42, + "learning_rate": 2.8831905326502762e-05, + "loss": 0.1502, "step": 190330 }, { - "epoch": 0.85, - "learning_rate": 7.565804224025828e-06, - "loss": 0.1407, + "epoch": 0.42, + "learning_rate": 2.883078678329344e-05, + "loss": 0.1512, "step": 190340 }, { - "epoch": 0.85, - "learning_rate": 7.563562172099905e-06, - "loss": 0.141, + "epoch": 0.42, + "learning_rate": 2.8829668240084118e-05, + "loss": 0.1466, "step": 190350 }, { - "epoch": 0.85, - "learning_rate": 7.561320120173984e-06, - "loss": 0.1455, + "epoch": 0.42, + "learning_rate": 2.882854969687479e-05, + "loss": 0.1487, "step": 190360 }, { - "epoch": 0.85, - "learning_rate": 7.559078068248061e-06, - "loss": 0.1405, + "epoch": 0.42, + "learning_rate": 2.8827431153665467e-05, + "loss": 0.1467, "step": 190370 }, { - "epoch": 0.85, - "learning_rate": 7.556836016322139e-06, - "loss": 0.1393, + "epoch": 0.42, + "learning_rate": 2.8826312610456142e-05, + "loss": 0.1422, "step": 190380 }, { - "epoch": 0.85, - "learning_rate": 7.554593964396216e-06, - "loss": 0.1383, + "epoch": 0.42, + "learning_rate": 2.882519406724682e-05, + "loss": 0.1432, "step": 190390 }, { - "epoch": 0.85, - "learning_rate": 7.552351912470293e-06, - "loss": 0.1424, + "epoch": 0.42, + "learning_rate": 2.8824075524037498e-05, + "loss": 0.1504, "step": 190400 }, { - "epoch": 0.85, - "learning_rate": 7.55010986054437e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.882295698082817e-05, + "loss": 0.1488, "step": 190410 }, { - "epoch": 0.85, - "learning_rate": 7.547867808618447e-06, - "loss": 0.1453, + "epoch": 0.43, + "learning_rate": 2.8821838437618847e-05, + "loss": 0.1471, "step": 190420 }, { - "epoch": 0.85, - "learning_rate": 7.545625756692526e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.882071989440952e-05, + "loss": 0.148, "step": 190430 }, { - "epoch": 0.85, - "learning_rate": 7.543383704766603e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.88196013512002e-05, + "loss": 0.1434, "step": 190440 }, { - "epoch": 0.85, - "learning_rate": 7.541141652840681e-06, - "loss": 0.1399, + "epoch": 0.43, + "learning_rate": 2.8818482807990877e-05, + "loss": 0.1448, "step": 190450 }, { - "epoch": 0.85, - "learning_rate": 7.538899600914758e-06, - "loss": 0.1447, + "epoch": 0.43, + "learning_rate": 2.881736426478155e-05, + "loss": 0.1434, "step": 190460 }, { - "epoch": 0.85, - "learning_rate": 7.536657548988835e-06, - "loss": 0.1478, + "epoch": 0.43, + "learning_rate": 2.8816245721572226e-05, + "loss": 0.1435, "step": 190470 }, { - "epoch": 0.85, - "learning_rate": 7.534415497062912e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.88151271783629e-05, + "loss": 0.1422, "step": 190480 }, { - "epoch": 0.85, - "learning_rate": 7.532173445136989e-06, - "loss": 0.1405, + "epoch": 0.43, + "learning_rate": 2.881400863515358e-05, + "loss": 0.1434, "step": 190490 }, { - "epoch": 0.85, - "learning_rate": 7.5299313932110674e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.8812890091944257e-05, + "loss": 0.1401, "step": 190500 }, { - "epoch": 0.85, - "learning_rate": 7.5276893412851445e-06, - "loss": 0.1453, + "epoch": 0.43, + "learning_rate": 2.8811771548734928e-05, + "loss": 0.1456, "step": 190510 }, { - "epoch": 0.85, - "learning_rate": 7.525447289359222e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.8810653005525606e-05, + "loss": 0.1464, "step": 190520 }, { - "epoch": 0.85, - "learning_rate": 7.523205237433299e-06, - "loss": 0.1434, + "epoch": 0.43, + "learning_rate": 2.880953446231628e-05, + "loss": 0.1442, "step": 190530 }, { - "epoch": 0.85, - "learning_rate": 7.520963185507376e-06, - "loss": 0.1453, + "epoch": 0.43, + "learning_rate": 2.8808415919106958e-05, + "loss": 0.1445, "step": 190540 }, { - "epoch": 0.85, - "learning_rate": 7.518721133581453e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.8807297375897636e-05, + "loss": 0.1484, "step": 190550 }, { - "epoch": 0.85, - "learning_rate": 7.5164790816555304e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8806178832688307e-05, + "loss": 0.1418, "step": 190560 }, { - "epoch": 0.85, - "learning_rate": 7.514237029729609e-06, - "loss": 0.1457, + "epoch": 0.43, + "learning_rate": 2.8805060289478985e-05, + "loss": 0.1495, "step": 190570 }, { - "epoch": 0.85, - "learning_rate": 7.511994977803687e-06, - "loss": 0.1453, + "epoch": 0.43, + "learning_rate": 2.880394174626966e-05, + "loss": 0.1456, "step": 190580 }, { - "epoch": 0.85, - "learning_rate": 7.509752925877764e-06, - "loss": 0.1442, + "epoch": 0.43, + "learning_rate": 2.8802823203060338e-05, + "loss": 0.1472, "step": 190590 }, { - "epoch": 0.85, - "learning_rate": 7.507510873951841e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.880170465985101e-05, + "loss": 0.1416, "step": 190600 }, { - "epoch": 0.85, - "learning_rate": 7.505268822025918e-06, - "loss": 0.1483, + "epoch": 0.43, + "learning_rate": 2.8800586116641687e-05, + "loss": 0.1422, "step": 190610 }, { - "epoch": 0.85, - "learning_rate": 7.503026770099995e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.8799467573432365e-05, + "loss": 0.1442, "step": 190620 }, { - "epoch": 0.85, - "learning_rate": 7.500784718174073e-06, - "loss": 0.1395, + "epoch": 0.43, + "learning_rate": 2.8798349030223036e-05, + "loss": 0.1449, "step": 190630 }, { - "epoch": 0.85, - "learning_rate": 7.498542666248151e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.8797230487013717e-05, + "loss": 0.1435, "step": 190640 }, { - "epoch": 0.85, - "learning_rate": 7.496300614322229e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.879611194380439e-05, + "loss": 0.1474, "step": 190650 }, { - "epoch": 0.85, - "learning_rate": 7.494058562396306e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8794993400595066e-05, + "loss": 0.1476, "step": 190660 }, { - "epoch": 0.85, - "learning_rate": 7.491816510470383e-06, - "loss": 0.1486, + "epoch": 0.43, + "learning_rate": 2.8793874857385744e-05, + "loss": 0.1423, "step": 190670 }, { - "epoch": 0.85, - "learning_rate": 7.48957445854446e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.8792756314176415e-05, + "loss": 0.1399, "step": 190680 }, { - "epoch": 0.85, - "learning_rate": 7.487332406618537e-06, - "loss": 0.1462, + "epoch": 0.43, + "learning_rate": 2.8791637770967093e-05, + "loss": 0.1441, "step": 190690 }, { - "epoch": 0.85, - "learning_rate": 7.4850903546926155e-06, - "loss": 0.1461, + "epoch": 0.43, + "learning_rate": 2.8790519227757768e-05, + "loss": 0.1434, "step": 190700 }, { - "epoch": 0.85, - "learning_rate": 7.4828483027666926e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8789400684548446e-05, + "loss": 0.1451, "step": 190710 }, { - "epoch": 0.85, - "learning_rate": 7.4806062508407704e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.8788282141339124e-05, + "loss": 0.1452, "step": 190720 }, { - "epoch": 0.85, - "learning_rate": 7.4783641989148474e-06, - "loss": 0.1475, + "epoch": 0.43, + "learning_rate": 2.8787163598129795e-05, + "loss": 0.1436, "step": 190730 }, { - "epoch": 0.85, - "learning_rate": 7.4761221469889245e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.8786045054920473e-05, + "loss": 0.1427, "step": 190740 }, { - "epoch": 0.85, - "learning_rate": 7.4738800950630015e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.8784926511711147e-05, + "loss": 0.1434, "step": 190750 }, { - "epoch": 0.85, - "learning_rate": 7.4716380431370785e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.8783807968501825e-05, + "loss": 0.1452, "step": 190760 }, { - "epoch": 0.85, - "learning_rate": 7.469395991211157e-06, - "loss": 0.146, + "epoch": 0.43, + "learning_rate": 2.8782689425292503e-05, + "loss": 0.1492, "step": 190770 }, { - "epoch": 0.85, - "learning_rate": 7.467153939285234e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.8781570882083174e-05, + "loss": 0.1422, "step": 190780 }, { - "epoch": 0.85, - "learning_rate": 7.464911887359312e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.8780452338873852e-05, + "loss": 0.1488, "step": 190790 }, { - "epoch": 0.85, - "learning_rate": 7.462669835433389e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.8779333795664527e-05, + "loss": 0.1426, "step": 190800 }, { - "epoch": 0.85, - "learning_rate": 7.460427783507466e-06, - "loss": 0.137, + "epoch": 0.43, + "learning_rate": 2.8778215252455205e-05, + "loss": 0.146, "step": 190810 }, { - "epoch": 0.85, - "learning_rate": 7.458185731581543e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8777096709245883e-05, + "loss": 0.15, "step": 190820 }, { - "epoch": 0.85, - "learning_rate": 7.45594367965562e-06, - "loss": 0.1443, + "epoch": 0.43, + "learning_rate": 2.8775978166036554e-05, + "loss": 0.1417, "step": 190830 }, { - "epoch": 0.85, - "learning_rate": 7.453701627729699e-06, - "loss": 0.139, + "epoch": 0.43, + "learning_rate": 2.8774859622827232e-05, + "loss": 0.1482, "step": 190840 }, { - "epoch": 0.85, - "learning_rate": 7.451459575803777e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.8773741079617906e-05, + "loss": 0.1458, "step": 190850 }, { - "epoch": 0.85, - "learning_rate": 7.449217523877854e-06, - "loss": 0.1393, + "epoch": 0.43, + "learning_rate": 2.8772622536408584e-05, + "loss": 0.1497, "step": 190860 }, { - "epoch": 0.85, - "learning_rate": 7.446975471951931e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8771503993199262e-05, + "loss": 0.1463, "step": 190870 }, { - "epoch": 0.85, - "learning_rate": 7.444733420026008e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.8770385449989933e-05, + "loss": 0.1415, "step": 190880 }, { - "epoch": 0.85, - "learning_rate": 7.442491368100085e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.876926690678061e-05, + "loss": 0.1472, "step": 190890 }, { - "epoch": 0.85, - "learning_rate": 7.440249316174163e-06, - "loss": 0.1377, + "epoch": 0.43, + "learning_rate": 2.8768148363571286e-05, + "loss": 0.1471, "step": 190900 }, { - "epoch": 0.85, - "learning_rate": 7.438007264248241e-06, - "loss": 0.1394, + "epoch": 0.43, + "learning_rate": 2.8767029820361964e-05, + "loss": 0.1432, "step": 190910 }, { - "epoch": 0.85, - "learning_rate": 7.4357652123223185e-06, - "loss": 0.1376, + "epoch": 0.43, + "learning_rate": 2.8765911277152635e-05, + "loss": 0.1509, "step": 190920 }, { - "epoch": 0.85, - "learning_rate": 7.4335231603963955e-06, - "loss": 0.1401, + "epoch": 0.43, + "learning_rate": 2.8764792733943313e-05, + "loss": 0.1476, "step": 190930 }, { - "epoch": 0.85, - "learning_rate": 7.4312811084704726e-06, - "loss": 0.1417, + "epoch": 0.43, + "learning_rate": 2.876367419073399e-05, + "loss": 0.1463, "step": 190940 }, { - "epoch": 0.85, - "learning_rate": 7.42903905654455e-06, - "loss": 0.144, + "epoch": 0.43, + "learning_rate": 2.8762555647524665e-05, + "loss": 0.1414, "step": 190950 }, { - "epoch": 0.85, - "learning_rate": 7.426797004618627e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.8761437104315343e-05, + "loss": 0.1427, "step": 190960 }, { - "epoch": 0.85, - "learning_rate": 7.4245549526927045e-06, - "loss": 0.1433, + "epoch": 0.43, + "learning_rate": 2.8760318561106014e-05, + "loss": 0.1472, "step": 190970 }, { - "epoch": 0.85, - "learning_rate": 7.422312900766782e-06, - "loss": 0.1434, + "epoch": 0.43, + "learning_rate": 2.8759200017896692e-05, + "loss": 0.1492, "step": 190980 }, { - "epoch": 0.85, - "learning_rate": 7.42007084884086e-06, - "loss": 0.1413, + "epoch": 0.43, + "learning_rate": 2.875808147468737e-05, + "loss": 0.1495, "step": 190990 }, { - "epoch": 0.85, - "learning_rate": 7.417828796914937e-06, - "loss": 0.143, + "epoch": 0.43, + "learning_rate": 2.8756962931478045e-05, + "loss": 0.1474, "step": 191000 }, { - "epoch": 0.85, - "learning_rate": 7.415586744989014e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8755844388268723e-05, + "loss": 0.1439, "step": 191010 }, { - "epoch": 0.85, - "learning_rate": 7.413344693063091e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.8754725845059394e-05, + "loss": 0.1391, "step": 191020 }, { - "epoch": 0.85, - "learning_rate": 7.411102641137168e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.875360730185007e-05, + "loss": 0.1428, "step": 191030 }, { - "epoch": 0.85, - "learning_rate": 7.408860589211246e-06, - "loss": 0.1464, + "epoch": 0.43, + "learning_rate": 2.875248875864075e-05, + "loss": 0.1442, "step": 191040 }, { - "epoch": 0.85, - "learning_rate": 7.406618537285324e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.875137021543142e-05, + "loss": 0.137, "step": 191050 }, { - "epoch": 0.85, - "learning_rate": 7.404376485359402e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.8750251672222102e-05, + "loss": 0.1416, "step": 191060 }, { - "epoch": 0.85, - "learning_rate": 7.402134433433479e-06, - "loss": 0.1394, + "epoch": 0.43, + "learning_rate": 2.8749133129012773e-05, + "loss": 0.1415, "step": 191070 }, { - "epoch": 0.85, - "learning_rate": 7.399892381507556e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.874801458580345e-05, + "loss": 0.1415, "step": 191080 }, { - "epoch": 0.85, - "learning_rate": 7.397650329581633e-06, - "loss": 0.1377, + "epoch": 0.43, + "learning_rate": 2.874689604259413e-05, + "loss": 0.1472, "step": 191090 }, { - "epoch": 0.85, - "learning_rate": 7.39540827765571e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.87457774993848e-05, + "loss": 0.1433, "step": 191100 }, { - "epoch": 0.85, - "learning_rate": 7.393166225729788e-06, - "loss": 0.1401, + "epoch": 0.43, + "learning_rate": 2.8744658956175478e-05, + "loss": 0.1435, "step": 191110 }, { - "epoch": 0.85, - "learning_rate": 7.390924173803867e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.8743540412966153e-05, + "loss": 0.1445, "step": 191120 }, { - "epoch": 0.85, - "learning_rate": 7.388682121877944e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.874242186975683e-05, + "loss": 0.1445, "step": 191130 }, { - "epoch": 0.85, - "learning_rate": 7.386440069952021e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.874130332654751e-05, + "loss": 0.1389, "step": 191140 }, { - "epoch": 0.85, - "learning_rate": 7.384198018026098e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.874018478333818e-05, + "loss": 0.1396, "step": 191150 }, { - "epoch": 0.85, - "learning_rate": 7.381955966100175e-06, - "loss": 0.1446, + "epoch": 0.43, + "learning_rate": 2.8739066240128858e-05, + "loss": 0.1445, "step": 191160 }, { - "epoch": 0.85, - "learning_rate": 7.379713914174253e-06, - "loss": 0.1413, + "epoch": 0.43, + "learning_rate": 2.8737947696919532e-05, + "loss": 0.145, "step": 191170 }, { - "epoch": 0.85, - "learning_rate": 7.37747186224833e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.873682915371021e-05, + "loss": 0.1424, "step": 191180 }, { - "epoch": 0.85, - "learning_rate": 7.375229810322408e-06, - "loss": 0.147, + "epoch": 0.43, + "learning_rate": 2.8735710610500888e-05, + "loss": 0.1444, "step": 191190 }, { - "epoch": 0.85, - "learning_rate": 7.372987758396485e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.873459206729156e-05, + "loss": 0.1435, "step": 191200 }, { - "epoch": 0.85, - "learning_rate": 7.370745706470562e-06, - "loss": 0.1471, + "epoch": 0.43, + "learning_rate": 2.8733473524082237e-05, + "loss": 0.1428, "step": 191210 }, { - "epoch": 0.85, - "learning_rate": 7.368503654544639e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.873235498087291e-05, + "loss": 0.1461, "step": 191220 }, { - "epoch": 0.85, - "learning_rate": 7.366261602618716e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.873123643766359e-05, + "loss": 0.1459, "step": 191230 }, { - "epoch": 0.85, - "learning_rate": 7.364019550692794e-06, - "loss": 0.1404, + "epoch": 0.43, + "learning_rate": 2.873011789445426e-05, + "loss": 0.1413, "step": 191240 }, { - "epoch": 0.85, - "learning_rate": 7.361777498766871e-06, - "loss": 0.145, + "epoch": 0.43, + "learning_rate": 2.872899935124494e-05, + "loss": 0.1465, "step": 191250 }, { - "epoch": 0.85, - "learning_rate": 7.35953544684095e-06, - "loss": 0.1473, + "epoch": 0.43, + "learning_rate": 2.8727880808035617e-05, + "loss": 0.1456, "step": 191260 }, { - "epoch": 0.85, - "learning_rate": 7.357293394915027e-06, - "loss": 0.1402, + "epoch": 0.43, + "learning_rate": 2.872676226482629e-05, + "loss": 0.1426, "step": 191270 }, { - "epoch": 0.85, - "learning_rate": 7.355051342989104e-06, - "loss": 0.1478, + "epoch": 0.43, + "learning_rate": 2.872564372161697e-05, + "loss": 0.1438, "step": 191280 }, { - "epoch": 0.85, - "learning_rate": 7.352809291063181e-06, - "loss": 0.1433, + "epoch": 0.43, + "learning_rate": 2.872452517840764e-05, + "loss": 0.1477, "step": 191290 }, { - "epoch": 0.85, - "learning_rate": 7.350567239137258e-06, - "loss": 0.141, + "epoch": 0.43, + "learning_rate": 2.8723406635198318e-05, + "loss": 0.146, "step": 191300 }, { - "epoch": 0.85, - "learning_rate": 7.348325187211336e-06, - "loss": 0.1424, + "epoch": 0.43, + "learning_rate": 2.8722288091988996e-05, + "loss": 0.1425, "step": 191310 }, { - "epoch": 0.85, - "learning_rate": 7.346083135285414e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.872116954877967e-05, + "loss": 0.1429, "step": 191320 }, { - "epoch": 0.85, - "learning_rate": 7.343841083359492e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.872005100557035e-05, + "loss": 0.1462, "step": 191330 }, { - "epoch": 0.85, - "learning_rate": 7.341599031433569e-06, - "loss": 0.141, + "epoch": 0.43, + "learning_rate": 2.871893246236102e-05, + "loss": 0.15, "step": 191340 }, { - "epoch": 0.85, - "learning_rate": 7.339356979507646e-06, - "loss": 0.1473, + "epoch": 0.43, + "learning_rate": 2.8717813919151698e-05, + "loss": 0.1408, "step": 191350 }, { - "epoch": 0.85, - "learning_rate": 7.337114927581723e-06, - "loss": 0.146, + "epoch": 0.43, + "learning_rate": 2.8716695375942376e-05, + "loss": 0.1424, "step": 191360 }, { - "epoch": 0.85, - "learning_rate": 7.3348728756558e-06, - "loss": 0.1374, + "epoch": 0.43, + "learning_rate": 2.871557683273305e-05, + "loss": 0.1434, "step": 191370 }, { - "epoch": 0.85, - "learning_rate": 7.332630823729878e-06, - "loss": 0.1416, + "epoch": 0.43, + "learning_rate": 2.8714458289523728e-05, + "loss": 0.1474, "step": 191380 }, { - "epoch": 0.85, - "learning_rate": 7.3303887718039564e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.87133397463144e-05, + "loss": 0.1417, "step": 191390 }, { - "epoch": 0.85, - "learning_rate": 7.3281467198780334e-06, - "loss": 0.1442, + "epoch": 0.43, + "learning_rate": 2.8712221203105077e-05, + "loss": 0.1464, "step": 191400 }, { - "epoch": 0.85, - "learning_rate": 7.3259046679521105e-06, - "loss": 0.1432, + "epoch": 0.43, + "learning_rate": 2.8711102659895755e-05, + "loss": 0.1469, "step": 191410 }, { - "epoch": 0.85, - "learning_rate": 7.3236626160261875e-06, - "loss": 0.1444, + "epoch": 0.43, + "learning_rate": 2.870998411668643e-05, + "loss": 0.1401, "step": 191420 }, { - "epoch": 0.85, - "learning_rate": 7.3214205641002645e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.8708865573477107e-05, + "loss": 0.1446, "step": 191430 }, { - "epoch": 0.85, - "learning_rate": 7.319178512174342e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.870774703026778e-05, + "loss": 0.1481, "step": 191440 }, { - "epoch": 0.85, - "learning_rate": 7.316936460248419e-06, - "loss": 0.1464, + "epoch": 0.43, + "learning_rate": 2.8706628487058457e-05, + "loss": 0.1403, "step": 191450 }, { - "epoch": 0.85, - "learning_rate": 7.314694408322498e-06, - "loss": 0.1437, + "epoch": 0.43, + "learning_rate": 2.8705509943849134e-05, + "loss": 0.1423, "step": 191460 }, { - "epoch": 0.85, - "learning_rate": 7.312452356396575e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.870439140063981e-05, + "loss": 0.1419, "step": 191470 }, { - "epoch": 0.85, - "learning_rate": 7.310210304470652e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8703272857430487e-05, + "loss": 0.1468, "step": 191480 }, { - "epoch": 0.85, - "learning_rate": 7.307968252544729e-06, - "loss": 0.141, + "epoch": 0.43, + "learning_rate": 2.8702154314221158e-05, + "loss": 0.1408, "step": 191490 }, { - "epoch": 0.85, - "learning_rate": 7.305726200618806e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.8701035771011836e-05, + "loss": 0.1461, "step": 191500 }, { - "epoch": 0.85, - "learning_rate": 7.303484148692884e-06, - "loss": 0.1387, + "epoch": 0.43, + "learning_rate": 2.8699917227802514e-05, + "loss": 0.1411, "step": 191510 }, { - "epoch": 0.85, - "learning_rate": 7.301242096766961e-06, - "loss": 0.1439, + "epoch": 0.43, + "learning_rate": 2.8698798684593185e-05, + "loss": 0.1425, "step": 191520 }, { - "epoch": 0.86, - "learning_rate": 7.29900004484104e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.8697680141383866e-05, + "loss": 0.1411, "step": 191530 }, { - "epoch": 0.86, - "learning_rate": 7.296757992915117e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.8696561598174538e-05, + "loss": 0.1435, "step": 191540 }, { - "epoch": 0.86, - "learning_rate": 7.294515940989194e-06, - "loss": 0.1401, + "epoch": 0.43, + "learning_rate": 2.8695443054965215e-05, + "loss": 0.1454, "step": 191550 }, { - "epoch": 0.86, - "learning_rate": 7.292273889063271e-06, - "loss": 0.1447, + "epoch": 0.43, + "learning_rate": 2.8694324511755887e-05, + "loss": 0.1454, "step": 191560 }, { - "epoch": 0.86, - "learning_rate": 7.290031837137348e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.8693205968546565e-05, + "loss": 0.143, "step": 191570 }, { - "epoch": 0.86, - "learning_rate": 7.287789785211426e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.8692087425337242e-05, + "loss": 0.1452, "step": 191580 }, { - "epoch": 0.86, - "learning_rate": 7.285547733285503e-06, - "loss": 0.1451, + "epoch": 0.43, + "learning_rate": 2.8690968882127917e-05, + "loss": 0.1462, "step": 191590 }, { - "epoch": 0.86, - "learning_rate": 7.2833056813595815e-06, - "loss": 0.1464, + "epoch": 0.43, + "learning_rate": 2.8689850338918595e-05, + "loss": 0.1419, "step": 191600 }, { - "epoch": 0.86, - "learning_rate": 7.2810636294336586e-06, - "loss": 0.1394, + "epoch": 0.43, + "learning_rate": 2.8688731795709266e-05, + "loss": 0.1401, "step": 191610 }, { - "epoch": 0.86, - "learning_rate": 7.278821577507736e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.8687613252499944e-05, + "loss": 0.15, "step": 191620 }, { - "epoch": 0.86, - "learning_rate": 7.276579525581813e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.8686494709290622e-05, + "loss": 0.1443, "step": 191630 }, { - "epoch": 0.86, - "learning_rate": 7.27433747365589e-06, - "loss": 0.1424, + "epoch": 0.43, + "learning_rate": 2.8685376166081297e-05, + "loss": 0.145, "step": 191640 }, { - "epoch": 0.86, - "learning_rate": 7.2720954217299675e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.8684257622871974e-05, + "loss": 0.1427, "step": 191650 }, { - "epoch": 0.86, - "learning_rate": 7.2698533698040445e-06, - "loss": 0.1399, + "epoch": 0.43, + "learning_rate": 2.8683139079662646e-05, + "loss": 0.1466, "step": 191660 }, { - "epoch": 0.86, - "learning_rate": 7.267611317878123e-06, - "loss": 0.1438, + "epoch": 0.43, + "learning_rate": 2.8682020536453324e-05, + "loss": 0.1406, "step": 191670 }, { - "epoch": 0.86, - "learning_rate": 7.2653692659522e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8680901993244e-05, + "loss": 0.1471, "step": 191680 }, { - "epoch": 0.86, - "learning_rate": 7.263127214026277e-06, - "loss": 0.1452, + "epoch": 0.43, + "learning_rate": 2.8679783450034676e-05, + "loss": 0.1477, "step": 191690 }, { - "epoch": 0.86, - "learning_rate": 7.260885162100354e-06, - "loss": 0.1473, + "epoch": 0.43, + "learning_rate": 2.8678664906825354e-05, + "loss": 0.1487, "step": 191700 }, { - "epoch": 0.86, - "learning_rate": 7.258643110174432e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8677546363616025e-05, + "loss": 0.1417, "step": 191710 }, { - "epoch": 0.86, - "learning_rate": 7.256401058248509e-06, - "loss": 0.1433, + "epoch": 0.43, + "learning_rate": 2.8676427820406703e-05, + "loss": 0.147, "step": 191720 }, { - "epoch": 0.86, - "learning_rate": 7.254159006322586e-06, - "loss": 0.1372, + "epoch": 0.43, + "learning_rate": 2.867530927719738e-05, + "loss": 0.1449, "step": 191730 }, { - "epoch": 0.86, - "learning_rate": 7.251916954396665e-06, - "loss": 0.1469, + "epoch": 0.43, + "learning_rate": 2.8674190733988055e-05, + "loss": 0.1442, "step": 191740 }, { - "epoch": 0.86, - "learning_rate": 7.249674902470742e-06, - "loss": 0.1405, + "epoch": 0.43, + "learning_rate": 2.8673072190778733e-05, + "loss": 0.1449, "step": 191750 }, { - "epoch": 0.86, - "learning_rate": 7.247432850544819e-06, - "loss": 0.1467, + "epoch": 0.43, + "learning_rate": 2.8671953647569405e-05, + "loss": 0.1492, "step": 191760 }, { - "epoch": 0.86, - "learning_rate": 7.245190798618896e-06, - "loss": 0.1387, + "epoch": 0.43, + "learning_rate": 2.8670835104360082e-05, + "loss": 0.1445, "step": 191770 }, { - "epoch": 0.86, - "learning_rate": 7.242948746692974e-06, - "loss": 0.1358, + "epoch": 0.43, + "learning_rate": 2.866971656115076e-05, + "loss": 0.1424, "step": 191780 }, { - "epoch": 0.86, - "learning_rate": 7.240706694767051e-06, - "loss": 0.1401, + "epoch": 0.43, + "learning_rate": 2.8668598017941435e-05, + "loss": 0.1416, "step": 191790 }, { - "epoch": 0.86, - "learning_rate": 7.238464642841128e-06, - "loss": 0.1413, + "epoch": 0.43, + "learning_rate": 2.8667479474732113e-05, + "loss": 0.143, "step": 191800 }, { - "epoch": 0.86, - "learning_rate": 7.236222590915207e-06, - "loss": 0.1412, + "epoch": 0.43, + "learning_rate": 2.8666360931522784e-05, + "loss": 0.1404, "step": 191810 }, { - "epoch": 0.86, - "learning_rate": 7.233980538989284e-06, - "loss": 0.1439, + "epoch": 0.43, + "learning_rate": 2.8665242388313462e-05, + "loss": 0.146, "step": 191820 }, { - "epoch": 0.86, - "learning_rate": 7.231738487063361e-06, - "loss": 0.1442, + "epoch": 0.43, + "learning_rate": 2.866412384510414e-05, + "loss": 0.1457, "step": 191830 }, { - "epoch": 0.86, - "learning_rate": 7.229496435137438e-06, - "loss": 0.1432, + "epoch": 0.43, + "learning_rate": 2.8663005301894814e-05, + "loss": 0.141, "step": 191840 }, { - "epoch": 0.86, - "learning_rate": 7.227254383211516e-06, - "loss": 0.1412, + "epoch": 0.43, + "learning_rate": 2.8661886758685492e-05, + "loss": 0.1433, "step": 191850 }, { - "epoch": 0.86, - "learning_rate": 7.225012331285593e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8660768215476163e-05, + "loss": 0.1486, "step": 191860 }, { - "epoch": 0.86, - "learning_rate": 7.22277027935967e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.865964967226684e-05, + "loss": 0.1478, "step": 191870 }, { - "epoch": 0.86, - "learning_rate": 7.220528227433748e-06, - "loss": 0.1356, + "epoch": 0.43, + "learning_rate": 2.8658531129057513e-05, + "loss": 0.1467, "step": 191880 }, { - "epoch": 0.86, - "learning_rate": 7.218286175507825e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.8657412585848194e-05, + "loss": 0.1427, "step": 191890 }, { - "epoch": 0.86, - "learning_rate": 7.216044123581902e-06, - "loss": 0.1427, + "epoch": 0.43, + "learning_rate": 2.8656294042638872e-05, + "loss": 0.1401, "step": 191900 }, { - "epoch": 0.86, - "learning_rate": 7.2138020716559794e-06, - "loss": 0.1424, + "epoch": 0.43, + "learning_rate": 2.8655175499429543e-05, + "loss": 0.1464, "step": 191910 }, { - "epoch": 0.86, - "learning_rate": 7.211560019730057e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.865405695622022e-05, + "loss": 0.1406, "step": 191920 }, { - "epoch": 0.86, - "learning_rate": 7.209317967804134e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.8652938413010892e-05, + "loss": 0.1419, "step": 191930 }, { - "epoch": 0.86, - "learning_rate": 7.207075915878211e-06, - "loss": 0.1427, + "epoch": 0.43, + "learning_rate": 2.865181986980157e-05, + "loss": 0.1439, "step": 191940 }, { - "epoch": 0.86, - "learning_rate": 7.20483386395229e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.865070132659225e-05, + "loss": 0.143, "step": 191950 }, { - "epoch": 0.86, - "learning_rate": 7.202591812026367e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.8649582783382922e-05, + "loss": 0.1401, "step": 191960 }, { - "epoch": 0.86, - "learning_rate": 7.200349760100444e-06, - "loss": 0.135, + "epoch": 0.43, + "learning_rate": 2.86484642401736e-05, + "loss": 0.1391, "step": 191970 }, { - "epoch": 0.86, - "learning_rate": 7.198107708174521e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.864734569696427e-05, + "loss": 0.1397, "step": 191980 }, { - "epoch": 0.86, - "learning_rate": 7.195865656248599e-06, - "loss": 0.1426, + "epoch": 0.43, + "learning_rate": 2.864622715375495e-05, + "loss": 0.1468, "step": 191990 }, { - "epoch": 0.86, - "learning_rate": 7.193623604322676e-06, - "loss": 0.1439, + "epoch": 0.43, + "learning_rate": 2.8645108610545627e-05, + "loss": 0.1434, "step": 192000 }, { - "epoch": 0.86, - "eval_NEIMS_canon_smiles": 0.9442666666666667, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.10665, - "eval_NEIMS_daylight_tanimoto_simil": 0.508517053716457, - "eval_NEIMS_exact_mols": 0.10645, - "eval_NEIMS_exact_smiles": 0.10338333333333333, - "eval_NEIMS_loss": 0.18446384370326996, - "eval_NEIMS_matched_formulas": 0.6333, - "eval_NEIMS_morgan_tanimoto_simil": 0.4186830011326453, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.10686666666666667, - "eval_NEIMS_runtime": 715.0375, - "eval_NEIMS_samples_per_second": 83.912, - "eval_NEIMS_steps_per_second": 1.312, + "epoch": 0.43, + "eval_NEIMS_canon_smiles": 0.9512666666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.13321666666666668, + "eval_NEIMS_daylight_tanimoto_simil": 0.5353950661767752, + "eval_NEIMS_exact_mols": 0.13298333333333334, + "eval_NEIMS_exact_smiles": 0.12998333333333334, + "eval_NEIMS_loss": 0.1706952154636383, + "eval_NEIMS_matched_formulas": 0.6667166666666666, + "eval_NEIMS_morgan_tanimoto_simil": 0.4483474387986251, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.1335, + "eval_NEIMS_runtime": 728.4858, + "eval_NEIMS_samples_per_second": 82.363, + "eval_NEIMS_steps_per_second": 1.288, "step": 192000 }, { - "epoch": 0.86, - "eval_RASSP_canon_smiles": 0.9397268507696931, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.23414699302100378, - "eval_RASSP_daylight_tanimoto_simil": 0.6567451166528004, - "eval_RASSP_exact_mols": 0.23341236183924935, - "eval_RASSP_exact_smiles": 0.22701773132534145, - "eval_RASSP_loss": 0.12375875562429428, - "eval_RASSP_matched_formulas": 0.8093131198450596, - "eval_RASSP_morgan_tanimoto_simil": 0.5400474171561165, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.2336961966140181, - "eval_RASSP_runtime": 816.4158, - "eval_RASSP_samples_per_second": 73.362, - "eval_RASSP_steps_per_second": 1.146, + "epoch": 0.43, + "eval_RASSP_canon_smiles": 0.9463218352422613, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.18724747053127191, + "eval_RASSP_daylight_tanimoto_simil": 0.6298673114709867, + "eval_RASSP_exact_mols": 0.18644605469663073, + "eval_RASSP_exact_smiles": 0.18096971315991586, + "eval_RASSP_loss": 0.13743963837623596, + "eval_RASSP_matched_formulas": 0.8138043877516946, + "eval_RASSP_morgan_tanimoto_simil": 0.5035653582159272, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.18661301632884764, + "eval_RASSP_runtime": 832.9193, + "eval_RASSP_samples_per_second": 71.909, + "eval_RASSP_steps_per_second": 1.124, "step": 192000 }, { - "epoch": 0.86, - "eval_NIST_canon_smiles": 0.8672321396883983, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.016786740958938142, - "eval_NIST_daylight_tanimoto_simil": 0.279486469735125, - "eval_NIST_exact_mols": 0.015934982432480392, - "eval_NIST_exact_smiles": 0.014799304397203393, - "eval_NIST_loss": 1.8838388919830322, - "eval_NIST_matched_formulas": 0.10249494268374916, - "eval_NIST_morgan_tanimoto_simil": 0.23107522621292642, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.016680271143130924, - "eval_NIST_runtime": 492.9095, - "eval_NIST_samples_per_second": 57.165, - "eval_NIST_steps_per_second": 0.895, + "epoch": 0.43, + "eval_NEIMS_old_canon_smiles": 0.9518, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.1349, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5356224165672182, + "eval_NEIMS_old_exact_mols": 0.13456666666666667, + "eval_NEIMS_old_exact_smiles": 0.13156666666666667, + "eval_NEIMS_old_loss": 0.1701691895723343, + "eval_NEIMS_old_matched_formulas": 0.6625, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4489952257160061, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1351, + "eval_NEIMS_old_runtime": 366.8235, + "eval_NEIMS_old_samples_per_second": 81.783, + "eval_NEIMS_old_steps_per_second": 1.279, "step": 192000 }, { - "epoch": 0.86, - "learning_rate": 7.191381552396755e-06, - "loss": 0.1417, + "epoch": 0.43, + "eval_RASSP_old_canon_smiles": 0.9464410851937131, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.21039810458170655, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6478105112718161, + "eval_RASSP_old_exact_mols": 0.20973070377415157, + "eval_RASSP_old_exact_smiles": 0.20402442686955652, + "eval_RASSP_old_loss": 0.1303142011165619, + "eval_RASSP_old_matched_formulas": 0.823539226482464, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5251134073877861, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.20979744385490706, + "eval_RASSP_old_runtime": 415.5489, + "eval_RASSP_old_samples_per_second": 72.114, + "eval_RASSP_old_steps_per_second": 1.129, + "step": 192000 + }, + { + "epoch": 0.43, + "eval_NIST_canon_smiles": 0.8675160591972176, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02140043297725095, + "eval_NIST_daylight_tanimoto_simil": 0.28541157575111625, + "eval_NIST_exact_mols": 0.020406714696383575, + "eval_NIST_exact_smiles": 0.019377506476913796, + "eval_NIST_loss": 1.8597558736801147, + "eval_NIST_matched_formulas": 0.10668275543883309, + "eval_NIST_morgan_tanimoto_simil": 0.23762745213216818, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02129396316144373, + "eval_NIST_runtime": 559.406, + "eval_NIST_samples_per_second": 50.369, + "eval_NIST_steps_per_second": 0.788, + "step": 192000 + }, + { + "epoch": 0.43, + "learning_rate": 2.8643990067336302e-05, + "loss": 0.1382, "step": 192010 }, { - "epoch": 0.86, - "learning_rate": 7.189139500470832e-06, - "loss": 0.1425, + "epoch": 0.43, + "learning_rate": 2.864287152412698e-05, + "loss": 0.1472, "step": 192020 }, { - "epoch": 0.86, - "learning_rate": 7.186897448544909e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.864175298091765e-05, + "loss": 0.1417, "step": 192030 }, { - "epoch": 0.86, - "learning_rate": 7.184655396618986e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.864063443770833e-05, + "loss": 0.1426, "step": 192040 }, { - "epoch": 0.86, - "learning_rate": 7.182413344693064e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.8639515894499007e-05, + "loss": 0.1413, "step": 192050 }, { - "epoch": 0.86, - "learning_rate": 7.180171292767141e-06, - "loss": 0.1385, + "epoch": 0.43, + "learning_rate": 2.863839735128968e-05, + "loss": 0.1438, "step": 192060 }, { - "epoch": 0.86, - "learning_rate": 7.177929240841218e-06, - "loss": 0.1424, + "epoch": 0.43, + "learning_rate": 2.863727880808036e-05, + "loss": 0.1421, "step": 192070 }, { - "epoch": 0.86, - "learning_rate": 7.1756871889152965e-06, - "loss": 0.1426, + "epoch": 0.43, + "learning_rate": 2.863616026487103e-05, + "loss": 0.1424, "step": 192080 }, { - "epoch": 0.86, - "learning_rate": 7.1734451369893735e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.863504172166171e-05, + "loss": 0.1458, "step": 192090 }, { - "epoch": 0.86, - "learning_rate": 7.1712030850634505e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.8633923178452386e-05, + "loss": 0.1441, "step": 192100 }, { - "epoch": 0.86, - "learning_rate": 7.1689610331375275e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.863280463524306e-05, + "loss": 0.1421, "step": 192110 }, { - "epoch": 0.86, - "learning_rate": 7.166718981211605e-06, - "loss": 0.1427, + "epoch": 0.43, + "learning_rate": 2.863168609203374e-05, + "loss": 0.1433, "step": 192120 }, { - "epoch": 0.86, - "learning_rate": 7.1644769292856824e-06, - "loss": 0.143, + "epoch": 0.43, + "learning_rate": 2.863056754882441e-05, + "loss": 0.1445, "step": 192130 }, { - "epoch": 0.86, - "learning_rate": 7.1622348773597595e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8629449005615088e-05, + "loss": 0.1411, "step": 192140 }, { - "epoch": 0.86, - "learning_rate": 7.159992825433838e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8628330462405762e-05, + "loss": 0.1402, "step": 192150 }, { - "epoch": 0.86, - "learning_rate": 7.157750773507915e-06, - "loss": 0.1451, + "epoch": 0.43, + "learning_rate": 2.862721191919644e-05, + "loss": 0.146, "step": 192160 }, { - "epoch": 0.86, - "learning_rate": 7.155732926774585e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.8626093375987118e-05, + "loss": 0.1432, "step": 192170 }, { - "epoch": 0.86, - "learning_rate": 7.153490874848662e-06, - "loss": 0.1379, + "epoch": 0.43, + "learning_rate": 2.862497483277779e-05, + "loss": 0.145, "step": 192180 }, { - "epoch": 0.86, - "learning_rate": 7.151248822922739e-06, - "loss": 0.146, + "epoch": 0.43, + "learning_rate": 2.8623856289568467e-05, + "loss": 0.1417, "step": 192190 }, { - "epoch": 0.86, - "learning_rate": 7.149006770996816e-06, - "loss": 0.1454, + "epoch": 0.43, + "learning_rate": 2.8622737746359142e-05, + "loss": 0.1448, "step": 192200 }, { - "epoch": 0.86, - "learning_rate": 7.146764719070894e-06, - "loss": 0.1399, + "epoch": 0.43, + "learning_rate": 2.862161920314982e-05, + "loss": 0.1455, "step": 192210 }, { - "epoch": 0.86, - "learning_rate": 7.144522667144972e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.8620500659940498e-05, + "loss": 0.1403, "step": 192220 }, { - "epoch": 0.86, - "learning_rate": 7.142280615219049e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.861938211673117e-05, + "loss": 0.1452, "step": 192230 }, { - "epoch": 0.86, - "learning_rate": 7.140038563293126e-06, - "loss": 0.1459, + "epoch": 0.43, + "learning_rate": 2.8618263573521847e-05, + "loss": 0.1432, "step": 192240 }, { - "epoch": 0.86, - "learning_rate": 7.137796511367203e-06, - "loss": 0.1385, + "epoch": 0.43, + "learning_rate": 2.861714503031252e-05, + "loss": 0.146, "step": 192250 }, { - "epoch": 0.86, - "learning_rate": 7.1355544594412804e-06, - "loss": 0.1412, + "epoch": 0.43, + "learning_rate": 2.86160264871032e-05, + "loss": 0.1441, "step": 192260 }, { - "epoch": 0.86, - "learning_rate": 7.133312407515358e-06, - "loss": 0.1477, + "epoch": 0.43, + "learning_rate": 2.8614907943893877e-05, + "loss": 0.1438, "step": 192270 }, { - "epoch": 0.86, - "learning_rate": 7.131070355589436e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.861378940068455e-05, + "loss": 0.14, "step": 192280 }, { - "epoch": 0.86, - "learning_rate": 7.128828303663514e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8612670857475226e-05, + "loss": 0.1386, "step": 192290 }, { - "epoch": 0.86, - "learning_rate": 7.126586251737591e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.86115523142659e-05, + "loss": 0.1427, "step": 192300 }, { - "epoch": 0.86, - "learning_rate": 7.124344199811668e-06, - "loss": 0.1433, + "epoch": 0.43, + "learning_rate": 2.861043377105658e-05, + "loss": 0.1455, "step": 192310 }, { - "epoch": 0.86, - "learning_rate": 7.122102147885745e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.8609315227847257e-05, + "loss": 0.1483, "step": 192320 }, { - "epoch": 0.86, - "learning_rate": 7.119860095959822e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.8608196684637928e-05, + "loss": 0.1443, "step": 192330 }, { - "epoch": 0.86, - "learning_rate": 7.1176180440339e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.8607078141428606e-05, + "loss": 0.1454, "step": 192340 }, { - "epoch": 0.86, - "learning_rate": 7.115375992107978e-06, - "loss": 0.1458, + "epoch": 0.43, + "learning_rate": 2.8605959598219277e-05, + "loss": 0.1435, "step": 192350 }, { - "epoch": 0.86, - "learning_rate": 7.113133940182056e-06, - "loss": 0.1402, + "epoch": 0.43, + "learning_rate": 2.8604841055009958e-05, + "loss": 0.1433, "step": 192360 }, { - "epoch": 0.86, - "learning_rate": 7.110891888256133e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8603722511800636e-05, + "loss": 0.1438, "step": 192370 }, { - "epoch": 0.86, - "learning_rate": 7.10864983633021e-06, - "loss": 0.1448, + "epoch": 0.43, + "learning_rate": 2.8602603968591307e-05, + "loss": 0.1485, "step": 192380 }, { - "epoch": 0.86, - "learning_rate": 7.106407784404287e-06, - "loss": 0.1437, + "epoch": 0.43, + "learning_rate": 2.8601485425381985e-05, + "loss": 0.1474, "step": 192390 }, { - "epoch": 0.86, - "learning_rate": 7.104165732478364e-06, - "loss": 0.139, + "epoch": 0.43, + "learning_rate": 2.8600366882172656e-05, + "loss": 0.1385, "step": 192400 }, { - "epoch": 0.86, - "learning_rate": 7.101923680552442e-06, - "loss": 0.1381, + "epoch": 0.43, + "learning_rate": 2.8599248338963334e-05, + "loss": 0.1416, "step": 192410 }, { - "epoch": 0.86, - "learning_rate": 7.09968162862652e-06, - "loss": 0.1377, + "epoch": 0.43, + "learning_rate": 2.8598129795754016e-05, + "loss": 0.1422, "step": 192420 }, { - "epoch": 0.86, - "learning_rate": 7.0974395767005975e-06, - "loss": 0.1394, + "epoch": 0.43, + "learning_rate": 2.8597011252544687e-05, + "loss": 0.1429, "step": 192430 }, { - "epoch": 0.86, - "learning_rate": 7.0951975247746745e-06, - "loss": 0.1394, + "epoch": 0.43, + "learning_rate": 2.8595892709335365e-05, + "loss": 0.1428, "step": 192440 }, { - "epoch": 0.86, - "learning_rate": 7.0929554728487515e-06, - "loss": 0.1489, + "epoch": 0.43, + "learning_rate": 2.8594774166126036e-05, + "loss": 0.1473, "step": 192450 }, { - "epoch": 0.86, - "learning_rate": 7.0907134209228285e-06, - "loss": 0.136, + "epoch": 0.43, + "learning_rate": 2.8593655622916714e-05, + "loss": 0.1427, "step": 192460 }, { - "epoch": 0.86, - "learning_rate": 7.0884713689969056e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.859253707970739e-05, + "loss": 0.1446, "step": 192470 }, { - "epoch": 0.86, - "learning_rate": 7.0862293170709834e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.8591418536498066e-05, + "loss": 0.1411, "step": 192480 }, { - "epoch": 0.86, - "learning_rate": 7.083987265145061e-06, - "loss": 0.1471, + "epoch": 0.43, + "learning_rate": 2.8590299993288744e-05, + "loss": 0.1374, "step": 192490 }, { - "epoch": 0.86, - "learning_rate": 7.081745213219139e-06, - "loss": 0.1448, + "epoch": 0.43, + "learning_rate": 2.8589181450079415e-05, + "loss": 0.1459, "step": 192500 }, { - "epoch": 0.86, - "learning_rate": 7.079503161293216e-06, - "loss": 0.1471, + "epoch": 0.43, + "learning_rate": 2.8588062906870093e-05, + "loss": 0.1424, "step": 192510 }, { - "epoch": 0.86, - "learning_rate": 7.077261109367293e-06, - "loss": 0.147, + "epoch": 0.43, + "learning_rate": 2.8586944363660768e-05, + "loss": 0.1442, "step": 192520 }, { - "epoch": 0.86, - "learning_rate": 7.07501905744137e-06, - "loss": 0.1462, + "epoch": 0.43, + "learning_rate": 2.8585825820451446e-05, + "loss": 0.1485, "step": 192530 }, { - "epoch": 0.86, - "learning_rate": 7.072777005515448e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.8584707277242124e-05, + "loss": 0.1444, "step": 192540 }, { - "epoch": 0.86, - "learning_rate": 7.070534953589525e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8583588734032795e-05, + "loss": 0.1459, "step": 192550 }, { - "epoch": 0.86, - "learning_rate": 7.068292901663604e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8582470190823473e-05, + "loss": 0.1482, "step": 192560 }, { - "epoch": 0.86, - "learning_rate": 7.066050849737681e-06, - "loss": 0.1363, + "epoch": 0.43, + "learning_rate": 2.8581351647614147e-05, + "loss": 0.1467, "step": 192570 }, { - "epoch": 0.86, - "learning_rate": 7.063808797811758e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.8580344958725756e-05, + "loss": 0.1418, "step": 192580 }, { - "epoch": 0.86, - "learning_rate": 7.061566745885835e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.857922641551643e-05, + "loss": 0.1476, "step": 192590 }, { - "epoch": 0.86, - "learning_rate": 7.059324693959912e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.857810787230711e-05, + "loss": 0.1418, "step": 192600 }, { - "epoch": 0.86, - "learning_rate": 7.05708264203399e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8576989329097786e-05, + "loss": 0.1443, "step": 192610 }, { - "epoch": 0.86, - "learning_rate": 7.054840590108067e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.8575870785888458e-05, + "loss": 0.1437, "step": 192620 }, { - "epoch": 0.86, - "learning_rate": 7.0525985381821456e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.8574752242679136e-05, + "loss": 0.1395, "step": 192630 }, { - "epoch": 0.86, - "learning_rate": 7.050356486256223e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.857363369946981e-05, + "loss": 0.147, "step": 192640 }, { - "epoch": 0.86, - "learning_rate": 7.0481144343303e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8572515156260488e-05, + "loss": 0.1453, "step": 192650 }, { - "epoch": 0.86, - "learning_rate": 7.045872382404377e-06, - "loss": 0.1416, + "epoch": 0.43, + "learning_rate": 2.8571396613051166e-05, + "loss": 0.1441, "step": 192660 }, { - "epoch": 0.86, - "learning_rate": 7.043630330478454e-06, - "loss": 0.147, + "epoch": 0.43, + "learning_rate": 2.8570278069841837e-05, + "loss": 0.1395, "step": 192670 }, { - "epoch": 0.86, - "learning_rate": 7.0413882785525315e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.8569159526632515e-05, + "loss": 0.1509, "step": 192680 }, { - "epoch": 0.86, - "learning_rate": 7.0391462266266086e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.856804098342319e-05, + "loss": 0.1403, "step": 192690 }, { - "epoch": 0.86, - "learning_rate": 7.036904174700687e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.8566922440213867e-05, + "loss": 0.1413, "step": 192700 }, { - "epoch": 0.86, - "learning_rate": 7.034662122774764e-06, - "loss": 0.1395, + "epoch": 0.43, + "learning_rate": 2.8565803897004545e-05, + "loss": 0.1384, "step": 192710 }, { - "epoch": 0.86, - "learning_rate": 7.032420070848841e-06, - "loss": 0.1381, + "epoch": 0.43, + "learning_rate": 2.8564685353795217e-05, + "loss": 0.142, "step": 192720 }, { - "epoch": 0.86, - "learning_rate": 7.030178018922918e-06, - "loss": 0.1405, + "epoch": 0.43, + "learning_rate": 2.8563566810585894e-05, + "loss": 0.1418, "step": 192730 }, { - "epoch": 0.86, - "learning_rate": 7.027935966996995e-06, - "loss": 0.143, + "epoch": 0.43, + "learning_rate": 2.856244826737657e-05, + "loss": 0.1408, "step": 192740 }, { - "epoch": 0.86, - "learning_rate": 7.025693915071073e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.8561329724167247e-05, + "loss": 0.1411, "step": 192750 }, { - "epoch": 0.86, - "learning_rate": 7.02345186314515e-06, - "loss": 0.135, + "epoch": 0.43, + "learning_rate": 2.8560211180957925e-05, + "loss": 0.1435, "step": 192760 }, { - "epoch": 0.86, - "learning_rate": 7.021209811219229e-06, - "loss": 0.1417, + "epoch": 0.43, + "learning_rate": 2.8559092637748596e-05, + "loss": 0.143, "step": 192770 }, { - "epoch": 0.86, - "learning_rate": 7.018967759293306e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.8557974094539274e-05, + "loss": 0.146, "step": 192780 }, { - "epoch": 0.86, - "learning_rate": 7.016725707367383e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.855685555132995e-05, + "loss": 0.1445, "step": 192790 }, { - "epoch": 0.86, - "learning_rate": 7.01448365544146e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.8555737008120626e-05, + "loss": 0.1457, "step": 192800 }, { - "epoch": 0.86, - "learning_rate": 7.012241603515537e-06, - "loss": 0.134, + "epoch": 0.43, + "learning_rate": 2.8554618464911304e-05, + "loss": 0.1429, "step": 192810 }, { - "epoch": 0.86, - "learning_rate": 7.009999551589615e-06, - "loss": 0.1379, + "epoch": 0.43, + "learning_rate": 2.8553499921701975e-05, + "loss": 0.1497, "step": 192820 }, { - "epoch": 0.86, - "learning_rate": 7.007757499663692e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8552381378492653e-05, + "loss": 0.1421, "step": 192830 }, { - "epoch": 0.86, - "learning_rate": 7.005515447737771e-06, - "loss": 0.1364, + "epoch": 0.43, + "learning_rate": 2.8551262835283328e-05, + "loss": 0.1422, "step": 192840 }, { - "epoch": 0.86, - "learning_rate": 7.003273395811848e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.8550144292074006e-05, + "loss": 0.1412, "step": 192850 }, { - "epoch": 0.86, - "learning_rate": 7.001031343885925e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8549025748864677e-05, + "loss": 0.141, "step": 192860 }, { - "epoch": 0.86, - "learning_rate": 6.998789291960002e-06, - "loss": 0.1343, + "epoch": 0.43, + "learning_rate": 2.8547907205655355e-05, + "loss": 0.1439, "step": 192870 }, { - "epoch": 0.86, - "learning_rate": 6.99654724003408e-06, - "loss": 0.1426, + "epoch": 0.43, + "learning_rate": 2.8546788662446033e-05, + "loss": 0.1407, "step": 192880 }, { - "epoch": 0.86, - "learning_rate": 6.994305188108157e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.8545670119236707e-05, + "loss": 0.143, "step": 192890 }, { - "epoch": 0.86, - "learning_rate": 6.992063136182234e-06, - "loss": 0.1437, + "epoch": 0.43, + "learning_rate": 2.8544551576027385e-05, + "loss": 0.1429, "step": 192900 }, { - "epoch": 0.86, - "learning_rate": 6.989821084256312e-06, - "loss": 0.1463, + "epoch": 0.43, + "learning_rate": 2.8543433032818057e-05, + "loss": 0.1392, "step": 192910 }, { - "epoch": 0.86, - "learning_rate": 6.987579032330389e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.8542314489608734e-05, + "loss": 0.1425, "step": 192920 }, { - "epoch": 0.86, - "learning_rate": 6.9853369804044664e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.8541195946399412e-05, + "loss": 0.1457, "step": 192930 }, { - "epoch": 0.86, - "learning_rate": 6.9830949284785435e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8540077403190087e-05, + "loss": 0.1444, "step": 192940 }, { - "epoch": 0.86, - "learning_rate": 6.980852876552621e-06, - "loss": 0.1387, + "epoch": 0.43, + "learning_rate": 2.8538958859980765e-05, + "loss": 0.1421, "step": 192950 }, { - "epoch": 0.86, - "learning_rate": 6.978610824626698e-06, - "loss": 0.1452, + "epoch": 0.43, + "learning_rate": 2.8537840316771436e-05, + "loss": 0.1425, "step": 192960 }, { - "epoch": 0.86, - "learning_rate": 6.976368772700777e-06, - "loss": 0.1443, + "epoch": 0.43, + "learning_rate": 2.8536721773562114e-05, + "loss": 0.1427, "step": 192970 }, { - "epoch": 0.86, - "learning_rate": 6.974126720774854e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.8535603230352792e-05, + "loss": 0.1421, "step": 192980 }, { - "epoch": 0.86, - "learning_rate": 6.971884668848931e-06, - "loss": 0.1345, + "epoch": 0.43, + "learning_rate": 2.8534484687143463e-05, + "loss": 0.1443, "step": 192990 }, { - "epoch": 0.86, - "learning_rate": 6.969642616923008e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.8533366143934144e-05, + "loss": 0.1444, "step": 193000 }, { - "epoch": 0.86, - "learning_rate": 6.967400564997085e-06, - "loss": 0.1474, + "epoch": 0.43, + "learning_rate": 2.8532247600724815e-05, + "loss": 0.1458, "step": 193010 }, { - "epoch": 0.86, - "learning_rate": 6.965158513071163e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.8531129057515493e-05, + "loss": 0.141, "step": 193020 }, { - "epoch": 0.86, - "learning_rate": 6.96291646114524e-06, - "loss": 0.1417, + "epoch": 0.43, + "learning_rate": 2.853001051430617e-05, + "loss": 0.1399, "step": 193030 }, { - "epoch": 0.86, - "learning_rate": 6.960674409219319e-06, - "loss": 0.1379, + "epoch": 0.43, + "learning_rate": 2.8528891971096842e-05, + "loss": 0.1401, "step": 193040 }, { - "epoch": 0.86, - "learning_rate": 6.958432357293396e-06, - "loss": 0.1424, + "epoch": 0.43, + "learning_rate": 2.852777342788752e-05, + "loss": 0.141, "step": 193050 }, { - "epoch": 0.86, - "learning_rate": 6.956190305367473e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.8526654884678195e-05, + "loss": 0.1427, "step": 193060 }, { - "epoch": 0.86, - "learning_rate": 6.95394825344155e-06, - "loss": 0.1475, + "epoch": 0.43, + "learning_rate": 2.8525536341468873e-05, + "loss": 0.1474, "step": 193070 }, { - "epoch": 0.86, - "learning_rate": 6.951706201515627e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.852441779825955e-05, + "loss": 0.1448, "step": 193080 }, { - "epoch": 0.86, - "learning_rate": 6.949464149589705e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8523299255050222e-05, + "loss": 0.1472, "step": 193090 }, { - "epoch": 0.86, - "learning_rate": 6.947222097663782e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.85221807118409e-05, + "loss": 0.1471, "step": 193100 }, { - "epoch": 0.86, - "learning_rate": 6.9449800457378605e-06, - "loss": 0.1434, + "epoch": 0.43, + "learning_rate": 2.8521062168631574e-05, + "loss": 0.1499, "step": 193110 }, { - "epoch": 0.86, - "learning_rate": 6.9427379938119375e-06, - "loss": 0.1438, + "epoch": 0.43, + "learning_rate": 2.8519943625422252e-05, + "loss": 0.1428, "step": 193120 }, { - "epoch": 0.86, - "learning_rate": 6.9404959418860145e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.851882508221293e-05, + "loss": 0.1376, "step": 193130 }, { - "epoch": 0.86, - "learning_rate": 6.9382538899600916e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.85177065390036e-05, + "loss": 0.1475, "step": 193140 }, { - "epoch": 0.86, - "learning_rate": 6.9360118380341694e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.851658799579428e-05, + "loss": 0.1426, "step": 193150 }, { - "epoch": 0.86, - "learning_rate": 6.9337697861082465e-06, - "loss": 0.1454, + "epoch": 0.43, + "learning_rate": 2.8515469452584954e-05, + "loss": 0.1442, "step": 193160 }, { - "epoch": 0.86, - "learning_rate": 6.9315277341823235e-06, - "loss": 0.1467, + "epoch": 0.43, + "learning_rate": 2.8514350909375632e-05, + "loss": 0.1476, "step": 193170 }, { - "epoch": 0.86, - "learning_rate": 6.929285682256402e-06, - "loss": 0.1416, + "epoch": 0.43, + "learning_rate": 2.8513232366166303e-05, + "loss": 0.1436, "step": 193180 }, { - "epoch": 0.86, - "learning_rate": 6.927043630330479e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.851211382295698e-05, + "loss": 0.1421, "step": 193190 }, { - "epoch": 0.86, - "learning_rate": 6.924801578404556e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.851099527974766e-05, + "loss": 0.1443, "step": 193200 }, { - "epoch": 0.86, - "learning_rate": 6.922559526478633e-06, - "loss": 0.1471, + "epoch": 0.43, + "learning_rate": 2.8509876736538333e-05, + "loss": 0.1428, "step": 193210 }, { - "epoch": 0.86, - "learning_rate": 6.920317474552711e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.850875819332901e-05, + "loss": 0.1436, "step": 193220 }, { - "epoch": 0.86, - "learning_rate": 6.918075422626788e-06, - "loss": 0.1427, + "epoch": 0.43, + "learning_rate": 2.8507639650119682e-05, + "loss": 0.1393, "step": 193230 }, { - "epoch": 0.86, - "learning_rate": 6.915833370700865e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.850652110691036e-05, + "loss": 0.1417, "step": 193240 }, { - "epoch": 0.86, - "learning_rate": 6.913591318774944e-06, - "loss": 0.1404, + "epoch": 0.43, + "learning_rate": 2.8505402563701038e-05, + "loss": 0.1438, "step": 193250 }, { - "epoch": 0.86, - "learning_rate": 6.911349266849021e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.8504284020491713e-05, + "loss": 0.1432, "step": 193260 }, { - "epoch": 0.86, - "learning_rate": 6.909107214923098e-06, - "loss": 0.144, + "epoch": 0.43, + "learning_rate": 2.850316547728239e-05, + "loss": 0.138, "step": 193270 }, { - "epoch": 0.86, - "learning_rate": 6.906865162997175e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.8502046934073062e-05, + "loss": 0.1432, "step": 193280 }, { - "epoch": 0.86, - "learning_rate": 6.904623111071253e-06, - "loss": 0.141, + "epoch": 0.43, + "learning_rate": 2.850092839086374e-05, + "loss": 0.1447, "step": 193290 }, { - "epoch": 0.86, - "learning_rate": 6.90238105914533e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.8499809847654418e-05, + "loss": 0.1466, "step": 193300 }, { - "epoch": 0.86, - "learning_rate": 6.900139007219407e-06, - "loss": 0.1416, + "epoch": 0.43, + "learning_rate": 2.8498691304445092e-05, + "loss": 0.1382, "step": 193310 }, { - "epoch": 0.86, - "learning_rate": 6.897896955293486e-06, - "loss": 0.1441, + "epoch": 0.43, + "learning_rate": 2.849757276123577e-05, + "loss": 0.1421, "step": 193320 }, { - "epoch": 0.86, - "learning_rate": 6.895654903367563e-06, - "loss": 0.1387, + "epoch": 0.43, + "learning_rate": 2.849645421802644e-05, + "loss": 0.1425, "step": 193330 }, { - "epoch": 0.86, - "learning_rate": 6.89341285144164e-06, - "loss": 0.1369, + "epoch": 0.43, + "learning_rate": 2.849533567481712e-05, + "loss": 0.1432, "step": 193340 }, { - "epoch": 0.86, - "learning_rate": 6.891170799515717e-06, - "loss": 0.1379, + "epoch": 0.43, + "learning_rate": 2.8494217131607797e-05, + "loss": 0.1457, "step": 193350 }, { - "epoch": 0.86, - "learning_rate": 6.8889287475897946e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.8493098588398472e-05, + "loss": 0.148, "step": 193360 }, { - "epoch": 0.86, - "learning_rate": 6.886686695663872e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.849198004518915e-05, + "loss": 0.1481, "step": 193370 }, { - "epoch": 0.86, - "learning_rate": 6.884444643737949e-06, - "loss": 0.1413, + "epoch": 0.43, + "learning_rate": 2.849086150197982e-05, + "loss": 0.1409, "step": 193380 }, { - "epoch": 0.86, - "learning_rate": 6.882202591812027e-06, - "loss": 0.1476, + "epoch": 0.43, + "learning_rate": 2.84897429587705e-05, + "loss": 0.1448, "step": 193390 }, { - "epoch": 0.86, - "learning_rate": 6.879960539886104e-06, - "loss": 0.1402, + "epoch": 0.43, + "learning_rate": 2.8488624415561177e-05, + "loss": 0.1401, "step": 193400 }, { - "epoch": 0.86, - "learning_rate": 6.877718487960181e-06, - "loss": 0.1395, + "epoch": 0.43, + "learning_rate": 2.8487505872351848e-05, + "loss": 0.1474, "step": 193410 }, { - "epoch": 0.86, - "learning_rate": 6.875476436034259e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.848638732914253e-05, + "loss": 0.1461, "step": 193420 }, { - "epoch": 0.86, - "learning_rate": 6.873234384108336e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.84852687859332e-05, + "loss": 0.1449, "step": 193430 }, { - "epoch": 0.86, - "learning_rate": 6.870992332182413e-06, - "loss": 0.1446, + "epoch": 0.43, + "learning_rate": 2.8484150242723878e-05, + "loss": 0.1383, "step": 193440 }, { - "epoch": 0.86, - "learning_rate": 6.86875028025649e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.8483031699514556e-05, + "loss": 0.1482, "step": 193450 }, { - "epoch": 0.86, - "learning_rate": 6.866508228330569e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8481913156305227e-05, + "loss": 0.1457, "step": 193460 }, { - "epoch": 0.86, - "learning_rate": 6.864266176404646e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.8480794613095905e-05, + "loss": 0.1422, "step": 193470 }, { - "epoch": 0.86, - "learning_rate": 6.862024124478723e-06, - "loss": 0.1419, + "epoch": 0.43, + "learning_rate": 2.847967606988658e-05, + "loss": 0.142, "step": 193480 }, { - "epoch": 0.86, - "learning_rate": 6.859782072552801e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8478557526677258e-05, + "loss": 0.1419, "step": 193490 }, { - "epoch": 0.86, - "learning_rate": 6.857540020626878e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.847743898346793e-05, + "loss": 0.1392, "step": 193500 }, { - "epoch": 0.86, - "learning_rate": 6.855297968700955e-06, - "loss": 0.1467, + "epoch": 0.43, + "learning_rate": 2.8476320440258607e-05, + "loss": 0.1455, "step": 193510 }, { - "epoch": 0.86, - "learning_rate": 6.853055916775032e-06, - "loss": 0.148, + "epoch": 0.43, + "learning_rate": 2.8475201897049285e-05, + "loss": 0.1427, "step": 193520 }, { - "epoch": 0.86, - "learning_rate": 6.850813864849111e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.847408335383996e-05, + "loss": 0.1418, "step": 193530 }, { - "epoch": 0.86, - "learning_rate": 6.848571812923188e-06, - "loss": 0.1363, + "epoch": 0.43, + "learning_rate": 2.8472964810630637e-05, + "loss": 0.1411, "step": 193540 }, { - "epoch": 0.86, - "learning_rate": 6.846329760997265e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.847184626742131e-05, + "loss": 0.1478, "step": 193550 }, { - "epoch": 0.86, - "learning_rate": 6.844087709071343e-06, - "loss": 0.1378, + "epoch": 0.43, + "learning_rate": 2.8470727724211986e-05, + "loss": 0.1457, "step": 193560 }, { - "epoch": 0.86, - "learning_rate": 6.84184565714542e-06, - "loss": 0.1371, + "epoch": 0.43, + "learning_rate": 2.8469609181002664e-05, + "loss": 0.1463, "step": 193570 }, { - "epoch": 0.86, - "learning_rate": 6.839603605219497e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.846849063779334e-05, + "loss": 0.138, "step": 193580 }, { - "epoch": 0.86, - "learning_rate": 6.837361553293574e-06, - "loss": 0.1419, + "epoch": 0.43, + "learning_rate": 2.8467372094584017e-05, + "loss": 0.1431, "step": 193590 }, { - "epoch": 0.86, - "learning_rate": 6.8351195013676524e-06, - "loss": 0.1468, + "epoch": 0.43, + "learning_rate": 2.8466253551374688e-05, + "loss": 0.1432, "step": 193600 }, { - "epoch": 0.86, - "learning_rate": 6.8328774494417295e-06, - "loss": 0.1363, + "epoch": 0.43, + "learning_rate": 2.8465135008165366e-05, + "loss": 0.1469, "step": 193610 }, { - "epoch": 0.86, - "learning_rate": 6.8306353975158065e-06, - "loss": 0.1371, + "epoch": 0.43, + "learning_rate": 2.8464016464956044e-05, + "loss": 0.1479, "step": 193620 }, { - "epoch": 0.86, - "learning_rate": 6.828393345589884e-06, - "loss": 0.1469, + "epoch": 0.43, + "learning_rate": 2.8462897921746718e-05, + "loss": 0.146, "step": 193630 }, { - "epoch": 0.86, - "learning_rate": 6.826151293663961e-06, - "loss": 0.138, + "epoch": 0.43, + "learning_rate": 2.8461779378537396e-05, + "loss": 0.1432, "step": 193640 }, { - "epoch": 0.86, - "learning_rate": 6.823909241738038e-06, - "loss": 0.1417, + "epoch": 0.43, + "learning_rate": 2.8460660835328067e-05, + "loss": 0.1449, "step": 193650 }, { - "epoch": 0.86, - "learning_rate": 6.821667189812117e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.8459542292118745e-05, + "loss": 0.1466, "step": 193660 }, { - "epoch": 0.86, - "learning_rate": 6.819425137886194e-06, - "loss": 0.1393, + "epoch": 0.43, + "learning_rate": 2.8458423748909423e-05, + "loss": 0.1365, "step": 193670 }, { - "epoch": 0.86, - "learning_rate": 6.817183085960271e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.8457305205700098e-05, + "loss": 0.1443, "step": 193680 }, { - "epoch": 0.86, - "learning_rate": 6.814941034034349e-06, - "loss": 0.1404, + "epoch": 0.43, + "learning_rate": 2.8456186662490776e-05, + "loss": 0.141, "step": 193690 }, { - "epoch": 0.86, - "learning_rate": 6.812698982108426e-06, - "loss": 0.138, + "epoch": 0.43, + "learning_rate": 2.8455068119281447e-05, + "loss": 0.1461, "step": 193700 }, { - "epoch": 0.86, - "learning_rate": 6.810456930182503e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.8453949576072125e-05, + "loss": 0.1425, "step": 193710 }, { - "epoch": 0.86, - "learning_rate": 6.80821487825658e-06, - "loss": 0.1467, + "epoch": 0.43, + "learning_rate": 2.8452831032862803e-05, + "loss": 0.1418, "step": 193720 }, { - "epoch": 0.86, - "learning_rate": 6.805972826330659e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.8451712489653477e-05, + "loss": 0.145, "step": 193730 }, { - "epoch": 0.86, - "learning_rate": 6.803730774404736e-06, - "loss": 0.1438, + "epoch": 0.43, + "learning_rate": 2.8450593946444155e-05, + "loss": 0.1458, "step": 193740 }, { - "epoch": 0.86, - "learning_rate": 6.801488722478813e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.8449475403234826e-05, + "loss": 0.1435, "step": 193750 }, { - "epoch": 0.86, - "learning_rate": 6.799246670552891e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.8448356860025504e-05, + "loss": 0.1418, "step": 193760 }, { - "epoch": 0.87, - "learning_rate": 6.797004618626968e-06, - "loss": 0.1366, + "epoch": 0.43, + "learning_rate": 2.8447238316816182e-05, + "loss": 0.1415, "step": 193770 }, { - "epoch": 0.87, - "learning_rate": 6.794762566701045e-06, - "loss": 0.1433, + "epoch": 0.43, + "learning_rate": 2.8446119773606857e-05, + "loss": 0.1405, "step": 193780 }, { - "epoch": 0.87, - "learning_rate": 6.792520514775122e-06, - "loss": 0.1466, + "epoch": 0.43, + "learning_rate": 2.8445001230397535e-05, + "loss": 0.1473, "step": 193790 }, { - "epoch": 0.87, - "learning_rate": 6.7902784628492005e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.8443882687188206e-05, + "loss": 0.1395, "step": 193800 }, { - "epoch": 0.87, - "learning_rate": 6.7880364109232776e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.8442764143978884e-05, + "loss": 0.1423, "step": 193810 }, { - "epoch": 0.87, - "learning_rate": 6.785794358997355e-06, - "loss": 0.1402, + "epoch": 0.43, + "learning_rate": 2.8441645600769555e-05, + "loss": 0.1473, "step": 193820 }, { - "epoch": 0.87, - "learning_rate": 6.7835523070714325e-06, - "loss": 0.1416, + "epoch": 0.43, + "learning_rate": 2.8440527057560236e-05, + "loss": 0.1435, "step": 193830 }, { - "epoch": 0.87, - "learning_rate": 6.7813102551455095e-06, - "loss": 0.1396, + "epoch": 0.43, + "learning_rate": 2.8439408514350914e-05, + "loss": 0.1436, "step": 193840 }, { - "epoch": 0.87, - "learning_rate": 6.7790682032195865e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.8438289971141585e-05, + "loss": 0.1429, "step": 193850 }, { - "epoch": 0.87, - "learning_rate": 6.7768261512936635e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8437171427932263e-05, + "loss": 0.1434, "step": 193860 }, { - "epoch": 0.87, - "learning_rate": 6.774584099367742e-06, - "loss": 0.1425, + "epoch": 0.43, + "learning_rate": 2.8436052884722934e-05, + "loss": 0.1405, "step": 193870 }, { - "epoch": 0.87, - "learning_rate": 6.772342047441819e-06, - "loss": 0.1462, + "epoch": 0.43, + "learning_rate": 2.8434934341513612e-05, + "loss": 0.1395, "step": 193880 }, { - "epoch": 0.87, - "learning_rate": 6.770099995515896e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.8433815798304294e-05, + "loss": 0.1442, "step": 193890 }, { - "epoch": 0.87, - "learning_rate": 6.767857943589974e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.8432697255094965e-05, + "loss": 0.1426, "step": 193900 }, { - "epoch": 0.87, - "learning_rate": 6.765615891664051e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.8431578711885643e-05, + "loss": 0.144, "step": 193910 }, { - "epoch": 0.87, - "learning_rate": 6.763373839738128e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8430460168676314e-05, + "loss": 0.1431, "step": 193920 }, { - "epoch": 0.87, - "learning_rate": 6.761131787812205e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.842934162546699e-05, + "loss": 0.1429, "step": 193930 }, { - "epoch": 0.87, - "learning_rate": 6.758889735886284e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.842822308225767e-05, + "loss": 0.1434, "step": 193940 }, { - "epoch": 0.87, - "learning_rate": 6.756647683960361e-06, - "loss": 0.1413, + "epoch": 0.43, + "learning_rate": 2.8427104539048344e-05, + "loss": 0.1407, "step": 193950 }, { - "epoch": 0.87, - "learning_rate": 6.754405632034439e-06, - "loss": 0.143, + "epoch": 0.43, + "learning_rate": 2.8425985995839022e-05, + "loss": 0.1403, "step": 193960 }, { - "epoch": 0.87, - "learning_rate": 6.752163580108516e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8424867452629693e-05, + "loss": 0.1457, "step": 193970 }, { - "epoch": 0.87, - "learning_rate": 6.749921528182593e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.842374890942037e-05, + "loss": 0.1453, "step": 193980 }, { - "epoch": 0.87, - "learning_rate": 6.74767947625667e-06, - "loss": 0.1426, + "epoch": 0.43, + "learning_rate": 2.842263036621105e-05, + "loss": 0.1425, "step": 193990 }, { - "epoch": 0.87, - "learning_rate": 6.745437424330747e-06, - "loss": 0.1431, + "epoch": 0.43, + "learning_rate": 2.8421511823001724e-05, + "loss": 0.1422, "step": 194000 }, { - "epoch": 0.87, - "learning_rate": 6.743195372404826e-06, - "loss": 0.1415, + "epoch": 0.43, + "learning_rate": 2.84203932797924e-05, + "loss": 0.1403, "step": 194010 }, { - "epoch": 0.87, - "learning_rate": 6.740953320478903e-06, - "loss": 0.1456, + "epoch": 0.43, + "learning_rate": 2.8419274736583073e-05, + "loss": 0.1441, "step": 194020 }, { - "epoch": 0.87, - "learning_rate": 6.7387112685529806e-06, - "loss": 0.1378, + "epoch": 0.43, + "learning_rate": 2.841815619337375e-05, + "loss": 0.1415, "step": 194030 }, { - "epoch": 0.87, - "learning_rate": 6.7364692166270576e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.841703765016443e-05, + "loss": 0.1476, "step": 194040 }, { - "epoch": 0.87, - "learning_rate": 6.734227164701135e-06, - "loss": 0.137, + "epoch": 0.43, + "learning_rate": 2.8415919106955103e-05, + "loss": 0.1416, "step": 194050 }, { - "epoch": 0.87, - "learning_rate": 6.731985112775212e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.841480056374578e-05, + "loss": 0.1469, "step": 194060 }, { - "epoch": 0.87, - "learning_rate": 6.729743060849289e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.8413682020536452e-05, + "loss": 0.1463, "step": 194070 }, { - "epoch": 0.87, - "learning_rate": 6.727501008923367e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.841256347732713e-05, + "loss": 0.1462, "step": 194080 }, { - "epoch": 0.87, - "learning_rate": 6.725258956997444e-06, - "loss": 0.1395, + "epoch": 0.43, + "learning_rate": 2.8411444934117808e-05, + "loss": 0.1439, "step": 194090 }, { - "epoch": 0.87, - "learning_rate": 6.723016905071522e-06, - "loss": 0.1407, + "epoch": 0.43, + "learning_rate": 2.8410326390908483e-05, + "loss": 0.1423, "step": 194100 }, { - "epoch": 0.87, - "learning_rate": 6.720774853145599e-06, - "loss": 0.1399, + "epoch": 0.43, + "learning_rate": 2.840920784769916e-05, + "loss": 0.1425, "step": 194110 }, { - "epoch": 0.87, - "learning_rate": 6.718532801219676e-06, - "loss": 0.1439, + "epoch": 0.43, + "learning_rate": 2.840808930448983e-05, + "loss": 0.1435, "step": 194120 }, { - "epoch": 0.87, - "learning_rate": 6.716290749293753e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.840697076128051e-05, + "loss": 0.1452, "step": 194130 }, { - "epoch": 0.87, - "learning_rate": 6.71404869736783e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.8405852218071184e-05, + "loss": 0.138, "step": 194140 }, { - "epoch": 0.87, - "learning_rate": 6.711806645441909e-06, - "loss": 0.1436, + "epoch": 0.43, + "learning_rate": 2.8404733674861862e-05, + "loss": 0.1428, "step": 194150 }, { - "epoch": 0.87, - "learning_rate": 6.709564593515986e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.840361513165254e-05, + "loss": 0.1446, "step": 194160 }, { - "epoch": 0.87, - "learning_rate": 6.707322541590064e-06, - "loss": 0.1361, + "epoch": 0.43, + "learning_rate": 2.840249658844321e-05, + "loss": 0.1461, "step": 194170 }, { - "epoch": 0.87, - "learning_rate": 6.705080489664141e-06, - "loss": 0.1445, + "epoch": 0.43, + "learning_rate": 2.840137804523389e-05, + "loss": 0.1477, "step": 194180 }, { - "epoch": 0.87, - "learning_rate": 6.7030626429308105e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8400259502024564e-05, + "loss": 0.1422, "step": 194190 }, { - "epoch": 0.87, - "learning_rate": 6.7008205910048875e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.839914095881524e-05, + "loss": 0.1446, "step": 194200 }, { - "epoch": 0.87, - "learning_rate": 6.698578539078966e-06, - "loss": 0.1442, + "epoch": 0.43, + "learning_rate": 2.839802241560592e-05, + "loss": 0.144, "step": 194210 }, { - "epoch": 0.87, - "learning_rate": 6.696336487153043e-06, - "loss": 0.1429, + "epoch": 0.43, + "learning_rate": 2.839690387239659e-05, + "loss": 0.1484, "step": 194220 }, { - "epoch": 0.87, - "learning_rate": 6.69409443522712e-06, - "loss": 0.1452, + "epoch": 0.43, + "learning_rate": 2.839578532918727e-05, + "loss": 0.1419, "step": 194230 }, { - "epoch": 0.87, - "learning_rate": 6.691852383301197e-06, - "loss": 0.137, + "epoch": 0.43, + "learning_rate": 2.8394666785977943e-05, + "loss": 0.1412, "step": 194240 }, { - "epoch": 0.87, - "learning_rate": 6.689610331375275e-06, - "loss": 0.145, + "epoch": 0.43, + "learning_rate": 2.839354824276862e-05, + "loss": 0.1392, "step": 194250 }, { - "epoch": 0.87, - "learning_rate": 6.687368279449352e-06, - "loss": 0.1371, + "epoch": 0.43, + "learning_rate": 2.83924296995593e-05, + "loss": 0.1368, "step": 194260 }, { - "epoch": 0.87, - "learning_rate": 6.685126227523429e-06, - "loss": 0.1432, + "epoch": 0.43, + "learning_rate": 2.839131115634997e-05, + "loss": 0.146, "step": 194270 }, { - "epoch": 0.87, - "learning_rate": 6.682884175597508e-06, - "loss": 0.1449, + "epoch": 0.43, + "learning_rate": 2.8390192613140648e-05, + "loss": 0.1418, "step": 194280 }, { - "epoch": 0.87, - "learning_rate": 6.680642123671585e-06, - "loss": 0.1406, + "epoch": 0.43, + "learning_rate": 2.838907406993132e-05, + "loss": 0.147, "step": 194290 }, { - "epoch": 0.87, - "learning_rate": 6.678400071745662e-06, - "loss": 0.1409, + "epoch": 0.43, + "learning_rate": 2.8387955526721997e-05, + "loss": 0.1414, "step": 194300 }, { - "epoch": 0.87, - "learning_rate": 6.676158019819739e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.838683698351268e-05, + "loss": 0.1422, "step": 194310 }, { - "epoch": 0.87, - "learning_rate": 6.673915967893817e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.838571844030335e-05, + "loss": 0.1447, "step": 194320 }, { - "epoch": 0.87, - "learning_rate": 6.671673915967894e-06, - "loss": 0.1384, + "epoch": 0.43, + "learning_rate": 2.8384599897094027e-05, + "loss": 0.1407, "step": 194330 }, { - "epoch": 0.87, - "learning_rate": 6.669431864041971e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.83834813538847e-05, + "loss": 0.1389, "step": 194340 }, { - "epoch": 0.87, - "learning_rate": 6.66718981211605e-06, - "loss": 0.1434, + "epoch": 0.43, + "learning_rate": 2.8382362810675377e-05, + "loss": 0.1465, "step": 194350 }, { - "epoch": 0.87, - "learning_rate": 6.664947760190127e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.8381244267466054e-05, + "loss": 0.1486, "step": 194360 }, { - "epoch": 0.87, - "learning_rate": 6.662705708264204e-06, - "loss": 0.1386, + "epoch": 0.43, + "learning_rate": 2.838012572425673e-05, + "loss": 0.142, "step": 194370 }, { - "epoch": 0.87, - "learning_rate": 6.660463656338281e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.8379007181047407e-05, + "loss": 0.1447, "step": 194380 }, { - "epoch": 0.87, - "learning_rate": 6.658221604412359e-06, - "loss": 0.1391, + "epoch": 0.43, + "learning_rate": 2.8377888637838078e-05, + "loss": 0.137, "step": 194390 }, { - "epoch": 0.87, - "learning_rate": 6.655979552486436e-06, - "loss": 0.139, + "epoch": 0.43, + "learning_rate": 2.8376770094628756e-05, + "loss": 0.1395, "step": 194400 }, { - "epoch": 0.87, - "learning_rate": 6.653737500560513e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.8375651551419434e-05, + "loss": 0.142, "step": 194410 }, { - "epoch": 0.87, - "learning_rate": 6.651495448634591e-06, - "loss": 0.1388, + "epoch": 0.43, + "learning_rate": 2.837453300821011e-05, + "loss": 0.1436, "step": 194420 }, { - "epoch": 0.87, - "learning_rate": 6.649253396708668e-06, - "loss": 0.1414, + "epoch": 0.43, + "learning_rate": 2.8373414465000786e-05, + "loss": 0.1445, "step": 194430 }, { - "epoch": 0.87, - "learning_rate": 6.647011344782745e-06, - "loss": 0.1455, + "epoch": 0.43, + "learning_rate": 2.8372295921791458e-05, + "loss": 0.1473, "step": 194440 }, { - "epoch": 0.87, - "learning_rate": 6.644769292856822e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.8371177378582136e-05, + "loss": 0.1396, "step": 194450 }, { - "epoch": 0.87, - "learning_rate": 6.6425272409309e-06, - "loss": 0.1483, + "epoch": 0.43, + "learning_rate": 2.837005883537281e-05, + "loss": 0.1374, "step": 194460 }, { - "epoch": 0.87, - "learning_rate": 6.640285189004977e-06, - "loss": 0.1426, + "epoch": 0.43, + "learning_rate": 2.8368940292163488e-05, + "loss": 0.1335, "step": 194470 }, { - "epoch": 0.87, - "learning_rate": 6.638043137079054e-06, - "loss": 0.1418, + "epoch": 0.43, + "learning_rate": 2.8367821748954166e-05, + "loss": 0.1426, "step": 194480 }, { - "epoch": 0.87, - "learning_rate": 6.635801085153133e-06, - "loss": 0.1355, + "epoch": 0.43, + "learning_rate": 2.8366703205744837e-05, + "loss": 0.1439, "step": 194490 }, { - "epoch": 0.87, - "learning_rate": 6.63355903322721e-06, - "loss": 0.1398, + "epoch": 0.43, + "learning_rate": 2.8365584662535515e-05, + "loss": 0.1489, "step": 194500 }, { - "epoch": 0.87, - "learning_rate": 6.631316981301287e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.836446611932619e-05, + "loss": 0.1394, "step": 194510 }, { - "epoch": 0.87, - "learning_rate": 6.629074929375365e-06, - "loss": 0.1403, + "epoch": 0.43, + "learning_rate": 2.8363347576116867e-05, + "loss": 0.1444, "step": 194520 }, { - "epoch": 0.87, - "learning_rate": 6.626832877449442e-06, - "loss": 0.1383, + "epoch": 0.43, + "learning_rate": 2.8362229032907545e-05, + "loss": 0.1477, "step": 194530 }, { - "epoch": 0.87, - "learning_rate": 6.624590825523519e-06, - "loss": 0.1392, + "epoch": 0.43, + "learning_rate": 2.8361110489698217e-05, + "loss": 0.1418, "step": 194540 }, { - "epoch": 0.87, - "learning_rate": 6.622348773597596e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.8359991946488894e-05, + "loss": 0.1387, "step": 194550 }, { - "epoch": 0.87, - "learning_rate": 6.620106721671675e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.835887340327957e-05, + "loss": 0.1451, "step": 194560 }, { - "epoch": 0.87, - "learning_rate": 6.617864669745752e-06, - "loss": 0.1401, + "epoch": 0.43, + "learning_rate": 2.8357754860070247e-05, + "loss": 0.1409, "step": 194570 }, { - "epoch": 0.87, - "learning_rate": 6.615622617819829e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.8356636316860925e-05, + "loss": 0.1403, "step": 194580 }, { - "epoch": 0.87, - "learning_rate": 6.613380565893907e-06, - "loss": 0.1382, + "epoch": 0.43, + "learning_rate": 2.8355517773651596e-05, + "loss": 0.1445, "step": 194590 }, { - "epoch": 0.87, - "learning_rate": 6.611138513967984e-06, - "loss": 0.1384, + "epoch": 0.43, + "learning_rate": 2.8354399230442274e-05, + "loss": 0.1461, "step": 194600 }, { - "epoch": 0.87, - "learning_rate": 6.608896462042061e-06, - "loss": 0.1361, + "epoch": 0.43, + "learning_rate": 2.835328068723295e-05, + "loss": 0.1397, "step": 194610 }, { - "epoch": 0.87, - "learning_rate": 6.6066544101161394e-06, - "loss": 0.1397, + "epoch": 0.43, + "learning_rate": 2.8352162144023626e-05, + "loss": 0.1436, "step": 194620 }, { - "epoch": 0.87, - "learning_rate": 6.6044123581902165e-06, - "loss": 0.1435, + "epoch": 0.43, + "learning_rate": 2.8351043600814304e-05, + "loss": 0.1453, "step": 194630 }, { - "epoch": 0.87, - "learning_rate": 6.6021703062642935e-06, - "loss": 0.141, + "epoch": 0.43, + "learning_rate": 2.8349925057604975e-05, + "loss": 0.1514, "step": 194640 }, { - "epoch": 0.87, - "learning_rate": 6.5999282543383705e-06, - "loss": 0.1461, + "epoch": 0.43, + "learning_rate": 2.8348806514395653e-05, + "loss": 0.1401, "step": 194650 }, { - "epoch": 0.87, - "learning_rate": 6.597686202412448e-06, - "loss": 0.1411, + "epoch": 0.43, + "learning_rate": 2.8347687971186328e-05, + "loss": 0.1375, "step": 194660 }, { - "epoch": 0.87, - "learning_rate": 6.595444150486525e-06, - "loss": 0.1443, + "epoch": 0.43, + "learning_rate": 2.8346569427977006e-05, + "loss": 0.1399, "step": 194670 }, { - "epoch": 0.87, - "learning_rate": 6.5932020985606024e-06, - "loss": 0.1432, + "epoch": 0.43, + "learning_rate": 2.8345450884767684e-05, + "loss": 0.144, "step": 194680 }, { - "epoch": 0.87, - "learning_rate": 6.590960046634681e-06, - "loss": 0.1367, + "epoch": 0.43, + "learning_rate": 2.8344332341558355e-05, + "loss": 0.1468, "step": 194690 }, { - "epoch": 0.87, - "learning_rate": 6.588717994708758e-06, - "loss": 0.1408, + "epoch": 0.43, + "learning_rate": 2.8343213798349033e-05, + "loss": 0.144, "step": 194700 }, { - "epoch": 0.87, - "learning_rate": 6.586475942782835e-06, - "loss": 0.1399, + "epoch": 0.43, + "learning_rate": 2.8342095255139704e-05, + "loss": 0.1393, "step": 194710 }, { - "epoch": 0.87, - "learning_rate": 6.584233890856912e-06, - "loss": 0.14, + "epoch": 0.43, + "learning_rate": 2.8340976711930385e-05, + "loss": 0.1389, "step": 194720 }, { - "epoch": 0.87, - "learning_rate": 6.58199183893099e-06, - "loss": 0.1419, + "epoch": 0.43, + "learning_rate": 2.8339858168721063e-05, + "loss": 0.1401, "step": 194730 }, { - "epoch": 0.87, - "learning_rate": 6.579749787005067e-06, - "loss": 0.143, + "epoch": 0.43, + "learning_rate": 2.8338739625511734e-05, + "loss": 0.1416, "step": 194740 }, { - "epoch": 0.87, - "learning_rate": 6.577507735079144e-06, - "loss": 0.1448, + "epoch": 0.43, + "learning_rate": 2.8337621082302412e-05, + "loss": 0.1383, "step": 194750 }, { - "epoch": 0.87, - "learning_rate": 6.575265683153223e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.8336502539093083e-05, + "loss": 0.1445, "step": 194760 }, { - "epoch": 0.87, - "learning_rate": 6.5730236312273e-06, - "loss": 0.1384, + "epoch": 0.43, + "learning_rate": 2.833538399588376e-05, + "loss": 0.1475, "step": 194770 }, { - "epoch": 0.87, - "learning_rate": 6.570781579301377e-06, - "loss": 0.1351, + "epoch": 0.43, + "learning_rate": 2.8334265452674436e-05, + "loss": 0.1409, "step": 194780 }, { - "epoch": 0.87, - "learning_rate": 6.568539527375455e-06, - "loss": 0.1428, + "epoch": 0.43, + "learning_rate": 2.8333146909465114e-05, + "loss": 0.1471, "step": 194790 }, { - "epoch": 0.87, - "learning_rate": 6.566297475449532e-06, - "loss": 0.1351, + "epoch": 0.43, + "learning_rate": 2.8332028366255792e-05, + "loss": 0.1406, "step": 194800 }, { - "epoch": 0.87, - "learning_rate": 6.564055423523609e-06, - "loss": 0.1368, + "epoch": 0.43, + "learning_rate": 2.8330909823046463e-05, + "loss": 0.1413, "step": 194810 }, { - "epoch": 0.87, - "learning_rate": 6.561813371597686e-06, - "loss": 0.1423, + "epoch": 0.43, + "learning_rate": 2.832979127983714e-05, + "loss": 0.1432, "step": 194820 }, { - "epoch": 0.87, - "learning_rate": 6.5595713196717646e-06, - "loss": 0.139, + "epoch": 0.43, + "learning_rate": 2.8328672736627815e-05, + "loss": 0.1418, "step": 194830 }, { - "epoch": 0.87, - "learning_rate": 6.557329267745842e-06, - "loss": 0.1421, + "epoch": 0.43, + "learning_rate": 2.8327554193418493e-05, + "loss": 0.1419, "step": 194840 }, { - "epoch": 0.87, - "learning_rate": 6.555087215819919e-06, - "loss": 0.142, + "epoch": 0.43, + "learning_rate": 2.832643565020917e-05, + "loss": 0.1445, "step": 194850 }, { - "epoch": 0.87, - "learning_rate": 6.5528451638939965e-06, - "loss": 0.1422, + "epoch": 0.43, + "learning_rate": 2.8325317106999842e-05, + "loss": 0.1435, "step": 194860 }, { - "epoch": 0.87, - "learning_rate": 6.5506031119680735e-06, + "epoch": 0.43, + "learning_rate": 2.832419856379052e-05, "loss": 0.1407, "step": 194870 }, { - "epoch": 0.87, - "learning_rate": 6.5483610600421505e-06, - "loss": 0.1378, + "epoch": 0.43, + "learning_rate": 2.8323080020581195e-05, + "loss": 0.1435, "step": 194880 }, { - "epoch": 0.87, - "learning_rate": 6.5461190081162275e-06, - "loss": 0.1353, + "epoch": 0.44, + "learning_rate": 2.8321961477371873e-05, + "loss": 0.1464, "step": 194890 }, { - "epoch": 0.87, - "learning_rate": 6.543876956190306e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.832084293416255e-05, + "loss": 0.1455, "step": 194900 }, { - "epoch": 0.87, - "learning_rate": 6.541634904264383e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.8319724390953222e-05, + "loss": 0.1466, "step": 194910 }, { - "epoch": 0.87, - "learning_rate": 6.53939285233846e-06, - "loss": 0.1425, + "epoch": 0.44, + "learning_rate": 2.83186058477439e-05, + "loss": 0.1402, "step": 194920 }, { - "epoch": 0.87, - "learning_rate": 6.537150800412538e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.8317487304534574e-05, + "loss": 0.1419, "step": 194930 }, { - "epoch": 0.87, - "learning_rate": 6.534908748486615e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.8316368761325252e-05, + "loss": 0.1515, "step": 194940 }, { - "epoch": 0.87, - "learning_rate": 6.532666696560692e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.831525021811593e-05, + "loss": 0.1464, "step": 194950 }, { - "epoch": 0.87, - "learning_rate": 6.530424644634769e-06, - "loss": 0.1437, + "epoch": 0.44, + "learning_rate": 2.83141316749066e-05, + "loss": 0.1411, "step": 194960 }, { - "epoch": 0.87, - "learning_rate": 6.528182592708848e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.831301313169728e-05, + "loss": 0.1388, "step": 194970 }, { - "epoch": 0.87, - "learning_rate": 6.525940540782925e-06, - "loss": 0.1358, + "epoch": 0.44, + "learning_rate": 2.8311894588487954e-05, + "loss": 0.1439, "step": 194980 }, { - "epoch": 0.87, - "learning_rate": 6.523698488857002e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.8310776045278632e-05, + "loss": 0.1401, "step": 194990 }, { - "epoch": 0.87, - "learning_rate": 6.52145643693108e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.830965750206931e-05, + "loss": 0.1403, "step": 195000 }, { - "epoch": 0.87, - "learning_rate": 6.519214385005157e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.830853895885998e-05, + "loss": 0.1423, "step": 195010 }, { - "epoch": 0.87, - "learning_rate": 6.516972333079234e-06, - "loss": 0.137, + "epoch": 0.44, + "learning_rate": 2.830742041565066e-05, + "loss": 0.1427, "step": 195020 }, { - "epoch": 0.87, - "learning_rate": 6.514730281153311e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.8306301872441333e-05, + "loss": 0.1429, "step": 195030 }, { - "epoch": 0.87, - "learning_rate": 6.51248822922739e-06, - "loss": 0.1412, + "epoch": 0.44, + "learning_rate": 2.830518332923201e-05, + "loss": 0.1429, "step": 195040 }, { - "epoch": 0.87, - "learning_rate": 6.510246177301467e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.830406478602269e-05, + "loss": 0.143, "step": 195050 }, { - "epoch": 0.87, - "learning_rate": 6.5080041253755446e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.830294624281336e-05, + "loss": 0.1422, "step": 195060 }, { - "epoch": 0.87, - "learning_rate": 6.505762073449622e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.8301827699604038e-05, + "loss": 0.1415, "step": 195070 }, { - "epoch": 0.87, - "learning_rate": 6.503520021523699e-06, - "loss": 0.1413, + "epoch": 0.44, + "learning_rate": 2.8300709156394713e-05, + "loss": 0.1427, "step": 195080 }, { - "epoch": 0.87, - "learning_rate": 6.501277969597776e-06, - "loss": 0.1421, + "epoch": 0.44, + "learning_rate": 2.829959061318539e-05, + "loss": 0.1425, "step": 195090 }, { - "epoch": 0.87, - "learning_rate": 6.499035917671853e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.8298472069976062e-05, + "loss": 0.1455, "step": 195100 }, { - "epoch": 0.87, - "learning_rate": 6.496793865745931e-06, - "loss": 0.1391, + "epoch": 0.44, + "learning_rate": 2.829735352676674e-05, + "loss": 0.1437, "step": 195110 }, { - "epoch": 0.87, - "learning_rate": 6.494551813820008e-06, - "loss": 0.1458, + "epoch": 0.44, + "learning_rate": 2.8296234983557418e-05, + "loss": 0.1373, "step": 195120 }, { - "epoch": 0.87, - "learning_rate": 6.492309761894086e-06, - "loss": 0.1358, + "epoch": 0.44, + "learning_rate": 2.8295116440348092e-05, + "loss": 0.1418, "step": 195130 }, { - "epoch": 0.87, - "learning_rate": 6.490067709968163e-06, - "loss": 0.1402, + "epoch": 0.44, + "learning_rate": 2.829399789713877e-05, + "loss": 0.1459, "step": 195140 }, { - "epoch": 0.87, - "learning_rate": 6.48782565804224e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.829287935392944e-05, + "loss": 0.1466, "step": 195150 }, { - "epoch": 0.87, - "learning_rate": 6.485583606116317e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.829176081072012e-05, + "loss": 0.1407, "step": 195160 }, { - "epoch": 0.87, - "learning_rate": 6.483341554190394e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.8290754121831725e-05, + "loss": 0.1439, "step": 195170 }, { - "epoch": 0.87, - "learning_rate": 6.481099502264473e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.8289635578622403e-05, + "loss": 0.1399, "step": 195180 }, { - "epoch": 0.87, - "learning_rate": 6.47885745033855e-06, - "loss": 0.1372, + "epoch": 0.44, + "learning_rate": 2.828851703541308e-05, + "loss": 0.1428, "step": 195190 }, { - "epoch": 0.87, - "learning_rate": 6.476615398412628e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.8287398492203755e-05, + "loss": 0.146, "step": 195200 }, { - "epoch": 0.87, - "learning_rate": 6.474373346486705e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.8286279948994433e-05, + "loss": 0.1437, "step": 195210 }, { - "epoch": 0.87, - "learning_rate": 6.472131294560782e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.8285161405785104e-05, + "loss": 0.1431, "step": 195220 }, { - "epoch": 0.87, - "learning_rate": 6.469889242634859e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.8284042862575782e-05, + "loss": 0.1413, "step": 195230 }, { - "epoch": 0.87, - "learning_rate": 6.467647190708938e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.828292431936646e-05, + "loss": 0.1457, "step": 195240 }, { - "epoch": 0.87, - "learning_rate": 6.465405138783015e-06, - "loss": 0.1373, + "epoch": 0.44, + "learning_rate": 2.8281805776157135e-05, + "loss": 0.1463, "step": 195250 }, { - "epoch": 0.87, - "learning_rate": 6.463163086857092e-06, - "loss": 0.1419, + "epoch": 0.44, + "learning_rate": 2.8280687232947812e-05, + "loss": 0.1389, "step": 195260 }, { - "epoch": 0.87, - "learning_rate": 6.46092103493117e-06, - "loss": 0.1428, + "epoch": 0.44, + "learning_rate": 2.8279568689738484e-05, + "loss": 0.1437, "step": 195270 }, { - "epoch": 0.87, - "learning_rate": 6.458678983005247e-06, - "loss": 0.1354, + "epoch": 0.44, + "learning_rate": 2.827845014652916e-05, + "loss": 0.1454, "step": 195280 }, { - "epoch": 0.87, - "learning_rate": 6.456436931079324e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.827733160331984e-05, + "loss": 0.1409, "step": 195290 }, { - "epoch": 0.87, - "learning_rate": 6.454194879153401e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.8276213060110514e-05, + "loss": 0.1411, "step": 195300 }, { - "epoch": 0.87, - "learning_rate": 6.4519528272274795e-06, - "loss": 0.1412, + "epoch": 0.44, + "learning_rate": 2.8275094516901192e-05, + "loss": 0.1446, "step": 195310 }, { - "epoch": 0.87, - "learning_rate": 6.4497107753015565e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.8273975973691863e-05, + "loss": 0.1444, "step": 195320 }, { - "epoch": 0.87, - "learning_rate": 6.447468723375634e-06, - "loss": 0.1397, + "epoch": 0.44, + "learning_rate": 2.827285743048254e-05, + "loss": 0.1416, "step": 195330 }, { - "epoch": 0.87, - "learning_rate": 6.445226671449711e-06, - "loss": 0.1446, + "epoch": 0.44, + "learning_rate": 2.827173888727322e-05, + "loss": 0.1359, "step": 195340 }, { - "epoch": 0.87, - "learning_rate": 6.4429846195237884e-06, - "loss": 0.1403, + "epoch": 0.44, + "learning_rate": 2.827062034406389e-05, + "loss": 0.1425, "step": 195350 }, { - "epoch": 0.87, - "learning_rate": 6.4407425675978654e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.826950180085457e-05, + "loss": 0.1392, "step": 195360 }, { - "epoch": 0.87, - "learning_rate": 6.4385005156719425e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.8268383257645243e-05, + "loss": 0.1476, "step": 195370 }, { - "epoch": 0.87, - "learning_rate": 6.436258463746021e-06, - "loss": 0.1346, + "epoch": 0.44, + "learning_rate": 2.826726471443592e-05, + "loss": 0.1404, "step": 195380 }, { - "epoch": 0.87, - "learning_rate": 6.434016411820098e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.82661461712266e-05, + "loss": 0.1424, "step": 195390 }, { - "epoch": 0.87, - "learning_rate": 6.431774359894176e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.826502762801727e-05, + "loss": 0.1442, "step": 195400 }, { - "epoch": 0.87, - "learning_rate": 6.429532307968253e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.8263909084807948e-05, + "loss": 0.1425, "step": 195410 }, { - "epoch": 0.87, - "learning_rate": 6.42729025604233e-06, - "loss": 0.1364, + "epoch": 0.44, + "learning_rate": 2.8262790541598622e-05, + "loss": 0.1411, "step": 195420 }, { - "epoch": 0.87, - "learning_rate": 6.425048204116407e-06, - "loss": 0.1349, + "epoch": 0.44, + "learning_rate": 2.82616719983893e-05, + "loss": 0.1391, "step": 195430 }, { - "epoch": 0.87, - "learning_rate": 6.422806152190484e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.826055345517997e-05, + "loss": 0.1444, "step": 195440 }, { - "epoch": 0.87, - "learning_rate": 6.420564100264563e-06, - "loss": 0.1361, + "epoch": 0.44, + "learning_rate": 2.825943491197065e-05, + "loss": 0.1397, "step": 195450 }, { - "epoch": 0.87, - "learning_rate": 6.41832204833864e-06, - "loss": 0.1406, + "epoch": 0.44, + "learning_rate": 2.8258316368761327e-05, + "loss": 0.1336, "step": 195460 }, { - "epoch": 0.87, - "learning_rate": 6.416079996412718e-06, - "loss": 0.1413, + "epoch": 0.44, + "learning_rate": 2.8257197825552e-05, + "loss": 0.1402, "step": 195470 }, { - "epoch": 0.87, - "learning_rate": 6.413837944486795e-06, - "loss": 0.1391, + "epoch": 0.44, + "learning_rate": 2.825607928234268e-05, + "loss": 0.1428, "step": 195480 }, { - "epoch": 0.87, - "learning_rate": 6.411595892560872e-06, - "loss": 0.1399, + "epoch": 0.44, + "learning_rate": 2.825496073913335e-05, + "loss": 0.1403, "step": 195490 }, { - "epoch": 0.87, - "learning_rate": 6.409353840634949e-06, - "loss": 0.1334, + "epoch": 0.44, + "learning_rate": 2.825384219592403e-05, + "loss": 0.1385, "step": 195500 }, { - "epoch": 0.87, - "learning_rate": 6.407111788709026e-06, - "loss": 0.1385, + "epoch": 0.44, + "learning_rate": 2.8252723652714706e-05, + "loss": 0.1433, "step": 195510 }, { - "epoch": 0.87, - "learning_rate": 6.404869736783105e-06, - "loss": 0.1426, + "epoch": 0.44, + "learning_rate": 2.825160510950538e-05, + "loss": 0.1396, "step": 195520 }, { - "epoch": 0.87, - "learning_rate": 6.402627684857182e-06, - "loss": 0.1343, + "epoch": 0.44, + "learning_rate": 2.825048656629606e-05, + "loss": 0.1374, "step": 195530 }, { - "epoch": 0.87, - "learning_rate": 6.4003856329312595e-06, + "epoch": 0.44, + "learning_rate": 2.824936802308673e-05, "loss": 0.1409, "step": 195540 }, { - "epoch": 0.87, - "learning_rate": 6.3981435810053365e-06, - "loss": 0.1407, + "epoch": 0.44, + "learning_rate": 2.8248249479877408e-05, + "loss": 0.1465, "step": 195550 }, { - "epoch": 0.87, - "learning_rate": 6.3959015290794135e-06, - "loss": 0.1325, + "epoch": 0.44, + "learning_rate": 2.8247130936668086e-05, + "loss": 0.1451, "step": 195560 }, { - "epoch": 0.87, - "learning_rate": 6.3936594771534906e-06, - "loss": 0.1383, + "epoch": 0.44, + "learning_rate": 2.824601239345876e-05, + "loss": 0.1397, "step": 195570 }, { - "epoch": 0.87, - "learning_rate": 6.391417425227568e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.824489385024944e-05, + "loss": 0.14, "step": 195580 }, { - "epoch": 0.87, - "learning_rate": 6.389175373301646e-06, - "loss": 0.1406, + "epoch": 0.44, + "learning_rate": 2.824377530704011e-05, + "loss": 0.1455, "step": 195590 }, { - "epoch": 0.87, - "learning_rate": 6.386933321375723e-06, - "loss": 0.1382, + "epoch": 0.44, + "learning_rate": 2.8242656763830787e-05, + "loss": 0.1404, "step": 195600 }, { - "epoch": 0.87, - "learning_rate": 6.384691269449801e-06, - "loss": 0.1403, + "epoch": 0.44, + "learning_rate": 2.8241538220621465e-05, + "loss": 0.1449, "step": 195610 }, { - "epoch": 0.87, - "learning_rate": 6.382449217523878e-06, - "loss": 0.1406, + "epoch": 0.44, + "learning_rate": 2.824041967741214e-05, + "loss": 0.1415, "step": 195620 }, { - "epoch": 0.87, - "learning_rate": 6.380207165597955e-06, - "loss": 0.137, + "epoch": 0.44, + "learning_rate": 2.8239301134202818e-05, + "loss": 0.1393, "step": 195630 }, { - "epoch": 0.87, - "learning_rate": 6.377965113672032e-06, - "loss": 0.143, + "epoch": 0.44, + "learning_rate": 2.823818259099349e-05, + "loss": 0.1389, "step": 195640 }, { - "epoch": 0.87, - "learning_rate": 6.37572306174611e-06, - "loss": 0.1385, + "epoch": 0.44, + "learning_rate": 2.8237064047784167e-05, + "loss": 0.1447, "step": 195650 }, { - "epoch": 0.87, - "learning_rate": 6.373481009820188e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.8235945504574845e-05, + "loss": 0.141, "step": 195660 }, { - "epoch": 0.87, - "learning_rate": 6.371238957894266e-06, - "loss": 0.1375, + "epoch": 0.44, + "learning_rate": 2.823482696136552e-05, + "loss": 0.1411, "step": 195670 }, { - "epoch": 0.87, - "learning_rate": 6.368996905968343e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.8233708418156197e-05, + "loss": 0.1421, "step": 195680 }, { - "epoch": 0.87, - "learning_rate": 6.36675485404242e-06, - "loss": 0.1399, + "epoch": 0.44, + "learning_rate": 2.823258987494687e-05, + "loss": 0.1426, "step": 195690 }, { - "epoch": 0.87, - "learning_rate": 6.364512802116497e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.8231471331737546e-05, + "loss": 0.1355, "step": 195700 }, { - "epoch": 0.87, - "learning_rate": 6.362270750190574e-06, - "loss": 0.1451, + "epoch": 0.44, + "learning_rate": 2.8230352788528224e-05, + "loss": 0.1406, "step": 195710 }, { - "epoch": 0.87, - "learning_rate": 6.360028698264652e-06, - "loss": 0.1427, + "epoch": 0.44, + "learning_rate": 2.82292342453189e-05, + "loss": 0.1456, "step": 195720 }, { - "epoch": 0.87, - "learning_rate": 6.35778664633873e-06, - "loss": 0.1351, + "epoch": 0.44, + "learning_rate": 2.8228115702109577e-05, + "loss": 0.1426, "step": 195730 }, { - "epoch": 0.87, - "learning_rate": 6.355544594412808e-06, - "loss": 0.1402, + "epoch": 0.44, + "learning_rate": 2.8226997158900248e-05, + "loss": 0.1461, "step": 195740 }, { - "epoch": 0.87, - "learning_rate": 6.353302542486885e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.8225878615690926e-05, + "loss": 0.1405, "step": 195750 }, { - "epoch": 0.87, - "learning_rate": 6.351060490560962e-06, - "loss": 0.1448, + "epoch": 0.44, + "learning_rate": 2.8224760072481597e-05, + "loss": 0.14, "step": 195760 }, { - "epoch": 0.87, - "learning_rate": 6.348818438635039e-06, - "loss": 0.1467, + "epoch": 0.44, + "learning_rate": 2.8223641529272275e-05, + "loss": 0.1502, "step": 195770 }, { - "epoch": 0.87, - "learning_rate": 6.346576386709116e-06, - "loss": 0.1447, + "epoch": 0.44, + "learning_rate": 2.8222522986062956e-05, + "loss": 0.1391, "step": 195780 }, { - "epoch": 0.87, - "learning_rate": 6.3443343347831936e-06, - "loss": 0.1457, + "epoch": 0.44, + "learning_rate": 2.8221404442853627e-05, + "loss": 0.1453, "step": 195790 }, { - "epoch": 0.87, - "learning_rate": 6.3420922828572714e-06, - "loss": 0.1432, + "epoch": 0.44, + "learning_rate": 2.8220285899644305e-05, + "loss": 0.1457, "step": 195800 }, { - "epoch": 0.87, - "learning_rate": 6.339850230931349e-06, - "loss": 0.135, + "epoch": 0.44, + "learning_rate": 2.8219167356434977e-05, + "loss": 0.1436, "step": 195810 }, { - "epoch": 0.87, - "learning_rate": 6.337608179005426e-06, - "loss": 0.1409, + "epoch": 0.44, + "learning_rate": 2.8218048813225654e-05, + "loss": 0.1388, "step": 195820 }, { - "epoch": 0.87, - "learning_rate": 6.335366127079503e-06, - "loss": 0.1407, + "epoch": 0.44, + "learning_rate": 2.8216930270016332e-05, + "loss": 0.1417, "step": 195830 }, { - "epoch": 0.87, - "learning_rate": 6.33312407515358e-06, - "loss": 0.1434, + "epoch": 0.44, + "learning_rate": 2.8215811726807007e-05, + "loss": 0.1455, "step": 195840 }, { - "epoch": 0.87, - "learning_rate": 6.330882023227657e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.8214693183597685e-05, + "loss": 0.1442, "step": 195850 }, { - "epoch": 0.87, - "learning_rate": 6.328639971301735e-06, - "loss": 0.1358, + "epoch": 0.44, + "learning_rate": 2.8213574640388356e-05, + "loss": 0.1494, "step": 195860 }, { - "epoch": 0.87, - "learning_rate": 6.326397919375813e-06, - "loss": 0.1372, + "epoch": 0.44, + "learning_rate": 2.8212456097179034e-05, + "loss": 0.1433, "step": 195870 }, { - "epoch": 0.87, - "learning_rate": 6.324155867449891e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.8211337553969712e-05, + "loss": 0.1456, "step": 195880 }, { - "epoch": 0.87, - "learning_rate": 6.321913815523968e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.8210219010760386e-05, + "loss": 0.1469, "step": 195890 }, { - "epoch": 0.87, - "learning_rate": 6.319671763598045e-06, - "loss": 0.1422, + "epoch": 0.44, + "learning_rate": 2.8209100467551064e-05, + "loss": 0.1443, "step": 195900 }, { - "epoch": 0.87, - "learning_rate": 6.317429711672122e-06, - "loss": 0.1427, + "epoch": 0.44, + "learning_rate": 2.8207981924341735e-05, + "loss": 0.1481, "step": 195910 }, { - "epoch": 0.87, - "learning_rate": 6.315187659746199e-06, - "loss": 0.1423, + "epoch": 0.44, + "learning_rate": 2.8206863381132413e-05, + "loss": 0.1436, "step": 195920 }, { - "epoch": 0.87, - "learning_rate": 6.312945607820278e-06, - "loss": 0.1428, + "epoch": 0.44, + "learning_rate": 2.820574483792309e-05, + "loss": 0.1416, "step": 195930 }, { - "epoch": 0.87, - "learning_rate": 6.310703555894356e-06, - "loss": 0.1365, + "epoch": 0.44, + "learning_rate": 2.8204626294713766e-05, + "loss": 0.1431, "step": 195940 }, { - "epoch": 0.87, - "learning_rate": 6.308461503968433e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.8203507751504444e-05, + "loss": 0.1434, "step": 195950 }, { - "epoch": 0.87, - "learning_rate": 6.30621945204251e-06, - "loss": 0.1445, + "epoch": 0.44, + "learning_rate": 2.8202389208295115e-05, + "loss": 0.1394, "step": 195960 }, { - "epoch": 0.87, - "learning_rate": 6.303977400116587e-06, - "loss": 0.1421, + "epoch": 0.44, + "learning_rate": 2.8201270665085793e-05, + "loss": 0.1428, "step": 195970 }, { - "epoch": 0.87, - "learning_rate": 6.301735348190664e-06, - "loss": 0.1393, + "epoch": 0.44, + "learning_rate": 2.820015212187647e-05, + "loss": 0.1462, "step": 195980 }, { - "epoch": 0.87, - "learning_rate": 6.299493296264742e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.8199033578667145e-05, + "loss": 0.1455, "step": 195990 }, { - "epoch": 0.87, - "learning_rate": 6.2972512443388195e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.8197915035457823e-05, + "loss": 0.1432, "step": 196000 }, { - "epoch": 0.88, - "learning_rate": 6.295009192412897e-06, - "loss": 0.1354, + "epoch": 0.44, + "learning_rate": 2.8196796492248494e-05, + "loss": 0.143, "step": 196010 }, { - "epoch": 0.88, - "learning_rate": 6.2927671404869744e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.8195677949039172e-05, + "loss": 0.1478, "step": 196020 }, { - "epoch": 0.88, - "learning_rate": 6.2905250885610514e-06, - "loss": 0.1409, + "epoch": 0.44, + "learning_rate": 2.819455940582985e-05, + "loss": 0.1411, "step": 196030 }, { - "epoch": 0.88, - "learning_rate": 6.2882830366351285e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.8193440862620525e-05, + "loss": 0.1388, "step": 196040 }, { - "epoch": 0.88, - "learning_rate": 6.2860409847092055e-06, - "loss": 0.1333, + "epoch": 0.44, + "learning_rate": 2.8192322319411203e-05, + "loss": 0.1366, "step": 196050 }, { - "epoch": 0.88, - "learning_rate": 6.283798932783283e-06, - "loss": 0.1374, + "epoch": 0.44, + "learning_rate": 2.8191203776201874e-05, + "loss": 0.1442, "step": 196060 }, { - "epoch": 0.88, - "learning_rate": 6.281556880857361e-06, - "loss": 0.137, + "epoch": 0.44, + "learning_rate": 2.8190085232992552e-05, + "loss": 0.1394, "step": 196070 }, { - "epoch": 0.88, - "learning_rate": 6.279314828931439e-06, - "loss": 0.149, + "epoch": 0.44, + "learning_rate": 2.8188966689783226e-05, + "loss": 0.1405, "step": 196080 }, { - "epoch": 0.88, - "learning_rate": 6.277072777005516e-06, - "loss": 0.1391, + "epoch": 0.44, + "learning_rate": 2.8187848146573904e-05, + "loss": 0.1402, "step": 196090 }, { - "epoch": 0.88, - "learning_rate": 6.274830725079593e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.8186729603364582e-05, + "loss": 0.1396, "step": 196100 }, { - "epoch": 0.88, - "learning_rate": 6.27258867315367e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.8185611060155253e-05, + "loss": 0.1448, "step": 196110 }, { - "epoch": 0.88, - "learning_rate": 6.270346621227747e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.818449251694593e-05, + "loss": 0.1444, "step": 196120 }, { - "epoch": 0.88, - "learning_rate": 6.268104569301825e-06, - "loss": 0.1362, + "epoch": 0.44, + "learning_rate": 2.8183373973736606e-05, + "loss": 0.1395, "step": 196130 }, { - "epoch": 0.88, - "learning_rate": 6.265862517375903e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.8182255430527284e-05, + "loss": 0.1418, "step": 196140 }, { - "epoch": 0.88, - "learning_rate": 6.263620465449981e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.8181136887317962e-05, + "loss": 0.1416, "step": 196150 }, { - "epoch": 0.88, - "learning_rate": 6.261378413524058e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.8180018344108633e-05, + "loss": 0.1416, "step": 196160 }, { - "epoch": 0.88, - "learning_rate": 6.259136361598135e-06, - "loss": 0.1369, + "epoch": 0.44, + "learning_rate": 2.817889980089931e-05, + "loss": 0.1419, "step": 196170 }, { - "epoch": 0.88, - "learning_rate": 6.256894309672212e-06, - "loss": 0.1385, + "epoch": 0.44, + "learning_rate": 2.8177781257689982e-05, + "loss": 0.1389, "step": 196180 }, { - "epoch": 0.88, - "learning_rate": 6.254876462938881e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.8176662714480663e-05, + "loss": 0.1416, "step": 196190 }, { - "epoch": 0.88, - "learning_rate": 6.25263441101296e-06, - "loss": 0.14, + "epoch": 0.44, + "learning_rate": 2.817554417127134e-05, + "loss": 0.1414, "step": 196200 }, { - "epoch": 0.88, - "learning_rate": 6.250392359087037e-06, - "loss": 0.1386, + "epoch": 0.44, + "learning_rate": 2.8174425628062012e-05, + "loss": 0.1446, "step": 196210 }, { - "epoch": 0.88, - "learning_rate": 6.248150307161114e-06, - "loss": 0.143, + "epoch": 0.44, + "learning_rate": 2.817330708485269e-05, + "loss": 0.1433, "step": 196220 }, { - "epoch": 0.88, - "learning_rate": 6.245908255235192e-06, - "loss": 0.1411, + "epoch": 0.44, + "learning_rate": 2.817218854164336e-05, + "loss": 0.1403, "step": 196230 }, { - "epoch": 0.88, - "learning_rate": 6.243666203309269e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.817106999843404e-05, + "loss": 0.1411, "step": 196240 }, { - "epoch": 0.88, - "learning_rate": 6.241424151383346e-06, - "loss": 0.136, + "epoch": 0.44, + "learning_rate": 2.816995145522472e-05, + "loss": 0.1438, "step": 196250 }, { - "epoch": 0.88, - "learning_rate": 6.239182099457424e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.8168832912015392e-05, + "loss": 0.1421, "step": 196260 }, { - "epoch": 0.88, - "learning_rate": 6.236940047531501e-06, - "loss": 0.1368, + "epoch": 0.44, + "learning_rate": 2.816771436880607e-05, + "loss": 0.1438, "step": 196270 }, { - "epoch": 0.88, - "learning_rate": 6.234697995605578e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.816659582559674e-05, + "loss": 0.1426, "step": 196280 }, { - "epoch": 0.88, - "learning_rate": 6.232455943679656e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.816547728238742e-05, + "loss": 0.1485, "step": 196290 }, { - "epoch": 0.88, - "learning_rate": 6.230213891753734e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.8164358739178097e-05, + "loss": 0.1409, "step": 196300 }, { - "epoch": 0.88, - "learning_rate": 6.227971839827811e-06, - "loss": 0.1397, + "epoch": 0.44, + "learning_rate": 2.816324019596877e-05, + "loss": 0.141, "step": 196310 }, { - "epoch": 0.88, - "learning_rate": 6.225729787901888e-06, - "loss": 0.1383, + "epoch": 0.44, + "learning_rate": 2.816212165275945e-05, + "loss": 0.152, "step": 196320 }, { - "epoch": 0.88, - "learning_rate": 6.223487735975966e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.816100310955012e-05, + "loss": 0.1464, "step": 196330 }, { - "epoch": 0.88, - "learning_rate": 6.221245684050043e-06, - "loss": 0.1383, + "epoch": 0.44, + "learning_rate": 2.8159884566340798e-05, + "loss": 0.1387, "step": 196340 }, { - "epoch": 0.88, - "learning_rate": 6.21900363212412e-06, - "loss": 0.1331, + "epoch": 0.44, + "learning_rate": 2.8158766023131476e-05, + "loss": 0.1424, "step": 196350 }, { - "epoch": 0.88, - "learning_rate": 6.2167615801981976e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.815764747992215e-05, + "loss": 0.1389, "step": 196360 }, { - "epoch": 0.88, - "learning_rate": 6.2145195282722754e-06, - "loss": 0.1348, + "epoch": 0.44, + "learning_rate": 2.815652893671283e-05, + "loss": 0.1434, "step": 196370 }, { - "epoch": 0.88, - "learning_rate": 6.2122774763463524e-06, - "loss": 0.1429, + "epoch": 0.44, + "learning_rate": 2.81554103935035e-05, + "loss": 0.1418, "step": 196380 }, { - "epoch": 0.88, - "learning_rate": 6.21003542442043e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.8154291850294178e-05, + "loss": 0.1476, "step": 196390 }, { - "epoch": 0.88, - "learning_rate": 6.207793372494507e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.8153173307084852e-05, + "loss": 0.1441, "step": 196400 }, { - "epoch": 0.88, - "learning_rate": 6.205551320568584e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.815205476387553e-05, + "loss": 0.1423, "step": 196410 }, { - "epoch": 0.88, - "learning_rate": 6.203309268642661e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.8150936220666208e-05, + "loss": 0.1387, "step": 196420 }, { - "epoch": 0.88, - "learning_rate": 6.201067216716739e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.814981767745688e-05, + "loss": 0.1454, "step": 196430 }, { - "epoch": 0.88, - "learning_rate": 6.198825164790817e-06, - "loss": 0.1362, + "epoch": 0.44, + "learning_rate": 2.8148699134247557e-05, + "loss": 0.1378, "step": 196440 }, { - "epoch": 0.88, - "learning_rate": 6.196583112864894e-06, - "loss": 0.1329, + "epoch": 0.44, + "learning_rate": 2.8147580591038232e-05, + "loss": 0.1425, "step": 196450 }, { - "epoch": 0.88, - "learning_rate": 6.194341060938972e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.814646204782891e-05, + "loss": 0.1431, "step": 196460 }, { - "epoch": 0.88, - "learning_rate": 6.192099009013049e-06, - "loss": 0.136, + "epoch": 0.44, + "learning_rate": 2.8145343504619588e-05, + "loss": 0.1436, "step": 196470 }, { - "epoch": 0.88, - "learning_rate": 6.189856957087126e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.814422496141026e-05, + "loss": 0.1379, "step": 196480 }, { - "epoch": 0.88, - "learning_rate": 6.187614905161204e-06, - "loss": 0.1407, + "epoch": 0.44, + "learning_rate": 2.8143106418200937e-05, + "loss": 0.147, "step": 196490 }, { - "epoch": 0.88, - "learning_rate": 6.185372853235282e-06, - "loss": 0.141, + "epoch": 0.44, + "learning_rate": 2.814198787499161e-05, + "loss": 0.1444, "step": 196500 }, { - "epoch": 0.88, - "learning_rate": 6.183130801309359e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.814086933178229e-05, + "loss": 0.1395, "step": 196510 }, { - "epoch": 0.88, - "learning_rate": 6.180888749383436e-06, - "loss": 0.1348, + "epoch": 0.44, + "learning_rate": 2.8139750788572967e-05, + "loss": 0.1413, "step": 196520 }, { - "epoch": 0.88, - "learning_rate": 6.178646697457514e-06, - "loss": 0.1364, + "epoch": 0.44, + "learning_rate": 2.8138632245363638e-05, + "loss": 0.142, "step": 196530 }, { - "epoch": 0.88, - "learning_rate": 6.176404645531591e-06, - "loss": 0.1425, + "epoch": 0.44, + "learning_rate": 2.8137513702154316e-05, + "loss": 0.144, "step": 196540 }, { - "epoch": 0.88, - "learning_rate": 6.174162593605668e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.813639515894499e-05, + "loss": 0.1402, "step": 196550 }, { - "epoch": 0.88, - "learning_rate": 6.171920541679746e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.813527661573567e-05, + "loss": 0.1436, "step": 196560 }, { - "epoch": 0.88, - "learning_rate": 6.1696784897538235e-06, - "loss": 0.1365, + "epoch": 0.44, + "learning_rate": 2.8134158072526347e-05, + "loss": 0.1465, "step": 196570 }, { - "epoch": 0.88, - "learning_rate": 6.1674364378279005e-06, - "loss": 0.1357, + "epoch": 0.44, + "learning_rate": 2.8133039529317018e-05, + "loss": 0.1441, "step": 196580 }, { - "epoch": 0.88, - "learning_rate": 6.1651943859019776e-06, - "loss": 0.1373, + "epoch": 0.44, + "learning_rate": 2.8131920986107696e-05, + "loss": 0.139, "step": 196590 }, { - "epoch": 0.88, - "learning_rate": 6.1629523339760554e-06, - "loss": 0.1352, + "epoch": 0.44, + "learning_rate": 2.813080244289837e-05, + "loss": 0.1461, "step": 196600 }, { - "epoch": 0.88, - "learning_rate": 6.1607102820501325e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.8129683899689048e-05, + "loss": 0.143, "step": 196610 }, { - "epoch": 0.88, - "learning_rate": 6.1584682301242095e-06, - "loss": 0.1355, + "epoch": 0.44, + "learning_rate": 2.8128565356479726e-05, + "loss": 0.1441, "step": 196620 }, { - "epoch": 0.88, - "learning_rate": 6.156226178198287e-06, - "loss": 0.1362, + "epoch": 0.44, + "learning_rate": 2.8127446813270397e-05, + "loss": 0.1433, "step": 196630 }, { - "epoch": 0.88, - "learning_rate": 6.153984126272365e-06, - "loss": 0.1307, + "epoch": 0.44, + "learning_rate": 2.8126328270061075e-05, + "loss": 0.1399, "step": 196640 }, { - "epoch": 0.88, - "learning_rate": 6.151742074346442e-06, - "loss": 0.1403, + "epoch": 0.44, + "learning_rate": 2.8125209726851746e-05, + "loss": 0.1396, "step": 196650 }, { - "epoch": 0.88, - "learning_rate": 6.149500022420519e-06, - "loss": 0.136, + "epoch": 0.44, + "learning_rate": 2.8124091183642428e-05, + "loss": 0.1423, "step": 196660 }, { - "epoch": 0.88, - "learning_rate": 6.147257970494597e-06, - "loss": 0.1338, + "epoch": 0.44, + "learning_rate": 2.8122972640433106e-05, + "loss": 0.1502, "step": 196670 }, { - "epoch": 0.88, - "learning_rate": 6.145015918568674e-06, - "loss": 0.1359, + "epoch": 0.44, + "learning_rate": 2.8121854097223777e-05, + "loss": 0.1412, "step": 196680 }, { - "epoch": 0.88, - "learning_rate": 6.142773866642751e-06, - "loss": 0.1368, + "epoch": 0.44, + "learning_rate": 2.8120735554014455e-05, + "loss": 0.1413, "step": 196690 }, { - "epoch": 0.88, - "learning_rate": 6.140531814716829e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.8119617010805126e-05, + "loss": 0.1448, "step": 196700 }, { - "epoch": 0.88, - "learning_rate": 6.138289762790907e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.8118498467595804e-05, + "loss": 0.142, "step": 196710 }, { - "epoch": 0.88, - "learning_rate": 6.136047710864984e-06, - "loss": 0.1341, + "epoch": 0.44, + "learning_rate": 2.8117379924386478e-05, + "loss": 0.1387, "step": 196720 }, { - "epoch": 0.88, - "learning_rate": 6.133805658939061e-06, - "loss": 0.1303, + "epoch": 0.44, + "learning_rate": 2.8116261381177156e-05, + "loss": 0.1447, "step": 196730 }, { - "epoch": 0.88, - "learning_rate": 6.131563607013139e-06, - "loss": 0.1321, + "epoch": 0.44, + "learning_rate": 2.8115142837967834e-05, + "loss": 0.1428, "step": 196740 }, { - "epoch": 0.88, - "learning_rate": 6.129321555087216e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.8114024294758505e-05, + "loss": 0.1448, "step": 196750 }, { - "epoch": 0.88, - "learning_rate": 6.127079503161294e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.8112905751549183e-05, + "loss": 0.1399, "step": 196760 }, { - "epoch": 0.88, - "learning_rate": 6.124837451235372e-06, - "loss": 0.1369, + "epoch": 0.44, + "learning_rate": 2.8111787208339858e-05, + "loss": 0.1377, "step": 196770 }, { - "epoch": 0.88, - "learning_rate": 6.122595399309449e-06, - "loss": 0.1378, + "epoch": 0.44, + "learning_rate": 2.8110668665130536e-05, + "loss": 0.1451, "step": 196780 }, { - "epoch": 0.88, - "learning_rate": 6.120353347383526e-06, - "loss": 0.1403, + "epoch": 0.44, + "learning_rate": 2.8109550121921214e-05, + "loss": 0.1427, "step": 196790 }, { - "epoch": 0.88, - "learning_rate": 6.118111295457603e-06, - "loss": 0.1341, + "epoch": 0.44, + "learning_rate": 2.8108431578711885e-05, + "loss": 0.1394, "step": 196800 }, { - "epoch": 0.88, - "learning_rate": 6.1158692435316806e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.8107313035502563e-05, + "loss": 0.1414, "step": 196810 }, { - "epoch": 0.88, - "learning_rate": 6.113627191605758e-06, - "loss": 0.1401, + "epoch": 0.44, + "learning_rate": 2.8106194492293237e-05, + "loss": 0.1417, "step": 196820 }, { - "epoch": 0.88, - "learning_rate": 6.1113851396798355e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.8105075949083915e-05, + "loss": 0.1438, "step": 196830 }, { - "epoch": 0.88, - "learning_rate": 6.109143087753913e-06, - "loss": 0.1316, + "epoch": 0.44, + "learning_rate": 2.8103957405874593e-05, + "loss": 0.1411, "step": 196840 }, { - "epoch": 0.88, - "learning_rate": 6.10690103582799e-06, - "loss": 0.1326, + "epoch": 0.44, + "learning_rate": 2.8102838862665264e-05, + "loss": 0.1418, "step": 196850 }, { - "epoch": 0.88, - "learning_rate": 6.104658983902067e-06, - "loss": 0.1384, + "epoch": 0.44, + "learning_rate": 2.8101720319455942e-05, + "loss": 0.1487, "step": 196860 }, { - "epoch": 0.88, - "learning_rate": 6.102416931976144e-06, - "loss": 0.1318, + "epoch": 0.44, + "learning_rate": 2.8100601776246617e-05, + "loss": 0.1384, "step": 196870 }, { - "epoch": 0.88, - "learning_rate": 6.100174880050222e-06, - "loss": 0.1417, + "epoch": 0.44, + "learning_rate": 2.8099483233037295e-05, + "loss": 0.1437, "step": 196880 }, { - "epoch": 0.88, - "learning_rate": 6.097932828124299e-06, - "loss": 0.1345, + "epoch": 0.44, + "learning_rate": 2.8098364689827972e-05, + "loss": 0.145, "step": 196890 }, { - "epoch": 0.88, - "learning_rate": 6.095690776198377e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.8097246146618644e-05, + "loss": 0.1408, "step": 196900 }, { - "epoch": 0.88, - "learning_rate": 6.093448724272455e-06, - "loss": 0.1334, + "epoch": 0.44, + "learning_rate": 2.809612760340932e-05, + "loss": 0.1417, "step": 196910 }, { - "epoch": 0.88, - "learning_rate": 6.091206672346532e-06, - "loss": 0.1391, + "epoch": 0.44, + "learning_rate": 2.8095009060199996e-05, + "loss": 0.1414, "step": 196920 }, { - "epoch": 0.88, - "learning_rate": 6.088964620420609e-06, + "epoch": 0.44, + "learning_rate": 2.8093890516990674e-05, "loss": 0.1342, "step": 196930 }, { - "epoch": 0.88, - "learning_rate": 6.086722568494686e-06, - "loss": 0.137, + "epoch": 0.44, + "learning_rate": 2.8092771973781352e-05, + "loss": 0.1365, "step": 196940 }, { - "epoch": 0.88, - "learning_rate": 6.084480516568764e-06, - "loss": 0.1359, + "epoch": 0.44, + "learning_rate": 2.8091653430572023e-05, + "loss": 0.1422, "step": 196950 }, { - "epoch": 0.88, - "learning_rate": 6.082238464642841e-06, - "loss": 0.135, + "epoch": 0.44, + "learning_rate": 2.80905348873627e-05, + "loss": 0.1447, "step": 196960 }, { - "epoch": 0.88, - "learning_rate": 6.079996412716919e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.8089416344153376e-05, + "loss": 0.1409, "step": 196970 }, { - "epoch": 0.88, - "learning_rate": 6.077754360790997e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.8088297800944054e-05, + "loss": 0.1435, "step": 196980 }, { - "epoch": 0.88, - "learning_rate": 6.075512308865074e-06, - "loss": 0.1373, + "epoch": 0.44, + "learning_rate": 2.808717925773473e-05, + "loss": 0.1442, "step": 196990 }, { - "epoch": 0.88, - "learning_rate": 6.073270256939151e-06, - "loss": 0.1352, + "epoch": 0.44, + "learning_rate": 2.8086060714525403e-05, + "loss": 0.1434, "step": 197000 }, { - "epoch": 0.88, - "learning_rate": 6.071028205013228e-06, - "loss": 0.1369, + "epoch": 0.44, + "learning_rate": 2.808494217131608e-05, + "loss": 0.1424, "step": 197010 }, { - "epoch": 0.88, - "learning_rate": 6.068786153087306e-06, - "loss": 0.1329, + "epoch": 0.44, + "learning_rate": 2.8083823628106755e-05, + "loss": 0.1447, "step": 197020 }, { - "epoch": 0.88, - "learning_rate": 6.0665441011613836e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.8082705084897433e-05, + "loss": 0.1401, "step": 197030 }, { - "epoch": 0.88, - "learning_rate": 6.0643020492354606e-06, - "loss": 0.1328, + "epoch": 0.44, + "learning_rate": 2.8081586541688104e-05, + "loss": 0.1466, "step": 197040 }, { - "epoch": 0.88, - "learning_rate": 6.0620599973095384e-06, - "loss": 0.1318, + "epoch": 0.44, + "learning_rate": 2.8080467998478782e-05, + "loss": 0.148, "step": 197050 }, { - "epoch": 0.88, - "learning_rate": 6.0598179453836155e-06, - "loss": 0.1364, + "epoch": 0.44, + "learning_rate": 2.807934945526946e-05, + "loss": 0.1433, "step": 197060 }, { - "epoch": 0.88, - "learning_rate": 6.0575758934576925e-06, - "loss": 0.1345, + "epoch": 0.44, + "learning_rate": 2.807823091206013e-05, + "loss": 0.1423, "step": 197070 }, { - "epoch": 0.88, - "learning_rate": 6.05533384153177e-06, - "loss": 0.1347, + "epoch": 0.44, + "learning_rate": 2.8077112368850812e-05, + "loss": 0.1468, "step": 197080 }, { - "epoch": 0.88, - "learning_rate": 6.053091789605847e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.8075993825641484e-05, + "loss": 0.1464, "step": 197090 }, { - "epoch": 0.88, - "learning_rate": 6.050849737679925e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.807487528243216e-05, + "loss": 0.1436, "step": 197100 }, { - "epoch": 0.88, - "learning_rate": 6.048607685754002e-06, - "loss": 0.1349, + "epoch": 0.44, + "learning_rate": 2.807375673922284e-05, + "loss": 0.1407, "step": 197110 }, { - "epoch": 0.88, - "learning_rate": 6.04636563382808e-06, - "loss": 0.1316, + "epoch": 0.44, + "learning_rate": 2.807263819601351e-05, + "loss": 0.1416, "step": 197120 }, { - "epoch": 0.88, - "learning_rate": 6.044123581902157e-06, - "loss": 0.1366, + "epoch": 0.44, + "learning_rate": 2.807151965280419e-05, + "loss": 0.14, "step": 197130 }, { - "epoch": 0.88, - "learning_rate": 6.041881529976234e-06, - "loss": 0.1355, + "epoch": 0.44, + "learning_rate": 2.8070401109594863e-05, + "loss": 0.139, "step": 197140 }, { - "epoch": 0.88, - "learning_rate": 6.039639478050312e-06, - "loss": 0.1305, + "epoch": 0.44, + "learning_rate": 2.806928256638554e-05, + "loss": 0.1431, "step": 197150 }, { - "epoch": 0.88, - "learning_rate": 6.037397426124389e-06, - "loss": 0.1338, + "epoch": 0.44, + "learning_rate": 2.806816402317622e-05, + "loss": 0.1451, "step": 197160 }, { - "epoch": 0.88, - "learning_rate": 6.035155374198467e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.806704547996689e-05, + "loss": 0.1393, "step": 197170 }, { - "epoch": 0.88, - "learning_rate": 6.032913322272544e-06, - "loss": 0.1306, + "epoch": 0.44, + "learning_rate": 2.8065926936757568e-05, + "loss": 0.141, "step": 197180 }, { - "epoch": 0.88, - "learning_rate": 6.030671270346622e-06, - "loss": 0.1382, + "epoch": 0.44, + "learning_rate": 2.8064808393548243e-05, + "loss": 0.1445, "step": 197190 }, { - "epoch": 0.88, - "learning_rate": 6.028429218420699e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.806368985033892e-05, + "loss": 0.1411, "step": 197200 }, { - "epoch": 0.88, - "learning_rate": 6.026187166494776e-06, - "loss": 0.1345, + "epoch": 0.44, + "learning_rate": 2.80625713071296e-05, + "loss": 0.143, "step": 197210 }, { - "epoch": 0.88, - "learning_rate": 6.023945114568854e-06, - "loss": 0.132, + "epoch": 0.44, + "learning_rate": 2.806145276392027e-05, + "loss": 0.139, "step": 197220 }, { - "epoch": 0.88, - "learning_rate": 6.021703062642931e-06, - "loss": 0.1385, + "epoch": 0.44, + "learning_rate": 2.8060334220710947e-05, + "loss": 0.1424, "step": 197230 }, { - "epoch": 0.88, - "learning_rate": 6.019461010717009e-06, - "loss": 0.1296, + "epoch": 0.44, + "learning_rate": 2.8059215677501622e-05, + "loss": 0.1364, "step": 197240 }, { - "epoch": 0.88, - "learning_rate": 6.017218958791086e-06, - "loss": 0.1333, + "epoch": 0.44, + "learning_rate": 2.80580971342923e-05, + "loss": 0.1383, "step": 197250 }, { - "epoch": 0.88, - "learning_rate": 6.0149769068651636e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.8056978591082978e-05, + "loss": 0.1435, "step": 197260 }, { - "epoch": 0.88, - "learning_rate": 6.012734854939241e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.805586004787365e-05, + "loss": 0.1418, "step": 197270 }, { - "epoch": 0.88, - "learning_rate": 6.010492803013318e-06, - "loss": 0.1308, + "epoch": 0.44, + "learning_rate": 2.8054741504664327e-05, + "loss": 0.1422, "step": 197280 }, { - "epoch": 0.88, - "learning_rate": 6.0082507510873955e-06, - "loss": 0.1355, + "epoch": 0.44, + "learning_rate": 2.8053622961455e-05, + "loss": 0.1413, "step": 197290 }, { - "epoch": 0.88, - "learning_rate": 6.006008699161473e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.805250441824568e-05, + "loss": 0.144, "step": 197300 }, { - "epoch": 0.88, - "learning_rate": 6.00376664723555e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.8051385875036357e-05, + "loss": 0.1434, "step": 197310 }, { - "epoch": 0.88, - "learning_rate": 6.001524595309627e-06, - "loss": 0.1378, + "epoch": 0.44, + "learning_rate": 2.805026733182703e-05, + "loss": 0.1399, "step": 197320 }, { - "epoch": 0.88, - "learning_rate": 5.999282543383705e-06, - "loss": 0.1383, + "epoch": 0.44, + "learning_rate": 2.8049148788617706e-05, + "loss": 0.1386, "step": 197330 }, { - "epoch": 0.88, - "learning_rate": 5.997040491457782e-06, - "loss": 0.1387, + "epoch": 0.44, + "learning_rate": 2.804803024540838e-05, + "loss": 0.1383, "step": 197340 }, { - "epoch": 0.88, - "learning_rate": 5.994798439531859e-06, - "loss": 0.1319, + "epoch": 0.44, + "learning_rate": 2.804691170219906e-05, + "loss": 0.1437, "step": 197350 }, { - "epoch": 0.88, - "learning_rate": 5.992556387605937e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.804579315898973e-05, + "loss": 0.1402, "step": 197360 }, { - "epoch": 0.88, - "learning_rate": 5.990314335680015e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.8044674615780408e-05, + "loss": 0.1405, "step": 197370 }, { - "epoch": 0.88, - "learning_rate": 5.988072283754092e-06, - "loss": 0.139, + "epoch": 0.44, + "learning_rate": 2.8043556072571086e-05, + "loss": 0.1403, "step": 197380 }, { - "epoch": 0.88, - "learning_rate": 5.98583023182817e-06, - "loss": 0.1376, + "epoch": 0.44, + "learning_rate": 2.804243752936176e-05, + "loss": 0.1412, "step": 197390 }, { - "epoch": 0.88, - "learning_rate": 5.983588179902247e-06, - "loss": 0.1464, + "epoch": 0.44, + "learning_rate": 2.804131898615244e-05, + "loss": 0.1452, "step": 197400 }, { - "epoch": 0.88, - "learning_rate": 5.981346127976324e-06, - "loss": 0.1402, + "epoch": 0.44, + "learning_rate": 2.804020044294311e-05, + "loss": 0.1401, "step": 197410 }, { - "epoch": 0.88, - "learning_rate": 5.979104076050401e-06, - "loss": 0.1421, + "epoch": 0.44, + "learning_rate": 2.8039081899733787e-05, + "loss": 0.1476, "step": 197420 }, { - "epoch": 0.88, - "learning_rate": 5.976862024124479e-06, - "loss": 0.1351, + "epoch": 0.44, + "learning_rate": 2.8037963356524465e-05, + "loss": 0.1446, "step": 197430 }, { - "epoch": 0.88, - "learning_rate": 5.974619972198557e-06, - "loss": 0.1451, + "epoch": 0.44, + "learning_rate": 2.803684481331514e-05, + "loss": 0.1443, "step": 197440 }, { - "epoch": 0.88, - "learning_rate": 5.972377920272634e-06, - "loss": 0.1353, + "epoch": 0.44, + "learning_rate": 2.8035726270105818e-05, + "loss": 0.144, "step": 197450 }, { - "epoch": 0.88, - "learning_rate": 5.970135868346712e-06, - "loss": 0.1416, + "epoch": 0.44, + "learning_rate": 2.803460772689649e-05, + "loss": 0.1403, "step": 197460 }, { - "epoch": 0.88, - "learning_rate": 5.967893816420789e-06, - "loss": 0.1377, + "epoch": 0.44, + "learning_rate": 2.8033489183687167e-05, + "loss": 0.136, "step": 197470 }, { - "epoch": 0.88, - "learning_rate": 5.965651764494866e-06, - "loss": 0.1384, + "epoch": 0.44, + "learning_rate": 2.8032370640477845e-05, + "loss": 0.1418, "step": 197480 }, { - "epoch": 0.88, - "learning_rate": 5.963409712568943e-06, - "loss": 0.1386, + "epoch": 0.44, + "learning_rate": 2.803125209726852e-05, + "loss": 0.1398, "step": 197490 }, { - "epoch": 0.88, - "learning_rate": 5.961167660643021e-06, - "loss": 0.1371, + "epoch": 0.44, + "learning_rate": 2.8030133554059197e-05, + "loss": 0.1346, "step": 197500 }, { - "epoch": 0.88, - "learning_rate": 5.9589256087170985e-06, - "loss": 0.1378, + "epoch": 0.44, + "learning_rate": 2.802901501084987e-05, + "loss": 0.1433, "step": 197510 }, { - "epoch": 0.88, - "learning_rate": 5.9566835567911755e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.8027896467640546e-05, + "loss": 0.1386, "step": 197520 }, { - "epoch": 0.88, - "learning_rate": 5.954441504865253e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.8026777924431224e-05, + "loss": 0.1409, "step": 197530 }, { - "epoch": 0.88, - "learning_rate": 5.95219945293933e-06, - "loss": 0.137, + "epoch": 0.44, + "learning_rate": 2.8025659381221895e-05, + "loss": 0.1441, "step": 197540 }, { - "epoch": 0.88, - "learning_rate": 5.949957401013407e-06, - "loss": 0.1386, + "epoch": 0.44, + "learning_rate": 2.8024540838012577e-05, + "loss": 0.1435, "step": 197550 }, { - "epoch": 0.88, - "learning_rate": 5.9477153490874844e-06, - "loss": 0.1497, + "epoch": 0.44, + "learning_rate": 2.8023422294803248e-05, + "loss": 0.1377, "step": 197560 }, { - "epoch": 0.88, - "learning_rate": 5.945473297161562e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.8022303751593926e-05, + "loss": 0.1414, "step": 197570 }, { - "epoch": 0.88, - "learning_rate": 5.94323124523564e-06, - "loss": 0.1448, + "epoch": 0.44, + "learning_rate": 2.8021185208384604e-05, + "loss": 0.1407, "step": 197580 }, { - "epoch": 0.88, - "learning_rate": 5.940989193309717e-06, - "loss": 0.1402, + "epoch": 0.44, + "learning_rate": 2.8020066665175275e-05, + "loss": 0.1415, "step": 197590 }, { - "epoch": 0.88, - "learning_rate": 5.938747141383795e-06, - "loss": 0.1448, + "epoch": 0.44, + "learning_rate": 2.8018948121965953e-05, + "loss": 0.1355, "step": 197600 }, { - "epoch": 0.88, - "learning_rate": 5.936505089457872e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.8017829578756627e-05, + "loss": 0.1434, "step": 197610 }, { - "epoch": 0.88, - "learning_rate": 5.934263037531949e-06, - "loss": 0.1484, + "epoch": 0.44, + "learning_rate": 2.8016711035547305e-05, + "loss": 0.1496, "step": 197620 }, { - "epoch": 0.88, - "learning_rate": 5.932020985606027e-06, - "loss": 0.1472, + "epoch": 0.44, + "learning_rate": 2.8015592492337983e-05, + "loss": 0.1438, "step": 197630 }, { - "epoch": 0.88, - "learning_rate": 5.929778933680105e-06, - "loss": 0.1424, + "epoch": 0.44, + "learning_rate": 2.8014473949128654e-05, + "loss": 0.1417, "step": 197640 }, { - "epoch": 0.88, - "learning_rate": 5.927536881754182e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.8013355405919332e-05, + "loss": 0.139, "step": 197650 }, { - "epoch": 0.88, - "learning_rate": 5.925294829828259e-06, - "loss": 0.1455, + "epoch": 0.44, + "learning_rate": 2.8012236862710007e-05, + "loss": 0.1422, "step": 197660 }, { - "epoch": 0.88, - "learning_rate": 5.923052777902337e-06, - "loss": 0.1444, + "epoch": 0.44, + "learning_rate": 2.8011118319500685e-05, + "loss": 0.1435, "step": 197670 }, { - "epoch": 0.88, - "learning_rate": 5.920810725976414e-06, - "loss": 0.143, + "epoch": 0.44, + "learning_rate": 2.8009999776291356e-05, + "loss": 0.1398, "step": 197680 }, { - "epoch": 0.88, - "learning_rate": 5.918568674050491e-06, - "loss": 0.1484, + "epoch": 0.44, + "learning_rate": 2.8008881233082034e-05, + "loss": 0.1442, "step": 197690 }, { - "epoch": 0.88, - "learning_rate": 5.916326622124569e-06, - "loss": 0.146, + "epoch": 0.44, + "learning_rate": 2.8007762689872712e-05, + "loss": 0.1429, "step": 197700 }, { - "epoch": 0.88, - "learning_rate": 5.9140845701986466e-06, - "loss": 0.1454, + "epoch": 0.44, + "learning_rate": 2.8006644146663386e-05, + "loss": 0.143, "step": 197710 }, { - "epoch": 0.88, - "learning_rate": 5.911842518272724e-06, - "loss": 0.1466, + "epoch": 0.44, + "learning_rate": 2.8005525603454064e-05, + "loss": 0.1419, "step": 197720 }, { - "epoch": 0.88, - "learning_rate": 5.909600466346801e-06, - "loss": 0.144, + "epoch": 0.44, + "learning_rate": 2.8004407060244735e-05, + "loss": 0.1412, "step": 197730 }, { - "epoch": 0.88, - "learning_rate": 5.9073584144208785e-06, + "epoch": 0.44, + "learning_rate": 2.8003288517035413e-05, "loss": 0.1441, "step": 197740 }, { - "epoch": 0.88, - "learning_rate": 5.9051163624949555e-06, - "loss": 0.1458, + "epoch": 0.44, + "learning_rate": 2.800216997382609e-05, + "loss": 0.148, "step": 197750 }, { - "epoch": 0.88, - "learning_rate": 5.9028743105690325e-06, - "loss": 0.1413, + "epoch": 0.44, + "learning_rate": 2.8001051430616766e-05, + "loss": 0.1425, "step": 197760 }, { - "epoch": 0.88, - "learning_rate": 5.90063225864311e-06, - "loss": 0.1372, + "epoch": 0.44, + "learning_rate": 2.7999932887407444e-05, + "loss": 0.1432, "step": 197770 }, { - "epoch": 0.88, - "learning_rate": 5.898390206717188e-06, - "loss": 0.1435, + "epoch": 0.44, + "learning_rate": 2.7998814344198115e-05, + "loss": 0.1415, "step": 197780 }, { - "epoch": 0.88, - "learning_rate": 5.896148154791265e-06, - "loss": 0.1436, + "epoch": 0.44, + "learning_rate": 2.7997695800988793e-05, + "loss": 0.138, "step": 197790 }, { - "epoch": 0.88, - "learning_rate": 5.893906102865342e-06, - "loss": 0.1428, + "epoch": 0.44, + "learning_rate": 2.799657725777947e-05, + "loss": 0.1448, "step": 197800 }, { - "epoch": 0.88, - "learning_rate": 5.89166405093942e-06, - "loss": 0.1445, + "epoch": 0.44, + "learning_rate": 2.7995458714570145e-05, + "loss": 0.1467, "step": 197810 }, { - "epoch": 0.88, - "learning_rate": 5.889421999013497e-06, - "loss": 0.142, + "epoch": 0.44, + "learning_rate": 2.7994340171360823e-05, + "loss": 0.1431, "step": 197820 }, { - "epoch": 0.88, - "learning_rate": 5.887179947087574e-06, - "loss": 0.1454, + "epoch": 0.44, + "learning_rate": 2.7993221628151494e-05, + "loss": 0.1385, "step": 197830 }, { - "epoch": 0.88, - "learning_rate": 5.884937895161652e-06, - "loss": 0.145, + "epoch": 0.44, + "learning_rate": 2.7992103084942172e-05, + "loss": 0.1457, "step": 197840 }, { - "epoch": 0.88, - "learning_rate": 5.88269584323573e-06, - "loss": 0.1406, + "epoch": 0.44, + "learning_rate": 2.7991096396053778e-05, + "loss": 0.1459, "step": 197850 }, { - "epoch": 0.88, - "learning_rate": 5.880453791309807e-06, - "loss": 0.1421, + "epoch": 0.44, + "learning_rate": 2.7989977852844456e-05, + "loss": 0.1438, "step": 197860 }, { - "epoch": 0.88, - "learning_rate": 5.878211739383884e-06, - "loss": 0.1428, + "epoch": 0.44, + "learning_rate": 2.7988859309635134e-05, + "loss": 0.1402, "step": 197870 }, { - "epoch": 0.88, - "learning_rate": 5.875969687457962e-06, - "loss": 0.1447, + "epoch": 0.44, + "learning_rate": 2.7987740766425808e-05, + "loss": 0.1376, "step": 197880 }, { - "epoch": 0.88, - "learning_rate": 5.873727635532039e-06, - "loss": 0.1481, + "epoch": 0.44, + "learning_rate": 2.7986622223216486e-05, + "loss": 0.1447, "step": 197890 }, { - "epoch": 0.88, - "learning_rate": 5.871485583606117e-06, - "loss": 0.1467, + "epoch": 0.44, + "learning_rate": 2.7985503680007157e-05, + "loss": 0.1423, "step": 197900 }, { - "epoch": 0.88, - "learning_rate": 5.869243531680195e-06, - "loss": 0.1469, + "epoch": 0.44, + "learning_rate": 2.7984385136797835e-05, + "loss": 0.1411, "step": 197910 }, { - "epoch": 0.88, - "learning_rate": 5.867001479754272e-06, - "loss": 0.1447, + "epoch": 0.44, + "learning_rate": 2.7983266593588513e-05, + "loss": 0.1384, "step": 197920 }, { - "epoch": 0.88, - "learning_rate": 5.864759427828349e-06, - "loss": 0.1456, + "epoch": 0.44, + "learning_rate": 2.7982148050379188e-05, + "loss": 0.1375, "step": 197930 }, { - "epoch": 0.88, - "learning_rate": 5.862517375902426e-06, - "loss": 0.1419, + "epoch": 0.44, + "learning_rate": 2.7981029507169866e-05, + "loss": 0.1381, "step": 197940 }, { - "epoch": 0.88, - "learning_rate": 5.860275323976504e-06, - "loss": 0.141, + "epoch": 0.44, + "learning_rate": 2.7979910963960537e-05, + "loss": 0.1454, "step": 197950 }, { - "epoch": 0.88, - "learning_rate": 5.858033272050581e-06, - "loss": 0.1469, + "epoch": 0.44, + "learning_rate": 2.7978792420751215e-05, + "loss": 0.1397, "step": 197960 }, { - "epoch": 0.88, - "learning_rate": 5.8557912201246585e-06, - "loss": 0.1514, + "epoch": 0.44, + "learning_rate": 2.7977673877541893e-05, + "loss": 0.1448, "step": 197970 }, { - "epoch": 0.88, - "learning_rate": 5.853549168198736e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.7976555334332567e-05, + "loss": 0.1372, "step": 197980 }, { - "epoch": 0.88, - "learning_rate": 5.851307116272813e-06, - "loss": 0.1409, + "epoch": 0.44, + "learning_rate": 2.7975436791123245e-05, + "loss": 0.1418, "step": 197990 }, { - "epoch": 0.88, - "learning_rate": 5.8490650643468904e-06, - "loss": 0.1362, + "epoch": 0.44, + "learning_rate": 2.7974318247913916e-05, + "loss": 0.1395, "step": 198000 }, { - "epoch": 0.88, - "learning_rate": 5.8468230124209674e-06, - "loss": 0.1432, + "epoch": 0.44, + "learning_rate": 2.7973199704704594e-05, + "loss": 0.1394, "step": 198010 }, { - "epoch": 0.88, - "learning_rate": 5.844580960495045e-06, - "loss": 0.1464, + "epoch": 0.44, + "learning_rate": 2.797208116149527e-05, + "loss": 0.1448, "step": 198020 }, { - "epoch": 0.88, - "learning_rate": 5.842338908569122e-06, - "loss": 0.1426, + "epoch": 0.44, + "learning_rate": 2.7970962618285947e-05, + "loss": 0.1364, "step": 198030 }, { - "epoch": 0.88, - "learning_rate": 5.8400968566432e-06, - "loss": 0.1351, + "epoch": 0.44, + "learning_rate": 2.7969844075076624e-05, + "loss": 0.14, "step": 198040 }, { - "epoch": 0.88, - "learning_rate": 5.837854804717278e-06, - "loss": 0.145, + "epoch": 0.44, + "learning_rate": 2.7968725531867296e-05, + "loss": 0.137, "step": 198050 }, { - "epoch": 0.88, - "learning_rate": 5.835612752791355e-06, - "loss": 0.1408, + "epoch": 0.44, + "learning_rate": 2.7967606988657974e-05, + "loss": 0.1448, "step": 198060 }, { - "epoch": 0.88, - "learning_rate": 5.833370700865432e-06, - "loss": 0.1507, + "epoch": 0.44, + "learning_rate": 2.7966488445448648e-05, + "loss": 0.1445, "step": 198070 }, { - "epoch": 0.88, - "learning_rate": 5.83112864893951e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.7965369902239326e-05, + "loss": 0.1388, "step": 198080 }, { - "epoch": 0.88, - "learning_rate": 5.828886597013587e-06, - "loss": 0.1423, + "epoch": 0.44, + "learning_rate": 2.7964251359030004e-05, + "loss": 0.1477, "step": 198090 }, { - "epoch": 0.88, - "learning_rate": 5.826644545087664e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.7963132815820675e-05, + "loss": 0.1403, "step": 198100 }, { - "epoch": 0.88, - "learning_rate": 5.824402493161742e-06, - "loss": 0.1367, + "epoch": 0.44, + "learning_rate": 2.7962014272611353e-05, + "loss": 0.1429, "step": 198110 }, { - "epoch": 0.88, - "learning_rate": 5.82216044123582e-06, - "loss": 0.1426, + "epoch": 0.44, + "learning_rate": 2.7960895729402024e-05, + "loss": 0.1419, "step": 198120 }, { - "epoch": 0.88, - "learning_rate": 5.819918389309897e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.7959777186192705e-05, + "loss": 0.1408, "step": 198130 }, { - "epoch": 0.88, - "learning_rate": 5.817676337383974e-06, - "loss": 0.1445, + "epoch": 0.44, + "learning_rate": 2.7958658642983383e-05, + "loss": 0.1423, "step": 198140 }, { - "epoch": 0.88, - "learning_rate": 5.815434285458052e-06, - "loss": 0.1425, + "epoch": 0.44, + "learning_rate": 2.7957540099774055e-05, + "loss": 0.1409, "step": 198150 }, { - "epoch": 0.88, - "learning_rate": 5.813192233532129e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.7956421556564732e-05, + "loss": 0.1416, "step": 198160 }, { - "epoch": 0.88, - "learning_rate": 5.810950181606207e-06, - "loss": 0.1468, + "epoch": 0.44, + "learning_rate": 2.7955303013355404e-05, + "loss": 0.1425, "step": 198170 }, { - "epoch": 0.88, - "learning_rate": 5.808708129680284e-06, - "loss": 0.1428, + "epoch": 0.44, + "learning_rate": 2.795418447014608e-05, + "loss": 0.1445, "step": 198180 }, { - "epoch": 0.88, - "learning_rate": 5.8064660777543615e-06, - "loss": 0.1416, + "epoch": 0.44, + "learning_rate": 2.795306592693676e-05, + "loss": 0.1373, "step": 198190 }, { - "epoch": 0.88, - "learning_rate": 5.804448231021031e-06, - "loss": 0.1368, + "epoch": 0.44, + "learning_rate": 2.7951947383727434e-05, + "loss": 0.139, "step": 198200 }, { - "epoch": 0.88, - "learning_rate": 5.802206179095108e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.7950828840518112e-05, + "loss": 0.1502, "step": 198210 }, { - "epoch": 0.88, - "learning_rate": 5.799964127169186e-06, - "loss": 0.1411, + "epoch": 0.44, + "learning_rate": 2.7949710297308783e-05, + "loss": 0.1434, "step": 198220 }, { - "epoch": 0.88, - "learning_rate": 5.797722075243263e-06, - "loss": 0.1367, + "epoch": 0.44, + "learning_rate": 2.794859175409946e-05, + "loss": 0.1422, "step": 198230 }, { - "epoch": 0.88, - "learning_rate": 5.79548002331734e-06, - "loss": 0.1468, + "epoch": 0.44, + "learning_rate": 2.794747321089014e-05, + "loss": 0.1431, "step": 198240 }, { - "epoch": 0.89, - "learning_rate": 5.793237971391418e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.7946354667680814e-05, + "loss": 0.1414, "step": 198250 }, { - "epoch": 0.89, - "learning_rate": 5.790995919465495e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.794523612447149e-05, + "loss": 0.1385, "step": 198260 }, { - "epoch": 0.89, - "learning_rate": 5.788753867539573e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.7944117581262163e-05, + "loss": 0.1403, "step": 198270 }, { - "epoch": 0.89, - "learning_rate": 5.78651181561365e-06, - "loss": 0.1383, + "epoch": 0.44, + "learning_rate": 2.794299903805284e-05, + "loss": 0.1369, "step": 198280 }, { - "epoch": 0.89, - "learning_rate": 5.784269763687728e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.794188049484352e-05, + "loss": 0.1452, "step": 198290 }, { - "epoch": 0.89, - "learning_rate": 5.782027711761805e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.7940761951634193e-05, + "loss": 0.1412, "step": 198300 }, { - "epoch": 0.89, - "learning_rate": 5.779785659835882e-06, - "loss": 0.1438, + "epoch": 0.44, + "learning_rate": 2.793964340842487e-05, + "loss": 0.1433, "step": 198310 }, { - "epoch": 0.89, - "learning_rate": 5.7775436079099595e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.7938524865215542e-05, + "loss": 0.1365, "step": 198320 }, { - "epoch": 0.89, - "learning_rate": 5.7753015559840365e-06, - "loss": 0.1465, + "epoch": 0.44, + "learning_rate": 2.793740632200622e-05, + "loss": 0.1446, "step": 198330 }, { - "epoch": 0.89, - "learning_rate": 5.773059504058114e-06, - "loss": 0.1429, + "epoch": 0.44, + "learning_rate": 2.7936287778796895e-05, + "loss": 0.1418, "step": 198340 }, { - "epoch": 0.89, - "learning_rate": 5.770817452132192e-06, - "loss": 0.1448, + "epoch": 0.44, + "learning_rate": 2.7935169235587572e-05, + "loss": 0.1462, "step": 198350 }, { - "epoch": 0.89, - "learning_rate": 5.768575400206269e-06, - "loss": 0.1425, + "epoch": 0.44, + "learning_rate": 2.793405069237825e-05, + "loss": 0.1448, "step": 198360 }, { - "epoch": 0.89, - "learning_rate": 5.766333348280346e-06, - "loss": 0.1419, + "epoch": 0.44, + "learning_rate": 2.793293214916892e-05, + "loss": 0.1386, "step": 198370 }, { - "epoch": 0.89, - "learning_rate": 5.764091296354423e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.79318136059596e-05, + "loss": 0.143, "step": 198380 }, { - "epoch": 0.89, - "learning_rate": 5.761849244428501e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.7930695062750274e-05, + "loss": 0.1449, "step": 198390 }, { - "epoch": 0.89, - "learning_rate": 5.759607192502578e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.7929576519540952e-05, + "loss": 0.1385, "step": 198400 }, { - "epoch": 0.89, - "learning_rate": 5.757365140576656e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.792845797633163e-05, + "loss": 0.1448, "step": 198410 }, { - "epoch": 0.89, - "learning_rate": 5.755123088650734e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.79273394331223e-05, + "loss": 0.1411, "step": 198420 }, { - "epoch": 0.89, - "learning_rate": 5.752881036724811e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.792622088991298e-05, + "loss": 0.1431, "step": 198430 }, { - "epoch": 0.89, - "learning_rate": 5.750638984798888e-06, - "loss": 0.1353, + "epoch": 0.44, + "learning_rate": 2.7925102346703653e-05, + "loss": 0.1377, "step": 198440 }, { - "epoch": 0.89, - "learning_rate": 5.748396932872965e-06, - "loss": 0.1417, + "epoch": 0.44, + "learning_rate": 2.792398380349433e-05, + "loss": 0.1456, "step": 198450 }, { - "epoch": 0.89, - "learning_rate": 5.746154880947043e-06, - "loss": 0.1409, + "epoch": 0.44, + "learning_rate": 2.792286526028501e-05, + "loss": 0.144, "step": 198460 }, { - "epoch": 0.89, - "learning_rate": 5.743912829021121e-06, - "loss": 0.139, + "epoch": 0.44, + "learning_rate": 2.792174671707568e-05, + "loss": 0.1431, "step": 198470 }, { - "epoch": 0.89, - "learning_rate": 5.741670777095198e-06, - "loss": 0.1388, + "epoch": 0.44, + "learning_rate": 2.792062817386636e-05, + "loss": 0.1449, "step": 198480 }, { - "epoch": 0.89, - "learning_rate": 5.739428725169276e-06, - "loss": 0.1449, + "epoch": 0.44, + "learning_rate": 2.7919509630657033e-05, + "loss": 0.1444, "step": 198490 }, { - "epoch": 0.89, - "learning_rate": 5.737186673243353e-06, - "loss": 0.1363, + "epoch": 0.44, + "learning_rate": 2.791839108744771e-05, + "loss": 0.1414, "step": 198500 }, { - "epoch": 0.89, - "learning_rate": 5.73494462131743e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.791727254423839e-05, + "loss": 0.1473, "step": 198510 }, { - "epoch": 0.89, - "learning_rate": 5.732702569391507e-06, - "loss": 0.1441, + "epoch": 0.44, + "learning_rate": 2.791615400102906e-05, + "loss": 0.144, "step": 198520 }, { - "epoch": 0.89, - "learning_rate": 5.730460517465585e-06, - "loss": 0.1323, + "epoch": 0.44, + "learning_rate": 2.7915035457819738e-05, + "loss": 0.1384, "step": 198530 }, { - "epoch": 0.89, - "learning_rate": 5.7282184655396625e-06, - "loss": 0.1417, + "epoch": 0.44, + "learning_rate": 2.791391691461041e-05, + "loss": 0.1428, "step": 198540 }, { - "epoch": 0.89, - "learning_rate": 5.7259764136137395e-06, - "loss": 0.1434, + "epoch": 0.44, + "learning_rate": 2.791279837140109e-05, + "loss": 0.1405, "step": 198550 }, { - "epoch": 0.89, - "learning_rate": 5.723734361687817e-06, - "loss": 0.1411, + "epoch": 0.44, + "learning_rate": 2.7911679828191768e-05, + "loss": 0.1403, "step": 198560 }, { - "epoch": 0.89, - "learning_rate": 5.721492309761894e-06, - "loss": 0.1404, + "epoch": 0.44, + "learning_rate": 2.791056128498244e-05, + "loss": 0.1411, "step": 198570 }, { - "epoch": 0.89, - "learning_rate": 5.7192502578359714e-06, - "loss": 0.1449, + "epoch": 0.44, + "learning_rate": 2.7909442741773117e-05, + "loss": 0.1425, "step": 198580 }, { - "epoch": 0.89, - "learning_rate": 5.7170082059100485e-06, - "loss": 0.1457, + "epoch": 0.44, + "learning_rate": 2.790832419856379e-05, + "loss": 0.1444, "step": 198590 }, { - "epoch": 0.89, - "learning_rate": 5.714766153984126e-06, - "loss": 0.1425, + "epoch": 0.44, + "learning_rate": 2.7907205655354466e-05, + "loss": 0.1406, "step": 198600 }, { - "epoch": 0.89, - "learning_rate": 5.712524102058204e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.7906087112145148e-05, + "loss": 0.1399, "step": 198610 }, { - "epoch": 0.89, - "learning_rate": 5.710282050132281e-06, - "loss": 0.141, + "epoch": 0.44, + "learning_rate": 2.790496856893582e-05, + "loss": 0.1427, "step": 198620 }, { - "epoch": 0.89, - "learning_rate": 5.708039998206359e-06, - "loss": 0.1447, + "epoch": 0.44, + "learning_rate": 2.7903850025726497e-05, + "loss": 0.1412, "step": 198630 }, { - "epoch": 0.89, - "learning_rate": 5.705797946280436e-06, - "loss": 0.1434, + "epoch": 0.44, + "learning_rate": 2.7902731482517168e-05, + "loss": 0.1461, "step": 198640 }, { - "epoch": 0.89, - "learning_rate": 5.703555894354513e-06, - "loss": 0.1363, + "epoch": 0.44, + "learning_rate": 2.7901612939307846e-05, + "loss": 0.1477, "step": 198650 }, { - "epoch": 0.89, - "learning_rate": 5.701313842428591e-06, - "loss": 0.1377, + "epoch": 0.44, + "learning_rate": 2.790049439609852e-05, + "loss": 0.1416, "step": 198660 }, { - "epoch": 0.89, - "learning_rate": 5.699071790502668e-06, - "loss": 0.1363, + "epoch": 0.44, + "learning_rate": 2.78993758528892e-05, + "loss": 0.145, "step": 198670 }, { - "epoch": 0.89, - "learning_rate": 5.696829738576746e-06, - "loss": 0.144, + "epoch": 0.44, + "learning_rate": 2.7898257309679876e-05, + "loss": 0.1398, "step": 198680 }, { - "epoch": 0.89, - "learning_rate": 5.694587686650823e-06, - "loss": 0.1409, + "epoch": 0.44, + "learning_rate": 2.7897138766470547e-05, + "loss": 0.1416, "step": 198690 }, { - "epoch": 0.89, - "learning_rate": 5.692345634724901e-06, - "loss": 0.139, + "epoch": 0.44, + "learning_rate": 2.7896020223261225e-05, + "loss": 0.1446, "step": 198700 }, { - "epoch": 0.89, - "learning_rate": 5.690103582798978e-06, + "epoch": 0.44, + "learning_rate": 2.78949016800519e-05, "loss": 0.1416, "step": 198710 }, { - "epoch": 0.89, - "learning_rate": 5.687861530873055e-06, - "loss": 0.1435, + "epoch": 0.44, + "learning_rate": 2.7893783136842578e-05, + "loss": 0.1462, "step": 198720 }, { - "epoch": 0.89, - "learning_rate": 5.685619478947133e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.7892664593633256e-05, + "loss": 0.1419, "step": 198730 }, { - "epoch": 0.89, - "learning_rate": 5.683377427021211e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.7891546050423927e-05, + "loss": 0.1437, "step": 198740 }, { - "epoch": 0.89, - "learning_rate": 5.681135375095288e-06, - "loss": 0.14, + "epoch": 0.44, + "learning_rate": 2.7890427507214605e-05, + "loss": 0.1387, "step": 198750 }, { - "epoch": 0.89, - "learning_rate": 5.678893323169365e-06, - "loss": 0.1467, + "epoch": 0.44, + "learning_rate": 2.788930896400528e-05, + "loss": 0.1435, "step": 198760 }, { - "epoch": 0.89, - "learning_rate": 5.6766512712434425e-06, - "loss": 0.1379, + "epoch": 0.44, + "learning_rate": 2.7888190420795957e-05, + "loss": 0.1411, "step": 198770 }, { - "epoch": 0.89, - "learning_rate": 5.6744092193175195e-06, - "loss": 0.1378, + "epoch": 0.44, + "learning_rate": 2.7887071877586635e-05, + "loss": 0.1414, "step": 198780 }, { - "epoch": 0.89, - "learning_rate": 5.6721671673915966e-06, - "loss": 0.1417, + "epoch": 0.44, + "learning_rate": 2.7885953334377306e-05, + "loss": 0.1437, "step": 198790 }, { - "epoch": 0.89, - "learning_rate": 5.6699251154656744e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.7884834791167984e-05, + "loss": 0.1444, "step": 198800 }, { - "epoch": 0.89, - "learning_rate": 5.667683063539752e-06, - "loss": 0.1436, + "epoch": 0.44, + "learning_rate": 2.788371624795866e-05, + "loss": 0.1404, "step": 198810 }, { - "epoch": 0.89, - "learning_rate": 5.665441011613829e-06, - "loss": 0.1393, + "epoch": 0.44, + "learning_rate": 2.7882597704749337e-05, + "loss": 0.1437, "step": 198820 }, { - "epoch": 0.89, - "learning_rate": 5.663198959687906e-06, - "loss": 0.1394, + "epoch": 0.44, + "learning_rate": 2.7881479161540015e-05, + "loss": 0.1437, "step": 198830 }, { - "epoch": 0.89, - "learning_rate": 5.660956907761984e-06, - "loss": 0.1396, + "epoch": 0.44, + "learning_rate": 2.7880360618330686e-05, + "loss": 0.1425, "step": 198840 }, { - "epoch": 0.89, - "learning_rate": 5.658714855836061e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.7879242075121364e-05, + "loss": 0.1373, "step": 198850 }, { - "epoch": 0.89, - "learning_rate": 5.656472803910138e-06, - "loss": 0.1418, + "epoch": 0.44, + "learning_rate": 2.787812353191204e-05, + "loss": 0.141, "step": 198860 }, { - "epoch": 0.89, - "learning_rate": 5.654230751984216e-06, - "loss": 0.1427, + "epoch": 0.44, + "learning_rate": 2.7877004988702716e-05, + "loss": 0.1405, "step": 198870 }, { - "epoch": 0.89, - "learning_rate": 5.651988700058294e-06, - "loss": 0.1406, + "epoch": 0.44, + "learning_rate": 2.7875886445493394e-05, + "loss": 0.1431, "step": 198880 }, { - "epoch": 0.89, - "learning_rate": 5.649746648132371e-06, - "loss": 0.1433, + "epoch": 0.44, + "learning_rate": 2.7874767902284065e-05, + "loss": 0.1457, "step": 198890 }, { - "epoch": 0.89, - "learning_rate": 5.647504596206448e-06, - "loss": 0.1352, + "epoch": 0.44, + "learning_rate": 2.7873649359074743e-05, + "loss": 0.1432, "step": 198900 }, { - "epoch": 0.89, - "learning_rate": 5.645262544280526e-06, - "loss": 0.1412, + "epoch": 0.44, + "learning_rate": 2.7872530815865418e-05, + "loss": 0.1393, "step": 198910 }, { - "epoch": 0.89, - "learning_rate": 5.643020492354603e-06, - "loss": 0.1421, + "epoch": 0.44, + "learning_rate": 2.7871412272656096e-05, + "loss": 0.1392, "step": 198920 }, { - "epoch": 0.89, - "learning_rate": 5.64077844042868e-06, - "loss": 0.1415, + "epoch": 0.44, + "learning_rate": 2.7870293729446774e-05, + "loss": 0.1439, "step": 198930 }, { - "epoch": 0.89, - "learning_rate": 5.638536388502758e-06, - "loss": 0.1431, + "epoch": 0.44, + "learning_rate": 2.7869175186237445e-05, + "loss": 0.1456, "step": 198940 }, { - "epoch": 0.89, - "learning_rate": 5.636294336576836e-06, - "loss": 0.1422, + "epoch": 0.44, + "learning_rate": 2.7868056643028123e-05, + "loss": 0.1421, "step": 198950 }, { - "epoch": 0.89, - "learning_rate": 5.634052284650913e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.7866938099818797e-05, + "loss": 0.144, "step": 198960 }, { - "epoch": 0.89, - "learning_rate": 5.63181023272499e-06, - "loss": 0.1382, + "epoch": 0.44, + "learning_rate": 2.7865819556609475e-05, + "loss": 0.1441, "step": 198970 }, { - "epoch": 0.89, - "learning_rate": 5.629568180799068e-06, - "loss": 0.141, + "epoch": 0.44, + "learning_rate": 2.7864701013400146e-05, + "loss": 0.1449, "step": 198980 }, { - "epoch": 0.89, - "learning_rate": 5.627326128873145e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.7863582470190824e-05, + "loss": 0.1374, "step": 198990 }, { - "epoch": 0.89, - "learning_rate": 5.6250840769472225e-06, - "loss": 0.1426, + "epoch": 0.44, + "learning_rate": 2.7862463926981502e-05, + "loss": 0.1393, "step": 199000 }, { - "epoch": 0.89, - "learning_rate": 5.6228420250213e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.7861345383772173e-05, + "loss": 0.1461, "step": 199010 }, { - "epoch": 0.89, - "learning_rate": 5.6205999730953774e-06, - "loss": 0.1454, + "epoch": 0.44, + "learning_rate": 2.7860226840562855e-05, + "loss": 0.1419, "step": 199020 }, { - "epoch": 0.89, - "learning_rate": 5.6183579211694544e-06, - "loss": 0.1419, + "epoch": 0.44, + "learning_rate": 2.7859108297353526e-05, + "loss": 0.1385, "step": 199030 }, { - "epoch": 0.89, - "learning_rate": 5.616115869243532e-06, - "loss": 0.1372, + "epoch": 0.44, + "learning_rate": 2.7857989754144204e-05, + "loss": 0.1449, "step": 199040 }, { - "epoch": 0.89, - "learning_rate": 5.613873817317609e-06, - "loss": 0.1433, + "epoch": 0.44, + "learning_rate": 2.7856871210934882e-05, + "loss": 0.1414, "step": 199050 }, { - "epoch": 0.89, - "learning_rate": 5.611631765391686e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.7855752667725553e-05, + "loss": 0.1437, "step": 199060 }, { - "epoch": 0.89, - "learning_rate": 5.609389713465764e-06, - "loss": 0.138, + "epoch": 0.44, + "learning_rate": 2.785463412451623e-05, + "loss": 0.1462, "step": 199070 }, { - "epoch": 0.89, - "learning_rate": 5.607147661539842e-06, - "loss": 0.1442, + "epoch": 0.44, + "learning_rate": 2.7853515581306905e-05, + "loss": 0.1435, "step": 199080 }, { - "epoch": 0.89, - "learning_rate": 5.604905609613919e-06, - "loss": 0.1381, + "epoch": 0.44, + "learning_rate": 2.7852397038097583e-05, + "loss": 0.1386, "step": 199090 }, { - "epoch": 0.89, - "learning_rate": 5.602663557687996e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.785127849488826e-05, + "loss": 0.1419, "step": 199100 }, { - "epoch": 0.89, - "learning_rate": 5.600421505762074e-06, - "loss": 0.1461, + "epoch": 0.44, + "learning_rate": 2.7850159951678932e-05, + "loss": 0.1445, "step": 199110 }, { - "epoch": 0.89, - "learning_rate": 5.598179453836151e-06, - "loss": 0.1429, + "epoch": 0.44, + "learning_rate": 2.784904140846961e-05, + "loss": 0.1396, "step": 199120 }, { - "epoch": 0.89, - "learning_rate": 5.595937401910228e-06, - "loss": 0.1414, + "epoch": 0.44, + "learning_rate": 2.7847922865260285e-05, + "loss": 0.1427, "step": 199130 }, { - "epoch": 0.89, - "learning_rate": 5.593695349984306e-06, - "loss": 0.1369, + "epoch": 0.44, + "learning_rate": 2.7846804322050963e-05, + "loss": 0.1426, "step": 199140 }, { - "epoch": 0.89, - "learning_rate": 5.591453298058384e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.784568577884164e-05, + "loss": 0.1391, "step": 199150 }, { - "epoch": 0.89, - "learning_rate": 5.589211246132461e-06, - "loss": 0.1336, + "epoch": 0.44, + "learning_rate": 2.7844567235632312e-05, + "loss": 0.1412, "step": 199160 }, { - "epoch": 0.89, - "learning_rate": 5.586969194206538e-06, - "loss": 0.1403, + "epoch": 0.44, + "learning_rate": 2.784344869242299e-05, + "loss": 0.1423, "step": 199170 }, { - "epoch": 0.89, - "learning_rate": 5.584727142280616e-06, - "loss": 0.1385, + "epoch": 0.44, + "learning_rate": 2.7842330149213664e-05, + "loss": 0.1393, "step": 199180 }, { - "epoch": 0.89, - "learning_rate": 5.582485090354693e-06, - "loss": 0.1451, + "epoch": 0.44, + "learning_rate": 2.7841211606004342e-05, + "loss": 0.1417, "step": 199190 }, { - "epoch": 0.89, - "learning_rate": 5.58024303842877e-06, - "loss": 0.1458, + "epoch": 0.44, + "learning_rate": 2.784009306279502e-05, + "loss": 0.142, "step": 199200 }, { - "epoch": 0.89, - "learning_rate": 5.578000986502848e-06, - "loss": 0.1376, + "epoch": 0.44, + "learning_rate": 2.783897451958569e-05, + "loss": 0.1445, "step": 199210 }, { - "epoch": 0.89, - "learning_rate": 5.5757589345769255e-06, - "loss": 0.1361, + "epoch": 0.44, + "learning_rate": 2.783785597637637e-05, + "loss": 0.1415, "step": 199220 }, { - "epoch": 0.89, - "learning_rate": 5.5735168826510025e-06, - "loss": 0.1386, + "epoch": 0.44, + "learning_rate": 2.7836737433167044e-05, + "loss": 0.1418, "step": 199230 }, { - "epoch": 0.89, - "learning_rate": 5.5712748307250796e-06, - "loss": 0.1359, + "epoch": 0.44, + "learning_rate": 2.783561888995772e-05, + "loss": 0.1381, "step": 199240 }, { - "epoch": 0.89, - "learning_rate": 5.5690327787991574e-06, - "loss": 0.142, + "epoch": 0.44, + "learning_rate": 2.78345003467484e-05, + "loss": 0.1401, "step": 199250 }, { - "epoch": 0.89, - "learning_rate": 5.5667907268732345e-06, - "loss": 0.1405, + "epoch": 0.44, + "learning_rate": 2.783338180353907e-05, + "loss": 0.1433, "step": 199260 }, { - "epoch": 0.89, - "learning_rate": 5.564548674947312e-06, - "loss": 0.1392, + "epoch": 0.44, + "learning_rate": 2.783226326032975e-05, + "loss": 0.1422, "step": 199270 }, { - "epoch": 0.89, - "learning_rate": 5.562306623021389e-06, - "loss": 0.1389, + "epoch": 0.44, + "learning_rate": 2.7831144717120423e-05, + "loss": 0.1413, "step": 199280 }, { - "epoch": 0.89, - "learning_rate": 5.560064571095467e-06, - "loss": 0.1395, + "epoch": 0.44, + "learning_rate": 2.78300261739111e-05, + "loss": 0.1402, "step": 199290 }, { - "epoch": 0.89, - "learning_rate": 5.557822519169544e-06, - "loss": 0.1417, + "epoch": 0.44, + "learning_rate": 2.7828907630701772e-05, + "loss": 0.14, "step": 199300 }, { - "epoch": 0.89, - "learning_rate": 5.555580467243621e-06, - "loss": 0.1423, + "epoch": 0.44, + "learning_rate": 2.782778908749245e-05, + "loss": 0.1417, "step": 199310 }, { - "epoch": 0.89, - "learning_rate": 5.553338415317699e-06, - "loss": 0.1384, + "epoch": 0.44, + "learning_rate": 2.7826670544283128e-05, + "loss": 0.1424, "step": 199320 }, { - "epoch": 0.89, - "learning_rate": 5.551096363391776e-06, - "loss": 0.1407, + "epoch": 0.44, + "learning_rate": 2.7825552001073803e-05, + "loss": 0.1398, "step": 199330 }, { - "epoch": 0.89, - "learning_rate": 5.548854311465854e-06, - "loss": 0.1398, + "epoch": 0.44, + "learning_rate": 2.782443345786448e-05, + "loss": 0.1433, "step": 199340 }, { - "epoch": 0.89, - "learning_rate": 5.546612259539932e-06, - "loss": 0.1429, + "epoch": 0.44, + "learning_rate": 2.7823314914655152e-05, + "loss": 0.1397, "step": 199350 }, { - "epoch": 0.89, - "learning_rate": 5.544370207614009e-06, - "loss": 0.1455, + "epoch": 0.44, + "learning_rate": 2.782219637144583e-05, + "loss": 0.1384, "step": 199360 }, { - "epoch": 0.89, - "learning_rate": 5.542128155688086e-06, - "loss": 0.1415, + "epoch": 0.45, + "learning_rate": 2.7821077828236508e-05, + "loss": 0.1439, "step": 199370 }, { - "epoch": 0.89, - "learning_rate": 5.539886103762163e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.7819959285027182e-05, + "loss": 0.1427, "step": 199380 }, { - "epoch": 0.89, - "learning_rate": 5.537644051836241e-06, - "loss": 0.1342, + "epoch": 0.45, + "learning_rate": 2.781884074181786e-05, + "loss": 0.1386, "step": 199390 }, { - "epoch": 0.89, - "learning_rate": 5.535401999910318e-06, - "loss": 0.1401, + "epoch": 0.45, + "learning_rate": 2.781772219860853e-05, + "loss": 0.1406, "step": 199400 }, { - "epoch": 0.89, - "learning_rate": 5.533159947984396e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.781660365539921e-05, + "loss": 0.1391, "step": 199410 }, { - "epoch": 0.89, - "learning_rate": 5.530917896058474e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.7815485112189887e-05, + "loss": 0.1419, "step": 199420 }, { - "epoch": 0.89, - "learning_rate": 5.528675844132551e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.7814366568980558e-05, + "loss": 0.14, "step": 199430 }, { - "epoch": 0.89, - "learning_rate": 5.526433792206628e-06, - "loss": 0.1426, + "epoch": 0.45, + "learning_rate": 2.781324802577124e-05, + "loss": 0.1331, "step": 199440 }, { - "epoch": 0.89, - "learning_rate": 5.524191740280705e-06, - "loss": 0.1383, + "epoch": 0.45, + "learning_rate": 2.781212948256191e-05, + "loss": 0.1403, "step": 199450 }, { - "epoch": 0.89, - "learning_rate": 5.5219496883547826e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.781101093935259e-05, + "loss": 0.1464, "step": 199460 }, { - "epoch": 0.89, - "learning_rate": 5.51970763642886e-06, - "loss": 0.1418, + "epoch": 0.45, + "learning_rate": 2.7809892396143267e-05, + "loss": 0.1404, "step": 199470 }, { - "epoch": 0.89, - "learning_rate": 5.5174655845029375e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.7808773852933938e-05, + "loss": 0.1367, "step": 199480 }, { - "epoch": 0.89, - "learning_rate": 5.515223532577015e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.7807655309724616e-05, + "loss": 0.1477, "step": 199490 }, { - "epoch": 0.89, - "learning_rate": 5.512981480651092e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.780653676651529e-05, + "loss": 0.1457, "step": 199500 }, { - "epoch": 0.89, - "learning_rate": 5.510739428725169e-06, - "loss": 0.1462, + "epoch": 0.45, + "learning_rate": 2.7805418223305968e-05, + "loss": 0.1387, "step": 199510 }, { - "epoch": 0.89, - "learning_rate": 5.508497376799246e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.7804299680096646e-05, + "loss": 0.1423, "step": 199520 }, { - "epoch": 0.89, - "learning_rate": 5.506255324873324e-06, - "loss": 0.134, + "epoch": 0.45, + "learning_rate": 2.7803181136887317e-05, + "loss": 0.1392, "step": 199530 }, { - "epoch": 0.89, - "learning_rate": 5.504013272947401e-06, - "loss": 0.143, + "epoch": 0.45, + "learning_rate": 2.7802062593677995e-05, + "loss": 0.1392, "step": 199540 }, { - "epoch": 0.89, - "learning_rate": 5.501771221021479e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.780094405046867e-05, + "loss": 0.1373, "step": 199550 }, { - "epoch": 0.89, - "learning_rate": 5.499529169095557e-06, - "loss": 0.1415, + "epoch": 0.45, + "learning_rate": 2.7799825507259348e-05, + "loss": 0.1401, "step": 199560 }, { - "epoch": 0.89, - "learning_rate": 5.497287117169634e-06, - "loss": 0.1425, + "epoch": 0.45, + "learning_rate": 2.7798706964050026e-05, + "loss": 0.1388, "step": 199570 }, { - "epoch": 0.89, - "learning_rate": 5.495045065243711e-06, - "loss": 0.1395, + "epoch": 0.45, + "learning_rate": 2.7797588420840697e-05, + "loss": 0.1364, "step": 199580 }, { - "epoch": 0.89, - "learning_rate": 5.492803013317788e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.7796469877631375e-05, + "loss": 0.1363, "step": 199590 }, { - "epoch": 0.89, - "learning_rate": 5.490560961391866e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.779535133442205e-05, + "loss": 0.1387, "step": 199600 }, { - "epoch": 0.89, - "learning_rate": 5.488318909465944e-06, - "loss": 0.1398, + "epoch": 0.45, + "learning_rate": 2.7794232791212727e-05, + "loss": 0.1416, "step": 199610 }, { - "epoch": 0.89, - "learning_rate": 5.486076857540021e-06, - "loss": 0.1397, + "epoch": 0.45, + "learning_rate": 2.7793114248003398e-05, + "loss": 0.1381, "step": 199620 }, { - "epoch": 0.89, - "learning_rate": 5.483834805614099e-06, - "loss": 0.1391, + "epoch": 0.45, + "learning_rate": 2.7791995704794076e-05, + "loss": 0.1347, "step": 199630 }, { - "epoch": 0.89, - "learning_rate": 5.481592753688176e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.7790877161584754e-05, + "loss": 0.1396, "step": 199640 }, { - "epoch": 0.89, - "learning_rate": 5.479350701762253e-06, - "loss": 0.1439, + "epoch": 0.45, + "learning_rate": 2.778975861837543e-05, + "loss": 0.1412, "step": 199650 }, { - "epoch": 0.89, - "learning_rate": 5.477108649836331e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.7788640075166107e-05, + "loss": 0.1392, "step": 199660 }, { - "epoch": 0.89, - "learning_rate": 5.474866597910408e-06, - "loss": 0.1459, + "epoch": 0.45, + "learning_rate": 2.7787521531956778e-05, + "loss": 0.1423, "step": 199670 }, { - "epoch": 0.89, - "learning_rate": 5.4726245459844856e-06, - "loss": 0.1423, + "epoch": 0.45, + "learning_rate": 2.7786402988747456e-05, + "loss": 0.1461, "step": 199680 }, { - "epoch": 0.89, - "learning_rate": 5.4703824940585626e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.7785284445538134e-05, + "loss": 0.1423, "step": 199690 }, { - "epoch": 0.89, - "learning_rate": 5.4681404421326404e-06, - "loss": 0.145, + "epoch": 0.45, + "learning_rate": 2.7784165902328808e-05, + "loss": 0.1373, "step": 199700 }, { - "epoch": 0.89, - "learning_rate": 5.4658983902067175e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7783047359119486e-05, + "loss": 0.1434, "step": 199710 }, { - "epoch": 0.89, - "learning_rate": 5.4636563382807945e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.7781928815910157e-05, + "loss": 0.1486, "step": 199720 }, { - "epoch": 0.89, - "learning_rate": 5.461414286354872e-06, - "loss": 0.1421, + "epoch": 0.45, + "learning_rate": 2.7780810272700835e-05, + "loss": 0.1411, "step": 199730 }, { - "epoch": 0.89, - "learning_rate": 5.459172234428949e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7779691729491513e-05, + "loss": 0.1457, "step": 199740 }, { - "epoch": 0.89, - "learning_rate": 5.456930182503027e-06, - "loss": 0.1403, + "epoch": 0.45, + "learning_rate": 2.7778573186282188e-05, + "loss": 0.1393, "step": 199750 }, { - "epoch": 0.89, - "learning_rate": 5.454688130577104e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.7777454643072866e-05, + "loss": 0.1371, "step": 199760 }, { - "epoch": 0.89, - "learning_rate": 5.452446078651182e-06, - "loss": 0.1349, + "epoch": 0.45, + "learning_rate": 2.7776336099863537e-05, + "loss": 0.1386, "step": 199770 }, { - "epoch": 0.89, - "learning_rate": 5.450204026725259e-06, - "loss": 0.1423, + "epoch": 0.45, + "learning_rate": 2.7775217556654215e-05, + "loss": 0.1419, "step": 199780 }, { - "epoch": 0.89, - "learning_rate": 5.447961974799336e-06, - "loss": 0.1373, + "epoch": 0.45, + "learning_rate": 2.7774099013444893e-05, + "loss": 0.1422, "step": 199790 }, { - "epoch": 0.89, - "learning_rate": 5.445719922873414e-06, - "loss": 0.1438, + "epoch": 0.45, + "learning_rate": 2.7772980470235567e-05, + "loss": 0.1387, "step": 199800 }, { - "epoch": 0.89, - "learning_rate": 5.443477870947491e-06, - "loss": 0.1411, + "epoch": 0.45, + "learning_rate": 2.7771861927026245e-05, + "loss": 0.1412, "step": 199810 }, { - "epoch": 0.89, - "learning_rate": 5.441235819021569e-06, - "loss": 0.1401, + "epoch": 0.45, + "learning_rate": 2.7770743383816916e-05, + "loss": 0.1384, "step": 199820 }, { - "epoch": 0.89, - "learning_rate": 5.438993767095646e-06, - "loss": 0.1418, + "epoch": 0.45, + "learning_rate": 2.7769624840607594e-05, + "loss": 0.1385, "step": 199830 }, { - "epoch": 0.89, - "learning_rate": 5.436751715169724e-06, - "loss": 0.1355, + "epoch": 0.45, + "learning_rate": 2.7768506297398272e-05, + "loss": 0.1407, "step": 199840 }, { - "epoch": 0.89, - "learning_rate": 5.434509663243801e-06, - "loss": 0.1378, + "epoch": 0.45, + "learning_rate": 2.7767387754188947e-05, + "loss": 0.1423, "step": 199850 }, { - "epoch": 0.89, - "learning_rate": 5.432267611317878e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.7766269210979624e-05, + "loss": 0.1409, "step": 199860 }, { - "epoch": 0.89, - "learning_rate": 5.430025559391956e-06, - "loss": 0.1447, + "epoch": 0.45, + "learning_rate": 2.7765150667770296e-05, + "loss": 0.1376, "step": 199870 }, { - "epoch": 0.89, - "learning_rate": 5.427783507466034e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.7764032124560974e-05, + "loss": 0.1429, "step": 199880 }, { - "epoch": 0.89, - "learning_rate": 5.425541455540111e-06, - "loss": 0.1405, + "epoch": 0.45, + "learning_rate": 2.776291358135165e-05, + "loss": 0.1348, "step": 199890 }, { - "epoch": 0.89, - "learning_rate": 5.423299403614188e-06, - "loss": 0.1411, + "epoch": 0.45, + "learning_rate": 2.7761795038142323e-05, + "loss": 0.1432, "step": 199900 }, { - "epoch": 0.89, - "learning_rate": 5.4210573516882656e-06, - "loss": 0.1353, + "epoch": 0.45, + "learning_rate": 2.7760676494933004e-05, + "loss": 0.1365, "step": 199910 }, { - "epoch": 0.89, - "learning_rate": 5.418815299762343e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7759557951723675e-05, + "loss": 0.1399, "step": 199920 }, { - "epoch": 0.89, - "learning_rate": 5.41657324783642e-06, - "loss": 0.1366, + "epoch": 0.45, + "learning_rate": 2.7758439408514353e-05, + "loss": 0.1357, "step": 199930 }, { - "epoch": 0.89, - "learning_rate": 5.4143311959104975e-06, - "loss": 0.1351, + "epoch": 0.45, + "learning_rate": 2.7757320865305024e-05, + "loss": 0.1371, "step": 199940 }, { - "epoch": 0.89, - "learning_rate": 5.412089143984575e-06, - "loss": 0.1477, + "epoch": 0.45, + "learning_rate": 2.7756202322095702e-05, + "loss": 0.1366, "step": 199950 }, { - "epoch": 0.89, - "learning_rate": 5.409847092058652e-06, - "loss": 0.1378, + "epoch": 0.45, + "learning_rate": 2.775508377888638e-05, + "loss": 0.1399, "step": 199960 }, { - "epoch": 0.89, - "learning_rate": 5.407605040132729e-06, - "loss": 0.1435, + "epoch": 0.45, + "learning_rate": 2.7753965235677055e-05, + "loss": 0.138, "step": 199970 }, { - "epoch": 0.89, - "learning_rate": 5.405362988206807e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7752846692467732e-05, + "loss": 0.1359, "step": 199980 }, { - "epoch": 0.89, - "learning_rate": 5.403120936280884e-06, - "loss": 0.1443, + "epoch": 0.45, + "learning_rate": 2.7751728149258404e-05, + "loss": 0.1402, "step": 199990 }, { - "epoch": 0.89, - "learning_rate": 5.400878884354961e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.775060960604908e-05, + "loss": 0.1405, "step": 200000 }, { - "epoch": 0.89, - "learning_rate": 5.398636832429039e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.774949106283976e-05, + "loss": 0.1438, "step": 200010 }, { - "epoch": 0.89, - "learning_rate": 5.396394780503117e-06, - "loss": 0.1418, + "epoch": 0.45, + "learning_rate": 2.7748372519630434e-05, + "loss": 0.1359, "step": 200020 }, { - "epoch": 0.89, - "learning_rate": 5.394152728577194e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7747253976421112e-05, + "loss": 0.1417, "step": 200030 }, { - "epoch": 0.89, - "learning_rate": 5.391910676651272e-06, - "loss": 0.1422, + "epoch": 0.45, + "learning_rate": 2.7746135433211783e-05, + "loss": 0.1321, "step": 200040 }, { - "epoch": 0.89, - "learning_rate": 5.389668624725349e-06, - "loss": 0.1457, + "epoch": 0.45, + "learning_rate": 2.774501689000246e-05, + "loss": 0.1453, "step": 200050 }, { - "epoch": 0.89, - "learning_rate": 5.387426572799426e-06, - "loss": 0.1424, + "epoch": 0.45, + "learning_rate": 2.774389834679314e-05, + "loss": 0.141, "step": 200060 }, { - "epoch": 0.89, - "learning_rate": 5.385184520873503e-06, - "loss": 0.1383, + "epoch": 0.45, + "learning_rate": 2.7742779803583813e-05, + "loss": 0.1395, "step": 200070 }, { - "epoch": 0.89, - "learning_rate": 5.382942468947581e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.774166126037449e-05, + "loss": 0.1397, "step": 200080 }, { - "epoch": 0.89, - "learning_rate": 5.380700417021659e-06, - "loss": 0.1489, + "epoch": 0.45, + "learning_rate": 2.7740542717165163e-05, + "loss": 0.1417, "step": 200090 }, { - "epoch": 0.89, - "learning_rate": 5.378458365095736e-06, - "loss": 0.1379, + "epoch": 0.45, + "learning_rate": 2.773942417395584e-05, + "loss": 0.1409, "step": 200100 }, { - "epoch": 0.89, - "learning_rate": 5.376216313169814e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.773830563074652e-05, + "loss": 0.1366, "step": 200110 }, { - "epoch": 0.89, - "learning_rate": 5.373974261243891e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7737187087537193e-05, + "loss": 0.1397, "step": 200120 }, { - "epoch": 0.89, - "learning_rate": 5.371732209317968e-06, - "loss": 0.1351, + "epoch": 0.45, + "learning_rate": 2.773606854432787e-05, + "loss": 0.1407, "step": 200130 }, { - "epoch": 0.89, - "learning_rate": 5.369490157392046e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.7734950001118542e-05, + "loss": 0.1417, "step": 200140 }, { - "epoch": 0.89, - "learning_rate": 5.3672481054661235e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.773383145790922e-05, + "loss": 0.1429, "step": 200150 }, { - "epoch": 0.89, - "learning_rate": 5.3650060535402005e-06, - "loss": 0.1392, + "epoch": 0.45, + "learning_rate": 2.7732712914699898e-05, + "loss": 0.1431, "step": 200160 }, { - "epoch": 0.89, - "learning_rate": 5.3627640016142775e-06, - "loss": 0.1411, + "epoch": 0.45, + "learning_rate": 2.7731594371490572e-05, + "loss": 0.1391, "step": 200170 }, { - "epoch": 0.89, - "learning_rate": 5.360521949688355e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.773047582828125e-05, + "loss": 0.1381, "step": 200180 }, { - "epoch": 0.89, - "learning_rate": 5.358279897762432e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.772935728507192e-05, + "loss": 0.1382, "step": 200190 }, { - "epoch": 0.89, - "learning_rate": 5.356037845836509e-06, - "loss": 0.145, + "epoch": 0.45, + "learning_rate": 2.77282387418626e-05, + "loss": 0.1422, "step": 200200 }, { - "epoch": 0.89, - "learning_rate": 5.35401999910318e-06, - "loss": 0.1459, + "epoch": 0.45, + "learning_rate": 2.7727120198653277e-05, + "loss": 0.1426, "step": 200210 }, { - "epoch": 0.89, - "learning_rate": 5.351777947177257e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7726001655443952e-05, + "loss": 0.1387, "step": 200220 }, { - "epoch": 0.89, - "learning_rate": 5.349535895251334e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.772488311223463e-05, + "loss": 0.1381, "step": 200230 }, { - "epoch": 0.89, - "learning_rate": 5.347293843325412e-06, - "loss": 0.1415, + "epoch": 0.45, + "learning_rate": 2.77237645690253e-05, + "loss": 0.136, "step": 200240 }, { - "epoch": 0.89, - "learning_rate": 5.3450517913994895e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.772264602581598e-05, + "loss": 0.1372, "step": 200250 }, { - "epoch": 0.89, - "learning_rate": 5.3428097394735666e-06, - "loss": 0.1409, + "epoch": 0.45, + "learning_rate": 2.7721527482606653e-05, + "loss": 0.1402, "step": 200260 }, { - "epoch": 0.89, - "learning_rate": 5.340567687547644e-06, - "loss": 0.1407, + "epoch": 0.45, + "learning_rate": 2.772040893939733e-05, + "loss": 0.1424, "step": 200270 }, { - "epoch": 0.89, - "learning_rate": 5.3383256356217215e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.771929039618801e-05, + "loss": 0.1415, "step": 200280 }, { - "epoch": 0.89, - "learning_rate": 5.3360835836957985e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.771817185297868e-05, + "loss": 0.1373, "step": 200290 }, { - "epoch": 0.89, - "learning_rate": 5.3338415317698755e-06, - "loss": 0.1432, + "epoch": 0.45, + "learning_rate": 2.771705330976936e-05, + "loss": 0.1361, "step": 200300 }, { - "epoch": 0.89, - "learning_rate": 5.331599479843953e-06, - "loss": 0.1416, + "epoch": 0.45, + "learning_rate": 2.771593476656003e-05, + "loss": 0.1378, "step": 200310 }, { - "epoch": 0.89, - "learning_rate": 5.329357427918031e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.7714816223350707e-05, + "loss": 0.1388, "step": 200320 }, { - "epoch": 0.89, - "learning_rate": 5.327115375992108e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.771369768014139e-05, + "loss": 0.1423, "step": 200330 }, { - "epoch": 0.89, - "learning_rate": 5.324873324066185e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.771257913693206e-05, + "loss": 0.1393, "step": 200340 }, { - "epoch": 0.89, - "learning_rate": 5.322631272140263e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7711460593722738e-05, + "loss": 0.1415, "step": 200350 }, { - "epoch": 0.89, - "learning_rate": 5.32038922021434e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.771034205051341e-05, + "loss": 0.1401, "step": 200360 }, { - "epoch": 0.89, - "learning_rate": 5.318147168288417e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7709223507304087e-05, + "loss": 0.1431, "step": 200370 }, { - "epoch": 0.89, - "learning_rate": 5.315905116362496e-06, - "loss": 0.1317, + "epoch": 0.45, + "learning_rate": 2.7708104964094765e-05, + "loss": 0.1433, "step": 200380 }, { - "epoch": 0.89, - "learning_rate": 5.313663064436573e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.770698642088544e-05, + "loss": 0.1412, "step": 200390 }, { - "epoch": 0.89, - "learning_rate": 5.31142101251065e-06, - "loss": 0.143, + "epoch": 0.45, + "learning_rate": 2.7705867877676117e-05, + "loss": 0.1414, "step": 200400 }, { - "epoch": 0.89, - "learning_rate": 5.309178960584727e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.770474933446679e-05, + "loss": 0.1416, "step": 200410 }, { - "epoch": 0.89, - "learning_rate": 5.306936908658805e-06, - "loss": 0.1451, + "epoch": 0.45, + "learning_rate": 2.7703630791257466e-05, + "loss": 0.1429, "step": 200420 }, { - "epoch": 0.89, - "learning_rate": 5.304694856732882e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7702512248048144e-05, + "loss": 0.1416, "step": 200430 }, { - "epoch": 0.89, - "learning_rate": 5.30245280480696e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.770139370483882e-05, + "loss": 0.1404, "step": 200440 }, { - "epoch": 0.89, - "learning_rate": 5.300210752881038e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7700275161629497e-05, + "loss": 0.1389, "step": 200450 }, { - "epoch": 0.89, - "learning_rate": 5.297968700955115e-06, - "loss": 0.1413, + "epoch": 0.45, + "learning_rate": 2.7699156618420168e-05, + "loss": 0.1396, "step": 200460 }, { - "epoch": 0.89, - "learning_rate": 5.295726649029192e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.7698038075210846e-05, + "loss": 0.1452, "step": 200470 }, { - "epoch": 0.89, - "learning_rate": 5.293484597103269e-06, - "loss": 0.1387, + "epoch": 0.45, + "learning_rate": 2.7696919532001524e-05, + "loss": 0.1411, "step": 200480 }, { - "epoch": 0.9, - "learning_rate": 5.291242545177347e-06, - "loss": 0.1387, + "epoch": 0.45, + "learning_rate": 2.76958009887922e-05, + "loss": 0.1413, "step": 200490 }, { - "epoch": 0.9, - "learning_rate": 5.289000493251424e-06, - "loss": 0.1392, + "epoch": 0.45, + "learning_rate": 2.7694682445582876e-05, + "loss": 0.1423, "step": 200500 }, { - "epoch": 0.9, - "learning_rate": 5.2867584413255015e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.7693563902373547e-05, + "loss": 0.1378, "step": 200510 }, { - "epoch": 0.9, - "learning_rate": 5.284516389399579e-06, - "loss": 0.1407, + "epoch": 0.45, + "learning_rate": 2.7692445359164225e-05, + "loss": 0.1459, "step": 200520 }, { - "epoch": 0.9, - "learning_rate": 5.282274337473656e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.7691326815954903e-05, + "loss": 0.1438, "step": 200530 }, { - "epoch": 0.9, - "learning_rate": 5.280032285547733e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.7690208272745578e-05, + "loss": 0.1441, "step": 200540 }, { - "epoch": 0.9, - "learning_rate": 5.27779023362181e-06, - "loss": 0.142, + "epoch": 0.45, + "learning_rate": 2.7689089729536256e-05, + "loss": 0.1423, "step": 200550 }, { - "epoch": 0.9, - "learning_rate": 5.275548181695888e-06, - "loss": 0.1347, + "epoch": 0.45, + "learning_rate": 2.7687971186326927e-05, + "loss": 0.1421, "step": 200560 }, { - "epoch": 0.9, - "learning_rate": 5.273306129769965e-06, - "loss": 0.1405, + "epoch": 0.45, + "learning_rate": 2.7686852643117605e-05, + "loss": 0.1392, "step": 200570 }, { - "epoch": 0.9, - "learning_rate": 5.271064077844043e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.768573409990828e-05, + "loss": 0.1422, "step": 200580 }, { - "epoch": 0.9, - "learning_rate": 5.268822025918121e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.7684615556698957e-05, + "loss": 0.1409, "step": 200590 }, { - "epoch": 0.9, - "learning_rate": 5.266579973992198e-06, - "loss": 0.1366, + "epoch": 0.45, + "learning_rate": 2.7683497013489635e-05, + "loss": 0.1423, "step": 200600 }, { - "epoch": 0.9, - "learning_rate": 5.264337922066275e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.7682378470280306e-05, + "loss": 0.1419, "step": 200610 }, { - "epoch": 0.9, - "learning_rate": 5.262095870140353e-06, - "loss": 0.1375, + "epoch": 0.45, + "learning_rate": 2.7681259927070984e-05, + "loss": 0.142, "step": 200620 }, { - "epoch": 0.9, - "learning_rate": 5.25985381821443e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.768014138386166e-05, + "loss": 0.1454, "step": 200630 }, { - "epoch": 0.9, - "learning_rate": 5.257611766288507e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.7679022840652337e-05, + "loss": 0.1452, "step": 200640 }, { - "epoch": 0.9, - "learning_rate": 5.255369714362585e-06, - "loss": 0.1398, + "epoch": 0.45, + "learning_rate": 2.7677904297443015e-05, + "loss": 0.1422, "step": 200650 }, { - "epoch": 0.9, - "learning_rate": 5.253127662436663e-06, - "loss": 0.144, + "epoch": 0.45, + "learning_rate": 2.7676785754233686e-05, + "loss": 0.1416, "step": 200660 }, { - "epoch": 0.9, - "learning_rate": 5.25088561051074e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.7675667211024364e-05, + "loss": 0.1413, "step": 200670 }, { - "epoch": 0.9, - "learning_rate": 5.248643558584817e-06, - "loss": 0.1343, + "epoch": 0.45, + "learning_rate": 2.767454866781504e-05, + "loss": 0.1424, "step": 200680 }, { - "epoch": 0.9, - "learning_rate": 5.246401506658895e-06, - "loss": 0.1396, + "epoch": 0.45, + "learning_rate": 2.7673430124605716e-05, + "loss": 0.1419, "step": 200690 }, { - "epoch": 0.9, - "learning_rate": 5.244159454732972e-06, - "loss": 0.14, + "epoch": 0.45, + "learning_rate": 2.7672311581396394e-05, + "loss": 0.1407, "step": 200700 }, { - "epoch": 0.9, - "learning_rate": 5.2419174028070496e-06, - "loss": 0.134, + "epoch": 0.45, + "learning_rate": 2.7671193038187065e-05, + "loss": 0.1404, "step": 200710 }, { - "epoch": 0.9, - "learning_rate": 5.239675350881127e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.7670074494977743e-05, + "loss": 0.14, "step": 200720 }, { - "epoch": 0.9, - "learning_rate": 5.2374332989552045e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.7668955951768414e-05, + "loss": 0.1378, "step": 200730 }, { - "epoch": 0.9, - "learning_rate": 5.2351912470292815e-06, - "loss": 0.1451, + "epoch": 0.45, + "learning_rate": 2.7667837408559096e-05, + "loss": 0.1409, "step": 200740 }, { - "epoch": 0.9, - "learning_rate": 5.2329491951033585e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7666718865349774e-05, + "loss": 0.14, "step": 200750 }, { - "epoch": 0.9, - "learning_rate": 5.230707143177436e-06, - "loss": 0.1398, + "epoch": 0.45, + "learning_rate": 2.7665600322140445e-05, + "loss": 0.1394, "step": 200760 }, { - "epoch": 0.9, - "learning_rate": 5.228465091251513e-06, - "loss": 0.1379, + "epoch": 0.45, + "learning_rate": 2.7664481778931123e-05, + "loss": 0.1355, "step": 200770 }, { - "epoch": 0.9, - "learning_rate": 5.226223039325591e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7663363235721794e-05, + "loss": 0.1413, "step": 200780 }, { - "epoch": 0.9, - "learning_rate": 5.223980987399668e-06, - "loss": 0.1441, + "epoch": 0.45, + "learning_rate": 2.7662244692512472e-05, + "loss": 0.144, "step": 200790 }, { - "epoch": 0.9, - "learning_rate": 5.221738935473746e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7661126149303153e-05, + "loss": 0.1444, "step": 200800 }, { - "epoch": 0.9, - "learning_rate": 5.219496883547823e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.7660007606093824e-05, + "loss": 0.1437, "step": 200810 }, { - "epoch": 0.9, - "learning_rate": 5.2172548316219e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.7658889062884502e-05, + "loss": 0.141, "step": 200820 }, { - "epoch": 0.9, - "learning_rate": 5.215012779695978e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.7657770519675173e-05, + "loss": 0.1385, "step": 200830 }, { - "epoch": 0.9, - "learning_rate": 5.212770727770055e-06, - "loss": 0.1418, + "epoch": 0.45, + "learning_rate": 2.765665197646585e-05, + "loss": 0.1408, "step": 200840 }, { - "epoch": 0.9, - "learning_rate": 5.210528675844133e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.765553343325653e-05, + "loss": 0.1385, "step": 200850 }, { - "epoch": 0.9, - "learning_rate": 5.20828662391821e-06, - "loss": 0.1413, + "epoch": 0.45, + "learning_rate": 2.7654414890047204e-05, + "loss": 0.1396, "step": 200860 }, { - "epoch": 0.9, - "learning_rate": 5.206044571992288e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.765329634683788e-05, + "loss": 0.1395, "step": 200870 }, { - "epoch": 0.9, - "learning_rate": 5.203802520066365e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7652177803628553e-05, + "loss": 0.1388, "step": 200880 }, { - "epoch": 0.9, - "learning_rate": 5.201560468140442e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.765105926041923e-05, + "loss": 0.1412, "step": 200890 }, { - "epoch": 0.9, - "learning_rate": 5.19931841621452e-06, - "loss": 0.1378, + "epoch": 0.45, + "learning_rate": 2.7649940717209905e-05, + "loss": 0.1377, "step": 200900 }, { - "epoch": 0.9, - "learning_rate": 5.197076364288597e-06, - "loss": 0.1395, + "epoch": 0.45, + "learning_rate": 2.7648822174000583e-05, + "loss": 0.14, "step": 200910 }, { - "epoch": 0.9, - "learning_rate": 5.194834312362675e-06, - "loss": 0.1418, + "epoch": 0.45, + "learning_rate": 2.764770363079126e-05, + "loss": 0.1435, "step": 200920 }, { - "epoch": 0.9, - "learning_rate": 5.192592260436752e-06, - "loss": 0.1426, + "epoch": 0.45, + "learning_rate": 2.7646585087581932e-05, + "loss": 0.1414, "step": 200930 }, { - "epoch": 0.9, - "learning_rate": 5.19035020851083e-06, - "loss": 0.1412, + "epoch": 0.45, + "learning_rate": 2.764546654437261e-05, + "loss": 0.1423, "step": 200940 }, { - "epoch": 0.9, - "learning_rate": 5.188108156584907e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7644348001163285e-05, + "loss": 0.1404, "step": 200950 }, { - "epoch": 0.9, - "learning_rate": 5.185866104658984e-06, - "loss": 0.1424, + "epoch": 0.45, + "learning_rate": 2.7643229457953963e-05, + "loss": 0.1485, "step": 200960 }, { - "epoch": 0.9, - "learning_rate": 5.1836240527330615e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.764211091474464e-05, + "loss": 0.1379, "step": 200970 }, { - "epoch": 0.9, - "learning_rate": 5.181382000807139e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.7640992371535312e-05, + "loss": 0.1424, "step": 200980 }, { - "epoch": 0.9, - "learning_rate": 5.179139948881216e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.763987382832599e-05, + "loss": 0.1403, "step": 200990 }, { - "epoch": 0.9, - "learning_rate": 5.176897896955294e-06, - "loss": 0.1362, + "epoch": 0.45, + "learning_rate": 2.7638755285116664e-05, + "loss": 0.1399, "step": 201000 }, { - "epoch": 0.9, - "learning_rate": 5.174655845029371e-06, - "loss": 0.1322, + "epoch": 0.45, + "learning_rate": 2.7637636741907342e-05, + "loss": 0.1387, "step": 201010 }, { - "epoch": 0.9, - "learning_rate": 5.172413793103448e-06, - "loss": 0.1433, + "epoch": 0.45, + "learning_rate": 2.763651819869802e-05, + "loss": 0.1368, "step": 201020 }, { - "epoch": 0.9, - "learning_rate": 5.170171741177525e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.763539965548869e-05, + "loss": 0.1446, "step": 201030 }, { - "epoch": 0.9, - "learning_rate": 5.167929689251603e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.763428111227937e-05, + "loss": 0.137, "step": 201040 }, { - "epoch": 0.9, - "learning_rate": 5.165687637325681e-06, - "loss": 0.1392, + "epoch": 0.45, + "learning_rate": 2.7633162569070044e-05, + "loss": 0.1401, "step": 201050 }, { - "epoch": 0.9, - "learning_rate": 5.163445585399758e-06, - "loss": 0.1404, + "epoch": 0.45, + "learning_rate": 2.763204402586072e-05, + "loss": 0.1369, "step": 201060 }, { - "epoch": 0.9, - "learning_rate": 5.161203533473836e-06, - "loss": 0.1332, + "epoch": 0.45, + "learning_rate": 2.76309254826514e-05, + "loss": 0.1378, "step": 201070 }, { - "epoch": 0.9, - "learning_rate": 5.158961481547913e-06, - "loss": 0.1379, + "epoch": 0.45, + "learning_rate": 2.762980693944207e-05, + "loss": 0.1445, "step": 201080 }, { - "epoch": 0.9, - "learning_rate": 5.15671942962199e-06, - "loss": 0.1435, + "epoch": 0.45, + "learning_rate": 2.762868839623275e-05, + "loss": 0.1378, "step": 201090 }, { - "epoch": 0.9, - "learning_rate": 5.154477377696067e-06, - "loss": 0.1423, + "epoch": 0.45, + "learning_rate": 2.7627569853023423e-05, + "loss": 0.142, "step": 201100 }, { - "epoch": 0.9, - "learning_rate": 5.152235325770145e-06, - "loss": 0.1401, + "epoch": 0.45, + "learning_rate": 2.76264513098141e-05, + "loss": 0.138, "step": 201110 }, { - "epoch": 0.9, - "learning_rate": 5.149993273844223e-06, - "loss": 0.1434, + "epoch": 0.45, + "learning_rate": 2.762533276660478e-05, + "loss": 0.1362, "step": 201120 }, { - "epoch": 0.9, - "learning_rate": 5.1477512219183e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.762421422339545e-05, + "loss": 0.14, "step": 201130 }, { - "epoch": 0.9, - "learning_rate": 5.145509169992378e-06, - "loss": 0.1429, + "epoch": 0.45, + "learning_rate": 2.7623095680186128e-05, + "loss": 0.1409, "step": 201140 }, { - "epoch": 0.9, - "learning_rate": 5.143267118066455e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.7621977136976803e-05, + "loss": 0.1466, "step": 201150 }, { - "epoch": 0.9, - "learning_rate": 5.141025066140532e-06, - "loss": 0.1404, + "epoch": 0.45, + "learning_rate": 2.762085859376748e-05, + "loss": 0.1425, "step": 201160 }, { - "epoch": 0.9, - "learning_rate": 5.138783014214609e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.7619740050558152e-05, + "loss": 0.1401, "step": 201170 }, { - "epoch": 0.9, - "learning_rate": 5.136540962288687e-06, - "loss": 0.1325, + "epoch": 0.45, + "learning_rate": 2.761862150734883e-05, + "loss": 0.1432, "step": 201180 }, { - "epoch": 0.9, - "learning_rate": 5.1342989103627645e-06, - "loss": 0.135, + "epoch": 0.45, + "learning_rate": 2.7617502964139508e-05, + "loss": 0.1391, "step": 201190 }, { - "epoch": 0.9, - "learning_rate": 5.1320568584368415e-06, - "loss": 0.1352, + "epoch": 0.45, + "learning_rate": 2.761638442093018e-05, + "loss": 0.1325, "step": 201200 }, { - "epoch": 0.9, - "learning_rate": 5.129814806510919e-06, - "loss": 0.1427, + "epoch": 0.45, + "learning_rate": 2.7615265877720857e-05, + "loss": 0.1393, "step": 201210 }, { - "epoch": 0.9, - "learning_rate": 5.127572754584996e-06, - "loss": 0.1412, + "epoch": 0.45, + "learning_rate": 2.761414733451153e-05, + "loss": 0.1433, "step": 201220 }, { - "epoch": 0.9, - "learning_rate": 5.1253307026590734e-06, - "loss": 0.1441, + "epoch": 0.45, + "learning_rate": 2.761302879130221e-05, + "loss": 0.1442, "step": 201230 }, { - "epoch": 0.9, - "learning_rate": 5.123088650733151e-06, - "loss": 0.1459, + "epoch": 0.45, + "learning_rate": 2.7611910248092887e-05, + "loss": 0.139, "step": 201240 }, { - "epoch": 0.9, - "learning_rate": 5.120846598807229e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.7610791704883558e-05, + "loss": 0.1393, "step": 201250 }, { - "epoch": 0.9, - "learning_rate": 5.118604546881306e-06, - "loss": 0.1415, + "epoch": 0.45, + "learning_rate": 2.7609673161674236e-05, + "loss": 0.139, "step": 201260 }, { - "epoch": 0.9, - "learning_rate": 5.116362494955383e-06, + "epoch": 0.45, + "learning_rate": 2.7608666472785845e-05, "loss": 0.142, "step": 201270 }, { - "epoch": 0.9, - "learning_rate": 5.114120443029461e-06, - "loss": 0.1327, + "epoch": 0.45, + "learning_rate": 2.7607547929576523e-05, + "loss": 0.137, "step": 201280 }, { - "epoch": 0.9, - "learning_rate": 5.111878391103538e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7606429386367194e-05, + "loss": 0.145, "step": 201290 }, { - "epoch": 0.9, - "learning_rate": 5.109636339177615e-06, - "loss": 0.1366, + "epoch": 0.45, + "learning_rate": 2.7605310843157872e-05, + "loss": 0.1405, "step": 201300 }, { - "epoch": 0.9, - "learning_rate": 5.107394287251693e-06, - "loss": 0.1329, + "epoch": 0.45, + "learning_rate": 2.760419229994855e-05, + "loss": 0.1395, "step": 201310 }, { - "epoch": 0.9, - "learning_rate": 5.105152235325771e-06, - "loss": 0.1396, + "epoch": 0.45, + "learning_rate": 2.7603073756739224e-05, + "loss": 0.1393, "step": 201320 }, { - "epoch": 0.9, - "learning_rate": 5.102910183399848e-06, - "loss": 0.1355, + "epoch": 0.45, + "learning_rate": 2.7601955213529902e-05, + "loss": 0.14, "step": 201330 }, { - "epoch": 0.9, - "learning_rate": 5.100668131473925e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7600836670320574e-05, + "loss": 0.1375, "step": 201340 }, { - "epoch": 0.9, - "learning_rate": 5.098426079548003e-06, - "loss": 0.1435, + "epoch": 0.45, + "learning_rate": 2.759971812711125e-05, + "loss": 0.1465, "step": 201350 }, { - "epoch": 0.9, - "learning_rate": 5.09618402762208e-06, - "loss": 0.1422, + "epoch": 0.45, + "learning_rate": 2.759859958390193e-05, + "loss": 0.1364, "step": 201360 }, { - "epoch": 0.9, - "learning_rate": 5.093941975696157e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.75974810406926e-05, + "loss": 0.1441, "step": 201370 }, { - "epoch": 0.9, - "learning_rate": 5.091699923770235e-06, - "loss": 0.1424, + "epoch": 0.45, + "learning_rate": 2.7596362497483282e-05, + "loss": 0.1404, "step": 201380 }, { - "epoch": 0.9, - "learning_rate": 5.089457871844313e-06, - "loss": 0.1332, + "epoch": 0.45, + "learning_rate": 2.7595243954273953e-05, + "loss": 0.137, "step": 201390 }, { - "epoch": 0.9, - "learning_rate": 5.08721581991839e-06, - "loss": 0.1438, + "epoch": 0.45, + "learning_rate": 2.759412541106463e-05, + "loss": 0.1433, "step": 201400 }, { - "epoch": 0.9, - "learning_rate": 5.084973767992467e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.759300686785531e-05, + "loss": 0.1418, "step": 201410 }, { - "epoch": 0.9, - "learning_rate": 5.0827317160665445e-06, - "loss": 0.1423, + "epoch": 0.45, + "learning_rate": 2.759188832464598e-05, + "loss": 0.1415, "step": 201420 }, { - "epoch": 0.9, - "learning_rate": 5.0804896641406215e-06, - "loss": 0.141, + "epoch": 0.45, + "learning_rate": 2.7590769781436658e-05, + "loss": 0.1403, "step": 201430 }, { - "epoch": 0.9, - "learning_rate": 5.0782476122146986e-06, - "loss": 0.1403, + "epoch": 0.45, + "learning_rate": 2.7589651238227332e-05, + "loss": 0.1426, "step": 201440 }, { - "epoch": 0.9, - "learning_rate": 5.0760055602887764e-06, - "loss": 0.1397, + "epoch": 0.45, + "learning_rate": 2.758853269501801e-05, + "loss": 0.1354, "step": 201450 }, { - "epoch": 0.9, - "learning_rate": 5.073763508362854e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.7587414151808688e-05, + "loss": 0.1383, "step": 201460 }, { - "epoch": 0.9, - "learning_rate": 5.071521456436931e-06, - "loss": 0.1338, + "epoch": 0.45, + "learning_rate": 2.758629560859936e-05, + "loss": 0.1395, "step": 201470 }, { - "epoch": 0.9, - "learning_rate": 5.069279404511008e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.7585177065390037e-05, + "loss": 0.1344, "step": 201480 }, { - "epoch": 0.9, - "learning_rate": 5.067037352585086e-06, - "loss": 0.1381, + "epoch": 0.45, + "learning_rate": 2.7584058522180712e-05, + "loss": 0.1421, "step": 201490 }, { - "epoch": 0.9, - "learning_rate": 5.064795300659163e-06, - "loss": 0.1434, + "epoch": 0.45, + "learning_rate": 2.758293997897139e-05, + "loss": 0.1362, "step": 201500 }, { - "epoch": 0.9, - "learning_rate": 5.06255324873324e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7581821435762068e-05, + "loss": 0.1422, "step": 201510 }, { - "epoch": 0.9, - "learning_rate": 5.060311196807319e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.758070289255274e-05, + "loss": 0.1439, "step": 201520 }, { - "epoch": 0.9, - "learning_rate": 5.058069144881396e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7579584349343417e-05, + "loss": 0.1409, "step": 201530 }, { - "epoch": 0.9, - "learning_rate": 5.055827092955473e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.757846580613409e-05, + "loss": 0.1466, "step": 201540 }, { - "epoch": 0.9, - "learning_rate": 5.05358504102955e-06, - "loss": 0.1378, + "epoch": 0.45, + "learning_rate": 2.757734726292477e-05, + "loss": 0.1391, "step": 201550 }, { - "epoch": 0.9, - "learning_rate": 5.051342989103628e-06, - "loss": 0.1396, + "epoch": 0.45, + "learning_rate": 2.757622871971544e-05, + "loss": 0.1413, "step": 201560 }, { - "epoch": 0.9, - "learning_rate": 5.049100937177705e-06, - "loss": 0.145, + "epoch": 0.45, + "learning_rate": 2.757511017650612e-05, + "loss": 0.1434, "step": 201570 }, { - "epoch": 0.9, - "learning_rate": 5.046858885251783e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.7573991633296796e-05, + "loss": 0.1401, "step": 201580 }, { - "epoch": 0.9, - "learning_rate": 5.044616833325861e-06, - "loss": 0.146, + "epoch": 0.45, + "learning_rate": 2.757287309008747e-05, + "loss": 0.1419, "step": 201590 }, { - "epoch": 0.9, - "learning_rate": 5.042374781399938e-06, - "loss": 0.1429, + "epoch": 0.45, + "learning_rate": 2.757175454687815e-05, + "loss": 0.1411, "step": 201600 }, { - "epoch": 0.9, - "learning_rate": 5.040132729474015e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.757063600366882e-05, + "loss": 0.1398, "step": 201610 }, { - "epoch": 0.9, - "learning_rate": 5.037890677548092e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7569517460459498e-05, + "loss": 0.1394, "step": 201620 }, { - "epoch": 0.9, - "learning_rate": 5.03564862562217e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.7568398917250176e-05, + "loss": 0.1454, "step": 201630 }, { - "epoch": 0.9, - "learning_rate": 5.033406573696247e-06, - "loss": 0.142, + "epoch": 0.45, + "learning_rate": 2.756728037404085e-05, + "loss": 0.1359, "step": 201640 }, { - "epoch": 0.9, - "learning_rate": 5.0311645217703245e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7566161830831528e-05, + "loss": 0.1413, "step": 201650 }, { - "epoch": 0.9, - "learning_rate": 5.028922469844402e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.75650432876222e-05, + "loss": 0.1392, "step": 201660 }, { - "epoch": 0.9, - "learning_rate": 5.026680417918479e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.7563924744412877e-05, + "loss": 0.138, "step": 201670 }, { - "epoch": 0.9, - "learning_rate": 5.0244383659925564e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.7562806201203555e-05, + "loss": 0.14, "step": 201680 }, { - "epoch": 0.9, - "learning_rate": 5.022196314066634e-06, - "loss": 0.1407, + "epoch": 0.45, + "learning_rate": 2.756168765799423e-05, + "loss": 0.146, "step": 201690 }, { - "epoch": 0.9, - "learning_rate": 5.019954262140711e-06, - "loss": 0.1421, + "epoch": 0.45, + "learning_rate": 2.7560569114784908e-05, + "loss": 0.1398, "step": 201700 }, { - "epoch": 0.9, - "learning_rate": 5.017712210214788e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.755945057157558e-05, + "loss": 0.1397, "step": 201710 }, { - "epoch": 0.9, - "learning_rate": 5.015470158288866e-06, - "loss": 0.1424, + "epoch": 0.45, + "learning_rate": 2.7558332028366257e-05, + "loss": 0.1409, "step": 201720 }, { - "epoch": 0.9, - "learning_rate": 5.013228106362944e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.7557213485156935e-05, + "loss": 0.1428, "step": 201730 }, { - "epoch": 0.9, - "learning_rate": 5.010986054437021e-06, - "loss": 0.1412, + "epoch": 0.45, + "learning_rate": 2.755609494194761e-05, + "loss": 0.1437, "step": 201740 }, { - "epoch": 0.9, - "learning_rate": 5.008744002511098e-06, - "loss": 0.1387, + "epoch": 0.45, + "learning_rate": 2.7554976398738287e-05, + "loss": 0.1353, "step": 201750 }, { - "epoch": 0.9, - "learning_rate": 5.006501950585176e-06, - "loss": 0.1387, + "epoch": 0.45, + "learning_rate": 2.755385785552896e-05, + "loss": 0.141, "step": 201760 }, { - "epoch": 0.9, - "learning_rate": 5.004259898659253e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.7552739312319636e-05, + "loss": 0.1378, "step": 201770 }, { - "epoch": 0.9, - "learning_rate": 5.00201784673333e-06, - "loss": 0.1435, + "epoch": 0.45, + "learning_rate": 2.7551620769110314e-05, + "loss": 0.143, "step": 201780 }, { - "epoch": 0.9, - "learning_rate": 4.999775794807408e-06, - "loss": 0.1407, + "epoch": 0.45, + "learning_rate": 2.7550502225900985e-05, + "loss": 0.1441, "step": 201790 }, { - "epoch": 0.9, - "learning_rate": 4.997533742881486e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.7549383682691667e-05, + "loss": 0.1405, "step": 201800 }, { - "epoch": 0.9, - "learning_rate": 4.995291690955563e-06, - "loss": 0.1413, + "epoch": 0.45, + "learning_rate": 2.7548265139482338e-05, + "loss": 0.1471, "step": 201810 }, { - "epoch": 0.9, - "learning_rate": 4.99304963902964e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7547146596273016e-05, + "loss": 0.144, "step": 201820 }, { - "epoch": 0.9, - "learning_rate": 4.990807587103718e-06, - "loss": 0.1431, + "epoch": 0.45, + "learning_rate": 2.7546028053063694e-05, + "loss": 0.1357, "step": 201830 }, { - "epoch": 0.9, - "learning_rate": 4.988565535177795e-06, - "loss": 0.1333, + "epoch": 0.45, + "learning_rate": 2.7544909509854365e-05, + "loss": 0.1332, "step": 201840 }, { - "epoch": 0.9, - "learning_rate": 4.986323483251873e-06, - "loss": 0.1357, + "epoch": 0.45, + "learning_rate": 2.7543790966645043e-05, + "loss": 0.1451, "step": 201850 }, { - "epoch": 0.9, - "learning_rate": 4.98408143132595e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.7542672423435717e-05, + "loss": 0.1376, "step": 201860 }, { - "epoch": 0.9, - "learning_rate": 4.9818393794000275e-06, - "loss": 0.1433, + "epoch": 0.45, + "learning_rate": 2.7541553880226395e-05, + "loss": 0.1407, "step": 201870 }, { - "epoch": 0.9, - "learning_rate": 4.9795973274741045e-06, - "loss": 0.1366, + "epoch": 0.45, + "learning_rate": 2.7540435337017066e-05, + "loss": 0.1391, "step": 201880 }, { - "epoch": 0.9, - "learning_rate": 4.9773552755481816e-06, - "loss": 0.133, + "epoch": 0.45, + "learning_rate": 2.7539316793807744e-05, + "loss": 0.1424, "step": 201890 }, { - "epoch": 0.9, - "learning_rate": 4.9751132236222594e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.7538198250598422e-05, + "loss": 0.1385, "step": 201900 }, { - "epoch": 0.9, - "learning_rate": 4.9728711716963365e-06, - "loss": 0.1376, + "epoch": 0.45, + "learning_rate": 2.7537079707389097e-05, + "loss": 0.1432, "step": 201910 }, { - "epoch": 0.9, - "learning_rate": 4.970629119770414e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.7535961164179775e-05, + "loss": 0.1383, "step": 201920 }, { - "epoch": 0.9, - "learning_rate": 4.968387067844491e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7534842620970446e-05, + "loss": 0.1415, "step": 201930 }, { - "epoch": 0.9, - "learning_rate": 4.966145015918569e-06, - "loss": 0.1362, + "epoch": 0.45, + "learning_rate": 2.7533724077761124e-05, + "loss": 0.1422, "step": 201940 }, { - "epoch": 0.9, - "learning_rate": 4.963902963992646e-06, - "loss": 0.133, + "epoch": 0.45, + "learning_rate": 2.7532605534551802e-05, + "loss": 0.1448, "step": 201950 }, { - "epoch": 0.9, - "learning_rate": 4.961660912066723e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.7531486991342476e-05, + "loss": 0.1435, "step": 201960 }, { - "epoch": 0.9, - "learning_rate": 4.959418860140801e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.7530368448133154e-05, + "loss": 0.1426, "step": 201970 }, { - "epoch": 0.9, - "learning_rate": 4.957176808214878e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7529249904923825e-05, + "loss": 0.1389, "step": 201980 }, { - "epoch": 0.9, - "learning_rate": 4.954934756288956e-06, - "loss": 0.1374, + "epoch": 0.45, + "learning_rate": 2.7528131361714503e-05, + "loss": 0.1364, "step": 201990 }, { - "epoch": 0.9, - "learning_rate": 4.952692704363034e-06, - "loss": 0.14, + "epoch": 0.45, + "learning_rate": 2.752701281850518e-05, + "loss": 0.1373, "step": 202000 }, { - "epoch": 0.9, - "learning_rate": 4.950450652437111e-06, - "loss": 0.1389, + "epoch": 0.45, + "learning_rate": 2.7525894275295856e-05, + "loss": 0.1421, "step": 202010 }, { - "epoch": 0.9, - "learning_rate": 4.948208600511188e-06, - "loss": 0.1454, + "epoch": 0.45, + "learning_rate": 2.7524775732086534e-05, + "loss": 0.139, "step": 202020 }, { - "epoch": 0.9, - "learning_rate": 4.945966548585265e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.7523657188877205e-05, + "loss": 0.1421, "step": 202030 }, { - "epoch": 0.9, - "learning_rate": 4.943724496659343e-06, - "loss": 0.1335, + "epoch": 0.45, + "learning_rate": 2.7522538645667883e-05, + "loss": 0.1419, "step": 202040 }, { - "epoch": 0.9, - "learning_rate": 4.94148244473342e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.752142010245856e-05, + "loss": 0.1431, "step": 202050 }, { - "epoch": 0.9, - "learning_rate": 4.939240392807498e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.7520301559249235e-05, + "loss": 0.1407, "step": 202060 }, { - "epoch": 0.9, - "learning_rate": 4.936998340881576e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.7519183016039913e-05, + "loss": 0.1388, "step": 202070 }, { - "epoch": 0.9, - "learning_rate": 4.934756288955653e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.7518064472830584e-05, + "loss": 0.142, "step": 202080 }, { - "epoch": 0.9, - "learning_rate": 4.93251423702973e-06, - "loss": 0.1446, + "epoch": 0.45, + "learning_rate": 2.7516945929621262e-05, + "loss": 0.1377, "step": 202090 }, { - "epoch": 0.9, - "learning_rate": 4.930272185103807e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.751582738641194e-05, + "loss": 0.1359, "step": 202100 }, { - "epoch": 0.9, - "learning_rate": 4.9280301331778846e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.7514708843202615e-05, + "loss": 0.1398, "step": 202110 }, { - "epoch": 0.9, - "learning_rate": 4.9257880812519624e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7513590299993293e-05, + "loss": 0.1397, "step": 202120 }, { - "epoch": 0.9, - "learning_rate": 4.9235460293260395e-06, - "loss": 0.1362, + "epoch": 0.45, + "learning_rate": 2.7512471756783964e-05, + "loss": 0.142, "step": 202130 }, { - "epoch": 0.9, - "learning_rate": 4.921303977400117e-06, - "loss": 0.1353, + "epoch": 0.45, + "learning_rate": 2.7511353213574642e-05, + "loss": 0.1389, "step": 202140 }, { - "epoch": 0.9, - "learning_rate": 4.919061925474194e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.751023467036532e-05, + "loss": 0.1389, "step": 202150 }, { - "epoch": 0.9, - "learning_rate": 4.916819873548271e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.7509116127155994e-05, + "loss": 0.1391, "step": 202160 }, { - "epoch": 0.9, - "learning_rate": 4.914577821622348e-06, - "loss": 0.1344, + "epoch": 0.45, + "learning_rate": 2.7507997583946672e-05, + "loss": 0.1386, "step": 202170 }, { - "epoch": 0.9, - "learning_rate": 4.912335769696426e-06, - "loss": 0.1302, + "epoch": 0.45, + "learning_rate": 2.7506879040737343e-05, + "loss": 0.1331, "step": 202180 }, { - "epoch": 0.9, - "learning_rate": 4.910093717770504e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.750576049752802e-05, + "loss": 0.1398, "step": 202190 }, { - "epoch": 0.9, - "learning_rate": 4.907851665844581e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.7504641954318692e-05, + "loss": 0.1404, "step": 202200 }, { - "epoch": 0.9, - "learning_rate": 4.905609613918659e-06, - "loss": 0.1426, + "epoch": 0.45, + "learning_rate": 2.7503523411109374e-05, + "loss": 0.1332, "step": 202210 }, { - "epoch": 0.9, - "learning_rate": 4.903367561992736e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.750240486790005e-05, + "loss": 0.1376, "step": 202220 }, { - "epoch": 0.9, - "learning_rate": 4.901125510066813e-06, - "loss": 0.139, + "epoch": 0.45, + "learning_rate": 2.7501286324690723e-05, + "loss": 0.1402, "step": 202230 }, { - "epoch": 0.9, - "learning_rate": 4.89888345814089e-06, - "loss": 0.14, + "epoch": 0.45, + "learning_rate": 2.75001677814814e-05, + "loss": 0.1387, "step": 202240 }, { - "epoch": 0.9, - "learning_rate": 4.8968656114075604e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.7499049238272072e-05, + "loss": 0.1427, "step": 202250 }, { - "epoch": 0.9, - "learning_rate": 4.8946235594816375e-06, + "epoch": 0.45, + "learning_rate": 2.749793069506275e-05, "loss": 0.1364, "step": 202260 }, { - "epoch": 0.9, - "learning_rate": 4.892381507555715e-06, - "loss": 0.1355, + "epoch": 0.45, + "learning_rate": 2.749681215185343e-05, + "loss": 0.1401, "step": 202270 }, { - "epoch": 0.9, - "learning_rate": 4.890139455629792e-06, - "loss": 0.132, + "epoch": 0.45, + "learning_rate": 2.7495693608644102e-05, + "loss": 0.1457, "step": 202280 }, { - "epoch": 0.9, - "learning_rate": 4.88789740370387e-06, - "loss": 0.1374, + "epoch": 0.45, + "learning_rate": 2.749457506543478e-05, + "loss": 0.1441, "step": 202290 }, { - "epoch": 0.9, - "learning_rate": 4.885655351777947e-06, - "loss": 0.1343, + "epoch": 0.45, + "learning_rate": 2.749345652222545e-05, + "loss": 0.1414, "step": 202300 }, { - "epoch": 0.9, - "learning_rate": 4.883413299852025e-06, - "loss": 0.1403, + "epoch": 0.45, + "learning_rate": 2.749233797901613e-05, + "loss": 0.1404, "step": 202310 }, { - "epoch": 0.9, - "learning_rate": 4.881171247926102e-06, - "loss": 0.1395, + "epoch": 0.45, + "learning_rate": 2.7491219435806807e-05, + "loss": 0.142, "step": 202320 }, { - "epoch": 0.9, - "learning_rate": 4.878929196000179e-06, - "loss": 0.1404, + "epoch": 0.45, + "learning_rate": 2.749010089259748e-05, + "loss": 0.1324, "step": 202330 }, { - "epoch": 0.9, - "learning_rate": 4.876687144074257e-06, - "loss": 0.1411, + "epoch": 0.45, + "learning_rate": 2.748898234938816e-05, + "loss": 0.1442, "step": 202340 }, { - "epoch": 0.9, - "learning_rate": 4.874445092148335e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.748786380617883e-05, + "loss": 0.1429, "step": 202350 }, { - "epoch": 0.9, - "learning_rate": 4.872203040222412e-06, - "loss": 0.1414, + "epoch": 0.45, + "learning_rate": 2.748674526296951e-05, + "loss": 0.1465, "step": 202360 }, { - "epoch": 0.9, - "learning_rate": 4.869960988296489e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7485626719760187e-05, + "loss": 0.1365, "step": 202370 }, { - "epoch": 0.9, - "learning_rate": 4.867718936370567e-06, - "loss": 0.1386, + "epoch": 0.45, + "learning_rate": 2.748450817655086e-05, + "loss": 0.137, "step": 202380 }, { - "epoch": 0.9, - "learning_rate": 4.865476884444644e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.748338963334154e-05, + "loss": 0.1396, "step": 202390 }, { - "epoch": 0.9, - "learning_rate": 4.863234832518721e-06, - "loss": 0.1364, + "epoch": 0.45, + "learning_rate": 2.748227109013221e-05, + "loss": 0.1357, "step": 202400 }, { - "epoch": 0.9, - "learning_rate": 4.860992780592799e-06, - "loss": 0.1345, + "epoch": 0.45, + "learning_rate": 2.7481152546922888e-05, + "loss": 0.1394, "step": 202410 }, { - "epoch": 0.9, - "learning_rate": 4.858750728666877e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.7480034003713566e-05, + "loss": 0.1435, "step": 202420 }, { - "epoch": 0.9, - "learning_rate": 4.856508676740954e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.747891546050424e-05, + "loss": 0.1397, "step": 202430 }, { - "epoch": 0.9, - "learning_rate": 4.854266624815031e-06, - "loss": 0.1373, + "epoch": 0.45, + "learning_rate": 2.747779691729492e-05, + "loss": 0.1433, "step": 202440 }, { - "epoch": 0.9, - "learning_rate": 4.8520245728891085e-06, - "loss": 0.1401, + "epoch": 0.45, + "learning_rate": 2.747667837408559e-05, + "loss": 0.1407, "step": 202450 }, { - "epoch": 0.9, - "learning_rate": 4.8497825209631856e-06, - "loss": 0.1349, + "epoch": 0.45, + "learning_rate": 2.7475559830876268e-05, + "loss": 0.1404, "step": 202460 }, { - "epoch": 0.9, - "learning_rate": 4.847540469037263e-06, - "loss": 0.1425, + "epoch": 0.45, + "learning_rate": 2.7474441287666946e-05, + "loss": 0.1338, "step": 202470 }, { - "epoch": 0.9, - "learning_rate": 4.8452984171113405e-06, - "loss": 0.1422, + "epoch": 0.45, + "learning_rate": 2.747332274445762e-05, + "loss": 0.1345, "step": 202480 }, { - "epoch": 0.9, - "learning_rate": 4.843056365185418e-06, - "loss": 0.1425, + "epoch": 0.45, + "learning_rate": 2.7472204201248298e-05, + "loss": 0.1417, "step": 202490 }, { - "epoch": 0.9, - "learning_rate": 4.840814313259495e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.747108565803897e-05, + "loss": 0.1414, "step": 202500 }, { - "epoch": 0.9, - "learning_rate": 4.838572261333572e-06, - "loss": 0.1342, + "epoch": 0.45, + "learning_rate": 2.7469967114829647e-05, + "loss": 0.1417, "step": 202510 }, { - "epoch": 0.9, - "learning_rate": 4.83633020940765e-06, - "loss": 0.1416, + "epoch": 0.45, + "learning_rate": 2.746884857162032e-05, + "loss": 0.1417, "step": 202520 }, { - "epoch": 0.9, - "learning_rate": 4.834088157481727e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7467730028411e-05, + "loss": 0.1334, "step": 202530 }, { - "epoch": 0.9, - "learning_rate": 4.831846105555804e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7466611485201677e-05, + "loss": 0.1372, "step": 202540 }, { - "epoch": 0.9, - "learning_rate": 4.829604053629882e-06, - "loss": 0.1372, + "epoch": 0.45, + "learning_rate": 2.746549294199235e-05, + "loss": 0.1361, "step": 202550 }, { - "epoch": 0.9, - "learning_rate": 4.82736200170396e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7464374398783027e-05, + "loss": 0.1361, "step": 202560 }, { - "epoch": 0.9, - "learning_rate": 4.825119949778037e-06, - "loss": 0.145, + "epoch": 0.45, + "learning_rate": 2.74632558555737e-05, + "loss": 0.1395, "step": 202570 }, { - "epoch": 0.9, - "learning_rate": 4.822877897852115e-06, - "loss": 0.1438, + "epoch": 0.45, + "learning_rate": 2.746213731236438e-05, + "loss": 0.1396, "step": 202580 }, { - "epoch": 0.9, - "learning_rate": 4.820635845926192e-06, - "loss": 0.1338, + "epoch": 0.45, + "learning_rate": 2.7461018769155057e-05, + "loss": 0.141, "step": 202590 }, { - "epoch": 0.9, - "learning_rate": 4.818393794000269e-06, - "loss": 0.1448, + "epoch": 0.45, + "learning_rate": 2.7459900225945728e-05, + "loss": 0.1394, "step": 202600 }, { - "epoch": 0.9, - "learning_rate": 4.816151742074346e-06, - "loss": 0.1414, + "epoch": 0.45, + "learning_rate": 2.7458781682736406e-05, + "loss": 0.1394, "step": 202610 }, { - "epoch": 0.9, - "learning_rate": 4.813909690148425e-06, - "loss": 0.1352, + "epoch": 0.45, + "learning_rate": 2.745766313952708e-05, + "loss": 0.142, "step": 202620 }, { - "epoch": 0.9, - "learning_rate": 4.811667638222502e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.745654459631776e-05, + "loss": 0.1377, "step": 202630 }, { - "epoch": 0.9, - "learning_rate": 4.809425586296579e-06, - "loss": 0.1346, + "epoch": 0.45, + "learning_rate": 2.7455426053108436e-05, + "loss": 0.1398, "step": 202640 }, { - "epoch": 0.9, - "learning_rate": 4.807183534370657e-06, - "loss": 0.1422, + "epoch": 0.45, + "learning_rate": 2.7454307509899108e-05, + "loss": 0.1352, "step": 202650 }, { - "epoch": 0.9, - "learning_rate": 4.804941482444734e-06, - "loss": 0.142, + "epoch": 0.45, + "learning_rate": 2.7453188966689786e-05, + "loss": 0.1407, "step": 202660 }, { - "epoch": 0.9, - "learning_rate": 4.802699430518811e-06, - "loss": 0.1394, + "epoch": 0.45, + "learning_rate": 2.7452070423480457e-05, + "loss": 0.1427, "step": 202670 }, { - "epoch": 0.9, - "learning_rate": 4.8004573785928886e-06, - "loss": 0.1426, + "epoch": 0.45, + "learning_rate": 2.7450951880271138e-05, + "loss": 0.1412, "step": 202680 }, { - "epoch": 0.9, - "learning_rate": 4.798215326666966e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.7449833337061816e-05, + "loss": 0.1352, "step": 202690 }, { - "epoch": 0.9, - "learning_rate": 4.7959732747410434e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.7448714793852487e-05, + "loss": 0.1345, "step": 202700 }, { - "epoch": 0.9, - "learning_rate": 4.7937312228151205e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.7447596250643165e-05, + "loss": 0.1416, "step": 202710 }, { - "epoch": 0.9, - "learning_rate": 4.791489170889198e-06, - "loss": 0.1391, + "epoch": 0.45, + "learning_rate": 2.7446477707433836e-05, + "loss": 0.1422, "step": 202720 }, { - "epoch": 0.91, - "learning_rate": 4.789247118963275e-06, - "loss": 0.1373, + "epoch": 0.45, + "learning_rate": 2.7445359164224514e-05, + "loss": 0.1466, "step": 202730 }, { - "epoch": 0.91, - "learning_rate": 4.787005067037352e-06, - "loss": 0.1405, + "epoch": 0.45, + "learning_rate": 2.7444240621015192e-05, + "loss": 0.1376, "step": 202740 }, { - "epoch": 0.91, - "learning_rate": 4.78476301511143e-06, - "loss": 0.1335, + "epoch": 0.45, + "learning_rate": 2.7443122077805867e-05, + "loss": 0.1375, "step": 202750 }, { - "epoch": 0.91, - "learning_rate": 4.782520963185508e-06, - "loss": 0.1374, + "epoch": 0.45, + "learning_rate": 2.7442003534596544e-05, + "loss": 0.1439, "step": 202760 }, { - "epoch": 0.91, - "learning_rate": 4.780278911259585e-06, - "loss": 0.1349, + "epoch": 0.45, + "learning_rate": 2.7440884991387216e-05, + "loss": 0.1384, "step": 202770 }, { - "epoch": 0.91, - "learning_rate": 4.778036859333662e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.7439766448177894e-05, + "loss": 0.1421, "step": 202780 }, { - "epoch": 0.91, - "learning_rate": 4.77579480740774e-06, - "loss": 0.1374, + "epoch": 0.45, + "learning_rate": 2.743864790496857e-05, + "loss": 0.1361, "step": 202790 }, { - "epoch": 0.91, - "learning_rate": 4.773552755481817e-06, - "loss": 0.1389, + "epoch": 0.45, + "learning_rate": 2.7437529361759246e-05, + "loss": 0.1383, "step": 202800 }, { - "epoch": 0.91, - "learning_rate": 4.771310703555894e-06, - "loss": 0.1375, + "epoch": 0.45, + "learning_rate": 2.7436410818549924e-05, + "loss": 0.1376, "step": 202810 }, { - "epoch": 0.91, - "learning_rate": 4.769068651629972e-06, - "loss": 0.1391, + "epoch": 0.45, + "learning_rate": 2.7435292275340595e-05, + "loss": 0.1393, "step": 202820 }, { - "epoch": 0.91, - "learning_rate": 4.76682659970405e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7434173732131273e-05, + "loss": 0.135, "step": 202830 }, { - "epoch": 0.91, - "learning_rate": 4.764584547778127e-06, - "loss": 0.1392, + "epoch": 0.45, + "learning_rate": 2.7433055188921948e-05, + "loss": 0.1428, "step": 202840 }, { - "epoch": 0.91, - "learning_rate": 4.762342495852204e-06, - "loss": 0.1405, + "epoch": 0.45, + "learning_rate": 2.7431936645712625e-05, + "loss": 0.1393, "step": 202850 }, { - "epoch": 0.91, - "learning_rate": 4.760100443926282e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.7430818102503303e-05, + "loss": 0.1439, "step": 202860 }, { - "epoch": 0.91, - "learning_rate": 4.757858392000359e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.7429699559293975e-05, + "loss": 0.1414, "step": 202870 }, { - "epoch": 0.91, - "learning_rate": 4.755616340074436e-06, - "loss": 0.139, + "epoch": 0.45, + "learning_rate": 2.7428581016084652e-05, + "loss": 0.1384, "step": 202880 }, { - "epoch": 0.91, - "learning_rate": 4.753374288148514e-06, - "loss": 0.1397, + "epoch": 0.45, + "learning_rate": 2.7427462472875327e-05, + "loss": 0.1378, "step": 202890 }, { - "epoch": 0.91, - "learning_rate": 4.7511322362225915e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.7426343929666005e-05, + "loss": 0.1449, "step": 202900 }, { - "epoch": 0.91, - "learning_rate": 4.7488901842966686e-06, - "loss": 0.136, + "epoch": 0.45, + "learning_rate": 2.7425225386456683e-05, + "loss": 0.1394, "step": 202910 }, { - "epoch": 0.91, - "learning_rate": 4.746648132370746e-06, - "loss": 0.1403, + "epoch": 0.45, + "learning_rate": 2.7424106843247354e-05, + "loss": 0.137, "step": 202920 }, { - "epoch": 0.91, - "learning_rate": 4.7444060804448235e-06, + "epoch": 0.45, + "learning_rate": 2.7422988300038032e-05, "loss": 0.1398, "step": 202930 }, { - "epoch": 0.91, - "learning_rate": 4.7421640285189005e-06, - "loss": 0.1399, + "epoch": 0.45, + "learning_rate": 2.7421869756828707e-05, + "loss": 0.1394, "step": 202940 }, { - "epoch": 0.91, - "learning_rate": 4.739921976592978e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.7420751213619384e-05, + "loss": 0.1406, "step": 202950 }, { - "epoch": 0.91, - "learning_rate": 4.737679924667056e-06, - "loss": 0.1373, + "epoch": 0.45, + "learning_rate": 2.7419632670410062e-05, + "loss": 0.1364, "step": 202960 }, { - "epoch": 0.91, - "learning_rate": 4.735437872741133e-06, - "loss": 0.1375, + "epoch": 0.45, + "learning_rate": 2.7418514127200734e-05, + "loss": 0.1461, "step": 202970 }, { - "epoch": 0.91, - "learning_rate": 4.73319582081521e-06, - "loss": 0.1432, + "epoch": 0.45, + "learning_rate": 2.741739558399141e-05, + "loss": 0.1445, "step": 202980 }, { - "epoch": 0.91, - "learning_rate": 4.730953768889287e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.7416277040782086e-05, + "loss": 0.1402, "step": 202990 }, { - "epoch": 0.91, - "learning_rate": 4.728711716963365e-06, - "loss": 0.1371, + "epoch": 0.45, + "learning_rate": 2.7415158497572764e-05, + "loss": 0.1405, "step": 203000 }, { - "epoch": 0.91, - "learning_rate": 4.726469665037442e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.7414039954363442e-05, + "loss": 0.1385, "step": 203010 }, { - "epoch": 0.91, - "learning_rate": 4.72422761311152e-06, - "loss": 0.1346, + "epoch": 0.45, + "learning_rate": 2.7412921411154113e-05, + "loss": 0.1423, "step": 203020 }, { - "epoch": 0.91, - "learning_rate": 4.721985561185598e-06, - "loss": 0.1362, + "epoch": 0.45, + "learning_rate": 2.741180286794479e-05, + "loss": 0.1423, "step": 203030 }, { - "epoch": 0.91, - "learning_rate": 4.719743509259675e-06, - "loss": 0.1342, + "epoch": 0.45, + "learning_rate": 2.7410684324735465e-05, + "loss": 0.138, "step": 203040 }, { - "epoch": 0.91, - "learning_rate": 4.717501457333752e-06, - "loss": 0.1347, + "epoch": 0.45, + "learning_rate": 2.7409565781526143e-05, + "loss": 0.1377, "step": 203050 }, { - "epoch": 0.91, - "learning_rate": 4.715259405407829e-06, - "loss": 0.1383, + "epoch": 0.45, + "learning_rate": 2.740844723831682e-05, + "loss": 0.1402, "step": 203060 }, { - "epoch": 0.91, - "learning_rate": 4.713017353481907e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.7407328695107492e-05, + "loss": 0.1362, "step": 203070 }, { - "epoch": 0.91, - "learning_rate": 4.710775301555984e-06, - "loss": 0.1356, + "epoch": 0.45, + "learning_rate": 2.740621015189817e-05, + "loss": 0.14, "step": 203080 }, { - "epoch": 0.91, - "learning_rate": 4.708533249630062e-06, - "loss": 0.1382, + "epoch": 0.45, + "learning_rate": 2.740509160868884e-05, + "loss": 0.1407, "step": 203090 }, { - "epoch": 0.91, - "learning_rate": 4.70629119770414e-06, - "loss": 0.1365, + "epoch": 0.45, + "learning_rate": 2.7403973065479523e-05, + "loss": 0.1394, "step": 203100 }, { - "epoch": 0.91, - "learning_rate": 4.704049145778217e-06, - "loss": 0.1375, + "epoch": 0.45, + "learning_rate": 2.74028545222702e-05, + "loss": 0.1391, "step": 203110 }, { - "epoch": 0.91, - "learning_rate": 4.701807093852294e-06, - "loss": 0.1376, + "epoch": 0.45, + "learning_rate": 2.7401735979060872e-05, + "loss": 0.136, "step": 203120 }, { - "epoch": 0.91, - "learning_rate": 4.699565041926371e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.740061743585155e-05, + "loss": 0.1429, "step": 203130 }, { - "epoch": 0.91, - "learning_rate": 4.697322990000449e-06, - "loss": 0.1392, + "epoch": 0.45, + "learning_rate": 2.739949889264222e-05, + "loss": 0.1377, "step": 203140 }, { - "epoch": 0.91, - "learning_rate": 4.695080938074526e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.73983803494329e-05, + "loss": 0.1368, "step": 203150 }, { - "epoch": 0.91, - "learning_rate": 4.6928388861486035e-06, - "loss": 0.1429, + "epoch": 0.45, + "learning_rate": 2.7397261806223573e-05, + "loss": 0.1472, "step": 203160 }, { - "epoch": 0.91, - "learning_rate": 4.690596834222681e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.739614326301425e-05, + "loss": 0.1432, "step": 203170 }, { - "epoch": 0.91, - "learning_rate": 4.688354782296758e-06, - "loss": 0.1393, + "epoch": 0.45, + "learning_rate": 2.739502471980493e-05, + "loss": 0.1356, "step": 203180 }, { - "epoch": 0.91, - "learning_rate": 4.686112730370835e-06, - "loss": 0.133, + "epoch": 0.45, + "learning_rate": 2.73939061765956e-05, + "loss": 0.1356, "step": 203190 }, { - "epoch": 0.91, - "learning_rate": 4.683870678444912e-06, - "loss": 0.1334, + "epoch": 0.45, + "learning_rate": 2.739278763338628e-05, + "loss": 0.1418, "step": 203200 }, { - "epoch": 0.91, - "learning_rate": 4.68162862651899e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.7391669090176953e-05, + "loss": 0.1429, "step": 203210 }, { - "epoch": 0.91, - "learning_rate": 4.679386574593068e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.739055054696763e-05, + "loss": 0.1427, "step": 203220 }, { - "epoch": 0.91, - "learning_rate": 4.677144522667145e-06, - "loss": 0.1317, + "epoch": 0.45, + "learning_rate": 2.738943200375831e-05, + "loss": 0.1414, "step": 203230 }, { - "epoch": 0.91, - "learning_rate": 4.674902470741223e-06, - "loss": 0.1369, + "epoch": 0.45, + "learning_rate": 2.738831346054898e-05, + "loss": 0.136, "step": 203240 }, { - "epoch": 0.91, - "learning_rate": 4.6726604188153e-06, - "loss": 0.1391, + "epoch": 0.45, + "learning_rate": 2.7387194917339658e-05, + "loss": 0.1364, "step": 203250 }, { - "epoch": 0.91, - "learning_rate": 4.670418366889377e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.7386076374130332e-05, + "loss": 0.1391, "step": 203260 }, { - "epoch": 0.91, - "learning_rate": 4.668176314963455e-06, - "loss": 0.14, + "epoch": 0.45, + "learning_rate": 2.738495783092101e-05, + "loss": 0.1409, "step": 203270 }, { - "epoch": 0.91, - "learning_rate": 4.665934263037532e-06, - "loss": 0.1347, + "epoch": 0.45, + "learning_rate": 2.7383839287711688e-05, + "loss": 0.1419, "step": 203280 }, { - "epoch": 0.91, - "learning_rate": 4.66369221111161e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.7382832598823294e-05, + "loss": 0.1458, "step": 203290 }, { - "epoch": 0.91, - "learning_rate": 4.661450159185687e-06, - "loss": 0.1367, + "epoch": 0.45, + "learning_rate": 2.738171405561397e-05, + "loss": 0.1432, "step": 203300 }, { - "epoch": 0.91, - "learning_rate": 4.659208107259765e-06, - "loss": 0.139, + "epoch": 0.45, + "learning_rate": 2.7380595512404643e-05, + "loss": 0.1375, "step": 203310 }, { - "epoch": 0.91, - "learning_rate": 4.656966055333842e-06, - "loss": 0.1384, + "epoch": 0.45, + "learning_rate": 2.737947696919532e-05, + "loss": 0.1355, "step": 203320 }, { - "epoch": 0.91, - "learning_rate": 4.654724003407919e-06, - "loss": 0.1419, + "epoch": 0.45, + "learning_rate": 2.7378358425985995e-05, + "loss": 0.1378, "step": 203330 }, { - "epoch": 0.91, - "learning_rate": 4.652481951481997e-06, - "loss": 0.1427, + "epoch": 0.45, + "learning_rate": 2.7377239882776673e-05, + "loss": 0.1364, "step": 203340 }, { - "epoch": 0.91, - "learning_rate": 4.650239899556074e-06, - "loss": 0.1374, + "epoch": 0.45, + "learning_rate": 2.737612133956735e-05, + "loss": 0.1398, "step": 203350 }, { - "epoch": 0.91, - "learning_rate": 4.6479978476301516e-06, - "loss": 0.1427, + "epoch": 0.45, + "learning_rate": 2.7375002796358022e-05, + "loss": 0.1373, "step": 203360 }, { - "epoch": 0.91, - "learning_rate": 4.645755795704229e-06, + "epoch": 0.45, + "learning_rate": 2.73738842531487e-05, "loss": 0.1405, "step": 203370 }, { - "epoch": 0.91, - "learning_rate": 4.6435137437783065e-06, - "loss": 0.1327, + "epoch": 0.45, + "learning_rate": 2.7372765709939375e-05, + "loss": 0.1393, "step": 203380 }, { - "epoch": 0.91, - "learning_rate": 4.6412716918523835e-06, + "epoch": 0.45, + "learning_rate": 2.7371647166730053e-05, "loss": 0.1385, "step": 203390 }, { - "epoch": 0.91, - "learning_rate": 4.6390296399264605e-06, - "loss": 0.1332, + "epoch": 0.45, + "learning_rate": 2.737052862352073e-05, + "loss": 0.139, "step": 203400 }, { - "epoch": 0.91, - "learning_rate": 4.636787588000538e-06, - "loss": 0.1437, + "epoch": 0.45, + "learning_rate": 2.7369410080311402e-05, + "loss": 0.1399, "step": 203410 }, { - "epoch": 0.91, - "learning_rate": 4.634545536074615e-06, - "loss": 0.1396, + "epoch": 0.45, + "learning_rate": 2.736829153710208e-05, + "loss": 0.1381, "step": 203420 }, { - "epoch": 0.91, - "learning_rate": 4.632303484148693e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7367172993892754e-05, + "loss": 0.1414, "step": 203430 }, { - "epoch": 0.91, - "learning_rate": 4.63006143222277e-06, - "loss": 0.1398, + "epoch": 0.45, + "learning_rate": 2.7366054450683432e-05, + "loss": 0.1404, "step": 203440 }, { - "epoch": 0.91, - "learning_rate": 4.627819380296848e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.736493590747411e-05, + "loss": 0.1374, "step": 203450 }, { - "epoch": 0.91, - "learning_rate": 4.625577328370925e-06, - "loss": 0.1408, + "epoch": 0.45, + "learning_rate": 2.736381736426478e-05, + "loss": 0.1383, "step": 203460 }, { - "epoch": 0.91, - "learning_rate": 4.623335276445002e-06, - "loss": 0.138, + "epoch": 0.45, + "learning_rate": 2.736269882105546e-05, + "loss": 0.142, "step": 203470 }, { - "epoch": 0.91, - "learning_rate": 4.62109322451908e-06, - "loss": 0.1383, + "epoch": 0.45, + "learning_rate": 2.7361580277846134e-05, + "loss": 0.1412, "step": 203480 }, { - "epoch": 0.91, - "learning_rate": 4.618851172593158e-06, - "loss": 0.1425, + "epoch": 0.45, + "learning_rate": 2.736046173463681e-05, + "loss": 0.1406, "step": 203490 }, { - "epoch": 0.91, - "learning_rate": 4.616609120667235e-06, - "loss": 0.1351, + "epoch": 0.45, + "learning_rate": 2.735934319142749e-05, + "loss": 0.1365, "step": 203500 }, { - "epoch": 0.91, - "learning_rate": 4.614367068741312e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.735822464821816e-05, + "loss": 0.1378, "step": 203510 }, { - "epoch": 0.91, - "learning_rate": 4.612349222007982e-06, - "loss": 0.1388, + "epoch": 0.45, + "learning_rate": 2.735710610500884e-05, + "loss": 0.1396, "step": 203520 }, { - "epoch": 0.91, - "learning_rate": 4.610107170082059e-06, - "loss": 0.1438, + "epoch": 0.45, + "learning_rate": 2.7355987561799513e-05, + "loss": 0.1376, "step": 203530 }, { - "epoch": 0.91, - "learning_rate": 4.607865118156137e-06, - "loss": 0.1433, + "epoch": 0.45, + "learning_rate": 2.735486901859019e-05, + "loss": 0.1361, "step": 203540 }, { - "epoch": 0.91, - "learning_rate": 4.605623066230214e-06, - "loss": 0.1407, + "epoch": 0.45, + "learning_rate": 2.7353750475380862e-05, + "loss": 0.144, "step": 203550 }, { - "epoch": 0.91, - "learning_rate": 4.603381014304291e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.735263193217154e-05, + "loss": 0.1429, "step": 203560 }, { - "epoch": 0.91, - "learning_rate": 4.601138962378368e-06, - "loss": 0.1342, + "epoch": 0.45, + "learning_rate": 2.7351513388962218e-05, + "loss": 0.142, "step": 203570 }, { - "epoch": 0.91, - "learning_rate": 4.598896910452446e-06, - "loss": 0.1346, + "epoch": 0.45, + "learning_rate": 2.7350394845752893e-05, + "loss": 0.1428, "step": 203580 }, { - "epoch": 0.91, - "learning_rate": 4.596654858526524e-06, - "loss": 0.1423, + "epoch": 0.45, + "learning_rate": 2.734927630254357e-05, + "loss": 0.1355, "step": 203590 }, { - "epoch": 0.91, - "learning_rate": 4.594412806600601e-06, - "loss": 0.1403, + "epoch": 0.45, + "learning_rate": 2.734815775933424e-05, + "loss": 0.1406, "step": 203600 }, { - "epoch": 0.91, - "learning_rate": 4.592170754674679e-06, - "loss": 0.1428, + "epoch": 0.45, + "learning_rate": 2.734703921612492e-05, + "loss": 0.145, "step": 203610 }, { - "epoch": 0.91, - "learning_rate": 4.589928702748756e-06, - "loss": 0.1347, + "epoch": 0.45, + "learning_rate": 2.7345920672915598e-05, + "loss": 0.1403, "step": 203620 }, { - "epoch": 0.91, - "learning_rate": 4.587686650822833e-06, - "loss": 0.1451, + "epoch": 0.45, + "learning_rate": 2.7344802129706272e-05, + "loss": 0.1417, "step": 203630 }, { - "epoch": 0.91, - "learning_rate": 4.58544459889691e-06, - "loss": 0.1347, + "epoch": 0.45, + "learning_rate": 2.734368358649695e-05, + "loss": 0.137, "step": 203640 }, { - "epoch": 0.91, - "learning_rate": 4.583202546970988e-06, - "loss": 0.137, + "epoch": 0.45, + "learning_rate": 2.734256504328762e-05, + "loss": 0.1393, "step": 203650 }, { - "epoch": 0.91, - "learning_rate": 4.580960495045066e-06, - "loss": 0.1421, + "epoch": 0.45, + "learning_rate": 2.73414465000783e-05, + "loss": 0.1448, "step": 203660 }, { - "epoch": 0.91, - "learning_rate": 4.578718443119143e-06, - "loss": 0.1426, + "epoch": 0.45, + "learning_rate": 2.7340327956868977e-05, + "loss": 0.1407, "step": 203670 }, { - "epoch": 0.91, - "learning_rate": 4.576476391193221e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.733920941365965e-05, + "loss": 0.1403, "step": 203680 }, { - "epoch": 0.91, - "learning_rate": 4.574234339267298e-06, - "loss": 0.1411, + "epoch": 0.45, + "learning_rate": 2.733809087045033e-05, + "loss": 0.1367, "step": 203690 }, { - "epoch": 0.91, - "learning_rate": 4.571992287341375e-06, - "loss": 0.1385, + "epoch": 0.45, + "learning_rate": 2.7336972327241e-05, + "loss": 0.139, "step": 203700 }, { - "epoch": 0.91, - "learning_rate": 4.569750235415452e-06, - "loss": 0.1334, + "epoch": 0.45, + "learning_rate": 2.733585378403168e-05, + "loss": 0.1378, "step": 203710 }, { - "epoch": 0.91, - "learning_rate": 4.5675081834895304e-06, - "loss": 0.1361, + "epoch": 0.45, + "learning_rate": 2.7334735240822356e-05, + "loss": 0.1406, "step": 203720 }, { - "epoch": 0.91, - "learning_rate": 4.5652661315636075e-06, - "loss": 0.1359, + "epoch": 0.45, + "learning_rate": 2.7333616697613028e-05, + "loss": 0.1379, "step": 203730 }, { - "epoch": 0.91, - "learning_rate": 4.5630240796376845e-06, - "loss": 0.1379, + "epoch": 0.45, + "learning_rate": 2.733249815440371e-05, + "loss": 0.1369, "step": 203740 }, { - "epoch": 0.91, - "learning_rate": 4.560782027711762e-06, - "loss": 0.1406, + "epoch": 0.45, + "learning_rate": 2.733137961119438e-05, + "loss": 0.1424, "step": 203750 }, { - "epoch": 0.91, - "learning_rate": 4.558539975785839e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7330261067985058e-05, + "loss": 0.1377, "step": 203760 }, { - "epoch": 0.91, - "learning_rate": 4.556297923859916e-06, - "loss": 0.1377, + "epoch": 0.45, + "learning_rate": 2.7329142524775736e-05, + "loss": 0.1392, "step": 203770 }, { - "epoch": 0.91, - "learning_rate": 4.554055871933994e-06, - "loss": 0.1354, + "epoch": 0.45, + "learning_rate": 2.7328023981566407e-05, + "loss": 0.1367, "step": 203780 }, { - "epoch": 0.91, - "learning_rate": 4.551813820008072e-06, - "loss": 0.1368, + "epoch": 0.45, + "learning_rate": 2.7326905438357085e-05, + "loss": 0.1399, "step": 203790 }, { - "epoch": 0.91, - "learning_rate": 4.549571768082149e-06, - "loss": 0.1417, + "epoch": 0.45, + "learning_rate": 2.732578689514776e-05, + "loss": 0.1375, "step": 203800 }, { - "epoch": 0.91, - "learning_rate": 4.547329716156226e-06, - "loss": 0.1366, + "epoch": 0.45, + "learning_rate": 2.7324668351938437e-05, + "loss": 0.1387, "step": 203810 }, { - "epoch": 0.91, - "learning_rate": 4.545087664230304e-06, - "loss": 0.1364, + "epoch": 0.45, + "learning_rate": 2.732354980872911e-05, + "loss": 0.1375, "step": 203820 }, { - "epoch": 0.91, - "learning_rate": 4.542845612304381e-06, - "loss": 0.1402, + "epoch": 0.45, + "learning_rate": 2.7322431265519787e-05, + "loss": 0.138, "step": 203830 }, { - "epoch": 0.91, - "learning_rate": 4.540603560378458e-06, - "loss": 0.1383, + "epoch": 0.45, + "learning_rate": 2.7321312722310465e-05, + "loss": 0.1432, "step": 203840 }, { - "epoch": 0.91, - "learning_rate": 4.538361508452536e-06, - "loss": 0.1409, + "epoch": 0.46, + "learning_rate": 2.732019417910114e-05, + "loss": 0.1399, "step": 203850 }, { - "epoch": 0.91, - "learning_rate": 4.536119456526614e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.7319075635891817e-05, + "loss": 0.1437, "step": 203860 }, { - "epoch": 0.91, - "learning_rate": 4.533877404600691e-06, - "loss": 0.1334, + "epoch": 0.46, + "learning_rate": 2.7317957092682488e-05, + "loss": 0.1357, "step": 203870 }, { - "epoch": 0.91, - "learning_rate": 4.531635352674768e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.7316838549473166e-05, + "loss": 0.1361, "step": 203880 }, { - "epoch": 0.91, - "learning_rate": 4.529393300748846e-06, - "loss": 0.1415, + "epoch": 0.46, + "learning_rate": 2.7315720006263844e-05, + "loss": 0.1384, "step": 203890 }, { - "epoch": 0.91, - "learning_rate": 4.527151248822923e-06, - "loss": 0.1444, + "epoch": 0.46, + "learning_rate": 2.731460146305452e-05, + "loss": 0.139, "step": 203900 }, { - "epoch": 0.91, - "learning_rate": 4.524909196897e-06, - "loss": 0.1336, + "epoch": 0.46, + "learning_rate": 2.7313482919845196e-05, + "loss": 0.1392, "step": 203910 }, { - "epoch": 0.91, - "learning_rate": 4.522667144971078e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7312364376635868e-05, + "loss": 0.1419, "step": 203920 }, { - "epoch": 0.91, - "learning_rate": 4.5204250930451556e-06, - "loss": 0.1405, + "epoch": 0.46, + "learning_rate": 2.7311245833426546e-05, + "loss": 0.1383, "step": 203930 }, { - "epoch": 0.91, - "learning_rate": 4.518183041119233e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.7310127290217223e-05, + "loss": 0.1389, "step": 203940 }, { - "epoch": 0.91, - "learning_rate": 4.51594098919331e-06, - "loss": 0.1352, + "epoch": 0.46, + "learning_rate": 2.7309008747007898e-05, + "loss": 0.1431, "step": 203950 }, { - "epoch": 0.91, - "learning_rate": 4.5136989372673875e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.7307890203798576e-05, + "loss": 0.1391, "step": 203960 }, { - "epoch": 0.91, - "learning_rate": 4.5114568853414645e-06, - "loss": 0.1476, + "epoch": 0.46, + "learning_rate": 2.7306771660589247e-05, + "loss": 0.1407, "step": 203970 }, { - "epoch": 0.91, - "learning_rate": 4.5092148334155415e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7305653117379925e-05, + "loss": 0.1402, "step": 203980 }, { - "epoch": 0.91, - "learning_rate": 4.506972781489619e-06, - "loss": 0.1342, + "epoch": 0.46, + "learning_rate": 2.7304534574170603e-05, + "loss": 0.138, "step": 203990 }, { - "epoch": 0.91, - "learning_rate": 4.504730729563697e-06, - "loss": 0.1418, + "epoch": 0.46, + "learning_rate": 2.7303416030961277e-05, + "loss": 0.1375, "step": 204000 }, { - "epoch": 0.91, - "learning_rate": 4.502488677637774e-06, - "loss": 0.1355, + "epoch": 0.46, + "learning_rate": 2.7302297487751955e-05, + "loss": 0.1401, "step": 204010 }, { - "epoch": 0.91, - "learning_rate": 4.500246625711851e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.7301178944542627e-05, + "loss": 0.1406, "step": 204020 }, { - "epoch": 0.91, - "learning_rate": 4.498004573785929e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7300060401333304e-05, + "loss": 0.1383, "step": 204030 }, { - "epoch": 0.91, - "learning_rate": 4.495762521860006e-06, - "loss": 0.1429, + "epoch": 0.46, + "learning_rate": 2.7298941858123982e-05, + "loss": 0.1394, "step": 204040 }, { - "epoch": 0.91, - "learning_rate": 4.493520469934084e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.7297823314914657e-05, + "loss": 0.1441, "step": 204050 }, { - "epoch": 0.91, - "learning_rate": 4.491278418008162e-06, - "loss": 0.1408, + "epoch": 0.46, + "learning_rate": 2.7296704771705335e-05, + "loss": 0.1347, "step": 204060 }, { - "epoch": 0.91, - "learning_rate": 4.489036366082239e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.7295586228496006e-05, + "loss": 0.1446, "step": 204070 }, { - "epoch": 0.91, - "learning_rate": 4.486794314156316e-06, - "loss": 0.1374, + "epoch": 0.46, + "learning_rate": 2.7294467685286684e-05, + "loss": 0.142, "step": 204080 }, { - "epoch": 0.91, - "learning_rate": 4.484552262230393e-06, - "loss": 0.1386, + "epoch": 0.46, + "learning_rate": 2.7293349142077362e-05, + "loss": 0.1409, "step": 204090 }, { - "epoch": 0.91, - "learning_rate": 4.482310210304471e-06, - "loss": 0.1344, + "epoch": 0.46, + "learning_rate": 2.7292230598868036e-05, + "loss": 0.1363, "step": 204100 }, { - "epoch": 0.91, - "learning_rate": 4.480068158378548e-06, - "loss": 0.1409, + "epoch": 0.46, + "learning_rate": 2.7291112055658714e-05, + "loss": 0.1401, "step": 204110 }, { - "epoch": 0.91, - "learning_rate": 4.477826106452626e-06, - "loss": 0.1419, + "epoch": 0.46, + "learning_rate": 2.7289993512449385e-05, + "loss": 0.1365, "step": 204120 }, { - "epoch": 0.91, - "learning_rate": 4.475584054526704e-06, - "loss": 0.1374, + "epoch": 0.46, + "learning_rate": 2.7288874969240063e-05, + "loss": 0.1393, "step": 204130 }, { - "epoch": 0.91, - "learning_rate": 4.473342002600781e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.7287756426030735e-05, + "loss": 0.1414, "step": 204140 }, { - "epoch": 0.91, - "learning_rate": 4.471099950674858e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.7286637882821416e-05, + "loss": 0.1435, "step": 204150 }, { - "epoch": 0.91, - "learning_rate": 4.468857898748935e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.7285519339612094e-05, + "loss": 0.1387, "step": 204160 }, { - "epoch": 0.91, - "learning_rate": 4.466615846823013e-06, - "loss": 0.139, + "epoch": 0.46, + "learning_rate": 2.7284400796402765e-05, + "loss": 0.1371, "step": 204170 }, { - "epoch": 0.91, - "learning_rate": 4.46437379489709e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7283282253193443e-05, + "loss": 0.1394, "step": 204180 }, { - "epoch": 0.91, - "learning_rate": 4.4621317429711675e-06, - "loss": 0.1426, + "epoch": 0.46, + "learning_rate": 2.7282163709984114e-05, + "loss": 0.1436, "step": 204190 }, { - "epoch": 0.91, - "learning_rate": 4.459889691045245e-06, - "loss": 0.1414, + "epoch": 0.46, + "learning_rate": 2.7281045166774792e-05, + "loss": 0.1345, "step": 204200 }, { - "epoch": 0.91, - "learning_rate": 4.457647639119322e-06, - "loss": 0.1406, + "epoch": 0.46, + "learning_rate": 2.727992662356547e-05, + "loss": 0.1413, "step": 204210 }, { - "epoch": 0.91, - "learning_rate": 4.455405587193399e-06, - "loss": 0.1375, + "epoch": 0.46, + "learning_rate": 2.7278808080356144e-05, + "loss": 0.1398, "step": 204220 }, { - "epoch": 0.91, - "learning_rate": 4.453163535267477e-06, - "loss": 0.1396, + "epoch": 0.46, + "learning_rate": 2.7277689537146822e-05, + "loss": 0.1384, "step": 204230 }, { - "epoch": 0.91, - "learning_rate": 4.450921483341554e-06, - "loss": 0.1344, + "epoch": 0.46, + "learning_rate": 2.7276570993937494e-05, + "loss": 0.1377, "step": 204240 }, { - "epoch": 0.91, - "learning_rate": 4.448679431415631e-06, - "loss": 0.1377, + "epoch": 0.46, + "learning_rate": 2.727545245072817e-05, + "loss": 0.1389, "step": 204250 }, { - "epoch": 0.91, - "learning_rate": 4.446437379489709e-06, - "loss": 0.1394, + "epoch": 0.46, + "learning_rate": 2.727433390751885e-05, + "loss": 0.1361, "step": 204260 }, { - "epoch": 0.91, - "learning_rate": 4.444195327563787e-06, - "loss": 0.1437, + "epoch": 0.46, + "learning_rate": 2.7273215364309524e-05, + "loss": 0.1377, "step": 204270 }, { - "epoch": 0.91, - "learning_rate": 4.441953275637864e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.7272096821100202e-05, + "loss": 0.1371, "step": 204280 }, { - "epoch": 0.91, - "learning_rate": 4.439711223711941e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.7270978277890873e-05, + "loss": 0.139, "step": 204290 }, { - "epoch": 0.91, - "learning_rate": 4.437469171786019e-06, - "loss": 0.1314, + "epoch": 0.46, + "learning_rate": 2.726985973468155e-05, + "loss": 0.1424, "step": 204300 }, { - "epoch": 0.91, - "learning_rate": 4.435227119860096e-06, - "loss": 0.1355, + "epoch": 0.46, + "learning_rate": 2.726874119147223e-05, + "loss": 0.1412, "step": 204310 }, { - "epoch": 0.91, - "learning_rate": 4.432985067934174e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7267622648262903e-05, + "loss": 0.1382, "step": 204320 }, { - "epoch": 0.91, - "learning_rate": 4.430743016008251e-06, - "loss": 0.1418, + "epoch": 0.46, + "learning_rate": 2.726650410505358e-05, + "loss": 0.1396, "step": 204330 }, { - "epoch": 0.91, - "learning_rate": 4.428500964082329e-06, - "loss": 0.1432, + "epoch": 0.46, + "learning_rate": 2.7265385561844252e-05, + "loss": 0.1364, "step": 204340 }, { - "epoch": 0.91, - "learning_rate": 4.426258912156406e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.726426701863493e-05, + "loss": 0.139, "step": 204350 }, { - "epoch": 0.91, - "learning_rate": 4.424016860230483e-06, - "loss": 0.1346, + "epoch": 0.46, + "learning_rate": 2.726314847542561e-05, + "loss": 0.1411, "step": 204360 }, { - "epoch": 0.91, - "learning_rate": 4.421774808304561e-06, - "loss": 0.1425, + "epoch": 0.46, + "learning_rate": 2.7262029932216283e-05, + "loss": 0.1336, "step": 204370 }, { - "epoch": 0.91, - "learning_rate": 4.419532756378638e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.726091138900696e-05, + "loss": 0.1393, "step": 204380 }, { - "epoch": 0.91, - "learning_rate": 4.417290704452716e-06, - "loss": 0.1391, + "epoch": 0.46, + "learning_rate": 2.7259792845797632e-05, + "loss": 0.142, "step": 204390 }, { - "epoch": 0.91, - "learning_rate": 4.415048652526793e-06, - "loss": 0.1412, + "epoch": 0.46, + "learning_rate": 2.725867430258831e-05, + "loss": 0.1392, "step": 204400 }, { - "epoch": 0.91, - "learning_rate": 4.4128066006008705e-06, - "loss": 0.1401, + "epoch": 0.46, + "learning_rate": 2.7257555759378988e-05, + "loss": 0.1361, "step": 204410 }, { - "epoch": 0.91, - "learning_rate": 4.4105645486749475e-06, - "loss": 0.1384, + "epoch": 0.46, + "learning_rate": 2.7256437216169662e-05, + "loss": 0.1329, "step": 204420 }, { - "epoch": 0.91, - "learning_rate": 4.4083224967490245e-06, - "loss": 0.1358, + "epoch": 0.46, + "learning_rate": 2.725531867296034e-05, + "loss": 0.1401, "step": 204430 }, { - "epoch": 0.91, - "learning_rate": 4.406080444823102e-06, - "loss": 0.1346, + "epoch": 0.46, + "learning_rate": 2.725420012975101e-05, + "loss": 0.1359, "step": 204440 }, { - "epoch": 0.91, - "learning_rate": 4.4038383928971794e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.725308158654169e-05, + "loss": 0.1433, "step": 204450 }, { - "epoch": 0.91, - "learning_rate": 4.401596340971257e-06, - "loss": 0.1385, + "epoch": 0.46, + "learning_rate": 2.7251963043332364e-05, + "loss": 0.137, "step": 204460 }, { - "epoch": 0.91, - "learning_rate": 4.399354289045334e-06, - "loss": 0.1398, + "epoch": 0.46, + "learning_rate": 2.7250844500123042e-05, + "loss": 0.1378, "step": 204470 }, { - "epoch": 0.91, - "learning_rate": 4.397112237119412e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.724972595691372e-05, + "loss": 0.1425, "step": 204480 }, { - "epoch": 0.91, - "learning_rate": 4.394870185193489e-06, - "loss": 0.1417, + "epoch": 0.46, + "learning_rate": 2.724860741370439e-05, + "loss": 0.1378, "step": 204490 }, { - "epoch": 0.91, - "learning_rate": 4.392628133267566e-06, - "loss": 0.1357, + "epoch": 0.46, + "learning_rate": 2.724748887049507e-05, + "loss": 0.1418, "step": 204500 }, { - "epoch": 0.91, - "learning_rate": 4.390386081341644e-06, - "loss": 0.1435, + "epoch": 0.46, + "learning_rate": 2.7246370327285743e-05, + "loss": 0.1412, "step": 204510 }, { - "epoch": 0.91, - "learning_rate": 4.388144029415721e-06, - "loss": 0.1369, + "epoch": 0.46, + "learning_rate": 2.724525178407642e-05, + "loss": 0.1368, "step": 204520 }, { - "epoch": 0.91, - "learning_rate": 4.385901977489799e-06, - "loss": 0.1368, + "epoch": 0.46, + "learning_rate": 2.72441332408671e-05, + "loss": 0.1419, "step": 204530 }, { - "epoch": 0.91, - "learning_rate": 4.383659925563877e-06, - "loss": 0.1399, + "epoch": 0.46, + "learning_rate": 2.724301469765777e-05, + "loss": 0.1343, "step": 204540 }, { - "epoch": 0.91, - "learning_rate": 4.381417873637954e-06, - "loss": 0.1352, + "epoch": 0.46, + "learning_rate": 2.7241896154448448e-05, + "loss": 0.1402, "step": 204550 }, { - "epoch": 0.91, - "learning_rate": 4.379175821712031e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.724077761123912e-05, + "loss": 0.1366, "step": 204560 }, { - "epoch": 0.91, - "learning_rate": 4.376933769786108e-06, - "loss": 0.1393, + "epoch": 0.46, + "learning_rate": 2.72396590680298e-05, + "loss": 0.1337, "step": 204570 }, { - "epoch": 0.91, - "learning_rate": 4.374691717860186e-06, - "loss": 0.1369, + "epoch": 0.46, + "learning_rate": 2.723854052482048e-05, + "loss": 0.1433, "step": 204580 }, { - "epoch": 0.91, - "learning_rate": 4.372449665934264e-06, - "loss": 0.1428, + "epoch": 0.46, + "learning_rate": 2.723742198161115e-05, + "loss": 0.1391, "step": 204590 }, { - "epoch": 0.91, - "learning_rate": 4.370207614008341e-06, - "loss": 0.1373, + "epoch": 0.46, + "learning_rate": 2.7236303438401828e-05, + "loss": 0.1362, "step": 204600 }, { - "epoch": 0.91, - "learning_rate": 4.367965562082419e-06, - "loss": 0.1362, + "epoch": 0.46, + "learning_rate": 2.72351848951925e-05, + "loss": 0.1329, "step": 204610 }, { - "epoch": 0.91, - "learning_rate": 4.365723510156496e-06, - "loss": 0.1389, + "epoch": 0.46, + "learning_rate": 2.7234066351983177e-05, + "loss": 0.1353, "step": 204620 }, { - "epoch": 0.91, - "learning_rate": 4.363481458230573e-06, - "loss": 0.1365, + "epoch": 0.46, + "learning_rate": 2.7232947808773858e-05, + "loss": 0.1403, "step": 204630 }, { - "epoch": 0.91, - "learning_rate": 4.36123940630465e-06, - "loss": 0.1355, + "epoch": 0.46, + "learning_rate": 2.723182926556453e-05, + "loss": 0.1372, "step": 204640 }, { - "epoch": 0.91, - "learning_rate": 4.3589973543787275e-06, - "loss": 0.1338, + "epoch": 0.46, + "learning_rate": 2.7230710722355207e-05, + "loss": 0.1422, "step": 204650 }, { - "epoch": 0.91, - "learning_rate": 4.356755302452805e-06, - "loss": 0.1379, + "epoch": 0.46, + "learning_rate": 2.722959217914588e-05, + "loss": 0.1396, "step": 204660 }, { - "epoch": 0.91, - "learning_rate": 4.354513250526882e-06, - "loss": 0.1398, + "epoch": 0.46, + "learning_rate": 2.7228473635936556e-05, + "loss": 0.1382, "step": 204670 }, { - "epoch": 0.91, - "learning_rate": 4.35227119860096e-06, - "loss": 0.1385, + "epoch": 0.46, + "learning_rate": 2.7227355092727234e-05, + "loss": 0.1355, "step": 204680 }, { - "epoch": 0.91, - "learning_rate": 4.350029146675037e-06, - "loss": 0.1371, + "epoch": 0.46, + "learning_rate": 2.722623654951791e-05, + "loss": 0.1428, "step": 204690 }, { - "epoch": 0.91, - "learning_rate": 4.347787094749114e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7225118006308587e-05, + "loss": 0.1379, "step": 204700 }, { - "epoch": 0.91, - "learning_rate": 4.345545042823191e-06, - "loss": 0.1365, + "epoch": 0.46, + "learning_rate": 2.7223999463099258e-05, + "loss": 0.1386, "step": 204710 }, { - "epoch": 0.91, - "learning_rate": 4.343302990897269e-06, - "loss": 0.1344, + "epoch": 0.46, + "learning_rate": 2.7222880919889936e-05, + "loss": 0.1422, "step": 204720 }, { - "epoch": 0.91, - "learning_rate": 4.341060938971347e-06, - "loss": 0.1385, + "epoch": 0.46, + "learning_rate": 2.7221762376680614e-05, + "loss": 0.1364, "step": 204730 }, { - "epoch": 0.91, - "learning_rate": 4.338818887045424e-06, - "loss": 0.1437, + "epoch": 0.46, + "learning_rate": 2.7220643833471288e-05, + "loss": 0.1381, "step": 204740 }, { - "epoch": 0.91, - "learning_rate": 4.336576835119502e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.7219525290261966e-05, + "loss": 0.1358, "step": 204750 }, { - "epoch": 0.91, - "learning_rate": 4.334334783193579e-06, - "loss": 0.1373, + "epoch": 0.46, + "learning_rate": 2.7218406747052637e-05, + "loss": 0.1409, "step": 204760 }, { - "epoch": 0.91, - "learning_rate": 4.332092731267656e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.7217288203843315e-05, + "loss": 0.1392, "step": 204770 }, { - "epoch": 0.91, - "learning_rate": 4.329850679341733e-06, - "loss": 0.1349, + "epoch": 0.46, + "learning_rate": 2.721616966063399e-05, + "loss": 0.1367, "step": 204780 }, { - "epoch": 0.91, - "learning_rate": 4.327608627415811e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.7215051117424668e-05, + "loss": 0.1402, "step": 204790 }, { - "epoch": 0.91, - "learning_rate": 4.325366575489889e-06, - "loss": 0.1346, + "epoch": 0.46, + "learning_rate": 2.7213932574215346e-05, + "loss": 0.14, "step": 204800 }, { - "epoch": 0.91, - "learning_rate": 4.323124523563966e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.7212814031006017e-05, + "loss": 0.1388, "step": 204810 }, { - "epoch": 0.91, - "learning_rate": 4.320882471638044e-06, - "loss": 0.1466, + "epoch": 0.46, + "learning_rate": 2.7211695487796695e-05, + "loss": 0.1393, "step": 204820 }, { - "epoch": 0.91, - "learning_rate": 4.318640419712121e-06, - "loss": 0.1334, + "epoch": 0.46, + "learning_rate": 2.721057694458737e-05, + "loss": 0.1395, "step": 204830 }, { - "epoch": 0.91, - "learning_rate": 4.316398367786198e-06, - "loss": 0.1363, + "epoch": 0.46, + "learning_rate": 2.7209458401378047e-05, + "loss": 0.1397, "step": 204840 }, { - "epoch": 0.91, - "learning_rate": 4.314156315860275e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.7208339858168725e-05, + "loss": 0.1356, "step": 204850 }, { - "epoch": 0.91, - "learning_rate": 4.3119142639343535e-06, - "loss": 0.1391, + "epoch": 0.46, + "learning_rate": 2.7207221314959396e-05, + "loss": 0.1397, "step": 204860 }, { - "epoch": 0.91, - "learning_rate": 4.3096722120084305e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.7206102771750074e-05, + "loss": 0.1396, "step": 204870 }, { - "epoch": 0.91, - "learning_rate": 4.3074301600825075e-06, - "loss": 0.1408, + "epoch": 0.46, + "learning_rate": 2.720498422854075e-05, + "loss": 0.1365, "step": 204880 }, { - "epoch": 0.91, - "learning_rate": 4.305188108156585e-06, - "loss": 0.1386, + "epoch": 0.46, + "learning_rate": 2.7203865685331427e-05, + "loss": 0.1467, "step": 204890 }, { - "epoch": 0.91, - "learning_rate": 4.3029460562306624e-06, - "loss": 0.1417, + "epoch": 0.46, + "learning_rate": 2.7202747142122105e-05, + "loss": 0.1325, "step": 204900 }, { - "epoch": 0.91, - "learning_rate": 4.3007040043047395e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7201628598912776e-05, + "loss": 0.135, "step": 204910 }, { - "epoch": 0.91, - "learning_rate": 4.298461952378817e-06, - "loss": 0.1375, + "epoch": 0.46, + "learning_rate": 2.7200510055703454e-05, + "loss": 0.1365, "step": 204920 }, { - "epoch": 0.91, - "learning_rate": 4.296219900452895e-06, - "loss": 0.1394, + "epoch": 0.46, + "learning_rate": 2.7199391512494128e-05, + "loss": 0.1396, "step": 204930 }, { - "epoch": 0.91, - "learning_rate": 4.293977848526972e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.7198272969284806e-05, + "loss": 0.1394, "step": 204940 }, { - "epoch": 0.91, - "learning_rate": 4.291735796601049e-06, - "loss": 0.1379, + "epoch": 0.46, + "learning_rate": 2.7197154426075484e-05, + "loss": 0.1388, "step": 204950 }, { - "epoch": 0.91, - "learning_rate": 4.289493744675127e-06, - "loss": 0.1352, + "epoch": 0.46, + "learning_rate": 2.7196035882866155e-05, + "loss": 0.1406, "step": 204960 }, { - "epoch": 0.92, - "learning_rate": 4.287251692749204e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.7194917339656833e-05, + "loss": 0.1402, "step": 204970 }, { - "epoch": 0.92, - "learning_rate": 4.285009640823281e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7193798796447508e-05, + "loss": 0.1332, "step": 204980 }, { - "epoch": 0.92, - "learning_rate": 4.282767588897359e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7192680253238186e-05, + "loss": 0.135, "step": 204990 }, { - "epoch": 0.92, - "learning_rate": 4.280525536971437e-06, - "loss": 0.1402, + "epoch": 0.46, + "learning_rate": 2.7191561710028864e-05, + "loss": 0.1418, "step": 205000 }, { - "epoch": 0.92, - "learning_rate": 4.278283485045514e-06, - "loss": 0.1349, + "epoch": 0.46, + "learning_rate": 2.7190443166819535e-05, + "loss": 0.1385, "step": 205010 }, { - "epoch": 0.92, - "learning_rate": 4.276041433119591e-06, - "loss": 0.1348, + "epoch": 0.46, + "learning_rate": 2.7189324623610213e-05, + "loss": 0.1408, "step": 205020 }, { - "epoch": 0.92, - "learning_rate": 4.273799381193669e-06, - "loss": 0.1324, + "epoch": 0.46, + "learning_rate": 2.7188206080400884e-05, + "loss": 0.1377, "step": 205030 }, { - "epoch": 0.92, - "learning_rate": 4.271557329267746e-06, - "loss": 0.133, + "epoch": 0.46, + "learning_rate": 2.7187087537191565e-05, + "loss": 0.1379, "step": 205040 }, { - "epoch": 0.92, - "learning_rate": 4.269315277341823e-06, - "loss": 0.1325, + "epoch": 0.46, + "learning_rate": 2.7185968993982243e-05, + "loss": 0.1381, "step": 205050 }, { - "epoch": 0.92, - "learning_rate": 4.267073225415901e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.7184850450772914e-05, + "loss": 0.1422, "step": 205060 }, { - "epoch": 0.92, - "learning_rate": 4.264831173489979e-06, - "loss": 0.146, + "epoch": 0.46, + "learning_rate": 2.7183731907563592e-05, + "loss": 0.1346, "step": 205070 }, { - "epoch": 0.92, - "learning_rate": 4.262589121564056e-06, - "loss": 0.1354, + "epoch": 0.46, + "learning_rate": 2.7182613364354263e-05, + "loss": 0.1366, "step": 205080 }, { - "epoch": 0.92, - "learning_rate": 4.260347069638133e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.718149482114494e-05, + "loss": 0.1396, "step": 205090 }, { - "epoch": 0.92, - "learning_rate": 4.2581050177122105e-06, - "loss": 0.1375, + "epoch": 0.46, + "learning_rate": 2.7180376277935616e-05, + "loss": 0.14, "step": 205100 }, { - "epoch": 0.92, - "learning_rate": 4.2558629657862876e-06, - "loss": 0.1441, + "epoch": 0.46, + "learning_rate": 2.7179257734726294e-05, + "loss": 0.1383, "step": 205110 }, { - "epoch": 0.92, - "learning_rate": 4.253620913860365e-06, - "loss": 0.1388, + "epoch": 0.46, + "learning_rate": 2.717813919151697e-05, + "loss": 0.1402, "step": 205120 }, { - "epoch": 0.92, - "learning_rate": 4.2513788619344425e-06, - "loss": 0.1359, + "epoch": 0.46, + "learning_rate": 2.7177020648307643e-05, + "loss": 0.1383, "step": 205130 }, { - "epoch": 0.92, - "learning_rate": 4.24913681000852e-06, - "loss": 0.1384, + "epoch": 0.46, + "learning_rate": 2.717590210509832e-05, + "loss": 0.144, "step": 205140 }, { - "epoch": 0.92, - "learning_rate": 4.246894758082597e-06, - "loss": 0.1416, + "epoch": 0.46, + "learning_rate": 2.7174783561888995e-05, + "loss": 0.1398, "step": 205150 }, { - "epoch": 0.92, - "learning_rate": 4.244652706156674e-06, - "loss": 0.1387, + "epoch": 0.46, + "learning_rate": 2.7173665018679673e-05, + "loss": 0.14, "step": 205160 }, { - "epoch": 0.92, - "learning_rate": 4.242410654230752e-06, - "loss": 0.1351, + "epoch": 0.46, + "learning_rate": 2.717254647547035e-05, + "loss": 0.1397, "step": 205170 }, { - "epoch": 0.92, - "learning_rate": 4.240168602304829e-06, - "loss": 0.1441, + "epoch": 0.46, + "learning_rate": 2.7171427932261022e-05, + "loss": 0.1392, "step": 205180 }, { - "epoch": 0.92, - "learning_rate": 4.237926550378907e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.71703093890517e-05, + "loss": 0.1399, "step": 205190 }, { - "epoch": 0.92, - "learning_rate": 4.235684498452985e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.7169190845842375e-05, + "loss": 0.1401, "step": 205200 }, { - "epoch": 0.92, - "learning_rate": 4.233442446527062e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7168072302633053e-05, + "loss": 0.138, "step": 205210 }, { - "epoch": 0.92, - "learning_rate": 4.231200394601139e-06, - "loss": 0.1384, + "epoch": 0.46, + "learning_rate": 2.716695375942373e-05, + "loss": 0.1373, "step": 205220 }, { - "epoch": 0.92, - "learning_rate": 4.228958342675217e-06, - "loss": 0.1396, + "epoch": 0.46, + "learning_rate": 2.71658352162144e-05, + "loss": 0.1369, "step": 205230 }, { - "epoch": 0.92, - "learning_rate": 4.226716290749294e-06, - "loss": 0.1362, + "epoch": 0.46, + "learning_rate": 2.716471667300508e-05, + "loss": 0.1389, "step": 205240 }, { - "epoch": 0.92, - "learning_rate": 4.224474238823371e-06, - "loss": 0.1357, + "epoch": 0.46, + "learning_rate": 2.7163598129795754e-05, + "loss": 0.1371, "step": 205250 }, { - "epoch": 0.92, - "learning_rate": 4.222232186897449e-06, - "loss": 0.1407, + "epoch": 0.46, + "learning_rate": 2.7162479586586432e-05, + "loss": 0.1369, "step": 205260 }, { - "epoch": 0.92, - "learning_rate": 4.219990134971527e-06, - "loss": 0.1371, + "epoch": 0.46, + "learning_rate": 2.716136104337711e-05, + "loss": 0.1351, "step": 205270 }, { - "epoch": 0.92, - "learning_rate": 4.217748083045604e-06, - "loss": 0.1406, + "epoch": 0.46, + "learning_rate": 2.716024250016778e-05, + "loss": 0.1384, "step": 205280 }, { - "epoch": 0.92, - "learning_rate": 4.215506031119681e-06, - "loss": 0.1443, + "epoch": 0.46, + "learning_rate": 2.715912395695846e-05, + "loss": 0.137, "step": 205290 }, { - "epoch": 0.92, - "learning_rate": 4.213263979193759e-06, - "loss": 0.1357, + "epoch": 0.46, + "learning_rate": 2.7158005413749134e-05, + "loss": 0.1375, "step": 205300 }, { - "epoch": 0.92, - "learning_rate": 4.211021927267836e-06, - "loss": 0.1353, + "epoch": 0.46, + "learning_rate": 2.715688687053981e-05, + "loss": 0.1394, "step": 205310 }, { - "epoch": 0.92, - "learning_rate": 4.208779875341913e-06, - "loss": 0.1374, + "epoch": 0.46, + "learning_rate": 2.715576832733049e-05, + "loss": 0.1378, "step": 205320 }, { - "epoch": 0.92, - "learning_rate": 4.2065378234159905e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.715464978412116e-05, + "loss": 0.1391, "step": 205330 }, { - "epoch": 0.92, - "learning_rate": 4.204295771490068e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.715353124091184e-05, + "loss": 0.1404, "step": 205340 }, { - "epoch": 0.92, - "learning_rate": 4.2020537195641454e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.7152412697702513e-05, + "loss": 0.1397, "step": 205350 }, { - "epoch": 0.92, - "learning_rate": 4.1998116676382225e-06, - "loss": 0.1399, + "epoch": 0.46, + "learning_rate": 2.715129415449319e-05, + "loss": 0.1371, "step": 205360 }, { - "epoch": 0.92, - "learning_rate": 4.1975696157123e-06, - "loss": 0.1407, + "epoch": 0.46, + "learning_rate": 2.715017561128387e-05, + "loss": 0.1359, "step": 205370 }, { - "epoch": 0.92, - "learning_rate": 4.195327563786377e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.714905706807454e-05, + "loss": 0.1386, "step": 205380 }, { - "epoch": 0.92, - "learning_rate": 4.193085511860454e-06, - "loss": 0.142, + "epoch": 0.46, + "learning_rate": 2.7147938524865218e-05, + "loss": 0.1388, "step": 205390 }, { - "epoch": 0.92, - "learning_rate": 4.190843459934532e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.7146819981655893e-05, + "loss": 0.1431, "step": 205400 }, { - "epoch": 0.92, - "learning_rate": 4.18860140800861e-06, - "loss": 0.1363, + "epoch": 0.46, + "learning_rate": 2.714570143844657e-05, + "loss": 0.142, "step": 205410 }, { - "epoch": 0.92, - "learning_rate": 4.186359356082687e-06, - "loss": 0.1409, + "epoch": 0.46, + "learning_rate": 2.714458289523724e-05, + "loss": 0.1386, "step": 205420 }, { - "epoch": 0.92, - "learning_rate": 4.184117304156764e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.714346435202792e-05, + "loss": 0.1431, "step": 205430 }, { - "epoch": 0.92, - "learning_rate": 4.181875252230842e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.7142345808818598e-05, + "loss": 0.1395, "step": 205440 }, { - "epoch": 0.92, - "learning_rate": 4.179633200304919e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.714122726560927e-05, + "loss": 0.1421, "step": 205450 }, { - "epoch": 0.92, - "learning_rate": 4.177391148378997e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.714010872239995e-05, + "loss": 0.135, "step": 205460 }, { - "epoch": 0.92, - "learning_rate": 4.175149096453074e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.713899017919062e-05, + "loss": 0.1383, "step": 205470 }, { - "epoch": 0.92, - "learning_rate": 4.172907044527152e-06, - "loss": 0.1402, + "epoch": 0.46, + "learning_rate": 2.71378716359813e-05, + "loss": 0.1403, "step": 205480 }, { - "epoch": 0.92, - "learning_rate": 4.170664992601229e-06, - "loss": 0.1457, + "epoch": 0.46, + "learning_rate": 2.7136753092771977e-05, + "loss": 0.1386, "step": 205490 }, { - "epoch": 0.92, - "learning_rate": 4.168422940675306e-06, - "loss": 0.1352, + "epoch": 0.46, + "learning_rate": 2.7135634549562648e-05, + "loss": 0.139, "step": 205500 }, { - "epoch": 0.92, - "learning_rate": 4.166180888749384e-06, - "loss": 0.1355, + "epoch": 0.46, + "learning_rate": 2.7134516006353326e-05, + "loss": 0.1367, "step": 205510 }, { - "epoch": 0.92, - "learning_rate": 4.163938836823461e-06, - "loss": 0.1348, + "epoch": 0.46, + "learning_rate": 2.7133397463144e-05, + "loss": 0.1397, "step": 205520 }, { - "epoch": 0.92, - "learning_rate": 4.161696784897539e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.713227891993468e-05, + "loss": 0.1348, "step": 205530 }, { - "epoch": 0.92, - "learning_rate": 4.159454732971616e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7131160376725356e-05, + "loss": 0.1388, "step": 205540 }, { - "epoch": 0.92, - "learning_rate": 4.1572126810456935e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7130041833516028e-05, + "loss": 0.1409, "step": 205550 }, { - "epoch": 0.92, - "learning_rate": 4.1549706291197706e-06, - "loss": 0.1432, + "epoch": 0.46, + "learning_rate": 2.7128923290306706e-05, + "loss": 0.1409, "step": 205560 }, { - "epoch": 0.92, - "learning_rate": 4.152728577193848e-06, - "loss": 0.1309, + "epoch": 0.46, + "learning_rate": 2.712780474709738e-05, + "loss": 0.1314, "step": 205570 }, { - "epoch": 0.92, - "learning_rate": 4.1504865252679255e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.7126686203888058e-05, + "loss": 0.1364, "step": 205580 }, { - "epoch": 0.92, - "learning_rate": 4.1482444733420025e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7125567660678736e-05, + "loss": 0.1431, "step": 205590 }, { - "epoch": 0.92, - "learning_rate": 4.14600242141608e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.7124449117469407e-05, + "loss": 0.1341, "step": 205600 }, { - "epoch": 0.92, - "learning_rate": 4.143760369490158e-06, - "loss": 0.1426, + "epoch": 0.46, + "learning_rate": 2.7123330574260085e-05, + "loss": 0.1435, "step": 205610 }, { - "epoch": 0.92, - "learning_rate": 4.141518317564235e-06, - "loss": 0.1386, + "epoch": 0.46, + "learning_rate": 2.712221203105076e-05, + "loss": 0.1411, "step": 205620 }, { - "epoch": 0.92, - "learning_rate": 4.139276265638312e-06, - "loss": 0.1402, + "epoch": 0.46, + "learning_rate": 2.7121093487841437e-05, + "loss": 0.1383, "step": 205630 }, { - "epoch": 0.92, - "learning_rate": 4.137034213712389e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.7119974944632115e-05, + "loss": 0.1345, "step": 205640 }, { - "epoch": 0.92, - "learning_rate": 4.134792161786467e-06, - "loss": 0.1356, + "epoch": 0.46, + "learning_rate": 2.7118856401422787e-05, + "loss": 0.1389, "step": 205650 }, { - "epoch": 0.92, - "learning_rate": 4.132550109860544e-06, - "loss": 0.1386, + "epoch": 0.46, + "learning_rate": 2.7117737858213464e-05, + "loss": 0.1367, "step": 205660 }, { - "epoch": 0.92, - "learning_rate": 4.130308057934622e-06, - "loss": 0.133, + "epoch": 0.46, + "learning_rate": 2.711661931500414e-05, + "loss": 0.1356, "step": 205670 }, { - "epoch": 0.92, - "learning_rate": 4.1280660060087e-06, - "loss": 0.1354, + "epoch": 0.46, + "learning_rate": 2.7115500771794817e-05, + "loss": 0.1363, "step": 205680 }, { - "epoch": 0.92, - "learning_rate": 4.125823954082777e-06, - "loss": 0.1452, + "epoch": 0.46, + "learning_rate": 2.7114382228585495e-05, + "loss": 0.1441, "step": 205690 }, { - "epoch": 0.92, - "learning_rate": 4.123581902156854e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7113263685376166e-05, + "loss": 0.1436, "step": 205700 }, { - "epoch": 0.92, - "learning_rate": 4.121339850230931e-06, - "loss": 0.1394, + "epoch": 0.46, + "learning_rate": 2.7112145142166844e-05, + "loss": 0.1351, "step": 205710 }, { - "epoch": 0.92, - "learning_rate": 4.119097798305009e-06, - "loss": 0.143, + "epoch": 0.46, + "learning_rate": 2.711102659895752e-05, + "loss": 0.1371, "step": 205720 }, { - "epoch": 0.92, - "learning_rate": 4.116855746379087e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7109908055748196e-05, + "loss": 0.1378, "step": 205730 }, { - "epoch": 0.92, - "learning_rate": 4.114613694453164e-06, - "loss": 0.1387, + "epoch": 0.46, + "learning_rate": 2.7108789512538868e-05, + "loss": 0.1383, "step": 205740 }, { - "epoch": 0.92, - "learning_rate": 4.112371642527242e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7107670969329546e-05, + "loss": 0.1387, "step": 205750 }, { - "epoch": 0.92, - "learning_rate": 4.110129590601319e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.7106552426120223e-05, + "loss": 0.1413, "step": 205760 }, { - "epoch": 0.92, - "learning_rate": 4.107887538675396e-06, - "loss": 0.1422, + "epoch": 0.46, + "learning_rate": 2.7105433882910898e-05, + "loss": 0.1383, "step": 205770 }, { - "epoch": 0.92, - "learning_rate": 4.105645486749473e-06, - "loss": 0.1335, + "epoch": 0.46, + "learning_rate": 2.7104315339701576e-05, + "loss": 0.1413, "step": 205780 }, { - "epoch": 0.92, - "learning_rate": 4.103403434823551e-06, - "loss": 0.13, + "epoch": 0.46, + "learning_rate": 2.7103196796492247e-05, + "loss": 0.1391, "step": 205790 }, { - "epoch": 0.92, - "learning_rate": 4.1011613828976285e-06, - "loss": 0.1374, + "epoch": 0.46, + "learning_rate": 2.7102078253282925e-05, + "loss": 0.1427, "step": 205800 }, { - "epoch": 0.92, - "learning_rate": 4.0989193309717055e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.7100959710073603e-05, + "loss": 0.1347, "step": 205810 }, { - "epoch": 0.92, - "learning_rate": 4.096677279045783e-06, - "loss": 0.1337, + "epoch": 0.46, + "learning_rate": 2.7099841166864277e-05, + "loss": 0.1353, "step": 205820 }, { - "epoch": 0.92, - "learning_rate": 4.09443522711986e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7098722623654955e-05, + "loss": 0.1408, "step": 205830 }, { - "epoch": 0.92, - "learning_rate": 4.092193175193937e-06, - "loss": 0.1415, + "epoch": 0.46, + "learning_rate": 2.7097604080445627e-05, + "loss": 0.1405, "step": 205840 }, { - "epoch": 0.92, - "learning_rate": 4.089951123268014e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.7096485537236304e-05, + "loss": 0.136, "step": 205850 }, { - "epoch": 0.92, - "learning_rate": 4.087709071342092e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7095366994026982e-05, + "loss": 0.1332, "step": 205860 }, { - "epoch": 0.92, - "learning_rate": 4.08546701941617e-06, - "loss": 0.1422, + "epoch": 0.46, + "learning_rate": 2.7094248450817657e-05, + "loss": 0.1372, "step": 205870 }, { - "epoch": 0.92, - "learning_rate": 4.083224967490247e-06, - "loss": 0.1422, + "epoch": 0.46, + "learning_rate": 2.7093129907608335e-05, + "loss": 0.136, "step": 205880 }, { - "epoch": 0.92, - "learning_rate": 4.080982915564325e-06, - "loss": 0.1362, + "epoch": 0.46, + "learning_rate": 2.709212321871994e-05, + "loss": 0.1389, "step": 205890 }, { - "epoch": 0.92, - "learning_rate": 4.078740863638402e-06, - "loss": 0.134, + "epoch": 0.46, + "learning_rate": 2.7091004675510618e-05, + "loss": 0.1389, "step": 205900 }, { - "epoch": 0.92, - "learning_rate": 4.076498811712479e-06, - "loss": 0.1359, + "epoch": 0.46, + "learning_rate": 2.708988613230129e-05, + "loss": 0.1387, "step": 205910 }, { - "epoch": 0.92, - "learning_rate": 4.074256759786557e-06, - "loss": 0.1432, + "epoch": 0.46, + "learning_rate": 2.7088767589091967e-05, + "loss": 0.1434, "step": 205920 }, { - "epoch": 0.92, - "learning_rate": 4.072014707860634e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.7087649045882645e-05, + "loss": 0.1369, "step": 205930 }, { - "epoch": 0.92, - "learning_rate": 4.069772655934712e-06, - "loss": 0.1354, + "epoch": 0.46, + "learning_rate": 2.708653050267332e-05, + "loss": 0.14, "step": 205940 }, { - "epoch": 0.92, - "learning_rate": 4.067530604008789e-06, - "loss": 0.1335, + "epoch": 0.46, + "learning_rate": 2.7085411959463998e-05, + "loss": 0.1396, "step": 205950 }, { - "epoch": 0.92, - "learning_rate": 4.065288552082867e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.708429341625467e-05, + "loss": 0.1419, "step": 205960 }, { - "epoch": 0.92, - "learning_rate": 4.063046500156944e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.7083174873045347e-05, + "loss": 0.1351, "step": 205970 }, { - "epoch": 0.92, - "learning_rate": 4.060804448231021e-06, - "loss": 0.1439, + "epoch": 0.46, + "learning_rate": 2.7082056329836025e-05, + "loss": 0.1354, "step": 205980 }, { - "epoch": 0.92, - "learning_rate": 4.058562396305099e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.70809377866267e-05, + "loss": 0.1387, "step": 205990 }, { - "epoch": 0.92, - "learning_rate": 4.0563203443791765e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.7079819243417377e-05, + "loss": 0.1324, "step": 206000 }, { - "epoch": 0.92, - "learning_rate": 4.0540782924532536e-06, - "loss": 0.1465, + "epoch": 0.46, + "learning_rate": 2.7078700700208048e-05, + "loss": 0.1392, "step": 206010 }, { - "epoch": 0.92, - "learning_rate": 4.051836240527331e-06, - "loss": 0.1396, + "epoch": 0.46, + "learning_rate": 2.7077582156998726e-05, + "loss": 0.1424, "step": 206020 }, { - "epoch": 0.92, - "learning_rate": 4.0495941886014085e-06, - "loss": 0.1404, + "epoch": 0.46, + "learning_rate": 2.7076463613789404e-05, + "loss": 0.1402, "step": 206030 }, { - "epoch": 0.92, - "learning_rate": 4.0473521366754855e-06, - "loss": 0.1379, + "epoch": 0.46, + "learning_rate": 2.707534507058008e-05, + "loss": 0.1406, "step": 206040 }, { - "epoch": 0.92, - "learning_rate": 4.0451100847495625e-06, - "loss": 0.1381, + "epoch": 0.46, + "learning_rate": 2.7074226527370757e-05, + "loss": 0.1406, "step": 206050 }, { - "epoch": 0.92, - "learning_rate": 4.04286803282364e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.7073107984161428e-05, + "loss": 0.1434, "step": 206060 }, { - "epoch": 0.92, - "learning_rate": 4.040625980897718e-06, - "loss": 0.1398, + "epoch": 0.46, + "learning_rate": 2.7071989440952106e-05, + "loss": 0.1432, "step": 206070 }, { - "epoch": 0.92, - "learning_rate": 4.038383928971795e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7070870897742784e-05, + "loss": 0.1415, "step": 206080 }, { - "epoch": 0.92, - "learning_rate": 4.036141877045872e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.7069752354533455e-05, + "loss": 0.1399, "step": 206090 }, { - "epoch": 0.92, - "learning_rate": 4.03389982511995e-06, - "loss": 0.1342, + "epoch": 0.46, + "learning_rate": 2.7068633811324136e-05, + "loss": 0.138, "step": 206100 }, { - "epoch": 0.92, - "learning_rate": 4.031657773194027e-06, - "loss": 0.1336, + "epoch": 0.46, + "learning_rate": 2.7067515268114807e-05, + "loss": 0.1394, "step": 206110 }, { - "epoch": 0.92, - "learning_rate": 4.029415721268104e-06, - "loss": 0.1377, + "epoch": 0.46, + "learning_rate": 2.7066396724905485e-05, + "loss": 0.1397, "step": 206120 }, { - "epoch": 0.92, - "learning_rate": 4.027173669342182e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.7065278181696156e-05, + "loss": 0.1366, "step": 206130 }, { - "epoch": 0.92, - "learning_rate": 4.02493161741626e-06, - "loss": 0.1415, + "epoch": 0.46, + "learning_rate": 2.7064159638486834e-05, + "loss": 0.1382, "step": 206140 }, { - "epoch": 0.92, - "learning_rate": 4.022689565490337e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7063041095277512e-05, + "loss": 0.1379, "step": 206150 }, { - "epoch": 0.92, - "learning_rate": 4.020447513564414e-06, - "loss": 0.1336, + "epoch": 0.46, + "learning_rate": 2.7061922552068187e-05, + "loss": 0.1415, "step": 206160 }, { - "epoch": 0.92, - "learning_rate": 4.018205461638492e-06, - "loss": 0.1335, + "epoch": 0.46, + "learning_rate": 2.7060804008858865e-05, + "loss": 0.1371, "step": 206170 }, { - "epoch": 0.92, - "learning_rate": 4.015963409712569e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7059685465649536e-05, + "loss": 0.1423, "step": 206180 }, { - "epoch": 0.92, - "learning_rate": 4.013721357786646e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.7058566922440214e-05, + "loss": 0.1354, "step": 206190 }, { - "epoch": 0.92, - "learning_rate": 4.011479305860724e-06, - "loss": 0.1351, + "epoch": 0.46, + "learning_rate": 2.705744837923089e-05, + "loss": 0.1383, "step": 206200 }, { - "epoch": 0.92, - "learning_rate": 4.009237253934802e-06, - "loss": 0.1393, + "epoch": 0.46, + "learning_rate": 2.7056329836021566e-05, + "loss": 0.1444, "step": 206210 }, { - "epoch": 0.92, - "learning_rate": 4.006995202008879e-06, - "loss": 0.1359, + "epoch": 0.46, + "learning_rate": 2.7055211292812244e-05, + "loss": 0.1392, "step": 206220 }, { - "epoch": 0.92, - "learning_rate": 4.0047531500829566e-06, + "epoch": 0.46, + "learning_rate": 2.7054092749602915e-05, "loss": 0.1373, "step": 206230 }, { - "epoch": 0.92, - "learning_rate": 4.002511098157034e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.7052974206393593e-05, + "loss": 0.1428, "step": 206240 }, { - "epoch": 0.92, - "learning_rate": 4.000269046231111e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.705185566318427e-05, + "loss": 0.1399, "step": 206250 }, { - "epoch": 0.92, - "learning_rate": 3.998026994305188e-06, - "loss": 0.1401, + "epoch": 0.46, + "learning_rate": 2.7050737119974946e-05, + "loss": 0.138, "step": 206260 }, { - "epoch": 0.92, - "learning_rate": 3.9957849423792655e-06, - "loss": 0.1381, + "epoch": 0.46, + "learning_rate": 2.7049618576765624e-05, + "loss": 0.1342, "step": 206270 }, { - "epoch": 0.92, - "learning_rate": 3.993542890453343e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.7048500033556295e-05, + "loss": 0.135, "step": 206280 }, { - "epoch": 0.92, - "learning_rate": 3.99130083852742e-06, - "loss": 0.1424, + "epoch": 0.46, + "learning_rate": 2.7047381490346973e-05, + "loss": 0.135, "step": 206290 }, { - "epoch": 0.92, - "learning_rate": 3.989058786601498e-06, - "loss": 0.1431, + "epoch": 0.46, + "learning_rate": 2.704626294713765e-05, + "loss": 0.1423, "step": 206300 }, { - "epoch": 0.92, - "learning_rate": 3.986816734675575e-06, - "loss": 0.1388, + "epoch": 0.46, + "learning_rate": 2.7045144403928325e-05, + "loss": 0.14, "step": 206310 }, { - "epoch": 0.92, - "learning_rate": 3.984574682749652e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.7044025860719003e-05, + "loss": 0.1382, "step": 206320 }, { - "epoch": 0.92, - "learning_rate": 3.98233263082373e-06, - "loss": 0.1388, + "epoch": 0.46, + "learning_rate": 2.7042907317509674e-05, + "loss": 0.1439, "step": 206330 }, { - "epoch": 0.92, - "learning_rate": 3.980090578897808e-06, - "loss": 0.1394, + "epoch": 0.46, + "learning_rate": 2.7041788774300352e-05, + "loss": 0.1382, "step": 206340 }, { - "epoch": 0.92, - "learning_rate": 3.977848526971885e-06, - "loss": 0.1349, + "epoch": 0.46, + "learning_rate": 2.704067023109103e-05, + "loss": 0.1414, "step": 206350 }, { - "epoch": 0.92, - "learning_rate": 3.975606475045962e-06, - "loss": 0.1399, + "epoch": 0.46, + "learning_rate": 2.7039551687881705e-05, + "loss": 0.1404, "step": 206360 }, { - "epoch": 0.92, - "learning_rate": 3.97336442312004e-06, - "loss": 0.1388, + "epoch": 0.46, + "learning_rate": 2.7038433144672383e-05, + "loss": 0.1396, "step": 206370 }, { - "epoch": 0.92, - "learning_rate": 3.971122371194117e-06, - "loss": 0.1412, + "epoch": 0.46, + "learning_rate": 2.7037314601463054e-05, + "loss": 0.1386, "step": 206380 }, { - "epoch": 0.92, - "learning_rate": 3.968880319268194e-06, - "loss": 0.1415, + "epoch": 0.46, + "learning_rate": 2.703619605825373e-05, + "loss": 0.1386, "step": 206390 }, { - "epoch": 0.92, - "learning_rate": 3.966638267342272e-06, - "loss": 0.1375, + "epoch": 0.46, + "learning_rate": 2.703507751504441e-05, + "loss": 0.1365, "step": 206400 }, { - "epoch": 0.92, - "learning_rate": 3.96439621541635e-06, - "loss": 0.1409, + "epoch": 0.46, + "learning_rate": 2.7033958971835084e-05, + "loss": 0.1399, "step": 206410 }, { - "epoch": 0.92, - "learning_rate": 3.962154163490427e-06, - "loss": 0.1346, + "epoch": 0.46, + "learning_rate": 2.7032840428625762e-05, + "loss": 0.1341, "step": 206420 }, { - "epoch": 0.92, - "learning_rate": 3.959912111564504e-06, - "loss": 0.1394, + "epoch": 0.46, + "learning_rate": 2.7031721885416433e-05, + "loss": 0.14, "step": 206430 }, { - "epoch": 0.92, - "learning_rate": 3.957670059638582e-06, - "loss": 0.1348, + "epoch": 0.46, + "learning_rate": 2.703060334220711e-05, + "loss": 0.1385, "step": 206440 }, { - "epoch": 0.92, - "learning_rate": 3.955428007712659e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.7029484798997786e-05, + "loss": 0.1398, "step": 206450 }, { - "epoch": 0.92, - "learning_rate": 3.953185955786736e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.7028366255788464e-05, + "loss": 0.1354, "step": 206460 }, { - "epoch": 0.92, - "learning_rate": 3.950943903860814e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.702724771257914e-05, + "loss": 0.1433, "step": 206470 }, { - "epoch": 0.92, - "learning_rate": 3.9487018519348915e-06, - "loss": 0.1317, + "epoch": 0.46, + "learning_rate": 2.7026129169369813e-05, + "loss": 0.1363, "step": 206480 }, { - "epoch": 0.92, - "learning_rate": 3.9464598000089685e-06, - "loss": 0.1349, + "epoch": 0.46, + "learning_rate": 2.702501062616049e-05, + "loss": 0.1332, "step": 206490 }, { - "epoch": 0.92, - "learning_rate": 3.9442177480830455e-06, - "loss": 0.134, + "epoch": 0.46, + "learning_rate": 2.702389208295116e-05, + "loss": 0.1347, "step": 206500 }, { - "epoch": 0.92, - "learning_rate": 3.941975696157123e-06, - "loss": 0.1405, + "epoch": 0.46, + "learning_rate": 2.7022773539741843e-05, + "loss": 0.1423, "step": 206510 }, { - "epoch": 0.92, - "learning_rate": 3.9397336442312e-06, - "loss": 0.1452, + "epoch": 0.46, + "learning_rate": 2.702165499653252e-05, + "loss": 0.1393, "step": 206520 }, { - "epoch": 0.92, - "learning_rate": 3.9374915923052774e-06, - "loss": 0.1358, + "epoch": 0.46, + "learning_rate": 2.7020536453323192e-05, + "loss": 0.1385, "step": 206530 }, { - "epoch": 0.92, - "learning_rate": 3.935249540379355e-06, - "loss": 0.1405, + "epoch": 0.46, + "learning_rate": 2.701941791011387e-05, + "loss": 0.1351, "step": 206540 }, { - "epoch": 0.92, - "learning_rate": 3.933007488453433e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.701829936690454e-05, + "loss": 0.1351, "step": 206550 }, { - "epoch": 0.92, - "learning_rate": 3.93076543652751e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.701718082369522e-05, + "loss": 0.1414, "step": 206560 }, { - "epoch": 0.92, - "learning_rate": 3.928523384601587e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.70160622804859e-05, + "loss": 0.1403, "step": 206570 }, { - "epoch": 0.92, - "learning_rate": 3.926281332675665e-06, - "loss": 0.147, + "epoch": 0.46, + "learning_rate": 2.701494373727657e-05, + "loss": 0.1394, "step": 206580 }, { - "epoch": 0.92, - "learning_rate": 3.924039280749742e-06, - "loss": 0.1369, + "epoch": 0.46, + "learning_rate": 2.701382519406725e-05, + "loss": 0.1349, "step": 206590 }, { - "epoch": 0.92, - "learning_rate": 3.92179722882382e-06, - "loss": 0.1286, + "epoch": 0.46, + "learning_rate": 2.701270665085792e-05, + "loss": 0.1402, "step": 206600 }, { - "epoch": 0.92, - "learning_rate": 3.919555176897898e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.70115881076486e-05, + "loss": 0.1398, "step": 206610 }, { - "epoch": 0.92, - "learning_rate": 3.917313124971975e-06, - "loss": 0.1333, + "epoch": 0.46, + "learning_rate": 2.7010469564439276e-05, + "loss": 0.1334, "step": 206620 }, { - "epoch": 0.92, - "learning_rate": 3.915071073046052e-06, - "loss": 0.1315, + "epoch": 0.46, + "learning_rate": 2.700935102122995e-05, + "loss": 0.1349, "step": 206630 }, { - "epoch": 0.92, - "learning_rate": 3.912829021120129e-06, - "loss": 0.1365, + "epoch": 0.46, + "learning_rate": 2.700823247802063e-05, + "loss": 0.1402, "step": 206640 }, { - "epoch": 0.92, - "learning_rate": 3.910586969194207e-06, - "loss": 0.1332, + "epoch": 0.46, + "learning_rate": 2.70071139348113e-05, + "loss": 0.1319, "step": 206650 }, { - "epoch": 0.92, - "learning_rate": 3.908344917268284e-06, - "loss": 0.1354, + "epoch": 0.46, + "learning_rate": 2.7005995391601978e-05, + "loss": 0.1385, "step": 206660 }, { - "epoch": 0.92, - "learning_rate": 3.906102865342362e-06, - "loss": 0.1425, + "epoch": 0.46, + "learning_rate": 2.7004876848392656e-05, + "loss": 0.1382, "step": 206670 }, { - "epoch": 0.92, - "learning_rate": 3.9038608134164396e-06, - "loss": 0.1442, + "epoch": 0.46, + "learning_rate": 2.700375830518333e-05, + "loss": 0.1366, "step": 206680 }, { - "epoch": 0.92, - "learning_rate": 3.901618761490517e-06, - "loss": 0.1363, + "epoch": 0.46, + "learning_rate": 2.700263976197401e-05, + "loss": 0.1398, "step": 206690 }, { - "epoch": 0.92, - "learning_rate": 3.899376709564594e-06, - "loss": 0.1344, + "epoch": 0.46, + "learning_rate": 2.700152121876468e-05, + "loss": 0.136, "step": 206700 }, { - "epoch": 0.92, - "learning_rate": 3.897134657638671e-06, - "loss": 0.1347, + "epoch": 0.46, + "learning_rate": 2.7000402675555358e-05, + "loss": 0.1386, "step": 206710 }, { - "epoch": 0.92, - "learning_rate": 3.8948926057127485e-06, - "loss": 0.1404, + "epoch": 0.46, + "learning_rate": 2.6999284132346032e-05, + "loss": 0.1397, "step": 206720 }, { - "epoch": 0.92, - "learning_rate": 3.8926505537868255e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.699816558913671e-05, + "loss": 0.1406, "step": 206730 }, { - "epoch": 0.92, - "learning_rate": 3.890408501860903e-06, - "loss": 0.133, + "epoch": 0.46, + "learning_rate": 2.6997047045927388e-05, + "loss": 0.1375, "step": 206740 }, { - "epoch": 0.92, - "learning_rate": 3.888166449934981e-06, - "loss": 0.1418, + "epoch": 0.46, + "learning_rate": 2.699592850271806e-05, + "loss": 0.1384, "step": 206750 }, { - "epoch": 0.92, - "learning_rate": 3.885924398009058e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.6994809959508737e-05, + "loss": 0.1391, "step": 206760 }, { - "epoch": 0.92, - "learning_rate": 3.883682346083135e-06, - "loss": 0.1373, + "epoch": 0.46, + "learning_rate": 2.699369141629941e-05, + "loss": 0.1385, "step": 206770 }, { - "epoch": 0.92, - "learning_rate": 3.881440294157212e-06, - "loss": 0.1369, + "epoch": 0.46, + "learning_rate": 2.699257287309009e-05, + "loss": 0.1371, "step": 206780 }, { - "epoch": 0.92, - "learning_rate": 3.87919824223129e-06, - "loss": 0.132, + "epoch": 0.46, + "learning_rate": 2.6991454329880767e-05, + "loss": 0.1371, "step": 206790 }, { - "epoch": 0.92, - "learning_rate": 3.876956190305367e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.699033578667144e-05, + "loss": 0.1415, "step": 206800 }, { - "epoch": 0.92, - "learning_rate": 3.874714138379445e-06, - "loss": 0.1342, + "epoch": 0.46, + "learning_rate": 2.6989217243462116e-05, + "loss": 0.1392, "step": 206810 }, { - "epoch": 0.92, - "learning_rate": 3.872472086453523e-06, - "loss": 0.1337, + "epoch": 0.46, + "learning_rate": 2.698809870025279e-05, + "loss": 0.1372, "step": 206820 }, { - "epoch": 0.92, - "learning_rate": 3.8702300345276e-06, - "loss": 0.1401, + "epoch": 0.46, + "learning_rate": 2.698698015704347e-05, + "loss": 0.1382, "step": 206830 }, { - "epoch": 0.92, - "learning_rate": 3.867987982601677e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.6985861613834147e-05, + "loss": 0.1339, "step": 206840 }, { - "epoch": 0.92, - "learning_rate": 3.865745930675754e-06, - "loss": 0.1389, + "epoch": 0.46, + "learning_rate": 2.6984743070624818e-05, + "loss": 0.1374, "step": 206850 }, { - "epoch": 0.92, - "learning_rate": 3.863503878749832e-06, - "loss": 0.1332, + "epoch": 0.46, + "learning_rate": 2.6983624527415496e-05, + "loss": 0.1402, "step": 206860 }, { - "epoch": 0.92, - "learning_rate": 3.86126182682391e-06, - "loss": 0.1348, + "epoch": 0.46, + "learning_rate": 2.698250598420617e-05, + "loss": 0.1371, "step": 206870 }, { - "epoch": 0.92, - "learning_rate": 3.859019774897987e-06, - "loss": 0.1387, + "epoch": 0.46, + "learning_rate": 2.698138744099685e-05, + "loss": 0.1396, "step": 206880 }, { - "epoch": 0.92, - "learning_rate": 3.856777722972065e-06, - "loss": 0.1345, + "epoch": 0.46, + "learning_rate": 2.6980268897787526e-05, + "loss": 0.1368, "step": 206890 }, { - "epoch": 0.92, - "learning_rate": 3.854535671046142e-06, - "loss": 0.1387, + "epoch": 0.46, + "learning_rate": 2.6979150354578197e-05, + "loss": 0.1402, "step": 206900 }, { - "epoch": 0.92, - "learning_rate": 3.852293619120219e-06, - "loss": 0.1339, + "epoch": 0.46, + "learning_rate": 2.6978031811368875e-05, + "loss": 0.1407, "step": 206910 }, { - "epoch": 0.92, - "learning_rate": 3.850051567194297e-06, - "loss": 0.1339, + "epoch": 0.46, + "learning_rate": 2.6976913268159547e-05, + "loss": 0.1358, "step": 206920 }, { - "epoch": 0.92, - "learning_rate": 3.847809515268374e-06, - "loss": 0.1377, + "epoch": 0.46, + "learning_rate": 2.6975794724950228e-05, + "loss": 0.1421, "step": 206930 }, { - "epoch": 0.92, - "learning_rate": 3.8455674633424515e-06, - "loss": 0.1364, + "epoch": 0.46, + "learning_rate": 2.6974676181740906e-05, + "loss": 0.1368, "step": 206940 }, { - "epoch": 0.92, - "learning_rate": 3.8433254114165285e-06, - "loss": 0.1397, + "epoch": 0.46, + "learning_rate": 2.6973557638531577e-05, + "loss": 0.1393, "step": 206950 }, { - "epoch": 0.92, - "learning_rate": 3.841083359490606e-06, - "loss": 0.1363, + "epoch": 0.46, + "learning_rate": 2.6972439095322255e-05, + "loss": 0.142, "step": 206960 }, { - "epoch": 0.92, - "learning_rate": 3.838841307564683e-06, - "loss": 0.139, + "epoch": 0.46, + "learning_rate": 2.6971320552112926e-05, + "loss": 0.1358, "step": 206970 }, { - "epoch": 0.92, - "learning_rate": 3.8365992556387604e-06, - "loss": 0.1452, + "epoch": 0.46, + "learning_rate": 2.6970202008903604e-05, + "loss": 0.1397, "step": 206980 }, { - "epoch": 0.92, - "learning_rate": 3.834357203712838e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.6969083465694285e-05, + "loss": 0.1372, "step": 206990 }, { - "epoch": 0.92, - "learning_rate": 3.832115151786915e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.6967964922484956e-05, + "loss": 0.1351, "step": 207000 }, { - "epoch": 0.92, - "learning_rate": 3.829873099860993e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.6966846379275634e-05, + "loss": 0.1387, "step": 207010 }, { - "epoch": 0.92, - "learning_rate": 3.82763104793507e-06, - "loss": 0.1416, + "epoch": 0.46, + "learning_rate": 2.6965727836066306e-05, + "loss": 0.1328, "step": 207020 }, { - "epoch": 0.92, - "learning_rate": 3.825388996009148e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.6964609292856983e-05, + "loss": 0.1338, "step": 207030 }, { - "epoch": 0.92, - "learning_rate": 3.823146944083225e-06, - "loss": 0.1426, + "epoch": 0.46, + "learning_rate": 2.6963490749647658e-05, + "loss": 0.1371, "step": 207040 }, { - "epoch": 0.92, - "learning_rate": 3.820904892157302e-06, - "loss": 0.1405, + "epoch": 0.46, + "learning_rate": 2.6962372206438336e-05, + "loss": 0.1365, "step": 207050 }, { - "epoch": 0.92, - "learning_rate": 3.81866284023138e-06, - "loss": 0.1397, + "epoch": 0.46, + "learning_rate": 2.6961253663229014e-05, + "loss": 0.1382, "step": 207060 }, { - "epoch": 0.92, - "learning_rate": 3.816420788305457e-06, - "loss": 0.1359, + "epoch": 0.46, + "learning_rate": 2.6960135120019685e-05, + "loss": 0.142, "step": 207070 }, { - "epoch": 0.92, - "learning_rate": 3.8141787363795345e-06, - "loss": 0.1338, + "epoch": 0.46, + "learning_rate": 2.6959016576810363e-05, + "loss": 0.1409, "step": 207080 }, { - "epoch": 0.92, - "learning_rate": 3.811936684453612e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.6957898033601037e-05, + "loss": 0.1474, "step": 207090 }, { - "epoch": 0.92, - "learning_rate": 3.80969463252769e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.6956779490391715e-05, + "loss": 0.1372, "step": 207100 }, { - "epoch": 0.92, - "learning_rate": 3.807452580601767e-06, - "loss": 0.1343, + "epoch": 0.46, + "learning_rate": 2.6955660947182393e-05, + "loss": 0.1404, "step": 207110 }, { - "epoch": 0.92, - "learning_rate": 3.8052105286758443e-06, - "loss": 0.1397, + "epoch": 0.46, + "learning_rate": 2.6954542403973064e-05, + "loss": 0.1402, "step": 207120 }, { - "epoch": 0.92, - "learning_rate": 3.802968476749922e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.6953423860763742e-05, + "loss": 0.1391, "step": 207130 }, { - "epoch": 0.92, - "learning_rate": 3.800726424823999e-06, - "loss": 0.1347, + "epoch": 0.46, + "learning_rate": 2.6952305317554417e-05, + "loss": 0.1364, "step": 207140 }, { - "epoch": 0.92, - "learning_rate": 3.798484372898076e-06, - "loss": 0.1393, + "epoch": 0.46, + "learning_rate": 2.6951186774345095e-05, + "loss": 0.1403, "step": 207150 }, { - "epoch": 0.92, - "learning_rate": 3.7962423209721536e-06, - "loss": 0.1444, + "epoch": 0.46, + "learning_rate": 2.6950068231135773e-05, + "loss": 0.1393, "step": 207160 }, { - "epoch": 0.92, - "learning_rate": 3.7940002690462315e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.6948949687926444e-05, + "loss": 0.1418, "step": 207170 }, { - "epoch": 0.92, - "learning_rate": 3.7917582171203085e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.6947831144717122e-05, + "loss": 0.137, "step": 207180 }, { - "epoch": 0.92, - "learning_rate": 3.789516165194386e-06, - "loss": 0.1399, + "epoch": 0.46, + "learning_rate": 2.6946712601507796e-05, + "loss": 0.1405, "step": 207190 }, { - "epoch": 0.92, - "learning_rate": 3.787274113268464e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.6945594058298474e-05, + "loss": 0.1394, "step": 207200 }, { - "epoch": 0.93, - "learning_rate": 3.785032061342541e-06, - "loss": 0.1319, + "epoch": 0.46, + "learning_rate": 2.6944475515089152e-05, + "loss": 0.143, "step": 207210 }, { - "epoch": 0.93, - "learning_rate": 3.7827900094166183e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.6943356971879823e-05, + "loss": 0.1364, "step": 207220 }, { - "epoch": 0.93, - "learning_rate": 3.7805479574906954e-06, - "loss": 0.134, + "epoch": 0.46, + "learning_rate": 2.69422384286705e-05, + "loss": 0.1331, "step": 207230 }, { - "epoch": 0.93, - "learning_rate": 3.7783059055647732e-06, - "loss": 0.1356, + "epoch": 0.46, + "learning_rate": 2.6941119885461176e-05, + "loss": 0.1353, "step": 207240 }, { - "epoch": 0.93, - "learning_rate": 3.7760638536388502e-06, - "loss": 0.1357, + "epoch": 0.46, + "learning_rate": 2.6940001342251854e-05, + "loss": 0.1404, "step": 207250 }, { - "epoch": 0.93, - "learning_rate": 3.7738218017129277e-06, - "loss": 0.1336, + "epoch": 0.46, + "learning_rate": 2.6938882799042532e-05, + "loss": 0.1362, "step": 207260 }, { - "epoch": 0.93, - "learning_rate": 3.7715797497870056e-06, - "loss": 0.1366, + "epoch": 0.46, + "learning_rate": 2.6937764255833203e-05, + "loss": 0.1487, "step": 207270 }, { - "epoch": 0.93, - "learning_rate": 3.7693376978610826e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.693664571262388e-05, + "loss": 0.1372, "step": 207280 }, { - "epoch": 0.93, - "learning_rate": 3.76709564593516e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.6935527169414555e-05, + "loss": 0.1421, "step": 207290 }, { - "epoch": 0.93, - "learning_rate": 3.764853594009238e-06, - "loss": 0.1371, + "epoch": 0.46, + "learning_rate": 2.6934408626205233e-05, + "loss": 0.1406, "step": 207300 }, { - "epoch": 0.93, - "learning_rate": 3.762611542083315e-06, - "loss": 0.1353, + "epoch": 0.46, + "learning_rate": 2.693329008299591e-05, + "loss": 0.1346, "step": 207310 }, { - "epoch": 0.93, - "learning_rate": 3.760369490157392e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.6932171539786582e-05, + "loss": 0.1374, "step": 207320 }, { - "epoch": 0.93, - "learning_rate": 3.7581274382314694e-06, - "loss": 0.1393, + "epoch": 0.46, + "learning_rate": 2.693105299657726e-05, + "loss": 0.1382, "step": 207330 }, { - "epoch": 0.93, - "learning_rate": 3.7558853863055473e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.6929934453367935e-05, + "loss": 0.1384, "step": 207340 }, { - "epoch": 0.93, - "learning_rate": 3.7536433343796243e-06, - "loss": 0.1391, + "epoch": 0.46, + "learning_rate": 2.6928815910158613e-05, + "loss": 0.1374, "step": 207350 }, { - "epoch": 0.93, - "learning_rate": 3.7514012824537017e-06, - "loss": 0.1345, + "epoch": 0.46, + "learning_rate": 2.6927697366949284e-05, + "loss": 0.1382, "step": 207360 }, { - "epoch": 0.93, - "learning_rate": 3.7491592305277796e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.6926578823739962e-05, + "loss": 0.1352, "step": 207370 }, { - "epoch": 0.93, - "learning_rate": 3.7469171786018566e-06, - "loss": 0.1424, + "epoch": 0.46, + "learning_rate": 2.692546028053064e-05, + "loss": 0.1391, "step": 207380 }, { - "epoch": 0.93, - "learning_rate": 3.744675126675934e-06, - "loss": 0.1431, + "epoch": 0.46, + "learning_rate": 2.692434173732131e-05, + "loss": 0.1397, "step": 207390 }, { - "epoch": 0.93, - "learning_rate": 3.742433074750011e-06, - "loss": 0.1439, + "epoch": 0.46, + "learning_rate": 2.6923223194111992e-05, + "loss": 0.1361, "step": 207400 }, { - "epoch": 0.93, - "learning_rate": 3.740191022824089e-06, - "loss": 0.1358, + "epoch": 0.46, + "learning_rate": 2.6922104650902663e-05, + "loss": 0.1375, "step": 207410 }, { - "epoch": 0.93, - "learning_rate": 3.737948970898166e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.692098610769334e-05, + "loss": 0.1361, "step": 207420 }, { - "epoch": 0.93, - "learning_rate": 3.7357069189722435e-06, - "loss": 0.1351, + "epoch": 0.46, + "learning_rate": 2.691986756448402e-05, + "loss": 0.1374, "step": 207430 }, { - "epoch": 0.93, - "learning_rate": 3.7334648670463213e-06, - "loss": 0.1411, + "epoch": 0.46, + "learning_rate": 2.691874902127469e-05, + "loss": 0.1361, "step": 207440 }, { - "epoch": 0.93, - "learning_rate": 3.7312228151203983e-06, - "loss": 0.1421, + "epoch": 0.46, + "learning_rate": 2.6917630478065368e-05, + "loss": 0.1379, "step": 207450 }, { - "epoch": 0.93, - "learning_rate": 3.728980763194476e-06, - "loss": 0.1395, + "epoch": 0.46, + "learning_rate": 2.6916511934856043e-05, + "loss": 0.1393, "step": 207460 }, { - "epoch": 0.93, - "learning_rate": 3.726738711268553e-06, - "loss": 0.1414, + "epoch": 0.46, + "learning_rate": 2.691539339164672e-05, + "loss": 0.1356, "step": 207470 }, { - "epoch": 0.93, - "learning_rate": 3.7244966593426307e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.69142748484374e-05, + "loss": 0.1434, "step": 207480 }, { - "epoch": 0.93, - "learning_rate": 3.722254607416708e-06, - "loss": 0.1403, + "epoch": 0.46, + "learning_rate": 2.691315630522807e-05, + "loss": 0.1431, "step": 207490 }, { - "epoch": 0.93, - "learning_rate": 3.720012555490785e-06, - "loss": 0.1428, + "epoch": 0.46, + "learning_rate": 2.6912037762018748e-05, + "loss": 0.1356, "step": 207500 }, { - "epoch": 0.93, - "learning_rate": 3.717770503564863e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.6910919218809422e-05, + "loss": 0.1379, "step": 207510 }, { - "epoch": 0.93, - "learning_rate": 3.71552845163894e-06, - "loss": 0.1373, + "epoch": 0.46, + "learning_rate": 2.69098006756001e-05, + "loss": 0.1326, "step": 207520 }, { - "epoch": 0.93, - "learning_rate": 3.7135106049056095e-06, - "loss": 0.1322, + "epoch": 0.46, + "learning_rate": 2.6908682132390778e-05, + "loss": 0.1423, "step": 207530 }, { - "epoch": 0.93, - "learning_rate": 3.7112685529796874e-06, - "loss": 0.141, + "epoch": 0.46, + "learning_rate": 2.690756358918145e-05, + "loss": 0.1353, "step": 207540 }, { - "epoch": 0.93, - "learning_rate": 3.7090265010537644e-06, - "loss": 0.1381, + "epoch": 0.46, + "learning_rate": 2.6906445045972127e-05, + "loss": 0.1335, "step": 207550 }, { - "epoch": 0.93, - "learning_rate": 3.706784449127842e-06, - "loss": 0.1422, + "epoch": 0.46, + "learning_rate": 2.6905326502762802e-05, + "loss": 0.1362, "step": 207560 }, { - "epoch": 0.93, - "learning_rate": 3.7045423972019198e-06, - "loss": 0.1347, + "epoch": 0.46, + "learning_rate": 2.690420795955348e-05, + "loss": 0.1384, "step": 207570 }, { - "epoch": 0.93, - "learning_rate": 3.7023003452759968e-06, - "loss": 0.1337, + "epoch": 0.46, + "learning_rate": 2.6903089416344158e-05, + "loss": 0.142, "step": 207580 }, { - "epoch": 0.93, - "learning_rate": 3.7000582933500742e-06, - "loss": 0.1371, + "epoch": 0.46, + "learning_rate": 2.690197087313483e-05, + "loss": 0.1316, "step": 207590 }, { - "epoch": 0.93, - "learning_rate": 3.6978162414241512e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.6900852329925507e-05, + "loss": 0.1382, "step": 207600 }, { - "epoch": 0.93, - "learning_rate": 3.695574189498229e-06, - "loss": 0.1372, + "epoch": 0.46, + "learning_rate": 2.689973378671618e-05, + "loss": 0.1403, "step": 207610 }, { - "epoch": 0.93, - "learning_rate": 3.6933321375723066e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.689861524350686e-05, + "loss": 0.1346, "step": 207620 }, { - "epoch": 0.93, - "learning_rate": 3.6910900856463836e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.6897496700297537e-05, + "loss": 0.1395, "step": 207630 }, { - "epoch": 0.93, - "learning_rate": 3.6888480337204615e-06, - "loss": 0.1316, + "epoch": 0.46, + "learning_rate": 2.6896378157088208e-05, + "loss": 0.1362, "step": 207640 }, { - "epoch": 0.93, - "learning_rate": 3.6866059817945385e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.6895259613878886e-05, + "loss": 0.1315, "step": 207650 }, { - "epoch": 0.93, - "learning_rate": 3.684363929868616e-06, - "loss": 0.1412, + "epoch": 0.46, + "learning_rate": 2.689414107066956e-05, + "loss": 0.1405, "step": 207660 }, { - "epoch": 0.93, - "learning_rate": 3.682121877942693e-06, - "loss": 0.1357, + "epoch": 0.46, + "learning_rate": 2.689302252746024e-05, + "loss": 0.1349, "step": 207670 }, { - "epoch": 0.93, - "learning_rate": 3.679879826016771e-06, - "loss": 0.1353, + "epoch": 0.46, + "learning_rate": 2.689190398425091e-05, + "loss": 0.1402, "step": 207680 }, { - "epoch": 0.93, - "learning_rate": 3.6776377740908483e-06, - "loss": 0.1363, + "epoch": 0.46, + "learning_rate": 2.6890785441041588e-05, + "loss": 0.1373, "step": 207690 }, { - "epoch": 0.93, - "learning_rate": 3.6753957221649253e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.6889666897832266e-05, + "loss": 0.1408, "step": 207700 }, { - "epoch": 0.93, - "learning_rate": 3.673153670239003e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.688854835462294e-05, + "loss": 0.1425, "step": 207710 }, { - "epoch": 0.93, - "learning_rate": 3.67091161831308e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.6887429811413618e-05, + "loss": 0.1393, "step": 207720 }, { - "epoch": 0.93, - "learning_rate": 3.6686695663871576e-06, - "loss": 0.1368, + "epoch": 0.46, + "learning_rate": 2.688631126820429e-05, + "loss": 0.1358, "step": 207730 }, { - "epoch": 0.93, - "learning_rate": 3.6664275144612347e-06, - "loss": 0.1342, + "epoch": 0.46, + "learning_rate": 2.6885192724994967e-05, + "loss": 0.1367, "step": 207740 }, { - "epoch": 0.93, - "learning_rate": 3.6641854625353125e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.6884074181785645e-05, + "loss": 0.1355, "step": 207750 }, { - "epoch": 0.93, - "learning_rate": 3.66194341060939e-06, - "loss": 0.1389, + "epoch": 0.46, + "learning_rate": 2.688295563857632e-05, + "loss": 0.1391, "step": 207760 }, { - "epoch": 0.93, - "learning_rate": 3.659701358683467e-06, - "loss": 0.1418, + "epoch": 0.46, + "learning_rate": 2.6881837095366998e-05, + "loss": 0.1379, "step": 207770 }, { - "epoch": 0.93, - "learning_rate": 3.657459306757545e-06, + "epoch": 0.46, + "learning_rate": 2.688071855215767e-05, "loss": 0.1393, "step": 207780 }, { - "epoch": 0.93, - "learning_rate": 3.6552172548316223e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.6879600008948347e-05, + "loss": 0.1422, "step": 207790 }, { - "epoch": 0.93, - "learning_rate": 3.6529752029056993e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.6878481465739025e-05, + "loss": 0.1398, "step": 207800 }, { - "epoch": 0.93, - "learning_rate": 3.6507331509797764e-06, - "loss": 0.1353, + "epoch": 0.46, + "learning_rate": 2.6877362922529696e-05, + "loss": 0.1338, "step": 207810 }, { - "epoch": 0.93, - "learning_rate": 3.6484910990538542e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.6876244379320377e-05, + "loss": 0.139, "step": 207820 }, { - "epoch": 0.93, - "learning_rate": 3.6462490471279317e-06, - "loss": 0.1422, + "epoch": 0.46, + "learning_rate": 2.6875125836111048e-05, + "loss": 0.1383, "step": 207830 }, { - "epoch": 0.93, - "learning_rate": 3.6440069952020087e-06, - "loss": 0.135, + "epoch": 0.46, + "learning_rate": 2.6874007292901726e-05, + "loss": 0.1303, "step": 207840 }, { - "epoch": 0.93, - "learning_rate": 3.6417649432760866e-06, - "loss": 0.1349, + "epoch": 0.46, + "learning_rate": 2.6872888749692404e-05, + "loss": 0.1392, "step": 207850 }, { - "epoch": 0.93, - "learning_rate": 3.639522891350164e-06, - "loss": 0.1378, + "epoch": 0.46, + "learning_rate": 2.6871770206483075e-05, + "loss": 0.1402, "step": 207860 }, { - "epoch": 0.93, - "learning_rate": 3.637280839424241e-06, - "loss": 0.1334, + "epoch": 0.46, + "learning_rate": 2.6870651663273753e-05, + "loss": 0.1421, "step": 207870 }, { - "epoch": 0.93, - "learning_rate": 3.635038787498319e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.6869533120064428e-05, + "loss": 0.141, "step": 207880 }, { - "epoch": 0.93, - "learning_rate": 3.6327967355723964e-06, - "loss": 0.1341, + "epoch": 0.46, + "learning_rate": 2.6868414576855106e-05, + "loss": 0.1385, "step": 207890 }, { - "epoch": 0.93, - "learning_rate": 3.6305546836464734e-06, - "loss": 0.1455, + "epoch": 0.46, + "learning_rate": 2.6867296033645784e-05, + "loss": 0.1404, "step": 207900 }, { - "epoch": 0.93, - "learning_rate": 3.6283126317205504e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.6866177490436455e-05, + "loss": 0.1428, "step": 207910 }, { - "epoch": 0.93, - "learning_rate": 3.6260705797946283e-06, - "loss": 0.1384, + "epoch": 0.46, + "learning_rate": 2.6865058947227133e-05, + "loss": 0.1402, "step": 207920 }, { - "epoch": 0.93, - "learning_rate": 3.6238285278687057e-06, - "loss": 0.1376, + "epoch": 0.46, + "learning_rate": 2.6863940404017807e-05, + "loss": 0.1367, "step": 207930 }, { - "epoch": 0.93, - "learning_rate": 3.6215864759427828e-06, - "loss": 0.1344, + "epoch": 0.46, + "learning_rate": 2.6862821860808485e-05, + "loss": 0.1386, "step": 207940 }, { - "epoch": 0.93, - "learning_rate": 3.6193444240168606e-06, - "loss": 0.1338, + "epoch": 0.46, + "learning_rate": 2.6861703317599163e-05, + "loss": 0.1371, "step": 207950 }, { - "epoch": 0.93, - "learning_rate": 3.617102372090938e-06, - "loss": 0.1356, + "epoch": 0.46, + "learning_rate": 2.6860584774389834e-05, + "loss": 0.1379, "step": 207960 }, { - "epoch": 0.93, - "learning_rate": 3.614860320165015e-06, - "loss": 0.138, + "epoch": 0.46, + "learning_rate": 2.6859466231180512e-05, + "loss": 0.1374, "step": 207970 }, { - "epoch": 0.93, - "learning_rate": 3.612618268239092e-06, - "loss": 0.137, + "epoch": 0.46, + "learning_rate": 2.6858347687971187e-05, + "loss": 0.1358, "step": 207980 }, { - "epoch": 0.93, - "learning_rate": 3.61037621631317e-06, - "loss": 0.143, + "epoch": 0.46, + "learning_rate": 2.6857229144761865e-05, + "loss": 0.137, "step": 207990 }, { - "epoch": 0.93, - "learning_rate": 3.6081341643872474e-06, - "loss": 0.1383, + "epoch": 0.46, + "learning_rate": 2.6856110601552536e-05, + "loss": 0.1412, "step": 208000 }, { - "epoch": 0.93, - "eval_NEIMS_canon_smiles": 0.9464833333333333, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.11943333333333334, - "eval_NEIMS_daylight_tanimoto_simil": 0.5189043382837861, - "eval_NEIMS_exact_mols": 0.119, - "eval_NEIMS_exact_smiles": 0.11601666666666667, - "eval_NEIMS_loss": 0.17722082138061523, - "eval_NEIMS_matched_formulas": 0.6513, - "eval_NEIMS_morgan_tanimoto_simil": 0.4303859638570458, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.11956666666666667, - "eval_NEIMS_runtime": 713.3866, - "eval_NEIMS_samples_per_second": 84.106, - "eval_NEIMS_steps_per_second": 1.315, + "epoch": 0.46, + "eval_NEIMS_canon_smiles": 0.9527833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.14435, + "eval_NEIMS_daylight_tanimoto_simil": 0.5458916164287176, + "eval_NEIMS_exact_mols": 0.14408333333333334, + "eval_NEIMS_exact_smiles": 0.1409, + "eval_NEIMS_loss": 0.16587482392787933, + "eval_NEIMS_matched_formulas": 0.675, + "eval_NEIMS_morgan_tanimoto_simil": 0.4585181610297042, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.14468333333333333, + "eval_NEIMS_runtime": 723.2572, + "eval_NEIMS_samples_per_second": 82.958, + "eval_NEIMS_steps_per_second": 1.297, "step": 208000 }, { - "epoch": 0.93, - "eval_RASSP_canon_smiles": 0.9441847263498848, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.2553344241493305, - "eval_RASSP_daylight_tanimoto_simil": 0.6690008143553688, - "eval_RASSP_exact_mols": 0.25459979296757607, - "eval_RASSP_exact_smiles": 0.2474705312719137, - "eval_RASSP_loss": 0.11752571910619736, - "eval_RASSP_matched_formulas": 0.8234714662570541, - "eval_RASSP_morgan_tanimoto_simil": 0.5549820144524215, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.25480014692623637, - "eval_RASSP_runtime": 817.2827, - "eval_RASSP_samples_per_second": 73.284, - "eval_RASSP_steps_per_second": 1.145, + "epoch": 0.46, + "eval_RASSP_canon_smiles": 0.9510635455972217, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.2024409790630113, + "eval_RASSP_daylight_tanimoto_simil": 0.6403268248604859, + "eval_RASSP_exact_mols": 0.20182322102380873, + "eval_RASSP_exact_smiles": 0.1966808027515277, + "eval_RASSP_loss": 0.1327967643737793, + "eval_RASSP_matched_formulas": 0.8246902861722376, + "eval_RASSP_morgan_tanimoto_simil": 0.5161690128328978, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.20200687881924734, + "eval_RASSP_runtime": 825.786, + "eval_RASSP_samples_per_second": 72.53, + "eval_RASSP_steps_per_second": 1.133, "step": 208000 }, { - "epoch": 0.93, - "eval_NIST_canon_smiles": 0.8780920609007347, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.01838378819604642, - "eval_NIST_daylight_tanimoto_simil": 0.28151468193484197, - "eval_NIST_exact_mols": 0.017390069915179048, - "eval_NIST_exact_smiles": 0.016360861695709265, - "eval_NIST_loss": 1.9125394821166992, - "eval_NIST_matched_formulas": 0.10363062071902615, - "eval_NIST_morgan_tanimoto_simil": 0.23322152811744992, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.018064378748624765, - "eval_NIST_runtime": 478.1073, - "eval_NIST_samples_per_second": 58.934, - "eval_NIST_steps_per_second": 0.922, + "epoch": 0.46, + "eval_NEIMS_old_canon_smiles": 0.9539333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.14696666666666666, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5465215926836534, + "eval_NEIMS_old_exact_mols": 0.14666666666666667, + "eval_NEIMS_old_exact_smiles": 0.14306666666666668, + "eval_NEIMS_old_loss": 0.16525502502918243, + "eval_NEIMS_old_matched_formulas": 0.6727, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4612128274856213, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1473, + "eval_NEIMS_old_runtime": 365.9375, + "eval_NEIMS_old_samples_per_second": 81.981, + "eval_NEIMS_old_steps_per_second": 1.282, "step": 208000 }, { - "epoch": 0.93, - "learning_rate": 3.6058921124613245e-06, - "loss": 0.1409, - "step": 208010 + "epoch": 0.46, + "eval_RASSP_old_canon_smiles": 0.9497447191911103, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.22521440250942704, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6597704772065933, + "eval_RASSP_old_exact_mols": 0.2247138519037608, + "eval_RASSP_old_exact_smiles": 0.21807321386858877, + "eval_RASSP_old_loss": 0.125106081366539, + "eval_RASSP_old_matched_formulas": 0.8355524410184536, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5394262147033418, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.22494744218640506, + "eval_RASSP_old_runtime": 412.3379, + "eval_RASSP_old_samples_per_second": 72.676, + "eval_RASSP_old_steps_per_second": 1.137, + "step": 208000 }, { - "epoch": 0.93, - "learning_rate": 3.6036500605354023e-06, - "loss": 0.1395, - "step": 208020 + "epoch": 0.46, + "eval_NIST_canon_smiles": 0.8678709585832417, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.021897292117684635, + "eval_NIST_daylight_tanimoto_simil": 0.2891456596542381, + "eval_NIST_exact_mols": 0.02101004365262448, + "eval_NIST_exact_smiles": 0.019909855555949887, + "eval_NIST_loss": 1.8087174892425537, + "eval_NIST_matched_formulas": 0.10600844660538737, + "eval_NIST_morgan_tanimoto_simil": 0.24097267456681934, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02157788267026298, + "eval_NIST_runtime": 514.1861, + "eval_NIST_samples_per_second": 54.799, + "eval_NIST_steps_per_second": 0.858, + "step": 208000 }, { - "epoch": 0.93, - "learning_rate": 3.6014080086094798e-06, + "epoch": 0.46, + "learning_rate": 2.6854992058343214e-05, "loss": 0.1331, + "step": 208010 + }, + { + "epoch": 0.46, + "learning_rate": 2.685387351513389e-05, + "loss": 0.1369, + "step": 208020 + }, + { + "epoch": 0.46, + "learning_rate": 2.6852754971924566e-05, + "loss": 0.1345, "step": 208030 }, { - "epoch": 0.93, - "learning_rate": 3.599165956683557e-06, - "loss": 0.1416, + "epoch": 0.46, + "learning_rate": 2.6851636428715244e-05, + "loss": 0.1369, "step": 208040 }, { - "epoch": 0.93, - "learning_rate": 3.5969239047576343e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.6850517885505915e-05, + "loss": 0.1335, "step": 208050 }, { - "epoch": 0.93, - "learning_rate": 3.594681852831712e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.6849399342296593e-05, + "loss": 0.147, "step": 208060 }, { - "epoch": 0.93, - "learning_rate": 3.592439800905789e-06, - "loss": 0.1379, + "epoch": 0.46, + "learning_rate": 2.684828079908727e-05, + "loss": 0.137, "step": 208070 }, { - "epoch": 0.93, - "learning_rate": 3.590197748979866e-06, - "loss": 0.1356, + "epoch": 0.46, + "learning_rate": 2.6847162255877946e-05, + "loss": 0.1397, "step": 208080 }, { - "epoch": 0.93, - "learning_rate": 3.587955697053944e-06, - "loss": 0.1367, + "epoch": 0.46, + "learning_rate": 2.6846043712668624e-05, + "loss": 0.1352, "step": 208090 }, { - "epoch": 0.93, - "learning_rate": 3.5857136451280215e-06, - "loss": 0.136, + "epoch": 0.46, + "learning_rate": 2.6844925169459295e-05, + "loss": 0.1386, "step": 208100 }, { - "epoch": 0.93, - "learning_rate": 3.5834715932020985e-06, - "loss": 0.1353, + "epoch": 0.46, + "learning_rate": 2.6843806626249973e-05, + "loss": 0.1387, "step": 208110 }, { - "epoch": 0.93, - "learning_rate": 3.581229541276176e-06, - "loss": 0.1361, + "epoch": 0.46, + "learning_rate": 2.684268808304065e-05, + "loss": 0.1327, "step": 208120 }, { - "epoch": 0.93, - "learning_rate": 3.578987489350254e-06, - "loss": 0.1416, + "epoch": 0.46, + "learning_rate": 2.6841569539831325e-05, + "loss": 0.1369, "step": 208130 }, { - "epoch": 0.93, - "learning_rate": 3.576745437424331e-06, - "loss": 0.1328, + "epoch": 0.46, + "learning_rate": 2.6840450996622003e-05, + "loss": 0.1364, "step": 208140 }, { - "epoch": 0.93, - "learning_rate": 3.574503385498408e-06, - "loss": 0.1382, + "epoch": 0.46, + "learning_rate": 2.6839332453412674e-05, + "loss": 0.1385, "step": 208150 }, { - "epoch": 0.93, - "learning_rate": 3.572261333572486e-06, - "loss": 0.1443, + "epoch": 0.46, + "learning_rate": 2.6838213910203352e-05, + "loss": 0.137, "step": 208160 }, { - "epoch": 0.93, - "learning_rate": 3.570019281646563e-06, - "loss": 0.1417, + "epoch": 0.46, + "learning_rate": 2.683709536699403e-05, + "loss": 0.1411, "step": 208170 }, { - "epoch": 0.93, - "learning_rate": 3.5677772297206402e-06, - "loss": 0.1339, + "epoch": 0.46, + "learning_rate": 2.6835976823784705e-05, + "loss": 0.1344, "step": 208180 }, { - "epoch": 0.93, - "learning_rate": 3.565535177794718e-06, - "loss": 0.1386, + "epoch": 0.46, + "learning_rate": 2.6834858280575382e-05, + "loss": 0.135, "step": 208190 }, { - "epoch": 0.93, - "learning_rate": 3.5632931258687955e-06, - "loss": 0.1392, + "epoch": 0.46, + "learning_rate": 2.6833739737366054e-05, + "loss": 0.1387, "step": 208200 }, { - "epoch": 0.93, - "learning_rate": 3.5610510739428726e-06, - "loss": 0.1381, + "epoch": 0.46, + "learning_rate": 2.683262119415673e-05, + "loss": 0.1382, "step": 208210 }, { - "epoch": 0.93, - "learning_rate": 3.55880902201695e-06, - "loss": 0.1354, + "epoch": 0.46, + "learning_rate": 2.683150265094741e-05, + "loss": 0.1401, "step": 208220 }, { - "epoch": 0.93, - "learning_rate": 3.556566970091028e-06, - "loss": 0.1403, + "epoch": 0.46, + "learning_rate": 2.6830384107738084e-05, + "loss": 0.1363, "step": 208230 }, { - "epoch": 0.93, - "learning_rate": 3.554324918165105e-06, - "loss": 0.1368, + "epoch": 0.46, + "learning_rate": 2.6829265564528762e-05, + "loss": 0.1413, "step": 208240 }, { - "epoch": 0.93, - "learning_rate": 3.552082866239182e-06, - "loss": 0.142, + "epoch": 0.46, + "learning_rate": 2.6828147021319433e-05, + "loss": 0.1391, "step": 208250 }, { - "epoch": 0.93, - "learning_rate": 3.54984081431326e-06, - "loss": 0.1355, + "epoch": 0.46, + "learning_rate": 2.682702847811011e-05, + "loss": 0.1371, "step": 208260 }, { - "epoch": 0.93, - "learning_rate": 3.5475987623873372e-06, - "loss": 0.1402, + "epoch": 0.46, + "learning_rate": 2.682590993490079e-05, + "loss": 0.1359, "step": 208270 }, { - "epoch": 0.93, - "learning_rate": 3.5453567104614143e-06, - "loss": 0.1408, + "epoch": 0.46, + "learning_rate": 2.682479139169146e-05, + "loss": 0.1334, "step": 208280 }, { - "epoch": 0.93, - "learning_rate": 3.5431146585354917e-06, - "loss": 0.1351, + "epoch": 0.46, + "learning_rate": 2.682367284848214e-05, + "loss": 0.1374, "step": 208290 }, { - "epoch": 0.93, - "learning_rate": 3.5408726066095696e-06, - "loss": 0.1313, + "epoch": 0.46, + "learning_rate": 2.6822554305272813e-05, + "loss": 0.1379, "step": 208300 }, { - "epoch": 0.93, - "learning_rate": 3.5386305546836466e-06, - "loss": 0.1365, + "epoch": 0.46, + "learning_rate": 2.682143576206349e-05, + "loss": 0.1367, "step": 208310 }, { - "epoch": 0.93, - "learning_rate": 3.536388502757724e-06, - "loss": 0.14, + "epoch": 0.46, + "learning_rate": 2.682031721885416e-05, + "loss": 0.1398, "step": 208320 }, { - "epoch": 0.93, - "learning_rate": 3.534146450831802e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.681919867564484e-05, + "loss": 0.1371, "step": 208330 }, { - "epoch": 0.93, - "learning_rate": 3.531904398905879e-06, - "loss": 0.1391, + "epoch": 0.47, + "learning_rate": 2.6818191986756452e-05, + "loss": 0.1408, "step": 208340 }, { - "epoch": 0.93, - "learning_rate": 3.529662346979956e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.6817073443547126e-05, + "loss": 0.1407, "step": 208350 }, { - "epoch": 0.93, - "learning_rate": 3.5274202950540334e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.6815954900337804e-05, + "loss": 0.1342, "step": 208360 }, { - "epoch": 0.93, - "learning_rate": 3.5251782431281113e-06, + "epoch": 0.47, + "learning_rate": 2.6814836357128475e-05, "loss": 0.1405, "step": 208370 }, { - "epoch": 0.93, - "learning_rate": 3.5229361912021883e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6813717813919153e-05, + "loss": 0.1437, "step": 208380 }, { - "epoch": 0.93, - "learning_rate": 3.5206941392762658e-06, - "loss": 0.1381, + "epoch": 0.47, + "learning_rate": 2.6812599270709824e-05, + "loss": 0.1403, "step": 208390 }, { - "epoch": 0.93, - "learning_rate": 3.5184520873503436e-06, - "loss": 0.1352, + "epoch": 0.47, + "learning_rate": 2.6811480727500506e-05, + "loss": 0.138, "step": 208400 }, { - "epoch": 0.93, - "learning_rate": 3.5162100354244207e-06, - "loss": 0.1409, + "epoch": 0.47, + "learning_rate": 2.6810362184291184e-05, + "loss": 0.1389, "step": 208410 }, { - "epoch": 0.93, - "learning_rate": 3.5139679834984977e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.6809243641081855e-05, + "loss": 0.1385, "step": 208420 }, { - "epoch": 0.93, - "learning_rate": 3.511725931572575e-06, - "loss": 0.1338, + "epoch": 0.47, + "learning_rate": 2.6808125097872533e-05, + "loss": 0.1394, "step": 208430 }, { - "epoch": 0.93, - "learning_rate": 3.509483879646653e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6807006554663204e-05, + "loss": 0.14, "step": 208440 }, { - "epoch": 0.93, - "learning_rate": 3.50724182772073e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.6805888011453882e-05, + "loss": 0.1364, "step": 208450 }, { - "epoch": 0.93, - "learning_rate": 3.5049997757948075e-06, - "loss": 0.1387, + "epoch": 0.47, + "learning_rate": 2.6804769468244563e-05, + "loss": 0.1385, "step": 208460 }, { - "epoch": 0.93, - "learning_rate": 3.5027577238688853e-06, - "loss": 0.1367, + "epoch": 0.47, + "learning_rate": 2.6803650925035234e-05, + "loss": 0.1365, "step": 208470 }, { - "epoch": 0.93, - "learning_rate": 3.5005156719429624e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.6802532381825912e-05, + "loss": 0.1423, "step": 208480 }, { - "epoch": 0.93, - "learning_rate": 3.49827362001704e-06, - "loss": 0.136, + "epoch": 0.47, + "learning_rate": 2.6801413838616583e-05, + "loss": 0.1355, "step": 208490 }, { - "epoch": 0.93, - "learning_rate": 3.496031568091117e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.680029529540726e-05, + "loss": 0.1371, "step": 208500 }, { - "epoch": 0.93, - "learning_rate": 3.4937895161651947e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.679917675219794e-05, + "loss": 0.1378, "step": 208510 }, { - "epoch": 0.93, - "learning_rate": 3.4915474642392717e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.6798058208988614e-05, + "loss": 0.1366, "step": 208520 }, { - "epoch": 0.93, - "learning_rate": 3.489305412313349e-06, + "epoch": 0.47, + "learning_rate": 2.6796939665779292e-05, "loss": 0.1427, "step": 208530 }, { - "epoch": 0.93, - "learning_rate": 3.487063360387427e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.6795821122569963e-05, + "loss": 0.1381, "step": 208540 }, { - "epoch": 0.93, - "learning_rate": 3.484821308461504e-06, - "loss": 0.1365, + "epoch": 0.47, + "learning_rate": 2.679470257936064e-05, + "loss": 0.1362, "step": 208550 }, { - "epoch": 0.93, - "learning_rate": 3.4825792565355815e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.679358403615132e-05, + "loss": 0.138, "step": 208560 }, { - "epoch": 0.93, - "learning_rate": 3.4803372046096594e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.6792465492941993e-05, + "loss": 0.14, "step": 208570 }, { - "epoch": 0.93, - "learning_rate": 3.4780951526837364e-06, - "loss": 0.1419, + "epoch": 0.47, + "learning_rate": 2.679134694973267e-05, + "loss": 0.1363, "step": 208580 }, { - "epoch": 0.93, - "learning_rate": 3.4758531007578134e-06, - "loss": 0.1425, + "epoch": 0.47, + "learning_rate": 2.6790228406523342e-05, + "loss": 0.1396, "step": 208590 }, { - "epoch": 0.93, - "learning_rate": 3.473611048831891e-06, - "loss": 0.1407, + "epoch": 0.47, + "learning_rate": 2.678910986331402e-05, + "loss": 0.1403, "step": 208600 }, { - "epoch": 0.93, - "learning_rate": 3.4713689969059688e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.6787991320104698e-05, + "loss": 0.1343, "step": 208610 }, { - "epoch": 0.93, - "learning_rate": 3.4691269449800458e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.6786872776895373e-05, + "loss": 0.1367, "step": 208620 }, { - "epoch": 0.93, - "learning_rate": 3.4668848930541232e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.678575423368605e-05, + "loss": 0.1393, "step": 208630 }, { - "epoch": 0.93, - "learning_rate": 3.464642841128201e-06, - "loss": 0.1354, + "epoch": 0.47, + "learning_rate": 2.6784635690476722e-05, + "loss": 0.1434, "step": 208640 }, { - "epoch": 0.93, - "learning_rate": 3.462400789202278e-06, - "loss": 0.1392, + "epoch": 0.47, + "learning_rate": 2.67835171472674e-05, + "loss": 0.1369, "step": 208650 }, { - "epoch": 0.93, - "learning_rate": 3.4601587372763556e-06, - "loss": 0.1319, + "epoch": 0.47, + "learning_rate": 2.6782398604058078e-05, + "loss": 0.1376, "step": 208660 }, { - "epoch": 0.93, - "learning_rate": 3.4579166853504326e-06, - "loss": 0.1422, + "epoch": 0.47, + "learning_rate": 2.6781280060848752e-05, + "loss": 0.1319, "step": 208670 }, { - "epoch": 0.93, - "learning_rate": 3.4556746334245105e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.678016151763943e-05, + "loss": 0.1381, "step": 208680 }, { - "epoch": 0.93, - "learning_rate": 3.4534325814985875e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.67790429744301e-05, + "loss": 0.1364, "step": 208690 }, { - "epoch": 0.93, - "learning_rate": 3.451190529572665e-06, - "loss": 0.1424, + "epoch": 0.47, + "learning_rate": 2.677792443122078e-05, + "loss": 0.1393, "step": 208700 }, { - "epoch": 0.93, - "learning_rate": 3.448948477646743e-06, - "loss": 0.1368, + "epoch": 0.47, + "learning_rate": 2.6776805888011454e-05, + "loss": 0.1373, "step": 208710 }, { - "epoch": 0.93, - "learning_rate": 3.44670642572082e-06, - "loss": 0.1388, + "epoch": 0.47, + "learning_rate": 2.6775687344802132e-05, + "loss": 0.1371, "step": 208720 }, { - "epoch": 0.93, - "learning_rate": 3.4444643737948973e-06, - "loss": 0.1304, + "epoch": 0.47, + "learning_rate": 2.677456880159281e-05, + "loss": 0.1363, "step": 208730 }, { - "epoch": 0.93, - "learning_rate": 3.4422223218689743e-06, - "loss": 0.1421, + "epoch": 0.47, + "learning_rate": 2.677345025838348e-05, + "loss": 0.1401, "step": 208740 }, { - "epoch": 0.93, - "learning_rate": 3.439980269943052e-06, - "loss": 0.1322, + "epoch": 0.47, + "learning_rate": 2.677233171517416e-05, + "loss": 0.1355, "step": 208750 }, { - "epoch": 0.93, - "learning_rate": 3.4377382180171296e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.6771213171964833e-05, + "loss": 0.1397, "step": 208760 }, { - "epoch": 0.93, - "learning_rate": 3.4354961660912066e-06, - "loss": 0.1372, + "epoch": 0.47, + "learning_rate": 2.677009462875551e-05, + "loss": 0.1349, "step": 208770 }, { - "epoch": 0.93, - "learning_rate": 3.4332541141652845e-06, - "loss": 0.1356, + "epoch": 0.47, + "learning_rate": 2.676897608554619e-05, + "loss": 0.1303, "step": 208780 }, { - "epoch": 0.93, - "learning_rate": 3.4310120622393615e-06, - "loss": 0.1358, + "epoch": 0.47, + "learning_rate": 2.676785754233686e-05, + "loss": 0.1362, "step": 208790 }, { - "epoch": 0.93, - "learning_rate": 3.428770010313439e-06, - "loss": 0.1396, + "epoch": 0.47, + "learning_rate": 2.6766738999127538e-05, + "loss": 0.1364, "step": 208800 }, { - "epoch": 0.93, - "learning_rate": 3.426527958387516e-06, - "loss": 0.1389, + "epoch": 0.47, + "learning_rate": 2.6765620455918213e-05, + "loss": 0.1396, "step": 208810 }, { - "epoch": 0.93, - "learning_rate": 3.424285906461594e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.676450191270889e-05, + "loss": 0.1361, "step": 208820 }, { - "epoch": 0.93, - "learning_rate": 3.4220438545356713e-06, - "loss": 0.1421, + "epoch": 0.47, + "learning_rate": 2.676338336949957e-05, + "loss": 0.1417, "step": 208830 }, { - "epoch": 0.93, - "learning_rate": 3.4198018026097483e-06, - "loss": 0.1417, + "epoch": 0.47, + "learning_rate": 2.676226482629024e-05, + "loss": 0.1415, "step": 208840 }, { - "epoch": 0.93, - "learning_rate": 3.4175597506838262e-06, - "loss": 0.1365, + "epoch": 0.47, + "learning_rate": 2.6761146283080918e-05, + "loss": 0.1335, "step": 208850 }, { - "epoch": 0.93, - "learning_rate": 3.4153176987579032e-06, - "loss": 0.1296, + "epoch": 0.47, + "learning_rate": 2.676002773987159e-05, + "loss": 0.1362, "step": 208860 }, { - "epoch": 0.93, - "learning_rate": 3.4130756468319807e-06, - "loss": 0.1427, + "epoch": 0.47, + "learning_rate": 2.675890919666227e-05, + "loss": 0.1389, "step": 208870 }, { - "epoch": 0.93, - "learning_rate": 3.4108335949060586e-06, - "loss": 0.142, + "epoch": 0.47, + "learning_rate": 2.6757790653452948e-05, + "loss": 0.1368, "step": 208880 }, { - "epoch": 0.93, - "learning_rate": 3.4085915429801356e-06, - "loss": 0.1385, + "epoch": 0.47, + "learning_rate": 2.675667211024362e-05, + "loss": 0.1367, "step": 208890 }, { - "epoch": 0.93, - "learning_rate": 3.406349491054213e-06, - "loss": 0.1368, + "epoch": 0.47, + "learning_rate": 2.6755553567034297e-05, + "loss": 0.1372, "step": 208900 }, { - "epoch": 0.93, - "learning_rate": 3.40410743912829e-06, - "loss": 0.1423, + "epoch": 0.47, + "learning_rate": 2.6754435023824968e-05, + "loss": 0.1356, "step": 208910 }, { - "epoch": 0.93, - "learning_rate": 3.401865387202368e-06, - "loss": 0.1395, + "epoch": 0.47, + "learning_rate": 2.6753316480615646e-05, + "loss": 0.1392, "step": 208920 }, { - "epoch": 0.93, - "learning_rate": 3.3996233352764454e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.6752197937406328e-05, + "loss": 0.1428, "step": 208930 }, { - "epoch": 0.93, - "learning_rate": 3.3973812833505224e-06, - "loss": 0.1335, + "epoch": 0.47, + "learning_rate": 2.6751079394197e-05, + "loss": 0.1367, "step": 208940 }, { - "epoch": 0.93, - "learning_rate": 3.3951392314246003e-06, - "loss": 0.1365, + "epoch": 0.47, + "learning_rate": 2.6749960850987677e-05, + "loss": 0.1375, "step": 208950 }, { - "epoch": 0.93, - "learning_rate": 3.3928971794986773e-06, - "loss": 0.1445, + "epoch": 0.47, + "learning_rate": 2.6748842307778348e-05, + "loss": 0.1332, "step": 208960 }, { - "epoch": 0.93, - "learning_rate": 3.3906551275727547e-06, - "loss": 0.1307, + "epoch": 0.47, + "learning_rate": 2.6747723764569026e-05, + "loss": 0.1396, "step": 208970 }, { - "epoch": 0.93, - "learning_rate": 3.3884130756468318e-06, - "loss": 0.1372, + "epoch": 0.47, + "learning_rate": 2.6746605221359704e-05, + "loss": 0.1373, "step": 208980 }, { - "epoch": 0.93, - "learning_rate": 3.3861710237209096e-06, - "loss": 0.1333, + "epoch": 0.47, + "learning_rate": 2.6745486678150378e-05, + "loss": 0.1427, "step": 208990 }, { - "epoch": 0.93, - "learning_rate": 3.383928971794987e-06, - "loss": 0.1372, + "epoch": 0.47, + "learning_rate": 2.6744368134941056e-05, + "loss": 0.1373, "step": 209000 }, { - "epoch": 0.93, - "learning_rate": 3.381686919869064e-06, - "loss": 0.1435, + "epoch": 0.47, + "learning_rate": 2.6743249591731727e-05, + "loss": 0.1394, "step": 209010 }, { - "epoch": 0.93, - "learning_rate": 3.379444867943142e-06, - "loss": 0.1399, + "epoch": 0.47, + "learning_rate": 2.6742131048522405e-05, + "loss": 0.1373, "step": 209020 }, { - "epoch": 0.93, - "learning_rate": 3.3772028160172194e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.674101250531308e-05, + "loss": 0.1386, "step": 209030 }, { - "epoch": 0.93, - "learning_rate": 3.3749607640912964e-06, - "loss": 0.1395, + "epoch": 0.47, + "learning_rate": 2.6739893962103758e-05, + "loss": 0.1343, "step": 209040 }, { - "epoch": 0.93, - "learning_rate": 3.3727187121653735e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.6738775418894436e-05, + "loss": 0.1375, "step": 209050 }, { - "epoch": 0.93, - "learning_rate": 3.3704766602394513e-06, - "loss": 0.1335, + "epoch": 0.47, + "learning_rate": 2.6737656875685107e-05, + "loss": 0.1399, "step": 209060 }, { - "epoch": 0.93, - "learning_rate": 3.3682346083135288e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.6736538332475785e-05, + "loss": 0.1373, "step": 209070 }, { - "epoch": 0.93, - "learning_rate": 3.365992556387606e-06, - "loss": 0.131, + "epoch": 0.47, + "learning_rate": 2.673541978926646e-05, + "loss": 0.1428, "step": 209080 }, { - "epoch": 0.93, - "learning_rate": 3.3637505044616837e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.6734301246057137e-05, + "loss": 0.1393, "step": 209090 }, { - "epoch": 0.93, - "learning_rate": 3.361508452535761e-06, - "loss": 0.1386, + "epoch": 0.47, + "learning_rate": 2.6733182702847815e-05, + "loss": 0.1375, "step": 209100 }, { - "epoch": 0.93, - "learning_rate": 3.359266400609838e-06, - "loss": 0.1415, + "epoch": 0.47, + "learning_rate": 2.6732064159638486e-05, + "loss": 0.1405, "step": 209110 }, { - "epoch": 0.93, - "learning_rate": 3.357024348683915e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.6730945616429164e-05, + "loss": 0.1378, "step": 209120 }, { - "epoch": 0.93, - "learning_rate": 3.354782296757993e-06, - "loss": 0.1345, + "epoch": 0.47, + "learning_rate": 2.672982707321984e-05, + "loss": 0.1383, "step": 209130 }, { - "epoch": 0.93, - "learning_rate": 3.3525402448320705e-06, - "loss": 0.1403, + "epoch": 0.47, + "learning_rate": 2.6728708530010517e-05, + "loss": 0.1344, "step": 209140 }, { - "epoch": 0.93, - "learning_rate": 3.3502981929061475e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6727589986801194e-05, + "loss": 0.1381, "step": 209150 }, { - "epoch": 0.93, - "learning_rate": 3.3480561409802254e-06, - "loss": 0.1358, + "epoch": 0.47, + "learning_rate": 2.6726471443591866e-05, + "loss": 0.1318, "step": 209160 }, { - "epoch": 0.93, - "learning_rate": 3.345814089054303e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.6725352900382544e-05, + "loss": 0.1372, "step": 209170 }, { - "epoch": 0.93, - "learning_rate": 3.34357203712838e-06, - "loss": 0.1416, + "epoch": 0.47, + "learning_rate": 2.6724234357173218e-05, + "loss": 0.1342, "step": 209180 }, { - "epoch": 0.93, - "learning_rate": 3.3413299852024573e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.6723115813963896e-05, + "loss": 0.1401, "step": 209190 }, { - "epoch": 0.93, - "learning_rate": 3.339087933276535e-06, - "loss": 0.1321, + "epoch": 0.47, + "learning_rate": 2.6721997270754574e-05, + "loss": 0.1376, "step": 209200 }, { - "epoch": 0.93, - "learning_rate": 3.336845881350612e-06, - "loss": 0.1321, + "epoch": 0.47, + "learning_rate": 2.6720878727545245e-05, + "loss": 0.1384, "step": 209210 }, { - "epoch": 0.93, - "learning_rate": 3.3346038294246892e-06, - "loss": 0.1414, + "epoch": 0.47, + "learning_rate": 2.6719760184335923e-05, + "loss": 0.137, "step": 209220 }, { - "epoch": 0.93, - "learning_rate": 3.332361777498767e-06, - "loss": 0.1344, + "epoch": 0.47, + "learning_rate": 2.6718641641126598e-05, + "loss": 0.1399, "step": 209230 }, { - "epoch": 0.93, - "learning_rate": 3.3301197255728445e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.6717523097917276e-05, + "loss": 0.1351, "step": 209240 }, { - "epoch": 0.93, - "learning_rate": 3.3278776736469216e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.6716404554707953e-05, + "loss": 0.1375, "step": 209250 }, { - "epoch": 0.93, - "learning_rate": 3.3256356217209994e-06, - "loss": 0.1411, + "epoch": 0.47, + "learning_rate": 2.6715286011498625e-05, + "loss": 0.1427, "step": 209260 }, { - "epoch": 0.93, - "learning_rate": 3.323393569795077e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.6714167468289303e-05, + "loss": 0.133, "step": 209270 }, { - "epoch": 0.93, - "learning_rate": 3.321151517869154e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.6713048925079974e-05, + "loss": 0.1376, "step": 209280 }, { - "epoch": 0.93, - "learning_rate": 3.318909465943231e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.6711930381870655e-05, + "loss": 0.1374, "step": 209290 }, { - "epoch": 0.93, - "learning_rate": 3.3166674140173092e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.6710811838661333e-05, + "loss": 0.1384, "step": 209300 }, { - "epoch": 0.93, - "learning_rate": 3.3144253620913862e-06, - "loss": 0.1423, + "epoch": 0.47, + "learning_rate": 2.6709693295452004e-05, + "loss": 0.1414, "step": 209310 }, { - "epoch": 0.93, - "learning_rate": 3.3121833101654633e-06, - "loss": 0.1381, + "epoch": 0.47, + "learning_rate": 2.6708574752242682e-05, + "loss": 0.1413, "step": 209320 }, { - "epoch": 0.93, - "learning_rate": 3.309941258239541e-06, - "loss": 0.1393, + "epoch": 0.47, + "learning_rate": 2.6707456209033353e-05, + "loss": 0.1363, "step": 209330 }, { - "epoch": 0.93, - "learning_rate": 3.3076992063136186e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.670633766582403e-05, + "loss": 0.1394, "step": 209340 }, { - "epoch": 0.93, - "learning_rate": 3.3054571543876956e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.6705219122614706e-05, + "loss": 0.1352, "step": 209350 }, { - "epoch": 0.93, - "learning_rate": 3.303215102461773e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.6704100579405384e-05, + "loss": 0.1378, "step": 209360 }, { - "epoch": 0.93, - "learning_rate": 3.300973050535851e-06, - "loss": 0.1368, + "epoch": 0.47, + "learning_rate": 2.670298203619606e-05, + "loss": 0.139, "step": 209370 }, { - "epoch": 0.93, - "learning_rate": 3.298730998609928e-06, - "loss": 0.1389, + "epoch": 0.47, + "learning_rate": 2.6701863492986733e-05, + "loss": 0.1365, "step": 209380 }, { - "epoch": 0.93, - "learning_rate": 3.296488946684005e-06, - "loss": 0.1334, + "epoch": 0.47, + "learning_rate": 2.670074494977741e-05, + "loss": 0.1371, "step": 209390 }, { - "epoch": 0.93, - "learning_rate": 3.294246894758083e-06, - "loss": 0.1391, + "epoch": 0.47, + "learning_rate": 2.6699626406568085e-05, + "loss": 0.1361, "step": 209400 }, { - "epoch": 0.93, - "learning_rate": 3.2920048428321603e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.6698507863358763e-05, + "loss": 0.1379, "step": 209410 }, { - "epoch": 0.93, - "learning_rate": 3.2897627909062373e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.669738932014944e-05, + "loss": 0.1378, "step": 209420 }, { - "epoch": 0.93, - "learning_rate": 3.2875207389803148e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.6696270776940112e-05, + "loss": 0.1322, "step": 209430 }, { - "epoch": 0.93, - "learning_rate": 3.2852786870543926e-06, - "loss": 0.1399, + "epoch": 0.47, + "learning_rate": 2.669515223373079e-05, + "loss": 0.1381, "step": 209440 }, { - "epoch": 0.94, - "learning_rate": 3.2830366351284697e-06, - "loss": 0.1389, + "epoch": 0.47, + "learning_rate": 2.6694033690521465e-05, + "loss": 0.1333, "step": 209450 }, { - "epoch": 0.94, - "learning_rate": 3.280794583202547e-06, - "loss": 0.1344, + "epoch": 0.47, + "learning_rate": 2.6692915147312142e-05, + "loss": 0.1346, "step": 209460 }, { - "epoch": 0.94, - "learning_rate": 3.278552531276625e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.669179660410282e-05, + "loss": 0.1383, "step": 209470 }, { - "epoch": 0.94, - "learning_rate": 3.276310479350702e-06, - "loss": 0.1405, + "epoch": 0.47, + "learning_rate": 2.669067806089349e-05, + "loss": 0.142, "step": 209480 }, { - "epoch": 0.94, - "learning_rate": 3.274068427424779e-06, - "loss": 0.1445, + "epoch": 0.47, + "learning_rate": 2.668955951768417e-05, + "loss": 0.1306, "step": 209490 }, { - "epoch": 0.94, - "learning_rate": 3.2718263754988565e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.6688440974474844e-05, + "loss": 0.1426, "step": 209500 }, { - "epoch": 0.94, - "learning_rate": 3.2695843235729343e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6687322431265522e-05, + "loss": 0.1396, "step": 209510 }, { - "epoch": 0.94, - "learning_rate": 3.2673422716470114e-06, - "loss": 0.1409, + "epoch": 0.47, + "learning_rate": 2.66862038880562e-05, + "loss": 0.1362, "step": 209520 }, { - "epoch": 0.94, - "learning_rate": 3.265100219721089e-06, - "loss": 0.1401, + "epoch": 0.47, + "learning_rate": 2.668508534484687e-05, + "loss": 0.139, "step": 209530 }, { - "epoch": 0.94, - "learning_rate": 3.2630823729877587e-06, - "loss": 0.134, + "epoch": 0.47, + "learning_rate": 2.668396680163755e-05, + "loss": 0.1304, "step": 209540 }, { - "epoch": 0.94, - "learning_rate": 3.2608403210618358e-06, - "loss": 0.1363, + "epoch": 0.47, + "learning_rate": 2.6682848258428224e-05, + "loss": 0.1394, "step": 209550 }, { - "epoch": 0.94, - "learning_rate": 3.258598269135913e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.66817297152189e-05, + "loss": 0.1418, "step": 209560 }, { - "epoch": 0.94, - "learning_rate": 3.256356217209991e-06, - "loss": 0.1416, + "epoch": 0.47, + "learning_rate": 2.668061117200958e-05, + "loss": 0.1361, "step": 209570 }, { - "epoch": 0.94, - "learning_rate": 3.254114165284068e-06, - "loss": 0.1341, + "epoch": 0.47, + "learning_rate": 2.667949262880025e-05, + "loss": 0.1335, "step": 209580 }, { - "epoch": 0.94, - "learning_rate": 3.2518721133581455e-06, - "loss": 0.1399, + "epoch": 0.47, + "learning_rate": 2.667837408559093e-05, + "loss": 0.1408, "step": 209590 }, { - "epoch": 0.94, - "learning_rate": 3.2496300614322234e-06, - "loss": 0.1329, + "epoch": 0.47, + "learning_rate": 2.6677255542381603e-05, + "loss": 0.1341, "step": 209600 }, { - "epoch": 0.94, - "learning_rate": 3.2473880095063004e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.667613699917228e-05, + "loss": 0.1358, "step": 209610 }, { - "epoch": 0.94, - "learning_rate": 3.2451459575803775e-06, - "loss": 0.1351, + "epoch": 0.47, + "learning_rate": 2.667501845596296e-05, + "loss": 0.135, "step": 209620 }, { - "epoch": 0.94, - "learning_rate": 3.242903905654455e-06, - "loss": 0.1385, + "epoch": 0.47, + "learning_rate": 2.667389991275363e-05, + "loss": 0.1324, "step": 209630 }, { - "epoch": 0.94, - "learning_rate": 3.2406618537285328e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.6672781369544308e-05, + "loss": 0.1426, "step": 209640 }, { - "epoch": 0.94, - "learning_rate": 3.23841980180261e-06, - "loss": 0.1368, + "epoch": 0.47, + "learning_rate": 2.6671662826334982e-05, + "loss": 0.1388, "step": 209650 }, { - "epoch": 0.94, - "learning_rate": 3.2361777498766873e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.667054428312566e-05, + "loss": 0.1466, "step": 209660 }, { - "epoch": 0.94, - "learning_rate": 3.233935697950765e-06, - "loss": 0.1345, + "epoch": 0.47, + "learning_rate": 2.666942573991633e-05, + "loss": 0.1354, "step": 209670 }, { - "epoch": 0.94, - "learning_rate": 3.231693646024842e-06, - "loss": 0.1341, + "epoch": 0.47, + "learning_rate": 2.666830719670701e-05, + "loss": 0.1393, "step": 209680 }, { - "epoch": 0.94, - "learning_rate": 3.229451594098919e-06, - "loss": 0.1416, + "epoch": 0.47, + "learning_rate": 2.6667188653497687e-05, + "loss": 0.1408, "step": 209690 }, { - "epoch": 0.94, - "learning_rate": 3.2272095421729966e-06, - "loss": 0.1423, + "epoch": 0.47, + "learning_rate": 2.6666070110288362e-05, + "loss": 0.139, "step": 209700 }, { - "epoch": 0.94, - "learning_rate": 3.2249674902470745e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.666495156707904e-05, + "loss": 0.1343, "step": 209710 }, { - "epoch": 0.94, - "learning_rate": 3.2227254383211515e-06, - "loss": 0.1387, + "epoch": 0.47, + "learning_rate": 2.666383302386971e-05, + "loss": 0.1358, "step": 209720 }, { - "epoch": 0.94, - "learning_rate": 3.220483386395229e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.666271448066039e-05, + "loss": 0.1367, "step": 209730 }, { - "epoch": 0.94, - "learning_rate": 3.218241334469307e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.6661595937451067e-05, + "loss": 0.1375, "step": 209740 }, { - "epoch": 0.94, - "learning_rate": 3.215999282543384e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.6660477394241738e-05, + "loss": 0.135, "step": 209750 }, { - "epoch": 0.94, - "learning_rate": 3.2137572306174613e-06, - "loss": 0.1444, + "epoch": 0.47, + "learning_rate": 2.665935885103242e-05, + "loss": 0.1348, "step": 209760 }, { - "epoch": 0.94, - "learning_rate": 3.2115151786915383e-06, - "loss": 0.1408, + "epoch": 0.47, + "learning_rate": 2.665824030782309e-05, + "loss": 0.1361, "step": 209770 }, { - "epoch": 0.94, - "learning_rate": 3.209273126765616e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.665712176461377e-05, + "loss": 0.1391, "step": 209780 }, { - "epoch": 0.94, - "learning_rate": 3.2070310748396932e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.6656003221404446e-05, + "loss": 0.1366, "step": 209790 }, { - "epoch": 0.94, - "learning_rate": 3.2047890229137707e-06, - "loss": 0.1323, + "epoch": 0.47, + "learning_rate": 2.6654884678195117e-05, + "loss": 0.1368, "step": 209800 }, { - "epoch": 0.94, - "learning_rate": 3.2025469709878485e-06, - "loss": 0.1329, + "epoch": 0.47, + "learning_rate": 2.6653766134985795e-05, + "loss": 0.1383, "step": 209810 }, { - "epoch": 0.94, - "learning_rate": 3.2003049190619256e-06, - "loss": 0.133, + "epoch": 0.47, + "learning_rate": 2.665264759177647e-05, + "loss": 0.1377, "step": 209820 }, { - "epoch": 0.94, - "learning_rate": 3.198062867136003e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.6651529048567148e-05, + "loss": 0.1383, "step": 209830 }, { - "epoch": 0.94, - "learning_rate": 3.195820815210081e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6650410505357826e-05, + "loss": 0.133, "step": 209840 }, { - "epoch": 0.94, - "learning_rate": 3.193578763284158e-06, - "loss": 0.1371, + "epoch": 0.47, + "learning_rate": 2.6649291962148497e-05, + "loss": 0.1353, "step": 209850 }, { - "epoch": 0.94, - "learning_rate": 3.1913367113582353e-06, - "loss": 0.1405, + "epoch": 0.47, + "learning_rate": 2.6648173418939175e-05, + "loss": 0.1358, "step": 209860 }, { - "epoch": 0.94, - "learning_rate": 3.1890946594323124e-06, - "loss": 0.1363, + "epoch": 0.47, + "learning_rate": 2.664705487572985e-05, + "loss": 0.1395, "step": 209870 }, { - "epoch": 0.94, - "learning_rate": 3.1868526075063902e-06, + "epoch": 0.47, + "learning_rate": 2.6645936332520527e-05, "loss": 0.1373, "step": 209880 }, { - "epoch": 0.94, - "learning_rate": 3.1846105555804673e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.6644817789311205e-05, + "loss": 0.1387, "step": 209890 }, { - "epoch": 0.94, - "learning_rate": 3.1823685036545447e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.6643699246101876e-05, + "loss": 0.1394, "step": 209900 }, { - "epoch": 0.94, - "learning_rate": 3.1801264517286226e-06, - "loss": 0.1389, + "epoch": 0.47, + "learning_rate": 2.6642580702892554e-05, + "loss": 0.1346, "step": 209910 }, { - "epoch": 0.94, - "learning_rate": 3.1778843998026996e-06, - "loss": 0.1393, + "epoch": 0.47, + "learning_rate": 2.664146215968323e-05, + "loss": 0.1378, "step": 209920 }, { - "epoch": 0.94, - "learning_rate": 3.175642347876777e-06, + "epoch": 0.47, + "learning_rate": 2.6640343616473907e-05, "loss": 0.1361, "step": 209930 }, { - "epoch": 0.94, - "learning_rate": 3.173400295950854e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.6639225073264578e-05, + "loss": 0.1387, "step": 209940 }, { - "epoch": 0.94, - "learning_rate": 3.171158244024932e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.6638106530055256e-05, + "loss": 0.1398, "step": 209950 }, { - "epoch": 0.94, - "learning_rate": 3.168916192099009e-06, - "loss": 0.1358, + "epoch": 0.47, + "learning_rate": 2.6636987986845934e-05, + "loss": 0.1347, "step": 209960 }, { - "epoch": 0.94, - "learning_rate": 3.1666741401730864e-06, - "loss": 0.1373, + "epoch": 0.47, + "learning_rate": 2.663586944363661e-05, + "loss": 0.1346, "step": 209970 }, { - "epoch": 0.94, - "learning_rate": 3.1644320882471643e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.6634750900427286e-05, + "loss": 0.1394, "step": 209980 }, { - "epoch": 0.94, - "learning_rate": 3.1621900363212413e-06, - "loss": 0.1351, + "epoch": 0.47, + "learning_rate": 2.6633632357217957e-05, + "loss": 0.1343, "step": 209990 }, { - "epoch": 0.94, - "learning_rate": 3.1599479843953188e-06, - "loss": 0.1321, + "epoch": 0.47, + "learning_rate": 2.6632513814008635e-05, + "loss": 0.1326, "step": 210000 }, { - "epoch": 0.94, - "learning_rate": 3.1577059324693958e-06, - "loss": 0.1385, + "epoch": 0.47, + "learning_rate": 2.6631395270799313e-05, + "loss": 0.1402, "step": 210010 }, { - "epoch": 0.94, - "learning_rate": 3.1554638805434737e-06, - "loss": 0.1401, + "epoch": 0.47, + "learning_rate": 2.6630276727589988e-05, + "loss": 0.1379, "step": 210020 }, { - "epoch": 0.94, - "learning_rate": 3.153221828617551e-06, - "loss": 0.1335, + "epoch": 0.47, + "learning_rate": 2.6629158184380666e-05, + "loss": 0.1341, "step": 210030 }, { - "epoch": 0.94, - "learning_rate": 3.150979776691628e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.6628039641171337e-05, + "loss": 0.136, "step": 210040 }, { - "epoch": 0.94, - "learning_rate": 3.148737724765706e-06, - "loss": 0.1376, + "epoch": 0.47, + "learning_rate": 2.6626921097962015e-05, + "loss": 0.1359, "step": 210050 }, { - "epoch": 0.94, - "learning_rate": 3.146495672839783e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.6625802554752693e-05, + "loss": 0.1403, "step": 210060 }, { - "epoch": 0.94, - "learning_rate": 3.1442536209138605e-06, - "loss": 0.1343, + "epoch": 0.47, + "learning_rate": 2.6624684011543367e-05, + "loss": 0.1351, "step": 210070 }, { - "epoch": 0.94, - "learning_rate": 3.1420115689879375e-06, - "loss": 0.1324, + "epoch": 0.47, + "learning_rate": 2.6623565468334045e-05, + "loss": 0.1319, "step": 210080 }, { - "epoch": 0.94, - "learning_rate": 3.1397695170620154e-06, - "loss": 0.1412, + "epoch": 0.47, + "learning_rate": 2.6622446925124716e-05, + "loss": 0.1385, "step": 210090 }, { - "epoch": 0.94, - "learning_rate": 3.137527465136093e-06, - "loss": 0.1343, + "epoch": 0.47, + "learning_rate": 2.6621328381915394e-05, + "loss": 0.1349, "step": 210100 }, { - "epoch": 0.94, - "learning_rate": 3.13528541321017e-06, - "loss": 0.133, + "epoch": 0.47, + "learning_rate": 2.6620209838706072e-05, + "loss": 0.1351, "step": 210110 }, { - "epoch": 0.94, - "learning_rate": 3.1330433612842477e-06, - "loss": 0.1384, + "epoch": 0.47, + "learning_rate": 2.6619091295496747e-05, + "loss": 0.1381, "step": 210120 }, { - "epoch": 0.94, - "learning_rate": 3.130801309358325e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.6617972752287425e-05, + "loss": 0.1359, "step": 210130 }, { - "epoch": 0.94, - "learning_rate": 3.128559257432402e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.6616854209078096e-05, + "loss": 0.1355, "step": 210140 }, { - "epoch": 0.94, - "learning_rate": 3.12631720550648e-06, - "loss": 0.1408, + "epoch": 0.47, + "learning_rate": 2.6615735665868774e-05, + "loss": 0.1372, "step": 210150 }, { - "epoch": 0.94, - "learning_rate": 3.124075153580557e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.6614617122659452e-05, + "loss": 0.1351, "step": 210160 }, { - "epoch": 0.94, - "learning_rate": 3.1218331016546345e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.6613498579450126e-05, + "loss": 0.1377, "step": 210170 }, { - "epoch": 0.94, - "learning_rate": 3.119591049728712e-06, - "loss": 0.139, + "epoch": 0.47, + "learning_rate": 2.6612380036240804e-05, + "loss": 0.1374, "step": 210180 }, { - "epoch": 0.94, - "learning_rate": 3.117348997802789e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.6611261493031475e-05, + "loss": 0.1388, "step": 210190 }, { - "epoch": 0.94, - "learning_rate": 3.115106945876867e-06, + "epoch": 0.47, + "learning_rate": 2.6610142949822153e-05, "loss": 0.1361, "step": 210200 }, { - "epoch": 0.94, - "learning_rate": 3.112864893950944e-06, - "loss": 0.1388, + "epoch": 0.47, + "learning_rate": 2.660902440661283e-05, + "loss": 0.1334, "step": 210210 }, { - "epoch": 0.94, - "learning_rate": 3.1106228420250213e-06, - "loss": 0.1423, + "epoch": 0.47, + "learning_rate": 2.6607905863403502e-05, + "loss": 0.1381, "step": 210220 }, { - "epoch": 0.94, - "learning_rate": 3.1083807900990988e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.660678732019418e-05, + "loss": 0.1359, "step": 210230 }, { - "epoch": 0.94, - "learning_rate": 3.1061387381731762e-06, - "loss": 0.1403, + "epoch": 0.47, + "learning_rate": 2.6605668776984855e-05, + "loss": 0.1345, "step": 210240 }, { - "epoch": 0.94, - "learning_rate": 3.1038966862472537e-06, - "loss": 0.1341, + "epoch": 0.47, + "learning_rate": 2.6604550233775533e-05, + "loss": 0.1377, "step": 210250 }, { - "epoch": 0.94, - "learning_rate": 3.1016546343213307e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.6603431690566204e-05, + "loss": 0.1394, "step": 210260 }, { - "epoch": 0.94, - "learning_rate": 3.0994125823954086e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.6602313147356882e-05, + "loss": 0.1377, "step": 210270 }, { - "epoch": 0.94, - "learning_rate": 3.097170530469486e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.660119460414756e-05, + "loss": 0.1369, "step": 210280 }, { - "epoch": 0.94, - "learning_rate": 3.094928478543563e-06, - "loss": 0.1367, + "epoch": 0.47, + "learning_rate": 2.6600076060938234e-05, + "loss": 0.1366, "step": 210290 }, { - "epoch": 0.94, - "learning_rate": 3.092686426617641e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.6598957517728912e-05, + "loss": 0.1444, "step": 210300 }, { - "epoch": 0.94, - "learning_rate": 3.090444374691718e-06, - "loss": 0.1342, + "epoch": 0.47, + "learning_rate": 2.6597838974519583e-05, + "loss": 0.1384, "step": 210310 }, { - "epoch": 0.94, - "learning_rate": 3.0882023227657954e-06, - "loss": 0.1296, + "epoch": 0.47, + "learning_rate": 2.659672043131026e-05, + "loss": 0.1379, "step": 210320 }, { - "epoch": 0.94, - "learning_rate": 3.085960270839873e-06, - "loss": 0.1336, + "epoch": 0.47, + "learning_rate": 2.659560188810094e-05, + "loss": 0.1395, "step": 210330 }, { - "epoch": 0.94, - "learning_rate": 3.0837182189139503e-06, - "loss": 0.1417, + "epoch": 0.47, + "learning_rate": 2.6594483344891614e-05, + "loss": 0.1381, "step": 210340 }, { - "epoch": 0.94, - "learning_rate": 3.0814761669880277e-06, - "loss": 0.1405, + "epoch": 0.47, + "learning_rate": 2.6593364801682292e-05, + "loss": 0.1374, "step": 210350 }, { - "epoch": 0.94, - "learning_rate": 3.0792341150621047e-06, - "loss": 0.1343, + "epoch": 0.47, + "learning_rate": 2.6592246258472963e-05, + "loss": 0.1362, "step": 210360 }, { - "epoch": 0.94, - "learning_rate": 3.0769920631361826e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.659112771526364e-05, + "loss": 0.1366, "step": 210370 }, { - "epoch": 0.94, - "learning_rate": 3.0747500112102596e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.659000917205432e-05, + "loss": 0.1335, "step": 210380 }, { - "epoch": 0.94, - "learning_rate": 3.072507959284337e-06, - "loss": 0.1432, + "epoch": 0.47, + "learning_rate": 2.6588890628844993e-05, + "loss": 0.1323, "step": 210390 }, { - "epoch": 0.94, - "learning_rate": 3.0702659073584145e-06, - "loss": 0.1342, + "epoch": 0.47, + "learning_rate": 2.658777208563567e-05, + "loss": 0.1334, "step": 210400 }, { - "epoch": 0.94, - "learning_rate": 3.068023855432492e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.6586653542426342e-05, + "loss": 0.1399, "step": 210410 }, { - "epoch": 0.94, - "learning_rate": 3.0657818035065694e-06, - "loss": 0.1367, + "epoch": 0.47, + "learning_rate": 2.658553499921702e-05, + "loss": 0.141, "step": 210420 }, { - "epoch": 0.94, - "learning_rate": 3.063539751580647e-06, - "loss": 0.1333, + "epoch": 0.47, + "learning_rate": 2.6584416456007698e-05, + "loss": 0.1309, "step": 210430 }, { - "epoch": 0.94, - "learning_rate": 3.0612976996547243e-06, - "loss": 0.1404, + "epoch": 0.47, + "learning_rate": 2.6583297912798373e-05, + "loss": 0.1341, "step": 210440 }, { - "epoch": 0.94, - "learning_rate": 3.0590556477288013e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.658217936958905e-05, + "loss": 0.1414, "step": 210450 }, { - "epoch": 0.94, - "learning_rate": 3.056813595802879e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.6581060826379722e-05, + "loss": 0.1367, "step": 210460 }, { - "epoch": 0.94, - "learning_rate": 3.0545715438769567e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.65799422831704e-05, + "loss": 0.1414, "step": 210470 }, { - "epoch": 0.94, - "learning_rate": 3.0523294919510337e-06, - "loss": 0.1363, + "epoch": 0.47, + "learning_rate": 2.6578823739961078e-05, + "loss": 0.1365, "step": 210480 }, { - "epoch": 0.94, - "learning_rate": 3.050087440025111e-06, - "loss": 0.1371, + "epoch": 0.47, + "learning_rate": 2.6577705196751752e-05, + "loss": 0.1352, "step": 210490 }, { - "epoch": 0.94, - "learning_rate": 3.0478453880991886e-06, - "loss": 0.142, + "epoch": 0.47, + "learning_rate": 2.657658665354243e-05, + "loss": 0.1364, "step": 210500 }, { - "epoch": 0.94, - "learning_rate": 3.045603336173266e-06, - "loss": 0.1338, + "epoch": 0.47, + "learning_rate": 2.65754681103331e-05, + "loss": 0.1376, "step": 210510 }, { - "epoch": 0.94, - "learning_rate": 3.043361284247343e-06, - "loss": 0.1443, + "epoch": 0.47, + "learning_rate": 2.657434956712378e-05, + "loss": 0.1374, "step": 210520 }, { - "epoch": 0.94, - "learning_rate": 3.0411192323214205e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.6573231023914457e-05, + "loss": 0.1396, "step": 210530 }, { - "epoch": 0.94, - "learning_rate": 3.0388771803954984e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.657211248070513e-05, + "loss": 0.1432, "step": 210540 }, { - "epoch": 0.94, - "learning_rate": 3.0366351284695754e-06, - "loss": 0.139, + "epoch": 0.47, + "learning_rate": 2.657099393749581e-05, + "loss": 0.1397, "step": 210550 }, { - "epoch": 0.94, - "learning_rate": 3.034393076543653e-06, - "loss": 0.1373, + "epoch": 0.47, + "learning_rate": 2.656987539428648e-05, + "loss": 0.1398, "step": 210560 }, { - "epoch": 0.94, - "learning_rate": 3.0321510246177303e-06, - "loss": 0.1325, + "epoch": 0.47, + "learning_rate": 2.656875685107716e-05, + "loss": 0.1426, "step": 210570 }, { - "epoch": 0.94, - "learning_rate": 3.0299089726918077e-06, - "loss": 0.1412, + "epoch": 0.47, + "learning_rate": 2.656763830786783e-05, + "loss": 0.1455, "step": 210580 }, { - "epoch": 0.94, - "learning_rate": 3.027666920765885e-06, - "loss": 0.1405, + "epoch": 0.47, + "learning_rate": 2.656651976465851e-05, + "loss": 0.1384, "step": 210590 }, { - "epoch": 0.94, - "learning_rate": 3.0254248688399626e-06, - "loss": 0.1388, + "epoch": 0.47, + "learning_rate": 2.656540122144919e-05, + "loss": 0.1372, "step": 210600 }, { - "epoch": 0.94, - "learning_rate": 3.02318281691404e-06, - "loss": 0.1331, + "epoch": 0.47, + "learning_rate": 2.656428267823986e-05, + "loss": 0.1384, "step": 210610 }, { - "epoch": 0.94, - "learning_rate": 3.020940764988117e-06, - "loss": 0.1428, + "epoch": 0.47, + "learning_rate": 2.6563164135030538e-05, + "loss": 0.1344, "step": 210620 }, { - "epoch": 0.94, - "learning_rate": 3.0186987130621945e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.656204559182121e-05, + "loss": 0.1411, "step": 210630 }, { - "epoch": 0.94, - "learning_rate": 3.016456661136272e-06, - "loss": 0.1321, + "epoch": 0.47, + "learning_rate": 2.6560927048611887e-05, + "loss": 0.1351, "step": 210640 }, { - "epoch": 0.94, - "learning_rate": 3.0142146092103494e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.655980850540257e-05, + "loss": 0.1336, "step": 210650 }, { - "epoch": 0.94, - "learning_rate": 3.011972557284427e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.655868996219324e-05, + "loss": 0.1327, "step": 210660 }, { - "epoch": 0.94, - "learning_rate": 3.0097305053585043e-06, - "loss": 0.1387, + "epoch": 0.47, + "learning_rate": 2.6557571418983918e-05, + "loss": 0.1377, "step": 210670 }, { - "epoch": 0.94, - "learning_rate": 3.0074884534325818e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.655645287577459e-05, + "loss": 0.1344, "step": 210680 }, { - "epoch": 0.94, - "learning_rate": 3.005246401506659e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.6555334332565267e-05, + "loss": 0.1368, "step": 210690 }, { - "epoch": 0.94, - "learning_rate": 3.0030043495807367e-06, - "loss": 0.1315, + "epoch": 0.47, + "learning_rate": 2.6554215789355945e-05, + "loss": 0.1387, "step": 210700 }, { - "epoch": 0.94, - "learning_rate": 3.0007622976548137e-06, - "loss": 0.1338, + "epoch": 0.47, + "learning_rate": 2.655309724614662e-05, + "loss": 0.1396, "step": 210710 }, { - "epoch": 0.94, - "learning_rate": 2.998520245728891e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.6551978702937297e-05, + "loss": 0.1411, "step": 210720 }, { - "epoch": 0.94, - "learning_rate": 2.9962781938029686e-06, - "loss": 0.1331, + "epoch": 0.47, + "learning_rate": 2.6550860159727968e-05, + "loss": 0.1385, "step": 210730 }, { - "epoch": 0.94, - "learning_rate": 2.994036141877046e-06, - "loss": 0.1319, + "epoch": 0.47, + "learning_rate": 2.6549741616518646e-05, + "loss": 0.1354, "step": 210740 }, { - "epoch": 0.94, - "learning_rate": 2.9917940899511235e-06, - "loss": 0.1345, + "epoch": 0.47, + "learning_rate": 2.6548623073309324e-05, + "loss": 0.1321, "step": 210750 }, { - "epoch": 0.94, - "learning_rate": 2.9895520380252005e-06, - "loss": 0.1314, + "epoch": 0.47, + "learning_rate": 2.65475045301e-05, + "loss": 0.1335, "step": 210760 }, { - "epoch": 0.94, - "learning_rate": 2.9873099860992784e-06, - "loss": 0.143, + "epoch": 0.47, + "learning_rate": 2.6546385986890677e-05, + "loss": 0.1334, "step": 210770 }, { - "epoch": 0.94, - "learning_rate": 2.985067934173356e-06, - "loss": 0.1397, + "epoch": 0.47, + "learning_rate": 2.6545267443681348e-05, + "loss": 0.1395, "step": 210780 }, { - "epoch": 0.94, - "learning_rate": 2.982825882247433e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6544148900472026e-05, + "loss": 0.1423, "step": 210790 }, { - "epoch": 0.94, - "learning_rate": 2.9805838303215103e-06, - "loss": 0.1408, + "epoch": 0.47, + "learning_rate": 2.6543030357262704e-05, + "loss": 0.1373, "step": 210800 }, { - "epoch": 0.94, - "learning_rate": 2.9783417783955878e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.6541911814053378e-05, + "loss": 0.1373, "step": 210810 }, { - "epoch": 0.94, - "learning_rate": 2.976099726469665e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.6540793270844056e-05, + "loss": 0.14, "step": 210820 }, { - "epoch": 0.94, - "learning_rate": 2.9738576745437422e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.6539674727634727e-05, + "loss": 0.135, "step": 210830 }, { - "epoch": 0.94, - "learning_rate": 2.97161562261782e-06, - "loss": 0.1351, + "epoch": 0.47, + "learning_rate": 2.6538556184425405e-05, + "loss": 0.1391, "step": 210840 }, { - "epoch": 0.94, - "learning_rate": 2.9693735706918975e-06, - "loss": 0.1351, + "epoch": 0.47, + "learning_rate": 2.6537437641216083e-05, + "loss": 0.1372, "step": 210850 }, { - "epoch": 0.94, - "learning_rate": 2.9671315187659746e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.6536319098006758e-05, + "loss": 0.1368, "step": 210860 }, { - "epoch": 0.94, - "learning_rate": 2.9648894668400524e-06, - "loss": 0.1432, + "epoch": 0.47, + "learning_rate": 2.6535200554797436e-05, + "loss": 0.1333, "step": 210870 }, { - "epoch": 0.94, - "learning_rate": 2.9626474149141295e-06, - "loss": 0.1333, + "epoch": 0.47, + "learning_rate": 2.6534082011588107e-05, + "loss": 0.1421, "step": 210880 }, { - "epoch": 0.94, - "learning_rate": 2.960405362988207e-06, - "loss": 0.1311, + "epoch": 0.47, + "learning_rate": 2.6532963468378785e-05, + "loss": 0.1373, "step": 210890 }, { - "epoch": 0.94, - "learning_rate": 2.9581633110622844e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.653184492516946e-05, + "loss": 0.139, "step": 210900 }, { - "epoch": 0.94, - "learning_rate": 2.955921259136362e-06, - "loss": 0.1341, + "epoch": 0.47, + "learning_rate": 2.6530726381960137e-05, + "loss": 0.1339, "step": 210910 }, { - "epoch": 0.94, - "learning_rate": 2.9536792072104392e-06, - "loss": 0.1358, + "epoch": 0.47, + "learning_rate": 2.6529607838750815e-05, + "loss": 0.1354, "step": 210920 }, { - "epoch": 0.94, - "learning_rate": 2.9514371552845163e-06, - "loss": 0.1396, + "epoch": 0.47, + "learning_rate": 2.6528489295541486e-05, + "loss": 0.1331, "step": 210930 }, { - "epoch": 0.94, - "learning_rate": 2.949195103358594e-06, - "loss": 0.1326, + "epoch": 0.47, + "learning_rate": 2.6527370752332164e-05, + "loss": 0.139, "step": 210940 }, { - "epoch": 0.94, - "learning_rate": 2.946953051432671e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.652625220912284e-05, + "loss": 0.1353, "step": 210950 }, { - "epoch": 0.94, - "learning_rate": 2.9447109995067486e-06, - "loss": 0.1338, + "epoch": 0.47, + "learning_rate": 2.6525133665913517e-05, + "loss": 0.1316, "step": 210960 }, { - "epoch": 0.94, - "learning_rate": 2.942468947580826e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.6524015122704194e-05, + "loss": 0.1361, "step": 210970 }, { - "epoch": 0.94, - "learning_rate": 2.9402268956549035e-06, - "loss": 0.1348, + "epoch": 0.47, + "learning_rate": 2.6522896579494866e-05, + "loss": 0.1347, "step": 210980 }, { - "epoch": 0.94, - "learning_rate": 2.937984843728981e-06, - "loss": 0.1335, + "epoch": 0.47, + "learning_rate": 2.6521778036285544e-05, + "loss": 0.141, "step": 210990 }, { - "epoch": 0.94, - "learning_rate": 2.9357427918030584e-06, - "loss": 0.1367, + "epoch": 0.47, + "learning_rate": 2.6520659493076218e-05, + "loss": 0.1411, "step": 211000 }, { - "epoch": 0.94, - "learning_rate": 2.933500739877136e-06, - "loss": 0.136, + "epoch": 0.47, + "learning_rate": 2.6519540949866896e-05, + "loss": 0.1357, "step": 211010 }, { - "epoch": 0.94, - "learning_rate": 2.931258687951213e-06, - "loss": 0.1409, + "epoch": 0.47, + "learning_rate": 2.6518422406657574e-05, + "loss": 0.1348, "step": 211020 }, { - "epoch": 0.94, - "learning_rate": 2.9290166360252903e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.6517303863448245e-05, + "loss": 0.133, "step": 211030 }, { - "epoch": 0.94, - "learning_rate": 2.926774584099368e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.6516185320238923e-05, + "loss": 0.1372, "step": 211040 }, { - "epoch": 0.94, - "learning_rate": 2.9245325321734452e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.6515066777029594e-05, + "loss": 0.1349, "step": 211050 }, { - "epoch": 0.94, - "learning_rate": 2.9222904802475227e-06, - "loss": 0.1352, + "epoch": 0.47, + "learning_rate": 2.6513948233820275e-05, + "loss": 0.1328, "step": 211060 }, { - "epoch": 0.94, - "learning_rate": 2.9200484283216e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.6512829690610953e-05, + "loss": 0.1359, "step": 211070 }, { - "epoch": 0.94, - "learning_rate": 2.9178063763956776e-06, - "loss": 0.1376, + "epoch": 0.47, + "learning_rate": 2.6511711147401625e-05, + "loss": 0.1345, "step": 211080 }, { - "epoch": 0.94, - "learning_rate": 2.915564324469755e-06, - "loss": 0.1396, + "epoch": 0.47, + "learning_rate": 2.6510592604192303e-05, + "loss": 0.1378, "step": 211090 }, { - "epoch": 0.94, - "learning_rate": 2.913322272543832e-06, - "loss": 0.1391, + "epoch": 0.47, + "learning_rate": 2.6509474060982974e-05, + "loss": 0.1354, "step": 211100 }, { - "epoch": 0.94, - "learning_rate": 2.91108022061791e-06, - "loss": 0.1328, + "epoch": 0.47, + "learning_rate": 2.650835551777365e-05, + "loss": 0.1359, "step": 211110 }, { - "epoch": 0.94, - "learning_rate": 2.908838168691987e-06, - "loss": 0.1268, + "epoch": 0.47, + "learning_rate": 2.650723697456433e-05, + "loss": 0.1387, "step": 211120 }, { - "epoch": 0.94, - "learning_rate": 2.9065961167660644e-06, - "loss": 0.1367, + "epoch": 0.47, + "learning_rate": 2.6506118431355004e-05, + "loss": 0.1305, "step": 211130 }, { - "epoch": 0.94, - "learning_rate": 2.904354064840142e-06, - "loss": 0.1401, + "epoch": 0.47, + "learning_rate": 2.6504999888145682e-05, + "loss": 0.1391, "step": 211140 }, { - "epoch": 0.94, - "learning_rate": 2.9021120129142193e-06, - "loss": 0.1339, + "epoch": 0.47, + "learning_rate": 2.6503881344936353e-05, + "loss": 0.1365, "step": 211150 }, { - "epoch": 0.94, - "learning_rate": 2.8998699609882967e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.650276280172703e-05, + "loss": 0.1344, "step": 211160 }, { - "epoch": 0.94, - "learning_rate": 2.897627909062374e-06, - "loss": 0.1393, + "epoch": 0.47, + "learning_rate": 2.650164425851771e-05, + "loss": 0.138, "step": 211170 }, { - "epoch": 0.94, - "learning_rate": 2.8953858571364516e-06, - "loss": 0.1345, + "epoch": 0.47, + "learning_rate": 2.6500525715308384e-05, + "loss": 0.1395, "step": 211180 }, { - "epoch": 0.94, - "learning_rate": 2.8931438052105286e-06, - "loss": 0.1392, + "epoch": 0.47, + "learning_rate": 2.649940717209906e-05, + "loss": 0.1434, "step": 211190 }, { - "epoch": 0.94, - "learning_rate": 2.890901753284606e-06, - "loss": 0.1395, + "epoch": 0.47, + "learning_rate": 2.6498288628889733e-05, + "loss": 0.1365, "step": 211200 }, { - "epoch": 0.94, - "learning_rate": 2.8886597013586835e-06, - "loss": 0.1337, + "epoch": 0.47, + "learning_rate": 2.649717008568041e-05, + "loss": 0.1376, "step": 211210 }, { - "epoch": 0.94, - "learning_rate": 2.886417649432761e-06, - "loss": 0.1385, + "epoch": 0.47, + "learning_rate": 2.6496051542471085e-05, + "loss": 0.1346, "step": 211220 }, { - "epoch": 0.94, - "learning_rate": 2.8841755975068384e-06, - "loss": 0.1428, + "epoch": 0.47, + "learning_rate": 2.6494932999261763e-05, + "loss": 0.1413, "step": 211230 }, { - "epoch": 0.94, - "learning_rate": 2.881933545580916e-06, - "loss": 0.1291, + "epoch": 0.47, + "learning_rate": 2.649381445605244e-05, + "loss": 0.1397, "step": 211240 }, { - "epoch": 0.94, - "learning_rate": 2.8796914936549933e-06, - "loss": 0.1387, + "epoch": 0.47, + "learning_rate": 2.6492695912843112e-05, + "loss": 0.1323, "step": 211250 }, { - "epoch": 0.94, - "learning_rate": 2.8774494417290703e-06, - "loss": 0.1349, + "epoch": 0.47, + "learning_rate": 2.649157736963379e-05, + "loss": 0.1382, "step": 211260 }, { - "epoch": 0.94, - "learning_rate": 2.875207389803148e-06, - "loss": 0.1401, + "epoch": 0.47, + "learning_rate": 2.6490458826424465e-05, + "loss": 0.1351, "step": 211270 }, { - "epoch": 0.94, - "learning_rate": 2.8729653378772257e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6489340283215142e-05, + "loss": 0.1394, "step": 211280 }, { - "epoch": 0.94, - "learning_rate": 2.8707232859513027e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.648822174000582e-05, + "loss": 0.1369, "step": 211290 }, { - "epoch": 0.94, - "learning_rate": 2.86848123402538e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.648710319679649e-05, + "loss": 0.137, "step": 211300 }, { - "epoch": 0.94, - "learning_rate": 2.8662391820994576e-06, - "loss": 0.131, + "epoch": 0.47, + "learning_rate": 2.648598465358717e-05, + "loss": 0.1369, "step": 211310 }, { - "epoch": 0.94, - "learning_rate": 2.863997130173535e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.6484866110377844e-05, + "loss": 0.1368, "step": 211320 }, { - "epoch": 0.94, - "learning_rate": 2.861755078247612e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.6483747567168522e-05, + "loss": 0.1371, "step": 211330 }, { - "epoch": 0.94, - "learning_rate": 2.85951302632169e-06, - "loss": 0.1393, + "epoch": 0.47, + "learning_rate": 2.64826290239592e-05, + "loss": 0.134, "step": 211340 }, { - "epoch": 0.94, - "learning_rate": 2.8572709743957674e-06, - "loss": 0.1342, + "epoch": 0.47, + "learning_rate": 2.648151048074987e-05, + "loss": 0.1275, "step": 211350 }, { - "epoch": 0.94, - "learning_rate": 2.8550289224698444e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.648039193754055e-05, + "loss": 0.1368, "step": 211360 }, { - "epoch": 0.94, - "learning_rate": 2.852786870543922e-06, - "loss": 0.1345, + "epoch": 0.47, + "learning_rate": 2.6479273394331223e-05, + "loss": 0.1329, "step": 211370 }, { - "epoch": 0.94, - "learning_rate": 2.8505448186179993e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.64781548511219e-05, + "loss": 0.1398, "step": 211380 }, { - "epoch": 0.94, - "learning_rate": 2.8483027666920767e-06, - "loss": 0.1314, + "epoch": 0.47, + "learning_rate": 2.647703630791258e-05, + "loss": 0.1377, "step": 211390 }, { - "epoch": 0.94, - "learning_rate": 2.8460607147661537e-06, - "loss": 0.1356, + "epoch": 0.47, + "learning_rate": 2.647591776470325e-05, + "loss": 0.1405, "step": 211400 }, { - "epoch": 0.94, - "learning_rate": 2.8438186628402316e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.647479922149393e-05, + "loss": 0.1389, "step": 211410 }, { - "epoch": 0.94, - "learning_rate": 2.841576610914309e-06, - "loss": 0.1314, + "epoch": 0.47, + "learning_rate": 2.6473680678284603e-05, + "loss": 0.1386, "step": 211420 }, { - "epoch": 0.94, - "learning_rate": 2.839334558988386e-06, - "loss": 0.135, + "epoch": 0.47, + "learning_rate": 2.647256213507528e-05, + "loss": 0.142, "step": 211430 }, { - "epoch": 0.94, - "learning_rate": 2.837092507062464e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.647144359186596e-05, + "loss": 0.1393, "step": 211440 }, { - "epoch": 0.94, - "learning_rate": 2.834850455136541e-06, - "loss": 0.1339, + "epoch": 0.47, + "learning_rate": 2.647032504865663e-05, + "loss": 0.1295, "step": 211450 }, { - "epoch": 0.94, - "learning_rate": 2.8326084032106184e-06, - "loss": 0.139, + "epoch": 0.47, + "learning_rate": 2.6469206505447308e-05, + "loss": 0.1372, "step": 211460 }, { - "epoch": 0.94, - "learning_rate": 2.830366351284696e-06, - "loss": 0.1419, + "epoch": 0.47, + "learning_rate": 2.646808796223798e-05, + "loss": 0.1356, "step": 211470 }, { - "epoch": 0.94, - "learning_rate": 2.8281242993587733e-06, - "loss": 0.1428, + "epoch": 0.47, + "learning_rate": 2.646696941902866e-05, + "loss": 0.142, "step": 211480 }, { - "epoch": 0.94, - "learning_rate": 2.8258822474328508e-06, - "loss": 0.1363, + "epoch": 0.47, + "learning_rate": 2.6465850875819338e-05, + "loss": 0.1378, "step": 211490 }, { - "epoch": 0.94, - "learning_rate": 2.823640195506928e-06, - "loss": 0.143, + "epoch": 0.47, + "learning_rate": 2.646473233261001e-05, + "loss": 0.1411, "step": 211500 }, { - "epoch": 0.94, - "learning_rate": 2.8213981435810057e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.6463613789400687e-05, + "loss": 0.1365, "step": 211510 }, { - "epoch": 0.94, - "learning_rate": 2.8191560916550827e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.646249524619136e-05, + "loss": 0.1378, "step": 211520 }, { - "epoch": 0.94, - "learning_rate": 2.81691403972916e-06, - "loss": 0.1366, + "epoch": 0.47, + "learning_rate": 2.6461376702982036e-05, + "loss": 0.1351, "step": 211530 }, { - "epoch": 0.94, - "learning_rate": 2.8146719878032376e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.646025815977271e-05, + "loss": 0.137, "step": 211540 }, { - "epoch": 0.94, - "learning_rate": 2.8126541410699075e-06, - "loss": 0.1399, + "epoch": 0.47, + "learning_rate": 2.645913961656339e-05, + "loss": 0.1337, "step": 211550 }, { - "epoch": 0.94, - "learning_rate": 2.8104120891439845e-06, - "loss": 0.1433, + "epoch": 0.47, + "learning_rate": 2.6458021073354067e-05, + "loss": 0.1402, "step": 211560 }, { - "epoch": 0.94, - "learning_rate": 2.8081700372180624e-06, - "loss": 0.1363, + "epoch": 0.47, + "learning_rate": 2.6456902530144738e-05, + "loss": 0.1374, "step": 211570 }, { - "epoch": 0.94, - "learning_rate": 2.8059279852921394e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.6455783986935416e-05, + "loss": 0.1398, "step": 211580 }, { - "epoch": 0.94, - "learning_rate": 2.803685933366217e-06, - "loss": 0.1332, + "epoch": 0.47, + "learning_rate": 2.645466544372609e-05, + "loss": 0.1379, "step": 211590 }, { - "epoch": 0.94, - "learning_rate": 2.8014438814402943e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.645354690051677e-05, + "loss": 0.1413, "step": 211600 }, { - "epoch": 0.94, - "learning_rate": 2.7992018295143718e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6452428357307446e-05, + "loss": 0.1371, "step": 211610 }, { - "epoch": 0.94, - "learning_rate": 2.796959777588449e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.6451309814098117e-05, + "loss": 0.1331, "step": 211620 }, { - "epoch": 0.94, - "learning_rate": 2.7947177256625262e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.6450191270888795e-05, + "loss": 0.1386, "step": 211630 }, { - "epoch": 0.94, - "learning_rate": 2.792475673736604e-06, - "loss": 0.1409, + "epoch": 0.47, + "learning_rate": 2.644907272767947e-05, + "loss": 0.1396, "step": 211640 }, { - "epoch": 0.94, - "learning_rate": 2.790233621810681e-06, - "loss": 0.1364, + "epoch": 0.47, + "learning_rate": 2.6447954184470148e-05, + "loss": 0.1346, "step": 211650 }, { - "epoch": 0.94, - "learning_rate": 2.7879915698847586e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.6446835641260826e-05, + "loss": 0.1373, "step": 211660 }, { - "epoch": 0.94, - "learning_rate": 2.785749517958836e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.6445717098051497e-05, + "loss": 0.1366, "step": 211670 }, { - "epoch": 0.94, - "learning_rate": 2.7835074660329135e-06, - "loss": 0.1415, + "epoch": 0.47, + "learning_rate": 2.6444598554842175e-05, + "loss": 0.1424, "step": 211680 }, { - "epoch": 0.95, - "learning_rate": 2.781265414106991e-06, - "loss": 0.1395, + "epoch": 0.47, + "learning_rate": 2.644348001163285e-05, + "loss": 0.1354, "step": 211690 }, { - "epoch": 0.95, - "learning_rate": 2.7790233621810684e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.6442361468423527e-05, + "loss": 0.1382, "step": 211700 }, { - "epoch": 0.95, - "learning_rate": 2.776781310255146e-06, - "loss": 0.1391, + "epoch": 0.47, + "learning_rate": 2.6441242925214205e-05, + "loss": 0.137, "step": 211710 }, { - "epoch": 0.95, - "learning_rate": 2.774539258329223e-06, - "loss": 0.1317, + "epoch": 0.47, + "learning_rate": 2.6440124382004876e-05, + "loss": 0.1337, "step": 211720 }, { - "epoch": 0.95, - "learning_rate": 2.7722972064033003e-06, - "loss": 0.1397, + "epoch": 0.47, + "learning_rate": 2.6439005838795554e-05, + "loss": 0.1322, "step": 211730 }, { - "epoch": 0.95, - "learning_rate": 2.770055154477378e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.643788729558623e-05, + "loss": 0.1337, "step": 211740 }, { - "epoch": 0.95, - "learning_rate": 2.767813102551455e-06, - "loss": 0.1348, + "epoch": 0.47, + "learning_rate": 2.6436768752376907e-05, + "loss": 0.1374, "step": 211750 }, { - "epoch": 0.95, - "learning_rate": 2.7655710506255326e-06, - "loss": 0.1372, + "epoch": 0.47, + "learning_rate": 2.6435650209167585e-05, + "loss": 0.1355, "step": 211760 }, { - "epoch": 0.95, - "learning_rate": 2.76332899869961e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6434531665958256e-05, + "loss": 0.139, "step": 211770 }, { - "epoch": 0.95, - "learning_rate": 2.7610869467736875e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.6433413122748934e-05, + "loss": 0.137, "step": 211780 }, { - "epoch": 0.95, - "learning_rate": 2.7588448948477645e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.643229457953961e-05, + "loss": 0.1365, "step": 211790 }, { - "epoch": 0.95, - "learning_rate": 2.756602842921842e-06, - "loss": 0.1327, + "epoch": 0.47, + "learning_rate": 2.6431176036330286e-05, + "loss": 0.1342, "step": 211800 }, { - "epoch": 0.95, - "learning_rate": 2.75436079099592e-06, - "loss": 0.1417, + "epoch": 0.47, + "learning_rate": 2.6430057493120964e-05, + "loss": 0.1356, "step": 211810 }, { - "epoch": 0.95, - "learning_rate": 2.752118739069997e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.6428938949911635e-05, + "loss": 0.1387, "step": 211820 }, { - "epoch": 0.95, - "learning_rate": 2.7498766871440743e-06, - "loss": 0.1347, + "epoch": 0.47, + "learning_rate": 2.6427820406702313e-05, + "loss": 0.1343, "step": 211830 }, { - "epoch": 0.95, - "learning_rate": 2.7476346352181518e-06, - "loss": 0.1341, + "epoch": 0.47, + "learning_rate": 2.6426701863492988e-05, + "loss": 0.1373, "step": 211840 }, { - "epoch": 0.95, - "learning_rate": 2.7453925832922292e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.6425583320283666e-05, + "loss": 0.1377, "step": 211850 }, { - "epoch": 0.95, - "learning_rate": 2.7431505313663067e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6424464777074337e-05, + "loss": 0.1432, "step": 211860 }, { - "epoch": 0.95, - "learning_rate": 2.740908479440384e-06, - "loss": 0.1356, + "epoch": 0.47, + "learning_rate": 2.6423346233865015e-05, + "loss": 0.1331, "step": 211870 }, { - "epoch": 0.95, - "learning_rate": 2.7386664275144616e-06, - "loss": 0.1412, + "epoch": 0.47, + "learning_rate": 2.6422227690655693e-05, + "loss": 0.1373, "step": 211880 }, { - "epoch": 0.95, - "learning_rate": 2.7364243755885386e-06, - "loss": 0.1386, + "epoch": 0.47, + "learning_rate": 2.6421109147446367e-05, + "loss": 0.1369, "step": 211890 }, { - "epoch": 0.95, - "learning_rate": 2.734182323662616e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.6419990604237045e-05, + "loss": 0.1413, "step": 211900 }, { - "epoch": 0.95, - "learning_rate": 2.7319402717366935e-06, - "loss": 0.1386, + "epoch": 0.47, + "learning_rate": 2.6418872061027716e-05, + "loss": 0.137, "step": 211910 }, { - "epoch": 0.95, - "learning_rate": 2.729698219810771e-06, + "epoch": 0.47, + "learning_rate": 2.6417753517818394e-05, "loss": 0.1326, "step": 211920 }, { - "epoch": 0.95, - "learning_rate": 2.7274561678848484e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.6416634974609072e-05, + "loss": 0.1364, "step": 211930 }, { - "epoch": 0.95, - "learning_rate": 2.725214115958926e-06, - "loss": 0.1358, + "epoch": 0.47, + "learning_rate": 2.6415516431399743e-05, + "loss": 0.1418, "step": 211940 }, { - "epoch": 0.95, - "learning_rate": 2.7229720640330033e-06, - "loss": 0.1365, + "epoch": 0.47, + "learning_rate": 2.6414397888190425e-05, + "loss": 0.1337, "step": 211950 }, { - "epoch": 0.95, - "learning_rate": 2.7207300121070803e-06, - "loss": 0.1384, + "epoch": 0.47, + "learning_rate": 2.6413279344981096e-05, + "loss": 0.1353, "step": 211960 }, { - "epoch": 0.95, - "learning_rate": 2.718487960181158e-06, - "loss": 0.1412, + "epoch": 0.47, + "learning_rate": 2.6412160801771774e-05, + "loss": 0.135, "step": 211970 }, { - "epoch": 0.95, - "learning_rate": 2.716245908255235e-06, - "loss": 0.1365, + "epoch": 0.47, + "learning_rate": 2.6411042258562452e-05, + "loss": 0.1378, "step": 211980 }, { - "epoch": 0.95, - "learning_rate": 2.7140038563293126e-06, - "loss": 0.14, + "epoch": 0.47, + "learning_rate": 2.6409923715353123e-05, + "loss": 0.1323, "step": 211990 }, { - "epoch": 0.95, - "learning_rate": 2.71176180440339e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.64088051721438e-05, + "loss": 0.1318, "step": 212000 }, { - "epoch": 0.95, - "learning_rate": 2.7095197524774675e-06, - "loss": 0.1373, + "epoch": 0.47, + "learning_rate": 2.6407686628934475e-05, + "loss": 0.1389, "step": 212010 }, { - "epoch": 0.95, - "learning_rate": 2.707277700551545e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.6406568085725153e-05, + "loss": 0.1366, "step": 212020 }, { - "epoch": 0.95, - "learning_rate": 2.705035648625622e-06, - "loss": 0.1386, + "epoch": 0.47, + "learning_rate": 2.640544954251583e-05, + "loss": 0.1415, "step": 212030 }, { - "epoch": 0.95, - "learning_rate": 2.7027935966997e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.6404330999306502e-05, + "loss": 0.1348, "step": 212040 }, { - "epoch": 0.95, - "learning_rate": 2.7005515447737773e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.640321245609718e-05, + "loss": 0.1354, "step": 212050 }, { - "epoch": 0.95, - "learning_rate": 2.6983094928478543e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.6402093912887855e-05, + "loss": 0.1381, "step": 212060 }, { - "epoch": 0.95, - "learning_rate": 2.6960674409219318e-06, - "loss": 0.1408, + "epoch": 0.47, + "learning_rate": 2.6400975369678533e-05, + "loss": 0.1318, "step": 212070 }, { - "epoch": 0.95, - "learning_rate": 2.6938253889960092e-06, - "loss": 0.1408, + "epoch": 0.47, + "learning_rate": 2.639985682646921e-05, + "loss": 0.1345, "step": 212080 }, { - "epoch": 0.95, - "learning_rate": 2.6915833370700867e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.6398738283259882e-05, + "loss": 0.1346, "step": 212090 }, { - "epoch": 0.95, - "learning_rate": 2.689341285144164e-06, - "loss": 0.1377, + "epoch": 0.47, + "learning_rate": 2.639761974005056e-05, + "loss": 0.1326, "step": 212100 }, { - "epoch": 0.95, - "learning_rate": 2.6870992332182416e-06, - "loss": 0.1388, + "epoch": 0.47, + "learning_rate": 2.6396501196841234e-05, + "loss": 0.1369, "step": 212110 }, { - "epoch": 0.95, - "learning_rate": 2.684857181292319e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6395382653631912e-05, + "loss": 0.1389, "step": 212120 }, { - "epoch": 0.95, - "learning_rate": 2.682615129366396e-06, - "loss": 0.1337, + "epoch": 0.47, + "learning_rate": 2.639426411042259e-05, + "loss": 0.1393, "step": 212130 }, { - "epoch": 0.95, - "learning_rate": 2.680373077440474e-06, - "loss": 0.1344, + "epoch": 0.47, + "learning_rate": 2.639314556721326e-05, + "loss": 0.1359, "step": 212140 }, { - "epoch": 0.95, - "learning_rate": 2.678131025514551e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.639202702400394e-05, + "loss": 0.1335, "step": 212150 }, { - "epoch": 0.95, - "learning_rate": 2.6758889735886284e-06, - "loss": 0.1321, + "epoch": 0.47, + "learning_rate": 2.6390908480794614e-05, + "loss": 0.1365, "step": 212160 }, { - "epoch": 0.95, - "learning_rate": 2.673646921662706e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.638978993758529e-05, + "loss": 0.1387, "step": 212170 }, { - "epoch": 0.95, - "learning_rate": 2.6714048697367833e-06, - "loss": 0.1284, + "epoch": 0.47, + "learning_rate": 2.6388671394375963e-05, + "loss": 0.1385, "step": 212180 }, { - "epoch": 0.95, - "learning_rate": 2.6691628178108607e-06, - "loss": 0.1346, + "epoch": 0.47, + "learning_rate": 2.638755285116664e-05, + "loss": 0.133, "step": 212190 }, { - "epoch": 0.95, - "learning_rate": 2.6669207658849378e-06, - "loss": 0.1378, + "epoch": 0.47, + "learning_rate": 2.638643430795732e-05, + "loss": 0.1372, "step": 212200 }, { - "epoch": 0.95, - "learning_rate": 2.6646787139590156e-06, - "loss": 0.132, + "epoch": 0.47, + "learning_rate": 2.6385315764747993e-05, + "loss": 0.1384, "step": 212210 }, { - "epoch": 0.95, - "learning_rate": 2.6624366620330926e-06, - "loss": 0.1371, + "epoch": 0.47, + "learning_rate": 2.638419722153867e-05, + "loss": 0.1414, "step": 212220 }, { - "epoch": 0.95, - "learning_rate": 2.66019461010717e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6383078678329342e-05, + "loss": 0.1334, "step": 212230 }, { - "epoch": 0.95, - "learning_rate": 2.657952558181248e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.638196013512002e-05, + "loss": 0.1359, "step": 212240 }, { - "epoch": 0.95, - "learning_rate": 2.655710506255325e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6380841591910698e-05, + "loss": 0.139, "step": 212250 }, { - "epoch": 0.95, - "learning_rate": 2.6534684543294024e-06, - "loss": 0.1381, + "epoch": 0.47, + "learning_rate": 2.6379723048701373e-05, + "loss": 0.1403, "step": 212260 }, { - "epoch": 0.95, - "learning_rate": 2.65122640240348e-06, - "loss": 0.1369, + "epoch": 0.47, + "learning_rate": 2.637860450549205e-05, + "loss": 0.1344, "step": 212270 }, { - "epoch": 0.95, - "learning_rate": 2.6489843504775573e-06, - "loss": 0.142, + "epoch": 0.47, + "learning_rate": 2.6377485962282722e-05, + "loss": 0.1326, "step": 212280 }, { - "epoch": 0.95, - "learning_rate": 2.6467422985516344e-06, - "loss": 0.1319, + "epoch": 0.47, + "learning_rate": 2.63763674190734e-05, + "loss": 0.1437, "step": 212290 }, { - "epoch": 0.95, - "learning_rate": 2.644500246625712e-06, - "loss": 0.139, + "epoch": 0.47, + "learning_rate": 2.6375248875864078e-05, + "loss": 0.1367, "step": 212300 }, { - "epoch": 0.95, - "learning_rate": 2.6422581946997897e-06, - "loss": 0.1368, + "epoch": 0.47, + "learning_rate": 2.6374242186975683e-05, + "loss": 0.1342, "step": 212310 }, { - "epoch": 0.95, - "learning_rate": 2.6400161427738667e-06, - "loss": 0.1401, + "epoch": 0.47, + "learning_rate": 2.637312364376636e-05, + "loss": 0.137, "step": 212320 }, { - "epoch": 0.95, - "learning_rate": 2.637774090847944e-06, - "loss": 0.1412, + "epoch": 0.47, + "learning_rate": 2.6372005100557036e-05, + "loss": 0.136, "step": 212330 }, { - "epoch": 0.95, - "learning_rate": 2.6355320389220216e-06, - "loss": 0.1335, + "epoch": 0.47, + "learning_rate": 2.6370886557347713e-05, + "loss": 0.1332, "step": 212340 }, { - "epoch": 0.95, - "learning_rate": 2.633289986996099e-06, - "loss": 0.1347, + "epoch": 0.47, + "learning_rate": 2.6369768014138385e-05, + "loss": 0.1364, "step": 212350 }, { - "epoch": 0.95, - "learning_rate": 2.6310479350701765e-06, - "loss": 0.1344, + "epoch": 0.47, + "learning_rate": 2.6368649470929063e-05, + "loss": 0.131, "step": 212360 }, { - "epoch": 0.95, - "learning_rate": 2.6288058831442535e-06, - "loss": 0.1398, + "epoch": 0.47, + "learning_rate": 2.636753092771974e-05, + "loss": 0.1327, "step": 212370 }, { - "epoch": 0.95, - "learning_rate": 2.6265638312183314e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.6366412384510415e-05, + "loss": 0.1389, "step": 212380 }, { - "epoch": 0.95, - "learning_rate": 2.6243217792924084e-06, - "loss": 0.137, + "epoch": 0.47, + "learning_rate": 2.6365293841301093e-05, + "loss": 0.1379, "step": 212390 }, { - "epoch": 0.95, - "learning_rate": 2.622079727366486e-06, - "loss": 0.1362, + "epoch": 0.47, + "learning_rate": 2.6364175298091764e-05, + "loss": 0.142, "step": 212400 }, { - "epoch": 0.95, - "learning_rate": 2.6198376754405633e-06, - "loss": 0.1391, + "epoch": 0.47, + "learning_rate": 2.6363056754882442e-05, + "loss": 0.1397, "step": 212410 }, { - "epoch": 0.95, - "learning_rate": 2.6175956235146407e-06, - "loss": 0.1393, + "epoch": 0.47, + "learning_rate": 2.636193821167312e-05, + "loss": 0.1356, "step": 212420 }, { - "epoch": 0.95, - "learning_rate": 2.615353571588718e-06, - "loss": 0.1384, + "epoch": 0.47, + "learning_rate": 2.6360819668463794e-05, + "loss": 0.1382, "step": 212430 }, { - "epoch": 0.95, - "learning_rate": 2.6131115196627956e-06, - "loss": 0.1379, + "epoch": 0.47, + "learning_rate": 2.6359701125254472e-05, + "loss": 0.1342, "step": 212440 }, { - "epoch": 0.95, - "learning_rate": 2.610869467736873e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.6358582582045144e-05, + "loss": 0.1352, "step": 212450 }, { - "epoch": 0.95, - "learning_rate": 2.60862741581095e-06, - "loss": 0.1373, + "epoch": 0.47, + "learning_rate": 2.635746403883582e-05, + "loss": 0.1352, "step": 212460 }, { - "epoch": 0.95, - "learning_rate": 2.6063853638850276e-06, - "loss": 0.1414, + "epoch": 0.47, + "learning_rate": 2.63563454956265e-05, + "loss": 0.139, "step": 212470 }, { - "epoch": 0.95, - "learning_rate": 2.604143311959105e-06, - "loss": 0.1382, + "epoch": 0.47, + "learning_rate": 2.6355226952417174e-05, + "loss": 0.1372, "step": 212480 }, { - "epoch": 0.95, - "learning_rate": 2.6019012600331825e-06, - "loss": 0.1361, + "epoch": 0.47, + "learning_rate": 2.6354108409207852e-05, + "loss": 0.1357, "step": 212490 }, { - "epoch": 0.95, - "learning_rate": 2.59965920810726e-06, - "loss": 0.1383, + "epoch": 0.47, + "learning_rate": 2.6352989865998523e-05, + "loss": 0.1347, "step": 212500 }, { - "epoch": 0.95, - "learning_rate": 2.5974171561813373e-06, - "loss": 0.1357, + "epoch": 0.47, + "learning_rate": 2.63518713227892e-05, + "loss": 0.1375, "step": 212510 }, { - "epoch": 0.95, - "learning_rate": 2.595175104255415e-06, - "loss": 0.1406, + "epoch": 0.47, + "learning_rate": 2.635075277957988e-05, + "loss": 0.1309, "step": 212520 }, { - "epoch": 0.95, - "learning_rate": 2.592933052329492e-06, - "loss": 0.138, + "epoch": 0.47, + "learning_rate": 2.6349634236370553e-05, + "loss": 0.1365, "step": 212530 }, { - "epoch": 0.95, - "learning_rate": 2.5906910004035697e-06, - "loss": 0.1342, + "epoch": 0.47, + "learning_rate": 2.634851569316123e-05, + "loss": 0.1343, "step": 212540 }, { - "epoch": 0.95, - "learning_rate": 2.588448948477647e-06, - "loss": 0.1352, + "epoch": 0.47, + "learning_rate": 2.6347397149951902e-05, + "loss": 0.1463, "step": 212550 }, { - "epoch": 0.95, - "learning_rate": 2.586206896551724e-06, - "loss": 0.1388, + "epoch": 0.47, + "learning_rate": 2.634627860674258e-05, + "loss": 0.137, "step": 212560 }, { - "epoch": 0.95, - "learning_rate": 2.5839648446258016e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.634516006353325e-05, + "loss": 0.1353, "step": 212570 }, { - "epoch": 0.95, - "learning_rate": 2.581722792699879e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.634404152032393e-05, + "loss": 0.1407, "step": 212580 }, { - "epoch": 0.95, - "learning_rate": 2.5794807407739565e-06, - "loss": 0.1339, + "epoch": 0.47, + "learning_rate": 2.6342922977114607e-05, + "loss": 0.1372, "step": 212590 }, { - "epoch": 0.95, - "learning_rate": 2.5772386888480335e-06, - "loss": 0.134, + "epoch": 0.47, + "learning_rate": 2.6341804433905282e-05, + "loss": 0.14, "step": 212600 }, { - "epoch": 0.95, - "learning_rate": 2.5749966369221114e-06, - "loss": 0.1394, + "epoch": 0.47, + "learning_rate": 2.634068589069596e-05, + "loss": 0.1323, "step": 212610 }, { - "epoch": 0.95, - "learning_rate": 2.572754584996189e-06, - "loss": 0.1423, + "epoch": 0.47, + "learning_rate": 2.633956734748663e-05, + "loss": 0.1295, "step": 212620 }, { - "epoch": 0.95, - "learning_rate": 2.570512533070266e-06, - "loss": 0.142, + "epoch": 0.47, + "learning_rate": 2.633844880427731e-05, + "loss": 0.1359, "step": 212630 }, { - "epoch": 0.95, - "learning_rate": 2.5682704811443433e-06, - "loss": 0.1375, + "epoch": 0.47, + "learning_rate": 2.6337330261067987e-05, + "loss": 0.1366, "step": 212640 }, { - "epoch": 0.95, - "learning_rate": 2.5660284292184208e-06, - "loss": 0.1371, + "epoch": 0.47, + "learning_rate": 2.633621171785866e-05, + "loss": 0.1324, "step": 212650 }, { - "epoch": 0.95, - "learning_rate": 2.563786377292498e-06, - "loss": 0.1417, + "epoch": 0.47, + "learning_rate": 2.633509317464934e-05, + "loss": 0.1331, "step": 212660 }, { - "epoch": 0.95, - "learning_rate": 2.5615443253665757e-06, - "loss": 0.1372, + "epoch": 0.47, + "learning_rate": 2.633397463144001e-05, + "loss": 0.1345, "step": 212670 }, { - "epoch": 0.95, - "learning_rate": 2.559302273440653e-06, - "loss": 0.1387, + "epoch": 0.47, + "learning_rate": 2.633285608823069e-05, + "loss": 0.1338, "step": 212680 }, { - "epoch": 0.95, - "learning_rate": 2.5570602215147305e-06, - "loss": 0.1389, + "epoch": 0.47, + "learning_rate": 2.6331737545021366e-05, + "loss": 0.1363, "step": 212690 }, { - "epoch": 0.95, - "learning_rate": 2.5548181695888076e-06, - "loss": 0.1353, + "epoch": 0.47, + "learning_rate": 2.633061900181204e-05, + "loss": 0.1371, "step": 212700 }, { - "epoch": 0.95, - "learning_rate": 2.5525761176628854e-06, - "loss": 0.1374, + "epoch": 0.47, + "learning_rate": 2.632950045860272e-05, + "loss": 0.1385, "step": 212710 }, { - "epoch": 0.95, - "learning_rate": 2.5503340657369625e-06, - "loss": 0.1354, + "epoch": 0.47, + "learning_rate": 2.632838191539339e-05, + "loss": 0.1391, "step": 212720 }, { - "epoch": 0.95, - "learning_rate": 2.54809201381104e-06, - "loss": 0.1338, + "epoch": 0.47, + "learning_rate": 2.6327263372184068e-05, + "loss": 0.1371, "step": 212730 }, { - "epoch": 0.95, - "learning_rate": 2.5458499618851174e-06, - "loss": 0.1359, + "epoch": 0.47, + "learning_rate": 2.6326144828974746e-05, + "loss": 0.1392, "step": 212740 }, { - "epoch": 0.95, - "learning_rate": 2.543607909959195e-06, - "loss": 0.1355, + "epoch": 0.47, + "learning_rate": 2.632502628576542e-05, + "loss": 0.1366, "step": 212750 }, { - "epoch": 0.95, - "learning_rate": 2.5413658580332723e-06, - "loss": 0.1407, + "epoch": 0.47, + "learning_rate": 2.6323907742556098e-05, + "loss": 0.1385, "step": 212760 }, { - "epoch": 0.95, - "learning_rate": 2.5391238061073493e-06, - "loss": 0.1356, + "epoch": 0.47, + "learning_rate": 2.632278919934677e-05, + "loss": 0.1398, "step": 212770 }, { - "epoch": 0.95, - "learning_rate": 2.536881754181427e-06, - "loss": 0.1344, + "epoch": 0.47, + "learning_rate": 2.6321670656137447e-05, + "loss": 0.1332, "step": 212780 }, { - "epoch": 0.95, - "learning_rate": 2.534639702255504e-06, - "loss": 0.1402, + "epoch": 0.47, + "learning_rate": 2.6320552112928125e-05, + "loss": 0.133, "step": 212790 }, { - "epoch": 0.95, - "learning_rate": 2.5323976503295816e-06, - "loss": 0.1395, + "epoch": 0.47, + "learning_rate": 2.63194335697188e-05, + "loss": 0.1345, "step": 212800 }, { - "epoch": 0.95, - "learning_rate": 2.5301555984036595e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.6318315026509478e-05, + "loss": 0.1379, "step": 212810 }, { - "epoch": 0.95, - "learning_rate": 2.5279135464777365e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.631719648330015e-05, + "loss": 0.1319, "step": 212820 }, { - "epoch": 0.95, - "learning_rate": 2.525671494551814e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.6316077940090827e-05, + "loss": 0.1409, "step": 212830 }, { - "epoch": 0.95, - "learning_rate": 2.5234294426258914e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.63149593968815e-05, + "loss": 0.1351, "step": 212840 }, { - "epoch": 0.95, - "learning_rate": 2.521187390699969e-06, - "loss": 0.1402, + "epoch": 0.48, + "learning_rate": 2.631384085367218e-05, + "loss": 0.1396, "step": 212850 }, { - "epoch": 0.95, - "learning_rate": 2.518945338774046e-06, - "loss": 0.134, + "epoch": 0.48, + "learning_rate": 2.6312722310462857e-05, + "loss": 0.1384, "step": 212860 }, { - "epoch": 0.95, - "learning_rate": 2.5167032868481233e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.631160376725353e-05, + "loss": 0.1331, "step": 212870 }, { - "epoch": 0.95, - "learning_rate": 2.514461234922201e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.6310485224044206e-05, + "loss": 0.1361, "step": 212880 }, { - "epoch": 0.95, - "learning_rate": 2.5122191829962782e-06, - "loss": 0.1368, + "epoch": 0.48, + "learning_rate": 2.630936668083488e-05, + "loss": 0.1382, "step": 212890 }, { - "epoch": 0.95, - "learning_rate": 2.5099771310703557e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.630824813762556e-05, + "loss": 0.1397, "step": 212900 }, { - "epoch": 0.95, - "learning_rate": 2.507735079144433e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.6307129594416237e-05, + "loss": 0.1407, "step": 212910 }, { - "epoch": 0.95, - "learning_rate": 2.5054930272185106e-06, - "loss": 0.1411, + "epoch": 0.48, + "learning_rate": 2.6306011051206908e-05, + "loss": 0.1395, "step": 212920 }, { - "epoch": 0.95, - "learning_rate": 2.503250975292588e-06, - "loss": 0.1387, + "epoch": 0.48, + "learning_rate": 2.6304892507997586e-05, + "loss": 0.1338, "step": 212930 }, { - "epoch": 0.95, - "learning_rate": 2.501008923366665e-06, - "loss": 0.1378, + "epoch": 0.48, + "learning_rate": 2.6303773964788257e-05, + "loss": 0.1382, "step": 212940 }, { - "epoch": 0.95, - "learning_rate": 2.498766871440743e-06, - "loss": 0.141, + "epoch": 0.48, + "learning_rate": 2.6302655421578938e-05, + "loss": 0.1308, "step": 212950 }, { - "epoch": 0.95, - "learning_rate": 2.49652481951482e-06, - "loss": 0.1367, + "epoch": 0.48, + "learning_rate": 2.6301536878369616e-05, + "loss": 0.1372, "step": 212960 }, { - "epoch": 0.95, - "learning_rate": 2.4942827675888974e-06, - "loss": 0.133, + "epoch": 0.48, + "learning_rate": 2.6300418335160287e-05, + "loss": 0.1402, "step": 212970 }, { - "epoch": 0.95, - "learning_rate": 2.492040715662975e-06, - "loss": 0.142, + "epoch": 0.48, + "learning_rate": 2.6299299791950965e-05, + "loss": 0.1373, "step": 212980 }, { - "epoch": 0.95, - "learning_rate": 2.4897986637370523e-06, - "loss": 0.1411, + "epoch": 0.48, + "learning_rate": 2.6298181248741636e-05, + "loss": 0.1338, "step": 212990 }, { - "epoch": 0.95, - "learning_rate": 2.4875566118111297e-06, - "loss": 0.133, + "epoch": 0.48, + "learning_rate": 2.6297062705532314e-05, + "loss": 0.1403, "step": 213000 }, { - "epoch": 0.95, - "learning_rate": 2.485314559885207e-06, - "loss": 0.1427, + "epoch": 0.48, + "learning_rate": 2.6295944162322996e-05, + "loss": 0.1381, "step": 213010 }, { - "epoch": 0.95, - "learning_rate": 2.4830725079592846e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.6294825619113667e-05, + "loss": 0.1319, "step": 213020 }, { - "epoch": 0.95, - "learning_rate": 2.4808304560333616e-06, - "loss": 0.1411, + "epoch": 0.48, + "learning_rate": 2.6293707075904345e-05, + "loss": 0.1339, "step": 213030 }, { - "epoch": 0.95, - "learning_rate": 2.478588404107439e-06, - "loss": 0.1319, + "epoch": 0.48, + "learning_rate": 2.6292588532695016e-05, + "loss": 0.1392, "step": 213040 }, { - "epoch": 0.95, - "learning_rate": 2.476346352181517e-06, - "loss": 0.1404, + "epoch": 0.48, + "learning_rate": 2.6291469989485694e-05, + "loss": 0.1397, "step": 213050 }, { - "epoch": 0.95, - "learning_rate": 2.474104300255594e-06, - "loss": 0.1437, + "epoch": 0.48, + "learning_rate": 2.6290351446276372e-05, + "loss": 0.1388, "step": 213060 }, { - "epoch": 0.95, - "learning_rate": 2.4718622483296714e-06, - "loss": 0.1357, + "epoch": 0.48, + "learning_rate": 2.6289232903067046e-05, + "loss": 0.1405, "step": 213070 }, { - "epoch": 0.95, - "learning_rate": 2.469620196403749e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.6288114359857724e-05, + "loss": 0.1344, "step": 213080 }, { - "epoch": 0.95, - "learning_rate": 2.4673781444778263e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.6286995816648395e-05, + "loss": 0.1369, "step": 213090 }, { - "epoch": 0.95, - "learning_rate": 2.4651360925519033e-06, - "loss": 0.1326, + "epoch": 0.48, + "learning_rate": 2.6285877273439073e-05, + "loss": 0.1312, "step": 213100 }, { - "epoch": 0.95, - "learning_rate": 2.4628940406259812e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.628475873022975e-05, + "loss": 0.1336, "step": 213110 }, { - "epoch": 0.95, - "learning_rate": 2.4606519887000587e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.6283640187020426e-05, + "loss": 0.139, "step": 213120 }, { - "epoch": 0.95, - "learning_rate": 2.4584099367741357e-06, - "loss": 0.1392, + "epoch": 0.48, + "learning_rate": 2.6282521643811104e-05, + "loss": 0.1409, "step": 213130 }, { - "epoch": 0.95, - "learning_rate": 2.456167884848213e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6281403100601775e-05, + "loss": 0.1368, "step": 213140 }, { - "epoch": 0.95, - "learning_rate": 2.4539258329222906e-06, - "loss": 0.1336, + "epoch": 0.48, + "learning_rate": 2.6280284557392453e-05, + "loss": 0.1379, "step": 213150 }, { - "epoch": 0.95, - "learning_rate": 2.451683780996368e-06, - "loss": 0.1343, - "step": 213160 + "epoch": 0.48, + "learning_rate": 2.6279166014183127e-05, + "loss": 0.1325, + "step": 213160 }, { - "epoch": 0.95, - "learning_rate": 2.449441729070445e-06, - "loss": 0.1385, + "epoch": 0.48, + "learning_rate": 2.6278047470973805e-05, + "loss": 0.1341, "step": 213170 }, { - "epoch": 0.95, - "learning_rate": 2.447199677144523e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.6276928927764483e-05, + "loss": 0.1307, "step": 213180 }, { - "epoch": 0.95, - "learning_rate": 2.4449576252186004e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.6275810384555154e-05, + "loss": 0.1326, "step": 213190 }, { - "epoch": 0.95, - "learning_rate": 2.4427155732926774e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.6274691841345832e-05, + "loss": 0.1391, "step": 213200 }, { - "epoch": 0.95, - "learning_rate": 2.440473521366755e-06, - "loss": 0.1399, + "epoch": 0.48, + "learning_rate": 2.6273573298136507e-05, + "loss": 0.1407, "step": 213210 }, { - "epoch": 0.95, - "learning_rate": 2.4382314694408323e-06, - "loss": 0.1351, + "epoch": 0.48, + "learning_rate": 2.6272454754927185e-05, + "loss": 0.1342, "step": 213220 }, { - "epoch": 0.95, - "learning_rate": 2.4359894175149097e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.6271336211717863e-05, + "loss": 0.1356, "step": 213230 }, { - "epoch": 0.95, - "learning_rate": 2.433747365588987e-06, - "loss": 0.1346, + "epoch": 0.48, + "learning_rate": 2.6270217668508534e-05, + "loss": 0.1377, "step": 213240 }, { - "epoch": 0.95, - "learning_rate": 2.4315053136630646e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6269099125299212e-05, + "loss": 0.1372, "step": 213250 }, { - "epoch": 0.95, - "learning_rate": 2.429263261737142e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.6267980582089886e-05, + "loss": 0.1377, "step": 213260 }, { - "epoch": 0.95, - "learning_rate": 2.427021209811219e-06, - "loss": 0.1357, + "epoch": 0.48, + "learning_rate": 2.6266862038880564e-05, + "loss": 0.1349, "step": 213270 }, { - "epoch": 0.95, - "learning_rate": 2.424779157885297e-06, - "loss": 0.1422, + "epoch": 0.48, + "learning_rate": 2.6265743495671242e-05, + "loss": 0.133, "step": 213280 }, { - "epoch": 0.95, - "learning_rate": 2.422537105959374e-06, - "loss": 0.135, + "epoch": 0.48, + "learning_rate": 2.6264624952461913e-05, + "loss": 0.1337, "step": 213290 }, { - "epoch": 0.95, - "learning_rate": 2.4202950540334514e-06, - "loss": 0.141, + "epoch": 0.48, + "learning_rate": 2.626350640925259e-05, + "loss": 0.135, "step": 213300 }, { - "epoch": 0.95, - "learning_rate": 2.418053002107529e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.6262387866043266e-05, + "loss": 0.1379, "step": 213310 }, { - "epoch": 0.95, - "learning_rate": 2.4158109501816063e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.6261269322833944e-05, + "loss": 0.1341, "step": 213320 }, { - "epoch": 0.95, - "learning_rate": 2.4135688982556838e-06, - "loss": 0.1296, + "epoch": 0.48, + "learning_rate": 2.626015077962462e-05, + "loss": 0.1373, "step": 213330 }, { - "epoch": 0.95, - "learning_rate": 2.411326846329761e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6259032236415293e-05, + "loss": 0.1388, "step": 213340 }, { - "epoch": 0.95, - "learning_rate": 2.4090847944038387e-06, - "loss": 0.1322, + "epoch": 0.48, + "learning_rate": 2.625791369320597e-05, + "loss": 0.1379, "step": 213350 }, { - "epoch": 0.95, - "learning_rate": 2.4068427424779157e-06, - "loss": 0.135, + "epoch": 0.48, + "learning_rate": 2.6256795149996645e-05, + "loss": 0.1378, "step": 213360 }, { - "epoch": 0.95, - "learning_rate": 2.404600690551993e-06, - "loss": 0.133, + "epoch": 0.48, + "learning_rate": 2.6255676606787323e-05, + "loss": 0.1417, "step": 213370 }, { - "epoch": 0.95, - "learning_rate": 2.402358638626071e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6254558063578e-05, + "loss": 0.1388, "step": 213380 }, { - "epoch": 0.95, - "learning_rate": 2.400116586700148e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.6253439520368672e-05, + "loss": 0.13, "step": 213390 }, { - "epoch": 0.95, - "learning_rate": 2.3978745347742255e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.625232097715935e-05, + "loss": 0.1362, "step": 213400 }, { - "epoch": 0.95, - "learning_rate": 2.395632482848303e-06, - "loss": 0.1349, + "epoch": 0.48, + "learning_rate": 2.625120243395002e-05, + "loss": 0.1394, "step": 213410 }, { - "epoch": 0.95, - "learning_rate": 2.3933904309223804e-06, - "loss": 0.1386, + "epoch": 0.48, + "learning_rate": 2.6250083890740703e-05, + "loss": 0.1371, "step": 213420 }, { - "epoch": 0.95, - "learning_rate": 2.391148378996458e-06, - "loss": 0.1338, + "epoch": 0.48, + "learning_rate": 2.624896534753138e-05, + "loss": 0.1386, "step": 213430 }, { - "epoch": 0.95, - "learning_rate": 2.388906327070535e-06, - "loss": 0.1354, + "epoch": 0.48, + "learning_rate": 2.6247846804322052e-05, + "loss": 0.138, "step": 213440 }, { - "epoch": 0.95, - "learning_rate": 2.3866642751446127e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.624672826111273e-05, + "loss": 0.1393, "step": 213450 }, { - "epoch": 0.95, - "learning_rate": 2.3844222232186897e-06, - "loss": 0.135, + "epoch": 0.48, + "learning_rate": 2.62456097179034e-05, + "loss": 0.1313, "step": 213460 }, { - "epoch": 0.95, - "learning_rate": 2.382180171292767e-06, - "loss": 0.1402, + "epoch": 0.48, + "learning_rate": 2.624449117469408e-05, + "loss": 0.1413, "step": 213470 }, { - "epoch": 0.95, - "learning_rate": 2.3799381193668446e-06, - "loss": 0.1401, + "epoch": 0.48, + "learning_rate": 2.6243372631484753e-05, + "loss": 0.1372, "step": 213480 }, { - "epoch": 0.95, - "learning_rate": 2.377696067440922e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.624225408827543e-05, + "loss": 0.1371, "step": 213490 }, { - "epoch": 0.95, - "learning_rate": 2.3754540155149995e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.624113554506611e-05, + "loss": 0.1389, "step": 213500 }, { - "epoch": 0.95, - "learning_rate": 2.3732119635890766e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.624001700185678e-05, + "loss": 0.1346, "step": 213510 }, { - "epoch": 0.95, - "learning_rate": 2.3709699116631544e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.6238898458647458e-05, + "loss": 0.1388, "step": 213520 }, { - "epoch": 0.95, - "learning_rate": 2.3687278597372315e-06, - "loss": 0.1368, + "epoch": 0.48, + "learning_rate": 2.6237779915438133e-05, + "loss": 0.1388, "step": 213530 }, { - "epoch": 0.95, - "learning_rate": 2.366485807811309e-06, - "loss": 0.1324, + "epoch": 0.48, + "learning_rate": 2.623666137222881e-05, + "loss": 0.1365, "step": 213540 }, { - "epoch": 0.95, - "learning_rate": 2.3642437558853868e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.623554282901949e-05, + "loss": 0.136, "step": 213550 }, { - "epoch": 0.95, - "learning_rate": 2.362001703959464e-06, - "loss": 0.1374, + "epoch": 0.48, + "learning_rate": 2.623442428581016e-05, + "loss": 0.1348, "step": 213560 }, { - "epoch": 0.95, - "learning_rate": 2.3597596520335412e-06, - "loss": 0.1378, + "epoch": 0.48, + "learning_rate": 2.6233305742600838e-05, + "loss": 0.1375, "step": 213570 }, { - "epoch": 0.95, - "learning_rate": 2.357741805300211e-06, - "loss": 0.1394, + "epoch": 0.48, + "learning_rate": 2.6232187199391512e-05, + "loss": 0.135, "step": 213580 }, { - "epoch": 0.95, - "learning_rate": 2.355499753374288e-06, - "loss": 0.1429, + "epoch": 0.48, + "learning_rate": 2.623106865618219e-05, + "loss": 0.1321, "step": 213590 }, { - "epoch": 0.95, - "learning_rate": 2.3532577014483656e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.6229950112972868e-05, + "loss": 0.1353, "step": 213600 }, { - "epoch": 0.95, - "learning_rate": 2.351015649522443e-06, - "loss": 0.1416, + "epoch": 0.48, + "learning_rate": 2.622883156976354e-05, + "loss": 0.1361, "step": 213610 }, { - "epoch": 0.95, - "learning_rate": 2.3487735975965205e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.6227713026554217e-05, + "loss": 0.1385, "step": 213620 }, { - "epoch": 0.95, - "learning_rate": 2.3465315456705975e-06, - "loss": 0.136, + "epoch": 0.48, + "learning_rate": 2.622659448334489e-05, + "loss": 0.1391, "step": 213630 }, { - "epoch": 0.95, - "learning_rate": 2.3442894937446754e-06, - "loss": 0.142, + "epoch": 0.48, + "learning_rate": 2.622547594013557e-05, + "loss": 0.136, "step": 213640 }, { - "epoch": 0.95, - "learning_rate": 2.342047441818753e-06, - "loss": 0.1345, + "epoch": 0.48, + "learning_rate": 2.6224357396926248e-05, + "loss": 0.1357, "step": 213650 }, { - "epoch": 0.95, - "learning_rate": 2.33980538989283e-06, - "loss": 0.1387, + "epoch": 0.48, + "learning_rate": 2.622323885371692e-05, + "loss": 0.1341, "step": 213660 }, { - "epoch": 0.95, - "learning_rate": 2.3375633379669073e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6222120310507597e-05, + "loss": 0.1358, "step": 213670 }, { - "epoch": 0.95, - "learning_rate": 2.3353212860409848e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.622100176729827e-05, + "loss": 0.1351, "step": 213680 }, { - "epoch": 0.95, - "learning_rate": 2.3330792341150622e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.621988322408895e-05, + "loss": 0.1421, "step": 213690 }, { - "epoch": 0.95, - "learning_rate": 2.3308371821891397e-06, - "loss": 0.1393, + "epoch": 0.48, + "learning_rate": 2.6218764680879627e-05, + "loss": 0.1337, "step": 213700 }, { - "epoch": 0.95, - "learning_rate": 2.328595130263217e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.6217646137670298e-05, + "loss": 0.1368, "step": 213710 }, { - "epoch": 0.95, - "learning_rate": 2.3263530783372946e-06, - "loss": 0.1399, + "epoch": 0.48, + "learning_rate": 2.6216527594460976e-05, + "loss": 0.1373, "step": 213720 }, { - "epoch": 0.95, - "learning_rate": 2.3241110264113716e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.621540905125165e-05, + "loss": 0.139, "step": 213730 }, { - "epoch": 0.95, - "learning_rate": 2.321868974485449e-06, - "loss": 0.1356, + "epoch": 0.48, + "learning_rate": 2.621429050804233e-05, + "loss": 0.1339, "step": 213740 }, { - "epoch": 0.95, - "learning_rate": 2.3196269225595265e-06, - "loss": 0.1348, + "epoch": 0.48, + "learning_rate": 2.6213171964833006e-05, + "loss": 0.132, "step": 213750 }, { - "epoch": 0.95, - "learning_rate": 2.317384870633604e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.6212053421623678e-05, + "loss": 0.1344, "step": 213760 }, { - "epoch": 0.95, - "learning_rate": 2.3151428187076814e-06, - "loss": 0.1377, + "epoch": 0.48, + "learning_rate": 2.6210934878414356e-05, + "loss": 0.1324, "step": 213770 }, { - "epoch": 0.95, - "learning_rate": 2.312900766781759e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.620981633520503e-05, + "loss": 0.1366, "step": 213780 }, { - "epoch": 0.95, - "learning_rate": 2.3106587148558363e-06, - "loss": 0.136, + "epoch": 0.48, + "learning_rate": 2.6208697791995708e-05, + "loss": 0.1374, "step": 213790 }, { - "epoch": 0.95, - "learning_rate": 2.3084166629299133e-06, - "loss": 0.136, + "epoch": 0.48, + "learning_rate": 2.620757924878638e-05, + "loss": 0.1343, "step": 213800 }, { - "epoch": 0.95, - "learning_rate": 2.306174611003991e-06, - "loss": 0.1441, + "epoch": 0.48, + "learning_rate": 2.6206460705577057e-05, + "loss": 0.1318, "step": 213810 }, { - "epoch": 0.95, - "learning_rate": 2.3039325590780686e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.6205342162367735e-05, + "loss": 0.1349, "step": 213820 }, { - "epoch": 0.95, - "learning_rate": 2.3016905071521456e-06, - "loss": 0.1335, + "epoch": 0.48, + "learning_rate": 2.6204223619158406e-05, + "loss": 0.1363, "step": 213830 }, { - "epoch": 0.95, - "learning_rate": 2.299448455226223e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6203105075949087e-05, + "loss": 0.1379, "step": 213840 }, { - "epoch": 0.95, - "learning_rate": 2.2972064033003005e-06, - "loss": 0.1343, + "epoch": 0.48, + "learning_rate": 2.620198653273976e-05, + "loss": 0.1337, "step": 213850 }, { - "epoch": 0.95, - "learning_rate": 2.294964351374378e-06, - "loss": 0.1343, + "epoch": 0.48, + "learning_rate": 2.6200867989530437e-05, + "loss": 0.1374, "step": 213860 }, { - "epoch": 0.95, - "learning_rate": 2.292722299448455e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.6199749446321114e-05, + "loss": 0.1396, "step": 213870 }, { - "epoch": 0.95, - "learning_rate": 2.290480247522533e-06, - "loss": 0.1413, + "epoch": 0.48, + "learning_rate": 2.6198630903111786e-05, + "loss": 0.1321, "step": 213880 }, { - "epoch": 0.95, - "learning_rate": 2.2882381955966103e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.6197512359902464e-05, + "loss": 0.1401, "step": 213890 }, { - "epoch": 0.95, - "learning_rate": 2.2859961436706874e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.6196393816693138e-05, + "loss": 0.1344, "step": 213900 }, { - "epoch": 0.95, - "learning_rate": 2.2837540917447652e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.6195275273483816e-05, + "loss": 0.1354, "step": 213910 }, { - "epoch": 0.95, - "learning_rate": 2.2815120398188422e-06, - "loss": 0.1408, + "epoch": 0.48, + "learning_rate": 2.6194156730274494e-05, + "loss": 0.1373, "step": 213920 }, { - "epoch": 0.96, - "learning_rate": 2.2792699878929197e-06, - "loss": 0.1415, + "epoch": 0.48, + "learning_rate": 2.6193038187065165e-05, + "loss": 0.1353, "step": 213930 }, { - "epoch": 0.96, - "learning_rate": 2.277027935966997e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6191919643855843e-05, + "loss": 0.1351, "step": 213940 }, { - "epoch": 0.96, - "learning_rate": 2.2747858840410746e-06, - "loss": 0.1377, + "epoch": 0.48, + "learning_rate": 2.6190801100646518e-05, + "loss": 0.134, "step": 213950 }, { - "epoch": 0.96, - "learning_rate": 2.272543832115152e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.6189682557437196e-05, + "loss": 0.1388, "step": 213960 }, { - "epoch": 0.96, - "learning_rate": 2.270301780189229e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.6188564014227873e-05, + "loss": 0.1373, "step": 213970 }, { - "epoch": 0.96, - "learning_rate": 2.268059728263307e-06, - "loss": 0.1348, + "epoch": 0.48, + "learning_rate": 2.6187445471018545e-05, + "loss": 0.1386, "step": 213980 }, { - "epoch": 0.96, - "learning_rate": 2.265817676337384e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.6186326927809223e-05, + "loss": 0.1313, "step": 213990 }, { - "epoch": 0.96, - "learning_rate": 2.2635756244114614e-06, - "loss": 0.1325, + "epoch": 0.48, + "learning_rate": 2.6185208384599897e-05, + "loss": 0.1349, "step": 214000 }, { - "epoch": 0.96, - "learning_rate": 2.261333572485539e-06, - "loss": 0.1433, + "epoch": 0.48, + "learning_rate": 2.6184089841390575e-05, + "loss": 0.1358, "step": 214010 }, { - "epoch": 0.96, - "learning_rate": 2.2590915205596163e-06, - "loss": 0.1313, + "epoch": 0.48, + "learning_rate": 2.6182971298181253e-05, + "loss": 0.1329, "step": 214020 }, { - "epoch": 0.96, - "learning_rate": 2.2568494686336937e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.6181852754971924e-05, + "loss": 0.1371, "step": 214030 }, { - "epoch": 0.96, - "learning_rate": 2.2546074167077708e-06, - "loss": 0.1338, + "epoch": 0.48, + "learning_rate": 2.6180734211762602e-05, + "loss": 0.1343, "step": 214040 }, { - "epoch": 0.96, - "learning_rate": 2.2523653647818486e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.6179615668553277e-05, + "loss": 0.1389, "step": 214050 }, { - "epoch": 0.96, - "learning_rate": 2.2501233128559257e-06, - "loss": 0.1329, + "epoch": 0.48, + "learning_rate": 2.6178497125343954e-05, + "loss": 0.1337, "step": 214060 }, { - "epoch": 0.96, - "learning_rate": 2.247881260930003e-06, - "loss": 0.1427, + "epoch": 0.48, + "learning_rate": 2.6177378582134632e-05, + "loss": 0.1327, "step": 214070 }, { - "epoch": 0.96, - "learning_rate": 2.245639209004081e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.6176260038925304e-05, + "loss": 0.1354, "step": 214080 }, { - "epoch": 0.96, - "learning_rate": 2.243397157078158e-06, - "loss": 0.1323, + "epoch": 0.48, + "learning_rate": 2.617514149571598e-05, + "loss": 0.1378, "step": 214090 }, { - "epoch": 0.96, - "learning_rate": 2.2411551051522354e-06, - "loss": 0.1372, + "epoch": 0.48, + "learning_rate": 2.6174022952506656e-05, + "loss": 0.1345, "step": 214100 }, { - "epoch": 0.96, - "learning_rate": 2.238913053226313e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.6172904409297334e-05, + "loss": 0.1318, "step": 214110 }, { - "epoch": 0.96, - "learning_rate": 2.2366710013003903e-06, - "loss": 0.1332, + "epoch": 0.48, + "learning_rate": 2.6171785866088005e-05, + "loss": 0.1414, "step": 214120 }, { - "epoch": 0.96, - "learning_rate": 2.2344289493744674e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.6170667322878683e-05, + "loss": 0.1393, "step": 214130 }, { - "epoch": 0.96, - "learning_rate": 2.232186897448545e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.616954877966936e-05, + "loss": 0.1327, "step": 214140 }, { - "epoch": 0.96, - "learning_rate": 2.2299448455226227e-06, - "loss": 0.1407, + "epoch": 0.48, + "learning_rate": 2.6168430236460035e-05, + "loss": 0.1367, "step": 214150 }, { - "epoch": 0.96, - "learning_rate": 2.2277027935966997e-06, - "loss": 0.1374, + "epoch": 0.48, + "learning_rate": 2.6167311693250713e-05, + "loss": 0.1309, "step": 214160 }, { - "epoch": 0.96, - "learning_rate": 2.225460741670777e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6166193150041385e-05, + "loss": 0.1366, "step": 214170 }, { - "epoch": 0.96, - "learning_rate": 2.2232186897448546e-06, - "loss": 0.1418, + "epoch": 0.48, + "learning_rate": 2.6165074606832062e-05, + "loss": 0.1315, "step": 214180 }, { - "epoch": 0.96, - "learning_rate": 2.220976637818932e-06, - "loss": 0.1411, + "epoch": 0.48, + "learning_rate": 2.616395606362274e-05, + "loss": 0.1405, "step": 214190 }, { - "epoch": 0.96, - "learning_rate": 2.2187345858930095e-06, - "loss": 0.1429, + "epoch": 0.48, + "learning_rate": 2.6162837520413415e-05, + "loss": 0.135, "step": 214200 }, { - "epoch": 0.96, - "learning_rate": 2.216492533967087e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.6161718977204093e-05, + "loss": 0.1331, "step": 214210 }, { - "epoch": 0.96, - "learning_rate": 2.2142504820411644e-06, - "loss": 0.134, + "epoch": 0.48, + "learning_rate": 2.6160600433994764e-05, + "loss": 0.1349, "step": 214220 }, { - "epoch": 0.96, - "learning_rate": 2.2120084301152414e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.6159481890785442e-05, + "loss": 0.1387, "step": 214230 }, { - "epoch": 0.96, - "learning_rate": 2.209766378189319e-06, - "loss": 0.1347, + "epoch": 0.48, + "learning_rate": 2.615836334757612e-05, + "loss": 0.1345, "step": 214240 }, { - "epoch": 0.96, - "learning_rate": 2.2075243262633963e-06, - "loss": 0.1383, + "epoch": 0.48, + "learning_rate": 2.6157244804366794e-05, + "loss": 0.1413, "step": 214250 }, { - "epoch": 0.96, - "learning_rate": 2.2052822743374738e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.6156126261157472e-05, + "loss": 0.1401, "step": 214260 }, { - "epoch": 0.96, - "learning_rate": 2.203040222411551e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6155007717948144e-05, + "loss": 0.1357, "step": 214270 }, { - "epoch": 0.96, - "learning_rate": 2.2007981704856287e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.615388917473882e-05, + "loss": 0.1402, "step": 214280 }, { - "epoch": 0.96, - "learning_rate": 2.198556118559706e-06, - "loss": 0.1336, + "epoch": 0.48, + "learning_rate": 2.61527706315295e-05, + "loss": 0.1323, "step": 214290 }, { - "epoch": 0.96, - "learning_rate": 2.196314066633783e-06, - "loss": 0.1321, + "epoch": 0.48, + "learning_rate": 2.615165208832017e-05, + "loss": 0.1365, "step": 214300 }, { - "epoch": 0.96, - "learning_rate": 2.1940720147078606e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.6150533545110852e-05, + "loss": 0.1321, "step": 214310 }, { - "epoch": 0.96, - "learning_rate": 2.1918299627819384e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.6149415001901523e-05, + "loss": 0.1389, "step": 214320 }, { - "epoch": 0.96, - "learning_rate": 2.1895879108560155e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.61482964586922e-05, + "loss": 0.1342, "step": 214330 }, { - "epoch": 0.96, - "learning_rate": 2.187345858930093e-06, - "loss": 0.1337, + "epoch": 0.48, + "learning_rate": 2.614717791548288e-05, + "loss": 0.1313, "step": 214340 }, { - "epoch": 0.96, - "learning_rate": 2.1851038070041704e-06, - "loss": 0.1301, + "epoch": 0.48, + "learning_rate": 2.614605937227355e-05, + "loss": 0.1366, "step": 214350 }, { - "epoch": 0.96, - "learning_rate": 2.182861755078248e-06, - "loss": 0.1407, + "epoch": 0.48, + "learning_rate": 2.6144940829064228e-05, + "loss": 0.1388, "step": 214360 }, { - "epoch": 0.96, - "learning_rate": 2.180619703152325e-06, - "loss": 0.1333, + "epoch": 0.48, + "learning_rate": 2.6143822285854902e-05, + "loss": 0.1359, "step": 214370 }, { - "epoch": 0.96, - "learning_rate": 2.1783776512264027e-06, - "loss": 0.1422, + "epoch": 0.48, + "learning_rate": 2.614270374264558e-05, + "loss": 0.1371, "step": 214380 }, { - "epoch": 0.96, - "learning_rate": 2.17613559930048e-06, - "loss": 0.1371, + "epoch": 0.48, + "learning_rate": 2.614158519943626e-05, + "loss": 0.1356, "step": 214390 }, { - "epoch": 0.96, - "learning_rate": 2.173893547374557e-06, - "loss": 0.1374, + "epoch": 0.48, + "learning_rate": 2.614046665622693e-05, + "loss": 0.1319, "step": 214400 }, { - "epoch": 0.96, - "learning_rate": 2.1716514954486346e-06, - "loss": 0.1425, + "epoch": 0.48, + "learning_rate": 2.6139348113017607e-05, + "loss": 0.1358, "step": 214410 }, { - "epoch": 0.96, - "learning_rate": 2.169409443522712e-06, - "loss": 0.134, + "epoch": 0.48, + "learning_rate": 2.6138229569808282e-05, + "loss": 0.1335, "step": 214420 }, { - "epoch": 0.96, - "learning_rate": 2.1671673915967895e-06, - "loss": 0.1344, + "epoch": 0.48, + "learning_rate": 2.613711102659896e-05, + "loss": 0.1373, "step": 214430 }, { - "epoch": 0.96, - "learning_rate": 2.1649253396708665e-06, - "loss": 0.1322, + "epoch": 0.48, + "learning_rate": 2.613599248338963e-05, + "loss": 0.1392, "step": 214440 }, { - "epoch": 0.96, - "learning_rate": 2.1626832877449444e-06, - "loss": 0.133, + "epoch": 0.48, + "learning_rate": 2.613487394018031e-05, + "loss": 0.1436, "step": 214450 }, { - "epoch": 0.96, - "learning_rate": 2.160441235819022e-06, - "loss": 0.1366, + "epoch": 0.48, + "learning_rate": 2.6133755396970987e-05, + "loss": 0.139, "step": 214460 }, { - "epoch": 0.96, - "learning_rate": 2.158199183893099e-06, - "loss": 0.1386, + "epoch": 0.48, + "learning_rate": 2.613263685376166e-05, + "loss": 0.1352, "step": 214470 }, { - "epoch": 0.96, - "learning_rate": 2.1559571319671767e-06, - "loss": 0.1322, + "epoch": 0.48, + "learning_rate": 2.613151831055234e-05, + "loss": 0.1344, "step": 214480 }, { - "epoch": 0.96, - "learning_rate": 2.1537150800412538e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.613039976734301e-05, + "loss": 0.137, "step": 214490 }, { - "epoch": 0.96, - "learning_rate": 2.1514730281153312e-06, - "loss": 0.1317, + "epoch": 0.48, + "learning_rate": 2.612928122413369e-05, + "loss": 0.1325, "step": 214500 }, { - "epoch": 0.96, - "learning_rate": 2.1492309761894087e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6128162680924366e-05, + "loss": 0.1363, "step": 214510 }, { - "epoch": 0.96, - "learning_rate": 2.146988924263486e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.612704413771504e-05, + "loss": 0.1358, "step": 214520 }, { - "epoch": 0.96, - "learning_rate": 2.1447468723375636e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.612592559450572e-05, + "loss": 0.1318, "step": 214530 }, { - "epoch": 0.96, - "learning_rate": 2.1425048204116406e-06, - "loss": 0.1367, + "epoch": 0.48, + "learning_rate": 2.612480705129639e-05, + "loss": 0.1347, "step": 214540 }, { - "epoch": 0.96, - "learning_rate": 2.1402627684857185e-06, - "loss": 0.1383, + "epoch": 0.48, + "learning_rate": 2.6123688508087068e-05, + "loss": 0.1367, "step": 214550 }, { - "epoch": 0.96, - "learning_rate": 2.1380207165597955e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6122569964877746e-05, + "loss": 0.1347, "step": 214560 }, { - "epoch": 0.96, - "learning_rate": 2.135778664633873e-06, - "loss": 0.1401, + "epoch": 0.48, + "learning_rate": 2.612145142166842e-05, + "loss": 0.1391, "step": 214570 }, { - "epoch": 0.96, - "learning_rate": 2.1335366127079504e-06, - "loss": 0.1346, + "epoch": 0.48, + "learning_rate": 2.6120332878459098e-05, + "loss": 0.1357, "step": 214580 }, { - "epoch": 0.96, - "learning_rate": 2.131294560782028e-06, - "loss": 0.1352, + "epoch": 0.48, + "learning_rate": 2.611921433524977e-05, + "loss": 0.1386, "step": 214590 }, { - "epoch": 0.96, - "learning_rate": 2.1290525088561053e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.6118095792040447e-05, + "loss": 0.1339, "step": 214600 }, { - "epoch": 0.96, - "learning_rate": 2.1268104569301823e-06, - "loss": 0.132, + "epoch": 0.48, + "learning_rate": 2.6116977248831125e-05, + "loss": 0.1338, "step": 214610 }, { - "epoch": 0.96, - "learning_rate": 2.12456840500426e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.61158587056218e-05, + "loss": 0.1319, "step": 214620 }, { - "epoch": 0.96, - "learning_rate": 2.122326353078337e-06, - "loss": 0.1377, + "epoch": 0.48, + "learning_rate": 2.6114740162412478e-05, + "loss": 0.1363, "step": 214630 }, { - "epoch": 0.96, - "learning_rate": 2.1200843011524146e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.611362161920315e-05, + "loss": 0.13, "step": 214640 }, { - "epoch": 0.96, - "learning_rate": 2.1178422492264925e-06, - "loss": 0.132, + "epoch": 0.48, + "learning_rate": 2.6112503075993827e-05, + "loss": 0.1361, "step": 214650 }, { - "epoch": 0.96, - "learning_rate": 2.1156001973005695e-06, - "loss": 0.1372, + "epoch": 0.48, + "learning_rate": 2.6111384532784505e-05, + "loss": 0.1366, "step": 214660 }, { - "epoch": 0.96, - "learning_rate": 2.113358145374647e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.611026598957518e-05, + "loss": 0.1332, "step": 214670 }, { - "epoch": 0.96, - "learning_rate": 2.1111160934487244e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6109147446365857e-05, + "loss": 0.1295, "step": 214680 }, { - "epoch": 0.96, - "learning_rate": 2.108874041522802e-06, - "loss": 0.1377, + "epoch": 0.48, + "learning_rate": 2.610802890315653e-05, + "loss": 0.1369, "step": 214690 }, { - "epoch": 0.96, - "learning_rate": 2.1066319895968793e-06, - "loss": 0.1324, + "epoch": 0.48, + "learning_rate": 2.6106910359947206e-05, + "loss": 0.1363, "step": 214700 }, { - "epoch": 0.96, - "learning_rate": 2.1043899376709563e-06, - "loss": 0.1368, + "epoch": 0.48, + "learning_rate": 2.6105791816737884e-05, + "loss": 0.1379, "step": 214710 }, { - "epoch": 0.96, - "learning_rate": 2.102147885745034e-06, - "loss": 0.1304, + "epoch": 0.48, + "learning_rate": 2.6104673273528555e-05, + "loss": 0.1385, "step": 214720 }, { - "epoch": 0.96, - "learning_rate": 2.0999058338191112e-06, - "loss": 0.1372, + "epoch": 0.48, + "learning_rate": 2.6103554730319237e-05, + "loss": 0.1391, "step": 214730 }, { - "epoch": 0.96, - "learning_rate": 2.0976637818931887e-06, - "loss": 0.1336, + "epoch": 0.48, + "learning_rate": 2.6102436187109908e-05, + "loss": 0.1412, "step": 214740 }, { - "epoch": 0.96, - "learning_rate": 2.095421729967266e-06, - "loss": 0.1386, + "epoch": 0.48, + "learning_rate": 2.6101317643900586e-05, + "loss": 0.1368, "step": 214750 }, { - "epoch": 0.96, - "learning_rate": 2.0931796780413436e-06, - "loss": 0.1402, + "epoch": 0.48, + "learning_rate": 2.6100199100691257e-05, + "loss": 0.138, "step": 214760 }, { - "epoch": 0.96, - "learning_rate": 2.090937626115421e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.6099080557481935e-05, + "loss": 0.1342, "step": 214770 }, { - "epoch": 0.96, - "learning_rate": 2.0886955741894985e-06, - "loss": 0.1333, + "epoch": 0.48, + "learning_rate": 2.6097962014272613e-05, + "loss": 0.1329, "step": 214780 }, { - "epoch": 0.96, - "learning_rate": 2.086453522263576e-06, - "loss": 0.1393, + "epoch": 0.48, + "learning_rate": 2.6096843471063287e-05, + "loss": 0.1344, "step": 214790 }, { - "epoch": 0.96, - "learning_rate": 2.084211470337653e-06, - "loss": 0.1333, + "epoch": 0.48, + "learning_rate": 2.6095724927853965e-05, + "loss": 0.1364, "step": 214800 }, { - "epoch": 0.96, - "learning_rate": 2.0819694184117304e-06, - "loss": 0.1305, + "epoch": 0.48, + "learning_rate": 2.6094606384644636e-05, + "loss": 0.1346, "step": 214810 }, { - "epoch": 0.96, - "learning_rate": 2.079727366485808e-06, - "loss": 0.1371, + "epoch": 0.48, + "learning_rate": 2.6093487841435314e-05, + "loss": 0.132, "step": 214820 }, { - "epoch": 0.96, - "learning_rate": 2.0774853145598853e-06, - "loss": 0.1352, + "epoch": 0.48, + "learning_rate": 2.6092369298225992e-05, + "loss": 0.1327, "step": 214830 }, { - "epoch": 0.96, - "learning_rate": 2.0752432626339627e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.6091250755016667e-05, + "loss": 0.1387, "step": 214840 }, { - "epoch": 0.96, - "learning_rate": 2.07300121070804e-06, - "loss": 0.1354, + "epoch": 0.48, + "learning_rate": 2.6090132211807345e-05, + "loss": 0.1371, "step": 214850 }, { - "epoch": 0.96, - "learning_rate": 2.0707591587821176e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6089013668598016e-05, + "loss": 0.1354, "step": 214860 }, { - "epoch": 0.96, - "learning_rate": 2.0685171068561946e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.6087895125388694e-05, + "loss": 0.1352, "step": 214870 }, { - "epoch": 0.96, - "learning_rate": 2.066275054930272e-06, - "loss": 0.1356, + "epoch": 0.48, + "learning_rate": 2.6086776582179372e-05, + "loss": 0.1372, "step": 214880 }, { - "epoch": 0.96, - "learning_rate": 2.06403300300435e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.6085658038970046e-05, + "loss": 0.1331, "step": 214890 }, { - "epoch": 0.96, - "learning_rate": 2.061790951078427e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.6084539495760724e-05, + "loss": 0.1361, "step": 214900 }, { - "epoch": 0.96, - "learning_rate": 2.0595488991525044e-06, - "loss": 0.1399, + "epoch": 0.48, + "learning_rate": 2.6083420952551395e-05, + "loss": 0.1328, "step": 214910 }, { - "epoch": 0.96, - "learning_rate": 2.057306847226582e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.6082302409342073e-05, + "loss": 0.1369, "step": 214920 }, { - "epoch": 0.96, - "learning_rate": 2.0550647953006593e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.608118386613275e-05, + "loss": 0.1356, "step": 214930 }, { - "epoch": 0.96, - "learning_rate": 2.0528227433747364e-06, - "loss": 0.1366, + "epoch": 0.48, + "learning_rate": 2.6080065322923426e-05, + "loss": 0.1325, "step": 214940 }, { - "epoch": 0.96, - "learning_rate": 2.0505806914488142e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.6078946779714104e-05, + "loss": 0.1433, "step": 214950 }, { - "epoch": 0.96, - "learning_rate": 2.0483386395228917e-06, - "loss": 0.1397, + "epoch": 0.48, + "learning_rate": 2.6077828236504775e-05, + "loss": 0.1365, "step": 214960 }, { - "epoch": 0.96, - "learning_rate": 2.0460965875969687e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.6076709693295453e-05, + "loss": 0.1412, "step": 214970 }, { - "epoch": 0.96, - "learning_rate": 2.043854535671046e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.607559115008613e-05, + "loss": 0.1328, "step": 214980 }, { - "epoch": 0.96, - "learning_rate": 2.0416124837451236e-06, - "loss": 0.1349, + "epoch": 0.48, + "learning_rate": 2.6074472606876805e-05, + "loss": 0.1392, "step": 214990 }, { - "epoch": 0.96, - "learning_rate": 2.039370431819201e-06, - "loss": 0.1335, + "epoch": 0.48, + "learning_rate": 2.6073354063667483e-05, + "loss": 0.1269, "step": 215000 }, { - "epoch": 0.96, - "learning_rate": 2.0371283798932785e-06, - "loss": 0.1326, + "epoch": 0.48, + "learning_rate": 2.6072235520458154e-05, + "loss": 0.1328, "step": 215010 }, { - "epoch": 0.96, - "learning_rate": 2.034886327967356e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6071116977248832e-05, + "loss": 0.1318, "step": 215020 }, { - "epoch": 0.96, - "learning_rate": 2.0326442760414334e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.606999843403951e-05, + "loss": 0.1378, "step": 215030 }, { - "epoch": 0.96, - "learning_rate": 2.0304022241155104e-06, - "loss": 0.1352, + "epoch": 0.48, + "learning_rate": 2.6068879890830185e-05, + "loss": 0.1349, "step": 215040 }, { - "epoch": 0.96, - "learning_rate": 2.0281601721895883e-06, - "loss": 0.133, + "epoch": 0.48, + "learning_rate": 2.6067761347620863e-05, + "loss": 0.1358, "step": 215050 }, { - "epoch": 0.96, - "learning_rate": 2.0259181202636653e-06, - "loss": 0.1336, + "epoch": 0.48, + "learning_rate": 2.6066642804411534e-05, + "loss": 0.1318, "step": 215060 }, { - "epoch": 0.96, - "learning_rate": 2.0236760683377427e-06, - "loss": 0.1372, + "epoch": 0.48, + "learning_rate": 2.6065524261202212e-05, + "loss": 0.1361, "step": 215070 }, { - "epoch": 0.96, - "learning_rate": 2.02143401641182e-06, - "loss": 0.1334, + "epoch": 0.48, + "learning_rate": 2.6064405717992886e-05, + "loss": 0.1378, "step": 215080 }, { - "epoch": 0.96, - "learning_rate": 2.0191919644858976e-06, - "loss": 0.1285, + "epoch": 0.48, + "learning_rate": 2.6063287174783564e-05, + "loss": 0.1337, "step": 215090 }, { - "epoch": 0.96, - "learning_rate": 2.016949912559975e-06, - "loss": 0.1345, + "epoch": 0.48, + "learning_rate": 2.6062168631574242e-05, + "loss": 0.1386, "step": 215100 }, { - "epoch": 0.96, - "learning_rate": 2.014707860634052e-06, - "loss": 0.1362, + "epoch": 0.48, + "learning_rate": 2.6061050088364913e-05, + "loss": 0.1437, "step": 215110 }, { - "epoch": 0.96, - "learning_rate": 2.01246580870813e-06, - "loss": 0.1304, + "epoch": 0.48, + "learning_rate": 2.605993154515559e-05, + "loss": 0.1355, "step": 215120 }, { - "epoch": 0.96, - "learning_rate": 2.010223756782207e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.6058813001946262e-05, + "loss": 0.137, "step": 215130 }, { - "epoch": 0.96, - "learning_rate": 2.0079817048562845e-06, - "loss": 0.136, + "epoch": 0.48, + "learning_rate": 2.6057694458736944e-05, + "loss": 0.1386, "step": 215140 }, { - "epoch": 0.96, - "learning_rate": 2.005739652930362e-06, - "loss": 0.1412, + "epoch": 0.48, + "learning_rate": 2.605657591552762e-05, + "loss": 0.1337, "step": 215150 }, { - "epoch": 0.96, - "learning_rate": 2.0034976010044393e-06, - "loss": 0.1405, + "epoch": 0.48, + "learning_rate": 2.6055457372318293e-05, + "loss": 0.1348, "step": 215160 }, { - "epoch": 0.96, - "learning_rate": 2.001255549078517e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.605433882910897e-05, + "loss": 0.1418, "step": 215170 }, { - "epoch": 0.96, - "learning_rate": 1.999013497152594e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.6053220285899642e-05, + "loss": 0.1339, "step": 215180 }, { - "epoch": 0.96, - "learning_rate": 1.9967714452266717e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.605210174269032e-05, + "loss": 0.1328, "step": 215190 }, { - "epoch": 0.96, - "learning_rate": 1.994529393300749e-06, - "loss": 0.1367, + "epoch": 0.48, + "learning_rate": 2.6050983199481e-05, + "loss": 0.1361, "step": 215200 }, { - "epoch": 0.96, - "learning_rate": 1.992287341374826e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.6049864656271672e-05, + "loss": 0.1325, "step": 215210 }, { - "epoch": 0.96, - "learning_rate": 1.990045289448904e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.604874611306235e-05, + "loss": 0.1354, "step": 215220 }, { - "epoch": 0.96, - "learning_rate": 1.987803237522981e-06, - "loss": 0.1381, + "epoch": 0.48, + "learning_rate": 2.604762756985302e-05, + "loss": 0.1325, "step": 215230 }, { - "epoch": 0.96, - "learning_rate": 1.9855611855970585e-06, - "loss": 0.142, + "epoch": 0.48, + "learning_rate": 2.60465090266437e-05, + "loss": 0.1375, "step": 215240 }, { - "epoch": 0.96, - "learning_rate": 1.983319133671136e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.6045390483434377e-05, + "loss": 0.1331, "step": 215250 }, { - "epoch": 0.96, - "learning_rate": 1.9810770817452134e-06, - "loss": 0.1385, + "epoch": 0.48, + "learning_rate": 2.604427194022505e-05, + "loss": 0.141, "step": 215260 }, { - "epoch": 0.96, - "learning_rate": 1.978835029819291e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.604315339701573e-05, + "loss": 0.1355, "step": 215270 }, { - "epoch": 0.96, - "learning_rate": 1.976592977893368e-06, - "loss": 0.1296, + "epoch": 0.48, + "learning_rate": 2.60420348538064e-05, + "loss": 0.1354, "step": 215280 }, { - "epoch": 0.96, - "learning_rate": 1.9743509259674457e-06, - "loss": 0.1346, + "epoch": 0.48, + "learning_rate": 2.604091631059708e-05, + "loss": 0.135, "step": 215290 }, { - "epoch": 0.96, - "learning_rate": 1.9721088740415228e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.6039797767387757e-05, + "loss": 0.1337, "step": 215300 }, { - "epoch": 0.96, - "learning_rate": 1.9698668221156e-06, - "loss": 0.1339, + "epoch": 0.48, + "learning_rate": 2.603867922417843e-05, + "loss": 0.1331, "step": 215310 }, { - "epoch": 0.96, - "learning_rate": 1.9676247701896777e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.603756068096911e-05, + "loss": 0.1364, "step": 215320 }, { - "epoch": 0.96, - "learning_rate": 1.965382718263755e-06, - "loss": 0.1338, + "epoch": 0.48, + "learning_rate": 2.603644213775978e-05, + "loss": 0.1302, "step": 215330 }, { - "epoch": 0.96, - "learning_rate": 1.9631406663378325e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6035323594550458e-05, + "loss": 0.1364, "step": 215340 }, { - "epoch": 0.96, - "learning_rate": 1.96089861441191e-06, - "loss": 0.1378, + "epoch": 0.48, + "learning_rate": 2.6034205051341136e-05, + "loss": 0.1367, "step": 215350 }, { - "epoch": 0.96, - "learning_rate": 1.9586565624859874e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.603308650813181e-05, + "loss": 0.1315, "step": 215360 }, { - "epoch": 0.96, - "learning_rate": 1.9564145105600645e-06, - "loss": 0.139, + "epoch": 0.48, + "learning_rate": 2.603196796492249e-05, + "loss": 0.1409, "step": 215370 }, { - "epoch": 0.96, - "learning_rate": 1.954172458634142e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.603084942171316e-05, + "loss": 0.1386, "step": 215380 }, { - "epoch": 0.96, - "learning_rate": 1.9519304067082198e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.6029730878503838e-05, + "loss": 0.1369, "step": 215390 }, { - "epoch": 0.96, - "learning_rate": 1.949688354782297e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.6028612335294512e-05, + "loss": 0.1367, "step": 215400 }, { - "epoch": 0.96, - "learning_rate": 1.9474463028563743e-06, - "loss": 0.1351, + "epoch": 0.48, + "learning_rate": 2.602749379208519e-05, + "loss": 0.1345, "step": 215410 }, { - "epoch": 0.96, - "learning_rate": 1.9452042509304517e-06, - "loss": 0.1327, + "epoch": 0.48, + "learning_rate": 2.6026375248875868e-05, + "loss": 0.1338, "step": 215420 }, { - "epoch": 0.96, - "learning_rate": 1.942962199004529e-06, - "loss": 0.1364, + "epoch": 0.48, + "learning_rate": 2.602525670566654e-05, + "loss": 0.1343, "step": 215430 }, { - "epoch": 0.96, - "learning_rate": 1.940720147078606e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.6024138162457217e-05, + "loss": 0.1331, "step": 215440 }, { - "epoch": 0.96, - "learning_rate": 1.9384780951526836e-06, - "loss": 0.1386, + "epoch": 0.48, + "learning_rate": 2.602301961924789e-05, + "loss": 0.1324, "step": 215450 }, { - "epoch": 0.96, - "learning_rate": 1.9362360432267615e-06, - "loss": 0.137, + "epoch": 0.48, + "learning_rate": 2.602190107603857e-05, + "loss": 0.1384, "step": 215460 }, { - "epoch": 0.96, - "learning_rate": 1.9339939913008385e-06, - "loss": 0.1384, + "epoch": 0.48, + "learning_rate": 2.6020782532829247e-05, + "loss": 0.1344, "step": 215470 }, { - "epoch": 0.96, - "learning_rate": 1.931751939374916e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.601966398961992e-05, + "loss": 0.1329, "step": 215480 }, { - "epoch": 0.96, - "learning_rate": 1.9295098874489934e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.6018545446410597e-05, + "loss": 0.1377, "step": 215490 }, { - "epoch": 0.96, - "learning_rate": 1.927267835523071e-06, - "loss": 0.1314, + "epoch": 0.48, + "learning_rate": 2.601742690320127e-05, + "loss": 0.1294, "step": 215500 }, { - "epoch": 0.96, - "learning_rate": 1.9250257835971483e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.601630835999195e-05, + "loss": 0.1324, "step": 215510 }, { - "epoch": 0.96, - "learning_rate": 1.9227837316712258e-06, - "loss": 0.1407, + "epoch": 0.48, + "learning_rate": 2.6015189816782627e-05, + "loss": 0.1354, "step": 215520 }, { - "epoch": 0.96, - "learning_rate": 1.920541679745303e-06, - "loss": 0.1392, + "epoch": 0.48, + "learning_rate": 2.6014071273573298e-05, + "loss": 0.1382, "step": 215530 }, { - "epoch": 0.96, - "learning_rate": 1.9182996278193802e-06, - "loss": 0.1335, + "epoch": 0.48, + "learning_rate": 2.6012952730363976e-05, + "loss": 0.1348, "step": 215540 }, { - "epoch": 0.96, - "learning_rate": 1.9160575758934577e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.601183418715465e-05, + "loss": 0.1372, "step": 215550 }, { - "epoch": 0.96, - "learning_rate": 1.913815523967535e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.601071564394533e-05, + "loss": 0.1358, "step": 215560 }, { - "epoch": 0.96, - "learning_rate": 1.9115734720416126e-06, - "loss": 0.1322, + "epoch": 0.48, + "learning_rate": 2.6009597100736006e-05, + "loss": 0.1372, "step": 215570 }, { - "epoch": 0.96, - "learning_rate": 1.90933142011569e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.6008478557526678e-05, + "loss": 0.1334, "step": 215580 }, { - "epoch": 0.96, - "learning_rate": 1.9070893681897672e-06, - "loss": 0.1378, + "epoch": 0.48, + "learning_rate": 2.6007360014317356e-05, + "loss": 0.136, "step": 215590 }, { - "epoch": 0.96, - "learning_rate": 1.905071521456437e-06, - "loss": 0.142, + "epoch": 0.48, + "learning_rate": 2.6006241471108027e-05, + "loss": 0.1391, "step": 215600 }, { - "epoch": 0.96, - "learning_rate": 1.9028294695305146e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.6005122927898708e-05, + "loss": 0.1374, "step": 215610 }, { - "epoch": 0.96, - "learning_rate": 1.9005874176045916e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.6004004384689386e-05, + "loss": 0.1411, "step": 215620 }, { - "epoch": 0.96, - "learning_rate": 1.8983453656786693e-06, - "loss": 0.1415, + "epoch": 0.48, + "learning_rate": 2.6002885841480057e-05, + "loss": 0.1372, "step": 215630 }, { - "epoch": 0.96, - "learning_rate": 1.8961033137527465e-06, - "loss": 0.1366, + "epoch": 0.48, + "learning_rate": 2.6001767298270735e-05, + "loss": 0.1327, "step": 215640 }, { - "epoch": 0.96, - "learning_rate": 1.893861261826824e-06, - "loss": 0.1326, + "epoch": 0.48, + "learning_rate": 2.6000648755061406e-05, + "loss": 0.1356, "step": 215650 }, { - "epoch": 0.96, - "learning_rate": 1.8916192099009016e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.5999530211852084e-05, + "loss": 0.1383, "step": 215660 }, { - "epoch": 0.96, - "learning_rate": 1.8893771579749787e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.5998411668642762e-05, + "loss": 0.1379, "step": 215670 }, { - "epoch": 0.96, - "learning_rate": 1.8871351060490563e-06, - "loss": 0.1344, + "epoch": 0.48, + "learning_rate": 2.5997293125433437e-05, + "loss": 0.1341, "step": 215680 }, { - "epoch": 0.96, - "learning_rate": 1.8848930541231335e-06, - "loss": 0.1326, + "epoch": 0.48, + "learning_rate": 2.5996174582224114e-05, + "loss": 0.1383, "step": 215690 }, { - "epoch": 0.96, - "learning_rate": 1.882651002197211e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.5995056039014786e-05, + "loss": 0.1383, "step": 215700 }, { - "epoch": 0.96, - "learning_rate": 1.8804089502712882e-06, - "loss": 0.1385, + "epoch": 0.48, + "learning_rate": 2.5993937495805464e-05, + "loss": 0.1383, "step": 215710 }, { - "epoch": 0.96, - "learning_rate": 1.8781668983453657e-06, - "loss": 0.1329, + "epoch": 0.48, + "learning_rate": 2.5992818952596138e-05, + "loss": 0.1342, "step": 215720 }, { - "epoch": 0.96, - "learning_rate": 1.8759248464194433e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.5991700409386816e-05, + "loss": 0.1378, "step": 215730 }, { - "epoch": 0.96, - "learning_rate": 1.8736827944935206e-06, - "loss": 0.1351, + "epoch": 0.48, + "learning_rate": 2.5990581866177494e-05, + "loss": 0.1327, "step": 215740 }, { - "epoch": 0.96, - "learning_rate": 1.871440742567598e-06, - "loss": 0.1442, + "epoch": 0.48, + "learning_rate": 2.5989463322968165e-05, + "loss": 0.1388, "step": 215750 }, { - "epoch": 0.96, - "learning_rate": 1.8691986906416753e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.5988344779758843e-05, + "loss": 0.1391, "step": 215760 }, { - "epoch": 0.96, - "learning_rate": 1.8669566387157527e-06, - "loss": 0.1356, + "epoch": 0.48, + "learning_rate": 2.5987226236549518e-05, + "loss": 0.1355, "step": 215770 }, { - "epoch": 0.96, - "learning_rate": 1.8647145867898304e-06, - "loss": 0.132, + "epoch": 0.48, + "learning_rate": 2.5986107693340195e-05, + "loss": 0.1347, "step": 215780 }, { - "epoch": 0.96, - "learning_rate": 1.8624725348639076e-06, - "loss": 0.1357, + "epoch": 0.48, + "learning_rate": 2.5984989150130873e-05, + "loss": 0.1353, "step": 215790 }, { - "epoch": 0.96, - "learning_rate": 1.860230482937985e-06, - "loss": 0.1411, + "epoch": 0.48, + "learning_rate": 2.5983870606921545e-05, + "loss": 0.137, "step": 215800 }, { - "epoch": 0.96, - "learning_rate": 1.8579884310120623e-06, - "loss": 0.1385, + "epoch": 0.48, + "learning_rate": 2.5982752063712223e-05, + "loss": 0.1413, "step": 215810 }, { - "epoch": 0.96, - "learning_rate": 1.8557463790861397e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.5981633520502897e-05, + "loss": 0.1404, "step": 215820 }, { - "epoch": 0.96, - "learning_rate": 1.853504327160217e-06, - "loss": 0.1352, + "epoch": 0.48, + "learning_rate": 2.5980514977293575e-05, + "loss": 0.1361, "step": 215830 }, { - "epoch": 0.96, - "learning_rate": 1.8512622752342946e-06, - "loss": 0.136, + "epoch": 0.48, + "learning_rate": 2.5979396434084253e-05, + "loss": 0.1355, "step": 215840 }, { - "epoch": 0.96, - "learning_rate": 1.849020223308372e-06, - "loss": 0.1359, + "epoch": 0.48, + "learning_rate": 2.5978277890874924e-05, + "loss": 0.1388, "step": 215850 }, { - "epoch": 0.96, - "learning_rate": 1.8467781713824493e-06, - "loss": 0.1346, + "epoch": 0.48, + "learning_rate": 2.5977159347665602e-05, + "loss": 0.1393, "step": 215860 }, { - "epoch": 0.96, - "learning_rate": 1.8445361194565268e-06, - "loss": 0.1451, + "epoch": 0.48, + "learning_rate": 2.5976040804456277e-05, + "loss": 0.1389, "step": 215870 }, { - "epoch": 0.96, - "learning_rate": 1.842294067530604e-06, - "loss": 0.139, + "epoch": 0.48, + "learning_rate": 2.5974922261246954e-05, + "loss": 0.1363, "step": 215880 }, { - "epoch": 0.96, - "learning_rate": 1.8400520156046814e-06, - "loss": 0.1356, + "epoch": 0.48, + "learning_rate": 2.5973803718037632e-05, + "loss": 0.1361, "step": 215890 }, { - "epoch": 0.96, - "learning_rate": 1.8378099636787587e-06, - "loss": 0.1334, + "epoch": 0.48, + "learning_rate": 2.5972685174828304e-05, + "loss": 0.1347, "step": 215900 }, { - "epoch": 0.96, - "learning_rate": 1.8355679117528363e-06, - "loss": 0.1384, + "epoch": 0.48, + "learning_rate": 2.597156663161898e-05, + "loss": 0.1355, "step": 215910 }, { - "epoch": 0.96, - "learning_rate": 1.8333258598269138e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.5970448088409656e-05, + "loss": 0.1326, "step": 215920 }, { - "epoch": 0.96, - "learning_rate": 1.831083807900991e-06, - "loss": 0.1367, + "epoch": 0.48, + "learning_rate": 2.5969329545200334e-05, + "loss": 0.1353, "step": 215930 }, { - "epoch": 0.96, - "learning_rate": 1.8288417559750685e-06, - "loss": 0.1325, + "epoch": 0.48, + "learning_rate": 2.5968211001991012e-05, + "loss": 0.1365, "step": 215940 }, { - "epoch": 0.96, - "learning_rate": 1.8265997040491457e-06, - "loss": 0.1337, + "epoch": 0.48, + "learning_rate": 2.5967092458781683e-05, + "loss": 0.1359, "step": 215950 }, { - "epoch": 0.96, - "learning_rate": 1.8243576521232234e-06, - "loss": 0.1374, + "epoch": 0.48, + "learning_rate": 2.596597391557236e-05, + "loss": 0.1369, "step": 215960 }, { - "epoch": 0.96, - "learning_rate": 1.8221156001973008e-06, - "loss": 0.1415, + "epoch": 0.48, + "learning_rate": 2.5964855372363035e-05, + "loss": 0.1342, "step": 215970 }, { - "epoch": 0.96, - "learning_rate": 1.819873548271378e-06, - "loss": 0.1393, + "epoch": 0.48, + "learning_rate": 2.5963736829153713e-05, + "loss": 0.1371, "step": 215980 }, { - "epoch": 0.96, - "learning_rate": 1.8176314963454555e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.5962618285944385e-05, + "loss": 0.137, "step": 215990 }, { - "epoch": 0.96, - "learning_rate": 1.8153894444195327e-06, - "loss": 0.1387, + "epoch": 0.48, + "learning_rate": 2.5961499742735062e-05, + "loss": 0.1433, "step": 216000 }, { - "epoch": 0.96, - "learning_rate": 1.8131473924936104e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.596038119952574e-05, + "loss": 0.1362, "step": 216010 }, { - "epoch": 0.96, - "learning_rate": 1.8109053405676874e-06, + "epoch": 0.48, + "learning_rate": 2.595926265631641e-05, "loss": 0.1366, "step": 216020 }, { - "epoch": 0.96, - "learning_rate": 1.808663288641765e-06, - "loss": 0.1395, + "epoch": 0.48, + "learning_rate": 2.5958144113107093e-05, + "loss": 0.1334, "step": 216030 }, { - "epoch": 0.96, - "learning_rate": 1.8064212367158425e-06, - "loss": 0.1418, + "epoch": 0.48, + "learning_rate": 2.5957025569897764e-05, + "loss": 0.1388, "step": 216040 }, { - "epoch": 0.96, - "learning_rate": 1.8041791847899197e-06, - "loss": 0.1338, + "epoch": 0.48, + "learning_rate": 2.5955907026688442e-05, + "loss": 0.1381, "step": 216050 }, { - "epoch": 0.96, - "learning_rate": 1.8019371328639974e-06, - "loss": 0.1378, + "epoch": 0.48, + "learning_rate": 2.595478848347912e-05, + "loss": 0.1348, "step": 216060 }, { - "epoch": 0.96, - "learning_rate": 1.7996950809380744e-06, - "loss": 0.1357, + "epoch": 0.48, + "learning_rate": 2.595366994026979e-05, + "loss": 0.1329, "step": 216070 }, { - "epoch": 0.96, - "learning_rate": 1.797453029012152e-06, - "loss": 0.1374, + "epoch": 0.48, + "learning_rate": 2.595255139706047e-05, + "loss": 0.1309, "step": 216080 }, { - "epoch": 0.96, - "learning_rate": 1.7952109770862293e-06, - "loss": 0.1345, + "epoch": 0.48, + "learning_rate": 2.5951432853851143e-05, + "loss": 0.1363, "step": 216090 }, { - "epoch": 0.96, - "learning_rate": 1.7929689251603068e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.595031431064182e-05, + "loss": 0.1346, "step": 216100 }, { - "epoch": 0.96, - "learning_rate": 1.7907268732343842e-06, - "loss": 0.1327, + "epoch": 0.48, + "learning_rate": 2.59491957674325e-05, + "loss": 0.1378, "step": 216110 }, { - "epoch": 0.96, - "learning_rate": 1.7884848213084615e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.594807722422317e-05, + "loss": 0.1353, "step": 216120 }, { - "epoch": 0.96, - "learning_rate": 1.7862427693825391e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.594695868101385e-05, + "loss": 0.1397, "step": 216130 }, { - "epoch": 0.96, - "learning_rate": 1.7840007174566163e-06, - "loss": 0.1356, + "epoch": 0.48, + "learning_rate": 2.5945840137804523e-05, + "loss": 0.137, "step": 216140 }, { - "epoch": 0.96, - "learning_rate": 1.7817586655306938e-06, - "loss": 0.1371, + "epoch": 0.48, + "learning_rate": 2.59447215945952e-05, + "loss": 0.133, "step": 216150 }, { - "epoch": 0.96, - "learning_rate": 1.7795166136047712e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.594360305138588e-05, + "loss": 0.1325, "step": 216160 }, { - "epoch": 0.97, - "learning_rate": 1.7772745616788485e-06, - "loss": 0.1332, + "epoch": 0.48, + "learning_rate": 2.594248450817655e-05, + "loss": 0.133, "step": 216170 }, { - "epoch": 0.97, - "learning_rate": 1.7750325097529261e-06, - "loss": 0.1433, + "epoch": 0.48, + "learning_rate": 2.5941365964967228e-05, + "loss": 0.1291, "step": 216180 }, { - "epoch": 0.97, - "learning_rate": 1.7727904578270032e-06, - "loss": 0.1428, + "epoch": 0.48, + "learning_rate": 2.5940247421757902e-05, + "loss": 0.1333, "step": 216190 }, { - "epoch": 0.97, - "learning_rate": 1.7705484059010808e-06, - "loss": 0.1394, + "epoch": 0.48, + "learning_rate": 2.593912887854858e-05, + "loss": 0.1316, "step": 216200 }, { - "epoch": 0.97, - "learning_rate": 1.768306353975158e-06, - "loss": 0.1373, + "epoch": 0.48, + "learning_rate": 2.5938010335339258e-05, + "loss": 0.1349, "step": 216210 }, { - "epoch": 0.97, - "learning_rate": 1.7660643020492355e-06, - "loss": 0.1352, + "epoch": 0.48, + "learning_rate": 2.593689179212993e-05, + "loss": 0.1344, "step": 216220 }, { - "epoch": 0.97, - "learning_rate": 1.7638222501233132e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.5935773248920607e-05, + "loss": 0.1409, "step": 216230 }, { - "epoch": 0.97, - "learning_rate": 1.7615801981973902e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.5934654705711282e-05, + "loss": 0.1338, "step": 216240 }, { - "epoch": 0.97, - "learning_rate": 1.7593381462714678e-06, - "loss": 0.1387, + "epoch": 0.48, + "learning_rate": 2.593353616250196e-05, + "loss": 0.135, "step": 216250 }, { - "epoch": 0.97, - "learning_rate": 1.757096094345545e-06, - "loss": 0.1381, + "epoch": 0.48, + "learning_rate": 2.5932417619292638e-05, + "loss": 0.1357, "step": 216260 }, { - "epoch": 0.97, - "learning_rate": 1.7548540424196225e-06, - "loss": 0.1431, + "epoch": 0.48, + "learning_rate": 2.593129907608331e-05, + "loss": 0.1382, "step": 216270 }, { - "epoch": 0.97, - "learning_rate": 1.7526119904937002e-06, - "loss": 0.1413, + "epoch": 0.48, + "learning_rate": 2.5930180532873987e-05, + "loss": 0.1336, "step": 216280 }, { - "epoch": 0.97, - "learning_rate": 1.7503699385677772e-06, - "loss": 0.1406, + "epoch": 0.48, + "learning_rate": 2.592906198966466e-05, + "loss": 0.1348, "step": 216290 }, { - "epoch": 0.97, - "learning_rate": 1.7481278866418549e-06, - "loss": 0.1355, + "epoch": 0.48, + "learning_rate": 2.592794344645534e-05, + "loss": 0.1439, "step": 216300 }, { - "epoch": 0.97, - "learning_rate": 1.745885834715932e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.592682490324601e-05, + "loss": 0.1347, "step": 216310 }, { - "epoch": 0.97, - "learning_rate": 1.7436437827900095e-06, - "loss": 0.1428, + "epoch": 0.48, + "learning_rate": 2.5925818214357623e-05, + "loss": 0.1368, "step": 216320 }, { - "epoch": 0.97, - "learning_rate": 1.7414017308640868e-06, - "loss": 0.1381, + "epoch": 0.48, + "learning_rate": 2.59246996711483e-05, + "loss": 0.1348, "step": 216330 }, { - "epoch": 0.97, - "learning_rate": 1.7391596789381642e-06, - "loss": 0.1405, + "epoch": 0.48, + "learning_rate": 2.5923581127938972e-05, + "loss": 0.1401, "step": 216340 }, { - "epoch": 0.97, - "learning_rate": 1.7369176270122419e-06, - "loss": 0.1342, + "epoch": 0.48, + "learning_rate": 2.592246258472965e-05, + "loss": 0.1316, "step": 216350 }, { - "epoch": 0.97, - "learning_rate": 1.7346755750863191e-06, - "loss": 0.1377, + "epoch": 0.48, + "learning_rate": 2.5921344041520324e-05, + "loss": 0.1381, "step": 216360 }, { - "epoch": 0.97, - "learning_rate": 1.7324335231603966e-06, - "loss": 0.1322, + "epoch": 0.48, + "learning_rate": 2.5920225498311002e-05, + "loss": 0.1384, "step": 216370 }, { - "epoch": 0.97, - "learning_rate": 1.7301914712344738e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.5919106955101673e-05, + "loss": 0.1357, "step": 216380 }, { - "epoch": 0.97, - "learning_rate": 1.7279494193085513e-06, - "loss": 0.1368, + "epoch": 0.48, + "learning_rate": 2.591798841189235e-05, + "loss": 0.1345, "step": 216390 }, { - "epoch": 0.97, - "learning_rate": 1.7257073673826285e-06, - "loss": 0.1291, + "epoch": 0.48, + "learning_rate": 2.591686986868303e-05, + "loss": 0.1366, "step": 216400 }, { - "epoch": 0.97, - "learning_rate": 1.7234653154567061e-06, - "loss": 0.1359, + "epoch": 0.48, + "learning_rate": 2.5915751325473704e-05, + "loss": 0.1344, "step": 216410 }, { - "epoch": 0.97, - "learning_rate": 1.7212232635307836e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.591463278226438e-05, + "loss": 0.1364, "step": 216420 }, { - "epoch": 0.97, - "learning_rate": 1.7189812116048608e-06, - "loss": 0.134, + "epoch": 0.48, + "learning_rate": 2.5913514239055053e-05, + "loss": 0.1349, "step": 216430 }, { - "epoch": 0.97, - "learning_rate": 1.7167391596789383e-06, - "loss": 0.1366, + "epoch": 0.48, + "learning_rate": 2.591239569584573e-05, + "loss": 0.1308, "step": 216440 }, { - "epoch": 0.97, - "learning_rate": 1.7144971077530155e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.591127715263641e-05, + "loss": 0.1358, "step": 216450 }, { - "epoch": 0.97, - "learning_rate": 1.712255055827093e-06, - "loss": 0.1382, + "epoch": 0.48, + "learning_rate": 2.5910158609427083e-05, + "loss": 0.135, "step": 216460 }, { - "epoch": 0.97, - "learning_rate": 1.7100130039011706e-06, - "loss": 0.1412, + "epoch": 0.48, + "learning_rate": 2.590904006621776e-05, + "loss": 0.1388, "step": 216470 }, { - "epoch": 0.97, - "learning_rate": 1.7077709519752479e-06, - "loss": 0.1346, + "epoch": 0.48, + "learning_rate": 2.5907921523008432e-05, + "loss": 0.1344, "step": 216480 }, { - "epoch": 0.97, - "learning_rate": 1.7055289000493253e-06, - "loss": 0.1337, + "epoch": 0.48, + "learning_rate": 2.590680297979911e-05, + "loss": 0.1333, "step": 216490 }, { - "epoch": 0.97, - "learning_rate": 1.7032868481234025e-06, - "loss": 0.1339, + "epoch": 0.48, + "learning_rate": 2.5905684436589788e-05, + "loss": 0.1367, "step": 216500 }, { - "epoch": 0.97, - "learning_rate": 1.70104479619748e-06, - "loss": 0.1381, + "epoch": 0.48, + "learning_rate": 2.5904565893380463e-05, + "loss": 0.1344, "step": 216510 }, { - "epoch": 0.97, - "learning_rate": 1.6988027442715572e-06, - "loss": 0.1319, + "epoch": 0.48, + "learning_rate": 2.590344735017114e-05, + "loss": 0.1378, "step": 216520 }, { - "epoch": 0.97, - "learning_rate": 1.6965606923456349e-06, - "loss": 0.1368, + "epoch": 0.48, + "learning_rate": 2.590232880696181e-05, + "loss": 0.1401, "step": 216530 }, { - "epoch": 0.97, - "learning_rate": 1.6943186404197123e-06, - "loss": 0.1415, + "epoch": 0.48, + "learning_rate": 2.590121026375249e-05, + "loss": 0.1381, "step": 216540 }, { - "epoch": 0.97, - "learning_rate": 1.6920765884937896e-06, - "loss": 0.1349, + "epoch": 0.48, + "learning_rate": 2.5900091720543168e-05, + "loss": 0.1346, "step": 216550 }, { - "epoch": 0.97, - "learning_rate": 1.689834536567867e-06, - "loss": 0.1345, + "epoch": 0.48, + "learning_rate": 2.5898973177333842e-05, + "loss": 0.1411, "step": 216560 }, { - "epoch": 0.97, - "learning_rate": 1.6875924846419442e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.589785463412452e-05, + "loss": 0.1348, "step": 216570 }, { - "epoch": 0.97, - "learning_rate": 1.685350432716022e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.589673609091519e-05, + "loss": 0.137, "step": 216580 }, { - "epoch": 0.97, - "learning_rate": 1.683108380790099e-06, - "loss": 0.1326, + "epoch": 0.48, + "learning_rate": 2.589561754770587e-05, + "loss": 0.1347, "step": 216590 }, { - "epoch": 0.97, - "learning_rate": 1.6808663288641766e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.5894499004496547e-05, + "loss": 0.1314, "step": 216600 }, { - "epoch": 0.97, - "learning_rate": 1.678624276938254e-06, - "loss": 0.139, + "epoch": 0.48, + "learning_rate": 2.589338046128722e-05, + "loss": 0.1382, "step": 216610 }, { - "epoch": 0.97, - "learning_rate": 1.6763822250123313e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.58922619180779e-05, + "loss": 0.1334, "step": 216620 }, { - "epoch": 0.97, - "learning_rate": 1.674140173086409e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.589114337486857e-05, + "loss": 0.1369, "step": 216630 }, { - "epoch": 0.97, - "learning_rate": 1.671898121160486e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.589002483165925e-05, + "loss": 0.1356, "step": 216640 }, { - "epoch": 0.97, - "learning_rate": 1.6696560692345636e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.5888906288449926e-05, + "loss": 0.1386, "step": 216650 }, { - "epoch": 0.97, - "learning_rate": 1.667414017308641e-06, - "loss": 0.1383, + "epoch": 0.48, + "learning_rate": 2.5887787745240598e-05, + "loss": 0.138, "step": 216660 }, { - "epoch": 0.97, - "learning_rate": 1.6651719653827183e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.588666920203128e-05, + "loss": 0.1359, "step": 216670 }, { - "epoch": 0.97, - "learning_rate": 1.6629299134567957e-06, - "loss": 0.1363, + "epoch": 0.48, + "learning_rate": 2.588555065882195e-05, + "loss": 0.1335, "step": 216680 }, { - "epoch": 0.97, - "learning_rate": 1.660687861530873e-06, - "loss": 0.1397, + "epoch": 0.48, + "learning_rate": 2.5884432115612628e-05, + "loss": 0.1381, "step": 216690 }, { - "epoch": 0.97, - "learning_rate": 1.6584458096049506e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.58833135724033e-05, + "loss": 0.1373, "step": 216700 }, { - "epoch": 0.97, - "learning_rate": 1.6562037576790279e-06, - "loss": 0.138, + "epoch": 0.48, + "learning_rate": 2.5882195029193977e-05, + "loss": 0.1373, "step": 216710 }, { - "epoch": 0.97, - "learning_rate": 1.6539617057531053e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.5881076485984655e-05, + "loss": 0.1344, "step": 216720 }, { - "epoch": 0.97, - "learning_rate": 1.6517196538271828e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.587995794277533e-05, + "loss": 0.1354, "step": 216730 }, { - "epoch": 0.97, - "learning_rate": 1.64947760190126e-06, - "loss": 0.1354, + "epoch": 0.48, + "learning_rate": 2.5878839399566008e-05, + "loss": 0.136, "step": 216740 }, { - "epoch": 0.97, - "learning_rate": 1.6472355499753377e-06, - "loss": 0.1418, + "epoch": 0.48, + "learning_rate": 2.587772085635668e-05, + "loss": 0.1361, "step": 216750 }, { - "epoch": 0.97, - "learning_rate": 1.6449934980494147e-06, - "loss": 0.134, + "epoch": 0.48, + "learning_rate": 2.5876602313147357e-05, + "loss": 0.1344, "step": 216760 }, { - "epoch": 0.97, - "learning_rate": 1.6427514461234923e-06, - "loss": 0.139, + "epoch": 0.48, + "learning_rate": 2.5875483769938035e-05, + "loss": 0.1391, "step": 216770 }, { - "epoch": 0.97, - "learning_rate": 1.6405093941975696e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.587436522672871e-05, + "loss": 0.1383, "step": 216780 }, { - "epoch": 0.97, - "learning_rate": 1.638267342271647e-06, - "loss": 0.1341, + "epoch": 0.48, + "learning_rate": 2.5873246683519387e-05, + "loss": 0.1329, "step": 216790 }, { - "epoch": 0.97, - "learning_rate": 1.6360252903457247e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.5872128140310058e-05, + "loss": 0.1336, "step": 216800 }, { - "epoch": 0.97, - "learning_rate": 1.6337832384198017e-06, - "loss": 0.1358, + "epoch": 0.48, + "learning_rate": 2.5871009597100736e-05, + "loss": 0.1318, "step": 216810 }, { - "epoch": 0.97, - "learning_rate": 1.6315411864938794e-06, - "loss": 0.1383, + "epoch": 0.48, + "learning_rate": 2.5869891053891414e-05, + "loss": 0.1363, "step": 216820 }, { - "epoch": 0.97, - "learning_rate": 1.6292991345679566e-06, - "loss": 0.1361, + "epoch": 0.48, + "learning_rate": 2.586877251068209e-05, + "loss": 0.1335, "step": 216830 }, { - "epoch": 0.97, - "learning_rate": 1.627057082642034e-06, - "loss": 0.1292, + "epoch": 0.48, + "learning_rate": 2.5867653967472766e-05, + "loss": 0.132, "step": 216840 }, { - "epoch": 0.97, - "learning_rate": 1.6248150307161117e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.5866535424263438e-05, + "loss": 0.1374, "step": 216850 }, { - "epoch": 0.97, - "learning_rate": 1.6225729787901887e-06, - "loss": 0.1327, + "epoch": 0.48, + "learning_rate": 2.5865416881054116e-05, + "loss": 0.1306, "step": 216860 }, { - "epoch": 0.97, - "learning_rate": 1.6203309268642664e-06, - "loss": 0.131, + "epoch": 0.48, + "learning_rate": 2.5864298337844793e-05, + "loss": 0.1356, "step": 216870 }, { - "epoch": 0.97, - "learning_rate": 1.6180888749383436e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.5863179794635468e-05, + "loss": 0.1368, "step": 216880 }, { - "epoch": 0.97, - "learning_rate": 1.615846823012421e-06, - "loss": 0.1386, + "epoch": 0.48, + "learning_rate": 2.5862061251426146e-05, + "loss": 0.1333, "step": 216890 }, { - "epoch": 0.97, - "learning_rate": 1.6136047710864983e-06, - "loss": 0.1366, + "epoch": 0.48, + "learning_rate": 2.5860942708216817e-05, + "loss": 0.1408, "step": 216900 }, { - "epoch": 0.97, - "learning_rate": 1.6113627191605758e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.5859824165007495e-05, + "loss": 0.1312, "step": 216910 }, { - "epoch": 0.97, - "learning_rate": 1.6091206672346534e-06, - "loss": 0.1404, + "epoch": 0.48, + "learning_rate": 2.5858705621798173e-05, + "loss": 0.1364, "step": 216920 }, { - "epoch": 0.97, - "learning_rate": 1.6068786153087306e-06, - "loss": 0.1391, + "epoch": 0.48, + "learning_rate": 2.5857587078588847e-05, + "loss": 0.1348, "step": 216930 }, { - "epoch": 0.97, - "learning_rate": 1.604636563382808e-06, - "loss": 0.1392, + "epoch": 0.48, + "learning_rate": 2.5856468535379525e-05, + "loss": 0.1343, "step": 216940 }, { - "epoch": 0.97, - "learning_rate": 1.6023945114568853e-06, - "loss": 0.1369, + "epoch": 0.48, + "learning_rate": 2.5855349992170197e-05, + "loss": 0.1372, "step": 216950 }, { - "epoch": 0.97, - "learning_rate": 1.6001524595309628e-06, - "loss": 0.135, + "epoch": 0.48, + "learning_rate": 2.5854231448960874e-05, + "loss": 0.1329, "step": 216960 }, { - "epoch": 0.97, - "learning_rate": 1.5979104076050404e-06, - "loss": 0.1388, + "epoch": 0.48, + "learning_rate": 2.5853112905751552e-05, + "loss": 0.1322, "step": 216970 }, { - "epoch": 0.97, - "learning_rate": 1.5956683556791177e-06, - "loss": 0.1359, + "epoch": 0.48, + "learning_rate": 2.5851994362542227e-05, + "loss": 0.137, "step": 216980 }, { - "epoch": 0.97, - "learning_rate": 1.5934263037531951e-06, - "loss": 0.1376, + "epoch": 0.48, + "learning_rate": 2.5850875819332905e-05, + "loss": 0.1331, "step": 216990 }, { - "epoch": 0.97, - "learning_rate": 1.5911842518272724e-06, - "loss": 0.1333, + "epoch": 0.48, + "learning_rate": 2.5849757276123576e-05, + "loss": 0.1287, "step": 217000 }, { - "epoch": 0.97, - "learning_rate": 1.5889421999013498e-06, - "loss": 0.1331, + "epoch": 0.48, + "learning_rate": 2.5848638732914254e-05, + "loss": 0.1329, "step": 217010 }, { - "epoch": 0.97, - "learning_rate": 1.586700147975427e-06, - "loss": 0.1333, + "epoch": 0.48, + "learning_rate": 2.584752018970493e-05, + "loss": 0.1365, "step": 217020 }, { - "epoch": 0.97, - "learning_rate": 1.5844580960495045e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.5846401646495606e-05, + "loss": 0.1372, "step": 217030 }, { - "epoch": 0.97, - "learning_rate": 1.5822160441235821e-06, - "loss": 0.1317, + "epoch": 0.48, + "learning_rate": 2.5845283103286284e-05, + "loss": 0.1341, "step": 217040 }, { - "epoch": 0.97, - "learning_rate": 1.5799739921976594e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.5844164560076955e-05, + "loss": 0.1371, "step": 217050 }, { - "epoch": 0.97, - "learning_rate": 1.5777319402717368e-06, - "loss": 0.1414, + "epoch": 0.48, + "learning_rate": 2.5843046016867633e-05, + "loss": 0.1354, "step": 217060 }, { - "epoch": 0.97, - "learning_rate": 1.575489888345814e-06, - "loss": 0.1328, + "epoch": 0.48, + "learning_rate": 2.5841927473658305e-05, + "loss": 0.1332, "step": 217070 }, { - "epoch": 0.97, - "learning_rate": 1.5732478364198915e-06, - "loss": 0.1417, + "epoch": 0.48, + "learning_rate": 2.5840808930448986e-05, + "loss": 0.1288, "step": 217080 }, { - "epoch": 0.97, - "learning_rate": 1.5710057844939687e-06, - "loss": 0.1398, + "epoch": 0.48, + "learning_rate": 2.5839690387239664e-05, + "loss": 0.1371, "step": 217090 }, { - "epoch": 0.97, - "learning_rate": 1.5687637325680464e-06, - "loss": 0.1406, + "epoch": 0.48, + "learning_rate": 2.5838571844030335e-05, + "loss": 0.1287, "step": 217100 }, { - "epoch": 0.97, - "learning_rate": 1.5665216806421239e-06, - "loss": 0.1428, + "epoch": 0.48, + "learning_rate": 2.5837453300821013e-05, + "loss": 0.1331, "step": 217110 }, { - "epoch": 0.97, - "learning_rate": 1.564279628716201e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.5836334757611684e-05, + "loss": 0.1367, "step": 217120 }, { - "epoch": 0.97, - "learning_rate": 1.5620375767902785e-06, - "loss": 0.1402, + "epoch": 0.48, + "learning_rate": 2.5835216214402362e-05, + "loss": 0.1359, "step": 217130 }, { - "epoch": 0.97, - "learning_rate": 1.559795524864356e-06, - "loss": 0.132, + "epoch": 0.48, + "learning_rate": 2.583409767119304e-05, + "loss": 0.1313, "step": 217140 }, { - "epoch": 0.97, - "learning_rate": 1.5575534729384334e-06, - "loss": 0.14, + "epoch": 0.48, + "learning_rate": 2.5832979127983714e-05, + "loss": 0.137, "step": 217150 }, { - "epoch": 0.97, - "learning_rate": 1.5553114210125107e-06, - "loss": 0.1384, + "epoch": 0.48, + "learning_rate": 2.5831860584774392e-05, + "loss": 0.137, "step": 217160 }, { - "epoch": 0.97, - "learning_rate": 1.5530693690865881e-06, - "loss": 0.1343, + "epoch": 0.48, + "learning_rate": 2.5830742041565064e-05, + "loss": 0.1368, "step": 217170 }, { - "epoch": 0.97, - "learning_rate": 1.5508273171606653e-06, - "loss": 0.1365, + "epoch": 0.48, + "learning_rate": 2.582962349835574e-05, + "loss": 0.139, "step": 217180 }, { - "epoch": 0.97, - "learning_rate": 1.548585265234743e-06, - "loss": 0.1385, + "epoch": 0.48, + "learning_rate": 2.582850495514642e-05, + "loss": 0.1339, "step": 217190 }, { - "epoch": 0.97, - "learning_rate": 1.5463432133088205e-06, - "loss": 0.1307, + "epoch": 0.48, + "learning_rate": 2.5827386411937094e-05, + "loss": 0.1339, "step": 217200 }, { - "epoch": 0.97, - "learning_rate": 1.5441011613828977e-06, - "loss": 0.1323, + "epoch": 0.48, + "learning_rate": 2.5826267868727772e-05, + "loss": 0.1428, "step": 217210 }, { - "epoch": 0.97, - "learning_rate": 1.5418591094569751e-06, - "loss": 0.135, + "epoch": 0.48, + "learning_rate": 2.5825149325518443e-05, + "loss": 0.1381, "step": 217220 }, { - "epoch": 0.97, - "learning_rate": 1.5396170575310524e-06, - "loss": 0.1375, + "epoch": 0.48, + "learning_rate": 2.582403078230912e-05, + "loss": 0.1346, "step": 217230 }, { - "epoch": 0.97, - "learning_rate": 1.5373750056051298e-06, - "loss": 0.1379, + "epoch": 0.48, + "learning_rate": 2.58229122390998e-05, + "loss": 0.1361, "step": 217240 }, { - "epoch": 0.97, - "learning_rate": 1.5351329536792073e-06, - "loss": 0.1371, + "epoch": 0.48, + "learning_rate": 2.5821793695890473e-05, + "loss": 0.1336, "step": 217250 }, { - "epoch": 0.97, - "learning_rate": 1.5328909017532847e-06, - "loss": 0.1389, + "epoch": 0.48, + "learning_rate": 2.582067515268115e-05, + "loss": 0.1364, "step": 217260 }, { - "epoch": 0.97, - "learning_rate": 1.5306488498273622e-06, - "loss": 0.1394, + "epoch": 0.48, + "learning_rate": 2.5819556609471822e-05, + "loss": 0.1376, "step": 217270 }, { - "epoch": 0.97, - "learning_rate": 1.5284067979014394e-06, - "loss": 0.1353, + "epoch": 0.48, + "learning_rate": 2.58184380662625e-05, + "loss": 0.1337, "step": 217280 }, { - "epoch": 0.97, - "learning_rate": 1.5261647459755168e-06, - "loss": 0.1366, + "epoch": 0.49, + "learning_rate": 2.581731952305318e-05, + "loss": 0.1319, "step": 217290 }, { - "epoch": 0.97, - "learning_rate": 1.5239226940495943e-06, - "loss": 0.1336, + "epoch": 0.49, + "learning_rate": 2.5816200979843853e-05, + "loss": 0.1338, "step": 217300 }, { - "epoch": 0.97, - "learning_rate": 1.5216806421236715e-06, - "loss": 0.1361, + "epoch": 0.49, + "learning_rate": 2.581508243663453e-05, + "loss": 0.1333, "step": 217310 }, { - "epoch": 0.97, - "learning_rate": 1.5194385901977492e-06, - "loss": 0.1356, + "epoch": 0.49, + "learning_rate": 2.5813963893425202e-05, + "loss": 0.1374, "step": 217320 }, { - "epoch": 0.97, - "learning_rate": 1.5171965382718264e-06, - "loss": 0.1359, + "epoch": 0.49, + "learning_rate": 2.581284535021588e-05, + "loss": 0.1386, "step": 217330 }, { - "epoch": 0.97, - "learning_rate": 1.5149544863459039e-06, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.5811726807006554e-05, + "loss": 0.1346, "step": 217340 }, { - "epoch": 0.97, - "learning_rate": 1.5127124344199813e-06, - "loss": 0.1396, + "epoch": 0.49, + "learning_rate": 2.5810608263797232e-05, + "loss": 0.1359, "step": 217350 }, { - "epoch": 0.97, - "learning_rate": 1.5104703824940586e-06, - "loss": 0.1383, + "epoch": 0.49, + "learning_rate": 2.580948972058791e-05, + "loss": 0.1361, "step": 217360 }, { - "epoch": 0.97, - "learning_rate": 1.508228330568136e-06, - "loss": 0.1305, + "epoch": 0.49, + "learning_rate": 2.580837117737858e-05, + "loss": 0.1342, "step": 217370 }, { - "epoch": 0.97, - "learning_rate": 1.5059862786422134e-06, - "loss": 0.1408, + "epoch": 0.49, + "learning_rate": 2.580725263416926e-05, + "loss": 0.131, "step": 217380 }, { - "epoch": 0.97, - "learning_rate": 1.5037442267162909e-06, - "loss": 0.1324, + "epoch": 0.49, + "learning_rate": 2.5806134090959934e-05, + "loss": 0.1348, "step": 217390 }, { - "epoch": 0.97, - "learning_rate": 1.5015021747903683e-06, - "loss": 0.1309, + "epoch": 0.49, + "learning_rate": 2.5805015547750612e-05, + "loss": 0.1356, "step": 217400 }, { - "epoch": 0.97, - "learning_rate": 1.4992601228644456e-06, - "loss": 0.1395, + "epoch": 0.49, + "learning_rate": 2.580389700454129e-05, + "loss": 0.1363, "step": 217410 }, { - "epoch": 0.97, - "learning_rate": 1.497018070938523e-06, - "loss": 0.14, + "epoch": 0.49, + "learning_rate": 2.580277846133196e-05, + "loss": 0.1327, "step": 217420 }, { - "epoch": 0.97, - "learning_rate": 1.4947760190126003e-06, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.580165991812264e-05, + "loss": 0.1332, "step": 217430 }, { - "epoch": 0.97, - "learning_rate": 1.492533967086678e-06, - "loss": 0.1311, + "epoch": 0.49, + "learning_rate": 2.5800541374913313e-05, + "loss": 0.1331, "step": 217440 }, { - "epoch": 0.97, - "learning_rate": 1.4902919151607552e-06, - "loss": 0.1358, + "epoch": 0.49, + "learning_rate": 2.579942283170399e-05, + "loss": 0.1318, "step": 217450 }, { - "epoch": 0.97, - "learning_rate": 1.4880498632348326e-06, - "loss": 0.1346, + "epoch": 0.49, + "learning_rate": 2.579830428849467e-05, + "loss": 0.1356, "step": 217460 }, { - "epoch": 0.97, - "learning_rate": 1.48580781130891e-06, - "loss": 0.139, + "epoch": 0.49, + "learning_rate": 2.579718574528534e-05, + "loss": 0.1337, "step": 217470 }, { - "epoch": 0.97, - "learning_rate": 1.4835657593829873e-06, - "loss": 0.135, + "epoch": 0.49, + "learning_rate": 2.5796067202076018e-05, + "loss": 0.1354, "step": 217480 }, { - "epoch": 0.97, - "learning_rate": 1.4813237074570647e-06, - "loss": 0.1299, + "epoch": 0.49, + "learning_rate": 2.579494865886669e-05, + "loss": 0.1319, "step": 217490 }, { - "epoch": 0.97, - "learning_rate": 1.4790816555311422e-06, - "loss": 0.142, + "epoch": 0.49, + "learning_rate": 2.579383011565737e-05, + "loss": 0.1328, "step": 217500 }, { - "epoch": 0.97, - "learning_rate": 1.4768396036052196e-06, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.579271157244805e-05, + "loss": 0.1352, "step": 217510 }, { - "epoch": 0.97, - "learning_rate": 1.474597551679297e-06, - "loss": 0.1399, + "epoch": 0.49, + "learning_rate": 2.579159302923872e-05, + "loss": 0.1392, "step": 217520 }, { - "epoch": 0.97, - "learning_rate": 1.4723554997533743e-06, - "loss": 0.1333, + "epoch": 0.49, + "learning_rate": 2.5790474486029398e-05, + "loss": 0.1357, "step": 217530 }, { - "epoch": 0.97, - "learning_rate": 1.4701134478274518e-06, - "loss": 0.1375, + "epoch": 0.49, + "learning_rate": 2.578935594282007e-05, + "loss": 0.1327, "step": 217540 }, { - "epoch": 0.97, - "learning_rate": 1.4678713959015292e-06, - "loss": 0.1391, + "epoch": 0.49, + "learning_rate": 2.5788237399610747e-05, + "loss": 0.1346, "step": 217550 }, { - "epoch": 0.97, - "learning_rate": 1.4656293439756064e-06, - "loss": 0.1336, + "epoch": 0.49, + "learning_rate": 2.5787118856401428e-05, + "loss": 0.134, "step": 217560 }, { - "epoch": 0.97, - "learning_rate": 1.463387292049684e-06, - "loss": 0.1381, + "epoch": 0.49, + "learning_rate": 2.57860003131921e-05, + "loss": 0.1389, "step": 217570 }, { - "epoch": 0.97, - "learning_rate": 1.4611452401237613e-06, - "loss": 0.1313, + "epoch": 0.49, + "learning_rate": 2.5784881769982777e-05, + "loss": 0.1331, "step": 217580 }, { - "epoch": 0.97, - "learning_rate": 1.4589031881978388e-06, - "loss": 0.1427, + "epoch": 0.49, + "learning_rate": 2.578376322677345e-05, + "loss": 0.1339, "step": 217590 }, { - "epoch": 0.97, - "learning_rate": 1.456661136271916e-06, - "loss": 0.1318, + "epoch": 0.49, + "learning_rate": 2.5782644683564126e-05, + "loss": 0.1349, "step": 217600 }, { - "epoch": 0.97, - "learning_rate": 1.4544190843459935e-06, - "loss": 0.1353, + "epoch": 0.49, + "learning_rate": 2.5781526140354804e-05, + "loss": 0.137, "step": 217610 }, { - "epoch": 0.97, - "learning_rate": 1.4524012376126632e-06, - "loss": 0.1374, + "epoch": 0.49, + "learning_rate": 2.578040759714548e-05, + "loss": 0.1351, "step": 217620 }, { - "epoch": 0.97, - "learning_rate": 1.4501591856867406e-06, - "loss": 0.137, + "epoch": 0.49, + "learning_rate": 2.5779289053936157e-05, + "loss": 0.1379, "step": 217630 }, { - "epoch": 0.97, - "learning_rate": 1.4479171337608178e-06, - "loss": 0.1373, + "epoch": 0.49, + "learning_rate": 2.5778170510726828e-05, + "loss": 0.1347, "step": 217640 }, { - "epoch": 0.97, - "learning_rate": 1.4456750818348955e-06, - "loss": 0.1374, + "epoch": 0.49, + "learning_rate": 2.5777051967517506e-05, + "loss": 0.1375, "step": 217650 }, { - "epoch": 0.97, - "learning_rate": 1.4434330299089727e-06, + "epoch": 0.49, + "learning_rate": 2.577593342430818e-05, "loss": 0.1393, "step": 217660 }, { - "epoch": 0.97, - "learning_rate": 1.4411909779830502e-06, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.5774814881098858e-05, + "loss": 0.1351, "step": 217670 }, { - "epoch": 0.97, - "learning_rate": 1.4389489260571276e-06, - "loss": 0.1351, + "epoch": 0.49, + "learning_rate": 2.5773696337889536e-05, + "loss": 0.1316, "step": 217680 }, { - "epoch": 0.97, - "learning_rate": 1.4367068741312049e-06, - "loss": 0.1268, + "epoch": 0.49, + "learning_rate": 2.5772577794680207e-05, + "loss": 0.135, "step": 217690 }, { - "epoch": 0.97, - "learning_rate": 1.4344648222052823e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5771459251470885e-05, + "loss": 0.1287, "step": 217700 }, { - "epoch": 0.97, - "learning_rate": 1.4322227702793598e-06, - "loss": 0.1366, + "epoch": 0.49, + "learning_rate": 2.577034070826156e-05, + "loss": 0.1318, "step": 217710 }, { - "epoch": 0.97, - "learning_rate": 1.4299807183534372e-06, - "loss": 0.1409, + "epoch": 0.49, + "learning_rate": 2.5769222165052238e-05, + "loss": 0.13, "step": 217720 }, { - "epoch": 0.97, - "learning_rate": 1.4277386664275147e-06, - "loss": 0.1316, + "epoch": 0.49, + "learning_rate": 2.5768103621842916e-05, + "loss": 0.1348, "step": 217730 }, { - "epoch": 0.97, - "learning_rate": 1.4254966145015919e-06, - "loss": 0.1328, + "epoch": 0.49, + "learning_rate": 2.5766985078633587e-05, + "loss": 0.1363, "step": 217740 }, { - "epoch": 0.97, - "learning_rate": 1.4232545625756693e-06, - "loss": 0.1343, + "epoch": 0.49, + "learning_rate": 2.5765866535424265e-05, + "loss": 0.1378, "step": 217750 }, { - "epoch": 0.97, - "learning_rate": 1.4210125106497466e-06, - "loss": 0.1338, + "epoch": 0.49, + "learning_rate": 2.576474799221494e-05, + "loss": 0.1407, "step": 217760 }, { - "epoch": 0.97, - "learning_rate": 1.418770458723824e-06, - "loss": 0.1408, + "epoch": 0.49, + "learning_rate": 2.5763629449005617e-05, + "loss": 0.1381, "step": 217770 }, { - "epoch": 0.97, - "learning_rate": 1.4165284067979015e-06, - "loss": 0.1343, + "epoch": 0.49, + "learning_rate": 2.5762510905796295e-05, + "loss": 0.1319, "step": 217780 }, { - "epoch": 0.97, - "learning_rate": 1.414286354871979e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5761392362586966e-05, + "loss": 0.1351, "step": 217790 }, { - "epoch": 0.97, - "learning_rate": 1.4120443029460564e-06, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.5760273819377644e-05, + "loss": 0.132, "step": 217800 }, { - "epoch": 0.97, - "learning_rate": 1.4098022510201336e-06, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.575915527616832e-05, + "loss": 0.1319, "step": 217810 }, { - "epoch": 0.97, - "learning_rate": 1.407560199094211e-06, - "loss": 0.1447, + "epoch": 0.49, + "learning_rate": 2.5758036732958997e-05, + "loss": 0.1329, "step": 217820 }, { - "epoch": 0.97, - "learning_rate": 1.4053181471682885e-06, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.5756918189749675e-05, + "loss": 0.1338, "step": 217830 }, { - "epoch": 0.97, - "learning_rate": 1.403076095242366e-06, - "loss": 0.131, + "epoch": 0.49, + "learning_rate": 2.5755799646540346e-05, + "loss": 0.1397, "step": 217840 }, { - "epoch": 0.97, - "learning_rate": 1.4008340433164434e-06, - "loss": 0.133, + "epoch": 0.49, + "learning_rate": 2.5754681103331024e-05, + "loss": 0.1355, "step": 217850 }, { - "epoch": 0.97, - "learning_rate": 1.3985919913905206e-06, - "loss": 0.135, + "epoch": 0.49, + "learning_rate": 2.5753562560121698e-05, + "loss": 0.1344, "step": 217860 }, { - "epoch": 0.97, - "learning_rate": 1.396349939464598e-06, - "loss": 0.1359, + "epoch": 0.49, + "learning_rate": 2.5752555871233307e-05, + "loss": 0.1303, "step": 217870 }, { - "epoch": 0.97, - "learning_rate": 1.3941078875386755e-06, - "loss": 0.1326, + "epoch": 0.49, + "learning_rate": 2.575143732802398e-05, + "loss": 0.1331, "step": 217880 }, { - "epoch": 0.97, - "learning_rate": 1.3918658356127528e-06, - "loss": 0.132, + "epoch": 0.49, + "learning_rate": 2.575031878481466e-05, + "loss": 0.1329, "step": 217890 }, { - "epoch": 0.97, - "learning_rate": 1.3896237836868304e-06, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.5749200241605337e-05, + "loss": 0.1315, "step": 217900 }, { - "epoch": 0.97, - "learning_rate": 1.3873817317609076e-06, - "loss": 0.1331, + "epoch": 0.49, + "learning_rate": 2.574808169839601e-05, + "loss": 0.1307, "step": 217910 }, { - "epoch": 0.97, - "learning_rate": 1.385139679834985e-06, - "loss": 0.1297, + "epoch": 0.49, + "learning_rate": 2.5746963155186686e-05, + "loss": 0.1303, "step": 217920 }, { - "epoch": 0.97, - "learning_rate": 1.3828976279090623e-06, - "loss": 0.1433, + "epoch": 0.49, + "learning_rate": 2.574584461197736e-05, + "loss": 0.129, "step": 217930 }, { - "epoch": 0.97, - "learning_rate": 1.3806555759831398e-06, - "loss": 0.1415, + "epoch": 0.49, + "learning_rate": 2.574472606876804e-05, + "loss": 0.1341, "step": 217940 }, { - "epoch": 0.97, - "learning_rate": 1.3784135240572172e-06, - "loss": 0.1345, + "epoch": 0.49, + "learning_rate": 2.5743607525558717e-05, + "loss": 0.1321, "step": 217950 }, { - "epoch": 0.97, - "learning_rate": 1.3761714721312947e-06, - "loss": 0.1308, + "epoch": 0.49, + "learning_rate": 2.5742488982349388e-05, + "loss": 0.1319, "step": 217960 }, { - "epoch": 0.97, - "learning_rate": 1.3739294202053721e-06, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.5741370439140066e-05, + "loss": 0.1343, "step": 217970 }, { - "epoch": 0.97, - "learning_rate": 1.3716873682794494e-06, - "loss": 0.1361, + "epoch": 0.49, + "learning_rate": 2.574025189593074e-05, + "loss": 0.1368, "step": 217980 }, { - "epoch": 0.97, - "learning_rate": 1.3694453163535268e-06, - "loss": 0.1406, + "epoch": 0.49, + "learning_rate": 2.573913335272142e-05, + "loss": 0.1365, "step": 217990 }, { - "epoch": 0.97, - "learning_rate": 1.3672032644276042e-06, - "loss": 0.1398, + "epoch": 0.49, + "learning_rate": 2.5738014809512096e-05, + "loss": 0.1386, "step": 218000 }, { - "epoch": 0.97, - "learning_rate": 1.3649612125016815e-06, - "loss": 0.14, + "epoch": 0.49, + "learning_rate": 2.5736896266302768e-05, + "loss": 0.1424, "step": 218010 }, { - "epoch": 0.97, - "learning_rate": 1.362719160575759e-06, - "loss": 0.1404, + "epoch": 0.49, + "learning_rate": 2.5735777723093445e-05, + "loss": 0.1293, "step": 218020 }, { - "epoch": 0.97, - "learning_rate": 1.3604771086498364e-06, - "loss": 0.1426, + "epoch": 0.49, + "learning_rate": 2.573465917988412e-05, + "loss": 0.1323, "step": 218030 }, { - "epoch": 0.97, - "learning_rate": 1.3582350567239138e-06, - "loss": 0.1328, + "epoch": 0.49, + "learning_rate": 2.5733540636674798e-05, + "loss": 0.1336, "step": 218040 }, { - "epoch": 0.97, - "learning_rate": 1.3559930047979913e-06, - "loss": 0.135, + "epoch": 0.49, + "learning_rate": 2.573242209346547e-05, + "loss": 0.1363, "step": 218050 }, { - "epoch": 0.97, - "learning_rate": 1.3537509528720685e-06, - "loss": 0.1343, + "epoch": 0.49, + "learning_rate": 2.5731303550256147e-05, + "loss": 0.1363, "step": 218060 }, { - "epoch": 0.97, - "learning_rate": 1.351508900946146e-06, - "loss": 0.137, + "epoch": 0.49, + "learning_rate": 2.5730185007046825e-05, + "loss": 0.1371, "step": 218070 }, { - "epoch": 0.97, - "learning_rate": 1.3492668490202232e-06, - "loss": 0.1404, + "epoch": 0.49, + "learning_rate": 2.57290664638375e-05, + "loss": 0.1334, "step": 218080 }, { - "epoch": 0.97, - "learning_rate": 1.3470247970943009e-06, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.5727947920628177e-05, + "loss": 0.1406, "step": 218090 }, { - "epoch": 0.97, - "learning_rate": 1.3447827451683783e-06, - "loss": 0.1361, + "epoch": 0.49, + "learning_rate": 2.572682937741885e-05, + "loss": 0.1344, "step": 218100 }, { - "epoch": 0.97, - "learning_rate": 1.3425406932424555e-06, - "loss": 0.1403, + "epoch": 0.49, + "learning_rate": 2.5725710834209526e-05, + "loss": 0.1347, "step": 218110 }, { - "epoch": 0.97, - "learning_rate": 1.340298641316533e-06, - "loss": 0.138, + "epoch": 0.49, + "learning_rate": 2.5724592291000204e-05, + "loss": 0.1312, "step": 218120 }, { - "epoch": 0.97, - "learning_rate": 1.3380565893906102e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5723473747790876e-05, + "loss": 0.1362, "step": 218130 }, { - "epoch": 0.97, - "learning_rate": 1.3358145374646877e-06, - "loss": 0.1391, + "epoch": 0.49, + "learning_rate": 2.5722355204581557e-05, + "loss": 0.1312, "step": 218140 }, { - "epoch": 0.97, - "learning_rate": 1.3335724855387651e-06, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.5721236661372228e-05, + "loss": 0.1327, "step": 218150 }, { - "epoch": 0.97, - "learning_rate": 1.3313304336128426e-06, - "loss": 0.137, + "epoch": 0.49, + "learning_rate": 2.5720118118162906e-05, + "loss": 0.1346, "step": 218160 }, { - "epoch": 0.97, - "learning_rate": 1.32908838168692e-06, - "loss": 0.1315, + "epoch": 0.49, + "learning_rate": 2.5718999574953584e-05, + "loss": 0.1348, "step": 218170 }, { - "epoch": 0.97, - "learning_rate": 1.3268463297609972e-06, - "loss": 0.1352, + "epoch": 0.49, + "learning_rate": 2.5717881031744255e-05, + "loss": 0.1347, "step": 218180 }, { - "epoch": 0.97, - "learning_rate": 1.3246042778350747e-06, - "loss": 0.1337, + "epoch": 0.49, + "learning_rate": 2.5716762488534933e-05, + "loss": 0.1371, "step": 218190 }, { - "epoch": 0.97, - "learning_rate": 1.3223622259091521e-06, - "loss": 0.1333, + "epoch": 0.49, + "learning_rate": 2.5715643945325607e-05, + "loss": 0.1349, "step": 218200 }, { - "epoch": 0.97, - "learning_rate": 1.3201201739832296e-06, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.5714525402116285e-05, + "loss": 0.1382, "step": 218210 }, { - "epoch": 0.97, - "learning_rate": 1.317878122057307e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5713406858906963e-05, + "loss": 0.1337, "step": 218220 }, { - "epoch": 0.97, - "learning_rate": 1.3156360701313843e-06, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.5712288315697634e-05, + "loss": 0.1369, "step": 218230 }, { - "epoch": 0.97, - "learning_rate": 1.3133940182054617e-06, - "loss": 0.1365, + "epoch": 0.49, + "learning_rate": 2.5711169772488312e-05, + "loss": 0.1349, "step": 218240 }, { - "epoch": 0.97, - "learning_rate": 1.3111519662795392e-06, - "loss": 0.1351, + "epoch": 0.49, + "learning_rate": 2.5710051229278987e-05, + "loss": 0.132, "step": 218250 }, { - "epoch": 0.97, - "learning_rate": 1.3089099143536164e-06, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.5708932686069665e-05, + "loss": 0.1321, "step": 218260 }, { - "epoch": 0.97, - "learning_rate": 1.3066678624276938e-06, - "loss": 0.1413, + "epoch": 0.49, + "learning_rate": 2.5707814142860343e-05, + "loss": 0.1307, "step": 218270 }, { - "epoch": 0.97, - "learning_rate": 1.3044258105017713e-06, - "loss": 0.1393, + "epoch": 0.49, + "learning_rate": 2.5706695599651014e-05, + "loss": 0.1371, "step": 218280 }, { - "epoch": 0.97, - "learning_rate": 1.3021837585758487e-06, - "loss": 0.1364, + "epoch": 0.49, + "learning_rate": 2.5705577056441692e-05, + "loss": 0.1426, "step": 218290 }, { - "epoch": 0.97, - "learning_rate": 1.2999417066499262e-06, - "loss": 0.1308, + "epoch": 0.49, + "learning_rate": 2.5704458513232366e-05, + "loss": 0.1322, "step": 218300 }, { - "epoch": 0.97, - "learning_rate": 1.2976996547240034e-06, - "loss": 0.1327, + "epoch": 0.49, + "learning_rate": 2.5703339970023044e-05, + "loss": 0.1346, "step": 218310 }, { - "epoch": 0.97, - "learning_rate": 1.2954576027980809e-06, + "epoch": 0.49, + "learning_rate": 2.5702221426813722e-05, "loss": 0.1359, "step": 218320 }, { - "epoch": 0.97, - "learning_rate": 1.293215550872158e-06, - "loss": 0.137, + "epoch": 0.49, + "learning_rate": 2.5701102883604393e-05, + "loss": 0.1306, "step": 218330 }, { - "epoch": 0.97, - "learning_rate": 1.2909734989462358e-06, - "loss": 0.1304, + "epoch": 0.49, + "learning_rate": 2.569998434039507e-05, + "loss": 0.1316, "step": 218340 }, { - "epoch": 0.97, - "learning_rate": 1.288731447020313e-06, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.5698865797185746e-05, + "loss": 0.1309, "step": 218350 }, { - "epoch": 0.97, - "learning_rate": 1.2864893950943904e-06, - "loss": 0.1383, + "epoch": 0.49, + "learning_rate": 2.5697747253976424e-05, + "loss": 0.1301, "step": 218360 }, { - "epoch": 0.97, - "learning_rate": 1.2842473431684679e-06, - "loss": 0.1327, + "epoch": 0.49, + "learning_rate": 2.5696628710767095e-05, + "loss": 0.1341, "step": 218370 }, { - "epoch": 0.97, - "learning_rate": 1.2820052912425451e-06, - "loss": 0.136, + "epoch": 0.49, + "learning_rate": 2.5695510167557773e-05, + "loss": 0.1302, "step": 218380 }, { - "epoch": 0.97, - "learning_rate": 1.2797632393166226e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.569439162434845e-05, + "loss": 0.1293, "step": 218390 }, { - "epoch": 0.97, - "learning_rate": 1.2775211873907e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.5693273081139125e-05, + "loss": 0.1319, "step": 218400 }, { - "epoch": 0.98, - "learning_rate": 1.2752791354647775e-06, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.5692154537929803e-05, + "loss": 0.133, "step": 218410 }, { - "epoch": 0.98, - "learning_rate": 1.273037083538855e-06, - "loss": 0.1351, + "epoch": 0.49, + "learning_rate": 2.5691035994720474e-05, + "loss": 0.1344, "step": 218420 }, { - "epoch": 0.98, - "learning_rate": 1.2707950316129322e-06, - "loss": 0.1358, + "epoch": 0.49, + "learning_rate": 2.5689917451511152e-05, + "loss": 0.136, "step": 218430 }, { - "epoch": 0.98, - "learning_rate": 1.2685529796870096e-06, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.568879890830183e-05, + "loss": 0.1333, "step": 218440 }, { - "epoch": 0.98, - "learning_rate": 1.266310927761087e-06, - "loss": 0.1368, + "epoch": 0.49, + "learning_rate": 2.5687680365092505e-05, + "loss": 0.1385, "step": 218450 }, { - "epoch": 0.98, - "learning_rate": 1.2640688758351645e-06, - "loss": 0.13, + "epoch": 0.49, + "learning_rate": 2.5686561821883183e-05, + "loss": 0.1387, "step": 218460 }, { - "epoch": 0.98, - "learning_rate": 1.261826823909242e-06, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.5685443278673854e-05, + "loss": 0.1413, "step": 218470 }, { - "epoch": 0.98, - "learning_rate": 1.2595847719833192e-06, - "loss": 0.1366, + "epoch": 0.49, + "learning_rate": 2.5684324735464532e-05, + "loss": 0.1363, "step": 218480 }, { - "epoch": 0.98, - "learning_rate": 1.2573427200573966e-06, - "loss": 0.1369, + "epoch": 0.49, + "learning_rate": 2.568320619225521e-05, + "loss": 0.1338, "step": 218490 }, { - "epoch": 0.98, - "learning_rate": 1.2551006681314739e-06, - "loss": 0.1414, + "epoch": 0.49, + "learning_rate": 2.5682087649045884e-05, + "loss": 0.1366, "step": 218500 }, { - "epoch": 0.98, - "learning_rate": 1.2528586162055513e-06, - "loss": 0.1386, + "epoch": 0.49, + "learning_rate": 2.5680969105836562e-05, + "loss": 0.1329, "step": 218510 }, { - "epoch": 0.98, - "learning_rate": 1.2506165642796288e-06, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.5679850562627233e-05, + "loss": 0.1307, "step": 218520 }, { - "epoch": 0.98, - "learning_rate": 1.2483745123537062e-06, - "loss": 0.1343, + "epoch": 0.49, + "learning_rate": 2.567873201941791e-05, + "loss": 0.139, "step": 218530 }, { - "epoch": 0.98, - "learning_rate": 1.2461324604277836e-06, - "loss": 0.133, + "epoch": 0.49, + "learning_rate": 2.567761347620859e-05, + "loss": 0.1384, "step": 218540 }, { - "epoch": 0.98, - "learning_rate": 1.2438904085018609e-06, - "loss": 0.132, + "epoch": 0.49, + "learning_rate": 2.5676494932999264e-05, + "loss": 0.1322, "step": 218550 }, { - "epoch": 0.98, - "learning_rate": 1.2416483565759383e-06, - "loss": 0.1337, + "epoch": 0.49, + "learning_rate": 2.5675376389789942e-05, + "loss": 0.1371, "step": 218560 }, { - "epoch": 0.98, - "learning_rate": 1.2394063046500158e-06, - "loss": 0.1327, + "epoch": 0.49, + "learning_rate": 2.5674257846580613e-05, + "loss": 0.1312, "step": 218570 }, { - "epoch": 0.98, - "learning_rate": 1.237164252724093e-06, - "loss": 0.139, + "epoch": 0.49, + "learning_rate": 2.567313930337129e-05, + "loss": 0.1361, "step": 218580 }, { - "epoch": 0.98, - "learning_rate": 1.2349222007981707e-06, - "loss": 0.138, + "epoch": 0.49, + "learning_rate": 2.567202076016197e-05, + "loss": 0.1317, "step": 218590 }, { - "epoch": 0.98, - "learning_rate": 1.232680148872248e-06, - "loss": 0.1337, + "epoch": 0.49, + "learning_rate": 2.567090221695264e-05, + "loss": 0.138, "step": 218600 }, { - "epoch": 0.98, - "learning_rate": 1.2304380969463254e-06, - "loss": 0.1337, + "epoch": 0.49, + "learning_rate": 2.5669783673743318e-05, + "loss": 0.1343, "step": 218610 }, { - "epoch": 0.98, - "learning_rate": 1.2281960450204028e-06, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.5668665130533992e-05, + "loss": 0.1338, "step": 218620 }, { - "epoch": 0.98, - "learning_rate": 1.22595399309448e-06, - "loss": 0.1387, + "epoch": 0.49, + "learning_rate": 2.566754658732467e-05, + "loss": 0.1347, "step": 218630 }, { - "epoch": 0.98, - "learning_rate": 1.2237119411685575e-06, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.566642804411534e-05, + "loss": 0.1317, "step": 218640 }, { - "epoch": 0.98, - "learning_rate": 1.221469889242635e-06, - "loss": 0.1376, + "epoch": 0.49, + "learning_rate": 2.566530950090602e-05, + "loss": 0.1347, "step": 218650 }, { - "epoch": 0.98, - "learning_rate": 1.2192278373167124e-06, - "loss": 0.1339, + "epoch": 0.49, + "learning_rate": 2.5664190957696697e-05, + "loss": 0.134, "step": 218660 }, { - "epoch": 0.98, - "learning_rate": 1.2169857853907898e-06, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.5663072414487372e-05, + "loss": 0.1354, "step": 218670 }, { - "epoch": 0.98, - "learning_rate": 1.214743733464867e-06, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.566195387127805e-05, + "loss": 0.1337, "step": 218680 }, { - "epoch": 0.98, - "learning_rate": 1.2125016815389445e-06, - "loss": 0.1369, + "epoch": 0.49, + "learning_rate": 2.566083532806872e-05, + "loss": 0.1352, "step": 218690 }, { - "epoch": 0.98, - "learning_rate": 1.2102596296130217e-06, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.56597167848594e-05, + "loss": 0.1312, "step": 218700 }, { - "epoch": 0.98, - "learning_rate": 1.2080175776870994e-06, - "loss": 0.1326, + "epoch": 0.49, + "learning_rate": 2.5658598241650077e-05, + "loss": 0.1354, "step": 218710 }, { - "epoch": 0.98, - "learning_rate": 1.2057755257611768e-06, - "loss": 0.1313, + "epoch": 0.49, + "learning_rate": 2.565747969844075e-05, + "loss": 0.134, "step": 218720 }, { - "epoch": 0.98, - "learning_rate": 1.203533473835254e-06, - "loss": 0.1357, + "epoch": 0.49, + "learning_rate": 2.565636115523143e-05, + "loss": 0.1344, "step": 218730 }, { - "epoch": 0.98, - "learning_rate": 1.2012914219093315e-06, - "loss": 0.1367, + "epoch": 0.49, + "learning_rate": 2.56552426120221e-05, + "loss": 0.1376, "step": 218740 }, { - "epoch": 0.98, - "learning_rate": 1.1990493699834088e-06, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.5654124068812778e-05, + "loss": 0.1323, "step": 218750 }, { - "epoch": 0.98, - "learning_rate": 1.1968073180574862e-06, - "loss": 0.1472, + "epoch": 0.49, + "learning_rate": 2.5653005525603456e-05, + "loss": 0.1358, "step": 218760 }, { - "epoch": 0.98, - "learning_rate": 1.1945652661315637e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.565188698239413e-05, + "loss": 0.1341, "step": 218770 }, { - "epoch": 0.98, - "learning_rate": 1.1923232142056411e-06, - "loss": 0.1321, + "epoch": 0.49, + "learning_rate": 2.565076843918481e-05, + "loss": 0.1332, "step": 218780 }, { - "epoch": 0.98, - "learning_rate": 1.1900811622797186e-06, - "loss": 0.1361, + "epoch": 0.49, + "learning_rate": 2.564964989597548e-05, + "loss": 0.1374, "step": 218790 }, { - "epoch": 0.98, - "learning_rate": 1.1878391103537958e-06, - "loss": 0.1344, + "epoch": 0.49, + "learning_rate": 2.5648531352766158e-05, + "loss": 0.1346, "step": 218800 }, { - "epoch": 0.98, - "learning_rate": 1.1855970584278732e-06, - "loss": 0.1333, + "epoch": 0.49, + "learning_rate": 2.5647412809556836e-05, + "loss": 0.1347, "step": 218810 }, { - "epoch": 0.98, - "learning_rate": 1.1833550065019507e-06, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.564629426634751e-05, + "loss": 0.1311, "step": 218820 }, { - "epoch": 0.98, - "learning_rate": 1.181112954576028e-06, - "loss": 0.1362, + "epoch": 0.49, + "learning_rate": 2.5645175723138188e-05, + "loss": 0.1352, "step": 218830 }, { - "epoch": 0.98, - "learning_rate": 1.1788709026501056e-06, - "loss": 0.1399, + "epoch": 0.49, + "learning_rate": 2.564405717992886e-05, + "loss": 0.133, "step": 218840 }, { - "epoch": 0.98, - "learning_rate": 1.1766288507241828e-06, - "loss": 0.1399, + "epoch": 0.49, + "learning_rate": 2.5642938636719537e-05, + "loss": 0.1382, "step": 218850 }, { - "epoch": 0.98, - "learning_rate": 1.1743867987982603e-06, - "loss": 0.1374, + "epoch": 0.49, + "learning_rate": 2.5641820093510215e-05, + "loss": 0.1372, "step": 218860 }, { - "epoch": 0.98, - "learning_rate": 1.1721447468723377e-06, - "loss": 0.139, + "epoch": 0.49, + "learning_rate": 2.564070155030089e-05, + "loss": 0.1349, "step": 218870 }, { - "epoch": 0.98, - "learning_rate": 1.169902694946415e-06, - "loss": 0.1398, + "epoch": 0.49, + "learning_rate": 2.5639583007091568e-05, + "loss": 0.1384, "step": 218880 }, { - "epoch": 0.98, - "learning_rate": 1.1676606430204924e-06, - "loss": 0.1401, + "epoch": 0.49, + "learning_rate": 2.563846446388224e-05, + "loss": 0.1312, "step": 218890 }, { - "epoch": 0.98, - "learning_rate": 1.1654185910945698e-06, - "loss": 0.1354, + "epoch": 0.49, + "learning_rate": 2.5637345920672917e-05, + "loss": 0.135, "step": 218900 }, { - "epoch": 0.98, - "learning_rate": 1.1631765391686473e-06, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.5636227377463595e-05, + "loss": 0.136, "step": 218910 }, { - "epoch": 0.98, - "learning_rate": 1.1609344872427245e-06, - "loss": 0.1411, + "epoch": 0.49, + "learning_rate": 2.563510883425427e-05, + "loss": 0.1342, "step": 218920 }, { - "epoch": 0.98, - "learning_rate": 1.158692435316802e-06, - "loss": 0.1337, + "epoch": 0.49, + "learning_rate": 2.5633990291044947e-05, + "loss": 0.1282, "step": 218930 }, { - "epoch": 0.98, - "learning_rate": 1.1564503833908794e-06, - "loss": 0.1326, + "epoch": 0.49, + "learning_rate": 2.5632871747835618e-05, + "loss": 0.132, "step": 218940 }, { - "epoch": 0.98, - "learning_rate": 1.1542083314649567e-06, - "loss": 0.1348, + "epoch": 0.49, + "learning_rate": 2.5631753204626296e-05, + "loss": 0.1345, "step": 218950 }, { - "epoch": 0.98, - "learning_rate": 1.1519662795390343e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.5630634661416967e-05, + "loss": 0.1329, "step": 218960 }, { - "epoch": 0.98, - "learning_rate": 1.1497242276131115e-06, - "loss": 0.1403, + "epoch": 0.49, + "learning_rate": 2.562951611820765e-05, + "loss": 0.1289, "step": 218970 }, { - "epoch": 0.98, - "learning_rate": 1.147482175687189e-06, - "loss": 0.1366, + "epoch": 0.49, + "learning_rate": 2.5628397574998327e-05, + "loss": 0.1395, "step": 218980 }, { - "epoch": 0.98, - "learning_rate": 1.1452401237612664e-06, - "loss": 0.1359, + "epoch": 0.49, + "learning_rate": 2.5627279031788998e-05, + "loss": 0.1372, "step": 218990 }, { - "epoch": 0.98, - "learning_rate": 1.1429980718353437e-06, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.5626160488579676e-05, + "loss": 0.1392, "step": 219000 }, { - "epoch": 0.98, - "learning_rate": 1.1407560199094211e-06, - "loss": 0.1319, + "epoch": 0.49, + "learning_rate": 2.5625041945370347e-05, + "loss": 0.1382, "step": 219010 }, { - "epoch": 0.98, - "learning_rate": 1.1385139679834986e-06, - "loss": 0.1368, + "epoch": 0.49, + "learning_rate": 2.5623923402161025e-05, + "loss": 0.1366, "step": 219020 }, { - "epoch": 0.98, - "learning_rate": 1.136271916057576e-06, - "loss": 0.1322, + "epoch": 0.49, + "learning_rate": 2.5622804858951706e-05, + "loss": 0.1325, "step": 219030 }, { - "epoch": 0.98, - "learning_rate": 1.1340298641316535e-06, - "loss": 0.1407, + "epoch": 0.49, + "learning_rate": 2.5621686315742377e-05, + "loss": 0.1362, "step": 219040 }, { - "epoch": 0.98, - "learning_rate": 1.1317878122057307e-06, - "loss": 0.1356, + "epoch": 0.49, + "learning_rate": 2.5620567772533055e-05, + "loss": 0.1344, "step": 219050 }, { - "epoch": 0.98, - "learning_rate": 1.1295457602798081e-06, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.5619449229323726e-05, + "loss": 0.1361, "step": 219060 }, { - "epoch": 0.98, - "learning_rate": 1.1273037083538854e-06, - "loss": 0.1359, + "epoch": 0.49, + "learning_rate": 2.5618330686114404e-05, + "loss": 0.1314, "step": 219070 }, { - "epoch": 0.98, - "learning_rate": 1.1250616564279628e-06, - "loss": 0.1422, + "epoch": 0.49, + "learning_rate": 2.5617212142905082e-05, + "loss": 0.1349, "step": 219080 }, { - "epoch": 0.98, - "learning_rate": 1.1228196045020405e-06, - "loss": 0.135, + "epoch": 0.49, + "learning_rate": 2.5616093599695757e-05, + "loss": 0.1339, "step": 219090 }, { - "epoch": 0.98, - "learning_rate": 1.1205775525761177e-06, - "loss": 0.1367, + "epoch": 0.49, + "learning_rate": 2.5614975056486435e-05, + "loss": 0.1341, "step": 219100 }, { - "epoch": 0.98, - "learning_rate": 1.1183355006501952e-06, - "loss": 0.1406, + "epoch": 0.49, + "learning_rate": 2.5613856513277106e-05, + "loss": 0.1316, "step": 219110 }, { - "epoch": 0.98, - "learning_rate": 1.1160934487242724e-06, - "loss": 0.139, + "epoch": 0.49, + "learning_rate": 2.5612737970067784e-05, + "loss": 0.1369, "step": 219120 }, { - "epoch": 0.98, - "learning_rate": 1.1138513967983499e-06, - "loss": 0.1374, + "epoch": 0.49, + "learning_rate": 2.561161942685846e-05, + "loss": 0.1313, "step": 219130 }, { - "epoch": 0.98, - "learning_rate": 1.1116093448724273e-06, - "loss": 0.1408, + "epoch": 0.49, + "learning_rate": 2.5610500883649136e-05, + "loss": 0.1394, "step": 219140 }, { - "epoch": 0.98, - "learning_rate": 1.1093672929465047e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5609382340439814e-05, + "loss": 0.1405, "step": 219150 }, { - "epoch": 0.98, - "learning_rate": 1.1071252410205822e-06, - "loss": 0.1369, + "epoch": 0.49, + "learning_rate": 2.5608263797230485e-05, + "loss": 0.1337, "step": 219160 }, { - "epoch": 0.98, - "learning_rate": 1.1048831890946594e-06, - "loss": 0.1324, + "epoch": 0.49, + "learning_rate": 2.5607145254021163e-05, + "loss": 0.1299, "step": 219170 }, { - "epoch": 0.98, - "learning_rate": 1.1026411371687369e-06, - "loss": 0.1368, + "epoch": 0.49, + "learning_rate": 2.560602671081184e-05, + "loss": 0.1313, "step": 219180 }, { - "epoch": 0.98, - "learning_rate": 1.1003990852428143e-06, - "loss": 0.1332, + "epoch": 0.49, + "learning_rate": 2.5604908167602516e-05, + "loss": 0.1322, "step": 219190 }, { - "epoch": 0.98, - "learning_rate": 1.0981570333168916e-06, - "loss": 0.1301, + "epoch": 0.49, + "learning_rate": 2.5603789624393194e-05, + "loss": 0.1359, "step": 219200 }, { - "epoch": 0.98, - "learning_rate": 1.0959149813909692e-06, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.5602671081183865e-05, + "loss": 0.1304, "step": 219210 }, { - "epoch": 0.98, - "learning_rate": 1.0936729294650465e-06, - "loss": 0.1407, + "epoch": 0.49, + "learning_rate": 2.5601552537974543e-05, + "loss": 0.1389, "step": 219220 }, { - "epoch": 0.98, - "learning_rate": 1.091430877539124e-06, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.560043399476522e-05, + "loss": 0.1347, "step": 219230 }, { - "epoch": 0.98, - "learning_rate": 1.0891888256132013e-06, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.5599315451555895e-05, + "loss": 0.134, "step": 219240 }, { - "epoch": 0.98, - "learning_rate": 1.0869467736872786e-06, - "loss": 0.1353, + "epoch": 0.49, + "learning_rate": 2.5598196908346573e-05, + "loss": 0.1344, "step": 219250 }, { - "epoch": 0.98, - "learning_rate": 1.084704721761356e-06, - "loss": 0.1385, + "epoch": 0.49, + "learning_rate": 2.5597078365137244e-05, + "loss": 0.1332, "step": 219260 }, { - "epoch": 0.98, - "learning_rate": 1.0824626698354333e-06, - "loss": 0.1385, + "epoch": 0.49, + "learning_rate": 2.5595959821927922e-05, + "loss": 0.1373, "step": 219270 }, { - "epoch": 0.98, - "learning_rate": 1.080220617909511e-06, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.5594841278718597e-05, + "loss": 0.1289, "step": 219280 }, { - "epoch": 0.98, - "learning_rate": 1.0779785659835884e-06, - "loss": 0.1397, + "epoch": 0.49, + "learning_rate": 2.5593722735509275e-05, + "loss": 0.1332, "step": 219290 }, { - "epoch": 0.98, - "learning_rate": 1.0757365140576656e-06, - "loss": 0.1322, + "epoch": 0.49, + "learning_rate": 2.5592604192299953e-05, + "loss": 0.1384, "step": 219300 }, { - "epoch": 0.98, - "learning_rate": 1.073494462131743e-06, - "loss": 0.1408, + "epoch": 0.49, + "learning_rate": 2.5591485649090624e-05, + "loss": 0.132, "step": 219310 }, { - "epoch": 0.98, - "learning_rate": 1.0712524102058203e-06, - "loss": 0.1356, + "epoch": 0.49, + "learning_rate": 2.55903671058813e-05, + "loss": 0.132, "step": 219320 }, { - "epoch": 0.98, - "learning_rate": 1.0690103582798977e-06, - "loss": 0.1392, + "epoch": 0.49, + "learning_rate": 2.5589248562671976e-05, + "loss": 0.1284, "step": 219330 }, { - "epoch": 0.98, - "learning_rate": 1.0667683063539752e-06, - "loss": 0.1374, + "epoch": 0.49, + "learning_rate": 2.5588130019462654e-05, + "loss": 0.1328, "step": 219340 }, { - "epoch": 0.98, - "learning_rate": 1.0645262544280526e-06, - "loss": 0.1328, + "epoch": 0.49, + "learning_rate": 2.5587011476253332e-05, + "loss": 0.1318, "step": 219350 }, { - "epoch": 0.98, - "learning_rate": 1.06228420250213e-06, + "epoch": 0.49, + "learning_rate": 2.5585892933044003e-05, "loss": 0.139, "step": 219360 }, { - "epoch": 0.98, - "learning_rate": 1.0600421505762073e-06, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.558477438983468e-05, + "loss": 0.1312, "step": 219370 }, { - "epoch": 0.98, - "learning_rate": 1.0578000986502848e-06, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.5583655846625356e-05, + "loss": 0.1351, "step": 219380 }, { - "epoch": 0.98, - "learning_rate": 1.0555580467243622e-06, - "loss": 0.13, + "epoch": 0.49, + "learning_rate": 2.5582537303416034e-05, + "loss": 0.1367, "step": 219390 }, { - "epoch": 0.98, - "learning_rate": 1.0533159947984397e-06, - "loss": 0.1415, + "epoch": 0.49, + "learning_rate": 2.558141876020671e-05, + "loss": 0.1344, "step": 219400 }, { - "epoch": 0.98, - "learning_rate": 1.051073942872517e-06, - "loss": 0.1416, + "epoch": 0.49, + "learning_rate": 2.5580300216997383e-05, + "loss": 0.1374, "step": 219410 }, { - "epoch": 0.98, - "learning_rate": 1.0488318909465943e-06, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.557918167378806e-05, + "loss": 0.1314, "step": 219420 }, { - "epoch": 0.98, - "learning_rate": 1.0465898390206718e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.5578063130578732e-05, + "loss": 0.1333, "step": 219430 }, { - "epoch": 0.98, - "learning_rate": 1.0443477870947492e-06, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.5576944587369413e-05, + "loss": 0.1353, "step": 219440 }, { - "epoch": 0.98, - "learning_rate": 1.0421057351688265e-06, - "loss": 0.1338, + "epoch": 0.49, + "learning_rate": 2.557582604416009e-05, + "loss": 0.1348, "step": 219450 }, { - "epoch": 0.98, - "learning_rate": 1.039863683242904e-06, - "loss": 0.1375, + "epoch": 0.49, + "learning_rate": 2.5574707500950762e-05, + "loss": 0.1413, "step": 219460 }, { - "epoch": 0.98, - "learning_rate": 1.0376216313169814e-06, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.557358895774144e-05, + "loss": 0.1348, "step": 219470 }, { - "epoch": 0.98, - "learning_rate": 1.0353795793910588e-06, - "loss": 0.1397, + "epoch": 0.49, + "learning_rate": 2.557247041453211e-05, + "loss": 0.1342, "step": 219480 }, { - "epoch": 0.98, - "learning_rate": 1.033137527465136e-06, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.557135187132279e-05, + "loss": 0.1352, "step": 219490 }, { - "epoch": 0.98, - "learning_rate": 1.0308954755392135e-06, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.557023332811347e-05, + "loss": 0.133, "step": 219500 }, { - "epoch": 0.98, - "learning_rate": 1.028653423613291e-06, - "loss": 0.1355, + "epoch": 0.49, + "learning_rate": 2.556911478490414e-05, + "loss": 0.1372, "step": 219510 }, { - "epoch": 0.98, - "learning_rate": 1.0264113716873682e-06, - "loss": 0.137, + "epoch": 0.49, + "learning_rate": 2.556799624169482e-05, + "loss": 0.1374, "step": 219520 }, { - "epoch": 0.98, - "learning_rate": 1.0241693197614458e-06, - "loss": 0.1414, + "epoch": 0.49, + "learning_rate": 2.556687769848549e-05, + "loss": 0.1322, "step": 219530 }, { - "epoch": 0.98, - "learning_rate": 1.021927267835523e-06, - "loss": 0.1373, + "epoch": 0.49, + "learning_rate": 2.556575915527617e-05, + "loss": 0.1305, "step": 219540 }, { - "epoch": 0.98, - "learning_rate": 1.0196852159096005e-06, - "loss": 0.1345, + "epoch": 0.49, + "learning_rate": 2.5564640612066846e-05, + "loss": 0.1301, "step": 219550 }, { - "epoch": 0.98, - "learning_rate": 1.017443163983678e-06, - "loss": 0.1354, + "epoch": 0.49, + "learning_rate": 2.556352206885752e-05, + "loss": 0.1355, "step": 219560 }, { - "epoch": 0.98, - "learning_rate": 1.0152011120577552e-06, - "loss": 0.1387, + "epoch": 0.49, + "learning_rate": 2.55624035256482e-05, + "loss": 0.1365, "step": 219570 }, { - "epoch": 0.98, - "learning_rate": 1.0129590601318326e-06, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.556128498243887e-05, + "loss": 0.1339, "step": 219580 }, { - "epoch": 0.98, - "learning_rate": 1.01071700820591e-06, - "loss": 0.1323, + "epoch": 0.49, + "learning_rate": 2.5560166439229548e-05, + "loss": 0.1327, "step": 219590 }, { - "epoch": 0.98, - "learning_rate": 1.0084749562799875e-06, - "loss": 0.1386, + "epoch": 0.49, + "learning_rate": 2.5559047896020223e-05, + "loss": 0.1336, "step": 219600 }, { - "epoch": 0.98, - "learning_rate": 1.006232904354065e-06, - "loss": 0.1338, + "epoch": 0.49, + "learning_rate": 2.55579293528109e-05, + "loss": 0.1333, "step": 219610 }, { - "epoch": 0.98, - "learning_rate": 1.0042150576207347e-06, - "loss": 0.1369, + "epoch": 0.49, + "learning_rate": 2.555681080960158e-05, + "loss": 0.1368, "step": 219620 }, { - "epoch": 0.98, - "learning_rate": 1.001973005694812e-06, - "loss": 0.1349, + "epoch": 0.49, + "learning_rate": 2.555569226639225e-05, + "loss": 0.1365, "step": 219630 }, { - "epoch": 0.98, - "learning_rate": 9.997309537688894e-07, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.5554573723182928e-05, + "loss": 0.1273, "step": 219640 }, { - "epoch": 0.98, - "learning_rate": 9.974889018429666e-07, - "loss": 0.1361, + "epoch": 0.49, + "learning_rate": 2.5553455179973602e-05, + "loss": 0.1341, "step": 219650 }, { - "epoch": 0.98, - "learning_rate": 9.95246849917044e-07, - "loss": 0.1397, + "epoch": 0.49, + "learning_rate": 2.555233663676428e-05, + "loss": 0.133, "step": 219660 }, { - "epoch": 0.98, - "learning_rate": 9.930047979911215e-07, - "loss": 0.1324, + "epoch": 0.49, + "learning_rate": 2.5551218093554958e-05, + "loss": 0.1328, "step": 219670 }, { - "epoch": 0.98, - "learning_rate": 9.90762746065199e-07, - "loss": 0.1343, + "epoch": 0.49, + "learning_rate": 2.555009955034563e-05, + "loss": 0.1354, "step": 219680 }, { - "epoch": 0.98, - "learning_rate": 9.885206941392764e-07, - "loss": 0.1411, + "epoch": 0.49, + "learning_rate": 2.5548981007136307e-05, + "loss": 0.1371, "step": 219690 }, { - "epoch": 0.98, - "learning_rate": 9.862786422133536e-07, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.554786246392698e-05, + "loss": 0.1371, "step": 219700 }, { - "epoch": 0.98, - "learning_rate": 9.84036590287431e-07, - "loss": 0.134, + "epoch": 0.49, + "learning_rate": 2.554674392071766e-05, + "loss": 0.1359, "step": 219710 }, { - "epoch": 0.98, - "learning_rate": 9.817945383615085e-07, - "loss": 0.1419, + "epoch": 0.49, + "learning_rate": 2.5545625377508337e-05, + "loss": 0.1349, "step": 219720 }, { - "epoch": 0.98, - "learning_rate": 9.795524864355858e-07, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.554450683429901e-05, + "loss": 0.1349, "step": 219730 }, { - "epoch": 0.98, - "learning_rate": 9.773104345096634e-07, - "loss": 0.1358, + "epoch": 0.49, + "learning_rate": 2.5543388291089686e-05, + "loss": 0.1355, "step": 219740 }, { - "epoch": 0.98, - "learning_rate": 9.750683825837407e-07, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.554226974788036e-05, + "loss": 0.1369, "step": 219750 }, { - "epoch": 0.98, - "learning_rate": 9.728263306578181e-07, - "loss": 0.1326, + "epoch": 0.49, + "learning_rate": 2.554115120467104e-05, + "loss": 0.1344, "step": 219760 }, { - "epoch": 0.98, - "learning_rate": 9.705842787318956e-07, - "loss": 0.1336, + "epoch": 0.49, + "learning_rate": 2.5540032661461717e-05, + "loss": 0.1338, "step": 219770 }, { - "epoch": 0.98, - "learning_rate": 9.683422268059728e-07, - "loss": 0.1387, + "epoch": 0.49, + "learning_rate": 2.5538914118252388e-05, + "loss": 0.1328, "step": 219780 }, { - "epoch": 0.98, - "learning_rate": 9.661001748800502e-07, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.5537795575043066e-05, + "loss": 0.1306, "step": 219790 }, { - "epoch": 0.98, - "learning_rate": 9.638581229541277e-07, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.553667703183374e-05, + "loss": 0.1351, "step": 219800 }, { - "epoch": 0.98, - "learning_rate": 9.616160710282051e-07, - "loss": 0.1306, + "epoch": 0.49, + "learning_rate": 2.553555848862442e-05, + "loss": 0.131, "step": 219810 }, { - "epoch": 0.98, - "learning_rate": 9.593740191022824e-07, - "loss": 0.1397, + "epoch": 0.49, + "learning_rate": 2.5534439945415096e-05, + "loss": 0.1347, "step": 219820 }, { - "epoch": 0.98, - "learning_rate": 9.571319671763598e-07, - "loss": 0.1424, + "epoch": 0.49, + "learning_rate": 2.5533321402205767e-05, + "loss": 0.135, "step": 219830 }, { - "epoch": 0.98, - "learning_rate": 9.548899152504373e-07, - "loss": 0.1346, + "epoch": 0.49, + "learning_rate": 2.5532202858996445e-05, + "loss": 0.132, "step": 219840 }, { - "epoch": 0.98, - "learning_rate": 9.526478633245146e-07, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5531084315787117e-05, + "loss": 0.1318, "step": 219850 }, { - "epoch": 0.98, - "learning_rate": 9.504058113985922e-07, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.5529965772577798e-05, + "loss": 0.1321, "step": 219860 }, { - "epoch": 0.98, - "learning_rate": 9.481637594726695e-07, - "loss": 0.1372, + "epoch": 0.49, + "learning_rate": 2.5528847229368476e-05, + "loss": 0.1379, "step": 219870 }, { - "epoch": 0.98, - "learning_rate": 9.459217075467468e-07, - "loss": 0.1393, + "epoch": 0.49, + "learning_rate": 2.5527728686159147e-05, + "loss": 0.1351, "step": 219880 }, { - "epoch": 0.98, - "learning_rate": 9.436796556208242e-07, - "loss": 0.1376, + "epoch": 0.49, + "learning_rate": 2.5526610142949825e-05, + "loss": 0.1345, "step": 219890 }, { - "epoch": 0.98, - "learning_rate": 9.414376036949016e-07, - "loss": 0.1342, + "epoch": 0.49, + "learning_rate": 2.5525491599740496e-05, + "loss": 0.1354, "step": 219900 }, { - "epoch": 0.98, - "learning_rate": 9.39195551768979e-07, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.5524373056531174e-05, + "loss": 0.134, "step": 219910 }, { - "epoch": 0.98, - "learning_rate": 9.369534998430565e-07, - "loss": 0.1349, + "epoch": 0.49, + "learning_rate": 2.552325451332185e-05, + "loss": 0.1386, "step": 219920 }, { - "epoch": 0.98, - "learning_rate": 9.347114479171339e-07, - "loss": 0.1338, + "epoch": 0.49, + "learning_rate": 2.5522135970112526e-05, + "loss": 0.1321, "step": 219930 }, { - "epoch": 0.98, - "learning_rate": 9.324693959912112e-07, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.5521017426903204e-05, + "loss": 0.135, "step": 219940 }, { - "epoch": 0.98, - "learning_rate": 9.302273440652885e-07, - "loss": 0.1334, + "epoch": 0.49, + "learning_rate": 2.5519898883693876e-05, + "loss": 0.136, "step": 219950 }, { - "epoch": 0.98, - "learning_rate": 9.27985292139366e-07, - "loss": 0.1308, + "epoch": 0.49, + "learning_rate": 2.5518780340484553e-05, + "loss": 0.131, "step": 219960 }, { - "epoch": 0.98, - "learning_rate": 9.257432402134433e-07, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.5517661797275228e-05, + "loss": 0.1353, "step": 219970 }, { - "epoch": 0.98, - "learning_rate": 9.235011882875207e-07, - "loss": 0.1327, + "epoch": 0.49, + "learning_rate": 2.5516543254065906e-05, + "loss": 0.1309, "step": 219980 }, { - "epoch": 0.98, - "learning_rate": 9.212591363615982e-07, - "loss": 0.1364, + "epoch": 0.49, + "learning_rate": 2.5515424710856584e-05, + "loss": 0.1334, "step": 219990 }, { - "epoch": 0.98, - "learning_rate": 9.190170844356756e-07, - "loss": 0.1332, + "epoch": 0.49, + "learning_rate": 2.5514306167647255e-05, + "loss": 0.1289, "step": 220000 }, { - "epoch": 0.98, - "learning_rate": 9.16775032509753e-07, - "loss": 0.1371, + "epoch": 0.49, + "learning_rate": 2.5513187624437933e-05, + "loss": 0.1362, "step": 220010 }, { - "epoch": 0.98, - "learning_rate": 9.145329805838304e-07, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.5512069081228607e-05, + "loss": 0.1324, "step": 220020 }, { - "epoch": 0.98, - "learning_rate": 9.122909286579077e-07, - "loss": 0.1341, + "epoch": 0.49, + "learning_rate": 2.5510950538019285e-05, + "loss": 0.1355, "step": 220030 }, { - "epoch": 0.98, - "learning_rate": 9.10048876731985e-07, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.5509831994809963e-05, + "loss": 0.13, "step": 220040 }, { - "epoch": 0.98, - "learning_rate": 9.078068248060626e-07, - "loss": 0.1363, + "epoch": 0.49, + "learning_rate": 2.5508713451600634e-05, + "loss": 0.133, "step": 220050 }, { - "epoch": 0.98, - "learning_rate": 9.0556477288014e-07, - "loss": 0.1347, + "epoch": 0.49, + "learning_rate": 2.5507594908391312e-05, + "loss": 0.1342, "step": 220060 }, { - "epoch": 0.98, - "learning_rate": 9.033227209542174e-07, - "loss": 0.1314, + "epoch": 0.49, + "learning_rate": 2.5506476365181987e-05, + "loss": 0.1317, "step": 220070 }, { - "epoch": 0.98, - "learning_rate": 9.010806690282947e-07, - "loss": 0.1379, + "epoch": 0.49, + "learning_rate": 2.5505357821972665e-05, + "loss": 0.1363, "step": 220080 }, { - "epoch": 0.98, - "learning_rate": 8.988386171023721e-07, - "loss": 0.1391, + "epoch": 0.49, + "learning_rate": 2.5504239278763343e-05, + "loss": 0.1322, "step": 220090 }, { - "epoch": 0.98, - "learning_rate": 8.965965651764495e-07, - "loss": 0.1402, + "epoch": 0.49, + "learning_rate": 2.5503120735554014e-05, + "loss": 0.1322, "step": 220100 }, { - "epoch": 0.98, - "learning_rate": 8.94354513250527e-07, - "loss": 0.1409, + "epoch": 0.49, + "learning_rate": 2.5502002192344692e-05, + "loss": 0.1341, "step": 220110 }, { - "epoch": 0.98, - "learning_rate": 8.921124613246044e-07, - "loss": 0.1354, + "epoch": 0.49, + "learning_rate": 2.5500883649135366e-05, + "loss": 0.1346, "step": 220120 }, { - "epoch": 0.98, - "learning_rate": 8.898704093986817e-07, - "loss": 0.133, + "epoch": 0.49, + "learning_rate": 2.5499765105926044e-05, + "loss": 0.137, "step": 220130 }, { - "epoch": 0.98, - "learning_rate": 8.876283574727591e-07, - "loss": 0.1385, + "epoch": 0.49, + "learning_rate": 2.5498646562716722e-05, + "loss": 0.1296, "step": 220140 }, { - "epoch": 0.98, - "learning_rate": 8.853863055468364e-07, - "loss": 0.1356, + "epoch": 0.49, + "learning_rate": 2.5497528019507393e-05, + "loss": 0.1289, "step": 220150 }, { - "epoch": 0.98, - "learning_rate": 8.831442536209139e-07, - "loss": 0.1355, + "epoch": 0.49, + "learning_rate": 2.549640947629807e-05, + "loss": 0.1322, "step": 220160 }, { - "epoch": 0.98, - "learning_rate": 8.809022016949914e-07, - "loss": 0.1356, + "epoch": 0.49, + "learning_rate": 2.5495290933088746e-05, + "loss": 0.1354, "step": 220170 }, { - "epoch": 0.98, - "learning_rate": 8.786601497690688e-07, - "loss": 0.1365, + "epoch": 0.49, + "learning_rate": 2.5494172389879424e-05, + "loss": 0.1327, "step": 220180 }, { - "epoch": 0.98, - "learning_rate": 8.764180978431461e-07, - "loss": 0.1392, + "epoch": 0.49, + "learning_rate": 2.5493053846670102e-05, + "loss": 0.1305, "step": 220190 }, { - "epoch": 0.98, - "learning_rate": 8.741760459172235e-07, - "loss": 0.1363, + "epoch": 0.49, + "learning_rate": 2.5491935303460773e-05, + "loss": 0.1344, "step": 220200 }, { - "epoch": 0.98, - "learning_rate": 8.719339939913009e-07, - "loss": 0.1345, + "epoch": 0.49, + "learning_rate": 2.549081676025145e-05, + "loss": 0.1338, "step": 220210 }, { - "epoch": 0.98, - "learning_rate": 8.696919420653782e-07, - "loss": 0.1353, + "epoch": 0.49, + "learning_rate": 2.5489698217042125e-05, + "loss": 0.1302, "step": 220220 }, { - "epoch": 0.98, - "learning_rate": 8.674498901394556e-07, - "loss": 0.1312, + "epoch": 0.49, + "learning_rate": 2.5488579673832803e-05, + "loss": 0.1363, "step": 220230 }, { - "epoch": 0.98, - "learning_rate": 8.652078382135331e-07, - "loss": 0.1426, + "epoch": 0.49, + "learning_rate": 2.5487461130623474e-05, + "loss": 0.1364, "step": 220240 }, { - "epoch": 0.98, - "learning_rate": 8.629657862876105e-07, - "loss": 0.1438, + "epoch": 0.49, + "learning_rate": 2.5486342587414152e-05, + "loss": 0.1333, "step": 220250 }, { - "epoch": 0.98, - "learning_rate": 8.607237343616878e-07, - "loss": 0.1375, + "epoch": 0.49, + "learning_rate": 2.548522404420483e-05, + "loss": 0.1376, "step": 220260 }, { - "epoch": 0.98, - "learning_rate": 8.584816824357653e-07, - "loss": 0.1363, + "epoch": 0.49, + "learning_rate": 2.5484105500995505e-05, + "loss": 0.1331, "step": 220270 }, { - "epoch": 0.98, - "learning_rate": 8.562396305098426e-07, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.5482986957786183e-05, + "loss": 0.1291, "step": 220280 }, { - "epoch": 0.98, - "learning_rate": 8.5399757858392e-07, - "loss": 0.1357, + "epoch": 0.49, + "learning_rate": 2.5481868414576854e-05, + "loss": 0.133, "step": 220290 }, { - "epoch": 0.98, - "learning_rate": 8.517555266579975e-07, - "loss": 0.1384, + "epoch": 0.49, + "learning_rate": 2.5480749871367532e-05, + "loss": 0.1327, "step": 220300 }, { - "epoch": 0.98, - "learning_rate": 8.495134747320748e-07, - "loss": 0.1401, + "epoch": 0.49, + "learning_rate": 2.547963132815821e-05, + "loss": 0.1347, "step": 220310 }, { - "epoch": 0.98, - "learning_rate": 8.472714228061523e-07, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.547851278494888e-05, + "loss": 0.1356, "step": 220320 }, { - "epoch": 0.98, - "learning_rate": 8.450293708802296e-07, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.5477394241739562e-05, + "loss": 0.13, "step": 220330 }, { - "epoch": 0.98, - "learning_rate": 8.42787318954307e-07, - "loss": 0.1353, + "epoch": 0.49, + "learning_rate": 2.5476275698530233e-05, + "loss": 0.1335, "step": 220340 }, { - "epoch": 0.98, - "learning_rate": 8.405452670283843e-07, - "loss": 0.1329, + "epoch": 0.49, + "learning_rate": 2.547515715532091e-05, + "loss": 0.134, "step": 220350 }, { - "epoch": 0.98, - "learning_rate": 8.383032151024619e-07, - "loss": 0.14, + "epoch": 0.49, + "learning_rate": 2.547403861211159e-05, + "loss": 0.1366, "step": 220360 }, { - "epoch": 0.98, - "learning_rate": 8.360611631765392e-07, - "loss": 0.1332, + "epoch": 0.49, + "learning_rate": 2.547292006890226e-05, + "loss": 0.128, "step": 220370 }, { - "epoch": 0.98, - "learning_rate": 8.338191112506167e-07, - "loss": 0.132, + "epoch": 0.49, + "learning_rate": 2.547180152569294e-05, + "loss": 0.1351, "step": 220380 }, { - "epoch": 0.98, - "learning_rate": 8.31577059324694e-07, - "loss": 0.1405, + "epoch": 0.49, + "learning_rate": 2.5470682982483613e-05, + "loss": 0.1332, "step": 220390 }, { - "epoch": 0.98, - "learning_rate": 8.293350073987713e-07, - "loss": 0.1382, + "epoch": 0.49, + "learning_rate": 2.546956443927429e-05, + "loss": 0.1353, "step": 220400 }, { - "epoch": 0.98, - "learning_rate": 8.270929554728487e-07, - "loss": 0.1412, + "epoch": 0.49, + "learning_rate": 2.546844589606497e-05, + "loss": 0.1347, "step": 220410 }, { - "epoch": 0.98, - "learning_rate": 8.248509035469262e-07, - "loss": 0.1367, + "epoch": 0.49, + "learning_rate": 2.546732735285564e-05, + "loss": 0.1315, "step": 220420 }, { - "epoch": 0.98, - "learning_rate": 8.226088516210037e-07, - "loss": 0.1408, + "epoch": 0.49, + "learning_rate": 2.5466208809646318e-05, + "loss": 0.1288, "step": 220430 }, { - "epoch": 0.98, - "learning_rate": 8.20366799695081e-07, - "loss": 0.1368, + "epoch": 0.49, + "learning_rate": 2.5465090266436992e-05, + "loss": 0.1339, "step": 220440 }, { - "epoch": 0.98, - "learning_rate": 8.181247477691584e-07, - "loss": 0.1438, + "epoch": 0.49, + "learning_rate": 2.546397172322767e-05, + "loss": 0.1346, "step": 220450 }, { - "epoch": 0.98, - "learning_rate": 8.158826958432357e-07, - "loss": 0.1394, + "epoch": 0.49, + "learning_rate": 2.5462853180018348e-05, + "loss": 0.136, "step": 220460 }, { - "epoch": 0.98, - "learning_rate": 8.136406439173132e-07, - "loss": 0.1419, + "epoch": 0.49, + "learning_rate": 2.546173463680902e-05, + "loss": 0.1309, "step": 220470 }, { - "epoch": 0.98, - "learning_rate": 8.113985919913905e-07, - "loss": 0.1317, + "epoch": 0.49, + "learning_rate": 2.5460616093599697e-05, + "loss": 0.136, "step": 220480 }, { - "epoch": 0.98, - "learning_rate": 8.09156540065468e-07, - "loss": 0.1352, + "epoch": 0.49, + "learning_rate": 2.5459497550390372e-05, + "loss": 0.1301, "step": 220490 }, { - "epoch": 0.98, - "learning_rate": 8.069144881395454e-07, - "loss": 0.1377, + "epoch": 0.49, + "learning_rate": 2.545837900718105e-05, + "loss": 0.1364, "step": 220500 }, { - "epoch": 0.98, - "learning_rate": 8.046724362136227e-07, - "loss": 0.1345, + "epoch": 0.49, + "learning_rate": 2.5457260463971728e-05, + "loss": 0.1344, "step": 220510 }, { - "epoch": 0.98, - "learning_rate": 8.024303842877001e-07, - "loss": 0.139, + "epoch": 0.49, + "learning_rate": 2.54561419207624e-05, + "loss": 0.1336, "step": 220520 }, { - "epoch": 0.98, - "learning_rate": 8.001883323617775e-07, - "loss": 0.1395, + "epoch": 0.49, + "learning_rate": 2.5455023377553077e-05, + "loss": 0.1346, "step": 220530 }, { - "epoch": 0.98, - "learning_rate": 7.979462804358549e-07, - "loss": 0.1342, + "epoch": 0.49, + "learning_rate": 2.545390483434375e-05, + "loss": 0.1362, "step": 220540 }, { - "epoch": 0.98, - "learning_rate": 7.957042285099324e-07, - "loss": 0.1398, + "epoch": 0.49, + "learning_rate": 2.545289814545536e-05, + "loss": 0.1369, "step": 220550 }, { - "epoch": 0.98, - "learning_rate": 7.934621765840098e-07, - "loss": 0.131, + "epoch": 0.49, + "learning_rate": 2.5451779602246035e-05, + "loss": 0.1338, "step": 220560 }, { - "epoch": 0.98, - "learning_rate": 7.912201246580871e-07, - "loss": 0.1283, + "epoch": 0.49, + "learning_rate": 2.5450661059036713e-05, + "loss": 0.1326, "step": 220570 }, { - "epoch": 0.98, - "learning_rate": 7.889780727321645e-07, - "loss": 0.1307, + "epoch": 0.49, + "learning_rate": 2.544954251582739e-05, + "loss": 0.1325, "step": 220580 }, { - "epoch": 0.98, - "learning_rate": 7.867360208062419e-07, - "loss": 0.1378, + "epoch": 0.49, + "learning_rate": 2.544842397261806e-05, + "loss": 0.133, "step": 220590 }, { - "epoch": 0.98, - "learning_rate": 7.844939688803192e-07, - "loss": 0.1395, + "epoch": 0.49, + "learning_rate": 2.544730542940874e-05, + "loss": 0.1278, "step": 220600 }, { - "epoch": 0.98, - "learning_rate": 7.822519169543968e-07, - "loss": 0.1357, + "epoch": 0.49, + "learning_rate": 2.5446186886199414e-05, + "loss": 0.131, "step": 220610 }, { - "epoch": 0.98, - "learning_rate": 7.80009865028474e-07, - "loss": 0.1364, + "epoch": 0.49, + "learning_rate": 2.5445068342990092e-05, + "loss": 0.1342, "step": 220620 }, { - "epoch": 0.98, - "learning_rate": 7.777678131025516e-07, - "loss": 0.1432, + "epoch": 0.49, + "learning_rate": 2.5443949799780763e-05, + "loss": 0.1337, "step": 220630 }, { - "epoch": 0.98, - "learning_rate": 7.755257611766289e-07, - "loss": 0.1404, - "step": 220640 + "epoch": 0.49, + "learning_rate": 2.544283125657144e-05, + "loss": 0.1336, + "step": 220640 + }, + { + "epoch": 0.49, + "learning_rate": 2.544171271336212e-05, + "loss": 0.1313, + "step": 220650 + }, + { + "epoch": 0.49, + "learning_rate": 2.5440594170152794e-05, + "loss": 0.1359, + "step": 220660 + }, + { + "epoch": 0.49, + "learning_rate": 2.543947562694347e-05, + "loss": 0.1337, + "step": 220670 + }, + { + "epoch": 0.49, + "learning_rate": 2.5438357083734143e-05, + "loss": 0.1361, + "step": 220680 + }, + { + "epoch": 0.49, + "learning_rate": 2.543723854052482e-05, + "loss": 0.1299, + "step": 220690 + }, + { + "epoch": 0.49, + "learning_rate": 2.54361199973155e-05, + "loss": 0.1367, + "step": 220700 + }, + { + "epoch": 0.49, + "learning_rate": 2.5435001454106173e-05, + "loss": 0.1326, + "step": 220710 + }, + { + "epoch": 0.49, + "learning_rate": 2.543388291089685e-05, + "loss": 0.1371, + "step": 220720 + }, + { + "epoch": 0.49, + "learning_rate": 2.5432764367687522e-05, + "loss": 0.1363, + "step": 220730 + }, + { + "epoch": 0.49, + "learning_rate": 2.54316458244782e-05, + "loss": 0.1336, + "step": 220740 + }, + { + "epoch": 0.49, + "learning_rate": 2.5430527281268878e-05, + "loss": 0.1314, + "step": 220750 + }, + { + "epoch": 0.49, + "learning_rate": 2.5429408738059552e-05, + "loss": 0.1346, + "step": 220760 + }, + { + "epoch": 0.49, + "learning_rate": 2.542829019485023e-05, + "loss": 0.1403, + "step": 220770 + }, + { + "epoch": 0.49, + "learning_rate": 2.54271716516409e-05, + "loss": 0.1345, + "step": 220780 + }, + { + "epoch": 0.49, + "learning_rate": 2.542605310843158e-05, + "loss": 0.1333, + "step": 220790 + }, + { + "epoch": 0.49, + "learning_rate": 2.5424934565222257e-05, + "loss": 0.1322, + "step": 220800 + }, + { + "epoch": 0.49, + "learning_rate": 2.5423816022012932e-05, + "loss": 0.1359, + "step": 220810 + }, + { + "epoch": 0.49, + "learning_rate": 2.542269747880361e-05, + "loss": 0.1351, + "step": 220820 + }, + { + "epoch": 0.49, + "learning_rate": 2.542157893559428e-05, + "loss": 0.1388, + "step": 220830 + }, + { + "epoch": 0.49, + "learning_rate": 2.542046039238496e-05, + "loss": 0.1349, + "step": 220840 + }, + { + "epoch": 0.49, + "learning_rate": 2.5419341849175637e-05, + "loss": 0.1359, + "step": 220850 + }, + { + "epoch": 0.49, + "learning_rate": 2.541822330596631e-05, + "loss": 0.133, + "step": 220860 + }, + { + "epoch": 0.49, + "learning_rate": 2.541710476275699e-05, + "loss": 0.135, + "step": 220870 + }, + { + "epoch": 0.49, + "learning_rate": 2.541598621954766e-05, + "loss": 0.1315, + "step": 220880 + }, + { + "epoch": 0.49, + "learning_rate": 2.541486767633834e-05, + "loss": 0.1373, + "step": 220890 + }, + { + "epoch": 0.49, + "learning_rate": 2.5413749133129016e-05, + "loss": 0.1339, + "step": 220900 + }, + { + "epoch": 0.49, + "learning_rate": 2.541263058991969e-05, + "loss": 0.1348, + "step": 220910 + }, + { + "epoch": 0.49, + "learning_rate": 2.541151204671037e-05, + "loss": 0.1369, + "step": 220920 + }, + { + "epoch": 0.49, + "learning_rate": 2.541039350350104e-05, + "loss": 0.1327, + "step": 220930 + }, + { + "epoch": 0.49, + "learning_rate": 2.5409274960291718e-05, + "loss": 0.1351, + "step": 220940 + }, + { + "epoch": 0.49, + "learning_rate": 2.540815641708239e-05, + "loss": 0.1341, + "step": 220950 + }, + { + "epoch": 0.49, + "learning_rate": 2.5407037873873067e-05, + "loss": 0.1288, + "step": 220960 + }, + { + "epoch": 0.49, + "learning_rate": 2.540591933066375e-05, + "loss": 0.13, + "step": 220970 + }, + { + "epoch": 0.49, + "learning_rate": 2.540480078745442e-05, + "loss": 0.1352, + "step": 220980 + }, + { + "epoch": 0.49, + "learning_rate": 2.5403682244245097e-05, + "loss": 0.1367, + "step": 220990 + }, + { + "epoch": 0.49, + "learning_rate": 2.540256370103577e-05, + "loss": 0.1341, + "step": 221000 + }, + { + "epoch": 0.49, + "learning_rate": 2.5401445157826446e-05, + "loss": 0.1362, + "step": 221010 + }, + { + "epoch": 0.49, + "learning_rate": 2.5400326614617124e-05, + "loss": 0.1318, + "step": 221020 + }, + { + "epoch": 0.49, + "learning_rate": 2.53992080714078e-05, + "loss": 0.132, + "step": 221030 + }, + { + "epoch": 0.49, + "learning_rate": 2.5398089528198477e-05, + "loss": 0.1295, + "step": 221040 + }, + { + "epoch": 0.49, + "learning_rate": 2.5396970984989148e-05, + "loss": 0.1331, + "step": 221050 + }, + { + "epoch": 0.49, + "learning_rate": 2.5395852441779826e-05, + "loss": 0.1351, + "step": 221060 + }, + { + "epoch": 0.49, + "learning_rate": 2.5394733898570504e-05, + "loss": 0.1333, + "step": 221070 + }, + { + "epoch": 0.49, + "learning_rate": 2.539361535536118e-05, + "loss": 0.133, + "step": 221080 + }, + { + "epoch": 0.49, + "learning_rate": 2.5392496812151856e-05, + "loss": 0.1305, + "step": 221090 + }, + { + "epoch": 0.49, + "learning_rate": 2.5391378268942527e-05, + "loss": 0.1344, + "step": 221100 + }, + { + "epoch": 0.49, + "learning_rate": 2.5390259725733205e-05, + "loss": 0.1359, + "step": 221110 + }, + { + "epoch": 0.49, + "learning_rate": 2.5389141182523883e-05, + "loss": 0.1305, + "step": 221120 + }, + { + "epoch": 0.49, + "learning_rate": 2.5388022639314558e-05, + "loss": 0.1332, + "step": 221130 + }, + { + "epoch": 0.49, + "learning_rate": 2.5386904096105236e-05, + "loss": 0.1335, + "step": 221140 + }, + { + "epoch": 0.49, + "learning_rate": 2.5385785552895907e-05, + "loss": 0.1319, + "step": 221150 + }, + { + "epoch": 0.49, + "learning_rate": 2.5384667009686585e-05, + "loss": 0.1329, + "step": 221160 + }, + { + "epoch": 0.49, + "learning_rate": 2.5383548466477263e-05, + "loss": 0.1313, + "step": 221170 + }, + { + "epoch": 0.49, + "learning_rate": 2.5382429923267937e-05, + "loss": 0.128, + "step": 221180 + }, + { + "epoch": 0.49, + "learning_rate": 2.5381311380058615e-05, + "loss": 0.1329, + "step": 221190 + }, + { + "epoch": 0.49, + "learning_rate": 2.5380192836849286e-05, + "loss": 0.1328, + "step": 221200 + }, + { + "epoch": 0.49, + "learning_rate": 2.5379074293639964e-05, + "loss": 0.1371, + "step": 221210 + }, + { + "epoch": 0.49, + "learning_rate": 2.5377955750430642e-05, + "loss": 0.1372, + "step": 221220 + }, + { + "epoch": 0.49, + "learning_rate": 2.5376837207221317e-05, + "loss": 0.1345, + "step": 221230 + }, + { + "epoch": 0.49, + "learning_rate": 2.5375718664011995e-05, + "loss": 0.1381, + "step": 221240 + }, + { + "epoch": 0.49, + "learning_rate": 2.5374600120802666e-05, + "loss": 0.1294, + "step": 221250 + }, + { + "epoch": 0.49, + "learning_rate": 2.5373481577593344e-05, + "loss": 0.1333, + "step": 221260 + }, + { + "epoch": 0.49, + "learning_rate": 2.537236303438402e-05, + "loss": 0.1309, + "step": 221270 + }, + { + "epoch": 0.49, + "learning_rate": 2.5371244491174696e-05, + "loss": 0.1325, + "step": 221280 + }, + { + "epoch": 0.49, + "learning_rate": 2.5370125947965374e-05, + "loss": 0.1335, + "step": 221290 + }, + { + "epoch": 0.49, + "learning_rate": 2.5369007404756045e-05, + "loss": 0.136, + "step": 221300 + }, + { + "epoch": 0.49, + "learning_rate": 2.5367888861546723e-05, + "loss": 0.1317, + "step": 221310 + }, + { + "epoch": 0.49, + "learning_rate": 2.5366770318337394e-05, + "loss": 0.1356, + "step": 221320 + }, + { + "epoch": 0.49, + "learning_rate": 2.5365651775128076e-05, + "loss": 0.1355, + "step": 221330 + }, + { + "epoch": 0.49, + "learning_rate": 2.5364533231918754e-05, + "loss": 0.1346, + "step": 221340 + }, + { + "epoch": 0.49, + "learning_rate": 2.5363414688709425e-05, + "loss": 0.1299, + "step": 221350 + }, + { + "epoch": 0.49, + "learning_rate": 2.5362296145500103e-05, + "loss": 0.131, + "step": 221360 + }, + { + "epoch": 0.49, + "learning_rate": 2.5361177602290774e-05, + "loss": 0.138, + "step": 221370 + }, + { + "epoch": 0.49, + "learning_rate": 2.5360059059081452e-05, + "loss": 0.1344, + "step": 221380 + }, + { + "epoch": 0.49, + "learning_rate": 2.5358940515872133e-05, + "loss": 0.1323, + "step": 221390 + }, + { + "epoch": 0.49, + "learning_rate": 2.5357821972662804e-05, + "loss": 0.1291, + "step": 221400 + }, + { + "epoch": 0.49, + "learning_rate": 2.5356703429453482e-05, + "loss": 0.1328, + "step": 221410 + }, + { + "epoch": 0.49, + "learning_rate": 2.5355584886244153e-05, + "loss": 0.1368, + "step": 221420 + }, + { + "epoch": 0.49, + "learning_rate": 2.535446634303483e-05, + "loss": 0.1335, + "step": 221430 + }, + { + "epoch": 0.49, + "learning_rate": 2.535334779982551e-05, + "loss": 0.1378, + "step": 221440 + }, + { + "epoch": 0.49, + "learning_rate": 2.5352229256616184e-05, + "loss": 0.1331, + "step": 221450 + }, + { + "epoch": 0.49, + "learning_rate": 2.5351110713406862e-05, + "loss": 0.1378, + "step": 221460 + }, + { + "epoch": 0.49, + "learning_rate": 2.5349992170197533e-05, + "loss": 0.1338, + "step": 221470 + }, + { + "epoch": 0.49, + "learning_rate": 2.534887362698821e-05, + "loss": 0.1364, + "step": 221480 + }, + { + "epoch": 0.49, + "learning_rate": 2.534775508377889e-05, + "loss": 0.1365, + "step": 221490 + }, + { + "epoch": 0.49, + "learning_rate": 2.5346636540569563e-05, + "loss": 0.1334, + "step": 221500 + }, + { + "epoch": 0.49, + "learning_rate": 2.534551799736024e-05, + "loss": 0.1332, + "step": 221510 + }, + { + "epoch": 0.49, + "learning_rate": 2.5344399454150912e-05, + "loss": 0.134, + "step": 221520 + }, + { + "epoch": 0.49, + "learning_rate": 2.534328091094159e-05, + "loss": 0.1359, + "step": 221530 + }, + { + "epoch": 0.49, + "learning_rate": 2.5342162367732268e-05, + "loss": 0.1392, + "step": 221540 + }, + { + "epoch": 0.49, + "learning_rate": 2.5341043824522943e-05, + "loss": 0.139, + "step": 221550 + }, + { + "epoch": 0.49, + "learning_rate": 2.533992528131362e-05, + "loss": 0.1344, + "step": 221560 + }, + { + "epoch": 0.49, + "learning_rate": 2.5338806738104292e-05, + "loss": 0.1326, + "step": 221570 + }, + { + "epoch": 0.49, + "learning_rate": 2.533768819489497e-05, + "loss": 0.1359, + "step": 221580 + }, + { + "epoch": 0.49, + "learning_rate": 2.5336569651685644e-05, + "loss": 0.1304, + "step": 221590 + }, + { + "epoch": 0.49, + "learning_rate": 2.5335451108476322e-05, + "loss": 0.1353, + "step": 221600 + }, + { + "epoch": 0.49, + "learning_rate": 2.5334332565267e-05, + "loss": 0.1367, + "step": 221610 + }, + { + "epoch": 0.49, + "learning_rate": 2.533321402205767e-05, + "loss": 0.1351, + "step": 221620 + }, + { + "epoch": 0.49, + "learning_rate": 2.533209547884835e-05, + "loss": 0.1335, + "step": 221630 + }, + { + "epoch": 0.49, + "learning_rate": 2.5330976935639024e-05, + "loss": 0.1346, + "step": 221640 + }, + { + "epoch": 0.49, + "learning_rate": 2.5329858392429702e-05, + "loss": 0.132, + "step": 221650 + }, + { + "epoch": 0.49, + "learning_rate": 2.532873984922038e-05, + "loss": 0.1379, + "step": 221660 + }, + { + "epoch": 0.49, + "learning_rate": 2.532762130601105e-05, + "loss": 0.1347, + "step": 221670 + }, + { + "epoch": 0.49, + "learning_rate": 2.532650276280173e-05, + "loss": 0.1325, + "step": 221680 + }, + { + "epoch": 0.49, + "learning_rate": 2.5325384219592403e-05, + "loss": 0.136, + "step": 221690 + }, + { + "epoch": 0.49, + "learning_rate": 2.532426567638308e-05, + "loss": 0.1344, + "step": 221700 + }, + { + "epoch": 0.49, + "learning_rate": 2.532314713317376e-05, + "loss": 0.1328, + "step": 221710 + }, + { + "epoch": 0.49, + "learning_rate": 2.532202858996443e-05, + "loss": 0.1324, + "step": 221720 + }, + { + "epoch": 0.49, + "learning_rate": 2.5320910046755108e-05, + "loss": 0.1316, + "step": 221730 + }, + { + "epoch": 0.49, + "learning_rate": 2.5319791503545783e-05, + "loss": 0.134, + "step": 221740 + }, + { + "epoch": 0.49, + "learning_rate": 2.531867296033646e-05, + "loss": 0.1346, + "step": 221750 + }, + { + "epoch": 0.49, + "learning_rate": 2.531755441712714e-05, + "loss": 0.1393, + "step": 221760 + }, + { + "epoch": 0.5, + "learning_rate": 2.531643587391781e-05, + "loss": 0.1354, + "step": 221770 + }, + { + "epoch": 0.5, + "learning_rate": 2.5315317330708488e-05, + "loss": 0.1271, + "step": 221780 + }, + { + "epoch": 0.5, + "learning_rate": 2.531419878749916e-05, + "loss": 0.129, + "step": 221790 + }, + { + "epoch": 0.5, + "learning_rate": 2.531308024428984e-05, + "loss": 0.1327, + "step": 221800 + }, + { + "epoch": 0.5, + "learning_rate": 2.5311961701080518e-05, + "loss": 0.1311, + "step": 221810 + }, + { + "epoch": 0.5, + "learning_rate": 2.531084315787119e-05, + "loss": 0.1316, + "step": 221820 + }, + { + "epoch": 0.5, + "learning_rate": 2.5309724614661867e-05, + "loss": 0.1297, + "step": 221830 + }, + { + "epoch": 0.5, + "learning_rate": 2.5308606071452538e-05, + "loss": 0.1405, + "step": 221840 + }, + { + "epoch": 0.5, + "learning_rate": 2.5307487528243216e-05, + "loss": 0.1339, + "step": 221850 + }, + { + "epoch": 0.5, + "learning_rate": 2.530636898503389e-05, + "loss": 0.1325, + "step": 221860 + }, + { + "epoch": 0.5, + "learning_rate": 2.530525044182457e-05, + "loss": 0.1346, + "step": 221870 + }, + { + "epoch": 0.5, + "learning_rate": 2.5304131898615247e-05, + "loss": 0.1334, + "step": 221880 + }, + { + "epoch": 0.5, + "learning_rate": 2.5303013355405918e-05, + "loss": 0.138, + "step": 221890 + }, + { + "epoch": 0.5, + "learning_rate": 2.5301894812196596e-05, + "loss": 0.1319, + "step": 221900 + }, + { + "epoch": 0.5, + "learning_rate": 2.530077626898727e-05, + "loss": 0.1355, + "step": 221910 + }, + { + "epoch": 0.5, + "learning_rate": 2.5299657725777948e-05, + "loss": 0.1334, + "step": 221920 + }, + { + "epoch": 0.5, + "learning_rate": 2.5298539182568626e-05, + "loss": 0.1296, + "step": 221930 + }, + { + "epoch": 0.5, + "learning_rate": 2.5297420639359297e-05, + "loss": 0.1392, + "step": 221940 + }, + { + "epoch": 0.5, + "learning_rate": 2.5296302096149975e-05, + "loss": 0.1338, + "step": 221950 + }, + { + "epoch": 0.5, + "learning_rate": 2.529518355294065e-05, + "loss": 0.1343, + "step": 221960 + }, + { + "epoch": 0.5, + "learning_rate": 2.5294065009731328e-05, + "loss": 0.1341, + "step": 221970 + }, + { + "epoch": 0.5, + "learning_rate": 2.5292946466522006e-05, + "loss": 0.1294, + "step": 221980 + }, + { + "epoch": 0.5, + "learning_rate": 2.5291827923312677e-05, + "loss": 0.1318, + "step": 221990 + }, + { + "epoch": 0.5, + "learning_rate": 2.5290709380103355e-05, + "loss": 0.1338, + "step": 222000 + }, + { + "epoch": 0.5, + "learning_rate": 2.528959083689403e-05, + "loss": 0.1396, + "step": 222010 + }, + { + "epoch": 0.5, + "learning_rate": 2.5288472293684707e-05, + "loss": 0.1355, + "step": 222020 + }, + { + "epoch": 0.5, + "learning_rate": 2.5287353750475385e-05, + "loss": 0.1342, + "step": 222030 + }, + { + "epoch": 0.5, + "learning_rate": 2.5286235207266056e-05, + "loss": 0.1364, + "step": 222040 + }, + { + "epoch": 0.5, + "learning_rate": 2.5285116664056734e-05, + "loss": 0.1364, + "step": 222050 + }, + { + "epoch": 0.5, + "learning_rate": 2.528399812084741e-05, + "loss": 0.1324, + "step": 222060 + }, + { + "epoch": 0.5, + "learning_rate": 2.5282879577638087e-05, + "loss": 0.1315, + "step": 222070 + }, + { + "epoch": 0.5, + "learning_rate": 2.5281761034428765e-05, + "loss": 0.1308, + "step": 222080 + }, + { + "epoch": 0.5, + "learning_rate": 2.5280642491219436e-05, + "loss": 0.1334, + "step": 222090 + }, + { + "epoch": 0.5, + "learning_rate": 2.5279523948010114e-05, + "loss": 0.1368, + "step": 222100 + }, + { + "epoch": 0.5, + "learning_rate": 2.5278405404800788e-05, + "loss": 0.1369, + "step": 222110 + }, + { + "epoch": 0.5, + "learning_rate": 2.5277286861591466e-05, + "loss": 0.1326, + "step": 222120 + }, + { + "epoch": 0.5, + "learning_rate": 2.5276168318382144e-05, + "loss": 0.1349, + "step": 222130 + }, + { + "epoch": 0.5, + "learning_rate": 2.5275049775172815e-05, + "loss": 0.1337, + "step": 222140 + }, + { + "epoch": 0.5, + "learning_rate": 2.5273931231963493e-05, + "loss": 0.1341, + "step": 222150 + }, + { + "epoch": 0.5, + "learning_rate": 2.5272812688754168e-05, + "loss": 0.1285, + "step": 222160 + }, + { + "epoch": 0.5, + "learning_rate": 2.5271694145544846e-05, + "loss": 0.135, + "step": 222170 + }, + { + "epoch": 0.5, + "learning_rate": 2.5270575602335517e-05, + "loss": 0.1319, + "step": 222180 + }, + { + "epoch": 0.5, + "learning_rate": 2.5269457059126195e-05, + "loss": 0.1328, + "step": 222190 + }, + { + "epoch": 0.5, + "learning_rate": 2.5268338515916873e-05, + "loss": 0.128, + "step": 222200 + }, + { + "epoch": 0.5, + "learning_rate": 2.5267219972707544e-05, + "loss": 0.1326, + "step": 222210 + }, + { + "epoch": 0.5, + "learning_rate": 2.5266101429498225e-05, + "loss": 0.1344, + "step": 222220 + }, + { + "epoch": 0.5, + "learning_rate": 2.5264982886288896e-05, + "loss": 0.1348, + "step": 222230 + }, + { + "epoch": 0.5, + "learning_rate": 2.5263864343079574e-05, + "loss": 0.1359, + "step": 222240 + }, + { + "epoch": 0.5, + "learning_rate": 2.5262745799870252e-05, + "loss": 0.1327, + "step": 222250 + }, + { + "epoch": 0.5, + "learning_rate": 2.5261627256660923e-05, + "loss": 0.1346, + "step": 222260 + }, + { + "epoch": 0.5, + "learning_rate": 2.52605087134516e-05, + "loss": 0.1307, + "step": 222270 + }, + { + "epoch": 0.5, + "learning_rate": 2.5259390170242276e-05, + "loss": 0.1364, + "step": 222280 + }, + { + "epoch": 0.5, + "learning_rate": 2.5258271627032954e-05, + "loss": 0.1317, + "step": 222290 + }, + { + "epoch": 0.5, + "learning_rate": 2.525715308382363e-05, + "loss": 0.1337, + "step": 222300 + }, + { + "epoch": 0.5, + "learning_rate": 2.5256034540614303e-05, + "loss": 0.1295, + "step": 222310 + }, + { + "epoch": 0.5, + "learning_rate": 2.525491599740498e-05, + "loss": 0.1362, + "step": 222320 + }, + { + "epoch": 0.5, + "learning_rate": 2.5253797454195655e-05, + "loss": 0.1329, + "step": 222330 + }, + { + "epoch": 0.5, + "learning_rate": 2.5252678910986333e-05, + "loss": 0.1347, + "step": 222340 + }, + { + "epoch": 0.5, + "learning_rate": 2.525156036777701e-05, + "loss": 0.1301, + "step": 222350 + }, + { + "epoch": 0.5, + "learning_rate": 2.5250441824567682e-05, + "loss": 0.1376, + "step": 222360 + }, + { + "epoch": 0.5, + "learning_rate": 2.524932328135836e-05, + "loss": 0.1324, + "step": 222370 + }, + { + "epoch": 0.5, + "learning_rate": 2.5248204738149035e-05, + "loss": 0.1353, + "step": 222380 + }, + { + "epoch": 0.5, + "learning_rate": 2.5247086194939713e-05, + "loss": 0.1352, + "step": 222390 + }, + { + "epoch": 0.5, + "learning_rate": 2.524596765173039e-05, + "loss": 0.1334, + "step": 222400 + }, + { + "epoch": 0.5, + "learning_rate": 2.524484910852106e-05, + "loss": 0.1397, + "step": 222410 + }, + { + "epoch": 0.5, + "learning_rate": 2.524373056531174e-05, + "loss": 0.1371, + "step": 222420 + }, + { + "epoch": 0.5, + "learning_rate": 2.5242612022102414e-05, + "loss": 0.1325, + "step": 222430 + }, + { + "epoch": 0.5, + "learning_rate": 2.5241493478893092e-05, + "loss": 0.1373, + "step": 222440 + }, + { + "epoch": 0.5, + "learning_rate": 2.524037493568377e-05, + "loss": 0.133, + "step": 222450 + }, + { + "epoch": 0.5, + "learning_rate": 2.523925639247444e-05, + "loss": 0.1326, + "step": 222460 + }, + { + "epoch": 0.5, + "learning_rate": 2.523813784926512e-05, + "loss": 0.1316, + "step": 222470 + }, + { + "epoch": 0.5, + "learning_rate": 2.5237019306055794e-05, + "loss": 0.1321, + "step": 222480 + }, + { + "epoch": 0.5, + "learning_rate": 2.523590076284647e-05, + "loss": 0.1364, + "step": 222490 + }, + { + "epoch": 0.5, + "learning_rate": 2.5234782219637143e-05, + "loss": 0.1372, + "step": 222500 + }, + { + "epoch": 0.5, + "learning_rate": 2.523366367642782e-05, + "loss": 0.1368, + "step": 222510 + }, + { + "epoch": 0.5, + "learning_rate": 2.52325451332185e-05, + "loss": 0.1266, + "step": 222520 + }, + { + "epoch": 0.5, + "learning_rate": 2.5231426590009173e-05, + "loss": 0.1331, + "step": 222530 + }, + { + "epoch": 0.5, + "learning_rate": 2.523030804679985e-05, + "loss": 0.134, + "step": 222540 + }, + { + "epoch": 0.5, + "learning_rate": 2.5229189503590522e-05, + "loss": 0.1335, + "step": 222550 + }, + { + "epoch": 0.5, + "learning_rate": 2.52280709603812e-05, + "loss": 0.135, + "step": 222560 + }, + { + "epoch": 0.5, + "learning_rate": 2.5226952417171878e-05, + "loss": 0.1338, + "step": 222570 + }, + { + "epoch": 0.5, + "learning_rate": 2.5225833873962552e-05, + "loss": 0.1359, + "step": 222580 + }, + { + "epoch": 0.5, + "learning_rate": 2.522471533075323e-05, + "loss": 0.1299, + "step": 222590 + }, + { + "epoch": 0.5, + "learning_rate": 2.52235967875439e-05, + "loss": 0.1331, + "step": 222600 + }, + { + "epoch": 0.5, + "learning_rate": 2.522247824433458e-05, + "loss": 0.1331, + "step": 222610 + }, + { + "epoch": 0.5, + "learning_rate": 2.5221359701125257e-05, + "loss": 0.134, + "step": 222620 + }, + { + "epoch": 0.5, + "learning_rate": 2.5220241157915932e-05, + "loss": 0.132, + "step": 222630 + }, + { + "epoch": 0.5, + "learning_rate": 2.521912261470661e-05, + "loss": 0.1359, + "step": 222640 + }, + { + "epoch": 0.5, + "learning_rate": 2.521800407149728e-05, + "loss": 0.1379, + "step": 222650 + }, + { + "epoch": 0.5, + "learning_rate": 2.521688552828796e-05, + "loss": 0.1354, + "step": 222660 + }, + { + "epoch": 0.5, + "learning_rate": 2.5215766985078637e-05, + "loss": 0.1315, + "step": 222670 + }, + { + "epoch": 0.5, + "learning_rate": 2.5214648441869308e-05, + "loss": 0.1366, + "step": 222680 + }, + { + "epoch": 0.5, + "learning_rate": 2.521352989865999e-05, + "loss": 0.1329, + "step": 222690 + }, + { + "epoch": 0.5, + "learning_rate": 2.521241135545066e-05, + "loss": 0.1306, + "step": 222700 + }, + { + "epoch": 0.5, + "learning_rate": 2.521129281224134e-05, + "loss": 0.1347, + "step": 222710 + }, + { + "epoch": 0.5, + "learning_rate": 2.5210174269032016e-05, + "loss": 0.1319, + "step": 222720 + }, + { + "epoch": 0.5, + "learning_rate": 2.5209055725822688e-05, + "loss": 0.1313, + "step": 222730 + }, + { + "epoch": 0.5, + "learning_rate": 2.5207937182613365e-05, + "loss": 0.1344, + "step": 222740 + }, + { + "epoch": 0.5, + "learning_rate": 2.520681863940404e-05, + "loss": 0.1292, + "step": 222750 + }, + { + "epoch": 0.5, + "learning_rate": 2.5205700096194718e-05, + "loss": 0.1371, + "step": 222760 + }, + { + "epoch": 0.5, + "learning_rate": 2.5204581552985396e-05, + "loss": 0.1334, + "step": 222770 + }, + { + "epoch": 0.5, + "learning_rate": 2.5203463009776067e-05, + "loss": 0.1299, + "step": 222780 + }, + { + "epoch": 0.5, + "learning_rate": 2.5202344466566745e-05, + "loss": 0.1317, + "step": 222790 + }, + { + "epoch": 0.5, + "learning_rate": 2.520122592335742e-05, + "loss": 0.1289, + "step": 222800 + }, + { + "epoch": 0.5, + "learning_rate": 2.5200107380148097e-05, + "loss": 0.1355, + "step": 222810 + }, + { + "epoch": 0.5, + "learning_rate": 2.519898883693877e-05, + "loss": 0.1342, + "step": 222820 + }, + { + "epoch": 0.5, + "learning_rate": 2.5197870293729446e-05, + "loss": 0.1346, + "step": 222830 + }, + { + "epoch": 0.5, + "learning_rate": 2.5196751750520124e-05, + "loss": 0.1368, + "step": 222840 + }, + { + "epoch": 0.5, + "learning_rate": 2.51956332073108e-05, + "loss": 0.1306, + "step": 222850 + }, + { + "epoch": 0.5, + "learning_rate": 2.5194514664101477e-05, + "loss": 0.1292, + "step": 222860 + }, + { + "epoch": 0.5, + "learning_rate": 2.5193396120892148e-05, + "loss": 0.1334, + "step": 222870 + }, + { + "epoch": 0.5, + "learning_rate": 2.5192277577682826e-05, + "loss": 0.1339, + "step": 222880 + }, + { + "epoch": 0.5, + "learning_rate": 2.5191159034473504e-05, + "loss": 0.1301, + "step": 222890 + }, + { + "epoch": 0.5, + "learning_rate": 2.519004049126418e-05, + "loss": 0.1345, + "step": 222900 + }, + { + "epoch": 0.5, + "learning_rate": 2.5188921948054856e-05, + "loss": 0.1361, + "step": 222910 + }, + { + "epoch": 0.5, + "learning_rate": 2.5187803404845527e-05, + "loss": 0.1308, + "step": 222920 + }, + { + "epoch": 0.5, + "learning_rate": 2.5186684861636205e-05, + "loss": 0.1362, + "step": 222930 + }, + { + "epoch": 0.5, + "learning_rate": 2.5185566318426883e-05, + "loss": 0.1376, + "step": 222940 + }, + { + "epoch": 0.5, + "learning_rate": 2.5184447775217558e-05, + "loss": 0.1309, + "step": 222950 + }, + { + "epoch": 0.5, + "learning_rate": 2.5183329232008236e-05, + "loss": 0.1364, + "step": 222960 + }, + { + "epoch": 0.5, + "learning_rate": 2.5182210688798907e-05, + "loss": 0.1359, + "step": 222970 + }, + { + "epoch": 0.5, + "learning_rate": 2.5181092145589585e-05, + "loss": 0.1346, + "step": 222980 + }, + { + "epoch": 0.5, + "learning_rate": 2.5179973602380263e-05, + "loss": 0.1317, + "step": 222990 + }, + { + "epoch": 0.5, + "learning_rate": 2.5178855059170937e-05, + "loss": 0.1331, + "step": 223000 + }, + { + "epoch": 0.5, + "learning_rate": 2.5177736515961615e-05, + "loss": 0.1304, + "step": 223010 + }, + { + "epoch": 0.5, + "learning_rate": 2.5176617972752286e-05, + "loss": 0.1341, + "step": 223020 + }, + { + "epoch": 0.5, + "learning_rate": 2.5175499429542964e-05, + "loss": 0.1334, + "step": 223030 + }, + { + "epoch": 0.5, + "learning_rate": 2.5174380886333642e-05, + "loss": 0.1368, + "step": 223040 + }, + { + "epoch": 0.5, + "learning_rate": 2.5173262343124317e-05, + "loss": 0.1346, + "step": 223050 + }, + { + "epoch": 0.5, + "learning_rate": 2.5172143799914995e-05, + "loss": 0.1312, + "step": 223060 + }, + { + "epoch": 0.5, + "learning_rate": 2.5171025256705666e-05, + "loss": 0.133, + "step": 223070 + }, + { + "epoch": 0.5, + "learning_rate": 2.5169906713496344e-05, + "loss": 0.1325, + "step": 223080 + }, + { + "epoch": 0.5, + "learning_rate": 2.5168788170287022e-05, + "loss": 0.134, + "step": 223090 + }, + { + "epoch": 0.5, + "learning_rate": 2.5167669627077696e-05, + "loss": 0.1281, + "step": 223100 + }, + { + "epoch": 0.5, + "learning_rate": 2.5166551083868374e-05, + "loss": 0.132, + "step": 223110 + }, + { + "epoch": 0.5, + "learning_rate": 2.5165432540659045e-05, + "loss": 0.1319, + "step": 223120 + }, + { + "epoch": 0.5, + "learning_rate": 2.5164313997449723e-05, + "loss": 0.1346, + "step": 223130 + }, + { + "epoch": 0.5, + "learning_rate": 2.5163195454240394e-05, + "loss": 0.1362, + "step": 223140 + }, + { + "epoch": 0.5, + "learning_rate": 2.5162076911031072e-05, + "loss": 0.1358, + "step": 223150 + }, + { + "epoch": 0.5, + "learning_rate": 2.516095836782175e-05, + "loss": 0.1376, + "step": 223160 + }, + { + "epoch": 0.5, + "learning_rate": 2.5159839824612425e-05, + "loss": 0.1335, + "step": 223170 + }, + { + "epoch": 0.5, + "learning_rate": 2.5158721281403103e-05, + "loss": 0.136, + "step": 223180 + }, + { + "epoch": 0.5, + "learning_rate": 2.5157602738193774e-05, + "loss": 0.1321, + "step": 223190 + }, + { + "epoch": 0.5, + "learning_rate": 2.5156484194984452e-05, + "loss": 0.1337, + "step": 223200 + }, + { + "epoch": 0.5, + "learning_rate": 2.515536565177513e-05, + "loss": 0.1318, + "step": 223210 + }, + { + "epoch": 0.5, + "learning_rate": 2.5154247108565804e-05, + "loss": 0.1335, + "step": 223220 + }, + { + "epoch": 0.5, + "learning_rate": 2.5153128565356482e-05, + "loss": 0.1365, + "step": 223230 + }, + { + "epoch": 0.5, + "learning_rate": 2.5152010022147153e-05, + "loss": 0.1315, + "step": 223240 + }, + { + "epoch": 0.5, + "learning_rate": 2.515089147893783e-05, + "loss": 0.1308, + "step": 223250 + }, + { + "epoch": 0.5, + "learning_rate": 2.514977293572851e-05, + "loss": 0.1359, + "step": 223260 + }, + { + "epoch": 0.5, + "learning_rate": 2.5148654392519184e-05, + "loss": 0.1345, + "step": 223270 + }, + { + "epoch": 0.5, + "learning_rate": 2.5147535849309862e-05, + "loss": 0.126, + "step": 223280 + }, + { + "epoch": 0.5, + "learning_rate": 2.5146417306100533e-05, + "loss": 0.1345, + "step": 223290 + }, + { + "epoch": 0.5, + "learning_rate": 2.514529876289121e-05, + "loss": 0.1344, + "step": 223300 + }, + { + "epoch": 0.5, + "learning_rate": 2.514418021968189e-05, + "loss": 0.1323, + "step": 223310 + }, + { + "epoch": 0.5, + "learning_rate": 2.5143061676472563e-05, + "loss": 0.1327, + "step": 223320 + }, + { + "epoch": 0.5, + "learning_rate": 2.514194313326324e-05, + "loss": 0.1326, + "step": 223330 + }, + { + "epoch": 0.5, + "learning_rate": 2.5140824590053912e-05, + "loss": 0.1282, + "step": 223340 + }, + { + "epoch": 0.5, + "learning_rate": 2.513970604684459e-05, + "loss": 0.1367, + "step": 223350 + }, + { + "epoch": 0.5, + "learning_rate": 2.5138587503635268e-05, + "loss": 0.127, + "step": 223360 + }, + { + "epoch": 0.5, + "learning_rate": 2.5137468960425943e-05, + "loss": 0.1337, + "step": 223370 + }, + { + "epoch": 0.5, + "learning_rate": 2.513635041721662e-05, + "loss": 0.1357, + "step": 223380 + }, + { + "epoch": 0.5, + "learning_rate": 2.5135231874007292e-05, + "loss": 0.1354, + "step": 223390 + }, + { + "epoch": 0.5, + "learning_rate": 2.513411333079797e-05, + "loss": 0.1314, + "step": 223400 + }, + { + "epoch": 0.5, + "learning_rate": 2.5132994787588648e-05, + "loss": 0.13, + "step": 223410 + }, + { + "epoch": 0.5, + "learning_rate": 2.5131876244379322e-05, + "loss": 0.1286, + "step": 223420 + }, + { + "epoch": 0.5, + "learning_rate": 2.513075770117e-05, + "loss": 0.1297, + "step": 223430 + }, + { + "epoch": 0.5, + "learning_rate": 2.512963915796067e-05, + "loss": 0.1303, + "step": 223440 + }, + { + "epoch": 0.5, + "learning_rate": 2.512852061475135e-05, + "loss": 0.135, + "step": 223450 + }, + { + "epoch": 0.5, + "learning_rate": 2.5127402071542024e-05, + "loss": 0.1363, + "step": 223460 + }, + { + "epoch": 0.5, + "learning_rate": 2.51262835283327e-05, + "loss": 0.1319, + "step": 223470 + }, + { + "epoch": 0.5, + "learning_rate": 2.512516498512338e-05, + "loss": 0.1334, + "step": 223480 + }, + { + "epoch": 0.5, + "learning_rate": 2.512404644191405e-05, + "loss": 0.1284, + "step": 223490 + }, + { + "epoch": 0.5, + "learning_rate": 2.512292789870473e-05, + "loss": 0.1318, + "step": 223500 + }, + { + "epoch": 0.5, + "learning_rate": 2.51218093554954e-05, + "loss": 0.1338, + "step": 223510 + }, + { + "epoch": 0.5, + "learning_rate": 2.512069081228608e-05, + "loss": 0.1293, + "step": 223520 + }, + { + "epoch": 0.5, + "learning_rate": 2.511957226907676e-05, + "loss": 0.1319, + "step": 223530 + }, + { + "epoch": 0.5, + "learning_rate": 2.511845372586743e-05, + "loss": 0.1362, + "step": 223540 + }, + { + "epoch": 0.5, + "learning_rate": 2.5117335182658108e-05, + "loss": 0.1291, + "step": 223550 + }, + { + "epoch": 0.5, + "learning_rate": 2.511621663944878e-05, + "loss": 0.1372, + "step": 223560 + }, + { + "epoch": 0.5, + "learning_rate": 2.5115098096239457e-05, + "loss": 0.1367, + "step": 223570 + }, + { + "epoch": 0.5, + "learning_rate": 2.511397955303014e-05, + "loss": 0.1318, + "step": 223580 + }, + { + "epoch": 0.5, + "learning_rate": 2.511286100982081e-05, + "loss": 0.1379, + "step": 223590 + }, + { + "epoch": 0.5, + "learning_rate": 2.5111742466611488e-05, + "loss": 0.1345, + "step": 223600 + }, + { + "epoch": 0.5, + "learning_rate": 2.511062392340216e-05, + "loss": 0.1331, + "step": 223610 + }, + { + "epoch": 0.5, + "learning_rate": 2.5109505380192837e-05, + "loss": 0.1343, + "step": 223620 + }, + { + "epoch": 0.5, + "learning_rate": 2.5108498691304446e-05, + "loss": 0.1388, + "step": 223630 + }, + { + "epoch": 0.5, + "learning_rate": 2.5107380148095123e-05, + "loss": 0.1331, + "step": 223640 + }, + { + "epoch": 0.5, + "learning_rate": 2.51062616048858e-05, + "loss": 0.1361, + "step": 223650 + }, + { + "epoch": 0.5, + "learning_rate": 2.5105143061676473e-05, + "loss": 0.1317, + "step": 223660 + }, + { + "epoch": 0.5, + "learning_rate": 2.510402451846715e-05, + "loss": 0.1297, + "step": 223670 + }, + { + "epoch": 0.5, + "learning_rate": 2.5102905975257825e-05, + "loss": 0.131, + "step": 223680 + }, + { + "epoch": 0.5, + "learning_rate": 2.5101787432048503e-05, + "loss": 0.1317, + "step": 223690 + }, + { + "epoch": 0.5, + "learning_rate": 2.510066888883918e-05, + "loss": 0.1286, + "step": 223700 + }, + { + "epoch": 0.5, + "learning_rate": 2.5099550345629852e-05, + "loss": 0.1321, + "step": 223710 + }, + { + "epoch": 0.5, + "learning_rate": 2.509843180242053e-05, + "loss": 0.1301, + "step": 223720 + }, + { + "epoch": 0.5, + "learning_rate": 2.50973132592112e-05, + "loss": 0.1289, + "step": 223730 + }, + { + "epoch": 0.5, + "learning_rate": 2.509619471600188e-05, + "loss": 0.1333, + "step": 223740 + }, + { + "epoch": 0.5, + "learning_rate": 2.509507617279256e-05, + "loss": 0.1314, + "step": 223750 + }, + { + "epoch": 0.5, + "learning_rate": 2.509395762958323e-05, + "loss": 0.1339, + "step": 223760 + }, + { + "epoch": 0.5, + "learning_rate": 2.509283908637391e-05, + "loss": 0.1337, + "step": 223770 + }, + { + "epoch": 0.5, + "learning_rate": 2.509172054316458e-05, + "loss": 0.1336, + "step": 223780 + }, + { + "epoch": 0.5, + "learning_rate": 2.509060199995526e-05, + "loss": 0.1306, + "step": 223790 + }, + { + "epoch": 0.5, + "learning_rate": 2.5089483456745936e-05, + "loss": 0.1325, + "step": 223800 + }, + { + "epoch": 0.5, + "learning_rate": 2.508836491353661e-05, + "loss": 0.1334, + "step": 223810 + }, + { + "epoch": 0.5, + "learning_rate": 2.508724637032729e-05, + "loss": 0.1334, + "step": 223820 + }, + { + "epoch": 0.5, + "learning_rate": 2.508612782711796e-05, + "loss": 0.1293, + "step": 223830 + }, + { + "epoch": 0.5, + "learning_rate": 2.5085009283908638e-05, + "loss": 0.133, + "step": 223840 + }, + { + "epoch": 0.5, + "learning_rate": 2.5083890740699312e-05, + "loss": 0.1333, + "step": 223850 + }, + { + "epoch": 0.5, + "learning_rate": 2.508277219748999e-05, + "loss": 0.1348, + "step": 223860 + }, + { + "epoch": 0.5, + "learning_rate": 2.508165365428067e-05, + "loss": 0.1352, + "step": 223870 + }, + { + "epoch": 0.5, + "learning_rate": 2.508053511107134e-05, + "loss": 0.1335, + "step": 223880 + }, + { + "epoch": 0.5, + "learning_rate": 2.5079416567862017e-05, + "loss": 0.1332, + "step": 223890 + }, + { + "epoch": 0.5, + "learning_rate": 2.5078298024652692e-05, + "loss": 0.1381, + "step": 223900 + }, + { + "epoch": 0.5, + "learning_rate": 2.507717948144337e-05, + "loss": 0.1314, + "step": 223910 + }, + { + "epoch": 0.5, + "learning_rate": 2.5076060938234048e-05, + "loss": 0.1284, + "step": 223920 + }, + { + "epoch": 0.5, + "learning_rate": 2.507494239502472e-05, + "loss": 0.1314, + "step": 223930 + }, + { + "epoch": 0.5, + "learning_rate": 2.5073823851815397e-05, + "loss": 0.1324, + "step": 223940 + }, + { + "epoch": 0.5, + "learning_rate": 2.507270530860607e-05, + "loss": 0.1297, + "step": 223950 + }, + { + "epoch": 0.5, + "learning_rate": 2.507158676539675e-05, + "loss": 0.1332, + "step": 223960 + }, + { + "epoch": 0.5, + "learning_rate": 2.5070468222187427e-05, + "loss": 0.1338, + "step": 223970 + }, + { + "epoch": 0.5, + "learning_rate": 2.50693496789781e-05, + "loss": 0.1294, + "step": 223980 + }, + { + "epoch": 0.5, + "learning_rate": 2.5068231135768776e-05, + "loss": 0.1345, + "step": 223990 + }, + { + "epoch": 0.5, + "learning_rate": 2.506711259255945e-05, + "loss": 0.1361, + "step": 224000 + }, + { + "epoch": 0.5, + "eval_NEIMS_canon_smiles": 0.9504, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.1576, + "eval_NEIMS_daylight_tanimoto_simil": 0.5552145677850493, + "eval_NEIMS_exact_mols": 0.1574, + "eval_NEIMS_exact_smiles": 0.15376666666666666, + "eval_NEIMS_loss": 0.1608193963766098, + "eval_NEIMS_matched_formulas": 0.6860666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.4711805599621337, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.15803333333333333, + "eval_NEIMS_runtime": 733.1129, + "eval_NEIMS_samples_per_second": 81.843, + "eval_NEIMS_steps_per_second": 1.279, + "step": 224000 + }, + { + "epoch": 0.5, + "eval_RASSP_canon_smiles": 0.9502120412729155, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.21477944368384144, + "eval_RASSP_daylight_tanimoto_simil": 0.6512818144931016, + "eval_RASSP_exact_mols": 0.21414498948141716, + "eval_RASSP_exact_smiles": 0.20861855945503724, + "eval_RASSP_loss": 0.1288018375635147, + "eval_RASSP_matched_formulas": 0.8269609643703877, + "eval_RASSP_morgan_tanimoto_simil": 0.5301035841925773, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.214261862623969, + "eval_RASSP_runtime": 830.8283, + "eval_RASSP_samples_per_second": 72.09, + "eval_RASSP_steps_per_second": 1.127, + "step": 224000 + }, + { + "epoch": 0.5, + "eval_NEIMS_old_canon_smiles": 0.949, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.15696666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5543772953386225, + "eval_NEIMS_old_exact_mols": 0.15653333333333333, + "eval_NEIMS_old_exact_smiles": 0.15213333333333334, + "eval_NEIMS_old_loss": 0.1601402908563614, + "eval_NEIMS_old_matched_formulas": 0.6873, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4713788870043195, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.15726666666666667, + "eval_NEIMS_old_runtime": 368.9641, + "eval_NEIMS_old_samples_per_second": 81.309, + "eval_NEIMS_old_steps_per_second": 1.271, + "step": 224000 + }, + { + "epoch": 0.5, + "eval_RASSP_old_canon_smiles": 0.9481095872126005, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.23649347615710614, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6673788425323666, + "eval_RASSP_old_exact_mols": 0.23569259518804017, + "eval_RASSP_old_exact_smiles": 0.22918543731437915, + "eval_RASSP_old_loss": 0.12230634689331055, + "eval_RASSP_old_matched_formulas": 0.8320819568191677, + "eval_RASSP_old_morgan_tanimoto_simil": 0.550042058203146, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.23592618547068442, + "eval_RASSP_old_runtime": 416.1576, + "eval_RASSP_old_samples_per_second": 72.009, + "eval_RASSP_old_steps_per_second": 1.127, + "step": 224000 + }, + { + "epoch": 0.5, + "eval_NIST_canon_smiles": 0.8416438939560634, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02335237960038329, + "eval_NIST_daylight_tanimoto_simil": 0.28738896784322476, + "eval_NIST_exact_mols": 0.022216701565106294, + "eval_NIST_exact_smiles": 0.02101004365262448, + "eval_NIST_loss": 1.7980315685272217, + "eval_NIST_matched_formulas": 0.11158036696596516, + "eval_NIST_morgan_tanimoto_simil": 0.24131850904544705, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02328139972317848, + "eval_NIST_runtime": 568.2333, + "eval_NIST_samples_per_second": 49.587, + "eval_NIST_steps_per_second": 0.776, + "step": 224000 + }, + { + "epoch": 0.5, + "learning_rate": 2.506599404935013e-05, + "loss": 0.1338, + "step": 224010 + }, + { + "epoch": 0.5, + "learning_rate": 2.5064875506140807e-05, + "loss": 0.1303, + "step": 224020 + }, + { + "epoch": 0.5, + "learning_rate": 2.5063756962931478e-05, + "loss": 0.1282, + "step": 224030 + }, + { + "epoch": 0.5, + "learning_rate": 2.5062638419722156e-05, + "loss": 0.1316, + "step": 224040 + }, + { + "epoch": 0.5, + "learning_rate": 2.506151987651283e-05, + "loss": 0.1326, + "step": 224050 + }, + { + "epoch": 0.5, + "learning_rate": 2.5060401333303508e-05, + "loss": 0.1313, + "step": 224060 + }, + { + "epoch": 0.5, + "learning_rate": 2.5059282790094186e-05, + "loss": 0.1306, + "step": 224070 + }, + { + "epoch": 0.5, + "learning_rate": 2.5058164246884857e-05, + "loss": 0.129, + "step": 224080 + }, + { + "epoch": 0.5, + "learning_rate": 2.5057045703675535e-05, + "loss": 0.1266, + "step": 224090 + }, + { + "epoch": 0.5, + "learning_rate": 2.505592716046621e-05, + "loss": 0.1356, + "step": 224100 + }, + { + "epoch": 0.5, + "learning_rate": 2.5054808617256888e-05, + "loss": 0.1357, + "step": 224110 + }, + { + "epoch": 0.5, + "learning_rate": 2.5053690074047566e-05, + "loss": 0.1348, + "step": 224120 + }, + { + "epoch": 0.5, + "learning_rate": 2.5052571530838237e-05, + "loss": 0.1337, + "step": 224130 + }, + { + "epoch": 0.5, + "learning_rate": 2.5051452987628915e-05, + "loss": 0.1307, + "step": 224140 + }, + { + "epoch": 0.5, + "learning_rate": 2.5050334444419586e-05, + "loss": 0.1316, + "step": 224150 + }, + { + "epoch": 0.5, + "learning_rate": 2.5049215901210267e-05, + "loss": 0.1301, + "step": 224160 + }, + { + "epoch": 0.5, + "learning_rate": 2.504809735800094e-05, + "loss": 0.1341, + "step": 224170 + }, + { + "epoch": 0.5, + "learning_rate": 2.5046978814791616e-05, + "loss": 0.1292, + "step": 224180 + }, + { + "epoch": 0.5, + "learning_rate": 2.5045860271582294e-05, + "loss": 0.1331, + "step": 224190 + }, + { + "epoch": 0.5, + "learning_rate": 2.5044741728372965e-05, + "loss": 0.1341, + "step": 224200 + }, + { + "epoch": 0.5, + "learning_rate": 2.5043623185163643e-05, + "loss": 0.1343, + "step": 224210 + }, + { + "epoch": 0.5, + "learning_rate": 2.5042504641954318e-05, + "loss": 0.1341, + "step": 224220 + }, + { + "epoch": 0.5, + "learning_rate": 2.5041386098744996e-05, + "loss": 0.1307, + "step": 224230 + }, + { + "epoch": 0.5, + "learning_rate": 2.5040267555535674e-05, + "loss": 0.1309, + "step": 224240 + }, + { + "epoch": 0.5, + "learning_rate": 2.5039149012326345e-05, + "loss": 0.1364, + "step": 224250 + }, + { + "epoch": 0.5, + "learning_rate": 2.5038030469117023e-05, + "loss": 0.1362, + "step": 224260 + }, + { + "epoch": 0.5, + "learning_rate": 2.5036911925907697e-05, + "loss": 0.1378, + "step": 224270 + }, + { + "epoch": 0.5, + "learning_rate": 2.5035793382698375e-05, + "loss": 0.1334, + "step": 224280 + }, + { + "epoch": 0.5, + "learning_rate": 2.5034674839489053e-05, + "loss": 0.1277, + "step": 224290 + }, + { + "epoch": 0.5, + "learning_rate": 2.5033556296279724e-05, + "loss": 0.1295, + "step": 224300 + }, + { + "epoch": 0.5, + "learning_rate": 2.5032437753070402e-05, + "loss": 0.132, + "step": 224310 + }, + { + "epoch": 0.5, + "learning_rate": 2.5031319209861077e-05, + "loss": 0.1313, + "step": 224320 + }, + { + "epoch": 0.5, + "learning_rate": 2.5030200666651755e-05, + "loss": 0.1313, + "step": 224330 + }, + { + "epoch": 0.5, + "learning_rate": 2.5029082123442433e-05, + "loss": 0.1328, + "step": 224340 + }, + { + "epoch": 0.5, + "learning_rate": 2.5027963580233104e-05, + "loss": 0.1349, + "step": 224350 + }, + { + "epoch": 0.5, + "learning_rate": 2.5026845037023782e-05, + "loss": 0.1338, + "step": 224360 + }, + { + "epoch": 0.5, + "learning_rate": 2.5025726493814456e-05, + "loss": 0.1327, + "step": 224370 + }, + { + "epoch": 0.5, + "learning_rate": 2.5024607950605134e-05, + "loss": 0.1332, + "step": 224380 + }, + { + "epoch": 0.5, + "learning_rate": 2.5023489407395812e-05, + "loss": 0.133, + "step": 224390 + }, + { + "epoch": 0.5, + "learning_rate": 2.5022370864186483e-05, + "loss": 0.134, + "step": 224400 + }, + { + "epoch": 0.5, + "learning_rate": 2.502125232097716e-05, + "loss": 0.1322, + "step": 224410 + }, + { + "epoch": 0.5, + "learning_rate": 2.5020133777767836e-05, + "loss": 0.1307, + "step": 224420 + }, + { + "epoch": 0.5, + "learning_rate": 2.5019015234558514e-05, + "loss": 0.1362, + "step": 224430 + }, + { + "epoch": 0.5, + "learning_rate": 2.501789669134919e-05, + "loss": 0.136, + "step": 224440 + }, + { + "epoch": 0.5, + "learning_rate": 2.5016778148139863e-05, + "loss": 0.1363, + "step": 224450 + }, + { + "epoch": 0.5, + "learning_rate": 2.501565960493054e-05, + "loss": 0.1347, + "step": 224460 + }, + { + "epoch": 0.5, + "learning_rate": 2.5014541061721215e-05, + "loss": 0.1343, + "step": 224470 + }, + { + "epoch": 0.5, + "learning_rate": 2.5013422518511893e-05, + "loss": 0.1325, + "step": 224480 + }, + { + "epoch": 0.5, + "learning_rate": 2.5012303975302564e-05, + "loss": 0.1324, + "step": 224490 + }, + { + "epoch": 0.5, + "learning_rate": 2.5011185432093242e-05, + "loss": 0.135, + "step": 224500 + }, + { + "epoch": 0.5, + "learning_rate": 2.501006688888392e-05, + "loss": 0.1327, + "step": 224510 + }, + { + "epoch": 0.5, + "learning_rate": 2.5008948345674595e-05, + "loss": 0.1338, + "step": 224520 + }, + { + "epoch": 0.5, + "learning_rate": 2.5007829802465273e-05, + "loss": 0.1319, + "step": 224530 + }, + { + "epoch": 0.5, + "learning_rate": 2.5006711259255944e-05, + "loss": 0.1333, + "step": 224540 + }, + { + "epoch": 0.5, + "learning_rate": 2.5005592716046622e-05, + "loss": 0.1286, + "step": 224550 + }, + { + "epoch": 0.5, + "learning_rate": 2.50044741728373e-05, + "loss": 0.1336, + "step": 224560 + }, + { + "epoch": 0.5, + "learning_rate": 2.5003355629627974e-05, + "loss": 0.1338, + "step": 224570 + }, + { + "epoch": 0.5, + "learning_rate": 2.5002237086418652e-05, + "loss": 0.1296, + "step": 224580 + }, + { + "epoch": 0.5, + "learning_rate": 2.5001118543209323e-05, + "loss": 0.1301, + "step": 224590 + }, + { + "epoch": 0.5, + "learning_rate": 2.5e-05, + "loss": 0.1361, + "step": 224600 + }, + { + "epoch": 0.5, + "learning_rate": 2.4998881456790676e-05, + "loss": 0.1281, + "step": 224610 + }, + { + "epoch": 0.5, + "learning_rate": 2.499776291358135e-05, + "loss": 0.1283, + "step": 224620 + }, + { + "epoch": 0.5, + "learning_rate": 2.4996644370372028e-05, + "loss": 0.1374, + "step": 224630 + }, + { + "epoch": 0.5, + "learning_rate": 2.4995525827162706e-05, + "loss": 0.1344, + "step": 224640 + }, + { + "epoch": 0.5, + "learning_rate": 2.499440728395338e-05, + "loss": 0.1344, + "step": 224650 + }, + { + "epoch": 0.5, + "learning_rate": 2.4993288740744055e-05, + "loss": 0.1319, + "step": 224660 + }, + { + "epoch": 0.5, + "learning_rate": 2.499217019753473e-05, + "loss": 0.1321, + "step": 224670 + }, + { + "epoch": 0.5, + "learning_rate": 2.4991051654325408e-05, + "loss": 0.1293, + "step": 224680 + }, + { + "epoch": 0.5, + "learning_rate": 2.4989933111116086e-05, + "loss": 0.1354, + "step": 224690 + }, + { + "epoch": 0.5, + "learning_rate": 2.498881456790676e-05, + "loss": 0.1288, + "step": 224700 + }, + { + "epoch": 0.5, + "learning_rate": 2.4987696024697435e-05, + "loss": 0.1333, + "step": 224710 + }, + { + "epoch": 0.5, + "learning_rate": 2.498657748148811e-05, + "loss": 0.1301, + "step": 224720 + }, + { + "epoch": 0.5, + "learning_rate": 2.4985458938278787e-05, + "loss": 0.1382, + "step": 224730 + }, + { + "epoch": 0.5, + "learning_rate": 2.4984340395069465e-05, + "loss": 0.1302, + "step": 224740 + }, + { + "epoch": 0.5, + "learning_rate": 2.498322185186014e-05, + "loss": 0.1281, + "step": 224750 + }, + { + "epoch": 0.5, + "learning_rate": 2.4982103308650814e-05, + "loss": 0.1356, + "step": 224760 + }, + { + "epoch": 0.5, + "learning_rate": 2.498098476544149e-05, + "loss": 0.132, + "step": 224770 + }, + { + "epoch": 0.5, + "learning_rate": 2.4979866222232167e-05, + "loss": 0.1369, + "step": 224780 + }, + { + "epoch": 0.5, + "learning_rate": 2.4978747679022845e-05, + "loss": 0.1358, + "step": 224790 + }, + { + "epoch": 0.5, + "learning_rate": 2.497762913581352e-05, + "loss": 0.1333, + "step": 224800 + }, + { + "epoch": 0.5, + "learning_rate": 2.4976510592604194e-05, + "loss": 0.1332, + "step": 224810 + }, + { + "epoch": 0.5, + "learning_rate": 2.4975392049394868e-05, + "loss": 0.1336, + "step": 224820 + }, + { + "epoch": 0.5, + "learning_rate": 2.4974273506185543e-05, + "loss": 0.1342, + "step": 224830 + }, + { + "epoch": 0.5, + "learning_rate": 2.497315496297622e-05, + "loss": 0.1363, + "step": 224840 + }, + { + "epoch": 0.5, + "learning_rate": 2.49720364197669e-05, + "loss": 0.134, + "step": 224850 + }, + { + "epoch": 0.5, + "learning_rate": 2.4970917876557573e-05, + "loss": 0.1372, + "step": 224860 + }, + { + "epoch": 0.5, + "learning_rate": 2.4969799333348248e-05, + "loss": 0.1334, + "step": 224870 + }, + { + "epoch": 0.5, + "learning_rate": 2.4968680790138922e-05, + "loss": 0.1324, + "step": 224880 + }, + { + "epoch": 0.5, + "learning_rate": 2.49675622469296e-05, + "loss": 0.1362, + "step": 224890 + }, + { + "epoch": 0.5, + "learning_rate": 2.4966443703720278e-05, + "loss": 0.1324, + "step": 224900 + }, + { + "epoch": 0.5, + "learning_rate": 2.4965325160510953e-05, + "loss": 0.1378, + "step": 224910 + }, + { + "epoch": 0.5, + "learning_rate": 2.4964206617301627e-05, + "loss": 0.1349, + "step": 224920 + }, + { + "epoch": 0.5, + "learning_rate": 2.49630880740923e-05, + "loss": 0.1327, + "step": 224930 + }, + { + "epoch": 0.5, + "learning_rate": 2.496196953088298e-05, + "loss": 0.1325, + "step": 224940 + }, + { + "epoch": 0.5, + "learning_rate": 2.4960850987673658e-05, + "loss": 0.1307, + "step": 224950 + }, + { + "epoch": 0.5, + "learning_rate": 2.4959732444464332e-05, + "loss": 0.1375, + "step": 224960 + }, + { + "epoch": 0.5, + "learning_rate": 2.4958613901255007e-05, + "loss": 0.1318, + "step": 224970 + }, + { + "epoch": 0.5, + "learning_rate": 2.495749535804568e-05, + "loss": 0.1324, + "step": 224980 + }, + { + "epoch": 0.5, + "learning_rate": 2.495637681483636e-05, + "loss": 0.1343, + "step": 224990 + }, + { + "epoch": 0.5, + "learning_rate": 2.4955258271627034e-05, + "loss": 0.134, + "step": 225000 + }, + { + "epoch": 0.5, + "learning_rate": 2.495413972841771e-05, + "loss": 0.1276, + "step": 225010 + }, + { + "epoch": 0.5, + "learning_rate": 2.4953021185208386e-05, + "loss": 0.1272, + "step": 225020 + }, + { + "epoch": 0.5, + "learning_rate": 2.495190264199906e-05, + "loss": 0.1372, + "step": 225030 + }, + { + "epoch": 0.5, + "learning_rate": 2.4950784098789735e-05, + "loss": 0.1337, + "step": 225040 + }, + { + "epoch": 0.5, + "learning_rate": 2.4949665555580413e-05, + "loss": 0.136, + "step": 225050 + }, + { + "epoch": 0.5, + "learning_rate": 2.494854701237109e-05, + "loss": 0.1324, + "step": 225060 + }, + { + "epoch": 0.5, + "learning_rate": 2.4947428469161766e-05, + "loss": 0.1374, + "step": 225070 + }, + { + "epoch": 0.5, + "learning_rate": 2.494630992595244e-05, + "loss": 0.1325, + "step": 225080 + }, + { + "epoch": 0.5, + "learning_rate": 2.4945191382743115e-05, + "loss": 0.1325, + "step": 225090 + }, + { + "epoch": 0.5, + "learning_rate": 2.4944072839533793e-05, + "loss": 0.1289, + "step": 225100 + }, + { + "epoch": 0.5, + "learning_rate": 2.494295429632447e-05, + "loss": 0.1378, + "step": 225110 + }, + { + "epoch": 0.5, + "learning_rate": 2.4941835753115145e-05, + "loss": 0.1356, + "step": 225120 + }, + { + "epoch": 0.5, + "learning_rate": 2.494071720990582e-05, + "loss": 0.1271, + "step": 225130 + }, + { + "epoch": 0.5, + "learning_rate": 2.4939598666696494e-05, + "loss": 0.1279, + "step": 225140 + }, + { + "epoch": 0.5, + "learning_rate": 2.4938480123487172e-05, + "loss": 0.1326, + "step": 225150 + }, + { + "epoch": 0.5, + "learning_rate": 2.4937361580277847e-05, + "loss": 0.1357, + "step": 225160 + }, + { + "epoch": 0.5, + "learning_rate": 2.4936243037068524e-05, + "loss": 0.1312, + "step": 225170 + }, + { + "epoch": 0.5, + "learning_rate": 2.49351244938592e-05, + "loss": 0.1363, + "step": 225180 + }, + { + "epoch": 0.5, + "learning_rate": 2.4934005950649874e-05, + "loss": 0.1304, + "step": 225190 + }, + { + "epoch": 0.5, + "learning_rate": 2.493288740744055e-05, + "loss": 0.1336, + "step": 225200 + }, + { + "epoch": 0.5, + "learning_rate": 2.4931768864231226e-05, + "loss": 0.1365, + "step": 225210 + }, + { + "epoch": 0.5, + "learning_rate": 2.4930650321021904e-05, + "loss": 0.1313, + "step": 225220 + }, + { + "epoch": 0.5, + "learning_rate": 2.492953177781258e-05, + "loss": 0.1366, + "step": 225230 + }, + { + "epoch": 0.5, + "learning_rate": 2.4928413234603253e-05, + "loss": 0.1344, + "step": 225240 + }, + { + "epoch": 0.5, + "learning_rate": 2.4927294691393928e-05, + "loss": 0.1288, + "step": 225250 + }, + { + "epoch": 0.5, + "learning_rate": 2.4926176148184606e-05, + "loss": 0.1304, + "step": 225260 + }, + { + "epoch": 0.5, + "learning_rate": 2.4925057604975283e-05, + "loss": 0.1327, + "step": 225270 + }, + { + "epoch": 0.5, + "learning_rate": 2.4923939061765958e-05, + "loss": 0.1339, + "step": 225280 + }, + { + "epoch": 0.5, + "learning_rate": 2.4922820518556633e-05, + "loss": 0.1314, + "step": 225290 + }, + { + "epoch": 0.5, + "learning_rate": 2.4921701975347307e-05, + "loss": 0.1323, + "step": 225300 + }, + { + "epoch": 0.5, + "learning_rate": 2.4920583432137985e-05, + "loss": 0.1319, + "step": 225310 + }, + { + "epoch": 0.5, + "learning_rate": 2.491946488892866e-05, + "loss": 0.1275, + "step": 225320 + }, + { + "epoch": 0.5, + "learning_rate": 2.4918346345719337e-05, + "loss": 0.1316, + "step": 225330 + }, + { + "epoch": 0.5, + "learning_rate": 2.4917227802510012e-05, + "loss": 0.1366, + "step": 225340 + }, + { + "epoch": 0.5, + "learning_rate": 2.4916109259300687e-05, + "loss": 0.1393, + "step": 225350 + }, + { + "epoch": 0.5, + "learning_rate": 2.4914990716091364e-05, + "loss": 0.134, + "step": 225360 + }, + { + "epoch": 0.5, + "learning_rate": 2.491387217288204e-05, + "loss": 0.1356, + "step": 225370 + }, + { + "epoch": 0.5, + "learning_rate": 2.4912753629672717e-05, + "loss": 0.134, + "step": 225380 + }, + { + "epoch": 0.5, + "learning_rate": 2.491163508646339e-05, + "loss": 0.1322, + "step": 225390 + }, + { + "epoch": 0.5, + "learning_rate": 2.4910516543254066e-05, + "loss": 0.1323, + "step": 225400 + }, + { + "epoch": 0.5, + "learning_rate": 2.4909398000044744e-05, + "loss": 0.1312, + "step": 225410 + }, + { + "epoch": 0.5, + "learning_rate": 2.490827945683542e-05, + "loss": 0.1337, + "step": 225420 + }, + { + "epoch": 0.5, + "learning_rate": 2.4907160913626096e-05, + "loss": 0.1315, + "step": 225430 + }, + { + "epoch": 0.5, + "learning_rate": 2.490604237041677e-05, + "loss": 0.132, + "step": 225440 + }, + { + "epoch": 0.5, + "learning_rate": 2.4904923827207445e-05, + "loss": 0.1297, + "step": 225450 + }, + { + "epoch": 0.5, + "learning_rate": 2.4903805283998123e-05, + "loss": 0.133, + "step": 225460 + }, + { + "epoch": 0.5, + "learning_rate": 2.4902686740788798e-05, + "loss": 0.1346, + "step": 225470 + }, + { + "epoch": 0.5, + "learning_rate": 2.4901568197579472e-05, + "loss": 0.134, + "step": 225480 + }, + { + "epoch": 0.5, + "learning_rate": 2.490044965437015e-05, + "loss": 0.1308, + "step": 225490 + }, + { + "epoch": 0.5, + "learning_rate": 2.4899331111160825e-05, + "loss": 0.1348, + "step": 225500 + }, + { + "epoch": 0.5, + "learning_rate": 2.48982125679515e-05, + "loss": 0.1304, + "step": 225510 + }, + { + "epoch": 0.5, + "learning_rate": 2.4897094024742177e-05, + "loss": 0.1316, + "step": 225520 + }, + { + "epoch": 0.5, + "learning_rate": 2.4895975481532852e-05, + "loss": 0.1322, + "step": 225530 + }, + { + "epoch": 0.5, + "learning_rate": 2.489485693832353e-05, + "loss": 0.1321, + "step": 225540 + }, + { + "epoch": 0.5, + "learning_rate": 2.4893738395114204e-05, + "loss": 0.132, + "step": 225550 + }, + { + "epoch": 0.5, + "learning_rate": 2.489261985190488e-05, + "loss": 0.1325, + "step": 225560 + }, + { + "epoch": 0.5, + "learning_rate": 2.4891501308695557e-05, + "loss": 0.1335, + "step": 225570 + }, + { + "epoch": 0.5, + "learning_rate": 2.489038276548623e-05, + "loss": 0.1304, + "step": 225580 + }, + { + "epoch": 0.5, + "learning_rate": 2.488926422227691e-05, + "loss": 0.1339, + "step": 225590 + }, + { + "epoch": 0.5, + "learning_rate": 2.4888145679067584e-05, + "loss": 0.1317, + "step": 225600 + }, + { + "epoch": 0.5, + "learning_rate": 2.488702713585826e-05, + "loss": 0.138, + "step": 225610 + }, + { + "epoch": 0.5, + "learning_rate": 2.4885908592648936e-05, + "loss": 0.1285, + "step": 225620 + }, + { + "epoch": 0.5, + "learning_rate": 2.488479004943961e-05, + "loss": 0.1344, + "step": 225630 + }, + { + "epoch": 0.5, + "learning_rate": 2.4883671506230285e-05, + "loss": 0.1346, + "step": 225640 + }, + { + "epoch": 0.5, + "learning_rate": 2.4882552963020963e-05, + "loss": 0.1306, + "step": 225650 + }, + { + "epoch": 0.5, + "learning_rate": 2.4881434419811638e-05, + "loss": 0.1299, + "step": 225660 + }, + { + "epoch": 0.5, + "learning_rate": 2.4880315876602316e-05, + "loss": 0.1313, + "step": 225670 + }, + { + "epoch": 0.5, + "learning_rate": 2.487919733339299e-05, + "loss": 0.1336, + "step": 225680 + }, + { + "epoch": 0.5, + "learning_rate": 2.4878078790183665e-05, + "loss": 0.134, + "step": 225690 + }, + { + "epoch": 0.5, + "learning_rate": 2.4876960246974343e-05, + "loss": 0.134, + "step": 225700 + }, + { + "epoch": 0.5, + "learning_rate": 2.4875841703765017e-05, + "loss": 0.131, + "step": 225710 + }, + { + "epoch": 0.5, + "learning_rate": 2.4874723160555692e-05, + "loss": 0.1319, + "step": 225720 + }, + { + "epoch": 0.5, + "learning_rate": 2.487360461734637e-05, + "loss": 0.1328, + "step": 225730 + }, + { + "epoch": 0.5, + "learning_rate": 2.4872486074137044e-05, + "loss": 0.1295, + "step": 225740 + }, + { + "epoch": 0.5, + "learning_rate": 2.4871367530927722e-05, + "loss": 0.1247, + "step": 225750 + }, + { + "epoch": 0.5, + "learning_rate": 2.4870248987718397e-05, + "loss": 0.1292, + "step": 225760 + }, + { + "epoch": 0.5, + "learning_rate": 2.486913044450907e-05, + "loss": 0.1346, + "step": 225770 + }, + { + "epoch": 0.5, + "learning_rate": 2.486801190129975e-05, + "loss": 0.1353, + "step": 225780 + }, + { + "epoch": 0.5, + "learning_rate": 2.4866893358090424e-05, + "loss": 0.1355, + "step": 225790 + }, + { + "epoch": 0.5, + "learning_rate": 2.48657748148811e-05, + "loss": 0.1329, + "step": 225800 + }, + { + "epoch": 0.5, + "learning_rate": 2.4864656271671776e-05, + "loss": 0.1323, + "step": 225810 + }, + { + "epoch": 0.5, + "learning_rate": 2.486353772846245e-05, + "loss": 0.132, + "step": 225820 + }, + { + "epoch": 0.5, + "learning_rate": 2.486241918525313e-05, + "loss": 0.1322, + "step": 225830 + }, + { + "epoch": 0.5, + "learning_rate": 2.4861300642043803e-05, + "loss": 0.1331, + "step": 225840 + }, + { + "epoch": 0.5, + "learning_rate": 2.4860182098834478e-05, + "loss": 0.1286, + "step": 225850 + }, + { + "epoch": 0.5, + "learning_rate": 2.4859063555625156e-05, + "loss": 0.1337, + "step": 225860 + }, + { + "epoch": 0.5, + "learning_rate": 2.485794501241583e-05, + "loss": 0.1323, + "step": 225870 + }, + { + "epoch": 0.5, + "learning_rate": 2.4856826469206508e-05, + "loss": 0.1329, + "step": 225880 + }, + { + "epoch": 0.5, + "learning_rate": 2.4855707925997183e-05, + "loss": 0.133, + "step": 225890 + }, + { + "epoch": 0.5, + "learning_rate": 2.4854589382787857e-05, + "loss": 0.1314, + "step": 225900 + }, + { + "epoch": 0.5, + "learning_rate": 2.4853470839578535e-05, + "loss": 0.1339, + "step": 225910 + }, + { + "epoch": 0.5, + "learning_rate": 2.485235229636921e-05, + "loss": 0.1361, + "step": 225920 + }, + { + "epoch": 0.5, + "learning_rate": 2.4851233753159884e-05, + "loss": 0.1314, + "step": 225930 + }, + { + "epoch": 0.5, + "learning_rate": 2.4850115209950562e-05, + "loss": 0.1351, + "step": 225940 + }, + { + "epoch": 0.5, + "learning_rate": 2.4848996666741237e-05, + "loss": 0.1335, + "step": 225950 + }, + { + "epoch": 0.5, + "learning_rate": 2.484787812353191e-05, + "loss": 0.1349, + "step": 225960 + }, + { + "epoch": 0.5, + "learning_rate": 2.484675958032259e-05, + "loss": 0.1342, + "step": 225970 + }, + { + "epoch": 0.5, + "learning_rate": 2.4845641037113264e-05, + "loss": 0.1345, + "step": 225980 + }, + { + "epoch": 0.5, + "learning_rate": 2.4844522493903942e-05, + "loss": 0.1363, + "step": 225990 + }, + { + "epoch": 0.5, + "learning_rate": 2.4843403950694616e-05, + "loss": 0.1361, + "step": 226000 + }, + { + "epoch": 0.5, + "learning_rate": 2.484228540748529e-05, + "loss": 0.1248, + "step": 226010 + }, + { + "epoch": 0.5, + "learning_rate": 2.484116686427597e-05, + "loss": 0.1311, + "step": 226020 + }, + { + "epoch": 0.5, + "learning_rate": 2.4840048321066643e-05, + "loss": 0.1347, + "step": 226030 + }, + { + "epoch": 0.5, + "learning_rate": 2.483892977785732e-05, + "loss": 0.1342, + "step": 226040 + }, + { + "epoch": 0.5, + "learning_rate": 2.4837811234647996e-05, + "loss": 0.1328, + "step": 226050 + }, + { + "epoch": 0.5, + "learning_rate": 2.483669269143867e-05, + "loss": 0.135, + "step": 226060 + }, + { + "epoch": 0.5, + "learning_rate": 2.4835574148229348e-05, + "loss": 0.1327, + "step": 226070 + }, + { + "epoch": 0.5, + "learning_rate": 2.4834455605020023e-05, + "loss": 0.134, + "step": 226080 + }, + { + "epoch": 0.5, + "learning_rate": 2.48333370618107e-05, + "loss": 0.1333, + "step": 226090 + }, + { + "epoch": 0.5, + "learning_rate": 2.4832218518601375e-05, + "loss": 0.1321, + "step": 226100 + }, + { + "epoch": 0.5, + "learning_rate": 2.483109997539205e-05, + "loss": 0.1315, + "step": 226110 + }, + { + "epoch": 0.5, + "learning_rate": 2.4829981432182724e-05, + "loss": 0.1326, + "step": 226120 + }, + { + "epoch": 0.5, + "learning_rate": 2.4828862888973402e-05, + "loss": 0.1312, + "step": 226130 + }, + { + "epoch": 0.5, + "learning_rate": 2.4827744345764077e-05, + "loss": 0.1327, + "step": 226140 + }, + { + "epoch": 0.5, + "learning_rate": 2.4826625802554755e-05, + "loss": 0.1264, + "step": 226150 + }, + { + "epoch": 0.5, + "learning_rate": 2.482550725934543e-05, + "loss": 0.1344, + "step": 226160 + }, + { + "epoch": 0.5, + "learning_rate": 2.4824388716136104e-05, + "loss": 0.1302, + "step": 226170 + }, + { + "epoch": 0.5, + "learning_rate": 2.4823270172926782e-05, + "loss": 0.1323, + "step": 226180 + }, + { + "epoch": 0.5, + "learning_rate": 2.4822151629717456e-05, + "loss": 0.1298, + "step": 226190 + }, + { + "epoch": 0.5, + "learning_rate": 2.4821033086508134e-05, + "loss": 0.1293, + "step": 226200 + }, + { + "epoch": 0.5, + "learning_rate": 2.481991454329881e-05, + "loss": 0.1288, + "step": 226210 + }, + { + "epoch": 0.5, + "learning_rate": 2.4818796000089483e-05, + "loss": 0.1334, + "step": 226220 + }, + { + "epoch": 0.5, + "learning_rate": 2.481767745688016e-05, + "loss": 0.1362, + "step": 226230 + }, + { + "epoch": 0.5, + "learning_rate": 2.4816558913670836e-05, + "loss": 0.1338, + "step": 226240 + }, + { + "epoch": 0.51, + "learning_rate": 2.4815440370461514e-05, + "loss": 0.1317, + "step": 226250 + }, + { + "epoch": 0.51, + "learning_rate": 2.4814321827252188e-05, + "loss": 0.1277, + "step": 226260 + }, + { + "epoch": 0.51, + "learning_rate": 2.4813203284042863e-05, + "loss": 0.1326, + "step": 226270 + }, + { + "epoch": 0.51, + "learning_rate": 2.4812084740833537e-05, + "loss": 0.1352, + "step": 226280 + }, + { + "epoch": 0.51, + "learning_rate": 2.4810966197624215e-05, + "loss": 0.1333, + "step": 226290 + }, + { + "epoch": 0.51, + "learning_rate": 2.4809847654414893e-05, + "loss": 0.135, + "step": 226300 + }, + { + "epoch": 0.51, + "learning_rate": 2.4808729111205568e-05, + "loss": 0.1296, + "step": 226310 + }, + { + "epoch": 0.51, + "learning_rate": 2.4807610567996242e-05, + "loss": 0.1375, + "step": 226320 + }, + { + "epoch": 0.51, + "learning_rate": 2.4806492024786917e-05, + "loss": 0.1318, + "step": 226330 + }, + { + "epoch": 0.51, + "learning_rate": 2.4805373481577595e-05, + "loss": 0.1311, + "step": 226340 + }, + { + "epoch": 0.51, + "learning_rate": 2.4804254938368273e-05, + "loss": 0.1277, + "step": 226350 + }, + { + "epoch": 0.51, + "learning_rate": 2.4803136395158947e-05, + "loss": 0.133, + "step": 226360 + }, + { + "epoch": 0.51, + "learning_rate": 2.4802017851949622e-05, + "loss": 0.1301, + "step": 226370 + }, + { + "epoch": 0.51, + "learning_rate": 2.4800899308740296e-05, + "loss": 0.1324, + "step": 226380 + }, + { + "epoch": 0.51, + "learning_rate": 2.4799780765530974e-05, + "loss": 0.1348, + "step": 226390 + }, + { + "epoch": 0.51, + "learning_rate": 2.479866222232165e-05, + "loss": 0.1299, + "step": 226400 + }, + { + "epoch": 0.51, + "learning_rate": 2.4797543679112327e-05, + "loss": 0.1302, + "step": 226410 + }, + { + "epoch": 0.51, + "learning_rate": 2.4796425135903e-05, + "loss": 0.1316, + "step": 226420 + }, + { + "epoch": 0.51, + "learning_rate": 2.4795306592693676e-05, + "loss": 0.1319, + "step": 226430 + }, + { + "epoch": 0.51, + "learning_rate": 2.479418804948435e-05, + "loss": 0.1339, + "step": 226440 + }, + { + "epoch": 0.51, + "learning_rate": 2.4793069506275028e-05, + "loss": 0.1273, + "step": 226450 + }, + { + "epoch": 0.51, + "learning_rate": 2.4791950963065706e-05, + "loss": 0.1342, + "step": 226460 + }, + { + "epoch": 0.51, + "learning_rate": 2.479083241985638e-05, + "loss": 0.1325, + "step": 226470 + }, + { + "epoch": 0.51, + "learning_rate": 2.4789713876647055e-05, + "loss": 0.1283, + "step": 226480 + }, + { + "epoch": 0.51, + "learning_rate": 2.478859533343773e-05, + "loss": 0.1331, + "step": 226490 + }, + { + "epoch": 0.51, + "learning_rate": 2.4787476790228408e-05, + "loss": 0.1316, + "step": 226500 + }, + { + "epoch": 0.51, + "learning_rate": 2.4786358247019086e-05, + "loss": 0.132, + "step": 226510 + }, + { + "epoch": 0.51, + "learning_rate": 2.478523970380976e-05, + "loss": 0.1315, + "step": 226520 + }, + { + "epoch": 0.51, + "learning_rate": 2.4784121160600435e-05, + "loss": 0.1339, + "step": 226530 + }, + { + "epoch": 0.51, + "learning_rate": 2.478300261739111e-05, + "loss": 0.1329, + "step": 226540 + }, + { + "epoch": 0.51, + "learning_rate": 2.4781884074181787e-05, + "loss": 0.1298, + "step": 226550 + }, + { + "epoch": 0.51, + "learning_rate": 2.4780765530972465e-05, + "loss": 0.1371, + "step": 226560 + }, + { + "epoch": 0.51, + "learning_rate": 2.477964698776314e-05, + "loss": 0.1333, + "step": 226570 + }, + { + "epoch": 0.51, + "learning_rate": 2.4778528444553814e-05, + "loss": 0.1306, + "step": 226580 + }, + { + "epoch": 0.51, + "learning_rate": 2.477740990134449e-05, + "loss": 0.1324, + "step": 226590 + }, + { + "epoch": 0.51, + "learning_rate": 2.4776291358135163e-05, + "loss": 0.1329, + "step": 226600 + }, + { + "epoch": 0.51, + "learning_rate": 2.477517281492584e-05, + "loss": 0.1327, + "step": 226610 + }, + { + "epoch": 0.51, + "learning_rate": 2.477405427171652e-05, + "loss": 0.1344, + "step": 226620 + }, + { + "epoch": 0.51, + "learning_rate": 2.4772935728507194e-05, + "loss": 0.1331, + "step": 226630 + }, + { + "epoch": 0.51, + "learning_rate": 2.4771817185297868e-05, + "loss": 0.1334, + "step": 226640 + }, + { + "epoch": 0.51, + "learning_rate": 2.4770698642088543e-05, + "loss": 0.127, + "step": 226650 + }, + { + "epoch": 0.51, + "learning_rate": 2.476958009887922e-05, + "loss": 0.1296, + "step": 226660 + }, + { + "epoch": 0.51, + "learning_rate": 2.47684615556699e-05, + "loss": 0.1324, + "step": 226670 + }, + { + "epoch": 0.51, + "learning_rate": 2.4767343012460573e-05, + "loss": 0.1282, + "step": 226680 + }, + { + "epoch": 0.51, + "learning_rate": 2.4766224469251248e-05, + "loss": 0.134, + "step": 226690 + }, + { + "epoch": 0.51, + "learning_rate": 2.4765105926041922e-05, + "loss": 0.1371, + "step": 226700 + }, + { + "epoch": 0.51, + "learning_rate": 2.47639873828326e-05, + "loss": 0.1333, + "step": 226710 + }, + { + "epoch": 0.51, + "learning_rate": 2.4762868839623278e-05, + "loss": 0.1321, + "step": 226720 + }, + { + "epoch": 0.51, + "learning_rate": 2.4761750296413953e-05, + "loss": 0.1292, + "step": 226730 + }, + { + "epoch": 0.51, + "learning_rate": 2.4760631753204627e-05, + "loss": 0.1295, + "step": 226740 + }, + { + "epoch": 0.51, + "learning_rate": 2.47595132099953e-05, + "loss": 0.1267, + "step": 226750 + }, + { + "epoch": 0.51, + "learning_rate": 2.4758394666785976e-05, + "loss": 0.1294, + "step": 226760 + }, + { + "epoch": 0.51, + "learning_rate": 2.4757276123576657e-05, + "loss": 0.1296, + "step": 226770 + }, + { + "epoch": 0.51, + "learning_rate": 2.4756157580367332e-05, + "loss": 0.1334, + "step": 226780 + }, + { + "epoch": 0.51, + "learning_rate": 2.4755039037158007e-05, + "loss": 0.1353, + "step": 226790 + }, + { + "epoch": 0.51, + "learning_rate": 2.475392049394868e-05, + "loss": 0.1321, + "step": 226800 + }, + { + "epoch": 0.51, + "learning_rate": 2.4752801950739356e-05, + "loss": 0.1325, + "step": 226810 + }, + { + "epoch": 0.51, + "learning_rate": 2.4751683407530034e-05, + "loss": 0.128, + "step": 226820 + }, + { + "epoch": 0.51, + "learning_rate": 2.475056486432071e-05, + "loss": 0.1287, + "step": 226830 + }, + { + "epoch": 0.51, + "learning_rate": 2.4749446321111386e-05, + "loss": 0.1325, + "step": 226840 + }, + { + "epoch": 0.51, + "learning_rate": 2.474832777790206e-05, + "loss": 0.1299, + "step": 226850 + }, + { + "epoch": 0.51, + "learning_rate": 2.4747209234692735e-05, + "loss": 0.1328, + "step": 226860 + }, + { + "epoch": 0.51, + "learning_rate": 2.4746090691483413e-05, + "loss": 0.1342, + "step": 226870 + }, + { + "epoch": 0.51, + "learning_rate": 2.474497214827409e-05, + "loss": 0.132, + "step": 226880 + }, + { + "epoch": 0.51, + "learning_rate": 2.4743853605064766e-05, + "loss": 0.1337, + "step": 226890 + }, + { + "epoch": 0.51, + "learning_rate": 2.474273506185544e-05, + "loss": 0.1296, + "step": 226900 + }, + { + "epoch": 0.51, + "learning_rate": 2.4741616518646115e-05, + "loss": 0.13, + "step": 226910 + }, + { + "epoch": 0.51, + "learning_rate": 2.4740497975436793e-05, + "loss": 0.1309, + "step": 226920 + }, + { + "epoch": 0.51, + "learning_rate": 2.473937943222747e-05, + "loss": 0.1292, + "step": 226930 + }, + { + "epoch": 0.51, + "learning_rate": 2.4738260889018145e-05, + "loss": 0.1314, + "step": 226940 + }, + { + "epoch": 0.51, + "learning_rate": 2.473714234580882e-05, + "loss": 0.1301, + "step": 226950 + }, + { + "epoch": 0.51, + "learning_rate": 2.4736023802599494e-05, + "loss": 0.1295, + "step": 226960 + }, + { + "epoch": 0.51, + "learning_rate": 2.4734905259390172e-05, + "loss": 0.134, + "step": 226970 + }, + { + "epoch": 0.51, + "learning_rate": 2.473378671618085e-05, + "loss": 0.1322, + "step": 226980 + }, + { + "epoch": 0.51, + "learning_rate": 2.4732668172971524e-05, + "loss": 0.1321, + "step": 226990 + }, + { + "epoch": 0.51, + "learning_rate": 2.47315496297622e-05, + "loss": 0.1352, + "step": 227000 + }, + { + "epoch": 0.51, + "learning_rate": 2.4730431086552874e-05, + "loss": 0.1353, + "step": 227010 + }, + { + "epoch": 0.51, + "learning_rate": 2.4729312543343548e-05, + "loss": 0.1336, + "step": 227020 + }, + { + "epoch": 0.51, + "learning_rate": 2.472819400013423e-05, + "loss": 0.1322, + "step": 227030 + }, + { + "epoch": 0.51, + "learning_rate": 2.4727075456924904e-05, + "loss": 0.1333, + "step": 227040 + }, + { + "epoch": 0.51, + "learning_rate": 2.472595691371558e-05, + "loss": 0.1231, + "step": 227050 + }, + { + "epoch": 0.51, + "learning_rate": 2.4724838370506253e-05, + "loss": 0.1359, + "step": 227060 + }, + { + "epoch": 0.51, + "learning_rate": 2.4723719827296928e-05, + "loss": 0.1327, + "step": 227070 + }, + { + "epoch": 0.51, + "learning_rate": 2.4722601284087605e-05, + "loss": 0.1319, + "step": 227080 + }, + { + "epoch": 0.51, + "learning_rate": 2.4721482740878283e-05, + "loss": 0.1307, + "step": 227090 + }, + { + "epoch": 0.51, + "learning_rate": 2.4720364197668958e-05, + "loss": 0.132, + "step": 227100 + }, + { + "epoch": 0.51, + "learning_rate": 2.4719245654459632e-05, + "loss": 0.1406, + "step": 227110 + }, + { + "epoch": 0.51, + "learning_rate": 2.4718127111250307e-05, + "loss": 0.1351, + "step": 227120 + }, + { + "epoch": 0.51, + "learning_rate": 2.4717008568040985e-05, + "loss": 0.1311, + "step": 227130 + }, + { + "epoch": 0.51, + "learning_rate": 2.4715890024831663e-05, + "loss": 0.1316, + "step": 227140 + }, + { + "epoch": 0.51, + "learning_rate": 2.4714771481622337e-05, + "loss": 0.1348, + "step": 227150 + }, + { + "epoch": 0.51, + "learning_rate": 2.4713652938413012e-05, + "loss": 0.1373, + "step": 227160 + }, + { + "epoch": 0.51, + "learning_rate": 2.4712534395203687e-05, + "loss": 0.131, + "step": 227170 + }, + { + "epoch": 0.51, + "learning_rate": 2.4711415851994364e-05, + "loss": 0.1311, + "step": 227180 + }, + { + "epoch": 0.51, + "learning_rate": 2.4710297308785042e-05, + "loss": 0.1296, + "step": 227190 + }, + { + "epoch": 0.51, + "learning_rate": 2.4709178765575717e-05, + "loss": 0.132, + "step": 227200 + }, + { + "epoch": 0.51, + "learning_rate": 2.470806022236639e-05, + "loss": 0.1307, + "step": 227210 + }, + { + "epoch": 0.51, + "learning_rate": 2.4706941679157066e-05, + "loss": 0.1277, + "step": 227220 + }, + { + "epoch": 0.51, + "learning_rate": 2.470582313594774e-05, + "loss": 0.1292, + "step": 227230 + }, + { + "epoch": 0.51, + "learning_rate": 2.470470459273842e-05, + "loss": 0.1362, + "step": 227240 + }, + { + "epoch": 0.51, + "learning_rate": 2.4703586049529096e-05, + "loss": 0.1322, + "step": 227250 + }, + { + "epoch": 0.51, + "learning_rate": 2.470246750631977e-05, + "loss": 0.1315, + "step": 227260 + }, + { + "epoch": 0.51, + "learning_rate": 2.4701348963110445e-05, + "loss": 0.1294, + "step": 227270 + }, + { + "epoch": 0.51, + "learning_rate": 2.470023041990112e-05, + "loss": 0.1328, + "step": 227280 + }, + { + "epoch": 0.51, + "learning_rate": 2.4699111876691798e-05, + "loss": 0.1292, + "step": 227290 + }, + { + "epoch": 0.51, + "learning_rate": 2.4697993333482476e-05, + "loss": 0.129, + "step": 227300 + }, + { + "epoch": 0.51, + "learning_rate": 2.469687479027315e-05, + "loss": 0.1329, + "step": 227310 + }, + { + "epoch": 0.51, + "learning_rate": 2.4695756247063825e-05, + "loss": 0.133, + "step": 227320 + }, + { + "epoch": 0.51, + "learning_rate": 2.46946377038545e-05, + "loss": 0.1335, + "step": 227330 + }, + { + "epoch": 0.51, + "learning_rate": 2.4693519160645177e-05, + "loss": 0.1334, + "step": 227340 + }, + { + "epoch": 0.51, + "learning_rate": 2.4692400617435855e-05, + "loss": 0.1313, + "step": 227350 + }, + { + "epoch": 0.51, + "learning_rate": 2.469128207422653e-05, + "loss": 0.1329, + "step": 227360 + }, + { + "epoch": 0.51, + "learning_rate": 2.4690163531017204e-05, + "loss": 0.1244, + "step": 227370 + }, + { + "epoch": 0.51, + "learning_rate": 2.468904498780788e-05, + "loss": 0.1306, + "step": 227380 + }, + { + "epoch": 0.51, + "learning_rate": 2.4687926444598557e-05, + "loss": 0.1324, + "step": 227390 + }, + { + "epoch": 0.51, + "learning_rate": 2.468680790138923e-05, + "loss": 0.132, + "step": 227400 + }, + { + "epoch": 0.51, + "learning_rate": 2.468568935817991e-05, + "loss": 0.135, + "step": 227410 + }, + { + "epoch": 0.51, + "learning_rate": 2.4684570814970584e-05, + "loss": 0.1366, + "step": 227420 + }, + { + "epoch": 0.51, + "learning_rate": 2.468345227176126e-05, + "loss": 0.1291, + "step": 227430 + }, + { + "epoch": 0.51, + "learning_rate": 2.4682333728551933e-05, + "loss": 0.1318, + "step": 227440 + }, + { + "epoch": 0.51, + "learning_rate": 2.468121518534261e-05, + "loss": 0.1311, + "step": 227450 + }, + { + "epoch": 0.51, + "learning_rate": 2.468009664213329e-05, + "loss": 0.1279, + "step": 227460 + }, + { + "epoch": 0.51, + "learning_rate": 2.4678978098923963e-05, + "loss": 0.1343, + "step": 227470 + }, + { + "epoch": 0.51, + "learning_rate": 2.4677859555714638e-05, + "loss": 0.1309, + "step": 227480 + }, + { + "epoch": 0.51, + "learning_rate": 2.4676741012505312e-05, + "loss": 0.1336, + "step": 227490 + }, + { + "epoch": 0.51, + "learning_rate": 2.467562246929599e-05, + "loss": 0.1336, + "step": 227500 + }, + { + "epoch": 0.51, + "learning_rate": 2.4674503926086668e-05, + "loss": 0.1286, + "step": 227510 + }, + { + "epoch": 0.51, + "learning_rate": 2.4673385382877343e-05, + "loss": 0.1314, + "step": 227520 + }, + { + "epoch": 0.51, + "learning_rate": 2.4672266839668017e-05, + "loss": 0.1303, + "step": 227530 + }, + { + "epoch": 0.51, + "learning_rate": 2.4671148296458692e-05, + "loss": 0.1352, + "step": 227540 + }, + { + "epoch": 0.51, + "learning_rate": 2.467002975324937e-05, + "loss": 0.1357, + "step": 227550 + }, + { + "epoch": 0.51, + "learning_rate": 2.4668911210040044e-05, + "loss": 0.1348, + "step": 227560 + }, + { + "epoch": 0.51, + "learning_rate": 2.4667792666830722e-05, + "loss": 0.1272, + "step": 227570 + }, + { + "epoch": 0.51, + "learning_rate": 2.4666674123621397e-05, + "loss": 0.1324, + "step": 227580 + }, + { + "epoch": 0.51, + "learning_rate": 2.466555558041207e-05, + "loss": 0.1334, + "step": 227590 + }, + { + "epoch": 0.51, + "learning_rate": 2.466443703720275e-05, + "loss": 0.1362, + "step": 227600 + }, + { + "epoch": 0.51, + "learning_rate": 2.4663318493993424e-05, + "loss": 0.1313, + "step": 227610 + }, + { + "epoch": 0.51, + "learning_rate": 2.4662199950784102e-05, + "loss": 0.1321, + "step": 227620 + }, + { + "epoch": 0.51, + "learning_rate": 2.4661081407574776e-05, + "loss": 0.1302, + "step": 227630 + }, + { + "epoch": 0.51, + "learning_rate": 2.4660074718686385e-05, + "loss": 0.1271, + "step": 227640 + }, + { + "epoch": 0.51, + "learning_rate": 2.465895617547706e-05, + "loss": 0.1291, + "step": 227650 + }, + { + "epoch": 0.51, + "learning_rate": 2.4657837632267734e-05, + "loss": 0.1337, + "step": 227660 + }, + { + "epoch": 0.51, + "learning_rate": 2.4656719089058412e-05, + "loss": 0.1312, + "step": 227670 + }, + { + "epoch": 0.51, + "learning_rate": 2.4655600545849087e-05, + "loss": 0.1349, + "step": 227680 + }, + { + "epoch": 0.51, + "learning_rate": 2.4654482002639765e-05, + "loss": 0.1304, + "step": 227690 + }, + { + "epoch": 0.51, + "learning_rate": 2.465336345943044e-05, + "loss": 0.1365, + "step": 227700 + }, + { + "epoch": 0.51, + "learning_rate": 2.4652244916221114e-05, + "loss": 0.1361, + "step": 227710 + }, + { + "epoch": 0.51, + "learning_rate": 2.465112637301179e-05, + "loss": 0.1258, + "step": 227720 + }, + { + "epoch": 0.51, + "learning_rate": 2.4650007829802466e-05, + "loss": 0.1299, + "step": 227730 + }, + { + "epoch": 0.51, + "learning_rate": 2.464888928659314e-05, + "loss": 0.1319, + "step": 227740 + }, + { + "epoch": 0.51, + "learning_rate": 2.464777074338382e-05, + "loss": 0.1267, + "step": 227750 + }, + { + "epoch": 0.51, + "learning_rate": 2.4646652200174493e-05, + "loss": 0.1244, + "step": 227760 + }, + { + "epoch": 0.51, + "learning_rate": 2.464553365696517e-05, + "loss": 0.1328, + "step": 227770 + }, + { + "epoch": 0.51, + "learning_rate": 2.4644415113755846e-05, + "loss": 0.1294, + "step": 227780 + }, + { + "epoch": 0.51, + "learning_rate": 2.464329657054652e-05, + "loss": 0.1321, + "step": 227790 + }, + { + "epoch": 0.51, + "learning_rate": 2.4642178027337198e-05, + "loss": 0.1292, + "step": 227800 + }, + { + "epoch": 0.51, + "learning_rate": 2.4641059484127873e-05, + "loss": 0.1354, + "step": 227810 + }, + { + "epoch": 0.51, + "learning_rate": 2.463994094091855e-05, + "loss": 0.126, + "step": 227820 + }, + { + "epoch": 0.51, + "learning_rate": 2.4638822397709225e-05, + "loss": 0.1287, + "step": 227830 + }, + { + "epoch": 0.51, + "learning_rate": 2.46377038544999e-05, + "loss": 0.1326, + "step": 227840 + }, + { + "epoch": 0.51, + "learning_rate": 2.4636585311290578e-05, + "loss": 0.1308, + "step": 227850 + }, + { + "epoch": 0.51, + "learning_rate": 2.4635466768081252e-05, + "loss": 0.1315, + "step": 227860 + }, + { + "epoch": 0.51, + "learning_rate": 2.4634348224871927e-05, + "loss": 0.1324, + "step": 227870 + }, + { + "epoch": 0.51, + "learning_rate": 2.4633229681662605e-05, + "loss": 0.133, + "step": 227880 + }, + { + "epoch": 0.51, + "learning_rate": 2.463211113845328e-05, + "loss": 0.1331, + "step": 227890 + }, + { + "epoch": 0.51, + "learning_rate": 2.4630992595243954e-05, + "loss": 0.1288, + "step": 227900 + }, + { + "epoch": 0.51, + "learning_rate": 2.462987405203463e-05, + "loss": 0.1274, + "step": 227910 + }, + { + "epoch": 0.51, + "learning_rate": 2.4628755508825306e-05, + "loss": 0.134, + "step": 227920 + }, + { + "epoch": 0.51, + "learning_rate": 2.4627636965615984e-05, + "loss": 0.1307, + "step": 227930 + }, + { + "epoch": 0.51, + "learning_rate": 2.462651842240666e-05, + "loss": 0.1283, + "step": 227940 + }, + { + "epoch": 0.51, + "learning_rate": 2.4625399879197333e-05, + "loss": 0.132, + "step": 227950 + }, + { + "epoch": 0.51, + "learning_rate": 2.462428133598801e-05, + "loss": 0.1317, + "step": 227960 + }, + { + "epoch": 0.51, + "learning_rate": 2.4623162792778686e-05, + "loss": 0.1359, + "step": 227970 + }, + { + "epoch": 0.51, + "learning_rate": 2.4622044249569363e-05, + "loss": 0.1345, + "step": 227980 + }, + { + "epoch": 0.51, + "learning_rate": 2.4620925706360038e-05, + "loss": 0.1321, + "step": 227990 + }, + { + "epoch": 0.51, + "learning_rate": 2.4619807163150713e-05, + "loss": 0.132, + "step": 228000 + }, + { + "epoch": 0.51, + "learning_rate": 2.461868861994139e-05, + "loss": 0.1331, + "step": 228010 + }, + { + "epoch": 0.51, + "learning_rate": 2.4617681931052996e-05, + "loss": 0.1325, + "step": 228020 + }, + { + "epoch": 0.51, + "learning_rate": 2.4616563387843674e-05, + "loss": 0.1319, + "step": 228030 + }, + { + "epoch": 0.51, + "learning_rate": 2.461544484463435e-05, + "loss": 0.1303, + "step": 228040 + }, + { + "epoch": 0.51, + "learning_rate": 2.4614326301425026e-05, + "loss": 0.1324, + "step": 228050 + }, + { + "epoch": 0.51, + "learning_rate": 2.46132077582157e-05, + "loss": 0.1293, + "step": 228060 + }, + { + "epoch": 0.51, + "learning_rate": 2.4612089215006375e-05, + "loss": 0.1299, + "step": 228070 + }, + { + "epoch": 0.51, + "learning_rate": 2.4610970671797053e-05, + "loss": 0.1313, + "step": 228080 + }, + { + "epoch": 0.51, + "learning_rate": 2.4609852128587728e-05, + "loss": 0.1298, + "step": 228090 + }, + { + "epoch": 0.51, + "learning_rate": 2.4608733585378406e-05, + "loss": 0.1335, + "step": 228100 + }, + { + "epoch": 0.51, + "learning_rate": 2.460761504216908e-05, + "loss": 0.1339, + "step": 228110 + }, + { + "epoch": 0.51, + "learning_rate": 2.4606496498959755e-05, + "loss": 0.1313, + "step": 228120 + }, + { + "epoch": 0.51, + "learning_rate": 2.460537795575043e-05, + "loss": 0.1323, + "step": 228130 + }, + { + "epoch": 0.51, + "learning_rate": 2.4604259412541107e-05, + "loss": 0.1334, + "step": 228140 + }, + { + "epoch": 0.51, + "learning_rate": 2.4603140869331785e-05, + "loss": 0.1308, + "step": 228150 + }, + { + "epoch": 0.51, + "learning_rate": 2.460202232612246e-05, + "loss": 0.1314, + "step": 228160 + }, + { + "epoch": 0.51, + "learning_rate": 2.4600903782913134e-05, + "loss": 0.1304, + "step": 228170 + }, + { + "epoch": 0.51, + "learning_rate": 2.459978523970381e-05, + "loss": 0.131, + "step": 228180 + }, + { + "epoch": 0.51, + "learning_rate": 2.4598666696494487e-05, + "loss": 0.1295, + "step": 228190 + }, + { + "epoch": 0.51, + "learning_rate": 2.4597548153285165e-05, + "loss": 0.1314, + "step": 228200 + }, + { + "epoch": 0.51, + "learning_rate": 2.459642961007584e-05, + "loss": 0.133, + "step": 228210 + }, + { + "epoch": 0.51, + "learning_rate": 2.4595311066866514e-05, + "loss": 0.1377, + "step": 228220 + }, + { + "epoch": 0.51, + "learning_rate": 2.459419252365719e-05, + "loss": 0.1316, + "step": 228230 + }, + { + "epoch": 0.51, + "learning_rate": 2.4593073980447866e-05, + "loss": 0.1296, + "step": 228240 + }, + { + "epoch": 0.51, + "learning_rate": 2.459195543723854e-05, + "loss": 0.1274, + "step": 228250 + }, + { + "epoch": 0.51, + "learning_rate": 2.459083689402922e-05, + "loss": 0.1286, + "step": 228260 + }, + { + "epoch": 0.51, + "learning_rate": 2.4589718350819893e-05, + "loss": 0.1332, + "step": 228270 + }, + { + "epoch": 0.51, + "learning_rate": 2.4588599807610568e-05, + "loss": 0.1341, + "step": 228280 + }, + { + "epoch": 0.51, + "learning_rate": 2.4587481264401242e-05, + "loss": 0.1315, + "step": 228290 + }, + { + "epoch": 0.51, + "learning_rate": 2.458636272119192e-05, + "loss": 0.133, + "step": 228300 + }, + { + "epoch": 0.51, + "learning_rate": 2.4585244177982598e-05, + "loss": 0.1282, + "step": 228310 + }, + { + "epoch": 0.51, + "learning_rate": 2.4584125634773273e-05, + "loss": 0.1289, + "step": 228320 + }, + { + "epoch": 0.51, + "learning_rate": 2.4583007091563947e-05, + "loss": 0.1265, + "step": 228330 + }, + { + "epoch": 0.51, + "learning_rate": 2.4581888548354622e-05, + "loss": 0.1303, + "step": 228340 + }, + { + "epoch": 0.51, + "learning_rate": 2.45807700051453e-05, + "loss": 0.1342, + "step": 228350 + }, + { + "epoch": 0.51, + "learning_rate": 2.4579651461935978e-05, + "loss": 0.1289, + "step": 228360 + }, + { + "epoch": 0.51, + "learning_rate": 2.4578532918726652e-05, + "loss": 0.135, + "step": 228370 + }, + { + "epoch": 0.51, + "learning_rate": 2.4577414375517327e-05, + "loss": 0.1363, + "step": 228380 + }, + { + "epoch": 0.51, + "learning_rate": 2.4576295832308e-05, + "loss": 0.1316, + "step": 228390 + }, + { + "epoch": 0.51, + "learning_rate": 2.457517728909868e-05, + "loss": 0.1348, + "step": 228400 + }, + { + "epoch": 0.51, + "learning_rate": 2.4574058745889357e-05, + "loss": 0.1307, + "step": 228410 + }, + { + "epoch": 0.51, + "learning_rate": 2.457294020268003e-05, + "loss": 0.134, + "step": 228420 + }, + { + "epoch": 0.51, + "learning_rate": 2.4571821659470706e-05, + "loss": 0.1323, + "step": 228430 + }, + { + "epoch": 0.51, + "learning_rate": 2.457070311626138e-05, + "loss": 0.1329, + "step": 228440 + }, + { + "epoch": 0.51, + "learning_rate": 2.4569584573052055e-05, + "loss": 0.1285, + "step": 228450 + }, + { + "epoch": 0.51, + "learning_rate": 2.4568466029842737e-05, + "loss": 0.1315, + "step": 228460 + }, + { + "epoch": 0.51, + "learning_rate": 2.456734748663341e-05, + "loss": 0.1342, + "step": 228470 + }, + { + "epoch": 0.51, + "learning_rate": 2.4566228943424086e-05, + "loss": 0.134, + "step": 228480 + }, + { + "epoch": 0.51, + "learning_rate": 2.456511040021476e-05, + "loss": 0.1365, + "step": 228490 + }, + { + "epoch": 0.51, + "learning_rate": 2.4563991857005435e-05, + "loss": 0.1304, + "step": 228500 + }, + { + "epoch": 0.51, + "learning_rate": 2.4562873313796113e-05, + "loss": 0.1322, + "step": 228510 + }, + { + "epoch": 0.51, + "learning_rate": 2.456175477058679e-05, + "loss": 0.1272, + "step": 228520 + }, + { + "epoch": 0.51, + "learning_rate": 2.4560636227377465e-05, + "loss": 0.1372, + "step": 228530 + }, + { + "epoch": 0.51, + "learning_rate": 2.455951768416814e-05, + "loss": 0.1338, + "step": 228540 + }, + { + "epoch": 0.51, + "learning_rate": 2.4558399140958814e-05, + "loss": 0.1361, + "step": 228550 + }, + { + "epoch": 0.51, + "learning_rate": 2.4557280597749492e-05, + "loss": 0.1302, + "step": 228560 + }, + { + "epoch": 0.51, + "learning_rate": 2.455616205454017e-05, + "loss": 0.1331, + "step": 228570 + }, + { + "epoch": 0.51, + "learning_rate": 2.4555043511330845e-05, + "loss": 0.1305, + "step": 228580 + }, + { + "epoch": 0.51, + "learning_rate": 2.455392496812152e-05, + "loss": 0.1282, + "step": 228590 + }, + { + "epoch": 0.51, + "learning_rate": 2.4552806424912194e-05, + "loss": 0.1279, + "step": 228600 + }, + { + "epoch": 0.51, + "learning_rate": 2.455168788170287e-05, + "loss": 0.1317, + "step": 228610 + }, + { + "epoch": 0.51, + "learning_rate": 2.455056933849355e-05, + "loss": 0.1354, + "step": 228620 + }, + { + "epoch": 0.51, + "learning_rate": 2.4549450795284224e-05, + "loss": 0.1326, + "step": 228630 + }, + { + "epoch": 0.51, + "learning_rate": 2.45483322520749e-05, + "loss": 0.13, + "step": 228640 + }, + { + "epoch": 0.51, + "learning_rate": 2.4547213708865573e-05, + "loss": 0.1324, + "step": 228650 + }, + { + "epoch": 0.51, + "learning_rate": 2.4546095165656248e-05, + "loss": 0.1275, + "step": 228660 + }, + { + "epoch": 0.51, + "learning_rate": 2.454497662244693e-05, + "loss": 0.1319, + "step": 228670 + }, + { + "epoch": 0.51, + "learning_rate": 2.4543858079237604e-05, + "loss": 0.1263, + "step": 228680 + }, + { + "epoch": 0.51, + "learning_rate": 2.4542739536028278e-05, + "loss": 0.1335, + "step": 228690 + }, + { + "epoch": 0.51, + "learning_rate": 2.4541620992818953e-05, + "loss": 0.1318, + "step": 228700 + }, + { + "epoch": 0.51, + "learning_rate": 2.4540502449609627e-05, + "loss": 0.1267, + "step": 228710 + }, + { + "epoch": 0.51, + "learning_rate": 2.4539383906400305e-05, + "loss": 0.1297, + "step": 228720 + }, + { + "epoch": 0.51, + "learning_rate": 2.4538265363190983e-05, + "loss": 0.136, + "step": 228730 + }, + { + "epoch": 0.51, + "learning_rate": 2.4537146819981658e-05, + "loss": 0.1324, + "step": 228740 + }, + { + "epoch": 0.51, + "learning_rate": 2.4536028276772332e-05, + "loss": 0.1278, + "step": 228750 + }, + { + "epoch": 0.51, + "learning_rate": 2.4534909733563007e-05, + "loss": 0.1348, + "step": 228760 + }, + { + "epoch": 0.51, + "learning_rate": 2.4533791190353685e-05, + "loss": 0.1333, + "step": 228770 + }, + { + "epoch": 0.51, + "learning_rate": 2.4532672647144363e-05, + "loss": 0.132, + "step": 228780 + }, + { + "epoch": 0.51, + "learning_rate": 2.4531554103935037e-05, + "loss": 0.1294, + "step": 228790 + }, + { + "epoch": 0.51, + "learning_rate": 2.453043556072571e-05, + "loss": 0.1307, + "step": 228800 + }, + { + "epoch": 0.51, + "learning_rate": 2.4529317017516386e-05, + "loss": 0.1333, + "step": 228810 + }, + { + "epoch": 0.51, + "learning_rate": 2.4528198474307064e-05, + "loss": 0.1299, + "step": 228820 + }, + { + "epoch": 0.51, + "learning_rate": 2.4527079931097742e-05, + "loss": 0.1317, + "step": 228830 + }, + { + "epoch": 0.51, + "learning_rate": 2.4525961387888417e-05, + "loss": 0.1304, + "step": 228840 + }, + { + "epoch": 0.51, + "learning_rate": 2.452484284467909e-05, + "loss": 0.1329, + "step": 228850 + }, + { + "epoch": 0.51, + "learning_rate": 2.4523724301469766e-05, + "loss": 0.1318, + "step": 228860 + }, + { + "epoch": 0.51, + "learning_rate": 2.452260575826044e-05, + "loss": 0.1291, + "step": 228870 + }, + { + "epoch": 0.51, + "learning_rate": 2.452148721505112e-05, + "loss": 0.1259, + "step": 228880 + }, + { + "epoch": 0.51, + "learning_rate": 2.4520368671841796e-05, + "loss": 0.1363, + "step": 228890 + }, + { + "epoch": 0.51, + "learning_rate": 2.451925012863247e-05, + "loss": 0.1306, + "step": 228900 + }, + { + "epoch": 0.51, + "learning_rate": 2.4518131585423145e-05, + "loss": 0.1283, + "step": 228910 + }, + { + "epoch": 0.51, + "learning_rate": 2.451701304221382e-05, + "loss": 0.1346, + "step": 228920 + }, + { + "epoch": 0.51, + "learning_rate": 2.4515894499004498e-05, + "loss": 0.1319, + "step": 228930 + }, + { + "epoch": 0.51, + "learning_rate": 2.4514775955795175e-05, + "loss": 0.1394, + "step": 228940 + }, + { + "epoch": 0.51, + "learning_rate": 2.451365741258585e-05, + "loss": 0.135, + "step": 228950 + }, + { + "epoch": 0.51, + "learning_rate": 2.4512538869376525e-05, + "loss": 0.1311, + "step": 228960 + }, + { + "epoch": 0.51, + "learning_rate": 2.45114203261672e-05, + "loss": 0.1329, + "step": 228970 + }, + { + "epoch": 0.51, + "learning_rate": 2.4510301782957877e-05, + "loss": 0.1314, + "step": 228980 + }, + { + "epoch": 0.51, + "learning_rate": 2.4509183239748555e-05, + "loss": 0.1249, + "step": 228990 + }, + { + "epoch": 0.51, + "learning_rate": 2.450806469653923e-05, + "loss": 0.1322, + "step": 229000 + }, + { + "epoch": 0.51, + "learning_rate": 2.4506946153329904e-05, + "loss": 0.1309, + "step": 229010 + }, + { + "epoch": 0.51, + "learning_rate": 2.450582761012058e-05, + "loss": 0.1318, + "step": 229020 + }, + { + "epoch": 0.51, + "learning_rate": 2.4504709066911257e-05, + "loss": 0.1321, + "step": 229030 + }, + { + "epoch": 0.51, + "learning_rate": 2.4503590523701934e-05, + "loss": 0.1273, + "step": 229040 + }, + { + "epoch": 0.51, + "learning_rate": 2.450247198049261e-05, + "loss": 0.1311, + "step": 229050 + }, + { + "epoch": 0.51, + "learning_rate": 2.4501353437283284e-05, + "loss": 0.1299, + "step": 229060 + }, + { + "epoch": 0.51, + "learning_rate": 2.4500234894073958e-05, + "loss": 0.1339, + "step": 229070 + }, + { + "epoch": 0.51, + "learning_rate": 2.4499116350864636e-05, + "loss": 0.1297, + "step": 229080 + }, + { + "epoch": 0.51, + "learning_rate": 2.449799780765531e-05, + "loss": 0.1288, + "step": 229090 + }, + { + "epoch": 0.51, + "learning_rate": 2.449687926444599e-05, + "loss": 0.1331, + "step": 229100 + }, + { + "epoch": 0.51, + "learning_rate": 2.4495760721236663e-05, + "loss": 0.1344, + "step": 229110 + }, + { + "epoch": 0.51, + "learning_rate": 2.4494642178027338e-05, + "loss": 0.1367, + "step": 229120 + }, + { + "epoch": 0.51, + "learning_rate": 2.4493523634818012e-05, + "loss": 0.1345, + "step": 229130 + }, + { + "epoch": 0.51, + "learning_rate": 2.449240509160869e-05, + "loss": 0.1312, + "step": 229140 + }, + { + "epoch": 0.51, + "learning_rate": 2.4491286548399368e-05, + "loss": 0.1292, + "step": 229150 + }, + { + "epoch": 0.51, + "learning_rate": 2.4490168005190042e-05, + "loss": 0.1324, + "step": 229160 + }, + { + "epoch": 0.51, + "learning_rate": 2.4489049461980717e-05, + "loss": 0.1332, + "step": 229170 + }, + { + "epoch": 0.51, + "learning_rate": 2.448793091877139e-05, + "loss": 0.1348, + "step": 229180 + }, + { + "epoch": 0.51, + "learning_rate": 2.448681237556207e-05, + "loss": 0.1264, + "step": 229190 + }, + { + "epoch": 0.51, + "learning_rate": 2.4485693832352747e-05, + "loss": 0.1309, + "step": 229200 + }, + { + "epoch": 0.51, + "learning_rate": 2.4484575289143422e-05, + "loss": 0.1332, + "step": 229210 + }, + { + "epoch": 0.51, + "learning_rate": 2.4483456745934096e-05, + "loss": 0.1318, + "step": 229220 + }, + { + "epoch": 0.51, + "learning_rate": 2.448233820272477e-05, + "loss": 0.1291, + "step": 229230 + }, + { + "epoch": 0.51, + "learning_rate": 2.448121965951545e-05, + "loss": 0.1318, + "step": 229240 + }, + { + "epoch": 0.51, + "learning_rate": 2.4480101116306123e-05, + "loss": 0.1344, + "step": 229250 + }, + { + "epoch": 0.51, + "learning_rate": 2.44789825730968e-05, + "loss": 0.1297, + "step": 229260 + }, + { + "epoch": 0.51, + "learning_rate": 2.4477864029887476e-05, + "loss": 0.1343, + "step": 229270 + }, + { + "epoch": 0.51, + "learning_rate": 2.447674548667815e-05, + "loss": 0.1294, + "step": 229280 + }, + { + "epoch": 0.51, + "learning_rate": 2.447562694346883e-05, + "loss": 0.1323, + "step": 229290 + }, + { + "epoch": 0.51, + "learning_rate": 2.4474508400259503e-05, + "loss": 0.1331, + "step": 229300 + }, + { + "epoch": 0.51, + "learning_rate": 2.447338985705018e-05, + "loss": 0.1286, + "step": 229310 + }, + { + "epoch": 0.51, + "learning_rate": 2.4472271313840855e-05, + "loss": 0.1325, + "step": 229320 + }, + { + "epoch": 0.51, + "learning_rate": 2.447115277063153e-05, + "loss": 0.1302, + "step": 229330 + }, + { + "epoch": 0.51, + "learning_rate": 2.4470034227422205e-05, + "loss": 0.1289, + "step": 229340 + }, + { + "epoch": 0.51, + "learning_rate": 2.4468915684212882e-05, + "loss": 0.1255, + "step": 229350 + }, + { + "epoch": 0.51, + "learning_rate": 2.446779714100356e-05, + "loss": 0.1322, + "step": 229360 + }, + { + "epoch": 0.51, + "learning_rate": 2.4466678597794235e-05, + "loss": 0.1234, + "step": 229370 + }, + { + "epoch": 0.51, + "learning_rate": 2.446556005458491e-05, + "loss": 0.1284, + "step": 229380 + }, + { + "epoch": 0.51, + "learning_rate": 2.4464441511375584e-05, + "loss": 0.1308, + "step": 229390 + }, + { + "epoch": 0.51, + "learning_rate": 2.4463322968166262e-05, + "loss": 0.1282, + "step": 229400 + }, + { + "epoch": 0.51, + "learning_rate": 2.4462204424956936e-05, + "loss": 0.1308, + "step": 229410 + }, + { + "epoch": 0.51, + "learning_rate": 2.4461085881747614e-05, + "loss": 0.1371, + "step": 229420 + }, + { + "epoch": 0.51, + "learning_rate": 2.445996733853829e-05, + "loss": 0.1342, + "step": 229430 + }, + { + "epoch": 0.51, + "learning_rate": 2.4458848795328963e-05, + "loss": 0.1339, + "step": 229440 + }, + { + "epoch": 0.51, + "learning_rate": 2.445773025211964e-05, + "loss": 0.1292, + "step": 229450 + }, + { + "epoch": 0.51, + "learning_rate": 2.4456611708910316e-05, + "loss": 0.1305, + "step": 229460 + }, + { + "epoch": 0.51, + "learning_rate": 2.4455493165700994e-05, + "loss": 0.1352, + "step": 229470 + }, + { + "epoch": 0.51, + "learning_rate": 2.445437462249167e-05, + "loss": 0.1321, + "step": 229480 + }, + { + "epoch": 0.51, + "learning_rate": 2.4453256079282343e-05, + "loss": 0.1312, + "step": 229490 + }, + { + "epoch": 0.51, + "learning_rate": 2.445213753607302e-05, + "loss": 0.1329, + "step": 229500 + }, + { + "epoch": 0.51, + "learning_rate": 2.4451018992863695e-05, + "loss": 0.1288, + "step": 229510 + }, + { + "epoch": 0.51, + "learning_rate": 2.4449900449654373e-05, + "loss": 0.1364, + "step": 229520 + }, + { + "epoch": 0.51, + "learning_rate": 2.4448781906445048e-05, + "loss": 0.1355, + "step": 229530 + }, + { + "epoch": 0.51, + "learning_rate": 2.4447663363235722e-05, + "loss": 0.1366, + "step": 229540 + }, + { + "epoch": 0.51, + "learning_rate": 2.4446544820026397e-05, + "loss": 0.1351, + "step": 229550 + }, + { + "epoch": 0.51, + "learning_rate": 2.4445426276817075e-05, + "loss": 0.1313, + "step": 229560 + }, + { + "epoch": 0.51, + "learning_rate": 2.444430773360775e-05, + "loss": 0.131, + "step": 229570 + }, + { + "epoch": 0.51, + "learning_rate": 2.4443189190398427e-05, + "loss": 0.1333, + "step": 229580 + }, + { + "epoch": 0.51, + "learning_rate": 2.4442070647189102e-05, + "loss": 0.1346, + "step": 229590 + }, + { + "epoch": 0.51, + "learning_rate": 2.4440952103979776e-05, + "loss": 0.1277, + "step": 229600 + }, + { + "epoch": 0.51, + "learning_rate": 2.4439833560770454e-05, + "loss": 0.1313, + "step": 229610 + }, + { + "epoch": 0.51, + "learning_rate": 2.443871501756113e-05, + "loss": 0.1395, + "step": 229620 + }, + { + "epoch": 0.51, + "learning_rate": 2.4437596474351807e-05, + "loss": 0.1313, + "step": 229630 + }, + { + "epoch": 0.51, + "learning_rate": 2.443647793114248e-05, + "loss": 0.1303, + "step": 229640 + }, + { + "epoch": 0.51, + "learning_rate": 2.4435359387933156e-05, + "loss": 0.1304, + "step": 229650 + }, + { + "epoch": 0.51, + "learning_rate": 2.4434240844723834e-05, + "loss": 0.1321, + "step": 229660 + }, + { + "epoch": 0.51, + "learning_rate": 2.443312230151451e-05, + "loss": 0.1308, + "step": 229670 + }, + { + "epoch": 0.51, + "learning_rate": 2.4432003758305186e-05, + "loss": 0.1326, + "step": 229680 + }, + { + "epoch": 0.51, + "learning_rate": 2.443088521509586e-05, + "loss": 0.1293, + "step": 229690 + }, + { + "epoch": 0.51, + "learning_rate": 2.4429766671886535e-05, + "loss": 0.1332, + "step": 229700 + }, + { + "epoch": 0.51, + "learning_rate": 2.4428648128677213e-05, + "loss": 0.1311, + "step": 229710 + }, + { + "epoch": 0.51, + "learning_rate": 2.4427529585467888e-05, + "loss": 0.1259, + "step": 229720 + }, + { + "epoch": 0.51, + "learning_rate": 2.4426411042258562e-05, + "loss": 0.1313, + "step": 229730 + }, + { + "epoch": 0.51, + "learning_rate": 2.442529249904924e-05, + "loss": 0.131, + "step": 229740 + }, + { + "epoch": 0.51, + "learning_rate": 2.4424173955839915e-05, + "loss": 0.1337, + "step": 229750 + }, + { + "epoch": 0.51, + "learning_rate": 2.442305541263059e-05, + "loss": 0.1289, + "step": 229760 + }, + { + "epoch": 0.51, + "learning_rate": 2.4421936869421267e-05, + "loss": 0.1312, + "step": 229770 + }, + { + "epoch": 0.51, + "learning_rate": 2.4420818326211942e-05, + "loss": 0.1342, + "step": 229780 + }, + { + "epoch": 0.51, + "learning_rate": 2.441969978300262e-05, + "loss": 0.1293, + "step": 229790 + }, + { + "epoch": 0.51, + "learning_rate": 2.4418581239793294e-05, + "loss": 0.1308, + "step": 229800 + }, + { + "epoch": 0.51, + "learning_rate": 2.441746269658397e-05, + "loss": 0.1279, + "step": 229810 + }, + { + "epoch": 0.51, + "learning_rate": 2.4416344153374647e-05, + "loss": 0.1328, + "step": 229820 + }, + { + "epoch": 0.51, + "learning_rate": 2.441522561016532e-05, + "loss": 0.1265, + "step": 229830 + }, + { + "epoch": 0.51, + "learning_rate": 2.4414107066956e-05, + "loss": 0.1358, + "step": 229840 + }, + { + "epoch": 0.51, + "learning_rate": 2.4412988523746674e-05, + "loss": 0.1354, + "step": 229850 + }, + { + "epoch": 0.51, + "learning_rate": 2.441186998053735e-05, + "loss": 0.1397, + "step": 229860 + }, + { + "epoch": 0.51, + "learning_rate": 2.4410751437328026e-05, + "loss": 0.1288, + "step": 229870 + }, + { + "epoch": 0.51, + "learning_rate": 2.44096328941187e-05, + "loss": 0.1316, + "step": 229880 + }, + { + "epoch": 0.51, + "learning_rate": 2.4408514350909375e-05, + "loss": 0.1321, + "step": 229890 + }, + { + "epoch": 0.51, + "learning_rate": 2.4407395807700053e-05, + "loss": 0.1293, + "step": 229900 + }, + { + "epoch": 0.51, + "learning_rate": 2.4406277264490728e-05, + "loss": 0.1335, + "step": 229910 + }, + { + "epoch": 0.51, + "learning_rate": 2.4405158721281406e-05, + "loss": 0.1278, + "step": 229920 + }, + { + "epoch": 0.51, + "learning_rate": 2.440404017807208e-05, + "loss": 0.1368, + "step": 229930 + }, + { + "epoch": 0.51, + "learning_rate": 2.4402921634862755e-05, + "loss": 0.1306, + "step": 229940 + }, + { + "epoch": 0.51, + "learning_rate": 2.4401803091653433e-05, + "loss": 0.1335, + "step": 229950 + }, + { + "epoch": 0.51, + "learning_rate": 2.4400684548444107e-05, + "loss": 0.1355, + "step": 229960 + }, + { + "epoch": 0.51, + "learning_rate": 2.4399566005234785e-05, + "loss": 0.1274, + "step": 229970 + }, + { + "epoch": 0.51, + "learning_rate": 2.439844746202546e-05, + "loss": 0.1278, + "step": 229980 + }, + { + "epoch": 0.51, + "learning_rate": 2.4397328918816134e-05, + "loss": 0.1258, + "step": 229990 + }, + { + "epoch": 0.51, + "learning_rate": 2.4396210375606812e-05, + "loss": 0.1301, + "step": 230000 + }, + { + "epoch": 0.51, + "learning_rate": 2.4395091832397487e-05, + "loss": 0.1315, + "step": 230010 + }, + { + "epoch": 0.51, + "learning_rate": 2.439397328918816e-05, + "loss": 0.1318, + "step": 230020 + }, + { + "epoch": 0.51, + "learning_rate": 2.439285474597884e-05, + "loss": 0.1283, + "step": 230030 + }, + { + "epoch": 0.51, + "learning_rate": 2.4391736202769514e-05, + "loss": 0.1332, + "step": 230040 + }, + { + "epoch": 0.51, + "learning_rate": 2.4390617659560188e-05, + "loss": 0.1316, + "step": 230050 + }, + { + "epoch": 0.51, + "learning_rate": 2.4389499116350866e-05, + "loss": 0.1348, + "step": 230060 + }, + { + "epoch": 0.51, + "learning_rate": 2.438838057314154e-05, + "loss": 0.1295, + "step": 230070 + }, + { + "epoch": 0.51, + "learning_rate": 2.438726202993222e-05, + "loss": 0.1307, + "step": 230080 + }, + { + "epoch": 0.51, + "learning_rate": 2.4386143486722893e-05, + "loss": 0.1308, + "step": 230090 + }, + { + "epoch": 0.51, + "learning_rate": 2.4385024943513568e-05, + "loss": 0.1269, + "step": 230100 + }, + { + "epoch": 0.51, + "learning_rate": 2.4383906400304246e-05, + "loss": 0.1312, + "step": 230110 + }, + { + "epoch": 0.51, + "learning_rate": 2.438278785709492e-05, + "loss": 0.1305, + "step": 230120 + }, + { + "epoch": 0.51, + "learning_rate": 2.4381669313885598e-05, + "loss": 0.1313, + "step": 230130 + }, + { + "epoch": 0.51, + "learning_rate": 2.4380550770676273e-05, + "loss": 0.1322, + "step": 230140 + }, + { + "epoch": 0.51, + "learning_rate": 2.4379432227466947e-05, + "loss": 0.1273, + "step": 230150 + }, + { + "epoch": 0.51, + "learning_rate": 2.4378313684257625e-05, + "loss": 0.1335, + "step": 230160 + }, + { + "epoch": 0.51, + "learning_rate": 2.43771951410483e-05, + "loss": 0.1308, + "step": 230170 + }, + { + "epoch": 0.51, + "learning_rate": 2.4376076597838978e-05, + "loss": 0.1268, + "step": 230180 + }, + { + "epoch": 0.51, + "learning_rate": 2.4374958054629652e-05, + "loss": 0.1313, + "step": 230190 + }, + { + "epoch": 0.51, + "learning_rate": 2.4373839511420327e-05, + "loss": 0.1287, + "step": 230200 + }, + { + "epoch": 0.51, + "learning_rate": 2.4372720968211e-05, + "loss": 0.1294, + "step": 230210 + }, + { + "epoch": 0.51, + "learning_rate": 2.437160242500168e-05, + "loss": 0.1248, + "step": 230220 + }, + { + "epoch": 0.51, + "learning_rate": 2.4370483881792354e-05, + "loss": 0.1277, + "step": 230230 + }, + { + "epoch": 0.51, + "learning_rate": 2.436936533858303e-05, + "loss": 0.1276, + "step": 230240 + }, + { + "epoch": 0.51, + "learning_rate": 2.4368246795373706e-05, + "loss": 0.1323, + "step": 230250 + }, + { + "epoch": 0.51, + "learning_rate": 2.436712825216438e-05, + "loss": 0.1295, + "step": 230260 + }, + { + "epoch": 0.51, + "learning_rate": 2.436600970895506e-05, + "loss": 0.1305, + "step": 230270 + }, + { + "epoch": 0.51, + "learning_rate": 2.4364891165745733e-05, + "loss": 0.1269, + "step": 230280 + }, + { + "epoch": 0.51, + "learning_rate": 2.436377262253641e-05, + "loss": 0.1335, + "step": 230290 + }, + { + "epoch": 0.51, + "learning_rate": 2.4362654079327086e-05, + "loss": 0.1292, + "step": 230300 + }, + { + "epoch": 0.51, + "learning_rate": 2.436153553611776e-05, + "loss": 0.1338, + "step": 230310 + }, + { + "epoch": 0.51, + "learning_rate": 2.4360416992908438e-05, + "loss": 0.1292, + "step": 230320 + }, + { + "epoch": 0.51, + "learning_rate": 2.4359298449699113e-05, + "loss": 0.1295, + "step": 230330 + }, + { + "epoch": 0.51, + "learning_rate": 2.435817990648979e-05, + "loss": 0.1301, + "step": 230340 + }, + { + "epoch": 0.51, + "learning_rate": 2.4357061363280465e-05, + "loss": 0.1339, + "step": 230350 + }, + { + "epoch": 0.51, + "learning_rate": 2.435594282007114e-05, + "loss": 0.1314, + "step": 230360 + }, + { + "epoch": 0.51, + "learning_rate": 2.4354824276861814e-05, + "loss": 0.1271, + "step": 230370 + }, + { + "epoch": 0.51, + "learning_rate": 2.4353705733652492e-05, + "loss": 0.1284, + "step": 230380 + }, + { + "epoch": 0.51, + "learning_rate": 2.435258719044317e-05, + "loss": 0.128, + "step": 230390 + }, + { + "epoch": 0.51, + "learning_rate": 2.4351468647233845e-05, + "loss": 0.1333, + "step": 230400 + }, + { + "epoch": 0.51, + "learning_rate": 2.435035010402452e-05, + "loss": 0.1289, + "step": 230410 + }, + { + "epoch": 0.51, + "learning_rate": 2.4349231560815194e-05, + "loss": 0.131, + "step": 230420 + }, + { + "epoch": 0.51, + "learning_rate": 2.434811301760587e-05, + "loss": 0.1312, + "step": 230430 + }, + { + "epoch": 0.51, + "learning_rate": 2.4346994474396546e-05, + "loss": 0.1254, + "step": 230440 + }, + { + "epoch": 0.51, + "learning_rate": 2.4345875931187224e-05, + "loss": 0.1349, + "step": 230450 + }, + { + "epoch": 0.51, + "learning_rate": 2.43447573879779e-05, + "loss": 0.132, + "step": 230460 + }, + { + "epoch": 0.51, + "learning_rate": 2.4343638844768573e-05, + "loss": 0.1279, + "step": 230470 + }, + { + "epoch": 0.51, + "learning_rate": 2.434252030155925e-05, + "loss": 0.1303, + "step": 230480 + }, + { + "epoch": 0.51, + "learning_rate": 2.4341401758349926e-05, + "loss": 0.1324, + "step": 230490 + }, + { + "epoch": 0.51, + "learning_rate": 2.4340283215140604e-05, + "loss": 0.1303, + "step": 230500 + }, + { + "epoch": 0.51, + "learning_rate": 2.4339164671931278e-05, + "loss": 0.1293, + "step": 230510 + }, + { + "epoch": 0.51, + "learning_rate": 2.4338046128721953e-05, + "loss": 0.1288, + "step": 230520 + }, + { + "epoch": 0.51, + "learning_rate": 2.4336927585512627e-05, + "loss": 0.1276, + "step": 230530 + }, + { + "epoch": 0.51, + "learning_rate": 2.4335809042303305e-05, + "loss": 0.1351, + "step": 230540 + }, + { + "epoch": 0.51, + "learning_rate": 2.4334690499093983e-05, + "loss": 0.1341, + "step": 230550 + }, + { + "epoch": 0.51, + "learning_rate": 2.4333571955884658e-05, + "loss": 0.1303, + "step": 230560 + }, + { + "epoch": 0.51, + "learning_rate": 2.4332453412675332e-05, + "loss": 0.1311, + "step": 230570 + }, + { + "epoch": 0.51, + "learning_rate": 2.4331334869466007e-05, + "loss": 0.1338, + "step": 230580 + }, + { + "epoch": 0.51, + "learning_rate": 2.4330216326256685e-05, + "loss": 0.1307, + "step": 230590 + }, + { + "epoch": 0.51, + "learning_rate": 2.4329097783047363e-05, + "loss": 0.129, + "step": 230600 + }, + { + "epoch": 0.51, + "learning_rate": 2.4327979239838037e-05, + "loss": 0.126, + "step": 230610 + }, + { + "epoch": 0.51, + "learning_rate": 2.432686069662871e-05, + "loss": 0.1321, + "step": 230620 + }, + { + "epoch": 0.51, + "learning_rate": 2.4325742153419386e-05, + "loss": 0.1272, + "step": 230630 + }, + { + "epoch": 0.51, + "learning_rate": 2.432462361021006e-05, + "loss": 0.1286, + "step": 230640 + }, + { + "epoch": 0.51, + "learning_rate": 2.432350506700074e-05, + "loss": 0.1291, + "step": 230650 + }, + { + "epoch": 0.51, + "learning_rate": 2.4322386523791417e-05, + "loss": 0.1272, + "step": 230660 + }, + { + "epoch": 0.51, + "learning_rate": 2.432126798058209e-05, + "loss": 0.1356, + "step": 230670 + }, + { + "epoch": 0.51, + "learning_rate": 2.4320149437372766e-05, + "loss": 0.1292, + "step": 230680 + }, + { + "epoch": 0.51, + "learning_rate": 2.431903089416344e-05, + "loss": 0.1262, + "step": 230690 + }, + { + "epoch": 0.51, + "learning_rate": 2.4317912350954118e-05, + "loss": 0.1321, + "step": 230700 + }, + { + "epoch": 0.51, + "learning_rate": 2.4316793807744796e-05, + "loss": 0.133, + "step": 230710 + }, + { + "epoch": 0.51, + "learning_rate": 2.431567526453547e-05, + "loss": 0.131, + "step": 230720 + }, + { + "epoch": 0.52, + "learning_rate": 2.4314556721326145e-05, + "loss": 0.1314, + "step": 230730 + }, + { + "epoch": 0.52, + "learning_rate": 2.431343817811682e-05, + "loss": 0.1281, + "step": 230740 + }, + { + "epoch": 0.52, + "learning_rate": 2.4312319634907498e-05, + "loss": 0.1325, + "step": 230750 + }, + { + "epoch": 0.52, + "learning_rate": 2.4311201091698175e-05, + "loss": 0.1323, + "step": 230760 + }, + { + "epoch": 0.52, + "learning_rate": 2.431008254848885e-05, + "loss": 0.126, + "step": 230770 + }, + { + "epoch": 0.52, + "learning_rate": 2.4308964005279525e-05, + "loss": 0.1261, + "step": 230780 + }, + { + "epoch": 0.52, + "learning_rate": 2.43078454620702e-05, + "loss": 0.1283, + "step": 230790 + }, + { + "epoch": 0.52, + "learning_rate": 2.4306726918860877e-05, + "loss": 0.1317, + "step": 230800 + }, + { + "epoch": 0.52, + "learning_rate": 2.4305608375651555e-05, + "loss": 0.1316, + "step": 230810 + }, + { + "epoch": 0.52, + "learning_rate": 2.430448983244223e-05, + "loss": 0.131, + "step": 230820 + }, + { + "epoch": 0.52, + "learning_rate": 2.4303371289232904e-05, + "loss": 0.1241, + "step": 230830 + }, + { + "epoch": 0.52, + "learning_rate": 2.430225274602358e-05, + "loss": 0.1313, + "step": 230840 + }, + { + "epoch": 0.52, + "learning_rate": 2.4301134202814253e-05, + "loss": 0.1261, + "step": 230850 + }, + { + "epoch": 0.52, + "learning_rate": 2.4300015659604934e-05, + "loss": 0.1343, + "step": 230860 + }, + { + "epoch": 0.52, + "learning_rate": 2.429889711639561e-05, + "loss": 0.1292, + "step": 230870 + }, + { + "epoch": 0.52, + "learning_rate": 2.4297778573186284e-05, + "loss": 0.1278, + "step": 230880 + }, + { + "epoch": 0.52, + "learning_rate": 2.4296660029976958e-05, + "loss": 0.1321, + "step": 230890 + }, + { + "epoch": 0.52, + "learning_rate": 2.4295541486767633e-05, + "loss": 0.1306, + "step": 230900 + }, + { + "epoch": 0.52, + "learning_rate": 2.429442294355831e-05, + "loss": 0.1297, + "step": 230910 + }, + { + "epoch": 0.52, + "learning_rate": 2.429330440034899e-05, + "loss": 0.1352, + "step": 230920 + }, + { + "epoch": 0.52, + "learning_rate": 2.4292185857139663e-05, + "loss": 0.1355, + "step": 230930 + }, + { + "epoch": 0.52, + "learning_rate": 2.4291067313930338e-05, + "loss": 0.1249, + "step": 230940 + }, + { + "epoch": 0.52, + "learning_rate": 2.4289948770721012e-05, + "loss": 0.1253, + "step": 230950 + }, + { + "epoch": 0.52, + "learning_rate": 2.428883022751169e-05, + "loss": 0.1274, + "step": 230960 + }, + { + "epoch": 0.52, + "learning_rate": 2.4287711684302368e-05, + "loss": 0.1325, + "step": 230970 + }, + { + "epoch": 0.52, + "learning_rate": 2.4286593141093042e-05, + "loss": 0.1303, + "step": 230980 + }, + { + "epoch": 0.52, + "learning_rate": 2.4285474597883717e-05, + "loss": 0.129, + "step": 230990 + }, + { + "epoch": 0.52, + "learning_rate": 2.428435605467439e-05, + "loss": 0.1345, + "step": 231000 + }, + { + "epoch": 0.52, + "learning_rate": 2.428323751146507e-05, + "loss": 0.1276, + "step": 231010 + }, + { + "epoch": 0.52, + "learning_rate": 2.4282118968255747e-05, + "loss": 0.131, + "step": 231020 + }, + { + "epoch": 0.52, + "learning_rate": 2.4281000425046422e-05, + "loss": 0.13, + "step": 231030 + }, + { + "epoch": 0.52, + "learning_rate": 2.4279881881837096e-05, + "loss": 0.1319, + "step": 231040 + }, + { + "epoch": 0.52, + "learning_rate": 2.427876333862777e-05, + "loss": 0.1292, + "step": 231050 + }, + { + "epoch": 0.52, + "learning_rate": 2.4277644795418446e-05, + "loss": 0.131, + "step": 231060 + }, + { + "epoch": 0.52, + "learning_rate": 2.4276526252209127e-05, + "loss": 0.1317, + "step": 231070 + }, + { + "epoch": 0.52, + "learning_rate": 2.42754077089998e-05, + "loss": 0.1287, + "step": 231080 + }, + { + "epoch": 0.52, + "learning_rate": 2.4274289165790476e-05, + "loss": 0.1281, + "step": 231090 + }, + { + "epoch": 0.52, + "learning_rate": 2.427317062258115e-05, + "loss": 0.1243, + "step": 231100 + }, + { + "epoch": 0.52, + "learning_rate": 2.4272052079371825e-05, + "loss": 0.1288, + "step": 231110 + }, + { + "epoch": 0.52, + "learning_rate": 2.4270933536162503e-05, + "loss": 0.1325, + "step": 231120 + }, + { + "epoch": 0.52, + "learning_rate": 2.426981499295318e-05, + "loss": 0.1275, + "step": 231130 + }, + { + "epoch": 0.52, + "learning_rate": 2.4268696449743855e-05, + "loss": 0.1318, + "step": 231140 + }, + { + "epoch": 0.52, + "learning_rate": 2.426757790653453e-05, + "loss": 0.1278, + "step": 231150 + }, + { + "epoch": 0.52, + "learning_rate": 2.4266459363325204e-05, + "loss": 0.1342, + "step": 231160 + }, + { + "epoch": 0.52, + "learning_rate": 2.4265340820115882e-05, + "loss": 0.1294, + "step": 231170 + }, + { + "epoch": 0.52, + "learning_rate": 2.426422227690656e-05, + "loss": 0.1253, + "step": 231180 + }, + { + "epoch": 0.52, + "learning_rate": 2.4263103733697235e-05, + "loss": 0.1265, + "step": 231190 + }, + { + "epoch": 0.52, + "learning_rate": 2.426198519048791e-05, + "loss": 0.1287, + "step": 231200 + }, + { + "epoch": 0.52, + "learning_rate": 2.4260866647278584e-05, + "loss": 0.1269, + "step": 231210 + }, + { + "epoch": 0.52, + "learning_rate": 2.4259748104069262e-05, + "loss": 0.1372, + "step": 231220 + }, + { + "epoch": 0.52, + "learning_rate": 2.425862956085994e-05, + "loss": 0.1308, + "step": 231230 + }, + { + "epoch": 0.52, + "learning_rate": 2.4257511017650614e-05, + "loss": 0.1344, + "step": 231240 + }, + { + "epoch": 0.52, + "learning_rate": 2.425639247444129e-05, + "loss": 0.1304, + "step": 231250 + }, + { + "epoch": 0.52, + "learning_rate": 2.4255273931231963e-05, + "loss": 0.1293, + "step": 231260 + }, + { + "epoch": 0.52, + "learning_rate": 2.4254155388022638e-05, + "loss": 0.1325, + "step": 231270 + }, + { + "epoch": 0.52, + "learning_rate": 2.4253036844813316e-05, + "loss": 0.1281, + "step": 231280 + }, + { + "epoch": 0.52, + "learning_rate": 2.4251918301603994e-05, + "loss": 0.1325, + "step": 231290 + }, + { + "epoch": 0.52, + "learning_rate": 2.425079975839467e-05, + "loss": 0.1344, + "step": 231300 + }, + { + "epoch": 0.52, + "learning_rate": 2.4249681215185343e-05, + "loss": 0.1257, + "step": 231310 + }, + { + "epoch": 0.52, + "learning_rate": 2.4248562671976017e-05, + "loss": 0.1314, + "step": 231320 + }, + { + "epoch": 0.52, + "learning_rate": 2.4247444128766695e-05, + "loss": 0.1306, + "step": 231330 + }, + { + "epoch": 0.52, + "learning_rate": 2.4246325585557373e-05, + "loss": 0.1355, + "step": 231340 + }, + { + "epoch": 0.52, + "learning_rate": 2.4245207042348048e-05, + "loss": 0.126, + "step": 231350 + }, + { + "epoch": 0.52, + "learning_rate": 2.4244088499138722e-05, + "loss": 0.1301, + "step": 231360 + }, + { + "epoch": 0.52, + "learning_rate": 2.4242969955929397e-05, + "loss": 0.1325, + "step": 231370 + }, + { + "epoch": 0.52, + "learning_rate": 2.4241851412720075e-05, + "loss": 0.1281, + "step": 231380 + }, + { + "epoch": 0.52, + "learning_rate": 2.4240732869510753e-05, + "loss": 0.1297, + "step": 231390 + }, + { + "epoch": 0.52, + "learning_rate": 2.4239614326301427e-05, + "loss": 0.1318, + "step": 231400 + }, + { + "epoch": 0.52, + "learning_rate": 2.4238495783092102e-05, + "loss": 0.1313, + "step": 231410 + }, + { + "epoch": 0.52, + "learning_rate": 2.4237377239882776e-05, + "loss": 0.1264, + "step": 231420 + }, + { + "epoch": 0.52, + "learning_rate": 2.4236258696673454e-05, + "loss": 0.1286, + "step": 231430 + }, + { + "epoch": 0.52, + "learning_rate": 2.423514015346413e-05, + "loss": 0.1337, + "step": 231440 + }, + { + "epoch": 0.52, + "learning_rate": 2.4234021610254807e-05, + "loss": 0.1278, + "step": 231450 + }, + { + "epoch": 0.52, + "learning_rate": 2.423290306704548e-05, + "loss": 0.1287, + "step": 231460 + }, + { + "epoch": 0.52, + "learning_rate": 2.4231784523836156e-05, + "loss": 0.1311, + "step": 231470 + }, + { + "epoch": 0.52, + "learning_rate": 2.4230665980626834e-05, + "loss": 0.1269, + "step": 231480 + }, + { + "epoch": 0.52, + "learning_rate": 2.422954743741751e-05, + "loss": 0.1287, + "step": 231490 + }, + { + "epoch": 0.52, + "learning_rate": 2.4228428894208186e-05, + "loss": 0.1283, + "step": 231500 + }, + { + "epoch": 0.52, + "learning_rate": 2.422731035099886e-05, + "loss": 0.1294, + "step": 231510 + }, + { + "epoch": 0.52, + "learning_rate": 2.4226191807789535e-05, + "loss": 0.132, + "step": 231520 + }, + { + "epoch": 0.52, + "learning_rate": 2.422507326458021e-05, + "loss": 0.1265, + "step": 231530 + }, + { + "epoch": 0.52, + "learning_rate": 2.4223954721370888e-05, + "loss": 0.13, + "step": 231540 + }, + { + "epoch": 0.52, + "learning_rate": 2.4222836178161566e-05, + "loss": 0.1314, + "step": 231550 + }, + { + "epoch": 0.52, + "learning_rate": 2.422171763495224e-05, + "loss": 0.1296, + "step": 231560 + }, + { + "epoch": 0.52, + "learning_rate": 2.4220599091742915e-05, + "loss": 0.1292, + "step": 231570 + }, + { + "epoch": 0.52, + "learning_rate": 2.421948054853359e-05, + "loss": 0.131, + "step": 231580 + }, + { + "epoch": 0.52, + "learning_rate": 2.4218362005324267e-05, + "loss": 0.1325, + "step": 231590 + }, + { + "epoch": 0.52, + "learning_rate": 2.4217243462114942e-05, + "loss": 0.1276, + "step": 231600 + }, + { + "epoch": 0.52, + "learning_rate": 2.421612491890562e-05, + "loss": 0.1299, + "step": 231610 + }, + { + "epoch": 0.52, + "learning_rate": 2.4215006375696294e-05, + "loss": 0.133, + "step": 231620 + }, + { + "epoch": 0.52, + "learning_rate": 2.421388783248697e-05, + "loss": 0.1343, + "step": 231630 + }, + { + "epoch": 0.52, + "learning_rate": 2.4212769289277647e-05, + "loss": 0.1242, + "step": 231640 + }, + { + "epoch": 0.52, + "learning_rate": 2.421165074606832e-05, + "loss": 0.1287, + "step": 231650 + }, + { + "epoch": 0.52, + "learning_rate": 2.4210532202859e-05, + "loss": 0.132, + "step": 231660 + }, + { + "epoch": 0.52, + "learning_rate": 2.4209413659649674e-05, + "loss": 0.1296, + "step": 231670 + }, + { + "epoch": 0.52, + "learning_rate": 2.420829511644035e-05, + "loss": 0.1313, + "step": 231680 + }, + { + "epoch": 0.52, + "learning_rate": 2.4207176573231026e-05, + "loss": 0.131, + "step": 231690 + }, + { + "epoch": 0.52, + "learning_rate": 2.42060580300217e-05, + "loss": 0.1309, + "step": 231700 + }, + { + "epoch": 0.52, + "learning_rate": 2.420493948681238e-05, + "loss": 0.1342, + "step": 231710 + }, + { + "epoch": 0.52, + "learning_rate": 2.4203820943603053e-05, + "loss": 0.1307, + "step": 231720 + }, + { + "epoch": 0.52, + "learning_rate": 2.4202702400393728e-05, + "loss": 0.1303, + "step": 231730 + }, + { + "epoch": 0.52, + "learning_rate": 2.4201583857184402e-05, + "loss": 0.1301, + "step": 231740 + }, + { + "epoch": 0.52, + "learning_rate": 2.420046531397508e-05, + "loss": 0.1305, + "step": 231750 + }, + { + "epoch": 0.52, + "learning_rate": 2.4199346770765755e-05, + "loss": 0.129, + "step": 231760 + }, + { + "epoch": 0.52, + "learning_rate": 2.4198228227556433e-05, + "loss": 0.1295, + "step": 231770 + }, + { + "epoch": 0.52, + "learning_rate": 2.4197109684347107e-05, + "loss": 0.1287, + "step": 231780 + }, + { + "epoch": 0.52, + "learning_rate": 2.4195991141137782e-05, + "loss": 0.1309, + "step": 231790 + }, + { + "epoch": 0.52, + "learning_rate": 2.419487259792846e-05, + "loss": 0.1294, + "step": 231800 + }, + { + "epoch": 0.52, + "learning_rate": 2.4193754054719134e-05, + "loss": 0.1285, + "step": 231810 + }, + { + "epoch": 0.52, + "learning_rate": 2.4192635511509812e-05, + "loss": 0.1337, + "step": 231820 + }, + { + "epoch": 0.52, + "learning_rate": 2.4191516968300487e-05, + "loss": 0.1275, + "step": 231830 + }, + { + "epoch": 0.52, + "learning_rate": 2.419039842509116e-05, + "loss": 0.125, + "step": 231840 + }, + { + "epoch": 0.52, + "learning_rate": 2.418927988188184e-05, + "loss": 0.1328, + "step": 231850 + }, + { + "epoch": 0.52, + "learning_rate": 2.4188161338672514e-05, + "loss": 0.1283, + "step": 231860 + }, + { + "epoch": 0.52, + "learning_rate": 2.418704279546319e-05, + "loss": 0.1391, + "step": 231870 + }, + { + "epoch": 0.52, + "learning_rate": 2.4185924252253866e-05, + "loss": 0.1265, + "step": 231880 + }, + { + "epoch": 0.52, + "learning_rate": 2.418480570904454e-05, + "loss": 0.1298, + "step": 231890 + }, + { + "epoch": 0.52, + "learning_rate": 2.418368716583522e-05, + "loss": 0.1329, + "step": 231900 + }, + { + "epoch": 0.52, + "learning_rate": 2.4182568622625893e-05, + "loss": 0.1271, + "step": 231910 + }, + { + "epoch": 0.52, + "learning_rate": 2.4181450079416568e-05, + "loss": 0.1318, + "step": 231920 + }, + { + "epoch": 0.52, + "learning_rate": 2.4180331536207246e-05, + "loss": 0.1298, + "step": 231930 + }, + { + "epoch": 0.52, + "learning_rate": 2.417921299299792e-05, + "loss": 0.1314, + "step": 231940 + }, + { + "epoch": 0.52, + "learning_rate": 2.4178094449788595e-05, + "loss": 0.1336, + "step": 231950 + }, + { + "epoch": 0.52, + "learning_rate": 2.4176975906579273e-05, + "loss": 0.1293, + "step": 231960 + }, + { + "epoch": 0.52, + "learning_rate": 2.4175857363369947e-05, + "loss": 0.1341, + "step": 231970 + }, + { + "epoch": 0.52, + "learning_rate": 2.4174738820160625e-05, + "loss": 0.1318, + "step": 231980 + }, + { + "epoch": 0.52, + "learning_rate": 2.41736202769513e-05, + "loss": 0.1299, + "step": 231990 + }, + { + "epoch": 0.52, + "learning_rate": 2.4172501733741974e-05, + "loss": 0.1294, + "step": 232000 + }, + { + "epoch": 0.52, + "learning_rate": 2.4171383190532652e-05, + "loss": 0.1284, + "step": 232010 + }, + { + "epoch": 0.52, + "learning_rate": 2.4170264647323327e-05, + "loss": 0.129, + "step": 232020 + }, + { + "epoch": 0.52, + "learning_rate": 2.4169257958434935e-05, + "loss": 0.1293, + "step": 232030 + }, + { + "epoch": 0.52, + "learning_rate": 2.416813941522561e-05, + "loss": 0.1291, + "step": 232040 + }, + { + "epoch": 0.52, + "learning_rate": 2.4167020872016288e-05, + "loss": 0.1347, + "step": 232050 + }, + { + "epoch": 0.52, + "learning_rate": 2.4165902328806962e-05, + "loss": 0.1347, + "step": 232060 + }, + { + "epoch": 0.52, + "learning_rate": 2.416478378559764e-05, + "loss": 0.129, + "step": 232070 + }, + { + "epoch": 0.52, + "learning_rate": 2.4163665242388315e-05, + "loss": 0.1315, + "step": 232080 + }, + { + "epoch": 0.52, + "learning_rate": 2.416254669917899e-05, + "loss": 0.1343, + "step": 232090 + }, + { + "epoch": 0.52, + "learning_rate": 2.4161428155969667e-05, + "loss": 0.1338, + "step": 232100 + }, + { + "epoch": 0.52, + "learning_rate": 2.4160309612760342e-05, + "loss": 0.1276, + "step": 232110 + }, + { + "epoch": 0.52, + "learning_rate": 2.4159191069551017e-05, + "loss": 0.1305, + "step": 232120 + }, + { + "epoch": 0.52, + "learning_rate": 2.4158072526341694e-05, + "loss": 0.1275, + "step": 232130 + }, + { + "epoch": 0.52, + "learning_rate": 2.415695398313237e-05, + "loss": 0.1306, + "step": 232140 + }, + { + "epoch": 0.52, + "learning_rate": 2.4155835439923044e-05, + "loss": 0.1269, + "step": 232150 + }, + { + "epoch": 0.52, + "learning_rate": 2.415471689671372e-05, + "loss": 0.1297, + "step": 232160 + }, + { + "epoch": 0.52, + "learning_rate": 2.4153598353504396e-05, + "loss": 0.1293, + "step": 232170 + }, + { + "epoch": 0.52, + "learning_rate": 2.4152479810295074e-05, + "loss": 0.1334, + "step": 232180 + }, + { + "epoch": 0.52, + "learning_rate": 2.415136126708575e-05, + "loss": 0.1252, + "step": 232190 + }, + { + "epoch": 0.52, + "learning_rate": 2.4150242723876423e-05, + "loss": 0.1292, + "step": 232200 + }, + { + "epoch": 0.52, + "learning_rate": 2.41491241806671e-05, + "loss": 0.1286, + "step": 232210 + }, + { + "epoch": 0.52, + "learning_rate": 2.4148005637457775e-05, + "loss": 0.1278, + "step": 232220 + }, + { + "epoch": 0.52, + "learning_rate": 2.4146887094248453e-05, + "loss": 0.1321, + "step": 232230 + }, + { + "epoch": 0.52, + "learning_rate": 2.4145768551039128e-05, + "loss": 0.1293, + "step": 232240 + }, + { + "epoch": 0.52, + "learning_rate": 2.4144650007829802e-05, + "loss": 0.1303, + "step": 232250 + }, + { + "epoch": 0.52, + "learning_rate": 2.414353146462048e-05, + "loss": 0.1327, + "step": 232260 + }, + { + "epoch": 0.52, + "learning_rate": 2.4142412921411155e-05, + "loss": 0.1268, + "step": 232270 + }, + { + "epoch": 0.52, + "learning_rate": 2.4141294378201833e-05, + "loss": 0.1346, + "step": 232280 + }, + { + "epoch": 0.52, + "learning_rate": 2.4140175834992507e-05, + "loss": 0.1302, + "step": 232290 + }, + { + "epoch": 0.52, + "learning_rate": 2.4139057291783182e-05, + "loss": 0.1366, + "step": 232300 + }, + { + "epoch": 0.52, + "learning_rate": 2.4137938748573856e-05, + "loss": 0.1305, + "step": 232310 + }, + { + "epoch": 0.52, + "learning_rate": 2.4136820205364534e-05, + "loss": 0.1297, + "step": 232320 + }, + { + "epoch": 0.52, + "learning_rate": 2.4135701662155212e-05, + "loss": 0.1327, + "step": 232330 + }, + { + "epoch": 0.52, + "learning_rate": 2.4134583118945887e-05, + "loss": 0.1288, + "step": 232340 + }, + { + "epoch": 0.52, + "learning_rate": 2.413346457573656e-05, + "loss": 0.1278, + "step": 232350 + }, + { + "epoch": 0.52, + "learning_rate": 2.4132346032527236e-05, + "loss": 0.1301, + "step": 232360 + }, + { + "epoch": 0.52, + "learning_rate": 2.4131227489317914e-05, + "loss": 0.1323, + "step": 232370 + }, + { + "epoch": 0.52, + "learning_rate": 2.413010894610859e-05, + "loss": 0.1322, + "step": 232380 + }, + { + "epoch": 0.52, + "learning_rate": 2.4128990402899266e-05, + "loss": 0.124, + "step": 232390 + }, + { + "epoch": 0.52, + "learning_rate": 2.412787185968994e-05, + "loss": 0.1258, + "step": 232400 + }, + { + "epoch": 0.52, + "learning_rate": 2.4126753316480615e-05, + "loss": 0.1317, + "step": 232410 + }, + { + "epoch": 0.52, + "learning_rate": 2.4125634773271293e-05, + "loss": 0.1312, + "step": 232420 + }, + { + "epoch": 0.52, + "learning_rate": 2.4124516230061968e-05, + "loss": 0.1251, + "step": 232430 + }, + { + "epoch": 0.52, + "learning_rate": 2.4123397686852646e-05, + "loss": 0.1337, + "step": 232440 + }, + { + "epoch": 0.52, + "learning_rate": 2.412227914364332e-05, + "loss": 0.1287, + "step": 232450 + }, + { + "epoch": 0.52, + "learning_rate": 2.4121160600433995e-05, + "loss": 0.1291, + "step": 232460 + }, + { + "epoch": 0.52, + "learning_rate": 2.412004205722467e-05, + "loss": 0.1296, + "step": 232470 + }, + { + "epoch": 0.52, + "learning_rate": 2.4118923514015347e-05, + "loss": 0.1329, + "step": 232480 + }, + { + "epoch": 0.52, + "learning_rate": 2.4117804970806025e-05, + "loss": 0.1334, + "step": 232490 + }, + { + "epoch": 0.52, + "learning_rate": 2.41166864275967e-05, + "loss": 0.1367, + "step": 232500 + }, + { + "epoch": 0.52, + "learning_rate": 2.4115567884387374e-05, + "loss": 0.1349, + "step": 232510 + }, + { + "epoch": 0.52, + "learning_rate": 2.411444934117805e-05, + "loss": 0.1258, + "step": 232520 + }, + { + "epoch": 0.52, + "learning_rate": 2.4113330797968727e-05, + "loss": 0.1318, + "step": 232530 + }, + { + "epoch": 0.52, + "learning_rate": 2.4112212254759405e-05, + "loss": 0.1265, + "step": 232540 + }, + { + "epoch": 0.52, + "learning_rate": 2.411109371155008e-05, + "loss": 0.1321, + "step": 232550 + }, + { + "epoch": 0.52, + "learning_rate": 2.4109975168340754e-05, + "loss": 0.1301, + "step": 232560 + }, + { + "epoch": 0.52, + "learning_rate": 2.410885662513143e-05, + "loss": 0.128, + "step": 232570 + }, + { + "epoch": 0.52, + "learning_rate": 2.4107738081922106e-05, + "loss": 0.1318, + "step": 232580 + }, + { + "epoch": 0.52, + "learning_rate": 2.410661953871278e-05, + "loss": 0.1306, + "step": 232590 + }, + { + "epoch": 0.52, + "learning_rate": 2.410550099550346e-05, + "loss": 0.128, + "step": 232600 + }, + { + "epoch": 0.52, + "learning_rate": 2.4104382452294133e-05, + "loss": 0.131, + "step": 232610 + }, + { + "epoch": 0.52, + "learning_rate": 2.4103263909084808e-05, + "loss": 0.1292, + "step": 232620 + }, + { + "epoch": 0.52, + "learning_rate": 2.4102145365875482e-05, + "loss": 0.1269, + "step": 232630 + }, + { + "epoch": 0.52, + "learning_rate": 2.410102682266616e-05, + "loss": 0.1311, + "step": 232640 + }, + { + "epoch": 0.52, + "learning_rate": 2.4099908279456838e-05, + "loss": 0.13, + "step": 232650 + }, + { + "epoch": 0.52, + "learning_rate": 2.4098789736247513e-05, + "loss": 0.1378, + "step": 232660 + }, + { + "epoch": 0.52, + "learning_rate": 2.4097671193038187e-05, + "loss": 0.1297, + "step": 232670 + }, + { + "epoch": 0.52, + "learning_rate": 2.4096552649828862e-05, + "loss": 0.1324, + "step": 232680 + }, + { + "epoch": 0.52, + "learning_rate": 2.409543410661954e-05, + "loss": 0.1311, + "step": 232690 + }, + { + "epoch": 0.52, + "learning_rate": 2.4094315563410218e-05, + "loss": 0.1315, + "step": 232700 + }, + { + "epoch": 0.52, + "learning_rate": 2.4093197020200892e-05, + "loss": 0.1306, + "step": 232710 + }, + { + "epoch": 0.52, + "learning_rate": 2.4092078476991567e-05, + "loss": 0.1336, + "step": 232720 + }, + { + "epoch": 0.52, + "learning_rate": 2.409095993378224e-05, + "loss": 0.1282, + "step": 232730 + }, + { + "epoch": 0.52, + "learning_rate": 2.408984139057292e-05, + "loss": 0.1295, + "step": 232740 + }, + { + "epoch": 0.52, + "learning_rate": 2.4088722847363597e-05, + "loss": 0.1298, + "step": 232750 + }, + { + "epoch": 0.52, + "learning_rate": 2.4087604304154272e-05, + "loss": 0.1318, + "step": 232760 + }, + { + "epoch": 0.52, + "learning_rate": 2.4086485760944946e-05, + "loss": 0.1279, + "step": 232770 + }, + { + "epoch": 0.52, + "learning_rate": 2.408536721773562e-05, + "loss": 0.1322, + "step": 232780 + }, + { + "epoch": 0.52, + "learning_rate": 2.4084248674526295e-05, + "loss": 0.1246, + "step": 232790 + }, + { + "epoch": 0.52, + "learning_rate": 2.4083130131316973e-05, + "loss": 0.1228, + "step": 232800 + }, + { + "epoch": 0.52, + "learning_rate": 2.408201158810765e-05, + "loss": 0.1286, + "step": 232810 + }, + { + "epoch": 0.52, + "learning_rate": 2.4080893044898326e-05, + "loss": 0.1282, + "step": 232820 + }, + { + "epoch": 0.52, + "learning_rate": 2.4079774501689e-05, + "loss": 0.1276, + "step": 232830 + }, + { + "epoch": 0.52, + "learning_rate": 2.4078655958479675e-05, + "loss": 0.1297, + "step": 232840 + }, + { + "epoch": 0.52, + "learning_rate": 2.4077537415270353e-05, + "loss": 0.1316, + "step": 232850 + }, + { + "epoch": 0.52, + "learning_rate": 2.407641887206103e-05, + "loss": 0.1321, + "step": 232860 + }, + { + "epoch": 0.52, + "learning_rate": 2.4075300328851705e-05, + "loss": 0.1295, + "step": 232870 + }, + { + "epoch": 0.52, + "learning_rate": 2.407418178564238e-05, + "loss": 0.1303, + "step": 232880 + }, + { + "epoch": 0.52, + "learning_rate": 2.4073063242433054e-05, + "loss": 0.1324, + "step": 232890 + }, + { + "epoch": 0.52, + "learning_rate": 2.4071944699223732e-05, + "loss": 0.1307, + "step": 232900 + }, + { + "epoch": 0.52, + "learning_rate": 2.407082615601441e-05, + "loss": 0.1311, + "step": 232910 + }, + { + "epoch": 0.52, + "learning_rate": 2.4069707612805085e-05, + "loss": 0.1277, + "step": 232920 + }, + { + "epoch": 0.52, + "learning_rate": 2.406858906959576e-05, + "loss": 0.1309, + "step": 232930 + }, + { + "epoch": 0.52, + "learning_rate": 2.4067470526386434e-05, + "loss": 0.1312, + "step": 232940 + }, + { + "epoch": 0.52, + "learning_rate": 2.4066351983177112e-05, + "loss": 0.1306, + "step": 232950 + }, + { + "epoch": 0.52, + "learning_rate": 2.406523343996779e-05, + "loss": 0.1308, + "step": 232960 + }, + { + "epoch": 0.52, + "learning_rate": 2.4064114896758464e-05, + "loss": 0.1256, + "step": 232970 + }, + { + "epoch": 0.52, + "learning_rate": 2.406299635354914e-05, + "loss": 0.13, + "step": 232980 + }, + { + "epoch": 0.52, + "learning_rate": 2.4061877810339813e-05, + "loss": 0.1302, + "step": 232990 + }, + { + "epoch": 0.52, + "learning_rate": 2.4060759267130488e-05, + "loss": 0.1284, + "step": 233000 + }, + { + "epoch": 0.52, + "learning_rate": 2.405964072392117e-05, + "loss": 0.1306, + "step": 233010 + }, + { + "epoch": 0.52, + "learning_rate": 2.4058522180711844e-05, + "loss": 0.1284, + "step": 233020 + }, + { + "epoch": 0.52, + "learning_rate": 2.4057403637502518e-05, + "loss": 0.1334, + "step": 233030 + }, + { + "epoch": 0.52, + "learning_rate": 2.4056285094293193e-05, + "loss": 0.1329, + "step": 233040 + }, + { + "epoch": 0.52, + "learning_rate": 2.4055166551083867e-05, + "loss": 0.1272, + "step": 233050 + }, + { + "epoch": 0.52, + "learning_rate": 2.4054048007874545e-05, + "loss": 0.1258, + "step": 233060 + }, + { + "epoch": 0.52, + "learning_rate": 2.4052929464665223e-05, + "loss": 0.1309, + "step": 233070 + }, + { + "epoch": 0.52, + "learning_rate": 2.4051810921455898e-05, + "loss": 0.1285, + "step": 233080 + }, + { + "epoch": 0.52, + "learning_rate": 2.4050692378246572e-05, + "loss": 0.1256, + "step": 233090 + }, + { + "epoch": 0.52, + "learning_rate": 2.4049573835037247e-05, + "loss": 0.1256, + "step": 233100 + }, + { + "epoch": 0.52, + "learning_rate": 2.4048455291827925e-05, + "loss": 0.1348, + "step": 233110 + }, + { + "epoch": 0.52, + "learning_rate": 2.4047336748618603e-05, + "loss": 0.134, + "step": 233120 + }, + { + "epoch": 0.52, + "learning_rate": 2.4046218205409277e-05, + "loss": 0.1278, + "step": 233130 + }, + { + "epoch": 0.52, + "learning_rate": 2.404509966219995e-05, + "loss": 0.1278, + "step": 233140 + }, + { + "epoch": 0.52, + "learning_rate": 2.4043981118990626e-05, + "loss": 0.1287, + "step": 233150 + }, + { + "epoch": 0.52, + "learning_rate": 2.4042862575781304e-05, + "loss": 0.1264, + "step": 233160 + }, + { + "epoch": 0.52, + "learning_rate": 2.4041744032571982e-05, + "loss": 0.1304, + "step": 233170 + }, + { + "epoch": 0.52, + "learning_rate": 2.4040625489362657e-05, + "loss": 0.1271, + "step": 233180 + }, + { + "epoch": 0.52, + "learning_rate": 2.403950694615333e-05, + "loss": 0.1303, + "step": 233190 + }, + { + "epoch": 0.52, + "learning_rate": 2.4038388402944006e-05, + "loss": 0.131, + "step": 233200 + }, + { + "epoch": 0.52, + "learning_rate": 2.403726985973468e-05, + "loss": 0.1335, + "step": 233210 + }, + { + "epoch": 0.52, + "learning_rate": 2.403615131652536e-05, + "loss": 0.1259, + "step": 233220 + }, + { + "epoch": 0.52, + "learning_rate": 2.4035032773316036e-05, + "loss": 0.1304, + "step": 233230 + }, + { + "epoch": 0.52, + "learning_rate": 2.403391423010671e-05, + "loss": 0.1283, + "step": 233240 + }, + { + "epoch": 0.52, + "learning_rate": 2.4032795686897385e-05, + "loss": 0.1298, + "step": 233250 + }, + { + "epoch": 0.52, + "learning_rate": 2.403167714368806e-05, + "loss": 0.1284, + "step": 233260 + }, + { + "epoch": 0.52, + "learning_rate": 2.4030558600478738e-05, + "loss": 0.1272, + "step": 233270 + }, + { + "epoch": 0.52, + "learning_rate": 2.4029440057269416e-05, + "loss": 0.1316, + "step": 233280 + }, + { + "epoch": 0.52, + "learning_rate": 2.402832151406009e-05, + "loss": 0.1301, + "step": 233290 + }, + { + "epoch": 0.52, + "learning_rate": 2.4027202970850765e-05, + "loss": 0.1331, + "step": 233300 + }, + { + "epoch": 0.52, + "learning_rate": 2.402608442764144e-05, + "loss": 0.1295, + "step": 233310 + }, + { + "epoch": 0.52, + "learning_rate": 2.4024965884432117e-05, + "loss": 0.1304, + "step": 233320 + }, + { + "epoch": 0.52, + "learning_rate": 2.4023847341222795e-05, + "loss": 0.1318, + "step": 233330 + }, + { + "epoch": 0.52, + "learning_rate": 2.402272879801347e-05, + "loss": 0.1246, + "step": 233340 + }, + { + "epoch": 0.52, + "learning_rate": 2.4021610254804144e-05, + "loss": 0.1277, + "step": 233350 + }, + { + "epoch": 0.52, + "learning_rate": 2.402049171159482e-05, + "loss": 0.1278, + "step": 233360 + }, + { + "epoch": 0.52, + "learning_rate": 2.4019373168385497e-05, + "loss": 0.1323, + "step": 233370 + }, + { + "epoch": 0.52, + "learning_rate": 2.4018254625176175e-05, + "loss": 0.1266, + "step": 233380 + }, + { + "epoch": 0.52, + "learning_rate": 2.401713608196685e-05, + "loss": 0.1311, + "step": 233390 + }, + { + "epoch": 0.52, + "learning_rate": 2.4016017538757524e-05, + "loss": 0.1306, + "step": 233400 + }, + { + "epoch": 0.52, + "learning_rate": 2.4014898995548198e-05, + "loss": 0.1303, + "step": 233410 + }, + { + "epoch": 0.52, + "learning_rate": 2.4013780452338873e-05, + "loss": 0.1319, + "step": 233420 + }, + { + "epoch": 0.52, + "learning_rate": 2.401266190912955e-05, + "loss": 0.1324, + "step": 233430 + }, + { + "epoch": 0.52, + "learning_rate": 2.401154336592023e-05, + "loss": 0.131, + "step": 233440 + }, + { + "epoch": 0.52, + "learning_rate": 2.4010424822710903e-05, + "loss": 0.129, + "step": 233450 + }, + { + "epoch": 0.52, + "learning_rate": 2.4009306279501578e-05, + "loss": 0.1288, + "step": 233460 + }, + { + "epoch": 0.52, + "learning_rate": 2.4008187736292252e-05, + "loss": 0.1253, + "step": 233470 + }, + { + "epoch": 0.52, + "learning_rate": 2.400706919308293e-05, + "loss": 0.1337, + "step": 233480 + }, + { + "epoch": 0.52, + "learning_rate": 2.4005950649873608e-05, + "loss": 0.1283, + "step": 233490 + }, + { + "epoch": 0.52, + "learning_rate": 2.4004832106664283e-05, + "loss": 0.1319, + "step": 233500 + }, + { + "epoch": 0.52, + "learning_rate": 2.4003713563454957e-05, + "loss": 0.1311, + "step": 233510 + }, + { + "epoch": 0.52, + "learning_rate": 2.400259502024563e-05, + "loss": 0.1339, + "step": 233520 + }, + { + "epoch": 0.52, + "learning_rate": 2.400147647703631e-05, + "loss": 0.1297, + "step": 233530 + }, + { + "epoch": 0.52, + "learning_rate": 2.4000357933826987e-05, + "loss": 0.1317, + "step": 233540 + }, + { + "epoch": 0.52, + "learning_rate": 2.3999239390617662e-05, + "loss": 0.1288, + "step": 233550 + }, + { + "epoch": 0.52, + "learning_rate": 2.3998120847408337e-05, + "loss": 0.1324, + "step": 233560 + }, + { + "epoch": 0.52, + "learning_rate": 2.399700230419901e-05, + "loss": 0.1317, + "step": 233570 + }, + { + "epoch": 0.52, + "learning_rate": 2.399588376098969e-05, + "loss": 0.1324, + "step": 233580 + }, + { + "epoch": 0.52, + "learning_rate": 2.3994765217780364e-05, + "loss": 0.132, + "step": 233590 + }, + { + "epoch": 0.52, + "learning_rate": 2.399364667457104e-05, + "loss": 0.1312, + "step": 233600 + }, + { + "epoch": 0.52, + "learning_rate": 2.3992528131361716e-05, + "loss": 0.1272, + "step": 233610 + }, + { + "epoch": 0.52, + "learning_rate": 2.399140958815239e-05, + "loss": 0.1236, + "step": 233620 + }, + { + "epoch": 0.52, + "learning_rate": 2.3990291044943065e-05, + "loss": 0.1259, + "step": 233630 + }, + { + "epoch": 0.52, + "learning_rate": 2.3989172501733743e-05, + "loss": 0.1289, + "step": 233640 + }, + { + "epoch": 0.52, + "learning_rate": 2.398805395852442e-05, + "loss": 0.1304, + "step": 233650 + }, + { + "epoch": 0.52, + "learning_rate": 2.3986935415315095e-05, + "loss": 0.1289, + "step": 233660 + }, + { + "epoch": 0.52, + "learning_rate": 2.398581687210577e-05, + "loss": 0.1358, + "step": 233670 + }, + { + "epoch": 0.52, + "learning_rate": 2.3984698328896445e-05, + "loss": 0.1327, + "step": 233680 + }, + { + "epoch": 0.52, + "learning_rate": 2.3983579785687122e-05, + "loss": 0.1297, + "step": 233690 + }, + { + "epoch": 0.52, + "learning_rate": 2.3982461242477797e-05, + "loss": 0.1341, + "step": 233700 + }, + { + "epoch": 0.52, + "learning_rate": 2.3981342699268475e-05, + "loss": 0.13, + "step": 233710 + }, + { + "epoch": 0.52, + "learning_rate": 2.398022415605915e-05, + "loss": 0.1373, + "step": 233720 + }, + { + "epoch": 0.52, + "learning_rate": 2.3979105612849824e-05, + "loss": 0.1318, + "step": 233730 + }, + { + "epoch": 0.52, + "learning_rate": 2.3977987069640502e-05, + "loss": 0.1317, + "step": 233740 + }, + { + "epoch": 0.52, + "learning_rate": 2.3976868526431177e-05, + "loss": 0.1296, + "step": 233750 + }, + { + "epoch": 0.52, + "learning_rate": 2.3975749983221854e-05, + "loss": 0.1332, + "step": 233760 + }, + { + "epoch": 0.52, + "learning_rate": 2.397463144001253e-05, + "loss": 0.1294, + "step": 233770 + }, + { + "epoch": 0.52, + "learning_rate": 2.3973512896803204e-05, + "loss": 0.1323, + "step": 233780 + }, + { + "epoch": 0.52, + "learning_rate": 2.397239435359388e-05, + "loss": 0.1254, + "step": 233790 + }, + { + "epoch": 0.52, + "learning_rate": 2.3971275810384556e-05, + "loss": 0.1286, + "step": 233800 + }, + { + "epoch": 0.52, + "learning_rate": 2.3970157267175234e-05, + "loss": 0.1281, + "step": 233810 + }, + { + "epoch": 0.52, + "learning_rate": 2.396903872396591e-05, + "loss": 0.1319, + "step": 233820 + }, + { + "epoch": 0.52, + "learning_rate": 2.3967920180756583e-05, + "loss": 0.1324, + "step": 233830 + }, + { + "epoch": 0.52, + "learning_rate": 2.396680163754726e-05, + "loss": 0.1339, + "step": 233840 + }, + { + "epoch": 0.52, + "learning_rate": 2.3965683094337935e-05, + "loss": 0.1288, + "step": 233850 + }, + { + "epoch": 0.52, + "learning_rate": 2.396456455112861e-05, + "loss": 0.1214, + "step": 233860 + }, + { + "epoch": 0.52, + "learning_rate": 2.3963446007919288e-05, + "loss": 0.1298, + "step": 233870 + }, + { + "epoch": 0.52, + "learning_rate": 2.3962327464709962e-05, + "loss": 0.1336, + "step": 233880 + }, + { + "epoch": 0.52, + "learning_rate": 2.3961208921500637e-05, + "loss": 0.1314, + "step": 233890 + }, + { + "epoch": 0.52, + "learning_rate": 2.3960090378291315e-05, + "loss": 0.1288, + "step": 233900 + }, + { + "epoch": 0.52, + "learning_rate": 2.395897183508199e-05, + "loss": 0.1307, + "step": 233910 + }, + { + "epoch": 0.52, + "learning_rate": 2.3957853291872667e-05, + "loss": 0.128, + "step": 233920 + }, + { + "epoch": 0.52, + "learning_rate": 2.3956734748663342e-05, + "loss": 0.1275, + "step": 233930 + }, + { + "epoch": 0.52, + "learning_rate": 2.3955616205454016e-05, + "loss": 0.1313, + "step": 233940 + }, + { + "epoch": 0.52, + "learning_rate": 2.3954497662244694e-05, + "loss": 0.1306, + "step": 233950 + }, + { + "epoch": 0.52, + "learning_rate": 2.395337911903537e-05, + "loss": 0.127, + "step": 233960 + }, + { + "epoch": 0.52, + "learning_rate": 2.3952260575826047e-05, + "loss": 0.1308, + "step": 233970 + }, + { + "epoch": 0.52, + "learning_rate": 2.395114203261672e-05, + "loss": 0.1356, + "step": 233980 + }, + { + "epoch": 0.52, + "learning_rate": 2.3950023489407396e-05, + "loss": 0.131, + "step": 233990 + }, + { + "epoch": 0.52, + "learning_rate": 2.3948904946198074e-05, + "loss": 0.1273, + "step": 234000 + }, + { + "epoch": 0.52, + "learning_rate": 2.394778640298875e-05, + "loss": 0.1289, + "step": 234010 + }, + { + "epoch": 0.52, + "learning_rate": 2.3946667859779423e-05, + "loss": 0.1324, + "step": 234020 + }, + { + "epoch": 0.52, + "learning_rate": 2.3945661170891032e-05, + "loss": 0.1332, + "step": 234030 + }, + { + "epoch": 0.52, + "learning_rate": 2.394454262768171e-05, + "loss": 0.1251, + "step": 234040 + }, + { + "epoch": 0.52, + "learning_rate": 2.3943424084472384e-05, + "loss": 0.1336, + "step": 234050 + }, + { + "epoch": 0.52, + "learning_rate": 2.394230554126306e-05, + "loss": 0.1278, + "step": 234060 + }, + { + "epoch": 0.52, + "learning_rate": 2.3941186998053737e-05, + "loss": 0.1306, + "step": 234070 + }, + { + "epoch": 0.52, + "learning_rate": 2.394006845484441e-05, + "loss": 0.1308, + "step": 234080 + }, + { + "epoch": 0.52, + "learning_rate": 2.3938949911635086e-05, + "loss": 0.1303, + "step": 234090 + }, + { + "epoch": 0.52, + "learning_rate": 2.3937831368425764e-05, + "loss": 0.1252, + "step": 234100 + }, + { + "epoch": 0.52, + "learning_rate": 2.3936712825216438e-05, + "loss": 0.1265, + "step": 234110 + }, + { + "epoch": 0.52, + "learning_rate": 2.3935594282007116e-05, + "loss": 0.1289, + "step": 234120 + }, + { + "epoch": 0.52, + "learning_rate": 2.393447573879779e-05, + "loss": 0.1315, + "step": 234130 + }, + { + "epoch": 0.52, + "learning_rate": 2.3933357195588465e-05, + "loss": 0.1315, + "step": 234140 + }, + { + "epoch": 0.52, + "learning_rate": 2.3932238652379143e-05, + "loss": 0.1306, + "step": 234150 + }, + { + "epoch": 0.52, + "learning_rate": 2.3931120109169818e-05, + "loss": 0.1294, + "step": 234160 + }, + { + "epoch": 0.52, + "learning_rate": 2.3930001565960496e-05, + "loss": 0.1312, + "step": 234170 + }, + { + "epoch": 0.52, + "learning_rate": 2.392888302275117e-05, + "loss": 0.1259, + "step": 234180 + }, + { + "epoch": 0.52, + "learning_rate": 2.3927764479541845e-05, + "loss": 0.1305, + "step": 234190 + }, + { + "epoch": 0.52, + "learning_rate": 2.3926645936332523e-05, + "loss": 0.1284, + "step": 234200 + }, + { + "epoch": 0.52, + "learning_rate": 2.3925527393123197e-05, + "loss": 0.127, + "step": 234210 + }, + { + "epoch": 0.52, + "learning_rate": 2.3924408849913875e-05, + "loss": 0.1308, + "step": 234220 + }, + { + "epoch": 0.52, + "learning_rate": 2.392329030670455e-05, + "loss": 0.1269, + "step": 234230 + }, + { + "epoch": 0.52, + "learning_rate": 2.3922171763495224e-05, + "loss": 0.1275, + "step": 234240 + }, + { + "epoch": 0.52, + "learning_rate": 2.39210532202859e-05, + "loss": 0.1312, + "step": 234250 + }, + { + "epoch": 0.52, + "learning_rate": 2.3919934677076577e-05, + "loss": 0.1274, + "step": 234260 + }, + { + "epoch": 0.52, + "learning_rate": 2.391881613386725e-05, + "loss": 0.1373, + "step": 234270 + }, + { + "epoch": 0.52, + "learning_rate": 2.391769759065793e-05, + "loss": 0.1232, + "step": 234280 + }, + { + "epoch": 0.52, + "learning_rate": 2.3916579047448604e-05, + "loss": 0.1296, + "step": 234290 + }, + { + "epoch": 0.52, + "learning_rate": 2.3915460504239278e-05, + "loss": 0.1303, + "step": 234300 + }, + { + "epoch": 0.52, + "learning_rate": 2.3914341961029956e-05, + "loss": 0.1299, + "step": 234310 + }, + { + "epoch": 0.52, + "learning_rate": 2.391322341782063e-05, + "loss": 0.126, + "step": 234320 + }, + { + "epoch": 0.52, + "learning_rate": 2.391210487461131e-05, + "loss": 0.1283, + "step": 234330 + }, + { + "epoch": 0.52, + "learning_rate": 2.3910986331401983e-05, + "loss": 0.1306, + "step": 234340 + }, + { + "epoch": 0.52, + "learning_rate": 2.3909867788192658e-05, + "loss": 0.1341, + "step": 234350 + }, + { + "epoch": 0.52, + "learning_rate": 2.3908749244983336e-05, + "loss": 0.1308, + "step": 234360 + }, + { + "epoch": 0.52, + "learning_rate": 2.390763070177401e-05, + "loss": 0.1335, + "step": 234370 + }, + { + "epoch": 0.52, + "learning_rate": 2.3906512158564688e-05, + "loss": 0.1312, + "step": 234380 + }, + { + "epoch": 0.52, + "learning_rate": 2.3905393615355363e-05, + "loss": 0.1307, + "step": 234390 + }, + { + "epoch": 0.52, + "learning_rate": 2.3904275072146037e-05, + "loss": 0.1311, + "step": 234400 + }, + { + "epoch": 0.52, + "learning_rate": 2.390315652893671e-05, + "loss": 0.1298, + "step": 234410 + }, + { + "epoch": 0.52, + "learning_rate": 2.390203798572739e-05, + "loss": 0.1279, + "step": 234420 + }, + { + "epoch": 0.52, + "learning_rate": 2.3900919442518068e-05, + "loss": 0.1297, + "step": 234430 + }, + { + "epoch": 0.52, + "learning_rate": 2.3899800899308742e-05, + "loss": 0.128, + "step": 234440 + }, + { + "epoch": 0.52, + "learning_rate": 2.3898682356099417e-05, + "loss": 0.1293, + "step": 234450 + }, + { + "epoch": 0.52, + "learning_rate": 2.389756381289009e-05, + "loss": 0.1248, + "step": 234460 + }, + { + "epoch": 0.52, + "learning_rate": 2.389644526968077e-05, + "loss": 0.1305, + "step": 234470 + }, + { + "epoch": 0.52, + "learning_rate": 2.3895326726471447e-05, + "loss": 0.1279, + "step": 234480 + }, + { + "epoch": 0.52, + "learning_rate": 2.389420818326212e-05, + "loss": 0.1327, + "step": 234490 + }, + { + "epoch": 0.52, + "learning_rate": 2.3893089640052796e-05, + "loss": 0.132, + "step": 234500 + }, + { + "epoch": 0.52, + "learning_rate": 2.389197109684347e-05, + "loss": 0.1325, + "step": 234510 + }, + { + "epoch": 0.52, + "learning_rate": 2.389085255363415e-05, + "loss": 0.133, + "step": 234520 + }, + { + "epoch": 0.52, + "learning_rate": 2.3889734010424823e-05, + "loss": 0.1292, + "step": 234530 + }, + { + "epoch": 0.52, + "learning_rate": 2.38886154672155e-05, + "loss": 0.1313, + "step": 234540 + }, + { + "epoch": 0.52, + "learning_rate": 2.3887496924006176e-05, + "loss": 0.1274, + "step": 234550 + }, + { + "epoch": 0.52, + "learning_rate": 2.388637838079685e-05, + "loss": 0.1281, + "step": 234560 + }, + { + "epoch": 0.52, + "learning_rate": 2.3885259837587525e-05, + "loss": 0.1323, + "step": 234570 + }, + { + "epoch": 0.52, + "learning_rate": 2.3884141294378203e-05, + "loss": 0.1251, + "step": 234580 + }, + { + "epoch": 0.52, + "learning_rate": 2.388302275116888e-05, + "loss": 0.1271, + "step": 234590 + }, + { + "epoch": 0.52, + "learning_rate": 2.3881904207959555e-05, + "loss": 0.1264, + "step": 234600 + }, + { + "epoch": 0.52, + "learning_rate": 2.388078566475023e-05, + "loss": 0.1288, + "step": 234610 + }, + { + "epoch": 0.52, + "learning_rate": 2.3879667121540904e-05, + "loss": 0.1284, + "step": 234620 + }, + { + "epoch": 0.52, + "learning_rate": 2.3878548578331582e-05, + "loss": 0.1247, + "step": 234630 + }, + { + "epoch": 0.52, + "learning_rate": 2.387743003512226e-05, + "loss": 0.1266, + "step": 234640 + }, + { + "epoch": 0.52, + "learning_rate": 2.3876311491912935e-05, + "loss": 0.1267, + "step": 234650 + }, + { + "epoch": 0.52, + "learning_rate": 2.387519294870361e-05, + "loss": 0.1297, + "step": 234660 + }, + { + "epoch": 0.52, + "learning_rate": 2.3874074405494284e-05, + "loss": 0.129, + "step": 234670 + }, + { + "epoch": 0.52, + "learning_rate": 2.387295586228496e-05, + "loss": 0.1268, + "step": 234680 + }, + { + "epoch": 0.52, + "learning_rate": 2.387183731907564e-05, + "loss": 0.1293, + "step": 234690 + }, + { + "epoch": 0.52, + "learning_rate": 2.3870718775866314e-05, + "loss": 0.1261, + "step": 234700 + }, + { + "epoch": 0.52, + "learning_rate": 2.386960023265699e-05, + "loss": 0.1317, + "step": 234710 + }, + { + "epoch": 0.52, + "learning_rate": 2.3868481689447663e-05, + "loss": 0.13, + "step": 234720 + }, + { + "epoch": 0.52, + "learning_rate": 2.3867363146238338e-05, + "loss": 0.1353, + "step": 234730 + }, + { + "epoch": 0.52, + "learning_rate": 2.3866244603029016e-05, + "loss": 0.1291, + "step": 234740 + }, + { + "epoch": 0.52, + "learning_rate": 2.3865126059819693e-05, + "loss": 0.1299, + "step": 234750 + }, + { + "epoch": 0.52, + "learning_rate": 2.3864007516610368e-05, + "loss": 0.1346, + "step": 234760 + }, + { + "epoch": 0.52, + "learning_rate": 2.3862888973401043e-05, + "loss": 0.1281, + "step": 234770 + }, + { + "epoch": 0.52, + "learning_rate": 2.3861770430191717e-05, + "loss": 0.127, + "step": 234780 + }, + { + "epoch": 0.52, + "learning_rate": 2.3860651886982395e-05, + "loss": 0.1274, + "step": 234790 + }, + { + "epoch": 0.52, + "learning_rate": 2.3859533343773073e-05, + "loss": 0.1301, + "step": 234800 + }, + { + "epoch": 0.52, + "learning_rate": 2.3858414800563747e-05, + "loss": 0.1308, + "step": 234810 + }, + { + "epoch": 0.52, + "learning_rate": 2.3857296257354422e-05, + "loss": 0.1305, + "step": 234820 + }, + { + "epoch": 0.52, + "learning_rate": 2.3856177714145097e-05, + "loss": 0.1316, + "step": 234830 + }, + { + "epoch": 0.52, + "learning_rate": 2.3855059170935774e-05, + "loss": 0.1265, + "step": 234840 + }, + { + "epoch": 0.52, + "learning_rate": 2.3853940627726452e-05, + "loss": 0.125, + "step": 234850 + }, + { + "epoch": 0.52, + "learning_rate": 2.3852822084517127e-05, + "loss": 0.1303, + "step": 234860 + }, + { + "epoch": 0.52, + "learning_rate": 2.38517035413078e-05, + "loss": 0.1293, + "step": 234870 + }, + { + "epoch": 0.52, + "learning_rate": 2.3850584998098476e-05, + "loss": 0.1266, + "step": 234880 + }, + { + "epoch": 0.52, + "learning_rate": 2.384946645488915e-05, + "loss": 0.1309, + "step": 234890 + }, + { + "epoch": 0.52, + "learning_rate": 2.3848347911679832e-05, + "loss": 0.1317, + "step": 234900 + }, + { + "epoch": 0.52, + "learning_rate": 2.3847229368470506e-05, + "loss": 0.1292, + "step": 234910 + }, + { + "epoch": 0.52, + "learning_rate": 2.384611082526118e-05, + "loss": 0.1282, + "step": 234920 + }, + { + "epoch": 0.52, + "learning_rate": 2.3844992282051855e-05, + "loss": 0.135, + "step": 234930 + }, + { + "epoch": 0.52, + "learning_rate": 2.384387373884253e-05, + "loss": 0.1301, + "step": 234940 + }, + { + "epoch": 0.52, + "learning_rate": 2.3842755195633208e-05, + "loss": 0.1261, + "step": 234950 + }, + { + "epoch": 0.52, + "learning_rate": 2.3841636652423886e-05, + "loss": 0.1317, + "step": 234960 + }, + { + "epoch": 0.52, + "learning_rate": 2.384051810921456e-05, + "loss": 0.1302, + "step": 234970 + }, + { + "epoch": 0.52, + "learning_rate": 2.3839399566005235e-05, + "loss": 0.1301, + "step": 234980 + }, + { + "epoch": 0.52, + "learning_rate": 2.383828102279591e-05, + "loss": 0.1298, + "step": 234990 + }, + { + "epoch": 0.52, + "learning_rate": 2.3837162479586587e-05, + "loss": 0.1267, + "step": 235000 + }, + { + "epoch": 0.52, + "learning_rate": 2.3836043936377265e-05, + "loss": 0.1304, + "step": 235010 + }, + { + "epoch": 0.52, + "learning_rate": 2.383492539316794e-05, + "loss": 0.1285, + "step": 235020 + }, + { + "epoch": 0.52, + "learning_rate": 2.3833806849958614e-05, + "loss": 0.1286, + "step": 235030 + }, + { + "epoch": 0.52, + "learning_rate": 2.383268830674929e-05, + "loss": 0.1248, + "step": 235040 + }, + { + "epoch": 0.52, + "learning_rate": 2.3831569763539967e-05, + "loss": 0.1282, + "step": 235050 + }, + { + "epoch": 0.52, + "learning_rate": 2.3830451220330645e-05, + "loss": 0.1312, + "step": 235060 + }, + { + "epoch": 0.52, + "learning_rate": 2.382933267712132e-05, + "loss": 0.1295, + "step": 235070 + }, + { + "epoch": 0.52, + "learning_rate": 2.3828214133911994e-05, + "loss": 0.1321, + "step": 235080 + }, + { + "epoch": 0.52, + "learning_rate": 2.382709559070267e-05, + "loss": 0.1282, + "step": 235090 + }, + { + "epoch": 0.52, + "learning_rate": 2.3825977047493346e-05, + "loss": 0.1312, + "step": 235100 + }, + { + "epoch": 0.52, + "learning_rate": 2.3824858504284024e-05, + "loss": 0.1345, + "step": 235110 + }, + { + "epoch": 0.52, + "learning_rate": 2.38237399610747e-05, + "loss": 0.1302, + "step": 235120 + }, + { + "epoch": 0.52, + "learning_rate": 2.3822621417865373e-05, + "loss": 0.1302, + "step": 235130 + }, + { + "epoch": 0.52, + "learning_rate": 2.3821502874656048e-05, + "loss": 0.1337, + "step": 235140 + }, + { + "epoch": 0.52, + "learning_rate": 2.3820384331446722e-05, + "loss": 0.134, + "step": 235150 + }, + { + "epoch": 0.52, + "learning_rate": 2.38192657882374e-05, + "loss": 0.1321, + "step": 235160 + }, + { + "epoch": 0.52, + "learning_rate": 2.381814724502808e-05, + "loss": 0.1291, + "step": 235170 + }, + { + "epoch": 0.52, + "learning_rate": 2.3817028701818753e-05, + "loss": 0.1276, + "step": 235180 + }, + { + "epoch": 0.52, + "learning_rate": 2.3815910158609427e-05, + "loss": 0.12, + "step": 235190 + }, + { + "epoch": 0.52, + "learning_rate": 2.3814791615400102e-05, + "loss": 0.1243, + "step": 235200 + }, + { + "epoch": 0.53, + "learning_rate": 2.381367307219078e-05, + "loss": 0.136, + "step": 235210 + }, + { + "epoch": 0.53, + "learning_rate": 2.3812554528981458e-05, + "loss": 0.1271, + "step": 235220 + }, + { + "epoch": 0.53, + "learning_rate": 2.3811435985772132e-05, + "loss": 0.1312, + "step": 235230 + }, + { + "epoch": 0.53, + "learning_rate": 2.3810317442562807e-05, + "loss": 0.1312, + "step": 235240 + }, + { + "epoch": 0.53, + "learning_rate": 2.380919889935348e-05, + "loss": 0.1281, + "step": 235250 + }, + { + "epoch": 0.53, + "learning_rate": 2.380808035614416e-05, + "loss": 0.1252, + "step": 235260 + }, + { + "epoch": 0.53, + "learning_rate": 2.3806961812934837e-05, + "loss": 0.1284, + "step": 235270 + }, + { + "epoch": 0.53, + "learning_rate": 2.3805843269725512e-05, + "loss": 0.1277, + "step": 235280 + }, + { + "epoch": 0.53, + "learning_rate": 2.3804724726516186e-05, + "loss": 0.1296, + "step": 235290 + }, + { + "epoch": 0.53, + "learning_rate": 2.380360618330686e-05, + "loss": 0.1285, + "step": 235300 + }, + { + "epoch": 0.53, + "learning_rate": 2.380248764009754e-05, + "loss": 0.1271, + "step": 235310 + }, + { + "epoch": 0.53, + "learning_rate": 2.3801369096888217e-05, + "loss": 0.1367, + "step": 235320 + }, + { + "epoch": 0.53, + "learning_rate": 2.380025055367889e-05, + "loss": 0.1308, + "step": 235330 + }, + { + "epoch": 0.53, + "learning_rate": 2.3799132010469566e-05, + "loss": 0.134, + "step": 235340 + }, + { + "epoch": 0.53, + "learning_rate": 2.379801346726024e-05, + "loss": 0.1257, + "step": 235350 + }, + { + "epoch": 0.53, + "learning_rate": 2.3796894924050915e-05, + "loss": 0.1302, + "step": 235360 + }, + { + "epoch": 0.53, + "learning_rate": 2.3795776380841593e-05, + "loss": 0.129, + "step": 235370 + }, + { + "epoch": 0.53, + "learning_rate": 2.379465783763227e-05, + "loss": 0.1281, + "step": 235380 + }, + { + "epoch": 0.53, + "learning_rate": 2.3793539294422945e-05, + "loss": 0.1267, + "step": 235390 + }, + { + "epoch": 0.53, + "learning_rate": 2.379242075121362e-05, + "loss": 0.1291, + "step": 235400 + }, + { + "epoch": 0.53, + "learning_rate": 2.3791302208004294e-05, + "loss": 0.1297, + "step": 235410 + }, + { + "epoch": 0.53, + "learning_rate": 2.3790183664794972e-05, + "loss": 0.1314, + "step": 235420 + }, + { + "epoch": 0.53, + "learning_rate": 2.378906512158565e-05, + "loss": 0.1355, + "step": 235430 + }, + { + "epoch": 0.53, + "learning_rate": 2.3787946578376325e-05, + "loss": 0.1313, + "step": 235440 + }, + { + "epoch": 0.53, + "learning_rate": 2.3786828035167e-05, + "loss": 0.1279, + "step": 235450 + }, + { + "epoch": 0.53, + "learning_rate": 2.3785709491957674e-05, + "loss": 0.127, + "step": 235460 + }, + { + "epoch": 0.53, + "learning_rate": 2.3784590948748352e-05, + "loss": 0.1328, + "step": 235470 + }, + { + "epoch": 0.53, + "learning_rate": 2.378347240553903e-05, + "loss": 0.1269, + "step": 235480 + }, + { + "epoch": 0.53, + "learning_rate": 2.3782353862329704e-05, + "loss": 0.1239, + "step": 235490 + }, + { + "epoch": 0.53, + "learning_rate": 2.378123531912038e-05, + "loss": 0.1266, + "step": 235500 + }, + { + "epoch": 0.53, + "learning_rate": 2.3780116775911053e-05, + "loss": 0.129, + "step": 235510 + }, + { + "epoch": 0.53, + "learning_rate": 2.377899823270173e-05, + "loss": 0.128, + "step": 235520 + }, + { + "epoch": 0.53, + "learning_rate": 2.3777879689492406e-05, + "loss": 0.128, + "step": 235530 + }, + { + "epoch": 0.53, + "learning_rate": 2.3776761146283084e-05, + "loss": 0.1268, + "step": 235540 + }, + { + "epoch": 0.53, + "learning_rate": 2.3775642603073758e-05, + "loss": 0.1238, + "step": 235550 + }, + { + "epoch": 0.53, + "learning_rate": 2.3774524059864433e-05, + "loss": 0.1289, + "step": 235560 + }, + { + "epoch": 0.53, + "learning_rate": 2.3773405516655107e-05, + "loss": 0.1291, + "step": 235570 + }, + { + "epoch": 0.53, + "learning_rate": 2.3772286973445785e-05, + "loss": 0.1284, + "step": 235580 + }, + { + "epoch": 0.53, + "learning_rate": 2.3771168430236463e-05, + "loss": 0.1305, + "step": 235590 + }, + { + "epoch": 0.53, + "learning_rate": 2.3770049887027138e-05, + "loss": 0.1297, + "step": 235600 + }, + { + "epoch": 0.53, + "learning_rate": 2.3768931343817812e-05, + "loss": 0.1274, + "step": 235610 + }, + { + "epoch": 0.53, + "learning_rate": 2.3767812800608487e-05, + "loss": 0.1302, + "step": 235620 + }, + { + "epoch": 0.53, + "learning_rate": 2.3766694257399165e-05, + "loss": 0.1262, + "step": 235630 + }, + { + "epoch": 0.53, + "learning_rate": 2.3765575714189843e-05, + "loss": 0.1276, + "step": 235640 + }, + { + "epoch": 0.53, + "learning_rate": 2.3764457170980517e-05, + "loss": 0.1275, + "step": 235650 + }, + { + "epoch": 0.53, + "learning_rate": 2.3763338627771192e-05, + "loss": 0.1263, + "step": 235660 + }, + { + "epoch": 0.53, + "learning_rate": 2.3762220084561866e-05, + "loss": 0.1315, + "step": 235670 + }, + { + "epoch": 0.53, + "learning_rate": 2.3761101541352544e-05, + "loss": 0.1296, + "step": 235680 + }, + { + "epoch": 0.53, + "learning_rate": 2.375998299814322e-05, + "loss": 0.1284, + "step": 235690 + }, + { + "epoch": 0.53, + "learning_rate": 2.3758864454933897e-05, + "loss": 0.1278, + "step": 235700 + }, + { + "epoch": 0.53, + "learning_rate": 2.375774591172457e-05, + "loss": 0.1306, + "step": 235710 + }, + { + "epoch": 0.53, + "learning_rate": 2.3756627368515246e-05, + "loss": 0.1323, + "step": 235720 + }, + { + "epoch": 0.53, + "learning_rate": 2.3755508825305924e-05, + "loss": 0.1315, + "step": 235730 + }, + { + "epoch": 0.53, + "learning_rate": 2.3754390282096598e-05, + "loss": 0.1273, + "step": 235740 + }, + { + "epoch": 0.53, + "learning_rate": 2.3753271738887276e-05, + "loss": 0.132, + "step": 235750 + }, + { + "epoch": 0.53, + "learning_rate": 2.375215319567795e-05, + "loss": 0.1326, + "step": 235760 + }, + { + "epoch": 0.53, + "learning_rate": 2.3751034652468625e-05, + "loss": 0.1298, + "step": 235770 + }, + { + "epoch": 0.53, + "learning_rate": 2.37499161092593e-05, + "loss": 0.13, + "step": 235780 + }, + { + "epoch": 0.53, + "learning_rate": 2.3748797566049978e-05, + "loss": 0.1281, + "step": 235790 + }, + { + "epoch": 0.53, + "learning_rate": 2.3747679022840656e-05, + "loss": 0.1291, + "step": 235800 + }, + { + "epoch": 0.53, + "learning_rate": 2.374656047963133e-05, + "loss": 0.1276, + "step": 235810 + }, + { + "epoch": 0.53, + "learning_rate": 2.3745441936422005e-05, + "loss": 0.1264, + "step": 235820 + }, + { + "epoch": 0.53, + "learning_rate": 2.374432339321268e-05, + "loss": 0.127, + "step": 235830 + }, + { + "epoch": 0.53, + "learning_rate": 2.3743204850003357e-05, + "loss": 0.1253, + "step": 235840 + }, + { + "epoch": 0.53, + "learning_rate": 2.3742086306794032e-05, + "loss": 0.1324, + "step": 235850 + }, + { + "epoch": 0.53, + "learning_rate": 2.374096776358471e-05, + "loss": 0.1259, + "step": 235860 + }, + { + "epoch": 0.53, + "learning_rate": 2.3739849220375384e-05, + "loss": 0.1298, + "step": 235870 + }, + { + "epoch": 0.53, + "learning_rate": 2.373873067716606e-05, + "loss": 0.1265, + "step": 235880 + }, + { + "epoch": 0.53, + "learning_rate": 2.3737612133956737e-05, + "loss": 0.1327, + "step": 235890 + }, + { + "epoch": 0.53, + "learning_rate": 2.373649359074741e-05, + "loss": 0.131, + "step": 235900 + }, + { + "epoch": 0.53, + "learning_rate": 2.373537504753809e-05, + "loss": 0.1297, + "step": 235910 + }, + { + "epoch": 0.53, + "learning_rate": 2.3734256504328764e-05, + "loss": 0.1316, + "step": 235920 + }, + { + "epoch": 0.53, + "learning_rate": 2.3733137961119438e-05, + "loss": 0.1265, + "step": 235930 + }, + { + "epoch": 0.53, + "learning_rate": 2.3732019417910116e-05, + "loss": 0.1259, + "step": 235940 + }, + { + "epoch": 0.53, + "learning_rate": 2.373090087470079e-05, + "loss": 0.1329, + "step": 235950 + }, + { + "epoch": 0.53, + "learning_rate": 2.372978233149147e-05, + "loss": 0.1324, + "step": 235960 + }, + { + "epoch": 0.53, + "learning_rate": 2.3728663788282143e-05, + "loss": 0.1249, + "step": 235970 + }, + { + "epoch": 0.53, + "learning_rate": 2.3727545245072818e-05, + "loss": 0.1286, + "step": 235980 + }, + { + "epoch": 0.53, + "learning_rate": 2.3726426701863496e-05, + "loss": 0.1291, + "step": 235990 + }, + { + "epoch": 0.53, + "learning_rate": 2.372530815865417e-05, + "loss": 0.1299, + "step": 236000 + }, + { + "epoch": 0.53, + "learning_rate": 2.3724189615444845e-05, + "loss": 0.1267, + "step": 236010 + }, + { + "epoch": 0.53, + "learning_rate": 2.3723071072235523e-05, + "loss": 0.1298, + "step": 236020 + }, + { + "epoch": 0.53, + "learning_rate": 2.372206438334713e-05, + "loss": 0.1244, + "step": 236030 + }, + { + "epoch": 0.53, + "learning_rate": 2.3720945840137806e-05, + "loss": 0.1297, + "step": 236040 + }, + { + "epoch": 0.53, + "learning_rate": 2.371982729692848e-05, + "loss": 0.1258, + "step": 236050 + }, + { + "epoch": 0.53, + "learning_rate": 2.371870875371916e-05, + "loss": 0.1275, + "step": 236060 + }, + { + "epoch": 0.53, + "learning_rate": 2.3717590210509833e-05, + "loss": 0.1281, + "step": 236070 + }, + { + "epoch": 0.53, + "learning_rate": 2.3716471667300507e-05, + "loss": 0.1292, + "step": 236080 + }, + { + "epoch": 0.53, + "learning_rate": 2.3715353124091185e-05, + "loss": 0.1298, + "step": 236090 + }, + { + "epoch": 0.53, + "learning_rate": 2.371423458088186e-05, + "loss": 0.1247, + "step": 236100 + }, + { + "epoch": 0.53, + "learning_rate": 2.3713116037672538e-05, + "loss": 0.1285, + "step": 236110 + }, + { + "epoch": 0.53, + "learning_rate": 2.3711997494463212e-05, + "loss": 0.1269, + "step": 236120 + }, + { + "epoch": 0.53, + "learning_rate": 2.3710878951253887e-05, + "loss": 0.1285, + "step": 236130 + }, + { + "epoch": 0.53, + "learning_rate": 2.3709760408044565e-05, + "loss": 0.1261, + "step": 236140 + }, + { + "epoch": 0.53, + "learning_rate": 2.370864186483524e-05, + "loss": 0.1261, + "step": 236150 + }, + { + "epoch": 0.53, + "learning_rate": 2.3707523321625917e-05, + "loss": 0.1304, + "step": 236160 + }, + { + "epoch": 0.53, + "learning_rate": 2.3706404778416592e-05, + "loss": 0.1263, + "step": 236170 + }, + { + "epoch": 0.53, + "learning_rate": 2.3705286235207266e-05, + "loss": 0.1265, + "step": 236180 + }, + { + "epoch": 0.53, + "learning_rate": 2.3704167691997944e-05, + "loss": 0.1286, + "step": 236190 + }, + { + "epoch": 0.53, + "learning_rate": 2.370304914878862e-05, + "loss": 0.1318, + "step": 236200 + }, + { + "epoch": 0.53, + "learning_rate": 2.3701930605579293e-05, + "loss": 0.1302, + "step": 236210 + }, + { + "epoch": 0.53, + "learning_rate": 2.370081206236997e-05, + "loss": 0.1309, + "step": 236220 + }, + { + "epoch": 0.53, + "learning_rate": 2.3699693519160646e-05, + "loss": 0.1284, + "step": 236230 + }, + { + "epoch": 0.53, + "learning_rate": 2.369857497595132e-05, + "loss": 0.1237, + "step": 236240 + }, + { + "epoch": 0.53, + "learning_rate": 2.3697456432742e-05, + "loss": 0.1288, + "step": 236250 + }, + { + "epoch": 0.53, + "learning_rate": 2.3696337889532673e-05, + "loss": 0.1315, + "step": 236260 + }, + { + "epoch": 0.53, + "learning_rate": 2.369521934632335e-05, + "loss": 0.1313, + "step": 236270 + }, + { + "epoch": 0.53, + "learning_rate": 2.3694100803114025e-05, + "loss": 0.1331, + "step": 236280 + }, + { + "epoch": 0.53, + "learning_rate": 2.36929822599047e-05, + "loss": 0.1314, + "step": 236290 + }, + { + "epoch": 0.53, + "learning_rate": 2.3691863716695378e-05, + "loss": 0.129, + "step": 236300 + }, + { + "epoch": 0.53, + "learning_rate": 2.3690745173486052e-05, + "loss": 0.1297, + "step": 236310 + }, + { + "epoch": 0.53, + "learning_rate": 2.368962663027673e-05, + "loss": 0.1274, + "step": 236320 + }, + { + "epoch": 0.53, + "learning_rate": 2.3688508087067405e-05, + "loss": 0.1287, + "step": 236330 + }, + { + "epoch": 0.53, + "learning_rate": 2.368738954385808e-05, + "loss": 0.1307, + "step": 236340 + }, + { + "epoch": 0.53, + "learning_rate": 2.3686271000648754e-05, + "loss": 0.1274, + "step": 236350 + }, + { + "epoch": 0.53, + "learning_rate": 2.3685152457439432e-05, + "loss": 0.128, + "step": 236360 + }, + { + "epoch": 0.53, + "learning_rate": 2.368403391423011e-05, + "loss": 0.1285, + "step": 236370 + }, + { + "epoch": 0.53, + "learning_rate": 2.3682915371020784e-05, + "loss": 0.1315, + "step": 236380 + }, + { + "epoch": 0.53, + "learning_rate": 2.368179682781146e-05, + "loss": 0.1258, + "step": 236390 + }, + { + "epoch": 0.53, + "learning_rate": 2.3680678284602133e-05, + "loss": 0.1273, + "step": 236400 + }, + { + "epoch": 0.53, + "learning_rate": 2.367955974139281e-05, + "loss": 0.1295, + "step": 236410 + }, + { + "epoch": 0.53, + "learning_rate": 2.3678441198183486e-05, + "loss": 0.1274, + "step": 236420 + }, + { + "epoch": 0.53, + "learning_rate": 2.3677322654974164e-05, + "loss": 0.1299, + "step": 236430 + }, + { + "epoch": 0.53, + "learning_rate": 2.367620411176484e-05, + "loss": 0.1307, + "step": 236440 + }, + { + "epoch": 0.53, + "learning_rate": 2.3675085568555513e-05, + "loss": 0.1273, + "step": 236450 + }, + { + "epoch": 0.53, + "learning_rate": 2.367396702534619e-05, + "loss": 0.1347, + "step": 236460 + }, + { + "epoch": 0.53, + "learning_rate": 2.3672848482136865e-05, + "loss": 0.1284, + "step": 236470 + }, + { + "epoch": 0.53, + "learning_rate": 2.3671729938927543e-05, + "loss": 0.1281, + "step": 236480 + }, + { + "epoch": 0.53, + "learning_rate": 2.3670611395718218e-05, + "loss": 0.1276, + "step": 236490 + }, + { + "epoch": 0.53, + "learning_rate": 2.3669492852508892e-05, + "loss": 0.1284, + "step": 236500 + }, + { + "epoch": 0.53, + "learning_rate": 2.3668374309299567e-05, + "loss": 0.1305, + "step": 236510 + }, + { + "epoch": 0.53, + "learning_rate": 2.3667255766090245e-05, + "loss": 0.1317, + "step": 236520 + }, + { + "epoch": 0.53, + "learning_rate": 2.3666137222880923e-05, + "loss": 0.1266, + "step": 236530 + }, + { + "epoch": 0.53, + "learning_rate": 2.3665018679671597e-05, + "loss": 0.1308, + "step": 236540 + }, + { + "epoch": 0.53, + "learning_rate": 2.3663900136462272e-05, + "loss": 0.1298, + "step": 236550 + }, + { + "epoch": 0.53, + "learning_rate": 2.3662781593252946e-05, + "loss": 0.1281, + "step": 236560 + }, + { + "epoch": 0.53, + "learning_rate": 2.3661663050043624e-05, + "loss": 0.1239, + "step": 236570 + }, + { + "epoch": 0.53, + "learning_rate": 2.3660544506834302e-05, + "loss": 0.1275, + "step": 236580 + }, + { + "epoch": 0.53, + "learning_rate": 2.3659425963624977e-05, + "loss": 0.1261, + "step": 236590 + }, + { + "epoch": 0.53, + "learning_rate": 2.365830742041565e-05, + "loss": 0.1293, + "step": 236600 + }, + { + "epoch": 0.53, + "learning_rate": 2.3657188877206326e-05, + "loss": 0.1285, + "step": 236610 + }, + { + "epoch": 0.53, + "learning_rate": 2.3656070333997004e-05, + "loss": 0.1356, + "step": 236620 + }, + { + "epoch": 0.53, + "learning_rate": 2.3654951790787678e-05, + "loss": 0.1281, + "step": 236630 + }, + { + "epoch": 0.53, + "learning_rate": 2.3653833247578356e-05, + "loss": 0.1308, + "step": 236640 + }, + { + "epoch": 0.53, + "learning_rate": 2.365271470436903e-05, + "loss": 0.129, + "step": 236650 + }, + { + "epoch": 0.53, + "learning_rate": 2.3651596161159705e-05, + "loss": 0.1294, + "step": 236660 + }, + { + "epoch": 0.53, + "learning_rate": 2.365047761795038e-05, + "loss": 0.1271, + "step": 236670 + }, + { + "epoch": 0.53, + "learning_rate": 2.3649359074741058e-05, + "loss": 0.1303, + "step": 236680 + }, + { + "epoch": 0.53, + "learning_rate": 2.3648240531531736e-05, + "loss": 0.1275, + "step": 236690 + }, + { + "epoch": 0.53, + "learning_rate": 2.364712198832241e-05, + "loss": 0.1288, + "step": 236700 + }, + { + "epoch": 0.53, + "learning_rate": 2.3646003445113085e-05, + "loss": 0.1269, + "step": 236710 + }, + { + "epoch": 0.53, + "learning_rate": 2.364488490190376e-05, + "loss": 0.1257, + "step": 236720 + }, + { + "epoch": 0.53, + "learning_rate": 2.3643766358694437e-05, + "loss": 0.1255, + "step": 236730 + }, + { + "epoch": 0.53, + "learning_rate": 2.3642647815485115e-05, + "loss": 0.1289, + "step": 236740 + }, + { + "epoch": 0.53, + "learning_rate": 2.364152927227579e-05, + "loss": 0.1327, + "step": 236750 + }, + { + "epoch": 0.53, + "learning_rate": 2.3640410729066464e-05, + "loss": 0.1337, + "step": 236760 + }, + { + "epoch": 0.53, + "learning_rate": 2.363929218585714e-05, + "loss": 0.1297, + "step": 236770 + }, + { + "epoch": 0.53, + "learning_rate": 2.3638173642647817e-05, + "loss": 0.1283, + "step": 236780 + }, + { + "epoch": 0.53, + "learning_rate": 2.3637055099438495e-05, + "loss": 0.1275, + "step": 236790 + }, + { + "epoch": 0.53, + "learning_rate": 2.363593655622917e-05, + "loss": 0.1245, + "step": 236800 + }, + { + "epoch": 0.53, + "learning_rate": 2.3634818013019844e-05, + "loss": 0.1262, + "step": 236810 + }, + { + "epoch": 0.53, + "learning_rate": 2.3633699469810518e-05, + "loss": 0.1324, + "step": 236820 + }, + { + "epoch": 0.53, + "learning_rate": 2.3632580926601193e-05, + "loss": 0.127, + "step": 236830 + }, + { + "epoch": 0.53, + "learning_rate": 2.3631462383391874e-05, + "loss": 0.1224, + "step": 236840 + }, + { + "epoch": 0.53, + "learning_rate": 2.363034384018255e-05, + "loss": 0.1313, + "step": 236850 + }, + { + "epoch": 0.53, + "learning_rate": 2.3629225296973223e-05, + "loss": 0.1312, + "step": 236860 + }, + { + "epoch": 0.53, + "learning_rate": 2.3628106753763898e-05, + "loss": 0.1262, + "step": 236870 + }, + { + "epoch": 0.53, + "learning_rate": 2.3626988210554572e-05, + "loss": 0.1272, + "step": 236880 + }, + { + "epoch": 0.53, + "learning_rate": 2.362586966734525e-05, + "loss": 0.1323, + "step": 236890 + }, + { + "epoch": 0.53, + "learning_rate": 2.3624751124135928e-05, + "loss": 0.1309, + "step": 236900 + }, + { + "epoch": 0.53, + "learning_rate": 2.3623632580926603e-05, + "loss": 0.1267, + "step": 236910 + }, + { + "epoch": 0.53, + "learning_rate": 2.3622514037717277e-05, + "loss": 0.1305, + "step": 236920 + }, + { + "epoch": 0.53, + "learning_rate": 2.3621395494507952e-05, + "loss": 0.1266, + "step": 236930 + }, + { + "epoch": 0.53, + "learning_rate": 2.362027695129863e-05, + "loss": 0.133, + "step": 236940 + }, + { + "epoch": 0.53, + "learning_rate": 2.3619158408089308e-05, + "loss": 0.1246, + "step": 236950 + }, + { + "epoch": 0.53, + "learning_rate": 2.3618039864879982e-05, + "loss": 0.1304, + "step": 236960 + }, + { + "epoch": 0.53, + "learning_rate": 2.3616921321670657e-05, + "loss": 0.1271, + "step": 236970 + }, + { + "epoch": 0.53, + "learning_rate": 2.361580277846133e-05, + "loss": 0.1264, + "step": 236980 + }, + { + "epoch": 0.53, + "learning_rate": 2.361468423525201e-05, + "loss": 0.1331, + "step": 236990 + }, + { + "epoch": 0.53, + "learning_rate": 2.3613565692042687e-05, + "loss": 0.1272, + "step": 237000 + }, + { + "epoch": 0.53, + "learning_rate": 2.361244714883336e-05, + "loss": 0.1253, + "step": 237010 + }, + { + "epoch": 0.53, + "learning_rate": 2.3611328605624036e-05, + "loss": 0.1276, + "step": 237020 + }, + { + "epoch": 0.53, + "learning_rate": 2.361021006241471e-05, + "loss": 0.1264, + "step": 237030 + }, + { + "epoch": 0.53, + "learning_rate": 2.3609091519205385e-05, + "loss": 0.1301, + "step": 237040 + }, + { + "epoch": 0.53, + "learning_rate": 2.3607972975996067e-05, + "loss": 0.1275, + "step": 237050 + }, + { + "epoch": 0.53, + "learning_rate": 2.360685443278674e-05, + "loss": 0.1296, + "step": 237060 + }, + { + "epoch": 0.53, + "learning_rate": 2.3605735889577416e-05, + "loss": 0.1305, + "step": 237070 + }, + { + "epoch": 0.53, + "learning_rate": 2.360461734636809e-05, + "loss": 0.1297, + "step": 237080 + }, + { + "epoch": 0.53, + "learning_rate": 2.3603498803158765e-05, + "loss": 0.1337, + "step": 237090 + }, + { + "epoch": 0.53, + "learning_rate": 2.3602380259949443e-05, + "loss": 0.1267, + "step": 237100 + }, + { + "epoch": 0.53, + "learning_rate": 2.360126171674012e-05, + "loss": 0.1283, + "step": 237110 + }, + { + "epoch": 0.53, + "learning_rate": 2.3600143173530795e-05, + "loss": 0.1298, + "step": 237120 + }, + { + "epoch": 0.53, + "learning_rate": 2.359902463032147e-05, + "loss": 0.134, + "step": 237130 + }, + { + "epoch": 0.53, + "learning_rate": 2.3597906087112144e-05, + "loss": 0.1259, + "step": 237140 + }, + { + "epoch": 0.53, + "learning_rate": 2.3596787543902822e-05, + "loss": 0.1292, + "step": 237150 + }, + { + "epoch": 0.53, + "learning_rate": 2.35956690006935e-05, + "loss": 0.1333, + "step": 237160 + }, + { + "epoch": 0.53, + "learning_rate": 2.3594550457484175e-05, + "loss": 0.1265, + "step": 237170 + }, + { + "epoch": 0.53, + "learning_rate": 2.359343191427485e-05, + "loss": 0.1323, + "step": 237180 + }, + { + "epoch": 0.53, + "learning_rate": 2.3592313371065524e-05, + "loss": 0.1289, + "step": 237190 + }, + { + "epoch": 0.53, + "learning_rate": 2.35911948278562e-05, + "loss": 0.1286, + "step": 237200 + }, + { + "epoch": 0.53, + "learning_rate": 2.359007628464688e-05, + "loss": 0.1258, + "step": 237210 + }, + { + "epoch": 0.53, + "learning_rate": 2.3588957741437554e-05, + "loss": 0.1296, + "step": 237220 + }, + { + "epoch": 0.53, + "learning_rate": 2.358783919822823e-05, + "loss": 0.1271, + "step": 237230 + }, + { + "epoch": 0.53, + "learning_rate": 2.3586720655018903e-05, + "loss": 0.124, + "step": 237240 + }, + { + "epoch": 0.53, + "learning_rate": 2.3585602111809578e-05, + "loss": 0.129, + "step": 237250 + }, + { + "epoch": 0.53, + "learning_rate": 2.358448356860026e-05, + "loss": 0.1296, + "step": 237260 + }, + { + "epoch": 0.53, + "learning_rate": 2.3583365025390934e-05, + "loss": 0.1299, + "step": 237270 + }, + { + "epoch": 0.53, + "learning_rate": 2.3582246482181608e-05, + "loss": 0.1247, + "step": 237280 + }, + { + "epoch": 0.53, + "learning_rate": 2.3581127938972283e-05, + "loss": 0.124, + "step": 237290 + }, + { + "epoch": 0.53, + "learning_rate": 2.3580009395762957e-05, + "loss": 0.1232, + "step": 237300 + }, + { + "epoch": 0.53, + "learning_rate": 2.3578890852553635e-05, + "loss": 0.1284, + "step": 237310 + }, + { + "epoch": 0.53, + "learning_rate": 2.3577772309344313e-05, + "loss": 0.1293, + "step": 237320 + }, + { + "epoch": 0.53, + "learning_rate": 2.3576653766134988e-05, + "loss": 0.1343, + "step": 237330 + }, + { + "epoch": 0.53, + "learning_rate": 2.3575535222925662e-05, + "loss": 0.1322, + "step": 237340 + }, + { + "epoch": 0.53, + "learning_rate": 2.3574416679716337e-05, + "loss": 0.1302, + "step": 237350 + }, + { + "epoch": 0.53, + "learning_rate": 2.3573298136507015e-05, + "loss": 0.1269, + "step": 237360 + }, + { + "epoch": 0.53, + "learning_rate": 2.3572179593297692e-05, + "loss": 0.1332, + "step": 237370 + }, + { + "epoch": 0.53, + "learning_rate": 2.3571061050088367e-05, + "loss": 0.1299, + "step": 237380 + }, + { + "epoch": 0.53, + "learning_rate": 2.356994250687904e-05, + "loss": 0.1282, + "step": 237390 + }, + { + "epoch": 0.53, + "learning_rate": 2.3568823963669716e-05, + "loss": 0.1257, + "step": 237400 + }, + { + "epoch": 0.53, + "learning_rate": 2.3567705420460394e-05, + "loss": 0.1278, + "step": 237410 + }, + { + "epoch": 0.53, + "learning_rate": 2.3566586877251072e-05, + "loss": 0.1255, + "step": 237420 + }, + { + "epoch": 0.53, + "learning_rate": 2.3565468334041746e-05, + "loss": 0.1293, + "step": 237430 + }, + { + "epoch": 0.53, + "learning_rate": 2.356434979083242e-05, + "loss": 0.126, + "step": 237440 + }, + { + "epoch": 0.53, + "learning_rate": 2.3563231247623096e-05, + "loss": 0.1234, + "step": 237450 + }, + { + "epoch": 0.53, + "learning_rate": 2.3562112704413774e-05, + "loss": 0.1244, + "step": 237460 + }, + { + "epoch": 0.53, + "learning_rate": 2.3560994161204448e-05, + "loss": 0.1265, + "step": 237470 + }, + { + "epoch": 0.53, + "learning_rate": 2.3559875617995126e-05, + "loss": 0.1268, + "step": 237480 + }, + { + "epoch": 0.53, + "learning_rate": 2.35587570747858e-05, + "loss": 0.1324, + "step": 237490 + }, + { + "epoch": 0.53, + "learning_rate": 2.3557638531576475e-05, + "loss": 0.1284, + "step": 237500 + }, + { + "epoch": 0.53, + "learning_rate": 2.355651998836715e-05, + "loss": 0.1266, + "step": 237510 + }, + { + "epoch": 0.53, + "learning_rate": 2.3555401445157828e-05, + "loss": 0.1295, + "step": 237520 + }, + { + "epoch": 0.53, + "learning_rate": 2.3554282901948505e-05, + "loss": 0.1262, + "step": 237530 + }, + { + "epoch": 0.53, + "learning_rate": 2.355316435873918e-05, + "loss": 0.1286, + "step": 237540 + }, + { + "epoch": 0.53, + "learning_rate": 2.3552045815529855e-05, + "loss": 0.1288, + "step": 237550 + }, + { + "epoch": 0.53, + "learning_rate": 2.355092727232053e-05, + "loss": 0.1338, + "step": 237560 + }, + { + "epoch": 0.53, + "learning_rate": 2.3549808729111207e-05, + "loss": 0.1315, + "step": 237570 + }, + { + "epoch": 0.53, + "learning_rate": 2.3548690185901885e-05, + "loss": 0.1295, + "step": 237580 + }, + { + "epoch": 0.53, + "learning_rate": 2.354757164269256e-05, + "loss": 0.1301, + "step": 237590 + }, + { + "epoch": 0.53, + "learning_rate": 2.3546453099483234e-05, + "loss": 0.1227, + "step": 237600 + }, + { + "epoch": 0.53, + "learning_rate": 2.354533455627391e-05, + "loss": 0.1211, + "step": 237610 + }, + { + "epoch": 0.53, + "learning_rate": 2.3544216013064586e-05, + "loss": 0.129, + "step": 237620 + }, + { + "epoch": 0.53, + "learning_rate": 2.354309746985526e-05, + "loss": 0.1271, + "step": 237630 + }, + { + "epoch": 0.53, + "learning_rate": 2.354197892664594e-05, + "loss": 0.1269, + "step": 237640 + }, + { + "epoch": 0.53, + "learning_rate": 2.3540860383436613e-05, + "loss": 0.1327, + "step": 237650 + }, + { + "epoch": 0.53, + "learning_rate": 2.3539741840227288e-05, + "loss": 0.1209, + "step": 237660 + }, + { + "epoch": 0.53, + "learning_rate": 2.3538623297017966e-05, + "loss": 0.1279, + "step": 237670 + }, + { + "epoch": 0.53, + "learning_rate": 2.353750475380864e-05, + "loss": 0.1301, + "step": 237680 + }, + { + "epoch": 0.53, + "learning_rate": 2.353638621059932e-05, + "loss": 0.1307, + "step": 237690 + }, + { + "epoch": 0.53, + "learning_rate": 2.3535267667389993e-05, + "loss": 0.1239, + "step": 237700 + }, + { + "epoch": 0.53, + "learning_rate": 2.3534149124180667e-05, + "loss": 0.1275, + "step": 237710 + }, + { + "epoch": 0.53, + "learning_rate": 2.3533030580971342e-05, + "loss": 0.127, + "step": 237720 + }, + { + "epoch": 0.53, + "learning_rate": 2.353191203776202e-05, + "loss": 0.1289, + "step": 237730 + }, + { + "epoch": 0.53, + "learning_rate": 2.3530793494552698e-05, + "loss": 0.1287, + "step": 237740 + }, + { + "epoch": 0.53, + "learning_rate": 2.3529674951343372e-05, + "loss": 0.1247, + "step": 237750 + }, + { + "epoch": 0.53, + "learning_rate": 2.3528556408134047e-05, + "loss": 0.1288, + "step": 237760 + }, + { + "epoch": 0.53, + "learning_rate": 2.3527549719245656e-05, + "loss": 0.1299, + "step": 237770 + }, + { + "epoch": 0.53, + "learning_rate": 2.352643117603633e-05, + "loss": 0.1263, + "step": 237780 + }, + { + "epoch": 0.53, + "learning_rate": 2.3525312632827008e-05, + "loss": 0.1297, + "step": 237790 + }, + { + "epoch": 0.53, + "learning_rate": 2.3524194089617683e-05, + "loss": 0.129, + "step": 237800 + }, + { + "epoch": 0.53, + "learning_rate": 2.352307554640836e-05, + "loss": 0.129, + "step": 237810 + }, + { + "epoch": 0.53, + "learning_rate": 2.3521957003199035e-05, + "loss": 0.1269, + "step": 237820 + }, + { + "epoch": 0.53, + "learning_rate": 2.352083845998971e-05, + "loss": 0.1321, + "step": 237830 + }, + { + "epoch": 0.53, + "learning_rate": 2.3519719916780388e-05, + "loss": 0.1246, + "step": 237840 + }, + { + "epoch": 0.53, + "learning_rate": 2.3518601373571062e-05, + "loss": 0.1291, + "step": 237850 + }, + { + "epoch": 0.53, + "learning_rate": 2.3517482830361737e-05, + "loss": 0.1302, + "step": 237860 + }, + { + "epoch": 0.53, + "learning_rate": 2.3516364287152415e-05, + "loss": 0.1281, + "step": 237870 + }, + { + "epoch": 0.53, + "learning_rate": 2.351524574394309e-05, + "loss": 0.1285, + "step": 237880 + }, + { + "epoch": 0.53, + "learning_rate": 2.3514127200733764e-05, + "loss": 0.1233, + "step": 237890 + }, + { + "epoch": 0.53, + "learning_rate": 2.3513008657524442e-05, + "loss": 0.1288, + "step": 237900 + }, + { + "epoch": 0.53, + "learning_rate": 2.3511890114315116e-05, + "loss": 0.1222, + "step": 237910 + }, + { + "epoch": 0.53, + "learning_rate": 2.3510771571105794e-05, + "loss": 0.1225, + "step": 237920 + }, + { + "epoch": 0.53, + "learning_rate": 2.350965302789647e-05, + "loss": 0.1315, + "step": 237930 + }, + { + "epoch": 0.53, + "learning_rate": 2.3508534484687143e-05, + "loss": 0.1253, + "step": 237940 + }, + { + "epoch": 0.53, + "learning_rate": 2.350741594147782e-05, + "loss": 0.1282, + "step": 237950 + }, + { + "epoch": 0.53, + "learning_rate": 2.3506297398268496e-05, + "loss": 0.1261, + "step": 237960 + }, + { + "epoch": 0.53, + "learning_rate": 2.3505178855059174e-05, + "loss": 0.1293, + "step": 237970 + }, + { + "epoch": 0.53, + "learning_rate": 2.3504060311849848e-05, + "loss": 0.1279, + "step": 237980 + }, + { + "epoch": 0.53, + "learning_rate": 2.3502941768640523e-05, + "loss": 0.1245, + "step": 237990 + }, + { + "epoch": 0.53, + "learning_rate": 2.35018232254312e-05, + "loss": 0.1266, + "step": 238000 + }, + { + "epoch": 0.53, + "learning_rate": 2.3500704682221875e-05, + "loss": 0.1344, + "step": 238010 + }, + { + "epoch": 0.53, + "learning_rate": 2.349958613901255e-05, + "loss": 0.1252, + "step": 238020 + }, + { + "epoch": 0.53, + "learning_rate": 2.3498467595803228e-05, + "loss": 0.1258, + "step": 238030 + }, + { + "epoch": 0.53, + "learning_rate": 2.3497349052593902e-05, + "loss": 0.1291, + "step": 238040 + }, + { + "epoch": 0.53, + "learning_rate": 2.349623050938458e-05, + "loss": 0.1307, + "step": 238050 + }, + { + "epoch": 0.53, + "learning_rate": 2.3495111966175255e-05, + "loss": 0.1326, + "step": 238060 + }, + { + "epoch": 0.53, + "learning_rate": 2.349399342296593e-05, + "loss": 0.1275, + "step": 238070 + }, + { + "epoch": 0.53, + "learning_rate": 2.3492874879756607e-05, + "loss": 0.1282, + "step": 238080 + }, + { + "epoch": 0.53, + "learning_rate": 2.349175633654728e-05, + "loss": 0.1276, + "step": 238090 + }, + { + "epoch": 0.53, + "learning_rate": 2.3490637793337956e-05, + "loss": 0.1284, + "step": 238100 + }, + { + "epoch": 0.53, + "learning_rate": 2.3489519250128634e-05, + "loss": 0.1265, + "step": 238110 + }, + { + "epoch": 0.53, + "learning_rate": 2.348840070691931e-05, + "loss": 0.1264, + "step": 238120 + }, + { + "epoch": 0.53, + "learning_rate": 2.3487282163709987e-05, + "loss": 0.1307, + "step": 238130 + }, + { + "epoch": 0.53, + "learning_rate": 2.348616362050066e-05, + "loss": 0.1289, + "step": 238140 + }, + { + "epoch": 0.53, + "learning_rate": 2.3485045077291336e-05, + "loss": 0.13, + "step": 238150 + }, + { + "epoch": 0.53, + "learning_rate": 2.3483926534082014e-05, + "loss": 0.1305, + "step": 238160 + }, + { + "epoch": 0.53, + "learning_rate": 2.3482807990872688e-05, + "loss": 0.1324, + "step": 238170 + }, + { + "epoch": 0.53, + "learning_rate": 2.3481689447663363e-05, + "loss": 0.1302, + "step": 238180 + }, + { + "epoch": 0.53, + "learning_rate": 2.348057090445404e-05, + "loss": 0.1256, + "step": 238190 + }, + { + "epoch": 0.53, + "learning_rate": 2.3479452361244715e-05, + "loss": 0.1264, + "step": 238200 + }, + { + "epoch": 0.53, + "learning_rate": 2.3478333818035393e-05, + "loss": 0.1284, + "step": 238210 + }, + { + "epoch": 0.53, + "learning_rate": 2.3477215274826068e-05, + "loss": 0.1271, + "step": 238220 + }, + { + "epoch": 0.53, + "learning_rate": 2.3476096731616742e-05, + "loss": 0.1301, + "step": 238230 + }, + { + "epoch": 0.53, + "learning_rate": 2.347497818840742e-05, + "loss": 0.1261, + "step": 238240 + }, + { + "epoch": 0.53, + "learning_rate": 2.3473859645198095e-05, + "loss": 0.1282, + "step": 238250 + }, + { + "epoch": 0.53, + "learning_rate": 2.3472741101988773e-05, + "loss": 0.1275, + "step": 238260 + }, + { + "epoch": 0.53, + "learning_rate": 2.3471622558779447e-05, + "loss": 0.1268, + "step": 238270 + }, + { + "epoch": 0.53, + "learning_rate": 2.347050401557012e-05, + "loss": 0.1262, + "step": 238280 + }, + { + "epoch": 0.53, + "learning_rate": 2.34693854723608e-05, + "loss": 0.1295, + "step": 238290 + }, + { + "epoch": 0.53, + "learning_rate": 2.3468266929151474e-05, + "loss": 0.1301, + "step": 238300 + }, + { + "epoch": 0.53, + "learning_rate": 2.3467148385942152e-05, + "loss": 0.1289, + "step": 238310 + }, + { + "epoch": 0.53, + "learning_rate": 2.3466029842732827e-05, + "loss": 0.1291, + "step": 238320 + }, + { + "epoch": 0.53, + "learning_rate": 2.34649112995235e-05, + "loss": 0.1262, + "step": 238330 + }, + { + "epoch": 0.53, + "learning_rate": 2.3463792756314176e-05, + "loss": 0.1256, + "step": 238340 + }, + { + "epoch": 0.53, + "learning_rate": 2.3462674213104854e-05, + "loss": 0.1306, + "step": 238350 + }, + { + "epoch": 0.53, + "learning_rate": 2.3461555669895528e-05, + "loss": 0.1265, + "step": 238360 + }, + { + "epoch": 0.53, + "learning_rate": 2.3460437126686206e-05, + "loss": 0.1273, + "step": 238370 + }, + { + "epoch": 0.53, + "learning_rate": 2.345931858347688e-05, + "loss": 0.1261, + "step": 238380 + }, + { + "epoch": 0.53, + "learning_rate": 2.3458200040267555e-05, + "loss": 0.1309, + "step": 238390 + }, + { + "epoch": 0.53, + "learning_rate": 2.3457081497058233e-05, + "loss": 0.125, + "step": 238400 + }, + { + "epoch": 0.53, + "learning_rate": 2.3455962953848908e-05, + "loss": 0.1276, + "step": 238410 + }, + { + "epoch": 0.53, + "learning_rate": 2.3454844410639586e-05, + "loss": 0.1275, + "step": 238420 + }, + { + "epoch": 0.53, + "learning_rate": 2.345372586743026e-05, + "loss": 0.1279, + "step": 238430 + }, + { + "epoch": 0.53, + "learning_rate": 2.3452607324220935e-05, + "loss": 0.1289, + "step": 238440 + }, + { + "epoch": 0.53, + "learning_rate": 2.3451488781011613e-05, + "loss": 0.1323, + "step": 238450 + }, + { + "epoch": 0.53, + "learning_rate": 2.3450370237802287e-05, + "loss": 0.1283, + "step": 238460 + }, + { + "epoch": 0.53, + "learning_rate": 2.3449251694592965e-05, + "loss": 0.1347, + "step": 238470 + }, + { + "epoch": 0.53, + "learning_rate": 2.344813315138364e-05, + "loss": 0.1254, + "step": 238480 + }, + { + "epoch": 0.53, + "learning_rate": 2.3447014608174314e-05, + "loss": 0.1305, + "step": 238490 + }, + { + "epoch": 0.53, + "learning_rate": 2.344589606496499e-05, + "loss": 0.1322, + "step": 238500 + }, + { + "epoch": 0.53, + "learning_rate": 2.3444777521755667e-05, + "loss": 0.1268, + "step": 238510 + }, + { + "epoch": 0.53, + "learning_rate": 2.3443658978546344e-05, + "loss": 0.1286, + "step": 238520 + }, + { + "epoch": 0.53, + "learning_rate": 2.344254043533702e-05, + "loss": 0.1274, + "step": 238530 + }, + { + "epoch": 0.53, + "learning_rate": 2.3441421892127694e-05, + "loss": 0.1269, + "step": 238540 + }, + { + "epoch": 0.53, + "learning_rate": 2.3440303348918368e-05, + "loss": 0.1337, + "step": 238550 + }, + { + "epoch": 0.53, + "learning_rate": 2.3439184805709046e-05, + "loss": 0.1234, + "step": 238560 + }, + { + "epoch": 0.53, + "learning_rate": 2.343806626249972e-05, + "loss": 0.1242, + "step": 238570 + }, + { + "epoch": 0.53, + "learning_rate": 2.34369477192904e-05, + "loss": 0.1229, + "step": 238580 + }, + { + "epoch": 0.53, + "learning_rate": 2.3435829176081073e-05, + "loss": 0.1275, + "step": 238590 + }, + { + "epoch": 0.53, + "learning_rate": 2.3434710632871748e-05, + "loss": 0.1249, + "step": 238600 + }, + { + "epoch": 0.53, + "learning_rate": 2.3433592089662425e-05, + "loss": 0.1292, + "step": 238610 + }, + { + "epoch": 0.53, + "learning_rate": 2.34324735464531e-05, + "loss": 0.1303, + "step": 238620 + }, + { + "epoch": 0.53, + "learning_rate": 2.3431355003243778e-05, + "loss": 0.1265, + "step": 238630 + }, + { + "epoch": 0.53, + "learning_rate": 2.3430236460034452e-05, + "loss": 0.1288, + "step": 238640 + }, + { + "epoch": 0.53, + "learning_rate": 2.3429117916825127e-05, + "loss": 0.1282, + "step": 238650 + }, + { + "epoch": 0.53, + "learning_rate": 2.34279993736158e-05, + "loss": 0.1297, + "step": 238660 + }, + { + "epoch": 0.53, + "learning_rate": 2.342688083040648e-05, + "loss": 0.1307, + "step": 238670 + }, + { + "epoch": 0.53, + "learning_rate": 2.3425762287197157e-05, + "loss": 0.1322, + "step": 238680 + }, + { + "epoch": 0.53, + "learning_rate": 2.3424643743987832e-05, + "loss": 0.1281, + "step": 238690 + }, + { + "epoch": 0.53, + "learning_rate": 2.3423525200778507e-05, + "loss": 0.1294, + "step": 238700 + }, + { + "epoch": 0.53, + "learning_rate": 2.342240665756918e-05, + "loss": 0.1297, + "step": 238710 + }, + { + "epoch": 0.53, + "learning_rate": 2.342128811435986e-05, + "loss": 0.1333, + "step": 238720 + }, + { + "epoch": 0.53, + "learning_rate": 2.3420169571150537e-05, + "loss": 0.1267, + "step": 238730 + }, + { + "epoch": 0.53, + "learning_rate": 2.341905102794121e-05, + "loss": 0.1279, + "step": 238740 + }, + { + "epoch": 0.53, + "learning_rate": 2.3417932484731886e-05, + "loss": 0.1251, + "step": 238750 + }, + { + "epoch": 0.53, + "learning_rate": 2.341681394152256e-05, + "loss": 0.127, + "step": 238760 + }, + { + "epoch": 0.53, + "learning_rate": 2.341569539831324e-05, + "loss": 0.1299, + "step": 238770 + }, + { + "epoch": 0.53, + "learning_rate": 2.3414576855103913e-05, + "loss": 0.1262, + "step": 238780 + }, + { + "epoch": 0.53, + "learning_rate": 2.341345831189459e-05, + "loss": 0.1278, + "step": 238790 + }, + { + "epoch": 0.53, + "learning_rate": 2.3412339768685265e-05, + "loss": 0.1294, + "step": 238800 + }, + { + "epoch": 0.53, + "learning_rate": 2.341122122547594e-05, + "loss": 0.1249, + "step": 238810 + }, + { + "epoch": 0.53, + "learning_rate": 2.3410102682266615e-05, + "loss": 0.1276, + "step": 238820 + }, + { + "epoch": 0.53, + "learning_rate": 2.3408984139057292e-05, + "loss": 0.1275, + "step": 238830 + }, + { + "epoch": 0.53, + "learning_rate": 2.340786559584797e-05, + "loss": 0.1287, + "step": 238840 + }, + { + "epoch": 0.53, + "learning_rate": 2.3406747052638645e-05, + "loss": 0.1306, + "step": 238850 + }, + { + "epoch": 0.53, + "learning_rate": 2.340562850942932e-05, + "loss": 0.1291, + "step": 238860 + }, + { + "epoch": 0.53, + "learning_rate": 2.3404509966219994e-05, + "loss": 0.1292, + "step": 238870 + }, + { + "epoch": 0.53, + "learning_rate": 2.3403391423010672e-05, + "loss": 0.1288, + "step": 238880 + }, + { + "epoch": 0.53, + "learning_rate": 2.340227287980135e-05, + "loss": 0.1311, + "step": 238890 + }, + { + "epoch": 0.53, + "learning_rate": 2.3401154336592024e-05, + "loss": 0.1266, + "step": 238900 + }, + { + "epoch": 0.53, + "learning_rate": 2.34000357933827e-05, + "loss": 0.1255, + "step": 238910 + }, + { + "epoch": 0.53, + "learning_rate": 2.3398917250173373e-05, + "loss": 0.1264, + "step": 238920 + }, + { + "epoch": 0.53, + "learning_rate": 2.339779870696405e-05, + "loss": 0.1274, + "step": 238930 + }, + { + "epoch": 0.53, + "learning_rate": 2.339668016375473e-05, + "loss": 0.1294, + "step": 238940 + }, + { + "epoch": 0.53, + "learning_rate": 2.3395561620545404e-05, + "loss": 0.1272, + "step": 238950 + }, + { + "epoch": 0.53, + "learning_rate": 2.339444307733608e-05, + "loss": 0.1318, + "step": 238960 + }, + { + "epoch": 0.53, + "learning_rate": 2.3393324534126753e-05, + "loss": 0.1286, + "step": 238970 + }, + { + "epoch": 0.53, + "learning_rate": 2.3392205990917427e-05, + "loss": 0.1327, + "step": 238980 + }, + { + "epoch": 0.53, + "learning_rate": 2.339108744770811e-05, + "loss": 0.1291, + "step": 238990 + }, + { + "epoch": 0.53, + "learning_rate": 2.3389968904498783e-05, + "loss": 0.129, + "step": 239000 + }, + { + "epoch": 0.53, + "learning_rate": 2.3388850361289458e-05, + "loss": 0.1219, + "step": 239010 + }, + { + "epoch": 0.53, + "learning_rate": 2.3387731818080132e-05, + "loss": 0.1267, + "step": 239020 + }, + { + "epoch": 0.53, + "learning_rate": 2.3386613274870807e-05, + "loss": 0.1317, + "step": 239030 + }, + { + "epoch": 0.53, + "learning_rate": 2.3385494731661485e-05, + "loss": 0.1279, + "step": 239040 + }, + { + "epoch": 0.53, + "learning_rate": 2.3384376188452163e-05, + "loss": 0.1254, + "step": 239050 + }, + { + "epoch": 0.53, + "learning_rate": 2.3383257645242837e-05, + "loss": 0.1248, + "step": 239060 + }, + { + "epoch": 0.53, + "learning_rate": 2.3382139102033512e-05, + "loss": 0.1292, + "step": 239070 + }, + { + "epoch": 0.53, + "learning_rate": 2.3381020558824186e-05, + "loss": 0.1306, + "step": 239080 + }, + { + "epoch": 0.53, + "learning_rate": 2.3379902015614864e-05, + "loss": 0.1282, + "step": 239090 + }, + { + "epoch": 0.53, + "learning_rate": 2.3378783472405542e-05, + "loss": 0.1267, + "step": 239100 + }, + { + "epoch": 0.53, + "learning_rate": 2.3377664929196217e-05, + "loss": 0.1306, + "step": 239110 + }, + { + "epoch": 0.53, + "learning_rate": 2.337654638598689e-05, + "loss": 0.1308, + "step": 239120 + }, + { + "epoch": 0.53, + "learning_rate": 2.3375427842777566e-05, + "loss": 0.1273, + "step": 239130 + }, + { + "epoch": 0.53, + "learning_rate": 2.3374309299568244e-05, + "loss": 0.1277, + "step": 239140 + }, + { + "epoch": 0.53, + "learning_rate": 2.3373190756358922e-05, + "loss": 0.1277, + "step": 239150 + }, + { + "epoch": 0.53, + "learning_rate": 2.3372072213149596e-05, + "loss": 0.1279, + "step": 239160 + }, + { + "epoch": 0.53, + "learning_rate": 2.337095366994027e-05, + "loss": 0.1261, + "step": 239170 + }, + { + "epoch": 0.53, + "learning_rate": 2.3369835126730945e-05, + "loss": 0.1267, + "step": 239180 + }, + { + "epoch": 0.53, + "learning_rate": 2.336871658352162e-05, + "loss": 0.1259, + "step": 239190 + }, + { + "epoch": 0.53, + "learning_rate": 2.33675980403123e-05, + "loss": 0.133, + "step": 239200 + }, + { + "epoch": 0.53, + "learning_rate": 2.3366479497102976e-05, + "loss": 0.1285, + "step": 239210 + }, + { + "epoch": 0.53, + "learning_rate": 2.336536095389365e-05, + "loss": 0.1296, + "step": 239220 + }, + { + "epoch": 0.53, + "learning_rate": 2.3364242410684325e-05, + "loss": 0.1292, + "step": 239230 + }, + { + "epoch": 0.53, + "learning_rate": 2.3363123867475e-05, + "loss": 0.1288, + "step": 239240 + }, + { + "epoch": 0.53, + "learning_rate": 2.3362005324265677e-05, + "loss": 0.1275, + "step": 239250 + }, + { + "epoch": 0.53, + "learning_rate": 2.3360886781056355e-05, + "loss": 0.126, + "step": 239260 + }, + { + "epoch": 0.53, + "learning_rate": 2.335976823784703e-05, + "loss": 0.1306, + "step": 239270 + }, + { + "epoch": 0.53, + "learning_rate": 2.3358649694637704e-05, + "loss": 0.1284, + "step": 239280 + }, + { + "epoch": 0.53, + "learning_rate": 2.335753115142838e-05, + "loss": 0.123, + "step": 239290 + }, + { + "epoch": 0.53, + "learning_rate": 2.3356412608219057e-05, + "loss": 0.1297, + "step": 239300 + }, + { + "epoch": 0.53, + "learning_rate": 2.3355294065009735e-05, + "loss": 0.1327, + "step": 239310 + }, + { + "epoch": 0.53, + "learning_rate": 2.335417552180041e-05, + "loss": 0.1245, + "step": 239320 + }, + { + "epoch": 0.53, + "learning_rate": 2.3353056978591084e-05, + "loss": 0.1251, + "step": 239330 + }, + { + "epoch": 0.53, + "learning_rate": 2.335193843538176e-05, + "loss": 0.1267, + "step": 239340 + }, + { + "epoch": 0.53, + "learning_rate": 2.3350819892172436e-05, + "loss": 0.1272, + "step": 239350 + }, + { + "epoch": 0.53, + "learning_rate": 2.3349701348963114e-05, + "loss": 0.1239, + "step": 239360 + }, + { + "epoch": 0.53, + "learning_rate": 2.334858280575379e-05, + "loss": 0.127, + "step": 239370 + }, + { + "epoch": 0.53, + "learning_rate": 2.3347464262544463e-05, + "loss": 0.1313, + "step": 239380 + }, + { + "epoch": 0.53, + "learning_rate": 2.3346345719335138e-05, + "loss": 0.1295, + "step": 239390 + }, + { + "epoch": 0.53, + "learning_rate": 2.3345227176125812e-05, + "loss": 0.1267, + "step": 239400 + }, + { + "epoch": 0.53, + "learning_rate": 2.334410863291649e-05, + "loss": 0.1301, + "step": 239410 + }, + { + "epoch": 0.53, + "learning_rate": 2.3342990089707168e-05, + "loss": 0.1253, + "step": 239420 + }, + { + "epoch": 0.53, + "learning_rate": 2.3341871546497843e-05, + "loss": 0.1288, + "step": 239430 + }, + { + "epoch": 0.53, + "learning_rate": 2.3340753003288517e-05, + "loss": 0.1286, + "step": 239440 + }, + { + "epoch": 0.53, + "learning_rate": 2.3339634460079192e-05, + "loss": 0.1219, + "step": 239450 + }, + { + "epoch": 0.53, + "learning_rate": 2.333851591686987e-05, + "loss": 0.1278, + "step": 239460 + }, + { + "epoch": 0.53, + "learning_rate": 2.3337397373660548e-05, + "loss": 0.1269, + "step": 239470 + }, + { + "epoch": 0.53, + "learning_rate": 2.3336278830451222e-05, + "loss": 0.1266, + "step": 239480 + }, + { + "epoch": 0.53, + "learning_rate": 2.3335160287241897e-05, + "loss": 0.1292, + "step": 239490 + }, + { + "epoch": 0.53, + "learning_rate": 2.333404174403257e-05, + "loss": 0.129, + "step": 239500 + }, + { + "epoch": 0.53, + "learning_rate": 2.333292320082325e-05, + "loss": 0.1299, + "step": 239510 + }, + { + "epoch": 0.53, + "learning_rate": 2.3331804657613927e-05, + "loss": 0.1265, + "step": 239520 + }, + { + "epoch": 0.53, + "learning_rate": 2.3330686114404602e-05, + "loss": 0.1307, + "step": 239530 + }, + { + "epoch": 0.53, + "learning_rate": 2.3329567571195276e-05, + "loss": 0.1274, + "step": 239540 + }, + { + "epoch": 0.53, + "learning_rate": 2.332844902798595e-05, + "loss": 0.1258, + "step": 239550 + }, + { + "epoch": 0.53, + "learning_rate": 2.332733048477663e-05, + "loss": 0.1267, + "step": 239560 + }, + { + "epoch": 0.53, + "learning_rate": 2.3326211941567303e-05, + "loss": 0.127, + "step": 239570 + }, + { + "epoch": 0.53, + "learning_rate": 2.332509339835798e-05, + "loss": 0.126, + "step": 239580 + }, + { + "epoch": 0.53, + "learning_rate": 2.3323974855148656e-05, + "loss": 0.1293, + "step": 239590 + }, + { + "epoch": 0.53, + "learning_rate": 2.332285631193933e-05, + "loss": 0.133, + "step": 239600 + }, + { + "epoch": 0.53, + "learning_rate": 2.3321737768730005e-05, + "loss": 0.1277, + "step": 239610 + }, + { + "epoch": 0.53, + "learning_rate": 2.3320619225520683e-05, + "loss": 0.1243, + "step": 239620 + }, + { + "epoch": 0.53, + "learning_rate": 2.331950068231136e-05, + "loss": 0.1273, + "step": 239630 + }, + { + "epoch": 0.53, + "learning_rate": 2.3318382139102035e-05, + "loss": 0.1301, + "step": 239640 + }, + { + "epoch": 0.53, + "learning_rate": 2.331726359589271e-05, + "loss": 0.1282, + "step": 239650 + }, + { + "epoch": 0.53, + "learning_rate": 2.3316145052683384e-05, + "loss": 0.1286, + "step": 239660 + }, + { + "epoch": 0.53, + "learning_rate": 2.3315026509474062e-05, + "loss": 0.1265, + "step": 239670 + }, + { + "epoch": 0.53, + "learning_rate": 2.331390796626474e-05, + "loss": 0.1263, + "step": 239680 + }, + { + "epoch": 0.54, + "learning_rate": 2.3312789423055415e-05, + "loss": 0.1267, + "step": 239690 + }, + { + "epoch": 0.54, + "learning_rate": 2.331167087984609e-05, + "loss": 0.1266, + "step": 239700 + }, + { + "epoch": 0.54, + "learning_rate": 2.3310552336636764e-05, + "loss": 0.1267, + "step": 239710 + }, + { + "epoch": 0.54, + "learning_rate": 2.330943379342744e-05, + "loss": 0.1215, + "step": 239720 + }, + { + "epoch": 0.54, + "learning_rate": 2.3308315250218116e-05, + "loss": 0.1277, + "step": 239730 + }, + { + "epoch": 0.54, + "learning_rate": 2.3307196707008794e-05, + "loss": 0.1252, + "step": 239740 + }, + { + "epoch": 0.54, + "learning_rate": 2.330607816379947e-05, + "loss": 0.1281, + "step": 239750 + }, + { + "epoch": 0.54, + "learning_rate": 2.3304959620590143e-05, + "loss": 0.1278, + "step": 239760 + }, + { + "epoch": 0.54, + "learning_rate": 2.330384107738082e-05, + "loss": 0.1238, + "step": 239770 + }, + { + "epoch": 0.54, + "learning_rate": 2.3302722534171496e-05, + "loss": 0.1262, + "step": 239780 + }, + { + "epoch": 0.54, + "learning_rate": 2.3301603990962174e-05, + "loss": 0.127, + "step": 239790 + }, + { + "epoch": 0.54, + "learning_rate": 2.3300485447752848e-05, + "loss": 0.1265, + "step": 239800 + }, + { + "epoch": 0.54, + "learning_rate": 2.3299366904543523e-05, + "loss": 0.1318, + "step": 239810 + }, + { + "epoch": 0.54, + "learning_rate": 2.32982483613342e-05, + "loss": 0.1286, + "step": 239820 + }, + { + "epoch": 0.54, + "learning_rate": 2.3297129818124875e-05, + "loss": 0.125, + "step": 239830 + }, + { + "epoch": 0.54, + "learning_rate": 2.3296011274915553e-05, + "loss": 0.1227, + "step": 239840 + }, + { + "epoch": 0.54, + "learning_rate": 2.3294892731706228e-05, + "loss": 0.1296, + "step": 239850 + }, + { + "epoch": 0.54, + "learning_rate": 2.3293774188496902e-05, + "loss": 0.1335, + "step": 239860 + }, + { + "epoch": 0.54, + "learning_rate": 2.3292655645287577e-05, + "loss": 0.1258, + "step": 239870 + }, + { + "epoch": 0.54, + "learning_rate": 2.3291537102078255e-05, + "loss": 0.1294, + "step": 239880 + }, + { + "epoch": 0.54, + "learning_rate": 2.329041855886893e-05, + "loss": 0.1288, + "step": 239890 + }, + { + "epoch": 0.54, + "learning_rate": 2.3289300015659607e-05, + "loss": 0.1272, + "step": 239900 + }, + { + "epoch": 0.54, + "learning_rate": 2.328818147245028e-05, + "loss": 0.1291, + "step": 239910 + }, + { + "epoch": 0.54, + "learning_rate": 2.3287062929240956e-05, + "loss": 0.1284, + "step": 239920 + }, + { + "epoch": 0.54, + "learning_rate": 2.3285944386031634e-05, + "loss": 0.124, + "step": 239930 + }, + { + "epoch": 0.54, + "learning_rate": 2.328482584282231e-05, + "loss": 0.1292, + "step": 239940 + }, + { + "epoch": 0.54, + "learning_rate": 2.3283707299612987e-05, + "loss": 0.1263, + "step": 239950 + }, + { + "epoch": 0.54, + "learning_rate": 2.328258875640366e-05, + "loss": 0.1251, + "step": 239960 + }, + { + "epoch": 0.54, + "learning_rate": 2.3281470213194336e-05, + "loss": 0.1317, + "step": 239970 + }, + { + "epoch": 0.54, + "learning_rate": 2.3280351669985014e-05, + "loss": 0.1254, + "step": 239980 + }, + { + "epoch": 0.54, + "learning_rate": 2.3279233126775688e-05, + "loss": 0.1279, + "step": 239990 + }, + { + "epoch": 0.54, + "learning_rate": 2.3278114583566366e-05, + "loss": 0.1237, + "step": 240000 + }, + { + "epoch": 0.54, + "eval_NEIMS_canon_smiles": 0.9549666666666666, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.1689, + "eval_NEIMS_daylight_tanimoto_simil": 0.5648183631931242, + "eval_NEIMS_exact_mols": 0.1686, + "eval_NEIMS_exact_smiles": 0.16473333333333334, + "eval_NEIMS_loss": 0.15587209165096283, + "eval_NEIMS_matched_formulas": 0.6976333333333333, + "eval_NEIMS_morgan_tanimoto_simil": 0.48087817748490336, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.16925, + "eval_NEIMS_runtime": 727.6507, + "eval_NEIMS_samples_per_second": 82.457, + "eval_NEIMS_steps_per_second": 1.289, + "step": 240000 + }, + { + "epoch": 0.54, + "eval_RASSP_canon_smiles": 0.9513974688616555, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.23013991384779778, + "eval_RASSP_daylight_tanimoto_simil": 0.6615702326396767, + "eval_RASSP_exact_mols": 0.22937189033959995, + "eval_RASSP_exact_smiles": 0.22342805623267772, + "eval_RASSP_loss": 0.12360317260026932, + "eval_RASSP_matched_formulas": 0.8399004908671988, + "eval_RASSP_morgan_tanimoto_simil": 0.5399549836764758, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.2295221558085952, + "eval_RASSP_runtime": 827.5902, + "eval_RASSP_samples_per_second": 72.372, + "eval_RASSP_steps_per_second": 1.131, + "step": 240000 + }, + { + "epoch": 0.54, + "eval_NEIMS_old_canon_smiles": 0.9533666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.16783333333333333, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5625883247367006, + "eval_NEIMS_old_exact_mols": 0.16743333333333332, + "eval_NEIMS_old_exact_smiles": 0.16303333333333334, + "eval_NEIMS_old_loss": 0.15619391202926636, + "eval_NEIMS_old_matched_formulas": 0.6950666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.4809150177709264, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.16823333333333335, + "eval_NEIMS_old_runtime": 366.8667, + "eval_NEIMS_old_samples_per_second": 81.774, + "eval_NEIMS_old_steps_per_second": 1.278, + "step": 240000 + }, + { + "epoch": 0.54, + "eval_RASSP_old_canon_smiles": 0.9529482430673741, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.2585177028064204, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6806752187825149, + "eval_RASSP_old_exact_mols": 0.25754997163546567, + "eval_RASSP_old_exact_smiles": 0.2511095538425602, + "eval_RASSP_old_loss": 0.11589321494102478, + "eval_RASSP_old_matched_formulas": 0.8526045316514833, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5648131916489839, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.2577835619181099, + "eval_RASSP_old_runtime": 411.3167, + "eval_RASSP_old_samples_per_second": 72.856, + "eval_RASSP_old_steps_per_second": 1.14, + "step": 240000 + }, + { + "epoch": 0.54, + "eval_NIST_canon_smiles": 0.8602051318451219, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.024559037512865103, + "eval_NIST_daylight_tanimoto_simil": 0.2953428108902583, + "eval_NIST_exact_mols": 0.0233878695389857, + "eval_NIST_exact_smiles": 0.022358661319515916, + "eval_NIST_loss": 1.8028345108032227, + "eval_NIST_matched_formulas": 0.12009795223054263, + "eval_NIST_morgan_tanimoto_simil": 0.24779068341518123, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02423962806544345, + "eval_NIST_runtime": 650.917, + "eval_NIST_samples_per_second": 43.288, + "eval_NIST_steps_per_second": 0.678, + "step": 240000 + }, + { + "epoch": 0.54, + "learning_rate": 2.327699604035704e-05, + "loss": 0.1272, + "step": 240010 + }, + { + "epoch": 0.54, + "learning_rate": 2.3275877497147715e-05, + "loss": 0.1314, + "step": 240020 + }, + { + "epoch": 0.54, + "learning_rate": 2.3274758953938393e-05, + "loss": 0.1273, + "step": 240030 + }, + { + "epoch": 0.54, + "learning_rate": 2.3273640410729068e-05, + "loss": 0.1244, + "step": 240040 + }, + { + "epoch": 0.54, + "learning_rate": 2.3272521867519742e-05, + "loss": 0.1255, + "step": 240050 + }, + { + "epoch": 0.54, + "learning_rate": 2.327140332431042e-05, + "loss": 0.1345, + "step": 240060 + }, + { + "epoch": 0.54, + "learning_rate": 2.3270284781101095e-05, + "loss": 0.1287, + "step": 240070 + }, + { + "epoch": 0.54, + "learning_rate": 2.326916623789177e-05, + "loss": 0.126, + "step": 240080 + }, + { + "epoch": 0.54, + "learning_rate": 2.3268047694682447e-05, + "loss": 0.1285, + "step": 240090 + }, + { + "epoch": 0.54, + "learning_rate": 2.326692915147312e-05, + "loss": 0.1288, + "step": 240100 + }, + { + "epoch": 0.54, + "learning_rate": 2.32658106082638e-05, + "loss": 0.1255, + "step": 240110 + }, + { + "epoch": 0.54, + "learning_rate": 2.3264692065054474e-05, + "loss": 0.1257, + "step": 240120 + }, + { + "epoch": 0.54, + "learning_rate": 2.326357352184515e-05, + "loss": 0.1344, + "step": 240130 + }, + { + "epoch": 0.54, + "learning_rate": 2.3262454978635827e-05, + "loss": 0.1283, + "step": 240140 + }, + { + "epoch": 0.54, + "learning_rate": 2.32613364354265e-05, + "loss": 0.1264, + "step": 240150 + }, + { + "epoch": 0.54, + "learning_rate": 2.326021789221718e-05, + "loss": 0.1233, + "step": 240160 + }, + { + "epoch": 0.54, + "learning_rate": 2.3259099349007854e-05, + "loss": 0.1304, + "step": 240170 + }, + { + "epoch": 0.54, + "learning_rate": 2.3257980805798528e-05, + "loss": 0.1248, + "step": 240180 + }, + { + "epoch": 0.54, + "learning_rate": 2.3256862262589206e-05, + "loss": 0.1277, + "step": 240190 + }, + { + "epoch": 0.54, + "learning_rate": 2.325574371937988e-05, + "loss": 0.1238, + "step": 240200 + }, + { + "epoch": 0.54, + "learning_rate": 2.3254625176170555e-05, + "loss": 0.125, + "step": 240210 + }, + { + "epoch": 0.54, + "learning_rate": 2.3253506632961233e-05, + "loss": 0.1269, + "step": 240220 + }, + { + "epoch": 0.54, + "learning_rate": 2.3252388089751908e-05, + "loss": 0.1275, + "step": 240230 + }, + { + "epoch": 0.54, + "learning_rate": 2.3251269546542585e-05, + "loss": 0.1274, + "step": 240240 + }, + { + "epoch": 0.54, + "learning_rate": 2.325015100333326e-05, + "loss": 0.1244, + "step": 240250 + }, + { + "epoch": 0.54, + "learning_rate": 2.3249032460123935e-05, + "loss": 0.1302, + "step": 240260 + }, + { + "epoch": 0.54, + "learning_rate": 2.3247913916914613e-05, + "loss": 0.1302, + "step": 240270 + }, + { + "epoch": 0.54, + "learning_rate": 2.3246795373705287e-05, + "loss": 0.1244, + "step": 240280 + }, + { + "epoch": 0.54, + "learning_rate": 2.324567683049596e-05, + "loss": 0.126, + "step": 240290 + }, + { + "epoch": 0.54, + "learning_rate": 2.324455828728664e-05, + "loss": 0.1299, + "step": 240300 + }, + { + "epoch": 0.54, + "learning_rate": 2.3243439744077314e-05, + "loss": 0.1286, + "step": 240310 + }, + { + "epoch": 0.54, + "learning_rate": 2.3242321200867992e-05, + "loss": 0.1282, + "step": 240320 + }, + { + "epoch": 0.54, + "learning_rate": 2.3241202657658667e-05, + "loss": 0.1286, + "step": 240330 + }, + { + "epoch": 0.54, + "learning_rate": 2.324008411444934e-05, + "loss": 0.1322, + "step": 240340 + }, + { + "epoch": 0.54, + "learning_rate": 2.323896557124002e-05, + "loss": 0.1295, + "step": 240350 + }, + { + "epoch": 0.54, + "learning_rate": 2.3237847028030694e-05, + "loss": 0.1312, + "step": 240360 + }, + { + "epoch": 0.54, + "learning_rate": 2.3236728484821368e-05, + "loss": 0.1285, + "step": 240370 + }, + { + "epoch": 0.54, + "learning_rate": 2.3235609941612046e-05, + "loss": 0.1298, + "step": 240380 + }, + { + "epoch": 0.54, + "learning_rate": 2.323449139840272e-05, + "loss": 0.1248, + "step": 240390 + }, + { + "epoch": 0.54, + "learning_rate": 2.32333728551934e-05, + "loss": 0.1309, + "step": 240400 + }, + { + "epoch": 0.54, + "learning_rate": 2.3232254311984073e-05, + "loss": 0.1251, + "step": 240410 + }, + { + "epoch": 0.54, + "learning_rate": 2.3231135768774748e-05, + "loss": 0.1258, + "step": 240420 + }, + { + "epoch": 0.54, + "learning_rate": 2.3230017225565425e-05, + "loss": 0.1229, + "step": 240430 + }, + { + "epoch": 0.54, + "learning_rate": 2.32288986823561e-05, + "loss": 0.128, + "step": 240440 + }, + { + "epoch": 0.54, + "learning_rate": 2.3227780139146778e-05, + "loss": 0.1317, + "step": 240450 + }, + { + "epoch": 0.54, + "learning_rate": 2.3226661595937452e-05, + "loss": 0.1264, + "step": 240460 + }, + { + "epoch": 0.54, + "learning_rate": 2.3225543052728127e-05, + "loss": 0.1265, + "step": 240470 + }, + { + "epoch": 0.54, + "learning_rate": 2.3224424509518805e-05, + "loss": 0.1317, + "step": 240480 + }, + { + "epoch": 0.54, + "learning_rate": 2.322330596630948e-05, + "loss": 0.133, + "step": 240490 + }, + { + "epoch": 0.54, + "learning_rate": 2.3222187423100157e-05, + "loss": 0.129, + "step": 240500 + }, + { + "epoch": 0.54, + "learning_rate": 2.3221068879890832e-05, + "loss": 0.1298, + "step": 240510 + }, + { + "epoch": 0.54, + "learning_rate": 2.3219950336681506e-05, + "loss": 0.1255, + "step": 240520 + }, + { + "epoch": 0.54, + "learning_rate": 2.321883179347218e-05, + "loss": 0.1251, + "step": 240530 + }, + { + "epoch": 0.54, + "learning_rate": 2.321771325026286e-05, + "loss": 0.1308, + "step": 240540 + }, + { + "epoch": 0.54, + "learning_rate": 2.3216594707053533e-05, + "loss": 0.1327, + "step": 240550 + }, + { + "epoch": 0.54, + "learning_rate": 2.321547616384421e-05, + "loss": 0.1293, + "step": 240560 + }, + { + "epoch": 0.54, + "learning_rate": 2.3214357620634886e-05, + "loss": 0.1282, + "step": 240570 + }, + { + "epoch": 0.54, + "learning_rate": 2.321323907742556e-05, + "loss": 0.1258, + "step": 240580 + }, + { + "epoch": 0.54, + "learning_rate": 2.321212053421624e-05, + "loss": 0.1327, + "step": 240590 + }, + { + "epoch": 0.54, + "learning_rate": 2.3211001991006913e-05, + "loss": 0.1283, + "step": 240600 + }, + { + "epoch": 0.54, + "learning_rate": 2.320988344779759e-05, + "loss": 0.1246, + "step": 240610 + }, + { + "epoch": 0.54, + "learning_rate": 2.3208764904588265e-05, + "loss": 0.1241, + "step": 240620 + }, + { + "epoch": 0.54, + "learning_rate": 2.320764636137894e-05, + "loss": 0.1363, + "step": 240630 + }, + { + "epoch": 0.54, + "learning_rate": 2.3206527818169618e-05, + "loss": 0.1258, + "step": 240640 + }, + { + "epoch": 0.54, + "learning_rate": 2.3205409274960292e-05, + "loss": 0.1266, + "step": 240650 + }, + { + "epoch": 0.54, + "learning_rate": 2.320429073175097e-05, + "loss": 0.1285, + "step": 240660 + }, + { + "epoch": 0.54, + "learning_rate": 2.3203172188541645e-05, + "loss": 0.129, + "step": 240670 + }, + { + "epoch": 0.54, + "learning_rate": 2.320205364533232e-05, + "loss": 0.1321, + "step": 240680 + }, + { + "epoch": 0.54, + "learning_rate": 2.3200935102122994e-05, + "loss": 0.1263, + "step": 240690 + }, + { + "epoch": 0.54, + "learning_rate": 2.3199816558913672e-05, + "loss": 0.1285, + "step": 240700 + }, + { + "epoch": 0.54, + "learning_rate": 2.319869801570435e-05, + "loss": 0.1243, + "step": 240710 + }, + { + "epoch": 0.54, + "learning_rate": 2.3197579472495024e-05, + "loss": 0.1283, + "step": 240720 + }, + { + "epoch": 0.54, + "learning_rate": 2.31964609292857e-05, + "loss": 0.1304, + "step": 240730 + }, + { + "epoch": 0.54, + "learning_rate": 2.3195342386076373e-05, + "loss": 0.1318, + "step": 240740 + }, + { + "epoch": 0.54, + "learning_rate": 2.319422384286705e-05, + "loss": 0.1268, + "step": 240750 + }, + { + "epoch": 0.54, + "learning_rate": 2.3193105299657726e-05, + "loss": 0.1225, + "step": 240760 + }, + { + "epoch": 0.54, + "learning_rate": 2.3191986756448404e-05, + "loss": 0.1232, + "step": 240770 + }, + { + "epoch": 0.54, + "learning_rate": 2.319086821323908e-05, + "loss": 0.1186, + "step": 240780 + }, + { + "epoch": 0.54, + "learning_rate": 2.3189749670029753e-05, + "loss": 0.1287, + "step": 240790 + }, + { + "epoch": 0.54, + "learning_rate": 2.318863112682043e-05, + "loss": 0.134, + "step": 240800 + }, + { + "epoch": 0.54, + "learning_rate": 2.3187512583611105e-05, + "loss": 0.1246, + "step": 240810 + }, + { + "epoch": 0.54, + "learning_rate": 2.3186394040401783e-05, + "loss": 0.1261, + "step": 240820 + }, + { + "epoch": 0.54, + "learning_rate": 2.3185275497192458e-05, + "loss": 0.1258, + "step": 240830 + }, + { + "epoch": 0.54, + "learning_rate": 2.3184156953983132e-05, + "loss": 0.1287, + "step": 240840 + }, + { + "epoch": 0.54, + "learning_rate": 2.3183038410773807e-05, + "loss": 0.1266, + "step": 240850 + }, + { + "epoch": 0.54, + "learning_rate": 2.3181919867564485e-05, + "loss": 0.1284, + "step": 240860 + }, + { + "epoch": 0.54, + "learning_rate": 2.3180801324355163e-05, + "loss": 0.1243, + "step": 240870 + }, + { + "epoch": 0.54, + "learning_rate": 2.3179682781145837e-05, + "loss": 0.1257, + "step": 240880 + }, + { + "epoch": 0.54, + "learning_rate": 2.3178564237936512e-05, + "loss": 0.1274, + "step": 240890 + }, + { + "epoch": 0.54, + "learning_rate": 2.3177445694727186e-05, + "loss": 0.1281, + "step": 240900 + }, + { + "epoch": 0.54, + "learning_rate": 2.3176327151517864e-05, + "loss": 0.1299, + "step": 240910 + }, + { + "epoch": 0.54, + "learning_rate": 2.3175208608308542e-05, + "loss": 0.1259, + "step": 240920 + }, + { + "epoch": 0.54, + "learning_rate": 2.3174090065099217e-05, + "loss": 0.1252, + "step": 240930 + }, + { + "epoch": 0.54, + "learning_rate": 2.317297152188989e-05, + "loss": 0.1271, + "step": 240940 + }, + { + "epoch": 0.54, + "learning_rate": 2.3171852978680566e-05, + "loss": 0.1231, + "step": 240950 + }, + { + "epoch": 0.54, + "learning_rate": 2.3170734435471244e-05, + "loss": 0.1239, + "step": 240960 + }, + { + "epoch": 0.54, + "learning_rate": 2.316961589226192e-05, + "loss": 0.1352, + "step": 240970 + }, + { + "epoch": 0.54, + "learning_rate": 2.3168497349052596e-05, + "loss": 0.1317, + "step": 240980 + }, + { + "epoch": 0.54, + "learning_rate": 2.316737880584327e-05, + "loss": 0.1269, + "step": 240990 + }, + { + "epoch": 0.54, + "learning_rate": 2.3166260262633945e-05, + "loss": 0.1291, + "step": 241000 + }, + { + "epoch": 0.54, + "learning_rate": 2.316514171942462e-05, + "loss": 0.1263, + "step": 241010 + }, + { + "epoch": 0.54, + "learning_rate": 2.3164023176215298e-05, + "loss": 0.1259, + "step": 241020 + }, + { + "epoch": 0.54, + "learning_rate": 2.3162904633005976e-05, + "loss": 0.1223, + "step": 241030 + }, + { + "epoch": 0.54, + "learning_rate": 2.316178608979665e-05, + "loss": 0.1283, + "step": 241040 + }, + { + "epoch": 0.54, + "learning_rate": 2.3160667546587325e-05, + "loss": 0.1241, + "step": 241050 + }, + { + "epoch": 0.54, + "learning_rate": 2.3159549003378e-05, + "loss": 0.1261, + "step": 241060 + }, + { + "epoch": 0.54, + "learning_rate": 2.3158430460168677e-05, + "loss": 0.1252, + "step": 241070 + }, + { + "epoch": 0.54, + "learning_rate": 2.3157311916959355e-05, + "loss": 0.129, + "step": 241080 + }, + { + "epoch": 0.54, + "learning_rate": 2.315619337375003e-05, + "loss": 0.1304, + "step": 241090 + }, + { + "epoch": 0.54, + "learning_rate": 2.3155074830540704e-05, + "loss": 0.129, + "step": 241100 + }, + { + "epoch": 0.54, + "learning_rate": 2.315395628733138e-05, + "loss": 0.1268, + "step": 241110 + }, + { + "epoch": 0.54, + "learning_rate": 2.3152837744122057e-05, + "loss": 0.1302, + "step": 241120 + }, + { + "epoch": 0.54, + "learning_rate": 2.3151719200912735e-05, + "loss": 0.1315, + "step": 241130 + }, + { + "epoch": 0.54, + "learning_rate": 2.315060065770341e-05, + "loss": 0.1289, + "step": 241140 + }, + { + "epoch": 0.54, + "learning_rate": 2.3149482114494084e-05, + "loss": 0.1268, + "step": 241150 + }, + { + "epoch": 0.54, + "learning_rate": 2.314836357128476e-05, + "loss": 0.1245, + "step": 241160 + }, + { + "epoch": 0.54, + "learning_rate": 2.3147245028075433e-05, + "loss": 0.1241, + "step": 241170 + }, + { + "epoch": 0.54, + "learning_rate": 2.314612648486611e-05, + "loss": 0.1291, + "step": 241180 + }, + { + "epoch": 0.54, + "learning_rate": 2.314500794165679e-05, + "loss": 0.1302, + "step": 241190 + }, + { + "epoch": 0.54, + "learning_rate": 2.3143889398447463e-05, + "loss": 0.124, + "step": 241200 + }, + { + "epoch": 0.54, + "learning_rate": 2.3142770855238138e-05, + "loss": 0.1188, + "step": 241210 + }, + { + "epoch": 0.54, + "learning_rate": 2.3141652312028812e-05, + "loss": 0.1257, + "step": 241220 + }, + { + "epoch": 0.54, + "learning_rate": 2.314053376881949e-05, + "loss": 0.1257, + "step": 241230 + }, + { + "epoch": 0.54, + "learning_rate": 2.3139415225610168e-05, + "loss": 0.1326, + "step": 241240 + }, + { + "epoch": 0.54, + "learning_rate": 2.3138296682400843e-05, + "loss": 0.1284, + "step": 241250 + }, + { + "epoch": 0.54, + "learning_rate": 2.3137178139191517e-05, + "loss": 0.1277, + "step": 241260 + }, + { + "epoch": 0.54, + "learning_rate": 2.3136059595982192e-05, + "loss": 0.1279, + "step": 241270 + }, + { + "epoch": 0.54, + "learning_rate": 2.313494105277287e-05, + "loss": 0.1322, + "step": 241280 + }, + { + "epoch": 0.54, + "learning_rate": 2.3133822509563548e-05, + "loss": 0.1263, + "step": 241290 + }, + { + "epoch": 0.54, + "learning_rate": 2.3132703966354222e-05, + "loss": 0.124, + "step": 241300 + }, + { + "epoch": 0.54, + "learning_rate": 2.3131585423144897e-05, + "loss": 0.1245, + "step": 241310 + }, + { + "epoch": 0.54, + "learning_rate": 2.313046687993557e-05, + "loss": 0.129, + "step": 241320 + }, + { + "epoch": 0.54, + "learning_rate": 2.312934833672625e-05, + "loss": 0.1246, + "step": 241330 + }, + { + "epoch": 0.54, + "learning_rate": 2.3128229793516927e-05, + "loss": 0.1261, + "step": 241340 + }, + { + "epoch": 0.54, + "learning_rate": 2.31271112503076e-05, + "loss": 0.1271, + "step": 241350 + }, + { + "epoch": 0.54, + "learning_rate": 2.3125992707098276e-05, + "loss": 0.1248, + "step": 241360 + }, + { + "epoch": 0.54, + "learning_rate": 2.312487416388895e-05, + "loss": 0.1255, + "step": 241370 + }, + { + "epoch": 0.54, + "learning_rate": 2.3123755620679625e-05, + "loss": 0.1323, + "step": 241380 + }, + { + "epoch": 0.54, + "learning_rate": 2.3122637077470307e-05, + "loss": 0.1268, + "step": 241390 + }, + { + "epoch": 0.54, + "learning_rate": 2.312151853426098e-05, + "loss": 0.1282, + "step": 241400 + }, + { + "epoch": 0.54, + "learning_rate": 2.3120399991051656e-05, + "loss": 0.1256, + "step": 241410 + }, + { + "epoch": 0.54, + "learning_rate": 2.311928144784233e-05, + "loss": 0.1288, + "step": 241420 + }, + { + "epoch": 0.54, + "learning_rate": 2.3118162904633005e-05, + "loss": 0.1297, + "step": 241430 + }, + { + "epoch": 0.54, + "learning_rate": 2.3117044361423683e-05, + "loss": 0.1258, + "step": 241440 + }, + { + "epoch": 0.54, + "learning_rate": 2.311592581821436e-05, + "loss": 0.1291, + "step": 241450 + }, + { + "epoch": 0.54, + "learning_rate": 2.3114807275005035e-05, + "loss": 0.1244, + "step": 241460 + }, + { + "epoch": 0.54, + "learning_rate": 2.311368873179571e-05, + "loss": 0.1255, + "step": 241470 + }, + { + "epoch": 0.54, + "learning_rate": 2.3112570188586384e-05, + "loss": 0.1318, + "step": 241480 + }, + { + "epoch": 0.54, + "learning_rate": 2.3111451645377062e-05, + "loss": 0.1257, + "step": 241490 + }, + { + "epoch": 0.54, + "learning_rate": 2.311033310216774e-05, + "loss": 0.1286, + "step": 241500 + }, + { + "epoch": 0.54, + "learning_rate": 2.3109214558958415e-05, + "loss": 0.1281, + "step": 241510 + }, + { + "epoch": 0.54, + "learning_rate": 2.310809601574909e-05, + "loss": 0.1265, + "step": 241520 + }, + { + "epoch": 0.54, + "learning_rate": 2.3106977472539764e-05, + "loss": 0.1222, + "step": 241530 + }, + { + "epoch": 0.54, + "learning_rate": 2.310585892933044e-05, + "loss": 0.1253, + "step": 241540 + }, + { + "epoch": 0.54, + "learning_rate": 2.310474038612112e-05, + "loss": 0.1258, + "step": 241550 + }, + { + "epoch": 0.54, + "learning_rate": 2.3103621842911794e-05, + "loss": 0.1282, + "step": 241560 + }, + { + "epoch": 0.54, + "learning_rate": 2.310250329970247e-05, + "loss": 0.1282, + "step": 241570 + }, + { + "epoch": 0.54, + "learning_rate": 2.3101384756493143e-05, + "loss": 0.1292, + "step": 241580 + }, + { + "epoch": 0.54, + "learning_rate": 2.3100266213283818e-05, + "loss": 0.13, + "step": 241590 + }, + { + "epoch": 0.54, + "learning_rate": 2.30991476700745e-05, + "loss": 0.1287, + "step": 241600 + }, + { + "epoch": 0.54, + "learning_rate": 2.3098029126865174e-05, + "loss": 0.1266, + "step": 241610 + }, + { + "epoch": 0.54, + "learning_rate": 2.3096910583655848e-05, + "loss": 0.1283, + "step": 241620 + }, + { + "epoch": 0.54, + "learning_rate": 2.3095792040446523e-05, + "loss": 0.1312, + "step": 241630 + }, + { + "epoch": 0.54, + "learning_rate": 2.3094673497237197e-05, + "loss": 0.1295, + "step": 241640 + }, + { + "epoch": 0.54, + "learning_rate": 2.3093554954027875e-05, + "loss": 0.1299, + "step": 241650 + }, + { + "epoch": 0.54, + "learning_rate": 2.3092436410818553e-05, + "loss": 0.1258, + "step": 241660 + }, + { + "epoch": 0.54, + "learning_rate": 2.3091317867609228e-05, + "loss": 0.1306, + "step": 241670 + }, + { + "epoch": 0.54, + "learning_rate": 2.3090199324399902e-05, + "loss": 0.1262, + "step": 241680 + }, + { + "epoch": 0.54, + "learning_rate": 2.3089080781190577e-05, + "loss": 0.1238, + "step": 241690 + }, + { + "epoch": 0.54, + "learning_rate": 2.3087962237981255e-05, + "loss": 0.1242, + "step": 241700 + }, + { + "epoch": 0.54, + "learning_rate": 2.3086843694771933e-05, + "loss": 0.1251, + "step": 241710 + }, + { + "epoch": 0.54, + "learning_rate": 2.3085725151562607e-05, + "loss": 0.1247, + "step": 241720 + }, + { + "epoch": 0.54, + "learning_rate": 2.308460660835328e-05, + "loss": 0.126, + "step": 241730 + }, + { + "epoch": 0.54, + "learning_rate": 2.3083488065143956e-05, + "loss": 0.1313, + "step": 241740 + }, + { + "epoch": 0.54, + "learning_rate": 2.3082369521934634e-05, + "loss": 0.1285, + "step": 241750 + }, + { + "epoch": 0.54, + "learning_rate": 2.3081250978725312e-05, + "loss": 0.127, + "step": 241760 + }, + { + "epoch": 0.54, + "learning_rate": 2.3080132435515987e-05, + "loss": 0.1231, + "step": 241770 + }, + { + "epoch": 0.54, + "learning_rate": 2.3079125746627595e-05, + "loss": 0.1248, + "step": 241780 + }, + { + "epoch": 0.54, + "learning_rate": 2.307800720341827e-05, + "loss": 0.1306, + "step": 241790 + }, + { + "epoch": 0.54, + "learning_rate": 2.3076888660208944e-05, + "loss": 0.1271, + "step": 241800 + }, + { + "epoch": 0.54, + "learning_rate": 2.307577011699962e-05, + "loss": 0.1286, + "step": 241810 + }, + { + "epoch": 0.54, + "learning_rate": 2.3074651573790297e-05, + "loss": 0.1293, + "step": 241820 + }, + { + "epoch": 0.54, + "learning_rate": 2.3073533030580975e-05, + "loss": 0.1256, + "step": 241830 + }, + { + "epoch": 0.54, + "learning_rate": 2.307241448737165e-05, + "loss": 0.1247, + "step": 241840 + }, + { + "epoch": 0.54, + "learning_rate": 2.3071295944162324e-05, + "loss": 0.1279, + "step": 241850 + }, + { + "epoch": 0.54, + "learning_rate": 2.3070177400953e-05, + "loss": 0.129, + "step": 241860 + }, + { + "epoch": 0.54, + "learning_rate": 2.3069058857743676e-05, + "loss": 0.1315, + "step": 241870 + }, + { + "epoch": 0.54, + "learning_rate": 2.306794031453435e-05, + "loss": 0.1265, + "step": 241880 + }, + { + "epoch": 0.54, + "learning_rate": 2.306682177132503e-05, + "loss": 0.1293, + "step": 241890 + }, + { + "epoch": 0.54, + "learning_rate": 2.3065703228115703e-05, + "loss": 0.13, + "step": 241900 + }, + { + "epoch": 0.54, + "learning_rate": 2.3064584684906378e-05, + "loss": 0.1284, + "step": 241910 + }, + { + "epoch": 0.54, + "learning_rate": 2.3063466141697056e-05, + "loss": 0.1271, + "step": 241920 + }, + { + "epoch": 0.54, + "learning_rate": 2.306234759848773e-05, + "loss": 0.1248, + "step": 241930 + }, + { + "epoch": 0.54, + "learning_rate": 2.3061229055278408e-05, + "loss": 0.1221, + "step": 241940 + }, + { + "epoch": 0.54, + "learning_rate": 2.3060110512069083e-05, + "loss": 0.1279, + "step": 241950 + }, + { + "epoch": 0.54, + "learning_rate": 2.3058991968859757e-05, + "loss": 0.1292, + "step": 241960 + }, + { + "epoch": 0.54, + "learning_rate": 2.3057873425650435e-05, + "loss": 0.1277, + "step": 241970 + }, + { + "epoch": 0.54, + "learning_rate": 2.305675488244111e-05, + "loss": 0.1231, + "step": 241980 + }, + { + "epoch": 0.54, + "learning_rate": 2.3055636339231788e-05, + "loss": 0.1236, + "step": 241990 + }, + { + "epoch": 0.54, + "learning_rate": 2.3054517796022462e-05, + "loss": 0.1285, + "step": 242000 + }, + { + "epoch": 0.54, + "learning_rate": 2.3053399252813137e-05, + "loss": 0.1276, + "step": 242010 + }, + { + "epoch": 0.54, + "learning_rate": 2.305228070960381e-05, + "loss": 0.1317, + "step": 242020 + }, + { + "epoch": 0.54, + "learning_rate": 2.305116216639449e-05, + "loss": 0.1311, + "step": 242030 + }, + { + "epoch": 0.54, + "learning_rate": 2.3050043623185164e-05, + "loss": 0.1264, + "step": 242040 + }, + { + "epoch": 0.54, + "learning_rate": 2.3048925079975842e-05, + "loss": 0.125, + "step": 242050 + }, + { + "epoch": 0.54, + "learning_rate": 2.3047806536766516e-05, + "loss": 0.1276, + "step": 242060 + }, + { + "epoch": 0.54, + "learning_rate": 2.304668799355719e-05, + "loss": 0.125, + "step": 242070 + }, + { + "epoch": 0.54, + "learning_rate": 2.304556945034787e-05, + "loss": 0.1239, + "step": 242080 + }, + { + "epoch": 0.54, + "learning_rate": 2.3044450907138543e-05, + "loss": 0.1261, + "step": 242090 + }, + { + "epoch": 0.54, + "learning_rate": 2.304333236392922e-05, + "loss": 0.1314, + "step": 242100 + }, + { + "epoch": 0.54, + "learning_rate": 2.3042213820719896e-05, + "loss": 0.1278, + "step": 242110 + }, + { + "epoch": 0.54, + "learning_rate": 2.304109527751057e-05, + "loss": 0.1264, + "step": 242120 + }, + { + "epoch": 0.54, + "learning_rate": 2.3039976734301248e-05, + "loss": 0.1301, + "step": 242130 + }, + { + "epoch": 0.54, + "learning_rate": 2.3038858191091923e-05, + "loss": 0.1272, + "step": 242140 + }, + { + "epoch": 0.54, + "learning_rate": 2.30377396478826e-05, + "loss": 0.1266, + "step": 242150 + }, + { + "epoch": 0.54, + "learning_rate": 2.3036621104673275e-05, + "loss": 0.1329, + "step": 242160 + }, + { + "epoch": 0.54, + "learning_rate": 2.303550256146395e-05, + "loss": 0.1275, + "step": 242170 + }, + { + "epoch": 0.54, + "learning_rate": 2.3034384018254628e-05, + "loss": 0.1259, + "step": 242180 + }, + { + "epoch": 0.54, + "learning_rate": 2.3033265475045302e-05, + "loss": 0.1252, + "step": 242190 + }, + { + "epoch": 0.54, + "learning_rate": 2.3032146931835977e-05, + "loss": 0.1256, + "step": 242200 + }, + { + "epoch": 0.54, + "learning_rate": 2.3031028388626655e-05, + "loss": 0.1232, + "step": 242210 + }, + { + "epoch": 0.54, + "learning_rate": 2.302990984541733e-05, + "loss": 0.1272, + "step": 242220 + }, + { + "epoch": 0.54, + "learning_rate": 2.3028791302208004e-05, + "loss": 0.1275, + "step": 242230 + }, + { + "epoch": 0.54, + "learning_rate": 2.3027672758998682e-05, + "loss": 0.1297, + "step": 242240 + }, + { + "epoch": 0.54, + "learning_rate": 2.3026554215789356e-05, + "loss": 0.1291, + "step": 242250 + }, + { + "epoch": 0.54, + "learning_rate": 2.3025435672580034e-05, + "loss": 0.1256, + "step": 242260 + }, + { + "epoch": 0.54, + "learning_rate": 2.302431712937071e-05, + "loss": 0.1322, + "step": 242270 + }, + { + "epoch": 0.54, + "learning_rate": 2.3023198586161383e-05, + "loss": 0.1255, + "step": 242280 + }, + { + "epoch": 0.54, + "learning_rate": 2.302208004295206e-05, + "loss": 0.1306, + "step": 242290 + }, + { + "epoch": 0.54, + "learning_rate": 2.3020961499742736e-05, + "loss": 0.1254, + "step": 242300 + }, + { + "epoch": 0.54, + "learning_rate": 2.301984295653341e-05, + "loss": 0.1295, + "step": 242310 + }, + { + "epoch": 0.54, + "learning_rate": 2.3018724413324088e-05, + "loss": 0.1238, + "step": 242320 + }, + { + "epoch": 0.54, + "learning_rate": 2.3017605870114763e-05, + "loss": 0.1316, + "step": 242330 + }, + { + "epoch": 0.54, + "learning_rate": 2.301648732690544e-05, + "loss": 0.1224, + "step": 242340 + }, + { + "epoch": 0.54, + "learning_rate": 2.3015368783696115e-05, + "loss": 0.1245, + "step": 242350 + }, + { + "epoch": 0.54, + "learning_rate": 2.301425024048679e-05, + "loss": 0.1227, + "step": 242360 + }, + { + "epoch": 0.54, + "learning_rate": 2.3013131697277468e-05, + "loss": 0.1266, + "step": 242370 + }, + { + "epoch": 0.54, + "learning_rate": 2.3012013154068142e-05, + "loss": 0.1242, + "step": 242380 + }, + { + "epoch": 0.54, + "learning_rate": 2.301089461085882e-05, + "loss": 0.1219, + "step": 242390 + }, + { + "epoch": 0.54, + "learning_rate": 2.3009776067649495e-05, + "loss": 0.1289, + "step": 242400 + }, + { + "epoch": 0.54, + "learning_rate": 2.300865752444017e-05, + "loss": 0.1295, + "step": 242410 + }, + { + "epoch": 0.54, + "learning_rate": 2.3007538981230847e-05, + "loss": 0.1272, + "step": 242420 + }, + { + "epoch": 0.54, + "learning_rate": 2.3006420438021522e-05, + "loss": 0.1266, + "step": 242430 + }, + { + "epoch": 0.54, + "learning_rate": 2.3005301894812196e-05, + "loss": 0.1265, + "step": 242440 + }, + { + "epoch": 0.54, + "learning_rate": 2.3004183351602874e-05, + "loss": 0.1267, + "step": 242450 + }, + { + "epoch": 0.54, + "learning_rate": 2.300306480839355e-05, + "loss": 0.1266, + "step": 242460 + }, + { + "epoch": 0.54, + "learning_rate": 2.3001946265184223e-05, + "loss": 0.1304, + "step": 242470 + }, + { + "epoch": 0.54, + "learning_rate": 2.30008277219749e-05, + "loss": 0.1232, + "step": 242480 + }, + { + "epoch": 0.54, + "learning_rate": 2.2999709178765576e-05, + "loss": 0.1231, + "step": 242490 + }, + { + "epoch": 0.54, + "learning_rate": 2.2998590635556254e-05, + "loss": 0.1259, + "step": 242500 + }, + { + "epoch": 0.54, + "learning_rate": 2.2997472092346928e-05, + "loss": 0.1259, + "step": 242510 + }, + { + "epoch": 0.54, + "learning_rate": 2.2996353549137603e-05, + "loss": 0.1298, + "step": 242520 + }, + { + "epoch": 0.54, + "learning_rate": 2.299523500592828e-05, + "loss": 0.1249, + "step": 242530 + }, + { + "epoch": 0.54, + "learning_rate": 2.2994116462718955e-05, + "loss": 0.1267, + "step": 242540 + }, + { + "epoch": 0.54, + "learning_rate": 2.2992997919509633e-05, + "loss": 0.1309, + "step": 242550 + }, + { + "epoch": 0.54, + "learning_rate": 2.2991879376300308e-05, + "loss": 0.1292, + "step": 242560 + }, + { + "epoch": 0.54, + "learning_rate": 2.2990760833090982e-05, + "loss": 0.1273, + "step": 242570 + }, + { + "epoch": 0.54, + "learning_rate": 2.298964228988166e-05, + "loss": 0.1258, + "step": 242580 + }, + { + "epoch": 0.54, + "learning_rate": 2.2988523746672335e-05, + "loss": 0.1229, + "step": 242590 + }, + { + "epoch": 0.54, + "learning_rate": 2.2987405203463013e-05, + "loss": 0.1232, + "step": 242600 + }, + { + "epoch": 0.54, + "learning_rate": 2.2986286660253687e-05, + "loss": 0.1273, + "step": 242610 + }, + { + "epoch": 0.54, + "learning_rate": 2.298516811704436e-05, + "loss": 0.1288, + "step": 242620 + }, + { + "epoch": 0.54, + "learning_rate": 2.2984049573835036e-05, + "loss": 0.1276, + "step": 242630 + }, + { + "epoch": 0.54, + "learning_rate": 2.2982931030625714e-05, + "loss": 0.1281, + "step": 242640 + }, + { + "epoch": 0.54, + "learning_rate": 2.298181248741639e-05, + "loss": 0.1296, + "step": 242650 + }, + { + "epoch": 0.54, + "learning_rate": 2.2980693944207067e-05, + "loss": 0.1283, + "step": 242660 + }, + { + "epoch": 0.54, + "learning_rate": 2.297957540099774e-05, + "loss": 0.1262, + "step": 242670 + }, + { + "epoch": 0.54, + "learning_rate": 2.2978456857788416e-05, + "loss": 0.1286, + "step": 242680 + }, + { + "epoch": 0.54, + "learning_rate": 2.2977338314579094e-05, + "loss": 0.1301, + "step": 242690 + }, + { + "epoch": 0.54, + "learning_rate": 2.2976219771369768e-05, + "loss": 0.1285, + "step": 242700 + }, + { + "epoch": 0.54, + "learning_rate": 2.2975101228160446e-05, + "loss": 0.1266, + "step": 242710 + }, + { + "epoch": 0.54, + "learning_rate": 2.297398268495112e-05, + "loss": 0.1238, + "step": 242720 + }, + { + "epoch": 0.54, + "learning_rate": 2.2972864141741795e-05, + "loss": 0.1279, + "step": 242730 + }, + { + "epoch": 0.54, + "learning_rate": 2.2971745598532473e-05, + "loss": 0.1261, + "step": 242740 + }, + { + "epoch": 0.54, + "learning_rate": 2.2970627055323148e-05, + "loss": 0.1276, + "step": 242750 + }, + { + "epoch": 0.54, + "learning_rate": 2.2969508512113826e-05, + "loss": 0.1261, + "step": 242760 + }, + { + "epoch": 0.54, + "learning_rate": 2.29683899689045e-05, + "loss": 0.1257, + "step": 242770 + }, + { + "epoch": 0.54, + "learning_rate": 2.2967271425695175e-05, + "loss": 0.1288, + "step": 242780 + }, + { + "epoch": 0.54, + "learning_rate": 2.296615288248585e-05, + "loss": 0.1208, + "step": 242790 + }, + { + "epoch": 0.54, + "learning_rate": 2.2965034339276527e-05, + "loss": 0.1266, + "step": 242800 + }, + { + "epoch": 0.54, + "learning_rate": 2.2963915796067205e-05, + "loss": 0.1253, + "step": 242810 + }, + { + "epoch": 0.54, + "learning_rate": 2.296279725285788e-05, + "loss": 0.1241, + "step": 242820 + }, + { + "epoch": 0.54, + "learning_rate": 2.2961678709648554e-05, + "loss": 0.1275, + "step": 242830 + }, + { + "epoch": 0.54, + "learning_rate": 2.296056016643923e-05, + "loss": 0.125, + "step": 242840 + }, + { + "epoch": 0.54, + "learning_rate": 2.2959441623229907e-05, + "loss": 0.1243, + "step": 242850 + }, + { + "epoch": 0.54, + "learning_rate": 2.2958323080020585e-05, + "loss": 0.1275, + "step": 242860 + }, + { + "epoch": 0.54, + "learning_rate": 2.295720453681126e-05, + "loss": 0.1283, + "step": 242870 + }, + { + "epoch": 0.54, + "learning_rate": 2.2956085993601934e-05, + "loss": 0.1252, + "step": 242880 + }, + { + "epoch": 0.54, + "learning_rate": 2.2954967450392608e-05, + "loss": 0.1278, + "step": 242890 + }, + { + "epoch": 0.54, + "learning_rate": 2.2953848907183286e-05, + "loss": 0.1239, + "step": 242900 + }, + { + "epoch": 0.54, + "learning_rate": 2.295273036397396e-05, + "loss": 0.132, + "step": 242910 + }, + { + "epoch": 0.54, + "learning_rate": 2.295161182076464e-05, + "loss": 0.1256, + "step": 242920 + }, + { + "epoch": 0.54, + "learning_rate": 2.2950493277555313e-05, + "loss": 0.1231, + "step": 242930 + }, + { + "epoch": 0.54, + "learning_rate": 2.2949374734345988e-05, + "loss": 0.1242, + "step": 242940 + }, + { + "epoch": 0.54, + "learning_rate": 2.2948256191136662e-05, + "loss": 0.1307, + "step": 242950 + }, + { + "epoch": 0.54, + "learning_rate": 2.294713764792734e-05, + "loss": 0.126, + "step": 242960 + }, + { + "epoch": 0.54, + "learning_rate": 2.2946019104718018e-05, + "loss": 0.1211, + "step": 242970 + }, + { + "epoch": 0.54, + "learning_rate": 2.2944900561508693e-05, + "loss": 0.1313, + "step": 242980 + }, + { + "epoch": 0.54, + "learning_rate": 2.2943782018299367e-05, + "loss": 0.1206, + "step": 242990 + }, + { + "epoch": 0.54, + "learning_rate": 2.294266347509004e-05, + "loss": 0.127, + "step": 243000 + }, + { + "epoch": 0.54, + "learning_rate": 2.294154493188072e-05, + "loss": 0.1254, + "step": 243010 + }, + { + "epoch": 0.54, + "learning_rate": 2.2940426388671397e-05, + "loss": 0.1231, + "step": 243020 + }, + { + "epoch": 0.54, + "learning_rate": 2.2939307845462072e-05, + "loss": 0.1285, + "step": 243030 + }, + { + "epoch": 0.54, + "learning_rate": 2.2938189302252747e-05, + "loss": 0.1308, + "step": 243040 + }, + { + "epoch": 0.54, + "learning_rate": 2.293707075904342e-05, + "loss": 0.1282, + "step": 243050 + }, + { + "epoch": 0.54, + "learning_rate": 2.29359522158341e-05, + "loss": 0.1293, + "step": 243060 + }, + { + "epoch": 0.54, + "learning_rate": 2.2934833672624777e-05, + "loss": 0.1226, + "step": 243070 + }, + { + "epoch": 0.54, + "learning_rate": 2.293371512941545e-05, + "loss": 0.1269, + "step": 243080 + }, + { + "epoch": 0.54, + "learning_rate": 2.2932596586206126e-05, + "loss": 0.129, + "step": 243090 + }, + { + "epoch": 0.54, + "learning_rate": 2.29314780429968e-05, + "loss": 0.1275, + "step": 243100 + }, + { + "epoch": 0.54, + "learning_rate": 2.2930359499787475e-05, + "loss": 0.1269, + "step": 243110 + }, + { + "epoch": 0.54, + "learning_rate": 2.2929240956578153e-05, + "loss": 0.1283, + "step": 243120 + }, + { + "epoch": 0.54, + "learning_rate": 2.292812241336883e-05, + "loss": 0.1276, + "step": 243130 + }, + { + "epoch": 0.54, + "learning_rate": 2.2927003870159506e-05, + "loss": 0.1279, + "step": 243140 + }, + { + "epoch": 0.54, + "learning_rate": 2.292588532695018e-05, + "loss": 0.1218, + "step": 243150 + }, + { + "epoch": 0.54, + "learning_rate": 2.2924766783740855e-05, + "loss": 0.1246, + "step": 243160 + }, + { + "epoch": 0.54, + "learning_rate": 2.2923648240531533e-05, + "loss": 0.1275, + "step": 243170 + }, + { + "epoch": 0.54, + "learning_rate": 2.292252969732221e-05, + "loss": 0.1272, + "step": 243180 + }, + { + "epoch": 0.54, + "learning_rate": 2.2921411154112885e-05, + "loss": 0.1286, + "step": 243190 + }, + { + "epoch": 0.54, + "learning_rate": 2.292029261090356e-05, + "loss": 0.1299, + "step": 243200 + }, + { + "epoch": 0.54, + "learning_rate": 2.2919174067694234e-05, + "loss": 0.1261, + "step": 243210 + }, + { + "epoch": 0.54, + "learning_rate": 2.2918055524484912e-05, + "loss": 0.1249, + "step": 243220 + }, + { + "epoch": 0.54, + "learning_rate": 2.291693698127559e-05, + "loss": 0.1244, + "step": 243230 + }, + { + "epoch": 0.54, + "learning_rate": 2.2915818438066264e-05, + "loss": 0.1282, + "step": 243240 + }, + { + "epoch": 0.54, + "learning_rate": 2.291469989485694e-05, + "loss": 0.1245, + "step": 243250 + }, + { + "epoch": 0.54, + "learning_rate": 2.2913581351647614e-05, + "loss": 0.127, + "step": 243260 + }, + { + "epoch": 0.54, + "learning_rate": 2.2912462808438288e-05, + "loss": 0.1321, + "step": 243270 + }, + { + "epoch": 0.54, + "learning_rate": 2.291134426522897e-05, + "loss": 0.1282, + "step": 243280 + }, + { + "epoch": 0.54, + "learning_rate": 2.2910225722019644e-05, + "loss": 0.1285, + "step": 243290 + }, + { + "epoch": 0.54, + "learning_rate": 2.290910717881032e-05, + "loss": 0.1267, + "step": 243300 + }, + { + "epoch": 0.54, + "learning_rate": 2.2907988635600993e-05, + "loss": 0.122, + "step": 243310 + }, + { + "epoch": 0.54, + "learning_rate": 2.2906870092391668e-05, + "loss": 0.1271, + "step": 243320 + }, + { + "epoch": 0.54, + "learning_rate": 2.2905751549182345e-05, + "loss": 0.126, + "step": 243330 + }, + { + "epoch": 0.54, + "learning_rate": 2.2904633005973023e-05, + "loss": 0.1233, + "step": 243340 + }, + { + "epoch": 0.54, + "learning_rate": 2.2903514462763698e-05, + "loss": 0.13, + "step": 243350 + }, + { + "epoch": 0.54, + "learning_rate": 2.2902395919554372e-05, + "loss": 0.1305, + "step": 243360 + }, + { + "epoch": 0.54, + "learning_rate": 2.2901277376345047e-05, + "loss": 0.126, + "step": 243370 + }, + { + "epoch": 0.54, + "learning_rate": 2.2900158833135725e-05, + "loss": 0.1329, + "step": 243380 + }, + { + "epoch": 0.54, + "learning_rate": 2.2899040289926403e-05, + "loss": 0.1267, + "step": 243390 + }, + { + "epoch": 0.54, + "learning_rate": 2.2897921746717077e-05, + "loss": 0.1281, + "step": 243400 + }, + { + "epoch": 0.54, + "learning_rate": 2.2896803203507752e-05, + "loss": 0.1256, + "step": 243410 + }, + { + "epoch": 0.54, + "learning_rate": 2.2895684660298426e-05, + "loss": 0.1253, + "step": 243420 + }, + { + "epoch": 0.54, + "learning_rate": 2.2894566117089104e-05, + "loss": 0.1287, + "step": 243430 + }, + { + "epoch": 0.54, + "learning_rate": 2.2893447573879782e-05, + "loss": 0.1228, + "step": 243440 + }, + { + "epoch": 0.54, + "learning_rate": 2.2892329030670457e-05, + "loss": 0.124, + "step": 243450 + }, + { + "epoch": 0.54, + "learning_rate": 2.289121048746113e-05, + "loss": 0.1204, + "step": 243460 + }, + { + "epoch": 0.54, + "learning_rate": 2.2890091944251806e-05, + "loss": 0.1271, + "step": 243470 + }, + { + "epoch": 0.54, + "learning_rate": 2.2888973401042484e-05, + "loss": 0.126, + "step": 243480 + }, + { + "epoch": 0.54, + "learning_rate": 2.2887854857833162e-05, + "loss": 0.1235, + "step": 243490 + }, + { + "epoch": 0.54, + "learning_rate": 2.2886736314623836e-05, + "loss": 0.1286, + "step": 243500 + }, + { + "epoch": 0.54, + "learning_rate": 2.288561777141451e-05, + "loss": 0.1245, + "step": 243510 + }, + { + "epoch": 0.54, + "learning_rate": 2.2884499228205185e-05, + "loss": 0.1221, + "step": 243520 + }, + { + "epoch": 0.54, + "learning_rate": 2.288338068499586e-05, + "loss": 0.1325, + "step": 243530 + }, + { + "epoch": 0.54, + "learning_rate": 2.2882262141786538e-05, + "loss": 0.1235, + "step": 243540 + }, + { + "epoch": 0.54, + "learning_rate": 2.2881143598577216e-05, + "loss": 0.1247, + "step": 243550 + }, + { + "epoch": 0.54, + "learning_rate": 2.288002505536789e-05, + "loss": 0.1292, + "step": 243560 + }, + { + "epoch": 0.54, + "learning_rate": 2.2878906512158565e-05, + "loss": 0.1278, + "step": 243570 + }, + { + "epoch": 0.54, + "learning_rate": 2.287778796894924e-05, + "loss": 0.1266, + "step": 243580 + }, + { + "epoch": 0.54, + "learning_rate": 2.2876669425739917e-05, + "loss": 0.1286, + "step": 243590 + }, + { + "epoch": 0.54, + "learning_rate": 2.2875550882530595e-05, + "loss": 0.1247, + "step": 243600 + }, + { + "epoch": 0.54, + "learning_rate": 2.287443233932127e-05, + "loss": 0.1236, + "step": 243610 + }, + { + "epoch": 0.54, + "learning_rate": 2.2873313796111944e-05, + "loss": 0.1292, + "step": 243620 + }, + { + "epoch": 0.54, + "learning_rate": 2.287219525290262e-05, + "loss": 0.1224, + "step": 243630 + }, + { + "epoch": 0.54, + "learning_rate": 2.2871076709693297e-05, + "loss": 0.1295, + "step": 243640 + }, + { + "epoch": 0.54, + "learning_rate": 2.2869958166483975e-05, + "loss": 0.1291, + "step": 243650 + }, + { + "epoch": 0.54, + "learning_rate": 2.286883962327465e-05, + "loss": 0.126, + "step": 243660 + }, + { + "epoch": 0.54, + "learning_rate": 2.2867832934386258e-05, + "loss": 0.1254, + "step": 243670 + }, + { + "epoch": 0.54, + "learning_rate": 2.2866714391176933e-05, + "loss": 0.1323, + "step": 243680 + }, + { + "epoch": 0.54, + "learning_rate": 2.2865595847967607e-05, + "loss": 0.129, + "step": 243690 + }, + { + "epoch": 0.54, + "learning_rate": 2.2864477304758282e-05, + "loss": 0.1268, + "step": 243700 + }, + { + "epoch": 0.54, + "learning_rate": 2.286335876154896e-05, + "loss": 0.128, + "step": 243710 + }, + { + "epoch": 0.54, + "learning_rate": 2.2862240218339638e-05, + "loss": 0.1314, + "step": 243720 + }, + { + "epoch": 0.54, + "learning_rate": 2.2861121675130312e-05, + "loss": 0.126, + "step": 243730 + }, + { + "epoch": 0.54, + "learning_rate": 2.2860003131920987e-05, + "loss": 0.1253, + "step": 243740 + }, + { + "epoch": 0.54, + "learning_rate": 2.285888458871166e-05, + "loss": 0.1282, + "step": 243750 + }, + { + "epoch": 0.54, + "learning_rate": 2.285776604550234e-05, + "loss": 0.1231, + "step": 243760 + }, + { + "epoch": 0.54, + "learning_rate": 2.2856647502293017e-05, + "loss": 0.1254, + "step": 243770 + }, + { + "epoch": 0.54, + "learning_rate": 2.285552895908369e-05, + "loss": 0.1261, + "step": 243780 + }, + { + "epoch": 0.54, + "learning_rate": 2.2854410415874366e-05, + "loss": 0.1244, + "step": 243790 + }, + { + "epoch": 0.54, + "learning_rate": 2.285329187266504e-05, + "loss": 0.1208, + "step": 243800 + }, + { + "epoch": 0.54, + "learning_rate": 2.285217332945572e-05, + "loss": 0.1236, + "step": 243810 + }, + { + "epoch": 0.54, + "learning_rate": 2.2851054786246393e-05, + "loss": 0.1278, + "step": 243820 + }, + { + "epoch": 0.54, + "learning_rate": 2.284993624303707e-05, + "loss": 0.1268, + "step": 243830 + }, + { + "epoch": 0.54, + "learning_rate": 2.2848817699827746e-05, + "loss": 0.1262, + "step": 243840 + }, + { + "epoch": 0.54, + "learning_rate": 2.284769915661842e-05, + "loss": 0.1267, + "step": 243850 + }, + { + "epoch": 0.54, + "learning_rate": 2.2846580613409098e-05, + "loss": 0.1209, + "step": 243860 + }, + { + "epoch": 0.54, + "learning_rate": 2.2845462070199773e-05, + "loss": 0.1274, + "step": 243870 + }, + { + "epoch": 0.54, + "learning_rate": 2.284434352699045e-05, + "loss": 0.1316, + "step": 243880 + }, + { + "epoch": 0.54, + "learning_rate": 2.2843224983781125e-05, + "loss": 0.1257, + "step": 243890 + }, + { + "epoch": 0.54, + "learning_rate": 2.28421064405718e-05, + "loss": 0.1268, + "step": 243900 + }, + { + "epoch": 0.54, + "learning_rate": 2.2840987897362474e-05, + "loss": 0.1296, + "step": 243910 + }, + { + "epoch": 0.54, + "learning_rate": 2.2839869354153152e-05, + "loss": 0.1226, + "step": 243920 + }, + { + "epoch": 0.54, + "learning_rate": 2.283875081094383e-05, + "loss": 0.1273, + "step": 243930 + }, + { + "epoch": 0.54, + "learning_rate": 2.2837632267734505e-05, + "loss": 0.1213, + "step": 243940 + }, + { + "epoch": 0.54, + "learning_rate": 2.283651372452518e-05, + "loss": 0.1231, + "step": 243950 + }, + { + "epoch": 0.54, + "learning_rate": 2.2835395181315854e-05, + "loss": 0.1252, + "step": 243960 + }, + { + "epoch": 0.54, + "learning_rate": 2.283427663810653e-05, + "loss": 0.1246, + "step": 243970 + }, + { + "epoch": 0.54, + "learning_rate": 2.2833158094897206e-05, + "loss": 0.1292, + "step": 243980 + }, + { + "epoch": 0.54, + "learning_rate": 2.2832039551687884e-05, + "loss": 0.1266, + "step": 243990 + }, + { + "epoch": 0.54, + "learning_rate": 2.283092100847856e-05, + "loss": 0.1313, + "step": 244000 + }, + { + "epoch": 0.54, + "learning_rate": 2.2829802465269233e-05, + "loss": 0.127, + "step": 244010 + }, + { + "epoch": 0.54, + "learning_rate": 2.282868392205991e-05, + "loss": 0.1271, + "step": 244020 + }, + { + "epoch": 0.54, + "learning_rate": 2.2827565378850586e-05, + "loss": 0.131, + "step": 244030 + }, + { + "epoch": 0.54, + "learning_rate": 2.2826446835641264e-05, + "loss": 0.126, + "step": 244040 + }, + { + "epoch": 0.54, + "learning_rate": 2.2825328292431938e-05, + "loss": 0.1251, + "step": 244050 + }, + { + "epoch": 0.54, + "learning_rate": 2.2824209749222613e-05, + "loss": 0.134, + "step": 244060 + }, + { + "epoch": 0.54, + "learning_rate": 2.282309120601329e-05, + "loss": 0.1259, + "step": 244070 + }, + { + "epoch": 0.54, + "learning_rate": 2.2821972662803965e-05, + "loss": 0.1267, + "step": 244080 + }, + { + "epoch": 0.54, + "learning_rate": 2.2820854119594643e-05, + "loss": 0.1284, + "step": 244090 + }, + { + "epoch": 0.54, + "learning_rate": 2.2819735576385318e-05, + "loss": 0.1283, + "step": 244100 + }, + { + "epoch": 0.54, + "learning_rate": 2.2818617033175992e-05, + "loss": 0.1242, + "step": 244110 + }, + { + "epoch": 0.54, + "learning_rate": 2.2817498489966667e-05, + "loss": 0.1289, + "step": 244120 + }, + { + "epoch": 0.54, + "learning_rate": 2.2816379946757345e-05, + "loss": 0.1235, + "step": 244130 + }, + { + "epoch": 0.54, + "learning_rate": 2.281526140354802e-05, + "loss": 0.1258, + "step": 244140 + }, + { + "epoch": 0.54, + "learning_rate": 2.2814142860338697e-05, + "loss": 0.1263, + "step": 244150 + }, + { + "epoch": 0.54, + "learning_rate": 2.281302431712937e-05, + "loss": 0.123, + "step": 244160 + }, + { + "epoch": 0.55, + "learning_rate": 2.2811905773920046e-05, + "loss": 0.1335, + "step": 244170 + }, + { + "epoch": 0.55, + "learning_rate": 2.2810787230710724e-05, + "loss": 0.1272, + "step": 244180 + }, + { + "epoch": 0.55, + "learning_rate": 2.28096686875014e-05, + "loss": 0.131, + "step": 244190 + }, + { + "epoch": 0.55, + "learning_rate": 2.2808550144292076e-05, + "loss": 0.1271, + "step": 244200 + }, + { + "epoch": 0.55, + "learning_rate": 2.280743160108275e-05, + "loss": 0.1267, + "step": 244210 + }, + { + "epoch": 0.55, + "learning_rate": 2.2806313057873426e-05, + "loss": 0.128, + "step": 244220 + }, + { + "epoch": 0.55, + "learning_rate": 2.2805194514664103e-05, + "loss": 0.1251, + "step": 244230 + }, + { + "epoch": 0.55, + "learning_rate": 2.2804075971454778e-05, + "loss": 0.1258, + "step": 244240 + }, + { + "epoch": 0.55, + "learning_rate": 2.2802957428245456e-05, + "loss": 0.1252, + "step": 244250 + }, + { + "epoch": 0.55, + "learning_rate": 2.280183888503613e-05, + "loss": 0.125, + "step": 244260 + }, + { + "epoch": 0.55, + "learning_rate": 2.2800720341826805e-05, + "loss": 0.127, + "step": 244270 + }, + { + "epoch": 0.55, + "learning_rate": 2.2799601798617483e-05, + "loss": 0.1276, + "step": 244280 + }, + { + "epoch": 0.55, + "learning_rate": 2.2798483255408157e-05, + "loss": 0.1281, + "step": 244290 + }, + { + "epoch": 0.55, + "learning_rate": 2.2797364712198832e-05, + "loss": 0.1306, + "step": 244300 + }, + { + "epoch": 0.55, + "learning_rate": 2.279624616898951e-05, + "loss": 0.1297, + "step": 244310 + }, + { + "epoch": 0.55, + "learning_rate": 2.2795127625780184e-05, + "loss": 0.1263, + "step": 244320 + }, + { + "epoch": 0.55, + "learning_rate": 2.2794009082570862e-05, + "loss": 0.1276, + "step": 244330 + }, + { + "epoch": 0.55, + "learning_rate": 2.2792890539361537e-05, + "loss": 0.1249, + "step": 244340 + }, + { + "epoch": 0.55, + "learning_rate": 2.279177199615221e-05, + "loss": 0.1257, + "step": 244350 + }, + { + "epoch": 0.55, + "learning_rate": 2.279065345294289e-05, + "loss": 0.1295, + "step": 244360 + }, + { + "epoch": 0.55, + "learning_rate": 2.2789534909733564e-05, + "loss": 0.1246, + "step": 244370 + }, + { + "epoch": 0.55, + "learning_rate": 2.278841636652424e-05, + "loss": 0.1257, + "step": 244380 + }, + { + "epoch": 0.55, + "learning_rate": 2.2787297823314916e-05, + "loss": 0.1263, + "step": 244390 + }, + { + "epoch": 0.55, + "learning_rate": 2.278617928010559e-05, + "loss": 0.1212, + "step": 244400 + }, + { + "epoch": 0.55, + "learning_rate": 2.278506073689627e-05, + "loss": 0.1301, + "step": 244410 + }, + { + "epoch": 0.55, + "learning_rate": 2.2783942193686943e-05, + "loss": 0.1284, + "step": 244420 + }, + { + "epoch": 0.55, + "learning_rate": 2.2782823650477618e-05, + "loss": 0.1274, + "step": 244430 + }, + { + "epoch": 0.55, + "learning_rate": 2.2781705107268296e-05, + "loss": 0.1285, + "step": 244440 + }, + { + "epoch": 0.55, + "learning_rate": 2.278058656405897e-05, + "loss": 0.1251, + "step": 244450 + }, + { + "epoch": 0.55, + "learning_rate": 2.2779468020849645e-05, + "loss": 0.1322, + "step": 244460 + }, + { + "epoch": 0.55, + "learning_rate": 2.2778349477640323e-05, + "loss": 0.1301, + "step": 244470 + }, + { + "epoch": 0.55, + "learning_rate": 2.2777230934430997e-05, + "loss": 0.1242, + "step": 244480 + }, + { + "epoch": 0.55, + "learning_rate": 2.2776112391221675e-05, + "loss": 0.1253, + "step": 244490 + }, + { + "epoch": 0.55, + "learning_rate": 2.277499384801235e-05, + "loss": 0.1269, + "step": 244500 + }, + { + "epoch": 0.55, + "learning_rate": 2.2773875304803024e-05, + "loss": 0.1228, + "step": 244510 + }, + { + "epoch": 0.55, + "learning_rate": 2.2772756761593702e-05, + "loss": 0.1256, + "step": 244520 + }, + { + "epoch": 0.55, + "learning_rate": 2.2771638218384377e-05, + "loss": 0.1233, + "step": 244530 + }, + { + "epoch": 0.55, + "learning_rate": 2.2770519675175055e-05, + "loss": 0.1291, + "step": 244540 + }, + { + "epoch": 0.55, + "learning_rate": 2.276940113196573e-05, + "loss": 0.1243, + "step": 244550 + }, + { + "epoch": 0.55, + "learning_rate": 2.2768282588756404e-05, + "loss": 0.1271, + "step": 244560 + }, + { + "epoch": 0.55, + "learning_rate": 2.2767164045547082e-05, + "loss": 0.1282, + "step": 244570 + }, + { + "epoch": 0.55, + "learning_rate": 2.2766045502337756e-05, + "loss": 0.1251, + "step": 244580 + }, + { + "epoch": 0.55, + "learning_rate": 2.276492695912843e-05, + "loss": 0.1215, + "step": 244590 + }, + { + "epoch": 0.55, + "learning_rate": 2.276380841591911e-05, + "loss": 0.1246, + "step": 244600 + }, + { + "epoch": 0.55, + "learning_rate": 2.2762689872709783e-05, + "loss": 0.1246, + "step": 244610 + }, + { + "epoch": 0.55, + "learning_rate": 2.2761571329500458e-05, + "loss": 0.1254, + "step": 244620 + }, + { + "epoch": 0.55, + "learning_rate": 2.2760452786291136e-05, + "loss": 0.1236, + "step": 244630 + }, + { + "epoch": 0.55, + "learning_rate": 2.275933424308181e-05, + "loss": 0.1272, + "step": 244640 + }, + { + "epoch": 0.55, + "learning_rate": 2.275821569987249e-05, + "loss": 0.1292, + "step": 244650 + }, + { + "epoch": 0.55, + "learning_rate": 2.2757097156663163e-05, + "loss": 0.1278, + "step": 244660 + }, + { + "epoch": 0.55, + "learning_rate": 2.2755978613453837e-05, + "loss": 0.1312, + "step": 244670 + }, + { + "epoch": 0.55, + "learning_rate": 2.2754860070244515e-05, + "loss": 0.1304, + "step": 244680 + }, + { + "epoch": 0.55, + "learning_rate": 2.275374152703519e-05, + "loss": 0.1274, + "step": 244690 + }, + { + "epoch": 0.55, + "learning_rate": 2.2752622983825868e-05, + "loss": 0.126, + "step": 244700 + }, + { + "epoch": 0.55, + "learning_rate": 2.2751504440616542e-05, + "loss": 0.129, + "step": 244710 + }, + { + "epoch": 0.55, + "learning_rate": 2.2750385897407217e-05, + "loss": 0.1277, + "step": 244720 + }, + { + "epoch": 0.55, + "learning_rate": 2.2749267354197895e-05, + "loss": 0.1274, + "step": 244730 + }, + { + "epoch": 0.55, + "learning_rate": 2.274814881098857e-05, + "loss": 0.1248, + "step": 244740 + }, + { + "epoch": 0.55, + "learning_rate": 2.2747030267779247e-05, + "loss": 0.1257, + "step": 244750 + }, + { + "epoch": 0.55, + "learning_rate": 2.2745911724569922e-05, + "loss": 0.1252, + "step": 244760 + }, + { + "epoch": 0.55, + "learning_rate": 2.2744793181360596e-05, + "loss": 0.1256, + "step": 244770 + }, + { + "epoch": 0.55, + "learning_rate": 2.274367463815127e-05, + "loss": 0.1278, + "step": 244780 + }, + { + "epoch": 0.55, + "learning_rate": 2.274255609494195e-05, + "loss": 0.1246, + "step": 244790 + }, + { + "epoch": 0.55, + "learning_rate": 2.2741437551732623e-05, + "loss": 0.1274, + "step": 244800 + }, + { + "epoch": 0.55, + "learning_rate": 2.27403190085233e-05, + "loss": 0.1241, + "step": 244810 + }, + { + "epoch": 0.55, + "learning_rate": 2.2739200465313976e-05, + "loss": 0.1262, + "step": 244820 + }, + { + "epoch": 0.55, + "learning_rate": 2.273808192210465e-05, + "loss": 0.1287, + "step": 244830 + }, + { + "epoch": 0.55, + "learning_rate": 2.273696337889533e-05, + "loss": 0.1263, + "step": 244840 + }, + { + "epoch": 0.55, + "learning_rate": 2.2735844835686003e-05, + "loss": 0.1214, + "step": 244850 + }, + { + "epoch": 0.55, + "learning_rate": 2.273472629247668e-05, + "loss": 0.1237, + "step": 244860 + }, + { + "epoch": 0.55, + "learning_rate": 2.2733607749267355e-05, + "loss": 0.1285, + "step": 244870 + }, + { + "epoch": 0.55, + "learning_rate": 2.273248920605803e-05, + "loss": 0.1268, + "step": 244880 + }, + { + "epoch": 0.55, + "learning_rate": 2.2731370662848708e-05, + "loss": 0.1291, + "step": 244890 + }, + { + "epoch": 0.55, + "learning_rate": 2.2730252119639382e-05, + "loss": 0.1258, + "step": 244900 + }, + { + "epoch": 0.55, + "learning_rate": 2.272913357643006e-05, + "loss": 0.1258, + "step": 244910 + }, + { + "epoch": 0.55, + "learning_rate": 2.2728015033220735e-05, + "loss": 0.1277, + "step": 244920 + }, + { + "epoch": 0.55, + "learning_rate": 2.272689649001141e-05, + "loss": 0.1235, + "step": 244930 + }, + { + "epoch": 0.55, + "learning_rate": 2.2725777946802084e-05, + "loss": 0.1201, + "step": 244940 + }, + { + "epoch": 0.55, + "learning_rate": 2.2724659403592762e-05, + "loss": 0.1234, + "step": 244950 + }, + { + "epoch": 0.55, + "learning_rate": 2.272354086038344e-05, + "loss": 0.1308, + "step": 244960 + }, + { + "epoch": 0.55, + "learning_rate": 2.2722422317174114e-05, + "loss": 0.127, + "step": 244970 + }, + { + "epoch": 0.55, + "learning_rate": 2.272130377396479e-05, + "loss": 0.1305, + "step": 244980 + }, + { + "epoch": 0.55, + "learning_rate": 2.2720185230755463e-05, + "loss": 0.1255, + "step": 244990 + }, + { + "epoch": 0.55, + "learning_rate": 2.271906668754614e-05, + "loss": 0.125, + "step": 245000 + }, + { + "epoch": 0.55, + "learning_rate": 2.2717948144336816e-05, + "loss": 0.1231, + "step": 245010 + }, + { + "epoch": 0.55, + "learning_rate": 2.2716829601127494e-05, + "loss": 0.1295, + "step": 245020 + }, + { + "epoch": 0.55, + "learning_rate": 2.2715711057918168e-05, + "loss": 0.1241, + "step": 245030 + }, + { + "epoch": 0.55, + "learning_rate": 2.2714592514708843e-05, + "loss": 0.1255, + "step": 245040 + }, + { + "epoch": 0.55, + "learning_rate": 2.271347397149952e-05, + "loss": 0.1277, + "step": 245050 + }, + { + "epoch": 0.55, + "learning_rate": 2.2712355428290195e-05, + "loss": 0.1297, + "step": 245060 + }, + { + "epoch": 0.55, + "learning_rate": 2.2711236885080873e-05, + "loss": 0.1214, + "step": 245070 + }, + { + "epoch": 0.55, + "learning_rate": 2.2710118341871548e-05, + "loss": 0.1305, + "step": 245080 + }, + { + "epoch": 0.55, + "learning_rate": 2.2708999798662222e-05, + "loss": 0.1258, + "step": 245090 + }, + { + "epoch": 0.55, + "learning_rate": 2.2707881255452897e-05, + "loss": 0.125, + "step": 245100 + }, + { + "epoch": 0.55, + "learning_rate": 2.2706762712243575e-05, + "loss": 0.1277, + "step": 245110 + }, + { + "epoch": 0.55, + "learning_rate": 2.2705644169034253e-05, + "loss": 0.1252, + "step": 245120 + }, + { + "epoch": 0.55, + "learning_rate": 2.2704525625824927e-05, + "loss": 0.1234, + "step": 245130 + }, + { + "epoch": 0.55, + "learning_rate": 2.2703407082615602e-05, + "loss": 0.1257, + "step": 245140 + }, + { + "epoch": 0.55, + "learning_rate": 2.2702288539406276e-05, + "loss": 0.1206, + "step": 245150 + }, + { + "epoch": 0.55, + "learning_rate": 2.2701169996196954e-05, + "loss": 0.1287, + "step": 245160 + }, + { + "epoch": 0.55, + "learning_rate": 2.2700051452987632e-05, + "loss": 0.1279, + "step": 245170 + }, + { + "epoch": 0.55, + "learning_rate": 2.2698932909778307e-05, + "loss": 0.125, + "step": 245180 + }, + { + "epoch": 0.55, + "learning_rate": 2.269781436656898e-05, + "loss": 0.1271, + "step": 245190 + }, + { + "epoch": 0.55, + "learning_rate": 2.2696695823359656e-05, + "loss": 0.1297, + "step": 245200 + }, + { + "epoch": 0.55, + "learning_rate": 2.269557728015033e-05, + "loss": 0.1257, + "step": 245210 + }, + { + "epoch": 0.55, + "learning_rate": 2.269445873694101e-05, + "loss": 0.1272, + "step": 245220 + }, + { + "epoch": 0.55, + "learning_rate": 2.2693340193731686e-05, + "loss": 0.1244, + "step": 245230 + }, + { + "epoch": 0.55, + "learning_rate": 2.269222165052236e-05, + "loss": 0.1239, + "step": 245240 + }, + { + "epoch": 0.55, + "learning_rate": 2.2691103107313035e-05, + "loss": 0.1259, + "step": 245250 + }, + { + "epoch": 0.55, + "learning_rate": 2.268998456410371e-05, + "loss": 0.1246, + "step": 245260 + }, + { + "epoch": 0.55, + "learning_rate": 2.2688866020894388e-05, + "loss": 0.1251, + "step": 245270 + }, + { + "epoch": 0.55, + "learning_rate": 2.2687747477685066e-05, + "loss": 0.1283, + "step": 245280 + }, + { + "epoch": 0.55, + "learning_rate": 2.268662893447574e-05, + "loss": 0.1246, + "step": 245290 + }, + { + "epoch": 0.55, + "learning_rate": 2.2685510391266415e-05, + "loss": 0.1294, + "step": 245300 + }, + { + "epoch": 0.55, + "learning_rate": 2.268439184805709e-05, + "loss": 0.1317, + "step": 245310 + }, + { + "epoch": 0.55, + "learning_rate": 2.2683273304847767e-05, + "loss": 0.1268, + "step": 245320 + }, + { + "epoch": 0.55, + "learning_rate": 2.2682154761638445e-05, + "loss": 0.123, + "step": 245330 + }, + { + "epoch": 0.55, + "learning_rate": 2.268103621842912e-05, + "loss": 0.125, + "step": 245340 + }, + { + "epoch": 0.55, + "learning_rate": 2.2679917675219794e-05, + "loss": 0.129, + "step": 245350 + }, + { + "epoch": 0.55, + "learning_rate": 2.267879913201047e-05, + "loss": 0.1262, + "step": 245360 + }, + { + "epoch": 0.55, + "learning_rate": 2.2677680588801147e-05, + "loss": 0.128, + "step": 245370 + }, + { + "epoch": 0.55, + "learning_rate": 2.2676562045591825e-05, + "loss": 0.1259, + "step": 245380 + }, + { + "epoch": 0.55, + "learning_rate": 2.26754435023825e-05, + "loss": 0.1232, + "step": 245390 + }, + { + "epoch": 0.55, + "learning_rate": 2.2674324959173174e-05, + "loss": 0.1215, + "step": 245400 + }, + { + "epoch": 0.55, + "learning_rate": 2.2673206415963848e-05, + "loss": 0.1275, + "step": 245410 + }, + { + "epoch": 0.55, + "learning_rate": 2.2672087872754523e-05, + "loss": 0.1274, + "step": 245420 + }, + { + "epoch": 0.55, + "learning_rate": 2.2670969329545204e-05, + "loss": 0.126, + "step": 245430 + }, + { + "epoch": 0.55, + "learning_rate": 2.266985078633588e-05, + "loss": 0.1288, + "step": 245440 + }, + { + "epoch": 0.55, + "learning_rate": 2.2668732243126553e-05, + "loss": 0.1273, + "step": 245450 + }, + { + "epoch": 0.55, + "learning_rate": 2.2667613699917228e-05, + "loss": 0.1334, + "step": 245460 + }, + { + "epoch": 0.55, + "learning_rate": 2.2666495156707902e-05, + "loss": 0.1242, + "step": 245470 + }, + { + "epoch": 0.55, + "learning_rate": 2.266537661349858e-05, + "loss": 0.1257, + "step": 245480 + }, + { + "epoch": 0.55, + "learning_rate": 2.2664258070289258e-05, + "loss": 0.1272, + "step": 245490 + }, + { + "epoch": 0.55, + "learning_rate": 2.2663139527079933e-05, + "loss": 0.1223, + "step": 245500 + }, + { + "epoch": 0.55, + "learning_rate": 2.2662020983870607e-05, + "loss": 0.1319, + "step": 245510 + }, + { + "epoch": 0.55, + "learning_rate": 2.2660902440661282e-05, + "loss": 0.1225, + "step": 245520 + }, + { + "epoch": 0.55, + "learning_rate": 2.265978389745196e-05, + "loss": 0.1323, + "step": 245530 + }, + { + "epoch": 0.55, + "learning_rate": 2.2658665354242638e-05, + "loss": 0.1277, + "step": 245540 + }, + { + "epoch": 0.55, + "learning_rate": 2.2657546811033312e-05, + "loss": 0.1287, + "step": 245550 + }, + { + "epoch": 0.55, + "learning_rate": 2.2656428267823987e-05, + "loss": 0.1198, + "step": 245560 + }, + { + "epoch": 0.55, + "learning_rate": 2.265530972461466e-05, + "loss": 0.1271, + "step": 245570 + }, + { + "epoch": 0.55, + "learning_rate": 2.265419118140534e-05, + "loss": 0.1291, + "step": 245580 + }, + { + "epoch": 0.55, + "learning_rate": 2.2653072638196017e-05, + "loss": 0.1228, + "step": 245590 + }, + { + "epoch": 0.55, + "learning_rate": 2.265195409498669e-05, + "loss": 0.1183, + "step": 245600 + }, + { + "epoch": 0.55, + "learning_rate": 2.2650835551777366e-05, + "loss": 0.1273, + "step": 245610 + }, + { + "epoch": 0.55, + "learning_rate": 2.264971700856804e-05, + "loss": 0.1267, + "step": 245620 + }, + { + "epoch": 0.55, + "learning_rate": 2.2648598465358715e-05, + "loss": 0.1246, + "step": 245630 + }, + { + "epoch": 0.55, + "learning_rate": 2.2647479922149397e-05, + "loss": 0.1254, + "step": 245640 + }, + { + "epoch": 0.55, + "learning_rate": 2.264636137894007e-05, + "loss": 0.1262, + "step": 245650 + }, + { + "epoch": 0.55, + "learning_rate": 2.2645242835730746e-05, + "loss": 0.123, + "step": 245660 + }, + { + "epoch": 0.55, + "learning_rate": 2.264412429252142e-05, + "loss": 0.1264, + "step": 245670 + }, + { + "epoch": 0.55, + "learning_rate": 2.2643005749312095e-05, + "loss": 0.1227, + "step": 245680 + }, + { + "epoch": 0.55, + "learning_rate": 2.2641887206102773e-05, + "loss": 0.1261, + "step": 245690 + }, + { + "epoch": 0.55, + "learning_rate": 2.264076866289345e-05, + "loss": 0.1254, + "step": 245700 + }, + { + "epoch": 0.55, + "learning_rate": 2.2639650119684125e-05, + "loss": 0.1285, + "step": 245710 + }, + { + "epoch": 0.55, + "learning_rate": 2.26385315764748e-05, + "loss": 0.1234, + "step": 245720 + }, + { + "epoch": 0.55, + "learning_rate": 2.2637413033265474e-05, + "loss": 0.121, + "step": 245730 + }, + { + "epoch": 0.55, + "learning_rate": 2.2636294490056152e-05, + "loss": 0.1227, + "step": 245740 + }, + { + "epoch": 0.55, + "learning_rate": 2.263517594684683e-05, + "loss": 0.127, + "step": 245750 + }, + { + "epoch": 0.55, + "learning_rate": 2.2634057403637505e-05, + "loss": 0.1253, + "step": 245760 + }, + { + "epoch": 0.55, + "learning_rate": 2.263293886042818e-05, + "loss": 0.1256, + "step": 245770 + }, + { + "epoch": 0.55, + "learning_rate": 2.2631820317218854e-05, + "loss": 0.1268, + "step": 245780 + }, + { + "epoch": 0.55, + "learning_rate": 2.263070177400953e-05, + "loss": 0.1272, + "step": 245790 + }, + { + "epoch": 0.55, + "learning_rate": 2.262958323080021e-05, + "loss": 0.1237, + "step": 245800 + }, + { + "epoch": 0.55, + "learning_rate": 2.2628464687590884e-05, + "loss": 0.124, + "step": 245810 + }, + { + "epoch": 0.55, + "learning_rate": 2.262734614438156e-05, + "loss": 0.1302, + "step": 245820 + }, + { + "epoch": 0.55, + "learning_rate": 2.2626227601172233e-05, + "loss": 0.1235, + "step": 245830 + }, + { + "epoch": 0.55, + "learning_rate": 2.262510905796291e-05, + "loss": 0.1236, + "step": 245840 + }, + { + "epoch": 0.55, + "learning_rate": 2.2623990514753586e-05, + "loss": 0.1291, + "step": 245850 + }, + { + "epoch": 0.55, + "learning_rate": 2.2622871971544263e-05, + "loss": 0.1275, + "step": 245860 + }, + { + "epoch": 0.55, + "learning_rate": 2.2621753428334938e-05, + "loss": 0.1302, + "step": 245870 + }, + { + "epoch": 0.55, + "learning_rate": 2.2620634885125613e-05, + "loss": 0.1227, + "step": 245880 + }, + { + "epoch": 0.55, + "learning_rate": 2.2619516341916287e-05, + "loss": 0.1257, + "step": 245890 + }, + { + "epoch": 0.55, + "learning_rate": 2.2618397798706965e-05, + "loss": 0.1304, + "step": 245900 + }, + { + "epoch": 0.55, + "learning_rate": 2.2617279255497643e-05, + "loss": 0.1276, + "step": 245910 + }, + { + "epoch": 0.55, + "learning_rate": 2.2616160712288318e-05, + "loss": 0.1281, + "step": 245920 + }, + { + "epoch": 0.55, + "learning_rate": 2.2615042169078992e-05, + "loss": 0.1239, + "step": 245930 + }, + { + "epoch": 0.55, + "learning_rate": 2.2613923625869667e-05, + "loss": 0.1222, + "step": 245940 + }, + { + "epoch": 0.55, + "learning_rate": 2.2612805082660345e-05, + "loss": 0.1249, + "step": 245950 + }, + { + "epoch": 0.55, + "learning_rate": 2.2611686539451022e-05, + "loss": 0.1282, + "step": 245960 + }, + { + "epoch": 0.55, + "learning_rate": 2.2610567996241697e-05, + "loss": 0.1278, + "step": 245970 + }, + { + "epoch": 0.55, + "learning_rate": 2.260944945303237e-05, + "loss": 0.1303, + "step": 245980 + }, + { + "epoch": 0.55, + "learning_rate": 2.2608330909823046e-05, + "loss": 0.1299, + "step": 245990 + }, + { + "epoch": 0.55, + "learning_rate": 2.2607212366613724e-05, + "loss": 0.1294, + "step": 246000 + }, + { + "epoch": 0.55, + "learning_rate": 2.26060938234044e-05, + "loss": 0.1315, + "step": 246010 + }, + { + "epoch": 0.55, + "learning_rate": 2.2604975280195076e-05, + "loss": 0.1257, + "step": 246020 + }, + { + "epoch": 0.55, + "learning_rate": 2.260385673698575e-05, + "loss": 0.1188, + "step": 246030 + }, + { + "epoch": 0.55, + "learning_rate": 2.2602738193776426e-05, + "loss": 0.1263, + "step": 246040 + }, + { + "epoch": 0.55, + "learning_rate": 2.2601619650567103e-05, + "loss": 0.1227, + "step": 246050 + }, + { + "epoch": 0.55, + "learning_rate": 2.2600501107357778e-05, + "loss": 0.126, + "step": 246060 + }, + { + "epoch": 0.55, + "learning_rate": 2.2599382564148456e-05, + "loss": 0.1249, + "step": 246070 + }, + { + "epoch": 0.55, + "learning_rate": 2.259826402093913e-05, + "loss": 0.1238, + "step": 246080 + }, + { + "epoch": 0.55, + "learning_rate": 2.2597145477729805e-05, + "loss": 0.1272, + "step": 246090 + }, + { + "epoch": 0.55, + "learning_rate": 2.259602693452048e-05, + "loss": 0.1257, + "step": 246100 + }, + { + "epoch": 0.55, + "learning_rate": 2.2594908391311157e-05, + "loss": 0.1253, + "step": 246110 + }, + { + "epoch": 0.55, + "learning_rate": 2.2593789848101835e-05, + "loss": 0.122, + "step": 246120 + }, + { + "epoch": 0.55, + "learning_rate": 2.259267130489251e-05, + "loss": 0.124, + "step": 246130 + }, + { + "epoch": 0.55, + "learning_rate": 2.2591552761683184e-05, + "loss": 0.1231, + "step": 246140 + }, + { + "epoch": 0.55, + "learning_rate": 2.259043421847386e-05, + "loss": 0.1219, + "step": 246150 + }, + { + "epoch": 0.55, + "learning_rate": 2.2589315675264537e-05, + "loss": 0.1299, + "step": 246160 + }, + { + "epoch": 0.55, + "learning_rate": 2.258819713205521e-05, + "loss": 0.1271, + "step": 246170 + }, + { + "epoch": 0.55, + "learning_rate": 2.258707858884589e-05, + "loss": 0.1248, + "step": 246180 + }, + { + "epoch": 0.55, + "learning_rate": 2.2585960045636564e-05, + "loss": 0.1297, + "step": 246190 + }, + { + "epoch": 0.55, + "learning_rate": 2.258484150242724e-05, + "loss": 0.1255, + "step": 246200 + }, + { + "epoch": 0.55, + "learning_rate": 2.2583722959217916e-05, + "loss": 0.1273, + "step": 246210 + }, + { + "epoch": 0.55, + "learning_rate": 2.258260441600859e-05, + "loss": 0.1298, + "step": 246220 + }, + { + "epoch": 0.55, + "learning_rate": 2.258148587279927e-05, + "loss": 0.1248, + "step": 246230 + }, + { + "epoch": 0.55, + "learning_rate": 2.2580367329589943e-05, + "loss": 0.1225, + "step": 246240 + }, + { + "epoch": 0.55, + "learning_rate": 2.2579248786380618e-05, + "loss": 0.1249, + "step": 246250 + }, + { + "epoch": 0.55, + "learning_rate": 2.2578130243171296e-05, + "loss": 0.124, + "step": 246260 + }, + { + "epoch": 0.55, + "learning_rate": 2.257701169996197e-05, + "loss": 0.125, + "step": 246270 + }, + { + "epoch": 0.55, + "learning_rate": 2.257589315675265e-05, + "loss": 0.126, + "step": 246280 + }, + { + "epoch": 0.55, + "learning_rate": 2.2574774613543323e-05, + "loss": 0.1268, + "step": 246290 + }, + { + "epoch": 0.55, + "learning_rate": 2.2573656070333997e-05, + "loss": 0.125, + "step": 246300 + }, + { + "epoch": 0.55, + "learning_rate": 2.2572537527124672e-05, + "loss": 0.1255, + "step": 246310 + }, + { + "epoch": 0.55, + "learning_rate": 2.257141898391535e-05, + "loss": 0.124, + "step": 246320 + }, + { + "epoch": 0.55, + "learning_rate": 2.2570300440706024e-05, + "loss": 0.1275, + "step": 246330 + }, + { + "epoch": 0.55, + "learning_rate": 2.2569181897496702e-05, + "loss": 0.1262, + "step": 246340 + }, + { + "epoch": 0.55, + "learning_rate": 2.2568063354287377e-05, + "loss": 0.127, + "step": 246350 + }, + { + "epoch": 0.55, + "learning_rate": 2.256694481107805e-05, + "loss": 0.1293, + "step": 246360 + }, + { + "epoch": 0.55, + "learning_rate": 2.256582626786873e-05, + "loss": 0.1273, + "step": 246370 + }, + { + "epoch": 0.55, + "learning_rate": 2.2564707724659404e-05, + "loss": 0.1276, + "step": 246380 + }, + { + "epoch": 0.55, + "learning_rate": 2.2563589181450082e-05, + "loss": 0.1279, + "step": 246390 + }, + { + "epoch": 0.55, + "learning_rate": 2.2562470638240756e-05, + "loss": 0.1243, + "step": 246400 + }, + { + "epoch": 0.55, + "learning_rate": 2.256135209503143e-05, + "loss": 0.1248, + "step": 246410 + }, + { + "epoch": 0.55, + "learning_rate": 2.256023355182211e-05, + "loss": 0.1251, + "step": 246420 + }, + { + "epoch": 0.55, + "learning_rate": 2.2559115008612783e-05, + "loss": 0.133, + "step": 246430 + }, + { + "epoch": 0.55, + "learning_rate": 2.255799646540346e-05, + "loss": 0.1275, + "step": 246440 + }, + { + "epoch": 0.55, + "learning_rate": 2.2556877922194136e-05, + "loss": 0.1254, + "step": 246450 + }, + { + "epoch": 0.55, + "learning_rate": 2.255575937898481e-05, + "loss": 0.1245, + "step": 246460 + }, + { + "epoch": 0.55, + "learning_rate": 2.255464083577549e-05, + "loss": 0.1235, + "step": 246470 + }, + { + "epoch": 0.55, + "learning_rate": 2.2553522292566163e-05, + "loss": 0.1272, + "step": 246480 + }, + { + "epoch": 0.55, + "learning_rate": 2.2552403749356837e-05, + "loss": 0.1256, + "step": 246490 + }, + { + "epoch": 0.55, + "learning_rate": 2.2551285206147515e-05, + "loss": 0.1238, + "step": 246500 + }, + { + "epoch": 0.55, + "learning_rate": 2.255016666293819e-05, + "loss": 0.1249, + "step": 246510 + }, + { + "epoch": 0.55, + "learning_rate": 2.2549048119728864e-05, + "loss": 0.1215, + "step": 246520 + }, + { + "epoch": 0.55, + "learning_rate": 2.2547929576519542e-05, + "loss": 0.1243, + "step": 246530 + }, + { + "epoch": 0.55, + "learning_rate": 2.2546811033310217e-05, + "loss": 0.1259, + "step": 246540 + }, + { + "epoch": 0.55, + "learning_rate": 2.2545692490100895e-05, + "loss": 0.1265, + "step": 246550 + }, + { + "epoch": 0.55, + "learning_rate": 2.254457394689157e-05, + "loss": 0.1263, + "step": 246560 + }, + { + "epoch": 0.55, + "learning_rate": 2.2543455403682244e-05, + "loss": 0.1261, + "step": 246570 + }, + { + "epoch": 0.55, + "learning_rate": 2.2542336860472922e-05, + "loss": 0.1244, + "step": 246580 + }, + { + "epoch": 0.55, + "learning_rate": 2.2541218317263596e-05, + "loss": 0.1261, + "step": 246590 + }, + { + "epoch": 0.55, + "learning_rate": 2.2540099774054274e-05, + "loss": 0.1305, + "step": 246600 + }, + { + "epoch": 0.55, + "learning_rate": 2.253898123084495e-05, + "loss": 0.122, + "step": 246610 + }, + { + "epoch": 0.55, + "learning_rate": 2.2537862687635623e-05, + "loss": 0.1265, + "step": 246620 + }, + { + "epoch": 0.55, + "learning_rate": 2.25367441444263e-05, + "loss": 0.13, + "step": 246630 + }, + { + "epoch": 0.55, + "learning_rate": 2.2535625601216976e-05, + "loss": 0.1251, + "step": 246640 + }, + { + "epoch": 0.55, + "learning_rate": 2.253450705800765e-05, + "loss": 0.1242, + "step": 246650 + }, + { + "epoch": 0.55, + "learning_rate": 2.2533388514798328e-05, + "loss": 0.1253, + "step": 246660 + }, + { + "epoch": 0.55, + "learning_rate": 2.2532269971589003e-05, + "loss": 0.1238, + "step": 246670 + }, + { + "epoch": 0.55, + "learning_rate": 2.253115142837968e-05, + "loss": 0.1297, + "step": 246680 + }, + { + "epoch": 0.55, + "learning_rate": 2.2530032885170355e-05, + "loss": 0.1248, + "step": 246690 + }, + { + "epoch": 0.55, + "learning_rate": 2.252891434196103e-05, + "loss": 0.1247, + "step": 246700 + }, + { + "epoch": 0.55, + "learning_rate": 2.2527795798751708e-05, + "loss": 0.1272, + "step": 246710 + }, + { + "epoch": 0.55, + "learning_rate": 2.2526677255542382e-05, + "loss": 0.1232, + "step": 246720 + }, + { + "epoch": 0.55, + "learning_rate": 2.252555871233306e-05, + "loss": 0.126, + "step": 246730 + }, + { + "epoch": 0.55, + "learning_rate": 2.2524440169123735e-05, + "loss": 0.1274, + "step": 246740 + }, + { + "epoch": 0.55, + "learning_rate": 2.252332162591441e-05, + "loss": 0.1267, + "step": 246750 + }, + { + "epoch": 0.55, + "learning_rate": 2.2522203082705087e-05, + "loss": 0.1283, + "step": 246760 + }, + { + "epoch": 0.55, + "learning_rate": 2.2521084539495762e-05, + "loss": 0.1286, + "step": 246770 + }, + { + "epoch": 0.55, + "learning_rate": 2.2519965996286436e-05, + "loss": 0.13, + "step": 246780 + }, + { + "epoch": 0.55, + "learning_rate": 2.2518847453077114e-05, + "loss": 0.1273, + "step": 246790 + }, + { + "epoch": 0.55, + "learning_rate": 2.251772890986779e-05, + "loss": 0.1267, + "step": 246800 + }, + { + "epoch": 0.55, + "learning_rate": 2.2516610366658463e-05, + "loss": 0.1289, + "step": 246810 + }, + { + "epoch": 0.55, + "learning_rate": 2.251549182344914e-05, + "loss": 0.1277, + "step": 246820 + }, + { + "epoch": 0.55, + "learning_rate": 2.2514373280239816e-05, + "loss": 0.1222, + "step": 246830 + }, + { + "epoch": 0.55, + "learning_rate": 2.2513254737030494e-05, + "loss": 0.1254, + "step": 246840 + }, + { + "epoch": 0.55, + "learning_rate": 2.2512136193821168e-05, + "loss": 0.1261, + "step": 246850 + }, + { + "epoch": 0.55, + "learning_rate": 2.2511017650611843e-05, + "loss": 0.1217, + "step": 246860 + }, + { + "epoch": 0.55, + "learning_rate": 2.250989910740252e-05, + "loss": 0.125, + "step": 246870 + }, + { + "epoch": 0.55, + "learning_rate": 2.2508780564193195e-05, + "loss": 0.1234, + "step": 246880 + }, + { + "epoch": 0.55, + "learning_rate": 2.2507662020983873e-05, + "loss": 0.1304, + "step": 246890 + }, + { + "epoch": 0.55, + "learning_rate": 2.2506543477774548e-05, + "loss": 0.1247, + "step": 246900 + }, + { + "epoch": 0.55, + "learning_rate": 2.2505424934565222e-05, + "loss": 0.1251, + "step": 246910 + }, + { + "epoch": 0.55, + "learning_rate": 2.25043063913559e-05, + "loss": 0.1222, + "step": 246920 + }, + { + "epoch": 0.55, + "learning_rate": 2.2503187848146575e-05, + "loss": 0.1262, + "step": 246930 + }, + { + "epoch": 0.55, + "learning_rate": 2.2502069304937253e-05, + "loss": 0.1258, + "step": 246940 + }, + { + "epoch": 0.55, + "learning_rate": 2.2500950761727927e-05, + "loss": 0.1251, + "step": 246950 + }, + { + "epoch": 0.55, + "learning_rate": 2.2499832218518602e-05, + "loss": 0.1275, + "step": 246960 + }, + { + "epoch": 0.55, + "learning_rate": 2.2498713675309276e-05, + "loss": 0.1237, + "step": 246970 + }, + { + "epoch": 0.55, + "learning_rate": 2.2497595132099954e-05, + "loss": 0.1307, + "step": 246980 + }, + { + "epoch": 0.55, + "learning_rate": 2.249647658889063e-05, + "loss": 0.1266, + "step": 246990 + }, + { + "epoch": 0.55, + "learning_rate": 2.2495358045681307e-05, + "loss": 0.1254, + "step": 247000 + }, + { + "epoch": 0.55, + "learning_rate": 2.249423950247198e-05, + "loss": 0.1252, + "step": 247010 + }, + { + "epoch": 0.55, + "learning_rate": 2.2493120959262656e-05, + "loss": 0.1253, + "step": 247020 + }, + { + "epoch": 0.55, + "learning_rate": 2.2492002416053334e-05, + "loss": 0.1248, + "step": 247030 + }, + { + "epoch": 0.55, + "learning_rate": 2.2490883872844008e-05, + "loss": 0.1268, + "step": 247040 + }, + { + "epoch": 0.55, + "learning_rate": 2.2489765329634686e-05, + "loss": 0.1247, + "step": 247050 + }, + { + "epoch": 0.55, + "learning_rate": 2.248864678642536e-05, + "loss": 0.1247, + "step": 247060 + }, + { + "epoch": 0.55, + "learning_rate": 2.2487528243216035e-05, + "loss": 0.1255, + "step": 247070 + }, + { + "epoch": 0.55, + "learning_rate": 2.2486409700006713e-05, + "loss": 0.1237, + "step": 247080 + }, + { + "epoch": 0.55, + "learning_rate": 2.2485291156797388e-05, + "loss": 0.1315, + "step": 247090 + }, + { + "epoch": 0.55, + "learning_rate": 2.2484172613588066e-05, + "loss": 0.1201, + "step": 247100 + }, + { + "epoch": 0.55, + "learning_rate": 2.248305407037874e-05, + "loss": 0.1268, + "step": 247110 + }, + { + "epoch": 0.55, + "learning_rate": 2.2481935527169415e-05, + "loss": 0.1266, + "step": 247120 + }, + { + "epoch": 0.55, + "learning_rate": 2.248081698396009e-05, + "loss": 0.1234, + "step": 247130 + }, + { + "epoch": 0.55, + "learning_rate": 2.2479698440750767e-05, + "loss": 0.1195, + "step": 247140 + }, + { + "epoch": 0.55, + "learning_rate": 2.2478579897541445e-05, + "loss": 0.1268, + "step": 247150 + }, + { + "epoch": 0.55, + "learning_rate": 2.247746135433212e-05, + "loss": 0.1229, + "step": 247160 + }, + { + "epoch": 0.55, + "learning_rate": 2.2476342811122794e-05, + "loss": 0.1279, + "step": 247170 + }, + { + "epoch": 0.55, + "learning_rate": 2.247522426791347e-05, + "loss": 0.1267, + "step": 247180 + }, + { + "epoch": 0.55, + "learning_rate": 2.2474105724704147e-05, + "loss": 0.1305, + "step": 247190 + }, + { + "epoch": 0.55, + "learning_rate": 2.247298718149482e-05, + "loss": 0.1258, + "step": 247200 + }, + { + "epoch": 0.55, + "learning_rate": 2.24718686382855e-05, + "loss": 0.1286, + "step": 247210 + }, + { + "epoch": 0.55, + "learning_rate": 2.2470750095076174e-05, + "loss": 0.1264, + "step": 247220 + }, + { + "epoch": 0.55, + "learning_rate": 2.2469631551866848e-05, + "loss": 0.1256, + "step": 247230 + }, + { + "epoch": 0.55, + "learning_rate": 2.2468513008657526e-05, + "loss": 0.1289, + "step": 247240 + }, + { + "epoch": 0.55, + "learning_rate": 2.24673944654482e-05, + "loss": 0.1253, + "step": 247250 + }, + { + "epoch": 0.55, + "learning_rate": 2.246627592223888e-05, + "loss": 0.1218, + "step": 247260 + }, + { + "epoch": 0.55, + "learning_rate": 2.2465157379029553e-05, + "loss": 0.1228, + "step": 247270 + }, + { + "epoch": 0.55, + "learning_rate": 2.2464038835820228e-05, + "loss": 0.1265, + "step": 247280 + }, + { + "epoch": 0.55, + "learning_rate": 2.2462920292610902e-05, + "loss": 0.1248, + "step": 247290 + }, + { + "epoch": 0.55, + "learning_rate": 2.246180174940158e-05, + "loss": 0.127, + "step": 247300 + }, + { + "epoch": 0.55, + "learning_rate": 2.2460683206192258e-05, + "loss": 0.1269, + "step": 247310 + }, + { + "epoch": 0.55, + "learning_rate": 2.2459564662982933e-05, + "loss": 0.1243, + "step": 247320 + }, + { + "epoch": 0.55, + "learning_rate": 2.2458446119773607e-05, + "loss": 0.1259, + "step": 247330 + }, + { + "epoch": 0.55, + "learning_rate": 2.245732757656428e-05, + "loss": 0.1244, + "step": 247340 + }, + { + "epoch": 0.55, + "learning_rate": 2.245620903335496e-05, + "loss": 0.1279, + "step": 247350 + }, + { + "epoch": 0.55, + "learning_rate": 2.2455090490145638e-05, + "loss": 0.1273, + "step": 247360 + }, + { + "epoch": 0.55, + "learning_rate": 2.2453971946936312e-05, + "loss": 0.1261, + "step": 247370 + }, + { + "epoch": 0.55, + "learning_rate": 2.2452853403726987e-05, + "loss": 0.1248, + "step": 247380 + }, + { + "epoch": 0.55, + "learning_rate": 2.245173486051766e-05, + "loss": 0.1189, + "step": 247390 + }, + { + "epoch": 0.55, + "learning_rate": 2.245061631730834e-05, + "loss": 0.1265, + "step": 247400 + }, + { + "epoch": 0.55, + "learning_rate": 2.2449497774099017e-05, + "loss": 0.1253, + "step": 247410 + }, + { + "epoch": 0.55, + "learning_rate": 2.244837923088969e-05, + "loss": 0.1261, + "step": 247420 + }, + { + "epoch": 0.55, + "learning_rate": 2.2447260687680366e-05, + "loss": 0.1195, + "step": 247430 + }, + { + "epoch": 0.55, + "learning_rate": 2.244614214447104e-05, + "loss": 0.127, + "step": 247440 + }, + { + "epoch": 0.55, + "learning_rate": 2.2445023601261715e-05, + "loss": 0.1277, + "step": 247450 + }, + { + "epoch": 0.55, + "learning_rate": 2.2443905058052393e-05, + "loss": 0.1285, + "step": 247460 + }, + { + "epoch": 0.55, + "learning_rate": 2.244278651484307e-05, + "loss": 0.1242, + "step": 247470 + }, + { + "epoch": 0.55, + "learning_rate": 2.2441667971633746e-05, + "loss": 0.1207, + "step": 247480 + }, + { + "epoch": 0.55, + "learning_rate": 2.244054942842442e-05, + "loss": 0.1257, + "step": 247490 + }, + { + "epoch": 0.55, + "learning_rate": 2.2439430885215095e-05, + "loss": 0.1236, + "step": 247500 + }, + { + "epoch": 0.55, + "learning_rate": 2.2438312342005773e-05, + "loss": 0.1291, + "step": 247510 + }, + { + "epoch": 0.55, + "learning_rate": 2.243719379879645e-05, + "loss": 0.1219, + "step": 247520 + }, + { + "epoch": 0.55, + "learning_rate": 2.2436075255587125e-05, + "loss": 0.124, + "step": 247530 + }, + { + "epoch": 0.55, + "learning_rate": 2.24349567123778e-05, + "loss": 0.1225, + "step": 247540 + }, + { + "epoch": 0.55, + "learning_rate": 2.2433838169168474e-05, + "loss": 0.1202, + "step": 247550 + }, + { + "epoch": 0.55, + "learning_rate": 2.2432719625959152e-05, + "loss": 0.1205, + "step": 247560 + }, + { + "epoch": 0.55, + "learning_rate": 2.243160108274983e-05, + "loss": 0.1256, + "step": 247570 + }, + { + "epoch": 0.55, + "learning_rate": 2.2430482539540505e-05, + "loss": 0.1252, + "step": 247580 + }, + { + "epoch": 0.55, + "learning_rate": 2.242936399633118e-05, + "loss": 0.1253, + "step": 247590 + }, + { + "epoch": 0.55, + "learning_rate": 2.2428245453121854e-05, + "loss": 0.1245, + "step": 247600 + }, + { + "epoch": 0.55, + "learning_rate": 2.2427126909912528e-05, + "loss": 0.1267, + "step": 247610 + }, + { + "epoch": 0.55, + "learning_rate": 2.242600836670321e-05, + "loss": 0.1291, + "step": 247620 + }, + { + "epoch": 0.55, + "learning_rate": 2.2424889823493884e-05, + "loss": 0.1266, + "step": 247630 + }, + { + "epoch": 0.55, + "learning_rate": 2.242377128028456e-05, + "loss": 0.1235, + "step": 247640 + }, + { + "epoch": 0.55, + "learning_rate": 2.2422652737075233e-05, + "loss": 0.1246, + "step": 247650 + }, + { + "epoch": 0.55, + "learning_rate": 2.2421534193865908e-05, + "loss": 0.1234, + "step": 247660 + }, + { + "epoch": 0.55, + "learning_rate": 2.2420527504977516e-05, + "loss": 0.1204, + "step": 247670 + }, + { + "epoch": 0.55, + "learning_rate": 2.2419408961768194e-05, + "loss": 0.1244, + "step": 247680 + }, + { + "epoch": 0.55, + "learning_rate": 2.2418290418558872e-05, + "loss": 0.1227, + "step": 247690 + }, + { + "epoch": 0.55, + "learning_rate": 2.2417171875349547e-05, + "loss": 0.1311, + "step": 247700 + }, + { + "epoch": 0.55, + "learning_rate": 2.241605333214022e-05, + "loss": 0.1261, + "step": 247710 + }, + { + "epoch": 0.55, + "learning_rate": 2.2414934788930896e-05, + "loss": 0.1304, + "step": 247720 + }, + { + "epoch": 0.55, + "learning_rate": 2.2413816245721574e-05, + "loss": 0.1268, + "step": 247730 + }, + { + "epoch": 0.55, + "learning_rate": 2.2412697702512252e-05, + "loss": 0.1259, + "step": 247740 + }, + { + "epoch": 0.55, + "learning_rate": 2.2411579159302926e-05, + "loss": 0.1292, + "step": 247750 + }, + { + "epoch": 0.55, + "learning_rate": 2.24104606160936e-05, + "loss": 0.1197, + "step": 247760 + }, + { + "epoch": 0.55, + "learning_rate": 2.2409342072884275e-05, + "loss": 0.1257, + "step": 247770 + }, + { + "epoch": 0.55, + "learning_rate": 2.240822352967495e-05, + "loss": 0.1271, + "step": 247780 + }, + { + "epoch": 0.55, + "learning_rate": 2.240710498646563e-05, + "loss": 0.1239, + "step": 247790 + }, + { + "epoch": 0.55, + "learning_rate": 2.2405986443256306e-05, + "loss": 0.1268, + "step": 247800 + }, + { + "epoch": 0.55, + "learning_rate": 2.240486790004698e-05, + "loss": 0.1295, + "step": 247810 + }, + { + "epoch": 0.55, + "learning_rate": 2.2403749356837655e-05, + "loss": 0.1264, + "step": 247820 + }, + { + "epoch": 0.55, + "learning_rate": 2.240263081362833e-05, + "loss": 0.1267, + "step": 247830 + }, + { + "epoch": 0.55, + "learning_rate": 2.2401512270419007e-05, + "loss": 0.1227, + "step": 247840 + }, + { + "epoch": 0.55, + "learning_rate": 2.2400393727209685e-05, + "loss": 0.1238, + "step": 247850 + }, + { + "epoch": 0.55, + "learning_rate": 2.239927518400036e-05, + "loss": 0.1261, + "step": 247860 + }, + { + "epoch": 0.55, + "learning_rate": 2.2398156640791034e-05, + "loss": 0.1308, + "step": 247870 + }, + { + "epoch": 0.55, + "learning_rate": 2.239703809758171e-05, + "loss": 0.1213, + "step": 247880 + }, + { + "epoch": 0.55, + "learning_rate": 2.2395919554372387e-05, + "loss": 0.1292, + "step": 247890 + }, + { + "epoch": 0.55, + "learning_rate": 2.2394801011163065e-05, + "loss": 0.1262, + "step": 247900 + }, + { + "epoch": 0.55, + "learning_rate": 2.239368246795374e-05, + "loss": 0.1282, + "step": 247910 + }, + { + "epoch": 0.55, + "learning_rate": 2.2392563924744414e-05, + "loss": 0.1266, + "step": 247920 + }, + { + "epoch": 0.55, + "learning_rate": 2.2391445381535088e-05, + "loss": 0.1273, + "step": 247930 + }, + { + "epoch": 0.55, + "learning_rate": 2.2390326838325766e-05, + "loss": 0.1272, + "step": 247940 + }, + { + "epoch": 0.55, + "learning_rate": 2.2389208295116444e-05, + "loss": 0.1268, + "step": 247950 + }, + { + "epoch": 0.55, + "learning_rate": 2.238808975190712e-05, + "loss": 0.1229, + "step": 247960 + }, + { + "epoch": 0.55, + "learning_rate": 2.2386971208697793e-05, + "loss": 0.1249, + "step": 247970 + }, + { + "epoch": 0.55, + "learning_rate": 2.2385852665488468e-05, + "loss": 0.1226, + "step": 247980 + }, + { + "epoch": 0.55, + "learning_rate": 2.2384734122279146e-05, + "loss": 0.1251, + "step": 247990 + }, + { + "epoch": 0.55, + "learning_rate": 2.238361557906982e-05, + "loss": 0.126, + "step": 248000 + }, + { + "epoch": 0.55, + "learning_rate": 2.2382497035860498e-05, + "loss": 0.1302, + "step": 248010 + }, + { + "epoch": 0.55, + "learning_rate": 2.2381378492651173e-05, + "loss": 0.1232, + "step": 248020 + }, + { + "epoch": 0.55, + "learning_rate": 2.2380259949441847e-05, + "loss": 0.1216, + "step": 248030 + }, + { + "epoch": 0.55, + "learning_rate": 2.2379141406232522e-05, + "loss": 0.1253, + "step": 248040 + }, + { + "epoch": 0.55, + "learning_rate": 2.23780228630232e-05, + "loss": 0.1229, + "step": 248050 + }, + { + "epoch": 0.55, + "learning_rate": 2.2376904319813878e-05, + "loss": 0.1227, + "step": 248060 + }, + { + "epoch": 0.55, + "learning_rate": 2.2375785776604552e-05, + "loss": 0.1231, + "step": 248070 + }, + { + "epoch": 0.55, + "learning_rate": 2.2374667233395227e-05, + "loss": 0.125, + "step": 248080 + }, + { + "epoch": 0.55, + "learning_rate": 2.23735486901859e-05, + "loss": 0.1195, + "step": 248090 + }, + { + "epoch": 0.55, + "learning_rate": 2.237243014697658e-05, + "loss": 0.1227, + "step": 248100 + }, + { + "epoch": 0.55, + "learning_rate": 2.2371311603767257e-05, + "loss": 0.1221, + "step": 248110 + }, + { + "epoch": 0.55, + "learning_rate": 2.237019306055793e-05, + "loss": 0.1266, + "step": 248120 + }, + { + "epoch": 0.55, + "learning_rate": 2.2369074517348606e-05, + "loss": 0.1259, + "step": 248130 + }, + { + "epoch": 0.55, + "learning_rate": 2.236795597413928e-05, + "loss": 0.1264, + "step": 248140 + }, + { + "epoch": 0.55, + "learning_rate": 2.236683743092996e-05, + "loss": 0.1324, + "step": 248150 + }, + { + "epoch": 0.55, + "learning_rate": 2.2365718887720633e-05, + "loss": 0.131, + "step": 248160 + }, + { + "epoch": 0.55, + "learning_rate": 2.236460034451131e-05, + "loss": 0.1291, + "step": 248170 + }, + { + "epoch": 0.55, + "learning_rate": 2.2363481801301986e-05, + "loss": 0.1303, + "step": 248180 + }, + { + "epoch": 0.55, + "learning_rate": 2.236236325809266e-05, + "loss": 0.1239, + "step": 248190 + }, + { + "epoch": 0.55, + "learning_rate": 2.2361244714883338e-05, + "loss": 0.1223, + "step": 248200 + }, + { + "epoch": 0.55, + "learning_rate": 2.2360126171674013e-05, + "loss": 0.1243, + "step": 248210 + }, + { + "epoch": 0.55, + "learning_rate": 2.235900762846469e-05, + "loss": 0.1256, + "step": 248220 + }, + { + "epoch": 0.55, + "learning_rate": 2.2357889085255365e-05, + "loss": 0.1212, + "step": 248230 + }, + { + "epoch": 0.55, + "learning_rate": 2.235677054204604e-05, + "loss": 0.1242, + "step": 248240 + }, + { + "epoch": 0.55, + "learning_rate": 2.2355651998836714e-05, + "loss": 0.1259, + "step": 248250 + }, + { + "epoch": 0.55, + "learning_rate": 2.2354533455627392e-05, + "loss": 0.1309, + "step": 248260 + }, + { + "epoch": 0.55, + "learning_rate": 2.2353414912418067e-05, + "loss": 0.1235, + "step": 248270 + }, + { + "epoch": 0.55, + "learning_rate": 2.2352296369208745e-05, + "loss": 0.1225, + "step": 248280 + }, + { + "epoch": 0.55, + "learning_rate": 2.235117782599942e-05, + "loss": 0.1268, + "step": 248290 + }, + { + "epoch": 0.55, + "learning_rate": 2.2350059282790094e-05, + "loss": 0.1267, + "step": 248300 + }, + { + "epoch": 0.55, + "learning_rate": 2.234894073958077e-05, + "loss": 0.1299, + "step": 248310 + }, + { + "epoch": 0.55, + "learning_rate": 2.2347822196371446e-05, + "loss": 0.1244, + "step": 248320 + }, + { + "epoch": 0.55, + "learning_rate": 2.2346703653162124e-05, + "loss": 0.1264, + "step": 248330 + }, + { + "epoch": 0.55, + "learning_rate": 2.23455851099528e-05, + "loss": 0.1236, + "step": 248340 + }, + { + "epoch": 0.55, + "learning_rate": 2.2344466566743473e-05, + "loss": 0.1231, + "step": 248350 + }, + { + "epoch": 0.55, + "learning_rate": 2.234334802353415e-05, + "loss": 0.121, + "step": 248360 + }, + { + "epoch": 0.55, + "learning_rate": 2.2342229480324826e-05, + "loss": 0.124, + "step": 248370 + }, + { + "epoch": 0.55, + "learning_rate": 2.2341110937115504e-05, + "loss": 0.1284, + "step": 248380 + }, + { + "epoch": 0.55, + "learning_rate": 2.2339992393906178e-05, + "loss": 0.1256, + "step": 248390 + }, + { + "epoch": 0.55, + "learning_rate": 2.2338873850696853e-05, + "loss": 0.1286, + "step": 248400 + }, + { + "epoch": 0.55, + "learning_rate": 2.233775530748753e-05, + "loss": 0.1247, + "step": 248410 + }, + { + "epoch": 0.55, + "learning_rate": 2.2336636764278205e-05, + "loss": 0.1173, + "step": 248420 + }, + { + "epoch": 0.55, + "learning_rate": 2.233551822106888e-05, + "loss": 0.1189, + "step": 248430 + }, + { + "epoch": 0.55, + "learning_rate": 2.2334399677859558e-05, + "loss": 0.1271, + "step": 248440 + }, + { + "epoch": 0.55, + "learning_rate": 2.2333281134650232e-05, + "loss": 0.1232, + "step": 248450 + }, + { + "epoch": 0.55, + "learning_rate": 2.2332162591440907e-05, + "loss": 0.1257, + "step": 248460 + }, + { + "epoch": 0.55, + "learning_rate": 2.2331044048231585e-05, + "loss": 0.1266, + "step": 248470 + }, + { + "epoch": 0.55, + "learning_rate": 2.232992550502226e-05, + "loss": 0.1256, + "step": 248480 + }, + { + "epoch": 0.55, + "learning_rate": 2.2328806961812937e-05, + "loss": 0.1239, + "step": 248490 + }, + { + "epoch": 0.55, + "learning_rate": 2.232768841860361e-05, + "loss": 0.1242, + "step": 248500 + }, + { + "epoch": 0.55, + "learning_rate": 2.2326569875394286e-05, + "loss": 0.1248, + "step": 248510 + }, + { + "epoch": 0.55, + "learning_rate": 2.2325451332184964e-05, + "loss": 0.1264, + "step": 248520 + }, + { + "epoch": 0.55, + "learning_rate": 2.232433278897564e-05, + "loss": 0.1238, + "step": 248530 + }, + { + "epoch": 0.55, + "learning_rate": 2.2323214245766317e-05, + "loss": 0.1261, + "step": 248540 + }, + { + "epoch": 0.55, + "learning_rate": 2.232209570255699e-05, + "loss": 0.1266, + "step": 248550 + }, + { + "epoch": 0.55, + "learning_rate": 2.2320977159347666e-05, + "loss": 0.1248, + "step": 248560 + }, + { + "epoch": 0.55, + "learning_rate": 2.2319858616138344e-05, + "loss": 0.1302, + "step": 248570 + }, + { + "epoch": 0.55, + "learning_rate": 2.2318740072929018e-05, + "loss": 0.1285, + "step": 248580 + }, + { + "epoch": 0.55, + "learning_rate": 2.2317621529719693e-05, + "loss": 0.1206, + "step": 248590 + }, + { + "epoch": 0.55, + "learning_rate": 2.231650298651037e-05, + "loss": 0.1259, + "step": 248600 + }, + { + "epoch": 0.55, + "learning_rate": 2.2315384443301045e-05, + "loss": 0.1225, + "step": 248610 + }, + { + "epoch": 0.55, + "learning_rate": 2.2314265900091723e-05, + "loss": 0.1273, + "step": 248620 + }, + { + "epoch": 0.55, + "learning_rate": 2.2313147356882398e-05, + "loss": 0.1201, + "step": 248630 + }, + { + "epoch": 0.55, + "learning_rate": 2.2312028813673072e-05, + "loss": 0.129, + "step": 248640 + }, + { + "epoch": 0.56, + "learning_rate": 2.231091027046375e-05, + "loss": 0.1246, + "step": 248650 + }, + { + "epoch": 0.56, + "learning_rate": 2.2309791727254425e-05, + "loss": 0.1239, + "step": 248660 + }, + { + "epoch": 0.56, + "learning_rate": 2.23086731840451e-05, + "loss": 0.1234, + "step": 248670 + }, + { + "epoch": 0.56, + "learning_rate": 2.2307554640835777e-05, + "loss": 0.1249, + "step": 248680 + }, + { + "epoch": 0.56, + "learning_rate": 2.230643609762645e-05, + "loss": 0.1242, + "step": 248690 + }, + { + "epoch": 0.56, + "learning_rate": 2.230531755441713e-05, + "loss": 0.1275, + "step": 248700 + }, + { + "epoch": 0.56, + "learning_rate": 2.2304310865528735e-05, + "loss": 0.1281, + "step": 248710 + }, + { + "epoch": 0.56, + "learning_rate": 2.2303192322319413e-05, + "loss": 0.1236, + "step": 248720 + }, + { + "epoch": 0.56, + "learning_rate": 2.2302073779110087e-05, + "loss": 0.1209, + "step": 248730 + }, + { + "epoch": 0.56, + "learning_rate": 2.2300955235900765e-05, + "loss": 0.1275, + "step": 248740 + }, + { + "epoch": 0.56, + "learning_rate": 2.229983669269144e-05, + "loss": 0.1288, + "step": 248750 + }, + { + "epoch": 0.56, + "learning_rate": 2.2298718149482114e-05, + "loss": 0.1259, + "step": 248760 + }, + { + "epoch": 0.56, + "learning_rate": 2.2297599606272792e-05, + "loss": 0.1289, + "step": 248770 + }, + { + "epoch": 0.56, + "learning_rate": 2.2296481063063467e-05, + "loss": 0.125, + "step": 248780 + }, + { + "epoch": 0.56, + "learning_rate": 2.2295362519854145e-05, + "loss": 0.1252, + "step": 248790 + }, + { + "epoch": 0.56, + "learning_rate": 2.229424397664482e-05, + "loss": 0.1264, + "step": 248800 + }, + { + "epoch": 0.56, + "learning_rate": 2.2293125433435494e-05, + "loss": 0.1257, + "step": 248810 + }, + { + "epoch": 0.56, + "learning_rate": 2.229200689022617e-05, + "loss": 0.1269, + "step": 248820 + }, + { + "epoch": 0.56, + "learning_rate": 2.2290888347016846e-05, + "loss": 0.1231, + "step": 248830 + }, + { + "epoch": 0.56, + "learning_rate": 2.2289769803807524e-05, + "loss": 0.1287, + "step": 248840 + }, + { + "epoch": 0.56, + "learning_rate": 2.22886512605982e-05, + "loss": 0.1255, + "step": 248850 + }, + { + "epoch": 0.56, + "learning_rate": 2.2287532717388873e-05, + "loss": 0.1256, + "step": 248860 + }, + { + "epoch": 0.56, + "learning_rate": 2.2286414174179548e-05, + "loss": 0.1233, + "step": 248870 + }, + { + "epoch": 0.56, + "learning_rate": 2.2285295630970226e-05, + "loss": 0.1242, + "step": 248880 + }, + { + "epoch": 0.56, + "learning_rate": 2.22841770877609e-05, + "loss": 0.1251, + "step": 248890 + }, + { + "epoch": 0.56, + "learning_rate": 2.2283058544551578e-05, + "loss": 0.1244, + "step": 248900 + }, + { + "epoch": 0.56, + "learning_rate": 2.2281940001342253e-05, + "loss": 0.1267, + "step": 248910 + }, + { + "epoch": 0.56, + "learning_rate": 2.2280821458132927e-05, + "loss": 0.1253, + "step": 248920 + }, + { + "epoch": 0.56, + "learning_rate": 2.2279702914923605e-05, + "loss": 0.1249, + "step": 248930 + }, + { + "epoch": 0.56, + "learning_rate": 2.227858437171428e-05, + "loss": 0.1244, + "step": 248940 + }, + { + "epoch": 0.56, + "learning_rate": 2.2277465828504958e-05, + "loss": 0.1258, + "step": 248950 + }, + { + "epoch": 0.56, + "learning_rate": 2.2276347285295632e-05, + "loss": 0.1296, + "step": 248960 + }, + { + "epoch": 0.56, + "learning_rate": 2.2275228742086307e-05, + "loss": 0.1261, + "step": 248970 + }, + { + "epoch": 0.56, + "learning_rate": 2.227411019887698e-05, + "loss": 0.1239, + "step": 248980 + }, + { + "epoch": 0.56, + "learning_rate": 2.227299165566766e-05, + "loss": 0.1265, + "step": 248990 + }, + { + "epoch": 0.56, + "learning_rate": 2.2271873112458337e-05, + "loss": 0.1257, + "step": 249000 + }, + { + "epoch": 0.56, + "learning_rate": 2.2270754569249012e-05, + "loss": 0.1252, + "step": 249010 + }, + { + "epoch": 0.56, + "learning_rate": 2.2269636026039686e-05, + "loss": 0.1254, + "step": 249020 + }, + { + "epoch": 0.56, + "learning_rate": 2.226851748283036e-05, + "loss": 0.1299, + "step": 249030 + }, + { + "epoch": 0.56, + "learning_rate": 2.226739893962104e-05, + "loss": 0.1205, + "step": 249040 + }, + { + "epoch": 0.56, + "learning_rate": 2.2266280396411717e-05, + "loss": 0.1261, + "step": 249050 + }, + { + "epoch": 0.56, + "learning_rate": 2.226516185320239e-05, + "loss": 0.124, + "step": 249060 + }, + { + "epoch": 0.56, + "learning_rate": 2.2264043309993066e-05, + "loss": 0.1221, + "step": 249070 + }, + { + "epoch": 0.56, + "learning_rate": 2.226292476678374e-05, + "loss": 0.1229, + "step": 249080 + }, + { + "epoch": 0.56, + "learning_rate": 2.2261806223574418e-05, + "loss": 0.1285, + "step": 249090 + }, + { + "epoch": 0.56, + "learning_rate": 2.2260687680365093e-05, + "loss": 0.1213, + "step": 249100 + }, + { + "epoch": 0.56, + "learning_rate": 2.225956913715577e-05, + "loss": 0.1263, + "step": 249110 + }, + { + "epoch": 0.56, + "learning_rate": 2.2258450593946445e-05, + "loss": 0.1239, + "step": 249120 + }, + { + "epoch": 0.56, + "learning_rate": 2.225733205073712e-05, + "loss": 0.1257, + "step": 249130 + }, + { + "epoch": 0.56, + "learning_rate": 2.2256213507527794e-05, + "loss": 0.1247, + "step": 249140 + }, + { + "epoch": 0.56, + "learning_rate": 2.2255094964318472e-05, + "loss": 0.1285, + "step": 249150 + }, + { + "epoch": 0.56, + "learning_rate": 2.225397642110915e-05, + "loss": 0.1208, + "step": 249160 + }, + { + "epoch": 0.56, + "learning_rate": 2.2252857877899825e-05, + "loss": 0.124, + "step": 249170 + }, + { + "epoch": 0.56, + "learning_rate": 2.22517393346905e-05, + "loss": 0.1262, + "step": 249180 + }, + { + "epoch": 0.56, + "learning_rate": 2.2250620791481174e-05, + "loss": 0.119, + "step": 249190 + }, + { + "epoch": 0.56, + "learning_rate": 2.224950224827185e-05, + "loss": 0.1278, + "step": 249200 + }, + { + "epoch": 0.56, + "learning_rate": 2.224838370506253e-05, + "loss": 0.1272, + "step": 249210 + }, + { + "epoch": 0.56, + "learning_rate": 2.2247265161853204e-05, + "loss": 0.1253, + "step": 249220 + }, + { + "epoch": 0.56, + "learning_rate": 2.224614661864388e-05, + "loss": 0.1291, + "step": 249230 + }, + { + "epoch": 0.56, + "learning_rate": 2.2245028075434553e-05, + "loss": 0.124, + "step": 249240 + }, + { + "epoch": 0.56, + "learning_rate": 2.224390953222523e-05, + "loss": 0.121, + "step": 249250 + }, + { + "epoch": 0.56, + "learning_rate": 2.224279098901591e-05, + "loss": 0.1248, + "step": 249260 + }, + { + "epoch": 0.56, + "learning_rate": 2.2241672445806584e-05, + "loss": 0.1267, + "step": 249270 + }, + { + "epoch": 0.56, + "learning_rate": 2.2240553902597258e-05, + "loss": 0.128, + "step": 249280 + }, + { + "epoch": 0.56, + "learning_rate": 2.2239435359387933e-05, + "loss": 0.1275, + "step": 249290 + }, + { + "epoch": 0.56, + "learning_rate": 2.2238316816178607e-05, + "loss": 0.1243, + "step": 249300 + }, + { + "epoch": 0.56, + "learning_rate": 2.2237198272969285e-05, + "loss": 0.1276, + "step": 249310 + }, + { + "epoch": 0.56, + "learning_rate": 2.2236079729759963e-05, + "loss": 0.1268, + "step": 249320 + }, + { + "epoch": 0.56, + "learning_rate": 2.2234961186550638e-05, + "loss": 0.1237, + "step": 249330 + }, + { + "epoch": 0.56, + "learning_rate": 2.2233842643341312e-05, + "loss": 0.1268, + "step": 249340 + }, + { + "epoch": 0.56, + "learning_rate": 2.2232724100131987e-05, + "loss": 0.1239, + "step": 249350 + }, + { + "epoch": 0.56, + "learning_rate": 2.2231605556922665e-05, + "loss": 0.1272, + "step": 249360 + }, + { + "epoch": 0.56, + "learning_rate": 2.2230487013713343e-05, + "loss": 0.1235, + "step": 249370 + }, + { + "epoch": 0.56, + "learning_rate": 2.2229368470504017e-05, + "loss": 0.1276, + "step": 249380 + }, + { + "epoch": 0.56, + "learning_rate": 2.222824992729469e-05, + "loss": 0.1213, + "step": 249390 + }, + { + "epoch": 0.56, + "learning_rate": 2.2227131384085366e-05, + "loss": 0.126, + "step": 249400 + }, + { + "epoch": 0.56, + "learning_rate": 2.2226012840876044e-05, + "loss": 0.1239, + "step": 249410 + }, + { + "epoch": 0.56, + "learning_rate": 2.2224894297666722e-05, + "loss": 0.1283, + "step": 249420 + }, + { + "epoch": 0.56, + "learning_rate": 2.2223775754457397e-05, + "loss": 0.1305, + "step": 249430 + }, + { + "epoch": 0.56, + "learning_rate": 2.222265721124807e-05, + "loss": 0.1276, + "step": 249440 + }, + { + "epoch": 0.56, + "learning_rate": 2.2221538668038746e-05, + "loss": 0.1241, + "step": 249450 + }, + { + "epoch": 0.56, + "learning_rate": 2.2220420124829424e-05, + "loss": 0.1242, + "step": 249460 + }, + { + "epoch": 0.56, + "learning_rate": 2.22193015816201e-05, + "loss": 0.1259, + "step": 249470 + }, + { + "epoch": 0.56, + "learning_rate": 2.2218183038410776e-05, + "loss": 0.1163, + "step": 249480 + }, + { + "epoch": 0.56, + "learning_rate": 2.221706449520145e-05, + "loss": 0.121, + "step": 249490 + }, + { + "epoch": 0.56, + "learning_rate": 2.2215945951992125e-05, + "loss": 0.1173, + "step": 249500 + }, + { + "epoch": 0.56, + "learning_rate": 2.22148274087828e-05, + "loss": 0.1266, + "step": 249510 + }, + { + "epoch": 0.56, + "learning_rate": 2.2213708865573478e-05, + "loss": 0.1236, + "step": 249520 + }, + { + "epoch": 0.56, + "learning_rate": 2.2212590322364156e-05, + "loss": 0.1219, + "step": 249530 + }, + { + "epoch": 0.56, + "learning_rate": 2.221147177915483e-05, + "loss": 0.1246, + "step": 249540 + }, + { + "epoch": 0.56, + "learning_rate": 2.2210353235945505e-05, + "loss": 0.1243, + "step": 249550 + }, + { + "epoch": 0.56, + "learning_rate": 2.220923469273618e-05, + "loss": 0.1261, + "step": 249560 + }, + { + "epoch": 0.56, + "learning_rate": 2.2208116149526857e-05, + "loss": 0.1224, + "step": 249570 + }, + { + "epoch": 0.56, + "learning_rate": 2.2206997606317535e-05, + "loss": 0.124, + "step": 249580 + }, + { + "epoch": 0.56, + "learning_rate": 2.220587906310821e-05, + "loss": 0.1318, + "step": 249590 + }, + { + "epoch": 0.56, + "learning_rate": 2.2204760519898884e-05, + "loss": 0.1253, + "step": 249600 + }, + { + "epoch": 0.56, + "learning_rate": 2.220364197668956e-05, + "loss": 0.1258, + "step": 249610 + }, + { + "epoch": 0.56, + "learning_rate": 2.2202523433480237e-05, + "loss": 0.1224, + "step": 249620 + }, + { + "epoch": 0.56, + "learning_rate": 2.2201404890270914e-05, + "loss": 0.1231, + "step": 249630 + }, + { + "epoch": 0.56, + "learning_rate": 2.220028634706159e-05, + "loss": 0.1247, + "step": 249640 + }, + { + "epoch": 0.56, + "learning_rate": 2.2199167803852264e-05, + "loss": 0.1278, + "step": 249650 + }, + { + "epoch": 0.56, + "learning_rate": 2.2198049260642938e-05, + "loss": 0.1258, + "step": 249660 + }, + { + "epoch": 0.56, + "learning_rate": 2.2196930717433616e-05, + "loss": 0.1232, + "step": 249670 + }, + { + "epoch": 0.56, + "learning_rate": 2.2195812174224294e-05, + "loss": 0.124, + "step": 249680 + }, + { + "epoch": 0.56, + "learning_rate": 2.219469363101497e-05, + "loss": 0.1225, + "step": 249690 + }, + { + "epoch": 0.56, + "learning_rate": 2.2193575087805643e-05, + "loss": 0.1289, + "step": 249700 + }, + { + "epoch": 0.56, + "learning_rate": 2.2192456544596318e-05, + "loss": 0.1251, + "step": 249710 + }, + { + "epoch": 0.56, + "learning_rate": 2.2191338001386992e-05, + "loss": 0.1268, + "step": 249720 + }, + { + "epoch": 0.56, + "learning_rate": 2.2190219458177673e-05, + "loss": 0.1248, + "step": 249730 + }, + { + "epoch": 0.56, + "learning_rate": 2.2189100914968348e-05, + "loss": 0.1288, + "step": 249740 + }, + { + "epoch": 0.56, + "learning_rate": 2.2187982371759023e-05, + "loss": 0.1183, + "step": 249750 + }, + { + "epoch": 0.56, + "learning_rate": 2.2186863828549697e-05, + "loss": 0.1246, + "step": 249760 + }, + { + "epoch": 0.56, + "learning_rate": 2.218574528534037e-05, + "loss": 0.124, + "step": 249770 + }, + { + "epoch": 0.56, + "learning_rate": 2.218462674213105e-05, + "loss": 0.1203, + "step": 249780 + }, + { + "epoch": 0.56, + "learning_rate": 2.2183508198921727e-05, + "loss": 0.1272, + "step": 249790 + }, + { + "epoch": 0.56, + "learning_rate": 2.2182389655712402e-05, + "loss": 0.1259, + "step": 249800 + }, + { + "epoch": 0.56, + "learning_rate": 2.2181271112503077e-05, + "loss": 0.1217, + "step": 249810 + }, + { + "epoch": 0.56, + "learning_rate": 2.218015256929375e-05, + "loss": 0.1229, + "step": 249820 + }, + { + "epoch": 0.56, + "learning_rate": 2.217903402608443e-05, + "loss": 0.1188, + "step": 249830 + }, + { + "epoch": 0.56, + "learning_rate": 2.2177915482875107e-05, + "loss": 0.1224, + "step": 249840 + }, + { + "epoch": 0.56, + "learning_rate": 2.217679693966578e-05, + "loss": 0.1223, + "step": 249850 + }, + { + "epoch": 0.56, + "learning_rate": 2.2175678396456456e-05, + "loss": 0.1238, + "step": 249860 + }, + { + "epoch": 0.56, + "learning_rate": 2.217455985324713e-05, + "loss": 0.1275, + "step": 249870 + }, + { + "epoch": 0.56, + "learning_rate": 2.217344131003781e-05, + "loss": 0.1234, + "step": 249880 + }, + { + "epoch": 0.56, + "learning_rate": 2.2172322766828486e-05, + "loss": 0.129, + "step": 249890 + }, + { + "epoch": 0.56, + "learning_rate": 2.217120422361916e-05, + "loss": 0.1167, + "step": 249900 + }, + { + "epoch": 0.56, + "learning_rate": 2.2170085680409835e-05, + "loss": 0.1217, + "step": 249910 + }, + { + "epoch": 0.56, + "learning_rate": 2.216896713720051e-05, + "loss": 0.1248, + "step": 249920 + }, + { + "epoch": 0.56, + "learning_rate": 2.2167848593991185e-05, + "loss": 0.1267, + "step": 249930 + }, + { + "epoch": 0.56, + "learning_rate": 2.2166730050781862e-05, + "loss": 0.123, + "step": 249940 + }, + { + "epoch": 0.56, + "learning_rate": 2.216561150757254e-05, + "loss": 0.1277, + "step": 249950 + }, + { + "epoch": 0.56, + "learning_rate": 2.2164492964363215e-05, + "loss": 0.123, + "step": 249960 + }, + { + "epoch": 0.56, + "learning_rate": 2.216337442115389e-05, + "loss": 0.1278, + "step": 249970 + }, + { + "epoch": 0.56, + "learning_rate": 2.2162255877944564e-05, + "loss": 0.1252, + "step": 249980 + }, + { + "epoch": 0.56, + "learning_rate": 2.2161137334735242e-05, + "loss": 0.1257, + "step": 249990 + }, + { + "epoch": 0.56, + "learning_rate": 2.216001879152592e-05, + "loss": 0.1232, + "step": 250000 + }, + { + "epoch": 0.56, + "learning_rate": 2.2158900248316594e-05, + "loss": 0.125, + "step": 250010 + }, + { + "epoch": 0.56, + "learning_rate": 2.215778170510727e-05, + "loss": 0.1256, + "step": 250020 + }, + { + "epoch": 0.56, + "learning_rate": 2.2156663161897944e-05, + "loss": 0.1209, + "step": 250030 + }, + { + "epoch": 0.56, + "learning_rate": 2.215554461868862e-05, + "loss": 0.1247, + "step": 250040 + }, + { + "epoch": 0.56, + "learning_rate": 2.21544260754793e-05, + "loss": 0.1228, + "step": 250050 + }, + { + "epoch": 0.56, + "learning_rate": 2.2153307532269974e-05, + "loss": 0.122, + "step": 250060 + }, + { + "epoch": 0.56, + "learning_rate": 2.215218898906065e-05, + "loss": 0.1242, + "step": 250070 + }, + { + "epoch": 0.56, + "learning_rate": 2.2151070445851323e-05, + "loss": 0.1258, + "step": 250080 + }, + { + "epoch": 0.56, + "learning_rate": 2.2149951902642e-05, + "loss": 0.1274, + "step": 250090 + }, + { + "epoch": 0.56, + "learning_rate": 2.2148833359432675e-05, + "loss": 0.1237, + "step": 250100 + }, + { + "epoch": 0.56, + "learning_rate": 2.2147714816223353e-05, + "loss": 0.1219, + "step": 250110 + }, + { + "epoch": 0.56, + "learning_rate": 2.2146596273014028e-05, + "loss": 0.1261, + "step": 250120 + }, + { + "epoch": 0.56, + "learning_rate": 2.2145477729804702e-05, + "loss": 0.1221, + "step": 250130 + }, + { + "epoch": 0.56, + "learning_rate": 2.2144359186595377e-05, + "loss": 0.1218, + "step": 250140 + }, + { + "epoch": 0.56, + "learning_rate": 2.2143240643386055e-05, + "loss": 0.1271, + "step": 250150 + }, + { + "epoch": 0.56, + "learning_rate": 2.2142122100176733e-05, + "loss": 0.1277, + "step": 250160 + }, + { + "epoch": 0.56, + "learning_rate": 2.2141003556967407e-05, + "loss": 0.1235, + "step": 250170 + }, + { + "epoch": 0.56, + "learning_rate": 2.2139885013758082e-05, + "loss": 0.1298, + "step": 250180 + }, + { + "epoch": 0.56, + "learning_rate": 2.2138766470548756e-05, + "loss": 0.1224, + "step": 250190 + }, + { + "epoch": 0.56, + "learning_rate": 2.2137647927339434e-05, + "loss": 0.1244, + "step": 250200 + }, + { + "epoch": 0.56, + "learning_rate": 2.2136529384130112e-05, + "loss": 0.1206, + "step": 250210 + }, + { + "epoch": 0.56, + "learning_rate": 2.2135410840920787e-05, + "loss": 0.1281, + "step": 250220 + }, + { + "epoch": 0.56, + "learning_rate": 2.213429229771146e-05, + "loss": 0.125, + "step": 250230 + }, + { + "epoch": 0.56, + "learning_rate": 2.2133173754502136e-05, + "loss": 0.1243, + "step": 250240 + }, + { + "epoch": 0.56, + "learning_rate": 2.2132055211292814e-05, + "loss": 0.1196, + "step": 250250 + }, + { + "epoch": 0.56, + "learning_rate": 2.213093666808349e-05, + "loss": 0.1231, + "step": 250260 + }, + { + "epoch": 0.56, + "learning_rate": 2.2129818124874166e-05, + "loss": 0.1215, + "step": 250270 + }, + { + "epoch": 0.56, + "learning_rate": 2.212869958166484e-05, + "loss": 0.1263, + "step": 250280 + }, + { + "epoch": 0.56, + "learning_rate": 2.2127581038455515e-05, + "loss": 0.125, + "step": 250290 + }, + { + "epoch": 0.56, + "learning_rate": 2.2126462495246193e-05, + "loss": 0.1202, + "step": 250300 + }, + { + "epoch": 0.56, + "learning_rate": 2.2125343952036868e-05, + "loss": 0.124, + "step": 250310 + }, + { + "epoch": 0.56, + "learning_rate": 2.2124225408827546e-05, + "loss": 0.1264, + "step": 250320 + }, + { + "epoch": 0.56, + "learning_rate": 2.212310686561822e-05, + "loss": 0.1245, + "step": 250330 + }, + { + "epoch": 0.56, + "learning_rate": 2.2121988322408895e-05, + "loss": 0.1276, + "step": 250340 + }, + { + "epoch": 0.56, + "learning_rate": 2.2120869779199573e-05, + "loss": 0.1275, + "step": 250350 + }, + { + "epoch": 0.56, + "learning_rate": 2.2119751235990247e-05, + "loss": 0.1229, + "step": 250360 + }, + { + "epoch": 0.56, + "learning_rate": 2.2118632692780925e-05, + "loss": 0.1285, + "step": 250370 + }, + { + "epoch": 0.56, + "learning_rate": 2.21175141495716e-05, + "loss": 0.1216, + "step": 250380 + }, + { + "epoch": 0.56, + "learning_rate": 2.2116395606362274e-05, + "loss": 0.1259, + "step": 250390 + }, + { + "epoch": 0.56, + "learning_rate": 2.211527706315295e-05, + "loss": 0.1217, + "step": 250400 + }, + { + "epoch": 0.56, + "learning_rate": 2.2114158519943627e-05, + "loss": 0.1232, + "step": 250410 + }, + { + "epoch": 0.56, + "learning_rate": 2.21130399767343e-05, + "loss": 0.1197, + "step": 250420 + }, + { + "epoch": 0.56, + "learning_rate": 2.211192143352498e-05, + "loss": 0.1269, + "step": 250430 + }, + { + "epoch": 0.56, + "learning_rate": 2.2110802890315654e-05, + "loss": 0.1233, + "step": 250440 + }, + { + "epoch": 0.56, + "learning_rate": 2.210968434710633e-05, + "loss": 0.1209, + "step": 250450 + }, + { + "epoch": 0.56, + "learning_rate": 2.2108565803897006e-05, + "loss": 0.1302, + "step": 250460 + }, + { + "epoch": 0.56, + "learning_rate": 2.210744726068768e-05, + "loss": 0.1257, + "step": 250470 + }, + { + "epoch": 0.56, + "learning_rate": 2.210632871747836e-05, + "loss": 0.1236, + "step": 250480 + }, + { + "epoch": 0.56, + "learning_rate": 2.2105210174269033e-05, + "loss": 0.1276, + "step": 250490 + }, + { + "epoch": 0.56, + "learning_rate": 2.2104091631059708e-05, + "loss": 0.1271, + "step": 250500 + }, + { + "epoch": 0.56, + "learning_rate": 2.2102973087850386e-05, + "loss": 0.122, + "step": 250510 + }, + { + "epoch": 0.56, + "learning_rate": 2.210185454464106e-05, + "loss": 0.1288, + "step": 250520 + }, + { + "epoch": 0.56, + "learning_rate": 2.2100736001431738e-05, + "loss": 0.1299, + "step": 250530 + }, + { + "epoch": 0.56, + "learning_rate": 2.2099617458222413e-05, + "loss": 0.1278, + "step": 250540 + }, + { + "epoch": 0.56, + "learning_rate": 2.2098498915013087e-05, + "loss": 0.1214, + "step": 250550 + }, + { + "epoch": 0.56, + "learning_rate": 2.2097380371803765e-05, + "loss": 0.1246, + "step": 250560 + }, + { + "epoch": 0.56, + "learning_rate": 2.209626182859444e-05, + "loss": 0.1251, + "step": 250570 + }, + { + "epoch": 0.56, + "learning_rate": 2.2095143285385114e-05, + "loss": 0.1262, + "step": 250580 + }, + { + "epoch": 0.56, + "learning_rate": 2.2094024742175792e-05, + "loss": 0.1242, + "step": 250590 + }, + { + "epoch": 0.56, + "learning_rate": 2.2092906198966467e-05, + "loss": 0.1248, + "step": 250600 + }, + { + "epoch": 0.56, + "learning_rate": 2.209178765575714e-05, + "loss": 0.1251, + "step": 250610 + }, + { + "epoch": 0.56, + "learning_rate": 2.209066911254782e-05, + "loss": 0.1224, + "step": 250620 + }, + { + "epoch": 0.56, + "learning_rate": 2.2089550569338494e-05, + "loss": 0.1254, + "step": 250630 + }, + { + "epoch": 0.56, + "learning_rate": 2.2088432026129172e-05, + "loss": 0.1307, + "step": 250640 + }, + { + "epoch": 0.56, + "learning_rate": 2.2087313482919846e-05, + "loss": 0.1241, + "step": 250650 + }, + { + "epoch": 0.56, + "learning_rate": 2.208619493971052e-05, + "loss": 0.1241, + "step": 250660 + }, + { + "epoch": 0.56, + "learning_rate": 2.20850763965012e-05, + "loss": 0.1222, + "step": 250670 + }, + { + "epoch": 0.56, + "learning_rate": 2.2083957853291873e-05, + "loss": 0.1225, + "step": 250680 + }, + { + "epoch": 0.56, + "learning_rate": 2.208283931008255e-05, + "loss": 0.1252, + "step": 250690 + }, + { + "epoch": 0.56, + "learning_rate": 2.2081720766873226e-05, + "loss": 0.1242, + "step": 250700 + }, + { + "epoch": 0.56, + "learning_rate": 2.20806022236639e-05, + "loss": 0.122, + "step": 250710 + }, + { + "epoch": 0.56, + "learning_rate": 2.2079483680454578e-05, + "loss": 0.1223, + "step": 250720 + }, + { + "epoch": 0.56, + "learning_rate": 2.2078365137245253e-05, + "loss": 0.1248, + "step": 250730 + }, + { + "epoch": 0.56, + "learning_rate": 2.2077246594035927e-05, + "loss": 0.1249, + "step": 250740 + }, + { + "epoch": 0.56, + "learning_rate": 2.2076128050826605e-05, + "loss": 0.1274, + "step": 250750 + }, + { + "epoch": 0.56, + "learning_rate": 2.207500950761728e-05, + "loss": 0.1259, + "step": 250760 + }, + { + "epoch": 0.56, + "learning_rate": 2.2073890964407958e-05, + "loss": 0.1272, + "step": 250770 + }, + { + "epoch": 0.56, + "learning_rate": 2.2072772421198632e-05, + "loss": 0.1235, + "step": 250780 + }, + { + "epoch": 0.56, + "learning_rate": 2.2071653877989307e-05, + "loss": 0.1255, + "step": 250790 + }, + { + "epoch": 0.56, + "learning_rate": 2.2070535334779985e-05, + "loss": 0.1233, + "step": 250800 + }, + { + "epoch": 0.56, + "learning_rate": 2.206941679157066e-05, + "loss": 0.1185, + "step": 250810 + }, + { + "epoch": 0.56, + "learning_rate": 2.2068298248361334e-05, + "loss": 0.1268, + "step": 250820 + }, + { + "epoch": 0.56, + "learning_rate": 2.2067179705152012e-05, + "loss": 0.1258, + "step": 250830 + }, + { + "epoch": 0.56, + "learning_rate": 2.2066061161942686e-05, + "loss": 0.1254, + "step": 250840 + }, + { + "epoch": 0.56, + "learning_rate": 2.2064942618733364e-05, + "loss": 0.1225, + "step": 250850 + }, + { + "epoch": 0.56, + "learning_rate": 2.206382407552404e-05, + "loss": 0.124, + "step": 250860 + }, + { + "epoch": 0.56, + "learning_rate": 2.2062705532314713e-05, + "loss": 0.1294, + "step": 250870 + }, + { + "epoch": 0.56, + "learning_rate": 2.206158698910539e-05, + "loss": 0.1243, + "step": 250880 + }, + { + "epoch": 0.56, + "learning_rate": 2.2060468445896066e-05, + "loss": 0.1274, + "step": 250890 + }, + { + "epoch": 0.56, + "learning_rate": 2.205934990268674e-05, + "loss": 0.1256, + "step": 250900 + }, + { + "epoch": 0.56, + "learning_rate": 2.2058231359477418e-05, + "loss": 0.125, + "step": 250910 + }, + { + "epoch": 0.56, + "learning_rate": 2.2057112816268093e-05, + "loss": 0.1231, + "step": 250920 + }, + { + "epoch": 0.56, + "learning_rate": 2.205599427305877e-05, + "loss": 0.1228, + "step": 250930 + }, + { + "epoch": 0.56, + "learning_rate": 2.2054875729849445e-05, + "loss": 0.1304, + "step": 250940 + }, + { + "epoch": 0.56, + "learning_rate": 2.205375718664012e-05, + "loss": 0.1275, + "step": 250950 + }, + { + "epoch": 0.56, + "learning_rate": 2.2052638643430798e-05, + "loss": 0.1267, + "step": 250960 + }, + { + "epoch": 0.56, + "learning_rate": 2.2051520100221472e-05, + "loss": 0.1247, + "step": 250970 + }, + { + "epoch": 0.56, + "learning_rate": 2.205040155701215e-05, + "loss": 0.1231, + "step": 250980 + }, + { + "epoch": 0.56, + "learning_rate": 2.2049283013802825e-05, + "loss": 0.1277, + "step": 250990 + }, + { + "epoch": 0.56, + "learning_rate": 2.20481644705935e-05, + "loss": 0.1252, + "step": 251000 + }, + { + "epoch": 0.56, + "learning_rate": 2.2047045927384177e-05, + "loss": 0.1246, + "step": 251010 + }, + { + "epoch": 0.56, + "learning_rate": 2.204592738417485e-05, + "loss": 0.1264, + "step": 251020 + }, + { + "epoch": 0.56, + "learning_rate": 2.2044808840965526e-05, + "loss": 0.1316, + "step": 251030 + }, + { + "epoch": 0.56, + "learning_rate": 2.2043690297756204e-05, + "loss": 0.1243, + "step": 251040 + }, + { + "epoch": 0.56, + "learning_rate": 2.204257175454688e-05, + "loss": 0.1241, + "step": 251050 + }, + { + "epoch": 0.56, + "learning_rate": 2.2041453211337553e-05, + "loss": 0.1252, + "step": 251060 + }, + { + "epoch": 0.56, + "learning_rate": 2.204033466812823e-05, + "loss": 0.1275, + "step": 251070 + }, + { + "epoch": 0.56, + "learning_rate": 2.2039216124918906e-05, + "loss": 0.122, + "step": 251080 + }, + { + "epoch": 0.56, + "learning_rate": 2.2038097581709584e-05, + "loss": 0.1274, + "step": 251090 + }, + { + "epoch": 0.56, + "learning_rate": 2.2036979038500258e-05, + "loss": 0.1274, + "step": 251100 + }, + { + "epoch": 0.56, + "learning_rate": 2.2035860495290933e-05, + "loss": 0.1238, + "step": 251110 + }, + { + "epoch": 0.56, + "learning_rate": 2.203474195208161e-05, + "loss": 0.1278, + "step": 251120 + }, + { + "epoch": 0.56, + "learning_rate": 2.2033623408872285e-05, + "loss": 0.126, + "step": 251130 + }, + { + "epoch": 0.56, + "learning_rate": 2.2032504865662963e-05, + "loss": 0.1273, + "step": 251140 + }, + { + "epoch": 0.56, + "learning_rate": 2.2031386322453638e-05, + "loss": 0.1202, + "step": 251150 + }, + { + "epoch": 0.56, + "learning_rate": 2.2030267779244312e-05, + "loss": 0.1243, + "step": 251160 + }, + { + "epoch": 0.56, + "learning_rate": 2.2029149236034987e-05, + "loss": 0.1186, + "step": 251170 + }, + { + "epoch": 0.56, + "learning_rate": 2.2028030692825665e-05, + "loss": 0.1223, + "step": 251180 + }, + { + "epoch": 0.56, + "learning_rate": 2.2026912149616343e-05, + "loss": 0.126, + "step": 251190 + }, + { + "epoch": 0.56, + "learning_rate": 2.2025793606407017e-05, + "loss": 0.1297, + "step": 251200 + }, + { + "epoch": 0.56, + "learning_rate": 2.202467506319769e-05, + "loss": 0.1237, + "step": 251210 + }, + { + "epoch": 0.56, + "learning_rate": 2.2023556519988366e-05, + "loss": 0.1258, + "step": 251220 + }, + { + "epoch": 0.56, + "learning_rate": 2.2022437976779044e-05, + "loss": 0.1229, + "step": 251230 + }, + { + "epoch": 0.56, + "learning_rate": 2.2021319433569722e-05, + "loss": 0.1235, + "step": 251240 + }, + { + "epoch": 0.56, + "learning_rate": 2.2020200890360397e-05, + "loss": 0.1241, + "step": 251250 + }, + { + "epoch": 0.56, + "learning_rate": 2.201908234715107e-05, + "loss": 0.1255, + "step": 251260 + }, + { + "epoch": 0.56, + "learning_rate": 2.2017963803941746e-05, + "loss": 0.123, + "step": 251270 + }, + { + "epoch": 0.56, + "learning_rate": 2.2016845260732424e-05, + "loss": 0.1234, + "step": 251280 + }, + { + "epoch": 0.56, + "learning_rate": 2.2015726717523098e-05, + "loss": 0.1256, + "step": 251290 + }, + { + "epoch": 0.56, + "learning_rate": 2.2014608174313776e-05, + "loss": 0.1211, + "step": 251300 + }, + { + "epoch": 0.56, + "learning_rate": 2.201348963110445e-05, + "loss": 0.1269, + "step": 251310 + }, + { + "epoch": 0.56, + "learning_rate": 2.2012371087895125e-05, + "loss": 0.1278, + "step": 251320 + }, + { + "epoch": 0.56, + "learning_rate": 2.20112525446858e-05, + "loss": 0.1279, + "step": 251330 + }, + { + "epoch": 0.56, + "learning_rate": 2.2010134001476478e-05, + "loss": 0.1258, + "step": 251340 + }, + { + "epoch": 0.56, + "learning_rate": 2.2009015458267156e-05, + "loss": 0.1313, + "step": 251350 + }, + { + "epoch": 0.56, + "learning_rate": 2.200789691505783e-05, + "loss": 0.1225, + "step": 251360 + }, + { + "epoch": 0.56, + "learning_rate": 2.2006778371848505e-05, + "loss": 0.1252, + "step": 251370 + }, + { + "epoch": 0.56, + "learning_rate": 2.200565982863918e-05, + "loss": 0.1238, + "step": 251380 + }, + { + "epoch": 0.56, + "learning_rate": 2.2004541285429857e-05, + "loss": 0.1195, + "step": 251390 + }, + { + "epoch": 0.56, + "learning_rate": 2.2003422742220535e-05, + "loss": 0.129, + "step": 251400 + }, + { + "epoch": 0.56, + "learning_rate": 2.200230419901121e-05, + "loss": 0.125, + "step": 251410 + }, + { + "epoch": 0.56, + "learning_rate": 2.2001185655801884e-05, + "loss": 0.1216, + "step": 251420 + }, + { + "epoch": 0.56, + "learning_rate": 2.200006711259256e-05, + "loss": 0.1261, + "step": 251430 + }, + { + "epoch": 0.56, + "learning_rate": 2.1998948569383237e-05, + "loss": 0.1292, + "step": 251440 + }, + { + "epoch": 0.56, + "learning_rate": 2.1997830026173914e-05, + "loss": 0.1267, + "step": 251450 + }, + { + "epoch": 0.56, + "learning_rate": 2.199671148296459e-05, + "loss": 0.1227, + "step": 251460 + }, + { + "epoch": 0.56, + "learning_rate": 2.1995592939755264e-05, + "loss": 0.1214, + "step": 251470 + }, + { + "epoch": 0.56, + "learning_rate": 2.1994474396545938e-05, + "loss": 0.1269, + "step": 251480 + }, + { + "epoch": 0.56, + "learning_rate": 2.1993355853336613e-05, + "loss": 0.1216, + "step": 251490 + }, + { + "epoch": 0.56, + "learning_rate": 2.199223731012729e-05, + "loss": 0.1238, + "step": 251500 + }, + { + "epoch": 0.56, + "learning_rate": 2.199111876691797e-05, + "loss": 0.1247, + "step": 251510 + }, + { + "epoch": 0.56, + "learning_rate": 2.1990000223708643e-05, + "loss": 0.1263, + "step": 251520 + }, + { + "epoch": 0.56, + "learning_rate": 2.1988881680499318e-05, + "loss": 0.1251, + "step": 251530 + }, + { + "epoch": 0.56, + "learning_rate": 2.1987763137289992e-05, + "loss": 0.1258, + "step": 251540 + }, + { + "epoch": 0.56, + "learning_rate": 2.198664459408067e-05, + "loss": 0.121, + "step": 251550 + }, + { + "epoch": 0.56, + "learning_rate": 2.1985526050871348e-05, + "loss": 0.1244, + "step": 251560 + }, + { + "epoch": 0.56, + "learning_rate": 2.1984407507662022e-05, + "loss": 0.1199, + "step": 251570 + }, + { + "epoch": 0.56, + "learning_rate": 2.1983288964452697e-05, + "loss": 0.1226, + "step": 251580 + }, + { + "epoch": 0.56, + "learning_rate": 2.198217042124337e-05, + "loss": 0.1247, + "step": 251590 + }, + { + "epoch": 0.56, + "learning_rate": 2.198105187803405e-05, + "loss": 0.1167, + "step": 251600 + }, + { + "epoch": 0.56, + "learning_rate": 2.1979933334824727e-05, + "loss": 0.1251, + "step": 251610 + }, + { + "epoch": 0.56, + "learning_rate": 2.1978814791615402e-05, + "loss": 0.1232, + "step": 251620 + }, + { + "epoch": 0.56, + "learning_rate": 2.1977696248406077e-05, + "loss": 0.1266, + "step": 251630 + }, + { + "epoch": 0.56, + "learning_rate": 2.197657770519675e-05, + "loss": 0.1283, + "step": 251640 + }, + { + "epoch": 0.56, + "learning_rate": 2.1975459161987426e-05, + "loss": 0.1271, + "step": 251650 + }, + { + "epoch": 0.56, + "learning_rate": 2.1974340618778107e-05, + "loss": 0.1234, + "step": 251660 + }, + { + "epoch": 0.56, + "learning_rate": 2.197322207556878e-05, + "loss": 0.1271, + "step": 251670 + }, + { + "epoch": 0.56, + "learning_rate": 2.1972103532359456e-05, + "loss": 0.1239, + "step": 251680 + }, + { + "epoch": 0.56, + "learning_rate": 2.197098498915013e-05, + "loss": 0.1209, + "step": 251690 + }, + { + "epoch": 0.56, + "learning_rate": 2.1969866445940805e-05, + "loss": 0.1297, + "step": 251700 + }, + { + "epoch": 0.56, + "learning_rate": 2.1968747902731483e-05, + "loss": 0.1184, + "step": 251710 + }, + { + "epoch": 0.56, + "learning_rate": 2.196762935952216e-05, + "loss": 0.1255, + "step": 251720 + }, + { + "epoch": 0.56, + "learning_rate": 2.1966510816312835e-05, + "loss": 0.1275, + "step": 251730 + }, + { + "epoch": 0.56, + "learning_rate": 2.196539227310351e-05, + "loss": 0.1268, + "step": 251740 + }, + { + "epoch": 0.56, + "learning_rate": 2.1964273729894185e-05, + "loss": 0.1245, + "step": 251750 + }, + { + "epoch": 0.56, + "learning_rate": 2.1963155186684862e-05, + "loss": 0.1259, + "step": 251760 + }, + { + "epoch": 0.56, + "learning_rate": 2.196203664347554e-05, + "loss": 0.1203, + "step": 251770 + }, + { + "epoch": 0.56, + "learning_rate": 2.1960918100266215e-05, + "loss": 0.1262, + "step": 251780 + }, + { + "epoch": 0.56, + "learning_rate": 2.195979955705689e-05, + "loss": 0.119, + "step": 251790 + }, + { + "epoch": 0.56, + "learning_rate": 2.1958681013847564e-05, + "loss": 0.1203, + "step": 251800 + }, + { + "epoch": 0.56, + "learning_rate": 2.1957562470638242e-05, + "loss": 0.1237, + "step": 251810 + }, + { + "epoch": 0.56, + "learning_rate": 2.195644392742892e-05, + "loss": 0.121, + "step": 251820 + }, + { + "epoch": 0.56, + "learning_rate": 2.1955325384219594e-05, + "loss": 0.1219, + "step": 251830 + }, + { + "epoch": 0.56, + "learning_rate": 2.195420684101027e-05, + "loss": 0.1229, + "step": 251840 + }, + { + "epoch": 0.56, + "learning_rate": 2.1953088297800943e-05, + "loss": 0.1253, + "step": 251850 + }, + { + "epoch": 0.56, + "learning_rate": 2.195196975459162e-05, + "loss": 0.1283, + "step": 251860 + }, + { + "epoch": 0.56, + "learning_rate": 2.19508512113823e-05, + "loss": 0.1225, + "step": 251870 + }, + { + "epoch": 0.56, + "learning_rate": 2.1949732668172974e-05, + "loss": 0.1247, + "step": 251880 + }, + { + "epoch": 0.56, + "learning_rate": 2.194861412496365e-05, + "loss": 0.1244, + "step": 251890 + }, + { + "epoch": 0.56, + "learning_rate": 2.1947495581754323e-05, + "loss": 0.1267, + "step": 251900 + }, + { + "epoch": 0.56, + "learning_rate": 2.1946377038544998e-05, + "loss": 0.127, + "step": 251910 + }, + { + "epoch": 0.56, + "learning_rate": 2.194525849533568e-05, + "loss": 0.1237, + "step": 251920 + }, + { + "epoch": 0.56, + "learning_rate": 2.1944139952126353e-05, + "loss": 0.1255, + "step": 251930 + }, + { + "epoch": 0.56, + "learning_rate": 2.1943021408917028e-05, + "loss": 0.1213, + "step": 251940 + }, + { + "epoch": 0.56, + "learning_rate": 2.1941902865707702e-05, + "loss": 0.1227, + "step": 251950 + }, + { + "epoch": 0.56, + "learning_rate": 2.1940784322498377e-05, + "loss": 0.1276, + "step": 251960 + }, + { + "epoch": 0.56, + "learning_rate": 2.1939665779289055e-05, + "loss": 0.1263, + "step": 251970 + }, + { + "epoch": 0.56, + "learning_rate": 2.1938547236079733e-05, + "loss": 0.1275, + "step": 251980 + }, + { + "epoch": 0.56, + "learning_rate": 2.1937428692870407e-05, + "loss": 0.1206, + "step": 251990 + }, + { + "epoch": 0.56, + "learning_rate": 2.1936310149661082e-05, + "loss": 0.1293, + "step": 252000 + }, + { + "epoch": 0.56, + "learning_rate": 2.1935191606451756e-05, + "loss": 0.1278, + "step": 252010 + }, + { + "epoch": 0.56, + "learning_rate": 2.1934073063242434e-05, + "loss": 0.1306, + "step": 252020 + }, + { + "epoch": 0.56, + "learning_rate": 2.1932954520033112e-05, + "loss": 0.1227, + "step": 252030 + }, + { + "epoch": 0.56, + "learning_rate": 2.1931835976823787e-05, + "loss": 0.1227, + "step": 252040 + }, + { + "epoch": 0.56, + "learning_rate": 2.193071743361446e-05, + "loss": 0.1259, + "step": 252050 + }, + { + "epoch": 0.56, + "learning_rate": 2.1929598890405136e-05, + "loss": 0.1235, + "step": 252060 + }, + { + "epoch": 0.56, + "learning_rate": 2.1928480347195814e-05, + "loss": 0.1261, + "step": 252070 + }, + { + "epoch": 0.56, + "learning_rate": 2.1927361803986492e-05, + "loss": 0.117, + "step": 252080 + }, + { + "epoch": 0.56, + "learning_rate": 2.1926243260777166e-05, + "loss": 0.1209, + "step": 252090 + }, + { + "epoch": 0.56, + "learning_rate": 2.192512471756784e-05, + "loss": 0.123, + "step": 252100 + }, + { + "epoch": 0.56, + "learning_rate": 2.1924006174358515e-05, + "loss": 0.1211, + "step": 252110 + }, + { + "epoch": 0.56, + "learning_rate": 2.192288763114919e-05, + "loss": 0.1308, + "step": 252120 + }, + { + "epoch": 0.56, + "learning_rate": 2.1921769087939868e-05, + "loss": 0.1207, + "step": 252130 + }, + { + "epoch": 0.56, + "learning_rate": 2.1920650544730546e-05, + "loss": 0.1289, + "step": 252140 + }, + { + "epoch": 0.56, + "learning_rate": 2.191953200152122e-05, + "loss": 0.1237, + "step": 252150 + }, + { + "epoch": 0.56, + "learning_rate": 2.1918413458311895e-05, + "loss": 0.1249, + "step": 252160 + }, + { + "epoch": 0.56, + "learning_rate": 2.191729491510257e-05, + "loss": 0.1264, + "step": 252170 + }, + { + "epoch": 0.56, + "learning_rate": 2.1916176371893247e-05, + "loss": 0.1185, + "step": 252180 + }, + { + "epoch": 0.56, + "learning_rate": 2.1915057828683925e-05, + "loss": 0.1225, + "step": 252190 + }, + { + "epoch": 0.56, + "learning_rate": 2.19139392854746e-05, + "loss": 0.1256, + "step": 252200 + }, + { + "epoch": 0.56, + "learning_rate": 2.1912820742265274e-05, + "loss": 0.1253, + "step": 252210 + }, + { + "epoch": 0.56, + "learning_rate": 2.191170219905595e-05, + "loss": 0.1239, + "step": 252220 + }, + { + "epoch": 0.56, + "learning_rate": 2.1910583655846627e-05, + "loss": 0.1197, + "step": 252230 + }, + { + "epoch": 0.56, + "learning_rate": 2.1909576966958236e-05, + "loss": 0.1238, + "step": 252240 + }, + { + "epoch": 0.56, + "learning_rate": 2.190845842374891e-05, + "loss": 0.1208, + "step": 252250 + }, + { + "epoch": 0.56, + "learning_rate": 2.1907339880539588e-05, + "loss": 0.1233, + "step": 252260 + }, + { + "epoch": 0.56, + "learning_rate": 2.1906221337330263e-05, + "loss": 0.1233, + "step": 252270 + }, + { + "epoch": 0.56, + "learning_rate": 2.1905102794120937e-05, + "loss": 0.1228, + "step": 252280 + }, + { + "epoch": 0.56, + "learning_rate": 2.190398425091161e-05, + "loss": 0.1287, + "step": 252290 + }, + { + "epoch": 0.56, + "learning_rate": 2.190286570770229e-05, + "loss": 0.1266, + "step": 252300 + }, + { + "epoch": 0.56, + "learning_rate": 2.1901747164492968e-05, + "loss": 0.1257, + "step": 252310 + }, + { + "epoch": 0.56, + "learning_rate": 2.1900628621283642e-05, + "loss": 0.1247, + "step": 252320 + }, + { + "epoch": 0.56, + "learning_rate": 2.1899510078074317e-05, + "loss": 0.1229, + "step": 252330 + }, + { + "epoch": 0.56, + "learning_rate": 2.189839153486499e-05, + "loss": 0.1315, + "step": 252340 + }, + { + "epoch": 0.56, + "learning_rate": 2.189727299165567e-05, + "loss": 0.1227, + "step": 252350 + }, + { + "epoch": 0.56, + "learning_rate": 2.1896154448446344e-05, + "loss": 0.1238, + "step": 252360 + }, + { + "epoch": 0.56, + "learning_rate": 2.189503590523702e-05, + "loss": 0.126, + "step": 252370 + }, + { + "epoch": 0.56, + "learning_rate": 2.1893917362027696e-05, + "loss": 0.128, + "step": 252380 + }, + { + "epoch": 0.56, + "learning_rate": 2.189279881881837e-05, + "loss": 0.1277, + "step": 252390 + }, + { + "epoch": 0.56, + "learning_rate": 2.189168027560905e-05, + "loss": 0.1261, + "step": 252400 + }, + { + "epoch": 0.56, + "learning_rate": 2.1890561732399723e-05, + "loss": 0.1263, + "step": 252410 + }, + { + "epoch": 0.56, + "learning_rate": 2.18894431891904e-05, + "loss": 0.1216, + "step": 252420 + }, + { + "epoch": 0.56, + "learning_rate": 2.1888324645981076e-05, + "loss": 0.1257, + "step": 252430 + }, + { + "epoch": 0.56, + "learning_rate": 2.188720610277175e-05, + "loss": 0.1215, + "step": 252440 + }, + { + "epoch": 0.56, + "learning_rate": 2.1886087559562428e-05, + "loss": 0.1248, + "step": 252450 + }, + { + "epoch": 0.56, + "learning_rate": 2.1884969016353103e-05, + "loss": 0.1209, + "step": 252460 + }, + { + "epoch": 0.56, + "learning_rate": 2.188385047314378e-05, + "loss": 0.1276, + "step": 252470 + }, + { + "epoch": 0.56, + "learning_rate": 2.1882731929934455e-05, + "loss": 0.1256, + "step": 252480 + }, + { + "epoch": 0.56, + "learning_rate": 2.188161338672513e-05, + "loss": 0.1246, + "step": 252490 + }, + { + "epoch": 0.56, + "learning_rate": 2.1880494843515804e-05, + "loss": 0.124, + "step": 252500 + }, + { + "epoch": 0.56, + "learning_rate": 2.1879376300306482e-05, + "loss": 0.1256, + "step": 252510 + }, + { + "epoch": 0.56, + "learning_rate": 2.1878257757097157e-05, + "loss": 0.1263, + "step": 252520 + }, + { + "epoch": 0.56, + "learning_rate": 2.1877139213887835e-05, + "loss": 0.1246, + "step": 252530 + }, + { + "epoch": 0.56, + "learning_rate": 2.187602067067851e-05, + "loss": 0.1285, + "step": 252540 + }, + { + "epoch": 0.56, + "learning_rate": 2.1874902127469184e-05, + "loss": 0.1254, + "step": 252550 + }, + { + "epoch": 0.56, + "learning_rate": 2.187378358425986e-05, + "loss": 0.1217, + "step": 252560 + }, + { + "epoch": 0.56, + "learning_rate": 2.1872665041050536e-05, + "loss": 0.1251, + "step": 252570 + }, + { + "epoch": 0.56, + "learning_rate": 2.1871546497841214e-05, + "loss": 0.128, + "step": 252580 + }, + { + "epoch": 0.56, + "learning_rate": 2.187042795463189e-05, + "loss": 0.1208, + "step": 252590 + }, + { + "epoch": 0.56, + "learning_rate": 2.1869309411422563e-05, + "loss": 0.1244, + "step": 252600 + }, + { + "epoch": 0.56, + "learning_rate": 2.186819086821324e-05, + "loss": 0.1277, + "step": 252610 + }, + { + "epoch": 0.56, + "learning_rate": 2.1867072325003916e-05, + "loss": 0.1233, + "step": 252620 + }, + { + "epoch": 0.56, + "learning_rate": 2.1865953781794593e-05, + "loss": 0.1217, + "step": 252630 + }, + { + "epoch": 0.56, + "learning_rate": 2.1864835238585268e-05, + "loss": 0.1246, + "step": 252640 + }, + { + "epoch": 0.56, + "learning_rate": 2.1863716695375943e-05, + "loss": 0.1246, + "step": 252650 + }, + { + "epoch": 0.56, + "learning_rate": 2.186259815216662e-05, + "loss": 0.1265, + "step": 252660 + }, + { + "epoch": 0.56, + "learning_rate": 2.1861479608957295e-05, + "loss": 0.1235, + "step": 252670 + }, + { + "epoch": 0.56, + "learning_rate": 2.186036106574797e-05, + "loss": 0.1194, + "step": 252680 + }, + { + "epoch": 0.56, + "learning_rate": 2.1859242522538647e-05, + "loss": 0.1225, + "step": 252690 + }, + { + "epoch": 0.56, + "learning_rate": 2.1858123979329322e-05, + "loss": 0.1231, + "step": 252700 + }, + { + "epoch": 0.56, + "learning_rate": 2.185700543612e-05, + "loss": 0.1262, + "step": 252710 + }, + { + "epoch": 0.56, + "learning_rate": 2.1855886892910674e-05, + "loss": 0.1245, + "step": 252720 + }, + { + "epoch": 0.56, + "learning_rate": 2.185476834970135e-05, + "loss": 0.121, + "step": 252730 + }, + { + "epoch": 0.56, + "learning_rate": 2.1853649806492027e-05, + "loss": 0.1275, + "step": 252740 + }, + { + "epoch": 0.56, + "learning_rate": 2.18525312632827e-05, + "loss": 0.1205, + "step": 252750 + }, + { + "epoch": 0.56, + "learning_rate": 2.1851412720073376e-05, + "loss": 0.1249, + "step": 252760 + }, + { + "epoch": 0.56, + "learning_rate": 2.1850294176864054e-05, + "loss": 0.1242, + "step": 252770 + }, + { + "epoch": 0.56, + "learning_rate": 2.184917563365473e-05, + "loss": 0.1249, + "step": 252780 + }, + { + "epoch": 0.56, + "learning_rate": 2.1848057090445406e-05, + "loss": 0.1313, + "step": 252790 + }, + { + "epoch": 0.56, + "learning_rate": 2.184693854723608e-05, + "loss": 0.1184, + "step": 252800 + }, + { + "epoch": 0.56, + "learning_rate": 2.1845820004026755e-05, + "loss": 0.1244, + "step": 252810 + }, + { + "epoch": 0.56, + "learning_rate": 2.1844701460817433e-05, + "loss": 0.1316, + "step": 252820 + }, + { + "epoch": 0.56, + "learning_rate": 2.1843582917608108e-05, + "loss": 0.1293, + "step": 252830 + }, + { + "epoch": 0.56, + "learning_rate": 2.1842464374398783e-05, + "loss": 0.1219, + "step": 252840 + }, + { + "epoch": 0.56, + "learning_rate": 2.184134583118946e-05, + "loss": 0.1241, + "step": 252850 + }, + { + "epoch": 0.56, + "learning_rate": 2.1840227287980135e-05, + "loss": 0.1246, + "step": 252860 + }, + { + "epoch": 0.56, + "learning_rate": 2.1839108744770813e-05, + "loss": 0.1324, + "step": 252870 + }, + { + "epoch": 0.56, + "learning_rate": 2.1837990201561487e-05, + "loss": 0.1243, + "step": 252880 + }, + { + "epoch": 0.56, + "learning_rate": 2.1836871658352162e-05, + "loss": 0.1274, + "step": 252890 + }, + { + "epoch": 0.56, + "learning_rate": 2.183575311514284e-05, + "loss": 0.1242, + "step": 252900 + }, + { + "epoch": 0.56, + "learning_rate": 2.1834634571933514e-05, + "loss": 0.124, + "step": 252910 + }, + { + "epoch": 0.56, + "learning_rate": 2.1833516028724192e-05, + "loss": 0.1267, + "step": 252920 + }, + { + "epoch": 0.56, + "learning_rate": 2.1832397485514867e-05, + "loss": 0.1236, + "step": 252930 + }, + { + "epoch": 0.56, + "learning_rate": 2.183127894230554e-05, + "loss": 0.1256, + "step": 252940 + }, + { + "epoch": 0.56, + "learning_rate": 2.183016039909622e-05, + "loss": 0.1205, + "step": 252950 + }, + { + "epoch": 0.56, + "learning_rate": 2.1829041855886894e-05, + "loss": 0.1228, + "step": 252960 + }, + { + "epoch": 0.56, + "learning_rate": 2.182792331267757e-05, + "loss": 0.1235, + "step": 252970 + }, + { + "epoch": 0.56, + "learning_rate": 2.1826804769468246e-05, + "loss": 0.1247, + "step": 252980 + }, + { + "epoch": 0.56, + "learning_rate": 2.182568622625892e-05, + "loss": 0.1291, + "step": 252990 + }, + { + "epoch": 0.56, + "learning_rate": 2.1824567683049595e-05, + "loss": 0.1216, + "step": 253000 + }, + { + "epoch": 0.56, + "learning_rate": 2.1823449139840273e-05, + "loss": 0.1248, + "step": 253010 + }, + { + "epoch": 0.56, + "learning_rate": 2.1822330596630948e-05, + "loss": 0.1271, + "step": 253020 + }, + { + "epoch": 0.56, + "learning_rate": 2.1821212053421626e-05, + "loss": 0.1245, + "step": 253030 + }, + { + "epoch": 0.56, + "learning_rate": 2.18200935102123e-05, + "loss": 0.1196, + "step": 253040 + }, + { + "epoch": 0.56, + "learning_rate": 2.1818974967002975e-05, + "loss": 0.1235, + "step": 253050 + }, + { + "epoch": 0.56, + "learning_rate": 2.1817856423793653e-05, + "loss": 0.1231, + "step": 253060 + }, + { + "epoch": 0.56, + "learning_rate": 2.1816737880584327e-05, + "loss": 0.1274, + "step": 253070 + }, + { + "epoch": 0.56, + "learning_rate": 2.1815619337375005e-05, + "loss": 0.1228, + "step": 253080 + }, + { + "epoch": 0.56, + "learning_rate": 2.181450079416568e-05, + "loss": 0.1262, + "step": 253090 + }, + { + "epoch": 0.56, + "learning_rate": 2.1813382250956354e-05, + "loss": 0.1252, + "step": 253100 + }, + { + "epoch": 0.56, + "learning_rate": 2.1812263707747032e-05, + "loss": 0.1269, + "step": 253110 + }, + { + "epoch": 0.56, + "learning_rate": 2.1811145164537707e-05, + "loss": 0.123, + "step": 253120 + }, + { + "epoch": 0.57, + "learning_rate": 2.1810026621328385e-05, + "loss": 0.1244, + "step": 253130 + }, + { + "epoch": 0.57, + "learning_rate": 2.180890807811906e-05, + "loss": 0.1218, + "step": 253140 + }, + { + "epoch": 0.57, + "learning_rate": 2.1807789534909734e-05, + "loss": 0.1255, + "step": 253150 + }, + { + "epoch": 0.57, + "learning_rate": 2.180667099170041e-05, + "loss": 0.1262, + "step": 253160 + }, + { + "epoch": 0.57, + "learning_rate": 2.1805552448491086e-05, + "loss": 0.1232, + "step": 253170 + }, + { + "epoch": 0.57, + "learning_rate": 2.180443390528176e-05, + "loss": 0.1255, + "step": 253180 + }, + { + "epoch": 0.57, + "learning_rate": 2.180331536207244e-05, + "loss": 0.1256, + "step": 253190 + }, + { + "epoch": 0.57, + "learning_rate": 2.1802196818863113e-05, + "loss": 0.1215, + "step": 253200 + }, + { + "epoch": 0.57, + "learning_rate": 2.1801078275653788e-05, + "loss": 0.1246, + "step": 253210 + }, + { + "epoch": 0.57, + "learning_rate": 2.1799959732444466e-05, + "loss": 0.1238, + "step": 253220 + }, + { + "epoch": 0.57, + "learning_rate": 2.179884118923514e-05, + "loss": 0.1223, + "step": 253230 + }, + { + "epoch": 0.57, + "learning_rate": 2.1797722646025818e-05, + "loss": 0.121, + "step": 253240 + }, + { + "epoch": 0.57, + "learning_rate": 2.1796604102816493e-05, + "loss": 0.1226, + "step": 253250 + }, + { + "epoch": 0.57, + "learning_rate": 2.1795485559607167e-05, + "loss": 0.1232, + "step": 253260 + }, + { + "epoch": 0.57, + "learning_rate": 2.1794367016397845e-05, + "loss": 0.1231, + "step": 253270 + }, + { + "epoch": 0.57, + "learning_rate": 2.179324847318852e-05, + "loss": 0.1223, + "step": 253280 + }, + { + "epoch": 0.57, + "learning_rate": 2.1792129929979198e-05, + "loss": 0.122, + "step": 253290 + }, + { + "epoch": 0.57, + "learning_rate": 2.1791011386769872e-05, + "loss": 0.122, + "step": 253300 + }, + { + "epoch": 0.57, + "learning_rate": 2.1789892843560547e-05, + "loss": 0.125, + "step": 253310 + }, + { + "epoch": 0.57, + "learning_rate": 2.178877430035122e-05, + "loss": 0.1233, + "step": 253320 + }, + { + "epoch": 0.57, + "learning_rate": 2.17876557571419e-05, + "loss": 0.1232, + "step": 253330 + }, + { + "epoch": 0.57, + "learning_rate": 2.1786537213932577e-05, + "loss": 0.1212, + "step": 253340 + }, + { + "epoch": 0.57, + "learning_rate": 2.1785418670723252e-05, + "loss": 0.1268, + "step": 253350 + }, + { + "epoch": 0.57, + "learning_rate": 2.1784300127513926e-05, + "loss": 0.1223, + "step": 253360 + }, + { + "epoch": 0.57, + "learning_rate": 2.17831815843046e-05, + "loss": 0.1217, + "step": 253370 + }, + { + "epoch": 0.57, + "learning_rate": 2.178206304109528e-05, + "loss": 0.1257, + "step": 253380 + }, + { + "epoch": 0.57, + "learning_rate": 2.1780944497885957e-05, + "loss": 0.1259, + "step": 253390 + }, + { + "epoch": 0.57, + "learning_rate": 2.177982595467663e-05, + "loss": 0.1214, + "step": 253400 + }, + { + "epoch": 0.57, + "learning_rate": 2.1778707411467306e-05, + "loss": 0.1206, + "step": 253410 + }, + { + "epoch": 0.57, + "learning_rate": 2.177758886825798e-05, + "loss": 0.124, + "step": 253420 + }, + { + "epoch": 0.57, + "learning_rate": 2.1776470325048658e-05, + "loss": 0.1274, + "step": 253430 + }, + { + "epoch": 0.57, + "learning_rate": 2.1775351781839333e-05, + "loss": 0.1236, + "step": 253440 + }, + { + "epoch": 0.57, + "learning_rate": 2.177423323863001e-05, + "loss": 0.119, + "step": 253450 + }, + { + "epoch": 0.57, + "learning_rate": 2.1773114695420685e-05, + "loss": 0.1203, + "step": 253460 + }, + { + "epoch": 0.57, + "learning_rate": 2.177199615221136e-05, + "loss": 0.1212, + "step": 253470 + }, + { + "epoch": 0.57, + "learning_rate": 2.1770877609002034e-05, + "loss": 0.1237, + "step": 253480 + }, + { + "epoch": 0.57, + "learning_rate": 2.1769759065792712e-05, + "loss": 0.1248, + "step": 253490 + }, + { + "epoch": 0.57, + "learning_rate": 2.176864052258339e-05, + "loss": 0.1225, + "step": 253500 + }, + { + "epoch": 0.57, + "learning_rate": 2.1767521979374065e-05, + "loss": 0.1281, + "step": 253510 + }, + { + "epoch": 0.57, + "learning_rate": 2.176640343616474e-05, + "loss": 0.1274, + "step": 253520 + }, + { + "epoch": 0.57, + "learning_rate": 2.1765284892955414e-05, + "loss": 0.126, + "step": 253530 + }, + { + "epoch": 0.57, + "learning_rate": 2.1764166349746092e-05, + "loss": 0.1215, + "step": 253540 + }, + { + "epoch": 0.57, + "learning_rate": 2.176304780653677e-05, + "loss": 0.1235, + "step": 253550 + }, + { + "epoch": 0.57, + "learning_rate": 2.1761929263327444e-05, + "loss": 0.1272, + "step": 253560 + }, + { + "epoch": 0.57, + "learning_rate": 2.176081072011812e-05, + "loss": 0.1218, + "step": 253570 + }, + { + "epoch": 0.57, + "learning_rate": 2.1759692176908793e-05, + "loss": 0.1206, + "step": 253580 + }, + { + "epoch": 0.57, + "learning_rate": 2.175857363369947e-05, + "loss": 0.1258, + "step": 253590 + }, + { + "epoch": 0.57, + "learning_rate": 2.175745509049015e-05, + "loss": 0.1234, + "step": 253600 + }, + { + "epoch": 0.57, + "learning_rate": 2.1756336547280824e-05, + "loss": 0.1263, + "step": 253610 + }, + { + "epoch": 0.57, + "learning_rate": 2.1755218004071498e-05, + "loss": 0.1266, + "step": 253620 + }, + { + "epoch": 0.57, + "learning_rate": 2.1754099460862173e-05, + "loss": 0.1208, + "step": 253630 + }, + { + "epoch": 0.57, + "learning_rate": 2.1752980917652847e-05, + "loss": 0.1216, + "step": 253640 + }, + { + "epoch": 0.57, + "learning_rate": 2.1751862374443525e-05, + "loss": 0.1218, + "step": 253650 + }, + { + "epoch": 0.57, + "learning_rate": 2.1750743831234203e-05, + "loss": 0.1214, + "step": 253660 + }, + { + "epoch": 0.57, + "learning_rate": 2.1749625288024878e-05, + "loss": 0.1236, + "step": 253670 + }, + { + "epoch": 0.57, + "learning_rate": 2.1748506744815552e-05, + "loss": 0.1257, + "step": 253680 + }, + { + "epoch": 0.57, + "learning_rate": 2.1747388201606227e-05, + "loss": 0.1251, + "step": 253690 + }, + { + "epoch": 0.57, + "learning_rate": 2.1746269658396905e-05, + "loss": 0.124, + "step": 253700 + }, + { + "epoch": 0.57, + "learning_rate": 2.1745151115187583e-05, + "loss": 0.1237, + "step": 253710 + }, + { + "epoch": 0.57, + "learning_rate": 2.1744032571978257e-05, + "loss": 0.1245, + "step": 253720 + }, + { + "epoch": 0.57, + "learning_rate": 2.1742914028768932e-05, + "loss": 0.122, + "step": 253730 + }, + { + "epoch": 0.57, + "learning_rate": 2.1741795485559606e-05, + "loss": 0.1231, + "step": 253740 + }, + { + "epoch": 0.57, + "learning_rate": 2.1740676942350284e-05, + "loss": 0.1224, + "step": 253750 + }, + { + "epoch": 0.57, + "learning_rate": 2.1739558399140962e-05, + "loss": 0.1283, + "step": 253760 + }, + { + "epoch": 0.57, + "learning_rate": 2.1738439855931637e-05, + "loss": 0.1242, + "step": 253770 + }, + { + "epoch": 0.57, + "learning_rate": 2.173732131272231e-05, + "loss": 0.1243, + "step": 253780 + }, + { + "epoch": 0.57, + "learning_rate": 2.1736202769512986e-05, + "loss": 0.1211, + "step": 253790 + }, + { + "epoch": 0.57, + "learning_rate": 2.173508422630366e-05, + "loss": 0.1221, + "step": 253800 + }, + { + "epoch": 0.57, + "learning_rate": 2.173396568309434e-05, + "loss": 0.1183, + "step": 253810 + }, + { + "epoch": 0.57, + "learning_rate": 2.1732847139885016e-05, + "loss": 0.1204, + "step": 253820 + }, + { + "epoch": 0.57, + "learning_rate": 2.173172859667569e-05, + "loss": 0.1228, + "step": 253830 + }, + { + "epoch": 0.57, + "learning_rate": 2.1730610053466365e-05, + "loss": 0.125, + "step": 253840 + }, + { + "epoch": 0.57, + "learning_rate": 2.172949151025704e-05, + "loss": 0.1259, + "step": 253850 + }, + { + "epoch": 0.57, + "learning_rate": 2.1728372967047718e-05, + "loss": 0.1254, + "step": 253860 + }, + { + "epoch": 0.57, + "learning_rate": 2.1727254423838396e-05, + "loss": 0.1256, + "step": 253870 + }, + { + "epoch": 0.57, + "learning_rate": 2.172613588062907e-05, + "loss": 0.1226, + "step": 253880 + }, + { + "epoch": 0.57, + "learning_rate": 2.1725017337419745e-05, + "loss": 0.1248, + "step": 253890 + }, + { + "epoch": 0.57, + "learning_rate": 2.172389879421042e-05, + "loss": 0.1239, + "step": 253900 + }, + { + "epoch": 0.57, + "learning_rate": 2.1722780251001097e-05, + "loss": 0.1251, + "step": 253910 + }, + { + "epoch": 0.57, + "learning_rate": 2.1721661707791775e-05, + "loss": 0.1263, + "step": 253920 + }, + { + "epoch": 0.57, + "learning_rate": 2.172054316458245e-05, + "loss": 0.1259, + "step": 253930 + }, + { + "epoch": 0.57, + "learning_rate": 2.1719424621373124e-05, + "loss": 0.1244, + "step": 253940 + }, + { + "epoch": 0.57, + "learning_rate": 2.17183060781638e-05, + "loss": 0.1243, + "step": 253950 + }, + { + "epoch": 0.57, + "learning_rate": 2.1717187534954477e-05, + "loss": 0.1266, + "step": 253960 + }, + { + "epoch": 0.57, + "learning_rate": 2.1716068991745155e-05, + "loss": 0.1255, + "step": 253970 + }, + { + "epoch": 0.57, + "learning_rate": 2.171495044853583e-05, + "loss": 0.122, + "step": 253980 + }, + { + "epoch": 0.57, + "learning_rate": 2.1713831905326504e-05, + "loss": 0.125, + "step": 253990 + }, + { + "epoch": 0.57, + "learning_rate": 2.1712713362117178e-05, + "loss": 0.1269, + "step": 254000 + }, + { + "epoch": 0.57, + "learning_rate": 2.1711594818907856e-05, + "loss": 0.1263, + "step": 254010 + }, + { + "epoch": 0.57, + "learning_rate": 2.1710476275698534e-05, + "loss": 0.1244, + "step": 254020 + }, + { + "epoch": 0.57, + "learning_rate": 2.170935773248921e-05, + "loss": 0.1257, + "step": 254030 + }, + { + "epoch": 0.57, + "learning_rate": 2.1708239189279883e-05, + "loss": 0.1217, + "step": 254040 + }, + { + "epoch": 0.57, + "learning_rate": 2.1707120646070558e-05, + "loss": 0.1263, + "step": 254050 + }, + { + "epoch": 0.57, + "learning_rate": 2.1706002102861232e-05, + "loss": 0.1269, + "step": 254060 + }, + { + "epoch": 0.57, + "learning_rate": 2.170488355965191e-05, + "loss": 0.1205, + "step": 254070 + }, + { + "epoch": 0.57, + "learning_rate": 2.1703765016442588e-05, + "loss": 0.1281, + "step": 254080 + }, + { + "epoch": 0.57, + "learning_rate": 2.1702646473233263e-05, + "loss": 0.1262, + "step": 254090 + }, + { + "epoch": 0.57, + "learning_rate": 2.1701527930023937e-05, + "loss": 0.1231, + "step": 254100 + }, + { + "epoch": 0.57, + "learning_rate": 2.170040938681461e-05, + "loss": 0.1238, + "step": 254110 + }, + { + "epoch": 0.57, + "learning_rate": 2.169929084360529e-05, + "loss": 0.1235, + "step": 254120 + }, + { + "epoch": 0.57, + "learning_rate": 2.1698172300395968e-05, + "loss": 0.1181, + "step": 254130 + }, + { + "epoch": 0.57, + "learning_rate": 2.1697053757186642e-05, + "loss": 0.1224, + "step": 254140 + }, + { + "epoch": 0.57, + "learning_rate": 2.1695935213977317e-05, + "loss": 0.126, + "step": 254150 + }, + { + "epoch": 0.57, + "learning_rate": 2.169481667076799e-05, + "loss": 0.1237, + "step": 254160 + }, + { + "epoch": 0.57, + "learning_rate": 2.169369812755867e-05, + "loss": 0.1211, + "step": 254170 + }, + { + "epoch": 0.57, + "learning_rate": 2.1692579584349347e-05, + "loss": 0.1198, + "step": 254180 + }, + { + "epoch": 0.57, + "learning_rate": 2.169146104114002e-05, + "loss": 0.1237, + "step": 254190 + }, + { + "epoch": 0.57, + "learning_rate": 2.1690342497930696e-05, + "loss": 0.1236, + "step": 254200 + }, + { + "epoch": 0.57, + "learning_rate": 2.168922395472137e-05, + "loss": 0.1217, + "step": 254210 + }, + { + "epoch": 0.57, + "learning_rate": 2.168810541151205e-05, + "loss": 0.1218, + "step": 254220 + }, + { + "epoch": 0.57, + "learning_rate": 2.1686986868302723e-05, + "loss": 0.124, + "step": 254230 + }, + { + "epoch": 0.57, + "learning_rate": 2.16858683250934e-05, + "loss": 0.1236, + "step": 254240 + }, + { + "epoch": 0.57, + "learning_rate": 2.1684749781884076e-05, + "loss": 0.1234, + "step": 254250 + }, + { + "epoch": 0.57, + "learning_rate": 2.168363123867475e-05, + "loss": 0.1248, + "step": 254260 + }, + { + "epoch": 0.57, + "learning_rate": 2.1682512695465425e-05, + "loss": 0.1232, + "step": 254270 + }, + { + "epoch": 0.57, + "learning_rate": 2.1681394152256103e-05, + "loss": 0.1254, + "step": 254280 + }, + { + "epoch": 0.57, + "learning_rate": 2.168027560904678e-05, + "loss": 0.1218, + "step": 254290 + }, + { + "epoch": 0.57, + "learning_rate": 2.1679157065837455e-05, + "loss": 0.1266, + "step": 254300 + }, + { + "epoch": 0.57, + "learning_rate": 2.167803852262813e-05, + "loss": 0.1251, + "step": 254310 + }, + { + "epoch": 0.57, + "learning_rate": 2.1676919979418804e-05, + "loss": 0.1217, + "step": 254320 + }, + { + "epoch": 0.57, + "learning_rate": 2.1675801436209482e-05, + "loss": 0.1236, + "step": 254330 + }, + { + "epoch": 0.57, + "learning_rate": 2.167468289300016e-05, + "loss": 0.1207, + "step": 254340 + }, + { + "epoch": 0.57, + "learning_rate": 2.1673564349790834e-05, + "loss": 0.1238, + "step": 254350 + }, + { + "epoch": 0.57, + "learning_rate": 2.167244580658151e-05, + "loss": 0.1209, + "step": 254360 + }, + { + "epoch": 0.57, + "learning_rate": 2.1671327263372184e-05, + "loss": 0.1236, + "step": 254370 + }, + { + "epoch": 0.57, + "learning_rate": 2.167020872016286e-05, + "loss": 0.1228, + "step": 254380 + }, + { + "epoch": 0.57, + "learning_rate": 2.1669090176953536e-05, + "loss": 0.1284, + "step": 254390 + }, + { + "epoch": 0.57, + "learning_rate": 2.1667971633744214e-05, + "loss": 0.1257, + "step": 254400 + }, + { + "epoch": 0.57, + "learning_rate": 2.166685309053489e-05, + "loss": 0.1238, + "step": 254410 + }, + { + "epoch": 0.57, + "learning_rate": 2.1665734547325563e-05, + "loss": 0.1213, + "step": 254420 + }, + { + "epoch": 0.57, + "learning_rate": 2.166461600411624e-05, + "loss": 0.1277, + "step": 254430 + }, + { + "epoch": 0.57, + "learning_rate": 2.1663497460906916e-05, + "loss": 0.1236, + "step": 254440 + }, + { + "epoch": 0.57, + "learning_rate": 2.1662378917697593e-05, + "loss": 0.1247, + "step": 254450 + }, + { + "epoch": 0.57, + "learning_rate": 2.1661260374488268e-05, + "loss": 0.1169, + "step": 254460 + }, + { + "epoch": 0.57, + "learning_rate": 2.1660141831278943e-05, + "loss": 0.1265, + "step": 254470 + }, + { + "epoch": 0.57, + "learning_rate": 2.1659023288069617e-05, + "loss": 0.1216, + "step": 254480 + }, + { + "epoch": 0.57, + "learning_rate": 2.1657904744860295e-05, + "loss": 0.1266, + "step": 254490 + }, + { + "epoch": 0.57, + "learning_rate": 2.1656786201650973e-05, + "loss": 0.1256, + "step": 254500 + }, + { + "epoch": 0.57, + "learning_rate": 2.1655667658441647e-05, + "loss": 0.1212, + "step": 254510 + }, + { + "epoch": 0.57, + "learning_rate": 2.1654549115232322e-05, + "loss": 0.1225, + "step": 254520 + }, + { + "epoch": 0.57, + "learning_rate": 2.1653430572022997e-05, + "loss": 0.1283, + "step": 254530 + }, + { + "epoch": 0.57, + "learning_rate": 2.1652312028813674e-05, + "loss": 0.123, + "step": 254540 + }, + { + "epoch": 0.57, + "learning_rate": 2.165119348560435e-05, + "loss": 0.1223, + "step": 254550 + }, + { + "epoch": 0.57, + "learning_rate": 2.1650074942395027e-05, + "loss": 0.1232, + "step": 254560 + }, + { + "epoch": 0.57, + "learning_rate": 2.16489563991857e-05, + "loss": 0.1277, + "step": 254570 + }, + { + "epoch": 0.57, + "learning_rate": 2.1647837855976376e-05, + "loss": 0.1226, + "step": 254580 + }, + { + "epoch": 0.57, + "learning_rate": 2.1646719312767054e-05, + "loss": 0.1228, + "step": 254590 + }, + { + "epoch": 0.57, + "learning_rate": 2.164560076955773e-05, + "loss": 0.1215, + "step": 254600 + }, + { + "epoch": 0.57, + "learning_rate": 2.1644482226348406e-05, + "loss": 0.1209, + "step": 254610 + }, + { + "epoch": 0.57, + "learning_rate": 2.164336368313908e-05, + "loss": 0.1278, + "step": 254620 + }, + { + "epoch": 0.57, + "learning_rate": 2.1642245139929755e-05, + "loss": 0.119, + "step": 254630 + }, + { + "epoch": 0.57, + "learning_rate": 2.1641126596720433e-05, + "loss": 0.1204, + "step": 254640 + }, + { + "epoch": 0.57, + "learning_rate": 2.1640008053511108e-05, + "loss": 0.121, + "step": 254650 + }, + { + "epoch": 0.57, + "learning_rate": 2.1638889510301786e-05, + "loss": 0.1232, + "step": 254660 + }, + { + "epoch": 0.57, + "learning_rate": 2.163777096709246e-05, + "loss": 0.1255, + "step": 254670 + }, + { + "epoch": 0.57, + "learning_rate": 2.1636652423883135e-05, + "loss": 0.1228, + "step": 254680 + }, + { + "epoch": 0.57, + "learning_rate": 2.163553388067381e-05, + "loss": 0.1242, + "step": 254690 + }, + { + "epoch": 0.57, + "learning_rate": 2.1634415337464487e-05, + "loss": 0.1276, + "step": 254700 + }, + { + "epoch": 0.57, + "learning_rate": 2.1633296794255162e-05, + "loss": 0.125, + "step": 254710 + }, + { + "epoch": 0.57, + "learning_rate": 2.163217825104584e-05, + "loss": 0.1192, + "step": 254720 + }, + { + "epoch": 0.57, + "learning_rate": 2.1631059707836514e-05, + "loss": 0.1216, + "step": 254730 + }, + { + "epoch": 0.57, + "learning_rate": 2.162994116462719e-05, + "loss": 0.1203, + "step": 254740 + }, + { + "epoch": 0.57, + "learning_rate": 2.1628822621417867e-05, + "loss": 0.1239, + "step": 254750 + }, + { + "epoch": 0.57, + "learning_rate": 2.162770407820854e-05, + "loss": 0.1237, + "step": 254760 + }, + { + "epoch": 0.57, + "learning_rate": 2.162658553499922e-05, + "loss": 0.1232, + "step": 254770 + }, + { + "epoch": 0.57, + "learning_rate": 2.1625466991789894e-05, + "loss": 0.1255, + "step": 254780 + }, + { + "epoch": 0.57, + "learning_rate": 2.162434844858057e-05, + "loss": 0.1244, + "step": 254790 + }, + { + "epoch": 0.57, + "learning_rate": 2.1623229905371246e-05, + "loss": 0.1252, + "step": 254800 + }, + { + "epoch": 0.57, + "learning_rate": 2.162211136216192e-05, + "loss": 0.1244, + "step": 254810 + }, + { + "epoch": 0.57, + "learning_rate": 2.16209928189526e-05, + "loss": 0.1249, + "step": 254820 + }, + { + "epoch": 0.57, + "learning_rate": 2.1619874275743273e-05, + "loss": 0.1176, + "step": 254830 + }, + { + "epoch": 0.57, + "learning_rate": 2.1618755732533948e-05, + "loss": 0.1216, + "step": 254840 + }, + { + "epoch": 0.57, + "learning_rate": 2.1617637189324626e-05, + "loss": 0.1225, + "step": 254850 + }, + { + "epoch": 0.57, + "learning_rate": 2.16165186461153e-05, + "loss": 0.1238, + "step": 254860 + }, + { + "epoch": 0.57, + "learning_rate": 2.1615400102905975e-05, + "loss": 0.1243, + "step": 254870 + }, + { + "epoch": 0.57, + "learning_rate": 2.1614281559696653e-05, + "loss": 0.1279, + "step": 254880 + }, + { + "epoch": 0.57, + "learning_rate": 2.1613163016487327e-05, + "loss": 0.1233, + "step": 254890 + }, + { + "epoch": 0.57, + "learning_rate": 2.1612044473278005e-05, + "loss": 0.1244, + "step": 254900 + }, + { + "epoch": 0.57, + "learning_rate": 2.161092593006868e-05, + "loss": 0.1213, + "step": 254910 + }, + { + "epoch": 0.57, + "learning_rate": 2.1609807386859354e-05, + "loss": 0.1225, + "step": 254920 + }, + { + "epoch": 0.57, + "learning_rate": 2.1608688843650032e-05, + "loss": 0.122, + "step": 254930 + }, + { + "epoch": 0.57, + "learning_rate": 2.1607570300440707e-05, + "loss": 0.1256, + "step": 254940 + }, + { + "epoch": 0.57, + "learning_rate": 2.160645175723138e-05, + "loss": 0.1232, + "step": 254950 + }, + { + "epoch": 0.57, + "learning_rate": 2.160533321402206e-05, + "loss": 0.1178, + "step": 254960 + }, + { + "epoch": 0.57, + "learning_rate": 2.1604214670812734e-05, + "loss": 0.1247, + "step": 254970 + }, + { + "epoch": 0.57, + "learning_rate": 2.1603096127603412e-05, + "loss": 0.1255, + "step": 254980 + }, + { + "epoch": 0.57, + "learning_rate": 2.1601977584394086e-05, + "loss": 0.1232, + "step": 254990 + }, + { + "epoch": 0.57, + "learning_rate": 2.160085904118476e-05, + "loss": 0.1263, + "step": 255000 + }, + { + "epoch": 0.57, + "learning_rate": 2.159974049797544e-05, + "loss": 0.1217, + "step": 255010 + }, + { + "epoch": 0.57, + "learning_rate": 2.1598621954766113e-05, + "loss": 0.1225, + "step": 255020 + }, + { + "epoch": 0.57, + "learning_rate": 2.1597503411556788e-05, + "loss": 0.1255, + "step": 255030 + }, + { + "epoch": 0.57, + "learning_rate": 2.1596384868347466e-05, + "loss": 0.1232, + "step": 255040 + }, + { + "epoch": 0.57, + "learning_rate": 2.159526632513814e-05, + "loss": 0.1269, + "step": 255050 + }, + { + "epoch": 0.57, + "learning_rate": 2.1594147781928818e-05, + "loss": 0.1238, + "step": 255060 + }, + { + "epoch": 0.57, + "learning_rate": 2.1593029238719493e-05, + "loss": 0.1257, + "step": 255070 + }, + { + "epoch": 0.57, + "learning_rate": 2.1591910695510167e-05, + "loss": 0.1251, + "step": 255080 + }, + { + "epoch": 0.57, + "learning_rate": 2.1590792152300845e-05, + "loss": 0.124, + "step": 255090 + }, + { + "epoch": 0.57, + "learning_rate": 2.158967360909152e-05, + "loss": 0.1255, + "step": 255100 + }, + { + "epoch": 0.57, + "learning_rate": 2.1588555065882198e-05, + "loss": 0.1227, + "step": 255110 + }, + { + "epoch": 0.57, + "learning_rate": 2.1587436522672872e-05, + "loss": 0.1249, + "step": 255120 + }, + { + "epoch": 0.57, + "learning_rate": 2.1586317979463547e-05, + "loss": 0.1251, + "step": 255130 + }, + { + "epoch": 0.57, + "learning_rate": 2.1585199436254225e-05, + "loss": 0.1234, + "step": 255140 + }, + { + "epoch": 0.57, + "learning_rate": 2.15840808930449e-05, + "loss": 0.1259, + "step": 255150 + }, + { + "epoch": 0.57, + "learning_rate": 2.1582962349835574e-05, + "loss": 0.1236, + "step": 255160 + }, + { + "epoch": 0.57, + "learning_rate": 2.1581843806626252e-05, + "loss": 0.1226, + "step": 255170 + }, + { + "epoch": 0.57, + "learning_rate": 2.1580725263416926e-05, + "loss": 0.1198, + "step": 255180 + }, + { + "epoch": 0.57, + "learning_rate": 2.15796067202076e-05, + "loss": 0.1245, + "step": 255190 + }, + { + "epoch": 0.57, + "learning_rate": 2.157848817699828e-05, + "loss": 0.1216, + "step": 255200 + }, + { + "epoch": 0.57, + "learning_rate": 2.1577369633788953e-05, + "loss": 0.1255, + "step": 255210 + }, + { + "epoch": 0.57, + "learning_rate": 2.157625109057963e-05, + "loss": 0.1206, + "step": 255220 + }, + { + "epoch": 0.57, + "learning_rate": 2.1575132547370306e-05, + "loss": 0.124, + "step": 255230 + }, + { + "epoch": 0.57, + "learning_rate": 2.157401400416098e-05, + "loss": 0.1229, + "step": 255240 + }, + { + "epoch": 0.57, + "learning_rate": 2.1572895460951658e-05, + "loss": 0.124, + "step": 255250 + }, + { + "epoch": 0.57, + "learning_rate": 2.1571776917742333e-05, + "loss": 0.1234, + "step": 255260 + }, + { + "epoch": 0.57, + "learning_rate": 2.157065837453301e-05, + "loss": 0.1268, + "step": 255270 + }, + { + "epoch": 0.57, + "learning_rate": 2.1569539831323685e-05, + "loss": 0.1224, + "step": 255280 + }, + { + "epoch": 0.57, + "learning_rate": 2.156842128811436e-05, + "loss": 0.1239, + "step": 255290 + }, + { + "epoch": 0.57, + "learning_rate": 2.1567302744905038e-05, + "loss": 0.1179, + "step": 255300 + }, + { + "epoch": 0.57, + "learning_rate": 2.1566184201695712e-05, + "loss": 0.1296, + "step": 255310 + }, + { + "epoch": 0.57, + "learning_rate": 2.156506565848639e-05, + "loss": 0.1196, + "step": 255320 + }, + { + "epoch": 0.57, + "learning_rate": 2.1563947115277065e-05, + "loss": 0.1232, + "step": 255330 + }, + { + "epoch": 0.57, + "learning_rate": 2.156282857206774e-05, + "loss": 0.1253, + "step": 255340 + }, + { + "epoch": 0.57, + "learning_rate": 2.1561710028858414e-05, + "loss": 0.1254, + "step": 255350 + }, + { + "epoch": 0.57, + "learning_rate": 2.1560591485649092e-05, + "loss": 0.1243, + "step": 255360 + }, + { + "epoch": 0.57, + "learning_rate": 2.1559472942439766e-05, + "loss": 0.1313, + "step": 255370 + }, + { + "epoch": 0.57, + "learning_rate": 2.1558354399230444e-05, + "loss": 0.122, + "step": 255380 + }, + { + "epoch": 0.57, + "learning_rate": 2.155723585602112e-05, + "loss": 0.1249, + "step": 255390 + }, + { + "epoch": 0.57, + "learning_rate": 2.1556117312811793e-05, + "loss": 0.1201, + "step": 255400 + }, + { + "epoch": 0.57, + "learning_rate": 2.155499876960247e-05, + "loss": 0.1223, + "step": 255410 + }, + { + "epoch": 0.57, + "learning_rate": 2.1553880226393146e-05, + "loss": 0.13, + "step": 255420 + }, + { + "epoch": 0.57, + "learning_rate": 2.1552761683183824e-05, + "loss": 0.1228, + "step": 255430 + }, + { + "epoch": 0.57, + "learning_rate": 2.1551643139974498e-05, + "loss": 0.123, + "step": 255440 + }, + { + "epoch": 0.57, + "learning_rate": 2.1550524596765173e-05, + "loss": 0.1229, + "step": 255450 + }, + { + "epoch": 0.57, + "learning_rate": 2.154940605355585e-05, + "loss": 0.1228, + "step": 255460 + }, + { + "epoch": 0.57, + "learning_rate": 2.1548287510346525e-05, + "loss": 0.1226, + "step": 255470 + }, + { + "epoch": 0.57, + "learning_rate": 2.1547168967137203e-05, + "loss": 0.1232, + "step": 255480 + }, + { + "epoch": 0.57, + "learning_rate": 2.1546050423927878e-05, + "loss": 0.1262, + "step": 255490 + }, + { + "epoch": 0.57, + "learning_rate": 2.1544931880718552e-05, + "loss": 0.1248, + "step": 255500 + }, + { + "epoch": 0.57, + "learning_rate": 2.1543813337509227e-05, + "loss": 0.123, + "step": 255510 + }, + { + "epoch": 0.57, + "learning_rate": 2.1542694794299905e-05, + "loss": 0.1259, + "step": 255520 + }, + { + "epoch": 0.57, + "learning_rate": 2.1541576251090583e-05, + "loss": 0.1205, + "step": 255530 + }, + { + "epoch": 0.57, + "learning_rate": 2.1540457707881257e-05, + "loss": 0.1223, + "step": 255540 + }, + { + "epoch": 0.57, + "learning_rate": 2.1539339164671932e-05, + "loss": 0.1219, + "step": 255550 + }, + { + "epoch": 0.57, + "learning_rate": 2.1538220621462606e-05, + "loss": 0.1214, + "step": 255560 + }, + { + "epoch": 0.57, + "learning_rate": 2.1537102078253284e-05, + "loss": 0.1232, + "step": 255570 + }, + { + "epoch": 0.57, + "learning_rate": 2.153598353504396e-05, + "loss": 0.1237, + "step": 255580 + }, + { + "epoch": 0.57, + "learning_rate": 2.1534864991834637e-05, + "loss": 0.1237, + "step": 255590 + }, + { + "epoch": 0.57, + "learning_rate": 2.153374644862531e-05, + "loss": 0.1264, + "step": 255600 + }, + { + "epoch": 0.57, + "learning_rate": 2.1532627905415986e-05, + "loss": 0.1272, + "step": 255610 + }, + { + "epoch": 0.57, + "learning_rate": 2.1531509362206664e-05, + "loss": 0.1237, + "step": 255620 + }, + { + "epoch": 0.57, + "learning_rate": 2.1530390818997338e-05, + "loss": 0.1264, + "step": 255630 + }, + { + "epoch": 0.57, + "learning_rate": 2.1529272275788016e-05, + "loss": 0.1221, + "step": 255640 + }, + { + "epoch": 0.57, + "learning_rate": 2.152815373257869e-05, + "loss": 0.1263, + "step": 255650 + }, + { + "epoch": 0.57, + "learning_rate": 2.1527035189369365e-05, + "loss": 0.1238, + "step": 255660 + }, + { + "epoch": 0.57, + "learning_rate": 2.152591664616004e-05, + "loss": 0.1252, + "step": 255670 + }, + { + "epoch": 0.57, + "learning_rate": 2.1524798102950718e-05, + "loss": 0.1241, + "step": 255680 + }, + { + "epoch": 0.57, + "learning_rate": 2.1523679559741396e-05, + "loss": 0.1213, + "step": 255690 + }, + { + "epoch": 0.57, + "learning_rate": 2.152256101653207e-05, + "loss": 0.1215, + "step": 255700 + }, + { + "epoch": 0.57, + "learning_rate": 2.1521442473322745e-05, + "loss": 0.1231, + "step": 255710 + }, + { + "epoch": 0.57, + "learning_rate": 2.152032393011342e-05, + "loss": 0.1232, + "step": 255720 + }, + { + "epoch": 0.57, + "learning_rate": 2.1519205386904097e-05, + "loss": 0.1255, + "step": 255730 + }, + { + "epoch": 0.57, + "learning_rate": 2.1518086843694775e-05, + "loss": 0.1229, + "step": 255740 + }, + { + "epoch": 0.57, + "learning_rate": 2.151696830048545e-05, + "loss": 0.1234, + "step": 255750 + }, + { + "epoch": 0.57, + "learning_rate": 2.1515849757276124e-05, + "loss": 0.1219, + "step": 255760 + }, + { + "epoch": 0.57, + "learning_rate": 2.15147312140668e-05, + "loss": 0.1207, + "step": 255770 + }, + { + "epoch": 0.57, + "learning_rate": 2.1513612670857477e-05, + "loss": 0.1234, + "step": 255780 + }, + { + "epoch": 0.57, + "learning_rate": 2.1512494127648155e-05, + "loss": 0.1281, + "step": 255790 + }, + { + "epoch": 0.57, + "learning_rate": 2.151137558443883e-05, + "loss": 0.1251, + "step": 255800 + }, + { + "epoch": 0.57, + "learning_rate": 2.1510257041229504e-05, + "loss": 0.1278, + "step": 255810 + }, + { + "epoch": 0.57, + "learning_rate": 2.1509138498020178e-05, + "loss": 0.1217, + "step": 255820 + }, + { + "epoch": 0.57, + "learning_rate": 2.1508019954810853e-05, + "loss": 0.1245, + "step": 255830 + }, + { + "epoch": 0.57, + "learning_rate": 2.150690141160153e-05, + "loss": 0.1238, + "step": 255840 + }, + { + "epoch": 0.57, + "learning_rate": 2.150578286839221e-05, + "loss": 0.1191, + "step": 255850 + }, + { + "epoch": 0.57, + "learning_rate": 2.1504664325182883e-05, + "loss": 0.1203, + "step": 255860 + }, + { + "epoch": 0.57, + "learning_rate": 2.1503545781973558e-05, + "loss": 0.1207, + "step": 255870 + }, + { + "epoch": 0.57, + "learning_rate": 2.1502427238764232e-05, + "loss": 0.1242, + "step": 255880 + }, + { + "epoch": 0.57, + "learning_rate": 2.150130869555491e-05, + "loss": 0.1177, + "step": 255890 + }, + { + "epoch": 0.57, + "learning_rate": 2.1500190152345588e-05, + "loss": 0.1257, + "step": 255900 + }, + { + "epoch": 0.57, + "learning_rate": 2.1499071609136263e-05, + "loss": 0.1206, + "step": 255910 + }, + { + "epoch": 0.57, + "learning_rate": 2.1497953065926937e-05, + "loss": 0.1263, + "step": 255920 + }, + { + "epoch": 0.57, + "learning_rate": 2.149683452271761e-05, + "loss": 0.1215, + "step": 255930 + }, + { + "epoch": 0.57, + "learning_rate": 2.149571597950829e-05, + "loss": 0.1208, + "step": 255940 + }, + { + "epoch": 0.57, + "learning_rate": 2.1494597436298967e-05, + "loss": 0.1247, + "step": 255950 + }, + { + "epoch": 0.57, + "learning_rate": 2.1493478893089642e-05, + "loss": 0.1212, + "step": 255960 + }, + { + "epoch": 0.57, + "learning_rate": 2.1492360349880317e-05, + "loss": 0.1217, + "step": 255970 + }, + { + "epoch": 0.57, + "learning_rate": 2.149124180667099e-05, + "loss": 0.1215, + "step": 255980 + }, + { + "epoch": 0.57, + "learning_rate": 2.1490123263461666e-05, + "loss": 0.124, + "step": 255990 + }, + { + "epoch": 0.57, + "learning_rate": 2.1489004720252347e-05, + "loss": 0.1225, + "step": 256000 + }, + { + "epoch": 0.57, + "eval_NEIMS_canon_smiles": 0.9561, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.17915, + "eval_NEIMS_daylight_tanimoto_simil": 0.5732546938456836, + "eval_NEIMS_exact_mols": 0.17893333333333333, + "eval_NEIMS_exact_smiles": 0.17501666666666665, + "eval_NEIMS_loss": 0.15140371024608612, + "eval_NEIMS_matched_formulas": 0.70625, + "eval_NEIMS_morgan_tanimoto_simil": 0.4912442990130183, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.17948333333333333, + "eval_NEIMS_runtime": 725.9372, + "eval_NEIMS_samples_per_second": 82.652, + "eval_NEIMS_steps_per_second": 1.292, + "step": 256000 + }, + { + "epoch": 0.57, + "eval_RASSP_canon_smiles": 0.9539853741610178, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.24199418973519884, + "eval_RASSP_daylight_tanimoto_simil": 0.6673510856040585, + "eval_RASSP_exact_mols": 0.24137643169599626, + "eval_RASSP_exact_smiles": 0.2356997362006211, + "eval_RASSP_loss": 0.12042906135320663, + "eval_RASSP_matched_formulas": 0.8439409623668481, + "eval_RASSP_morgan_tanimoto_simil": 0.5495892780574381, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.24161017798109993, + "eval_RASSP_runtime": 829.897, + "eval_RASSP_samples_per_second": 72.17, + "eval_RASSP_steps_per_second": 1.128, + "step": 256000 + }, + { + "epoch": 0.57, + "eval_NEIMS_old_canon_smiles": 0.9541, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.1777, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5694210084911036, + "eval_NEIMS_old_exact_mols": 0.17733333333333334, + "eval_NEIMS_old_exact_smiles": 0.1728, + "eval_NEIMS_old_loss": 0.15082356333732605, + "eval_NEIMS_old_matched_formulas": 0.7080333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.489037654469636, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1782, + "eval_NEIMS_old_runtime": 365.7759, + "eval_NEIMS_old_samples_per_second": 82.017, + "eval_NEIMS_old_steps_per_second": 1.282, + "step": 256000 + }, + { + "epoch": 0.57, + "eval_RASSP_old_canon_smiles": 0.9556845863783495, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.2685620849601228, + "eval_RASSP_old_daylight_tanimoto_simil": 0.687940410922175, + "eval_RASSP_old_exact_mols": 0.2678279440718123, + "eval_RASSP_old_exact_smiles": 0.2610204558347516, + "eval_RASSP_old_loss": 0.11312191188335419, + "eval_RASSP_old_matched_formulas": 0.8570761170621016, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5743464065664815, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.2681282744352121, + "eval_RASSP_old_runtime": 410.9369, + "eval_RASSP_old_samples_per_second": 72.924, + "eval_RASSP_old_steps_per_second": 1.141, + "step": 256000 + }, + { + "epoch": 0.57, + "eval_NIST_canon_smiles": 0.858643574546616, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02448805763566029, + "eval_NIST_daylight_tanimoto_simil": 0.29264352678489414, + "eval_NIST_exact_mols": 0.0233878695389857, + "eval_NIST_exact_smiles": 0.022323171380913512, + "eval_NIST_loss": 1.7422006130218506, + "eval_NIST_matched_formulas": 0.1181460056074103, + "eval_NIST_morgan_tanimoto_simil": 0.24550805271543785, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02420413812684104, + "eval_NIST_runtime": 555.3659, + "eval_NIST_samples_per_second": 50.736, + "eval_NIST_steps_per_second": 0.794, + "step": 256000 + }, + { + "epoch": 0.57, + "learning_rate": 2.148788617704302e-05, + "loss": 0.1258, + "step": 256010 + }, + { + "epoch": 0.57, + "learning_rate": 2.1486767633833696e-05, + "loss": 0.1245, + "step": 256020 + }, + { + "epoch": 0.57, + "learning_rate": 2.148564909062437e-05, + "loss": 0.124, + "step": 256030 + }, + { + "epoch": 0.57, + "learning_rate": 2.1484530547415045e-05, + "loss": 0.1249, + "step": 256040 + }, + { + "epoch": 0.57, + "learning_rate": 2.1483412004205723e-05, + "loss": 0.1231, + "step": 256050 + }, + { + "epoch": 0.57, + "learning_rate": 2.14822934609964e-05, + "loss": 0.1264, + "step": 256060 + }, + { + "epoch": 0.57, + "learning_rate": 2.1481174917787076e-05, + "loss": 0.1252, + "step": 256070 + }, + { + "epoch": 0.57, + "learning_rate": 2.148005637457775e-05, + "loss": 0.1207, + "step": 256080 + }, + { + "epoch": 0.57, + "learning_rate": 2.1478937831368425e-05, + "loss": 0.1284, + "step": 256090 + }, + { + "epoch": 0.57, + "learning_rate": 2.1477819288159103e-05, + "loss": 0.1238, + "step": 256100 + }, + { + "epoch": 0.57, + "learning_rate": 2.147670074494978e-05, + "loss": 0.128, + "step": 256110 + }, + { + "epoch": 0.57, + "learning_rate": 2.1475582201740455e-05, + "loss": 0.1261, + "step": 256120 + }, + { + "epoch": 0.57, + "learning_rate": 2.147446365853113e-05, + "loss": 0.1236, + "step": 256130 + }, + { + "epoch": 0.57, + "learning_rate": 2.1473345115321804e-05, + "loss": 0.1177, + "step": 256140 + }, + { + "epoch": 0.57, + "learning_rate": 2.1472226572112482e-05, + "loss": 0.1195, + "step": 256150 + }, + { + "epoch": 0.57, + "learning_rate": 2.147110802890316e-05, + "loss": 0.1242, + "step": 256160 + }, + { + "epoch": 0.57, + "learning_rate": 2.1469989485693834e-05, + "loss": 0.1237, + "step": 256170 + }, + { + "epoch": 0.57, + "learning_rate": 2.146887094248451e-05, + "loss": 0.1218, + "step": 256180 + }, + { + "epoch": 0.57, + "learning_rate": 2.1467752399275184e-05, + "loss": 0.127, + "step": 256190 + }, + { + "epoch": 0.57, + "learning_rate": 2.1466633856065858e-05, + "loss": 0.1229, + "step": 256200 + }, + { + "epoch": 0.57, + "learning_rate": 2.146551531285654e-05, + "loss": 0.1196, + "step": 256210 + }, + { + "epoch": 0.57, + "learning_rate": 2.1464396769647214e-05, + "loss": 0.1217, + "step": 256220 + }, + { + "epoch": 0.57, + "learning_rate": 2.146327822643789e-05, + "loss": 0.1227, + "step": 256230 + }, + { + "epoch": 0.57, + "learning_rate": 2.1462271537549497e-05, + "loss": 0.1225, + "step": 256240 + }, + { + "epoch": 0.57, + "learning_rate": 2.1461152994340172e-05, + "loss": 0.1172, + "step": 256250 + }, + { + "epoch": 0.57, + "learning_rate": 2.1460034451130846e-05, + "loss": 0.1253, + "step": 256260 + }, + { + "epoch": 0.57, + "learning_rate": 2.1458915907921524e-05, + "loss": 0.1247, + "step": 256270 + }, + { + "epoch": 0.57, + "learning_rate": 2.1457797364712202e-05, + "loss": 0.1223, + "step": 256280 + }, + { + "epoch": 0.57, + "learning_rate": 2.1456678821502877e-05, + "loss": 0.1235, + "step": 256290 + }, + { + "epoch": 0.57, + "learning_rate": 2.145556027829355e-05, + "loss": 0.1203, + "step": 256300 + }, + { + "epoch": 0.57, + "learning_rate": 2.1454441735084226e-05, + "loss": 0.1187, + "step": 256310 + }, + { + "epoch": 0.57, + "learning_rate": 2.1453323191874904e-05, + "loss": 0.1216, + "step": 256320 + }, + { + "epoch": 0.57, + "learning_rate": 2.145220464866558e-05, + "loss": 0.123, + "step": 256330 + }, + { + "epoch": 0.57, + "learning_rate": 2.1451086105456256e-05, + "loss": 0.1237, + "step": 256340 + }, + { + "epoch": 0.57, + "learning_rate": 2.144996756224693e-05, + "loss": 0.1219, + "step": 256350 + }, + { + "epoch": 0.57, + "learning_rate": 2.1448849019037605e-05, + "loss": 0.1283, + "step": 256360 + }, + { + "epoch": 0.57, + "learning_rate": 2.1447730475828283e-05, + "loss": 0.122, + "step": 256370 + }, + { + "epoch": 0.57, + "learning_rate": 2.1446611932618958e-05, + "loss": 0.1196, + "step": 256380 + }, + { + "epoch": 0.57, + "learning_rate": 2.1445493389409636e-05, + "loss": 0.129, + "step": 256390 + }, + { + "epoch": 0.57, + "learning_rate": 2.144437484620031e-05, + "loss": 0.12, + "step": 256400 + }, + { + "epoch": 0.57, + "learning_rate": 2.1443256302990985e-05, + "loss": 0.1282, + "step": 256410 + }, + { + "epoch": 0.57, + "learning_rate": 2.144213775978166e-05, + "loss": 0.1237, + "step": 256420 + }, + { + "epoch": 0.57, + "learning_rate": 2.1441019216572337e-05, + "loss": 0.1225, + "step": 256430 + }, + { + "epoch": 0.57, + "learning_rate": 2.1439900673363015e-05, + "loss": 0.1262, + "step": 256440 + }, + { + "epoch": 0.57, + "learning_rate": 2.143878213015369e-05, + "loss": 0.1212, + "step": 256450 + }, + { + "epoch": 0.57, + "learning_rate": 2.1437663586944364e-05, + "loss": 0.1264, + "step": 256460 + }, + { + "epoch": 0.57, + "learning_rate": 2.143654504373504e-05, + "loss": 0.1253, + "step": 256470 + }, + { + "epoch": 0.57, + "learning_rate": 2.1435426500525717e-05, + "loss": 0.1223, + "step": 256480 + }, + { + "epoch": 0.57, + "learning_rate": 2.1434307957316395e-05, + "loss": 0.1202, + "step": 256490 + }, + { + "epoch": 0.57, + "learning_rate": 2.143318941410707e-05, + "loss": 0.1254, + "step": 256500 + }, + { + "epoch": 0.57, + "learning_rate": 2.1432070870897744e-05, + "loss": 0.1251, + "step": 256510 + }, + { + "epoch": 0.57, + "learning_rate": 2.1430952327688418e-05, + "loss": 0.1195, + "step": 256520 + }, + { + "epoch": 0.57, + "learning_rate": 2.1429833784479096e-05, + "loss": 0.1232, + "step": 256530 + }, + { + "epoch": 0.57, + "learning_rate": 2.142871524126977e-05, + "loss": 0.1262, + "step": 256540 + }, + { + "epoch": 0.57, + "learning_rate": 2.142759669806045e-05, + "loss": 0.1223, + "step": 256550 + }, + { + "epoch": 0.57, + "learning_rate": 2.1426478154851123e-05, + "loss": 0.1262, + "step": 256560 + }, + { + "epoch": 0.57, + "learning_rate": 2.1425359611641798e-05, + "loss": 0.1203, + "step": 256570 + }, + { + "epoch": 0.57, + "learning_rate": 2.1424241068432476e-05, + "loss": 0.1245, + "step": 256580 + }, + { + "epoch": 0.57, + "learning_rate": 2.142312252522315e-05, + "loss": 0.1204, + "step": 256590 + }, + { + "epoch": 0.57, + "learning_rate": 2.1422003982013828e-05, + "loss": 0.1266, + "step": 256600 + }, + { + "epoch": 0.57, + "learning_rate": 2.1420885438804503e-05, + "loss": 0.1235, + "step": 256610 + }, + { + "epoch": 0.57, + "learning_rate": 2.1419766895595177e-05, + "loss": 0.1195, + "step": 256620 + }, + { + "epoch": 0.57, + "learning_rate": 2.1418648352385852e-05, + "loss": 0.1268, + "step": 256630 + }, + { + "epoch": 0.57, + "learning_rate": 2.141752980917653e-05, + "loss": 0.123, + "step": 256640 + }, + { + "epoch": 0.57, + "learning_rate": 2.1416411265967208e-05, + "loss": 0.1201, + "step": 256650 + }, + { + "epoch": 0.57, + "learning_rate": 2.1415292722757882e-05, + "loss": 0.118, + "step": 256660 + }, + { + "epoch": 0.57, + "learning_rate": 2.1414174179548557e-05, + "loss": 0.1246, + "step": 256670 + }, + { + "epoch": 0.57, + "learning_rate": 2.141305563633923e-05, + "loss": 0.1222, + "step": 256680 + }, + { + "epoch": 0.57, + "learning_rate": 2.141193709312991e-05, + "loss": 0.122, + "step": 256690 + }, + { + "epoch": 0.57, + "learning_rate": 2.1410818549920584e-05, + "loss": 0.1223, + "step": 256700 + }, + { + "epoch": 0.57, + "learning_rate": 2.140970000671126e-05, + "loss": 0.1238, + "step": 256710 + }, + { + "epoch": 0.57, + "learning_rate": 2.1408581463501936e-05, + "loss": 0.1246, + "step": 256720 + }, + { + "epoch": 0.57, + "learning_rate": 2.140746292029261e-05, + "loss": 0.126, + "step": 256730 + }, + { + "epoch": 0.57, + "learning_rate": 2.140634437708329e-05, + "loss": 0.1196, + "step": 256740 + }, + { + "epoch": 0.57, + "learning_rate": 2.1405225833873963e-05, + "loss": 0.1219, + "step": 256750 + }, + { + "epoch": 0.57, + "learning_rate": 2.140410729066464e-05, + "loss": 0.1235, + "step": 256760 + }, + { + "epoch": 0.57, + "learning_rate": 2.1402988747455316e-05, + "loss": 0.123, + "step": 256770 + }, + { + "epoch": 0.57, + "learning_rate": 2.140187020424599e-05, + "loss": 0.1209, + "step": 256780 + }, + { + "epoch": 0.57, + "learning_rate": 2.1400751661036668e-05, + "loss": 0.1269, + "step": 256790 + }, + { + "epoch": 0.57, + "learning_rate": 2.1399633117827343e-05, + "loss": 0.1267, + "step": 256800 + }, + { + "epoch": 0.57, + "learning_rate": 2.139851457461802e-05, + "loss": 0.1243, + "step": 256810 + }, + { + "epoch": 0.57, + "learning_rate": 2.1397396031408695e-05, + "loss": 0.1234, + "step": 256820 + }, + { + "epoch": 0.57, + "learning_rate": 2.139627748819937e-05, + "loss": 0.1261, + "step": 256830 + }, + { + "epoch": 0.57, + "learning_rate": 2.1395158944990044e-05, + "loss": 0.1295, + "step": 256840 + }, + { + "epoch": 0.57, + "learning_rate": 2.1394040401780722e-05, + "loss": 0.1224, + "step": 256850 + }, + { + "epoch": 0.57, + "learning_rate": 2.1392921858571397e-05, + "loss": 0.1237, + "step": 256860 + }, + { + "epoch": 0.57, + "learning_rate": 2.1391803315362075e-05, + "loss": 0.1248, + "step": 256870 + }, + { + "epoch": 0.57, + "learning_rate": 2.139068477215275e-05, + "loss": 0.1233, + "step": 256880 + }, + { + "epoch": 0.57, + "learning_rate": 2.1389566228943424e-05, + "loss": 0.1228, + "step": 256890 + }, + { + "epoch": 0.57, + "learning_rate": 2.13884476857341e-05, + "loss": 0.1251, + "step": 256900 + }, + { + "epoch": 0.57, + "learning_rate": 2.1387329142524776e-05, + "loss": 0.1214, + "step": 256910 + }, + { + "epoch": 0.57, + "learning_rate": 2.1386210599315454e-05, + "loss": 0.1197, + "step": 256920 + }, + { + "epoch": 0.57, + "learning_rate": 2.138509205610613e-05, + "loss": 0.1234, + "step": 256930 + }, + { + "epoch": 0.57, + "learning_rate": 2.1383973512896803e-05, + "loss": 0.1253, + "step": 256940 + }, + { + "epoch": 0.57, + "learning_rate": 2.138285496968748e-05, + "loss": 0.1238, + "step": 256950 + }, + { + "epoch": 0.57, + "learning_rate": 2.1381736426478156e-05, + "loss": 0.1168, + "step": 256960 + }, + { + "epoch": 0.57, + "learning_rate": 2.1380617883268834e-05, + "loss": 0.1181, + "step": 256970 + }, + { + "epoch": 0.57, + "learning_rate": 2.1379499340059508e-05, + "loss": 0.1255, + "step": 256980 + }, + { + "epoch": 0.57, + "learning_rate": 2.1378380796850183e-05, + "loss": 0.1221, + "step": 256990 + }, + { + "epoch": 0.57, + "learning_rate": 2.137726225364086e-05, + "loss": 0.1252, + "step": 257000 + }, + { + "epoch": 0.57, + "learning_rate": 2.1376143710431535e-05, + "loss": 0.1212, + "step": 257010 + }, + { + "epoch": 0.57, + "learning_rate": 2.137502516722221e-05, + "loss": 0.1252, + "step": 257020 + }, + { + "epoch": 0.57, + "learning_rate": 2.1373906624012888e-05, + "loss": 0.124, + "step": 257030 + }, + { + "epoch": 0.57, + "learning_rate": 2.1372788080803562e-05, + "loss": 0.1192, + "step": 257040 + }, + { + "epoch": 0.57, + "learning_rate": 2.1371669537594237e-05, + "loss": 0.1215, + "step": 257050 + }, + { + "epoch": 0.57, + "learning_rate": 2.1370550994384915e-05, + "loss": 0.1218, + "step": 257060 + }, + { + "epoch": 0.57, + "learning_rate": 2.136943245117559e-05, + "loss": 0.124, + "step": 257070 + }, + { + "epoch": 0.57, + "learning_rate": 2.1368313907966267e-05, + "loss": 0.1195, + "step": 257080 + }, + { + "epoch": 0.57, + "learning_rate": 2.136719536475694e-05, + "loss": 0.1221, + "step": 257090 + }, + { + "epoch": 0.57, + "learning_rate": 2.1366076821547616e-05, + "loss": 0.1204, + "step": 257100 + }, + { + "epoch": 0.57, + "learning_rate": 2.1364958278338294e-05, + "loss": 0.1216, + "step": 257110 + }, + { + "epoch": 0.57, + "learning_rate": 2.136383973512897e-05, + "loss": 0.1261, + "step": 257120 + }, + { + "epoch": 0.57, + "learning_rate": 2.1362721191919643e-05, + "loss": 0.1219, + "step": 257130 + }, + { + "epoch": 0.57, + "learning_rate": 2.136160264871032e-05, + "loss": 0.1198, + "step": 257140 + }, + { + "epoch": 0.57, + "learning_rate": 2.1360484105500996e-05, + "loss": 0.1215, + "step": 257150 + }, + { + "epoch": 0.57, + "learning_rate": 2.1359365562291673e-05, + "loss": 0.1195, + "step": 257160 + }, + { + "epoch": 0.57, + "learning_rate": 2.1358247019082348e-05, + "loss": 0.1199, + "step": 257170 + }, + { + "epoch": 0.57, + "learning_rate": 2.1357128475873023e-05, + "loss": 0.1241, + "step": 257180 + }, + { + "epoch": 0.57, + "learning_rate": 2.13560099326637e-05, + "loss": 0.1281, + "step": 257190 + }, + { + "epoch": 0.57, + "learning_rate": 2.1354891389454375e-05, + "loss": 0.1179, + "step": 257200 + }, + { + "epoch": 0.57, + "learning_rate": 2.1353772846245053e-05, + "loss": 0.1255, + "step": 257210 + }, + { + "epoch": 0.57, + "learning_rate": 2.1352654303035727e-05, + "loss": 0.1247, + "step": 257220 + }, + { + "epoch": 0.57, + "learning_rate": 2.1351535759826402e-05, + "loss": 0.1275, + "step": 257230 + }, + { + "epoch": 0.57, + "learning_rate": 2.135041721661708e-05, + "loss": 0.1179, + "step": 257240 + }, + { + "epoch": 0.57, + "learning_rate": 2.1349298673407755e-05, + "loss": 0.1208, + "step": 257250 + }, + { + "epoch": 0.57, + "learning_rate": 2.1348180130198432e-05, + "loss": 0.1192, + "step": 257260 + }, + { + "epoch": 0.57, + "learning_rate": 2.1347061586989107e-05, + "loss": 0.1223, + "step": 257270 + }, + { + "epoch": 0.57, + "learning_rate": 2.134594304377978e-05, + "loss": 0.1218, + "step": 257280 + }, + { + "epoch": 0.57, + "learning_rate": 2.1344824500570456e-05, + "loss": 0.1229, + "step": 257290 + }, + { + "epoch": 0.57, + "learning_rate": 2.1343705957361134e-05, + "loss": 0.1209, + "step": 257300 + }, + { + "epoch": 0.57, + "learning_rate": 2.134258741415181e-05, + "loss": 0.1208, + "step": 257310 + }, + { + "epoch": 0.57, + "learning_rate": 2.1341468870942486e-05, + "loss": 0.1188, + "step": 257320 + }, + { + "epoch": 0.57, + "learning_rate": 2.134035032773316e-05, + "loss": 0.1202, + "step": 257330 + }, + { + "epoch": 0.57, + "learning_rate": 2.1339231784523836e-05, + "loss": 0.1256, + "step": 257340 + }, + { + "epoch": 0.57, + "learning_rate": 2.1338225095635444e-05, + "loss": 0.1207, + "step": 257350 + }, + { + "epoch": 0.57, + "learning_rate": 2.133710655242612e-05, + "loss": 0.1227, + "step": 257360 + }, + { + "epoch": 0.57, + "learning_rate": 2.1335988009216797e-05, + "loss": 0.1177, + "step": 257370 + }, + { + "epoch": 0.57, + "learning_rate": 2.1334869466007475e-05, + "loss": 0.1212, + "step": 257380 + }, + { + "epoch": 0.57, + "learning_rate": 2.133375092279815e-05, + "loss": 0.122, + "step": 257390 + }, + { + "epoch": 0.57, + "learning_rate": 2.1332632379588824e-05, + "loss": 0.1243, + "step": 257400 + }, + { + "epoch": 0.57, + "learning_rate": 2.13315138363795e-05, + "loss": 0.1238, + "step": 257410 + }, + { + "epoch": 0.57, + "learning_rate": 2.1330395293170176e-05, + "loss": 0.1247, + "step": 257420 + }, + { + "epoch": 0.57, + "learning_rate": 2.1329276749960854e-05, + "loss": 0.1266, + "step": 257430 + }, + { + "epoch": 0.57, + "learning_rate": 2.132815820675153e-05, + "loss": 0.1254, + "step": 257440 + }, + { + "epoch": 0.57, + "learning_rate": 2.1327039663542203e-05, + "loss": 0.1226, + "step": 257450 + }, + { + "epoch": 0.57, + "learning_rate": 2.1325921120332878e-05, + "loss": 0.1201, + "step": 257460 + }, + { + "epoch": 0.57, + "learning_rate": 2.1324802577123556e-05, + "loss": 0.1203, + "step": 257470 + }, + { + "epoch": 0.57, + "learning_rate": 2.132368403391423e-05, + "loss": 0.1232, + "step": 257480 + }, + { + "epoch": 0.57, + "learning_rate": 2.1322565490704908e-05, + "loss": 0.1209, + "step": 257490 + }, + { + "epoch": 0.57, + "learning_rate": 2.1321446947495583e-05, + "loss": 0.1218, + "step": 257500 + }, + { + "epoch": 0.57, + "learning_rate": 2.1320328404286257e-05, + "loss": 0.1211, + "step": 257510 + }, + { + "epoch": 0.57, + "learning_rate": 2.1319209861076932e-05, + "loss": 0.1254, + "step": 257520 + }, + { + "epoch": 0.57, + "learning_rate": 2.131809131786761e-05, + "loss": 0.1202, + "step": 257530 + }, + { + "epoch": 0.57, + "learning_rate": 2.1316972774658288e-05, + "loss": 0.126, + "step": 257540 + }, + { + "epoch": 0.57, + "learning_rate": 2.1315854231448962e-05, + "loss": 0.1267, + "step": 257550 + }, + { + "epoch": 0.57, + "learning_rate": 2.1314735688239637e-05, + "loss": 0.1149, + "step": 257560 + }, + { + "epoch": 0.57, + "learning_rate": 2.131361714503031e-05, + "loss": 0.1247, + "step": 257570 + }, + { + "epoch": 0.57, + "learning_rate": 2.131249860182099e-05, + "loss": 0.1235, + "step": 257580 + }, + { + "epoch": 0.57, + "learning_rate": 2.1311380058611667e-05, + "loss": 0.121, + "step": 257590 + }, + { + "epoch": 0.57, + "learning_rate": 2.131026151540234e-05, + "loss": 0.1284, + "step": 257600 + }, + { + "epoch": 0.58, + "learning_rate": 2.1309142972193016e-05, + "loss": 0.1252, + "step": 257610 + }, + { + "epoch": 0.58, + "learning_rate": 2.130802442898369e-05, + "loss": 0.1222, + "step": 257620 + }, + { + "epoch": 0.58, + "learning_rate": 2.130690588577437e-05, + "loss": 0.1215, + "step": 257630 + }, + { + "epoch": 0.58, + "learning_rate": 2.1305787342565047e-05, + "loss": 0.1208, + "step": 257640 + }, + { + "epoch": 0.58, + "learning_rate": 2.130466879935572e-05, + "loss": 0.1257, + "step": 257650 + }, + { + "epoch": 0.58, + "learning_rate": 2.1303550256146396e-05, + "loss": 0.1286, + "step": 257660 + }, + { + "epoch": 0.58, + "learning_rate": 2.130243171293707e-05, + "loss": 0.1287, + "step": 257670 + }, + { + "epoch": 0.58, + "learning_rate": 2.1301313169727745e-05, + "loss": 0.1207, + "step": 257680 + }, + { + "epoch": 0.58, + "learning_rate": 2.1300194626518423e-05, + "loss": 0.1224, + "step": 257690 + }, + { + "epoch": 0.58, + "learning_rate": 2.12990760833091e-05, + "loss": 0.1252, + "step": 257700 + }, + { + "epoch": 0.58, + "learning_rate": 2.1297957540099775e-05, + "loss": 0.1199, + "step": 257710 + }, + { + "epoch": 0.58, + "learning_rate": 2.129683899689045e-05, + "loss": 0.1256, + "step": 257720 + }, + { + "epoch": 0.58, + "learning_rate": 2.1295720453681124e-05, + "loss": 0.1252, + "step": 257730 + }, + { + "epoch": 0.58, + "learning_rate": 2.1294601910471802e-05, + "loss": 0.12, + "step": 257740 + }, + { + "epoch": 0.58, + "learning_rate": 2.129348336726248e-05, + "loss": 0.1202, + "step": 257750 + }, + { + "epoch": 0.58, + "learning_rate": 2.1292364824053155e-05, + "loss": 0.1265, + "step": 257760 + }, + { + "epoch": 0.58, + "learning_rate": 2.129124628084383e-05, + "loss": 0.1259, + "step": 257770 + }, + { + "epoch": 0.58, + "learning_rate": 2.1290127737634504e-05, + "loss": 0.1268, + "step": 257780 + }, + { + "epoch": 0.58, + "learning_rate": 2.128900919442518e-05, + "loss": 0.122, + "step": 257790 + }, + { + "epoch": 0.58, + "learning_rate": 2.128789065121586e-05, + "loss": 0.1224, + "step": 257800 + }, + { + "epoch": 0.58, + "learning_rate": 2.1286772108006534e-05, + "loss": 0.1203, + "step": 257810 + }, + { + "epoch": 0.58, + "learning_rate": 2.128565356479721e-05, + "loss": 0.123, + "step": 257820 + }, + { + "epoch": 0.58, + "learning_rate": 2.1284535021587883e-05, + "loss": 0.1233, + "step": 257830 + }, + { + "epoch": 0.58, + "learning_rate": 2.128341647837856e-05, + "loss": 0.1227, + "step": 257840 + }, + { + "epoch": 0.58, + "learning_rate": 2.128229793516924e-05, + "loss": 0.1242, + "step": 257850 + }, + { + "epoch": 0.58, + "learning_rate": 2.1281179391959914e-05, + "loss": 0.1252, + "step": 257860 + }, + { + "epoch": 0.58, + "learning_rate": 2.1280060848750588e-05, + "loss": 0.1191, + "step": 257870 + }, + { + "epoch": 0.58, + "learning_rate": 2.1278942305541263e-05, + "loss": 0.1245, + "step": 257880 + }, + { + "epoch": 0.58, + "learning_rate": 2.1277823762331937e-05, + "loss": 0.124, + "step": 257890 + }, + { + "epoch": 0.58, + "learning_rate": 2.127670521912262e-05, + "loss": 0.1238, + "step": 257900 + }, + { + "epoch": 0.58, + "learning_rate": 2.1275586675913293e-05, + "loss": 0.1248, + "step": 257910 + }, + { + "epoch": 0.58, + "learning_rate": 2.1274468132703968e-05, + "loss": 0.1209, + "step": 257920 + }, + { + "epoch": 0.58, + "learning_rate": 2.1273349589494642e-05, + "loss": 0.1233, + "step": 257930 + }, + { + "epoch": 0.58, + "learning_rate": 2.1272231046285317e-05, + "loss": 0.1261, + "step": 257940 + }, + { + "epoch": 0.58, + "learning_rate": 2.1271112503075995e-05, + "loss": 0.1247, + "step": 257950 + }, + { + "epoch": 0.58, + "learning_rate": 2.1269993959866673e-05, + "loss": 0.1221, + "step": 257960 + }, + { + "epoch": 0.58, + "learning_rate": 2.1268875416657347e-05, + "loss": 0.122, + "step": 257970 + }, + { + "epoch": 0.58, + "learning_rate": 2.126775687344802e-05, + "loss": 0.1213, + "step": 257980 + }, + { + "epoch": 0.58, + "learning_rate": 2.1266638330238696e-05, + "loss": 0.1207, + "step": 257990 + }, + { + "epoch": 0.58, + "learning_rate": 2.1265519787029374e-05, + "loss": 0.1253, + "step": 258000 + }, + { + "epoch": 0.58, + "learning_rate": 2.1264401243820052e-05, + "loss": 0.1221, + "step": 258010 + }, + { + "epoch": 0.58, + "learning_rate": 2.1263282700610727e-05, + "loss": 0.1262, + "step": 258020 + }, + { + "epoch": 0.58, + "learning_rate": 2.12621641574014e-05, + "loss": 0.1215, + "step": 258030 + }, + { + "epoch": 0.58, + "learning_rate": 2.1261045614192076e-05, + "loss": 0.1231, + "step": 258040 + }, + { + "epoch": 0.58, + "learning_rate": 2.1259927070982754e-05, + "loss": 0.1223, + "step": 258050 + }, + { + "epoch": 0.58, + "learning_rate": 2.125880852777343e-05, + "loss": 0.1231, + "step": 258060 + }, + { + "epoch": 0.58, + "learning_rate": 2.1257689984564106e-05, + "loss": 0.1259, + "step": 258070 + }, + { + "epoch": 0.58, + "learning_rate": 2.125657144135478e-05, + "loss": 0.1169, + "step": 258080 + }, + { + "epoch": 0.58, + "learning_rate": 2.1255452898145455e-05, + "loss": 0.1219, + "step": 258090 + }, + { + "epoch": 0.58, + "learning_rate": 2.125433435493613e-05, + "loss": 0.1239, + "step": 258100 + }, + { + "epoch": 0.58, + "learning_rate": 2.125321581172681e-05, + "loss": 0.1234, + "step": 258110 + }, + { + "epoch": 0.58, + "learning_rate": 2.1252097268517485e-05, + "loss": 0.1242, + "step": 258120 + }, + { + "epoch": 0.58, + "learning_rate": 2.125097872530816e-05, + "loss": 0.1232, + "step": 258130 + }, + { + "epoch": 0.58, + "learning_rate": 2.1249860182098835e-05, + "loss": 0.1223, + "step": 258140 + }, + { + "epoch": 0.58, + "learning_rate": 2.124874163888951e-05, + "loss": 0.1264, + "step": 258150 + }, + { + "epoch": 0.58, + "learning_rate": 2.1247623095680187e-05, + "loss": 0.1224, + "step": 258160 + }, + { + "epoch": 0.58, + "learning_rate": 2.1246504552470865e-05, + "loss": 0.1218, + "step": 258170 + }, + { + "epoch": 0.58, + "learning_rate": 2.124538600926154e-05, + "loss": 0.125, + "step": 258180 + }, + { + "epoch": 0.58, + "learning_rate": 2.1244267466052214e-05, + "loss": 0.1171, + "step": 258190 + }, + { + "epoch": 0.58, + "learning_rate": 2.124314892284289e-05, + "loss": 0.124, + "step": 258200 + }, + { + "epoch": 0.58, + "learning_rate": 2.1242030379633567e-05, + "loss": 0.1235, + "step": 258210 + }, + { + "epoch": 0.58, + "learning_rate": 2.1240911836424244e-05, + "loss": 0.1247, + "step": 258220 + }, + { + "epoch": 0.58, + "learning_rate": 2.123979329321492e-05, + "loss": 0.1227, + "step": 258230 + }, + { + "epoch": 0.58, + "learning_rate": 2.1238674750005594e-05, + "loss": 0.1257, + "step": 258240 + }, + { + "epoch": 0.58, + "learning_rate": 2.1237556206796268e-05, + "loss": 0.1215, + "step": 258250 + }, + { + "epoch": 0.58, + "learning_rate": 2.1236437663586946e-05, + "loss": 0.1215, + "step": 258260 + }, + { + "epoch": 0.58, + "learning_rate": 2.1235319120377624e-05, + "loss": 0.1211, + "step": 258270 + }, + { + "epoch": 0.58, + "learning_rate": 2.12342005771683e-05, + "loss": 0.1213, + "step": 258280 + }, + { + "epoch": 0.58, + "learning_rate": 2.1233082033958973e-05, + "loss": 0.1226, + "step": 258290 + }, + { + "epoch": 0.58, + "learning_rate": 2.1231963490749648e-05, + "loss": 0.1281, + "step": 258300 + }, + { + "epoch": 0.58, + "learning_rate": 2.1230844947540322e-05, + "loss": 0.1243, + "step": 258310 + }, + { + "epoch": 0.58, + "learning_rate": 2.1229726404331e-05, + "loss": 0.1288, + "step": 258320 + }, + { + "epoch": 0.58, + "learning_rate": 2.1228607861121678e-05, + "loss": 0.1238, + "step": 258330 + }, + { + "epoch": 0.58, + "learning_rate": 2.1227489317912352e-05, + "loss": 0.1251, + "step": 258340 + }, + { + "epoch": 0.58, + "learning_rate": 2.1226370774703027e-05, + "loss": 0.1205, + "step": 258350 + }, + { + "epoch": 0.58, + "learning_rate": 2.12252522314937e-05, + "loss": 0.1202, + "step": 258360 + }, + { + "epoch": 0.58, + "learning_rate": 2.122413368828438e-05, + "loss": 0.1285, + "step": 258370 + }, + { + "epoch": 0.58, + "learning_rate": 2.1223015145075057e-05, + "loss": 0.1228, + "step": 258380 + }, + { + "epoch": 0.58, + "learning_rate": 2.1221896601865732e-05, + "loss": 0.1235, + "step": 258390 + }, + { + "epoch": 0.58, + "learning_rate": 2.1220778058656406e-05, + "loss": 0.1271, + "step": 258400 + }, + { + "epoch": 0.58, + "learning_rate": 2.121965951544708e-05, + "loss": 0.1238, + "step": 258410 + }, + { + "epoch": 0.58, + "learning_rate": 2.121854097223776e-05, + "loss": 0.1251, + "step": 258420 + }, + { + "epoch": 0.58, + "learning_rate": 2.1217422429028437e-05, + "loss": 0.1253, + "step": 258430 + }, + { + "epoch": 0.58, + "learning_rate": 2.121630388581911e-05, + "loss": 0.1236, + "step": 258440 + }, + { + "epoch": 0.58, + "learning_rate": 2.1215185342609786e-05, + "loss": 0.1182, + "step": 258450 + }, + { + "epoch": 0.58, + "learning_rate": 2.121406679940046e-05, + "loss": 0.1264, + "step": 258460 + }, + { + "epoch": 0.58, + "learning_rate": 2.121294825619114e-05, + "loss": 0.1222, + "step": 258470 + }, + { + "epoch": 0.58, + "learning_rate": 2.1211829712981813e-05, + "loss": 0.1209, + "step": 258480 + }, + { + "epoch": 0.58, + "learning_rate": 2.121071116977249e-05, + "loss": 0.1244, + "step": 258490 + }, + { + "epoch": 0.58, + "learning_rate": 2.1209592626563165e-05, + "loss": 0.1221, + "step": 258500 + }, + { + "epoch": 0.58, + "learning_rate": 2.120847408335384e-05, + "loss": 0.1222, + "step": 258510 + }, + { + "epoch": 0.58, + "learning_rate": 2.1207355540144515e-05, + "loss": 0.1183, + "step": 258520 + }, + { + "epoch": 0.58, + "learning_rate": 2.1206236996935192e-05, + "loss": 0.1206, + "step": 258530 + }, + { + "epoch": 0.58, + "learning_rate": 2.120511845372587e-05, + "loss": 0.1248, + "step": 258540 + }, + { + "epoch": 0.58, + "learning_rate": 2.1203999910516545e-05, + "loss": 0.1276, + "step": 258550 + }, + { + "epoch": 0.58, + "learning_rate": 2.120288136730722e-05, + "loss": 0.1223, + "step": 258560 + }, + { + "epoch": 0.58, + "learning_rate": 2.1201762824097894e-05, + "loss": 0.1174, + "step": 258570 + }, + { + "epoch": 0.58, + "learning_rate": 2.1200644280888572e-05, + "loss": 0.1184, + "step": 258580 + }, + { + "epoch": 0.58, + "learning_rate": 2.119952573767925e-05, + "loss": 0.1209, + "step": 258590 + }, + { + "epoch": 0.58, + "learning_rate": 2.1198407194469924e-05, + "loss": 0.1196, + "step": 258600 + }, + { + "epoch": 0.58, + "learning_rate": 2.11972886512606e-05, + "loss": 0.1226, + "step": 258610 + }, + { + "epoch": 0.58, + "learning_rate": 2.1196170108051273e-05, + "loss": 0.1177, + "step": 258620 + }, + { + "epoch": 0.58, + "learning_rate": 2.119505156484195e-05, + "loss": 0.1213, + "step": 258630 + }, + { + "epoch": 0.58, + "learning_rate": 2.1193933021632626e-05, + "loss": 0.1256, + "step": 258640 + }, + { + "epoch": 0.58, + "learning_rate": 2.1192814478423304e-05, + "loss": 0.1241, + "step": 258650 + }, + { + "epoch": 0.58, + "learning_rate": 2.119169593521398e-05, + "loss": 0.1233, + "step": 258660 + }, + { + "epoch": 0.58, + "learning_rate": 2.1190577392004653e-05, + "loss": 0.1235, + "step": 258670 + }, + { + "epoch": 0.58, + "learning_rate": 2.118945884879533e-05, + "loss": 0.1184, + "step": 258680 + }, + { + "epoch": 0.58, + "learning_rate": 2.1188340305586005e-05, + "loss": 0.1193, + "step": 258690 + }, + { + "epoch": 0.58, + "learning_rate": 2.1187221762376683e-05, + "loss": 0.1215, + "step": 258700 + }, + { + "epoch": 0.58, + "learning_rate": 2.1186103219167358e-05, + "loss": 0.1196, + "step": 258710 + }, + { + "epoch": 0.58, + "learning_rate": 2.1184984675958032e-05, + "loss": 0.1259, + "step": 258720 + }, + { + "epoch": 0.58, + "learning_rate": 2.118386613274871e-05, + "loss": 0.1191, + "step": 258730 + }, + { + "epoch": 0.58, + "learning_rate": 2.1182747589539385e-05, + "loss": 0.1255, + "step": 258740 + }, + { + "epoch": 0.58, + "learning_rate": 2.1181629046330063e-05, + "loss": 0.127, + "step": 258750 + }, + { + "epoch": 0.58, + "learning_rate": 2.1180510503120737e-05, + "loss": 0.1234, + "step": 258760 + }, + { + "epoch": 0.58, + "learning_rate": 2.1179391959911412e-05, + "loss": 0.1255, + "step": 258770 + }, + { + "epoch": 0.58, + "learning_rate": 2.1178273416702086e-05, + "loss": 0.1296, + "step": 258780 + }, + { + "epoch": 0.58, + "learning_rate": 2.1177154873492764e-05, + "loss": 0.1253, + "step": 258790 + }, + { + "epoch": 0.58, + "learning_rate": 2.117603633028344e-05, + "loss": 0.1221, + "step": 258800 + }, + { + "epoch": 0.58, + "learning_rate": 2.1174917787074117e-05, + "loss": 0.1177, + "step": 258810 + }, + { + "epoch": 0.58, + "learning_rate": 2.117379924386479e-05, + "loss": 0.1224, + "step": 258820 + }, + { + "epoch": 0.58, + "learning_rate": 2.1172680700655466e-05, + "loss": 0.1225, + "step": 258830 + }, + { + "epoch": 0.58, + "learning_rate": 2.1171562157446144e-05, + "loss": 0.1257, + "step": 258840 + }, + { + "epoch": 0.58, + "learning_rate": 2.117044361423682e-05, + "loss": 0.1222, + "step": 258850 + }, + { + "epoch": 0.58, + "learning_rate": 2.1169325071027496e-05, + "loss": 0.1182, + "step": 258860 + }, + { + "epoch": 0.58, + "learning_rate": 2.116820652781817e-05, + "loss": 0.1178, + "step": 258870 + }, + { + "epoch": 0.58, + "learning_rate": 2.1167087984608845e-05, + "loss": 0.1221, + "step": 258880 + }, + { + "epoch": 0.58, + "learning_rate": 2.1165969441399523e-05, + "loss": 0.1199, + "step": 258890 + }, + { + "epoch": 0.58, + "learning_rate": 2.1164850898190198e-05, + "loss": 0.1188, + "step": 258900 + }, + { + "epoch": 0.58, + "learning_rate": 2.1163732354980876e-05, + "loss": 0.1182, + "step": 258910 + }, + { + "epoch": 0.58, + "learning_rate": 2.116261381177155e-05, + "loss": 0.1243, + "step": 258920 + }, + { + "epoch": 0.58, + "learning_rate": 2.1161495268562225e-05, + "loss": 0.1275, + "step": 258930 + }, + { + "epoch": 0.58, + "learning_rate": 2.1160376725352903e-05, + "loss": 0.1247, + "step": 258940 + }, + { + "epoch": 0.58, + "learning_rate": 2.1159258182143577e-05, + "loss": 0.1225, + "step": 258950 + }, + { + "epoch": 0.58, + "learning_rate": 2.1158139638934252e-05, + "loss": 0.1226, + "step": 258960 + }, + { + "epoch": 0.58, + "learning_rate": 2.115702109572493e-05, + "loss": 0.1161, + "step": 258970 + }, + { + "epoch": 0.58, + "learning_rate": 2.1155902552515604e-05, + "loss": 0.126, + "step": 258980 + }, + { + "epoch": 0.58, + "learning_rate": 2.115478400930628e-05, + "loss": 0.1209, + "step": 258990 + }, + { + "epoch": 0.58, + "learning_rate": 2.1153665466096957e-05, + "loss": 0.124, + "step": 259000 + }, + { + "epoch": 0.58, + "learning_rate": 2.115254692288763e-05, + "loss": 0.1209, + "step": 259010 + }, + { + "epoch": 0.58, + "learning_rate": 2.115142837967831e-05, + "loss": 0.1242, + "step": 259020 + }, + { + "epoch": 0.58, + "learning_rate": 2.1150309836468984e-05, + "loss": 0.1208, + "step": 259030 + }, + { + "epoch": 0.58, + "learning_rate": 2.114919129325966e-05, + "loss": 0.1211, + "step": 259040 + }, + { + "epoch": 0.58, + "learning_rate": 2.1148072750050336e-05, + "loss": 0.1244, + "step": 259050 + }, + { + "epoch": 0.58, + "learning_rate": 2.114695420684101e-05, + "loss": 0.125, + "step": 259060 + }, + { + "epoch": 0.58, + "learning_rate": 2.114583566363169e-05, + "loss": 0.1257, + "step": 259070 + }, + { + "epoch": 0.58, + "learning_rate": 2.1144717120422363e-05, + "loss": 0.119, + "step": 259080 + }, + { + "epoch": 0.58, + "learning_rate": 2.1143598577213038e-05, + "loss": 0.1216, + "step": 259090 + }, + { + "epoch": 0.58, + "learning_rate": 2.1142480034003716e-05, + "loss": 0.1273, + "step": 259100 + }, + { + "epoch": 0.58, + "learning_rate": 2.114136149079439e-05, + "loss": 0.1197, + "step": 259110 + }, + { + "epoch": 0.58, + "learning_rate": 2.1140242947585065e-05, + "loss": 0.1241, + "step": 259120 + }, + { + "epoch": 0.58, + "learning_rate": 2.1139124404375743e-05, + "loss": 0.1243, + "step": 259130 + }, + { + "epoch": 0.58, + "learning_rate": 2.1138005861166417e-05, + "loss": 0.1197, + "step": 259140 + }, + { + "epoch": 0.58, + "learning_rate": 2.1136887317957095e-05, + "loss": 0.129, + "step": 259150 + }, + { + "epoch": 0.58, + "learning_rate": 2.113576877474777e-05, + "loss": 0.1259, + "step": 259160 + }, + { + "epoch": 0.58, + "learning_rate": 2.1134650231538444e-05, + "loss": 0.125, + "step": 259170 + }, + { + "epoch": 0.58, + "learning_rate": 2.1133531688329122e-05, + "loss": 0.1273, + "step": 259180 + }, + { + "epoch": 0.58, + "learning_rate": 2.1132413145119797e-05, + "loss": 0.1229, + "step": 259190 + }, + { + "epoch": 0.58, + "learning_rate": 2.113129460191047e-05, + "loss": 0.1256, + "step": 259200 + }, + { + "epoch": 0.58, + "learning_rate": 2.113017605870115e-05, + "loss": 0.1234, + "step": 259210 + }, + { + "epoch": 0.58, + "learning_rate": 2.1129057515491824e-05, + "loss": 0.1242, + "step": 259220 + }, + { + "epoch": 0.58, + "learning_rate": 2.11279389722825e-05, + "loss": 0.1223, + "step": 259230 + }, + { + "epoch": 0.58, + "learning_rate": 2.1126820429073176e-05, + "loss": 0.1215, + "step": 259240 + }, + { + "epoch": 0.58, + "learning_rate": 2.112570188586385e-05, + "loss": 0.1226, + "step": 259250 + }, + { + "epoch": 0.58, + "learning_rate": 2.112458334265453e-05, + "loss": 0.1203, + "step": 259260 + }, + { + "epoch": 0.58, + "learning_rate": 2.1123464799445203e-05, + "loss": 0.1244, + "step": 259270 + }, + { + "epoch": 0.58, + "learning_rate": 2.1122346256235878e-05, + "loss": 0.1224, + "step": 259280 + }, + { + "epoch": 0.58, + "learning_rate": 2.1121227713026556e-05, + "loss": 0.123, + "step": 259290 + }, + { + "epoch": 0.58, + "learning_rate": 2.112010916981723e-05, + "loss": 0.1232, + "step": 259300 + }, + { + "epoch": 0.58, + "learning_rate": 2.1118990626607908e-05, + "loss": 0.1222, + "step": 259310 + }, + { + "epoch": 0.58, + "learning_rate": 2.1117872083398583e-05, + "loss": 0.1276, + "step": 259320 + }, + { + "epoch": 0.58, + "learning_rate": 2.1116753540189257e-05, + "loss": 0.1203, + "step": 259330 + }, + { + "epoch": 0.58, + "learning_rate": 2.1115634996979935e-05, + "loss": 0.121, + "step": 259340 + }, + { + "epoch": 0.58, + "learning_rate": 2.111451645377061e-05, + "loss": 0.1162, + "step": 259350 + }, + { + "epoch": 0.58, + "learning_rate": 2.1113397910561288e-05, + "loss": 0.1235, + "step": 259360 + }, + { + "epoch": 0.58, + "learning_rate": 2.1112279367351962e-05, + "loss": 0.1194, + "step": 259370 + }, + { + "epoch": 0.58, + "learning_rate": 2.1111160824142637e-05, + "loss": 0.1258, + "step": 259380 + }, + { + "epoch": 0.58, + "learning_rate": 2.1110042280933315e-05, + "loss": 0.1271, + "step": 259390 + }, + { + "epoch": 0.58, + "learning_rate": 2.110892373772399e-05, + "loss": 0.1233, + "step": 259400 + }, + { + "epoch": 0.58, + "learning_rate": 2.1107805194514667e-05, + "loss": 0.1207, + "step": 259410 + }, + { + "epoch": 0.58, + "learning_rate": 2.110668665130534e-05, + "loss": 0.1236, + "step": 259420 + }, + { + "epoch": 0.58, + "learning_rate": 2.1105568108096016e-05, + "loss": 0.1222, + "step": 259430 + }, + { + "epoch": 0.58, + "learning_rate": 2.110444956488669e-05, + "loss": 0.121, + "step": 259440 + }, + { + "epoch": 0.58, + "learning_rate": 2.110333102167737e-05, + "loss": 0.1168, + "step": 259450 + }, + { + "epoch": 0.58, + "learning_rate": 2.1102212478468043e-05, + "loss": 0.1206, + "step": 259460 + }, + { + "epoch": 0.58, + "learning_rate": 2.110109393525872e-05, + "loss": 0.1233, + "step": 259470 + }, + { + "epoch": 0.58, + "learning_rate": 2.1099975392049396e-05, + "loss": 0.1252, + "step": 259480 + }, + { + "epoch": 0.58, + "learning_rate": 2.109885684884007e-05, + "loss": 0.1241, + "step": 259490 + }, + { + "epoch": 0.58, + "learning_rate": 2.1097738305630748e-05, + "loss": 0.1236, + "step": 259500 + }, + { + "epoch": 0.58, + "learning_rate": 2.1096619762421423e-05, + "loss": 0.1192, + "step": 259510 + }, + { + "epoch": 0.58, + "learning_rate": 2.10955012192121e-05, + "loss": 0.1229, + "step": 259520 + }, + { + "epoch": 0.58, + "learning_rate": 2.1094382676002775e-05, + "loss": 0.1201, + "step": 259530 + }, + { + "epoch": 0.58, + "learning_rate": 2.109326413279345e-05, + "loss": 0.118, + "step": 259540 + }, + { + "epoch": 0.58, + "learning_rate": 2.1092145589584128e-05, + "loss": 0.1211, + "step": 259550 + }, + { + "epoch": 0.58, + "learning_rate": 2.1091027046374802e-05, + "loss": 0.121, + "step": 259560 + }, + { + "epoch": 0.58, + "learning_rate": 2.108990850316548e-05, + "loss": 0.1224, + "step": 259570 + }, + { + "epoch": 0.58, + "learning_rate": 2.1088789959956155e-05, + "loss": 0.1222, + "step": 259580 + }, + { + "epoch": 0.58, + "learning_rate": 2.108767141674683e-05, + "loss": 0.1237, + "step": 259590 + }, + { + "epoch": 0.58, + "learning_rate": 2.1086552873537504e-05, + "loss": 0.1232, + "step": 259600 + }, + { + "epoch": 0.58, + "learning_rate": 2.108543433032818e-05, + "loss": 0.1236, + "step": 259610 + }, + { + "epoch": 0.58, + "learning_rate": 2.108431578711886e-05, + "loss": 0.1229, + "step": 259620 + }, + { + "epoch": 0.58, + "learning_rate": 2.1083197243909534e-05, + "loss": 0.1202, + "step": 259630 + }, + { + "epoch": 0.58, + "learning_rate": 2.108207870070021e-05, + "loss": 0.1265, + "step": 259640 + }, + { + "epoch": 0.58, + "learning_rate": 2.1080960157490883e-05, + "loss": 0.1228, + "step": 259650 + }, + { + "epoch": 0.58, + "learning_rate": 2.107984161428156e-05, + "loss": 0.1205, + "step": 259660 + }, + { + "epoch": 0.58, + "learning_rate": 2.1078723071072236e-05, + "loss": 0.1196, + "step": 259670 + }, + { + "epoch": 0.58, + "learning_rate": 2.1077604527862914e-05, + "loss": 0.1196, + "step": 259680 + }, + { + "epoch": 0.58, + "learning_rate": 2.1076485984653588e-05, + "loss": 0.1216, + "step": 259690 + }, + { + "epoch": 0.58, + "learning_rate": 2.1075367441444263e-05, + "loss": 0.1238, + "step": 259700 + }, + { + "epoch": 0.58, + "learning_rate": 2.107424889823494e-05, + "loss": 0.1253, + "step": 259710 + }, + { + "epoch": 0.58, + "learning_rate": 2.1073130355025615e-05, + "loss": 0.1243, + "step": 259720 + }, + { + "epoch": 0.58, + "learning_rate": 2.1072011811816293e-05, + "loss": 0.1202, + "step": 259730 + }, + { + "epoch": 0.58, + "learning_rate": 2.1070893268606968e-05, + "loss": 0.1265, + "step": 259740 + }, + { + "epoch": 0.58, + "learning_rate": 2.1069774725397642e-05, + "loss": 0.1207, + "step": 259750 + }, + { + "epoch": 0.58, + "learning_rate": 2.1068656182188317e-05, + "loss": 0.1245, + "step": 259760 + }, + { + "epoch": 0.58, + "learning_rate": 2.1067537638978995e-05, + "loss": 0.1245, + "step": 259770 + }, + { + "epoch": 0.58, + "learning_rate": 2.1066419095769673e-05, + "loss": 0.1193, + "step": 259780 + }, + { + "epoch": 0.58, + "learning_rate": 2.1065300552560347e-05, + "loss": 0.1214, + "step": 259790 + }, + { + "epoch": 0.58, + "learning_rate": 2.106418200935102e-05, + "loss": 0.1231, + "step": 259800 + }, + { + "epoch": 0.58, + "learning_rate": 2.1063063466141696e-05, + "loss": 0.1185, + "step": 259810 + }, + { + "epoch": 0.58, + "learning_rate": 2.1061944922932374e-05, + "loss": 0.1235, + "step": 259820 + }, + { + "epoch": 0.58, + "learning_rate": 2.1060826379723052e-05, + "loss": 0.1238, + "step": 259830 + }, + { + "epoch": 0.58, + "learning_rate": 2.1059707836513727e-05, + "loss": 0.1266, + "step": 259840 + }, + { + "epoch": 0.58, + "learning_rate": 2.10585892933044e-05, + "loss": 0.1243, + "step": 259850 + }, + { + "epoch": 0.58, + "learning_rate": 2.1057470750095076e-05, + "loss": 0.1192, + "step": 259860 + }, + { + "epoch": 0.58, + "learning_rate": 2.1056352206885754e-05, + "loss": 0.1225, + "step": 259870 + }, + { + "epoch": 0.58, + "learning_rate": 2.1055233663676428e-05, + "loss": 0.1236, + "step": 259880 + }, + { + "epoch": 0.58, + "learning_rate": 2.1054115120467106e-05, + "loss": 0.1256, + "step": 259890 + }, + { + "epoch": 0.58, + "learning_rate": 2.105299657725778e-05, + "loss": 0.1245, + "step": 259900 + }, + { + "epoch": 0.58, + "learning_rate": 2.1051878034048455e-05, + "loss": 0.1248, + "step": 259910 + }, + { + "epoch": 0.58, + "learning_rate": 2.105075949083913e-05, + "loss": 0.1276, + "step": 259920 + }, + { + "epoch": 0.58, + "learning_rate": 2.1049640947629808e-05, + "loss": 0.1222, + "step": 259930 + }, + { + "epoch": 0.58, + "learning_rate": 2.1048522404420485e-05, + "loss": 0.1234, + "step": 259940 + }, + { + "epoch": 0.58, + "learning_rate": 2.104740386121116e-05, + "loss": 0.1215, + "step": 259950 + }, + { + "epoch": 0.58, + "learning_rate": 2.1046285318001835e-05, + "loss": 0.1223, + "step": 259960 + }, + { + "epoch": 0.58, + "learning_rate": 2.104516677479251e-05, + "loss": 0.1257, + "step": 259970 + }, + { + "epoch": 0.58, + "learning_rate": 2.1044048231583187e-05, + "loss": 0.1214, + "step": 259980 + }, + { + "epoch": 0.58, + "learning_rate": 2.1042929688373865e-05, + "loss": 0.1209, + "step": 259990 + }, + { + "epoch": 0.58, + "learning_rate": 2.104181114516454e-05, + "loss": 0.1231, + "step": 260000 + }, + { + "epoch": 0.58, + "learning_rate": 2.1040692601955214e-05, + "loss": 0.1214, + "step": 260010 + }, + { + "epoch": 0.58, + "learning_rate": 2.103957405874589e-05, + "loss": 0.1223, + "step": 260020 + }, + { + "epoch": 0.58, + "learning_rate": 2.1038455515536566e-05, + "loss": 0.122, + "step": 260030 + }, + { + "epoch": 0.58, + "learning_rate": 2.1037336972327244e-05, + "loss": 0.1243, + "step": 260040 + }, + { + "epoch": 0.58, + "learning_rate": 2.103621842911792e-05, + "loss": 0.1249, + "step": 260050 + }, + { + "epoch": 0.58, + "learning_rate": 2.1035099885908594e-05, + "loss": 0.1204, + "step": 260060 + }, + { + "epoch": 0.58, + "learning_rate": 2.1033981342699268e-05, + "loss": 0.1201, + "step": 260070 + }, + { + "epoch": 0.58, + "learning_rate": 2.1032862799489943e-05, + "loss": 0.1224, + "step": 260080 + }, + { + "epoch": 0.58, + "learning_rate": 2.103174425628062e-05, + "loss": 0.1199, + "step": 260090 + }, + { + "epoch": 0.58, + "learning_rate": 2.10306257130713e-05, + "loss": 0.1236, + "step": 260100 + }, + { + "epoch": 0.58, + "learning_rate": 2.1029507169861973e-05, + "loss": 0.1247, + "step": 260110 + }, + { + "epoch": 0.58, + "learning_rate": 2.1028388626652648e-05, + "loss": 0.1187, + "step": 260120 + }, + { + "epoch": 0.58, + "learning_rate": 2.1027270083443322e-05, + "loss": 0.1213, + "step": 260130 + }, + { + "epoch": 0.58, + "learning_rate": 2.1026151540234e-05, + "loss": 0.1267, + "step": 260140 + }, + { + "epoch": 0.58, + "learning_rate": 2.1025032997024678e-05, + "loss": 0.1183, + "step": 260150 + }, + { + "epoch": 0.58, + "learning_rate": 2.1023914453815352e-05, + "loss": 0.1203, + "step": 260160 + }, + { + "epoch": 0.58, + "learning_rate": 2.1022795910606027e-05, + "loss": 0.1264, + "step": 260170 + }, + { + "epoch": 0.58, + "learning_rate": 2.10216773673967e-05, + "loss": 0.1233, + "step": 260180 + }, + { + "epoch": 0.58, + "learning_rate": 2.102055882418738e-05, + "loss": 0.1205, + "step": 260190 + }, + { + "epoch": 0.58, + "learning_rate": 2.1019440280978057e-05, + "loss": 0.1186, + "step": 260200 + }, + { + "epoch": 0.58, + "learning_rate": 2.1018321737768732e-05, + "loss": 0.1192, + "step": 260210 + }, + { + "epoch": 0.58, + "learning_rate": 2.1017203194559406e-05, + "loss": 0.1233, + "step": 260220 + }, + { + "epoch": 0.58, + "learning_rate": 2.101608465135008e-05, + "loss": 0.1234, + "step": 260230 + }, + { + "epoch": 0.58, + "learning_rate": 2.101496610814076e-05, + "loss": 0.1188, + "step": 260240 + }, + { + "epoch": 0.58, + "learning_rate": 2.1013847564931437e-05, + "loss": 0.1207, + "step": 260250 + }, + { + "epoch": 0.58, + "learning_rate": 2.101272902172211e-05, + "loss": 0.1196, + "step": 260260 + }, + { + "epoch": 0.58, + "learning_rate": 2.1011610478512786e-05, + "loss": 0.1189, + "step": 260270 + }, + { + "epoch": 0.58, + "learning_rate": 2.101049193530346e-05, + "loss": 0.1259, + "step": 260280 + }, + { + "epoch": 0.58, + "learning_rate": 2.1009373392094135e-05, + "loss": 0.1223, + "step": 260290 + }, + { + "epoch": 0.58, + "learning_rate": 2.1008254848884816e-05, + "loss": 0.1194, + "step": 260300 + }, + { + "epoch": 0.58, + "learning_rate": 2.100713630567549e-05, + "loss": 0.1242, + "step": 260310 + }, + { + "epoch": 0.58, + "learning_rate": 2.1006017762466165e-05, + "loss": 0.1212, + "step": 260320 + }, + { + "epoch": 0.58, + "learning_rate": 2.100489921925684e-05, + "loss": 0.1216, + "step": 260330 + }, + { + "epoch": 0.58, + "learning_rate": 2.1003780676047514e-05, + "loss": 0.1211, + "step": 260340 + }, + { + "epoch": 0.58, + "learning_rate": 2.1002662132838192e-05, + "loss": 0.12, + "step": 260350 + }, + { + "epoch": 0.58, + "learning_rate": 2.100154358962887e-05, + "loss": 0.1196, + "step": 260360 + }, + { + "epoch": 0.58, + "learning_rate": 2.1000425046419545e-05, + "loss": 0.1212, + "step": 260370 + }, + { + "epoch": 0.58, + "learning_rate": 2.099930650321022e-05, + "loss": 0.1201, + "step": 260380 + }, + { + "epoch": 0.58, + "learning_rate": 2.0998187960000894e-05, + "loss": 0.1221, + "step": 260390 + }, + { + "epoch": 0.58, + "learning_rate": 2.0997069416791572e-05, + "loss": 0.1194, + "step": 260400 + }, + { + "epoch": 0.58, + "learning_rate": 2.099595087358225e-05, + "loss": 0.1211, + "step": 260410 + }, + { + "epoch": 0.58, + "learning_rate": 2.0994832330372924e-05, + "loss": 0.119, + "step": 260420 + }, + { + "epoch": 0.58, + "learning_rate": 2.09937137871636e-05, + "loss": 0.1193, + "step": 260430 + }, + { + "epoch": 0.58, + "learning_rate": 2.0992595243954273e-05, + "loss": 0.1238, + "step": 260440 + }, + { + "epoch": 0.58, + "learning_rate": 2.099147670074495e-05, + "loss": 0.1178, + "step": 260450 + }, + { + "epoch": 0.58, + "learning_rate": 2.099035815753563e-05, + "loss": 0.1197, + "step": 260460 + }, + { + "epoch": 0.58, + "learning_rate": 2.0989239614326304e-05, + "loss": 0.1234, + "step": 260470 + }, + { + "epoch": 0.58, + "learning_rate": 2.098812107111698e-05, + "loss": 0.1212, + "step": 260480 + }, + { + "epoch": 0.58, + "learning_rate": 2.0987002527907653e-05, + "loss": 0.1221, + "step": 260490 + }, + { + "epoch": 0.58, + "learning_rate": 2.0985883984698327e-05, + "loss": 0.1228, + "step": 260500 + }, + { + "epoch": 0.58, + "learning_rate": 2.0984765441489005e-05, + "loss": 0.1207, + "step": 260510 + }, + { + "epoch": 0.58, + "learning_rate": 2.0983646898279683e-05, + "loss": 0.12, + "step": 260520 + }, + { + "epoch": 0.58, + "learning_rate": 2.0982528355070358e-05, + "loss": 0.1205, + "step": 260530 + }, + { + "epoch": 0.58, + "learning_rate": 2.0981409811861032e-05, + "loss": 0.1196, + "step": 260540 + }, + { + "epoch": 0.58, + "learning_rate": 2.0980291268651707e-05, + "loss": 0.1227, + "step": 260550 + }, + { + "epoch": 0.58, + "learning_rate": 2.0979172725442385e-05, + "loss": 0.1243, + "step": 260560 + }, + { + "epoch": 0.58, + "learning_rate": 2.0978054182233063e-05, + "loss": 0.1174, + "step": 260570 + }, + { + "epoch": 0.58, + "learning_rate": 2.0976935639023737e-05, + "loss": 0.123, + "step": 260580 + }, + { + "epoch": 0.58, + "learning_rate": 2.0975817095814412e-05, + "loss": 0.1187, + "step": 260590 + }, + { + "epoch": 0.58, + "learning_rate": 2.0974698552605086e-05, + "loss": 0.1202, + "step": 260600 + }, + { + "epoch": 0.58, + "learning_rate": 2.0973580009395764e-05, + "loss": 0.1199, + "step": 260610 + }, + { + "epoch": 0.58, + "learning_rate": 2.0972461466186442e-05, + "loss": 0.1179, + "step": 260620 + }, + { + "epoch": 0.58, + "learning_rate": 2.0971342922977117e-05, + "loss": 0.1151, + "step": 260630 + }, + { + "epoch": 0.58, + "learning_rate": 2.097022437976779e-05, + "loss": 0.122, + "step": 260640 + }, + { + "epoch": 0.58, + "learning_rate": 2.0969105836558466e-05, + "loss": 0.1252, + "step": 260650 + }, + { + "epoch": 0.58, + "learning_rate": 2.0967987293349144e-05, + "loss": 0.1212, + "step": 260660 + }, + { + "epoch": 0.58, + "learning_rate": 2.096686875013982e-05, + "loss": 0.1142, + "step": 260670 + }, + { + "epoch": 0.58, + "learning_rate": 2.0965750206930496e-05, + "loss": 0.1204, + "step": 260680 + }, + { + "epoch": 0.58, + "learning_rate": 2.096463166372117e-05, + "loss": 0.1176, + "step": 260690 + }, + { + "epoch": 0.58, + "learning_rate": 2.0963513120511845e-05, + "loss": 0.1221, + "step": 260700 + }, + { + "epoch": 0.58, + "learning_rate": 2.096239457730252e-05, + "loss": 0.1216, + "step": 260710 + }, + { + "epoch": 0.58, + "learning_rate": 2.0961276034093198e-05, + "loss": 0.1242, + "step": 260720 + }, + { + "epoch": 0.58, + "learning_rate": 2.0960157490883876e-05, + "loss": 0.1246, + "step": 260730 + }, + { + "epoch": 0.58, + "learning_rate": 2.095903894767455e-05, + "loss": 0.1249, + "step": 260740 + }, + { + "epoch": 0.58, + "learning_rate": 2.0957920404465225e-05, + "loss": 0.1208, + "step": 260750 + }, + { + "epoch": 0.58, + "learning_rate": 2.09568018612559e-05, + "loss": 0.1226, + "step": 260760 + }, + { + "epoch": 0.58, + "learning_rate": 2.0955683318046577e-05, + "loss": 0.1216, + "step": 260770 + }, + { + "epoch": 0.58, + "learning_rate": 2.0954564774837255e-05, + "loss": 0.1188, + "step": 260780 + }, + { + "epoch": 0.58, + "learning_rate": 2.095344623162793e-05, + "loss": 0.1177, + "step": 260790 + }, + { + "epoch": 0.58, + "learning_rate": 2.0952327688418604e-05, + "loss": 0.1262, + "step": 260800 + }, + { + "epoch": 0.58, + "learning_rate": 2.095120914520928e-05, + "loss": 0.1238, + "step": 260810 + }, + { + "epoch": 0.58, + "learning_rate": 2.0950090601999957e-05, + "loss": 0.1202, + "step": 260820 + }, + { + "epoch": 0.58, + "learning_rate": 2.094897205879063e-05, + "loss": 0.1201, + "step": 260830 + }, + { + "epoch": 0.58, + "learning_rate": 2.094785351558131e-05, + "loss": 0.1203, + "step": 260840 + }, + { + "epoch": 0.58, + "learning_rate": 2.0946734972371984e-05, + "loss": 0.1205, + "step": 260850 + }, + { + "epoch": 0.58, + "learning_rate": 2.094561642916266e-05, + "loss": 0.1188, + "step": 260860 + }, + { + "epoch": 0.58, + "learning_rate": 2.0944497885953336e-05, + "loss": 0.1183, + "step": 260870 + }, + { + "epoch": 0.58, + "learning_rate": 2.094337934274401e-05, + "loss": 0.1209, + "step": 260880 + }, + { + "epoch": 0.58, + "learning_rate": 2.094226079953469e-05, + "loss": 0.1151, + "step": 260890 + }, + { + "epoch": 0.58, + "learning_rate": 2.0941142256325363e-05, + "loss": 0.1227, + "step": 260900 + }, + { + "epoch": 0.58, + "learning_rate": 2.0940023713116038e-05, + "loss": 0.1188, + "step": 260910 + }, + { + "epoch": 0.58, + "learning_rate": 2.0938905169906716e-05, + "loss": 0.1184, + "step": 260920 + }, + { + "epoch": 0.58, + "learning_rate": 2.093778662669739e-05, + "loss": 0.1158, + "step": 260930 + }, + { + "epoch": 0.58, + "learning_rate": 2.0936668083488068e-05, + "loss": 0.1208, + "step": 260940 + }, + { + "epoch": 0.58, + "learning_rate": 2.0935549540278743e-05, + "loss": 0.1208, + "step": 260950 + }, + { + "epoch": 0.58, + "learning_rate": 2.0934430997069417e-05, + "loss": 0.1212, + "step": 260960 + }, + { + "epoch": 0.58, + "learning_rate": 2.0933312453860092e-05, + "loss": 0.1185, + "step": 260970 + }, + { + "epoch": 0.58, + "learning_rate": 2.093219391065077e-05, + "loss": 0.1179, + "step": 260980 + }, + { + "epoch": 0.58, + "learning_rate": 2.0931075367441444e-05, + "loss": 0.1173, + "step": 260990 + }, + { + "epoch": 0.58, + "learning_rate": 2.0929956824232122e-05, + "loss": 0.1197, + "step": 261000 + }, + { + "epoch": 0.58, + "learning_rate": 2.0928838281022797e-05, + "loss": 0.1209, + "step": 261010 + }, + { + "epoch": 0.58, + "learning_rate": 2.092771973781347e-05, + "loss": 0.1198, + "step": 261020 + }, + { + "epoch": 0.58, + "learning_rate": 2.092660119460415e-05, + "loss": 0.1187, + "step": 261030 + }, + { + "epoch": 0.58, + "learning_rate": 2.0925482651394824e-05, + "loss": 0.1222, + "step": 261040 + }, + { + "epoch": 0.58, + "learning_rate": 2.09243641081855e-05, + "loss": 0.1197, + "step": 261050 + }, + { + "epoch": 0.58, + "learning_rate": 2.0923245564976176e-05, + "loss": 0.1215, + "step": 261060 + }, + { + "epoch": 0.58, + "learning_rate": 2.092212702176685e-05, + "loss": 0.1211, + "step": 261070 + }, + { + "epoch": 0.58, + "learning_rate": 2.092100847855753e-05, + "loss": 0.1188, + "step": 261080 + }, + { + "epoch": 0.58, + "learning_rate": 2.0919889935348203e-05, + "loss": 0.1181, + "step": 261090 + }, + { + "epoch": 0.58, + "learning_rate": 2.091877139213888e-05, + "loss": 0.12, + "step": 261100 + }, + { + "epoch": 0.58, + "learning_rate": 2.0917652848929556e-05, + "loss": 0.1228, + "step": 261110 + }, + { + "epoch": 0.58, + "learning_rate": 2.091653430572023e-05, + "loss": 0.1178, + "step": 261120 + }, + { + "epoch": 0.58, + "learning_rate": 2.0915415762510908e-05, + "loss": 0.1273, + "step": 261130 + }, + { + "epoch": 0.58, + "learning_rate": 2.0914297219301583e-05, + "loss": 0.1213, + "step": 261140 + }, + { + "epoch": 0.58, + "learning_rate": 2.0913178676092257e-05, + "loss": 0.1192, + "step": 261150 + }, + { + "epoch": 0.58, + "learning_rate": 2.0912060132882935e-05, + "loss": 0.1195, + "step": 261160 + }, + { + "epoch": 0.58, + "learning_rate": 2.091094158967361e-05, + "loss": 0.1226, + "step": 261170 + }, + { + "epoch": 0.58, + "learning_rate": 2.0909823046464284e-05, + "loss": 0.1212, + "step": 261180 + }, + { + "epoch": 0.58, + "learning_rate": 2.0908704503254962e-05, + "loss": 0.1205, + "step": 261190 + }, + { + "epoch": 0.58, + "learning_rate": 2.0907585960045637e-05, + "loss": 0.1189, + "step": 261200 + }, + { + "epoch": 0.58, + "learning_rate": 2.0906467416836315e-05, + "loss": 0.121, + "step": 261210 + }, + { + "epoch": 0.58, + "learning_rate": 2.090534887362699e-05, + "loss": 0.1161, + "step": 261220 + }, + { + "epoch": 0.58, + "learning_rate": 2.0904230330417664e-05, + "loss": 0.1201, + "step": 261230 + }, + { + "epoch": 0.58, + "learning_rate": 2.090311178720834e-05, + "loss": 0.1156, + "step": 261240 + }, + { + "epoch": 0.58, + "learning_rate": 2.0901993243999016e-05, + "loss": 0.1229, + "step": 261250 + }, + { + "epoch": 0.58, + "learning_rate": 2.0900874700789694e-05, + "loss": 0.1215, + "step": 261260 + }, + { + "epoch": 0.58, + "learning_rate": 2.089975615758037e-05, + "loss": 0.1243, + "step": 261270 + }, + { + "epoch": 0.58, + "learning_rate": 2.0898637614371043e-05, + "loss": 0.1185, + "step": 261280 + }, + { + "epoch": 0.58, + "learning_rate": 2.089751907116172e-05, + "loss": 0.1205, + "step": 261290 + }, + { + "epoch": 0.58, + "learning_rate": 2.0896400527952396e-05, + "loss": 0.1216, + "step": 261300 + }, + { + "epoch": 0.58, + "learning_rate": 2.089528198474307e-05, + "loss": 0.1219, + "step": 261310 + }, + { + "epoch": 0.58, + "learning_rate": 2.0894163441533748e-05, + "loss": 0.1192, + "step": 261320 + }, + { + "epoch": 0.58, + "learning_rate": 2.0893044898324423e-05, + "loss": 0.1204, + "step": 261330 + }, + { + "epoch": 0.58, + "learning_rate": 2.08919263551151e-05, + "loss": 0.1164, + "step": 261340 + }, + { + "epoch": 0.58, + "learning_rate": 2.0890807811905775e-05, + "loss": 0.1176, + "step": 261350 + }, + { + "epoch": 0.58, + "learning_rate": 2.088968926869645e-05, + "loss": 0.1184, + "step": 261360 + }, + { + "epoch": 0.58, + "learning_rate": 2.088868257980806e-05, + "loss": 0.1211, + "step": 261370 + }, + { + "epoch": 0.58, + "learning_rate": 2.0887564036598733e-05, + "loss": 0.1236, + "step": 261380 + }, + { + "epoch": 0.58, + "learning_rate": 2.088644549338941e-05, + "loss": 0.1203, + "step": 261390 + }, + { + "epoch": 0.58, + "learning_rate": 2.0885326950180085e-05, + "loss": 0.1202, + "step": 261400 + }, + { + "epoch": 0.58, + "learning_rate": 2.0884208406970763e-05, + "loss": 0.1195, + "step": 261410 + }, + { + "epoch": 0.58, + "learning_rate": 2.0883089863761438e-05, + "loss": 0.1198, + "step": 261420 + }, + { + "epoch": 0.58, + "learning_rate": 2.0881971320552112e-05, + "loss": 0.1203, + "step": 261430 + }, + { + "epoch": 0.58, + "learning_rate": 2.088085277734279e-05, + "loss": 0.1167, + "step": 261440 + }, + { + "epoch": 0.58, + "learning_rate": 2.0879734234133465e-05, + "loss": 0.115, + "step": 261450 + }, + { + "epoch": 0.58, + "learning_rate": 2.0878615690924143e-05, + "loss": 0.1171, + "step": 261460 + }, + { + "epoch": 0.58, + "learning_rate": 2.0877497147714817e-05, + "loss": 0.1183, + "step": 261470 + }, + { + "epoch": 0.58, + "learning_rate": 2.0876378604505492e-05, + "loss": 0.1181, + "step": 261480 + }, + { + "epoch": 0.58, + "learning_rate": 2.087526006129617e-05, + "loss": 0.1214, + "step": 261490 + }, + { + "epoch": 0.58, + "learning_rate": 2.0874141518086844e-05, + "loss": 0.1206, + "step": 261500 + }, + { + "epoch": 0.58, + "learning_rate": 2.0873022974877522e-05, + "loss": 0.1197, + "step": 261510 + }, + { + "epoch": 0.58, + "learning_rate": 2.0871904431668197e-05, + "loss": 0.1199, + "step": 261520 + }, + { + "epoch": 0.58, + "learning_rate": 2.087078588845887e-05, + "loss": 0.1178, + "step": 261530 + }, + { + "epoch": 0.58, + "learning_rate": 2.0869667345249546e-05, + "loss": 0.1219, + "step": 261540 + }, + { + "epoch": 0.58, + "learning_rate": 2.0868548802040224e-05, + "loss": 0.1203, + "step": 261550 + }, + { + "epoch": 0.58, + "learning_rate": 2.08674302588309e-05, + "loss": 0.1187, + "step": 261560 + }, + { + "epoch": 0.58, + "learning_rate": 2.0866311715621576e-05, + "loss": 0.1238, + "step": 261570 + }, + { + "epoch": 0.58, + "learning_rate": 2.086519317241225e-05, + "loss": 0.1201, + "step": 261580 + }, + { + "epoch": 0.58, + "learning_rate": 2.0864074629202925e-05, + "loss": 0.1187, + "step": 261590 + }, + { + "epoch": 0.58, + "learning_rate": 2.0862956085993603e-05, + "loss": 0.1205, + "step": 261600 + }, + { + "epoch": 0.58, + "learning_rate": 2.0861837542784278e-05, + "loss": 0.1219, + "step": 261610 + }, + { + "epoch": 0.58, + "learning_rate": 2.0860718999574956e-05, + "loss": 0.1197, + "step": 261620 + }, + { + "epoch": 0.58, + "learning_rate": 2.085960045636563e-05, + "loss": 0.1159, + "step": 261630 + }, + { + "epoch": 0.58, + "learning_rate": 2.0858481913156305e-05, + "loss": 0.122, + "step": 261640 + }, + { + "epoch": 0.58, + "learning_rate": 2.0857363369946983e-05, + "loss": 0.1167, + "step": 261650 + }, + { + "epoch": 0.58, + "learning_rate": 2.0856244826737657e-05, + "loss": 0.1205, + "step": 261660 + }, + { + "epoch": 0.58, + "learning_rate": 2.0855126283528335e-05, + "loss": 0.1178, + "step": 261670 + }, + { + "epoch": 0.58, + "learning_rate": 2.085400774031901e-05, + "loss": 0.1262, + "step": 261680 + }, + { + "epoch": 0.58, + "learning_rate": 2.0852889197109684e-05, + "loss": 0.1231, + "step": 261690 + }, + { + "epoch": 0.58, + "learning_rate": 2.085177065390036e-05, + "loss": 0.1187, + "step": 261700 + }, + { + "epoch": 0.58, + "learning_rate": 2.0850652110691037e-05, + "loss": 0.1223, + "step": 261710 + }, + { + "epoch": 0.58, + "learning_rate": 2.0849533567481715e-05, + "loss": 0.1224, + "step": 261720 + }, + { + "epoch": 0.58, + "learning_rate": 2.084841502427239e-05, + "loss": 0.1253, + "step": 261730 + }, + { + "epoch": 0.58, + "learning_rate": 2.0847296481063064e-05, + "loss": 0.1178, + "step": 261740 + }, + { + "epoch": 0.58, + "learning_rate": 2.084617793785374e-05, + "loss": 0.1177, + "step": 261750 + }, + { + "epoch": 0.58, + "learning_rate": 2.0845059394644416e-05, + "loss": 0.1202, + "step": 261760 + }, + { + "epoch": 0.58, + "learning_rate": 2.0843940851435094e-05, + "loss": 0.1203, + "step": 261770 + }, + { + "epoch": 0.58, + "learning_rate": 2.084282230822577e-05, + "loss": 0.1177, + "step": 261780 + }, + { + "epoch": 0.58, + "learning_rate": 2.0841703765016443e-05, + "loss": 0.1209, + "step": 261790 + }, + { + "epoch": 0.58, + "learning_rate": 2.0840585221807118e-05, + "loss": 0.1201, + "step": 261800 + }, + { + "epoch": 0.58, + "learning_rate": 2.0839466678597796e-05, + "loss": 0.1161, + "step": 261810 + }, + { + "epoch": 0.58, + "learning_rate": 2.083834813538847e-05, + "loss": 0.1209, + "step": 261820 + }, + { + "epoch": 0.58, + "learning_rate": 2.0837229592179148e-05, + "loss": 0.1193, + "step": 261830 + }, + { + "epoch": 0.58, + "learning_rate": 2.0836111048969823e-05, + "loss": 0.119, + "step": 261840 + }, + { + "epoch": 0.58, + "learning_rate": 2.0834992505760497e-05, + "loss": 0.1222, + "step": 261850 + }, + { + "epoch": 0.58, + "learning_rate": 2.0833873962551172e-05, + "loss": 0.114, + "step": 261860 + }, + { + "epoch": 0.58, + "learning_rate": 2.083275541934185e-05, + "loss": 0.1188, + "step": 261870 + }, + { + "epoch": 0.58, + "learning_rate": 2.0831636876132528e-05, + "loss": 0.113, + "step": 261880 + }, + { + "epoch": 0.58, + "learning_rate": 2.0830518332923202e-05, + "loss": 0.1175, + "step": 261890 + }, + { + "epoch": 0.58, + "learning_rate": 2.0829399789713877e-05, + "loss": 0.1147, + "step": 261900 + }, + { + "epoch": 0.58, + "learning_rate": 2.082828124650455e-05, + "loss": 0.1267, + "step": 261910 + }, + { + "epoch": 0.58, + "learning_rate": 2.082716270329523e-05, + "loss": 0.1186, + "step": 261920 + }, + { + "epoch": 0.58, + "learning_rate": 2.0826044160085907e-05, + "loss": 0.1169, + "step": 261930 + }, + { + "epoch": 0.58, + "learning_rate": 2.0824925616876582e-05, + "loss": 0.1225, + "step": 261940 + }, + { + "epoch": 0.58, + "learning_rate": 2.0823807073667256e-05, + "loss": 0.1212, + "step": 261950 + }, + { + "epoch": 0.58, + "learning_rate": 2.082268853045793e-05, + "loss": 0.1214, + "step": 261960 + }, + { + "epoch": 0.58, + "learning_rate": 2.082156998724861e-05, + "loss": 0.118, + "step": 261970 + }, + { + "epoch": 0.58, + "learning_rate": 2.0820451444039287e-05, + "loss": 0.1209, + "step": 261980 + }, + { + "epoch": 0.58, + "learning_rate": 2.081933290082996e-05, + "loss": 0.1164, + "step": 261990 + }, + { + "epoch": 0.58, + "learning_rate": 2.0818214357620636e-05, + "loss": 0.1206, + "step": 262000 + }, + { + "epoch": 0.58, + "learning_rate": 2.081709581441131e-05, + "loss": 0.1228, + "step": 262010 + }, + { + "epoch": 0.58, + "learning_rate": 2.0815977271201985e-05, + "loss": 0.118, + "step": 262020 + }, + { + "epoch": 0.58, + "learning_rate": 2.0814858727992663e-05, + "loss": 0.1171, + "step": 262030 + }, + { + "epoch": 0.58, + "learning_rate": 2.081374018478334e-05, + "loss": 0.1198, + "step": 262040 + }, + { + "epoch": 0.58, + "learning_rate": 2.0812621641574015e-05, + "loss": 0.1193, + "step": 262050 + }, + { + "epoch": 0.58, + "learning_rate": 2.081150309836469e-05, + "loss": 0.1205, + "step": 262060 + }, + { + "epoch": 0.58, + "learning_rate": 2.0810384555155364e-05, + "loss": 0.1174, + "step": 262070 + }, + { + "epoch": 0.58, + "learning_rate": 2.0809266011946042e-05, + "loss": 0.1166, + "step": 262080 + }, + { + "epoch": 0.59, + "learning_rate": 2.080814746873672e-05, + "loss": 0.1186, + "step": 262090 + }, + { + "epoch": 0.59, + "learning_rate": 2.0807028925527395e-05, + "loss": 0.123, + "step": 262100 + }, + { + "epoch": 0.59, + "learning_rate": 2.080591038231807e-05, + "loss": 0.114, + "step": 262110 + }, + { + "epoch": 0.59, + "learning_rate": 2.0804791839108744e-05, + "loss": 0.1126, + "step": 262120 + }, + { + "epoch": 0.59, + "learning_rate": 2.0803673295899422e-05, + "loss": 0.1158, + "step": 262130 + }, + { + "epoch": 0.59, + "learning_rate": 2.08025547526901e-05, + "loss": 0.1212, + "step": 262140 + }, + { + "epoch": 0.59, + "learning_rate": 2.0801436209480774e-05, + "loss": 0.1241, + "step": 262150 + }, + { + "epoch": 0.59, + "learning_rate": 2.080031766627145e-05, + "loss": 0.1174, + "step": 262160 + }, + { + "epoch": 0.59, + "learning_rate": 2.0799199123062123e-05, + "loss": 0.1172, + "step": 262170 + }, + { + "epoch": 0.59, + "learning_rate": 2.0798080579852798e-05, + "loss": 0.1229, + "step": 262180 + }, + { + "epoch": 0.59, + "learning_rate": 2.079696203664348e-05, + "loss": 0.1172, + "step": 262190 + }, + { + "epoch": 0.59, + "learning_rate": 2.0795843493434154e-05, + "loss": 0.1147, + "step": 262200 + }, + { + "epoch": 0.59, + "learning_rate": 2.0794724950224828e-05, + "loss": 0.1173, + "step": 262210 + }, + { + "epoch": 0.59, + "learning_rate": 2.0793606407015503e-05, + "loss": 0.1196, + "step": 262220 + }, + { + "epoch": 0.59, + "learning_rate": 2.0792487863806177e-05, + "loss": 0.1147, + "step": 262230 + }, + { + "epoch": 0.59, + "learning_rate": 2.0791369320596855e-05, + "loss": 0.1195, + "step": 262240 + }, + { + "epoch": 0.59, + "learning_rate": 2.0790250777387533e-05, + "loss": 0.1254, + "step": 262250 + }, + { + "epoch": 0.59, + "learning_rate": 2.0789132234178208e-05, + "loss": 0.1226, + "step": 262260 + }, + { + "epoch": 0.59, + "learning_rate": 2.0788013690968882e-05, + "loss": 0.1237, + "step": 262270 + }, + { + "epoch": 0.59, + "learning_rate": 2.0786895147759557e-05, + "loss": 0.1187, + "step": 262280 + }, + { + "epoch": 0.59, + "learning_rate": 2.0785776604550235e-05, + "loss": 0.1151, + "step": 262290 + }, + { + "epoch": 0.59, + "learning_rate": 2.0784658061340913e-05, + "loss": 0.1194, + "step": 262300 + }, + { + "epoch": 0.59, + "learning_rate": 2.0783539518131587e-05, + "loss": 0.1191, + "step": 262310 + }, + { + "epoch": 0.59, + "learning_rate": 2.078242097492226e-05, + "loss": 0.1184, + "step": 262320 + }, + { + "epoch": 0.59, + "learning_rate": 2.0781302431712936e-05, + "loss": 0.117, + "step": 262330 + }, + { + "epoch": 0.59, + "learning_rate": 2.0780183888503614e-05, + "loss": 0.116, + "step": 262340 + }, + { + "epoch": 0.59, + "learning_rate": 2.0779065345294292e-05, + "loss": 0.1199, + "step": 262350 + }, + { + "epoch": 0.59, + "learning_rate": 2.0777946802084967e-05, + "loss": 0.1216, + "step": 262360 + }, + { + "epoch": 0.59, + "learning_rate": 2.077682825887564e-05, + "loss": 0.1218, + "step": 262370 + }, + { + "epoch": 0.59, + "learning_rate": 2.0775709715666316e-05, + "loss": 0.1152, + "step": 262380 + }, + { + "epoch": 0.59, + "learning_rate": 2.0774591172456994e-05, + "loss": 0.1154, + "step": 262390 + }, + { + "epoch": 0.59, + "learning_rate": 2.077347262924767e-05, + "loss": 0.1192, + "step": 262400 + }, + { + "epoch": 0.59, + "learning_rate": 2.0772354086038346e-05, + "loss": 0.1195, + "step": 262410 + }, + { + "epoch": 0.59, + "learning_rate": 2.077123554282902e-05, + "loss": 0.1177, + "step": 262420 + }, + { + "epoch": 0.59, + "learning_rate": 2.0770116999619695e-05, + "loss": 0.1154, + "step": 262430 + }, + { + "epoch": 0.59, + "learning_rate": 2.076899845641037e-05, + "loss": 0.116, + "step": 262440 + }, + { + "epoch": 0.59, + "learning_rate": 2.0767879913201048e-05, + "loss": 0.1179, + "step": 262450 + }, + { + "epoch": 0.59, + "learning_rate": 2.0766761369991726e-05, + "loss": 0.118, + "step": 262460 + }, + { + "epoch": 0.59, + "learning_rate": 2.07656428267824e-05, + "loss": 0.1194, + "step": 262470 + }, + { + "epoch": 0.59, + "learning_rate": 2.0764524283573075e-05, + "loss": 0.1173, + "step": 262480 + }, + { + "epoch": 0.59, + "learning_rate": 2.076340574036375e-05, + "loss": 0.1199, + "step": 262490 + }, + { + "epoch": 0.59, + "learning_rate": 2.0762287197154427e-05, + "loss": 0.1171, + "step": 262500 + }, + { + "epoch": 0.59, + "learning_rate": 2.0761168653945105e-05, + "loss": 0.118, + "step": 262510 + }, + { + "epoch": 0.59, + "learning_rate": 2.076005011073578e-05, + "loss": 0.1194, + "step": 262520 + }, + { + "epoch": 0.59, + "learning_rate": 2.0758931567526454e-05, + "loss": 0.1223, + "step": 262530 + }, + { + "epoch": 0.59, + "learning_rate": 2.075781302431713e-05, + "loss": 0.1171, + "step": 262540 + }, + { + "epoch": 0.59, + "learning_rate": 2.0756694481107807e-05, + "loss": 0.1177, + "step": 262550 + }, + { + "epoch": 0.59, + "learning_rate": 2.0755575937898485e-05, + "loss": 0.1153, + "step": 262560 + }, + { + "epoch": 0.59, + "learning_rate": 2.075445739468916e-05, + "loss": 0.1114, + "step": 262570 + }, + { + "epoch": 0.59, + "learning_rate": 2.0753338851479834e-05, + "loss": 0.1169, + "step": 262580 + }, + { + "epoch": 0.59, + "learning_rate": 2.0752220308270508e-05, + "loss": 0.1134, + "step": 262590 + }, + { + "epoch": 0.59, + "learning_rate": 2.0751101765061186e-05, + "loss": 0.1222, + "step": 262600 + }, + { + "epoch": 0.59, + "learning_rate": 2.0749983221851864e-05, + "loss": 0.1199, + "step": 262610 + }, + { + "epoch": 0.59, + "learning_rate": 2.074886467864254e-05, + "loss": 0.1206, + "step": 262620 + }, + { + "epoch": 0.59, + "learning_rate": 2.0747746135433213e-05, + "loss": 0.1208, + "step": 262630 + }, + { + "epoch": 0.59, + "learning_rate": 2.0746627592223888e-05, + "loss": 0.1179, + "step": 262640 + }, + { + "epoch": 0.59, + "learning_rate": 2.0745509049014562e-05, + "loss": 0.122, + "step": 262650 + }, + { + "epoch": 0.59, + "learning_rate": 2.074439050580524e-05, + "loss": 0.1163, + "step": 262660 + }, + { + "epoch": 0.59, + "learning_rate": 2.0743271962595918e-05, + "loss": 0.1134, + "step": 262670 + }, + { + "epoch": 0.59, + "learning_rate": 2.0742153419386593e-05, + "loss": 0.1226, + "step": 262680 + }, + { + "epoch": 0.59, + "learning_rate": 2.0741034876177267e-05, + "loss": 0.1184, + "step": 262690 + }, + { + "epoch": 0.59, + "learning_rate": 2.073991633296794e-05, + "loss": 0.1148, + "step": 262700 + }, + { + "epoch": 0.59, + "learning_rate": 2.073879778975862e-05, + "loss": 0.1199, + "step": 262710 + }, + { + "epoch": 0.59, + "learning_rate": 2.0737679246549297e-05, + "loss": 0.121, + "step": 262720 + }, + { + "epoch": 0.59, + "learning_rate": 2.0736560703339972e-05, + "loss": 0.121, + "step": 262730 + }, + { + "epoch": 0.59, + "learning_rate": 2.0735442160130647e-05, + "loss": 0.1188, + "step": 262740 + }, + { + "epoch": 0.59, + "learning_rate": 2.073432361692132e-05, + "loss": 0.1204, + "step": 262750 + }, + { + "epoch": 0.59, + "learning_rate": 2.0733205073712e-05, + "loss": 0.1189, + "step": 262760 + }, + { + "epoch": 0.59, + "learning_rate": 2.0732086530502677e-05, + "loss": 0.1094, + "step": 262770 + }, + { + "epoch": 0.59, + "learning_rate": 2.073096798729335e-05, + "loss": 0.1162, + "step": 262780 + }, + { + "epoch": 0.59, + "learning_rate": 2.0729849444084026e-05, + "loss": 0.1187, + "step": 262790 + }, + { + "epoch": 0.59, + "learning_rate": 2.07287309008747e-05, + "loss": 0.1198, + "step": 262800 + }, + { + "epoch": 0.59, + "learning_rate": 2.072761235766538e-05, + "loss": 0.1184, + "step": 262810 + }, + { + "epoch": 0.59, + "learning_rate": 2.0726493814456053e-05, + "loss": 0.1169, + "step": 262820 + }, + { + "epoch": 0.59, + "learning_rate": 2.072537527124673e-05, + "loss": 0.1161, + "step": 262830 + }, + { + "epoch": 0.59, + "learning_rate": 2.0724256728037405e-05, + "loss": 0.1162, + "step": 262840 + }, + { + "epoch": 0.59, + "learning_rate": 2.072313818482808e-05, + "loss": 0.1159, + "step": 262850 + }, + { + "epoch": 0.59, + "learning_rate": 2.0722019641618755e-05, + "loss": 0.1171, + "step": 262860 + }, + { + "epoch": 0.59, + "learning_rate": 2.0720901098409432e-05, + "loss": 0.1201, + "step": 262870 + }, + { + "epoch": 0.59, + "learning_rate": 2.071978255520011e-05, + "loss": 0.1177, + "step": 262880 + }, + { + "epoch": 0.59, + "learning_rate": 2.0718664011990785e-05, + "loss": 0.1163, + "step": 262890 + }, + { + "epoch": 0.59, + "learning_rate": 2.071754546878146e-05, + "loss": 0.117, + "step": 262900 + }, + { + "epoch": 0.59, + "learning_rate": 2.0716426925572134e-05, + "loss": 0.1154, + "step": 262910 + }, + { + "epoch": 0.59, + "learning_rate": 2.0715308382362812e-05, + "loss": 0.1197, + "step": 262920 + }, + { + "epoch": 0.59, + "learning_rate": 2.071418983915349e-05, + "loss": 0.1169, + "step": 262930 + }, + { + "epoch": 0.59, + "learning_rate": 2.0713071295944164e-05, + "loss": 0.1215, + "step": 262940 + }, + { + "epoch": 0.59, + "learning_rate": 2.071195275273484e-05, + "loss": 0.117, + "step": 262950 + }, + { + "epoch": 0.59, + "learning_rate": 2.0710834209525514e-05, + "loss": 0.121, + "step": 262960 + }, + { + "epoch": 0.59, + "learning_rate": 2.070971566631619e-05, + "loss": 0.115, + "step": 262970 + }, + { + "epoch": 0.59, + "learning_rate": 2.0708597123106866e-05, + "loss": 0.1225, + "step": 262980 + }, + { + "epoch": 0.59, + "learning_rate": 2.0707478579897544e-05, + "loss": 0.1192, + "step": 262990 + }, + { + "epoch": 0.59, + "learning_rate": 2.070636003668822e-05, + "loss": 0.122, + "step": 263000 + }, + { + "epoch": 0.59, + "learning_rate": 2.0705241493478893e-05, + "loss": 0.1145, + "step": 263010 + }, + { + "epoch": 0.59, + "learning_rate": 2.070412295026957e-05, + "loss": 0.1149, + "step": 263020 + }, + { + "epoch": 0.59, + "learning_rate": 2.0703004407060245e-05, + "loss": 0.1216, + "step": 263030 + }, + { + "epoch": 0.59, + "learning_rate": 2.0701885863850923e-05, + "loss": 0.1235, + "step": 263040 + }, + { + "epoch": 0.59, + "learning_rate": 2.0700767320641598e-05, + "loss": 0.1228, + "step": 263050 + }, + { + "epoch": 0.59, + "learning_rate": 2.0699648777432272e-05, + "loss": 0.1246, + "step": 263060 + }, + { + "epoch": 0.59, + "learning_rate": 2.0698530234222947e-05, + "loss": 0.1245, + "step": 263070 + }, + { + "epoch": 0.59, + "learning_rate": 2.0697411691013625e-05, + "loss": 0.1182, + "step": 263080 + }, + { + "epoch": 0.59, + "learning_rate": 2.06962931478043e-05, + "loss": 0.1224, + "step": 263090 + }, + { + "epoch": 0.59, + "learning_rate": 2.0695174604594977e-05, + "loss": 0.1235, + "step": 263100 + }, + { + "epoch": 0.59, + "learning_rate": 2.0694056061385652e-05, + "loss": 0.1182, + "step": 263110 + }, + { + "epoch": 0.59, + "learning_rate": 2.0692937518176326e-05, + "loss": 0.1205, + "step": 263120 + }, + { + "epoch": 0.59, + "learning_rate": 2.0691818974967004e-05, + "loss": 0.1218, + "step": 263130 + }, + { + "epoch": 0.59, + "learning_rate": 2.069070043175768e-05, + "loss": 0.1211, + "step": 263140 + }, + { + "epoch": 0.59, + "learning_rate": 2.0689581888548357e-05, + "loss": 0.1202, + "step": 263150 + }, + { + "epoch": 0.59, + "learning_rate": 2.068846334533903e-05, + "loss": 0.1242, + "step": 263160 + }, + { + "epoch": 0.59, + "learning_rate": 2.0687344802129706e-05, + "loss": 0.1202, + "step": 263170 + }, + { + "epoch": 0.59, + "learning_rate": 2.0686226258920384e-05, + "loss": 0.1195, + "step": 263180 + }, + { + "epoch": 0.59, + "learning_rate": 2.068510771571106e-05, + "loss": 0.1214, + "step": 263190 + }, + { + "epoch": 0.59, + "learning_rate": 2.0683989172501736e-05, + "loss": 0.1262, + "step": 263200 + }, + { + "epoch": 0.59, + "learning_rate": 2.068287062929241e-05, + "loss": 0.1185, + "step": 263210 + }, + { + "epoch": 0.59, + "learning_rate": 2.0681752086083085e-05, + "loss": 0.1159, + "step": 263220 + }, + { + "epoch": 0.59, + "learning_rate": 2.0680633542873763e-05, + "loss": 0.1259, + "step": 263230 + }, + { + "epoch": 0.59, + "learning_rate": 2.0679514999664438e-05, + "loss": 0.1221, + "step": 263240 + }, + { + "epoch": 0.59, + "learning_rate": 2.0678396456455112e-05, + "loss": 0.122, + "step": 263250 + }, + { + "epoch": 0.59, + "learning_rate": 2.067727791324579e-05, + "loss": 0.121, + "step": 263260 + }, + { + "epoch": 0.59, + "learning_rate": 2.0676159370036465e-05, + "loss": 0.1235, + "step": 263270 + }, + { + "epoch": 0.59, + "learning_rate": 2.0675040826827143e-05, + "loss": 0.123, + "step": 263280 + }, + { + "epoch": 0.59, + "learning_rate": 2.0673922283617817e-05, + "loss": 0.1235, + "step": 263290 + }, + { + "epoch": 0.59, + "learning_rate": 2.0672803740408492e-05, + "loss": 0.1174, + "step": 263300 + }, + { + "epoch": 0.59, + "learning_rate": 2.067168519719917e-05, + "loss": 0.1189, + "step": 263310 + }, + { + "epoch": 0.59, + "learning_rate": 2.0670566653989844e-05, + "loss": 0.1245, + "step": 263320 + }, + { + "epoch": 0.59, + "learning_rate": 2.066944811078052e-05, + "loss": 0.1227, + "step": 263330 + }, + { + "epoch": 0.59, + "learning_rate": 2.0668329567571197e-05, + "loss": 0.1193, + "step": 263340 + }, + { + "epoch": 0.59, + "learning_rate": 2.066721102436187e-05, + "loss": 0.1215, + "step": 263350 + }, + { + "epoch": 0.59, + "learning_rate": 2.066609248115255e-05, + "loss": 0.1254, + "step": 263360 + }, + { + "epoch": 0.59, + "learning_rate": 2.0664973937943224e-05, + "loss": 0.115, + "step": 263370 + }, + { + "epoch": 0.59, + "learning_rate": 2.06638553947339e-05, + "loss": 0.1269, + "step": 263380 + }, + { + "epoch": 0.59, + "learning_rate": 2.0662848705845507e-05, + "loss": 0.1211, + "step": 263390 + }, + { + "epoch": 0.59, + "learning_rate": 2.0661730162636185e-05, + "loss": 0.12, + "step": 263400 + }, + { + "epoch": 0.59, + "learning_rate": 2.066061161942686e-05, + "loss": 0.1229, + "step": 263410 + }, + { + "epoch": 0.59, + "learning_rate": 2.0659493076217534e-05, + "loss": 0.1219, + "step": 263420 + }, + { + "epoch": 0.59, + "learning_rate": 2.0658374533008212e-05, + "loss": 0.1172, + "step": 263430 + }, + { + "epoch": 0.59, + "learning_rate": 2.0657255989798887e-05, + "loss": 0.1214, + "step": 263440 + }, + { + "epoch": 0.59, + "learning_rate": 2.0656137446589565e-05, + "loss": 0.121, + "step": 263450 + }, + { + "epoch": 0.59, + "learning_rate": 2.065501890338024e-05, + "loss": 0.1212, + "step": 263460 + }, + { + "epoch": 0.59, + "learning_rate": 2.0653900360170914e-05, + "loss": 0.1191, + "step": 263470 + }, + { + "epoch": 0.59, + "learning_rate": 2.0652781816961588e-05, + "loss": 0.1187, + "step": 263480 + }, + { + "epoch": 0.59, + "learning_rate": 2.0651663273752266e-05, + "loss": 0.1248, + "step": 263490 + }, + { + "epoch": 0.59, + "learning_rate": 2.065054473054294e-05, + "loss": 0.1314, + "step": 263500 + }, + { + "epoch": 0.59, + "learning_rate": 2.064942618733362e-05, + "loss": 0.126, + "step": 263510 + }, + { + "epoch": 0.59, + "learning_rate": 2.0648307644124293e-05, + "loss": 0.1269, + "step": 263520 + }, + { + "epoch": 0.59, + "learning_rate": 2.0647189100914968e-05, + "loss": 0.1267, + "step": 263530 + }, + { + "epoch": 0.59, + "learning_rate": 2.0646070557705646e-05, + "loss": 0.1268, + "step": 263540 + }, + { + "epoch": 0.59, + "learning_rate": 2.064495201449632e-05, + "loss": 0.13, + "step": 263550 + }, + { + "epoch": 0.59, + "learning_rate": 2.0643833471286998e-05, + "loss": 0.127, + "step": 263560 + }, + { + "epoch": 0.59, + "learning_rate": 2.0642714928077673e-05, + "loss": 0.1226, + "step": 263570 + }, + { + "epoch": 0.59, + "learning_rate": 2.0641596384868347e-05, + "loss": 0.1225, + "step": 263580 + }, + { + "epoch": 0.59, + "learning_rate": 2.0640477841659025e-05, + "loss": 0.1264, + "step": 263590 + }, + { + "epoch": 0.59, + "learning_rate": 2.06393592984497e-05, + "loss": 0.1236, + "step": 263600 + }, + { + "epoch": 0.59, + "learning_rate": 2.0638240755240378e-05, + "loss": 0.126, + "step": 263610 + }, + { + "epoch": 0.59, + "learning_rate": 2.0637122212031052e-05, + "loss": 0.1215, + "step": 263620 + }, + { + "epoch": 0.59, + "learning_rate": 2.0636003668821727e-05, + "loss": 0.1261, + "step": 263630 + }, + { + "epoch": 0.59, + "learning_rate": 2.06348851256124e-05, + "loss": 0.126, + "step": 263640 + }, + { + "epoch": 0.59, + "learning_rate": 2.063376658240308e-05, + "loss": 0.1227, + "step": 263650 + }, + { + "epoch": 0.59, + "learning_rate": 2.0632648039193757e-05, + "loss": 0.1281, + "step": 263660 + }, + { + "epoch": 0.59, + "learning_rate": 2.063152949598443e-05, + "loss": 0.1272, + "step": 263670 + }, + { + "epoch": 0.59, + "learning_rate": 2.0630410952775106e-05, + "loss": 0.1189, + "step": 263680 + }, + { + "epoch": 0.59, + "learning_rate": 2.062929240956578e-05, + "loss": 0.1251, + "step": 263690 + }, + { + "epoch": 0.59, + "learning_rate": 2.062817386635646e-05, + "loss": 0.1183, + "step": 263700 + }, + { + "epoch": 0.59, + "learning_rate": 2.0627055323147133e-05, + "loss": 0.1215, + "step": 263710 + }, + { + "epoch": 0.59, + "learning_rate": 2.062593677993781e-05, + "loss": 0.1255, + "step": 263720 + }, + { + "epoch": 0.59, + "learning_rate": 2.0624818236728486e-05, + "loss": 0.1267, + "step": 263730 + }, + { + "epoch": 0.59, + "learning_rate": 2.062369969351916e-05, + "loss": 0.1243, + "step": 263740 + }, + { + "epoch": 0.59, + "learning_rate": 2.0622581150309838e-05, + "loss": 0.1286, + "step": 263750 + }, + { + "epoch": 0.59, + "learning_rate": 2.0621462607100513e-05, + "loss": 0.1222, + "step": 263760 + }, + { + "epoch": 0.59, + "learning_rate": 2.062034406389119e-05, + "loss": 0.122, + "step": 263770 + }, + { + "epoch": 0.59, + "learning_rate": 2.0619225520681865e-05, + "loss": 0.1243, + "step": 263780 + }, + { + "epoch": 0.59, + "learning_rate": 2.061810697747254e-05, + "loss": 0.1239, + "step": 263790 + }, + { + "epoch": 0.59, + "learning_rate": 2.0616988434263214e-05, + "loss": 0.1244, + "step": 263800 + }, + { + "epoch": 0.59, + "learning_rate": 2.0615869891053892e-05, + "loss": 0.121, + "step": 263810 + }, + { + "epoch": 0.59, + "learning_rate": 2.061475134784457e-05, + "loss": 0.1259, + "step": 263820 + }, + { + "epoch": 0.59, + "learning_rate": 2.0613632804635245e-05, + "loss": 0.127, + "step": 263830 + }, + { + "epoch": 0.59, + "learning_rate": 2.061251426142592e-05, + "loss": 0.1205, + "step": 263840 + }, + { + "epoch": 0.59, + "learning_rate": 2.0611395718216594e-05, + "loss": 0.122, + "step": 263850 + }, + { + "epoch": 0.59, + "learning_rate": 2.061027717500727e-05, + "loss": 0.1244, + "step": 263860 + }, + { + "epoch": 0.59, + "learning_rate": 2.060915863179795e-05, + "loss": 0.1254, + "step": 263870 + }, + { + "epoch": 0.59, + "learning_rate": 2.0608040088588624e-05, + "loss": 0.126, + "step": 263880 + }, + { + "epoch": 0.59, + "learning_rate": 2.06069215453793e-05, + "loss": 0.1246, + "step": 263890 + }, + { + "epoch": 0.59, + "learning_rate": 2.0605803002169973e-05, + "loss": 0.1256, + "step": 263900 + }, + { + "epoch": 0.59, + "learning_rate": 2.060468445896065e-05, + "loss": 0.1262, + "step": 263910 + }, + { + "epoch": 0.59, + "learning_rate": 2.0603565915751326e-05, + "loss": 0.129, + "step": 263920 + }, + { + "epoch": 0.59, + "learning_rate": 2.0602447372542003e-05, + "loss": 0.1266, + "step": 263930 + }, + { + "epoch": 0.59, + "learning_rate": 2.0601328829332678e-05, + "loss": 0.1272, + "step": 263940 + }, + { + "epoch": 0.59, + "learning_rate": 2.0600210286123353e-05, + "loss": 0.1216, + "step": 263950 + }, + { + "epoch": 0.59, + "learning_rate": 2.0599091742914027e-05, + "loss": 0.1246, + "step": 263960 + }, + { + "epoch": 0.59, + "learning_rate": 2.0597973199704705e-05, + "loss": 0.1187, + "step": 263970 + }, + { + "epoch": 0.59, + "learning_rate": 2.0596854656495383e-05, + "loss": 0.1203, + "step": 263980 + }, + { + "epoch": 0.59, + "learning_rate": 2.0595736113286057e-05, + "loss": 0.1228, + "step": 263990 + }, + { + "epoch": 0.59, + "learning_rate": 2.0594617570076732e-05, + "loss": 0.1258, + "step": 264000 + }, + { + "epoch": 0.59, + "learning_rate": 2.0593499026867407e-05, + "loss": 0.1231, + "step": 264010 + }, + { + "epoch": 0.59, + "learning_rate": 2.0592380483658084e-05, + "loss": 0.1212, + "step": 264020 + }, + { + "epoch": 0.59, + "learning_rate": 2.0591261940448762e-05, + "loss": 0.1185, + "step": 264030 + }, + { + "epoch": 0.59, + "learning_rate": 2.0590143397239437e-05, + "loss": 0.1247, + "step": 264040 + }, + { + "epoch": 0.59, + "learning_rate": 2.058902485403011e-05, + "loss": 0.1278, + "step": 264050 + }, + { + "epoch": 0.59, + "learning_rate": 2.0587906310820786e-05, + "loss": 0.1243, + "step": 264060 + }, + { + "epoch": 0.59, + "learning_rate": 2.0586787767611464e-05, + "loss": 0.1255, + "step": 264070 + }, + { + "epoch": 0.59, + "learning_rate": 2.0585669224402142e-05, + "loss": 0.1215, + "step": 264080 + }, + { + "epoch": 0.59, + "learning_rate": 2.0584550681192816e-05, + "loss": 0.127, + "step": 264090 + }, + { + "epoch": 0.59, + "learning_rate": 2.058343213798349e-05, + "loss": 0.1254, + "step": 264100 + }, + { + "epoch": 0.59, + "learning_rate": 2.0582313594774165e-05, + "loss": 0.1247, + "step": 264110 + }, + { + "epoch": 0.59, + "learning_rate": 2.058119505156484e-05, + "loss": 0.1244, + "step": 264120 + }, + { + "epoch": 0.59, + "learning_rate": 2.058007650835552e-05, + "loss": 0.1239, + "step": 264130 + }, + { + "epoch": 0.59, + "learning_rate": 2.0578957965146196e-05, + "loss": 0.1221, + "step": 264140 + }, + { + "epoch": 0.59, + "learning_rate": 2.057783942193687e-05, + "loss": 0.1185, + "step": 264150 + }, + { + "epoch": 0.59, + "learning_rate": 2.0576720878727545e-05, + "loss": 0.1281, + "step": 264160 + }, + { + "epoch": 0.59, + "learning_rate": 2.057560233551822e-05, + "loss": 0.1201, + "step": 264170 + }, + { + "epoch": 0.59, + "learning_rate": 2.0574483792308897e-05, + "loss": 0.128, + "step": 264180 + }, + { + "epoch": 0.59, + "learning_rate": 2.0573365249099575e-05, + "loss": 0.1216, + "step": 264190 + }, + { + "epoch": 0.59, + "learning_rate": 2.057224670589025e-05, + "loss": 0.1246, + "step": 264200 + }, + { + "epoch": 0.59, + "learning_rate": 2.0571128162680924e-05, + "loss": 0.1268, + "step": 264210 + }, + { + "epoch": 0.59, + "learning_rate": 2.05700096194716e-05, + "loss": 0.1247, + "step": 264220 + }, + { + "epoch": 0.59, + "learning_rate": 2.0568891076262277e-05, + "loss": 0.1213, + "step": 264230 + }, + { + "epoch": 0.59, + "learning_rate": 2.0567772533052955e-05, + "loss": 0.1226, + "step": 264240 + }, + { + "epoch": 0.59, + "learning_rate": 2.056665398984363e-05, + "loss": 0.1255, + "step": 264250 + }, + { + "epoch": 0.59, + "learning_rate": 2.0565535446634304e-05, + "loss": 0.1226, + "step": 264260 + }, + { + "epoch": 0.59, + "learning_rate": 2.056441690342498e-05, + "loss": 0.1276, + "step": 264270 + }, + { + "epoch": 0.59, + "learning_rate": 2.0563298360215656e-05, + "loss": 0.122, + "step": 264280 + }, + { + "epoch": 0.59, + "learning_rate": 2.0562179817006334e-05, + "loss": 0.128, + "step": 264290 + }, + { + "epoch": 0.59, + "learning_rate": 2.056106127379701e-05, + "loss": 0.1235, + "step": 264300 + }, + { + "epoch": 0.59, + "learning_rate": 2.0559942730587683e-05, + "loss": 0.1235, + "step": 264310 + }, + { + "epoch": 0.59, + "learning_rate": 2.0558824187378358e-05, + "loss": 0.1263, + "step": 264320 + }, + { + "epoch": 0.59, + "learning_rate": 2.0557705644169032e-05, + "loss": 0.1249, + "step": 264330 + }, + { + "epoch": 0.59, + "learning_rate": 2.0556587100959714e-05, + "loss": 0.1174, + "step": 264340 + }, + { + "epoch": 0.59, + "learning_rate": 2.055546855775039e-05, + "loss": 0.1255, + "step": 264350 + }, + { + "epoch": 0.59, + "learning_rate": 2.0554350014541063e-05, + "loss": 0.1195, + "step": 264360 + }, + { + "epoch": 0.59, + "learning_rate": 2.0553231471331737e-05, + "loss": 0.1225, + "step": 264370 + }, + { + "epoch": 0.59, + "learning_rate": 2.0552112928122412e-05, + "loss": 0.126, + "step": 264380 + }, + { + "epoch": 0.59, + "learning_rate": 2.055099438491309e-05, + "loss": 0.1235, + "step": 264390 + }, + { + "epoch": 0.59, + "learning_rate": 2.0549875841703768e-05, + "loss": 0.1221, + "step": 264400 + }, + { + "epoch": 0.59, + "learning_rate": 2.0548757298494442e-05, + "loss": 0.125, + "step": 264410 + }, + { + "epoch": 0.59, + "learning_rate": 2.0547638755285117e-05, + "loss": 0.1291, + "step": 264420 + }, + { + "epoch": 0.59, + "learning_rate": 2.054652021207579e-05, + "loss": 0.1223, + "step": 264430 + }, + { + "epoch": 0.59, + "learning_rate": 2.054540166886647e-05, + "loss": 0.1214, + "step": 264440 + }, + { + "epoch": 0.59, + "learning_rate": 2.0544283125657147e-05, + "loss": 0.1267, + "step": 264450 + }, + { + "epoch": 0.59, + "learning_rate": 2.0543164582447822e-05, + "loss": 0.1219, + "step": 264460 + }, + { + "epoch": 0.59, + "learning_rate": 2.0542046039238496e-05, + "loss": 0.1239, + "step": 264470 + }, + { + "epoch": 0.59, + "learning_rate": 2.054092749602917e-05, + "loss": 0.1167, + "step": 264480 + }, + { + "epoch": 0.59, + "learning_rate": 2.053980895281985e-05, + "loss": 0.1182, + "step": 264490 + }, + { + "epoch": 0.59, + "learning_rate": 2.0538802263931454e-05, + "loss": 0.125, + "step": 264500 + }, + { + "epoch": 0.59, + "learning_rate": 2.0537683720722132e-05, + "loss": 0.1229, + "step": 264510 + }, + { + "epoch": 0.59, + "learning_rate": 2.053656517751281e-05, + "loss": 0.1213, + "step": 264520 + }, + { + "epoch": 0.59, + "learning_rate": 2.0535446634303485e-05, + "loss": 0.1187, + "step": 264530 + }, + { + "epoch": 0.59, + "learning_rate": 2.053432809109416e-05, + "loss": 0.1242, + "step": 264540 + }, + { + "epoch": 0.59, + "learning_rate": 2.0533209547884834e-05, + "loss": 0.122, + "step": 264550 + }, + { + "epoch": 0.59, + "learning_rate": 2.053209100467551e-05, + "loss": 0.1226, + "step": 264560 + }, + { + "epoch": 0.59, + "learning_rate": 2.053097246146619e-05, + "loss": 0.1246, + "step": 264570 + }, + { + "epoch": 0.59, + "learning_rate": 2.0529853918256864e-05, + "loss": 0.1222, + "step": 264580 + }, + { + "epoch": 0.59, + "learning_rate": 2.052873537504754e-05, + "loss": 0.1239, + "step": 264590 + }, + { + "epoch": 0.59, + "learning_rate": 2.0527616831838213e-05, + "loss": 0.1192, + "step": 264600 + }, + { + "epoch": 0.59, + "learning_rate": 2.052649828862889e-05, + "loss": 0.1183, + "step": 264610 + }, + { + "epoch": 0.59, + "learning_rate": 2.052537974541957e-05, + "loss": 0.1248, + "step": 264620 + }, + { + "epoch": 0.59, + "learning_rate": 2.0524261202210244e-05, + "loss": 0.1271, + "step": 264630 + }, + { + "epoch": 0.59, + "learning_rate": 2.0523142659000918e-05, + "loss": 0.125, + "step": 264640 + }, + { + "epoch": 0.59, + "learning_rate": 2.0522024115791593e-05, + "loss": 0.1249, + "step": 264650 + }, + { + "epoch": 0.59, + "learning_rate": 2.052090557258227e-05, + "loss": 0.1247, + "step": 264660 + }, + { + "epoch": 0.59, + "learning_rate": 2.0519787029372945e-05, + "loss": 0.1203, + "step": 264670 + }, + { + "epoch": 0.59, + "learning_rate": 2.0518668486163623e-05, + "loss": 0.1232, + "step": 264680 + }, + { + "epoch": 0.59, + "learning_rate": 2.0517549942954298e-05, + "loss": 0.1253, + "step": 264690 + }, + { + "epoch": 0.59, + "learning_rate": 2.0516431399744972e-05, + "loss": 0.1244, + "step": 264700 + }, + { + "epoch": 0.59, + "learning_rate": 2.051531285653565e-05, + "loss": 0.1209, + "step": 264710 + }, + { + "epoch": 0.59, + "learning_rate": 2.0514194313326325e-05, + "loss": 0.1208, + "step": 264720 + }, + { + "epoch": 0.59, + "learning_rate": 2.0513075770117003e-05, + "loss": 0.1259, + "step": 264730 + }, + { + "epoch": 0.59, + "learning_rate": 2.0511957226907677e-05, + "loss": 0.1262, + "step": 264740 + }, + { + "epoch": 0.59, + "learning_rate": 2.051083868369835e-05, + "loss": 0.1176, + "step": 264750 + }, + { + "epoch": 0.59, + "learning_rate": 2.0509720140489026e-05, + "loss": 0.1202, + "step": 264760 + }, + { + "epoch": 0.59, + "learning_rate": 2.0508601597279704e-05, + "loss": 0.1189, + "step": 264770 + }, + { + "epoch": 0.59, + "learning_rate": 2.0507483054070382e-05, + "loss": 0.1274, + "step": 264780 + }, + { + "epoch": 0.59, + "learning_rate": 2.0506364510861057e-05, + "loss": 0.1187, + "step": 264790 + }, + { + "epoch": 0.59, + "learning_rate": 2.050524596765173e-05, + "loss": 0.1268, + "step": 264800 + }, + { + "epoch": 0.59, + "learning_rate": 2.0504127424442406e-05, + "loss": 0.1283, + "step": 264810 + }, + { + "epoch": 0.59, + "learning_rate": 2.0503008881233084e-05, + "loss": 0.1205, + "step": 264820 + }, + { + "epoch": 0.59, + "learning_rate": 2.0501890338023758e-05, + "loss": 0.1266, + "step": 264830 + }, + { + "epoch": 0.59, + "learning_rate": 2.0500771794814436e-05, + "loss": 0.1194, + "step": 264840 + }, + { + "epoch": 0.59, + "learning_rate": 2.049965325160511e-05, + "loss": 0.1169, + "step": 264850 + }, + { + "epoch": 0.59, + "learning_rate": 2.0498534708395785e-05, + "loss": 0.1224, + "step": 264860 + }, + { + "epoch": 0.59, + "learning_rate": 2.0497416165186463e-05, + "loss": 0.1203, + "step": 264870 + }, + { + "epoch": 0.59, + "learning_rate": 2.0496297621977138e-05, + "loss": 0.1221, + "step": 264880 + }, + { + "epoch": 0.59, + "learning_rate": 2.0495179078767815e-05, + "loss": 0.1237, + "step": 264890 + }, + { + "epoch": 0.59, + "learning_rate": 2.049406053555849e-05, + "loss": 0.1234, + "step": 264900 + }, + { + "epoch": 0.59, + "learning_rate": 2.0492941992349165e-05, + "loss": 0.1204, + "step": 264910 + }, + { + "epoch": 0.59, + "learning_rate": 2.0491823449139842e-05, + "loss": 0.1209, + "step": 264920 + }, + { + "epoch": 0.59, + "learning_rate": 2.0490704905930517e-05, + "loss": 0.1261, + "step": 264930 + }, + { + "epoch": 0.59, + "learning_rate": 2.0489586362721195e-05, + "loss": 0.123, + "step": 264940 + }, + { + "epoch": 0.59, + "learning_rate": 2.048846781951187e-05, + "loss": 0.1195, + "step": 264950 + }, + { + "epoch": 0.59, + "learning_rate": 2.0487349276302544e-05, + "loss": 0.1211, + "step": 264960 + }, + { + "epoch": 0.59, + "learning_rate": 2.048623073309322e-05, + "loss": 0.1223, + "step": 264970 + }, + { + "epoch": 0.59, + "learning_rate": 2.0485112189883896e-05, + "loss": 0.1249, + "step": 264980 + }, + { + "epoch": 0.59, + "learning_rate": 2.048399364667457e-05, + "loss": 0.1233, + "step": 264990 + }, + { + "epoch": 0.59, + "learning_rate": 2.048287510346525e-05, + "loss": 0.1218, + "step": 265000 + }, + { + "epoch": 0.59, + "learning_rate": 2.0481756560255923e-05, + "loss": 0.1259, + "step": 265010 + }, + { + "epoch": 0.59, + "learning_rate": 2.0480638017046598e-05, + "loss": 0.1223, + "step": 265020 + }, + { + "epoch": 0.59, + "learning_rate": 2.0479519473837276e-05, + "loss": 0.1207, + "step": 265030 + }, + { + "epoch": 0.59, + "learning_rate": 2.047840093062795e-05, + "loss": 0.1247, + "step": 265040 + }, + { + "epoch": 0.59, + "learning_rate": 2.047728238741863e-05, + "loss": 0.1245, + "step": 265050 + }, + { + "epoch": 0.59, + "learning_rate": 2.0476163844209303e-05, + "loss": 0.1248, + "step": 265060 + }, + { + "epoch": 0.59, + "learning_rate": 2.0475045300999978e-05, + "loss": 0.1213, + "step": 265070 + }, + { + "epoch": 0.59, + "learning_rate": 2.0473926757790655e-05, + "loss": 0.1227, + "step": 265080 + }, + { + "epoch": 0.59, + "learning_rate": 2.047280821458133e-05, + "loss": 0.1202, + "step": 265090 + }, + { + "epoch": 0.59, + "learning_rate": 2.0471689671372008e-05, + "loss": 0.1252, + "step": 265100 + }, + { + "epoch": 0.59, + "learning_rate": 2.0470571128162682e-05, + "loss": 0.1231, + "step": 265110 + }, + { + "epoch": 0.59, + "learning_rate": 2.0469452584953357e-05, + "loss": 0.1229, + "step": 265120 + }, + { + "epoch": 0.59, + "learning_rate": 2.0468334041744035e-05, + "loss": 0.1203, + "step": 265130 + }, + { + "epoch": 0.59, + "learning_rate": 2.046721549853471e-05, + "loss": 0.122, + "step": 265140 + }, + { + "epoch": 0.59, + "learning_rate": 2.0466096955325384e-05, + "loss": 0.1247, + "step": 265150 + }, + { + "epoch": 0.59, + "learning_rate": 2.0464978412116062e-05, + "loss": 0.1232, + "step": 265160 + }, + { + "epoch": 0.59, + "learning_rate": 2.0463859868906736e-05, + "loss": 0.1226, + "step": 265170 + }, + { + "epoch": 0.59, + "learning_rate": 2.046274132569741e-05, + "loss": 0.1215, + "step": 265180 + }, + { + "epoch": 0.59, + "learning_rate": 2.046162278248809e-05, + "loss": 0.1204, + "step": 265190 + }, + { + "epoch": 0.59, + "learning_rate": 2.0460504239278763e-05, + "loss": 0.1281, + "step": 265200 + }, + { + "epoch": 0.59, + "learning_rate": 2.045938569606944e-05, + "loss": 0.1242, + "step": 265210 + }, + { + "epoch": 0.59, + "learning_rate": 2.0458267152860116e-05, + "loss": 0.1198, + "step": 265220 + }, + { + "epoch": 0.59, + "learning_rate": 2.045714860965079e-05, + "loss": 0.1194, + "step": 265230 + }, + { + "epoch": 0.59, + "learning_rate": 2.045603006644147e-05, + "loss": 0.1197, + "step": 265240 + }, + { + "epoch": 0.59, + "learning_rate": 2.0454911523232143e-05, + "loss": 0.1197, + "step": 265250 + }, + { + "epoch": 0.59, + "learning_rate": 2.045379298002282e-05, + "loss": 0.1197, + "step": 265260 + }, + { + "epoch": 0.59, + "learning_rate": 2.0452674436813495e-05, + "loss": 0.1168, + "step": 265270 + }, + { + "epoch": 0.59, + "learning_rate": 2.045155589360417e-05, + "loss": 0.1161, + "step": 265280 + }, + { + "epoch": 0.59, + "learning_rate": 2.0450437350394848e-05, + "loss": 0.1247, + "step": 265290 + }, + { + "epoch": 0.59, + "learning_rate": 2.0449318807185522e-05, + "loss": 0.1192, + "step": 265300 + }, + { + "epoch": 0.59, + "learning_rate": 2.0448200263976197e-05, + "loss": 0.1216, + "step": 265310 + }, + { + "epoch": 0.59, + "learning_rate": 2.0447081720766875e-05, + "loss": 0.1215, + "step": 265320 + }, + { + "epoch": 0.59, + "learning_rate": 2.044596317755755e-05, + "loss": 0.1197, + "step": 265330 + }, + { + "epoch": 0.59, + "learning_rate": 2.0444844634348227e-05, + "loss": 0.1222, + "step": 265340 + }, + { + "epoch": 0.59, + "learning_rate": 2.0443726091138902e-05, + "loss": 0.1205, + "step": 265350 + }, + { + "epoch": 0.59, + "learning_rate": 2.0442607547929576e-05, + "loss": 0.1188, + "step": 265360 + }, + { + "epoch": 0.59, + "learning_rate": 2.0441489004720254e-05, + "loss": 0.1192, + "step": 265370 + }, + { + "epoch": 0.59, + "learning_rate": 2.044037046151093e-05, + "loss": 0.1218, + "step": 265380 + }, + { + "epoch": 0.59, + "learning_rate": 2.0439251918301607e-05, + "loss": 0.1183, + "step": 265390 + }, + { + "epoch": 0.59, + "learning_rate": 2.043813337509228e-05, + "loss": 0.1204, + "step": 265400 + }, + { + "epoch": 0.59, + "learning_rate": 2.0437014831882956e-05, + "loss": 0.1232, + "step": 265410 + }, + { + "epoch": 0.59, + "learning_rate": 2.0435896288673634e-05, + "loss": 0.1193, + "step": 265420 + }, + { + "epoch": 0.59, + "learning_rate": 2.043477774546431e-05, + "loss": 0.1239, + "step": 265430 + }, + { + "epoch": 0.59, + "learning_rate": 2.0433659202254983e-05, + "loss": 0.1236, + "step": 265440 + }, + { + "epoch": 0.59, + "learning_rate": 2.043254065904566e-05, + "loss": 0.119, + "step": 265450 + }, + { + "epoch": 0.59, + "learning_rate": 2.0431422115836335e-05, + "loss": 0.1154, + "step": 265460 + }, + { + "epoch": 0.59, + "learning_rate": 2.043030357262701e-05, + "loss": 0.124, + "step": 265470 + }, + { + "epoch": 0.59, + "learning_rate": 2.0429185029417688e-05, + "loss": 0.1258, + "step": 265480 + }, + { + "epoch": 0.59, + "learning_rate": 2.0428066486208362e-05, + "loss": 0.1203, + "step": 265490 + }, + { + "epoch": 0.59, + "learning_rate": 2.042694794299904e-05, + "loss": 0.1188, + "step": 265500 + }, + { + "epoch": 0.59, + "learning_rate": 2.0425829399789715e-05, + "loss": 0.1209, + "step": 265510 + }, + { + "epoch": 0.59, + "learning_rate": 2.042471085658039e-05, + "loss": 0.12, + "step": 265520 + }, + { + "epoch": 0.59, + "learning_rate": 2.0423592313371067e-05, + "loss": 0.1198, + "step": 265530 + }, + { + "epoch": 0.59, + "learning_rate": 2.0422473770161742e-05, + "loss": 0.1236, + "step": 265540 + }, + { + "epoch": 0.59, + "learning_rate": 2.042135522695242e-05, + "loss": 0.1228, + "step": 265550 + }, + { + "epoch": 0.59, + "learning_rate": 2.0420236683743094e-05, + "loss": 0.1185, + "step": 265560 + }, + { + "epoch": 0.59, + "learning_rate": 2.041911814053377e-05, + "loss": 0.1213, + "step": 265570 + }, + { + "epoch": 0.59, + "learning_rate": 2.0417999597324447e-05, + "loss": 0.1194, + "step": 265580 + }, + { + "epoch": 0.59, + "learning_rate": 2.041688105411512e-05, + "loss": 0.125, + "step": 265590 + }, + { + "epoch": 0.59, + "learning_rate": 2.04157625109058e-05, + "loss": 0.1206, + "step": 265600 + }, + { + "epoch": 0.59, + "learning_rate": 2.0414643967696474e-05, + "loss": 0.1208, + "step": 265610 + }, + { + "epoch": 0.59, + "learning_rate": 2.041352542448715e-05, + "loss": 0.123, + "step": 265620 + }, + { + "epoch": 0.59, + "learning_rate": 2.0412406881277823e-05, + "loss": 0.1217, + "step": 265630 + }, + { + "epoch": 0.59, + "learning_rate": 2.04112883380685e-05, + "loss": 0.1248, + "step": 265640 + }, + { + "epoch": 0.59, + "learning_rate": 2.0410169794859175e-05, + "loss": 0.1214, + "step": 265650 + }, + { + "epoch": 0.59, + "learning_rate": 2.0409051251649853e-05, + "loss": 0.1276, + "step": 265660 + }, + { + "epoch": 0.59, + "learning_rate": 2.0407932708440528e-05, + "loss": 0.1239, + "step": 265670 + }, + { + "epoch": 0.59, + "learning_rate": 2.0406814165231202e-05, + "loss": 0.125, + "step": 265680 + }, + { + "epoch": 0.59, + "learning_rate": 2.040569562202188e-05, + "loss": 0.1191, + "step": 265690 + }, + { + "epoch": 0.59, + "learning_rate": 2.0404577078812555e-05, + "loss": 0.1249, + "step": 265700 + }, + { + "epoch": 0.59, + "learning_rate": 2.0403458535603233e-05, + "loss": 0.1241, + "step": 265710 + }, + { + "epoch": 0.59, + "learning_rate": 2.0402339992393907e-05, + "loss": 0.1253, + "step": 265720 + }, + { + "epoch": 0.59, + "learning_rate": 2.0401221449184582e-05, + "loss": 0.1253, + "step": 265730 + }, + { + "epoch": 0.59, + "learning_rate": 2.0400102905975256e-05, + "loss": 0.121, + "step": 265740 + }, + { + "epoch": 0.59, + "learning_rate": 2.0398984362765934e-05, + "loss": 0.1179, + "step": 265750 + }, + { + "epoch": 0.59, + "learning_rate": 2.0397865819556612e-05, + "loss": 0.1211, + "step": 265760 + }, + { + "epoch": 0.59, + "learning_rate": 2.0396747276347287e-05, + "loss": 0.1236, + "step": 265770 + }, + { + "epoch": 0.59, + "learning_rate": 2.039562873313796e-05, + "loss": 0.1205, + "step": 265780 + }, + { + "epoch": 0.59, + "learning_rate": 2.0394510189928636e-05, + "loss": 0.1199, + "step": 265790 + }, + { + "epoch": 0.59, + "learning_rate": 2.0393391646719314e-05, + "loss": 0.1201, + "step": 265800 + }, + { + "epoch": 0.59, + "learning_rate": 2.039227310350999e-05, + "loss": 0.122, + "step": 265810 + }, + { + "epoch": 0.59, + "learning_rate": 2.0391154560300666e-05, + "loss": 0.1232, + "step": 265820 + }, + { + "epoch": 0.59, + "learning_rate": 2.039003601709134e-05, + "loss": 0.1243, + "step": 265830 + }, + { + "epoch": 0.59, + "learning_rate": 2.0388917473882015e-05, + "loss": 0.122, + "step": 265840 + }, + { + "epoch": 0.59, + "learning_rate": 2.0387798930672693e-05, + "loss": 0.1222, + "step": 265850 + }, + { + "epoch": 0.59, + "learning_rate": 2.0386680387463368e-05, + "loss": 0.1216, + "step": 265860 + }, + { + "epoch": 0.59, + "learning_rate": 2.0385561844254046e-05, + "loss": 0.1217, + "step": 265870 + }, + { + "epoch": 0.59, + "learning_rate": 2.038444330104472e-05, + "loss": 0.1237, + "step": 265880 + }, + { + "epoch": 0.59, + "learning_rate": 2.0383324757835395e-05, + "loss": 0.1203, + "step": 265890 + }, + { + "epoch": 0.59, + "learning_rate": 2.038220621462607e-05, + "loss": 0.124, + "step": 265900 + }, + { + "epoch": 0.59, + "learning_rate": 2.0381087671416747e-05, + "loss": 0.1186, + "step": 265910 + }, + { + "epoch": 0.59, + "learning_rate": 2.0379969128207425e-05, + "loss": 0.1229, + "step": 265920 + }, + { + "epoch": 0.59, + "learning_rate": 2.03788505849981e-05, + "loss": 0.1237, + "step": 265930 + }, + { + "epoch": 0.59, + "learning_rate": 2.0377732041788774e-05, + "loss": 0.121, + "step": 265940 + }, + { + "epoch": 0.59, + "learning_rate": 2.037661349857945e-05, + "loss": 0.1207, + "step": 265950 + }, + { + "epoch": 0.59, + "learning_rate": 2.0375494955370127e-05, + "loss": 0.1246, + "step": 265960 + }, + { + "epoch": 0.59, + "learning_rate": 2.0374376412160805e-05, + "loss": 0.125, + "step": 265970 + }, + { + "epoch": 0.59, + "learning_rate": 2.037325786895148e-05, + "loss": 0.1213, + "step": 265980 + }, + { + "epoch": 0.59, + "learning_rate": 2.0372139325742154e-05, + "loss": 0.1194, + "step": 265990 + }, + { + "epoch": 0.59, + "learning_rate": 2.0371020782532828e-05, + "loss": 0.1226, + "step": 266000 + }, + { + "epoch": 0.59, + "learning_rate": 2.0369902239323506e-05, + "loss": 0.1265, + "step": 266010 + }, + { + "epoch": 0.59, + "learning_rate": 2.0368783696114184e-05, + "loss": 0.1219, + "step": 266020 + }, + { + "epoch": 0.59, + "learning_rate": 2.036766515290486e-05, + "loss": 0.1225, + "step": 266030 + }, + { + "epoch": 0.59, + "learning_rate": 2.0366546609695533e-05, + "loss": 0.1209, + "step": 266040 + }, + { + "epoch": 0.59, + "learning_rate": 2.0365428066486208e-05, + "loss": 0.1232, + "step": 266050 + }, + { + "epoch": 0.59, + "learning_rate": 2.0364309523276882e-05, + "loss": 0.1208, + "step": 266060 + }, + { + "epoch": 0.59, + "learning_rate": 2.036319098006756e-05, + "loss": 0.1193, + "step": 266070 + }, + { + "epoch": 0.59, + "learning_rate": 2.0362072436858238e-05, + "loss": 0.1217, + "step": 266080 + }, + { + "epoch": 0.59, + "learning_rate": 2.0360953893648913e-05, + "loss": 0.1215, + "step": 266090 + }, + { + "epoch": 0.59, + "learning_rate": 2.0359835350439587e-05, + "loss": 0.1238, + "step": 266100 + }, + { + "epoch": 0.59, + "learning_rate": 2.0358716807230262e-05, + "loss": 0.1258, + "step": 266110 + }, + { + "epoch": 0.59, + "learning_rate": 2.035759826402094e-05, + "loss": 0.1248, + "step": 266120 + }, + { + "epoch": 0.59, + "learning_rate": 2.0356479720811618e-05, + "loss": 0.1248, + "step": 266130 + }, + { + "epoch": 0.59, + "learning_rate": 2.0355361177602292e-05, + "loss": 0.1205, + "step": 266140 + }, + { + "epoch": 0.59, + "learning_rate": 2.0354242634392967e-05, + "loss": 0.1243, + "step": 266150 + }, + { + "epoch": 0.59, + "learning_rate": 2.035312409118364e-05, + "loss": 0.1213, + "step": 266160 + }, + { + "epoch": 0.59, + "learning_rate": 2.035200554797432e-05, + "loss": 0.1177, + "step": 266170 + }, + { + "epoch": 0.59, + "learning_rate": 2.0350887004764997e-05, + "loss": 0.1191, + "step": 266180 + }, + { + "epoch": 0.59, + "learning_rate": 2.034976846155567e-05, + "loss": 0.12, + "step": 266190 + }, + { + "epoch": 0.59, + "learning_rate": 2.0348649918346346e-05, + "loss": 0.1176, + "step": 266200 + }, + { + "epoch": 0.59, + "learning_rate": 2.034753137513702e-05, + "loss": 0.1205, + "step": 266210 + }, + { + "epoch": 0.59, + "learning_rate": 2.03464128319277e-05, + "loss": 0.119, + "step": 266220 + }, + { + "epoch": 0.59, + "learning_rate": 2.0345294288718377e-05, + "loss": 0.1207, + "step": 266230 + }, + { + "epoch": 0.59, + "learning_rate": 2.034417574550905e-05, + "loss": 0.1187, + "step": 266240 + }, + { + "epoch": 0.59, + "learning_rate": 2.0343057202299726e-05, + "loss": 0.118, + "step": 266250 + }, + { + "epoch": 0.59, + "learning_rate": 2.03419386590904e-05, + "loss": 0.1237, + "step": 266260 + }, + { + "epoch": 0.59, + "learning_rate": 2.0340820115881075e-05, + "loss": 0.1196, + "step": 266270 + }, + { + "epoch": 0.59, + "learning_rate": 2.0339701572671756e-05, + "loss": 0.1237, + "step": 266280 + }, + { + "epoch": 0.59, + "learning_rate": 2.033858302946243e-05, + "loss": 0.117, + "step": 266290 + }, + { + "epoch": 0.59, + "learning_rate": 2.0337464486253105e-05, + "loss": 0.1224, + "step": 266300 + }, + { + "epoch": 0.59, + "learning_rate": 2.033634594304378e-05, + "loss": 0.1254, + "step": 266310 + }, + { + "epoch": 0.59, + "learning_rate": 2.0335227399834454e-05, + "loss": 0.1205, + "step": 266320 + }, + { + "epoch": 0.59, + "learning_rate": 2.0334108856625132e-05, + "loss": 0.1215, + "step": 266330 + }, + { + "epoch": 0.59, + "learning_rate": 2.033299031341581e-05, + "loss": 0.122, + "step": 266340 + }, + { + "epoch": 0.59, + "learning_rate": 2.0331871770206485e-05, + "loss": 0.1208, + "step": 266350 + }, + { + "epoch": 0.59, + "learning_rate": 2.033075322699716e-05, + "loss": 0.1223, + "step": 266360 + }, + { + "epoch": 0.59, + "learning_rate": 2.0329634683787834e-05, + "loss": 0.1263, + "step": 266370 + }, + { + "epoch": 0.59, + "learning_rate": 2.032851614057851e-05, + "loss": 0.121, + "step": 266380 + }, + { + "epoch": 0.59, + "learning_rate": 2.032739759736919e-05, + "loss": 0.1201, + "step": 266390 + }, + { + "epoch": 0.59, + "learning_rate": 2.0326279054159864e-05, + "loss": 0.1212, + "step": 266400 + }, + { + "epoch": 0.59, + "learning_rate": 2.032516051095054e-05, + "loss": 0.1247, + "step": 266410 + }, + { + "epoch": 0.59, + "learning_rate": 2.0324041967741213e-05, + "loss": 0.1185, + "step": 266420 + }, + { + "epoch": 0.59, + "learning_rate": 2.032292342453189e-05, + "loss": 0.118, + "step": 266430 + }, + { + "epoch": 0.59, + "learning_rate": 2.032180488132257e-05, + "loss": 0.1208, + "step": 266440 + }, + { + "epoch": 0.59, + "learning_rate": 2.0320686338113244e-05, + "loss": 0.1199, + "step": 266450 + }, + { + "epoch": 0.59, + "learning_rate": 2.0319567794903918e-05, + "loss": 0.1217, + "step": 266460 + }, + { + "epoch": 0.59, + "learning_rate": 2.0318449251694593e-05, + "loss": 0.1196, + "step": 266470 + }, + { + "epoch": 0.59, + "learning_rate": 2.0317330708485267e-05, + "loss": 0.1248, + "step": 266480 + }, + { + "epoch": 0.59, + "learning_rate": 2.031621216527595e-05, + "loss": 0.1185, + "step": 266490 + }, + { + "epoch": 0.59, + "learning_rate": 2.0315093622066623e-05, + "loss": 0.1206, + "step": 266500 + }, + { + "epoch": 0.59, + "learning_rate": 2.0313975078857298e-05, + "loss": 0.1213, + "step": 266510 + }, + { + "epoch": 0.59, + "learning_rate": 2.0312856535647972e-05, + "loss": 0.1209, + "step": 266520 + }, + { + "epoch": 0.59, + "learning_rate": 2.0311737992438647e-05, + "loss": 0.1221, + "step": 266530 + }, + { + "epoch": 0.59, + "learning_rate": 2.0310619449229325e-05, + "loss": 0.1231, + "step": 266540 + }, + { + "epoch": 0.59, + "learning_rate": 2.0309500906020002e-05, + "loss": 0.1201, + "step": 266550 + }, + { + "epoch": 0.59, + "learning_rate": 2.0308382362810677e-05, + "loss": 0.1159, + "step": 266560 + }, + { + "epoch": 0.6, + "learning_rate": 2.030726381960135e-05, + "loss": 0.1187, + "step": 266570 + }, + { + "epoch": 0.6, + "learning_rate": 2.0306145276392026e-05, + "loss": 0.1173, + "step": 266580 + }, + { + "epoch": 0.6, + "learning_rate": 2.0305026733182704e-05, + "loss": 0.1211, + "step": 266590 + }, + { + "epoch": 0.6, + "learning_rate": 2.0303908189973382e-05, + "loss": 0.122, + "step": 266600 + }, + { + "epoch": 0.6, + "learning_rate": 2.0302789646764056e-05, + "loss": 0.1225, + "step": 266610 + }, + { + "epoch": 0.6, + "learning_rate": 2.030167110355473e-05, + "loss": 0.1228, + "step": 266620 + }, + { + "epoch": 0.6, + "learning_rate": 2.0300552560345406e-05, + "loss": 0.1197, + "step": 266630 + }, + { + "epoch": 0.6, + "learning_rate": 2.0299434017136084e-05, + "loss": 0.1204, + "step": 266640 + }, + { + "epoch": 0.6, + "learning_rate": 2.029831547392676e-05, + "loss": 0.1206, + "step": 266650 + }, + { + "epoch": 0.6, + "learning_rate": 2.0297196930717436e-05, + "loss": 0.1252, + "step": 266660 + }, + { + "epoch": 0.6, + "learning_rate": 2.029607838750811e-05, + "loss": 0.1193, + "step": 266670 + }, + { + "epoch": 0.6, + "learning_rate": 2.0294959844298785e-05, + "loss": 0.1234, + "step": 266680 + }, + { + "epoch": 0.6, + "learning_rate": 2.029384130108946e-05, + "loss": 0.1218, + "step": 266690 + }, + { + "epoch": 0.6, + "learning_rate": 2.0292722757880138e-05, + "loss": 0.1186, + "step": 266700 + }, + { + "epoch": 0.6, + "learning_rate": 2.0291604214670815e-05, + "loss": 0.123, + "step": 266710 + }, + { + "epoch": 0.6, + "learning_rate": 2.029048567146149e-05, + "loss": 0.1206, + "step": 266720 + }, + { + "epoch": 0.6, + "learning_rate": 2.0289367128252165e-05, + "loss": 0.1193, + "step": 266730 + }, + { + "epoch": 0.6, + "learning_rate": 2.028824858504284e-05, + "loss": 0.1238, + "step": 266740 + }, + { + "epoch": 0.6, + "learning_rate": 2.0287130041833517e-05, + "loss": 0.1223, + "step": 266750 + }, + { + "epoch": 0.6, + "learning_rate": 2.0286011498624195e-05, + "loss": 0.1218, + "step": 266760 + }, + { + "epoch": 0.6, + "learning_rate": 2.028489295541487e-05, + "loss": 0.1221, + "step": 266770 + }, + { + "epoch": 0.6, + "learning_rate": 2.0283774412205544e-05, + "loss": 0.1197, + "step": 266780 + }, + { + "epoch": 0.6, + "learning_rate": 2.028265586899622e-05, + "loss": 0.1184, + "step": 266790 + }, + { + "epoch": 0.6, + "learning_rate": 2.0281537325786896e-05, + "loss": 0.1223, + "step": 266800 + }, + { + "epoch": 0.6, + "learning_rate": 2.0280418782577574e-05, + "loss": 0.1208, + "step": 266810 + }, + { + "epoch": 0.6, + "learning_rate": 2.027930023936825e-05, + "loss": 0.1254, + "step": 266820 + }, + { + "epoch": 0.6, + "learning_rate": 2.0278181696158923e-05, + "loss": 0.1175, + "step": 266830 + }, + { + "epoch": 0.6, + "learning_rate": 2.0277063152949598e-05, + "loss": 0.1238, + "step": 266840 + }, + { + "epoch": 0.6, + "learning_rate": 2.0275944609740276e-05, + "loss": 0.1142, + "step": 266850 + }, + { + "epoch": 0.6, + "learning_rate": 2.027482606653095e-05, + "loss": 0.1146, + "step": 266860 + }, + { + "epoch": 0.6, + "learning_rate": 2.027370752332163e-05, + "loss": 0.1196, + "step": 266870 + }, + { + "epoch": 0.6, + "learning_rate": 2.0272588980112303e-05, + "loss": 0.1254, + "step": 266880 + }, + { + "epoch": 0.6, + "learning_rate": 2.0271470436902977e-05, + "loss": 0.114, + "step": 266890 + }, + { + "epoch": 0.6, + "learning_rate": 2.0270351893693655e-05, + "loss": 0.1144, + "step": 266900 + }, + { + "epoch": 0.6, + "learning_rate": 2.026923335048433e-05, + "loss": 0.1223, + "step": 266910 + }, + { + "epoch": 0.6, + "learning_rate": 2.0268114807275008e-05, + "loss": 0.1196, + "step": 266920 + }, + { + "epoch": 0.6, + "learning_rate": 2.0266996264065682e-05, + "loss": 0.1199, + "step": 266930 + }, + { + "epoch": 0.6, + "learning_rate": 2.0265877720856357e-05, + "loss": 0.1167, + "step": 266940 + }, + { + "epoch": 0.6, + "learning_rate": 2.026475917764703e-05, + "loss": 0.1221, + "step": 266950 + }, + { + "epoch": 0.6, + "learning_rate": 2.026364063443771e-05, + "loss": 0.1179, + "step": 266960 + }, + { + "epoch": 0.6, + "learning_rate": 2.0262522091228387e-05, + "loss": 0.1233, + "step": 266970 + }, + { + "epoch": 0.6, + "learning_rate": 2.0261403548019062e-05, + "loss": 0.1211, + "step": 266980 + }, + { + "epoch": 0.6, + "learning_rate": 2.0260285004809736e-05, + "loss": 0.1217, + "step": 266990 + }, + { + "epoch": 0.6, + "learning_rate": 2.025916646160041e-05, + "loss": 0.121, + "step": 267000 + }, + { + "epoch": 0.6, + "learning_rate": 2.025804791839109e-05, + "loss": 0.1202, + "step": 267010 + }, + { + "epoch": 0.6, + "learning_rate": 2.0256929375181763e-05, + "loss": 0.1196, + "step": 267020 + }, + { + "epoch": 0.6, + "learning_rate": 2.025581083197244e-05, + "loss": 0.1251, + "step": 267030 + }, + { + "epoch": 0.6, + "learning_rate": 2.0254692288763116e-05, + "loss": 0.1234, + "step": 267040 + }, + { + "epoch": 0.6, + "learning_rate": 2.025357374555379e-05, + "loss": 0.1248, + "step": 267050 + }, + { + "epoch": 0.6, + "learning_rate": 2.025245520234447e-05, + "loss": 0.124, + "step": 267060 + }, + { + "epoch": 0.6, + "learning_rate": 2.0251336659135143e-05, + "loss": 0.1192, + "step": 267070 + }, + { + "epoch": 0.6, + "learning_rate": 2.025021811592582e-05, + "loss": 0.1189, + "step": 267080 + }, + { + "epoch": 0.6, + "learning_rate": 2.0249099572716495e-05, + "loss": 0.123, + "step": 267090 + }, + { + "epoch": 0.6, + "learning_rate": 2.024798102950717e-05, + "loss": 0.1208, + "step": 267100 + }, + { + "epoch": 0.6, + "learning_rate": 2.0246862486297848e-05, + "loss": 0.1178, + "step": 267110 + }, + { + "epoch": 0.6, + "learning_rate": 2.0245743943088522e-05, + "loss": 0.1146, + "step": 267120 + }, + { + "epoch": 0.6, + "learning_rate": 2.02446253998792e-05, + "loss": 0.1215, + "step": 267130 + }, + { + "epoch": 0.6, + "learning_rate": 2.0243506856669875e-05, + "loss": 0.1213, + "step": 267140 + }, + { + "epoch": 0.6, + "learning_rate": 2.024238831346055e-05, + "loss": 0.1201, + "step": 267150 + }, + { + "epoch": 0.6, + "learning_rate": 2.0241269770251224e-05, + "loss": 0.1171, + "step": 267160 + }, + { + "epoch": 0.6, + "learning_rate": 2.0240151227041902e-05, + "loss": 0.118, + "step": 267170 + }, + { + "epoch": 0.6, + "learning_rate": 2.0239032683832576e-05, + "loss": 0.1207, + "step": 267180 + }, + { + "epoch": 0.6, + "learning_rate": 2.0237914140623254e-05, + "loss": 0.1225, + "step": 267190 + }, + { + "epoch": 0.6, + "learning_rate": 2.023679559741393e-05, + "loss": 0.123, + "step": 267200 + }, + { + "epoch": 0.6, + "learning_rate": 2.0235677054204603e-05, + "loss": 0.1232, + "step": 267210 + }, + { + "epoch": 0.6, + "learning_rate": 2.0234670365316212e-05, + "loss": 0.1184, + "step": 267220 + }, + { + "epoch": 0.6, + "learning_rate": 2.023355182210689e-05, + "loss": 0.1204, + "step": 267230 + }, + { + "epoch": 0.6, + "learning_rate": 2.0232433278897565e-05, + "loss": 0.1195, + "step": 267240 + }, + { + "epoch": 0.6, + "learning_rate": 2.023131473568824e-05, + "loss": 0.1245, + "step": 267250 + }, + { + "epoch": 0.6, + "learning_rate": 2.0230196192478917e-05, + "loss": 0.1225, + "step": 267260 + }, + { + "epoch": 0.6, + "learning_rate": 2.022907764926959e-05, + "loss": 0.1186, + "step": 267270 + }, + { + "epoch": 0.6, + "learning_rate": 2.022795910606027e-05, + "loss": 0.1181, + "step": 267280 + }, + { + "epoch": 0.6, + "learning_rate": 2.0226840562850944e-05, + "loss": 0.1173, + "step": 267290 + }, + { + "epoch": 0.6, + "learning_rate": 2.022572201964162e-05, + "loss": 0.1229, + "step": 267300 + }, + { + "epoch": 0.6, + "learning_rate": 2.0224603476432297e-05, + "loss": 0.1201, + "step": 267310 + }, + { + "epoch": 0.6, + "learning_rate": 2.022348493322297e-05, + "loss": 0.1252, + "step": 267320 + }, + { + "epoch": 0.6, + "learning_rate": 2.0222366390013646e-05, + "loss": 0.1232, + "step": 267330 + }, + { + "epoch": 0.6, + "learning_rate": 2.0221247846804324e-05, + "loss": 0.1198, + "step": 267340 + }, + { + "epoch": 0.6, + "learning_rate": 2.0220129303594998e-05, + "loss": 0.1197, + "step": 267350 + }, + { + "epoch": 0.6, + "learning_rate": 2.0219010760385676e-05, + "loss": 0.1202, + "step": 267360 + }, + { + "epoch": 0.6, + "learning_rate": 2.021789221717635e-05, + "loss": 0.1174, + "step": 267370 + }, + { + "epoch": 0.6, + "learning_rate": 2.0216773673967025e-05, + "loss": 0.1221, + "step": 267380 + }, + { + "epoch": 0.6, + "learning_rate": 2.0215655130757703e-05, + "loss": 0.1201, + "step": 267390 + }, + { + "epoch": 0.6, + "learning_rate": 2.0214536587548378e-05, + "loss": 0.1182, + "step": 267400 + }, + { + "epoch": 0.6, + "learning_rate": 2.0213418044339052e-05, + "loss": 0.1224, + "step": 267410 + }, + { + "epoch": 0.6, + "learning_rate": 2.021229950112973e-05, + "loss": 0.1182, + "step": 267420 + }, + { + "epoch": 0.6, + "learning_rate": 2.0211180957920405e-05, + "loss": 0.1208, + "step": 267430 + }, + { + "epoch": 0.6, + "learning_rate": 2.0210062414711083e-05, + "loss": 0.1144, + "step": 267440 + }, + { + "epoch": 0.6, + "learning_rate": 2.0208943871501757e-05, + "loss": 0.1214, + "step": 267450 + }, + { + "epoch": 0.6, + "learning_rate": 2.020782532829243e-05, + "loss": 0.1128, + "step": 267460 + }, + { + "epoch": 0.6, + "learning_rate": 2.020670678508311e-05, + "loss": 0.1203, + "step": 267470 + }, + { + "epoch": 0.6, + "learning_rate": 2.0205588241873784e-05, + "loss": 0.1231, + "step": 267480 + }, + { + "epoch": 0.6, + "learning_rate": 2.0204469698664462e-05, + "loss": 0.1209, + "step": 267490 + }, + { + "epoch": 0.6, + "learning_rate": 2.0203351155455137e-05, + "loss": 0.1224, + "step": 267500 + }, + { + "epoch": 0.6, + "learning_rate": 2.020223261224581e-05, + "loss": 0.1213, + "step": 267510 + }, + { + "epoch": 0.6, + "learning_rate": 2.020111406903649e-05, + "loss": 0.1177, + "step": 267520 + }, + { + "epoch": 0.6, + "learning_rate": 2.0199995525827164e-05, + "loss": 0.1179, + "step": 267530 + }, + { + "epoch": 0.6, + "learning_rate": 2.0198876982617838e-05, + "loss": 0.1199, + "step": 267540 + }, + { + "epoch": 0.6, + "learning_rate": 2.0197758439408516e-05, + "loss": 0.1259, + "step": 267550 + }, + { + "epoch": 0.6, + "learning_rate": 2.019663989619919e-05, + "loss": 0.1181, + "step": 267560 + }, + { + "epoch": 0.6, + "learning_rate": 2.0195521352989865e-05, + "loss": 0.1212, + "step": 267570 + }, + { + "epoch": 0.6, + "learning_rate": 2.0194402809780543e-05, + "loss": 0.1216, + "step": 267580 + }, + { + "epoch": 0.6, + "learning_rate": 2.0193284266571218e-05, + "loss": 0.1191, + "step": 267590 + }, + { + "epoch": 0.6, + "learning_rate": 2.0192165723361896e-05, + "loss": 0.1184, + "step": 267600 + }, + { + "epoch": 0.6, + "learning_rate": 2.019104718015257e-05, + "loss": 0.117, + "step": 267610 + }, + { + "epoch": 0.6, + "learning_rate": 2.0189928636943245e-05, + "loss": 0.1239, + "step": 267620 + }, + { + "epoch": 0.6, + "learning_rate": 2.0188810093733923e-05, + "loss": 0.1221, + "step": 267630 + }, + { + "epoch": 0.6, + "learning_rate": 2.0187691550524597e-05, + "loss": 0.1184, + "step": 267640 + }, + { + "epoch": 0.6, + "learning_rate": 2.0186573007315275e-05, + "loss": 0.1222, + "step": 267650 + }, + { + "epoch": 0.6, + "learning_rate": 2.018545446410595e-05, + "loss": 0.1248, + "step": 267660 + }, + { + "epoch": 0.6, + "learning_rate": 2.0184335920896624e-05, + "loss": 0.1187, + "step": 267670 + }, + { + "epoch": 0.6, + "learning_rate": 2.0183217377687302e-05, + "loss": 0.1188, + "step": 267680 + }, + { + "epoch": 0.6, + "learning_rate": 2.0182098834477977e-05, + "loss": 0.1181, + "step": 267690 + }, + { + "epoch": 0.6, + "learning_rate": 2.0180980291268654e-05, + "loss": 0.1219, + "step": 267700 + }, + { + "epoch": 0.6, + "learning_rate": 2.017986174805933e-05, + "loss": 0.1226, + "step": 267710 + }, + { + "epoch": 0.6, + "learning_rate": 2.0178743204850004e-05, + "loss": 0.121, + "step": 267720 + }, + { + "epoch": 0.6, + "learning_rate": 2.0177624661640678e-05, + "loss": 0.1223, + "step": 267730 + }, + { + "epoch": 0.6, + "learning_rate": 2.0176506118431356e-05, + "loss": 0.1182, + "step": 267740 + }, + { + "epoch": 0.6, + "learning_rate": 2.0175387575222034e-05, + "loss": 0.1224, + "step": 267750 + }, + { + "epoch": 0.6, + "learning_rate": 2.017426903201271e-05, + "loss": 0.122, + "step": 267760 + }, + { + "epoch": 0.6, + "learning_rate": 2.0173150488803383e-05, + "loss": 0.1248, + "step": 267770 + }, + { + "epoch": 0.6, + "learning_rate": 2.0172031945594058e-05, + "loss": 0.1197, + "step": 267780 + }, + { + "epoch": 0.6, + "learning_rate": 2.0170913402384735e-05, + "loss": 0.1223, + "step": 267790 + }, + { + "epoch": 0.6, + "learning_rate": 2.016979485917541e-05, + "loss": 0.1204, + "step": 267800 + }, + { + "epoch": 0.6, + "learning_rate": 2.0168676315966088e-05, + "loss": 0.1197, + "step": 267810 + }, + { + "epoch": 0.6, + "learning_rate": 2.0167557772756762e-05, + "loss": 0.1212, + "step": 267820 + }, + { + "epoch": 0.6, + "learning_rate": 2.0166439229547437e-05, + "loss": 0.1191, + "step": 267830 + }, + { + "epoch": 0.6, + "learning_rate": 2.0165320686338115e-05, + "loss": 0.123, + "step": 267840 + }, + { + "epoch": 0.6, + "learning_rate": 2.016420214312879e-05, + "loss": 0.1193, + "step": 267850 + }, + { + "epoch": 0.6, + "learning_rate": 2.0163083599919467e-05, + "loss": 0.1156, + "step": 267860 + }, + { + "epoch": 0.6, + "learning_rate": 2.0161965056710142e-05, + "loss": 0.123, + "step": 267870 + }, + { + "epoch": 0.6, + "learning_rate": 2.0160846513500817e-05, + "loss": 0.1175, + "step": 267880 + }, + { + "epoch": 0.6, + "learning_rate": 2.015972797029149e-05, + "loss": 0.1183, + "step": 267890 + }, + { + "epoch": 0.6, + "learning_rate": 2.015860942708217e-05, + "loss": 0.1227, + "step": 267900 + }, + { + "epoch": 0.6, + "learning_rate": 2.0157490883872847e-05, + "loss": 0.1204, + "step": 267910 + }, + { + "epoch": 0.6, + "learning_rate": 2.015637234066352e-05, + "loss": 0.1217, + "step": 267920 + }, + { + "epoch": 0.6, + "learning_rate": 2.0155253797454196e-05, + "loss": 0.1284, + "step": 267930 + }, + { + "epoch": 0.6, + "learning_rate": 2.015413525424487e-05, + "loss": 0.1191, + "step": 267940 + }, + { + "epoch": 0.6, + "learning_rate": 2.015301671103555e-05, + "loss": 0.1212, + "step": 267950 + }, + { + "epoch": 0.6, + "learning_rate": 2.0151898167826226e-05, + "loss": 0.1206, + "step": 267960 + }, + { + "epoch": 0.6, + "learning_rate": 2.01507796246169e-05, + "loss": 0.1212, + "step": 267970 + }, + { + "epoch": 0.6, + "learning_rate": 2.0149661081407575e-05, + "loss": 0.1197, + "step": 267980 + }, + { + "epoch": 0.6, + "learning_rate": 2.014854253819825e-05, + "loss": 0.1181, + "step": 267990 + }, + { + "epoch": 0.6, + "learning_rate": 2.0147423994988928e-05, + "loss": 0.1197, + "step": 268000 + }, + { + "epoch": 0.6, + "learning_rate": 2.0146305451779602e-05, + "loss": 0.1185, + "step": 268010 + }, + { + "epoch": 0.6, + "learning_rate": 2.014518690857028e-05, + "loss": 0.122, + "step": 268020 + }, + { + "epoch": 0.6, + "learning_rate": 2.0144068365360955e-05, + "loss": 0.1217, + "step": 268030 + }, + { + "epoch": 0.6, + "learning_rate": 2.014294982215163e-05, + "loss": 0.1174, + "step": 268040 + }, + { + "epoch": 0.6, + "learning_rate": 2.0141831278942304e-05, + "loss": 0.1184, + "step": 268050 + }, + { + "epoch": 0.6, + "learning_rate": 2.0140712735732982e-05, + "loss": 0.123, + "step": 268060 + }, + { + "epoch": 0.6, + "learning_rate": 2.013959419252366e-05, + "loss": 0.1183, + "step": 268070 + }, + { + "epoch": 0.6, + "learning_rate": 2.0138475649314334e-05, + "loss": 0.1233, + "step": 268080 + }, + { + "epoch": 0.6, + "learning_rate": 2.013735710610501e-05, + "loss": 0.1196, + "step": 268090 + }, + { + "epoch": 0.6, + "learning_rate": 2.0136238562895683e-05, + "loss": 0.1244, + "step": 268100 + }, + { + "epoch": 0.6, + "learning_rate": 2.013512001968636e-05, + "loss": 0.1211, + "step": 268110 + }, + { + "epoch": 0.6, + "learning_rate": 2.013400147647704e-05, + "loss": 0.1199, + "step": 268120 + }, + { + "epoch": 0.6, + "learning_rate": 2.0132882933267714e-05, + "loss": 0.1225, + "step": 268130 + }, + { + "epoch": 0.6, + "learning_rate": 2.013176439005839e-05, + "loss": 0.1192, + "step": 268140 + }, + { + "epoch": 0.6, + "learning_rate": 2.0130645846849063e-05, + "loss": 0.1219, + "step": 268150 + }, + { + "epoch": 0.6, + "learning_rate": 2.012952730363974e-05, + "loss": 0.1166, + "step": 268160 + }, + { + "epoch": 0.6, + "learning_rate": 2.012840876043042e-05, + "loss": 0.1196, + "step": 268170 + }, + { + "epoch": 0.6, + "learning_rate": 2.0127290217221093e-05, + "loss": 0.1177, + "step": 268180 + }, + { + "epoch": 0.6, + "learning_rate": 2.0126171674011768e-05, + "loss": 0.122, + "step": 268190 + }, + { + "epoch": 0.6, + "learning_rate": 2.0125053130802442e-05, + "loss": 0.1232, + "step": 268200 + }, + { + "epoch": 0.6, + "learning_rate": 2.0123934587593117e-05, + "loss": 0.1203, + "step": 268210 + }, + { + "epoch": 0.6, + "learning_rate": 2.0122816044383795e-05, + "loss": 0.1196, + "step": 268220 + }, + { + "epoch": 0.6, + "learning_rate": 2.0121697501174473e-05, + "loss": 0.1214, + "step": 268230 + }, + { + "epoch": 0.6, + "learning_rate": 2.0120578957965147e-05, + "loss": 0.1234, + "step": 268240 + }, + { + "epoch": 0.6, + "learning_rate": 2.0119460414755822e-05, + "loss": 0.1208, + "step": 268250 + }, + { + "epoch": 0.6, + "learning_rate": 2.0118341871546496e-05, + "loss": 0.1204, + "step": 268260 + }, + { + "epoch": 0.6, + "learning_rate": 2.0117223328337174e-05, + "loss": 0.1206, + "step": 268270 + }, + { + "epoch": 0.6, + "learning_rate": 2.0116104785127852e-05, + "loss": 0.1183, + "step": 268280 + }, + { + "epoch": 0.6, + "learning_rate": 2.0114986241918527e-05, + "loss": 0.1237, + "step": 268290 + }, + { + "epoch": 0.6, + "learning_rate": 2.01138676987092e-05, + "loss": 0.12, + "step": 268300 + }, + { + "epoch": 0.6, + "learning_rate": 2.0112749155499876e-05, + "loss": 0.1224, + "step": 268310 + }, + { + "epoch": 0.6, + "learning_rate": 2.0111630612290554e-05, + "loss": 0.1189, + "step": 268320 + }, + { + "epoch": 0.6, + "learning_rate": 2.0110512069081232e-05, + "loss": 0.1224, + "step": 268330 + }, + { + "epoch": 0.6, + "learning_rate": 2.0109393525871906e-05, + "loss": 0.1173, + "step": 268340 + }, + { + "epoch": 0.6, + "learning_rate": 2.010827498266258e-05, + "loss": 0.1216, + "step": 268350 + }, + { + "epoch": 0.6, + "learning_rate": 2.0107156439453255e-05, + "loss": 0.113, + "step": 268360 + }, + { + "epoch": 0.6, + "learning_rate": 2.0106037896243933e-05, + "loss": 0.1187, + "step": 268370 + }, + { + "epoch": 0.6, + "learning_rate": 2.010491935303461e-05, + "loss": 0.1207, + "step": 268380 + }, + { + "epoch": 0.6, + "learning_rate": 2.0103800809825286e-05, + "loss": 0.119, + "step": 268390 + }, + { + "epoch": 0.6, + "learning_rate": 2.010268226661596e-05, + "loss": 0.1244, + "step": 268400 + }, + { + "epoch": 0.6, + "learning_rate": 2.0101563723406635e-05, + "loss": 0.1214, + "step": 268410 + }, + { + "epoch": 0.6, + "learning_rate": 2.010044518019731e-05, + "loss": 0.1168, + "step": 268420 + }, + { + "epoch": 0.6, + "learning_rate": 2.0099326636987987e-05, + "loss": 0.1205, + "step": 268430 + }, + { + "epoch": 0.6, + "learning_rate": 2.0098208093778665e-05, + "loss": 0.118, + "step": 268440 + }, + { + "epoch": 0.6, + "learning_rate": 2.009708955056934e-05, + "loss": 0.1206, + "step": 268450 + }, + { + "epoch": 0.6, + "learning_rate": 2.0095971007360014e-05, + "loss": 0.1162, + "step": 268460 + }, + { + "epoch": 0.6, + "learning_rate": 2.009485246415069e-05, + "loss": 0.1178, + "step": 268470 + }, + { + "epoch": 0.6, + "learning_rate": 2.0093733920941367e-05, + "loss": 0.1214, + "step": 268480 + }, + { + "epoch": 0.6, + "learning_rate": 2.0092615377732045e-05, + "loss": 0.1265, + "step": 268490 + }, + { + "epoch": 0.6, + "learning_rate": 2.009149683452272e-05, + "loss": 0.1224, + "step": 268500 + }, + { + "epoch": 0.6, + "learning_rate": 2.0090378291313394e-05, + "loss": 0.1207, + "step": 268510 + }, + { + "epoch": 0.6, + "learning_rate": 2.008925974810407e-05, + "loss": 0.1213, + "step": 268520 + }, + { + "epoch": 0.6, + "learning_rate": 2.0088141204894746e-05, + "loss": 0.1177, + "step": 268530 + }, + { + "epoch": 0.6, + "learning_rate": 2.0087022661685424e-05, + "loss": 0.1201, + "step": 268540 + }, + { + "epoch": 0.6, + "learning_rate": 2.00859041184761e-05, + "loss": 0.1234, + "step": 268550 + }, + { + "epoch": 0.6, + "learning_rate": 2.0084785575266773e-05, + "loss": 0.1229, + "step": 268560 + }, + { + "epoch": 0.6, + "learning_rate": 2.0083667032057448e-05, + "loss": 0.1174, + "step": 268570 + }, + { + "epoch": 0.6, + "learning_rate": 2.0082548488848126e-05, + "loss": 0.127, + "step": 268580 + }, + { + "epoch": 0.6, + "learning_rate": 2.0081429945638804e-05, + "loss": 0.1183, + "step": 268590 + }, + { + "epoch": 0.6, + "learning_rate": 2.0080311402429478e-05, + "loss": 0.1231, + "step": 268600 + }, + { + "epoch": 0.6, + "learning_rate": 2.0079192859220153e-05, + "loss": 0.1227, + "step": 268610 + }, + { + "epoch": 0.6, + "learning_rate": 2.0078074316010827e-05, + "loss": 0.1205, + "step": 268620 + }, + { + "epoch": 0.6, + "learning_rate": 2.0076955772801502e-05, + "loss": 0.1206, + "step": 268630 + }, + { + "epoch": 0.6, + "learning_rate": 2.0075837229592183e-05, + "loss": 0.1199, + "step": 268640 + }, + { + "epoch": 0.6, + "learning_rate": 2.0074718686382858e-05, + "loss": 0.1223, + "step": 268650 + }, + { + "epoch": 0.6, + "learning_rate": 2.0073600143173532e-05, + "loss": 0.1221, + "step": 268660 + }, + { + "epoch": 0.6, + "learning_rate": 2.0072481599964207e-05, + "loss": 0.1201, + "step": 268670 + }, + { + "epoch": 0.6, + "learning_rate": 2.007136305675488e-05, + "loss": 0.1218, + "step": 268680 + }, + { + "epoch": 0.6, + "learning_rate": 2.007024451354556e-05, + "loss": 0.1193, + "step": 268690 + }, + { + "epoch": 0.6, + "learning_rate": 2.0069125970336237e-05, + "loss": 0.1216, + "step": 268700 + }, + { + "epoch": 0.6, + "learning_rate": 2.0068007427126912e-05, + "loss": 0.1202, + "step": 268710 + }, + { + "epoch": 0.6, + "learning_rate": 2.0066888883917586e-05, + "loss": 0.1171, + "step": 268720 + }, + { + "epoch": 0.6, + "learning_rate": 2.006577034070826e-05, + "loss": 0.1197, + "step": 268730 + }, + { + "epoch": 0.6, + "learning_rate": 2.006465179749894e-05, + "loss": 0.1155, + "step": 268740 + }, + { + "epoch": 0.6, + "learning_rate": 2.0063533254289617e-05, + "loss": 0.1186, + "step": 268750 + }, + { + "epoch": 0.6, + "learning_rate": 2.006241471108029e-05, + "loss": 0.1254, + "step": 268760 + }, + { + "epoch": 0.6, + "learning_rate": 2.0061296167870966e-05, + "loss": 0.1242, + "step": 268770 + }, + { + "epoch": 0.6, + "learning_rate": 2.006017762466164e-05, + "loss": 0.1201, + "step": 268780 + }, + { + "epoch": 0.6, + "learning_rate": 2.0059059081452318e-05, + "loss": 0.1191, + "step": 268790 + }, + { + "epoch": 0.6, + "learning_rate": 2.0057940538242993e-05, + "loss": 0.1185, + "step": 268800 + }, + { + "epoch": 0.6, + "learning_rate": 2.005682199503367e-05, + "loss": 0.1169, + "step": 268810 + }, + { + "epoch": 0.6, + "learning_rate": 2.0055703451824345e-05, + "loss": 0.1221, + "step": 268820 + }, + { + "epoch": 0.6, + "learning_rate": 2.005458490861502e-05, + "loss": 0.1188, + "step": 268830 + }, + { + "epoch": 0.6, + "learning_rate": 2.0053466365405694e-05, + "loss": 0.12, + "step": 268840 + }, + { + "epoch": 0.6, + "learning_rate": 2.0052347822196372e-05, + "loss": 0.1225, + "step": 268850 + }, + { + "epoch": 0.6, + "learning_rate": 2.005122927898705e-05, + "loss": 0.1195, + "step": 268860 + }, + { + "epoch": 0.6, + "learning_rate": 2.0050110735777725e-05, + "loss": 0.1229, + "step": 268870 + }, + { + "epoch": 0.6, + "learning_rate": 2.00489921925684e-05, + "loss": 0.1212, + "step": 268880 + }, + { + "epoch": 0.6, + "learning_rate": 2.0047873649359074e-05, + "loss": 0.1229, + "step": 268890 + }, + { + "epoch": 0.6, + "learning_rate": 2.004675510614975e-05, + "loss": 0.1222, + "step": 268900 + }, + { + "epoch": 0.6, + "learning_rate": 2.004563656294043e-05, + "loss": 0.125, + "step": 268910 + }, + { + "epoch": 0.6, + "learning_rate": 2.0044518019731104e-05, + "loss": 0.121, + "step": 268920 + }, + { + "epoch": 0.6, + "learning_rate": 2.004339947652178e-05, + "loss": 0.1243, + "step": 268930 + }, + { + "epoch": 0.6, + "learning_rate": 2.0042280933312453e-05, + "loss": 0.1217, + "step": 268940 + }, + { + "epoch": 0.6, + "learning_rate": 2.004116239010313e-05, + "loss": 0.1268, + "step": 268950 + }, + { + "epoch": 0.6, + "learning_rate": 2.0040043846893806e-05, + "loss": 0.1219, + "step": 268960 + }, + { + "epoch": 0.6, + "learning_rate": 2.0038925303684484e-05, + "loss": 0.1162, + "step": 268970 + }, + { + "epoch": 0.6, + "learning_rate": 2.0037806760475158e-05, + "loss": 0.1164, + "step": 268980 + }, + { + "epoch": 0.6, + "learning_rate": 2.0036688217265833e-05, + "loss": 0.1184, + "step": 268990 + }, + { + "epoch": 0.6, + "learning_rate": 2.003556967405651e-05, + "loss": 0.1214, + "step": 269000 + }, + { + "epoch": 0.6, + "learning_rate": 2.0034451130847185e-05, + "loss": 0.1245, + "step": 269010 + }, + { + "epoch": 0.6, + "learning_rate": 2.0033332587637863e-05, + "loss": 0.12, + "step": 269020 + }, + { + "epoch": 0.6, + "learning_rate": 2.0032214044428538e-05, + "loss": 0.1197, + "step": 269030 + }, + { + "epoch": 0.6, + "learning_rate": 2.0031095501219212e-05, + "loss": 0.1157, + "step": 269040 + }, + { + "epoch": 0.6, + "learning_rate": 2.0029976958009887e-05, + "loss": 0.1164, + "step": 269050 + }, + { + "epoch": 0.6, + "learning_rate": 2.0028858414800565e-05, + "loss": 0.118, + "step": 269060 + }, + { + "epoch": 0.6, + "learning_rate": 2.0027739871591243e-05, + "loss": 0.1191, + "step": 269070 + }, + { + "epoch": 0.6, + "learning_rate": 2.0026621328381917e-05, + "loss": 0.1193, + "step": 269080 + }, + { + "epoch": 0.6, + "learning_rate": 2.002550278517259e-05, + "loss": 0.1221, + "step": 269090 + }, + { + "epoch": 0.6, + "learning_rate": 2.0024384241963266e-05, + "loss": 0.1193, + "step": 269100 + }, + { + "epoch": 0.6, + "learning_rate": 2.0023265698753944e-05, + "loss": 0.1206, + "step": 269110 + }, + { + "epoch": 0.6, + "learning_rate": 2.002214715554462e-05, + "loss": 0.1213, + "step": 269120 + }, + { + "epoch": 0.6, + "learning_rate": 2.0021028612335297e-05, + "loss": 0.1276, + "step": 269130 + }, + { + "epoch": 0.6, + "learning_rate": 2.001991006912597e-05, + "loss": 0.1245, + "step": 269140 + }, + { + "epoch": 0.6, + "learning_rate": 2.0018791525916646e-05, + "loss": 0.1217, + "step": 269150 + }, + { + "epoch": 0.6, + "learning_rate": 2.0017672982707324e-05, + "loss": 0.1161, + "step": 269160 + }, + { + "epoch": 0.6, + "learning_rate": 2.0016554439497998e-05, + "loss": 0.1208, + "step": 269170 + }, + { + "epoch": 0.6, + "learning_rate": 2.0015435896288676e-05, + "loss": 0.1195, + "step": 269180 + }, + { + "epoch": 0.6, + "learning_rate": 2.001431735307935e-05, + "loss": 0.1218, + "step": 269190 + }, + { + "epoch": 0.6, + "learning_rate": 2.0013198809870025e-05, + "loss": 0.1169, + "step": 269200 + }, + { + "epoch": 0.6, + "learning_rate": 2.0012080266660703e-05, + "loss": 0.1204, + "step": 269210 + }, + { + "epoch": 0.6, + "learning_rate": 2.0010961723451378e-05, + "loss": 0.1177, + "step": 269220 + }, + { + "epoch": 0.6, + "learning_rate": 2.0009843180242056e-05, + "loss": 0.1201, + "step": 269230 + }, + { + "epoch": 0.6, + "learning_rate": 2.000872463703273e-05, + "loss": 0.1185, + "step": 269240 + }, + { + "epoch": 0.6, + "learning_rate": 2.0007606093823405e-05, + "loss": 0.1189, + "step": 269250 + }, + { + "epoch": 0.6, + "learning_rate": 2.0006487550614083e-05, + "loss": 0.1224, + "step": 269260 + }, + { + "epoch": 0.6, + "learning_rate": 2.0005369007404757e-05, + "loss": 0.1145, + "step": 269270 + }, + { + "epoch": 0.6, + "learning_rate": 2.000425046419543e-05, + "loss": 0.1182, + "step": 269280 + }, + { + "epoch": 0.6, + "learning_rate": 2.000313192098611e-05, + "loss": 0.1195, + "step": 269290 + }, + { + "epoch": 0.6, + "learning_rate": 2.0002013377776784e-05, + "loss": 0.1222, + "step": 269300 + }, + { + "epoch": 0.6, + "learning_rate": 2.000089483456746e-05, + "loss": 0.1207, + "step": 269310 + }, + { + "epoch": 0.6, + "learning_rate": 1.9999776291358137e-05, + "loss": 0.1215, + "step": 269320 + }, + { + "epoch": 0.6, + "learning_rate": 1.999865774814881e-05, + "loss": 0.1201, + "step": 269330 + }, + { + "epoch": 0.6, + "learning_rate": 1.999753920493949e-05, + "loss": 0.1199, + "step": 269340 + }, + { + "epoch": 0.6, + "learning_rate": 1.9996420661730164e-05, + "loss": 0.1145, + "step": 269350 + }, + { + "epoch": 0.6, + "learning_rate": 1.9995302118520838e-05, + "loss": 0.1246, + "step": 269360 + }, + { + "epoch": 0.6, + "learning_rate": 1.9994183575311516e-05, + "loss": 0.1188, + "step": 269370 + }, + { + "epoch": 0.6, + "learning_rate": 1.999306503210219e-05, + "loss": 0.1208, + "step": 269380 + }, + { + "epoch": 0.6, + "learning_rate": 1.999194648889287e-05, + "loss": 0.125, + "step": 269390 + }, + { + "epoch": 0.6, + "learning_rate": 1.9990827945683543e-05, + "loss": 0.1191, + "step": 269400 + }, + { + "epoch": 0.6, + "learning_rate": 1.9989709402474218e-05, + "loss": 0.1156, + "step": 269410 + }, + { + "epoch": 0.6, + "learning_rate": 1.9988590859264895e-05, + "loss": 0.1235, + "step": 269420 + }, + { + "epoch": 0.6, + "learning_rate": 1.998747231605557e-05, + "loss": 0.1183, + "step": 269430 + }, + { + "epoch": 0.6, + "learning_rate": 1.9986353772846245e-05, + "loss": 0.1176, + "step": 269440 + }, + { + "epoch": 0.6, + "learning_rate": 1.9985235229636922e-05, + "loss": 0.1207, + "step": 269450 + }, + { + "epoch": 0.6, + "learning_rate": 1.9984116686427597e-05, + "loss": 0.1206, + "step": 269460 + }, + { + "epoch": 0.6, + "learning_rate": 1.9982998143218275e-05, + "loss": 0.1188, + "step": 269470 + }, + { + "epoch": 0.6, + "learning_rate": 1.998187960000895e-05, + "loss": 0.1204, + "step": 269480 + }, + { + "epoch": 0.6, + "learning_rate": 1.9980761056799624e-05, + "loss": 0.1199, + "step": 269490 + }, + { + "epoch": 0.6, + "learning_rate": 1.9979642513590302e-05, + "loss": 0.1218, + "step": 269500 + }, + { + "epoch": 0.6, + "learning_rate": 1.9978523970380977e-05, + "loss": 0.1217, + "step": 269510 + }, + { + "epoch": 0.6, + "learning_rate": 1.997740542717165e-05, + "loss": 0.1175, + "step": 269520 + }, + { + "epoch": 0.6, + "learning_rate": 1.997628688396233e-05, + "loss": 0.1191, + "step": 269530 + }, + { + "epoch": 0.6, + "learning_rate": 1.9975168340753004e-05, + "loss": 0.1206, + "step": 269540 + }, + { + "epoch": 0.6, + "learning_rate": 1.997404979754368e-05, + "loss": 0.1162, + "step": 269550 + }, + { + "epoch": 0.6, + "learning_rate": 1.9972931254334356e-05, + "loss": 0.1185, + "step": 269560 + }, + { + "epoch": 0.6, + "learning_rate": 1.997181271112503e-05, + "loss": 0.1208, + "step": 269570 + }, + { + "epoch": 0.6, + "learning_rate": 1.997069416791571e-05, + "loss": 0.1167, + "step": 269580 + }, + { + "epoch": 0.6, + "learning_rate": 1.9969575624706383e-05, + "loss": 0.1185, + "step": 269590 + }, + { + "epoch": 0.6, + "learning_rate": 1.9968457081497058e-05, + "loss": 0.1222, + "step": 269600 + }, + { + "epoch": 0.6, + "learning_rate": 1.9967338538287735e-05, + "loss": 0.1226, + "step": 269610 + }, + { + "epoch": 0.6, + "learning_rate": 1.996621999507841e-05, + "loss": 0.1209, + "step": 269620 + }, + { + "epoch": 0.6, + "learning_rate": 1.9965101451869088e-05, + "loss": 0.1226, + "step": 269630 + }, + { + "epoch": 0.6, + "learning_rate": 1.9963982908659762e-05, + "loss": 0.1218, + "step": 269640 + }, + { + "epoch": 0.6, + "learning_rate": 1.9962864365450437e-05, + "loss": 0.1205, + "step": 269650 + }, + { + "epoch": 0.6, + "learning_rate": 1.9961745822241115e-05, + "loss": 0.1188, + "step": 269660 + }, + { + "epoch": 0.6, + "learning_rate": 1.996062727903179e-05, + "loss": 0.1165, + "step": 269670 + }, + { + "epoch": 0.6, + "learning_rate": 1.9959508735822467e-05, + "loss": 0.1182, + "step": 269680 + }, + { + "epoch": 0.6, + "learning_rate": 1.9958390192613142e-05, + "loss": 0.1156, + "step": 269690 + }, + { + "epoch": 0.6, + "learning_rate": 1.9957271649403816e-05, + "loss": 0.1171, + "step": 269700 + }, + { + "epoch": 0.6, + "learning_rate": 1.9956153106194494e-05, + "loss": 0.1199, + "step": 269710 + }, + { + "epoch": 0.6, + "learning_rate": 1.995503456298517e-05, + "loss": 0.1212, + "step": 269720 + }, + { + "epoch": 0.6, + "learning_rate": 1.9953916019775843e-05, + "loss": 0.1181, + "step": 269730 + }, + { + "epoch": 0.6, + "learning_rate": 1.995279747656652e-05, + "loss": 0.121, + "step": 269740 + }, + { + "epoch": 0.6, + "learning_rate": 1.9951678933357196e-05, + "loss": 0.1176, + "step": 269750 + }, + { + "epoch": 0.6, + "learning_rate": 1.995056039014787e-05, + "loss": 0.1164, + "step": 269760 + }, + { + "epoch": 0.6, + "learning_rate": 1.994944184693855e-05, + "loss": 0.12, + "step": 269770 + }, + { + "epoch": 0.6, + "learning_rate": 1.9948323303729223e-05, + "loss": 0.1236, + "step": 269780 + }, + { + "epoch": 0.6, + "learning_rate": 1.99472047605199e-05, + "loss": 0.1218, + "step": 269790 + }, + { + "epoch": 0.6, + "learning_rate": 1.9946086217310575e-05, + "loss": 0.1216, + "step": 269800 + }, + { + "epoch": 0.6, + "learning_rate": 1.994496767410125e-05, + "loss": 0.1223, + "step": 269810 + }, + { + "epoch": 0.6, + "learning_rate": 1.9943849130891928e-05, + "loss": 0.1198, + "step": 269820 + }, + { + "epoch": 0.6, + "learning_rate": 1.9942730587682602e-05, + "loss": 0.1167, + "step": 269830 + }, + { + "epoch": 0.6, + "learning_rate": 1.994161204447328e-05, + "loss": 0.1204, + "step": 269840 + }, + { + "epoch": 0.6, + "learning_rate": 1.9940493501263955e-05, + "loss": 0.1158, + "step": 269850 + }, + { + "epoch": 0.6, + "learning_rate": 1.993937495805463e-05, + "loss": 0.1191, + "step": 269860 + }, + { + "epoch": 0.6, + "learning_rate": 1.9938256414845307e-05, + "loss": 0.1227, + "step": 269870 + }, + { + "epoch": 0.6, + "learning_rate": 1.9937137871635982e-05, + "loss": 0.1168, + "step": 269880 + }, + { + "epoch": 0.6, + "learning_rate": 1.993601932842666e-05, + "loss": 0.1178, + "step": 269890 + }, + { + "epoch": 0.6, + "learning_rate": 1.9934900785217334e-05, + "loss": 0.1167, + "step": 269900 + }, + { + "epoch": 0.6, + "learning_rate": 1.993378224200801e-05, + "loss": 0.116, + "step": 269910 + }, + { + "epoch": 0.6, + "learning_rate": 1.9932663698798683e-05, + "loss": 0.1195, + "step": 269920 + }, + { + "epoch": 0.6, + "learning_rate": 1.993154515558936e-05, + "loss": 0.1168, + "step": 269930 + }, + { + "epoch": 0.6, + "learning_rate": 1.9930426612380036e-05, + "loss": 0.1153, + "step": 269940 + }, + { + "epoch": 0.6, + "learning_rate": 1.9929308069170714e-05, + "loss": 0.1167, + "step": 269950 + }, + { + "epoch": 0.6, + "learning_rate": 1.992818952596139e-05, + "loss": 0.121, + "step": 269960 + }, + { + "epoch": 0.6, + "learning_rate": 1.9927070982752063e-05, + "loss": 0.1186, + "step": 269970 + }, + { + "epoch": 0.6, + "learning_rate": 1.992595243954274e-05, + "loss": 0.1198, + "step": 269980 + }, + { + "epoch": 0.6, + "learning_rate": 1.9924833896333415e-05, + "loss": 0.1162, + "step": 269990 + }, + { + "epoch": 0.6, + "learning_rate": 1.9923715353124093e-05, + "loss": 0.1214, + "step": 270000 + }, + { + "epoch": 0.6, + "learning_rate": 1.9922596809914768e-05, + "loss": 0.1152, + "step": 270010 + }, + { + "epoch": 0.6, + "learning_rate": 1.9921478266705442e-05, + "loss": 0.1199, + "step": 270020 + }, + { + "epoch": 0.6, + "learning_rate": 1.992035972349612e-05, + "loss": 0.1209, + "step": 270030 + }, + { + "epoch": 0.6, + "learning_rate": 1.9919241180286795e-05, + "loss": 0.1182, + "step": 270040 + }, + { + "epoch": 0.6, + "learning_rate": 1.9918122637077473e-05, + "loss": 0.1171, + "step": 270050 + }, + { + "epoch": 0.6, + "learning_rate": 1.9917004093868147e-05, + "loss": 0.1154, + "step": 270060 + }, + { + "epoch": 0.6, + "learning_rate": 1.9915885550658822e-05, + "loss": 0.1189, + "step": 270070 + }, + { + "epoch": 0.6, + "learning_rate": 1.9914767007449496e-05, + "loss": 0.1165, + "step": 270080 + }, + { + "epoch": 0.6, + "learning_rate": 1.9913648464240174e-05, + "loss": 0.1228, + "step": 270090 + }, + { + "epoch": 0.6, + "learning_rate": 1.9912529921030852e-05, + "loss": 0.1163, + "step": 270100 + }, + { + "epoch": 0.6, + "learning_rate": 1.9911411377821527e-05, + "loss": 0.1196, + "step": 270110 + }, + { + "epoch": 0.6, + "learning_rate": 1.99102928346122e-05, + "loss": 0.1246, + "step": 270120 + }, + { + "epoch": 0.6, + "learning_rate": 1.9909174291402876e-05, + "loss": 0.1214, + "step": 270130 + }, + { + "epoch": 0.6, + "learning_rate": 1.9908055748193554e-05, + "loss": 0.1217, + "step": 270140 + }, + { + "epoch": 0.6, + "learning_rate": 1.9906937204984232e-05, + "loss": 0.116, + "step": 270150 + }, + { + "epoch": 0.6, + "learning_rate": 1.9905818661774906e-05, + "loss": 0.117, + "step": 270160 + }, + { + "epoch": 0.6, + "learning_rate": 1.990470011856558e-05, + "loss": 0.118, + "step": 270170 + }, + { + "epoch": 0.6, + "learning_rate": 1.9903581575356255e-05, + "loss": 0.1261, + "step": 270180 + }, + { + "epoch": 0.6, + "learning_rate": 1.9902463032146933e-05, + "loss": 0.1183, + "step": 270190 + }, + { + "epoch": 0.6, + "learning_rate": 1.9901344488937608e-05, + "loss": 0.1202, + "step": 270200 + }, + { + "epoch": 0.6, + "learning_rate": 1.9900225945728286e-05, + "loss": 0.1169, + "step": 270210 + }, + { + "epoch": 0.6, + "learning_rate": 1.989910740251896e-05, + "loss": 0.1178, + "step": 270220 + }, + { + "epoch": 0.6, + "learning_rate": 1.9897988859309635e-05, + "loss": 0.1197, + "step": 270230 + }, + { + "epoch": 0.6, + "learning_rate": 1.989687031610031e-05, + "loss": 0.1219, + "step": 270240 + }, + { + "epoch": 0.6, + "learning_rate": 1.9895751772890987e-05, + "loss": 0.1195, + "step": 270250 + }, + { + "epoch": 0.6, + "learning_rate": 1.9894633229681665e-05, + "loss": 0.1185, + "step": 270260 + }, + { + "epoch": 0.6, + "learning_rate": 1.989351468647234e-05, + "loss": 0.1209, + "step": 270270 + }, + { + "epoch": 0.6, + "learning_rate": 1.9892396143263014e-05, + "loss": 0.1145, + "step": 270280 + }, + { + "epoch": 0.6, + "learning_rate": 1.989127760005369e-05, + "loss": 0.1181, + "step": 270290 + }, + { + "epoch": 0.6, + "learning_rate": 1.9890159056844367e-05, + "loss": 0.1209, + "step": 270300 + }, + { + "epoch": 0.6, + "learning_rate": 1.9889040513635045e-05, + "loss": 0.1159, + "step": 270310 + }, + { + "epoch": 0.6, + "learning_rate": 1.988792197042572e-05, + "loss": 0.1165, + "step": 270320 + }, + { + "epoch": 0.6, + "learning_rate": 1.9886803427216394e-05, + "loss": 0.1157, + "step": 270330 + }, + { + "epoch": 0.6, + "learning_rate": 1.988568488400707e-05, + "loss": 0.1232, + "step": 270340 + }, + { + "epoch": 0.6, + "learning_rate": 1.9884566340797746e-05, + "loss": 0.1189, + "step": 270350 + }, + { + "epoch": 0.6, + "learning_rate": 1.9883447797588424e-05, + "loss": 0.1178, + "step": 270360 + }, + { + "epoch": 0.6, + "learning_rate": 1.98823292543791e-05, + "loss": 0.1203, + "step": 270370 + }, + { + "epoch": 0.6, + "learning_rate": 1.9881210711169773e-05, + "loss": 0.1174, + "step": 270380 + }, + { + "epoch": 0.6, + "learning_rate": 1.9880092167960448e-05, + "loss": 0.1169, + "step": 270390 + }, + { + "epoch": 0.6, + "learning_rate": 1.9878973624751122e-05, + "loss": 0.1205, + "step": 270400 + }, + { + "epoch": 0.6, + "learning_rate": 1.98778550815418e-05, + "loss": 0.113, + "step": 270410 + }, + { + "epoch": 0.6, + "learning_rate": 1.9876736538332478e-05, + "loss": 0.121, + "step": 270420 + }, + { + "epoch": 0.6, + "learning_rate": 1.9875617995123153e-05, + "loss": 0.1182, + "step": 270430 + }, + { + "epoch": 0.6, + "learning_rate": 1.9874499451913827e-05, + "loss": 0.1213, + "step": 270440 + }, + { + "epoch": 0.6, + "learning_rate": 1.9873380908704502e-05, + "loss": 0.1223, + "step": 270450 + }, + { + "epoch": 0.6, + "learning_rate": 1.987226236549518e-05, + "loss": 0.1206, + "step": 270460 + }, + { + "epoch": 0.6, + "learning_rate": 1.9871143822285858e-05, + "loss": 0.109, + "step": 270470 + }, + { + "epoch": 0.6, + "learning_rate": 1.9870025279076532e-05, + "loss": 0.1189, + "step": 270480 + }, + { + "epoch": 0.6, + "learning_rate": 1.9868906735867207e-05, + "loss": 0.1146, + "step": 270490 + }, + { + "epoch": 0.6, + "learning_rate": 1.986778819265788e-05, + "loss": 0.1151, + "step": 270500 + }, + { + "epoch": 0.6, + "learning_rate": 1.986666964944856e-05, + "loss": 0.1133, + "step": 270510 + }, + { + "epoch": 0.6, + "learning_rate": 1.9865551106239237e-05, + "loss": 0.1167, + "step": 270520 + }, + { + "epoch": 0.6, + "learning_rate": 1.986443256302991e-05, + "loss": 0.1197, + "step": 270530 + }, + { + "epoch": 0.6, + "learning_rate": 1.9863314019820586e-05, + "loss": 0.118, + "step": 270540 + }, + { + "epoch": 0.6, + "learning_rate": 1.986219547661126e-05, + "loss": 0.1178, + "step": 270550 + }, + { + "epoch": 0.6, + "learning_rate": 1.9861076933401935e-05, + "loss": 0.1125, + "step": 270560 + }, + { + "epoch": 0.6, + "learning_rate": 1.9859958390192617e-05, + "loss": 0.1185, + "step": 270570 + }, + { + "epoch": 0.6, + "learning_rate": 1.985883984698329e-05, + "loss": 0.118, + "step": 270580 + }, + { + "epoch": 0.6, + "learning_rate": 1.9857721303773966e-05, + "loss": 0.1197, + "step": 270590 + }, + { + "epoch": 0.6, + "learning_rate": 1.985660276056464e-05, + "loss": 0.1162, + "step": 270600 + }, + { + "epoch": 0.6, + "learning_rate": 1.9855484217355315e-05, + "loss": 0.1212, + "step": 270610 + }, + { + "epoch": 0.6, + "learning_rate": 1.9854365674145993e-05, + "loss": 0.1172, + "step": 270620 + }, + { + "epoch": 0.6, + "learning_rate": 1.985324713093667e-05, + "loss": 0.1156, + "step": 270630 + }, + { + "epoch": 0.6, + "learning_rate": 1.9852128587727345e-05, + "loss": 0.118, + "step": 270640 + }, + { + "epoch": 0.6, + "learning_rate": 1.985101004451802e-05, + "loss": 0.1157, + "step": 270650 + }, + { + "epoch": 0.6, + "learning_rate": 1.9849891501308694e-05, + "loss": 0.1191, + "step": 270660 + }, + { + "epoch": 0.6, + "learning_rate": 1.9848772958099372e-05, + "loss": 0.1129, + "step": 270670 + }, + { + "epoch": 0.6, + "learning_rate": 1.984765441489005e-05, + "loss": 0.1203, + "step": 270680 + }, + { + "epoch": 0.6, + "learning_rate": 1.9846535871680725e-05, + "loss": 0.1191, + "step": 270690 + }, + { + "epoch": 0.6, + "learning_rate": 1.98454173284714e-05, + "loss": 0.1177, + "step": 270700 + }, + { + "epoch": 0.6, + "learning_rate": 1.9844298785262074e-05, + "loss": 0.1152, + "step": 270710 + }, + { + "epoch": 0.6, + "learning_rate": 1.984318024205275e-05, + "loss": 0.1212, + "step": 270720 + }, + { + "epoch": 0.6, + "learning_rate": 1.984206169884343e-05, + "loss": 0.1129, + "step": 270730 + }, + { + "epoch": 0.6, + "learning_rate": 1.9840943155634104e-05, + "loss": 0.1115, + "step": 270740 + }, + { + "epoch": 0.6, + "learning_rate": 1.983982461242478e-05, + "loss": 0.1143, + "step": 270750 + }, + { + "epoch": 0.6, + "learning_rate": 1.9838706069215453e-05, + "loss": 0.116, + "step": 270760 + }, + { + "epoch": 0.6, + "learning_rate": 1.983758752600613e-05, + "loss": 0.1152, + "step": 270770 + }, + { + "epoch": 0.6, + "learning_rate": 1.983646898279681e-05, + "loss": 0.1156, + "step": 270780 + }, + { + "epoch": 0.6, + "learning_rate": 1.9835350439587484e-05, + "loss": 0.1162, + "step": 270790 + }, + { + "epoch": 0.6, + "learning_rate": 1.9834231896378158e-05, + "loss": 0.1143, + "step": 270800 + }, + { + "epoch": 0.6, + "learning_rate": 1.9833113353168833e-05, + "loss": 0.1183, + "step": 270810 + }, + { + "epoch": 0.6, + "learning_rate": 1.9831994809959507e-05, + "loss": 0.1168, + "step": 270820 + }, + { + "epoch": 0.6, + "learning_rate": 1.983087626675019e-05, + "loss": 0.1183, + "step": 270830 + }, + { + "epoch": 0.6, + "learning_rate": 1.9829757723540863e-05, + "loss": 0.1186, + "step": 270840 + }, + { + "epoch": 0.6, + "learning_rate": 1.9828639180331538e-05, + "loss": 0.1164, + "step": 270850 + }, + { + "epoch": 0.6, + "learning_rate": 1.9827520637122212e-05, + "loss": 0.1172, + "step": 270860 + }, + { + "epoch": 0.6, + "learning_rate": 1.9826402093912887e-05, + "loss": 0.1173, + "step": 270870 + }, + { + "epoch": 0.6, + "learning_rate": 1.9825283550703565e-05, + "loss": 0.1145, + "step": 270880 + }, + { + "epoch": 0.6, + "learning_rate": 1.9824165007494243e-05, + "loss": 0.1204, + "step": 270890 + }, + { + "epoch": 0.6, + "learning_rate": 1.9823046464284917e-05, + "loss": 0.123, + "step": 270900 + }, + { + "epoch": 0.6, + "learning_rate": 1.982192792107559e-05, + "loss": 0.1138, + "step": 270910 + }, + { + "epoch": 0.6, + "learning_rate": 1.9820809377866266e-05, + "loss": 0.1142, + "step": 270920 + }, + { + "epoch": 0.6, + "learning_rate": 1.9819690834656944e-05, + "loss": 0.1189, + "step": 270930 + }, + { + "epoch": 0.6, + "learning_rate": 1.9818572291447622e-05, + "loss": 0.1215, + "step": 270940 + }, + { + "epoch": 0.6, + "learning_rate": 1.9817453748238297e-05, + "loss": 0.1225, + "step": 270950 + }, + { + "epoch": 0.6, + "learning_rate": 1.981633520502897e-05, + "loss": 0.1167, + "step": 270960 + }, + { + "epoch": 0.6, + "learning_rate": 1.9815216661819646e-05, + "loss": 0.1139, + "step": 270970 + }, + { + "epoch": 0.6, + "learning_rate": 1.9814098118610324e-05, + "loss": 0.1215, + "step": 270980 + }, + { + "epoch": 0.6, + "learning_rate": 1.9812979575401e-05, + "loss": 0.1146, + "step": 270990 + }, + { + "epoch": 0.6, + "learning_rate": 1.9811861032191676e-05, + "loss": 0.118, + "step": 271000 + }, + { + "epoch": 0.6, + "learning_rate": 1.981074248898235e-05, + "loss": 0.1169, + "step": 271010 + }, + { + "epoch": 0.6, + "learning_rate": 1.9809623945773025e-05, + "loss": 0.115, + "step": 271020 + }, + { + "epoch": 0.6, + "learning_rate": 1.98085054025637e-05, + "loss": 0.1158, + "step": 271030 + }, + { + "epoch": 0.6, + "learning_rate": 1.9807386859354378e-05, + "loss": 0.1128, + "step": 271040 + }, + { + "epoch": 0.61, + "learning_rate": 1.9806268316145056e-05, + "loss": 0.1153, + "step": 271050 + }, + { + "epoch": 0.61, + "learning_rate": 1.980514977293573e-05, + "loss": 0.1149, + "step": 271060 + }, + { + "epoch": 0.61, + "learning_rate": 1.9804031229726405e-05, + "loss": 0.1168, + "step": 271070 + }, + { + "epoch": 0.61, + "learning_rate": 1.980291268651708e-05, + "loss": 0.1179, + "step": 271080 + }, + { + "epoch": 0.61, + "learning_rate": 1.9801794143307757e-05, + "loss": 0.1183, + "step": 271090 + }, + { + "epoch": 0.61, + "learning_rate": 1.9800675600098435e-05, + "loss": 0.1179, + "step": 271100 + }, + { + "epoch": 0.61, + "learning_rate": 1.979955705688911e-05, + "loss": 0.1143, + "step": 271110 + }, + { + "epoch": 0.61, + "learning_rate": 1.9798438513679784e-05, + "loss": 0.1183, + "step": 271120 + }, + { + "epoch": 0.61, + "learning_rate": 1.979731997047046e-05, + "loss": 0.1156, + "step": 271130 + }, + { + "epoch": 0.61, + "learning_rate": 1.9796201427261137e-05, + "loss": 0.1139, + "step": 271140 + }, + { + "epoch": 0.61, + "learning_rate": 1.9795082884051814e-05, + "loss": 0.1205, + "step": 271150 + }, + { + "epoch": 0.61, + "learning_rate": 1.979396434084249e-05, + "loss": 0.1192, + "step": 271160 + }, + { + "epoch": 0.61, + "learning_rate": 1.9792845797633164e-05, + "loss": 0.1194, + "step": 271170 + }, + { + "epoch": 0.61, + "learning_rate": 1.9791727254423838e-05, + "loss": 0.12, + "step": 271180 + }, + { + "epoch": 0.61, + "learning_rate": 1.9790608711214516e-05, + "loss": 0.119, + "step": 271190 + }, + { + "epoch": 0.61, + "learning_rate": 1.978949016800519e-05, + "loss": 0.117, + "step": 271200 + }, + { + "epoch": 0.61, + "learning_rate": 1.978837162479587e-05, + "loss": 0.1099, + "step": 271210 + }, + { + "epoch": 0.61, + "learning_rate": 1.9787253081586543e-05, + "loss": 0.117, + "step": 271220 + }, + { + "epoch": 0.61, + "learning_rate": 1.9786246392698152e-05, + "loss": 0.118, + "step": 271230 + }, + { + "epoch": 0.61, + "learning_rate": 1.9785127849488826e-05, + "loss": 0.1133, + "step": 271240 + }, + { + "epoch": 0.61, + "learning_rate": 1.97840093062795e-05, + "loss": 0.1171, + "step": 271250 + }, + { + "epoch": 0.61, + "learning_rate": 1.978289076307018e-05, + "loss": 0.124, + "step": 271260 + }, + { + "epoch": 0.61, + "learning_rate": 1.9781772219860853e-05, + "loss": 0.1159, + "step": 271270 + }, + { + "epoch": 0.61, + "learning_rate": 1.978065367665153e-05, + "loss": 0.1152, + "step": 271280 + }, + { + "epoch": 0.61, + "learning_rate": 1.9779535133442206e-05, + "loss": 0.114, + "step": 271290 + }, + { + "epoch": 0.61, + "learning_rate": 1.977841659023288e-05, + "loss": 0.1167, + "step": 271300 + }, + { + "epoch": 0.61, + "learning_rate": 1.9777298047023558e-05, + "loss": 0.117, + "step": 271310 + }, + { + "epoch": 0.61, + "learning_rate": 1.9776179503814233e-05, + "loss": 0.1176, + "step": 271320 + }, + { + "epoch": 0.61, + "learning_rate": 1.977506096060491e-05, + "loss": 0.1176, + "step": 271330 + }, + { + "epoch": 0.61, + "learning_rate": 1.9773942417395585e-05, + "loss": 0.1181, + "step": 271340 + }, + { + "epoch": 0.61, + "learning_rate": 1.977282387418626e-05, + "loss": 0.1163, + "step": 271350 + }, + { + "epoch": 0.61, + "learning_rate": 1.9771705330976938e-05, + "loss": 0.1149, + "step": 271360 + }, + { + "epoch": 0.61, + "learning_rate": 1.9770586787767612e-05, + "loss": 0.1198, + "step": 271370 + }, + { + "epoch": 0.61, + "learning_rate": 1.976946824455829e-05, + "loss": 0.1128, + "step": 271380 + }, + { + "epoch": 0.61, + "learning_rate": 1.9768349701348965e-05, + "loss": 0.1172, + "step": 271390 + }, + { + "epoch": 0.61, + "learning_rate": 1.976723115813964e-05, + "loss": 0.1172, + "step": 271400 + }, + { + "epoch": 0.61, + "learning_rate": 1.9766112614930317e-05, + "loss": 0.1165, + "step": 271410 + }, + { + "epoch": 0.61, + "learning_rate": 1.9764994071720992e-05, + "loss": 0.1175, + "step": 271420 + }, + { + "epoch": 0.61, + "learning_rate": 1.9763875528511666e-05, + "loss": 0.1176, + "step": 271430 + }, + { + "epoch": 0.61, + "learning_rate": 1.9762756985302344e-05, + "loss": 0.114, + "step": 271440 + }, + { + "epoch": 0.61, + "learning_rate": 1.976163844209302e-05, + "loss": 0.1193, + "step": 271450 + }, + { + "epoch": 0.61, + "learning_rate": 1.9760519898883693e-05, + "loss": 0.1157, + "step": 271460 + }, + { + "epoch": 0.61, + "learning_rate": 1.975940135567437e-05, + "loss": 0.1123, + "step": 271470 + }, + { + "epoch": 0.61, + "learning_rate": 1.9758282812465046e-05, + "loss": 0.115, + "step": 271480 + }, + { + "epoch": 0.61, + "learning_rate": 1.9757164269255724e-05, + "loss": 0.1117, + "step": 271490 + }, + { + "epoch": 0.61, + "learning_rate": 1.9756045726046398e-05, + "loss": 0.1188, + "step": 271500 + }, + { + "epoch": 0.61, + "learning_rate": 1.9754927182837073e-05, + "loss": 0.1174, + "step": 271510 + }, + { + "epoch": 0.61, + "learning_rate": 1.975380863962775e-05, + "loss": 0.1154, + "step": 271520 + }, + { + "epoch": 0.61, + "learning_rate": 1.9752690096418425e-05, + "loss": 0.1188, + "step": 271530 + }, + { + "epoch": 0.61, + "learning_rate": 1.9751571553209103e-05, + "loss": 0.1232, + "step": 271540 + }, + { + "epoch": 0.61, + "learning_rate": 1.9750453009999778e-05, + "loss": 0.1201, + "step": 271550 + }, + { + "epoch": 0.61, + "learning_rate": 1.9749334466790452e-05, + "loss": 0.1124, + "step": 271560 + }, + { + "epoch": 0.61, + "learning_rate": 1.974821592358113e-05, + "loss": 0.1095, + "step": 271570 + }, + { + "epoch": 0.61, + "learning_rate": 1.9747097380371805e-05, + "loss": 0.1198, + "step": 271580 + }, + { + "epoch": 0.61, + "learning_rate": 1.974597883716248e-05, + "loss": 0.1169, + "step": 271590 + }, + { + "epoch": 0.61, + "learning_rate": 1.9744860293953157e-05, + "loss": 0.1165, + "step": 271600 + }, + { + "epoch": 0.61, + "learning_rate": 1.9743741750743832e-05, + "loss": 0.1219, + "step": 271610 + }, + { + "epoch": 0.61, + "learning_rate": 1.974262320753451e-05, + "loss": 0.1173, + "step": 271620 + }, + { + "epoch": 0.61, + "learning_rate": 1.9741504664325184e-05, + "loss": 0.1206, + "step": 271630 + }, + { + "epoch": 0.61, + "learning_rate": 1.974038612111586e-05, + "loss": 0.1172, + "step": 271640 + }, + { + "epoch": 0.61, + "learning_rate": 1.9739267577906537e-05, + "loss": 0.1203, + "step": 271650 + }, + { + "epoch": 0.61, + "learning_rate": 1.973814903469721e-05, + "loss": 0.1149, + "step": 271660 + }, + { + "epoch": 0.61, + "learning_rate": 1.9737030491487886e-05, + "loss": 0.1158, + "step": 271670 + }, + { + "epoch": 0.61, + "learning_rate": 1.9735911948278564e-05, + "loss": 0.1139, + "step": 271680 + }, + { + "epoch": 0.61, + "learning_rate": 1.9734793405069238e-05, + "loss": 0.1183, + "step": 271690 + }, + { + "epoch": 0.61, + "learning_rate": 1.9733674861859913e-05, + "loss": 0.1166, + "step": 271700 + }, + { + "epoch": 0.61, + "learning_rate": 1.973255631865059e-05, + "loss": 0.1162, + "step": 271710 + }, + { + "epoch": 0.61, + "learning_rate": 1.9731437775441265e-05, + "loss": 0.1146, + "step": 271720 + }, + { + "epoch": 0.61, + "learning_rate": 1.9730319232231943e-05, + "loss": 0.118, + "step": 271730 + }, + { + "epoch": 0.61, + "learning_rate": 1.9729200689022618e-05, + "loss": 0.1137, + "step": 271740 + }, + { + "epoch": 0.61, + "learning_rate": 1.9728082145813292e-05, + "loss": 0.1139, + "step": 271750 + }, + { + "epoch": 0.61, + "learning_rate": 1.972696360260397e-05, + "loss": 0.1148, + "step": 271760 + }, + { + "epoch": 0.61, + "learning_rate": 1.9725845059394645e-05, + "loss": 0.1184, + "step": 271770 + }, + { + "epoch": 0.61, + "learning_rate": 1.9724726516185323e-05, + "loss": 0.1136, + "step": 271780 + }, + { + "epoch": 0.61, + "learning_rate": 1.9723607972975997e-05, + "loss": 0.1164, + "step": 271790 + }, + { + "epoch": 0.61, + "learning_rate": 1.972248942976667e-05, + "loss": 0.1176, + "step": 271800 + }, + { + "epoch": 0.61, + "learning_rate": 1.972137088655735e-05, + "loss": 0.1181, + "step": 271810 + }, + { + "epoch": 0.61, + "learning_rate": 1.9720252343348024e-05, + "loss": 0.1161, + "step": 271820 + }, + { + "epoch": 0.61, + "learning_rate": 1.9719133800138702e-05, + "loss": 0.1141, + "step": 271830 + }, + { + "epoch": 0.61, + "learning_rate": 1.9718015256929377e-05, + "loss": 0.1219, + "step": 271840 + }, + { + "epoch": 0.61, + "learning_rate": 1.971689671372005e-05, + "loss": 0.117, + "step": 271850 + }, + { + "epoch": 0.61, + "learning_rate": 1.9715778170510726e-05, + "loss": 0.116, + "step": 271860 + }, + { + "epoch": 0.61, + "learning_rate": 1.9714659627301404e-05, + "loss": 0.1182, + "step": 271870 + }, + { + "epoch": 0.61, + "learning_rate": 1.9713541084092078e-05, + "loss": 0.1151, + "step": 271880 + }, + { + "epoch": 0.61, + "learning_rate": 1.9712422540882756e-05, + "loss": 0.1175, + "step": 271890 + }, + { + "epoch": 0.61, + "learning_rate": 1.971130399767343e-05, + "loss": 0.1131, + "step": 271900 + }, + { + "epoch": 0.61, + "learning_rate": 1.9710185454464105e-05, + "loss": 0.119, + "step": 271910 + }, + { + "epoch": 0.61, + "learning_rate": 1.9709066911254783e-05, + "loss": 0.118, + "step": 271920 + }, + { + "epoch": 0.61, + "learning_rate": 1.9707948368045458e-05, + "loss": 0.1165, + "step": 271930 + }, + { + "epoch": 0.61, + "learning_rate": 1.9706829824836136e-05, + "loss": 0.1158, + "step": 271940 + }, + { + "epoch": 0.61, + "learning_rate": 1.970571128162681e-05, + "loss": 0.1117, + "step": 271950 + }, + { + "epoch": 0.61, + "learning_rate": 1.9704592738417485e-05, + "loss": 0.1182, + "step": 271960 + }, + { + "epoch": 0.61, + "learning_rate": 1.9703474195208163e-05, + "loss": 0.1141, + "step": 271970 + }, + { + "epoch": 0.61, + "learning_rate": 1.9702355651998837e-05, + "loss": 0.1179, + "step": 271980 + }, + { + "epoch": 0.61, + "learning_rate": 1.9701237108789515e-05, + "loss": 0.1154, + "step": 271990 + }, + { + "epoch": 0.61, + "learning_rate": 1.970011856558019e-05, + "loss": 0.1182, + "step": 272000 + }, + { + "epoch": 0.61, + "eval_NEIMS_canon_smiles": 0.95485, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.18763333333333335, + "eval_NEIMS_daylight_tanimoto_simil": 0.5784484096296032, + "eval_NEIMS_exact_mols": 0.18745, + "eval_NEIMS_exact_smiles": 0.18318333333333334, + "eval_NEIMS_loss": 0.14869239926338196, + "eval_NEIMS_matched_formulas": 0.7114, + "eval_NEIMS_morgan_tanimoto_simil": 0.497468752807355, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.18805, + "eval_NEIMS_runtime": 728.6793, + "eval_NEIMS_samples_per_second": 82.341, + "eval_NEIMS_steps_per_second": 1.287, + "step": 272000 + }, + { + "epoch": 0.61, + "eval_RASSP_canon_smiles": 0.9543693859151167, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.2559354860253114, + "eval_RASSP_daylight_tanimoto_simil": 0.6767238723323885, + "eval_RASSP_exact_mols": 0.2551173740274485, + "eval_RASSP_exact_smiles": 0.24927371689985642, + "eval_RASSP_loss": 0.11704910546541214, + "eval_RASSP_matched_formulas": 0.8515043243062744, + "eval_RASSP_morgan_tanimoto_simil": 0.5597314511480299, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.2552342471700003, + "eval_RASSP_runtime": 829.0198, + "eval_RASSP_samples_per_second": 72.247, + "eval_RASSP_steps_per_second": 1.129, + "step": 272000 + }, + { + "epoch": 0.61, + "eval_NEIMS_old_canon_smiles": 0.9543666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.18693333333333334, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5768216159250155, + "eval_NEIMS_old_exact_mols": 0.18656666666666666, + "eval_NEIMS_old_exact_smiles": 0.1821, + "eval_NEIMS_old_loss": 0.14844359457492828, + "eval_NEIMS_old_matched_formulas": 0.7108, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.49742459676388656, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1874, + "eval_NEIMS_old_runtime": 368.767, + "eval_NEIMS_old_samples_per_second": 81.352, + "eval_NEIMS_old_steps_per_second": 1.272, + "step": 272000 + }, + { + "epoch": 0.61, + "eval_RASSP_old_canon_smiles": 0.9529148730269964, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.28227717155537757, + "eval_RASSP_old_daylight_tanimoto_simil": 0.6954865411845788, + "eval_RASSP_old_exact_mols": 0.2817432509093336, + "eval_RASSP_old_exact_smiles": 0.27480228251076183, + "eval_RASSP_old_loss": 0.10987779498100281, + "eval_RASSP_old_matched_formulas": 0.8646844862682284, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5832676306070302, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.28194347115160007, + "eval_RASSP_old_runtime": 415.1719, + "eval_RASSP_old_samples_per_second": 72.18, + "eval_RASSP_old_steps_per_second": 1.13, + "step": 272000 + }, + { + "epoch": 0.61, + "eval_NIST_canon_smiles": 0.8645349043546154, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.025126876530503602, + "eval_NIST_daylight_tanimoto_simil": 0.29465860188434156, + "eval_NIST_exact_mols": 0.02374276892500976, + "eval_NIST_exact_smiles": 0.022216701565106294, + "eval_NIST_loss": 1.7978724241256714, + "eval_NIST_matched_formulas": 0.11622954892288036, + "eval_NIST_morgan_tanimoto_simil": 0.24539636893789793, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.024913936898889166, + "eval_NIST_runtime": 601.6261, + "eval_NIST_samples_per_second": 46.835, + "eval_NIST_steps_per_second": 0.733, + "step": 272000 + }, + { + "epoch": 0.61, + "learning_rate": 1.9699000022370864e-05, + "loss": 0.1144, + "step": 272010 + }, + { + "epoch": 0.61, + "learning_rate": 1.969788147916154e-05, + "loss": 0.1139, + "step": 272020 + }, + { + "epoch": 0.61, + "learning_rate": 1.9696762935952217e-05, + "loss": 0.115, + "step": 272030 + }, + { + "epoch": 0.61, + "learning_rate": 1.9695644392742895e-05, + "loss": 0.1201, + "step": 272040 + }, + { + "epoch": 0.61, + "learning_rate": 1.969452584953357e-05, + "loss": 0.1142, + "step": 272050 + }, + { + "epoch": 0.61, + "learning_rate": 1.9693407306324244e-05, + "loss": 0.1101, + "step": 272060 + }, + { + "epoch": 0.61, + "learning_rate": 1.9692288763114918e-05, + "loss": 0.1208, + "step": 272070 + }, + { + "epoch": 0.61, + "learning_rate": 1.9691170219905596e-05, + "loss": 0.109, + "step": 272080 + }, + { + "epoch": 0.61, + "learning_rate": 1.969005167669627e-05, + "loss": 0.1143, + "step": 272090 + }, + { + "epoch": 0.61, + "learning_rate": 1.968893313348695e-05, + "loss": 0.1164, + "step": 272100 + }, + { + "epoch": 0.61, + "learning_rate": 1.9687814590277623e-05, + "loss": 0.1108, + "step": 272110 + }, + { + "epoch": 0.61, + "learning_rate": 1.9686696047068298e-05, + "loss": 0.1125, + "step": 272120 + }, + { + "epoch": 0.61, + "learning_rate": 1.9685577503858976e-05, + "loss": 0.113, + "step": 272130 + }, + { + "epoch": 0.61, + "learning_rate": 1.968445896064965e-05, + "loss": 0.1128, + "step": 272140 + }, + { + "epoch": 0.61, + "learning_rate": 1.9683340417440328e-05, + "loss": 0.112, + "step": 272150 + }, + { + "epoch": 0.61, + "learning_rate": 1.9682221874231003e-05, + "loss": 0.1165, + "step": 272160 + }, + { + "epoch": 0.61, + "learning_rate": 1.9681103331021677e-05, + "loss": 0.118, + "step": 272170 + }, + { + "epoch": 0.61, + "learning_rate": 1.967998478781235e-05, + "loss": 0.1155, + "step": 272180 + }, + { + "epoch": 0.61, + "learning_rate": 1.967886624460303e-05, + "loss": 0.1182, + "step": 272190 + }, + { + "epoch": 0.61, + "learning_rate": 1.9677747701393707e-05, + "loss": 0.1151, + "step": 272200 + }, + { + "epoch": 0.61, + "learning_rate": 1.9676629158184382e-05, + "loss": 0.1169, + "step": 272210 + }, + { + "epoch": 0.61, + "learning_rate": 1.9675510614975057e-05, + "loss": 0.115, + "step": 272220 + }, + { + "epoch": 0.61, + "learning_rate": 1.967439207176573e-05, + "loss": 0.1158, + "step": 272230 + }, + { + "epoch": 0.61, + "learning_rate": 1.967327352855641e-05, + "loss": 0.1131, + "step": 272240 + }, + { + "epoch": 0.61, + "learning_rate": 1.9672154985347087e-05, + "loss": 0.1159, + "step": 272250 + }, + { + "epoch": 0.61, + "learning_rate": 1.967103644213776e-05, + "loss": 0.1134, + "step": 272260 + }, + { + "epoch": 0.61, + "learning_rate": 1.9669917898928436e-05, + "loss": 0.1155, + "step": 272270 + }, + { + "epoch": 0.61, + "learning_rate": 1.966879935571911e-05, + "loss": 0.1197, + "step": 272280 + }, + { + "epoch": 0.61, + "learning_rate": 1.966768081250979e-05, + "loss": 0.1126, + "step": 272290 + }, + { + "epoch": 0.61, + "learning_rate": 1.9666562269300466e-05, + "loss": 0.1124, + "step": 272300 + }, + { + "epoch": 0.61, + "learning_rate": 1.966544372609114e-05, + "loss": 0.1165, + "step": 272310 + }, + { + "epoch": 0.61, + "learning_rate": 1.9664325182881816e-05, + "loss": 0.1153, + "step": 272320 + }, + { + "epoch": 0.61, + "learning_rate": 1.966320663967249e-05, + "loss": 0.1156, + "step": 272330 + }, + { + "epoch": 0.61, + "learning_rate": 1.9662088096463165e-05, + "loss": 0.1182, + "step": 272340 + }, + { + "epoch": 0.61, + "learning_rate": 1.9660969553253843e-05, + "loss": 0.1117, + "step": 272350 + }, + { + "epoch": 0.61, + "learning_rate": 1.965985101004452e-05, + "loss": 0.1161, + "step": 272360 + }, + { + "epoch": 0.61, + "learning_rate": 1.9658732466835195e-05, + "loss": 0.1152, + "step": 272370 + }, + { + "epoch": 0.61, + "learning_rate": 1.965761392362587e-05, + "loss": 0.1184, + "step": 272380 + }, + { + "epoch": 0.61, + "learning_rate": 1.9656495380416544e-05, + "loss": 0.1131, + "step": 272390 + }, + { + "epoch": 0.61, + "learning_rate": 1.9655376837207222e-05, + "loss": 0.1142, + "step": 272400 + }, + { + "epoch": 0.61, + "learning_rate": 1.96542582939979e-05, + "loss": 0.1188, + "step": 272410 + }, + { + "epoch": 0.61, + "learning_rate": 1.9653139750788574e-05, + "loss": 0.1143, + "step": 272420 + }, + { + "epoch": 0.61, + "learning_rate": 1.965202120757925e-05, + "loss": 0.115, + "step": 272430 + }, + { + "epoch": 0.61, + "learning_rate": 1.9650902664369924e-05, + "loss": 0.1156, + "step": 272440 + }, + { + "epoch": 0.61, + "learning_rate": 1.96497841211606e-05, + "loss": 0.1142, + "step": 272450 + }, + { + "epoch": 0.61, + "learning_rate": 1.964866557795128e-05, + "loss": 0.1154, + "step": 272460 + }, + { + "epoch": 0.61, + "learning_rate": 1.9647547034741954e-05, + "loss": 0.1092, + "step": 272470 + }, + { + "epoch": 0.61, + "learning_rate": 1.964642849153263e-05, + "loss": 0.1135, + "step": 272480 + }, + { + "epoch": 0.61, + "learning_rate": 1.9645309948323303e-05, + "loss": 0.1135, + "step": 272490 + }, + { + "epoch": 0.61, + "learning_rate": 1.9644191405113978e-05, + "loss": 0.1161, + "step": 272500 + }, + { + "epoch": 0.61, + "learning_rate": 1.964307286190466e-05, + "loss": 0.1225, + "step": 272510 + }, + { + "epoch": 0.61, + "learning_rate": 1.9641954318695333e-05, + "loss": 0.1134, + "step": 272520 + }, + { + "epoch": 0.61, + "learning_rate": 1.9640835775486008e-05, + "loss": 0.1214, + "step": 272530 + }, + { + "epoch": 0.61, + "learning_rate": 1.9639717232276682e-05, + "loss": 0.1158, + "step": 272540 + }, + { + "epoch": 0.61, + "learning_rate": 1.9638598689067357e-05, + "loss": 0.116, + "step": 272550 + }, + { + "epoch": 0.61, + "learning_rate": 1.9637480145858035e-05, + "loss": 0.1196, + "step": 272560 + }, + { + "epoch": 0.61, + "learning_rate": 1.9636361602648713e-05, + "loss": 0.1166, + "step": 272570 + }, + { + "epoch": 0.61, + "learning_rate": 1.9635243059439387e-05, + "loss": 0.1119, + "step": 272580 + }, + { + "epoch": 0.61, + "learning_rate": 1.9634124516230062e-05, + "loss": 0.1103, + "step": 272590 + }, + { + "epoch": 0.61, + "learning_rate": 1.9633005973020736e-05, + "loss": 0.1172, + "step": 272600 + }, + { + "epoch": 0.61, + "learning_rate": 1.9631887429811414e-05, + "loss": 0.1204, + "step": 272610 + }, + { + "epoch": 0.61, + "learning_rate": 1.9630768886602092e-05, + "loss": 0.1211, + "step": 272620 + }, + { + "epoch": 0.61, + "learning_rate": 1.9629650343392767e-05, + "loss": 0.1184, + "step": 272630 + }, + { + "epoch": 0.61, + "learning_rate": 1.962853180018344e-05, + "loss": 0.1227, + "step": 272640 + }, + { + "epoch": 0.61, + "learning_rate": 1.9627413256974116e-05, + "loss": 0.1163, + "step": 272650 + }, + { + "epoch": 0.61, + "learning_rate": 1.9626294713764794e-05, + "loss": 0.1171, + "step": 272660 + }, + { + "epoch": 0.61, + "learning_rate": 1.9625176170555472e-05, + "loss": 0.1239, + "step": 272670 + }, + { + "epoch": 0.61, + "learning_rate": 1.9624057627346146e-05, + "loss": 0.1274, + "step": 272680 + }, + { + "epoch": 0.61, + "learning_rate": 1.962293908413682e-05, + "loss": 0.1237, + "step": 272690 + }, + { + "epoch": 0.61, + "learning_rate": 1.9621820540927495e-05, + "loss": 0.1258, + "step": 272700 + }, + { + "epoch": 0.61, + "learning_rate": 1.962070199771817e-05, + "loss": 0.1236, + "step": 272710 + }, + { + "epoch": 0.61, + "learning_rate": 1.961958345450885e-05, + "loss": 0.1253, + "step": 272720 + }, + { + "epoch": 0.61, + "learning_rate": 1.9618464911299526e-05, + "loss": 0.127, + "step": 272730 + }, + { + "epoch": 0.61, + "learning_rate": 1.96173463680902e-05, + "loss": 0.1248, + "step": 272740 + }, + { + "epoch": 0.61, + "learning_rate": 1.9616227824880875e-05, + "loss": 0.1196, + "step": 272750 + }, + { + "epoch": 0.61, + "learning_rate": 1.961510928167155e-05, + "loss": 0.1244, + "step": 272760 + }, + { + "epoch": 0.61, + "learning_rate": 1.9613990738462227e-05, + "loss": 0.1212, + "step": 272770 + }, + { + "epoch": 0.61, + "learning_rate": 1.9612872195252905e-05, + "loss": 0.1237, + "step": 272780 + }, + { + "epoch": 0.61, + "learning_rate": 1.961175365204358e-05, + "loss": 0.1235, + "step": 272790 + }, + { + "epoch": 0.61, + "learning_rate": 1.9610635108834254e-05, + "loss": 0.1217, + "step": 272800 + }, + { + "epoch": 0.61, + "learning_rate": 1.960951656562493e-05, + "loss": 0.1195, + "step": 272810 + }, + { + "epoch": 0.61, + "learning_rate": 1.9608398022415607e-05, + "loss": 0.121, + "step": 272820 + }, + { + "epoch": 0.61, + "learning_rate": 1.9607279479206285e-05, + "loss": 0.1225, + "step": 272830 + }, + { + "epoch": 0.61, + "learning_rate": 1.960616093599696e-05, + "loss": 0.122, + "step": 272840 + }, + { + "epoch": 0.61, + "learning_rate": 1.9605042392787634e-05, + "loss": 0.1242, + "step": 272850 + }, + { + "epoch": 0.61, + "learning_rate": 1.960392384957831e-05, + "loss": 0.1259, + "step": 272860 + }, + { + "epoch": 0.61, + "learning_rate": 1.9602805306368986e-05, + "loss": 0.1198, + "step": 272870 + }, + { + "epoch": 0.61, + "learning_rate": 1.9601686763159664e-05, + "loss": 0.1254, + "step": 272880 + }, + { + "epoch": 0.61, + "learning_rate": 1.960056821995034e-05, + "loss": 0.1182, + "step": 272890 + }, + { + "epoch": 0.61, + "learning_rate": 1.9599449676741013e-05, + "loss": 0.1207, + "step": 272900 + }, + { + "epoch": 0.61, + "learning_rate": 1.9598331133531688e-05, + "loss": 0.1229, + "step": 272910 + }, + { + "epoch": 0.61, + "learning_rate": 1.9597212590322366e-05, + "loss": 0.1251, + "step": 272920 + }, + { + "epoch": 0.61, + "learning_rate": 1.9596094047113044e-05, + "loss": 0.1217, + "step": 272930 + }, + { + "epoch": 0.61, + "learning_rate": 1.9594975503903718e-05, + "loss": 0.1223, + "step": 272940 + }, + { + "epoch": 0.61, + "learning_rate": 1.9593856960694393e-05, + "loss": 0.1213, + "step": 272950 + }, + { + "epoch": 0.61, + "learning_rate": 1.9592738417485067e-05, + "loss": 0.1218, + "step": 272960 + }, + { + "epoch": 0.61, + "learning_rate": 1.9591619874275742e-05, + "loss": 0.1244, + "step": 272970 + }, + { + "epoch": 0.61, + "learning_rate": 1.959050133106642e-05, + "loss": 0.1278, + "step": 272980 + }, + { + "epoch": 0.61, + "learning_rate": 1.9589382787857098e-05, + "loss": 0.1219, + "step": 272990 + }, + { + "epoch": 0.61, + "learning_rate": 1.9588264244647772e-05, + "loss": 0.1195, + "step": 273000 + }, + { + "epoch": 0.61, + "learning_rate": 1.9587145701438447e-05, + "loss": 0.1211, + "step": 273010 + }, + { + "epoch": 0.61, + "learning_rate": 1.958602715822912e-05, + "loss": 0.1194, + "step": 273020 + }, + { + "epoch": 0.61, + "learning_rate": 1.95849086150198e-05, + "loss": 0.1169, + "step": 273030 + }, + { + "epoch": 0.61, + "learning_rate": 1.9583790071810477e-05, + "loss": 0.1199, + "step": 273040 + }, + { + "epoch": 0.61, + "learning_rate": 1.9582671528601152e-05, + "loss": 0.1244, + "step": 273050 + }, + { + "epoch": 0.61, + "learning_rate": 1.9581552985391826e-05, + "loss": 0.127, + "step": 273060 + }, + { + "epoch": 0.61, + "learning_rate": 1.95804344421825e-05, + "loss": 0.1229, + "step": 273070 + }, + { + "epoch": 0.61, + "learning_rate": 1.957931589897318e-05, + "loss": 0.1234, + "step": 273080 + }, + { + "epoch": 0.61, + "learning_rate": 1.9578197355763857e-05, + "loss": 0.1235, + "step": 273090 + }, + { + "epoch": 0.61, + "learning_rate": 1.957707881255453e-05, + "loss": 0.1224, + "step": 273100 + }, + { + "epoch": 0.61, + "learning_rate": 1.9575960269345206e-05, + "loss": 0.1197, + "step": 273110 + }, + { + "epoch": 0.61, + "learning_rate": 1.957484172613588e-05, + "loss": 0.1224, + "step": 273120 + }, + { + "epoch": 0.61, + "learning_rate": 1.9573723182926558e-05, + "loss": 0.1216, + "step": 273130 + }, + { + "epoch": 0.61, + "learning_rate": 1.9572604639717233e-05, + "loss": 0.1235, + "step": 273140 + }, + { + "epoch": 0.61, + "learning_rate": 1.957148609650791e-05, + "loss": 0.1271, + "step": 273150 + }, + { + "epoch": 0.61, + "learning_rate": 1.9570367553298585e-05, + "loss": 0.1206, + "step": 273160 + }, + { + "epoch": 0.61, + "learning_rate": 1.956924901008926e-05, + "loss": 0.1253, + "step": 273170 + }, + { + "epoch": 0.61, + "learning_rate": 1.9568130466879934e-05, + "loss": 0.1229, + "step": 273180 + }, + { + "epoch": 0.61, + "learning_rate": 1.9567011923670612e-05, + "loss": 0.1197, + "step": 273190 + }, + { + "epoch": 0.61, + "learning_rate": 1.956589338046129e-05, + "loss": 0.123, + "step": 273200 + }, + { + "epoch": 0.61, + "learning_rate": 1.9564774837251965e-05, + "loss": 0.1187, + "step": 273210 + }, + { + "epoch": 0.61, + "learning_rate": 1.956365629404264e-05, + "loss": 0.1188, + "step": 273220 + }, + { + "epoch": 0.61, + "learning_rate": 1.9562537750833314e-05, + "loss": 0.1276, + "step": 273230 + }, + { + "epoch": 0.61, + "learning_rate": 1.9561531061944923e-05, + "loss": 0.1248, + "step": 273240 + }, + { + "epoch": 0.61, + "learning_rate": 1.95604125187356e-05, + "loss": 0.1242, + "step": 273250 + }, + { + "epoch": 0.61, + "learning_rate": 1.9559293975526275e-05, + "loss": 0.1186, + "step": 273260 + }, + { + "epoch": 0.61, + "learning_rate": 1.9558175432316953e-05, + "loss": 0.1239, + "step": 273270 + }, + { + "epoch": 0.61, + "learning_rate": 1.9557056889107628e-05, + "loss": 0.1216, + "step": 273280 + }, + { + "epoch": 0.61, + "learning_rate": 1.9555938345898302e-05, + "loss": 0.1217, + "step": 273290 + }, + { + "epoch": 0.61, + "learning_rate": 1.955481980268898e-05, + "loss": 0.1276, + "step": 273300 + }, + { + "epoch": 0.61, + "learning_rate": 1.9553701259479655e-05, + "loss": 0.1224, + "step": 273310 + }, + { + "epoch": 0.61, + "learning_rate": 1.9552582716270332e-05, + "loss": 0.124, + "step": 273320 + }, + { + "epoch": 0.61, + "learning_rate": 1.9551464173061007e-05, + "loss": 0.1204, + "step": 273330 + }, + { + "epoch": 0.61, + "learning_rate": 1.955034562985168e-05, + "loss": 0.1251, + "step": 273340 + }, + { + "epoch": 0.61, + "learning_rate": 1.9549227086642356e-05, + "loss": 0.1188, + "step": 273350 + }, + { + "epoch": 0.61, + "learning_rate": 1.9548108543433034e-05, + "loss": 0.1179, + "step": 273360 + }, + { + "epoch": 0.61, + "learning_rate": 1.954699000022371e-05, + "loss": 0.1208, + "step": 273370 + }, + { + "epoch": 0.61, + "learning_rate": 1.9545871457014386e-05, + "loss": 0.1242, + "step": 273380 + }, + { + "epoch": 0.61, + "learning_rate": 1.954475291380506e-05, + "loss": 0.1221, + "step": 273390 + }, + { + "epoch": 0.61, + "learning_rate": 1.9543634370595736e-05, + "loss": 0.1188, + "step": 273400 + }, + { + "epoch": 0.61, + "learning_rate": 1.9542515827386413e-05, + "loss": 0.1245, + "step": 273410 + }, + { + "epoch": 0.61, + "learning_rate": 1.9541397284177088e-05, + "loss": 0.1228, + "step": 273420 + }, + { + "epoch": 0.61, + "learning_rate": 1.9540278740967766e-05, + "loss": 0.1199, + "step": 273430 + }, + { + "epoch": 0.61, + "learning_rate": 1.953916019775844e-05, + "loss": 0.1155, + "step": 273440 + }, + { + "epoch": 0.61, + "learning_rate": 1.9538041654549115e-05, + "loss": 0.1186, + "step": 273450 + }, + { + "epoch": 0.61, + "learning_rate": 1.9536923111339793e-05, + "loss": 0.1232, + "step": 273460 + }, + { + "epoch": 0.61, + "learning_rate": 1.9535804568130467e-05, + "loss": 0.1227, + "step": 273470 + }, + { + "epoch": 0.61, + "learning_rate": 1.9534686024921145e-05, + "loss": 0.1184, + "step": 273480 + }, + { + "epoch": 0.61, + "learning_rate": 1.953356748171182e-05, + "loss": 0.1246, + "step": 273490 + }, + { + "epoch": 0.61, + "learning_rate": 1.9532448938502494e-05, + "loss": 0.1213, + "step": 273500 + }, + { + "epoch": 0.61, + "learning_rate": 1.9531330395293172e-05, + "loss": 0.1169, + "step": 273510 + }, + { + "epoch": 0.61, + "learning_rate": 1.9530211852083847e-05, + "loss": 0.1214, + "step": 273520 + }, + { + "epoch": 0.61, + "learning_rate": 1.952909330887452e-05, + "loss": 0.1197, + "step": 273530 + }, + { + "epoch": 0.61, + "learning_rate": 1.95279747656652e-05, + "loss": 0.1187, + "step": 273540 + }, + { + "epoch": 0.61, + "learning_rate": 1.9526856222455874e-05, + "loss": 0.1242, + "step": 273550 + }, + { + "epoch": 0.61, + "learning_rate": 1.952573767924655e-05, + "loss": 0.1194, + "step": 273560 + }, + { + "epoch": 0.61, + "learning_rate": 1.9524619136037226e-05, + "loss": 0.1267, + "step": 273570 + }, + { + "epoch": 0.61, + "learning_rate": 1.95235005928279e-05, + "loss": 0.1198, + "step": 273580 + }, + { + "epoch": 0.61, + "learning_rate": 1.952238204961858e-05, + "loss": 0.1244, + "step": 273590 + }, + { + "epoch": 0.61, + "learning_rate": 1.9521263506409253e-05, + "loss": 0.1242, + "step": 273600 + }, + { + "epoch": 0.61, + "learning_rate": 1.9520144963199928e-05, + "loss": 0.1188, + "step": 273610 + }, + { + "epoch": 0.61, + "learning_rate": 1.9519026419990606e-05, + "loss": 0.1209, + "step": 273620 + }, + { + "epoch": 0.61, + "learning_rate": 1.951790787678128e-05, + "loss": 0.121, + "step": 273630 + }, + { + "epoch": 0.61, + "learning_rate": 1.951678933357196e-05, + "loss": 0.1201, + "step": 273640 + }, + { + "epoch": 0.61, + "learning_rate": 1.9515670790362633e-05, + "loss": 0.122, + "step": 273650 + }, + { + "epoch": 0.61, + "learning_rate": 1.9514552247153307e-05, + "loss": 0.1256, + "step": 273660 + }, + { + "epoch": 0.61, + "learning_rate": 1.9513433703943985e-05, + "loss": 0.1228, + "step": 273670 + }, + { + "epoch": 0.61, + "learning_rate": 1.951231516073466e-05, + "loss": 0.1186, + "step": 273680 + }, + { + "epoch": 0.61, + "learning_rate": 1.9511196617525334e-05, + "loss": 0.1181, + "step": 273690 + }, + { + "epoch": 0.61, + "learning_rate": 1.9510078074316012e-05, + "loss": 0.121, + "step": 273700 + }, + { + "epoch": 0.61, + "learning_rate": 1.9508959531106687e-05, + "loss": 0.1193, + "step": 273710 + }, + { + "epoch": 0.61, + "learning_rate": 1.9507840987897365e-05, + "loss": 0.1242, + "step": 273720 + }, + { + "epoch": 0.61, + "learning_rate": 1.950672244468804e-05, + "loss": 0.1196, + "step": 273730 + }, + { + "epoch": 0.61, + "learning_rate": 1.9505603901478714e-05, + "loss": 0.1231, + "step": 273740 + }, + { + "epoch": 0.61, + "learning_rate": 1.9504485358269392e-05, + "loss": 0.1185, + "step": 273750 + }, + { + "epoch": 0.61, + "learning_rate": 1.9503366815060066e-05, + "loss": 0.1178, + "step": 273760 + }, + { + "epoch": 0.61, + "learning_rate": 1.9502248271850744e-05, + "loss": 0.1179, + "step": 273770 + }, + { + "epoch": 0.61, + "learning_rate": 1.950112972864142e-05, + "loss": 0.1231, + "step": 273780 + }, + { + "epoch": 0.61, + "learning_rate": 1.9500011185432093e-05, + "loss": 0.1208, + "step": 273790 + }, + { + "epoch": 0.61, + "learning_rate": 1.949889264222277e-05, + "loss": 0.1183, + "step": 273800 + }, + { + "epoch": 0.61, + "learning_rate": 1.9497774099013446e-05, + "loss": 0.1176, + "step": 273810 + }, + { + "epoch": 0.61, + "learning_rate": 1.949665555580412e-05, + "loss": 0.1249, + "step": 273820 + }, + { + "epoch": 0.61, + "learning_rate": 1.94955370125948e-05, + "loss": 0.1217, + "step": 273830 + }, + { + "epoch": 0.61, + "learning_rate": 1.9494418469385473e-05, + "loss": 0.1162, + "step": 273840 + }, + { + "epoch": 0.61, + "learning_rate": 1.9493299926176147e-05, + "loss": 0.1213, + "step": 273850 + }, + { + "epoch": 0.61, + "learning_rate": 1.9492181382966825e-05, + "loss": 0.1158, + "step": 273860 + }, + { + "epoch": 0.61, + "learning_rate": 1.94910628397575e-05, + "loss": 0.1241, + "step": 273870 + }, + { + "epoch": 0.61, + "learning_rate": 1.9489944296548178e-05, + "loss": 0.1176, + "step": 273880 + }, + { + "epoch": 0.61, + "learning_rate": 1.9488825753338852e-05, + "loss": 0.1145, + "step": 273890 + }, + { + "epoch": 0.61, + "learning_rate": 1.9487707210129527e-05, + "loss": 0.1242, + "step": 273900 + }, + { + "epoch": 0.61, + "learning_rate": 1.9486588666920205e-05, + "loss": 0.1223, + "step": 273910 + }, + { + "epoch": 0.61, + "learning_rate": 1.948547012371088e-05, + "loss": 0.1222, + "step": 273920 + }, + { + "epoch": 0.61, + "learning_rate": 1.9484351580501557e-05, + "loss": 0.1181, + "step": 273930 + }, + { + "epoch": 0.61, + "learning_rate": 1.9483233037292232e-05, + "loss": 0.1212, + "step": 273940 + }, + { + "epoch": 0.61, + "learning_rate": 1.9482114494082906e-05, + "loss": 0.1195, + "step": 273950 + }, + { + "epoch": 0.61, + "learning_rate": 1.9480995950873584e-05, + "loss": 0.1179, + "step": 273960 + }, + { + "epoch": 0.61, + "learning_rate": 1.947987740766426e-05, + "loss": 0.1246, + "step": 273970 + }, + { + "epoch": 0.61, + "learning_rate": 1.9478758864454937e-05, + "loss": 0.1168, + "step": 273980 + }, + { + "epoch": 0.61, + "learning_rate": 1.947764032124561e-05, + "loss": 0.1209, + "step": 273990 + }, + { + "epoch": 0.61, + "learning_rate": 1.9476521778036286e-05, + "loss": 0.1198, + "step": 274000 + }, + { + "epoch": 0.61, + "learning_rate": 1.947540323482696e-05, + "loss": 0.1217, + "step": 274010 + }, + { + "epoch": 0.61, + "learning_rate": 1.947428469161764e-05, + "loss": 0.1198, + "step": 274020 + }, + { + "epoch": 0.61, + "learning_rate": 1.9473166148408313e-05, + "loss": 0.1192, + "step": 274030 + }, + { + "epoch": 0.61, + "learning_rate": 1.947204760519899e-05, + "loss": 0.1191, + "step": 274040 + }, + { + "epoch": 0.61, + "learning_rate": 1.9470929061989665e-05, + "loss": 0.119, + "step": 274050 + }, + { + "epoch": 0.61, + "learning_rate": 1.946981051878034e-05, + "loss": 0.1183, + "step": 274060 + }, + { + "epoch": 0.61, + "learning_rate": 1.9468691975571018e-05, + "loss": 0.1197, + "step": 274070 + }, + { + "epoch": 0.61, + "learning_rate": 1.9467573432361692e-05, + "loss": 0.1187, + "step": 274080 + }, + { + "epoch": 0.61, + "learning_rate": 1.946645488915237e-05, + "loss": 0.1206, + "step": 274090 + }, + { + "epoch": 0.61, + "learning_rate": 1.9465336345943045e-05, + "loss": 0.1182, + "step": 274100 + }, + { + "epoch": 0.61, + "learning_rate": 1.946421780273372e-05, + "loss": 0.1228, + "step": 274110 + }, + { + "epoch": 0.61, + "learning_rate": 1.9463099259524397e-05, + "loss": 0.1177, + "step": 274120 + }, + { + "epoch": 0.61, + "learning_rate": 1.9461980716315072e-05, + "loss": 0.1173, + "step": 274130 + }, + { + "epoch": 0.61, + "learning_rate": 1.946086217310575e-05, + "loss": 0.1169, + "step": 274140 + }, + { + "epoch": 0.61, + "learning_rate": 1.9459743629896424e-05, + "loss": 0.1233, + "step": 274150 + }, + { + "epoch": 0.61, + "learning_rate": 1.94586250866871e-05, + "loss": 0.1205, + "step": 274160 + }, + { + "epoch": 0.61, + "learning_rate": 1.9457506543477773e-05, + "loss": 0.1167, + "step": 274170 + }, + { + "epoch": 0.61, + "learning_rate": 1.945638800026845e-05, + "loss": 0.1241, + "step": 274180 + }, + { + "epoch": 0.61, + "learning_rate": 1.945526945705913e-05, + "loss": 0.1209, + "step": 274190 + }, + { + "epoch": 0.61, + "learning_rate": 1.9454150913849804e-05, + "loss": 0.118, + "step": 274200 + }, + { + "epoch": 0.61, + "learning_rate": 1.9453032370640478e-05, + "loss": 0.1194, + "step": 274210 + }, + { + "epoch": 0.61, + "learning_rate": 1.9451913827431153e-05, + "loss": 0.1166, + "step": 274220 + }, + { + "epoch": 0.61, + "learning_rate": 1.945079528422183e-05, + "loss": 0.1226, + "step": 274230 + }, + { + "epoch": 0.61, + "learning_rate": 1.9449676741012505e-05, + "loss": 0.1162, + "step": 274240 + }, + { + "epoch": 0.61, + "learning_rate": 1.9448558197803183e-05, + "loss": 0.1262, + "step": 274250 + }, + { + "epoch": 0.61, + "learning_rate": 1.9447439654593858e-05, + "loss": 0.1221, + "step": 274260 + }, + { + "epoch": 0.61, + "learning_rate": 1.9446321111384532e-05, + "loss": 0.1209, + "step": 274270 + }, + { + "epoch": 0.61, + "learning_rate": 1.944520256817521e-05, + "loss": 0.1189, + "step": 274280 + }, + { + "epoch": 0.61, + "learning_rate": 1.9444084024965885e-05, + "loss": 0.1258, + "step": 274290 + }, + { + "epoch": 0.61, + "learning_rate": 1.9442965481756563e-05, + "loss": 0.1221, + "step": 274300 + }, + { + "epoch": 0.61, + "learning_rate": 1.9441846938547237e-05, + "loss": 0.117, + "step": 274310 + }, + { + "epoch": 0.61, + "learning_rate": 1.9440728395337912e-05, + "loss": 0.1208, + "step": 274320 + }, + { + "epoch": 0.61, + "learning_rate": 1.9439609852128586e-05, + "loss": 0.1211, + "step": 274330 + }, + { + "epoch": 0.61, + "learning_rate": 1.9438491308919264e-05, + "loss": 0.1192, + "step": 274340 + }, + { + "epoch": 0.61, + "learning_rate": 1.9437372765709942e-05, + "loss": 0.1227, + "step": 274350 + }, + { + "epoch": 0.61, + "learning_rate": 1.9436254222500617e-05, + "loss": 0.1182, + "step": 274360 + }, + { + "epoch": 0.61, + "learning_rate": 1.943513567929129e-05, + "loss": 0.1194, + "step": 274370 + }, + { + "epoch": 0.61, + "learning_rate": 1.9434017136081966e-05, + "loss": 0.116, + "step": 274380 + }, + { + "epoch": 0.61, + "learning_rate": 1.9432898592872644e-05, + "loss": 0.1215, + "step": 274390 + }, + { + "epoch": 0.61, + "learning_rate": 1.943178004966332e-05, + "loss": 0.1184, + "step": 274400 + }, + { + "epoch": 0.61, + "learning_rate": 1.9430661506453996e-05, + "loss": 0.117, + "step": 274410 + }, + { + "epoch": 0.61, + "learning_rate": 1.942954296324467e-05, + "loss": 0.1246, + "step": 274420 + }, + { + "epoch": 0.61, + "learning_rate": 1.9428424420035345e-05, + "loss": 0.1207, + "step": 274430 + }, + { + "epoch": 0.61, + "learning_rate": 1.9427305876826023e-05, + "loss": 0.1207, + "step": 274440 + }, + { + "epoch": 0.61, + "learning_rate": 1.9426187333616698e-05, + "loss": 0.1199, + "step": 274450 + }, + { + "epoch": 0.61, + "learning_rate": 1.9425068790407376e-05, + "loss": 0.1215, + "step": 274460 + }, + { + "epoch": 0.61, + "learning_rate": 1.942395024719805e-05, + "loss": 0.1231, + "step": 274470 + }, + { + "epoch": 0.61, + "learning_rate": 1.9422831703988725e-05, + "loss": 0.121, + "step": 274480 + }, + { + "epoch": 0.61, + "learning_rate": 1.94217131607794e-05, + "loss": 0.1153, + "step": 274490 + }, + { + "epoch": 0.61, + "learning_rate": 1.9420594617570077e-05, + "loss": 0.1209, + "step": 274500 + }, + { + "epoch": 0.61, + "learning_rate": 1.9419476074360755e-05, + "loss": 0.1203, + "step": 274510 + }, + { + "epoch": 0.61, + "learning_rate": 1.941835753115143e-05, + "loss": 0.1212, + "step": 274520 + }, + { + "epoch": 0.61, + "learning_rate": 1.9417238987942104e-05, + "loss": 0.1144, + "step": 274530 + }, + { + "epoch": 0.61, + "learning_rate": 1.941612044473278e-05, + "loss": 0.1207, + "step": 274540 + }, + { + "epoch": 0.61, + "learning_rate": 1.9415001901523457e-05, + "loss": 0.1207, + "step": 274550 + }, + { + "epoch": 0.61, + "learning_rate": 1.9413883358314135e-05, + "loss": 0.1164, + "step": 274560 + }, + { + "epoch": 0.61, + "learning_rate": 1.941276481510481e-05, + "loss": 0.1131, + "step": 274570 + }, + { + "epoch": 0.61, + "learning_rate": 1.9411646271895484e-05, + "loss": 0.1197, + "step": 274580 + }, + { + "epoch": 0.61, + "learning_rate": 1.9410527728686158e-05, + "loss": 0.1139, + "step": 274590 + }, + { + "epoch": 0.61, + "learning_rate": 1.9409409185476836e-05, + "loss": 0.1184, + "step": 274600 + }, + { + "epoch": 0.61, + "learning_rate": 1.9408290642267514e-05, + "loss": 0.1196, + "step": 274610 + }, + { + "epoch": 0.61, + "learning_rate": 1.940717209905819e-05, + "loss": 0.1219, + "step": 274620 + }, + { + "epoch": 0.61, + "learning_rate": 1.9406053555848863e-05, + "loss": 0.1171, + "step": 274630 + }, + { + "epoch": 0.61, + "learning_rate": 1.9404935012639538e-05, + "loss": 0.1158, + "step": 274640 + }, + { + "epoch": 0.61, + "learning_rate": 1.9403816469430212e-05, + "loss": 0.1178, + "step": 274650 + }, + { + "epoch": 0.61, + "learning_rate": 1.9402697926220894e-05, + "loss": 0.1163, + "step": 274660 + }, + { + "epoch": 0.61, + "learning_rate": 1.9401579383011568e-05, + "loss": 0.1166, + "step": 274670 + }, + { + "epoch": 0.61, + "learning_rate": 1.9400460839802243e-05, + "loss": 0.1163, + "step": 274680 + }, + { + "epoch": 0.61, + "learning_rate": 1.9399342296592917e-05, + "loss": 0.1168, + "step": 274690 + }, + { + "epoch": 0.61, + "learning_rate": 1.9398223753383592e-05, + "loss": 0.1197, + "step": 274700 + }, + { + "epoch": 0.61, + "learning_rate": 1.939710521017427e-05, + "loss": 0.1202, + "step": 274710 + }, + { + "epoch": 0.61, + "learning_rate": 1.9395986666964948e-05, + "loss": 0.1216, + "step": 274720 + }, + { + "epoch": 0.61, + "learning_rate": 1.9394868123755622e-05, + "loss": 0.1137, + "step": 274730 + }, + { + "epoch": 0.61, + "learning_rate": 1.9393749580546297e-05, + "loss": 0.1162, + "step": 274740 + }, + { + "epoch": 0.61, + "learning_rate": 1.939263103733697e-05, + "loss": 0.1222, + "step": 274750 + }, + { + "epoch": 0.61, + "learning_rate": 1.939151249412765e-05, + "loss": 0.1193, + "step": 274760 + }, + { + "epoch": 0.61, + "learning_rate": 1.9390393950918327e-05, + "loss": 0.1175, + "step": 274770 + }, + { + "epoch": 0.61, + "learning_rate": 1.9389275407709e-05, + "loss": 0.121, + "step": 274780 + }, + { + "epoch": 0.61, + "learning_rate": 1.9388156864499676e-05, + "loss": 0.1217, + "step": 274790 + }, + { + "epoch": 0.61, + "learning_rate": 1.938703832129035e-05, + "loss": 0.1206, + "step": 274800 + }, + { + "epoch": 0.61, + "learning_rate": 1.938591977808103e-05, + "loss": 0.1227, + "step": 274810 + }, + { + "epoch": 0.61, + "learning_rate": 1.9384801234871707e-05, + "loss": 0.1255, + "step": 274820 + }, + { + "epoch": 0.61, + "learning_rate": 1.938368269166238e-05, + "loss": 0.1168, + "step": 274830 + }, + { + "epoch": 0.61, + "learning_rate": 1.9382564148453056e-05, + "loss": 0.1204, + "step": 274840 + }, + { + "epoch": 0.61, + "learning_rate": 1.938144560524373e-05, + "loss": 0.1138, + "step": 274850 + }, + { + "epoch": 0.61, + "learning_rate": 1.9380327062034405e-05, + "loss": 0.1161, + "step": 274860 + }, + { + "epoch": 0.61, + "learning_rate": 1.9379208518825086e-05, + "loss": 0.1205, + "step": 274870 + }, + { + "epoch": 0.61, + "learning_rate": 1.937808997561576e-05, + "loss": 0.118, + "step": 274880 + }, + { + "epoch": 0.61, + "learning_rate": 1.9376971432406435e-05, + "loss": 0.1184, + "step": 274890 + }, + { + "epoch": 0.61, + "learning_rate": 1.937585288919711e-05, + "loss": 0.1182, + "step": 274900 + }, + { + "epoch": 0.61, + "learning_rate": 1.9374734345987784e-05, + "loss": 0.1173, + "step": 274910 + }, + { + "epoch": 0.61, + "learning_rate": 1.9373615802778462e-05, + "loss": 0.1203, + "step": 274920 + }, + { + "epoch": 0.61, + "learning_rate": 1.937249725956914e-05, + "loss": 0.119, + "step": 274930 + }, + { + "epoch": 0.61, + "learning_rate": 1.9371378716359815e-05, + "loss": 0.1182, + "step": 274940 + }, + { + "epoch": 0.61, + "learning_rate": 1.937026017315049e-05, + "loss": 0.1217, + "step": 274950 + }, + { + "epoch": 0.61, + "learning_rate": 1.9369141629941164e-05, + "loss": 0.1164, + "step": 274960 + }, + { + "epoch": 0.61, + "learning_rate": 1.936802308673184e-05, + "loss": 0.1159, + "step": 274970 + }, + { + "epoch": 0.61, + "learning_rate": 1.936690454352252e-05, + "loss": 0.1147, + "step": 274980 + }, + { + "epoch": 0.61, + "learning_rate": 1.9365786000313194e-05, + "loss": 0.1227, + "step": 274990 + }, + { + "epoch": 0.61, + "learning_rate": 1.936466745710387e-05, + "loss": 0.1233, + "step": 275000 + }, + { + "epoch": 0.61, + "learning_rate": 1.9363548913894543e-05, + "loss": 0.1176, + "step": 275010 + }, + { + "epoch": 0.61, + "learning_rate": 1.936243037068522e-05, + "loss": 0.1177, + "step": 275020 + }, + { + "epoch": 0.61, + "learning_rate": 1.93613118274759e-05, + "loss": 0.12, + "step": 275030 + }, + { + "epoch": 0.61, + "learning_rate": 1.9360193284266573e-05, + "loss": 0.1237, + "step": 275040 + }, + { + "epoch": 0.61, + "learning_rate": 1.9359074741057248e-05, + "loss": 0.1178, + "step": 275050 + }, + { + "epoch": 0.61, + "learning_rate": 1.9357956197847923e-05, + "loss": 0.1185, + "step": 275060 + }, + { + "epoch": 0.61, + "learning_rate": 1.9356837654638597e-05, + "loss": 0.1138, + "step": 275070 + }, + { + "epoch": 0.61, + "learning_rate": 1.9355719111429275e-05, + "loss": 0.1145, + "step": 275080 + }, + { + "epoch": 0.61, + "learning_rate": 1.9354600568219953e-05, + "loss": 0.1183, + "step": 275090 + }, + { + "epoch": 0.61, + "learning_rate": 1.9353482025010627e-05, + "loss": 0.118, + "step": 275100 + }, + { + "epoch": 0.61, + "learning_rate": 1.9352363481801302e-05, + "loss": 0.1184, + "step": 275110 + }, + { + "epoch": 0.61, + "learning_rate": 1.9351244938591977e-05, + "loss": 0.1222, + "step": 275120 + }, + { + "epoch": 0.61, + "learning_rate": 1.9350126395382655e-05, + "loss": 0.1239, + "step": 275130 + }, + { + "epoch": 0.61, + "learning_rate": 1.9349007852173332e-05, + "loss": 0.1175, + "step": 275140 + }, + { + "epoch": 0.61, + "learning_rate": 1.9347889308964007e-05, + "loss": 0.1198, + "step": 275150 + }, + { + "epoch": 0.61, + "learning_rate": 1.934677076575468e-05, + "loss": 0.1191, + "step": 275160 + }, + { + "epoch": 0.61, + "learning_rate": 1.9345652222545356e-05, + "loss": 0.1233, + "step": 275170 + }, + { + "epoch": 0.61, + "learning_rate": 1.9344533679336034e-05, + "loss": 0.121, + "step": 275180 + }, + { + "epoch": 0.61, + "learning_rate": 1.9343415136126712e-05, + "loss": 0.118, + "step": 275190 + }, + { + "epoch": 0.61, + "learning_rate": 1.9342296592917386e-05, + "loss": 0.117, + "step": 275200 + }, + { + "epoch": 0.61, + "learning_rate": 1.934117804970806e-05, + "loss": 0.1179, + "step": 275210 + }, + { + "epoch": 0.61, + "learning_rate": 1.9340059506498736e-05, + "loss": 0.1193, + "step": 275220 + }, + { + "epoch": 0.61, + "learning_rate": 1.9338940963289413e-05, + "loss": 0.1182, + "step": 275230 + }, + { + "epoch": 0.61, + "learning_rate": 1.9337934274401022e-05, + "loss": 0.1169, + "step": 275240 + }, + { + "epoch": 0.61, + "learning_rate": 1.9336815731191697e-05, + "loss": 0.1214, + "step": 275250 + }, + { + "epoch": 0.61, + "learning_rate": 1.9335697187982375e-05, + "loss": 0.1193, + "step": 275260 + }, + { + "epoch": 0.61, + "learning_rate": 1.933457864477305e-05, + "loss": 0.1122, + "step": 275270 + }, + { + "epoch": 0.61, + "learning_rate": 1.9333460101563724e-05, + "loss": 0.119, + "step": 275280 + }, + { + "epoch": 0.61, + "learning_rate": 1.93323415583544e-05, + "loss": 0.1204, + "step": 275290 + }, + { + "epoch": 0.61, + "learning_rate": 1.9331223015145076e-05, + "loss": 0.1156, + "step": 275300 + }, + { + "epoch": 0.61, + "learning_rate": 1.933010447193575e-05, + "loss": 0.1179, + "step": 275310 + }, + { + "epoch": 0.61, + "learning_rate": 1.932898592872643e-05, + "loss": 0.1203, + "step": 275320 + }, + { + "epoch": 0.61, + "learning_rate": 1.9327867385517103e-05, + "loss": 0.1157, + "step": 275330 + }, + { + "epoch": 0.61, + "learning_rate": 1.9326748842307778e-05, + "loss": 0.1145, + "step": 275340 + }, + { + "epoch": 0.61, + "learning_rate": 1.9325630299098456e-05, + "loss": 0.1206, + "step": 275350 + }, + { + "epoch": 0.61, + "learning_rate": 1.932451175588913e-05, + "loss": 0.1187, + "step": 275360 + }, + { + "epoch": 0.61, + "learning_rate": 1.9323393212679808e-05, + "loss": 0.1187, + "step": 275370 + }, + { + "epoch": 0.61, + "learning_rate": 1.9322274669470483e-05, + "loss": 0.1154, + "step": 275380 + }, + { + "epoch": 0.61, + "learning_rate": 1.9321156126261157e-05, + "loss": 0.1137, + "step": 275390 + }, + { + "epoch": 0.61, + "learning_rate": 1.9320037583051835e-05, + "loss": 0.1175, + "step": 275400 + }, + { + "epoch": 0.61, + "learning_rate": 1.931891903984251e-05, + "loss": 0.1212, + "step": 275410 + }, + { + "epoch": 0.61, + "learning_rate": 1.9317800496633188e-05, + "loss": 0.1177, + "step": 275420 + }, + { + "epoch": 0.61, + "learning_rate": 1.9316681953423862e-05, + "loss": 0.116, + "step": 275430 + }, + { + "epoch": 0.61, + "learning_rate": 1.9315563410214537e-05, + "loss": 0.1167, + "step": 275440 + }, + { + "epoch": 0.61, + "learning_rate": 1.9314444867005215e-05, + "loss": 0.1205, + "step": 275450 + }, + { + "epoch": 0.61, + "learning_rate": 1.931332632379589e-05, + "loss": 0.119, + "step": 275460 + }, + { + "epoch": 0.61, + "learning_rate": 1.9312207780586564e-05, + "loss": 0.1157, + "step": 275470 + }, + { + "epoch": 0.61, + "learning_rate": 1.931108923737724e-05, + "loss": 0.1184, + "step": 275480 + }, + { + "epoch": 0.61, + "learning_rate": 1.9309970694167916e-05, + "loss": 0.1221, + "step": 275490 + }, + { + "epoch": 0.61, + "learning_rate": 1.930885215095859e-05, + "loss": 0.1167, + "step": 275500 + }, + { + "epoch": 0.61, + "learning_rate": 1.930773360774927e-05, + "loss": 0.1172, + "step": 275510 + }, + { + "epoch": 0.61, + "learning_rate": 1.9306615064539943e-05, + "loss": 0.1155, + "step": 275520 + }, + { + "epoch": 0.62, + "learning_rate": 1.930549652133062e-05, + "loss": 0.1178, + "step": 275530 + }, + { + "epoch": 0.62, + "learning_rate": 1.9304377978121296e-05, + "loss": 0.1184, + "step": 275540 + }, + { + "epoch": 0.62, + "learning_rate": 1.930325943491197e-05, + "loss": 0.118, + "step": 275550 + }, + { + "epoch": 0.62, + "learning_rate": 1.9302140891702648e-05, + "loss": 0.1211, + "step": 275560 + }, + { + "epoch": 0.62, + "learning_rate": 1.9301022348493323e-05, + "loss": 0.1245, + "step": 275570 + }, + { + "epoch": 0.62, + "learning_rate": 1.9299903805284e-05, + "loss": 0.1165, + "step": 275580 + }, + { + "epoch": 0.62, + "learning_rate": 1.9298785262074675e-05, + "loss": 0.1146, + "step": 275590 + }, + { + "epoch": 0.62, + "learning_rate": 1.929766671886535e-05, + "loss": 0.1169, + "step": 275600 + }, + { + "epoch": 0.62, + "learning_rate": 1.9296548175656028e-05, + "loss": 0.1183, + "step": 275610 + }, + { + "epoch": 0.62, + "learning_rate": 1.9295429632446702e-05, + "loss": 0.1181, + "step": 275620 + }, + { + "epoch": 0.62, + "learning_rate": 1.9294311089237377e-05, + "loss": 0.1174, + "step": 275630 + }, + { + "epoch": 0.62, + "learning_rate": 1.9293192546028055e-05, + "loss": 0.1168, + "step": 275640 + }, + { + "epoch": 0.62, + "learning_rate": 1.929207400281873e-05, + "loss": 0.1202, + "step": 275650 + }, + { + "epoch": 0.62, + "learning_rate": 1.9290955459609407e-05, + "loss": 0.1207, + "step": 275660 + }, + { + "epoch": 0.62, + "learning_rate": 1.928983691640008e-05, + "loss": 0.1194, + "step": 275670 + }, + { + "epoch": 0.62, + "learning_rate": 1.9288718373190756e-05, + "loss": 0.1174, + "step": 275680 + }, + { + "epoch": 0.62, + "learning_rate": 1.9287599829981434e-05, + "loss": 0.1159, + "step": 275690 + }, + { + "epoch": 0.62, + "learning_rate": 1.928648128677211e-05, + "loss": 0.1138, + "step": 275700 + }, + { + "epoch": 0.62, + "learning_rate": 1.9285362743562783e-05, + "loss": 0.1192, + "step": 275710 + }, + { + "epoch": 0.62, + "learning_rate": 1.928424420035346e-05, + "loss": 0.1204, + "step": 275720 + }, + { + "epoch": 0.62, + "learning_rate": 1.9283125657144136e-05, + "loss": 0.1161, + "step": 275730 + }, + { + "epoch": 0.62, + "learning_rate": 1.9282007113934814e-05, + "loss": 0.1145, + "step": 275740 + }, + { + "epoch": 0.62, + "learning_rate": 1.9280888570725488e-05, + "loss": 0.1173, + "step": 275750 + }, + { + "epoch": 0.62, + "learning_rate": 1.9279770027516163e-05, + "loss": 0.1149, + "step": 275760 + }, + { + "epoch": 0.62, + "learning_rate": 1.927865148430684e-05, + "loss": 0.1199, + "step": 275770 + }, + { + "epoch": 0.62, + "learning_rate": 1.9277532941097515e-05, + "loss": 0.1193, + "step": 275780 + }, + { + "epoch": 0.62, + "learning_rate": 1.927641439788819e-05, + "loss": 0.1198, + "step": 275790 + }, + { + "epoch": 0.62, + "learning_rate": 1.9275295854678868e-05, + "loss": 0.1156, + "step": 275800 + }, + { + "epoch": 0.62, + "learning_rate": 1.9274177311469542e-05, + "loss": 0.1218, + "step": 275810 + }, + { + "epoch": 0.62, + "learning_rate": 1.927305876826022e-05, + "loss": 0.1154, + "step": 275820 + }, + { + "epoch": 0.62, + "learning_rate": 1.9271940225050895e-05, + "loss": 0.1195, + "step": 275830 + }, + { + "epoch": 0.62, + "learning_rate": 1.927082168184157e-05, + "loss": 0.1177, + "step": 275840 + }, + { + "epoch": 0.62, + "learning_rate": 1.9269703138632247e-05, + "loss": 0.1128, + "step": 275850 + }, + { + "epoch": 0.62, + "learning_rate": 1.926858459542292e-05, + "loss": 0.1164, + "step": 275860 + }, + { + "epoch": 0.62, + "learning_rate": 1.92674660522136e-05, + "loss": 0.1202, + "step": 275870 + }, + { + "epoch": 0.62, + "learning_rate": 1.9266347509004274e-05, + "loss": 0.1204, + "step": 275880 + }, + { + "epoch": 0.62, + "learning_rate": 1.926522896579495e-05, + "loss": 0.1187, + "step": 275890 + }, + { + "epoch": 0.62, + "learning_rate": 1.9264110422585627e-05, + "loss": 0.1182, + "step": 275900 + }, + { + "epoch": 0.62, + "learning_rate": 1.92629918793763e-05, + "loss": 0.1154, + "step": 275910 + }, + { + "epoch": 0.62, + "learning_rate": 1.9261873336166976e-05, + "loss": 0.1153, + "step": 275920 + }, + { + "epoch": 0.62, + "learning_rate": 1.9260754792957654e-05, + "loss": 0.1149, + "step": 275930 + }, + { + "epoch": 0.62, + "learning_rate": 1.9259636249748328e-05, + "loss": 0.1155, + "step": 275940 + }, + { + "epoch": 0.62, + "learning_rate": 1.9258517706539003e-05, + "loss": 0.118, + "step": 275950 + }, + { + "epoch": 0.62, + "learning_rate": 1.925739916332968e-05, + "loss": 0.12, + "step": 275960 + }, + { + "epoch": 0.62, + "learning_rate": 1.9256280620120355e-05, + "loss": 0.1179, + "step": 275970 + }, + { + "epoch": 0.62, + "learning_rate": 1.9255162076911033e-05, + "loss": 0.1209, + "step": 275980 + }, + { + "epoch": 0.62, + "learning_rate": 1.9254043533701708e-05, + "loss": 0.1207, + "step": 275990 + }, + { + "epoch": 0.62, + "learning_rate": 1.9252924990492382e-05, + "loss": 0.1206, + "step": 276000 + }, + { + "epoch": 0.62, + "learning_rate": 1.925180644728306e-05, + "loss": 0.1234, + "step": 276010 + }, + { + "epoch": 0.62, + "learning_rate": 1.9250687904073735e-05, + "loss": 0.1196, + "step": 276020 + }, + { + "epoch": 0.62, + "learning_rate": 1.9249569360864413e-05, + "loss": 0.1178, + "step": 276030 + }, + { + "epoch": 0.62, + "learning_rate": 1.9248450817655087e-05, + "loss": 0.1209, + "step": 276040 + }, + { + "epoch": 0.62, + "learning_rate": 1.924733227444576e-05, + "loss": 0.118, + "step": 276050 + }, + { + "epoch": 0.62, + "learning_rate": 1.924621373123644e-05, + "loss": 0.1189, + "step": 276060 + }, + { + "epoch": 0.62, + "learning_rate": 1.9245095188027114e-05, + "loss": 0.1186, + "step": 276070 + }, + { + "epoch": 0.62, + "learning_rate": 1.9243976644817792e-05, + "loss": 0.1153, + "step": 276080 + }, + { + "epoch": 0.62, + "learning_rate": 1.9242858101608467e-05, + "loss": 0.1158, + "step": 276090 + }, + { + "epoch": 0.62, + "learning_rate": 1.924173955839914e-05, + "loss": 0.1158, + "step": 276100 + }, + { + "epoch": 0.62, + "learning_rate": 1.9240621015189816e-05, + "loss": 0.117, + "step": 276110 + }, + { + "epoch": 0.62, + "learning_rate": 1.9239502471980494e-05, + "loss": 0.1153, + "step": 276120 + }, + { + "epoch": 0.62, + "learning_rate": 1.923838392877117e-05, + "loss": 0.117, + "step": 276130 + }, + { + "epoch": 0.62, + "learning_rate": 1.9237265385561846e-05, + "loss": 0.115, + "step": 276140 + }, + { + "epoch": 0.62, + "learning_rate": 1.923614684235252e-05, + "loss": 0.1205, + "step": 276150 + }, + { + "epoch": 0.62, + "learning_rate": 1.9235028299143195e-05, + "loss": 0.1201, + "step": 276160 + }, + { + "epoch": 0.62, + "learning_rate": 1.9233909755933873e-05, + "loss": 0.117, + "step": 276170 + }, + { + "epoch": 0.62, + "learning_rate": 1.9232791212724548e-05, + "loss": 0.1186, + "step": 276180 + }, + { + "epoch": 0.62, + "learning_rate": 1.9231672669515225e-05, + "loss": 0.1205, + "step": 276190 + }, + { + "epoch": 0.62, + "learning_rate": 1.92305541263059e-05, + "loss": 0.122, + "step": 276200 + }, + { + "epoch": 0.62, + "learning_rate": 1.9229435583096575e-05, + "loss": 0.117, + "step": 276210 + }, + { + "epoch": 0.62, + "learning_rate": 1.9228317039887252e-05, + "loss": 0.1182, + "step": 276220 + }, + { + "epoch": 0.62, + "learning_rate": 1.9227198496677927e-05, + "loss": 0.1164, + "step": 276230 + }, + { + "epoch": 0.62, + "learning_rate": 1.9226079953468605e-05, + "loss": 0.1165, + "step": 276240 + }, + { + "epoch": 0.62, + "learning_rate": 1.922496141025928e-05, + "loss": 0.1175, + "step": 276250 + }, + { + "epoch": 0.62, + "learning_rate": 1.9223842867049954e-05, + "loss": 0.1178, + "step": 276260 + }, + { + "epoch": 0.62, + "learning_rate": 1.922272432384063e-05, + "loss": 0.1161, + "step": 276270 + }, + { + "epoch": 0.62, + "learning_rate": 1.9221605780631306e-05, + "loss": 0.1213, + "step": 276280 + }, + { + "epoch": 0.62, + "learning_rate": 1.9220487237421984e-05, + "loss": 0.1187, + "step": 276290 + }, + { + "epoch": 0.62, + "learning_rate": 1.921936869421266e-05, + "loss": 0.1174, + "step": 276300 + }, + { + "epoch": 0.62, + "learning_rate": 1.9218250151003333e-05, + "loss": 0.1182, + "step": 276310 + }, + { + "epoch": 0.62, + "learning_rate": 1.9217131607794008e-05, + "loss": 0.1204, + "step": 276320 + }, + { + "epoch": 0.62, + "learning_rate": 1.9216013064584686e-05, + "loss": 0.1184, + "step": 276330 + }, + { + "epoch": 0.62, + "learning_rate": 1.9214894521375364e-05, + "loss": 0.1154, + "step": 276340 + }, + { + "epoch": 0.62, + "learning_rate": 1.921377597816604e-05, + "loss": 0.1208, + "step": 276350 + }, + { + "epoch": 0.62, + "learning_rate": 1.9212657434956713e-05, + "loss": 0.1229, + "step": 276360 + }, + { + "epoch": 0.62, + "learning_rate": 1.9211538891747388e-05, + "loss": 0.121, + "step": 276370 + }, + { + "epoch": 0.62, + "learning_rate": 1.9210420348538065e-05, + "loss": 0.1162, + "step": 276380 + }, + { + "epoch": 0.62, + "learning_rate": 1.920930180532874e-05, + "loss": 0.1161, + "step": 276390 + }, + { + "epoch": 0.62, + "learning_rate": 1.9208183262119418e-05, + "loss": 0.1163, + "step": 276400 + }, + { + "epoch": 0.62, + "learning_rate": 1.9207064718910092e-05, + "loss": 0.1163, + "step": 276410 + }, + { + "epoch": 0.62, + "learning_rate": 1.9205946175700767e-05, + "loss": 0.1175, + "step": 276420 + }, + { + "epoch": 0.62, + "learning_rate": 1.920482763249144e-05, + "loss": 0.1135, + "step": 276430 + }, + { + "epoch": 0.62, + "learning_rate": 1.920370908928212e-05, + "loss": 0.1191, + "step": 276440 + }, + { + "epoch": 0.62, + "learning_rate": 1.9202590546072797e-05, + "loss": 0.1223, + "step": 276450 + }, + { + "epoch": 0.62, + "learning_rate": 1.9201472002863472e-05, + "loss": 0.1195, + "step": 276460 + }, + { + "epoch": 0.62, + "learning_rate": 1.9200353459654146e-05, + "loss": 0.1221, + "step": 276470 + }, + { + "epoch": 0.62, + "learning_rate": 1.919923491644482e-05, + "loss": 0.1109, + "step": 276480 + }, + { + "epoch": 0.62, + "learning_rate": 1.91981163732355e-05, + "loss": 0.1152, + "step": 276490 + }, + { + "epoch": 0.62, + "learning_rate": 1.9196997830026177e-05, + "loss": 0.1169, + "step": 276500 + }, + { + "epoch": 0.62, + "learning_rate": 1.919587928681685e-05, + "loss": 0.1222, + "step": 276510 + }, + { + "epoch": 0.62, + "learning_rate": 1.9194760743607526e-05, + "loss": 0.1212, + "step": 276520 + }, + { + "epoch": 0.62, + "learning_rate": 1.91936422003982e-05, + "loss": 0.1165, + "step": 276530 + }, + { + "epoch": 0.62, + "learning_rate": 1.919252365718888e-05, + "loss": 0.1187, + "step": 276540 + }, + { + "epoch": 0.62, + "learning_rate": 1.9191405113979556e-05, + "loss": 0.1218, + "step": 276550 + }, + { + "epoch": 0.62, + "learning_rate": 1.919028657077023e-05, + "loss": 0.1173, + "step": 276560 + }, + { + "epoch": 0.62, + "learning_rate": 1.9189168027560905e-05, + "loss": 0.1188, + "step": 276570 + }, + { + "epoch": 0.62, + "learning_rate": 1.918804948435158e-05, + "loss": 0.1206, + "step": 276580 + }, + { + "epoch": 0.62, + "learning_rate": 1.9186930941142254e-05, + "loss": 0.1151, + "step": 276590 + }, + { + "epoch": 0.62, + "learning_rate": 1.9185812397932932e-05, + "loss": 0.1144, + "step": 276600 + }, + { + "epoch": 0.62, + "learning_rate": 1.918469385472361e-05, + "loss": 0.1185, + "step": 276610 + }, + { + "epoch": 0.62, + "learning_rate": 1.9183575311514285e-05, + "loss": 0.1165, + "step": 276620 + }, + { + "epoch": 0.62, + "learning_rate": 1.918245676830496e-05, + "loss": 0.1176, + "step": 276630 + }, + { + "epoch": 0.62, + "learning_rate": 1.9181338225095634e-05, + "loss": 0.1228, + "step": 276640 + }, + { + "epoch": 0.62, + "learning_rate": 1.9180219681886312e-05, + "loss": 0.121, + "step": 276650 + }, + { + "epoch": 0.62, + "learning_rate": 1.917910113867699e-05, + "loss": 0.1159, + "step": 276660 + }, + { + "epoch": 0.62, + "learning_rate": 1.9177982595467664e-05, + "loss": 0.1135, + "step": 276670 + }, + { + "epoch": 0.62, + "learning_rate": 1.917686405225834e-05, + "loss": 0.118, + "step": 276680 + }, + { + "epoch": 0.62, + "learning_rate": 1.9175745509049013e-05, + "loss": 0.1187, + "step": 276690 + }, + { + "epoch": 0.62, + "learning_rate": 1.917462696583969e-05, + "loss": 0.1221, + "step": 276700 + }, + { + "epoch": 0.62, + "learning_rate": 1.917350842263037e-05, + "loss": 0.1193, + "step": 276710 + }, + { + "epoch": 0.62, + "learning_rate": 1.9172389879421044e-05, + "loss": 0.1213, + "step": 276720 + }, + { + "epoch": 0.62, + "learning_rate": 1.917127133621172e-05, + "loss": 0.1185, + "step": 276730 + }, + { + "epoch": 0.62, + "learning_rate": 1.9170152793002393e-05, + "loss": 0.1224, + "step": 276740 + }, + { + "epoch": 0.62, + "learning_rate": 1.916903424979307e-05, + "loss": 0.1154, + "step": 276750 + }, + { + "epoch": 0.62, + "learning_rate": 1.916791570658375e-05, + "loss": 0.12, + "step": 276760 + }, + { + "epoch": 0.62, + "learning_rate": 1.9166797163374423e-05, + "loss": 0.1127, + "step": 276770 + }, + { + "epoch": 0.62, + "learning_rate": 1.9165678620165098e-05, + "loss": 0.1175, + "step": 276780 + }, + { + "epoch": 0.62, + "learning_rate": 1.9164560076955772e-05, + "loss": 0.1194, + "step": 276790 + }, + { + "epoch": 0.62, + "learning_rate": 1.9163441533746447e-05, + "loss": 0.1153, + "step": 276800 + }, + { + "epoch": 0.62, + "learning_rate": 1.9162322990537128e-05, + "loss": 0.1204, + "step": 276810 + }, + { + "epoch": 0.62, + "learning_rate": 1.9161204447327803e-05, + "loss": 0.1152, + "step": 276820 + }, + { + "epoch": 0.62, + "learning_rate": 1.9160085904118477e-05, + "loss": 0.1125, + "step": 276830 + }, + { + "epoch": 0.62, + "learning_rate": 1.9158967360909152e-05, + "loss": 0.1177, + "step": 276840 + }, + { + "epoch": 0.62, + "learning_rate": 1.9157848817699826e-05, + "loss": 0.1188, + "step": 276850 + }, + { + "epoch": 0.62, + "learning_rate": 1.9156730274490504e-05, + "loss": 0.1145, + "step": 276860 + }, + { + "epoch": 0.62, + "learning_rate": 1.9155611731281182e-05, + "loss": 0.1131, + "step": 276870 + }, + { + "epoch": 0.62, + "learning_rate": 1.9154493188071857e-05, + "loss": 0.1163, + "step": 276880 + }, + { + "epoch": 0.62, + "learning_rate": 1.915337464486253e-05, + "loss": 0.1186, + "step": 276890 + }, + { + "epoch": 0.62, + "learning_rate": 1.9152256101653206e-05, + "loss": 0.1198, + "step": 276900 + }, + { + "epoch": 0.62, + "learning_rate": 1.9151137558443884e-05, + "loss": 0.1221, + "step": 276910 + }, + { + "epoch": 0.62, + "learning_rate": 1.9150019015234562e-05, + "loss": 0.1171, + "step": 276920 + }, + { + "epoch": 0.62, + "learning_rate": 1.9148900472025236e-05, + "loss": 0.1174, + "step": 276930 + }, + { + "epoch": 0.62, + "learning_rate": 1.914778192881591e-05, + "loss": 0.1179, + "step": 276940 + }, + { + "epoch": 0.62, + "learning_rate": 1.9146663385606585e-05, + "loss": 0.118, + "step": 276950 + }, + { + "epoch": 0.62, + "learning_rate": 1.9145544842397263e-05, + "loss": 0.1181, + "step": 276960 + }, + { + "epoch": 0.62, + "learning_rate": 1.914442629918794e-05, + "loss": 0.1143, + "step": 276970 + }, + { + "epoch": 0.62, + "learning_rate": 1.9143307755978616e-05, + "loss": 0.119, + "step": 276980 + }, + { + "epoch": 0.62, + "learning_rate": 1.914218921276929e-05, + "loss": 0.1202, + "step": 276990 + }, + { + "epoch": 0.62, + "learning_rate": 1.9141070669559965e-05, + "loss": 0.1143, + "step": 277000 + }, + { + "epoch": 0.62, + "learning_rate": 1.913995212635064e-05, + "loss": 0.116, + "step": 277010 + }, + { + "epoch": 0.62, + "learning_rate": 1.913883358314132e-05, + "loss": 0.1178, + "step": 277020 + }, + { + "epoch": 0.62, + "learning_rate": 1.9137715039931995e-05, + "loss": 0.1169, + "step": 277030 + }, + { + "epoch": 0.62, + "learning_rate": 1.913659649672267e-05, + "loss": 0.1154, + "step": 277040 + }, + { + "epoch": 0.62, + "learning_rate": 1.9135477953513344e-05, + "loss": 0.1167, + "step": 277050 + }, + { + "epoch": 0.62, + "learning_rate": 1.913435941030402e-05, + "loss": 0.1211, + "step": 277060 + }, + { + "epoch": 0.62, + "learning_rate": 1.9133240867094697e-05, + "loss": 0.1184, + "step": 277070 + }, + { + "epoch": 0.62, + "learning_rate": 1.9132122323885375e-05, + "loss": 0.1191, + "step": 277080 + }, + { + "epoch": 0.62, + "learning_rate": 1.913100378067605e-05, + "loss": 0.119, + "step": 277090 + }, + { + "epoch": 0.62, + "learning_rate": 1.9129885237466724e-05, + "loss": 0.1175, + "step": 277100 + }, + { + "epoch": 0.62, + "learning_rate": 1.9128766694257398e-05, + "loss": 0.1243, + "step": 277110 + }, + { + "epoch": 0.62, + "learning_rate": 1.9127648151048076e-05, + "loss": 0.1183, + "step": 277120 + }, + { + "epoch": 0.62, + "learning_rate": 1.9126529607838754e-05, + "loss": 0.1187, + "step": 277130 + }, + { + "epoch": 0.62, + "learning_rate": 1.912541106462943e-05, + "loss": 0.1129, + "step": 277140 + }, + { + "epoch": 0.62, + "learning_rate": 1.9124292521420103e-05, + "loss": 0.1156, + "step": 277150 + }, + { + "epoch": 0.62, + "learning_rate": 1.9123173978210778e-05, + "loss": 0.1194, + "step": 277160 + }, + { + "epoch": 0.62, + "learning_rate": 1.9122055435001456e-05, + "loss": 0.1158, + "step": 277170 + }, + { + "epoch": 0.62, + "learning_rate": 1.9120936891792134e-05, + "loss": 0.1177, + "step": 277180 + }, + { + "epoch": 0.62, + "learning_rate": 1.9119818348582808e-05, + "loss": 0.1192, + "step": 277190 + }, + { + "epoch": 0.62, + "learning_rate": 1.9118699805373483e-05, + "loss": 0.1191, + "step": 277200 + }, + { + "epoch": 0.62, + "learning_rate": 1.9117581262164157e-05, + "loss": 0.1165, + "step": 277210 + }, + { + "epoch": 0.62, + "learning_rate": 1.9116462718954832e-05, + "loss": 0.1151, + "step": 277220 + }, + { + "epoch": 0.62, + "learning_rate": 1.911534417574551e-05, + "loss": 0.117, + "step": 277230 + }, + { + "epoch": 0.62, + "learning_rate": 1.9114225632536188e-05, + "loss": 0.1201, + "step": 277240 + }, + { + "epoch": 0.62, + "learning_rate": 1.9113107089326862e-05, + "loss": 0.1202, + "step": 277250 + }, + { + "epoch": 0.62, + "learning_rate": 1.911210040043847e-05, + "loss": 0.1211, + "step": 277260 + }, + { + "epoch": 0.62, + "learning_rate": 1.9110981857229145e-05, + "loss": 0.1208, + "step": 277270 + }, + { + "epoch": 0.62, + "learning_rate": 1.910986331401982e-05, + "loss": 0.1173, + "step": 277280 + }, + { + "epoch": 0.62, + "learning_rate": 1.9108744770810498e-05, + "loss": 0.1233, + "step": 277290 + }, + { + "epoch": 0.62, + "learning_rate": 1.9107626227601173e-05, + "loss": 0.1196, + "step": 277300 + }, + { + "epoch": 0.62, + "learning_rate": 1.910650768439185e-05, + "loss": 0.1192, + "step": 277310 + }, + { + "epoch": 0.62, + "learning_rate": 1.9105389141182525e-05, + "loss": 0.1145, + "step": 277320 + }, + { + "epoch": 0.62, + "learning_rate": 1.91042705979732e-05, + "loss": 0.1173, + "step": 277330 + }, + { + "epoch": 0.62, + "learning_rate": 1.9103152054763877e-05, + "loss": 0.1205, + "step": 277340 + }, + { + "epoch": 0.62, + "learning_rate": 1.9102033511554552e-05, + "loss": 0.1189, + "step": 277350 + }, + { + "epoch": 0.62, + "learning_rate": 1.910091496834523e-05, + "loss": 0.1193, + "step": 277360 + }, + { + "epoch": 0.62, + "learning_rate": 1.9099796425135904e-05, + "loss": 0.1144, + "step": 277370 + }, + { + "epoch": 0.62, + "learning_rate": 1.909867788192658e-05, + "loss": 0.116, + "step": 277380 + }, + { + "epoch": 0.62, + "learning_rate": 1.9097559338717257e-05, + "loss": 0.1145, + "step": 277390 + }, + { + "epoch": 0.62, + "learning_rate": 1.909644079550793e-05, + "loss": 0.1193, + "step": 277400 + }, + { + "epoch": 0.62, + "learning_rate": 1.9095322252298606e-05, + "loss": 0.1217, + "step": 277410 + }, + { + "epoch": 0.62, + "learning_rate": 1.9094203709089284e-05, + "loss": 0.122, + "step": 277420 + }, + { + "epoch": 0.62, + "learning_rate": 1.909308516587996e-05, + "loss": 0.1197, + "step": 277430 + }, + { + "epoch": 0.62, + "learning_rate": 1.9091966622670633e-05, + "loss": 0.1188, + "step": 277440 + }, + { + "epoch": 0.62, + "learning_rate": 1.909084807946131e-05, + "loss": 0.1187, + "step": 277450 + }, + { + "epoch": 0.62, + "learning_rate": 1.9089729536251985e-05, + "loss": 0.118, + "step": 277460 + }, + { + "epoch": 0.62, + "learning_rate": 1.9088610993042663e-05, + "loss": 0.1217, + "step": 277470 + }, + { + "epoch": 0.62, + "learning_rate": 1.9087492449833338e-05, + "loss": 0.1167, + "step": 277480 + }, + { + "epoch": 0.62, + "learning_rate": 1.9086373906624012e-05, + "loss": 0.1163, + "step": 277490 + }, + { + "epoch": 0.62, + "learning_rate": 1.908525536341469e-05, + "loss": 0.1197, + "step": 277500 + }, + { + "epoch": 0.62, + "learning_rate": 1.9084136820205365e-05, + "loss": 0.1143, + "step": 277510 + }, + { + "epoch": 0.62, + "learning_rate": 1.9083018276996043e-05, + "loss": 0.1136, + "step": 277520 + }, + { + "epoch": 0.62, + "learning_rate": 1.9081899733786717e-05, + "loss": 0.1196, + "step": 277530 + }, + { + "epoch": 0.62, + "learning_rate": 1.9080781190577392e-05, + "loss": 0.1171, + "step": 277540 + }, + { + "epoch": 0.62, + "learning_rate": 1.907966264736807e-05, + "loss": 0.1204, + "step": 277550 + }, + { + "epoch": 0.62, + "learning_rate": 1.9078544104158744e-05, + "loss": 0.1186, + "step": 277560 + }, + { + "epoch": 0.62, + "learning_rate": 1.907742556094942e-05, + "loss": 0.1161, + "step": 277570 + }, + { + "epoch": 0.62, + "learning_rate": 1.9076307017740097e-05, + "loss": 0.1183, + "step": 277580 + }, + { + "epoch": 0.62, + "learning_rate": 1.907518847453077e-05, + "loss": 0.1187, + "step": 277590 + }, + { + "epoch": 0.62, + "learning_rate": 1.907406993132145e-05, + "loss": 0.1149, + "step": 277600 + }, + { + "epoch": 0.62, + "learning_rate": 1.9072951388112124e-05, + "loss": 0.1148, + "step": 277610 + }, + { + "epoch": 0.62, + "learning_rate": 1.90718328449028e-05, + "loss": 0.122, + "step": 277620 + }, + { + "epoch": 0.62, + "learning_rate": 1.9070714301693476e-05, + "loss": 0.1143, + "step": 277630 + }, + { + "epoch": 0.62, + "learning_rate": 1.906959575848415e-05, + "loss": 0.1212, + "step": 277640 + }, + { + "epoch": 0.62, + "learning_rate": 1.9068477215274825e-05, + "loss": 0.1224, + "step": 277650 + }, + { + "epoch": 0.62, + "learning_rate": 1.9067358672065503e-05, + "loss": 0.12, + "step": 277660 + }, + { + "epoch": 0.62, + "learning_rate": 1.9066240128856178e-05, + "loss": 0.1221, + "step": 277670 + }, + { + "epoch": 0.62, + "learning_rate": 1.9065121585646856e-05, + "loss": 0.1202, + "step": 277680 + }, + { + "epoch": 0.62, + "learning_rate": 1.906400304243753e-05, + "loss": 0.122, + "step": 277690 + }, + { + "epoch": 0.62, + "learning_rate": 1.9062884499228205e-05, + "loss": 0.1177, + "step": 277700 + }, + { + "epoch": 0.62, + "learning_rate": 1.9061765956018883e-05, + "loss": 0.1166, + "step": 277710 + }, + { + "epoch": 0.62, + "learning_rate": 1.9060647412809557e-05, + "loss": 0.1176, + "step": 277720 + }, + { + "epoch": 0.62, + "learning_rate": 1.9059528869600232e-05, + "loss": 0.117, + "step": 277730 + }, + { + "epoch": 0.62, + "learning_rate": 1.905841032639091e-05, + "loss": 0.115, + "step": 277740 + }, + { + "epoch": 0.62, + "learning_rate": 1.9057291783181584e-05, + "loss": 0.1205, + "step": 277750 + }, + { + "epoch": 0.62, + "learning_rate": 1.9056173239972262e-05, + "loss": 0.1178, + "step": 277760 + }, + { + "epoch": 0.62, + "learning_rate": 1.9055054696762937e-05, + "loss": 0.1145, + "step": 277770 + }, + { + "epoch": 0.62, + "learning_rate": 1.905393615355361e-05, + "loss": 0.1159, + "step": 277780 + }, + { + "epoch": 0.62, + "learning_rate": 1.905281761034429e-05, + "loss": 0.1186, + "step": 277790 + }, + { + "epoch": 0.62, + "learning_rate": 1.9051699067134964e-05, + "loss": 0.1133, + "step": 277800 + }, + { + "epoch": 0.62, + "learning_rate": 1.9050580523925642e-05, + "loss": 0.1206, + "step": 277810 + }, + { + "epoch": 0.62, + "learning_rate": 1.9049461980716316e-05, + "loss": 0.1123, + "step": 277820 + }, + { + "epoch": 0.62, + "learning_rate": 1.904834343750699e-05, + "loss": 0.1162, + "step": 277830 + }, + { + "epoch": 0.62, + "learning_rate": 1.904722489429767e-05, + "loss": 0.1164, + "step": 277840 + }, + { + "epoch": 0.62, + "learning_rate": 1.9046106351088343e-05, + "loss": 0.1173, + "step": 277850 + }, + { + "epoch": 0.62, + "learning_rate": 1.9044987807879018e-05, + "loss": 0.117, + "step": 277860 + }, + { + "epoch": 0.62, + "learning_rate": 1.9043869264669696e-05, + "loss": 0.12, + "step": 277870 + }, + { + "epoch": 0.62, + "learning_rate": 1.904275072146037e-05, + "loss": 0.1199, + "step": 277880 + }, + { + "epoch": 0.62, + "learning_rate": 1.9041632178251045e-05, + "loss": 0.1201, + "step": 277890 + }, + { + "epoch": 0.62, + "learning_rate": 1.9040513635041723e-05, + "loss": 0.1139, + "step": 277900 + }, + { + "epoch": 0.62, + "learning_rate": 1.9039395091832397e-05, + "loss": 0.1177, + "step": 277910 + }, + { + "epoch": 0.62, + "learning_rate": 1.9038276548623075e-05, + "loss": 0.1155, + "step": 277920 + }, + { + "epoch": 0.62, + "learning_rate": 1.903715800541375e-05, + "loss": 0.1205, + "step": 277930 + }, + { + "epoch": 0.62, + "learning_rate": 1.9036039462204424e-05, + "loss": 0.1191, + "step": 277940 + }, + { + "epoch": 0.62, + "learning_rate": 1.9034920918995102e-05, + "loss": 0.1138, + "step": 277950 + }, + { + "epoch": 0.62, + "learning_rate": 1.9033802375785777e-05, + "loss": 0.1209, + "step": 277960 + }, + { + "epoch": 0.62, + "learning_rate": 1.9032683832576455e-05, + "loss": 0.1192, + "step": 277970 + }, + { + "epoch": 0.62, + "learning_rate": 1.903156528936713e-05, + "loss": 0.1193, + "step": 277980 + }, + { + "epoch": 0.62, + "learning_rate": 1.9030446746157804e-05, + "loss": 0.1158, + "step": 277990 + }, + { + "epoch": 0.62, + "learning_rate": 1.9029328202948482e-05, + "loss": 0.1178, + "step": 278000 + }, + { + "epoch": 0.62, + "learning_rate": 1.9028209659739156e-05, + "loss": 0.1201, + "step": 278010 + }, + { + "epoch": 0.62, + "learning_rate": 1.9027091116529834e-05, + "loss": 0.1195, + "step": 278020 + }, + { + "epoch": 0.62, + "learning_rate": 1.902597257332051e-05, + "loss": 0.1194, + "step": 278030 + }, + { + "epoch": 0.62, + "learning_rate": 1.9024854030111183e-05, + "loss": 0.1233, + "step": 278040 + }, + { + "epoch": 0.62, + "learning_rate": 1.9023735486901858e-05, + "loss": 0.1165, + "step": 278050 + }, + { + "epoch": 0.62, + "learning_rate": 1.9022616943692536e-05, + "loss": 0.1204, + "step": 278060 + }, + { + "epoch": 0.62, + "learning_rate": 1.902149840048321e-05, + "loss": 0.1178, + "step": 278070 + }, + { + "epoch": 0.62, + "learning_rate": 1.9020379857273888e-05, + "loss": 0.1149, + "step": 278080 + }, + { + "epoch": 0.62, + "learning_rate": 1.9019261314064563e-05, + "loss": 0.1183, + "step": 278090 + }, + { + "epoch": 0.62, + "learning_rate": 1.9018142770855237e-05, + "loss": 0.1194, + "step": 278100 + }, + { + "epoch": 0.62, + "learning_rate": 1.9017024227645915e-05, + "loss": 0.117, + "step": 278110 + }, + { + "epoch": 0.62, + "learning_rate": 1.901590568443659e-05, + "loss": 0.1169, + "step": 278120 + }, + { + "epoch": 0.62, + "learning_rate": 1.9014787141227268e-05, + "loss": 0.1121, + "step": 278130 + }, + { + "epoch": 0.62, + "learning_rate": 1.9013668598017942e-05, + "loss": 0.1157, + "step": 278140 + }, + { + "epoch": 0.62, + "learning_rate": 1.9012550054808617e-05, + "loss": 0.1107, + "step": 278150 + }, + { + "epoch": 0.62, + "learning_rate": 1.9011431511599295e-05, + "loss": 0.1223, + "step": 278160 + }, + { + "epoch": 0.62, + "learning_rate": 1.901031296838997e-05, + "loss": 0.1196, + "step": 278170 + }, + { + "epoch": 0.62, + "learning_rate": 1.9009194425180647e-05, + "loss": 0.1138, + "step": 278180 + }, + { + "epoch": 0.62, + "learning_rate": 1.9008075881971322e-05, + "loss": 0.1173, + "step": 278190 + }, + { + "epoch": 0.62, + "learning_rate": 1.9006957338761996e-05, + "loss": 0.12, + "step": 278200 + }, + { + "epoch": 0.62, + "learning_rate": 1.900583879555267e-05, + "loss": 0.1194, + "step": 278210 + }, + { + "epoch": 0.62, + "learning_rate": 1.900472025234335e-05, + "loss": 0.1199, + "step": 278220 + }, + { + "epoch": 0.62, + "learning_rate": 1.9003601709134027e-05, + "loss": 0.1162, + "step": 278230 + }, + { + "epoch": 0.62, + "learning_rate": 1.90024831659247e-05, + "loss": 0.1222, + "step": 278240 + }, + { + "epoch": 0.62, + "learning_rate": 1.9001364622715376e-05, + "loss": 0.117, + "step": 278250 + }, + { + "epoch": 0.62, + "learning_rate": 1.900024607950605e-05, + "loss": 0.1182, + "step": 278260 + }, + { + "epoch": 0.62, + "learning_rate": 1.8999127536296728e-05, + "loss": 0.1155, + "step": 278270 + }, + { + "epoch": 0.62, + "learning_rate": 1.8998008993087406e-05, + "loss": 0.1122, + "step": 278280 + }, + { + "epoch": 0.62, + "learning_rate": 1.899689044987808e-05, + "loss": 0.1174, + "step": 278290 + }, + { + "epoch": 0.62, + "learning_rate": 1.8995771906668755e-05, + "loss": 0.1183, + "step": 278300 + }, + { + "epoch": 0.62, + "learning_rate": 1.899465336345943e-05, + "loss": 0.1206, + "step": 278310 + }, + { + "epoch": 0.62, + "learning_rate": 1.8993534820250108e-05, + "loss": 0.1168, + "step": 278320 + }, + { + "epoch": 0.62, + "learning_rate": 1.8992416277040782e-05, + "loss": 0.119, + "step": 278330 + }, + { + "epoch": 0.62, + "learning_rate": 1.899129773383146e-05, + "loss": 0.1185, + "step": 278340 + }, + { + "epoch": 0.62, + "learning_rate": 1.899029104494307e-05, + "loss": 0.1153, + "step": 278350 + }, + { + "epoch": 0.62, + "learning_rate": 1.8989172501733743e-05, + "loss": 0.1181, + "step": 278360 + }, + { + "epoch": 0.62, + "learning_rate": 1.8988053958524418e-05, + "loss": 0.1174, + "step": 278370 + }, + { + "epoch": 0.62, + "learning_rate": 1.8986935415315093e-05, + "loss": 0.115, + "step": 278380 + }, + { + "epoch": 0.62, + "learning_rate": 1.898581687210577e-05, + "loss": 0.1137, + "step": 278390 + }, + { + "epoch": 0.62, + "learning_rate": 1.898469832889645e-05, + "loss": 0.1177, + "step": 278400 + }, + { + "epoch": 0.62, + "learning_rate": 1.8983579785687123e-05, + "loss": 0.1134, + "step": 278410 + }, + { + "epoch": 0.62, + "learning_rate": 1.8982461242477797e-05, + "loss": 0.1211, + "step": 278420 + }, + { + "epoch": 0.62, + "learning_rate": 1.8981342699268472e-05, + "loss": 0.1165, + "step": 278430 + }, + { + "epoch": 0.62, + "learning_rate": 1.8980224156059147e-05, + "loss": 0.1212, + "step": 278440 + }, + { + "epoch": 0.62, + "learning_rate": 1.8979105612849828e-05, + "loss": 0.1191, + "step": 278450 + }, + { + "epoch": 0.62, + "learning_rate": 1.8977987069640502e-05, + "loss": 0.1181, + "step": 278460 + }, + { + "epoch": 0.62, + "learning_rate": 1.8976868526431177e-05, + "loss": 0.1183, + "step": 278470 + }, + { + "epoch": 0.62, + "learning_rate": 1.897574998322185e-05, + "loss": 0.1179, + "step": 278480 + }, + { + "epoch": 0.62, + "learning_rate": 1.8974631440012526e-05, + "loss": 0.1125, + "step": 278490 + }, + { + "epoch": 0.62, + "learning_rate": 1.8973512896803204e-05, + "loss": 0.1216, + "step": 278500 + }, + { + "epoch": 0.62, + "learning_rate": 1.8972394353593882e-05, + "loss": 0.1198, + "step": 278510 + }, + { + "epoch": 0.62, + "learning_rate": 1.8971275810384556e-05, + "loss": 0.1136, + "step": 278520 + }, + { + "epoch": 0.62, + "learning_rate": 1.897015726717523e-05, + "loss": 0.1195, + "step": 278530 + }, + { + "epoch": 0.62, + "learning_rate": 1.8969038723965906e-05, + "loss": 0.1185, + "step": 278540 + }, + { + "epoch": 0.62, + "learning_rate": 1.8967920180756583e-05, + "loss": 0.1221, + "step": 278550 + }, + { + "epoch": 0.62, + "learning_rate": 1.896680163754726e-05, + "loss": 0.1182, + "step": 278560 + }, + { + "epoch": 0.62, + "learning_rate": 1.8965683094337936e-05, + "loss": 0.1131, + "step": 278570 + }, + { + "epoch": 0.62, + "learning_rate": 1.896456455112861e-05, + "loss": 0.1182, + "step": 278580 + }, + { + "epoch": 0.62, + "learning_rate": 1.8963446007919285e-05, + "loss": 0.1117, + "step": 278590 + }, + { + "epoch": 0.62, + "learning_rate": 1.8962327464709963e-05, + "loss": 0.1205, + "step": 278600 + }, + { + "epoch": 0.62, + "learning_rate": 1.896120892150064e-05, + "loss": 0.1194, + "step": 278610 + }, + { + "epoch": 0.62, + "learning_rate": 1.8960090378291315e-05, + "loss": 0.117, + "step": 278620 + }, + { + "epoch": 0.62, + "learning_rate": 1.895897183508199e-05, + "loss": 0.1199, + "step": 278630 + }, + { + "epoch": 0.62, + "learning_rate": 1.8957853291872664e-05, + "loss": 0.1221, + "step": 278640 + }, + { + "epoch": 0.62, + "learning_rate": 1.895673474866334e-05, + "loss": 0.1186, + "step": 278650 + }, + { + "epoch": 0.62, + "learning_rate": 1.895561620545402e-05, + "loss": 0.1227, + "step": 278660 + }, + { + "epoch": 0.62, + "learning_rate": 1.8954497662244695e-05, + "loss": 0.114, + "step": 278670 + }, + { + "epoch": 0.62, + "learning_rate": 1.895337911903537e-05, + "loss": 0.1147, + "step": 278680 + }, + { + "epoch": 0.62, + "learning_rate": 1.8952260575826044e-05, + "loss": 0.1169, + "step": 278690 + }, + { + "epoch": 0.62, + "learning_rate": 1.895114203261672e-05, + "loss": 0.12, + "step": 278700 + }, + { + "epoch": 0.62, + "learning_rate": 1.8950023489407396e-05, + "loss": 0.1198, + "step": 278710 + }, + { + "epoch": 0.62, + "learning_rate": 1.8948904946198074e-05, + "loss": 0.1147, + "step": 278720 + }, + { + "epoch": 0.62, + "learning_rate": 1.894778640298875e-05, + "loss": 0.1198, + "step": 278730 + }, + { + "epoch": 0.62, + "learning_rate": 1.8946667859779423e-05, + "loss": 0.1194, + "step": 278740 + }, + { + "epoch": 0.62, + "learning_rate": 1.8945549316570098e-05, + "loss": 0.1241, + "step": 278750 + }, + { + "epoch": 0.62, + "learning_rate": 1.8944430773360776e-05, + "loss": 0.1169, + "step": 278760 + }, + { + "epoch": 0.62, + "learning_rate": 1.8943312230151454e-05, + "loss": 0.1162, + "step": 278770 + }, + { + "epoch": 0.62, + "learning_rate": 1.894219368694213e-05, + "loss": 0.1207, + "step": 278780 + }, + { + "epoch": 0.62, + "learning_rate": 1.8941075143732803e-05, + "loss": 0.1134, + "step": 278790 + }, + { + "epoch": 0.62, + "learning_rate": 1.8939956600523477e-05, + "loss": 0.1156, + "step": 278800 + }, + { + "epoch": 0.62, + "learning_rate": 1.8938838057314155e-05, + "loss": 0.1181, + "step": 278810 + }, + { + "epoch": 0.62, + "learning_rate": 1.8937719514104833e-05, + "loss": 0.1194, + "step": 278820 + }, + { + "epoch": 0.62, + "learning_rate": 1.8936600970895508e-05, + "loss": 0.1112, + "step": 278830 + }, + { + "epoch": 0.62, + "learning_rate": 1.8935482427686182e-05, + "loss": 0.116, + "step": 278840 + }, + { + "epoch": 0.62, + "learning_rate": 1.8934363884476857e-05, + "loss": 0.1182, + "step": 278850 + }, + { + "epoch": 0.62, + "learning_rate": 1.8933245341267535e-05, + "loss": 0.1185, + "step": 278860 + }, + { + "epoch": 0.62, + "learning_rate": 1.8932126798058213e-05, + "loss": 0.1196, + "step": 278870 + }, + { + "epoch": 0.62, + "learning_rate": 1.8931008254848887e-05, + "loss": 0.1211, + "step": 278880 + }, + { + "epoch": 0.62, + "learning_rate": 1.8929889711639562e-05, + "loss": 0.119, + "step": 278890 + }, + { + "epoch": 0.62, + "learning_rate": 1.8928771168430236e-05, + "loss": 0.1136, + "step": 278900 + }, + { + "epoch": 0.62, + "learning_rate": 1.892765262522091e-05, + "loss": 0.1154, + "step": 278910 + }, + { + "epoch": 0.62, + "learning_rate": 1.892653408201159e-05, + "loss": 0.116, + "step": 278920 + }, + { + "epoch": 0.62, + "learning_rate": 1.8925415538802267e-05, + "loss": 0.1149, + "step": 278930 + }, + { + "epoch": 0.62, + "learning_rate": 1.892429699559294e-05, + "loss": 0.1192, + "step": 278940 + }, + { + "epoch": 0.62, + "learning_rate": 1.8923178452383616e-05, + "loss": 0.1164, + "step": 278950 + }, + { + "epoch": 0.62, + "learning_rate": 1.892205990917429e-05, + "loss": 0.1203, + "step": 278960 + }, + { + "epoch": 0.62, + "learning_rate": 1.8920941365964968e-05, + "loss": 0.1157, + "step": 278970 + }, + { + "epoch": 0.62, + "learning_rate": 1.8919822822755646e-05, + "loss": 0.1157, + "step": 278980 + }, + { + "epoch": 0.62, + "learning_rate": 1.891870427954632e-05, + "loss": 0.1164, + "step": 278990 + }, + { + "epoch": 0.62, + "learning_rate": 1.8917585736336995e-05, + "loss": 0.1177, + "step": 279000 + }, + { + "epoch": 0.62, + "learning_rate": 1.891646719312767e-05, + "loss": 0.1201, + "step": 279010 + }, + { + "epoch": 0.62, + "learning_rate": 1.8915348649918348e-05, + "loss": 0.1145, + "step": 279020 + }, + { + "epoch": 0.62, + "learning_rate": 1.8914230106709026e-05, + "loss": 0.1174, + "step": 279030 + }, + { + "epoch": 0.62, + "learning_rate": 1.89131115634997e-05, + "loss": 0.1206, + "step": 279040 + }, + { + "epoch": 0.62, + "learning_rate": 1.8911993020290375e-05, + "loss": 0.1159, + "step": 279050 + }, + { + "epoch": 0.62, + "learning_rate": 1.891087447708105e-05, + "loss": 0.1177, + "step": 279060 + }, + { + "epoch": 0.62, + "learning_rate": 1.8909755933871727e-05, + "loss": 0.1171, + "step": 279070 + }, + { + "epoch": 0.62, + "learning_rate": 1.8908637390662402e-05, + "loss": 0.1181, + "step": 279080 + }, + { + "epoch": 0.62, + "learning_rate": 1.890751884745308e-05, + "loss": 0.118, + "step": 279090 + }, + { + "epoch": 0.62, + "learning_rate": 1.8906400304243754e-05, + "loss": 0.1183, + "step": 279100 + }, + { + "epoch": 0.62, + "learning_rate": 1.890528176103443e-05, + "loss": 0.1193, + "step": 279110 + }, + { + "epoch": 0.62, + "learning_rate": 1.8904163217825103e-05, + "loss": 0.1171, + "step": 279120 + }, + { + "epoch": 0.62, + "learning_rate": 1.890304467461578e-05, + "loss": 0.1159, + "step": 279130 + }, + { + "epoch": 0.62, + "learning_rate": 1.890192613140646e-05, + "loss": 0.1206, + "step": 279140 + }, + { + "epoch": 0.62, + "learning_rate": 1.8900807588197134e-05, + "loss": 0.1179, + "step": 279150 + }, + { + "epoch": 0.62, + "learning_rate": 1.8899689044987808e-05, + "loss": 0.1202, + "step": 279160 + }, + { + "epoch": 0.62, + "learning_rate": 1.8898570501778483e-05, + "loss": 0.1163, + "step": 279170 + }, + { + "epoch": 0.62, + "learning_rate": 1.889745195856916e-05, + "loss": 0.1142, + "step": 279180 + }, + { + "epoch": 0.62, + "learning_rate": 1.889633341535984e-05, + "loss": 0.1215, + "step": 279190 + }, + { + "epoch": 0.62, + "learning_rate": 1.8895214872150513e-05, + "loss": 0.1191, + "step": 279200 + }, + { + "epoch": 0.62, + "learning_rate": 1.8894096328941188e-05, + "loss": 0.1166, + "step": 279210 + }, + { + "epoch": 0.62, + "learning_rate": 1.8892977785731862e-05, + "loss": 0.1183, + "step": 279220 + }, + { + "epoch": 0.62, + "learning_rate": 1.889185924252254e-05, + "loss": 0.1173, + "step": 279230 + }, + { + "epoch": 0.62, + "learning_rate": 1.8890740699313215e-05, + "loss": 0.1163, + "step": 279240 + }, + { + "epoch": 0.62, + "learning_rate": 1.8889622156103893e-05, + "loss": 0.1194, + "step": 279250 + }, + { + "epoch": 0.62, + "learning_rate": 1.8888503612894567e-05, + "loss": 0.1202, + "step": 279260 + }, + { + "epoch": 0.62, + "learning_rate": 1.8887385069685242e-05, + "loss": 0.1173, + "step": 279270 + }, + { + "epoch": 0.62, + "learning_rate": 1.888626652647592e-05, + "loss": 0.1178, + "step": 279280 + }, + { + "epoch": 0.62, + "learning_rate": 1.8885147983266594e-05, + "loss": 0.1155, + "step": 279290 + }, + { + "epoch": 0.62, + "learning_rate": 1.8884029440057272e-05, + "loss": 0.1163, + "step": 279300 + }, + { + "epoch": 0.62, + "learning_rate": 1.8882910896847947e-05, + "loss": 0.1224, + "step": 279310 + }, + { + "epoch": 0.62, + "learning_rate": 1.888179235363862e-05, + "loss": 0.1117, + "step": 279320 + }, + { + "epoch": 0.62, + "learning_rate": 1.8880673810429296e-05, + "loss": 0.1189, + "step": 279330 + }, + { + "epoch": 0.62, + "learning_rate": 1.8879555267219974e-05, + "loss": 0.1151, + "step": 279340 + }, + { + "epoch": 0.62, + "learning_rate": 1.887843672401065e-05, + "loss": 0.1176, + "step": 279350 + }, + { + "epoch": 0.62, + "learning_rate": 1.8877318180801326e-05, + "loss": 0.1191, + "step": 279360 + }, + { + "epoch": 0.62, + "learning_rate": 1.8876199637592e-05, + "loss": 0.1207, + "step": 279370 + }, + { + "epoch": 0.62, + "learning_rate": 1.8875081094382675e-05, + "loss": 0.1185, + "step": 279380 + }, + { + "epoch": 0.62, + "learning_rate": 1.8873962551173353e-05, + "loss": 0.1195, + "step": 279390 + }, + { + "epoch": 0.62, + "learning_rate": 1.8872844007964028e-05, + "loss": 0.1156, + "step": 279400 + }, + { + "epoch": 0.62, + "learning_rate": 1.8871725464754706e-05, + "loss": 0.1165, + "step": 279410 + }, + { + "epoch": 0.62, + "learning_rate": 1.887060692154538e-05, + "loss": 0.1208, + "step": 279420 + }, + { + "epoch": 0.62, + "learning_rate": 1.8869488378336055e-05, + "loss": 0.1186, + "step": 279430 + }, + { + "epoch": 0.62, + "learning_rate": 1.8868369835126733e-05, + "loss": 0.1174, + "step": 279440 + }, + { + "epoch": 0.62, + "learning_rate": 1.8867251291917407e-05, + "loss": 0.1167, + "step": 279450 + }, + { + "epoch": 0.62, + "learning_rate": 1.8866132748708085e-05, + "loss": 0.1166, + "step": 279460 + }, + { + "epoch": 0.62, + "learning_rate": 1.886501420549876e-05, + "loss": 0.1162, + "step": 279470 + }, + { + "epoch": 0.62, + "learning_rate": 1.8863895662289434e-05, + "loss": 0.1165, + "step": 279480 + }, + { + "epoch": 0.62, + "learning_rate": 1.8862777119080112e-05, + "loss": 0.1191, + "step": 279490 + }, + { + "epoch": 0.62, + "learning_rate": 1.8861658575870787e-05, + "loss": 0.1169, + "step": 279500 + }, + { + "epoch": 0.62, + "learning_rate": 1.8860540032661465e-05, + "loss": 0.1138, + "step": 279510 + }, + { + "epoch": 0.62, + "learning_rate": 1.885942148945214e-05, + "loss": 0.1167, + "step": 279520 + }, + { + "epoch": 0.62, + "learning_rate": 1.8858302946242814e-05, + "loss": 0.1161, + "step": 279530 + }, + { + "epoch": 0.62, + "learning_rate": 1.8857184403033488e-05, + "loss": 0.1171, + "step": 279540 + }, + { + "epoch": 0.62, + "learning_rate": 1.8856065859824166e-05, + "loss": 0.1173, + "step": 279550 + }, + { + "epoch": 0.62, + "learning_rate": 1.885494731661484e-05, + "loss": 0.1209, + "step": 279560 + }, + { + "epoch": 0.62, + "learning_rate": 1.885382877340552e-05, + "loss": 0.1164, + "step": 279570 + }, + { + "epoch": 0.62, + "learning_rate": 1.8852710230196193e-05, + "loss": 0.124, + "step": 279580 + }, + { + "epoch": 0.62, + "learning_rate": 1.8851591686986868e-05, + "loss": 0.1175, + "step": 279590 + }, + { + "epoch": 0.62, + "learning_rate": 1.8850473143777546e-05, + "loss": 0.1187, + "step": 279600 + }, + { + "epoch": 0.62, + "learning_rate": 1.884935460056822e-05, + "loss": 0.1165, + "step": 279610 + }, + { + "epoch": 0.62, + "learning_rate": 1.8848236057358898e-05, + "loss": 0.1133, + "step": 279620 + }, + { + "epoch": 0.62, + "learning_rate": 1.8847117514149573e-05, + "loss": 0.1195, + "step": 279630 + }, + { + "epoch": 0.62, + "learning_rate": 1.8845998970940247e-05, + "loss": 0.1155, + "step": 279640 + }, + { + "epoch": 0.62, + "learning_rate": 1.8844880427730925e-05, + "loss": 0.121, + "step": 279650 + }, + { + "epoch": 0.62, + "learning_rate": 1.88437618845216e-05, + "loss": 0.1143, + "step": 279660 + }, + { + "epoch": 0.62, + "learning_rate": 1.8842643341312278e-05, + "loss": 0.1169, + "step": 279670 + }, + { + "epoch": 0.62, + "learning_rate": 1.8841524798102952e-05, + "loss": 0.1193, + "step": 279680 + }, + { + "epoch": 0.62, + "learning_rate": 1.8840406254893627e-05, + "loss": 0.123, + "step": 279690 + }, + { + "epoch": 0.62, + "learning_rate": 1.8839287711684305e-05, + "loss": 0.1198, + "step": 279700 + }, + { + "epoch": 0.62, + "learning_rate": 1.883816916847498e-05, + "loss": 0.1205, + "step": 279710 + }, + { + "epoch": 0.62, + "learning_rate": 1.8837050625265654e-05, + "loss": 0.1177, + "step": 279720 + }, + { + "epoch": 0.62, + "learning_rate": 1.883593208205633e-05, + "loss": 0.1205, + "step": 279730 + }, + { + "epoch": 0.62, + "learning_rate": 1.8834813538847006e-05, + "loss": 0.1153, + "step": 279740 + }, + { + "epoch": 0.62, + "learning_rate": 1.8833694995637684e-05, + "loss": 0.1202, + "step": 279750 + }, + { + "epoch": 0.62, + "learning_rate": 1.883257645242836e-05, + "loss": 0.1157, + "step": 279760 + }, + { + "epoch": 0.62, + "learning_rate": 1.8831457909219033e-05, + "loss": 0.1174, + "step": 279770 + }, + { + "epoch": 0.62, + "learning_rate": 1.883033936600971e-05, + "loss": 0.1154, + "step": 279780 + }, + { + "epoch": 0.62, + "learning_rate": 1.8829220822800386e-05, + "loss": 0.1177, + "step": 279790 + }, + { + "epoch": 0.62, + "learning_rate": 1.882810227959106e-05, + "loss": 0.1197, + "step": 279800 + }, + { + "epoch": 0.62, + "learning_rate": 1.8826983736381738e-05, + "loss": 0.1155, + "step": 279810 + }, + { + "epoch": 0.62, + "learning_rate": 1.8825865193172413e-05, + "loss": 0.1152, + "step": 279820 + }, + { + "epoch": 0.62, + "learning_rate": 1.882474664996309e-05, + "loss": 0.1164, + "step": 279830 + }, + { + "epoch": 0.62, + "learning_rate": 1.8823628106753765e-05, + "loss": 0.1229, + "step": 279840 + }, + { + "epoch": 0.62, + "learning_rate": 1.882250956354444e-05, + "loss": 0.1212, + "step": 279850 + }, + { + "epoch": 0.62, + "learning_rate": 1.8821391020335118e-05, + "loss": 0.1199, + "step": 279860 + }, + { + "epoch": 0.62, + "learning_rate": 1.8820272477125792e-05, + "loss": 0.1198, + "step": 279870 + }, + { + "epoch": 0.62, + "learning_rate": 1.8819153933916467e-05, + "loss": 0.1144, + "step": 279880 + }, + { + "epoch": 0.62, + "learning_rate": 1.8818035390707145e-05, + "loss": 0.1154, + "step": 279890 + }, + { + "epoch": 0.62, + "learning_rate": 1.881691684749782e-05, + "loss": 0.1168, + "step": 279900 + }, + { + "epoch": 0.62, + "learning_rate": 1.8815798304288497e-05, + "loss": 0.1163, + "step": 279910 + }, + { + "epoch": 0.62, + "learning_rate": 1.881467976107917e-05, + "loss": 0.1142, + "step": 279920 + }, + { + "epoch": 0.62, + "learning_rate": 1.8813561217869846e-05, + "loss": 0.1183, + "step": 279930 + }, + { + "epoch": 0.62, + "learning_rate": 1.8812442674660524e-05, + "loss": 0.115, + "step": 279940 + }, + { + "epoch": 0.62, + "learning_rate": 1.88113241314512e-05, + "loss": 0.1174, + "step": 279950 + }, + { + "epoch": 0.62, + "learning_rate": 1.8810205588241876e-05, + "loss": 0.1209, + "step": 279960 + }, + { + "epoch": 0.62, + "learning_rate": 1.880908704503255e-05, + "loss": 0.1165, + "step": 279970 + }, + { + "epoch": 0.62, + "learning_rate": 1.8807968501823226e-05, + "loss": 0.1156, + "step": 279980 + }, + { + "epoch": 0.62, + "learning_rate": 1.8806849958613903e-05, + "loss": 0.1182, + "step": 279990 + }, + { + "epoch": 0.62, + "learning_rate": 1.8805731415404578e-05, + "loss": 0.1168, + "step": 280000 + }, + { + "epoch": 0.63, + "learning_rate": 1.8804612872195253e-05, + "loss": 0.1169, + "step": 280010 + }, + { + "epoch": 0.63, + "learning_rate": 1.880349432898593e-05, + "loss": 0.1197, + "step": 280020 + }, + { + "epoch": 0.63, + "learning_rate": 1.8802375785776605e-05, + "loss": 0.1166, + "step": 280030 + }, + { + "epoch": 0.63, + "learning_rate": 1.880125724256728e-05, + "loss": 0.1173, + "step": 280040 + }, + { + "epoch": 0.63, + "learning_rate": 1.8800138699357957e-05, + "loss": 0.1167, + "step": 280050 + }, + { + "epoch": 0.63, + "learning_rate": 1.8799020156148632e-05, + "loss": 0.1165, + "step": 280060 + }, + { + "epoch": 0.63, + "learning_rate": 1.879790161293931e-05, + "loss": 0.12, + "step": 280070 + }, + { + "epoch": 0.63, + "learning_rate": 1.8796783069729984e-05, + "loss": 0.1211, + "step": 280080 + }, + { + "epoch": 0.63, + "learning_rate": 1.879566452652066e-05, + "loss": 0.1181, + "step": 280090 + }, + { + "epoch": 0.63, + "learning_rate": 1.8794545983311337e-05, + "loss": 0.1115, + "step": 280100 + }, + { + "epoch": 0.63, + "learning_rate": 1.879342744010201e-05, + "loss": 0.1202, + "step": 280110 + }, + { + "epoch": 0.63, + "learning_rate": 1.879230889689269e-05, + "loss": 0.1175, + "step": 280120 + }, + { + "epoch": 0.63, + "learning_rate": 1.8791190353683364e-05, + "loss": 0.1181, + "step": 280130 + }, + { + "epoch": 0.63, + "learning_rate": 1.879007181047404e-05, + "loss": 0.113, + "step": 280140 + }, + { + "epoch": 0.63, + "learning_rate": 1.8788953267264716e-05, + "loss": 0.1204, + "step": 280150 + }, + { + "epoch": 0.63, + "learning_rate": 1.878783472405539e-05, + "loss": 0.115, + "step": 280160 + }, + { + "epoch": 0.63, + "learning_rate": 1.878671618084607e-05, + "loss": 0.1166, + "step": 280170 + }, + { + "epoch": 0.63, + "learning_rate": 1.8785597637636743e-05, + "loss": 0.1144, + "step": 280180 + }, + { + "epoch": 0.63, + "learning_rate": 1.8784479094427418e-05, + "loss": 0.1125, + "step": 280190 + }, + { + "epoch": 0.63, + "learning_rate": 1.8783360551218093e-05, + "loss": 0.1195, + "step": 280200 + }, + { + "epoch": 0.63, + "learning_rate": 1.878224200800877e-05, + "loss": 0.1142, + "step": 280210 + }, + { + "epoch": 0.63, + "learning_rate": 1.8781123464799445e-05, + "loss": 0.1204, + "step": 280220 + }, + { + "epoch": 0.63, + "learning_rate": 1.8780004921590123e-05, + "loss": 0.1171, + "step": 280230 + }, + { + "epoch": 0.63, + "learning_rate": 1.8778886378380797e-05, + "loss": 0.1147, + "step": 280240 + }, + { + "epoch": 0.63, + "learning_rate": 1.8777767835171472e-05, + "loss": 0.1196, + "step": 280250 + }, + { + "epoch": 0.63, + "learning_rate": 1.877664929196215e-05, + "loss": 0.1199, + "step": 280260 + }, + { + "epoch": 0.63, + "learning_rate": 1.8775530748752824e-05, + "loss": 0.1203, + "step": 280270 + }, + { + "epoch": 0.63, + "learning_rate": 1.8774412205543502e-05, + "loss": 0.1178, + "step": 280280 + }, + { + "epoch": 0.63, + "learning_rate": 1.8773293662334177e-05, + "loss": 0.1168, + "step": 280290 + }, + { + "epoch": 0.63, + "learning_rate": 1.877217511912485e-05, + "loss": 0.1202, + "step": 280300 + }, + { + "epoch": 0.63, + "learning_rate": 1.8771056575915526e-05, + "loss": 0.1123, + "step": 280310 + }, + { + "epoch": 0.63, + "learning_rate": 1.8769938032706204e-05, + "loss": 0.1216, + "step": 280320 + }, + { + "epoch": 0.63, + "learning_rate": 1.8768819489496882e-05, + "loss": 0.1173, + "step": 280330 + }, + { + "epoch": 0.63, + "learning_rate": 1.8767700946287556e-05, + "loss": 0.119, + "step": 280340 + }, + { + "epoch": 0.63, + "learning_rate": 1.876658240307823e-05, + "loss": 0.1162, + "step": 280350 + }, + { + "epoch": 0.63, + "learning_rate": 1.8765463859868905e-05, + "loss": 0.1191, + "step": 280360 + }, + { + "epoch": 0.63, + "learning_rate": 1.8764345316659583e-05, + "loss": 0.1214, + "step": 280370 + }, + { + "epoch": 0.63, + "learning_rate": 1.876322677345026e-05, + "loss": 0.1179, + "step": 280380 + }, + { + "epoch": 0.63, + "learning_rate": 1.8762108230240936e-05, + "loss": 0.1173, + "step": 280390 + }, + { + "epoch": 0.63, + "learning_rate": 1.876098968703161e-05, + "loss": 0.1229, + "step": 280400 + }, + { + "epoch": 0.63, + "learning_rate": 1.8759871143822285e-05, + "loss": 0.1154, + "step": 280410 + }, + { + "epoch": 0.63, + "learning_rate": 1.8758752600612963e-05, + "loss": 0.1217, + "step": 280420 + }, + { + "epoch": 0.63, + "learning_rate": 1.8757634057403637e-05, + "loss": 0.1145, + "step": 280430 + }, + { + "epoch": 0.63, + "learning_rate": 1.8756515514194315e-05, + "loss": 0.1159, + "step": 280440 + }, + { + "epoch": 0.63, + "learning_rate": 1.875539697098499e-05, + "loss": 0.1225, + "step": 280450 + }, + { + "epoch": 0.63, + "learning_rate": 1.8754278427775664e-05, + "loss": 0.1175, + "step": 280460 + }, + { + "epoch": 0.63, + "learning_rate": 1.875315988456634e-05, + "loss": 0.1204, + "step": 280470 + }, + { + "epoch": 0.63, + "learning_rate": 1.8752041341357017e-05, + "loss": 0.1209, + "step": 280480 + }, + { + "epoch": 0.63, + "learning_rate": 1.8750922798147695e-05, + "loss": 0.1201, + "step": 280490 + }, + { + "epoch": 0.63, + "learning_rate": 1.874980425493837e-05, + "loss": 0.117, + "step": 280500 + }, + { + "epoch": 0.63, + "learning_rate": 1.8748685711729044e-05, + "loss": 0.1183, + "step": 280510 + }, + { + "epoch": 0.63, + "learning_rate": 1.874756716851972e-05, + "loss": 0.1172, + "step": 280520 + }, + { + "epoch": 0.63, + "learning_rate": 1.8746448625310396e-05, + "loss": 0.1194, + "step": 280530 + }, + { + "epoch": 0.63, + "learning_rate": 1.8745330082101074e-05, + "loss": 0.1154, + "step": 280540 + }, + { + "epoch": 0.63, + "learning_rate": 1.874421153889175e-05, + "loss": 0.1218, + "step": 280550 + }, + { + "epoch": 0.63, + "learning_rate": 1.8743092995682423e-05, + "loss": 0.1133, + "step": 280560 + }, + { + "epoch": 0.63, + "learning_rate": 1.8741974452473098e-05, + "loss": 0.1193, + "step": 280570 + }, + { + "epoch": 0.63, + "learning_rate": 1.8740855909263776e-05, + "loss": 0.1171, + "step": 280580 + }, + { + "epoch": 0.63, + "learning_rate": 1.8739737366054454e-05, + "loss": 0.1155, + "step": 280590 + }, + { + "epoch": 0.63, + "learning_rate": 1.873861882284513e-05, + "loss": 0.119, + "step": 280600 + }, + { + "epoch": 0.63, + "learning_rate": 1.8737500279635803e-05, + "loss": 0.1163, + "step": 280610 + }, + { + "epoch": 0.63, + "learning_rate": 1.8736381736426477e-05, + "loss": 0.1119, + "step": 280620 + }, + { + "epoch": 0.63, + "learning_rate": 1.8735263193217152e-05, + "loss": 0.1154, + "step": 280630 + }, + { + "epoch": 0.63, + "learning_rate": 1.8734144650007833e-05, + "loss": 0.1199, + "step": 280640 + }, + { + "epoch": 0.63, + "learning_rate": 1.8733026106798508e-05, + "loss": 0.1183, + "step": 280650 + }, + { + "epoch": 0.63, + "learning_rate": 1.8731907563589182e-05, + "loss": 0.1168, + "step": 280660 + }, + { + "epoch": 0.63, + "learning_rate": 1.8730789020379857e-05, + "loss": 0.114, + "step": 280670 + }, + { + "epoch": 0.63, + "learning_rate": 1.872967047717053e-05, + "loss": 0.1159, + "step": 280680 + }, + { + "epoch": 0.63, + "learning_rate": 1.872855193396121e-05, + "loss": 0.1157, + "step": 280690 + }, + { + "epoch": 0.63, + "learning_rate": 1.8727433390751887e-05, + "loss": 0.1152, + "step": 280700 + }, + { + "epoch": 0.63, + "learning_rate": 1.8726314847542562e-05, + "loss": 0.1128, + "step": 280710 + }, + { + "epoch": 0.63, + "learning_rate": 1.8725196304333236e-05, + "loss": 0.1163, + "step": 280720 + }, + { + "epoch": 0.63, + "learning_rate": 1.872407776112391e-05, + "loss": 0.114, + "step": 280730 + }, + { + "epoch": 0.63, + "learning_rate": 1.872295921791459e-05, + "loss": 0.1179, + "step": 280740 + }, + { + "epoch": 0.63, + "learning_rate": 1.8721840674705267e-05, + "loss": 0.1176, + "step": 280750 + }, + { + "epoch": 0.63, + "learning_rate": 1.872072213149594e-05, + "loss": 0.1172, + "step": 280760 + }, + { + "epoch": 0.63, + "learning_rate": 1.8719603588286616e-05, + "loss": 0.1157, + "step": 280770 + }, + { + "epoch": 0.63, + "learning_rate": 1.871848504507729e-05, + "loss": 0.117, + "step": 280780 + }, + { + "epoch": 0.63, + "learning_rate": 1.8717366501867968e-05, + "loss": 0.118, + "step": 280790 + }, + { + "epoch": 0.63, + "learning_rate": 1.8716247958658646e-05, + "loss": 0.1134, + "step": 280800 + }, + { + "epoch": 0.63, + "learning_rate": 1.871512941544932e-05, + "loss": 0.1168, + "step": 280810 + }, + { + "epoch": 0.63, + "learning_rate": 1.8714010872239995e-05, + "loss": 0.1135, + "step": 280820 + }, + { + "epoch": 0.63, + "learning_rate": 1.871289232903067e-05, + "loss": 0.1182, + "step": 280830 + }, + { + "epoch": 0.63, + "learning_rate": 1.8711773785821344e-05, + "loss": 0.1175, + "step": 280840 + }, + { + "epoch": 0.63, + "learning_rate": 1.8710655242612026e-05, + "loss": 0.1169, + "step": 280850 + }, + { + "epoch": 0.63, + "learning_rate": 1.87095366994027e-05, + "loss": 0.1202, + "step": 280860 + }, + { + "epoch": 0.63, + "learning_rate": 1.8708418156193375e-05, + "loss": 0.1174, + "step": 280870 + }, + { + "epoch": 0.63, + "learning_rate": 1.870729961298405e-05, + "loss": 0.1201, + "step": 280880 + }, + { + "epoch": 0.63, + "learning_rate": 1.8706181069774724e-05, + "loss": 0.1192, + "step": 280890 + }, + { + "epoch": 0.63, + "learning_rate": 1.8705062526565402e-05, + "loss": 0.1163, + "step": 280900 + }, + { + "epoch": 0.63, + "learning_rate": 1.870394398335608e-05, + "loss": 0.1168, + "step": 280910 + }, + { + "epoch": 0.63, + "learning_rate": 1.8702825440146754e-05, + "loss": 0.1203, + "step": 280920 + }, + { + "epoch": 0.63, + "learning_rate": 1.870170689693743e-05, + "loss": 0.1154, + "step": 280930 + }, + { + "epoch": 0.63, + "learning_rate": 1.8700588353728103e-05, + "loss": 0.1164, + "step": 280940 + }, + { + "epoch": 0.63, + "learning_rate": 1.869946981051878e-05, + "loss": 0.1198, + "step": 280950 + }, + { + "epoch": 0.63, + "learning_rate": 1.869835126730946e-05, + "loss": 0.1201, + "step": 280960 + }, + { + "epoch": 0.63, + "learning_rate": 1.8697232724100134e-05, + "loss": 0.1223, + "step": 280970 + }, + { + "epoch": 0.63, + "learning_rate": 1.8696114180890808e-05, + "loss": 0.1145, + "step": 280980 + }, + { + "epoch": 0.63, + "learning_rate": 1.8694995637681483e-05, + "loss": 0.117, + "step": 280990 + }, + { + "epoch": 0.63, + "learning_rate": 1.869387709447216e-05, + "loss": 0.1195, + "step": 281000 + }, + { + "epoch": 0.63, + "learning_rate": 1.869275855126284e-05, + "loss": 0.1136, + "step": 281010 + }, + { + "epoch": 0.63, + "learning_rate": 1.8691640008053513e-05, + "loss": 0.1184, + "step": 281020 + }, + { + "epoch": 0.63, + "learning_rate": 1.8690521464844188e-05, + "loss": 0.1157, + "step": 281030 + }, + { + "epoch": 0.63, + "learning_rate": 1.8689402921634862e-05, + "loss": 0.1179, + "step": 281040 + }, + { + "epoch": 0.63, + "learning_rate": 1.8688284378425537e-05, + "loss": 0.1185, + "step": 281050 + }, + { + "epoch": 0.63, + "learning_rate": 1.8687165835216218e-05, + "loss": 0.119, + "step": 281060 + }, + { + "epoch": 0.63, + "learning_rate": 1.8686047292006893e-05, + "loss": 0.1179, + "step": 281070 + }, + { + "epoch": 0.63, + "learning_rate": 1.8684928748797567e-05, + "loss": 0.1182, + "step": 281080 + }, + { + "epoch": 0.63, + "learning_rate": 1.8683810205588242e-05, + "loss": 0.1158, + "step": 281090 + }, + { + "epoch": 0.63, + "learning_rate": 1.8682691662378916e-05, + "loss": 0.1161, + "step": 281100 + }, + { + "epoch": 0.63, + "learning_rate": 1.8681573119169594e-05, + "loss": 0.1144, + "step": 281110 + }, + { + "epoch": 0.63, + "learning_rate": 1.8680454575960272e-05, + "loss": 0.1205, + "step": 281120 + }, + { + "epoch": 0.63, + "learning_rate": 1.8679336032750947e-05, + "loss": 0.1154, + "step": 281130 + }, + { + "epoch": 0.63, + "learning_rate": 1.867821748954162e-05, + "loss": 0.1151, + "step": 281140 + }, + { + "epoch": 0.63, + "learning_rate": 1.8677098946332296e-05, + "loss": 0.1131, + "step": 281150 + }, + { + "epoch": 0.63, + "learning_rate": 1.8675980403122974e-05, + "loss": 0.1171, + "step": 281160 + }, + { + "epoch": 0.63, + "learning_rate": 1.867486185991365e-05, + "loss": 0.1187, + "step": 281170 + }, + { + "epoch": 0.63, + "learning_rate": 1.8673743316704326e-05, + "loss": 0.1137, + "step": 281180 + }, + { + "epoch": 0.63, + "learning_rate": 1.8672624773495e-05, + "loss": 0.1203, + "step": 281190 + }, + { + "epoch": 0.63, + "learning_rate": 1.8671506230285675e-05, + "loss": 0.1121, + "step": 281200 + }, + { + "epoch": 0.63, + "learning_rate": 1.8670387687076353e-05, + "loss": 0.1156, + "step": 281210 + }, + { + "epoch": 0.63, + "learning_rate": 1.866926914386703e-05, + "loss": 0.1203, + "step": 281220 + }, + { + "epoch": 0.63, + "learning_rate": 1.8668150600657706e-05, + "loss": 0.1171, + "step": 281230 + }, + { + "epoch": 0.63, + "learning_rate": 1.866703205744838e-05, + "loss": 0.1116, + "step": 281240 + }, + { + "epoch": 0.63, + "learning_rate": 1.8665913514239055e-05, + "loss": 0.1162, + "step": 281250 + }, + { + "epoch": 0.63, + "learning_rate": 1.8664794971029733e-05, + "loss": 0.1168, + "step": 281260 + }, + { + "epoch": 0.63, + "learning_rate": 1.8663676427820407e-05, + "loss": 0.1138, + "step": 281270 + }, + { + "epoch": 0.63, + "learning_rate": 1.8662557884611085e-05, + "loss": 0.1194, + "step": 281280 + }, + { + "epoch": 0.63, + "learning_rate": 1.866143934140176e-05, + "loss": 0.1162, + "step": 281290 + }, + { + "epoch": 0.63, + "learning_rate": 1.8660320798192434e-05, + "loss": 0.1119, + "step": 281300 + }, + { + "epoch": 0.63, + "learning_rate": 1.865920225498311e-05, + "loss": 0.1138, + "step": 281310 + }, + { + "epoch": 0.63, + "learning_rate": 1.8658083711773787e-05, + "loss": 0.117, + "step": 281320 + }, + { + "epoch": 0.63, + "learning_rate": 1.8656965168564465e-05, + "loss": 0.1163, + "step": 281330 + }, + { + "epoch": 0.63, + "learning_rate": 1.865584662535514e-05, + "loss": 0.1203, + "step": 281340 + }, + { + "epoch": 0.63, + "learning_rate": 1.8654728082145814e-05, + "loss": 0.1176, + "step": 281350 + }, + { + "epoch": 0.63, + "learning_rate": 1.8653609538936488e-05, + "loss": 0.1164, + "step": 281360 + }, + { + "epoch": 0.63, + "learning_rate": 1.8652490995727166e-05, + "loss": 0.1152, + "step": 281370 + }, + { + "epoch": 0.63, + "learning_rate": 1.8651372452517844e-05, + "loss": 0.116, + "step": 281380 + }, + { + "epoch": 0.63, + "learning_rate": 1.865025390930852e-05, + "loss": 0.1158, + "step": 281390 + }, + { + "epoch": 0.63, + "learning_rate": 1.8649135366099193e-05, + "loss": 0.1193, + "step": 281400 + }, + { + "epoch": 0.63, + "learning_rate": 1.8648016822889868e-05, + "loss": 0.1126, + "step": 281410 + }, + { + "epoch": 0.63, + "learning_rate": 1.8646898279680546e-05, + "loss": 0.114, + "step": 281420 + }, + { + "epoch": 0.63, + "learning_rate": 1.864577973647122e-05, + "loss": 0.1202, + "step": 281430 + }, + { + "epoch": 0.63, + "learning_rate": 1.8644661193261898e-05, + "loss": 0.1172, + "step": 281440 + }, + { + "epoch": 0.63, + "learning_rate": 1.8643542650052573e-05, + "loss": 0.1179, + "step": 281450 + }, + { + "epoch": 0.63, + "learning_rate": 1.8642424106843247e-05, + "loss": 0.1157, + "step": 281460 + }, + { + "epoch": 0.63, + "learning_rate": 1.8641305563633925e-05, + "loss": 0.1201, + "step": 281470 + }, + { + "epoch": 0.63, + "learning_rate": 1.86401870204246e-05, + "loss": 0.1233, + "step": 281480 + }, + { + "epoch": 0.63, + "learning_rate": 1.8639068477215278e-05, + "loss": 0.1165, + "step": 281490 + }, + { + "epoch": 0.63, + "learning_rate": 1.8637949934005952e-05, + "loss": 0.1146, + "step": 281500 + }, + { + "epoch": 0.63, + "learning_rate": 1.8636831390796627e-05, + "loss": 0.1145, + "step": 281510 + }, + { + "epoch": 0.63, + "learning_rate": 1.86357128475873e-05, + "loss": 0.1174, + "step": 281520 + }, + { + "epoch": 0.63, + "learning_rate": 1.863459430437798e-05, + "loss": 0.1168, + "step": 281530 + }, + { + "epoch": 0.63, + "learning_rate": 1.8633475761168657e-05, + "loss": 0.1152, + "step": 281540 + }, + { + "epoch": 0.63, + "learning_rate": 1.863235721795933e-05, + "loss": 0.1122, + "step": 281550 + }, + { + "epoch": 0.63, + "learning_rate": 1.8631238674750006e-05, + "loss": 0.1152, + "step": 281560 + }, + { + "epoch": 0.63, + "learning_rate": 1.863012013154068e-05, + "loss": 0.1187, + "step": 281570 + }, + { + "epoch": 0.63, + "learning_rate": 1.862900158833136e-05, + "loss": 0.1139, + "step": 281580 + }, + { + "epoch": 0.63, + "learning_rate": 1.8627883045122033e-05, + "loss": 0.1174, + "step": 281590 + }, + { + "epoch": 0.63, + "learning_rate": 1.862676450191271e-05, + "loss": 0.1191, + "step": 281600 + }, + { + "epoch": 0.63, + "learning_rate": 1.8625645958703386e-05, + "loss": 0.116, + "step": 281610 + }, + { + "epoch": 0.63, + "learning_rate": 1.862452741549406e-05, + "loss": 0.1147, + "step": 281620 + }, + { + "epoch": 0.63, + "learning_rate": 1.8623408872284738e-05, + "loss": 0.1145, + "step": 281630 + }, + { + "epoch": 0.63, + "learning_rate": 1.8622290329075413e-05, + "loss": 0.1203, + "step": 281640 + }, + { + "epoch": 0.63, + "learning_rate": 1.862117178586609e-05, + "loss": 0.1191, + "step": 281650 + }, + { + "epoch": 0.63, + "learning_rate": 1.8620053242656765e-05, + "loss": 0.1185, + "step": 281660 + }, + { + "epoch": 0.63, + "learning_rate": 1.861893469944744e-05, + "loss": 0.1159, + "step": 281670 + }, + { + "epoch": 0.63, + "learning_rate": 1.8617816156238117e-05, + "loss": 0.1207, + "step": 281680 + }, + { + "epoch": 0.63, + "learning_rate": 1.8616697613028792e-05, + "loss": 0.113, + "step": 281690 + }, + { + "epoch": 0.63, + "learning_rate": 1.861557906981947e-05, + "loss": 0.1146, + "step": 281700 + }, + { + "epoch": 0.63, + "learning_rate": 1.8614460526610145e-05, + "loss": 0.117, + "step": 281710 + }, + { + "epoch": 0.63, + "learning_rate": 1.861334198340082e-05, + "loss": 0.1135, + "step": 281720 + }, + { + "epoch": 0.63, + "learning_rate": 1.8612223440191494e-05, + "loss": 0.119, + "step": 281730 + }, + { + "epoch": 0.63, + "learning_rate": 1.861110489698217e-05, + "loss": 0.1171, + "step": 281740 + }, + { + "epoch": 0.63, + "learning_rate": 1.8609986353772846e-05, + "loss": 0.1187, + "step": 281750 + }, + { + "epoch": 0.63, + "learning_rate": 1.8608867810563524e-05, + "loss": 0.1124, + "step": 281760 + }, + { + "epoch": 0.63, + "learning_rate": 1.86077492673542e-05, + "loss": 0.1182, + "step": 281770 + }, + { + "epoch": 0.63, + "learning_rate": 1.8606630724144873e-05, + "loss": 0.1172, + "step": 281780 + }, + { + "epoch": 0.63, + "learning_rate": 1.860551218093555e-05, + "loss": 0.1179, + "step": 281790 + }, + { + "epoch": 0.63, + "learning_rate": 1.8604393637726226e-05, + "loss": 0.1148, + "step": 281800 + }, + { + "epoch": 0.63, + "learning_rate": 1.8603275094516903e-05, + "loss": 0.1198, + "step": 281810 + }, + { + "epoch": 0.63, + "learning_rate": 1.8602156551307578e-05, + "loss": 0.11, + "step": 281820 + }, + { + "epoch": 0.63, + "learning_rate": 1.8601038008098253e-05, + "loss": 0.1111, + "step": 281830 + }, + { + "epoch": 0.63, + "learning_rate": 1.859991946488893e-05, + "loss": 0.1202, + "step": 281840 + }, + { + "epoch": 0.63, + "learning_rate": 1.8598800921679605e-05, + "loss": 0.1182, + "step": 281850 + }, + { + "epoch": 0.63, + "learning_rate": 1.8597682378470283e-05, + "loss": 0.1191, + "step": 281860 + }, + { + "epoch": 0.63, + "learning_rate": 1.8596563835260957e-05, + "loss": 0.1132, + "step": 281870 + }, + { + "epoch": 0.63, + "learning_rate": 1.8595445292051632e-05, + "loss": 0.1156, + "step": 281880 + }, + { + "epoch": 0.63, + "learning_rate": 1.859432674884231e-05, + "loss": 0.122, + "step": 281890 + }, + { + "epoch": 0.63, + "learning_rate": 1.8593208205632984e-05, + "loss": 0.1193, + "step": 281900 + }, + { + "epoch": 0.63, + "learning_rate": 1.859208966242366e-05, + "loss": 0.1153, + "step": 281910 + }, + { + "epoch": 0.63, + "learning_rate": 1.8590971119214337e-05, + "loss": 0.1183, + "step": 281920 + }, + { + "epoch": 0.63, + "learning_rate": 1.858985257600501e-05, + "loss": 0.1143, + "step": 281930 + }, + { + "epoch": 0.63, + "learning_rate": 1.8588734032795686e-05, + "loss": 0.1239, + "step": 281940 + }, + { + "epoch": 0.63, + "learning_rate": 1.8587615489586364e-05, + "loss": 0.1165, + "step": 281950 + }, + { + "epoch": 0.63, + "learning_rate": 1.858649694637704e-05, + "loss": 0.1141, + "step": 281960 + }, + { + "epoch": 0.63, + "learning_rate": 1.8585378403167716e-05, + "loss": 0.1197, + "step": 281970 + }, + { + "epoch": 0.63, + "learning_rate": 1.858425985995839e-05, + "loss": 0.1148, + "step": 281980 + }, + { + "epoch": 0.63, + "learning_rate": 1.8583141316749065e-05, + "loss": 0.1156, + "step": 281990 + }, + { + "epoch": 0.63, + "learning_rate": 1.8582022773539743e-05, + "loss": 0.1148, + "step": 282000 + }, + { + "epoch": 0.63, + "learning_rate": 1.8580904230330418e-05, + "loss": 0.1186, + "step": 282010 + }, + { + "epoch": 0.63, + "learning_rate": 1.8579785687121096e-05, + "loss": 0.1171, + "step": 282020 + }, + { + "epoch": 0.63, + "learning_rate": 1.857866714391177e-05, + "loss": 0.1161, + "step": 282030 + }, + { + "epoch": 0.63, + "learning_rate": 1.8577548600702445e-05, + "loss": 0.1172, + "step": 282040 + }, + { + "epoch": 0.63, + "learning_rate": 1.8576430057493123e-05, + "loss": 0.1134, + "step": 282050 + }, + { + "epoch": 0.63, + "learning_rate": 1.8575311514283797e-05, + "loss": 0.1123, + "step": 282060 + }, + { + "epoch": 0.63, + "learning_rate": 1.8574192971074472e-05, + "loss": 0.1187, + "step": 282070 + }, + { + "epoch": 0.63, + "learning_rate": 1.857307442786515e-05, + "loss": 0.1131, + "step": 282080 + }, + { + "epoch": 0.63, + "learning_rate": 1.8571955884655824e-05, + "loss": 0.1182, + "step": 282090 + }, + { + "epoch": 0.63, + "learning_rate": 1.8570837341446502e-05, + "loss": 0.1174, + "step": 282100 + }, + { + "epoch": 0.63, + "learning_rate": 1.8569718798237177e-05, + "loss": 0.1152, + "step": 282110 + }, + { + "epoch": 0.63, + "learning_rate": 1.856860025502785e-05, + "loss": 0.1186, + "step": 282120 + }, + { + "epoch": 0.63, + "learning_rate": 1.856748171181853e-05, + "loss": 0.1164, + "step": 282130 + }, + { + "epoch": 0.63, + "learning_rate": 1.8566363168609204e-05, + "loss": 0.1157, + "step": 282140 + }, + { + "epoch": 0.63, + "learning_rate": 1.8565244625399882e-05, + "loss": 0.1121, + "step": 282150 + }, + { + "epoch": 0.63, + "learning_rate": 1.8564126082190556e-05, + "loss": 0.1176, + "step": 282160 + }, + { + "epoch": 0.63, + "learning_rate": 1.856300753898123e-05, + "loss": 0.1218, + "step": 282170 + }, + { + "epoch": 0.63, + "learning_rate": 1.856188899577191e-05, + "loss": 0.1165, + "step": 282180 + }, + { + "epoch": 0.63, + "learning_rate": 1.8560770452562583e-05, + "loss": 0.1173, + "step": 282190 + }, + { + "epoch": 0.63, + "learning_rate": 1.8559651909353258e-05, + "loss": 0.1142, + "step": 282200 + }, + { + "epoch": 0.63, + "learning_rate": 1.8558533366143936e-05, + "loss": 0.1172, + "step": 282210 + }, + { + "epoch": 0.63, + "learning_rate": 1.855741482293461e-05, + "loss": 0.1209, + "step": 282220 + }, + { + "epoch": 0.63, + "learning_rate": 1.8556296279725285e-05, + "loss": 0.1195, + "step": 282230 + }, + { + "epoch": 0.63, + "learning_rate": 1.8555177736515963e-05, + "loss": 0.1156, + "step": 282240 + }, + { + "epoch": 0.63, + "learning_rate": 1.8554059193306637e-05, + "loss": 0.1156, + "step": 282250 + }, + { + "epoch": 0.63, + "learning_rate": 1.8552940650097315e-05, + "loss": 0.1153, + "step": 282260 + }, + { + "epoch": 0.63, + "learning_rate": 1.855182210688799e-05, + "loss": 0.1161, + "step": 282270 + }, + { + "epoch": 0.63, + "learning_rate": 1.8550703563678664e-05, + "loss": 0.1125, + "step": 282280 + }, + { + "epoch": 0.63, + "learning_rate": 1.8549585020469342e-05, + "loss": 0.1189, + "step": 282290 + }, + { + "epoch": 0.63, + "learning_rate": 1.8548466477260017e-05, + "loss": 0.1189, + "step": 282300 + }, + { + "epoch": 0.63, + "learning_rate": 1.8547347934050695e-05, + "loss": 0.1209, + "step": 282310 + }, + { + "epoch": 0.63, + "learning_rate": 1.854622939084137e-05, + "loss": 0.1186, + "step": 282320 + }, + { + "epoch": 0.63, + "learning_rate": 1.8545110847632044e-05, + "loss": 0.1177, + "step": 282330 + }, + { + "epoch": 0.63, + "learning_rate": 1.8543992304422722e-05, + "loss": 0.1165, + "step": 282340 + }, + { + "epoch": 0.63, + "learning_rate": 1.8542873761213396e-05, + "loss": 0.1178, + "step": 282350 + }, + { + "epoch": 0.63, + "learning_rate": 1.8541867072325005e-05, + "loss": 0.1162, + "step": 282360 + }, + { + "epoch": 0.63, + "learning_rate": 1.854074852911568e-05, + "loss": 0.1108, + "step": 282370 + }, + { + "epoch": 0.63, + "learning_rate": 1.8539629985906358e-05, + "loss": 0.1224, + "step": 282380 + }, + { + "epoch": 0.63, + "learning_rate": 1.8538511442697032e-05, + "loss": 0.1164, + "step": 282390 + }, + { + "epoch": 0.63, + "learning_rate": 1.8537392899487707e-05, + "loss": 0.1164, + "step": 282400 + }, + { + "epoch": 0.63, + "learning_rate": 1.8536274356278385e-05, + "loss": 0.1161, + "step": 282410 + }, + { + "epoch": 0.63, + "learning_rate": 1.853515581306906e-05, + "loss": 0.1203, + "step": 282420 + }, + { + "epoch": 0.63, + "learning_rate": 1.8534037269859737e-05, + "loss": 0.1158, + "step": 282430 + }, + { + "epoch": 0.63, + "learning_rate": 1.853291872665041e-05, + "loss": 0.1163, + "step": 282440 + }, + { + "epoch": 0.63, + "learning_rate": 1.8531800183441086e-05, + "loss": 0.1159, + "step": 282450 + }, + { + "epoch": 0.63, + "learning_rate": 1.853068164023176e-05, + "loss": 0.1152, + "step": 282460 + }, + { + "epoch": 0.63, + "learning_rate": 1.852956309702244e-05, + "loss": 0.1139, + "step": 282470 + }, + { + "epoch": 0.63, + "learning_rate": 1.8528444553813117e-05, + "loss": 0.1164, + "step": 282480 + }, + { + "epoch": 0.63, + "learning_rate": 1.852732601060379e-05, + "loss": 0.117, + "step": 282490 + }, + { + "epoch": 0.63, + "learning_rate": 1.8526207467394466e-05, + "loss": 0.116, + "step": 282500 + }, + { + "epoch": 0.63, + "learning_rate": 1.852508892418514e-05, + "loss": 0.1194, + "step": 282510 + }, + { + "epoch": 0.63, + "learning_rate": 1.8523970380975818e-05, + "loss": 0.1152, + "step": 282520 + }, + { + "epoch": 0.63, + "learning_rate": 1.8522851837766496e-05, + "loss": 0.1173, + "step": 282530 + }, + { + "epoch": 0.63, + "learning_rate": 1.852173329455717e-05, + "loss": 0.1199, + "step": 282540 + }, + { + "epoch": 0.63, + "learning_rate": 1.8520614751347845e-05, + "loss": 0.1158, + "step": 282550 + }, + { + "epoch": 0.63, + "learning_rate": 1.851949620813852e-05, + "loss": 0.1138, + "step": 282560 + }, + { + "epoch": 0.63, + "learning_rate": 1.8518377664929198e-05, + "loss": 0.12, + "step": 282570 + }, + { + "epoch": 0.63, + "learning_rate": 1.8517259121719872e-05, + "loss": 0.1165, + "step": 282580 + }, + { + "epoch": 0.63, + "learning_rate": 1.851614057851055e-05, + "loss": 0.1166, + "step": 282590 + }, + { + "epoch": 0.63, + "learning_rate": 1.8515022035301225e-05, + "loss": 0.1205, + "step": 282600 + }, + { + "epoch": 0.63, + "learning_rate": 1.85139034920919e-05, + "loss": 0.1188, + "step": 282610 + }, + { + "epoch": 0.63, + "learning_rate": 1.8512784948882574e-05, + "loss": 0.1208, + "step": 282620 + }, + { + "epoch": 0.63, + "learning_rate": 1.851166640567325e-05, + "loss": 0.1182, + "step": 282630 + }, + { + "epoch": 0.63, + "learning_rate": 1.851054786246393e-05, + "loss": 0.1171, + "step": 282640 + }, + { + "epoch": 0.63, + "learning_rate": 1.8509429319254604e-05, + "loss": 0.1217, + "step": 282650 + }, + { + "epoch": 0.63, + "learning_rate": 1.850831077604528e-05, + "loss": 0.1171, + "step": 282660 + }, + { + "epoch": 0.63, + "learning_rate": 1.8507192232835953e-05, + "loss": 0.1159, + "step": 282670 + }, + { + "epoch": 0.63, + "learning_rate": 1.850607368962663e-05, + "loss": 0.113, + "step": 282680 + }, + { + "epoch": 0.63, + "learning_rate": 1.850495514641731e-05, + "loss": 0.1169, + "step": 282690 + }, + { + "epoch": 0.63, + "learning_rate": 1.8503836603207984e-05, + "loss": 0.1155, + "step": 282700 + }, + { + "epoch": 0.63, + "learning_rate": 1.8502718059998658e-05, + "loss": 0.1174, + "step": 282710 + }, + { + "epoch": 0.63, + "learning_rate": 1.8501599516789333e-05, + "loss": 0.1145, + "step": 282720 + }, + { + "epoch": 0.63, + "learning_rate": 1.850048097358001e-05, + "loss": 0.1163, + "step": 282730 + }, + { + "epoch": 0.63, + "learning_rate": 1.849936243037069e-05, + "loss": 0.1173, + "step": 282740 + }, + { + "epoch": 0.63, + "learning_rate": 1.8498243887161363e-05, + "loss": 0.1221, + "step": 282750 + }, + { + "epoch": 0.63, + "learning_rate": 1.8497125343952038e-05, + "loss": 0.1121, + "step": 282760 + }, + { + "epoch": 0.63, + "learning_rate": 1.8496006800742712e-05, + "loss": 0.1182, + "step": 282770 + }, + { + "epoch": 0.63, + "learning_rate": 1.8494888257533387e-05, + "loss": 0.1154, + "step": 282780 + }, + { + "epoch": 0.63, + "learning_rate": 1.8493769714324068e-05, + "loss": 0.1128, + "step": 282790 + }, + { + "epoch": 0.63, + "learning_rate": 1.8492651171114742e-05, + "loss": 0.1115, + "step": 282800 + }, + { + "epoch": 0.63, + "learning_rate": 1.8491532627905417e-05, + "loss": 0.1145, + "step": 282810 + }, + { + "epoch": 0.63, + "learning_rate": 1.849041408469609e-05, + "loss": 0.122, + "step": 282820 + }, + { + "epoch": 0.63, + "learning_rate": 1.8489295541486766e-05, + "loss": 0.1178, + "step": 282830 + }, + { + "epoch": 0.63, + "learning_rate": 1.8488176998277444e-05, + "loss": 0.1156, + "step": 282840 + }, + { + "epoch": 0.63, + "learning_rate": 1.8487058455068122e-05, + "loss": 0.1151, + "step": 282850 + }, + { + "epoch": 0.63, + "learning_rate": 1.8485939911858796e-05, + "loss": 0.1161, + "step": 282860 + }, + { + "epoch": 0.63, + "learning_rate": 1.848482136864947e-05, + "loss": 0.1169, + "step": 282870 + }, + { + "epoch": 0.63, + "learning_rate": 1.8483702825440146e-05, + "loss": 0.1168, + "step": 282880 + }, + { + "epoch": 0.63, + "learning_rate": 1.8482584282230823e-05, + "loss": 0.116, + "step": 282890 + }, + { + "epoch": 0.63, + "learning_rate": 1.84814657390215e-05, + "loss": 0.1222, + "step": 282900 + }, + { + "epoch": 0.63, + "learning_rate": 1.8480347195812176e-05, + "loss": 0.1151, + "step": 282910 + }, + { + "epoch": 0.63, + "learning_rate": 1.847922865260285e-05, + "loss": 0.1117, + "step": 282920 + }, + { + "epoch": 0.63, + "learning_rate": 1.8478110109393525e-05, + "loss": 0.1107, + "step": 282930 + }, + { + "epoch": 0.63, + "learning_rate": 1.8476991566184203e-05, + "loss": 0.1226, + "step": 282940 + }, + { + "epoch": 0.63, + "learning_rate": 1.847587302297488e-05, + "loss": 0.1206, + "step": 282950 + }, + { + "epoch": 0.63, + "learning_rate": 1.8474754479765555e-05, + "loss": 0.1185, + "step": 282960 + }, + { + "epoch": 0.63, + "learning_rate": 1.847363593655623e-05, + "loss": 0.11, + "step": 282970 + }, + { + "epoch": 0.63, + "learning_rate": 1.8472517393346905e-05, + "loss": 0.1169, + "step": 282980 + }, + { + "epoch": 0.63, + "learning_rate": 1.847139885013758e-05, + "loss": 0.1146, + "step": 282990 + }, + { + "epoch": 0.63, + "learning_rate": 1.847028030692826e-05, + "loss": 0.1128, + "step": 283000 + }, + { + "epoch": 0.63, + "learning_rate": 1.8469161763718935e-05, + "loss": 0.1139, + "step": 283010 + }, + { + "epoch": 0.63, + "learning_rate": 1.846804322050961e-05, + "loss": 0.1191, + "step": 283020 + }, + { + "epoch": 0.63, + "learning_rate": 1.8466924677300284e-05, + "loss": 0.1151, + "step": 283030 + }, + { + "epoch": 0.63, + "learning_rate": 1.846580613409096e-05, + "loss": 0.1186, + "step": 283040 + }, + { + "epoch": 0.63, + "learning_rate": 1.8464687590881636e-05, + "loss": 0.1179, + "step": 283050 + }, + { + "epoch": 0.63, + "learning_rate": 1.8463569047672314e-05, + "loss": 0.1181, + "step": 283060 + }, + { + "epoch": 0.63, + "learning_rate": 1.846245050446299e-05, + "loss": 0.1177, + "step": 283070 + }, + { + "epoch": 0.63, + "learning_rate": 1.8461331961253663e-05, + "loss": 0.1206, + "step": 283080 + }, + { + "epoch": 0.63, + "learning_rate": 1.8460213418044338e-05, + "loss": 0.1172, + "step": 283090 + }, + { + "epoch": 0.63, + "learning_rate": 1.8459094874835016e-05, + "loss": 0.1162, + "step": 283100 + }, + { + "epoch": 0.63, + "learning_rate": 1.8457976331625694e-05, + "loss": 0.1215, + "step": 283110 + }, + { + "epoch": 0.63, + "learning_rate": 1.845685778841637e-05, + "loss": 0.1164, + "step": 283120 + }, + { + "epoch": 0.63, + "learning_rate": 1.8455739245207043e-05, + "loss": 0.1166, + "step": 283130 + }, + { + "epoch": 0.63, + "learning_rate": 1.8454620701997717e-05, + "loss": 0.1165, + "step": 283140 + }, + { + "epoch": 0.63, + "learning_rate": 1.8453502158788395e-05, + "loss": 0.1115, + "step": 283150 + }, + { + "epoch": 0.63, + "learning_rate": 1.8452383615579073e-05, + "loss": 0.1162, + "step": 283160 + }, + { + "epoch": 0.63, + "learning_rate": 1.8451265072369748e-05, + "loss": 0.1213, + "step": 283170 + }, + { + "epoch": 0.63, + "learning_rate": 1.8450146529160422e-05, + "loss": 0.1163, + "step": 283180 + }, + { + "epoch": 0.63, + "learning_rate": 1.8449027985951097e-05, + "loss": 0.1211, + "step": 283190 + }, + { + "epoch": 0.63, + "learning_rate": 1.844790944274177e-05, + "loss": 0.1133, + "step": 283200 + }, + { + "epoch": 0.63, + "learning_rate": 1.8446790899532453e-05, + "loss": 0.1159, + "step": 283210 + }, + { + "epoch": 0.63, + "learning_rate": 1.8445672356323127e-05, + "loss": 0.1181, + "step": 283220 + }, + { + "epoch": 0.63, + "learning_rate": 1.8444553813113802e-05, + "loss": 0.1161, + "step": 283230 + }, + { + "epoch": 0.63, + "learning_rate": 1.8443435269904476e-05, + "loss": 0.1131, + "step": 283240 + }, + { + "epoch": 0.63, + "learning_rate": 1.844231672669515e-05, + "loss": 0.1185, + "step": 283250 + }, + { + "epoch": 0.63, + "learning_rate": 1.844119818348583e-05, + "loss": 0.1144, + "step": 283260 + }, + { + "epoch": 0.63, + "learning_rate": 1.8440079640276507e-05, + "loss": 0.1195, + "step": 283270 + }, + { + "epoch": 0.63, + "learning_rate": 1.843896109706718e-05, + "loss": 0.1156, + "step": 283280 + }, + { + "epoch": 0.63, + "learning_rate": 1.8437842553857856e-05, + "loss": 0.1176, + "step": 283290 + }, + { + "epoch": 0.63, + "learning_rate": 1.843672401064853e-05, + "loss": 0.1163, + "step": 283300 + }, + { + "epoch": 0.63, + "learning_rate": 1.843560546743921e-05, + "loss": 0.1189, + "step": 283310 + }, + { + "epoch": 0.63, + "learning_rate": 1.8434486924229886e-05, + "loss": 0.1192, + "step": 283320 + }, + { + "epoch": 0.63, + "learning_rate": 1.843336838102056e-05, + "loss": 0.1162, + "step": 283330 + }, + { + "epoch": 0.63, + "learning_rate": 1.8432249837811235e-05, + "loss": 0.1173, + "step": 283340 + }, + { + "epoch": 0.63, + "learning_rate": 1.843113129460191e-05, + "loss": 0.1129, + "step": 283350 + }, + { + "epoch": 0.63, + "learning_rate": 1.8430012751392588e-05, + "loss": 0.1169, + "step": 283360 + }, + { + "epoch": 0.63, + "learning_rate": 1.8428894208183262e-05, + "loss": 0.1088, + "step": 283370 + }, + { + "epoch": 0.63, + "learning_rate": 1.842777566497394e-05, + "loss": 0.1133, + "step": 283380 + }, + { + "epoch": 0.63, + "learning_rate": 1.8426657121764615e-05, + "loss": 0.1156, + "step": 283390 + }, + { + "epoch": 0.63, + "learning_rate": 1.842553857855529e-05, + "loss": 0.1143, + "step": 283400 + }, + { + "epoch": 0.63, + "learning_rate": 1.8424420035345964e-05, + "loss": 0.1181, + "step": 283410 + }, + { + "epoch": 0.63, + "learning_rate": 1.8423301492136642e-05, + "loss": 0.118, + "step": 283420 + }, + { + "epoch": 0.63, + "learning_rate": 1.842218294892732e-05, + "loss": 0.115, + "step": 283430 + }, + { + "epoch": 0.63, + "learning_rate": 1.8421064405717994e-05, + "loss": 0.1194, + "step": 283440 + }, + { + "epoch": 0.63, + "learning_rate": 1.841994586250867e-05, + "loss": 0.1203, + "step": 283450 + }, + { + "epoch": 0.63, + "learning_rate": 1.8418827319299343e-05, + "loss": 0.1186, + "step": 283460 + }, + { + "epoch": 0.63, + "learning_rate": 1.841770877609002e-05, + "loss": 0.1203, + "step": 283470 + }, + { + "epoch": 0.63, + "learning_rate": 1.84165902328807e-05, + "loss": 0.1157, + "step": 283480 + }, + { + "epoch": 0.63, + "learning_rate": 1.8415471689671374e-05, + "loss": 0.116, + "step": 283490 + }, + { + "epoch": 0.63, + "learning_rate": 1.841435314646205e-05, + "loss": 0.1143, + "step": 283500 + }, + { + "epoch": 0.63, + "learning_rate": 1.8413234603252723e-05, + "loss": 0.1189, + "step": 283510 + }, + { + "epoch": 0.63, + "learning_rate": 1.84121160600434e-05, + "loss": 0.1152, + "step": 283520 + }, + { + "epoch": 0.63, + "learning_rate": 1.8410997516834075e-05, + "loss": 0.117, + "step": 283530 + }, + { + "epoch": 0.63, + "learning_rate": 1.8409878973624753e-05, + "loss": 0.1167, + "step": 283540 + }, + { + "epoch": 0.63, + "learning_rate": 1.8408760430415428e-05, + "loss": 0.1169, + "step": 283550 + }, + { + "epoch": 0.63, + "learning_rate": 1.8407641887206102e-05, + "loss": 0.1143, + "step": 283560 + }, + { + "epoch": 0.63, + "learning_rate": 1.840652334399678e-05, + "loss": 0.1174, + "step": 283570 + }, + { + "epoch": 0.63, + "learning_rate": 1.8405404800787455e-05, + "loss": 0.1142, + "step": 283580 + }, + { + "epoch": 0.63, + "learning_rate": 1.8404286257578133e-05, + "loss": 0.1188, + "step": 283590 + }, + { + "epoch": 0.63, + "learning_rate": 1.8403167714368807e-05, + "loss": 0.1178, + "step": 283600 + }, + { + "epoch": 0.63, + "learning_rate": 1.8402049171159482e-05, + "loss": 0.115, + "step": 283610 + }, + { + "epoch": 0.63, + "learning_rate": 1.840093062795016e-05, + "loss": 0.1165, + "step": 283620 + }, + { + "epoch": 0.63, + "learning_rate": 1.8399812084740834e-05, + "loss": 0.1147, + "step": 283630 + }, + { + "epoch": 0.63, + "learning_rate": 1.8398693541531512e-05, + "loss": 0.1155, + "step": 283640 + }, + { + "epoch": 0.63, + "learning_rate": 1.8397574998322187e-05, + "loss": 0.1156, + "step": 283650 + }, + { + "epoch": 0.63, + "learning_rate": 1.839645645511286e-05, + "loss": 0.1139, + "step": 283660 + }, + { + "epoch": 0.63, + "learning_rate": 1.8395337911903536e-05, + "loss": 0.1162, + "step": 283670 + }, + { + "epoch": 0.63, + "learning_rate": 1.8394219368694214e-05, + "loss": 0.1181, + "step": 283680 + }, + { + "epoch": 0.63, + "learning_rate": 1.8393100825484888e-05, + "loss": 0.1177, + "step": 283690 + }, + { + "epoch": 0.63, + "learning_rate": 1.8391982282275566e-05, + "loss": 0.1171, + "step": 283700 + }, + { + "epoch": 0.63, + "learning_rate": 1.839086373906624e-05, + "loss": 0.1159, + "step": 283710 + }, + { + "epoch": 0.63, + "learning_rate": 1.8389745195856915e-05, + "loss": 0.1189, + "step": 283720 + }, + { + "epoch": 0.63, + "learning_rate": 1.8388626652647593e-05, + "loss": 0.1136, + "step": 283730 + }, + { + "epoch": 0.63, + "learning_rate": 1.8387508109438268e-05, + "loss": 0.118, + "step": 283740 + }, + { + "epoch": 0.63, + "learning_rate": 1.8386389566228946e-05, + "loss": 0.115, + "step": 283750 + }, + { + "epoch": 0.63, + "learning_rate": 1.838527102301962e-05, + "loss": 0.118, + "step": 283760 + }, + { + "epoch": 0.63, + "learning_rate": 1.8384152479810295e-05, + "loss": 0.1126, + "step": 283770 + }, + { + "epoch": 0.63, + "learning_rate": 1.8383033936600973e-05, + "loss": 0.1186, + "step": 283780 + }, + { + "epoch": 0.63, + "learning_rate": 1.8381915393391647e-05, + "loss": 0.1176, + "step": 283790 + }, + { + "epoch": 0.63, + "learning_rate": 1.8380796850182325e-05, + "loss": 0.1129, + "step": 283800 + }, + { + "epoch": 0.63, + "learning_rate": 1.8379678306973e-05, + "loss": 0.1187, + "step": 283810 + }, + { + "epoch": 0.63, + "learning_rate": 1.8378559763763674e-05, + "loss": 0.1171, + "step": 283820 + }, + { + "epoch": 0.63, + "learning_rate": 1.8377441220554352e-05, + "loss": 0.1187, + "step": 283830 + }, + { + "epoch": 0.63, + "learning_rate": 1.8376322677345027e-05, + "loss": 0.1175, + "step": 283840 + }, + { + "epoch": 0.63, + "learning_rate": 1.83752041341357e-05, + "loss": 0.117, + "step": 283850 + }, + { + "epoch": 0.63, + "learning_rate": 1.837408559092638e-05, + "loss": 0.121, + "step": 283860 + }, + { + "epoch": 0.63, + "learning_rate": 1.8372967047717054e-05, + "loss": 0.1173, + "step": 283870 + }, + { + "epoch": 0.63, + "learning_rate": 1.8371848504507728e-05, + "loss": 0.1173, + "step": 283880 + }, + { + "epoch": 0.63, + "learning_rate": 1.8370729961298406e-05, + "loss": 0.1161, + "step": 283890 + }, + { + "epoch": 0.63, + "learning_rate": 1.836961141808908e-05, + "loss": 0.1162, + "step": 283900 + }, + { + "epoch": 0.63, + "learning_rate": 1.836849287487976e-05, + "loss": 0.1148, + "step": 283910 + }, + { + "epoch": 0.63, + "learning_rate": 1.8367374331670433e-05, + "loss": 0.116, + "step": 283920 + }, + { + "epoch": 0.63, + "learning_rate": 1.8366255788461108e-05, + "loss": 0.1125, + "step": 283930 + }, + { + "epoch": 0.63, + "learning_rate": 1.8365137245251786e-05, + "loss": 0.1145, + "step": 283940 + }, + { + "epoch": 0.63, + "learning_rate": 1.836401870204246e-05, + "loss": 0.1116, + "step": 283950 + }, + { + "epoch": 0.63, + "learning_rate": 1.8362900158833138e-05, + "loss": 0.1159, + "step": 283960 + }, + { + "epoch": 0.63, + "learning_rate": 1.8361781615623813e-05, + "loss": 0.1126, + "step": 283970 + }, + { + "epoch": 0.63, + "learning_rate": 1.8360663072414487e-05, + "loss": 0.1164, + "step": 283980 + }, + { + "epoch": 0.63, + "learning_rate": 1.8359544529205165e-05, + "loss": 0.1163, + "step": 283990 + }, + { + "epoch": 0.63, + "learning_rate": 1.835842598599584e-05, + "loss": 0.1181, + "step": 284000 + }, + { + "epoch": 0.63, + "learning_rate": 1.8357307442786514e-05, + "loss": 0.1148, + "step": 284010 + }, + { + "epoch": 0.63, + "learning_rate": 1.8356188899577192e-05, + "loss": 0.1196, + "step": 284020 + }, + { + "epoch": 0.63, + "learning_rate": 1.8355070356367867e-05, + "loss": 0.1171, + "step": 284030 + }, + { + "epoch": 0.63, + "learning_rate": 1.8353951813158545e-05, + "loss": 0.1205, + "step": 284040 + }, + { + "epoch": 0.63, + "learning_rate": 1.835283326994922e-05, + "loss": 0.1118, + "step": 284050 + }, + { + "epoch": 0.63, + "learning_rate": 1.8351714726739894e-05, + "loss": 0.1162, + "step": 284060 + }, + { + "epoch": 0.63, + "learning_rate": 1.835059618353057e-05, + "loss": 0.1097, + "step": 284070 + }, + { + "epoch": 0.63, + "learning_rate": 1.8349477640321246e-05, + "loss": 0.1199, + "step": 284080 + }, + { + "epoch": 0.63, + "learning_rate": 1.834835909711192e-05, + "loss": 0.1155, + "step": 284090 + }, + { + "epoch": 0.63, + "learning_rate": 1.83472405539026e-05, + "loss": 0.1115, + "step": 284100 + }, + { + "epoch": 0.63, + "learning_rate": 1.8346122010693273e-05, + "loss": 0.1138, + "step": 284110 + }, + { + "epoch": 0.63, + "learning_rate": 1.834500346748395e-05, + "loss": 0.1124, + "step": 284120 + }, + { + "epoch": 0.63, + "learning_rate": 1.8343884924274626e-05, + "loss": 0.1133, + "step": 284130 + }, + { + "epoch": 0.63, + "learning_rate": 1.83427663810653e-05, + "loss": 0.1136, + "step": 284140 + }, + { + "epoch": 0.63, + "learning_rate": 1.8341647837855978e-05, + "loss": 0.1157, + "step": 284150 + }, + { + "epoch": 0.63, + "learning_rate": 1.8340529294646653e-05, + "loss": 0.1166, + "step": 284160 + }, + { + "epoch": 0.63, + "learning_rate": 1.8339410751437327e-05, + "loss": 0.1138, + "step": 284170 + }, + { + "epoch": 0.63, + "learning_rate": 1.8338292208228005e-05, + "loss": 0.1156, + "step": 284180 + }, + { + "epoch": 0.63, + "learning_rate": 1.833717366501868e-05, + "loss": 0.1164, + "step": 284190 + }, + { + "epoch": 0.63, + "learning_rate": 1.8336055121809358e-05, + "loss": 0.1181, + "step": 284200 + }, + { + "epoch": 0.63, + "learning_rate": 1.8334936578600032e-05, + "loss": 0.1202, + "step": 284210 + }, + { + "epoch": 0.63, + "learning_rate": 1.8333818035390707e-05, + "loss": 0.1188, + "step": 284220 + }, + { + "epoch": 0.63, + "learning_rate": 1.8332699492181385e-05, + "loss": 0.1135, + "step": 284230 + }, + { + "epoch": 0.63, + "learning_rate": 1.833158094897206e-05, + "loss": 0.1151, + "step": 284240 + }, + { + "epoch": 0.63, + "learning_rate": 1.8330462405762737e-05, + "loss": 0.1143, + "step": 284250 + }, + { + "epoch": 0.63, + "learning_rate": 1.832934386255341e-05, + "loss": 0.1149, + "step": 284260 + }, + { + "epoch": 0.63, + "learning_rate": 1.8328225319344086e-05, + "loss": 0.1199, + "step": 284270 + }, + { + "epoch": 0.63, + "learning_rate": 1.8327106776134764e-05, + "loss": 0.1203, + "step": 284280 + }, + { + "epoch": 0.63, + "learning_rate": 1.832598823292544e-05, + "loss": 0.1182, + "step": 284290 + }, + { + "epoch": 0.63, + "learning_rate": 1.8324869689716117e-05, + "loss": 0.1154, + "step": 284300 + }, + { + "epoch": 0.63, + "learning_rate": 1.832375114650679e-05, + "loss": 0.1134, + "step": 284310 + }, + { + "epoch": 0.63, + "learning_rate": 1.8322632603297466e-05, + "loss": 0.1147, + "step": 284320 + }, + { + "epoch": 0.63, + "learning_rate": 1.832151406008814e-05, + "loss": 0.1125, + "step": 284330 + }, + { + "epoch": 0.63, + "learning_rate": 1.8320395516878818e-05, + "loss": 0.116, + "step": 284340 + }, + { + "epoch": 0.63, + "learning_rate": 1.8319276973669493e-05, + "loss": 0.1185, + "step": 284350 + }, + { + "epoch": 0.63, + "learning_rate": 1.831815843046017e-05, + "loss": 0.1137, + "step": 284360 + }, + { + "epoch": 0.63, + "learning_rate": 1.8317039887250845e-05, + "loss": 0.1184, + "step": 284370 + }, + { + "epoch": 0.63, + "learning_rate": 1.8316033198362454e-05, + "loss": 0.1201, + "step": 284380 + }, + { + "epoch": 0.63, + "learning_rate": 1.831491465515313e-05, + "loss": 0.1173, + "step": 284390 + }, + { + "epoch": 0.63, + "learning_rate": 1.8313796111943803e-05, + "loss": 0.1183, + "step": 284400 + }, + { + "epoch": 0.63, + "learning_rate": 1.831267756873448e-05, + "loss": 0.1139, + "step": 284410 + }, + { + "epoch": 0.63, + "learning_rate": 1.831155902552516e-05, + "loss": 0.1151, + "step": 284420 + }, + { + "epoch": 0.63, + "learning_rate": 1.8310440482315833e-05, + "loss": 0.1171, + "step": 284430 + }, + { + "epoch": 0.63, + "learning_rate": 1.8309321939106508e-05, + "loss": 0.1194, + "step": 284440 + }, + { + "epoch": 0.63, + "learning_rate": 1.8308203395897182e-05, + "loss": 0.1176, + "step": 284450 + }, + { + "epoch": 0.63, + "learning_rate": 1.830708485268786e-05, + "loss": 0.1187, + "step": 284460 + }, + { + "epoch": 0.63, + "learning_rate": 1.8305966309478538e-05, + "loss": 0.1126, + "step": 284470 + }, + { + "epoch": 0.63, + "learning_rate": 1.8304847766269213e-05, + "loss": 0.1146, + "step": 284480 + }, + { + "epoch": 0.64, + "learning_rate": 1.8303729223059887e-05, + "loss": 0.1178, + "step": 284490 + }, + { + "epoch": 0.64, + "learning_rate": 1.8302610679850562e-05, + "loss": 0.114, + "step": 284500 + }, + { + "epoch": 0.64, + "learning_rate": 1.830149213664124e-05, + "loss": 0.1161, + "step": 284510 + }, + { + "epoch": 0.64, + "learning_rate": 1.8300373593431914e-05, + "loss": 0.1189, + "step": 284520 + }, + { + "epoch": 0.64, + "learning_rate": 1.8299255050222592e-05, + "loss": 0.1162, + "step": 284530 + }, + { + "epoch": 0.64, + "learning_rate": 1.8298136507013267e-05, + "loss": 0.1188, + "step": 284540 + }, + { + "epoch": 0.64, + "learning_rate": 1.829701796380394e-05, + "loss": 0.1211, + "step": 284550 + }, + { + "epoch": 0.64, + "learning_rate": 1.8295899420594616e-05, + "loss": 0.1196, + "step": 284560 + }, + { + "epoch": 0.64, + "learning_rate": 1.8294780877385294e-05, + "loss": 0.1136, + "step": 284570 + }, + { + "epoch": 0.64, + "learning_rate": 1.8293662334175972e-05, + "loss": 0.1153, + "step": 284580 + }, + { + "epoch": 0.64, + "learning_rate": 1.8292543790966646e-05, + "loss": 0.1204, + "step": 284590 + }, + { + "epoch": 0.64, + "learning_rate": 1.829142524775732e-05, + "loss": 0.1152, + "step": 284600 + }, + { + "epoch": 0.64, + "learning_rate": 1.8290306704547995e-05, + "loss": 0.1189, + "step": 284610 + }, + { + "epoch": 0.64, + "learning_rate": 1.8289188161338673e-05, + "loss": 0.1155, + "step": 284620 + }, + { + "epoch": 0.64, + "learning_rate": 1.828806961812935e-05, + "loss": 0.1176, + "step": 284630 + }, + { + "epoch": 0.64, + "learning_rate": 1.8286951074920026e-05, + "loss": 0.1182, + "step": 284640 + }, + { + "epoch": 0.64, + "learning_rate": 1.82858325317107e-05, + "loss": 0.1135, + "step": 284650 + }, + { + "epoch": 0.64, + "learning_rate": 1.8284713988501375e-05, + "loss": 0.116, + "step": 284660 + }, + { + "epoch": 0.64, + "learning_rate": 1.8283595445292053e-05, + "loss": 0.1195, + "step": 284670 + }, + { + "epoch": 0.64, + "learning_rate": 1.828247690208273e-05, + "loss": 0.1157, + "step": 284680 + }, + { + "epoch": 0.64, + "learning_rate": 1.8281358358873405e-05, + "loss": 0.1132, + "step": 284690 + }, + { + "epoch": 0.64, + "learning_rate": 1.828023981566408e-05, + "loss": 0.1156, + "step": 284700 + }, + { + "epoch": 0.64, + "learning_rate": 1.8279121272454754e-05, + "loss": 0.1178, + "step": 284710 + }, + { + "epoch": 0.64, + "learning_rate": 1.8278114583566363e-05, + "loss": 0.1155, + "step": 284720 + }, + { + "epoch": 0.64, + "learning_rate": 1.8276996040357038e-05, + "loss": 0.119, + "step": 284730 + }, + { + "epoch": 0.64, + "learning_rate": 1.8275877497147716e-05, + "loss": 0.114, + "step": 284740 + }, + { + "epoch": 0.64, + "learning_rate": 1.8274758953938393e-05, + "loss": 0.1211, + "step": 284750 + }, + { + "epoch": 0.64, + "learning_rate": 1.8273640410729068e-05, + "loss": 0.1181, + "step": 284760 + }, + { + "epoch": 0.64, + "learning_rate": 1.8272521867519743e-05, + "loss": 0.1183, + "step": 284770 + }, + { + "epoch": 0.64, + "learning_rate": 1.8271403324310417e-05, + "loss": 0.1152, + "step": 284780 + }, + { + "epoch": 0.64, + "learning_rate": 1.8270284781101095e-05, + "loss": 0.1158, + "step": 284790 + }, + { + "epoch": 0.64, + "learning_rate": 1.8269166237891773e-05, + "loss": 0.1164, + "step": 284800 + }, + { + "epoch": 0.64, + "learning_rate": 1.8268047694682448e-05, + "loss": 0.116, + "step": 284810 + }, + { + "epoch": 0.64, + "learning_rate": 1.8266929151473122e-05, + "loss": 0.1131, + "step": 284820 + }, + { + "epoch": 0.64, + "learning_rate": 1.8265810608263797e-05, + "loss": 0.1115, + "step": 284830 + }, + { + "epoch": 0.64, + "learning_rate": 1.8264692065054475e-05, + "loss": 0.1177, + "step": 284840 + }, + { + "epoch": 0.64, + "learning_rate": 1.8263573521845152e-05, + "loss": 0.1136, + "step": 284850 + }, + { + "epoch": 0.64, + "learning_rate": 1.8262454978635827e-05, + "loss": 0.1169, + "step": 284860 + }, + { + "epoch": 0.64, + "learning_rate": 1.82613364354265e-05, + "loss": 0.1123, + "step": 284870 + }, + { + "epoch": 0.64, + "learning_rate": 1.8260217892217176e-05, + "loss": 0.1126, + "step": 284880 + }, + { + "epoch": 0.64, + "learning_rate": 1.825909934900785e-05, + "loss": 0.113, + "step": 284890 + }, + { + "epoch": 0.64, + "learning_rate": 1.825798080579853e-05, + "loss": 0.1183, + "step": 284900 + }, + { + "epoch": 0.64, + "learning_rate": 1.8256862262589206e-05, + "loss": 0.1187, + "step": 284910 + }, + { + "epoch": 0.64, + "learning_rate": 1.825574371937988e-05, + "loss": 0.1209, + "step": 284920 + }, + { + "epoch": 0.64, + "learning_rate": 1.8254625176170556e-05, + "loss": 0.1185, + "step": 284930 + }, + { + "epoch": 0.64, + "learning_rate": 1.825350663296123e-05, + "loss": 0.1149, + "step": 284940 + }, + { + "epoch": 0.64, + "learning_rate": 1.8252388089751908e-05, + "loss": 0.1188, + "step": 284950 + }, + { + "epoch": 0.64, + "learning_rate": 1.8251269546542586e-05, + "loss": 0.111, + "step": 284960 + }, + { + "epoch": 0.64, + "learning_rate": 1.825015100333326e-05, + "loss": 0.1142, + "step": 284970 + }, + { + "epoch": 0.64, + "learning_rate": 1.8249032460123935e-05, + "loss": 0.1147, + "step": 284980 + }, + { + "epoch": 0.64, + "learning_rate": 1.824791391691461e-05, + "loss": 0.1147, + "step": 284990 + }, + { + "epoch": 0.64, + "learning_rate": 1.8246795373705287e-05, + "loss": 0.1189, + "step": 285000 + }, + { + "epoch": 0.64, + "learning_rate": 1.8245676830495965e-05, + "loss": 0.1167, + "step": 285010 + }, + { + "epoch": 0.64, + "learning_rate": 1.824455828728664e-05, + "loss": 0.121, + "step": 285020 + }, + { + "epoch": 0.64, + "learning_rate": 1.8243439744077314e-05, + "loss": 0.1198, + "step": 285030 + }, + { + "epoch": 0.64, + "learning_rate": 1.824232120086799e-05, + "loss": 0.1182, + "step": 285040 + }, + { + "epoch": 0.64, + "learning_rate": 1.8241202657658667e-05, + "loss": 0.114, + "step": 285050 + }, + { + "epoch": 0.64, + "learning_rate": 1.8240084114449345e-05, + "loss": 0.1165, + "step": 285060 + }, + { + "epoch": 0.64, + "learning_rate": 1.823896557124002e-05, + "loss": 0.1199, + "step": 285070 + }, + { + "epoch": 0.64, + "learning_rate": 1.8237847028030694e-05, + "loss": 0.1166, + "step": 285080 + }, + { + "epoch": 0.64, + "learning_rate": 1.823672848482137e-05, + "loss": 0.1148, + "step": 285090 + }, + { + "epoch": 0.64, + "learning_rate": 1.8235609941612043e-05, + "loss": 0.1162, + "step": 285100 + }, + { + "epoch": 0.64, + "learning_rate": 1.823449139840272e-05, + "loss": 0.1123, + "step": 285110 + }, + { + "epoch": 0.64, + "learning_rate": 1.82333728551934e-05, + "loss": 0.1178, + "step": 285120 + }, + { + "epoch": 0.64, + "learning_rate": 1.8232254311984073e-05, + "loss": 0.1138, + "step": 285130 + }, + { + "epoch": 0.64, + "learning_rate": 1.8231135768774748e-05, + "loss": 0.1152, + "step": 285140 + }, + { + "epoch": 0.64, + "learning_rate": 1.8230017225565423e-05, + "loss": 0.1139, + "step": 285150 + }, + { + "epoch": 0.64, + "learning_rate": 1.82288986823561e-05, + "loss": 0.1165, + "step": 285160 + }, + { + "epoch": 0.64, + "learning_rate": 1.822778013914678e-05, + "loss": 0.1146, + "step": 285170 + }, + { + "epoch": 0.64, + "learning_rate": 1.8226661595937453e-05, + "loss": 0.1153, + "step": 285180 + }, + { + "epoch": 0.64, + "learning_rate": 1.8225543052728127e-05, + "loss": 0.117, + "step": 285190 + }, + { + "epoch": 0.64, + "learning_rate": 1.8224424509518802e-05, + "loss": 0.1151, + "step": 285200 + }, + { + "epoch": 0.64, + "learning_rate": 1.822330596630948e-05, + "loss": 0.1184, + "step": 285210 + }, + { + "epoch": 0.64, + "learning_rate": 1.8222187423100158e-05, + "loss": 0.114, + "step": 285220 + }, + { + "epoch": 0.64, + "learning_rate": 1.8221068879890832e-05, + "loss": 0.1148, + "step": 285230 + }, + { + "epoch": 0.64, + "learning_rate": 1.8219950336681507e-05, + "loss": 0.1126, + "step": 285240 + }, + { + "epoch": 0.64, + "learning_rate": 1.821883179347218e-05, + "loss": 0.1147, + "step": 285250 + }, + { + "epoch": 0.64, + "learning_rate": 1.821771325026286e-05, + "loss": 0.1163, + "step": 285260 + }, + { + "epoch": 0.64, + "learning_rate": 1.8216594707053534e-05, + "loss": 0.1197, + "step": 285270 + }, + { + "epoch": 0.64, + "learning_rate": 1.8215476163844212e-05, + "loss": 0.1176, + "step": 285280 + }, + { + "epoch": 0.64, + "learning_rate": 1.8214357620634886e-05, + "loss": 0.1149, + "step": 285290 + }, + { + "epoch": 0.64, + "learning_rate": 1.821323907742556e-05, + "loss": 0.1132, + "step": 285300 + }, + { + "epoch": 0.64, + "learning_rate": 1.8212120534216235e-05, + "loss": 0.1135, + "step": 285310 + }, + { + "epoch": 0.64, + "learning_rate": 1.8211001991006913e-05, + "loss": 0.1156, + "step": 285320 + }, + { + "epoch": 0.64, + "learning_rate": 1.820988344779759e-05, + "loss": 0.112, + "step": 285330 + }, + { + "epoch": 0.64, + "learning_rate": 1.8208764904588266e-05, + "loss": 0.1179, + "step": 285340 + }, + { + "epoch": 0.64, + "learning_rate": 1.820764636137894e-05, + "loss": 0.1166, + "step": 285350 + }, + { + "epoch": 0.64, + "learning_rate": 1.8206527818169615e-05, + "loss": 0.1176, + "step": 285360 + }, + { + "epoch": 0.64, + "learning_rate": 1.8205409274960293e-05, + "loss": 0.1158, + "step": 285370 + }, + { + "epoch": 0.64, + "learning_rate": 1.820429073175097e-05, + "loss": 0.1184, + "step": 285380 + }, + { + "epoch": 0.64, + "learning_rate": 1.8203172188541645e-05, + "loss": 0.1145, + "step": 285390 + }, + { + "epoch": 0.64, + "learning_rate": 1.820205364533232e-05, + "loss": 0.1099, + "step": 285400 + }, + { + "epoch": 0.64, + "learning_rate": 1.8200935102122994e-05, + "loss": 0.1143, + "step": 285410 + }, + { + "epoch": 0.64, + "learning_rate": 1.8199816558913672e-05, + "loss": 0.1154, + "step": 285420 + }, + { + "epoch": 0.64, + "learning_rate": 1.8198698015704347e-05, + "loss": 0.1144, + "step": 285430 + }, + { + "epoch": 0.64, + "learning_rate": 1.8197579472495025e-05, + "loss": 0.116, + "step": 285440 + }, + { + "epoch": 0.64, + "learning_rate": 1.81964609292857e-05, + "loss": 0.1213, + "step": 285450 + }, + { + "epoch": 0.64, + "learning_rate": 1.8195342386076374e-05, + "loss": 0.1194, + "step": 285460 + }, + { + "epoch": 0.64, + "learning_rate": 1.8194223842867052e-05, + "loss": 0.1104, + "step": 285470 + }, + { + "epoch": 0.64, + "learning_rate": 1.8193105299657726e-05, + "loss": 0.1118, + "step": 285480 + }, + { + "epoch": 0.64, + "learning_rate": 1.8191986756448404e-05, + "loss": 0.1142, + "step": 285490 + }, + { + "epoch": 0.64, + "learning_rate": 1.819086821323908e-05, + "loss": 0.111, + "step": 285500 + }, + { + "epoch": 0.64, + "learning_rate": 1.8189749670029753e-05, + "loss": 0.1169, + "step": 285510 + }, + { + "epoch": 0.64, + "learning_rate": 1.8188631126820428e-05, + "loss": 0.1157, + "step": 285520 + }, + { + "epoch": 0.64, + "learning_rate": 1.8187512583611106e-05, + "loss": 0.1168, + "step": 285530 + }, + { + "epoch": 0.64, + "learning_rate": 1.8186394040401784e-05, + "loss": 0.1172, + "step": 285540 + }, + { + "epoch": 0.64, + "learning_rate": 1.8185275497192458e-05, + "loss": 0.1158, + "step": 285550 + }, + { + "epoch": 0.64, + "learning_rate": 1.8184156953983133e-05, + "loss": 0.1143, + "step": 285560 + }, + { + "epoch": 0.64, + "learning_rate": 1.8183038410773807e-05, + "loss": 0.11, + "step": 285570 + }, + { + "epoch": 0.64, + "learning_rate": 1.8181919867564485e-05, + "loss": 0.1147, + "step": 285580 + }, + { + "epoch": 0.64, + "learning_rate": 1.818080132435516e-05, + "loss": 0.118, + "step": 285590 + }, + { + "epoch": 0.64, + "learning_rate": 1.8179682781145838e-05, + "loss": 0.1163, + "step": 285600 + }, + { + "epoch": 0.64, + "learning_rate": 1.8178564237936512e-05, + "loss": 0.1179, + "step": 285610 + }, + { + "epoch": 0.64, + "learning_rate": 1.8177445694727187e-05, + "loss": 0.1138, + "step": 285620 + }, + { + "epoch": 0.64, + "learning_rate": 1.8176327151517865e-05, + "loss": 0.1174, + "step": 285630 + }, + { + "epoch": 0.64, + "learning_rate": 1.817520860830854e-05, + "loss": 0.1157, + "step": 285640 + }, + { + "epoch": 0.64, + "learning_rate": 1.8174090065099217e-05, + "loss": 0.1178, + "step": 285650 + }, + { + "epoch": 0.64, + "learning_rate": 1.8172971521889892e-05, + "loss": 0.1208, + "step": 285660 + }, + { + "epoch": 0.64, + "learning_rate": 1.8171852978680566e-05, + "loss": 0.1179, + "step": 285670 + }, + { + "epoch": 0.64, + "learning_rate": 1.8170734435471244e-05, + "loss": 0.1182, + "step": 285680 + }, + { + "epoch": 0.64, + "learning_rate": 1.816961589226192e-05, + "loss": 0.1174, + "step": 285690 + }, + { + "epoch": 0.64, + "learning_rate": 1.8168497349052597e-05, + "loss": 0.1125, + "step": 285700 + }, + { + "epoch": 0.64, + "learning_rate": 1.816737880584327e-05, + "loss": 0.1173, + "step": 285710 + }, + { + "epoch": 0.64, + "learning_rate": 1.8166260262633946e-05, + "loss": 0.1116, + "step": 285720 + }, + { + "epoch": 0.64, + "learning_rate": 1.8165141719424624e-05, + "loss": 0.1145, + "step": 285730 + }, + { + "epoch": 0.64, + "learning_rate": 1.8164023176215298e-05, + "loss": 0.1145, + "step": 285740 + }, + { + "epoch": 0.64, + "learning_rate": 1.8162904633005973e-05, + "loss": 0.1121, + "step": 285750 + }, + { + "epoch": 0.64, + "learning_rate": 1.816178608979665e-05, + "loss": 0.1194, + "step": 285760 + }, + { + "epoch": 0.64, + "learning_rate": 1.8160667546587325e-05, + "loss": 0.1151, + "step": 285770 + }, + { + "epoch": 0.64, + "learning_rate": 1.8159549003378e-05, + "loss": 0.112, + "step": 285780 + }, + { + "epoch": 0.64, + "learning_rate": 1.8158430460168678e-05, + "loss": 0.1189, + "step": 285790 + }, + { + "epoch": 0.64, + "learning_rate": 1.8157311916959352e-05, + "loss": 0.1155, + "step": 285800 + }, + { + "epoch": 0.64, + "learning_rate": 1.815619337375003e-05, + "loss": 0.1189, + "step": 285810 + }, + { + "epoch": 0.64, + "learning_rate": 1.8155074830540705e-05, + "loss": 0.1164, + "step": 285820 + }, + { + "epoch": 0.64, + "learning_rate": 1.815395628733138e-05, + "loss": 0.1178, + "step": 285830 + }, + { + "epoch": 0.64, + "learning_rate": 1.8152837744122057e-05, + "loss": 0.1143, + "step": 285840 + }, + { + "epoch": 0.64, + "learning_rate": 1.8151719200912732e-05, + "loss": 0.1213, + "step": 285850 + }, + { + "epoch": 0.64, + "learning_rate": 1.815060065770341e-05, + "loss": 0.1163, + "step": 285860 + }, + { + "epoch": 0.64, + "learning_rate": 1.8149482114494084e-05, + "loss": 0.119, + "step": 285870 + }, + { + "epoch": 0.64, + "learning_rate": 1.814836357128476e-05, + "loss": 0.1146, + "step": 285880 + }, + { + "epoch": 0.64, + "learning_rate": 1.8147245028075437e-05, + "loss": 0.1172, + "step": 285890 + }, + { + "epoch": 0.64, + "learning_rate": 1.814612648486611e-05, + "loss": 0.1232, + "step": 285900 + }, + { + "epoch": 0.64, + "learning_rate": 1.8145007941656786e-05, + "loss": 0.1156, + "step": 285910 + }, + { + "epoch": 0.64, + "learning_rate": 1.8143889398447464e-05, + "loss": 0.1136, + "step": 285920 + }, + { + "epoch": 0.64, + "learning_rate": 1.8142770855238138e-05, + "loss": 0.1187, + "step": 285930 + }, + { + "epoch": 0.64, + "learning_rate": 1.8141652312028816e-05, + "loss": 0.119, + "step": 285940 + }, + { + "epoch": 0.64, + "learning_rate": 1.814053376881949e-05, + "loss": 0.1153, + "step": 285950 + }, + { + "epoch": 0.64, + "learning_rate": 1.8139415225610165e-05, + "loss": 0.1154, + "step": 285960 + }, + { + "epoch": 0.64, + "learning_rate": 1.8138296682400843e-05, + "loss": 0.1154, + "step": 285970 + }, + { + "epoch": 0.64, + "learning_rate": 1.8137178139191518e-05, + "loss": 0.1134, + "step": 285980 + }, + { + "epoch": 0.64, + "learning_rate": 1.8136059595982192e-05, + "loss": 0.115, + "step": 285990 + }, + { + "epoch": 0.64, + "learning_rate": 1.813494105277287e-05, + "loss": 0.1145, + "step": 286000 + }, + { + "epoch": 0.64, + "learning_rate": 1.8133822509563545e-05, + "loss": 0.1173, + "step": 286010 + }, + { + "epoch": 0.64, + "learning_rate": 1.813270396635422e-05, + "loss": 0.1171, + "step": 286020 + }, + { + "epoch": 0.64, + "learning_rate": 1.8131585423144897e-05, + "loss": 0.1145, + "step": 286030 + }, + { + "epoch": 0.64, + "learning_rate": 1.8130466879935572e-05, + "loss": 0.1192, + "step": 286040 + }, + { + "epoch": 0.64, + "learning_rate": 1.812934833672625e-05, + "loss": 0.1152, + "step": 286050 + }, + { + "epoch": 0.64, + "learning_rate": 1.8128229793516924e-05, + "loss": 0.121, + "step": 286060 + }, + { + "epoch": 0.64, + "learning_rate": 1.81271112503076e-05, + "loss": 0.118, + "step": 286070 + }, + { + "epoch": 0.64, + "learning_rate": 1.8125992707098277e-05, + "loss": 0.1159, + "step": 286080 + }, + { + "epoch": 0.64, + "learning_rate": 1.812487416388895e-05, + "loss": 0.1161, + "step": 286090 + }, + { + "epoch": 0.64, + "learning_rate": 1.812375562067963e-05, + "loss": 0.1185, + "step": 286100 + }, + { + "epoch": 0.64, + "learning_rate": 1.8122637077470304e-05, + "loss": 0.1203, + "step": 286110 + }, + { + "epoch": 0.64, + "learning_rate": 1.8121518534260978e-05, + "loss": 0.1165, + "step": 286120 + }, + { + "epoch": 0.64, + "learning_rate": 1.8120399991051656e-05, + "loss": 0.1171, + "step": 286130 + }, + { + "epoch": 0.64, + "learning_rate": 1.811928144784233e-05, + "loss": 0.1133, + "step": 286140 + }, + { + "epoch": 0.64, + "learning_rate": 1.811816290463301e-05, + "loss": 0.1162, + "step": 286150 + }, + { + "epoch": 0.64, + "learning_rate": 1.8117044361423683e-05, + "loss": 0.1154, + "step": 286160 + }, + { + "epoch": 0.64, + "learning_rate": 1.8115925818214358e-05, + "loss": 0.1147, + "step": 286170 + }, + { + "epoch": 0.64, + "learning_rate": 1.8114807275005032e-05, + "loss": 0.1128, + "step": 286180 + }, + { + "epoch": 0.64, + "learning_rate": 1.811368873179571e-05, + "loss": 0.1162, + "step": 286190 + }, + { + "epoch": 0.64, + "learning_rate": 1.8112570188586385e-05, + "loss": 0.1206, + "step": 286200 + }, + { + "epoch": 0.64, + "learning_rate": 1.8111451645377063e-05, + "loss": 0.1105, + "step": 286210 + }, + { + "epoch": 0.64, + "learning_rate": 1.8110333102167737e-05, + "loss": 0.1137, + "step": 286220 + }, + { + "epoch": 0.64, + "learning_rate": 1.8109214558958412e-05, + "loss": 0.1184, + "step": 286230 + }, + { + "epoch": 0.64, + "learning_rate": 1.810809601574909e-05, + "loss": 0.116, + "step": 286240 + }, + { + "epoch": 0.64, + "learning_rate": 1.8106977472539764e-05, + "loss": 0.1152, + "step": 286250 + }, + { + "epoch": 0.64, + "learning_rate": 1.8105858929330442e-05, + "loss": 0.1138, + "step": 286260 + }, + { + "epoch": 0.64, + "learning_rate": 1.8104740386121117e-05, + "loss": 0.1179, + "step": 286270 + }, + { + "epoch": 0.64, + "learning_rate": 1.810362184291179e-05, + "loss": 0.1138, + "step": 286280 + }, + { + "epoch": 0.64, + "learning_rate": 1.810250329970247e-05, + "loss": 0.1139, + "step": 286290 + }, + { + "epoch": 0.64, + "learning_rate": 1.8101384756493144e-05, + "loss": 0.1095, + "step": 286300 + }, + { + "epoch": 0.64, + "learning_rate": 1.810026621328382e-05, + "loss": 0.1154, + "step": 286310 + }, + { + "epoch": 0.64, + "learning_rate": 1.8099147670074496e-05, + "loss": 0.1175, + "step": 286320 + }, + { + "epoch": 0.64, + "learning_rate": 1.809802912686517e-05, + "loss": 0.117, + "step": 286330 + }, + { + "epoch": 0.64, + "learning_rate": 1.8096910583655845e-05, + "loss": 0.1164, + "step": 286340 + }, + { + "epoch": 0.64, + "learning_rate": 1.8095792040446523e-05, + "loss": 0.1183, + "step": 286350 + }, + { + "epoch": 0.64, + "learning_rate": 1.80946734972372e-05, + "loss": 0.1159, + "step": 286360 + }, + { + "epoch": 0.64, + "learning_rate": 1.8093554954027876e-05, + "loss": 0.1163, + "step": 286370 + }, + { + "epoch": 0.64, + "learning_rate": 1.809243641081855e-05, + "loss": 0.1172, + "step": 286380 + }, + { + "epoch": 0.64, + "learning_rate": 1.8091317867609225e-05, + "loss": 0.1221, + "step": 286390 + }, + { + "epoch": 0.64, + "learning_rate": 1.8090199324399903e-05, + "loss": 0.1195, + "step": 286400 + }, + { + "epoch": 0.64, + "learning_rate": 1.8089080781190577e-05, + "loss": 0.1166, + "step": 286410 + }, + { + "epoch": 0.64, + "learning_rate": 1.8087962237981255e-05, + "loss": 0.1154, + "step": 286420 + }, + { + "epoch": 0.64, + "learning_rate": 1.808684369477193e-05, + "loss": 0.1125, + "step": 286430 + }, + { + "epoch": 0.64, + "learning_rate": 1.8085725151562604e-05, + "loss": 0.112, + "step": 286440 + }, + { + "epoch": 0.64, + "learning_rate": 1.8084606608353282e-05, + "loss": 0.1176, + "step": 286450 + }, + { + "epoch": 0.64, + "learning_rate": 1.8083488065143957e-05, + "loss": 0.1177, + "step": 286460 + }, + { + "epoch": 0.64, + "learning_rate": 1.8082369521934635e-05, + "loss": 0.114, + "step": 286470 + }, + { + "epoch": 0.64, + "learning_rate": 1.808125097872531e-05, + "loss": 0.1139, + "step": 286480 + }, + { + "epoch": 0.64, + "learning_rate": 1.8080132435515984e-05, + "loss": 0.1159, + "step": 286490 + }, + { + "epoch": 0.64, + "learning_rate": 1.8079013892306658e-05, + "loss": 0.1155, + "step": 286500 + }, + { + "epoch": 0.64, + "learning_rate": 1.8077895349097336e-05, + "loss": 0.114, + "step": 286510 + }, + { + "epoch": 0.64, + "learning_rate": 1.8076776805888014e-05, + "loss": 0.1248, + "step": 286520 + }, + { + "epoch": 0.64, + "learning_rate": 1.807565826267869e-05, + "loss": 0.1185, + "step": 286530 + }, + { + "epoch": 0.64, + "learning_rate": 1.8074539719469363e-05, + "loss": 0.1158, + "step": 286540 + }, + { + "epoch": 0.64, + "learning_rate": 1.8073421176260038e-05, + "loss": 0.1177, + "step": 286550 + }, + { + "epoch": 0.64, + "learning_rate": 1.8072302633050716e-05, + "loss": 0.1139, + "step": 286560 + }, + { + "epoch": 0.64, + "learning_rate": 1.8071184089841393e-05, + "loss": 0.1103, + "step": 286570 + }, + { + "epoch": 0.64, + "learning_rate": 1.8070065546632068e-05, + "loss": 0.1158, + "step": 286580 + }, + { + "epoch": 0.64, + "learning_rate": 1.8068947003422743e-05, + "loss": 0.1199, + "step": 286590 + }, + { + "epoch": 0.64, + "learning_rate": 1.8067828460213417e-05, + "loss": 0.1146, + "step": 286600 + }, + { + "epoch": 0.64, + "learning_rate": 1.8066709917004095e-05, + "loss": 0.1169, + "step": 286610 + }, + { + "epoch": 0.64, + "learning_rate": 1.8065591373794773e-05, + "loss": 0.117, + "step": 286620 + }, + { + "epoch": 0.64, + "learning_rate": 1.8064472830585447e-05, + "loss": 0.1158, + "step": 286630 + }, + { + "epoch": 0.64, + "learning_rate": 1.8063354287376122e-05, + "loss": 0.1202, + "step": 286640 + }, + { + "epoch": 0.64, + "learning_rate": 1.8062235744166797e-05, + "loss": 0.1176, + "step": 286650 + }, + { + "epoch": 0.64, + "learning_rate": 1.806111720095747e-05, + "loss": 0.1182, + "step": 286660 + }, + { + "epoch": 0.64, + "learning_rate": 1.805999865774815e-05, + "loss": 0.1136, + "step": 286670 + }, + { + "epoch": 0.64, + "learning_rate": 1.8058880114538827e-05, + "loss": 0.1184, + "step": 286680 + }, + { + "epoch": 0.64, + "learning_rate": 1.80577615713295e-05, + "loss": 0.1144, + "step": 286690 + }, + { + "epoch": 0.64, + "learning_rate": 1.8056643028120176e-05, + "loss": 0.1198, + "step": 286700 + }, + { + "epoch": 0.64, + "learning_rate": 1.805552448491085e-05, + "loss": 0.1197, + "step": 286710 + }, + { + "epoch": 0.64, + "learning_rate": 1.805440594170153e-05, + "loss": 0.1134, + "step": 286720 + }, + { + "epoch": 0.64, + "learning_rate": 1.8053287398492206e-05, + "loss": 0.1179, + "step": 286730 + }, + { + "epoch": 0.64, + "learning_rate": 1.805216885528288e-05, + "loss": 0.1141, + "step": 286740 + }, + { + "epoch": 0.64, + "learning_rate": 1.8051050312073556e-05, + "loss": 0.1185, + "step": 286750 + }, + { + "epoch": 0.64, + "learning_rate": 1.804993176886423e-05, + "loss": 0.1214, + "step": 286760 + }, + { + "epoch": 0.64, + "learning_rate": 1.8048813225654908e-05, + "loss": 0.1148, + "step": 286770 + }, + { + "epoch": 0.64, + "learning_rate": 1.8047694682445586e-05, + "loss": 0.114, + "step": 286780 + }, + { + "epoch": 0.64, + "learning_rate": 1.804657613923626e-05, + "loss": 0.1195, + "step": 286790 + }, + { + "epoch": 0.64, + "learning_rate": 1.8045457596026935e-05, + "loss": 0.1192, + "step": 286800 + }, + { + "epoch": 0.64, + "learning_rate": 1.804433905281761e-05, + "loss": 0.1136, + "step": 286810 + }, + { + "epoch": 0.64, + "learning_rate": 1.8043220509608284e-05, + "loss": 0.1141, + "step": 286820 + }, + { + "epoch": 0.64, + "learning_rate": 1.8042101966398965e-05, + "loss": 0.1149, + "step": 286830 + }, + { + "epoch": 0.64, + "learning_rate": 1.804098342318964e-05, + "loss": 0.1142, + "step": 286840 + }, + { + "epoch": 0.64, + "learning_rate": 1.8039864879980314e-05, + "loss": 0.1167, + "step": 286850 + }, + { + "epoch": 0.64, + "learning_rate": 1.803874633677099e-05, + "loss": 0.1141, + "step": 286860 + }, + { + "epoch": 0.64, + "learning_rate": 1.8037627793561664e-05, + "loss": 0.1224, + "step": 286870 + }, + { + "epoch": 0.64, + "learning_rate": 1.803650925035234e-05, + "loss": 0.1182, + "step": 286880 + }, + { + "epoch": 0.64, + "learning_rate": 1.803539070714302e-05, + "loss": 0.1177, + "step": 286890 + }, + { + "epoch": 0.64, + "learning_rate": 1.8034272163933694e-05, + "loss": 0.1134, + "step": 286900 + }, + { + "epoch": 0.64, + "learning_rate": 1.803315362072437e-05, + "loss": 0.1143, + "step": 286910 + }, + { + "epoch": 0.64, + "learning_rate": 1.8032035077515043e-05, + "loss": 0.1169, + "step": 286920 + }, + { + "epoch": 0.64, + "learning_rate": 1.803091653430572e-05, + "loss": 0.1111, + "step": 286930 + }, + { + "epoch": 0.64, + "learning_rate": 1.80297979910964e-05, + "loss": 0.1147, + "step": 286940 + }, + { + "epoch": 0.64, + "learning_rate": 1.8028679447887073e-05, + "loss": 0.1158, + "step": 286950 + }, + { + "epoch": 0.64, + "learning_rate": 1.8027560904677748e-05, + "loss": 0.1204, + "step": 286960 + }, + { + "epoch": 0.64, + "learning_rate": 1.8026442361468422e-05, + "loss": 0.1115, + "step": 286970 + }, + { + "epoch": 0.64, + "learning_rate": 1.80253238182591e-05, + "loss": 0.1184, + "step": 286980 + }, + { + "epoch": 0.64, + "learning_rate": 1.802420527504978e-05, + "loss": 0.1107, + "step": 286990 + }, + { + "epoch": 0.64, + "learning_rate": 1.8023086731840453e-05, + "loss": 0.1155, + "step": 287000 + }, + { + "epoch": 0.64, + "learning_rate": 1.8021968188631127e-05, + "loss": 0.1174, + "step": 287010 + }, + { + "epoch": 0.64, + "learning_rate": 1.8020849645421802e-05, + "loss": 0.1124, + "step": 287020 + }, + { + "epoch": 0.64, + "learning_rate": 1.8019731102212477e-05, + "loss": 0.1106, + "step": 287030 + }, + { + "epoch": 0.64, + "learning_rate": 1.8018612559003158e-05, + "loss": 0.1171, + "step": 287040 + }, + { + "epoch": 0.64, + "learning_rate": 1.8017494015793832e-05, + "loss": 0.1127, + "step": 287050 + }, + { + "epoch": 0.64, + "learning_rate": 1.8016375472584507e-05, + "loss": 0.117, + "step": 287060 + }, + { + "epoch": 0.64, + "learning_rate": 1.801525692937518e-05, + "loss": 0.1135, + "step": 287070 + }, + { + "epoch": 0.64, + "learning_rate": 1.8014138386165856e-05, + "loss": 0.1143, + "step": 287080 + }, + { + "epoch": 0.64, + "learning_rate": 1.8013019842956534e-05, + "loss": 0.1187, + "step": 287090 + }, + { + "epoch": 0.64, + "learning_rate": 1.8011901299747212e-05, + "loss": 0.114, + "step": 287100 + }, + { + "epoch": 0.64, + "learning_rate": 1.8010782756537886e-05, + "loss": 0.1144, + "step": 287110 + }, + { + "epoch": 0.64, + "learning_rate": 1.800966421332856e-05, + "loss": 0.1157, + "step": 287120 + }, + { + "epoch": 0.64, + "learning_rate": 1.8008545670119235e-05, + "loss": 0.1152, + "step": 287130 + }, + { + "epoch": 0.64, + "learning_rate": 1.8007427126909913e-05, + "loss": 0.1135, + "step": 287140 + }, + { + "epoch": 0.64, + "learning_rate": 1.800630858370059e-05, + "loss": 0.1186, + "step": 287150 + }, + { + "epoch": 0.64, + "learning_rate": 1.8005190040491266e-05, + "loss": 0.12, + "step": 287160 + }, + { + "epoch": 0.64, + "learning_rate": 1.800407149728194e-05, + "loss": 0.1124, + "step": 287170 + }, + { + "epoch": 0.64, + "learning_rate": 1.8002952954072615e-05, + "loss": 0.1157, + "step": 287180 + }, + { + "epoch": 0.64, + "learning_rate": 1.8001834410863293e-05, + "loss": 0.1074, + "step": 287190 + }, + { + "epoch": 0.64, + "learning_rate": 1.800071586765397e-05, + "loss": 0.1153, + "step": 287200 + }, + { + "epoch": 0.64, + "learning_rate": 1.7999597324444645e-05, + "loss": 0.1135, + "step": 287210 + }, + { + "epoch": 0.64, + "learning_rate": 1.799847878123532e-05, + "loss": 0.1116, + "step": 287220 + }, + { + "epoch": 0.64, + "learning_rate": 1.7997360238025994e-05, + "loss": 0.1156, + "step": 287230 + }, + { + "epoch": 0.64, + "learning_rate": 1.7996241694816672e-05, + "loss": 0.1143, + "step": 287240 + }, + { + "epoch": 0.64, + "learning_rate": 1.799512315160735e-05, + "loss": 0.1176, + "step": 287250 + }, + { + "epoch": 0.64, + "learning_rate": 1.7994004608398025e-05, + "loss": 0.1179, + "step": 287260 + }, + { + "epoch": 0.64, + "learning_rate": 1.79928860651887e-05, + "loss": 0.1182, + "step": 287270 + }, + { + "epoch": 0.64, + "learning_rate": 1.7991767521979374e-05, + "loss": 0.1117, + "step": 287280 + }, + { + "epoch": 0.64, + "learning_rate": 1.799064897877005e-05, + "loss": 0.1119, + "step": 287290 + }, + { + "epoch": 0.64, + "learning_rate": 1.7989530435560726e-05, + "loss": 0.1148, + "step": 287300 + }, + { + "epoch": 0.64, + "learning_rate": 1.7988411892351404e-05, + "loss": 0.1197, + "step": 287310 + }, + { + "epoch": 0.64, + "learning_rate": 1.798729334914208e-05, + "loss": 0.1185, + "step": 287320 + }, + { + "epoch": 0.64, + "learning_rate": 1.7986174805932753e-05, + "loss": 0.1141, + "step": 287330 + }, + { + "epoch": 0.64, + "learning_rate": 1.7985056262723428e-05, + "loss": 0.1162, + "step": 287340 + }, + { + "epoch": 0.64, + "learning_rate": 1.7983937719514106e-05, + "loss": 0.1159, + "step": 287350 + }, + { + "epoch": 0.64, + "learning_rate": 1.7982819176304784e-05, + "loss": 0.1164, + "step": 287360 + }, + { + "epoch": 0.64, + "learning_rate": 1.7981700633095458e-05, + "loss": 0.1184, + "step": 287370 + }, + { + "epoch": 0.64, + "learning_rate": 1.7980582089886133e-05, + "loss": 0.1178, + "step": 287380 + }, + { + "epoch": 0.64, + "learning_rate": 1.7979463546676807e-05, + "loss": 0.1142, + "step": 287390 + }, + { + "epoch": 0.64, + "learning_rate": 1.7978345003467485e-05, + "loss": 0.1168, + "step": 287400 + }, + { + "epoch": 0.64, + "learning_rate": 1.7977226460258163e-05, + "loss": 0.1158, + "step": 287410 + }, + { + "epoch": 0.64, + "learning_rate": 1.7976107917048838e-05, + "loss": 0.1155, + "step": 287420 + }, + { + "epoch": 0.64, + "learning_rate": 1.7974989373839512e-05, + "loss": 0.1195, + "step": 287430 + }, + { + "epoch": 0.64, + "learning_rate": 1.7973870830630187e-05, + "loss": 0.1181, + "step": 287440 + }, + { + "epoch": 0.64, + "learning_rate": 1.7972752287420865e-05, + "loss": 0.118, + "step": 287450 + }, + { + "epoch": 0.64, + "learning_rate": 1.797163374421154e-05, + "loss": 0.1168, + "step": 287460 + }, + { + "epoch": 0.64, + "learning_rate": 1.7970515201002217e-05, + "loss": 0.1185, + "step": 287470 + }, + { + "epoch": 0.64, + "learning_rate": 1.7969396657792892e-05, + "loss": 0.1175, + "step": 287480 + }, + { + "epoch": 0.64, + "learning_rate": 1.7968278114583566e-05, + "loss": 0.1164, + "step": 287490 + }, + { + "epoch": 0.64, + "learning_rate": 1.796715957137424e-05, + "loss": 0.111, + "step": 287500 + }, + { + "epoch": 0.64, + "learning_rate": 1.796604102816492e-05, + "loss": 0.1183, + "step": 287510 + }, + { + "epoch": 0.64, + "learning_rate": 1.7964922484955597e-05, + "loss": 0.116, + "step": 287520 + }, + { + "epoch": 0.64, + "learning_rate": 1.796380394174627e-05, + "loss": 0.1145, + "step": 287530 + }, + { + "epoch": 0.64, + "learning_rate": 1.7962685398536946e-05, + "loss": 0.1151, + "step": 287540 + }, + { + "epoch": 0.64, + "learning_rate": 1.796156685532762e-05, + "loss": 0.1157, + "step": 287550 + }, + { + "epoch": 0.64, + "learning_rate": 1.7960448312118298e-05, + "loss": 0.121, + "step": 287560 + }, + { + "epoch": 0.64, + "learning_rate": 1.7959329768908976e-05, + "loss": 0.1149, + "step": 287570 + }, + { + "epoch": 0.64, + "learning_rate": 1.795821122569965e-05, + "loss": 0.1162, + "step": 287580 + }, + { + "epoch": 0.64, + "learning_rate": 1.7957092682490325e-05, + "loss": 0.1172, + "step": 287590 + }, + { + "epoch": 0.64, + "learning_rate": 1.7955974139281e-05, + "loss": 0.1181, + "step": 287600 + }, + { + "epoch": 0.64, + "learning_rate": 1.7954855596071678e-05, + "loss": 0.1192, + "step": 287610 + }, + { + "epoch": 0.64, + "learning_rate": 1.7953737052862352e-05, + "loss": 0.1173, + "step": 287620 + }, + { + "epoch": 0.64, + "learning_rate": 1.795261850965303e-05, + "loss": 0.1187, + "step": 287630 + }, + { + "epoch": 0.64, + "learning_rate": 1.7951499966443705e-05, + "loss": 0.1173, + "step": 287640 + }, + { + "epoch": 0.64, + "learning_rate": 1.795038142323438e-05, + "loss": 0.1151, + "step": 287650 + }, + { + "epoch": 0.64, + "learning_rate": 1.7949262880025057e-05, + "loss": 0.1176, + "step": 287660 + }, + { + "epoch": 0.64, + "learning_rate": 1.7948144336815732e-05, + "loss": 0.1176, + "step": 287670 + }, + { + "epoch": 0.64, + "learning_rate": 1.794702579360641e-05, + "loss": 0.1159, + "step": 287680 + }, + { + "epoch": 0.64, + "learning_rate": 1.7945907250397084e-05, + "loss": 0.1158, + "step": 287690 + }, + { + "epoch": 0.64, + "learning_rate": 1.794478870718776e-05, + "loss": 0.1168, + "step": 287700 + }, + { + "epoch": 0.64, + "learning_rate": 1.7943670163978433e-05, + "loss": 0.1143, + "step": 287710 + }, + { + "epoch": 0.64, + "learning_rate": 1.794255162076911e-05, + "loss": 0.1137, + "step": 287720 + }, + { + "epoch": 0.64, + "learning_rate": 1.794143307755979e-05, + "loss": 0.1192, + "step": 287730 + }, + { + "epoch": 0.64, + "learning_rate": 1.7940314534350464e-05, + "loss": 0.1183, + "step": 287740 + }, + { + "epoch": 0.64, + "learning_rate": 1.7939195991141138e-05, + "loss": 0.1155, + "step": 287750 + }, + { + "epoch": 0.64, + "learning_rate": 1.7938077447931813e-05, + "loss": 0.1174, + "step": 287760 + }, + { + "epoch": 0.64, + "learning_rate": 1.793695890472249e-05, + "loss": 0.1174, + "step": 287770 + }, + { + "epoch": 0.64, + "learning_rate": 1.7935840361513165e-05, + "loss": 0.1123, + "step": 287780 + }, + { + "epoch": 0.64, + "learning_rate": 1.7934721818303843e-05, + "loss": 0.1184, + "step": 287790 + }, + { + "epoch": 0.64, + "learning_rate": 1.7933603275094518e-05, + "loss": 0.1175, + "step": 287800 + }, + { + "epoch": 0.64, + "learning_rate": 1.7932484731885192e-05, + "loss": 0.1133, + "step": 287810 + }, + { + "epoch": 0.64, + "learning_rate": 1.793136618867587e-05, + "loss": 0.1122, + "step": 287820 + }, + { + "epoch": 0.64, + "learning_rate": 1.7930247645466545e-05, + "loss": 0.1133, + "step": 287830 + }, + { + "epoch": 0.64, + "learning_rate": 1.7929129102257223e-05, + "loss": 0.1187, + "step": 287840 + }, + { + "epoch": 0.64, + "learning_rate": 1.7928010559047897e-05, + "loss": 0.1134, + "step": 287850 + }, + { + "epoch": 0.64, + "learning_rate": 1.7926892015838572e-05, + "loss": 0.1189, + "step": 287860 + }, + { + "epoch": 0.64, + "learning_rate": 1.792577347262925e-05, + "loss": 0.1138, + "step": 287870 + }, + { + "epoch": 0.64, + "learning_rate": 1.7924654929419924e-05, + "loss": 0.1119, + "step": 287880 + }, + { + "epoch": 0.64, + "learning_rate": 1.7923536386210602e-05, + "loss": 0.1173, + "step": 287890 + }, + { + "epoch": 0.64, + "learning_rate": 1.7922417843001277e-05, + "loss": 0.1114, + "step": 287900 + }, + { + "epoch": 0.64, + "learning_rate": 1.792129929979195e-05, + "loss": 0.1166, + "step": 287910 + }, + { + "epoch": 0.64, + "learning_rate": 1.7920180756582626e-05, + "loss": 0.1122, + "step": 287920 + }, + { + "epoch": 0.64, + "learning_rate": 1.7919062213373304e-05, + "loss": 0.1143, + "step": 287930 + }, + { + "epoch": 0.64, + "learning_rate": 1.7917943670163978e-05, + "loss": 0.1138, + "step": 287940 + }, + { + "epoch": 0.64, + "learning_rate": 1.7916825126954656e-05, + "loss": 0.1136, + "step": 287950 + }, + { + "epoch": 0.64, + "learning_rate": 1.791570658374533e-05, + "loss": 0.1165, + "step": 287960 + }, + { + "epoch": 0.64, + "learning_rate": 1.7914588040536005e-05, + "loss": 0.1188, + "step": 287970 + }, + { + "epoch": 0.64, + "learning_rate": 1.7913469497326683e-05, + "loss": 0.1144, + "step": 287980 + }, + { + "epoch": 0.64, + "learning_rate": 1.7912350954117358e-05, + "loss": 0.1179, + "step": 287990 + }, + { + "epoch": 0.64, + "learning_rate": 1.7911232410908036e-05, + "loss": 0.1152, + "step": 288000 + }, + { + "epoch": 0.64, + "eval_NEIMS_canon_smiles": 0.9586833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.19921666666666665, + "eval_NEIMS_daylight_tanimoto_simil": 0.5881733091929915, + "eval_NEIMS_exact_mols": 0.19895, + "eval_NEIMS_exact_smiles": 0.19528333333333334, + "eval_NEIMS_loss": 0.14393387734889984, + "eval_NEIMS_matched_formulas": 0.7153833333333334, + "eval_NEIMS_morgan_tanimoto_simil": 0.5077900595401424, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.19961666666666666, + "eval_NEIMS_runtime": 729.0769, + "eval_NEIMS_samples_per_second": 82.296, + "eval_NEIMS_steps_per_second": 1.287, + "step": 288000 + }, + { + "epoch": 0.64, + "eval_RASSP_canon_smiles": 0.9574581761111297, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.269709820683207, + "eval_RASSP_daylight_tanimoto_simil": 0.6864319360339366, + "eval_RASSP_exact_mols": 0.26902527799111764, + "eval_RASSP_exact_smiles": 0.2627475206197616, + "eval_RASSP_loss": 0.11323179304599762, + "eval_RASSP_matched_formulas": 0.8537249140147594, + "eval_RASSP_morgan_tanimoto_simil": 0.571618975833053, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.26915884729689116, + "eval_RASSP_runtime": 829.974, + "eval_RASSP_samples_per_second": 72.164, + "eval_RASSP_steps_per_second": 1.128, + "step": 288000 + }, + { + "epoch": 0.64, + "eval_NEIMS_old_canon_smiles": 0.9576666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.19863333333333333, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5857080139043928, + "eval_NEIMS_old_exact_mols": 0.19843333333333332, + "eval_NEIMS_old_exact_smiles": 0.194, + "eval_NEIMS_old_loss": 0.1436818689107895, + "eval_NEIMS_old_matched_formulas": 0.7117666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.507762403295439, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.1991, + "eval_NEIMS_old_runtime": 367.1535, + "eval_NEIMS_old_samples_per_second": 81.71, + "eval_NEIMS_old_steps_per_second": 1.277, + "step": 288000 + }, + { + "epoch": 0.64, + "eval_RASSP_old_canon_smiles": 0.9568525377915708, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.29769413020989755, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7037417372107411, + "eval_RASSP_old_exact_mols": 0.29695998932158707, + "eval_RASSP_old_exact_smiles": 0.28981880068074883, + "eval_RASSP_old_loss": 0.10671654343605042, + "eval_RASSP_old_matched_formulas": 0.8665532085293823, + "eval_RASSP_old_morgan_tanimoto_simil": 0.5943208885771611, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.29709346948309806, + "eval_RASSP_old_runtime": 414.8508, + "eval_RASSP_old_samples_per_second": 72.236, + "eval_RASSP_old_steps_per_second": 1.131, + "step": 288000 + }, + { + "epoch": 0.64, + "eval_NIST_canon_smiles": 0.8757852148915782, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02615608474997338, + "eval_NIST_daylight_tanimoto_simil": 0.2950594122241269, + "eval_NIST_exact_mols": 0.024984916776093977, + "eval_NIST_exact_smiles": 0.02392021861802179, + "eval_NIST_loss": 1.793601632118225, + "eval_NIST_matched_formulas": 0.12229832842389182, + "eval_NIST_morgan_tanimoto_simil": 0.2469883162168312, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.025907655179756538, + "eval_NIST_runtime": 524.4581, + "eval_NIST_samples_per_second": 53.726, + "eval_NIST_steps_per_second": 0.841, + "step": 288000 + }, + { + "epoch": 0.64, + "learning_rate": 1.791011386769871e-05, + "loss": 0.113, + "step": 288010 + }, + { + "epoch": 0.64, + "learning_rate": 1.7908995324489385e-05, + "loss": 0.1167, + "step": 288020 + }, + { + "epoch": 0.64, + "learning_rate": 1.7907876781280063e-05, + "loss": 0.1113, + "step": 288030 + }, + { + "epoch": 0.64, + "learning_rate": 1.7906758238070737e-05, + "loss": 0.1161, + "step": 288040 + }, + { + "epoch": 0.64, + "learning_rate": 1.7905639694861415e-05, + "loss": 0.1152, + "step": 288050 + }, + { + "epoch": 0.64, + "learning_rate": 1.790452115165209e-05, + "loss": 0.1167, + "step": 288060 + }, + { + "epoch": 0.64, + "learning_rate": 1.7903402608442764e-05, + "loss": 0.1149, + "step": 288070 + }, + { + "epoch": 0.64, + "learning_rate": 1.7902284065233442e-05, + "loss": 0.1165, + "step": 288080 + }, + { + "epoch": 0.64, + "learning_rate": 1.7901165522024117e-05, + "loss": 0.1225, + "step": 288090 + }, + { + "epoch": 0.64, + "learning_rate": 1.790004697881479e-05, + "loss": 0.1162, + "step": 288100 + }, + { + "epoch": 0.64, + "learning_rate": 1.789892843560547e-05, + "loss": 0.114, + "step": 288110 + }, + { + "epoch": 0.64, + "learning_rate": 1.7897809892396144e-05, + "loss": 0.1156, + "step": 288120 + }, + { + "epoch": 0.64, + "learning_rate": 1.789669134918682e-05, + "loss": 0.1117, + "step": 288130 + }, + { + "epoch": 0.64, + "learning_rate": 1.7895572805977496e-05, + "loss": 0.1125, + "step": 288140 + }, + { + "epoch": 0.64, + "learning_rate": 1.789445426276817e-05, + "loss": 0.1143, + "step": 288150 + }, + { + "epoch": 0.64, + "learning_rate": 1.789333571955885e-05, + "loss": 0.1113, + "step": 288160 + }, + { + "epoch": 0.64, + "learning_rate": 1.7892217176349523e-05, + "loss": 0.1116, + "step": 288170 + }, + { + "epoch": 0.64, + "learning_rate": 1.7891098633140198e-05, + "loss": 0.1134, + "step": 288180 + }, + { + "epoch": 0.64, + "learning_rate": 1.7889980089930876e-05, + "loss": 0.1181, + "step": 288190 + }, + { + "epoch": 0.64, + "learning_rate": 1.788886154672155e-05, + "loss": 0.1123, + "step": 288200 + }, + { + "epoch": 0.64, + "learning_rate": 1.7887743003512228e-05, + "loss": 0.1087, + "step": 288210 + }, + { + "epoch": 0.64, + "learning_rate": 1.7886624460302903e-05, + "loss": 0.1126, + "step": 288220 + }, + { + "epoch": 0.64, + "learning_rate": 1.7885505917093577e-05, + "loss": 0.1137, + "step": 288230 + }, + { + "epoch": 0.64, + "learning_rate": 1.7884387373884255e-05, + "loss": 0.1136, + "step": 288240 + }, + { + "epoch": 0.64, + "learning_rate": 1.788326883067493e-05, + "loss": 0.116, + "step": 288250 + }, + { + "epoch": 0.64, + "learning_rate": 1.7882150287465604e-05, + "loss": 0.1141, + "step": 288260 + }, + { + "epoch": 0.64, + "learning_rate": 1.7881031744256282e-05, + "loss": 0.1133, + "step": 288270 + }, + { + "epoch": 0.64, + "learning_rate": 1.7879913201046957e-05, + "loss": 0.1174, + "step": 288280 + }, + { + "epoch": 0.64, + "learning_rate": 1.7878794657837635e-05, + "loss": 0.114, + "step": 288290 + }, + { + "epoch": 0.64, + "learning_rate": 1.787767611462831e-05, + "loss": 0.113, + "step": 288300 + }, + { + "epoch": 0.64, + "learning_rate": 1.7876557571418984e-05, + "loss": 0.1142, + "step": 288310 + }, + { + "epoch": 0.64, + "learning_rate": 1.787543902820966e-05, + "loss": 0.116, + "step": 288320 + }, + { + "epoch": 0.64, + "learning_rate": 1.7874320485000336e-05, + "loss": 0.121, + "step": 288330 + }, + { + "epoch": 0.64, + "learning_rate": 1.7873201941791014e-05, + "loss": 0.1113, + "step": 288340 + }, + { + "epoch": 0.64, + "learning_rate": 1.787208339858169e-05, + "loss": 0.1134, + "step": 288350 + }, + { + "epoch": 0.64, + "learning_rate": 1.7870964855372363e-05, + "loss": 0.1123, + "step": 288360 + }, + { + "epoch": 0.64, + "learning_rate": 1.786984631216304e-05, + "loss": 0.1161, + "step": 288370 + }, + { + "epoch": 0.64, + "learning_rate": 1.7868727768953716e-05, + "loss": 0.1131, + "step": 288380 + }, + { + "epoch": 0.64, + "learning_rate": 1.786760922574439e-05, + "loss": 0.1121, + "step": 288390 + }, + { + "epoch": 0.64, + "learning_rate": 1.7866490682535068e-05, + "loss": 0.1159, + "step": 288400 + }, + { + "epoch": 0.64, + "learning_rate": 1.7865372139325743e-05, + "loss": 0.1161, + "step": 288410 + }, + { + "epoch": 0.64, + "learning_rate": 1.7864253596116417e-05, + "loss": 0.1114, + "step": 288420 + }, + { + "epoch": 0.64, + "learning_rate": 1.7863135052907095e-05, + "loss": 0.1186, + "step": 288430 + }, + { + "epoch": 0.64, + "learning_rate": 1.786201650969777e-05, + "loss": 0.115, + "step": 288440 + }, + { + "epoch": 0.64, + "learning_rate": 1.7860897966488447e-05, + "loss": 0.1208, + "step": 288450 + }, + { + "epoch": 0.64, + "learning_rate": 1.7859779423279122e-05, + "loss": 0.1131, + "step": 288460 + }, + { + "epoch": 0.64, + "learning_rate": 1.7858660880069797e-05, + "loss": 0.1114, + "step": 288470 + }, + { + "epoch": 0.64, + "learning_rate": 1.7857542336860474e-05, + "loss": 0.1125, + "step": 288480 + }, + { + "epoch": 0.64, + "learning_rate": 1.785642379365115e-05, + "loss": 0.1161, + "step": 288490 + }, + { + "epoch": 0.64, + "learning_rate": 1.7855305250441827e-05, + "loss": 0.1162, + "step": 288500 + }, + { + "epoch": 0.64, + "learning_rate": 1.78541867072325e-05, + "loss": 0.1217, + "step": 288510 + }, + { + "epoch": 0.64, + "learning_rate": 1.7853068164023176e-05, + "loss": 0.1135, + "step": 288520 + }, + { + "epoch": 0.64, + "learning_rate": 1.7851949620813854e-05, + "loss": 0.118, + "step": 288530 + }, + { + "epoch": 0.64, + "learning_rate": 1.785083107760453e-05, + "loss": 0.1157, + "step": 288540 + }, + { + "epoch": 0.64, + "learning_rate": 1.7849712534395206e-05, + "loss": 0.1141, + "step": 288550 + }, + { + "epoch": 0.64, + "learning_rate": 1.784859399118588e-05, + "loss": 0.1165, + "step": 288560 + }, + { + "epoch": 0.64, + "learning_rate": 1.7847475447976555e-05, + "loss": 0.1151, + "step": 288570 + }, + { + "epoch": 0.64, + "learning_rate": 1.784635690476723e-05, + "loss": 0.1215, + "step": 288580 + }, + { + "epoch": 0.64, + "learning_rate": 1.7845238361557908e-05, + "loss": 0.1121, + "step": 288590 + }, + { + "epoch": 0.64, + "learning_rate": 1.7844119818348583e-05, + "loss": 0.1132, + "step": 288600 + }, + { + "epoch": 0.64, + "learning_rate": 1.784300127513926e-05, + "loss": 0.114, + "step": 288610 + }, + { + "epoch": 0.64, + "learning_rate": 1.7841882731929935e-05, + "loss": 0.1152, + "step": 288620 + }, + { + "epoch": 0.64, + "learning_rate": 1.784076418872061e-05, + "loss": 0.1171, + "step": 288630 + }, + { + "epoch": 0.64, + "learning_rate": 1.7839645645511287e-05, + "loss": 0.1192, + "step": 288640 + }, + { + "epoch": 0.64, + "learning_rate": 1.7838527102301962e-05, + "loss": 0.1129, + "step": 288650 + }, + { + "epoch": 0.64, + "learning_rate": 1.783740855909264e-05, + "loss": 0.1099, + "step": 288660 + }, + { + "epoch": 0.64, + "learning_rate": 1.7836290015883314e-05, + "loss": 0.1125, + "step": 288670 + }, + { + "epoch": 0.64, + "learning_rate": 1.783517147267399e-05, + "loss": 0.1197, + "step": 288680 + }, + { + "epoch": 0.64, + "learning_rate": 1.7834052929464667e-05, + "loss": 0.111, + "step": 288690 + }, + { + "epoch": 0.64, + "learning_rate": 1.783293438625534e-05, + "loss": 0.117, + "step": 288700 + }, + { + "epoch": 0.64, + "learning_rate": 1.783181584304602e-05, + "loss": 0.1109, + "step": 288710 + }, + { + "epoch": 0.64, + "learning_rate": 1.7830697299836694e-05, + "loss": 0.1124, + "step": 288720 + }, + { + "epoch": 0.64, + "learning_rate": 1.7829690610948303e-05, + "loss": 0.1182, + "step": 288730 + }, + { + "epoch": 0.64, + "learning_rate": 1.7828572067738977e-05, + "loss": 0.1159, + "step": 288740 + }, + { + "epoch": 0.64, + "learning_rate": 1.7827453524529652e-05, + "loss": 0.1144, + "step": 288750 + }, + { + "epoch": 0.64, + "learning_rate": 1.782633498132033e-05, + "loss": 0.1136, + "step": 288760 + }, + { + "epoch": 0.64, + "learning_rate": 1.7825216438111008e-05, + "loss": 0.1142, + "step": 288770 + }, + { + "epoch": 0.64, + "learning_rate": 1.7824097894901682e-05, + "loss": 0.1139, + "step": 288780 + }, + { + "epoch": 0.64, + "learning_rate": 1.7822979351692357e-05, + "loss": 0.111, + "step": 288790 + }, + { + "epoch": 0.64, + "learning_rate": 1.782186080848303e-05, + "loss": 0.1195, + "step": 288800 + }, + { + "epoch": 0.64, + "learning_rate": 1.7820742265273706e-05, + "loss": 0.1119, + "step": 288810 + }, + { + "epoch": 0.64, + "learning_rate": 1.7819623722064384e-05, + "loss": 0.1165, + "step": 288820 + }, + { + "epoch": 0.64, + "learning_rate": 1.781850517885506e-05, + "loss": 0.1142, + "step": 288830 + }, + { + "epoch": 0.64, + "learning_rate": 1.7817386635645736e-05, + "loss": 0.1118, + "step": 288840 + }, + { + "epoch": 0.64, + "learning_rate": 1.781626809243641e-05, + "loss": 0.114, + "step": 288850 + }, + { + "epoch": 0.64, + "learning_rate": 1.7815149549227085e-05, + "loss": 0.1126, + "step": 288860 + }, + { + "epoch": 0.64, + "learning_rate": 1.7814031006017763e-05, + "loss": 0.1166, + "step": 288870 + }, + { + "epoch": 0.64, + "learning_rate": 1.781291246280844e-05, + "loss": 0.1145, + "step": 288880 + }, + { + "epoch": 0.64, + "learning_rate": 1.7811793919599116e-05, + "loss": 0.1131, + "step": 288890 + }, + { + "epoch": 0.64, + "learning_rate": 1.781067537638979e-05, + "loss": 0.1123, + "step": 288900 + }, + { + "epoch": 0.64, + "learning_rate": 1.7809556833180465e-05, + "loss": 0.1146, + "step": 288910 + }, + { + "epoch": 0.64, + "learning_rate": 1.7808438289971143e-05, + "loss": 0.1155, + "step": 288920 + }, + { + "epoch": 0.64, + "learning_rate": 1.780731974676182e-05, + "loss": 0.1132, + "step": 288930 + }, + { + "epoch": 0.64, + "learning_rate": 1.7806201203552495e-05, + "loss": 0.1121, + "step": 288940 + }, + { + "epoch": 0.64, + "learning_rate": 1.780508266034317e-05, + "loss": 0.1172, + "step": 288950 + }, + { + "epoch": 0.64, + "learning_rate": 1.7803964117133844e-05, + "loss": 0.1175, + "step": 288960 + }, + { + "epoch": 0.65, + "learning_rate": 1.780284557392452e-05, + "loss": 0.1171, + "step": 288970 + }, + { + "epoch": 0.65, + "learning_rate": 1.78017270307152e-05, + "loss": 0.1181, + "step": 288980 + }, + { + "epoch": 0.65, + "learning_rate": 1.7800608487505875e-05, + "loss": 0.1148, + "step": 288990 + }, + { + "epoch": 0.65, + "learning_rate": 1.779948994429655e-05, + "loss": 0.1167, + "step": 289000 + }, + { + "epoch": 0.65, + "learning_rate": 1.7798371401087224e-05, + "loss": 0.111, + "step": 289010 + }, + { + "epoch": 0.65, + "learning_rate": 1.7797252857877898e-05, + "loss": 0.1145, + "step": 289020 + }, + { + "epoch": 0.65, + "learning_rate": 1.7796134314668576e-05, + "loss": 0.1199, + "step": 289030 + }, + { + "epoch": 0.65, + "learning_rate": 1.7795015771459254e-05, + "loss": 0.1155, + "step": 289040 + }, + { + "epoch": 0.65, + "learning_rate": 1.779389722824993e-05, + "loss": 0.1178, + "step": 289050 + }, + { + "epoch": 0.65, + "learning_rate": 1.7792778685040603e-05, + "loss": 0.1147, + "step": 289060 + }, + { + "epoch": 0.65, + "learning_rate": 1.7791660141831278e-05, + "loss": 0.1129, + "step": 289070 + }, + { + "epoch": 0.65, + "learning_rate": 1.7790541598621956e-05, + "loss": 0.1185, + "step": 289080 + }, + { + "epoch": 0.65, + "learning_rate": 1.7789423055412634e-05, + "loss": 0.1174, + "step": 289090 + }, + { + "epoch": 0.65, + "learning_rate": 1.7788304512203308e-05, + "loss": 0.1159, + "step": 289100 + }, + { + "epoch": 0.65, + "learning_rate": 1.7787185968993983e-05, + "loss": 0.1173, + "step": 289110 + }, + { + "epoch": 0.65, + "learning_rate": 1.7786067425784657e-05, + "loss": 0.117, + "step": 289120 + }, + { + "epoch": 0.65, + "learning_rate": 1.7784948882575335e-05, + "loss": 0.1145, + "step": 289130 + }, + { + "epoch": 0.65, + "learning_rate": 1.7783830339366013e-05, + "loss": 0.1117, + "step": 289140 + }, + { + "epoch": 0.65, + "learning_rate": 1.7782711796156688e-05, + "loss": 0.1171, + "step": 289150 + }, + { + "epoch": 0.65, + "learning_rate": 1.7781593252947362e-05, + "loss": 0.1152, + "step": 289160 + }, + { + "epoch": 0.65, + "learning_rate": 1.7780474709738037e-05, + "loss": 0.112, + "step": 289170 + }, + { + "epoch": 0.65, + "learning_rate": 1.777935616652871e-05, + "loss": 0.1109, + "step": 289180 + }, + { + "epoch": 0.65, + "learning_rate": 1.7778237623319393e-05, + "loss": 0.1141, + "step": 289190 + }, + { + "epoch": 0.65, + "learning_rate": 1.7777119080110067e-05, + "loss": 0.1165, + "step": 289200 + }, + { + "epoch": 0.65, + "learning_rate": 1.777600053690074e-05, + "loss": 0.1158, + "step": 289210 + }, + { + "epoch": 0.65, + "learning_rate": 1.7774881993691416e-05, + "loss": 0.1166, + "step": 289220 + }, + { + "epoch": 0.65, + "learning_rate": 1.777376345048209e-05, + "loss": 0.1129, + "step": 289230 + }, + { + "epoch": 0.65, + "learning_rate": 1.777264490727277e-05, + "loss": 0.1124, + "step": 289240 + }, + { + "epoch": 0.65, + "learning_rate": 1.7771526364063447e-05, + "loss": 0.1177, + "step": 289250 + }, + { + "epoch": 0.65, + "learning_rate": 1.777040782085412e-05, + "loss": 0.117, + "step": 289260 + }, + { + "epoch": 0.65, + "learning_rate": 1.7769289277644796e-05, + "loss": 0.1178, + "step": 289270 + }, + { + "epoch": 0.65, + "learning_rate": 1.776817073443547e-05, + "loss": 0.1152, + "step": 289280 + }, + { + "epoch": 0.65, + "learning_rate": 1.7767052191226148e-05, + "loss": 0.1188, + "step": 289290 + }, + { + "epoch": 0.65, + "learning_rate": 1.7765933648016826e-05, + "loss": 0.114, + "step": 289300 + }, + { + "epoch": 0.65, + "learning_rate": 1.77648151048075e-05, + "loss": 0.1157, + "step": 289310 + }, + { + "epoch": 0.65, + "learning_rate": 1.7763696561598175e-05, + "loss": 0.1129, + "step": 289320 + }, + { + "epoch": 0.65, + "learning_rate": 1.776257801838885e-05, + "loss": 0.1205, + "step": 289330 + }, + { + "epoch": 0.65, + "learning_rate": 1.7761459475179528e-05, + "loss": 0.1105, + "step": 289340 + }, + { + "epoch": 0.65, + "learning_rate": 1.7760340931970205e-05, + "loss": 0.1157, + "step": 289350 + }, + { + "epoch": 0.65, + "learning_rate": 1.775922238876088e-05, + "loss": 0.1158, + "step": 289360 + }, + { + "epoch": 0.65, + "learning_rate": 1.7758103845551555e-05, + "loss": 0.1143, + "step": 289370 + }, + { + "epoch": 0.65, + "learning_rate": 1.775698530234223e-05, + "loss": 0.1191, + "step": 289380 + }, + { + "epoch": 0.65, + "learning_rate": 1.7755866759132904e-05, + "loss": 0.1147, + "step": 289390 + }, + { + "epoch": 0.65, + "learning_rate": 1.775474821592358e-05, + "loss": 0.1154, + "step": 289400 + }, + { + "epoch": 0.65, + "learning_rate": 1.775362967271426e-05, + "loss": 0.1143, + "step": 289410 + }, + { + "epoch": 0.65, + "learning_rate": 1.7752511129504934e-05, + "loss": 0.1162, + "step": 289420 + }, + { + "epoch": 0.65, + "learning_rate": 1.775139258629561e-05, + "loss": 0.1194, + "step": 289430 + }, + { + "epoch": 0.65, + "learning_rate": 1.7750274043086283e-05, + "loss": 0.1163, + "step": 289440 + }, + { + "epoch": 0.65, + "learning_rate": 1.774915549987696e-05, + "loss": 0.1116, + "step": 289450 + }, + { + "epoch": 0.65, + "learning_rate": 1.774803695666764e-05, + "loss": 0.1168, + "step": 289460 + }, + { + "epoch": 0.65, + "learning_rate": 1.7746918413458313e-05, + "loss": 0.1152, + "step": 289470 + }, + { + "epoch": 0.65, + "learning_rate": 1.7745799870248988e-05, + "loss": 0.116, + "step": 289480 + }, + { + "epoch": 0.65, + "learning_rate": 1.7744681327039663e-05, + "loss": 0.1192, + "step": 289490 + }, + { + "epoch": 0.65, + "learning_rate": 1.774356278383034e-05, + "loss": 0.1127, + "step": 289500 + }, + { + "epoch": 0.65, + "learning_rate": 1.774244424062102e-05, + "loss": 0.113, + "step": 289510 + }, + { + "epoch": 0.65, + "learning_rate": 1.7741325697411693e-05, + "loss": 0.1118, + "step": 289520 + }, + { + "epoch": 0.65, + "learning_rate": 1.7740207154202368e-05, + "loss": 0.1158, + "step": 289530 + }, + { + "epoch": 0.65, + "learning_rate": 1.7739088610993042e-05, + "loss": 0.1139, + "step": 289540 + }, + { + "epoch": 0.65, + "learning_rate": 1.773797006778372e-05, + "loss": 0.1157, + "step": 289550 + }, + { + "epoch": 0.65, + "learning_rate": 1.7736851524574395e-05, + "loss": 0.1073, + "step": 289560 + }, + { + "epoch": 0.65, + "learning_rate": 1.7735732981365072e-05, + "loss": 0.1191, + "step": 289570 + }, + { + "epoch": 0.65, + "learning_rate": 1.7734614438155747e-05, + "loss": 0.1132, + "step": 289580 + }, + { + "epoch": 0.65, + "learning_rate": 1.773349589494642e-05, + "loss": 0.1153, + "step": 289590 + }, + { + "epoch": 0.65, + "learning_rate": 1.77323773517371e-05, + "loss": 0.117, + "step": 289600 + }, + { + "epoch": 0.65, + "learning_rate": 1.7731258808527774e-05, + "loss": 0.112, + "step": 289610 + }, + { + "epoch": 0.65, + "learning_rate": 1.7730140265318452e-05, + "loss": 0.1143, + "step": 289620 + }, + { + "epoch": 0.65, + "learning_rate": 1.7729021722109126e-05, + "loss": 0.1196, + "step": 289630 + }, + { + "epoch": 0.65, + "learning_rate": 1.77279031788998e-05, + "loss": 0.1156, + "step": 289640 + }, + { + "epoch": 0.65, + "learning_rate": 1.7726784635690476e-05, + "loss": 0.1124, + "step": 289650 + }, + { + "epoch": 0.65, + "learning_rate": 1.7725666092481153e-05, + "loss": 0.1149, + "step": 289660 + }, + { + "epoch": 0.65, + "learning_rate": 1.772454754927183e-05, + "loss": 0.1173, + "step": 289670 + }, + { + "epoch": 0.65, + "learning_rate": 1.7723429006062506e-05, + "loss": 0.1188, + "step": 289680 + }, + { + "epoch": 0.65, + "learning_rate": 1.772231046285318e-05, + "loss": 0.1151, + "step": 289690 + }, + { + "epoch": 0.65, + "learning_rate": 1.7721191919643855e-05, + "loss": 0.1187, + "step": 289700 + }, + { + "epoch": 0.65, + "learning_rate": 1.7720073376434533e-05, + "loss": 0.1161, + "step": 289710 + }, + { + "epoch": 0.65, + "learning_rate": 1.7718954833225207e-05, + "loss": 0.1159, + "step": 289720 + }, + { + "epoch": 0.65, + "learning_rate": 1.7717836290015885e-05, + "loss": 0.116, + "step": 289730 + }, + { + "epoch": 0.65, + "learning_rate": 1.771671774680656e-05, + "loss": 0.1143, + "step": 289740 + }, + { + "epoch": 0.65, + "learning_rate": 1.7715599203597234e-05, + "loss": 0.1136, + "step": 289750 + }, + { + "epoch": 0.65, + "learning_rate": 1.7714480660387912e-05, + "loss": 0.1203, + "step": 289760 + }, + { + "epoch": 0.65, + "learning_rate": 1.7713362117178587e-05, + "loss": 0.114, + "step": 289770 + }, + { + "epoch": 0.65, + "learning_rate": 1.7712243573969265e-05, + "loss": 0.1146, + "step": 289780 + }, + { + "epoch": 0.65, + "learning_rate": 1.771112503075994e-05, + "loss": 0.1128, + "step": 289790 + }, + { + "epoch": 0.65, + "learning_rate": 1.7710006487550614e-05, + "loss": 0.1168, + "step": 289800 + }, + { + "epoch": 0.65, + "learning_rate": 1.7708887944341292e-05, + "loss": 0.1167, + "step": 289810 + }, + { + "epoch": 0.65, + "learning_rate": 1.7707769401131966e-05, + "loss": 0.1144, + "step": 289820 + }, + { + "epoch": 0.65, + "learning_rate": 1.7706650857922644e-05, + "loss": 0.1166, + "step": 289830 + }, + { + "epoch": 0.65, + "learning_rate": 1.770553231471332e-05, + "loss": 0.1128, + "step": 289840 + }, + { + "epoch": 0.65, + "learning_rate": 1.7704413771503993e-05, + "loss": 0.1129, + "step": 289850 + }, + { + "epoch": 0.65, + "learning_rate": 1.7703295228294668e-05, + "loss": 0.116, + "step": 289860 + }, + { + "epoch": 0.65, + "learning_rate": 1.7702176685085346e-05, + "loss": 0.1201, + "step": 289870 + }, + { + "epoch": 0.65, + "learning_rate": 1.770105814187602e-05, + "loss": 0.1166, + "step": 289880 + }, + { + "epoch": 0.65, + "learning_rate": 1.76999395986667e-05, + "loss": 0.117, + "step": 289890 + }, + { + "epoch": 0.65, + "learning_rate": 1.7698821055457373e-05, + "loss": 0.1182, + "step": 289900 + }, + { + "epoch": 0.65, + "learning_rate": 1.7697702512248047e-05, + "loss": 0.1128, + "step": 289910 + }, + { + "epoch": 0.65, + "learning_rate": 1.7696583969038725e-05, + "loss": 0.1223, + "step": 289920 + }, + { + "epoch": 0.65, + "learning_rate": 1.76954654258294e-05, + "loss": 0.1154, + "step": 289930 + }, + { + "epoch": 0.65, + "learning_rate": 1.7694346882620078e-05, + "loss": 0.1183, + "step": 289940 + }, + { + "epoch": 0.65, + "learning_rate": 1.7693228339410752e-05, + "loss": 0.1128, + "step": 289950 + }, + { + "epoch": 0.65, + "learning_rate": 1.7692109796201427e-05, + "loss": 0.1106, + "step": 289960 + }, + { + "epoch": 0.65, + "learning_rate": 1.7690991252992105e-05, + "loss": 0.1116, + "step": 289970 + }, + { + "epoch": 0.65, + "learning_rate": 1.768987270978278e-05, + "loss": 0.1114, + "step": 289980 + }, + { + "epoch": 0.65, + "learning_rate": 1.7688754166573457e-05, + "loss": 0.115, + "step": 289990 + }, + { + "epoch": 0.65, + "learning_rate": 1.7687635623364132e-05, + "loss": 0.1085, + "step": 290000 + }, + { + "epoch": 0.65, + "learning_rate": 1.7686517080154806e-05, + "loss": 0.1152, + "step": 290010 + }, + { + "epoch": 0.65, + "learning_rate": 1.7685398536945484e-05, + "loss": 0.1136, + "step": 290020 + }, + { + "epoch": 0.65, + "learning_rate": 1.768427999373616e-05, + "loss": 0.1138, + "step": 290030 + }, + { + "epoch": 0.65, + "learning_rate": 1.7683161450526833e-05, + "loss": 0.1103, + "step": 290040 + }, + { + "epoch": 0.65, + "learning_rate": 1.768204290731751e-05, + "loss": 0.1079, + "step": 290050 + }, + { + "epoch": 0.65, + "learning_rate": 1.7680924364108186e-05, + "loss": 0.1177, + "step": 290060 + }, + { + "epoch": 0.65, + "learning_rate": 1.767980582089886e-05, + "loss": 0.1147, + "step": 290070 + }, + { + "epoch": 0.65, + "learning_rate": 1.767868727768954e-05, + "loss": 0.1187, + "step": 290080 + }, + { + "epoch": 0.65, + "learning_rate": 1.7677568734480213e-05, + "loss": 0.1174, + "step": 290090 + }, + { + "epoch": 0.65, + "learning_rate": 1.767645019127089e-05, + "loss": 0.1174, + "step": 290100 + }, + { + "epoch": 0.65, + "learning_rate": 1.7675331648061565e-05, + "loss": 0.1158, + "step": 290110 + }, + { + "epoch": 0.65, + "learning_rate": 1.767421310485224e-05, + "loss": 0.1119, + "step": 290120 + }, + { + "epoch": 0.65, + "learning_rate": 1.7673094561642918e-05, + "loss": 0.115, + "step": 290130 + }, + { + "epoch": 0.65, + "learning_rate": 1.7671976018433592e-05, + "loss": 0.1095, + "step": 290140 + }, + { + "epoch": 0.65, + "learning_rate": 1.767085747522427e-05, + "loss": 0.1102, + "step": 290150 + }, + { + "epoch": 0.65, + "learning_rate": 1.7669738932014945e-05, + "loss": 0.119, + "step": 290160 + }, + { + "epoch": 0.65, + "learning_rate": 1.766862038880562e-05, + "loss": 0.1115, + "step": 290170 + }, + { + "epoch": 0.65, + "learning_rate": 1.7667501845596297e-05, + "loss": 0.1157, + "step": 290180 + }, + { + "epoch": 0.65, + "learning_rate": 1.7666383302386972e-05, + "loss": 0.1112, + "step": 290190 + }, + { + "epoch": 0.65, + "learning_rate": 1.7665264759177646e-05, + "loss": 0.11, + "step": 290200 + }, + { + "epoch": 0.65, + "learning_rate": 1.7664146215968324e-05, + "loss": 0.11, + "step": 290210 + }, + { + "epoch": 0.65, + "learning_rate": 1.7663027672759e-05, + "loss": 0.1126, + "step": 290220 + }, + { + "epoch": 0.65, + "learning_rate": 1.7661909129549677e-05, + "loss": 0.1154, + "step": 290230 + }, + { + "epoch": 0.65, + "learning_rate": 1.766079058634035e-05, + "loss": 0.119, + "step": 290240 + }, + { + "epoch": 0.65, + "learning_rate": 1.7659672043131026e-05, + "loss": 0.1146, + "step": 290250 + }, + { + "epoch": 0.65, + "learning_rate": 1.7658553499921704e-05, + "loss": 0.1144, + "step": 290260 + }, + { + "epoch": 0.65, + "learning_rate": 1.7657434956712378e-05, + "loss": 0.1187, + "step": 290270 + }, + { + "epoch": 0.65, + "learning_rate": 1.7656316413503056e-05, + "loss": 0.1173, + "step": 290280 + }, + { + "epoch": 0.65, + "learning_rate": 1.765519787029373e-05, + "loss": 0.1179, + "step": 290290 + }, + { + "epoch": 0.65, + "learning_rate": 1.7654079327084405e-05, + "loss": 0.1148, + "step": 290300 + }, + { + "epoch": 0.65, + "learning_rate": 1.7652960783875083e-05, + "loss": 0.1143, + "step": 290310 + }, + { + "epoch": 0.65, + "learning_rate": 1.7651842240665758e-05, + "loss": 0.112, + "step": 290320 + }, + { + "epoch": 0.65, + "learning_rate": 1.7650723697456432e-05, + "loss": 0.1143, + "step": 290330 + }, + { + "epoch": 0.65, + "learning_rate": 1.764960515424711e-05, + "loss": 0.1164, + "step": 290340 + }, + { + "epoch": 0.65, + "learning_rate": 1.7648486611037785e-05, + "loss": 0.1202, + "step": 290350 + }, + { + "epoch": 0.65, + "learning_rate": 1.764736806782846e-05, + "loss": 0.1138, + "step": 290360 + }, + { + "epoch": 0.65, + "learning_rate": 1.7646249524619137e-05, + "loss": 0.1135, + "step": 290370 + }, + { + "epoch": 0.65, + "learning_rate": 1.7645130981409812e-05, + "loss": 0.1112, + "step": 290380 + }, + { + "epoch": 0.65, + "learning_rate": 1.764401243820049e-05, + "loss": 0.1174, + "step": 290390 + }, + { + "epoch": 0.65, + "learning_rate": 1.7642893894991164e-05, + "loss": 0.1155, + "step": 290400 + }, + { + "epoch": 0.65, + "learning_rate": 1.764177535178184e-05, + "loss": 0.1196, + "step": 290410 + }, + { + "epoch": 0.65, + "learning_rate": 1.7640656808572517e-05, + "loss": 0.1175, + "step": 290420 + }, + { + "epoch": 0.65, + "learning_rate": 1.763953826536319e-05, + "loss": 0.1164, + "step": 290430 + }, + { + "epoch": 0.65, + "learning_rate": 1.763841972215387e-05, + "loss": 0.1131, + "step": 290440 + }, + { + "epoch": 0.65, + "learning_rate": 1.7637301178944544e-05, + "loss": 0.1166, + "step": 290450 + }, + { + "epoch": 0.65, + "learning_rate": 1.7636182635735218e-05, + "loss": 0.1123, + "step": 290460 + }, + { + "epoch": 0.65, + "learning_rate": 1.7635064092525896e-05, + "loss": 0.1104, + "step": 290470 + }, + { + "epoch": 0.65, + "learning_rate": 1.763394554931657e-05, + "loss": 0.1152, + "step": 290480 + }, + { + "epoch": 0.65, + "learning_rate": 1.763282700610725e-05, + "loss": 0.1108, + "step": 290490 + }, + { + "epoch": 0.65, + "learning_rate": 1.7631708462897923e-05, + "loss": 0.1104, + "step": 290500 + }, + { + "epoch": 0.65, + "learning_rate": 1.7630589919688598e-05, + "loss": 0.1122, + "step": 290510 + }, + { + "epoch": 0.65, + "learning_rate": 1.7629471376479272e-05, + "loss": 0.1119, + "step": 290520 + }, + { + "epoch": 0.65, + "learning_rate": 1.762835283326995e-05, + "loss": 0.1183, + "step": 290530 + }, + { + "epoch": 0.65, + "learning_rate": 1.7627234290060625e-05, + "loss": 0.1125, + "step": 290540 + }, + { + "epoch": 0.65, + "learning_rate": 1.7626115746851303e-05, + "loss": 0.1143, + "step": 290550 + }, + { + "epoch": 0.65, + "learning_rate": 1.7624997203641977e-05, + "loss": 0.1173, + "step": 290560 + }, + { + "epoch": 0.65, + "learning_rate": 1.7623878660432652e-05, + "loss": 0.1154, + "step": 290570 + }, + { + "epoch": 0.65, + "learning_rate": 1.762276011722333e-05, + "loss": 0.1125, + "step": 290580 + }, + { + "epoch": 0.65, + "learning_rate": 1.7621641574014004e-05, + "loss": 0.1138, + "step": 290590 + }, + { + "epoch": 0.65, + "learning_rate": 1.7620523030804682e-05, + "loss": 0.1174, + "step": 290600 + }, + { + "epoch": 0.65, + "learning_rate": 1.7619404487595357e-05, + "loss": 0.1156, + "step": 290610 + }, + { + "epoch": 0.65, + "learning_rate": 1.761828594438603e-05, + "loss": 0.1168, + "step": 290620 + }, + { + "epoch": 0.65, + "learning_rate": 1.761716740117671e-05, + "loss": 0.1126, + "step": 290630 + }, + { + "epoch": 0.65, + "learning_rate": 1.7616048857967384e-05, + "loss": 0.1148, + "step": 290640 + }, + { + "epoch": 0.65, + "learning_rate": 1.761493031475806e-05, + "loss": 0.1122, + "step": 290650 + }, + { + "epoch": 0.65, + "learning_rate": 1.7613811771548736e-05, + "loss": 0.1129, + "step": 290660 + }, + { + "epoch": 0.65, + "learning_rate": 1.761269322833941e-05, + "loss": 0.1188, + "step": 290670 + }, + { + "epoch": 0.65, + "learning_rate": 1.7611574685130085e-05, + "loss": 0.1148, + "step": 290680 + }, + { + "epoch": 0.65, + "learning_rate": 1.7610456141920763e-05, + "loss": 0.1152, + "step": 290690 + }, + { + "epoch": 0.65, + "learning_rate": 1.760933759871144e-05, + "loss": 0.1145, + "step": 290700 + }, + { + "epoch": 0.65, + "learning_rate": 1.7608219055502116e-05, + "loss": 0.1098, + "step": 290710 + }, + { + "epoch": 0.65, + "learning_rate": 1.760710051229279e-05, + "loss": 0.1193, + "step": 290720 + }, + { + "epoch": 0.65, + "learning_rate": 1.76060938234044e-05, + "loss": 0.1183, + "step": 290730 + }, + { + "epoch": 0.65, + "learning_rate": 1.7604975280195073e-05, + "loss": 0.1126, + "step": 290740 + }, + { + "epoch": 0.65, + "learning_rate": 1.7603856736985748e-05, + "loss": 0.1079, + "step": 290750 + }, + { + "epoch": 0.65, + "learning_rate": 1.7602738193776426e-05, + "loss": 0.1098, + "step": 290760 + }, + { + "epoch": 0.65, + "learning_rate": 1.7601619650567104e-05, + "loss": 0.1152, + "step": 290770 + }, + { + "epoch": 0.65, + "learning_rate": 1.760050110735778e-05, + "loss": 0.1121, + "step": 290780 + }, + { + "epoch": 0.65, + "learning_rate": 1.7599382564148453e-05, + "loss": 0.1126, + "step": 290790 + }, + { + "epoch": 0.65, + "learning_rate": 1.7598264020939128e-05, + "loss": 0.1165, + "step": 290800 + }, + { + "epoch": 0.65, + "learning_rate": 1.7597145477729805e-05, + "loss": 0.1107, + "step": 290810 + }, + { + "epoch": 0.65, + "learning_rate": 1.7596026934520483e-05, + "loss": 0.1128, + "step": 290820 + }, + { + "epoch": 0.65, + "learning_rate": 1.7594908391311158e-05, + "loss": 0.1172, + "step": 290830 + }, + { + "epoch": 0.65, + "learning_rate": 1.7593789848101832e-05, + "loss": 0.1124, + "step": 290840 + }, + { + "epoch": 0.65, + "learning_rate": 1.7592671304892507e-05, + "loss": 0.1128, + "step": 290850 + }, + { + "epoch": 0.65, + "learning_rate": 1.7591552761683185e-05, + "loss": 0.1155, + "step": 290860 + }, + { + "epoch": 0.65, + "learning_rate": 1.7590434218473863e-05, + "loss": 0.1169, + "step": 290870 + }, + { + "epoch": 0.65, + "learning_rate": 1.7589315675264537e-05, + "loss": 0.1172, + "step": 290880 + }, + { + "epoch": 0.65, + "learning_rate": 1.7588197132055212e-05, + "loss": 0.1119, + "step": 290890 + }, + { + "epoch": 0.65, + "learning_rate": 1.7587078588845886e-05, + "loss": 0.1163, + "step": 290900 + }, + { + "epoch": 0.65, + "learning_rate": 1.758596004563656e-05, + "loss": 0.1181, + "step": 290910 + }, + { + "epoch": 0.65, + "learning_rate": 1.758484150242724e-05, + "loss": 0.114, + "step": 290920 + }, + { + "epoch": 0.65, + "learning_rate": 1.7583722959217917e-05, + "loss": 0.1172, + "step": 290930 + }, + { + "epoch": 0.65, + "learning_rate": 1.758260441600859e-05, + "loss": 0.1136, + "step": 290940 + }, + { + "epoch": 0.65, + "learning_rate": 1.7581485872799266e-05, + "loss": 0.117, + "step": 290950 + }, + { + "epoch": 0.65, + "learning_rate": 1.758036732958994e-05, + "loss": 0.1124, + "step": 290960 + }, + { + "epoch": 0.65, + "learning_rate": 1.757924878638062e-05, + "loss": 0.1133, + "step": 290970 + }, + { + "epoch": 0.65, + "learning_rate": 1.7578130243171296e-05, + "loss": 0.1151, + "step": 290980 + }, + { + "epoch": 0.65, + "learning_rate": 1.757701169996197e-05, + "loss": 0.1142, + "step": 290990 + }, + { + "epoch": 0.65, + "learning_rate": 1.7575893156752645e-05, + "loss": 0.1154, + "step": 291000 + }, + { + "epoch": 0.65, + "learning_rate": 1.757477461354332e-05, + "loss": 0.1184, + "step": 291010 + }, + { + "epoch": 0.65, + "learning_rate": 1.7573656070333998e-05, + "loss": 0.1145, + "step": 291020 + }, + { + "epoch": 0.65, + "learning_rate": 1.7572537527124676e-05, + "loss": 0.1157, + "step": 291030 + }, + { + "epoch": 0.65, + "learning_rate": 1.757141898391535e-05, + "loss": 0.1164, + "step": 291040 + }, + { + "epoch": 0.65, + "learning_rate": 1.7570300440706025e-05, + "loss": 0.1163, + "step": 291050 + }, + { + "epoch": 0.65, + "learning_rate": 1.75691818974967e-05, + "loss": 0.1129, + "step": 291060 + }, + { + "epoch": 0.65, + "learning_rate": 1.7568063354287377e-05, + "loss": 0.1097, + "step": 291070 + }, + { + "epoch": 0.65, + "learning_rate": 1.7566944811078055e-05, + "loss": 0.1155, + "step": 291080 + }, + { + "epoch": 0.65, + "learning_rate": 1.756582626786873e-05, + "loss": 0.1134, + "step": 291090 + }, + { + "epoch": 0.65, + "learning_rate": 1.7564707724659404e-05, + "loss": 0.1115, + "step": 291100 + }, + { + "epoch": 0.65, + "learning_rate": 1.756358918145008e-05, + "loss": 0.1165, + "step": 291110 + }, + { + "epoch": 0.65, + "learning_rate": 1.7562470638240753e-05, + "loss": 0.1129, + "step": 291120 + }, + { + "epoch": 0.65, + "learning_rate": 1.7561352095031435e-05, + "loss": 0.114, + "step": 291130 + }, + { + "epoch": 0.65, + "learning_rate": 1.756023355182211e-05, + "loss": 0.1144, + "step": 291140 + }, + { + "epoch": 0.65, + "learning_rate": 1.7559115008612784e-05, + "loss": 0.1121, + "step": 291150 + }, + { + "epoch": 0.65, + "learning_rate": 1.755799646540346e-05, + "loss": 0.1143, + "step": 291160 + }, + { + "epoch": 0.65, + "learning_rate": 1.7556877922194133e-05, + "loss": 0.1218, + "step": 291170 + }, + { + "epoch": 0.65, + "learning_rate": 1.755575937898481e-05, + "loss": 0.1133, + "step": 291180 + }, + { + "epoch": 0.65, + "learning_rate": 1.755464083577549e-05, + "loss": 0.1136, + "step": 291190 + }, + { + "epoch": 0.65, + "learning_rate": 1.7553522292566163e-05, + "loss": 0.11, + "step": 291200 + }, + { + "epoch": 0.65, + "learning_rate": 1.7552403749356838e-05, + "loss": 0.1177, + "step": 291210 + }, + { + "epoch": 0.65, + "learning_rate": 1.7551285206147512e-05, + "loss": 0.1227, + "step": 291220 + }, + { + "epoch": 0.65, + "learning_rate": 1.755016666293819e-05, + "loss": 0.1128, + "step": 291230 + }, + { + "epoch": 0.65, + "learning_rate": 1.7549048119728868e-05, + "loss": 0.1161, + "step": 291240 + }, + { + "epoch": 0.65, + "learning_rate": 1.7547929576519543e-05, + "loss": 0.1116, + "step": 291250 + }, + { + "epoch": 0.65, + "learning_rate": 1.7546811033310217e-05, + "loss": 0.115, + "step": 291260 + }, + { + "epoch": 0.65, + "learning_rate": 1.7545692490100892e-05, + "loss": 0.1123, + "step": 291270 + }, + { + "epoch": 0.65, + "learning_rate": 1.754457394689157e-05, + "loss": 0.1129, + "step": 291280 + }, + { + "epoch": 0.65, + "learning_rate": 1.7543455403682248e-05, + "loss": 0.1148, + "step": 291290 + }, + { + "epoch": 0.65, + "learning_rate": 1.7542336860472922e-05, + "loss": 0.1137, + "step": 291300 + }, + { + "epoch": 0.65, + "learning_rate": 1.7541218317263597e-05, + "loss": 0.1157, + "step": 291310 + }, + { + "epoch": 0.65, + "learning_rate": 1.754009977405427e-05, + "loss": 0.1168, + "step": 291320 + }, + { + "epoch": 0.65, + "learning_rate": 1.7538981230844946e-05, + "loss": 0.1112, + "step": 291330 + }, + { + "epoch": 0.65, + "learning_rate": 1.7537862687635627e-05, + "loss": 0.1136, + "step": 291340 + }, + { + "epoch": 0.65, + "learning_rate": 1.7536744144426302e-05, + "loss": 0.1123, + "step": 291350 + }, + { + "epoch": 0.65, + "learning_rate": 1.7535625601216976e-05, + "loss": 0.1115, + "step": 291360 + }, + { + "epoch": 0.65, + "learning_rate": 1.753450705800765e-05, + "loss": 0.1153, + "step": 291370 + }, + { + "epoch": 0.65, + "learning_rate": 1.7533388514798325e-05, + "loss": 0.1147, + "step": 291380 + }, + { + "epoch": 0.65, + "learning_rate": 1.7532269971589003e-05, + "loss": 0.1172, + "step": 291390 + }, + { + "epoch": 0.65, + "learning_rate": 1.753115142837968e-05, + "loss": 0.1174, + "step": 291400 + }, + { + "epoch": 0.65, + "learning_rate": 1.7530032885170356e-05, + "loss": 0.1167, + "step": 291410 + }, + { + "epoch": 0.65, + "learning_rate": 1.752891434196103e-05, + "loss": 0.1131, + "step": 291420 + }, + { + "epoch": 0.65, + "learning_rate": 1.7527795798751705e-05, + "loss": 0.1088, + "step": 291430 + }, + { + "epoch": 0.65, + "learning_rate": 1.7526677255542383e-05, + "loss": 0.1142, + "step": 291440 + }, + { + "epoch": 0.65, + "learning_rate": 1.752555871233306e-05, + "loss": 0.1185, + "step": 291450 + }, + { + "epoch": 0.65, + "learning_rate": 1.7524440169123735e-05, + "loss": 0.1167, + "step": 291460 + }, + { + "epoch": 0.65, + "learning_rate": 1.752332162591441e-05, + "loss": 0.115, + "step": 291470 + }, + { + "epoch": 0.65, + "learning_rate": 1.7522203082705084e-05, + "loss": 0.1154, + "step": 291480 + }, + { + "epoch": 0.65, + "learning_rate": 1.7521084539495762e-05, + "loss": 0.1117, + "step": 291490 + }, + { + "epoch": 0.65, + "learning_rate": 1.751996599628644e-05, + "loss": 0.1138, + "step": 291500 + }, + { + "epoch": 0.65, + "learning_rate": 1.7518847453077115e-05, + "loss": 0.1153, + "step": 291510 + }, + { + "epoch": 0.65, + "learning_rate": 1.751772890986779e-05, + "loss": 0.1169, + "step": 291520 + }, + { + "epoch": 0.65, + "learning_rate": 1.7516610366658464e-05, + "loss": 0.1152, + "step": 291530 + }, + { + "epoch": 0.65, + "learning_rate": 1.751549182344914e-05, + "loss": 0.1158, + "step": 291540 + }, + { + "epoch": 0.65, + "learning_rate": 1.7514373280239816e-05, + "loss": 0.1173, + "step": 291550 + }, + { + "epoch": 0.65, + "learning_rate": 1.7513254737030494e-05, + "loss": 0.1143, + "step": 291560 + }, + { + "epoch": 0.65, + "learning_rate": 1.751213619382117e-05, + "loss": 0.1129, + "step": 291570 + }, + { + "epoch": 0.65, + "learning_rate": 1.7511017650611843e-05, + "loss": 0.1094, + "step": 291580 + }, + { + "epoch": 0.65, + "learning_rate": 1.7509899107402518e-05, + "loss": 0.1108, + "step": 291590 + }, + { + "epoch": 0.65, + "learning_rate": 1.7508780564193196e-05, + "loss": 0.1118, + "step": 291600 + }, + { + "epoch": 0.65, + "learning_rate": 1.7507662020983874e-05, + "loss": 0.1208, + "step": 291610 + }, + { + "epoch": 0.65, + "learning_rate": 1.7506543477774548e-05, + "loss": 0.1203, + "step": 291620 + }, + { + "epoch": 0.65, + "learning_rate": 1.7505424934565223e-05, + "loss": 0.1175, + "step": 291630 + }, + { + "epoch": 0.65, + "learning_rate": 1.7504306391355897e-05, + "loss": 0.1136, + "step": 291640 + }, + { + "epoch": 0.65, + "learning_rate": 1.7503187848146575e-05, + "loss": 0.1119, + "step": 291650 + }, + { + "epoch": 0.65, + "learning_rate": 1.7502069304937253e-05, + "loss": 0.1175, + "step": 291660 + }, + { + "epoch": 0.65, + "learning_rate": 1.7500950761727928e-05, + "loss": 0.1176, + "step": 291670 + }, + { + "epoch": 0.65, + "learning_rate": 1.7499832218518602e-05, + "loss": 0.1175, + "step": 291680 + }, + { + "epoch": 0.65, + "learning_rate": 1.7498713675309277e-05, + "loss": 0.1157, + "step": 291690 + }, + { + "epoch": 0.65, + "learning_rate": 1.7497595132099955e-05, + "loss": 0.12, + "step": 291700 + }, + { + "epoch": 0.65, + "learning_rate": 1.749647658889063e-05, + "loss": 0.1163, + "step": 291710 + }, + { + "epoch": 0.65, + "learning_rate": 1.7495358045681307e-05, + "loss": 0.1177, + "step": 291720 + }, + { + "epoch": 0.65, + "learning_rate": 1.749423950247198e-05, + "loss": 0.1153, + "step": 291730 + }, + { + "epoch": 0.65, + "learning_rate": 1.7493120959262656e-05, + "loss": 0.1147, + "step": 291740 + }, + { + "epoch": 0.65, + "learning_rate": 1.7492002416053334e-05, + "loss": 0.112, + "step": 291750 + }, + { + "epoch": 0.65, + "learning_rate": 1.749088387284401e-05, + "loss": 0.1134, + "step": 291760 + }, + { + "epoch": 0.65, + "learning_rate": 1.7489765329634687e-05, + "loss": 0.1178, + "step": 291770 + }, + { + "epoch": 0.65, + "learning_rate": 1.748864678642536e-05, + "loss": 0.1141, + "step": 291780 + }, + { + "epoch": 0.65, + "learning_rate": 1.7487528243216036e-05, + "loss": 0.1168, + "step": 291790 + }, + { + "epoch": 0.65, + "learning_rate": 1.748640970000671e-05, + "loss": 0.1161, + "step": 291800 + }, + { + "epoch": 0.65, + "learning_rate": 1.7485291156797388e-05, + "loss": 0.1135, + "step": 291810 + }, + { + "epoch": 0.65, + "learning_rate": 1.7484172613588066e-05, + "loss": 0.1156, + "step": 291820 + }, + { + "epoch": 0.65, + "learning_rate": 1.748305407037874e-05, + "loss": 0.1152, + "step": 291830 + }, + { + "epoch": 0.65, + "learning_rate": 1.7481935527169415e-05, + "loss": 0.113, + "step": 291840 + }, + { + "epoch": 0.65, + "learning_rate": 1.748081698396009e-05, + "loss": 0.1136, + "step": 291850 + }, + { + "epoch": 0.65, + "learning_rate": 1.7479698440750768e-05, + "loss": 0.1144, + "step": 291860 + }, + { + "epoch": 0.65, + "learning_rate": 1.7478579897541442e-05, + "loss": 0.1108, + "step": 291870 + }, + { + "epoch": 0.65, + "learning_rate": 1.747746135433212e-05, + "loss": 0.1148, + "step": 291880 + }, + { + "epoch": 0.65, + "learning_rate": 1.7476342811122795e-05, + "loss": 0.1129, + "step": 291890 + }, + { + "epoch": 0.65, + "learning_rate": 1.747522426791347e-05, + "loss": 0.1167, + "step": 291900 + }, + { + "epoch": 0.65, + "learning_rate": 1.7474105724704147e-05, + "loss": 0.1119, + "step": 291910 + }, + { + "epoch": 0.65, + "learning_rate": 1.747298718149482e-05, + "loss": 0.1145, + "step": 291920 + }, + { + "epoch": 0.65, + "learning_rate": 1.74718686382855e-05, + "loss": 0.1108, + "step": 291930 + }, + { + "epoch": 0.65, + "learning_rate": 1.7470750095076174e-05, + "loss": 0.1062, + "step": 291940 + }, + { + "epoch": 0.65, + "learning_rate": 1.746963155186685e-05, + "loss": 0.1158, + "step": 291950 + }, + { + "epoch": 0.65, + "learning_rate": 1.7468513008657527e-05, + "loss": 0.1137, + "step": 291960 + }, + { + "epoch": 0.65, + "learning_rate": 1.74673944654482e-05, + "loss": 0.108, + "step": 291970 + }, + { + "epoch": 0.65, + "learning_rate": 1.7466275922238876e-05, + "loss": 0.1124, + "step": 291980 + }, + { + "epoch": 0.65, + "learning_rate": 1.7465157379029554e-05, + "loss": 0.1176, + "step": 291990 + }, + { + "epoch": 0.65, + "learning_rate": 1.7464038835820228e-05, + "loss": 0.1114, + "step": 292000 + }, + { + "epoch": 0.65, + "learning_rate": 1.7462920292610903e-05, + "loss": 0.1138, + "step": 292010 + }, + { + "epoch": 0.65, + "learning_rate": 1.746180174940158e-05, + "loss": 0.1137, + "step": 292020 + }, + { + "epoch": 0.65, + "learning_rate": 1.7460683206192255e-05, + "loss": 0.1139, + "step": 292030 + }, + { + "epoch": 0.65, + "learning_rate": 1.7459564662982933e-05, + "loss": 0.1159, + "step": 292040 + }, + { + "epoch": 0.65, + "learning_rate": 1.7458446119773608e-05, + "loss": 0.114, + "step": 292050 + }, + { + "epoch": 0.65, + "learning_rate": 1.7457327576564282e-05, + "loss": 0.1122, + "step": 292060 + }, + { + "epoch": 0.65, + "learning_rate": 1.745620903335496e-05, + "loss": 0.1176, + "step": 292070 + }, + { + "epoch": 0.65, + "learning_rate": 1.7455090490145635e-05, + "loss": 0.112, + "step": 292080 + }, + { + "epoch": 0.65, + "learning_rate": 1.7453971946936313e-05, + "loss": 0.1124, + "step": 292090 + }, + { + "epoch": 0.65, + "learning_rate": 1.7452853403726987e-05, + "loss": 0.1171, + "step": 292100 + }, + { + "epoch": 0.65, + "learning_rate": 1.745173486051766e-05, + "loss": 0.1109, + "step": 292110 + }, + { + "epoch": 0.65, + "learning_rate": 1.745061631730834e-05, + "loss": 0.1101, + "step": 292120 + }, + { + "epoch": 0.65, + "learning_rate": 1.7449497774099014e-05, + "loss": 0.1106, + "step": 292130 + }, + { + "epoch": 0.65, + "learning_rate": 1.744837923088969e-05, + "loss": 0.1186, + "step": 292140 + }, + { + "epoch": 0.65, + "learning_rate": 1.7447260687680367e-05, + "loss": 0.1126, + "step": 292150 + }, + { + "epoch": 0.65, + "learning_rate": 1.744614214447104e-05, + "loss": 0.1167, + "step": 292160 + }, + { + "epoch": 0.65, + "learning_rate": 1.744502360126172e-05, + "loss": 0.1154, + "step": 292170 + }, + { + "epoch": 0.65, + "learning_rate": 1.7443905058052394e-05, + "loss": 0.1114, + "step": 292180 + }, + { + "epoch": 0.65, + "learning_rate": 1.7442786514843068e-05, + "loss": 0.121, + "step": 292190 + }, + { + "epoch": 0.65, + "learning_rate": 1.7441667971633746e-05, + "loss": 0.1138, + "step": 292200 + }, + { + "epoch": 0.65, + "learning_rate": 1.744054942842442e-05, + "loss": 0.1172, + "step": 292210 + }, + { + "epoch": 0.65, + "learning_rate": 1.7439430885215095e-05, + "loss": 0.1152, + "step": 292220 + }, + { + "epoch": 0.65, + "learning_rate": 1.7438312342005773e-05, + "loss": 0.1153, + "step": 292230 + }, + { + "epoch": 0.65, + "learning_rate": 1.7437193798796448e-05, + "loss": 0.1088, + "step": 292240 + }, + { + "epoch": 0.65, + "learning_rate": 1.7436075255587125e-05, + "loss": 0.1118, + "step": 292250 + }, + { + "epoch": 0.65, + "learning_rate": 1.74349567123778e-05, + "loss": 0.1135, + "step": 292260 + }, + { + "epoch": 0.65, + "learning_rate": 1.7433838169168475e-05, + "loss": 0.1143, + "step": 292270 + }, + { + "epoch": 0.65, + "learning_rate": 1.7432719625959152e-05, + "loss": 0.1159, + "step": 292280 + }, + { + "epoch": 0.65, + "learning_rate": 1.7431601082749827e-05, + "loss": 0.1165, + "step": 292290 + }, + { + "epoch": 0.65, + "learning_rate": 1.74304825395405e-05, + "loss": 0.119, + "step": 292300 + }, + { + "epoch": 0.65, + "learning_rate": 1.742936399633118e-05, + "loss": 0.1159, + "step": 292310 + }, + { + "epoch": 0.65, + "learning_rate": 1.7428245453121854e-05, + "loss": 0.1193, + "step": 292320 + }, + { + "epoch": 0.65, + "learning_rate": 1.7427126909912532e-05, + "loss": 0.1093, + "step": 292330 + }, + { + "epoch": 0.65, + "learning_rate": 1.7426008366703207e-05, + "loss": 0.116, + "step": 292340 + }, + { + "epoch": 0.65, + "learning_rate": 1.742488982349388e-05, + "loss": 0.1151, + "step": 292350 + }, + { + "epoch": 0.65, + "learning_rate": 1.742377128028456e-05, + "loss": 0.1176, + "step": 292360 + }, + { + "epoch": 0.65, + "learning_rate": 1.7422652737075234e-05, + "loss": 0.1096, + "step": 292370 + }, + { + "epoch": 0.65, + "learning_rate": 1.742153419386591e-05, + "loss": 0.1157, + "step": 292380 + }, + { + "epoch": 0.65, + "learning_rate": 1.7420415650656586e-05, + "loss": 0.1141, + "step": 292390 + }, + { + "epoch": 0.65, + "learning_rate": 1.741929710744726e-05, + "loss": 0.1147, + "step": 292400 + }, + { + "epoch": 0.65, + "learning_rate": 1.741817856423794e-05, + "loss": 0.1121, + "step": 292410 + }, + { + "epoch": 0.65, + "learning_rate": 1.7417060021028613e-05, + "loss": 0.1126, + "step": 292420 + }, + { + "epoch": 0.65, + "learning_rate": 1.7415941477819288e-05, + "loss": 0.1139, + "step": 292430 + }, + { + "epoch": 0.65, + "learning_rate": 1.7414822934609965e-05, + "loss": 0.1104, + "step": 292440 + }, + { + "epoch": 0.65, + "learning_rate": 1.741370439140064e-05, + "loss": 0.1163, + "step": 292450 + }, + { + "epoch": 0.65, + "learning_rate": 1.7412585848191315e-05, + "loss": 0.1103, + "step": 292460 + }, + { + "epoch": 0.65, + "learning_rate": 1.7411467304981992e-05, + "loss": 0.1179, + "step": 292470 + }, + { + "epoch": 0.65, + "learning_rate": 1.7410348761772667e-05, + "loss": 0.1155, + "step": 292480 + }, + { + "epoch": 0.65, + "learning_rate": 1.7409230218563345e-05, + "loss": 0.1136, + "step": 292490 + }, + { + "epoch": 0.65, + "learning_rate": 1.740811167535402e-05, + "loss": 0.1151, + "step": 292500 + }, + { + "epoch": 0.65, + "learning_rate": 1.7406993132144694e-05, + "loss": 0.1182, + "step": 292510 + }, + { + "epoch": 0.65, + "learning_rate": 1.7405874588935372e-05, + "loss": 0.1126, + "step": 292520 + }, + { + "epoch": 0.65, + "learning_rate": 1.7404756045726046e-05, + "loss": 0.1159, + "step": 292530 + }, + { + "epoch": 0.65, + "learning_rate": 1.7403637502516724e-05, + "loss": 0.1109, + "step": 292540 + }, + { + "epoch": 0.65, + "learning_rate": 1.74025189593074e-05, + "loss": 0.1157, + "step": 292550 + }, + { + "epoch": 0.65, + "learning_rate": 1.7401400416098073e-05, + "loss": 0.1137, + "step": 292560 + }, + { + "epoch": 0.65, + "learning_rate": 1.740028187288875e-05, + "loss": 0.11, + "step": 292570 + }, + { + "epoch": 0.65, + "learning_rate": 1.7399163329679426e-05, + "loss": 0.1151, + "step": 292580 + }, + { + "epoch": 0.65, + "learning_rate": 1.7398044786470104e-05, + "loss": 0.117, + "step": 292590 + }, + { + "epoch": 0.65, + "learning_rate": 1.739692624326078e-05, + "loss": 0.1135, + "step": 292600 + }, + { + "epoch": 0.65, + "learning_rate": 1.7395807700051453e-05, + "loss": 0.1098, + "step": 292610 + }, + { + "epoch": 0.65, + "learning_rate": 1.7394689156842127e-05, + "loss": 0.1142, + "step": 292620 + }, + { + "epoch": 0.65, + "learning_rate": 1.7393570613632805e-05, + "loss": 0.1135, + "step": 292630 + }, + { + "epoch": 0.65, + "learning_rate": 1.7392452070423483e-05, + "loss": 0.1153, + "step": 292640 + }, + { + "epoch": 0.65, + "learning_rate": 1.7391333527214158e-05, + "loss": 0.1149, + "step": 292650 + }, + { + "epoch": 0.65, + "learning_rate": 1.7390214984004832e-05, + "loss": 0.1112, + "step": 292660 + }, + { + "epoch": 0.65, + "learning_rate": 1.7389096440795507e-05, + "loss": 0.1122, + "step": 292670 + }, + { + "epoch": 0.65, + "learning_rate": 1.7387977897586185e-05, + "loss": 0.1167, + "step": 292680 + }, + { + "epoch": 0.65, + "learning_rate": 1.738685935437686e-05, + "loss": 0.114, + "step": 292690 + }, + { + "epoch": 0.65, + "learning_rate": 1.7385740811167537e-05, + "loss": 0.1159, + "step": 292700 + }, + { + "epoch": 0.65, + "learning_rate": 1.7384622267958212e-05, + "loss": 0.117, + "step": 292710 + }, + { + "epoch": 0.65, + "learning_rate": 1.7383503724748886e-05, + "loss": 0.1144, + "step": 292720 + }, + { + "epoch": 0.65, + "learning_rate": 1.7382497035860495e-05, + "loss": 0.1153, + "step": 292730 + }, + { + "epoch": 0.65, + "learning_rate": 1.738137849265117e-05, + "loss": 0.11, + "step": 292740 + }, + { + "epoch": 0.65, + "learning_rate": 1.7380259949441848e-05, + "loss": 0.1171, + "step": 292750 + }, + { + "epoch": 0.65, + "learning_rate": 1.7379141406232526e-05, + "loss": 0.1116, + "step": 292760 + }, + { + "epoch": 0.65, + "learning_rate": 1.73780228630232e-05, + "loss": 0.1161, + "step": 292770 + }, + { + "epoch": 0.65, + "learning_rate": 1.7376904319813875e-05, + "loss": 0.1151, + "step": 292780 + }, + { + "epoch": 0.65, + "learning_rate": 1.737578577660455e-05, + "loss": 0.1116, + "step": 292790 + }, + { + "epoch": 0.65, + "learning_rate": 1.7374667233395227e-05, + "loss": 0.1125, + "step": 292800 + }, + { + "epoch": 0.65, + "learning_rate": 1.7373548690185905e-05, + "loss": 0.116, + "step": 292810 + }, + { + "epoch": 0.65, + "learning_rate": 1.737243014697658e-05, + "loss": 0.1113, + "step": 292820 + }, + { + "epoch": 0.65, + "learning_rate": 1.7371311603767254e-05, + "loss": 0.1071, + "step": 292830 + }, + { + "epoch": 0.65, + "learning_rate": 1.737019306055793e-05, + "loss": 0.1161, + "step": 292840 + }, + { + "epoch": 0.65, + "learning_rate": 1.7369074517348603e-05, + "loss": 0.1091, + "step": 292850 + }, + { + "epoch": 0.65, + "learning_rate": 1.736795597413928e-05, + "loss": 0.1143, + "step": 292860 + }, + { + "epoch": 0.65, + "learning_rate": 1.736683743092996e-05, + "loss": 0.1122, + "step": 292870 + }, + { + "epoch": 0.65, + "learning_rate": 1.7365718887720634e-05, + "loss": 0.1152, + "step": 292880 + }, + { + "epoch": 0.65, + "learning_rate": 1.7364600344511308e-05, + "loss": 0.1124, + "step": 292890 + }, + { + "epoch": 0.65, + "learning_rate": 1.7363481801301983e-05, + "loss": 0.1137, + "step": 292900 + }, + { + "epoch": 0.65, + "learning_rate": 1.736236325809266e-05, + "loss": 0.1168, + "step": 292910 + }, + { + "epoch": 0.65, + "learning_rate": 1.736124471488334e-05, + "loss": 0.1137, + "step": 292920 + }, + { + "epoch": 0.65, + "learning_rate": 1.7360126171674013e-05, + "loss": 0.1126, + "step": 292930 + }, + { + "epoch": 0.65, + "learning_rate": 1.7359007628464688e-05, + "loss": 0.1129, + "step": 292940 + }, + { + "epoch": 0.65, + "learning_rate": 1.7357889085255362e-05, + "loss": 0.1159, + "step": 292950 + }, + { + "epoch": 0.65, + "learning_rate": 1.735677054204604e-05, + "loss": 0.1147, + "step": 292960 + }, + { + "epoch": 0.65, + "learning_rate": 1.7355651998836718e-05, + "loss": 0.1166, + "step": 292970 + }, + { + "epoch": 0.65, + "learning_rate": 1.7354533455627393e-05, + "loss": 0.1128, + "step": 292980 + }, + { + "epoch": 0.65, + "learning_rate": 1.7353414912418067e-05, + "loss": 0.1133, + "step": 292990 + }, + { + "epoch": 0.65, + "learning_rate": 1.735229636920874e-05, + "loss": 0.1132, + "step": 293000 + }, + { + "epoch": 0.65, + "learning_rate": 1.7351177825999416e-05, + "loss": 0.1168, + "step": 293010 + }, + { + "epoch": 0.65, + "learning_rate": 1.7350059282790098e-05, + "loss": 0.1172, + "step": 293020 + }, + { + "epoch": 0.65, + "learning_rate": 1.7348940739580772e-05, + "loss": 0.1175, + "step": 293030 + }, + { + "epoch": 0.65, + "learning_rate": 1.7347822196371447e-05, + "loss": 0.1121, + "step": 293040 + }, + { + "epoch": 0.65, + "learning_rate": 1.734670365316212e-05, + "loss": 0.1162, + "step": 293050 + }, + { + "epoch": 0.65, + "learning_rate": 1.7345585109952796e-05, + "loss": 0.1129, + "step": 293060 + }, + { + "epoch": 0.65, + "learning_rate": 1.7344466566743474e-05, + "loss": 0.1117, + "step": 293070 + }, + { + "epoch": 0.65, + "learning_rate": 1.734334802353415e-05, + "loss": 0.115, + "step": 293080 + }, + { + "epoch": 0.65, + "learning_rate": 1.7342229480324826e-05, + "loss": 0.1148, + "step": 293090 + }, + { + "epoch": 0.65, + "learning_rate": 1.73411109371155e-05, + "loss": 0.1126, + "step": 293100 + }, + { + "epoch": 0.65, + "learning_rate": 1.7339992393906175e-05, + "loss": 0.1164, + "step": 293110 + }, + { + "epoch": 0.65, + "learning_rate": 1.7338873850696853e-05, + "loss": 0.1102, + "step": 293120 + }, + { + "epoch": 0.65, + "learning_rate": 1.733775530748753e-05, + "loss": 0.1144, + "step": 293130 + }, + { + "epoch": 0.65, + "learning_rate": 1.7336636764278206e-05, + "loss": 0.1138, + "step": 293140 + }, + { + "epoch": 0.65, + "learning_rate": 1.733551822106888e-05, + "loss": 0.1152, + "step": 293150 + }, + { + "epoch": 0.65, + "learning_rate": 1.7334399677859555e-05, + "loss": 0.1163, + "step": 293160 + }, + { + "epoch": 0.65, + "learning_rate": 1.7333281134650233e-05, + "loss": 0.1135, + "step": 293170 + }, + { + "epoch": 0.65, + "learning_rate": 1.733216259144091e-05, + "loss": 0.1171, + "step": 293180 + }, + { + "epoch": 0.65, + "learning_rate": 1.7331044048231585e-05, + "loss": 0.1087, + "step": 293190 + }, + { + "epoch": 0.65, + "learning_rate": 1.732992550502226e-05, + "loss": 0.1161, + "step": 293200 + }, + { + "epoch": 0.65, + "learning_rate": 1.7328806961812934e-05, + "loss": 0.1132, + "step": 293210 + }, + { + "epoch": 0.65, + "learning_rate": 1.7327688418603612e-05, + "loss": 0.1096, + "step": 293220 + }, + { + "epoch": 0.65, + "learning_rate": 1.732656987539429e-05, + "loss": 0.1165, + "step": 293230 + }, + { + "epoch": 0.65, + "learning_rate": 1.7325451332184964e-05, + "loss": 0.1167, + "step": 293240 + }, + { + "epoch": 0.65, + "learning_rate": 1.732433278897564e-05, + "loss": 0.1119, + "step": 293250 + }, + { + "epoch": 0.65, + "learning_rate": 1.7323214245766314e-05, + "loss": 0.113, + "step": 293260 + }, + { + "epoch": 0.65, + "learning_rate": 1.7322095702556988e-05, + "loss": 0.1146, + "step": 293270 + }, + { + "epoch": 0.65, + "learning_rate": 1.7320977159347666e-05, + "loss": 0.1146, + "step": 293280 + }, + { + "epoch": 0.65, + "learning_rate": 1.7319858616138344e-05, + "loss": 0.1166, + "step": 293290 + }, + { + "epoch": 0.65, + "learning_rate": 1.731874007292902e-05, + "loss": 0.12, + "step": 293300 + }, + { + "epoch": 0.65, + "learning_rate": 1.7317621529719693e-05, + "loss": 0.1144, + "step": 293310 + }, + { + "epoch": 0.65, + "learning_rate": 1.7316502986510368e-05, + "loss": 0.1155, + "step": 293320 + }, + { + "epoch": 0.65, + "learning_rate": 1.7315384443301046e-05, + "loss": 0.1151, + "step": 293330 + }, + { + "epoch": 0.65, + "learning_rate": 1.7314265900091723e-05, + "loss": 0.1126, + "step": 293340 + }, + { + "epoch": 0.65, + "learning_rate": 1.7313147356882398e-05, + "loss": 0.114, + "step": 293350 + }, + { + "epoch": 0.65, + "learning_rate": 1.7312028813673073e-05, + "loss": 0.1115, + "step": 293360 + }, + { + "epoch": 0.65, + "learning_rate": 1.7310910270463747e-05, + "loss": 0.1156, + "step": 293370 + }, + { + "epoch": 0.65, + "learning_rate": 1.7309791727254425e-05, + "loss": 0.1205, + "step": 293380 + }, + { + "epoch": 0.65, + "learning_rate": 1.7308673184045103e-05, + "loss": 0.1114, + "step": 293390 + }, + { + "epoch": 0.65, + "learning_rate": 1.7307554640835777e-05, + "loss": 0.1122, + "step": 293400 + }, + { + "epoch": 0.65, + "learning_rate": 1.7306436097626452e-05, + "loss": 0.1109, + "step": 293410 + }, + { + "epoch": 0.65, + "learning_rate": 1.7305317554417127e-05, + "loss": 0.1135, + "step": 293420 + }, + { + "epoch": 0.65, + "learning_rate": 1.7304199011207804e-05, + "loss": 0.1129, + "step": 293430 + }, + { + "epoch": 0.65, + "learning_rate": 1.7303080467998482e-05, + "loss": 0.1114, + "step": 293440 + }, + { + "epoch": 0.66, + "learning_rate": 1.7301961924789157e-05, + "loss": 0.1122, + "step": 293450 + }, + { + "epoch": 0.66, + "learning_rate": 1.730084338157983e-05, + "loss": 0.1136, + "step": 293460 + }, + { + "epoch": 0.66, + "learning_rate": 1.7299724838370506e-05, + "loss": 0.1109, + "step": 293470 + }, + { + "epoch": 0.66, + "learning_rate": 1.729860629516118e-05, + "loss": 0.1143, + "step": 293480 + }, + { + "epoch": 0.66, + "learning_rate": 1.729748775195186e-05, + "loss": 0.117, + "step": 293490 + }, + { + "epoch": 0.66, + "learning_rate": 1.7296369208742536e-05, + "loss": 0.1173, + "step": 293500 + }, + { + "epoch": 0.66, + "learning_rate": 1.729525066553321e-05, + "loss": 0.1131, + "step": 293510 + }, + { + "epoch": 0.66, + "learning_rate": 1.7294132122323885e-05, + "loss": 0.1159, + "step": 293520 + }, + { + "epoch": 0.66, + "learning_rate": 1.729301357911456e-05, + "loss": 0.1184, + "step": 293530 + }, + { + "epoch": 0.66, + "learning_rate": 1.7291895035905238e-05, + "loss": 0.1156, + "step": 293540 + }, + { + "epoch": 0.66, + "learning_rate": 1.7290776492695916e-05, + "loss": 0.1144, + "step": 293550 + }, + { + "epoch": 0.66, + "learning_rate": 1.728965794948659e-05, + "loss": 0.1147, + "step": 293560 + }, + { + "epoch": 0.66, + "learning_rate": 1.7288539406277265e-05, + "loss": 0.1183, + "step": 293570 + }, + { + "epoch": 0.66, + "learning_rate": 1.728742086306794e-05, + "loss": 0.1155, + "step": 293580 + }, + { + "epoch": 0.66, + "learning_rate": 1.7286302319858617e-05, + "loss": 0.1122, + "step": 293590 + }, + { + "epoch": 0.66, + "learning_rate": 1.7285183776649295e-05, + "loss": 0.1163, + "step": 293600 + }, + { + "epoch": 0.66, + "learning_rate": 1.728406523343997e-05, + "loss": 0.113, + "step": 293610 + }, + { + "epoch": 0.66, + "learning_rate": 1.7282946690230644e-05, + "loss": 0.1124, + "step": 293620 + }, + { + "epoch": 0.66, + "learning_rate": 1.728182814702132e-05, + "loss": 0.1134, + "step": 293630 + }, + { + "epoch": 0.66, + "learning_rate": 1.7280709603811997e-05, + "loss": 0.1169, + "step": 293640 + }, + { + "epoch": 0.66, + "learning_rate": 1.727959106060267e-05, + "loss": 0.1132, + "step": 293650 + }, + { + "epoch": 0.66, + "learning_rate": 1.727847251739335e-05, + "loss": 0.1129, + "step": 293660 + }, + { + "epoch": 0.66, + "learning_rate": 1.7277353974184024e-05, + "loss": 0.1127, + "step": 293670 + }, + { + "epoch": 0.66, + "learning_rate": 1.72762354309747e-05, + "loss": 0.1104, + "step": 293680 + }, + { + "epoch": 0.66, + "learning_rate": 1.7275116887765373e-05, + "loss": 0.1164, + "step": 293690 + }, + { + "epoch": 0.66, + "learning_rate": 1.727399834455605e-05, + "loss": 0.1122, + "step": 293700 + }, + { + "epoch": 0.66, + "learning_rate": 1.727287980134673e-05, + "loss": 0.1172, + "step": 293710 + }, + { + "epoch": 0.66, + "learning_rate": 1.7271761258137403e-05, + "loss": 0.1097, + "step": 293720 + }, + { + "epoch": 0.66, + "learning_rate": 1.7270642714928078e-05, + "loss": 0.1142, + "step": 293730 + }, + { + "epoch": 0.66, + "learning_rate": 1.7269524171718752e-05, + "loss": 0.1123, + "step": 293740 + }, + { + "epoch": 0.66, + "learning_rate": 1.726840562850943e-05, + "loss": 0.1114, + "step": 293750 + }, + { + "epoch": 0.66, + "learning_rate": 1.726728708530011e-05, + "loss": 0.1131, + "step": 293760 + }, + { + "epoch": 0.66, + "learning_rate": 1.7266168542090783e-05, + "loss": 0.1144, + "step": 293770 + }, + { + "epoch": 0.66, + "learning_rate": 1.7265049998881457e-05, + "loss": 0.1145, + "step": 293780 + }, + { + "epoch": 0.66, + "learning_rate": 1.7263931455672132e-05, + "loss": 0.1146, + "step": 293790 + }, + { + "epoch": 0.66, + "learning_rate": 1.726281291246281e-05, + "loss": 0.1168, + "step": 293800 + }, + { + "epoch": 0.66, + "learning_rate": 1.7261694369253484e-05, + "loss": 0.1177, + "step": 293810 + }, + { + "epoch": 0.66, + "learning_rate": 1.7260575826044162e-05, + "loss": 0.115, + "step": 293820 + }, + { + "epoch": 0.66, + "learning_rate": 1.7259457282834837e-05, + "loss": 0.1139, + "step": 293830 + }, + { + "epoch": 0.66, + "learning_rate": 1.725833873962551e-05, + "loss": 0.1112, + "step": 293840 + }, + { + "epoch": 0.66, + "learning_rate": 1.725722019641619e-05, + "loss": 0.1109, + "step": 293850 + }, + { + "epoch": 0.66, + "learning_rate": 1.7256101653206864e-05, + "loss": 0.1104, + "step": 293860 + }, + { + "epoch": 0.66, + "learning_rate": 1.7254983109997542e-05, + "loss": 0.1143, + "step": 293870 + }, + { + "epoch": 0.66, + "learning_rate": 1.7253864566788216e-05, + "loss": 0.1182, + "step": 293880 + }, + { + "epoch": 0.66, + "learning_rate": 1.725274602357889e-05, + "loss": 0.108, + "step": 293890 + }, + { + "epoch": 0.66, + "learning_rate": 1.7251627480369565e-05, + "loss": 0.1135, + "step": 293900 + }, + { + "epoch": 0.66, + "learning_rate": 1.7250508937160243e-05, + "loss": 0.1109, + "step": 293910 + }, + { + "epoch": 0.66, + "learning_rate": 1.724939039395092e-05, + "loss": 0.1098, + "step": 293920 + }, + { + "epoch": 0.66, + "learning_rate": 1.7248271850741596e-05, + "loss": 0.1105, + "step": 293930 + }, + { + "epoch": 0.66, + "learning_rate": 1.724715330753227e-05, + "loss": 0.114, + "step": 293940 + }, + { + "epoch": 0.66, + "learning_rate": 1.7246034764322945e-05, + "loss": 0.1175, + "step": 293950 + }, + { + "epoch": 0.66, + "learning_rate": 1.7244916221113623e-05, + "loss": 0.1127, + "step": 293960 + }, + { + "epoch": 0.66, + "learning_rate": 1.7243797677904297e-05, + "loss": 0.1182, + "step": 293970 + }, + { + "epoch": 0.66, + "learning_rate": 1.7242679134694975e-05, + "loss": 0.1153, + "step": 293980 + }, + { + "epoch": 0.66, + "learning_rate": 1.724156059148565e-05, + "loss": 0.1118, + "step": 293990 + }, + { + "epoch": 0.66, + "learning_rate": 1.7240442048276324e-05, + "loss": 0.1155, + "step": 294000 + }, + { + "epoch": 0.66, + "learning_rate": 1.7239323505067002e-05, + "loss": 0.1105, + "step": 294010 + }, + { + "epoch": 0.66, + "learning_rate": 1.7238204961857677e-05, + "loss": 0.1196, + "step": 294020 + }, + { + "epoch": 0.66, + "learning_rate": 1.7237086418648355e-05, + "loss": 0.1114, + "step": 294030 + }, + { + "epoch": 0.66, + "learning_rate": 1.723596787543903e-05, + "loss": 0.1142, + "step": 294040 + }, + { + "epoch": 0.66, + "learning_rate": 1.7234849332229704e-05, + "loss": 0.1148, + "step": 294050 + }, + { + "epoch": 0.66, + "learning_rate": 1.7233730789020382e-05, + "loss": 0.1122, + "step": 294060 + }, + { + "epoch": 0.66, + "learning_rate": 1.7232612245811056e-05, + "loss": 0.1179, + "step": 294070 + }, + { + "epoch": 0.66, + "learning_rate": 1.7231493702601734e-05, + "loss": 0.1117, + "step": 294080 + }, + { + "epoch": 0.66, + "learning_rate": 1.723037515939241e-05, + "loss": 0.1124, + "step": 294090 + }, + { + "epoch": 0.66, + "learning_rate": 1.7229256616183083e-05, + "loss": 0.1106, + "step": 294100 + }, + { + "epoch": 0.66, + "learning_rate": 1.722813807297376e-05, + "loss": 0.1136, + "step": 294110 + }, + { + "epoch": 0.66, + "learning_rate": 1.7227019529764436e-05, + "loss": 0.1156, + "step": 294120 + }, + { + "epoch": 0.66, + "learning_rate": 1.722590098655511e-05, + "loss": 0.1148, + "step": 294130 + }, + { + "epoch": 0.66, + "learning_rate": 1.7224782443345788e-05, + "loss": 0.1184, + "step": 294140 + }, + { + "epoch": 0.66, + "learning_rate": 1.7223663900136463e-05, + "loss": 0.1155, + "step": 294150 + }, + { + "epoch": 0.66, + "learning_rate": 1.7222545356927137e-05, + "loss": 0.1152, + "step": 294160 + }, + { + "epoch": 0.66, + "learning_rate": 1.7221426813717815e-05, + "loss": 0.1125, + "step": 294170 + }, + { + "epoch": 0.66, + "learning_rate": 1.722030827050849e-05, + "loss": 0.1176, + "step": 294180 + }, + { + "epoch": 0.66, + "learning_rate": 1.7219189727299168e-05, + "loss": 0.1163, + "step": 294190 + }, + { + "epoch": 0.66, + "learning_rate": 1.7218071184089842e-05, + "loss": 0.1146, + "step": 294200 + }, + { + "epoch": 0.66, + "learning_rate": 1.7216952640880517e-05, + "loss": 0.1103, + "step": 294210 + }, + { + "epoch": 0.66, + "learning_rate": 1.7215834097671195e-05, + "loss": 0.1168, + "step": 294220 + }, + { + "epoch": 0.66, + "learning_rate": 1.721471555446187e-05, + "loss": 0.1155, + "step": 294230 + }, + { + "epoch": 0.66, + "learning_rate": 1.7213597011252547e-05, + "loss": 0.1153, + "step": 294240 + }, + { + "epoch": 0.66, + "learning_rate": 1.7212478468043222e-05, + "loss": 0.1112, + "step": 294250 + }, + { + "epoch": 0.66, + "learning_rate": 1.7211359924833896e-05, + "loss": 0.1163, + "step": 294260 + }, + { + "epoch": 0.66, + "learning_rate": 1.7210241381624574e-05, + "loss": 0.1145, + "step": 294270 + }, + { + "epoch": 0.66, + "learning_rate": 1.720912283841525e-05, + "loss": 0.1167, + "step": 294280 + }, + { + "epoch": 0.66, + "learning_rate": 1.7208004295205923e-05, + "loss": 0.1106, + "step": 294290 + }, + { + "epoch": 0.66, + "learning_rate": 1.72068857519966e-05, + "loss": 0.1166, + "step": 294300 + }, + { + "epoch": 0.66, + "learning_rate": 1.7205767208787276e-05, + "loss": 0.1126, + "step": 294310 + }, + { + "epoch": 0.66, + "learning_rate": 1.7204648665577954e-05, + "loss": 0.1126, + "step": 294320 + }, + { + "epoch": 0.66, + "learning_rate": 1.7203530122368628e-05, + "loss": 0.1146, + "step": 294330 + }, + { + "epoch": 0.66, + "learning_rate": 1.7202411579159303e-05, + "loss": 0.1128, + "step": 294340 + }, + { + "epoch": 0.66, + "learning_rate": 1.720129303594998e-05, + "loss": 0.1159, + "step": 294350 + }, + { + "epoch": 0.66, + "learning_rate": 1.7200174492740655e-05, + "loss": 0.1111, + "step": 294360 + }, + { + "epoch": 0.66, + "learning_rate": 1.719905594953133e-05, + "loss": 0.113, + "step": 294370 + }, + { + "epoch": 0.66, + "learning_rate": 1.7197937406322008e-05, + "loss": 0.1136, + "step": 294380 + }, + { + "epoch": 0.66, + "learning_rate": 1.7196818863112682e-05, + "loss": 0.1134, + "step": 294390 + }, + { + "epoch": 0.66, + "learning_rate": 1.719570031990336e-05, + "loss": 0.1146, + "step": 294400 + }, + { + "epoch": 0.66, + "learning_rate": 1.7194581776694035e-05, + "loss": 0.1142, + "step": 294410 + }, + { + "epoch": 0.66, + "learning_rate": 1.719346323348471e-05, + "loss": 0.115, + "step": 294420 + }, + { + "epoch": 0.66, + "learning_rate": 1.7192344690275387e-05, + "loss": 0.1083, + "step": 294430 + }, + { + "epoch": 0.66, + "learning_rate": 1.7191226147066062e-05, + "loss": 0.1129, + "step": 294440 + }, + { + "epoch": 0.66, + "learning_rate": 1.7190107603856736e-05, + "loss": 0.1155, + "step": 294450 + }, + { + "epoch": 0.66, + "learning_rate": 1.7188989060647414e-05, + "loss": 0.1127, + "step": 294460 + }, + { + "epoch": 0.66, + "learning_rate": 1.718787051743809e-05, + "loss": 0.1129, + "step": 294470 + }, + { + "epoch": 0.66, + "learning_rate": 1.7186751974228767e-05, + "loss": 0.112, + "step": 294480 + }, + { + "epoch": 0.66, + "learning_rate": 1.718563343101944e-05, + "loss": 0.1157, + "step": 294490 + }, + { + "epoch": 0.66, + "learning_rate": 1.7184514887810116e-05, + "loss": 0.1163, + "step": 294500 + }, + { + "epoch": 0.66, + "learning_rate": 1.7183396344600794e-05, + "loss": 0.1132, + "step": 294510 + }, + { + "epoch": 0.66, + "learning_rate": 1.7182277801391468e-05, + "loss": 0.1171, + "step": 294520 + }, + { + "epoch": 0.66, + "learning_rate": 1.7181159258182146e-05, + "loss": 0.112, + "step": 294530 + }, + { + "epoch": 0.66, + "learning_rate": 1.718004071497282e-05, + "loss": 0.1154, + "step": 294540 + }, + { + "epoch": 0.66, + "learning_rate": 1.7178922171763495e-05, + "loss": 0.1105, + "step": 294550 + }, + { + "epoch": 0.66, + "learning_rate": 1.7177803628554173e-05, + "loss": 0.1129, + "step": 294560 + }, + { + "epoch": 0.66, + "learning_rate": 1.7176685085344848e-05, + "loss": 0.1113, + "step": 294570 + }, + { + "epoch": 0.66, + "learning_rate": 1.7175566542135522e-05, + "loss": 0.1174, + "step": 294580 + }, + { + "epoch": 0.66, + "learning_rate": 1.71744479989262e-05, + "loss": 0.112, + "step": 294590 + }, + { + "epoch": 0.66, + "learning_rate": 1.7173329455716875e-05, + "loss": 0.1094, + "step": 294600 + }, + { + "epoch": 0.66, + "learning_rate": 1.717221091250755e-05, + "loss": 0.11, + "step": 294610 + }, + { + "epoch": 0.66, + "learning_rate": 1.7171092369298227e-05, + "loss": 0.1116, + "step": 294620 + }, + { + "epoch": 0.66, + "learning_rate": 1.71699738260889e-05, + "loss": 0.1159, + "step": 294630 + }, + { + "epoch": 0.66, + "learning_rate": 1.716885528287958e-05, + "loss": 0.1164, + "step": 294640 + }, + { + "epoch": 0.66, + "learning_rate": 1.7167736739670254e-05, + "loss": 0.1148, + "step": 294650 + }, + { + "epoch": 0.66, + "learning_rate": 1.716661819646093e-05, + "loss": 0.1146, + "step": 294660 + }, + { + "epoch": 0.66, + "learning_rate": 1.7165499653251607e-05, + "loss": 0.1135, + "step": 294670 + }, + { + "epoch": 0.66, + "learning_rate": 1.716438111004228e-05, + "loss": 0.1148, + "step": 294680 + }, + { + "epoch": 0.66, + "learning_rate": 1.716326256683296e-05, + "loss": 0.1128, + "step": 294690 + }, + { + "epoch": 0.66, + "learning_rate": 1.7162144023623634e-05, + "loss": 0.1138, + "step": 294700 + }, + { + "epoch": 0.66, + "learning_rate": 1.7161025480414308e-05, + "loss": 0.1111, + "step": 294710 + }, + { + "epoch": 0.66, + "learning_rate": 1.7159906937204986e-05, + "loss": 0.1092, + "step": 294720 + }, + { + "epoch": 0.66, + "learning_rate": 1.715878839399566e-05, + "loss": 0.1169, + "step": 294730 + }, + { + "epoch": 0.66, + "learning_rate": 1.715766985078634e-05, + "loss": 0.1123, + "step": 294740 + }, + { + "epoch": 0.66, + "learning_rate": 1.7156663161897947e-05, + "loss": 0.1104, + "step": 294750 + }, + { + "epoch": 0.66, + "learning_rate": 1.7155544618688622e-05, + "loss": 0.1139, + "step": 294760 + }, + { + "epoch": 0.66, + "learning_rate": 1.7154426075479296e-05, + "loss": 0.1102, + "step": 294770 + }, + { + "epoch": 0.66, + "learning_rate": 1.715330753226997e-05, + "loss": 0.1096, + "step": 294780 + }, + { + "epoch": 0.66, + "learning_rate": 1.7152188989060645e-05, + "loss": 0.118, + "step": 294790 + }, + { + "epoch": 0.66, + "learning_rate": 1.7151070445851323e-05, + "loss": 0.1154, + "step": 294800 + }, + { + "epoch": 0.66, + "learning_rate": 1.7149951902642e-05, + "loss": 0.1159, + "step": 294810 + }, + { + "epoch": 0.66, + "learning_rate": 1.7148833359432676e-05, + "loss": 0.1159, + "step": 294820 + }, + { + "epoch": 0.66, + "learning_rate": 1.714771481622335e-05, + "loss": 0.118, + "step": 294830 + }, + { + "epoch": 0.66, + "learning_rate": 1.7146596273014025e-05, + "loss": 0.1122, + "step": 294840 + }, + { + "epoch": 0.66, + "learning_rate": 1.7145477729804703e-05, + "loss": 0.1144, + "step": 294850 + }, + { + "epoch": 0.66, + "learning_rate": 1.714435918659538e-05, + "loss": 0.115, + "step": 294860 + }, + { + "epoch": 0.66, + "learning_rate": 1.7143240643386055e-05, + "loss": 0.1088, + "step": 294870 + }, + { + "epoch": 0.66, + "learning_rate": 1.714212210017673e-05, + "loss": 0.1154, + "step": 294880 + }, + { + "epoch": 0.66, + "learning_rate": 1.7141003556967404e-05, + "loss": 0.1117, + "step": 294890 + }, + { + "epoch": 0.66, + "learning_rate": 1.7139885013758082e-05, + "loss": 0.1149, + "step": 294900 + }, + { + "epoch": 0.66, + "learning_rate": 1.713876647054876e-05, + "loss": 0.1143, + "step": 294910 + }, + { + "epoch": 0.66, + "learning_rate": 1.7137647927339435e-05, + "loss": 0.1139, + "step": 294920 + }, + { + "epoch": 0.66, + "learning_rate": 1.713652938413011e-05, + "loss": 0.1137, + "step": 294930 + }, + { + "epoch": 0.66, + "learning_rate": 1.7135410840920784e-05, + "loss": 0.1116, + "step": 294940 + }, + { + "epoch": 0.66, + "learning_rate": 1.713429229771146e-05, + "loss": 0.1163, + "step": 294950 + }, + { + "epoch": 0.66, + "learning_rate": 1.713317375450214e-05, + "loss": 0.1108, + "step": 294960 + }, + { + "epoch": 0.66, + "learning_rate": 1.7132055211292814e-05, + "loss": 0.1125, + "step": 294970 + }, + { + "epoch": 0.66, + "learning_rate": 1.713093666808349e-05, + "loss": 0.1088, + "step": 294980 + }, + { + "epoch": 0.66, + "learning_rate": 1.7129818124874163e-05, + "loss": 0.1145, + "step": 294990 + }, + { + "epoch": 0.66, + "learning_rate": 1.7128699581664838e-05, + "loss": 0.1102, + "step": 295000 + }, + { + "epoch": 0.66, + "learning_rate": 1.7127581038455516e-05, + "loss": 0.1143, + "step": 295010 + }, + { + "epoch": 0.66, + "learning_rate": 1.7126462495246194e-05, + "loss": 0.1146, + "step": 295020 + }, + { + "epoch": 0.66, + "learning_rate": 1.712534395203687e-05, + "loss": 0.1148, + "step": 295030 + }, + { + "epoch": 0.66, + "learning_rate": 1.7124225408827543e-05, + "loss": 0.1136, + "step": 295040 + }, + { + "epoch": 0.66, + "learning_rate": 1.7123106865618217e-05, + "loss": 0.1094, + "step": 295050 + }, + { + "epoch": 0.66, + "learning_rate": 1.7121988322408895e-05, + "loss": 0.1138, + "step": 295060 + }, + { + "epoch": 0.66, + "learning_rate": 1.7120869779199573e-05, + "loss": 0.1126, + "step": 295070 + }, + { + "epoch": 0.66, + "learning_rate": 1.7119751235990248e-05, + "loss": 0.1135, + "step": 295080 + }, + { + "epoch": 0.66, + "learning_rate": 1.7118632692780922e-05, + "loss": 0.1136, + "step": 295090 + }, + { + "epoch": 0.66, + "learning_rate": 1.7117514149571597e-05, + "loss": 0.1201, + "step": 295100 + }, + { + "epoch": 0.66, + "learning_rate": 1.7116395606362275e-05, + "loss": 0.1079, + "step": 295110 + }, + { + "epoch": 0.66, + "learning_rate": 1.7115277063152953e-05, + "loss": 0.1128, + "step": 295120 + }, + { + "epoch": 0.66, + "learning_rate": 1.7114158519943627e-05, + "loss": 0.1147, + "step": 295130 + }, + { + "epoch": 0.66, + "learning_rate": 1.7113039976734302e-05, + "loss": 0.1153, + "step": 295140 + }, + { + "epoch": 0.66, + "learning_rate": 1.7111921433524976e-05, + "loss": 0.1171, + "step": 295150 + }, + { + "epoch": 0.66, + "learning_rate": 1.711080289031565e-05, + "loss": 0.1115, + "step": 295160 + }, + { + "epoch": 0.66, + "learning_rate": 1.7109684347106332e-05, + "loss": 0.1146, + "step": 295170 + }, + { + "epoch": 0.66, + "learning_rate": 1.7108565803897007e-05, + "loss": 0.1154, + "step": 295180 + }, + { + "epoch": 0.66, + "learning_rate": 1.710744726068768e-05, + "loss": 0.1111, + "step": 295190 + }, + { + "epoch": 0.66, + "learning_rate": 1.7106328717478356e-05, + "loss": 0.1085, + "step": 295200 + }, + { + "epoch": 0.66, + "learning_rate": 1.710521017426903e-05, + "loss": 0.1179, + "step": 295210 + }, + { + "epoch": 0.66, + "learning_rate": 1.7104091631059708e-05, + "loss": 0.1114, + "step": 295220 + }, + { + "epoch": 0.66, + "learning_rate": 1.7102973087850386e-05, + "loss": 0.1144, + "step": 295230 + }, + { + "epoch": 0.66, + "learning_rate": 1.710185454464106e-05, + "loss": 0.113, + "step": 295240 + }, + { + "epoch": 0.66, + "learning_rate": 1.7100736001431735e-05, + "loss": 0.1138, + "step": 295250 + }, + { + "epoch": 0.66, + "learning_rate": 1.709961745822241e-05, + "loss": 0.1113, + "step": 295260 + }, + { + "epoch": 0.66, + "learning_rate": 1.7098498915013088e-05, + "loss": 0.1118, + "step": 295270 + }, + { + "epoch": 0.66, + "learning_rate": 1.7097380371803766e-05, + "loss": 0.1167, + "step": 295280 + }, + { + "epoch": 0.66, + "learning_rate": 1.709626182859444e-05, + "loss": 0.1097, + "step": 295290 + }, + { + "epoch": 0.66, + "learning_rate": 1.7095143285385115e-05, + "loss": 0.1144, + "step": 295300 + }, + { + "epoch": 0.66, + "learning_rate": 1.709402474217579e-05, + "loss": 0.1168, + "step": 295310 + }, + { + "epoch": 0.66, + "learning_rate": 1.7092906198966467e-05, + "loss": 0.1146, + "step": 295320 + }, + { + "epoch": 0.66, + "learning_rate": 1.7091787655757145e-05, + "loss": 0.1155, + "step": 295330 + }, + { + "epoch": 0.66, + "learning_rate": 1.709066911254782e-05, + "loss": 0.1136, + "step": 295340 + }, + { + "epoch": 0.66, + "learning_rate": 1.7089550569338494e-05, + "loss": 0.1148, + "step": 295350 + }, + { + "epoch": 0.66, + "learning_rate": 1.708843202612917e-05, + "loss": 0.1134, + "step": 295360 + }, + { + "epoch": 0.66, + "learning_rate": 1.7087313482919843e-05, + "loss": 0.1113, + "step": 295370 + }, + { + "epoch": 0.66, + "learning_rate": 1.7086194939710525e-05, + "loss": 0.1175, + "step": 295380 + }, + { + "epoch": 0.66, + "learning_rate": 1.70850763965012e-05, + "loss": 0.1145, + "step": 295390 + }, + { + "epoch": 0.66, + "learning_rate": 1.7083957853291874e-05, + "loss": 0.1109, + "step": 295400 + }, + { + "epoch": 0.66, + "learning_rate": 1.7082839310082548e-05, + "loss": 0.1145, + "step": 295410 + }, + { + "epoch": 0.66, + "learning_rate": 1.7081720766873223e-05, + "loss": 0.1151, + "step": 295420 + }, + { + "epoch": 0.66, + "learning_rate": 1.70806022236639e-05, + "loss": 0.114, + "step": 295430 + }, + { + "epoch": 0.66, + "learning_rate": 1.707948368045458e-05, + "loss": 0.1138, + "step": 295440 + }, + { + "epoch": 0.66, + "learning_rate": 1.7078365137245253e-05, + "loss": 0.1156, + "step": 295450 + }, + { + "epoch": 0.66, + "learning_rate": 1.7077246594035928e-05, + "loss": 0.1157, + "step": 295460 + }, + { + "epoch": 0.66, + "learning_rate": 1.7076128050826602e-05, + "loss": 0.1175, + "step": 295470 + }, + { + "epoch": 0.66, + "learning_rate": 1.707500950761728e-05, + "loss": 0.1094, + "step": 295480 + }, + { + "epoch": 0.66, + "learning_rate": 1.7073890964407958e-05, + "loss": 0.1091, + "step": 295490 + }, + { + "epoch": 0.66, + "learning_rate": 1.7072772421198633e-05, + "loss": 0.11, + "step": 295500 + }, + { + "epoch": 0.66, + "learning_rate": 1.7071653877989307e-05, + "loss": 0.1172, + "step": 295510 + }, + { + "epoch": 0.66, + "learning_rate": 1.7070535334779982e-05, + "loss": 0.1117, + "step": 295520 + }, + { + "epoch": 0.66, + "learning_rate": 1.706941679157066e-05, + "loss": 0.1169, + "step": 295530 + }, + { + "epoch": 0.66, + "learning_rate": 1.7068298248361338e-05, + "loss": 0.12, + "step": 295540 + }, + { + "epoch": 0.66, + "learning_rate": 1.7067179705152012e-05, + "loss": 0.112, + "step": 295550 + }, + { + "epoch": 0.66, + "learning_rate": 1.7066061161942687e-05, + "loss": 0.1121, + "step": 295560 + }, + { + "epoch": 0.66, + "learning_rate": 1.706494261873336e-05, + "loss": 0.114, + "step": 295570 + }, + { + "epoch": 0.66, + "learning_rate": 1.706382407552404e-05, + "loss": 0.1158, + "step": 295580 + }, + { + "epoch": 0.66, + "learning_rate": 1.7062705532314714e-05, + "loss": 0.1136, + "step": 295590 + }, + { + "epoch": 0.66, + "learning_rate": 1.706158698910539e-05, + "loss": 0.1173, + "step": 295600 + }, + { + "epoch": 0.66, + "learning_rate": 1.7060468445896066e-05, + "loss": 0.1142, + "step": 295610 + }, + { + "epoch": 0.66, + "learning_rate": 1.705934990268674e-05, + "loss": 0.1139, + "step": 295620 + }, + { + "epoch": 0.66, + "learning_rate": 1.7058231359477415e-05, + "loss": 0.117, + "step": 295630 + }, + { + "epoch": 0.66, + "learning_rate": 1.7057112816268093e-05, + "loss": 0.117, + "step": 295640 + }, + { + "epoch": 0.66, + "learning_rate": 1.705599427305877e-05, + "loss": 0.1113, + "step": 295650 + }, + { + "epoch": 0.66, + "learning_rate": 1.7054875729849446e-05, + "loss": 0.113, + "step": 295660 + }, + { + "epoch": 0.66, + "learning_rate": 1.705375718664012e-05, + "loss": 0.1087, + "step": 295670 + }, + { + "epoch": 0.66, + "learning_rate": 1.7052638643430795e-05, + "loss": 0.1124, + "step": 295680 + }, + { + "epoch": 0.66, + "learning_rate": 1.7051520100221473e-05, + "loss": 0.1157, + "step": 295690 + }, + { + "epoch": 0.66, + "learning_rate": 1.705040155701215e-05, + "loss": 0.1158, + "step": 295700 + }, + { + "epoch": 0.66, + "learning_rate": 1.7049283013802825e-05, + "loss": 0.1146, + "step": 295710 + }, + { + "epoch": 0.66, + "learning_rate": 1.70481644705935e-05, + "loss": 0.1183, + "step": 295720 + }, + { + "epoch": 0.66, + "learning_rate": 1.7047045927384174e-05, + "loss": 0.1128, + "step": 295730 + }, + { + "epoch": 0.66, + "learning_rate": 1.7045927384174852e-05, + "loss": 0.1136, + "step": 295740 + }, + { + "epoch": 0.66, + "learning_rate": 1.7044808840965527e-05, + "loss": 0.1116, + "step": 295750 + }, + { + "epoch": 0.66, + "learning_rate": 1.7043690297756205e-05, + "loss": 0.1144, + "step": 295760 + }, + { + "epoch": 0.66, + "learning_rate": 1.704257175454688e-05, + "loss": 0.114, + "step": 295770 + }, + { + "epoch": 0.66, + "learning_rate": 1.7041453211337554e-05, + "loss": 0.1166, + "step": 295780 + }, + { + "epoch": 0.66, + "learning_rate": 1.704033466812823e-05, + "loss": 0.115, + "step": 295790 + }, + { + "epoch": 0.66, + "learning_rate": 1.7039216124918906e-05, + "loss": 0.1109, + "step": 295800 + }, + { + "epoch": 0.66, + "learning_rate": 1.7038097581709584e-05, + "loss": 0.1146, + "step": 295810 + }, + { + "epoch": 0.66, + "learning_rate": 1.703697903850026e-05, + "loss": 0.1124, + "step": 295820 + }, + { + "epoch": 0.66, + "learning_rate": 1.7035860495290933e-05, + "loss": 0.1176, + "step": 295830 + }, + { + "epoch": 0.66, + "learning_rate": 1.7034741952081608e-05, + "loss": 0.1141, + "step": 295840 + }, + { + "epoch": 0.66, + "learning_rate": 1.7033623408872286e-05, + "loss": 0.1151, + "step": 295850 + }, + { + "epoch": 0.66, + "learning_rate": 1.7032504865662964e-05, + "loss": 0.1109, + "step": 295860 + }, + { + "epoch": 0.66, + "learning_rate": 1.7031386322453638e-05, + "loss": 0.1135, + "step": 295870 + }, + { + "epoch": 0.66, + "learning_rate": 1.7030267779244313e-05, + "loss": 0.113, + "step": 295880 + }, + { + "epoch": 0.66, + "learning_rate": 1.7029149236034987e-05, + "loss": 0.114, + "step": 295890 + }, + { + "epoch": 0.66, + "learning_rate": 1.7028030692825665e-05, + "loss": 0.1135, + "step": 295900 + }, + { + "epoch": 0.66, + "learning_rate": 1.702691214961634e-05, + "loss": 0.1155, + "step": 295910 + }, + { + "epoch": 0.66, + "learning_rate": 1.7025793606407018e-05, + "loss": 0.1119, + "step": 295920 + }, + { + "epoch": 0.66, + "learning_rate": 1.7024675063197692e-05, + "loss": 0.1122, + "step": 295930 + }, + { + "epoch": 0.66, + "learning_rate": 1.7023556519988367e-05, + "loss": 0.1176, + "step": 295940 + }, + { + "epoch": 0.66, + "learning_rate": 1.7022437976779045e-05, + "loss": 0.1095, + "step": 295950 + }, + { + "epoch": 0.66, + "learning_rate": 1.702131943356972e-05, + "loss": 0.1125, + "step": 295960 + }, + { + "epoch": 0.66, + "learning_rate": 1.7020200890360397e-05, + "loss": 0.1111, + "step": 295970 + }, + { + "epoch": 0.66, + "learning_rate": 1.701908234715107e-05, + "loss": 0.1093, + "step": 295980 + }, + { + "epoch": 0.66, + "learning_rate": 1.7017963803941746e-05, + "loss": 0.1131, + "step": 295990 + }, + { + "epoch": 0.66, + "learning_rate": 1.7016845260732424e-05, + "loss": 0.1169, + "step": 296000 + }, + { + "epoch": 0.66, + "learning_rate": 1.70157267175231e-05, + "loss": 0.1111, + "step": 296010 + }, + { + "epoch": 0.66, + "learning_rate": 1.7014608174313776e-05, + "loss": 0.1198, + "step": 296020 + }, + { + "epoch": 0.66, + "learning_rate": 1.701348963110445e-05, + "loss": 0.1122, + "step": 296030 + }, + { + "epoch": 0.66, + "learning_rate": 1.7012371087895126e-05, + "loss": 0.1152, + "step": 296040 + }, + { + "epoch": 0.66, + "learning_rate": 1.70112525446858e-05, + "loss": 0.1171, + "step": 296050 + }, + { + "epoch": 0.66, + "learning_rate": 1.7010134001476478e-05, + "loss": 0.1129, + "step": 296060 + }, + { + "epoch": 0.66, + "learning_rate": 1.7009015458267153e-05, + "loss": 0.1133, + "step": 296070 + }, + { + "epoch": 0.66, + "learning_rate": 1.700789691505783e-05, + "loss": 0.1108, + "step": 296080 + }, + { + "epoch": 0.66, + "learning_rate": 1.7006778371848505e-05, + "loss": 0.1168, + "step": 296090 + }, + { + "epoch": 0.66, + "learning_rate": 1.700565982863918e-05, + "loss": 0.1135, + "step": 296100 + }, + { + "epoch": 0.66, + "learning_rate": 1.7004541285429858e-05, + "loss": 0.1104, + "step": 296110 + }, + { + "epoch": 0.66, + "learning_rate": 1.7003422742220532e-05, + "loss": 0.1119, + "step": 296120 + }, + { + "epoch": 0.66, + "learning_rate": 1.700230419901121e-05, + "loss": 0.1106, + "step": 296130 + }, + { + "epoch": 0.66, + "learning_rate": 1.7001185655801885e-05, + "loss": 0.1115, + "step": 296140 + }, + { + "epoch": 0.66, + "learning_rate": 1.700006711259256e-05, + "loss": 0.1113, + "step": 296150 + }, + { + "epoch": 0.66, + "learning_rate": 1.6998948569383237e-05, + "loss": 0.1121, + "step": 296160 + }, + { + "epoch": 0.66, + "learning_rate": 1.699783002617391e-05, + "loss": 0.1146, + "step": 296170 + }, + { + "epoch": 0.66, + "learning_rate": 1.699671148296459e-05, + "loss": 0.1172, + "step": 296180 + }, + { + "epoch": 0.66, + "learning_rate": 1.6995592939755264e-05, + "loss": 0.1124, + "step": 296190 + }, + { + "epoch": 0.66, + "learning_rate": 1.699447439654594e-05, + "loss": 0.1161, + "step": 296200 + }, + { + "epoch": 0.66, + "learning_rate": 1.6993355853336616e-05, + "loss": 0.1168, + "step": 296210 + }, + { + "epoch": 0.66, + "learning_rate": 1.699223731012729e-05, + "loss": 0.1115, + "step": 296220 + }, + { + "epoch": 0.66, + "learning_rate": 1.6991118766917966e-05, + "loss": 0.1115, + "step": 296230 + }, + { + "epoch": 0.66, + "learning_rate": 1.6990000223708643e-05, + "loss": 0.1117, + "step": 296240 + }, + { + "epoch": 0.66, + "learning_rate": 1.6988881680499318e-05, + "loss": 0.113, + "step": 296250 + }, + { + "epoch": 0.66, + "learning_rate": 1.6987763137289996e-05, + "loss": 0.1103, + "step": 296260 + }, + { + "epoch": 0.66, + "learning_rate": 1.698664459408067e-05, + "loss": 0.1087, + "step": 296270 + }, + { + "epoch": 0.66, + "learning_rate": 1.6985526050871345e-05, + "loss": 0.1123, + "step": 296280 + }, + { + "epoch": 0.66, + "learning_rate": 1.6984407507662023e-05, + "loss": 0.1103, + "step": 296290 + }, + { + "epoch": 0.66, + "learning_rate": 1.6983288964452697e-05, + "loss": 0.1141, + "step": 296300 + }, + { + "epoch": 0.66, + "learning_rate": 1.6982170421243372e-05, + "loss": 0.1187, + "step": 296310 + }, + { + "epoch": 0.66, + "learning_rate": 1.698105187803405e-05, + "loss": 0.1149, + "step": 296320 + }, + { + "epoch": 0.66, + "learning_rate": 1.6979933334824724e-05, + "loss": 0.1143, + "step": 296330 + }, + { + "epoch": 0.66, + "learning_rate": 1.6978814791615402e-05, + "loss": 0.1136, + "step": 296340 + }, + { + "epoch": 0.66, + "learning_rate": 1.6977696248406077e-05, + "loss": 0.1141, + "step": 296350 + }, + { + "epoch": 0.66, + "learning_rate": 1.697657770519675e-05, + "loss": 0.1114, + "step": 296360 + }, + { + "epoch": 0.66, + "learning_rate": 1.697545916198743e-05, + "loss": 0.1135, + "step": 296370 + }, + { + "epoch": 0.66, + "learning_rate": 1.6974340618778104e-05, + "loss": 0.1128, + "step": 296380 + }, + { + "epoch": 0.66, + "learning_rate": 1.697322207556878e-05, + "loss": 0.1132, + "step": 296390 + }, + { + "epoch": 0.66, + "learning_rate": 1.6972103532359456e-05, + "loss": 0.1105, + "step": 296400 + }, + { + "epoch": 0.66, + "learning_rate": 1.697098498915013e-05, + "loss": 0.1167, + "step": 296410 + }, + { + "epoch": 0.66, + "learning_rate": 1.696986644594081e-05, + "loss": 0.1114, + "step": 296420 + }, + { + "epoch": 0.66, + "learning_rate": 1.6968747902731483e-05, + "loss": 0.1174, + "step": 296430 + }, + { + "epoch": 0.66, + "learning_rate": 1.6967629359522158e-05, + "loss": 0.1103, + "step": 296440 + }, + { + "epoch": 0.66, + "learning_rate": 1.6966510816312836e-05, + "loss": 0.1148, + "step": 296450 + }, + { + "epoch": 0.66, + "learning_rate": 1.696539227310351e-05, + "loss": 0.1144, + "step": 296460 + }, + { + "epoch": 0.66, + "learning_rate": 1.696427372989419e-05, + "loss": 0.1132, + "step": 296470 + }, + { + "epoch": 0.66, + "learning_rate": 1.6963155186684863e-05, + "loss": 0.117, + "step": 296480 + }, + { + "epoch": 0.66, + "learning_rate": 1.6962036643475537e-05, + "loss": 0.1161, + "step": 296490 + }, + { + "epoch": 0.66, + "learning_rate": 1.6960918100266215e-05, + "loss": 0.1131, + "step": 296500 + }, + { + "epoch": 0.66, + "learning_rate": 1.695979955705689e-05, + "loss": 0.1116, + "step": 296510 + }, + { + "epoch": 0.66, + "learning_rate": 1.6958681013847564e-05, + "loss": 0.115, + "step": 296520 + }, + { + "epoch": 0.66, + "learning_rate": 1.6957562470638242e-05, + "loss": 0.1111, + "step": 296530 + }, + { + "epoch": 0.66, + "learning_rate": 1.6956443927428917e-05, + "loss": 0.1122, + "step": 296540 + }, + { + "epoch": 0.66, + "learning_rate": 1.695532538421959e-05, + "loss": 0.1093, + "step": 296550 + }, + { + "epoch": 0.66, + "learning_rate": 1.695420684101027e-05, + "loss": 0.1137, + "step": 296560 + }, + { + "epoch": 0.66, + "learning_rate": 1.6953088297800944e-05, + "loss": 0.1121, + "step": 296570 + }, + { + "epoch": 0.66, + "learning_rate": 1.6951969754591622e-05, + "loss": 0.1169, + "step": 296580 + }, + { + "epoch": 0.66, + "learning_rate": 1.6950851211382296e-05, + "loss": 0.1148, + "step": 296590 + }, + { + "epoch": 0.66, + "learning_rate": 1.694973266817297e-05, + "loss": 0.1089, + "step": 296600 + }, + { + "epoch": 0.66, + "learning_rate": 1.694861412496365e-05, + "loss": 0.1141, + "step": 296610 + }, + { + "epoch": 0.66, + "learning_rate": 1.6947495581754323e-05, + "loss": 0.1111, + "step": 296620 + }, + { + "epoch": 0.66, + "learning_rate": 1.6946377038545e-05, + "loss": 0.1149, + "step": 296630 + }, + { + "epoch": 0.66, + "learning_rate": 1.6945258495335676e-05, + "loss": 0.1199, + "step": 296640 + }, + { + "epoch": 0.66, + "learning_rate": 1.694413995212635e-05, + "loss": 0.1159, + "step": 296650 + }, + { + "epoch": 0.66, + "learning_rate": 1.694302140891703e-05, + "loss": 0.1078, + "step": 296660 + }, + { + "epoch": 0.66, + "learning_rate": 1.6941902865707703e-05, + "loss": 0.1125, + "step": 296670 + }, + { + "epoch": 0.66, + "learning_rate": 1.694078432249838e-05, + "loss": 0.1108, + "step": 296680 + }, + { + "epoch": 0.66, + "learning_rate": 1.6939665779289055e-05, + "loss": 0.1155, + "step": 296690 + }, + { + "epoch": 0.66, + "learning_rate": 1.693854723607973e-05, + "loss": 0.1149, + "step": 296700 + }, + { + "epoch": 0.66, + "learning_rate": 1.6937428692870404e-05, + "loss": 0.1132, + "step": 296710 + }, + { + "epoch": 0.66, + "learning_rate": 1.6936310149661082e-05, + "loss": 0.1164, + "step": 296720 + }, + { + "epoch": 0.66, + "learning_rate": 1.6935191606451757e-05, + "loss": 0.1143, + "step": 296730 + }, + { + "epoch": 0.66, + "learning_rate": 1.6934073063242435e-05, + "loss": 0.1147, + "step": 296740 + }, + { + "epoch": 0.66, + "learning_rate": 1.6933066374354044e-05, + "loss": 0.1198, + "step": 296750 + }, + { + "epoch": 0.66, + "learning_rate": 1.6931947831144718e-05, + "loss": 0.1104, + "step": 296760 + }, + { + "epoch": 0.66, + "learning_rate": 1.6930829287935393e-05, + "loss": 0.1128, + "step": 296770 + }, + { + "epoch": 0.66, + "learning_rate": 1.6929710744726067e-05, + "loss": 0.1136, + "step": 296780 + }, + { + "epoch": 0.66, + "learning_rate": 1.6928592201516745e-05, + "loss": 0.1129, + "step": 296790 + }, + { + "epoch": 0.66, + "learning_rate": 1.6927473658307423e-05, + "loss": 0.111, + "step": 296800 + }, + { + "epoch": 0.66, + "learning_rate": 1.6926355115098098e-05, + "loss": 0.1148, + "step": 296810 + }, + { + "epoch": 0.66, + "learning_rate": 1.6925236571888772e-05, + "loss": 0.1165, + "step": 296820 + }, + { + "epoch": 0.66, + "learning_rate": 1.6924118028679447e-05, + "loss": 0.1149, + "step": 296830 + }, + { + "epoch": 0.66, + "learning_rate": 1.6922999485470125e-05, + "loss": 0.1125, + "step": 296840 + }, + { + "epoch": 0.66, + "learning_rate": 1.6921880942260803e-05, + "loss": 0.112, + "step": 296850 + }, + { + "epoch": 0.66, + "learning_rate": 1.6920762399051477e-05, + "loss": 0.1178, + "step": 296860 + }, + { + "epoch": 0.66, + "learning_rate": 1.691964385584215e-05, + "loss": 0.108, + "step": 296870 + }, + { + "epoch": 0.66, + "learning_rate": 1.6918525312632826e-05, + "loss": 0.1153, + "step": 296880 + }, + { + "epoch": 0.66, + "learning_rate": 1.6917406769423504e-05, + "loss": 0.1158, + "step": 296890 + }, + { + "epoch": 0.66, + "learning_rate": 1.691628822621418e-05, + "loss": 0.1082, + "step": 296900 + }, + { + "epoch": 0.66, + "learning_rate": 1.6915169683004857e-05, + "loss": 0.1124, + "step": 296910 + }, + { + "epoch": 0.66, + "learning_rate": 1.691405113979553e-05, + "loss": 0.1084, + "step": 296920 + }, + { + "epoch": 0.66, + "learning_rate": 1.6912932596586206e-05, + "loss": 0.1129, + "step": 296930 + }, + { + "epoch": 0.66, + "learning_rate": 1.691181405337688e-05, + "loss": 0.1156, + "step": 296940 + }, + { + "epoch": 0.66, + "learning_rate": 1.6910695510167558e-05, + "loss": 0.1096, + "step": 296950 + }, + { + "epoch": 0.66, + "learning_rate": 1.6909576966958236e-05, + "loss": 0.113, + "step": 296960 + }, + { + "epoch": 0.66, + "learning_rate": 1.690845842374891e-05, + "loss": 0.1128, + "step": 296970 + }, + { + "epoch": 0.66, + "learning_rate": 1.6907339880539585e-05, + "loss": 0.112, + "step": 296980 + }, + { + "epoch": 0.66, + "learning_rate": 1.690622133733026e-05, + "loss": 0.1144, + "step": 296990 + }, + { + "epoch": 0.66, + "learning_rate": 1.6905102794120938e-05, + "loss": 0.1171, + "step": 297000 + }, + { + "epoch": 0.66, + "learning_rate": 1.6903984250911616e-05, + "loss": 0.1135, + "step": 297010 + }, + { + "epoch": 0.66, + "learning_rate": 1.690286570770229e-05, + "loss": 0.113, + "step": 297020 + }, + { + "epoch": 0.66, + "learning_rate": 1.6901747164492965e-05, + "loss": 0.1084, + "step": 297030 + }, + { + "epoch": 0.66, + "learning_rate": 1.690062862128364e-05, + "loss": 0.1127, + "step": 297040 + }, + { + "epoch": 0.66, + "learning_rate": 1.6899510078074317e-05, + "loss": 0.1124, + "step": 297050 + }, + { + "epoch": 0.66, + "learning_rate": 1.6898391534864995e-05, + "loss": 0.1162, + "step": 297060 + }, + { + "epoch": 0.66, + "learning_rate": 1.689727299165567e-05, + "loss": 0.1106, + "step": 297070 + }, + { + "epoch": 0.66, + "learning_rate": 1.6896154448446344e-05, + "loss": 0.1137, + "step": 297080 + }, + { + "epoch": 0.66, + "learning_rate": 1.689503590523702e-05, + "loss": 0.1112, + "step": 297090 + }, + { + "epoch": 0.66, + "learning_rate": 1.6893917362027693e-05, + "loss": 0.1122, + "step": 297100 + }, + { + "epoch": 0.66, + "learning_rate": 1.6892798818818374e-05, + "loss": 0.1098, + "step": 297110 + }, + { + "epoch": 0.66, + "learning_rate": 1.689168027560905e-05, + "loss": 0.1113, + "step": 297120 + }, + { + "epoch": 0.66, + "learning_rate": 1.6890561732399724e-05, + "loss": 0.1117, + "step": 297130 + }, + { + "epoch": 0.66, + "learning_rate": 1.6889443189190398e-05, + "loss": 0.113, + "step": 297140 + }, + { + "epoch": 0.66, + "learning_rate": 1.6888324645981073e-05, + "loss": 0.1161, + "step": 297150 + }, + { + "epoch": 0.66, + "learning_rate": 1.688720610277175e-05, + "loss": 0.108, + "step": 297160 + }, + { + "epoch": 0.66, + "learning_rate": 1.688608755956243e-05, + "loss": 0.112, + "step": 297170 + }, + { + "epoch": 0.66, + "learning_rate": 1.6884969016353103e-05, + "loss": 0.1156, + "step": 297180 + }, + { + "epoch": 0.66, + "learning_rate": 1.6883850473143778e-05, + "loss": 0.1115, + "step": 297190 + }, + { + "epoch": 0.66, + "learning_rate": 1.6882731929934452e-05, + "loss": 0.1134, + "step": 297200 + }, + { + "epoch": 0.66, + "learning_rate": 1.688161338672513e-05, + "loss": 0.1146, + "step": 297210 + }, + { + "epoch": 0.66, + "learning_rate": 1.6880494843515808e-05, + "loss": 0.1135, + "step": 297220 + }, + { + "epoch": 0.66, + "learning_rate": 1.6879376300306482e-05, + "loss": 0.1162, + "step": 297230 + }, + { + "epoch": 0.66, + "learning_rate": 1.6878257757097157e-05, + "loss": 0.1131, + "step": 297240 + }, + { + "epoch": 0.66, + "learning_rate": 1.687713921388783e-05, + "loss": 0.1151, + "step": 297250 + }, + { + "epoch": 0.66, + "learning_rate": 1.687602067067851e-05, + "loss": 0.1143, + "step": 297260 + }, + { + "epoch": 0.66, + "learning_rate": 1.6874902127469187e-05, + "loss": 0.1122, + "step": 297270 + }, + { + "epoch": 0.66, + "learning_rate": 1.6873783584259862e-05, + "loss": 0.115, + "step": 297280 + }, + { + "epoch": 0.66, + "learning_rate": 1.6872665041050536e-05, + "loss": 0.109, + "step": 297290 + }, + { + "epoch": 0.66, + "learning_rate": 1.687154649784121e-05, + "loss": 0.1143, + "step": 297300 + }, + { + "epoch": 0.66, + "learning_rate": 1.6870427954631886e-05, + "loss": 0.1131, + "step": 297310 + }, + { + "epoch": 0.66, + "learning_rate": 1.6869309411422567e-05, + "loss": 0.1164, + "step": 297320 + }, + { + "epoch": 0.66, + "learning_rate": 1.686819086821324e-05, + "loss": 0.1093, + "step": 297330 + }, + { + "epoch": 0.66, + "learning_rate": 1.6867072325003916e-05, + "loss": 0.1164, + "step": 297340 + }, + { + "epoch": 0.66, + "learning_rate": 1.686595378179459e-05, + "loss": 0.1108, + "step": 297350 + }, + { + "epoch": 0.66, + "learning_rate": 1.6864835238585265e-05, + "loss": 0.1126, + "step": 297360 + }, + { + "epoch": 0.66, + "learning_rate": 1.6863716695375943e-05, + "loss": 0.1213, + "step": 297370 + }, + { + "epoch": 0.66, + "learning_rate": 1.686259815216662e-05, + "loss": 0.1119, + "step": 297380 + }, + { + "epoch": 0.66, + "learning_rate": 1.6861479608957295e-05, + "loss": 0.111, + "step": 297390 + }, + { + "epoch": 0.66, + "learning_rate": 1.686036106574797e-05, + "loss": 0.1129, + "step": 297400 + }, + { + "epoch": 0.66, + "learning_rate": 1.6859242522538645e-05, + "loss": 0.1148, + "step": 297410 + }, + { + "epoch": 0.66, + "learning_rate": 1.6858123979329322e-05, + "loss": 0.1104, + "step": 297420 + }, + { + "epoch": 0.66, + "learning_rate": 1.685700543612e-05, + "loss": 0.1123, + "step": 297430 + }, + { + "epoch": 0.66, + "learning_rate": 1.6855886892910675e-05, + "loss": 0.1126, + "step": 297440 + }, + { + "epoch": 0.66, + "learning_rate": 1.685476834970135e-05, + "loss": 0.1104, + "step": 297450 + }, + { + "epoch": 0.66, + "learning_rate": 1.6853649806492024e-05, + "loss": 0.1137, + "step": 297460 + }, + { + "epoch": 0.66, + "learning_rate": 1.6852531263282702e-05, + "loss": 0.1143, + "step": 297470 + }, + { + "epoch": 0.66, + "learning_rate": 1.685141272007338e-05, + "loss": 0.1118, + "step": 297480 + }, + { + "epoch": 0.66, + "learning_rate": 1.6850294176864054e-05, + "loss": 0.112, + "step": 297490 + }, + { + "epoch": 0.66, + "learning_rate": 1.684917563365473e-05, + "loss": 0.1095, + "step": 297500 + }, + { + "epoch": 0.66, + "learning_rate": 1.6848057090445403e-05, + "loss": 0.1122, + "step": 297510 + }, + { + "epoch": 0.66, + "learning_rate": 1.6846938547236078e-05, + "loss": 0.111, + "step": 297520 + }, + { + "epoch": 0.66, + "learning_rate": 1.6845820004026756e-05, + "loss": 0.1154, + "step": 297530 + }, + { + "epoch": 0.66, + "learning_rate": 1.6844701460817434e-05, + "loss": 0.1122, + "step": 297540 + }, + { + "epoch": 0.66, + "learning_rate": 1.684358291760811e-05, + "loss": 0.1106, + "step": 297550 + }, + { + "epoch": 0.66, + "learning_rate": 1.6842464374398783e-05, + "loss": 0.1118, + "step": 297560 + }, + { + "epoch": 0.66, + "learning_rate": 1.6841345831189457e-05, + "loss": 0.1089, + "step": 297570 + }, + { + "epoch": 0.66, + "learning_rate": 1.6840227287980135e-05, + "loss": 0.1161, + "step": 297580 + }, + { + "epoch": 0.66, + "learning_rate": 1.6839108744770813e-05, + "loss": 0.1098, + "step": 297590 + }, + { + "epoch": 0.66, + "learning_rate": 1.6837990201561488e-05, + "loss": 0.1142, + "step": 297600 + }, + { + "epoch": 0.66, + "learning_rate": 1.6836871658352162e-05, + "loss": 0.1161, + "step": 297610 + }, + { + "epoch": 0.66, + "learning_rate": 1.6835753115142837e-05, + "loss": 0.1086, + "step": 297620 + }, + { + "epoch": 0.66, + "learning_rate": 1.6834634571933515e-05, + "loss": 0.1159, + "step": 297630 + }, + { + "epoch": 0.66, + "learning_rate": 1.6833516028724193e-05, + "loss": 0.1116, + "step": 297640 + }, + { + "epoch": 0.66, + "learning_rate": 1.6832397485514867e-05, + "loss": 0.1127, + "step": 297650 + }, + { + "epoch": 0.66, + "learning_rate": 1.6831278942305542e-05, + "loss": 0.1149, + "step": 297660 + }, + { + "epoch": 0.66, + "learning_rate": 1.6830160399096216e-05, + "loss": 0.112, + "step": 297670 + }, + { + "epoch": 0.66, + "learning_rate": 1.6829041855886894e-05, + "loss": 0.1111, + "step": 297680 + }, + { + "epoch": 0.66, + "learning_rate": 1.682792331267757e-05, + "loss": 0.1094, + "step": 297690 + }, + { + "epoch": 0.66, + "learning_rate": 1.6826804769468247e-05, + "loss": 0.1119, + "step": 297700 + }, + { + "epoch": 0.66, + "learning_rate": 1.682568622625892e-05, + "loss": 0.1146, + "step": 297710 + }, + { + "epoch": 0.66, + "learning_rate": 1.6824567683049596e-05, + "loss": 0.1156, + "step": 297720 + }, + { + "epoch": 0.66, + "learning_rate": 1.6823449139840274e-05, + "loss": 0.1117, + "step": 297730 + }, + { + "epoch": 0.66, + "learning_rate": 1.682233059663095e-05, + "loss": 0.109, + "step": 297740 + }, + { + "epoch": 0.66, + "learning_rate": 1.6821212053421626e-05, + "loss": 0.1119, + "step": 297750 + }, + { + "epoch": 0.66, + "learning_rate": 1.68200935102123e-05, + "loss": 0.1133, + "step": 297760 + }, + { + "epoch": 0.66, + "learning_rate": 1.6818974967002975e-05, + "loss": 0.1119, + "step": 297770 + }, + { + "epoch": 0.66, + "learning_rate": 1.681785642379365e-05, + "loss": 0.1162, + "step": 297780 + }, + { + "epoch": 0.66, + "learning_rate": 1.6816737880584328e-05, + "loss": 0.1136, + "step": 297790 + }, + { + "epoch": 0.66, + "learning_rate": 1.6815619337375006e-05, + "loss": 0.1158, + "step": 297800 + }, + { + "epoch": 0.66, + "learning_rate": 1.681450079416568e-05, + "loss": 0.1109, + "step": 297810 + }, + { + "epoch": 0.66, + "learning_rate": 1.6813382250956355e-05, + "loss": 0.1106, + "step": 297820 + }, + { + "epoch": 0.66, + "learning_rate": 1.681226370774703e-05, + "loss": 0.1147, + "step": 297830 + }, + { + "epoch": 0.66, + "learning_rate": 1.6811145164537707e-05, + "loss": 0.1117, + "step": 297840 + }, + { + "epoch": 0.66, + "learning_rate": 1.6810026621328382e-05, + "loss": 0.1131, + "step": 297850 + }, + { + "epoch": 0.66, + "learning_rate": 1.680890807811906e-05, + "loss": 0.1107, + "step": 297860 + }, + { + "epoch": 0.66, + "learning_rate": 1.6807789534909734e-05, + "loss": 0.1161, + "step": 297870 + }, + { + "epoch": 0.66, + "learning_rate": 1.680667099170041e-05, + "loss": 0.1139, + "step": 297880 + }, + { + "epoch": 0.66, + "learning_rate": 1.6805552448491087e-05, + "loss": 0.1097, + "step": 297890 + }, + { + "epoch": 0.66, + "learning_rate": 1.680443390528176e-05, + "loss": 0.1139, + "step": 297900 + }, + { + "epoch": 0.66, + "learning_rate": 1.680331536207244e-05, + "loss": 0.1118, + "step": 297910 + }, + { + "epoch": 0.66, + "learning_rate": 1.6802196818863114e-05, + "loss": 0.112, + "step": 297920 + }, + { + "epoch": 0.67, + "learning_rate": 1.680107827565379e-05, + "loss": 0.1126, + "step": 297930 + }, + { + "epoch": 0.67, + "learning_rate": 1.6799959732444466e-05, + "loss": 0.1103, + "step": 297940 + }, + { + "epoch": 0.67, + "learning_rate": 1.679884118923514e-05, + "loss": 0.1145, + "step": 297950 + }, + { + "epoch": 0.67, + "learning_rate": 1.679772264602582e-05, + "loss": 0.1113, + "step": 297960 + }, + { + "epoch": 0.67, + "learning_rate": 1.6796604102816493e-05, + "loss": 0.1175, + "step": 297970 + }, + { + "epoch": 0.67, + "learning_rate": 1.6795485559607168e-05, + "loss": 0.1165, + "step": 297980 + }, + { + "epoch": 0.67, + "learning_rate": 1.6794367016397842e-05, + "loss": 0.1115, + "step": 297990 + }, + { + "epoch": 0.67, + "learning_rate": 1.679324847318852e-05, + "loss": 0.1128, + "step": 298000 + }, + { + "epoch": 0.67, + "learning_rate": 1.6792129929979195e-05, + "loss": 0.1105, + "step": 298010 + }, + { + "epoch": 0.67, + "learning_rate": 1.6791011386769873e-05, + "loss": 0.1133, + "step": 298020 + }, + { + "epoch": 0.67, + "learning_rate": 1.6789892843560547e-05, + "loss": 0.1142, + "step": 298030 + }, + { + "epoch": 0.67, + "learning_rate": 1.6788774300351222e-05, + "loss": 0.1099, + "step": 298040 + }, + { + "epoch": 0.67, + "learning_rate": 1.67876557571419e-05, + "loss": 0.1176, + "step": 298050 + }, + { + "epoch": 0.67, + "learning_rate": 1.6786537213932574e-05, + "loss": 0.1101, + "step": 298060 + }, + { + "epoch": 0.67, + "learning_rate": 1.6785418670723252e-05, + "loss": 0.1117, + "step": 298070 + }, + { + "epoch": 0.67, + "learning_rate": 1.6784300127513927e-05, + "loss": 0.1111, + "step": 298080 + }, + { + "epoch": 0.67, + "learning_rate": 1.67831815843046e-05, + "loss": 0.1145, + "step": 298090 + }, + { + "epoch": 0.67, + "learning_rate": 1.678206304109528e-05, + "loss": 0.1126, + "step": 298100 + }, + { + "epoch": 0.67, + "learning_rate": 1.6780944497885954e-05, + "loss": 0.1175, + "step": 298110 + }, + { + "epoch": 0.67, + "learning_rate": 1.6779825954676632e-05, + "loss": 0.1108, + "step": 298120 + }, + { + "epoch": 0.67, + "learning_rate": 1.6778707411467306e-05, + "loss": 0.1129, + "step": 298130 + }, + { + "epoch": 0.67, + "learning_rate": 1.677758886825798e-05, + "loss": 0.1148, + "step": 298140 + }, + { + "epoch": 0.67, + "learning_rate": 1.677647032504866e-05, + "loss": 0.1124, + "step": 298150 + }, + { + "epoch": 0.67, + "learning_rate": 1.6775351781839333e-05, + "loss": 0.1157, + "step": 298160 + }, + { + "epoch": 0.67, + "learning_rate": 1.6774233238630008e-05, + "loss": 0.1179, + "step": 298170 + }, + { + "epoch": 0.67, + "learning_rate": 1.6773114695420686e-05, + "loss": 0.1093, + "step": 298180 + }, + { + "epoch": 0.67, + "learning_rate": 1.677199615221136e-05, + "loss": 0.1122, + "step": 298190 + }, + { + "epoch": 0.67, + "learning_rate": 1.6770877609002035e-05, + "loss": 0.1117, + "step": 298200 + }, + { + "epoch": 0.67, + "learning_rate": 1.6769759065792713e-05, + "loss": 0.1165, + "step": 298210 + }, + { + "epoch": 0.67, + "learning_rate": 1.6768640522583387e-05, + "loss": 0.1106, + "step": 298220 + }, + { + "epoch": 0.67, + "learning_rate": 1.6767521979374065e-05, + "loss": 0.1151, + "step": 298230 + }, + { + "epoch": 0.67, + "learning_rate": 1.676640343616474e-05, + "loss": 0.1163, + "step": 298240 + }, + { + "epoch": 0.67, + "learning_rate": 1.6765284892955414e-05, + "loss": 0.1154, + "step": 298250 + }, + { + "epoch": 0.67, + "learning_rate": 1.6764166349746092e-05, + "loss": 0.1198, + "step": 298260 + }, + { + "epoch": 0.67, + "learning_rate": 1.6763047806536767e-05, + "loss": 0.1097, + "step": 298270 + }, + { + "epoch": 0.67, + "learning_rate": 1.6761929263327445e-05, + "loss": 0.1166, + "step": 298280 + }, + { + "epoch": 0.67, + "learning_rate": 1.676081072011812e-05, + "loss": 0.11, + "step": 298290 + }, + { + "epoch": 0.67, + "learning_rate": 1.6759692176908794e-05, + "loss": 0.1122, + "step": 298300 + }, + { + "epoch": 0.67, + "learning_rate": 1.675857363369947e-05, + "loss": 0.1126, + "step": 298310 + }, + { + "epoch": 0.67, + "learning_rate": 1.6757455090490146e-05, + "loss": 0.1135, + "step": 298320 + }, + { + "epoch": 0.67, + "learning_rate": 1.675633654728082e-05, + "loss": 0.1161, + "step": 298330 + }, + { + "epoch": 0.67, + "learning_rate": 1.67552180040715e-05, + "loss": 0.1171, + "step": 298340 + }, + { + "epoch": 0.67, + "learning_rate": 1.6754099460862173e-05, + "loss": 0.1121, + "step": 298350 + }, + { + "epoch": 0.67, + "learning_rate": 1.675298091765285e-05, + "loss": 0.1143, + "step": 298360 + }, + { + "epoch": 0.67, + "learning_rate": 1.6751862374443526e-05, + "loss": 0.1103, + "step": 298370 + }, + { + "epoch": 0.67, + "learning_rate": 1.67507438312342e-05, + "loss": 0.1118, + "step": 298380 + }, + { + "epoch": 0.67, + "learning_rate": 1.6749625288024878e-05, + "loss": 0.1123, + "step": 298390 + }, + { + "epoch": 0.67, + "learning_rate": 1.6748506744815553e-05, + "loss": 0.1138, + "step": 298400 + }, + { + "epoch": 0.67, + "learning_rate": 1.6747388201606227e-05, + "loss": 0.114, + "step": 298410 + }, + { + "epoch": 0.67, + "learning_rate": 1.6746269658396905e-05, + "loss": 0.1123, + "step": 298420 + }, + { + "epoch": 0.67, + "learning_rate": 1.674515111518758e-05, + "loss": 0.1111, + "step": 298430 + }, + { + "epoch": 0.67, + "learning_rate": 1.6744032571978258e-05, + "loss": 0.1144, + "step": 298440 + }, + { + "epoch": 0.67, + "learning_rate": 1.6742914028768932e-05, + "loss": 0.1102, + "step": 298450 + }, + { + "epoch": 0.67, + "learning_rate": 1.6741795485559607e-05, + "loss": 0.1125, + "step": 298460 + }, + { + "epoch": 0.67, + "learning_rate": 1.6740676942350285e-05, + "loss": 0.1116, + "step": 298470 + }, + { + "epoch": 0.67, + "learning_rate": 1.673955839914096e-05, + "loss": 0.1097, + "step": 298480 + }, + { + "epoch": 0.67, + "learning_rate": 1.6738439855931634e-05, + "loss": 0.113, + "step": 298490 + }, + { + "epoch": 0.67, + "learning_rate": 1.673732131272231e-05, + "loss": 0.1061, + "step": 298500 + }, + { + "epoch": 0.67, + "learning_rate": 1.6736202769512986e-05, + "loss": 0.1086, + "step": 298510 + }, + { + "epoch": 0.67, + "learning_rate": 1.6735084226303664e-05, + "loss": 0.1109, + "step": 298520 + }, + { + "epoch": 0.67, + "learning_rate": 1.673396568309434e-05, + "loss": 0.1125, + "step": 298530 + }, + { + "epoch": 0.67, + "learning_rate": 1.6732847139885013e-05, + "loss": 0.1119, + "step": 298540 + }, + { + "epoch": 0.67, + "learning_rate": 1.673172859667569e-05, + "loss": 0.1128, + "step": 298550 + }, + { + "epoch": 0.67, + "learning_rate": 1.6730610053466366e-05, + "loss": 0.1108, + "step": 298560 + }, + { + "epoch": 0.67, + "learning_rate": 1.6729491510257044e-05, + "loss": 0.1118, + "step": 298570 + }, + { + "epoch": 0.67, + "learning_rate": 1.6728372967047718e-05, + "loss": 0.1137, + "step": 298580 + }, + { + "epoch": 0.67, + "learning_rate": 1.6727254423838393e-05, + "loss": 0.1161, + "step": 298590 + }, + { + "epoch": 0.67, + "learning_rate": 1.672613588062907e-05, + "loss": 0.1123, + "step": 298600 + }, + { + "epoch": 0.67, + "learning_rate": 1.6725017337419745e-05, + "loss": 0.1129, + "step": 298610 + }, + { + "epoch": 0.67, + "learning_rate": 1.6723898794210423e-05, + "loss": 0.1132, + "step": 298620 + }, + { + "epoch": 0.67, + "learning_rate": 1.6722780251001098e-05, + "loss": 0.1137, + "step": 298630 + }, + { + "epoch": 0.67, + "learning_rate": 1.6721661707791772e-05, + "loss": 0.1125, + "step": 298640 + }, + { + "epoch": 0.67, + "learning_rate": 1.6720543164582447e-05, + "loss": 0.1118, + "step": 298650 + }, + { + "epoch": 0.67, + "learning_rate": 1.6719424621373125e-05, + "loss": 0.1126, + "step": 298660 + }, + { + "epoch": 0.67, + "learning_rate": 1.67183060781638e-05, + "loss": 0.1091, + "step": 298670 + }, + { + "epoch": 0.67, + "learning_rate": 1.6717187534954477e-05, + "loss": 0.112, + "step": 298680 + }, + { + "epoch": 0.67, + "learning_rate": 1.671606899174515e-05, + "loss": 0.1144, + "step": 298690 + }, + { + "epoch": 0.67, + "learning_rate": 1.6714950448535826e-05, + "loss": 0.1116, + "step": 298700 + }, + { + "epoch": 0.67, + "learning_rate": 1.6713831905326504e-05, + "loss": 0.1124, + "step": 298710 + }, + { + "epoch": 0.67, + "learning_rate": 1.671271336211718e-05, + "loss": 0.114, + "step": 298720 + }, + { + "epoch": 0.67, + "learning_rate": 1.6711594818907857e-05, + "loss": 0.1128, + "step": 298730 + }, + { + "epoch": 0.67, + "learning_rate": 1.671047627569853e-05, + "loss": 0.1122, + "step": 298740 + }, + { + "epoch": 0.67, + "learning_rate": 1.670946958681014e-05, + "loss": 0.1136, + "step": 298750 + }, + { + "epoch": 0.67, + "learning_rate": 1.6708351043600814e-05, + "loss": 0.1135, + "step": 298760 + }, + { + "epoch": 0.67, + "learning_rate": 1.670723250039149e-05, + "loss": 0.1191, + "step": 298770 + }, + { + "epoch": 0.67, + "learning_rate": 1.6706113957182167e-05, + "loss": 0.1173, + "step": 298780 + }, + { + "epoch": 0.67, + "learning_rate": 1.6704995413972845e-05, + "loss": 0.1127, + "step": 298790 + }, + { + "epoch": 0.67, + "learning_rate": 1.670387687076352e-05, + "loss": 0.1127, + "step": 298800 + }, + { + "epoch": 0.67, + "learning_rate": 1.6702758327554194e-05, + "loss": 0.1134, + "step": 298810 + }, + { + "epoch": 0.67, + "learning_rate": 1.670163978434487e-05, + "loss": 0.1106, + "step": 298820 + }, + { + "epoch": 0.67, + "learning_rate": 1.6700521241135546e-05, + "loss": 0.1188, + "step": 298830 + }, + { + "epoch": 0.67, + "learning_rate": 1.669940269792622e-05, + "loss": 0.1145, + "step": 298840 + }, + { + "epoch": 0.67, + "learning_rate": 1.66982841547169e-05, + "loss": 0.1117, + "step": 298850 + }, + { + "epoch": 0.67, + "learning_rate": 1.6697165611507573e-05, + "loss": 0.1098, + "step": 298860 + }, + { + "epoch": 0.67, + "learning_rate": 1.6696047068298248e-05, + "loss": 0.1146, + "step": 298870 + }, + { + "epoch": 0.67, + "learning_rate": 1.6694928525088922e-05, + "loss": 0.1126, + "step": 298880 + }, + { + "epoch": 0.67, + "learning_rate": 1.66938099818796e-05, + "loss": 0.1115, + "step": 298890 + }, + { + "epoch": 0.67, + "learning_rate": 1.6692691438670278e-05, + "loss": 0.1133, + "step": 298900 + }, + { + "epoch": 0.67, + "learning_rate": 1.6691572895460953e-05, + "loss": 0.1092, + "step": 298910 + }, + { + "epoch": 0.67, + "learning_rate": 1.6690454352251627e-05, + "loss": 0.1148, + "step": 298920 + }, + { + "epoch": 0.67, + "learning_rate": 1.6689335809042302e-05, + "loss": 0.1129, + "step": 298930 + }, + { + "epoch": 0.67, + "learning_rate": 1.668821726583298e-05, + "loss": 0.1139, + "step": 298940 + }, + { + "epoch": 0.67, + "learning_rate": 1.6687098722623658e-05, + "loss": 0.1148, + "step": 298950 + }, + { + "epoch": 0.67, + "learning_rate": 1.6685980179414332e-05, + "loss": 0.1149, + "step": 298960 + }, + { + "epoch": 0.67, + "learning_rate": 1.6684861636205007e-05, + "loss": 0.1129, + "step": 298970 + }, + { + "epoch": 0.67, + "learning_rate": 1.668374309299568e-05, + "loss": 0.1142, + "step": 298980 + }, + { + "epoch": 0.67, + "learning_rate": 1.668262454978636e-05, + "loss": 0.1151, + "step": 298990 + }, + { + "epoch": 0.67, + "learning_rate": 1.6681506006577037e-05, + "loss": 0.1124, + "step": 299000 + }, + { + "epoch": 0.67, + "learning_rate": 1.6680387463367712e-05, + "loss": 0.1102, + "step": 299010 + }, + { + "epoch": 0.67, + "learning_rate": 1.6679268920158386e-05, + "loss": 0.118, + "step": 299020 + }, + { + "epoch": 0.67, + "learning_rate": 1.667815037694906e-05, + "loss": 0.1128, + "step": 299030 + }, + { + "epoch": 0.67, + "learning_rate": 1.6677031833739735e-05, + "loss": 0.1099, + "step": 299040 + }, + { + "epoch": 0.67, + "learning_rate": 1.6675913290530413e-05, + "loss": 0.1161, + "step": 299050 + }, + { + "epoch": 0.67, + "learning_rate": 1.667479474732109e-05, + "loss": 0.1128, + "step": 299060 + }, + { + "epoch": 0.67, + "learning_rate": 1.6673676204111766e-05, + "loss": 0.1125, + "step": 299070 + }, + { + "epoch": 0.67, + "learning_rate": 1.667255766090244e-05, + "loss": 0.1087, + "step": 299080 + }, + { + "epoch": 0.67, + "learning_rate": 1.6671439117693115e-05, + "loss": 0.1189, + "step": 299090 + }, + { + "epoch": 0.67, + "learning_rate": 1.6670320574483793e-05, + "loss": 0.1127, + "step": 299100 + }, + { + "epoch": 0.67, + "learning_rate": 1.666920203127447e-05, + "loss": 0.1121, + "step": 299110 + }, + { + "epoch": 0.67, + "learning_rate": 1.6668083488065145e-05, + "loss": 0.1089, + "step": 299120 + }, + { + "epoch": 0.67, + "learning_rate": 1.666696494485582e-05, + "loss": 0.1113, + "step": 299130 + }, + { + "epoch": 0.67, + "learning_rate": 1.6665846401646494e-05, + "loss": 0.1138, + "step": 299140 + }, + { + "epoch": 0.67, + "learning_rate": 1.6664727858437172e-05, + "loss": 0.112, + "step": 299150 + }, + { + "epoch": 0.67, + "learning_rate": 1.666360931522785e-05, + "loss": 0.1104, + "step": 299160 + }, + { + "epoch": 0.67, + "learning_rate": 1.6662490772018525e-05, + "loss": 0.1109, + "step": 299170 + }, + { + "epoch": 0.67, + "learning_rate": 1.66613722288092e-05, + "loss": 0.1101, + "step": 299180 + }, + { + "epoch": 0.67, + "learning_rate": 1.6660253685599874e-05, + "loss": 0.1129, + "step": 299190 + }, + { + "epoch": 0.67, + "learning_rate": 1.6659135142390552e-05, + "loss": 0.1144, + "step": 299200 + }, + { + "epoch": 0.67, + "learning_rate": 1.665801659918123e-05, + "loss": 0.1101, + "step": 299210 + }, + { + "epoch": 0.67, + "learning_rate": 1.6656898055971904e-05, + "loss": 0.1098, + "step": 299220 + }, + { + "epoch": 0.67, + "learning_rate": 1.665577951276258e-05, + "loss": 0.1179, + "step": 299230 + }, + { + "epoch": 0.67, + "learning_rate": 1.6654660969553253e-05, + "loss": 0.1164, + "step": 299240 + }, + { + "epoch": 0.67, + "learning_rate": 1.6653542426343928e-05, + "loss": 0.1119, + "step": 299250 + }, + { + "epoch": 0.67, + "learning_rate": 1.6652423883134606e-05, + "loss": 0.1146, + "step": 299260 + }, + { + "epoch": 0.67, + "learning_rate": 1.6651305339925284e-05, + "loss": 0.1141, + "step": 299270 + }, + { + "epoch": 0.67, + "learning_rate": 1.6650186796715958e-05, + "loss": 0.1139, + "step": 299280 + }, + { + "epoch": 0.67, + "learning_rate": 1.6649068253506633e-05, + "loss": 0.1117, + "step": 299290 + }, + { + "epoch": 0.67, + "learning_rate": 1.6647949710297307e-05, + "loss": 0.1164, + "step": 299300 + }, + { + "epoch": 0.67, + "learning_rate": 1.6646831167087985e-05, + "loss": 0.1119, + "step": 299310 + }, + { + "epoch": 0.67, + "learning_rate": 1.6645712623878663e-05, + "loss": 0.1117, + "step": 299320 + }, + { + "epoch": 0.67, + "learning_rate": 1.6644594080669338e-05, + "loss": 0.1136, + "step": 299330 + }, + { + "epoch": 0.67, + "learning_rate": 1.6643475537460012e-05, + "loss": 0.117, + "step": 299340 + }, + { + "epoch": 0.67, + "learning_rate": 1.6642356994250687e-05, + "loss": 0.1107, + "step": 299350 + }, + { + "epoch": 0.67, + "learning_rate": 1.6641238451041365e-05, + "loss": 0.1137, + "step": 299360 + }, + { + "epoch": 0.67, + "learning_rate": 1.6640119907832043e-05, + "loss": 0.108, + "step": 299370 + }, + { + "epoch": 0.67, + "learning_rate": 1.6639001364622717e-05, + "loss": 0.1115, + "step": 299380 + }, + { + "epoch": 0.67, + "learning_rate": 1.6637882821413392e-05, + "loss": 0.108, + "step": 299390 + }, + { + "epoch": 0.67, + "learning_rate": 1.6636764278204066e-05, + "loss": 0.1106, + "step": 299400 + }, + { + "epoch": 0.67, + "learning_rate": 1.6635645734994744e-05, + "loss": 0.1135, + "step": 299410 + }, + { + "epoch": 0.67, + "learning_rate": 1.6634527191785422e-05, + "loss": 0.1109, + "step": 299420 + }, + { + "epoch": 0.67, + "learning_rate": 1.6633408648576097e-05, + "loss": 0.1161, + "step": 299430 + }, + { + "epoch": 0.67, + "learning_rate": 1.663229010536677e-05, + "loss": 0.1117, + "step": 299440 + }, + { + "epoch": 0.67, + "learning_rate": 1.6631171562157446e-05, + "loss": 0.1118, + "step": 299450 + }, + { + "epoch": 0.67, + "learning_rate": 1.663005301894812e-05, + "loss": 0.1091, + "step": 299460 + }, + { + "epoch": 0.67, + "learning_rate": 1.66289344757388e-05, + "loss": 0.1131, + "step": 299470 + }, + { + "epoch": 0.67, + "learning_rate": 1.6627815932529476e-05, + "loss": 0.1123, + "step": 299480 + }, + { + "epoch": 0.67, + "learning_rate": 1.662669738932015e-05, + "loss": 0.1176, + "step": 299490 + }, + { + "epoch": 0.67, + "learning_rate": 1.6625578846110825e-05, + "loss": 0.108, + "step": 299500 + }, + { + "epoch": 0.67, + "learning_rate": 1.66244603029015e-05, + "loss": 0.1142, + "step": 299510 + }, + { + "epoch": 0.67, + "learning_rate": 1.6623341759692178e-05, + "loss": 0.1123, + "step": 299520 + }, + { + "epoch": 0.67, + "learning_rate": 1.6622223216482856e-05, + "loss": 0.1118, + "step": 299530 + }, + { + "epoch": 0.67, + "learning_rate": 1.662110467327353e-05, + "loss": 0.1193, + "step": 299540 + }, + { + "epoch": 0.67, + "learning_rate": 1.6619986130064205e-05, + "loss": 0.11, + "step": 299550 + }, + { + "epoch": 0.67, + "learning_rate": 1.661886758685488e-05, + "loss": 0.1123, + "step": 299560 + }, + { + "epoch": 0.67, + "learning_rate": 1.6617749043645557e-05, + "loss": 0.1109, + "step": 299570 + }, + { + "epoch": 0.67, + "learning_rate": 1.6616630500436235e-05, + "loss": 0.1155, + "step": 299580 + }, + { + "epoch": 0.67, + "learning_rate": 1.661551195722691e-05, + "loss": 0.1154, + "step": 299590 + }, + { + "epoch": 0.67, + "learning_rate": 1.6614393414017584e-05, + "loss": 0.1164, + "step": 299600 + }, + { + "epoch": 0.67, + "learning_rate": 1.661327487080826e-05, + "loss": 0.1177, + "step": 299610 + }, + { + "epoch": 0.67, + "learning_rate": 1.6612156327598937e-05, + "loss": 0.1095, + "step": 299620 + }, + { + "epoch": 0.67, + "learning_rate": 1.6611037784389615e-05, + "loss": 0.1119, + "step": 299630 + }, + { + "epoch": 0.67, + "learning_rate": 1.660991924118029e-05, + "loss": 0.111, + "step": 299640 + }, + { + "epoch": 0.67, + "learning_rate": 1.6608800697970964e-05, + "loss": 0.1134, + "step": 299650 + }, + { + "epoch": 0.67, + "learning_rate": 1.6607682154761638e-05, + "loss": 0.1116, + "step": 299660 + }, + { + "epoch": 0.67, + "learning_rate": 1.6606563611552313e-05, + "loss": 0.111, + "step": 299670 + }, + { + "epoch": 0.67, + "learning_rate": 1.660544506834299e-05, + "loss": 0.1161, + "step": 299680 + }, + { + "epoch": 0.67, + "learning_rate": 1.660432652513367e-05, + "loss": 0.1119, + "step": 299690 + }, + { + "epoch": 0.67, + "learning_rate": 1.6603207981924343e-05, + "loss": 0.1132, + "step": 299700 + }, + { + "epoch": 0.67, + "learning_rate": 1.6602089438715018e-05, + "loss": 0.1138, + "step": 299710 + }, + { + "epoch": 0.67, + "learning_rate": 1.6600970895505692e-05, + "loss": 0.1094, + "step": 299720 + }, + { + "epoch": 0.67, + "learning_rate": 1.659985235229637e-05, + "loss": 0.1146, + "step": 299730 + }, + { + "epoch": 0.67, + "learning_rate": 1.6598733809087048e-05, + "loss": 0.113, + "step": 299740 + }, + { + "epoch": 0.67, + "learning_rate": 1.6597615265877723e-05, + "loss": 0.1162, + "step": 299750 + }, + { + "epoch": 0.67, + "learning_rate": 1.6596496722668397e-05, + "loss": 0.1098, + "step": 299760 + }, + { + "epoch": 0.67, + "learning_rate": 1.659537817945907e-05, + "loss": 0.1123, + "step": 299770 + }, + { + "epoch": 0.67, + "learning_rate": 1.659425963624975e-05, + "loss": 0.1151, + "step": 299780 + }, + { + "epoch": 0.67, + "learning_rate": 1.6593141093040427e-05, + "loss": 0.1117, + "step": 299790 + }, + { + "epoch": 0.67, + "learning_rate": 1.6592022549831102e-05, + "loss": 0.1089, + "step": 299800 + }, + { + "epoch": 0.67, + "learning_rate": 1.6590904006621777e-05, + "loss": 0.1126, + "step": 299810 + }, + { + "epoch": 0.67, + "learning_rate": 1.658978546341245e-05, + "loss": 0.1125, + "step": 299820 + }, + { + "epoch": 0.67, + "learning_rate": 1.658866692020313e-05, + "loss": 0.109, + "step": 299830 + }, + { + "epoch": 0.67, + "learning_rate": 1.6587548376993804e-05, + "loss": 0.1109, + "step": 299840 + }, + { + "epoch": 0.67, + "learning_rate": 1.658642983378448e-05, + "loss": 0.1133, + "step": 299850 + }, + { + "epoch": 0.67, + "learning_rate": 1.6585311290575156e-05, + "loss": 0.1135, + "step": 299860 + }, + { + "epoch": 0.67, + "learning_rate": 1.658419274736583e-05, + "loss": 0.1108, + "step": 299870 + }, + { + "epoch": 0.67, + "learning_rate": 1.6583074204156505e-05, + "loss": 0.1089, + "step": 299880 + }, + { + "epoch": 0.67, + "learning_rate": 1.6581955660947183e-05, + "loss": 0.1111, + "step": 299890 + }, + { + "epoch": 0.67, + "learning_rate": 1.658083711773786e-05, + "loss": 0.1129, + "step": 299900 + }, + { + "epoch": 0.67, + "learning_rate": 1.6579718574528536e-05, + "loss": 0.1139, + "step": 299910 + }, + { + "epoch": 0.67, + "learning_rate": 1.657860003131921e-05, + "loss": 0.108, + "step": 299920 + }, + { + "epoch": 0.67, + "learning_rate": 1.6577481488109885e-05, + "loss": 0.1107, + "step": 299930 + }, + { + "epoch": 0.67, + "learning_rate": 1.6576362944900563e-05, + "loss": 0.1114, + "step": 299940 + }, + { + "epoch": 0.67, + "learning_rate": 1.657524440169124e-05, + "loss": 0.1113, + "step": 299950 + }, + { + "epoch": 0.67, + "learning_rate": 1.6574125858481915e-05, + "loss": 0.115, + "step": 299960 + }, + { + "epoch": 0.67, + "learning_rate": 1.657300731527259e-05, + "loss": 0.1111, + "step": 299970 + }, + { + "epoch": 0.67, + "learning_rate": 1.6571888772063264e-05, + "loss": 0.1129, + "step": 299980 + }, + { + "epoch": 0.67, + "learning_rate": 1.6570770228853942e-05, + "loss": 0.1147, + "step": 299990 + }, + { + "epoch": 0.67, + "learning_rate": 1.6569651685644617e-05, + "loss": 0.1136, + "step": 300000 + }, + { + "epoch": 0.67, + "learning_rate": 1.6568533142435294e-05, + "loss": 0.1118, + "step": 300010 + }, + { + "epoch": 0.67, + "learning_rate": 1.656741459922597e-05, + "loss": 0.1144, + "step": 300020 + }, + { + "epoch": 0.67, + "learning_rate": 1.6566296056016644e-05, + "loss": 0.1135, + "step": 300030 + }, + { + "epoch": 0.67, + "learning_rate": 1.656517751280732e-05, + "loss": 0.1139, + "step": 300040 + }, + { + "epoch": 0.67, + "learning_rate": 1.6564058969597996e-05, + "loss": 0.1128, + "step": 300050 + }, + { + "epoch": 0.67, + "learning_rate": 1.6562940426388674e-05, + "loss": 0.1123, + "step": 300060 + }, + { + "epoch": 0.67, + "learning_rate": 1.656182188317935e-05, + "loss": 0.1149, + "step": 300070 + }, + { + "epoch": 0.67, + "learning_rate": 1.6560703339970023e-05, + "loss": 0.1155, + "step": 300080 + }, + { + "epoch": 0.67, + "learning_rate": 1.65595847967607e-05, + "loss": 0.1118, + "step": 300090 + }, + { + "epoch": 0.67, + "learning_rate": 1.6558466253551375e-05, + "loss": 0.1144, + "step": 300100 + }, + { + "epoch": 0.67, + "learning_rate": 1.6557347710342053e-05, + "loss": 0.11, + "step": 300110 + }, + { + "epoch": 0.67, + "learning_rate": 1.6556229167132728e-05, + "loss": 0.1111, + "step": 300120 + }, + { + "epoch": 0.67, + "learning_rate": 1.6555110623923402e-05, + "loss": 0.1121, + "step": 300130 + }, + { + "epoch": 0.67, + "learning_rate": 1.6553992080714077e-05, + "loss": 0.1147, + "step": 300140 + }, + { + "epoch": 0.67, + "learning_rate": 1.6552873537504755e-05, + "loss": 0.1113, + "step": 300150 + }, + { + "epoch": 0.67, + "learning_rate": 1.655175499429543e-05, + "loss": 0.1101, + "step": 300160 + }, + { + "epoch": 0.67, + "learning_rate": 1.6550636451086107e-05, + "loss": 0.1087, + "step": 300170 + }, + { + "epoch": 0.67, + "learning_rate": 1.6549517907876782e-05, + "loss": 0.1116, + "step": 300180 + }, + { + "epoch": 0.67, + "learning_rate": 1.6548399364667457e-05, + "loss": 0.1104, + "step": 300190 + }, + { + "epoch": 0.67, + "learning_rate": 1.6547280821458134e-05, + "loss": 0.1094, + "step": 300200 + }, + { + "epoch": 0.67, + "learning_rate": 1.654616227824881e-05, + "loss": 0.1159, + "step": 300210 + }, + { + "epoch": 0.67, + "learning_rate": 1.6545043735039487e-05, + "loss": 0.1141, + "step": 300220 + }, + { + "epoch": 0.67, + "learning_rate": 1.654392519183016e-05, + "loss": 0.1077, + "step": 300230 + }, + { + "epoch": 0.67, + "learning_rate": 1.6542806648620836e-05, + "loss": 0.1131, + "step": 300240 + }, + { + "epoch": 0.67, + "learning_rate": 1.6541688105411514e-05, + "loss": 0.1123, + "step": 300250 + }, + { + "epoch": 0.67, + "learning_rate": 1.654056956220219e-05, + "loss": 0.1132, + "step": 300260 + }, + { + "epoch": 0.67, + "learning_rate": 1.6539451018992866e-05, + "loss": 0.1091, + "step": 300270 + }, + { + "epoch": 0.67, + "learning_rate": 1.653833247578354e-05, + "loss": 0.1145, + "step": 300280 + }, + { + "epoch": 0.67, + "learning_rate": 1.6537213932574215e-05, + "loss": 0.1127, + "step": 300290 + }, + { + "epoch": 0.67, + "learning_rate": 1.6536095389364893e-05, + "loss": 0.1133, + "step": 300300 + }, + { + "epoch": 0.67, + "learning_rate": 1.6534976846155568e-05, + "loss": 0.1134, + "step": 300310 + }, + { + "epoch": 0.67, + "learning_rate": 1.6533858302946242e-05, + "loss": 0.1098, + "step": 300320 + }, + { + "epoch": 0.67, + "learning_rate": 1.653273975973692e-05, + "loss": 0.1114, + "step": 300330 + }, + { + "epoch": 0.67, + "learning_rate": 1.6531621216527595e-05, + "loss": 0.1069, + "step": 300340 + }, + { + "epoch": 0.67, + "learning_rate": 1.653050267331827e-05, + "loss": 0.1137, + "step": 300350 + }, + { + "epoch": 0.67, + "learning_rate": 1.6529384130108947e-05, + "loss": 0.1155, + "step": 300360 + }, + { + "epoch": 0.67, + "learning_rate": 1.6528265586899622e-05, + "loss": 0.1108, + "step": 300370 + }, + { + "epoch": 0.67, + "learning_rate": 1.65271470436903e-05, + "loss": 0.1133, + "step": 300380 + }, + { + "epoch": 0.67, + "learning_rate": 1.6526028500480974e-05, + "loss": 0.1142, + "step": 300390 + }, + { + "epoch": 0.67, + "learning_rate": 1.652490995727165e-05, + "loss": 0.1121, + "step": 300400 + }, + { + "epoch": 0.67, + "learning_rate": 1.6523791414062327e-05, + "loss": 0.1141, + "step": 300410 + }, + { + "epoch": 0.67, + "learning_rate": 1.6522672870853e-05, + "loss": 0.1142, + "step": 300420 + }, + { + "epoch": 0.67, + "learning_rate": 1.652155432764368e-05, + "loss": 0.1129, + "step": 300430 + }, + { + "epoch": 0.67, + "learning_rate": 1.6520435784434354e-05, + "loss": 0.114, + "step": 300440 + }, + { + "epoch": 0.67, + "learning_rate": 1.651931724122503e-05, + "loss": 0.1103, + "step": 300450 + }, + { + "epoch": 0.67, + "learning_rate": 1.6518198698015706e-05, + "loss": 0.1113, + "step": 300460 + }, + { + "epoch": 0.67, + "learning_rate": 1.651708015480638e-05, + "loss": 0.1076, + "step": 300470 + }, + { + "epoch": 0.67, + "learning_rate": 1.6515961611597055e-05, + "loss": 0.1106, + "step": 300480 + }, + { + "epoch": 0.67, + "learning_rate": 1.6514843068387733e-05, + "loss": 0.1123, + "step": 300490 + }, + { + "epoch": 0.67, + "learning_rate": 1.6513724525178408e-05, + "loss": 0.1135, + "step": 300500 + }, + { + "epoch": 0.67, + "learning_rate": 1.6512605981969086e-05, + "loss": 0.1125, + "step": 300510 + }, + { + "epoch": 0.67, + "learning_rate": 1.651148743875976e-05, + "loss": 0.1144, + "step": 300520 + }, + { + "epoch": 0.67, + "learning_rate": 1.6510368895550435e-05, + "loss": 0.1138, + "step": 300530 + }, + { + "epoch": 0.67, + "learning_rate": 1.6509250352341113e-05, + "loss": 0.1146, + "step": 300540 + }, + { + "epoch": 0.67, + "learning_rate": 1.6508131809131787e-05, + "loss": 0.1139, + "step": 300550 + }, + { + "epoch": 0.67, + "learning_rate": 1.6507013265922462e-05, + "loss": 0.1163, + "step": 300560 + }, + { + "epoch": 0.67, + "learning_rate": 1.650589472271314e-05, + "loss": 0.1151, + "step": 300570 + }, + { + "epoch": 0.67, + "learning_rate": 1.6504776179503814e-05, + "loss": 0.1119, + "step": 300580 + }, + { + "epoch": 0.67, + "learning_rate": 1.650365763629449e-05, + "loss": 0.1069, + "step": 300590 + }, + { + "epoch": 0.67, + "learning_rate": 1.6502539093085167e-05, + "loss": 0.1103, + "step": 300600 + }, + { + "epoch": 0.67, + "learning_rate": 1.650142054987584e-05, + "loss": 0.1148, + "step": 300610 + }, + { + "epoch": 0.67, + "learning_rate": 1.650030200666652e-05, + "loss": 0.1072, + "step": 300620 + }, + { + "epoch": 0.67, + "learning_rate": 1.6499183463457194e-05, + "loss": 0.1159, + "step": 300630 + }, + { + "epoch": 0.67, + "learning_rate": 1.649806492024787e-05, + "loss": 0.1084, + "step": 300640 + }, + { + "epoch": 0.67, + "learning_rate": 1.6496946377038546e-05, + "loss": 0.1122, + "step": 300650 + }, + { + "epoch": 0.67, + "learning_rate": 1.649582783382922e-05, + "loss": 0.112, + "step": 300660 + }, + { + "epoch": 0.67, + "learning_rate": 1.64947092906199e-05, + "loss": 0.1135, + "step": 300670 + }, + { + "epoch": 0.67, + "learning_rate": 1.6493590747410573e-05, + "loss": 0.1078, + "step": 300680 + }, + { + "epoch": 0.67, + "learning_rate": 1.6492472204201248e-05, + "loss": 0.112, + "step": 300690 + }, + { + "epoch": 0.67, + "learning_rate": 1.6491353660991926e-05, + "loss": 0.1091, + "step": 300700 + }, + { + "epoch": 0.67, + "learning_rate": 1.64902351177826e-05, + "loss": 0.1112, + "step": 300710 + }, + { + "epoch": 0.67, + "learning_rate": 1.6489116574573278e-05, + "loss": 0.1123, + "step": 300720 + }, + { + "epoch": 0.67, + "learning_rate": 1.6487998031363953e-05, + "loss": 0.1146, + "step": 300730 + }, + { + "epoch": 0.67, + "learning_rate": 1.6486879488154627e-05, + "loss": 0.1101, + "step": 300740 + }, + { + "epoch": 0.67, + "learning_rate": 1.6485760944945302e-05, + "loss": 0.1146, + "step": 300750 + }, + { + "epoch": 0.67, + "learning_rate": 1.648464240173598e-05, + "loss": 0.1116, + "step": 300760 + }, + { + "epoch": 0.67, + "learning_rate": 1.6483523858526658e-05, + "loss": 0.1121, + "step": 300770 + }, + { + "epoch": 0.67, + "learning_rate": 1.6482517169638263e-05, + "loss": 0.1104, + "step": 300780 + }, + { + "epoch": 0.67, + "learning_rate": 1.648139862642894e-05, + "loss": 0.1129, + "step": 300790 + }, + { + "epoch": 0.67, + "learning_rate": 1.6480280083219616e-05, + "loss": 0.115, + "step": 300800 + }, + { + "epoch": 0.67, + "learning_rate": 1.647916154001029e-05, + "loss": 0.1113, + "step": 300810 + }, + { + "epoch": 0.67, + "learning_rate": 1.6478042996800965e-05, + "loss": 0.1111, + "step": 300820 + }, + { + "epoch": 0.67, + "learning_rate": 1.6476924453591643e-05, + "loss": 0.1078, + "step": 300830 + }, + { + "epoch": 0.67, + "learning_rate": 1.647580591038232e-05, + "loss": 0.1119, + "step": 300840 + }, + { + "epoch": 0.67, + "learning_rate": 1.6474687367172995e-05, + "loss": 0.1151, + "step": 300850 + }, + { + "epoch": 0.67, + "learning_rate": 1.647356882396367e-05, + "loss": 0.1104, + "step": 300860 + }, + { + "epoch": 0.67, + "learning_rate": 1.6472450280754344e-05, + "loss": 0.1194, + "step": 300870 + }, + { + "epoch": 0.67, + "learning_rate": 1.6471331737545022e-05, + "loss": 0.1116, + "step": 300880 + }, + { + "epoch": 0.67, + "learning_rate": 1.64702131943357e-05, + "loss": 0.1148, + "step": 300890 + }, + { + "epoch": 0.67, + "learning_rate": 1.6469094651126375e-05, + "loss": 0.1153, + "step": 300900 + }, + { + "epoch": 0.67, + "learning_rate": 1.646797610791705e-05, + "loss": 0.1114, + "step": 300910 + }, + { + "epoch": 0.67, + "learning_rate": 1.6466857564707724e-05, + "loss": 0.1164, + "step": 300920 + }, + { + "epoch": 0.67, + "learning_rate": 1.64657390214984e-05, + "loss": 0.1089, + "step": 300930 + }, + { + "epoch": 0.67, + "learning_rate": 1.646462047828908e-05, + "loss": 0.118, + "step": 300940 + }, + { + "epoch": 0.67, + "learning_rate": 1.6463501935079754e-05, + "loss": 0.112, + "step": 300950 + }, + { + "epoch": 0.67, + "learning_rate": 1.646238339187043e-05, + "loss": 0.1088, + "step": 300960 + }, + { + "epoch": 0.67, + "learning_rate": 1.6461264848661103e-05, + "loss": 0.1146, + "step": 300970 + }, + { + "epoch": 0.67, + "learning_rate": 1.6460146305451778e-05, + "loss": 0.1125, + "step": 300980 + }, + { + "epoch": 0.67, + "learning_rate": 1.6459027762242456e-05, + "loss": 0.1141, + "step": 300990 + }, + { + "epoch": 0.67, + "learning_rate": 1.6457909219033133e-05, + "loss": 0.1141, + "step": 301000 + }, + { + "epoch": 0.67, + "learning_rate": 1.6456790675823808e-05, + "loss": 0.1152, + "step": 301010 + }, + { + "epoch": 0.67, + "learning_rate": 1.6455672132614483e-05, + "loss": 0.1133, + "step": 301020 + }, + { + "epoch": 0.67, + "learning_rate": 1.6454553589405157e-05, + "loss": 0.1118, + "step": 301030 + }, + { + "epoch": 0.67, + "learning_rate": 1.6453435046195835e-05, + "loss": 0.1146, + "step": 301040 + }, + { + "epoch": 0.67, + "learning_rate": 1.6452316502986513e-05, + "loss": 0.1135, + "step": 301050 + }, + { + "epoch": 0.67, + "learning_rate": 1.6451197959777187e-05, + "loss": 0.1113, + "step": 301060 + }, + { + "epoch": 0.67, + "learning_rate": 1.6450079416567862e-05, + "loss": 0.1141, + "step": 301070 + }, + { + "epoch": 0.67, + "learning_rate": 1.6448960873358537e-05, + "loss": 0.1176, + "step": 301080 + }, + { + "epoch": 0.67, + "learning_rate": 1.6447842330149215e-05, + "loss": 0.1107, + "step": 301090 + }, + { + "epoch": 0.67, + "learning_rate": 1.6446723786939892e-05, + "loss": 0.114, + "step": 301100 + }, + { + "epoch": 0.67, + "learning_rate": 1.6445605243730567e-05, + "loss": 0.1126, + "step": 301110 + }, + { + "epoch": 0.67, + "learning_rate": 1.644448670052124e-05, + "loss": 0.1102, + "step": 301120 + }, + { + "epoch": 0.67, + "learning_rate": 1.6443368157311916e-05, + "loss": 0.1138, + "step": 301130 + }, + { + "epoch": 0.67, + "learning_rate": 1.644224961410259e-05, + "loss": 0.1101, + "step": 301140 + }, + { + "epoch": 0.67, + "learning_rate": 1.6441131070893272e-05, + "loss": 0.1103, + "step": 301150 + }, + { + "epoch": 0.67, + "learning_rate": 1.6440012527683946e-05, + "loss": 0.1073, + "step": 301160 + }, + { + "epoch": 0.67, + "learning_rate": 1.643889398447462e-05, + "loss": 0.1136, + "step": 301170 + }, + { + "epoch": 0.67, + "learning_rate": 1.6437775441265296e-05, + "loss": 0.1156, + "step": 301180 + }, + { + "epoch": 0.67, + "learning_rate": 1.643665689805597e-05, + "loss": 0.1111, + "step": 301190 + }, + { + "epoch": 0.67, + "learning_rate": 1.6435538354846648e-05, + "loss": 0.1075, + "step": 301200 + }, + { + "epoch": 0.67, + "learning_rate": 1.6434419811637326e-05, + "loss": 0.1114, + "step": 301210 + }, + { + "epoch": 0.67, + "learning_rate": 1.6433301268428e-05, + "loss": 0.1129, + "step": 301220 + }, + { + "epoch": 0.67, + "learning_rate": 1.6432182725218675e-05, + "loss": 0.1111, + "step": 301230 + }, + { + "epoch": 0.67, + "learning_rate": 1.643106418200935e-05, + "loss": 0.1163, + "step": 301240 + }, + { + "epoch": 0.67, + "learning_rate": 1.6429945638800027e-05, + "loss": 0.1142, + "step": 301250 + }, + { + "epoch": 0.67, + "learning_rate": 1.6428827095590705e-05, + "loss": 0.1145, + "step": 301260 + }, + { + "epoch": 0.67, + "learning_rate": 1.642770855238138e-05, + "loss": 0.1121, + "step": 301270 + }, + { + "epoch": 0.67, + "learning_rate": 1.6426590009172054e-05, + "loss": 0.1087, + "step": 301280 + }, + { + "epoch": 0.67, + "learning_rate": 1.642547146596273e-05, + "loss": 0.1073, + "step": 301290 + }, + { + "epoch": 0.67, + "learning_rate": 1.6424352922753407e-05, + "loss": 0.1103, + "step": 301300 + }, + { + "epoch": 0.67, + "learning_rate": 1.6423234379544085e-05, + "loss": 0.1156, + "step": 301310 + }, + { + "epoch": 0.67, + "learning_rate": 1.642211583633476e-05, + "loss": 0.1121, + "step": 301320 + }, + { + "epoch": 0.67, + "learning_rate": 1.6420997293125434e-05, + "loss": 0.1149, + "step": 301330 + }, + { + "epoch": 0.67, + "learning_rate": 1.641987874991611e-05, + "loss": 0.1192, + "step": 301340 + }, + { + "epoch": 0.67, + "learning_rate": 1.6418760206706783e-05, + "loss": 0.1091, + "step": 301350 + }, + { + "epoch": 0.67, + "learning_rate": 1.6417641663497464e-05, + "loss": 0.1117, + "step": 301360 + }, + { + "epoch": 0.67, + "learning_rate": 1.641652312028814e-05, + "loss": 0.1155, + "step": 301370 + }, + { + "epoch": 0.67, + "learning_rate": 1.6415404577078813e-05, + "loss": 0.1129, + "step": 301380 + }, + { + "epoch": 0.67, + "learning_rate": 1.6414286033869488e-05, + "loss": 0.1044, + "step": 301390 + }, + { + "epoch": 0.67, + "learning_rate": 1.6413167490660163e-05, + "loss": 0.1135, + "step": 301400 + }, + { + "epoch": 0.67, + "learning_rate": 1.641204894745084e-05, + "loss": 0.109, + "step": 301410 + }, + { + "epoch": 0.67, + "learning_rate": 1.641093040424152e-05, + "loss": 0.1097, + "step": 301420 + }, + { + "epoch": 0.67, + "learning_rate": 1.6409811861032193e-05, + "loss": 0.113, + "step": 301430 + }, + { + "epoch": 0.67, + "learning_rate": 1.6408693317822867e-05, + "loss": 0.1134, + "step": 301440 + }, + { + "epoch": 0.67, + "learning_rate": 1.6407574774613542e-05, + "loss": 0.1135, + "step": 301450 + }, + { + "epoch": 0.67, + "learning_rate": 1.640645623140422e-05, + "loss": 0.1132, + "step": 301460 + }, + { + "epoch": 0.67, + "learning_rate": 1.6405337688194898e-05, + "loss": 0.1103, + "step": 301470 + }, + { + "epoch": 0.67, + "learning_rate": 1.6404219144985572e-05, + "loss": 0.111, + "step": 301480 + }, + { + "epoch": 0.67, + "learning_rate": 1.6403100601776247e-05, + "loss": 0.1117, + "step": 301490 + }, + { + "epoch": 0.67, + "learning_rate": 1.640198205856692e-05, + "loss": 0.1096, + "step": 301500 + }, + { + "epoch": 0.67, + "learning_rate": 1.64008635153576e-05, + "loss": 0.1113, + "step": 301510 + }, + { + "epoch": 0.67, + "learning_rate": 1.6399744972148277e-05, + "loss": 0.1114, + "step": 301520 + }, + { + "epoch": 0.67, + "learning_rate": 1.6398626428938952e-05, + "loss": 0.1178, + "step": 301530 + }, + { + "epoch": 0.67, + "learning_rate": 1.6397507885729626e-05, + "loss": 0.1131, + "step": 301540 + }, + { + "epoch": 0.67, + "learning_rate": 1.63963893425203e-05, + "loss": 0.1117, + "step": 301550 + }, + { + "epoch": 0.67, + "learning_rate": 1.639527079931098e-05, + "loss": 0.1108, + "step": 301560 + }, + { + "epoch": 0.67, + "learning_rate": 1.6394152256101657e-05, + "loss": 0.1148, + "step": 301570 + }, + { + "epoch": 0.67, + "learning_rate": 1.639303371289233e-05, + "loss": 0.1127, + "step": 301580 + }, + { + "epoch": 0.67, + "learning_rate": 1.6391915169683006e-05, + "loss": 0.112, + "step": 301590 + }, + { + "epoch": 0.67, + "learning_rate": 1.639079662647368e-05, + "loss": 0.111, + "step": 301600 + }, + { + "epoch": 0.67, + "learning_rate": 1.6389678083264355e-05, + "loss": 0.1093, + "step": 301610 + }, + { + "epoch": 0.67, + "learning_rate": 1.6388559540055033e-05, + "loss": 0.117, + "step": 301620 + }, + { + "epoch": 0.67, + "learning_rate": 1.638744099684571e-05, + "loss": 0.1126, + "step": 301630 + }, + { + "epoch": 0.67, + "learning_rate": 1.6386322453636385e-05, + "loss": 0.1143, + "step": 301640 + }, + { + "epoch": 0.67, + "learning_rate": 1.638520391042706e-05, + "loss": 0.1135, + "step": 301650 + }, + { + "epoch": 0.67, + "learning_rate": 1.6384085367217734e-05, + "loss": 0.1099, + "step": 301660 + }, + { + "epoch": 0.67, + "learning_rate": 1.6382966824008412e-05, + "loss": 0.1124, + "step": 301670 + }, + { + "epoch": 0.67, + "learning_rate": 1.638184828079909e-05, + "loss": 0.1106, + "step": 301680 + }, + { + "epoch": 0.67, + "learning_rate": 1.6380729737589765e-05, + "loss": 0.1174, + "step": 301690 + }, + { + "epoch": 0.67, + "learning_rate": 1.637961119438044e-05, + "loss": 0.1126, + "step": 301700 + }, + { + "epoch": 0.67, + "learning_rate": 1.6378492651171114e-05, + "loss": 0.1101, + "step": 301710 + }, + { + "epoch": 0.67, + "learning_rate": 1.6377374107961792e-05, + "loss": 0.1106, + "step": 301720 + }, + { + "epoch": 0.67, + "learning_rate": 1.637625556475247e-05, + "loss": 0.1074, + "step": 301730 + }, + { + "epoch": 0.67, + "learning_rate": 1.6375137021543144e-05, + "loss": 0.1093, + "step": 301740 + }, + { + "epoch": 0.67, + "learning_rate": 1.637401847833382e-05, + "loss": 0.1151, + "step": 301750 + }, + { + "epoch": 0.67, + "learning_rate": 1.6372899935124493e-05, + "loss": 0.1069, + "step": 301760 + }, + { + "epoch": 0.67, + "learning_rate": 1.637178139191517e-05, + "loss": 0.1145, + "step": 301770 + }, + { + "epoch": 0.67, + "learning_rate": 1.6370662848705846e-05, + "loss": 0.1126, + "step": 301780 + }, + { + "epoch": 0.67, + "learning_rate": 1.6369544305496524e-05, + "loss": 0.1107, + "step": 301790 + }, + { + "epoch": 0.67, + "learning_rate": 1.6368425762287198e-05, + "loss": 0.1067, + "step": 301800 + }, + { + "epoch": 0.67, + "learning_rate": 1.6367307219077873e-05, + "loss": 0.1133, + "step": 301810 + }, + { + "epoch": 0.67, + "learning_rate": 1.6366188675868547e-05, + "loss": 0.1157, + "step": 301820 + }, + { + "epoch": 0.67, + "learning_rate": 1.6365070132659225e-05, + "loss": 0.1105, + "step": 301830 + }, + { + "epoch": 0.67, + "learning_rate": 1.6363951589449903e-05, + "loss": 0.1183, + "step": 301840 + }, + { + "epoch": 0.67, + "learning_rate": 1.6362833046240578e-05, + "loss": 0.1142, + "step": 301850 + }, + { + "epoch": 0.67, + "learning_rate": 1.6361714503031252e-05, + "loss": 0.1087, + "step": 301860 + }, + { + "epoch": 0.67, + "learning_rate": 1.6360595959821927e-05, + "loss": 0.1164, + "step": 301870 + }, + { + "epoch": 0.67, + "learning_rate": 1.6359477416612605e-05, + "loss": 0.1142, + "step": 301880 + }, + { + "epoch": 0.67, + "learning_rate": 1.6358358873403283e-05, + "loss": 0.1139, + "step": 301890 + }, + { + "epoch": 0.67, + "learning_rate": 1.6357240330193957e-05, + "loss": 0.1117, + "step": 301900 + }, + { + "epoch": 0.67, + "learning_rate": 1.6356121786984632e-05, + "loss": 0.1132, + "step": 301910 + }, + { + "epoch": 0.67, + "learning_rate": 1.6355003243775306e-05, + "loss": 0.1171, + "step": 301920 + }, + { + "epoch": 0.67, + "learning_rate": 1.6353884700565984e-05, + "loss": 0.1169, + "step": 301930 + }, + { + "epoch": 0.67, + "learning_rate": 1.635276615735666e-05, + "loss": 0.1124, + "step": 301940 + }, + { + "epoch": 0.67, + "learning_rate": 1.6351647614147337e-05, + "loss": 0.118, + "step": 301950 + }, + { + "epoch": 0.67, + "learning_rate": 1.635052907093801e-05, + "loss": 0.1144, + "step": 301960 + }, + { + "epoch": 0.67, + "learning_rate": 1.6349410527728686e-05, + "loss": 0.111, + "step": 301970 + }, + { + "epoch": 0.67, + "learning_rate": 1.6348291984519364e-05, + "loss": 0.1118, + "step": 301980 + }, + { + "epoch": 0.67, + "learning_rate": 1.6347173441310038e-05, + "loss": 0.1144, + "step": 301990 + }, + { + "epoch": 0.67, + "learning_rate": 1.6346054898100716e-05, + "loss": 0.1151, + "step": 302000 + }, + { + "epoch": 0.67, + "learning_rate": 1.634493635489139e-05, + "loss": 0.1121, + "step": 302010 + }, + { + "epoch": 0.67, + "learning_rate": 1.6343817811682065e-05, + "loss": 0.1091, + "step": 302020 + }, + { + "epoch": 0.67, + "learning_rate": 1.634269926847274e-05, + "loss": 0.1093, + "step": 302030 + }, + { + "epoch": 0.67, + "learning_rate": 1.6341580725263418e-05, + "loss": 0.1143, + "step": 302040 + }, + { + "epoch": 0.67, + "learning_rate": 1.6340462182054096e-05, + "loss": 0.1105, + "step": 302050 + }, + { + "epoch": 0.67, + "learning_rate": 1.633934363884477e-05, + "loss": 0.113, + "step": 302060 + }, + { + "epoch": 0.67, + "learning_rate": 1.6338225095635445e-05, + "loss": 0.1115, + "step": 302070 + }, + { + "epoch": 0.67, + "learning_rate": 1.633710655242612e-05, + "loss": 0.1086, + "step": 302080 + }, + { + "epoch": 0.67, + "learning_rate": 1.6335988009216797e-05, + "loss": 0.1098, + "step": 302090 + }, + { + "epoch": 0.67, + "learning_rate": 1.6334869466007472e-05, + "loss": 0.1124, + "step": 302100 + }, + { + "epoch": 0.67, + "learning_rate": 1.633375092279815e-05, + "loss": 0.1114, + "step": 302110 + }, + { + "epoch": 0.67, + "learning_rate": 1.6332632379588824e-05, + "loss": 0.1093, + "step": 302120 + }, + { + "epoch": 0.67, + "learning_rate": 1.63315138363795e-05, + "loss": 0.1131, + "step": 302130 + }, + { + "epoch": 0.67, + "learning_rate": 1.6330395293170177e-05, + "loss": 0.1132, + "step": 302140 + }, + { + "epoch": 0.67, + "learning_rate": 1.632927674996085e-05, + "loss": 0.1109, + "step": 302150 + }, + { + "epoch": 0.67, + "learning_rate": 1.632815820675153e-05, + "loss": 0.1109, + "step": 302160 + }, + { + "epoch": 0.67, + "learning_rate": 1.6327039663542204e-05, + "loss": 0.114, + "step": 302170 + }, + { + "epoch": 0.67, + "learning_rate": 1.6325921120332878e-05, + "loss": 0.1074, + "step": 302180 + }, + { + "epoch": 0.67, + "learning_rate": 1.6324802577123556e-05, + "loss": 0.1141, + "step": 302190 + }, + { + "epoch": 0.67, + "learning_rate": 1.632368403391423e-05, + "loss": 0.1091, + "step": 302200 + }, + { + "epoch": 0.67, + "learning_rate": 1.632256549070491e-05, + "loss": 0.1124, + "step": 302210 + }, + { + "epoch": 0.67, + "learning_rate": 1.6321446947495583e-05, + "loss": 0.113, + "step": 302220 + }, + { + "epoch": 0.67, + "learning_rate": 1.6320328404286258e-05, + "loss": 0.1126, + "step": 302230 + }, + { + "epoch": 0.67, + "learning_rate": 1.6319209861076936e-05, + "loss": 0.1094, + "step": 302240 + }, + { + "epoch": 0.67, + "learning_rate": 1.631809131786761e-05, + "loss": 0.1131, + "step": 302250 + }, + { + "epoch": 0.67, + "learning_rate": 1.6316972774658285e-05, + "loss": 0.1087, + "step": 302260 + }, + { + "epoch": 0.67, + "learning_rate": 1.6315854231448963e-05, + "loss": 0.1136, + "step": 302270 + }, + { + "epoch": 0.67, + "learning_rate": 1.6314735688239637e-05, + "loss": 0.111, + "step": 302280 + }, + { + "epoch": 0.67, + "learning_rate": 1.6313617145030312e-05, + "loss": 0.1106, + "step": 302290 + }, + { + "epoch": 0.67, + "learning_rate": 1.631249860182099e-05, + "loss": 0.1193, + "step": 302300 + }, + { + "epoch": 0.67, + "learning_rate": 1.6311380058611664e-05, + "loss": 0.1155, + "step": 302310 + }, + { + "epoch": 0.67, + "learning_rate": 1.6310261515402342e-05, + "loss": 0.1144, + "step": 302320 + }, + { + "epoch": 0.67, + "learning_rate": 1.6309142972193017e-05, + "loss": 0.1116, + "step": 302330 + }, + { + "epoch": 0.67, + "learning_rate": 1.630802442898369e-05, + "loss": 0.1148, + "step": 302340 + }, + { + "epoch": 0.67, + "learning_rate": 1.630690588577437e-05, + "loss": 0.1147, + "step": 302350 + }, + { + "epoch": 0.67, + "learning_rate": 1.6305787342565044e-05, + "loss": 0.1119, + "step": 302360 + }, + { + "epoch": 0.67, + "learning_rate": 1.630466879935572e-05, + "loss": 0.1148, + "step": 302370 + }, + { + "epoch": 0.67, + "learning_rate": 1.6303550256146396e-05, + "loss": 0.1129, + "step": 302380 + }, + { + "epoch": 0.67, + "learning_rate": 1.630243171293707e-05, + "loss": 0.1139, + "step": 302390 + }, + { + "epoch": 0.67, + "learning_rate": 1.630131316972775e-05, + "loss": 0.1114, + "step": 302400 + }, + { + "epoch": 0.68, + "learning_rate": 1.6300194626518423e-05, + "loss": 0.1094, + "step": 302410 + }, + { + "epoch": 0.68, + "learning_rate": 1.6299076083309098e-05, + "loss": 0.1067, + "step": 302420 + }, + { + "epoch": 0.68, + "learning_rate": 1.6297957540099776e-05, + "loss": 0.1107, + "step": 302430 + }, + { + "epoch": 0.68, + "learning_rate": 1.629683899689045e-05, + "loss": 0.1131, + "step": 302440 + }, + { + "epoch": 0.68, + "learning_rate": 1.6295720453681128e-05, + "loss": 0.1141, + "step": 302450 + }, + { + "epoch": 0.68, + "learning_rate": 1.6294601910471803e-05, + "loss": 0.1096, + "step": 302460 + }, + { + "epoch": 0.68, + "learning_rate": 1.6293483367262477e-05, + "loss": 0.1149, + "step": 302470 + }, + { + "epoch": 0.68, + "learning_rate": 1.6292364824053155e-05, + "loss": 0.1089, + "step": 302480 + }, + { + "epoch": 0.68, + "learning_rate": 1.629124628084383e-05, + "loss": 0.1162, + "step": 302490 + }, + { + "epoch": 0.68, + "learning_rate": 1.6290127737634504e-05, + "loss": 0.1127, + "step": 302500 + }, + { + "epoch": 0.68, + "learning_rate": 1.6289009194425182e-05, + "loss": 0.114, + "step": 302510 + }, + { + "epoch": 0.68, + "learning_rate": 1.6287890651215857e-05, + "loss": 0.1128, + "step": 302520 + }, + { + "epoch": 0.68, + "learning_rate": 1.6286772108006535e-05, + "loss": 0.1104, + "step": 302530 + }, + { + "epoch": 0.68, + "learning_rate": 1.628565356479721e-05, + "loss": 0.1151, + "step": 302540 + }, + { + "epoch": 0.68, + "learning_rate": 1.6284535021587884e-05, + "loss": 0.1137, + "step": 302550 + }, + { + "epoch": 0.68, + "learning_rate": 1.628341647837856e-05, + "loss": 0.1131, + "step": 302560 + }, + { + "epoch": 0.68, + "learning_rate": 1.6282297935169236e-05, + "loss": 0.1103, + "step": 302570 + }, + { + "epoch": 0.68, + "learning_rate": 1.628117939195991e-05, + "loss": 0.1102, + "step": 302580 + }, + { + "epoch": 0.68, + "learning_rate": 1.628006084875059e-05, + "loss": 0.1117, + "step": 302590 + }, + { + "epoch": 0.68, + "learning_rate": 1.6278942305541263e-05, + "loss": 0.1158, + "step": 302600 + }, + { + "epoch": 0.68, + "learning_rate": 1.627782376233194e-05, + "loss": 0.1172, + "step": 302610 + }, + { + "epoch": 0.68, + "learning_rate": 1.6276705219122616e-05, + "loss": 0.1103, + "step": 302620 + }, + { + "epoch": 0.68, + "learning_rate": 1.627558667591329e-05, + "loss": 0.1121, + "step": 302630 + }, + { + "epoch": 0.68, + "learning_rate": 1.6274468132703968e-05, + "loss": 0.115, + "step": 302640 + }, + { + "epoch": 0.68, + "learning_rate": 1.6273349589494643e-05, + "loss": 0.1138, + "step": 302650 + }, + { + "epoch": 0.68, + "learning_rate": 1.627223104628532e-05, + "loss": 0.1123, + "step": 302660 + }, + { + "epoch": 0.68, + "learning_rate": 1.6271112503075995e-05, + "loss": 0.1081, + "step": 302670 + }, + { + "epoch": 0.68, + "learning_rate": 1.626999395986667e-05, + "loss": 0.1135, + "step": 302680 + }, + { + "epoch": 0.68, + "learning_rate": 1.6268875416657348e-05, + "loss": 0.1139, + "step": 302690 + }, + { + "epoch": 0.68, + "learning_rate": 1.6267756873448022e-05, + "loss": 0.1151, + "step": 302700 + }, + { + "epoch": 0.68, + "learning_rate": 1.6266638330238697e-05, + "loss": 0.106, + "step": 302710 + }, + { + "epoch": 0.68, + "learning_rate": 1.6265519787029375e-05, + "loss": 0.1119, + "step": 302720 + }, + { + "epoch": 0.68, + "learning_rate": 1.626440124382005e-05, + "loss": 0.1109, + "step": 302730 + }, + { + "epoch": 0.68, + "learning_rate": 1.6263282700610724e-05, + "loss": 0.1151, + "step": 302740 + }, + { + "epoch": 0.68, + "learning_rate": 1.62621641574014e-05, + "loss": 0.1097, + "step": 302750 + }, + { + "epoch": 0.68, + "learning_rate": 1.6261045614192076e-05, + "loss": 0.1139, + "step": 302760 + }, + { + "epoch": 0.68, + "learning_rate": 1.6259927070982754e-05, + "loss": 0.1067, + "step": 302770 + }, + { + "epoch": 0.68, + "learning_rate": 1.625880852777343e-05, + "loss": 0.1135, + "step": 302780 + }, + { + "epoch": 0.68, + "learning_rate": 1.6257801838885037e-05, + "loss": 0.1141, + "step": 302790 + }, + { + "epoch": 0.68, + "learning_rate": 1.6256683295675712e-05, + "loss": 0.1127, + "step": 302800 + }, + { + "epoch": 0.68, + "learning_rate": 1.6255564752466386e-05, + "loss": 0.1114, + "step": 302810 + }, + { + "epoch": 0.68, + "learning_rate": 1.6254446209257064e-05, + "loss": 0.1143, + "step": 302820 + }, + { + "epoch": 0.68, + "learning_rate": 1.6253327666047742e-05, + "loss": 0.1134, + "step": 302830 + }, + { + "epoch": 0.68, + "learning_rate": 1.6252209122838417e-05, + "loss": 0.1126, + "step": 302840 + }, + { + "epoch": 0.68, + "learning_rate": 1.625109057962909e-05, + "loss": 0.1116, + "step": 302850 + }, + { + "epoch": 0.68, + "learning_rate": 1.6249972036419766e-05, + "loss": 0.111, + "step": 302860 + }, + { + "epoch": 0.68, + "learning_rate": 1.6248853493210444e-05, + "loss": 0.1085, + "step": 302870 + }, + { + "epoch": 0.68, + "learning_rate": 1.624773495000112e-05, + "loss": 0.1128, + "step": 302880 + }, + { + "epoch": 0.68, + "learning_rate": 1.6246616406791796e-05, + "loss": 0.1109, + "step": 302890 + }, + { + "epoch": 0.68, + "learning_rate": 1.624549786358247e-05, + "loss": 0.1082, + "step": 302900 + }, + { + "epoch": 0.68, + "learning_rate": 1.6244379320373145e-05, + "loss": 0.1122, + "step": 302910 + }, + { + "epoch": 0.68, + "learning_rate": 1.6243260777163823e-05, + "loss": 0.1134, + "step": 302920 + }, + { + "epoch": 0.68, + "learning_rate": 1.6242142233954498e-05, + "loss": 0.1082, + "step": 302930 + }, + { + "epoch": 0.68, + "learning_rate": 1.6241023690745176e-05, + "loss": 0.1118, + "step": 302940 + }, + { + "epoch": 0.68, + "learning_rate": 1.623990514753585e-05, + "loss": 0.1089, + "step": 302950 + }, + { + "epoch": 0.68, + "learning_rate": 1.6238786604326525e-05, + "loss": 0.1137, + "step": 302960 + }, + { + "epoch": 0.68, + "learning_rate": 1.62376680611172e-05, + "loss": 0.1092, + "step": 302970 + }, + { + "epoch": 0.68, + "learning_rate": 1.6236549517907877e-05, + "loss": 0.1183, + "step": 302980 + }, + { + "epoch": 0.68, + "learning_rate": 1.6235430974698555e-05, + "loss": 0.1164, + "step": 302990 + }, + { + "epoch": 0.68, + "learning_rate": 1.623431243148923e-05, + "loss": 0.1099, + "step": 303000 + }, + { + "epoch": 0.68, + "learning_rate": 1.6233193888279904e-05, + "loss": 0.1134, + "step": 303010 + }, + { + "epoch": 0.68, + "learning_rate": 1.623207534507058e-05, + "loss": 0.1106, + "step": 303020 + }, + { + "epoch": 0.68, + "learning_rate": 1.6230956801861257e-05, + "loss": 0.1142, + "step": 303030 + }, + { + "epoch": 0.68, + "learning_rate": 1.6229838258651935e-05, + "loss": 0.1102, + "step": 303040 + }, + { + "epoch": 0.68, + "learning_rate": 1.622871971544261e-05, + "loss": 0.1068, + "step": 303050 + }, + { + "epoch": 0.68, + "learning_rate": 1.6227601172233284e-05, + "loss": 0.1103, + "step": 303060 + }, + { + "epoch": 0.68, + "learning_rate": 1.6226482629023958e-05, + "loss": 0.1174, + "step": 303070 + }, + { + "epoch": 0.68, + "learning_rate": 1.6225364085814636e-05, + "loss": 0.1129, + "step": 303080 + }, + { + "epoch": 0.68, + "learning_rate": 1.6224245542605314e-05, + "loss": 0.1084, + "step": 303090 + }, + { + "epoch": 0.68, + "learning_rate": 1.622312699939599e-05, + "loss": 0.1066, + "step": 303100 + }, + { + "epoch": 0.68, + "learning_rate": 1.6222008456186663e-05, + "loss": 0.1098, + "step": 303110 + }, + { + "epoch": 0.68, + "learning_rate": 1.6220889912977338e-05, + "loss": 0.106, + "step": 303120 + }, + { + "epoch": 0.68, + "learning_rate": 1.6219771369768012e-05, + "loss": 0.1096, + "step": 303130 + }, + { + "epoch": 0.68, + "learning_rate": 1.621865282655869e-05, + "loss": 0.1123, + "step": 303140 + }, + { + "epoch": 0.68, + "learning_rate": 1.6217534283349368e-05, + "loss": 0.1101, + "step": 303150 + }, + { + "epoch": 0.68, + "learning_rate": 1.6216415740140043e-05, + "loss": 0.1104, + "step": 303160 + }, + { + "epoch": 0.68, + "learning_rate": 1.6215297196930717e-05, + "loss": 0.1075, + "step": 303170 + }, + { + "epoch": 0.68, + "learning_rate": 1.6214178653721392e-05, + "loss": 0.11, + "step": 303180 + }, + { + "epoch": 0.68, + "learning_rate": 1.621306011051207e-05, + "loss": 0.1137, + "step": 303190 + }, + { + "epoch": 0.68, + "learning_rate": 1.6211941567302748e-05, + "loss": 0.1113, + "step": 303200 + }, + { + "epoch": 0.68, + "learning_rate": 1.6210823024093422e-05, + "loss": 0.1136, + "step": 303210 + }, + { + "epoch": 0.68, + "learning_rate": 1.6209704480884097e-05, + "loss": 0.1104, + "step": 303220 + }, + { + "epoch": 0.68, + "learning_rate": 1.620858593767477e-05, + "loss": 0.1106, + "step": 303230 + }, + { + "epoch": 0.68, + "learning_rate": 1.620746739446545e-05, + "loss": 0.1097, + "step": 303240 + }, + { + "epoch": 0.68, + "learning_rate": 1.6206348851256127e-05, + "loss": 0.1095, + "step": 303250 + }, + { + "epoch": 0.68, + "learning_rate": 1.62052303080468e-05, + "loss": 0.1105, + "step": 303260 + }, + { + "epoch": 0.68, + "learning_rate": 1.6204111764837476e-05, + "loss": 0.107, + "step": 303270 + }, + { + "epoch": 0.68, + "learning_rate": 1.620299322162815e-05, + "loss": 0.1159, + "step": 303280 + }, + { + "epoch": 0.68, + "learning_rate": 1.6201874678418825e-05, + "loss": 0.1095, + "step": 303290 + }, + { + "epoch": 0.68, + "learning_rate": 1.6200756135209507e-05, + "loss": 0.1159, + "step": 303300 + }, + { + "epoch": 0.68, + "learning_rate": 1.619963759200018e-05, + "loss": 0.115, + "step": 303310 + }, + { + "epoch": 0.68, + "learning_rate": 1.6198519048790856e-05, + "loss": 0.1096, + "step": 303320 + }, + { + "epoch": 0.68, + "learning_rate": 1.619740050558153e-05, + "loss": 0.1127, + "step": 303330 + }, + { + "epoch": 0.68, + "learning_rate": 1.6196281962372205e-05, + "loss": 0.1133, + "step": 303340 + }, + { + "epoch": 0.68, + "learning_rate": 1.6195163419162883e-05, + "loss": 0.1118, + "step": 303350 + }, + { + "epoch": 0.68, + "learning_rate": 1.619404487595356e-05, + "loss": 0.115, + "step": 303360 + }, + { + "epoch": 0.68, + "learning_rate": 1.6192926332744235e-05, + "loss": 0.1111, + "step": 303370 + }, + { + "epoch": 0.68, + "learning_rate": 1.619180778953491e-05, + "loss": 0.1182, + "step": 303380 + }, + { + "epoch": 0.68, + "learning_rate": 1.6190689246325584e-05, + "loss": 0.1085, + "step": 303390 + }, + { + "epoch": 0.68, + "learning_rate": 1.6189570703116262e-05, + "loss": 0.1103, + "step": 303400 + }, + { + "epoch": 0.68, + "learning_rate": 1.618845215990694e-05, + "loss": 0.1104, + "step": 303410 + }, + { + "epoch": 0.68, + "learning_rate": 1.6187333616697615e-05, + "loss": 0.1124, + "step": 303420 + }, + { + "epoch": 0.68, + "learning_rate": 1.618621507348829e-05, + "loss": 0.1116, + "step": 303430 + }, + { + "epoch": 0.68, + "learning_rate": 1.6185096530278964e-05, + "loss": 0.1093, + "step": 303440 + }, + { + "epoch": 0.68, + "learning_rate": 1.618397798706964e-05, + "loss": 0.114, + "step": 303450 + }, + { + "epoch": 0.68, + "learning_rate": 1.618285944386032e-05, + "loss": 0.1125, + "step": 303460 + }, + { + "epoch": 0.68, + "learning_rate": 1.6181740900650994e-05, + "loss": 0.1125, + "step": 303470 + }, + { + "epoch": 0.68, + "learning_rate": 1.618062235744167e-05, + "loss": 0.1102, + "step": 303480 + }, + { + "epoch": 0.68, + "learning_rate": 1.6179503814232343e-05, + "loss": 0.111, + "step": 303490 + }, + { + "epoch": 0.68, + "learning_rate": 1.6178385271023018e-05, + "loss": 0.11, + "step": 303500 + }, + { + "epoch": 0.68, + "learning_rate": 1.61772667278137e-05, + "loss": 0.1152, + "step": 303510 + }, + { + "epoch": 0.68, + "learning_rate": 1.6176148184604374e-05, + "loss": 0.109, + "step": 303520 + }, + { + "epoch": 0.68, + "learning_rate": 1.6175029641395048e-05, + "loss": 0.1084, + "step": 303530 + }, + { + "epoch": 0.68, + "learning_rate": 1.6173911098185723e-05, + "loss": 0.1119, + "step": 303540 + }, + { + "epoch": 0.68, + "learning_rate": 1.6172792554976397e-05, + "loss": 0.1146, + "step": 303550 + }, + { + "epoch": 0.68, + "learning_rate": 1.6171674011767075e-05, + "loss": 0.1124, + "step": 303560 + }, + { + "epoch": 0.68, + "learning_rate": 1.6170555468557753e-05, + "loss": 0.1115, + "step": 303570 + }, + { + "epoch": 0.68, + "learning_rate": 1.6169436925348428e-05, + "loss": 0.1117, + "step": 303580 + }, + { + "epoch": 0.68, + "learning_rate": 1.6168318382139102e-05, + "loss": 0.1133, + "step": 303590 + }, + { + "epoch": 0.68, + "learning_rate": 1.6167199838929777e-05, + "loss": 0.1124, + "step": 303600 + }, + { + "epoch": 0.68, + "learning_rate": 1.6166081295720455e-05, + "loss": 0.1117, + "step": 303610 + }, + { + "epoch": 0.68, + "learning_rate": 1.6164962752511133e-05, + "loss": 0.1072, + "step": 303620 + }, + { + "epoch": 0.68, + "learning_rate": 1.6163844209301807e-05, + "loss": 0.1104, + "step": 303630 + }, + { + "epoch": 0.68, + "learning_rate": 1.616272566609248e-05, + "loss": 0.1127, + "step": 303640 + }, + { + "epoch": 0.68, + "learning_rate": 1.6161607122883156e-05, + "loss": 0.1099, + "step": 303650 + }, + { + "epoch": 0.68, + "learning_rate": 1.6160488579673834e-05, + "loss": 0.1098, + "step": 303660 + }, + { + "epoch": 0.68, + "learning_rate": 1.6159370036464512e-05, + "loss": 0.1149, + "step": 303670 + }, + { + "epoch": 0.68, + "learning_rate": 1.6158251493255187e-05, + "loss": 0.1096, + "step": 303680 + }, + { + "epoch": 0.68, + "learning_rate": 1.615713295004586e-05, + "loss": 0.1068, + "step": 303690 + }, + { + "epoch": 0.68, + "learning_rate": 1.6156014406836536e-05, + "loss": 0.1083, + "step": 303700 + }, + { + "epoch": 0.68, + "learning_rate": 1.6154895863627214e-05, + "loss": 0.1104, + "step": 303710 + }, + { + "epoch": 0.68, + "learning_rate": 1.6153777320417888e-05, + "loss": 0.1072, + "step": 303720 + }, + { + "epoch": 0.68, + "learning_rate": 1.6152658777208566e-05, + "loss": 0.1147, + "step": 303730 + }, + { + "epoch": 0.68, + "learning_rate": 1.615154023399924e-05, + "loss": 0.1107, + "step": 303740 + }, + { + "epoch": 0.68, + "learning_rate": 1.6150421690789915e-05, + "loss": 0.1162, + "step": 303750 + }, + { + "epoch": 0.68, + "learning_rate": 1.614930314758059e-05, + "loss": 0.117, + "step": 303760 + }, + { + "epoch": 0.68, + "learning_rate": 1.6148184604371268e-05, + "loss": 0.1098, + "step": 303770 + }, + { + "epoch": 0.68, + "learning_rate": 1.6147066061161945e-05, + "loss": 0.1098, + "step": 303780 + }, + { + "epoch": 0.68, + "learning_rate": 1.614594751795262e-05, + "loss": 0.1111, + "step": 303790 + }, + { + "epoch": 0.68, + "learning_rate": 1.6144828974743295e-05, + "loss": 0.1086, + "step": 303800 + }, + { + "epoch": 0.68, + "learning_rate": 1.614371043153397e-05, + "loss": 0.1082, + "step": 303810 + }, + { + "epoch": 0.68, + "learning_rate": 1.6142591888324647e-05, + "loss": 0.1137, + "step": 303820 + }, + { + "epoch": 0.68, + "learning_rate": 1.6141473345115325e-05, + "loss": 0.113, + "step": 303830 + }, + { + "epoch": 0.68, + "learning_rate": 1.6140354801906e-05, + "loss": 0.109, + "step": 303840 + }, + { + "epoch": 0.68, + "learning_rate": 1.6139236258696674e-05, + "loss": 0.1101, + "step": 303850 + }, + { + "epoch": 0.68, + "learning_rate": 1.613811771548735e-05, + "loss": 0.1127, + "step": 303860 + }, + { + "epoch": 0.68, + "learning_rate": 1.6136999172278026e-05, + "loss": 0.1074, + "step": 303870 + }, + { + "epoch": 0.68, + "learning_rate": 1.61358806290687e-05, + "loss": 0.1109, + "step": 303880 + }, + { + "epoch": 0.68, + "learning_rate": 1.613476208585938e-05, + "loss": 0.1135, + "step": 303890 + }, + { + "epoch": 0.68, + "learning_rate": 1.6133643542650054e-05, + "loss": 0.1109, + "step": 303900 + }, + { + "epoch": 0.68, + "learning_rate": 1.6132524999440728e-05, + "loss": 0.112, + "step": 303910 + }, + { + "epoch": 0.68, + "learning_rate": 1.6131406456231406e-05, + "loss": 0.1151, + "step": 303920 + }, + { + "epoch": 0.68, + "learning_rate": 1.613028791302208e-05, + "loss": 0.1125, + "step": 303930 + }, + { + "epoch": 0.68, + "learning_rate": 1.612916936981276e-05, + "loss": 0.1115, + "step": 303940 + }, + { + "epoch": 0.68, + "learning_rate": 1.6128050826603433e-05, + "loss": 0.1092, + "step": 303950 + }, + { + "epoch": 0.68, + "learning_rate": 1.6126932283394108e-05, + "loss": 0.11, + "step": 303960 + }, + { + "epoch": 0.68, + "learning_rate": 1.6125813740184782e-05, + "loss": 0.1118, + "step": 303970 + }, + { + "epoch": 0.68, + "learning_rate": 1.612469519697546e-05, + "loss": 0.1104, + "step": 303980 + }, + { + "epoch": 0.68, + "learning_rate": 1.6123576653766138e-05, + "loss": 0.1117, + "step": 303990 + }, + { + "epoch": 0.68, + "learning_rate": 1.6122458110556812e-05, + "loss": 0.1095, + "step": 304000 + }, + { + "epoch": 0.68, + "eval_NEIMS_canon_smiles": 0.9578833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.20911666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.5934243474176039, + "eval_NEIMS_exact_mols": 0.20885, + "eval_NEIMS_exact_smiles": 0.2044, + "eval_NEIMS_loss": 0.13997317850589752, + "eval_NEIMS_matched_formulas": 0.72885, + "eval_NEIMS_morgan_tanimoto_simil": 0.5155752522800903, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.20956666666666668, + "eval_NEIMS_runtime": 729.5736, + "eval_NEIMS_samples_per_second": 82.24, + "eval_NEIMS_steps_per_second": 1.286, + "step": 304000 + }, + { + "epoch": 0.68, + "eval_RASSP_canon_smiles": 0.9553711557084182, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.2851036831736067, + "eval_RASSP_daylight_tanimoto_simil": 0.6939910192769748, + "eval_RASSP_exact_mols": 0.28435235582863055, + "eval_RASSP_exact_smiles": 0.27800781380438777, + "eval_RASSP_loss": 0.10914087295532227, + "eval_RASSP_matched_formulas": 0.8677997796106455, + "eval_RASSP_morgan_tanimoto_simil": 0.582240506336762, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.28455270978729086, + "eval_RASSP_runtime": 827.1124, + "eval_RASSP_samples_per_second": 72.413, + "eval_RASSP_steps_per_second": 1.132, + "step": 304000 + }, + { + "epoch": 0.68, + "eval_NEIMS_old_canon_smiles": 0.9564333333333334, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2106, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5922646317853278, + "eval_NEIMS_old_exact_mols": 0.2102, + "eval_NEIMS_old_exact_smiles": 0.2055, + "eval_NEIMS_old_loss": 0.1393352895975113, + "eval_NEIMS_old_matched_formulas": 0.7296, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5155245356351781, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.21093333333333333, + "eval_NEIMS_old_runtime": 368.1709, + "eval_NEIMS_old_samples_per_second": 81.484, + "eval_NEIMS_old_steps_per_second": 1.274, + "step": 304000 + }, + { + "epoch": 0.68, + "eval_RASSP_old_canon_smiles": 0.9563853572262823, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.31237694797610704, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7120111103485639, + "eval_RASSP_old_exact_mols": 0.31164280708779657, + "eval_RASSP_old_exact_smiles": 0.3039676978009143, + "eval_RASSP_old_loss": 0.10274332761764526, + "eval_RASSP_old_matched_formulas": 0.8795007841959489, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6038183156288335, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.3118763973704408, + "eval_RASSP_old_runtime": 414.3661, + "eval_RASSP_old_samples_per_second": 72.32, + "eval_RASSP_old_steps_per_second": 1.132, + "step": 304000 + }, + { + "epoch": 0.68, + "eval_NIST_canon_smiles": 0.8680838982148561, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.029030769776768287, + "eval_NIST_daylight_tanimoto_simil": 0.3007446466853605, + "eval_NIST_exact_mols": 0.027930581680093693, + "eval_NIST_exact_smiles": 0.026120594811370978, + "eval_NIST_loss": 1.802420735359192, + "eval_NIST_matched_formulas": 0.12453419455584341, + "eval_NIST_morgan_tanimoto_simil": 0.2525662835202647, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02888881002235866, + "eval_NIST_runtime": 521.5876, + "eval_NIST_samples_per_second": 54.022, + "eval_NIST_steps_per_second": 0.845, + "step": 304000 + }, + { + "epoch": 0.68, + "learning_rate": 1.6121339567347487e-05, + "loss": 0.1121, + "step": 304010 + }, + { + "epoch": 0.68, + "learning_rate": 1.612022102413816e-05, + "loss": 0.1117, + "step": 304020 + }, + { + "epoch": 0.68, + "learning_rate": 1.611910248092884e-05, + "loss": 0.1069, + "step": 304030 + }, + { + "epoch": 0.68, + "learning_rate": 1.6117983937719514e-05, + "loss": 0.1157, + "step": 304040 + }, + { + "epoch": 0.68, + "learning_rate": 1.6116865394510192e-05, + "loss": 0.1077, + "step": 304050 + }, + { + "epoch": 0.68, + "learning_rate": 1.6115746851300866e-05, + "loss": 0.1104, + "step": 304060 + }, + { + "epoch": 0.68, + "learning_rate": 1.611462830809154e-05, + "loss": 0.1087, + "step": 304070 + }, + { + "epoch": 0.68, + "learning_rate": 1.611350976488222e-05, + "loss": 0.1129, + "step": 304080 + }, + { + "epoch": 0.68, + "learning_rate": 1.6112391221672893e-05, + "loss": 0.1145, + "step": 304090 + }, + { + "epoch": 0.68, + "learning_rate": 1.611127267846357e-05, + "loss": 0.116, + "step": 304100 + }, + { + "epoch": 0.68, + "learning_rate": 1.6110154135254246e-05, + "loss": 0.1088, + "step": 304110 + }, + { + "epoch": 0.68, + "learning_rate": 1.610903559204492e-05, + "loss": 0.1165, + "step": 304120 + }, + { + "epoch": 0.68, + "learning_rate": 1.61079170488356e-05, + "loss": 0.1106, + "step": 304130 + }, + { + "epoch": 0.68, + "learning_rate": 1.6106798505626273e-05, + "loss": 0.1091, + "step": 304140 + }, + { + "epoch": 0.68, + "learning_rate": 1.610567996241695e-05, + "loss": 0.1078, + "step": 304150 + }, + { + "epoch": 0.68, + "learning_rate": 1.6104561419207625e-05, + "loss": 0.1097, + "step": 304160 + }, + { + "epoch": 0.68, + "learning_rate": 1.61034428759983e-05, + "loss": 0.1091, + "step": 304170 + }, + { + "epoch": 0.68, + "learning_rate": 1.6102324332788974e-05, + "loss": 0.1097, + "step": 304180 + }, + { + "epoch": 0.68, + "learning_rate": 1.6101205789579652e-05, + "loss": 0.1111, + "step": 304190 + }, + { + "epoch": 0.68, + "learning_rate": 1.6100087246370327e-05, + "loss": 0.1094, + "step": 304200 + }, + { + "epoch": 0.68, + "learning_rate": 1.6098968703161005e-05, + "loss": 0.1144, + "step": 304210 + }, + { + "epoch": 0.68, + "learning_rate": 1.609785015995168e-05, + "loss": 0.1173, + "step": 304220 + }, + { + "epoch": 0.68, + "learning_rate": 1.6096731616742354e-05, + "loss": 0.1093, + "step": 304230 + }, + { + "epoch": 0.68, + "learning_rate": 1.6095613073533032e-05, + "loss": 0.1062, + "step": 304240 + }, + { + "epoch": 0.68, + "learning_rate": 1.6094494530323706e-05, + "loss": 0.1114, + "step": 304250 + }, + { + "epoch": 0.68, + "learning_rate": 1.6093375987114384e-05, + "loss": 0.1109, + "step": 304260 + }, + { + "epoch": 0.68, + "learning_rate": 1.609225744390506e-05, + "loss": 0.1121, + "step": 304270 + }, + { + "epoch": 0.68, + "learning_rate": 1.6091138900695733e-05, + "loss": 0.1137, + "step": 304280 + }, + { + "epoch": 0.68, + "learning_rate": 1.609002035748641e-05, + "loss": 0.1074, + "step": 304290 + }, + { + "epoch": 0.68, + "learning_rate": 1.6088901814277086e-05, + "loss": 0.1153, + "step": 304300 + }, + { + "epoch": 0.68, + "learning_rate": 1.6087783271067764e-05, + "loss": 0.1163, + "step": 304310 + }, + { + "epoch": 0.68, + "learning_rate": 1.608666472785844e-05, + "loss": 0.113, + "step": 304320 + }, + { + "epoch": 0.68, + "learning_rate": 1.6085546184649113e-05, + "loss": 0.1075, + "step": 304330 + }, + { + "epoch": 0.68, + "learning_rate": 1.608442764143979e-05, + "loss": 0.1134, + "step": 304340 + }, + { + "epoch": 0.68, + "learning_rate": 1.6083309098230465e-05, + "loss": 0.114, + "step": 304350 + }, + { + "epoch": 0.68, + "learning_rate": 1.608219055502114e-05, + "loss": 0.1113, + "step": 304360 + }, + { + "epoch": 0.68, + "learning_rate": 1.6081072011811818e-05, + "loss": 0.1146, + "step": 304370 + }, + { + "epoch": 0.68, + "learning_rate": 1.6079953468602492e-05, + "loss": 0.1131, + "step": 304380 + }, + { + "epoch": 0.68, + "learning_rate": 1.6078834925393167e-05, + "loss": 0.1127, + "step": 304390 + }, + { + "epoch": 0.68, + "learning_rate": 1.6077716382183845e-05, + "loss": 0.1093, + "step": 304400 + }, + { + "epoch": 0.68, + "learning_rate": 1.607659783897452e-05, + "loss": 0.1133, + "step": 304410 + }, + { + "epoch": 0.68, + "learning_rate": 1.6075479295765197e-05, + "loss": 0.1086, + "step": 304420 + }, + { + "epoch": 0.68, + "learning_rate": 1.6074360752555872e-05, + "loss": 0.1156, + "step": 304430 + }, + { + "epoch": 0.68, + "learning_rate": 1.6073242209346546e-05, + "loss": 0.1122, + "step": 304440 + }, + { + "epoch": 0.68, + "learning_rate": 1.6072123666137224e-05, + "loss": 0.1098, + "step": 304450 + }, + { + "epoch": 0.68, + "learning_rate": 1.60710051229279e-05, + "loss": 0.1169, + "step": 304460 + }, + { + "epoch": 0.68, + "learning_rate": 1.6069886579718577e-05, + "loss": 0.1088, + "step": 304470 + }, + { + "epoch": 0.68, + "learning_rate": 1.606876803650925e-05, + "loss": 0.1144, + "step": 304480 + }, + { + "epoch": 0.68, + "learning_rate": 1.6067649493299926e-05, + "loss": 0.1136, + "step": 304490 + }, + { + "epoch": 0.68, + "learning_rate": 1.6066530950090604e-05, + "loss": 0.1141, + "step": 304500 + }, + { + "epoch": 0.68, + "learning_rate": 1.606541240688128e-05, + "loss": 0.109, + "step": 304510 + }, + { + "epoch": 0.68, + "learning_rate": 1.6064293863671953e-05, + "loss": 0.1126, + "step": 304520 + }, + { + "epoch": 0.68, + "learning_rate": 1.606317532046263e-05, + "loss": 0.1125, + "step": 304530 + }, + { + "epoch": 0.68, + "learning_rate": 1.6062056777253305e-05, + "loss": 0.11, + "step": 304540 + }, + { + "epoch": 0.68, + "learning_rate": 1.6060938234043983e-05, + "loss": 0.1135, + "step": 304550 + }, + { + "epoch": 0.68, + "learning_rate": 1.6059819690834658e-05, + "loss": 0.1147, + "step": 304560 + }, + { + "epoch": 0.68, + "learning_rate": 1.6058701147625332e-05, + "loss": 0.1096, + "step": 304570 + }, + { + "epoch": 0.68, + "learning_rate": 1.605758260441601e-05, + "loss": 0.1102, + "step": 304580 + }, + { + "epoch": 0.68, + "learning_rate": 1.6056464061206685e-05, + "loss": 0.1143, + "step": 304590 + }, + { + "epoch": 0.68, + "learning_rate": 1.6055345517997363e-05, + "loss": 0.1122, + "step": 304600 + }, + { + "epoch": 0.68, + "learning_rate": 1.6054226974788037e-05, + "loss": 0.1125, + "step": 304610 + }, + { + "epoch": 0.68, + "learning_rate": 1.6053108431578712e-05, + "loss": 0.1091, + "step": 304620 + }, + { + "epoch": 0.68, + "learning_rate": 1.605198988836939e-05, + "loss": 0.1121, + "step": 304630 + }, + { + "epoch": 0.68, + "learning_rate": 1.6050871345160064e-05, + "loss": 0.1112, + "step": 304640 + }, + { + "epoch": 0.68, + "learning_rate": 1.604975280195074e-05, + "loss": 0.1103, + "step": 304650 + }, + { + "epoch": 0.68, + "learning_rate": 1.6048634258741417e-05, + "loss": 0.1126, + "step": 304660 + }, + { + "epoch": 0.68, + "learning_rate": 1.604751571553209e-05, + "loss": 0.113, + "step": 304670 + }, + { + "epoch": 0.68, + "learning_rate": 1.6046397172322766e-05, + "loss": 0.1171, + "step": 304680 + }, + { + "epoch": 0.68, + "learning_rate": 1.6045278629113444e-05, + "loss": 0.1144, + "step": 304690 + }, + { + "epoch": 0.68, + "learning_rate": 1.604416008590412e-05, + "loss": 0.1106, + "step": 304700 + }, + { + "epoch": 0.68, + "learning_rate": 1.6043041542694796e-05, + "loss": 0.114, + "step": 304710 + }, + { + "epoch": 0.68, + "learning_rate": 1.604192299948547e-05, + "loss": 0.1092, + "step": 304720 + }, + { + "epoch": 0.68, + "learning_rate": 1.6040804456276145e-05, + "loss": 0.1107, + "step": 304730 + }, + { + "epoch": 0.68, + "learning_rate": 1.6039685913066823e-05, + "loss": 0.1051, + "step": 304740 + }, + { + "epoch": 0.68, + "learning_rate": 1.6038567369857498e-05, + "loss": 0.1097, + "step": 304750 + }, + { + "epoch": 0.68, + "learning_rate": 1.6037448826648176e-05, + "loss": 0.112, + "step": 304760 + }, + { + "epoch": 0.68, + "learning_rate": 1.603633028343885e-05, + "loss": 0.1143, + "step": 304770 + }, + { + "epoch": 0.68, + "learning_rate": 1.6035211740229525e-05, + "loss": 0.1098, + "step": 304780 + }, + { + "epoch": 0.68, + "learning_rate": 1.6034093197020203e-05, + "loss": 0.1101, + "step": 304790 + }, + { + "epoch": 0.68, + "learning_rate": 1.6033086508131808e-05, + "loss": 0.1101, + "step": 304800 + }, + { + "epoch": 0.68, + "learning_rate": 1.6031967964922486e-05, + "loss": 0.1088, + "step": 304810 + }, + { + "epoch": 0.68, + "learning_rate": 1.603084942171316e-05, + "loss": 0.111, + "step": 304820 + }, + { + "epoch": 0.68, + "learning_rate": 1.602973087850384e-05, + "loss": 0.1163, + "step": 304830 + }, + { + "epoch": 0.68, + "learning_rate": 1.6028612335294513e-05, + "loss": 0.1143, + "step": 304840 + }, + { + "epoch": 0.68, + "learning_rate": 1.6027493792085188e-05, + "loss": 0.1117, + "step": 304850 + }, + { + "epoch": 0.68, + "learning_rate": 1.6026375248875866e-05, + "loss": 0.119, + "step": 304860 + }, + { + "epoch": 0.68, + "learning_rate": 1.602525670566654e-05, + "loss": 0.1128, + "step": 304870 + }, + { + "epoch": 0.68, + "learning_rate": 1.6024138162457218e-05, + "loss": 0.1122, + "step": 304880 + }, + { + "epoch": 0.68, + "learning_rate": 1.6023019619247893e-05, + "loss": 0.1135, + "step": 304890 + }, + { + "epoch": 0.68, + "learning_rate": 1.6021901076038567e-05, + "loss": 0.1089, + "step": 304900 + }, + { + "epoch": 0.68, + "learning_rate": 1.602078253282924e-05, + "loss": 0.108, + "step": 304910 + }, + { + "epoch": 0.68, + "learning_rate": 1.601966398961992e-05, + "loss": 0.1112, + "step": 304920 + }, + { + "epoch": 0.68, + "learning_rate": 1.6018545446410597e-05, + "loss": 0.1124, + "step": 304930 + }, + { + "epoch": 0.68, + "learning_rate": 1.6017426903201272e-05, + "loss": 0.1123, + "step": 304940 + }, + { + "epoch": 0.68, + "learning_rate": 1.6016308359991947e-05, + "loss": 0.1159, + "step": 304950 + }, + { + "epoch": 0.68, + "learning_rate": 1.601518981678262e-05, + "loss": 0.1101, + "step": 304960 + }, + { + "epoch": 0.68, + "learning_rate": 1.60140712735733e-05, + "loss": 0.112, + "step": 304970 + }, + { + "epoch": 0.68, + "learning_rate": 1.6012952730363977e-05, + "loss": 0.111, + "step": 304980 + }, + { + "epoch": 0.68, + "learning_rate": 1.601183418715465e-05, + "loss": 0.1149, + "step": 304990 + }, + { + "epoch": 0.68, + "learning_rate": 1.6010715643945326e-05, + "loss": 0.1129, + "step": 305000 + }, + { + "epoch": 0.68, + "learning_rate": 1.6009597100736e-05, + "loss": 0.115, + "step": 305010 + }, + { + "epoch": 0.68, + "learning_rate": 1.600847855752668e-05, + "loss": 0.1123, + "step": 305020 + }, + { + "epoch": 0.68, + "learning_rate": 1.6007360014317353e-05, + "loss": 0.1076, + "step": 305030 + }, + { + "epoch": 0.68, + "learning_rate": 1.600624147110803e-05, + "loss": 0.1153, + "step": 305040 + }, + { + "epoch": 0.68, + "learning_rate": 1.6005122927898705e-05, + "loss": 0.1122, + "step": 305050 + }, + { + "epoch": 0.68, + "learning_rate": 1.600400438468938e-05, + "loss": 0.1078, + "step": 305060 + }, + { + "epoch": 0.68, + "learning_rate": 1.6002885841480055e-05, + "loss": 0.113, + "step": 305070 + }, + { + "epoch": 0.68, + "learning_rate": 1.6001767298270732e-05, + "loss": 0.1084, + "step": 305080 + }, + { + "epoch": 0.68, + "learning_rate": 1.600064875506141e-05, + "loss": 0.1136, + "step": 305090 + }, + { + "epoch": 0.68, + "learning_rate": 1.5999530211852085e-05, + "loss": 0.1056, + "step": 305100 + }, + { + "epoch": 0.68, + "learning_rate": 1.599841166864276e-05, + "loss": 0.1101, + "step": 305110 + }, + { + "epoch": 0.68, + "learning_rate": 1.5997293125433434e-05, + "loss": 0.1107, + "step": 305120 + }, + { + "epoch": 0.68, + "learning_rate": 1.5996174582224112e-05, + "loss": 0.1105, + "step": 305130 + }, + { + "epoch": 0.68, + "learning_rate": 1.599505603901479e-05, + "loss": 0.1087, + "step": 305140 + }, + { + "epoch": 0.68, + "learning_rate": 1.5993937495805464e-05, + "loss": 0.1103, + "step": 305150 + }, + { + "epoch": 0.68, + "learning_rate": 1.599281895259614e-05, + "loss": 0.1103, + "step": 305160 + }, + { + "epoch": 0.68, + "learning_rate": 1.5991700409386814e-05, + "loss": 0.1114, + "step": 305170 + }, + { + "epoch": 0.68, + "learning_rate": 1.599058186617749e-05, + "loss": 0.109, + "step": 305180 + }, + { + "epoch": 0.68, + "learning_rate": 1.598946332296817e-05, + "loss": 0.1104, + "step": 305190 + }, + { + "epoch": 0.68, + "learning_rate": 1.5988344779758844e-05, + "loss": 0.1138, + "step": 305200 + }, + { + "epoch": 0.68, + "learning_rate": 1.598722623654952e-05, + "loss": 0.1126, + "step": 305210 + }, + { + "epoch": 0.68, + "learning_rate": 1.5986107693340193e-05, + "loss": 0.1113, + "step": 305220 + }, + { + "epoch": 0.68, + "learning_rate": 1.5984989150130868e-05, + "loss": 0.1168, + "step": 305230 + }, + { + "epoch": 0.68, + "learning_rate": 1.5983870606921545e-05, + "loss": 0.1101, + "step": 305240 + }, + { + "epoch": 0.68, + "learning_rate": 1.5982752063712223e-05, + "loss": 0.1102, + "step": 305250 + }, + { + "epoch": 0.68, + "learning_rate": 1.5981633520502898e-05, + "loss": 0.1106, + "step": 305260 + }, + { + "epoch": 0.68, + "learning_rate": 1.5980514977293572e-05, + "loss": 0.1108, + "step": 305270 + }, + { + "epoch": 0.68, + "learning_rate": 1.5979396434084247e-05, + "loss": 0.1078, + "step": 305280 + }, + { + "epoch": 0.68, + "learning_rate": 1.5978277890874925e-05, + "loss": 0.1077, + "step": 305290 + }, + { + "epoch": 0.68, + "learning_rate": 1.5977159347665603e-05, + "loss": 0.1132, + "step": 305300 + }, + { + "epoch": 0.68, + "learning_rate": 1.5976040804456277e-05, + "loss": 0.1046, + "step": 305310 + }, + { + "epoch": 0.68, + "learning_rate": 1.5974922261246952e-05, + "loss": 0.1096, + "step": 305320 + }, + { + "epoch": 0.68, + "learning_rate": 1.5973803718037626e-05, + "loss": 0.1138, + "step": 305330 + }, + { + "epoch": 0.68, + "learning_rate": 1.5972685174828304e-05, + "loss": 0.1135, + "step": 305340 + }, + { + "epoch": 0.68, + "learning_rate": 1.5971566631618982e-05, + "loss": 0.1108, + "step": 305350 + }, + { + "epoch": 0.68, + "learning_rate": 1.5970448088409657e-05, + "loss": 0.1136, + "step": 305360 + }, + { + "epoch": 0.68, + "learning_rate": 1.596932954520033e-05, + "loss": 0.1138, + "step": 305370 + }, + { + "epoch": 0.68, + "learning_rate": 1.5968211001991006e-05, + "loss": 0.1124, + "step": 305380 + }, + { + "epoch": 0.68, + "learning_rate": 1.5967092458781684e-05, + "loss": 0.1128, + "step": 305390 + }, + { + "epoch": 0.68, + "learning_rate": 1.5965973915572362e-05, + "loss": 0.1103, + "step": 305400 + }, + { + "epoch": 0.68, + "learning_rate": 1.5964855372363036e-05, + "loss": 0.1155, + "step": 305410 + }, + { + "epoch": 0.68, + "learning_rate": 1.596373682915371e-05, + "loss": 0.1119, + "step": 305420 + }, + { + "epoch": 0.68, + "learning_rate": 1.5962618285944385e-05, + "loss": 0.1091, + "step": 305430 + }, + { + "epoch": 0.68, + "learning_rate": 1.596149974273506e-05, + "loss": 0.1077, + "step": 305440 + }, + { + "epoch": 0.68, + "learning_rate": 1.596038119952574e-05, + "loss": 0.1117, + "step": 305450 + }, + { + "epoch": 0.68, + "learning_rate": 1.5959262656316416e-05, + "loss": 0.1134, + "step": 305460 + }, + { + "epoch": 0.68, + "learning_rate": 1.595814411310709e-05, + "loss": 0.1114, + "step": 305470 + }, + { + "epoch": 0.68, + "learning_rate": 1.5957025569897765e-05, + "loss": 0.1143, + "step": 305480 + }, + { + "epoch": 0.68, + "learning_rate": 1.595590702668844e-05, + "loss": 0.1144, + "step": 305490 + }, + { + "epoch": 0.68, + "learning_rate": 1.5954788483479117e-05, + "loss": 0.1111, + "step": 305500 + }, + { + "epoch": 0.68, + "learning_rate": 1.5953669940269795e-05, + "loss": 0.1105, + "step": 305510 + }, + { + "epoch": 0.68, + "learning_rate": 1.595255139706047e-05, + "loss": 0.1082, + "step": 305520 + }, + { + "epoch": 0.68, + "learning_rate": 1.5951432853851144e-05, + "loss": 0.1126, + "step": 305530 + }, + { + "epoch": 0.68, + "learning_rate": 1.595031431064182e-05, + "loss": 0.1132, + "step": 305540 + }, + { + "epoch": 0.68, + "learning_rate": 1.5949195767432497e-05, + "loss": 0.1143, + "step": 305550 + }, + { + "epoch": 0.68, + "learning_rate": 1.5948077224223175e-05, + "loss": 0.109, + "step": 305560 + }, + { + "epoch": 0.68, + "learning_rate": 1.594695868101385e-05, + "loss": 0.1094, + "step": 305570 + }, + { + "epoch": 0.68, + "learning_rate": 1.5945840137804524e-05, + "loss": 0.1085, + "step": 305580 + }, + { + "epoch": 0.68, + "learning_rate": 1.59447215945952e-05, + "loss": 0.1185, + "step": 305590 + }, + { + "epoch": 0.68, + "learning_rate": 1.5943603051385876e-05, + "loss": 0.1104, + "step": 305600 + }, + { + "epoch": 0.68, + "learning_rate": 1.5942484508176554e-05, + "loss": 0.1116, + "step": 305610 + }, + { + "epoch": 0.68, + "learning_rate": 1.594136596496723e-05, + "loss": 0.1137, + "step": 305620 + }, + { + "epoch": 0.68, + "learning_rate": 1.5940247421757903e-05, + "loss": 0.111, + "step": 305630 + }, + { + "epoch": 0.68, + "learning_rate": 1.5939128878548578e-05, + "loss": 0.1079, + "step": 305640 + }, + { + "epoch": 0.68, + "learning_rate": 1.5938010335339252e-05, + "loss": 0.112, + "step": 305650 + }, + { + "epoch": 0.68, + "learning_rate": 1.5936891792129934e-05, + "loss": 0.1127, + "step": 305660 + }, + { + "epoch": 0.68, + "learning_rate": 1.5935773248920608e-05, + "loss": 0.1144, + "step": 305670 + }, + { + "epoch": 0.68, + "learning_rate": 1.5934654705711283e-05, + "loss": 0.1124, + "step": 305680 + }, + { + "epoch": 0.68, + "learning_rate": 1.5933536162501957e-05, + "loss": 0.1097, + "step": 305690 + }, + { + "epoch": 0.68, + "learning_rate": 1.5932417619292632e-05, + "loss": 0.1113, + "step": 305700 + }, + { + "epoch": 0.68, + "learning_rate": 1.593129907608331e-05, + "loss": 0.109, + "step": 305710 + }, + { + "epoch": 0.68, + "learning_rate": 1.5930180532873988e-05, + "loss": 0.1086, + "step": 305720 + }, + { + "epoch": 0.68, + "learning_rate": 1.5929061989664662e-05, + "loss": 0.1135, + "step": 305730 + }, + { + "epoch": 0.68, + "learning_rate": 1.5927943446455337e-05, + "loss": 0.1083, + "step": 305740 + }, + { + "epoch": 0.68, + "learning_rate": 1.592682490324601e-05, + "loss": 0.1151, + "step": 305750 + }, + { + "epoch": 0.68, + "learning_rate": 1.592570636003669e-05, + "loss": 0.1088, + "step": 305760 + }, + { + "epoch": 0.68, + "learning_rate": 1.5924587816827367e-05, + "loss": 0.113, + "step": 305770 + }, + { + "epoch": 0.68, + "learning_rate": 1.5923469273618042e-05, + "loss": 0.1135, + "step": 305780 + }, + { + "epoch": 0.68, + "learning_rate": 1.5922350730408716e-05, + "loss": 0.1147, + "step": 305790 + }, + { + "epoch": 0.68, + "learning_rate": 1.592123218719939e-05, + "loss": 0.1082, + "step": 305800 + }, + { + "epoch": 0.68, + "learning_rate": 1.592011364399007e-05, + "loss": 0.1113, + "step": 305810 + }, + { + "epoch": 0.68, + "learning_rate": 1.5918995100780747e-05, + "loss": 0.1134, + "step": 305820 + }, + { + "epoch": 0.68, + "learning_rate": 1.591787655757142e-05, + "loss": 0.1144, + "step": 305830 + }, + { + "epoch": 0.68, + "learning_rate": 1.5916758014362096e-05, + "loss": 0.1101, + "step": 305840 + }, + { + "epoch": 0.68, + "learning_rate": 1.591563947115277e-05, + "loss": 0.1085, + "step": 305850 + }, + { + "epoch": 0.68, + "learning_rate": 1.5914520927943445e-05, + "loss": 0.1141, + "step": 305860 + }, + { + "epoch": 0.68, + "learning_rate": 1.5913402384734123e-05, + "loss": 0.1128, + "step": 305870 + }, + { + "epoch": 0.68, + "learning_rate": 1.59122838415248e-05, + "loss": 0.1122, + "step": 305880 + }, + { + "epoch": 0.68, + "learning_rate": 1.5911165298315475e-05, + "loss": 0.1087, + "step": 305890 + }, + { + "epoch": 0.68, + "learning_rate": 1.591004675510615e-05, + "loss": 0.1098, + "step": 305900 + }, + { + "epoch": 0.68, + "learning_rate": 1.5908928211896824e-05, + "loss": 0.1093, + "step": 305910 + }, + { + "epoch": 0.68, + "learning_rate": 1.5907809668687502e-05, + "loss": 0.1095, + "step": 305920 + }, + { + "epoch": 0.68, + "learning_rate": 1.590669112547818e-05, + "loss": 0.1102, + "step": 305930 + }, + { + "epoch": 0.68, + "learning_rate": 1.5905572582268855e-05, + "loss": 0.1117, + "step": 305940 + }, + { + "epoch": 0.68, + "learning_rate": 1.590445403905953e-05, + "loss": 0.1132, + "step": 305950 + }, + { + "epoch": 0.68, + "learning_rate": 1.5903335495850204e-05, + "loss": 0.1133, + "step": 305960 + }, + { + "epoch": 0.68, + "learning_rate": 1.5902216952640882e-05, + "loss": 0.1108, + "step": 305970 + }, + { + "epoch": 0.68, + "learning_rate": 1.590109840943156e-05, + "loss": 0.1154, + "step": 305980 + }, + { + "epoch": 0.68, + "learning_rate": 1.5899979866222234e-05, + "loss": 0.1143, + "step": 305990 + }, + { + "epoch": 0.68, + "learning_rate": 1.589886132301291e-05, + "loss": 0.1174, + "step": 306000 + }, + { + "epoch": 0.68, + "learning_rate": 1.5897742779803583e-05, + "loss": 0.11, + "step": 306010 + }, + { + "epoch": 0.68, + "learning_rate": 1.589662423659426e-05, + "loss": 0.113, + "step": 306020 + }, + { + "epoch": 0.68, + "learning_rate": 1.5895505693384936e-05, + "loss": 0.1082, + "step": 306030 + }, + { + "epoch": 0.68, + "learning_rate": 1.5894387150175614e-05, + "loss": 0.1121, + "step": 306040 + }, + { + "epoch": 0.68, + "learning_rate": 1.5893268606966288e-05, + "loss": 0.1118, + "step": 306050 + }, + { + "epoch": 0.68, + "learning_rate": 1.5892150063756963e-05, + "loss": 0.1066, + "step": 306060 + }, + { + "epoch": 0.68, + "learning_rate": 1.589103152054764e-05, + "loss": 0.1127, + "step": 306070 + }, + { + "epoch": 0.68, + "learning_rate": 1.5889912977338315e-05, + "loss": 0.1116, + "step": 306080 + }, + { + "epoch": 0.68, + "learning_rate": 1.5888794434128993e-05, + "loss": 0.1122, + "step": 306090 + }, + { + "epoch": 0.68, + "learning_rate": 1.5887675890919668e-05, + "loss": 0.1127, + "step": 306100 + }, + { + "epoch": 0.68, + "learning_rate": 1.5886557347710342e-05, + "loss": 0.1141, + "step": 306110 + }, + { + "epoch": 0.68, + "learning_rate": 1.5885438804501017e-05, + "loss": 0.1073, + "step": 306120 + }, + { + "epoch": 0.68, + "learning_rate": 1.5884320261291695e-05, + "loss": 0.1109, + "step": 306130 + }, + { + "epoch": 0.68, + "learning_rate": 1.588320171808237e-05, + "loss": 0.1099, + "step": 306140 + }, + { + "epoch": 0.68, + "learning_rate": 1.5882083174873047e-05, + "loss": 0.1112, + "step": 306150 + }, + { + "epoch": 0.68, + "learning_rate": 1.588096463166372e-05, + "loss": 0.1118, + "step": 306160 + }, + { + "epoch": 0.68, + "learning_rate": 1.5879846088454396e-05, + "loss": 0.1114, + "step": 306170 + }, + { + "epoch": 0.68, + "learning_rate": 1.5878727545245074e-05, + "loss": 0.109, + "step": 306180 + }, + { + "epoch": 0.68, + "learning_rate": 1.587760900203575e-05, + "loss": 0.1131, + "step": 306190 + }, + { + "epoch": 0.68, + "learning_rate": 1.5876490458826427e-05, + "loss": 0.112, + "step": 306200 + }, + { + "epoch": 0.68, + "learning_rate": 1.58753719156171e-05, + "loss": 0.1118, + "step": 306210 + }, + { + "epoch": 0.68, + "learning_rate": 1.5874253372407776e-05, + "loss": 0.1112, + "step": 306220 + }, + { + "epoch": 0.68, + "learning_rate": 1.5873134829198454e-05, + "loss": 0.1114, + "step": 306230 + }, + { + "epoch": 0.68, + "learning_rate": 1.5872016285989128e-05, + "loss": 0.1123, + "step": 306240 + }, + { + "epoch": 0.68, + "learning_rate": 1.5870897742779806e-05, + "loss": 0.1128, + "step": 306250 + }, + { + "epoch": 0.68, + "learning_rate": 1.586977919957048e-05, + "loss": 0.1123, + "step": 306260 + }, + { + "epoch": 0.68, + "learning_rate": 1.5868660656361155e-05, + "loss": 0.1079, + "step": 306270 + }, + { + "epoch": 0.68, + "learning_rate": 1.5867542113151833e-05, + "loss": 0.1109, + "step": 306280 + }, + { + "epoch": 0.68, + "learning_rate": 1.5866423569942508e-05, + "loss": 0.11, + "step": 306290 + }, + { + "epoch": 0.68, + "learning_rate": 1.5865305026733182e-05, + "loss": 0.1131, + "step": 306300 + }, + { + "epoch": 0.68, + "learning_rate": 1.586418648352386e-05, + "loss": 0.1076, + "step": 306310 + }, + { + "epoch": 0.68, + "learning_rate": 1.5863067940314535e-05, + "loss": 0.1095, + "step": 306320 + }, + { + "epoch": 0.68, + "learning_rate": 1.586194939710521e-05, + "loss": 0.1132, + "step": 306330 + }, + { + "epoch": 0.68, + "learning_rate": 1.5860830853895887e-05, + "loss": 0.1099, + "step": 306340 + }, + { + "epoch": 0.68, + "learning_rate": 1.585971231068656e-05, + "loss": 0.1098, + "step": 306350 + }, + { + "epoch": 0.68, + "learning_rate": 1.585859376747724e-05, + "loss": 0.1096, + "step": 306360 + }, + { + "epoch": 0.68, + "learning_rate": 1.5857475224267914e-05, + "loss": 0.1148, + "step": 306370 + }, + { + "epoch": 0.68, + "learning_rate": 1.585635668105859e-05, + "loss": 0.1152, + "step": 306380 + }, + { + "epoch": 0.68, + "learning_rate": 1.5855238137849267e-05, + "loss": 0.1091, + "step": 306390 + }, + { + "epoch": 0.68, + "learning_rate": 1.585411959463994e-05, + "loss": 0.1142, + "step": 306400 + }, + { + "epoch": 0.68, + "learning_rate": 1.585300105143062e-05, + "loss": 0.111, + "step": 306410 + }, + { + "epoch": 0.68, + "learning_rate": 1.5851882508221294e-05, + "loss": 0.114, + "step": 306420 + }, + { + "epoch": 0.68, + "learning_rate": 1.5850763965011968e-05, + "loss": 0.112, + "step": 306430 + }, + { + "epoch": 0.68, + "learning_rate": 1.5849645421802646e-05, + "loss": 0.1133, + "step": 306440 + }, + { + "epoch": 0.68, + "learning_rate": 1.584852687859332e-05, + "loss": 0.1098, + "step": 306450 + }, + { + "epoch": 0.68, + "learning_rate": 1.5847408335383995e-05, + "loss": 0.1117, + "step": 306460 + }, + { + "epoch": 0.68, + "learning_rate": 1.5846289792174673e-05, + "loss": 0.1086, + "step": 306470 + }, + { + "epoch": 0.68, + "learning_rate": 1.5845171248965348e-05, + "loss": 0.1116, + "step": 306480 + }, + { + "epoch": 0.68, + "learning_rate": 1.5844052705756026e-05, + "loss": 0.1106, + "step": 306490 + }, + { + "epoch": 0.68, + "learning_rate": 1.58429341625467e-05, + "loss": 0.1161, + "step": 306500 + }, + { + "epoch": 0.68, + "learning_rate": 1.5841815619337375e-05, + "loss": 0.1105, + "step": 306510 + }, + { + "epoch": 0.68, + "learning_rate": 1.5840697076128053e-05, + "loss": 0.1073, + "step": 306520 + }, + { + "epoch": 0.68, + "learning_rate": 1.5839578532918727e-05, + "loss": 0.1146, + "step": 306530 + }, + { + "epoch": 0.68, + "learning_rate": 1.58384599897094e-05, + "loss": 0.1108, + "step": 306540 + }, + { + "epoch": 0.68, + "learning_rate": 1.583734144650008e-05, + "loss": 0.1153, + "step": 306550 + }, + { + "epoch": 0.68, + "learning_rate": 1.5836222903290754e-05, + "loss": 0.111, + "step": 306560 + }, + { + "epoch": 0.68, + "learning_rate": 1.5835104360081432e-05, + "loss": 0.1085, + "step": 306570 + }, + { + "epoch": 0.68, + "learning_rate": 1.5833985816872107e-05, + "loss": 0.1111, + "step": 306580 + }, + { + "epoch": 0.68, + "learning_rate": 1.583286727366278e-05, + "loss": 0.1082, + "step": 306590 + }, + { + "epoch": 0.68, + "learning_rate": 1.583174873045346e-05, + "loss": 0.1135, + "step": 306600 + }, + { + "epoch": 0.68, + "learning_rate": 1.5830630187244134e-05, + "loss": 0.1126, + "step": 306610 + }, + { + "epoch": 0.68, + "learning_rate": 1.5829511644034808e-05, + "loss": 0.1098, + "step": 306620 + }, + { + "epoch": 0.68, + "learning_rate": 1.5828393100825486e-05, + "loss": 0.1106, + "step": 306630 + }, + { + "epoch": 0.68, + "learning_rate": 1.582727455761616e-05, + "loss": 0.1113, + "step": 306640 + }, + { + "epoch": 0.68, + "learning_rate": 1.582615601440684e-05, + "loss": 0.106, + "step": 306650 + }, + { + "epoch": 0.68, + "learning_rate": 1.5825037471197513e-05, + "loss": 0.1108, + "step": 306660 + }, + { + "epoch": 0.68, + "learning_rate": 1.5823918927988188e-05, + "loss": 0.1083, + "step": 306670 + }, + { + "epoch": 0.68, + "learning_rate": 1.5822800384778865e-05, + "loss": 0.1137, + "step": 306680 + }, + { + "epoch": 0.68, + "learning_rate": 1.582168184156954e-05, + "loss": 0.1085, + "step": 306690 + }, + { + "epoch": 0.68, + "learning_rate": 1.5820563298360218e-05, + "loss": 0.1066, + "step": 306700 + }, + { + "epoch": 0.68, + "learning_rate": 1.5819444755150892e-05, + "loss": 0.1114, + "step": 306710 + }, + { + "epoch": 0.68, + "learning_rate": 1.5818326211941567e-05, + "loss": 0.1081, + "step": 306720 + }, + { + "epoch": 0.68, + "learning_rate": 1.5817207668732245e-05, + "loss": 0.11, + "step": 306730 + }, + { + "epoch": 0.68, + "learning_rate": 1.581608912552292e-05, + "loss": 0.1138, + "step": 306740 + }, + { + "epoch": 0.68, + "learning_rate": 1.5814970582313597e-05, + "loss": 0.1122, + "step": 306750 + }, + { + "epoch": 0.68, + "learning_rate": 1.5813852039104272e-05, + "loss": 0.112, + "step": 306760 + }, + { + "epoch": 0.68, + "learning_rate": 1.5812733495894947e-05, + "loss": 0.1095, + "step": 306770 + }, + { + "epoch": 0.68, + "learning_rate": 1.581161495268562e-05, + "loss": 0.1092, + "step": 306780 + }, + { + "epoch": 0.68, + "learning_rate": 1.58104964094763e-05, + "loss": 0.1117, + "step": 306790 + }, + { + "epoch": 0.68, + "learning_rate": 1.5809377866266974e-05, + "loss": 0.1114, + "step": 306800 + }, + { + "epoch": 0.68, + "learning_rate": 1.5808371177378582e-05, + "loss": 0.1121, + "step": 306810 + }, + { + "epoch": 0.68, + "learning_rate": 1.580725263416926e-05, + "loss": 0.1108, + "step": 306820 + }, + { + "epoch": 0.68, + "learning_rate": 1.5806134090959935e-05, + "loss": 0.1129, + "step": 306830 + }, + { + "epoch": 0.68, + "learning_rate": 1.580501554775061e-05, + "loss": 0.1085, + "step": 306840 + }, + { + "epoch": 0.68, + "learning_rate": 1.5803897004541284e-05, + "loss": 0.1064, + "step": 306850 + }, + { + "epoch": 0.68, + "learning_rate": 1.5802778461331962e-05, + "loss": 0.1101, + "step": 306860 + }, + { + "epoch": 0.68, + "learning_rate": 1.580165991812264e-05, + "loss": 0.1114, + "step": 306870 + }, + { + "epoch": 0.68, + "learning_rate": 1.5800541374913314e-05, + "loss": 0.108, + "step": 306880 + }, + { + "epoch": 0.69, + "learning_rate": 1.579942283170399e-05, + "loss": 0.1116, + "step": 306890 + }, + { + "epoch": 0.69, + "learning_rate": 1.5798304288494663e-05, + "loss": 0.1132, + "step": 306900 + }, + { + "epoch": 0.69, + "learning_rate": 1.579718574528534e-05, + "loss": 0.1133, + "step": 306910 + }, + { + "epoch": 0.69, + "learning_rate": 1.579606720207602e-05, + "loss": 0.1093, + "step": 306920 + }, + { + "epoch": 0.69, + "learning_rate": 1.5794948658866694e-05, + "loss": 0.111, + "step": 306930 + }, + { + "epoch": 0.69, + "learning_rate": 1.5793830115657368e-05, + "loss": 0.1121, + "step": 306940 + }, + { + "epoch": 0.69, + "learning_rate": 1.5792711572448043e-05, + "loss": 0.109, + "step": 306950 + }, + { + "epoch": 0.69, + "learning_rate": 1.579159302923872e-05, + "loss": 0.1115, + "step": 306960 + }, + { + "epoch": 0.69, + "learning_rate": 1.5790474486029395e-05, + "loss": 0.1079, + "step": 306970 + }, + { + "epoch": 0.69, + "learning_rate": 1.5789355942820073e-05, + "loss": 0.1145, + "step": 306980 + }, + { + "epoch": 0.69, + "learning_rate": 1.5788237399610748e-05, + "loss": 0.1118, + "step": 306990 + }, + { + "epoch": 0.69, + "learning_rate": 1.5787118856401422e-05, + "loss": 0.111, + "step": 307000 + }, + { + "epoch": 0.69, + "learning_rate": 1.5786000313192097e-05, + "loss": 0.1085, + "step": 307010 + }, + { + "epoch": 0.69, + "learning_rate": 1.5784881769982775e-05, + "loss": 0.1156, + "step": 307020 + }, + { + "epoch": 0.69, + "learning_rate": 1.5783763226773453e-05, + "loss": 0.1077, + "step": 307030 + }, + { + "epoch": 0.69, + "learning_rate": 1.5782644683564127e-05, + "loss": 0.1106, + "step": 307040 + }, + { + "epoch": 0.69, + "learning_rate": 1.5781526140354802e-05, + "loss": 0.1098, + "step": 307050 + }, + { + "epoch": 0.69, + "learning_rate": 1.5780407597145476e-05, + "loss": 0.1119, + "step": 307060 + }, + { + "epoch": 0.69, + "learning_rate": 1.5779289053936154e-05, + "loss": 0.1067, + "step": 307070 + }, + { + "epoch": 0.69, + "learning_rate": 1.5778170510726832e-05, + "loss": 0.108, + "step": 307080 + }, + { + "epoch": 0.69, + "learning_rate": 1.5777051967517507e-05, + "loss": 0.1177, + "step": 307090 + }, + { + "epoch": 0.69, + "learning_rate": 1.577593342430818e-05, + "loss": 0.1113, + "step": 307100 + }, + { + "epoch": 0.69, + "learning_rate": 1.5774814881098856e-05, + "loss": 0.1085, + "step": 307110 + }, + { + "epoch": 0.69, + "learning_rate": 1.5773696337889534e-05, + "loss": 0.1097, + "step": 307120 + }, + { + "epoch": 0.69, + "learning_rate": 1.577257779468021e-05, + "loss": 0.1135, + "step": 307130 + }, + { + "epoch": 0.69, + "learning_rate": 1.5771459251470886e-05, + "loss": 0.1104, + "step": 307140 + }, + { + "epoch": 0.69, + "learning_rate": 1.577034070826156e-05, + "loss": 0.1144, + "step": 307150 + }, + { + "epoch": 0.69, + "learning_rate": 1.5769222165052235e-05, + "loss": 0.11, + "step": 307160 + }, + { + "epoch": 0.69, + "learning_rate": 1.576810362184291e-05, + "loss": 0.1126, + "step": 307170 + }, + { + "epoch": 0.69, + "learning_rate": 1.5766985078633588e-05, + "loss": 0.1102, + "step": 307180 + }, + { + "epoch": 0.69, + "learning_rate": 1.5765866535424266e-05, + "loss": 0.1124, + "step": 307190 + }, + { + "epoch": 0.69, + "learning_rate": 1.576474799221494e-05, + "loss": 0.117, + "step": 307200 + }, + { + "epoch": 0.69, + "learning_rate": 1.5763629449005615e-05, + "loss": 0.1045, + "step": 307210 + }, + { + "epoch": 0.69, + "learning_rate": 1.576251090579629e-05, + "loss": 0.1085, + "step": 307220 + }, + { + "epoch": 0.69, + "learning_rate": 1.5761392362586967e-05, + "loss": 0.114, + "step": 307230 + }, + { + "epoch": 0.69, + "learning_rate": 1.5760273819377645e-05, + "loss": 0.1043, + "step": 307240 + }, + { + "epoch": 0.69, + "learning_rate": 1.575915527616832e-05, + "loss": 0.1107, + "step": 307250 + }, + { + "epoch": 0.69, + "learning_rate": 1.5758036732958994e-05, + "loss": 0.1109, + "step": 307260 + }, + { + "epoch": 0.69, + "learning_rate": 1.575691818974967e-05, + "loss": 0.111, + "step": 307270 + }, + { + "epoch": 0.69, + "learning_rate": 1.5755799646540347e-05, + "loss": 0.1128, + "step": 307280 + }, + { + "epoch": 0.69, + "learning_rate": 1.5754681103331025e-05, + "loss": 0.1141, + "step": 307290 + }, + { + "epoch": 0.69, + "learning_rate": 1.57535625601217e-05, + "loss": 0.1124, + "step": 307300 + }, + { + "epoch": 0.69, + "learning_rate": 1.5752444016912374e-05, + "loss": 0.1071, + "step": 307310 + }, + { + "epoch": 0.69, + "learning_rate": 1.5751325473703048e-05, + "loss": 0.1083, + "step": 307320 + }, + { + "epoch": 0.69, + "learning_rate": 1.5750206930493723e-05, + "loss": 0.1157, + "step": 307330 + }, + { + "epoch": 0.69, + "learning_rate": 1.5749088387284404e-05, + "loss": 0.1083, + "step": 307340 + }, + { + "epoch": 0.69, + "learning_rate": 1.574796984407508e-05, + "loss": 0.1117, + "step": 307350 + }, + { + "epoch": 0.69, + "learning_rate": 1.5746851300865753e-05, + "loss": 0.1095, + "step": 307360 + }, + { + "epoch": 0.69, + "learning_rate": 1.5745732757656428e-05, + "loss": 0.1116, + "step": 307370 + }, + { + "epoch": 0.69, + "learning_rate": 1.5744614214447102e-05, + "loss": 0.117, + "step": 307380 + }, + { + "epoch": 0.69, + "learning_rate": 1.574349567123778e-05, + "loss": 0.1105, + "step": 307390 + }, + { + "epoch": 0.69, + "learning_rate": 1.5742377128028458e-05, + "loss": 0.113, + "step": 307400 + }, + { + "epoch": 0.69, + "learning_rate": 1.5741258584819133e-05, + "loss": 0.1106, + "step": 307410 + }, + { + "epoch": 0.69, + "learning_rate": 1.5740140041609807e-05, + "loss": 0.1138, + "step": 307420 + }, + { + "epoch": 0.69, + "learning_rate": 1.573902149840048e-05, + "loss": 0.1058, + "step": 307430 + }, + { + "epoch": 0.69, + "learning_rate": 1.573790295519116e-05, + "loss": 0.1124, + "step": 307440 + }, + { + "epoch": 0.69, + "learning_rate": 1.5736784411981838e-05, + "loss": 0.1111, + "step": 307450 + }, + { + "epoch": 0.69, + "learning_rate": 1.5735665868772512e-05, + "loss": 0.1052, + "step": 307460 + }, + { + "epoch": 0.69, + "learning_rate": 1.5734547325563187e-05, + "loss": 0.1115, + "step": 307470 + }, + { + "epoch": 0.69, + "learning_rate": 1.573342878235386e-05, + "loss": 0.1107, + "step": 307480 + }, + { + "epoch": 0.69, + "learning_rate": 1.573231023914454e-05, + "loss": 0.1164, + "step": 307490 + }, + { + "epoch": 0.69, + "learning_rate": 1.5731191695935217e-05, + "loss": 0.1105, + "step": 307500 + }, + { + "epoch": 0.69, + "learning_rate": 1.573007315272589e-05, + "loss": 0.1098, + "step": 307510 + }, + { + "epoch": 0.69, + "learning_rate": 1.5728954609516566e-05, + "loss": 0.1122, + "step": 307520 + }, + { + "epoch": 0.69, + "learning_rate": 1.572783606630724e-05, + "loss": 0.1133, + "step": 307530 + }, + { + "epoch": 0.69, + "learning_rate": 1.572671752309792e-05, + "loss": 0.1077, + "step": 307540 + }, + { + "epoch": 0.69, + "learning_rate": 1.5725598979888596e-05, + "loss": 0.1121, + "step": 307550 + }, + { + "epoch": 0.69, + "learning_rate": 1.572448043667927e-05, + "loss": 0.1094, + "step": 307560 + }, + { + "epoch": 0.69, + "learning_rate": 1.5723361893469946e-05, + "loss": 0.1063, + "step": 307570 + }, + { + "epoch": 0.69, + "learning_rate": 1.572224335026062e-05, + "loss": 0.1079, + "step": 307580 + }, + { + "epoch": 0.69, + "learning_rate": 1.5721124807051295e-05, + "loss": 0.1105, + "step": 307590 + }, + { + "epoch": 0.69, + "learning_rate": 1.5720006263841976e-05, + "loss": 0.1078, + "step": 307600 + }, + { + "epoch": 0.69, + "learning_rate": 1.571888772063265e-05, + "loss": 0.1163, + "step": 307610 + }, + { + "epoch": 0.69, + "learning_rate": 1.5717769177423325e-05, + "loss": 0.1146, + "step": 307620 + }, + { + "epoch": 0.69, + "learning_rate": 1.5716650634214e-05, + "loss": 0.1101, + "step": 307630 + }, + { + "epoch": 0.69, + "learning_rate": 1.5715532091004674e-05, + "loss": 0.1055, + "step": 307640 + }, + { + "epoch": 0.69, + "learning_rate": 1.5714413547795352e-05, + "loss": 0.1074, + "step": 307650 + }, + { + "epoch": 0.69, + "learning_rate": 1.571329500458603e-05, + "loss": 0.1077, + "step": 307660 + }, + { + "epoch": 0.69, + "learning_rate": 1.5712176461376705e-05, + "loss": 0.1088, + "step": 307670 + }, + { + "epoch": 0.69, + "learning_rate": 1.571105791816738e-05, + "loss": 0.1111, + "step": 307680 + }, + { + "epoch": 0.69, + "learning_rate": 1.5709939374958054e-05, + "loss": 0.1132, + "step": 307690 + }, + { + "epoch": 0.69, + "learning_rate": 1.570882083174873e-05, + "loss": 0.1106, + "step": 307700 + }, + { + "epoch": 0.69, + "learning_rate": 1.570770228853941e-05, + "loss": 0.1111, + "step": 307710 + }, + { + "epoch": 0.69, + "learning_rate": 1.5706583745330084e-05, + "loss": 0.1172, + "step": 307720 + }, + { + "epoch": 0.69, + "learning_rate": 1.570546520212076e-05, + "loss": 0.1109, + "step": 307730 + }, + { + "epoch": 0.69, + "learning_rate": 1.5704346658911433e-05, + "loss": 0.1138, + "step": 307740 + }, + { + "epoch": 0.69, + "learning_rate": 1.570322811570211e-05, + "loss": 0.112, + "step": 307750 + }, + { + "epoch": 0.69, + "learning_rate": 1.570210957249279e-05, + "loss": 0.1147, + "step": 307760 + }, + { + "epoch": 0.69, + "learning_rate": 1.5700991029283463e-05, + "loss": 0.1057, + "step": 307770 + }, + { + "epoch": 0.69, + "learning_rate": 1.5699872486074138e-05, + "loss": 0.1124, + "step": 307780 + }, + { + "epoch": 0.69, + "learning_rate": 1.5698753942864813e-05, + "loss": 0.1136, + "step": 307790 + }, + { + "epoch": 0.69, + "learning_rate": 1.5697635399655487e-05, + "loss": 0.1149, + "step": 307800 + }, + { + "epoch": 0.69, + "learning_rate": 1.5696516856446165e-05, + "loss": 0.1069, + "step": 307810 + }, + { + "epoch": 0.69, + "learning_rate": 1.5695398313236843e-05, + "loss": 0.1108, + "step": 307820 + }, + { + "epoch": 0.69, + "learning_rate": 1.5694279770027517e-05, + "loss": 0.1086, + "step": 307830 + }, + { + "epoch": 0.69, + "learning_rate": 1.5693161226818192e-05, + "loss": 0.1115, + "step": 307840 + }, + { + "epoch": 0.69, + "learning_rate": 1.5692042683608867e-05, + "loss": 0.1083, + "step": 307850 + }, + { + "epoch": 0.69, + "learning_rate": 1.5690924140399544e-05, + "loss": 0.1132, + "step": 307860 + }, + { + "epoch": 0.69, + "learning_rate": 1.5689805597190222e-05, + "loss": 0.1086, + "step": 307870 + }, + { + "epoch": 0.69, + "learning_rate": 1.5688687053980897e-05, + "loss": 0.111, + "step": 307880 + }, + { + "epoch": 0.69, + "learning_rate": 1.568756851077157e-05, + "loss": 0.1122, + "step": 307890 + }, + { + "epoch": 0.69, + "learning_rate": 1.5686449967562246e-05, + "loss": 0.113, + "step": 307900 + }, + { + "epoch": 0.69, + "learning_rate": 1.5685331424352924e-05, + "loss": 0.116, + "step": 307910 + }, + { + "epoch": 0.69, + "learning_rate": 1.5684212881143602e-05, + "loss": 0.1105, + "step": 307920 + }, + { + "epoch": 0.69, + "learning_rate": 1.5683094337934276e-05, + "loss": 0.1092, + "step": 307930 + }, + { + "epoch": 0.69, + "learning_rate": 1.568197579472495e-05, + "loss": 0.1132, + "step": 307940 + }, + { + "epoch": 0.69, + "learning_rate": 1.5680857251515625e-05, + "loss": 0.114, + "step": 307950 + }, + { + "epoch": 0.69, + "learning_rate": 1.5679738708306303e-05, + "loss": 0.1086, + "step": 307960 + }, + { + "epoch": 0.69, + "learning_rate": 1.5678620165096978e-05, + "loss": 0.1035, + "step": 307970 + }, + { + "epoch": 0.69, + "learning_rate": 1.5677501621887656e-05, + "loss": 0.1066, + "step": 307980 + }, + { + "epoch": 0.69, + "learning_rate": 1.567638307867833e-05, + "loss": 0.1068, + "step": 307990 + }, + { + "epoch": 0.69, + "learning_rate": 1.5675264535469005e-05, + "loss": 0.1148, + "step": 308000 + }, + { + "epoch": 0.69, + "learning_rate": 1.567414599225968e-05, + "loss": 0.1124, + "step": 308010 + }, + { + "epoch": 0.69, + "learning_rate": 1.5673027449050357e-05, + "loss": 0.1112, + "step": 308020 + }, + { + "epoch": 0.69, + "learning_rate": 1.5671908905841035e-05, + "loss": 0.1056, + "step": 308030 + }, + { + "epoch": 0.69, + "learning_rate": 1.567079036263171e-05, + "loss": 0.1091, + "step": 308040 + }, + { + "epoch": 0.69, + "learning_rate": 1.5669671819422384e-05, + "loss": 0.1103, + "step": 308050 + }, + { + "epoch": 0.69, + "learning_rate": 1.566855327621306e-05, + "loss": 0.1134, + "step": 308060 + }, + { + "epoch": 0.69, + "learning_rate": 1.5667434733003737e-05, + "loss": 0.11, + "step": 308070 + }, + { + "epoch": 0.69, + "learning_rate": 1.5666316189794415e-05, + "loss": 0.1119, + "step": 308080 + }, + { + "epoch": 0.69, + "learning_rate": 1.566519764658509e-05, + "loss": 0.1093, + "step": 308090 + }, + { + "epoch": 0.69, + "learning_rate": 1.5664079103375764e-05, + "loss": 0.1083, + "step": 308100 + }, + { + "epoch": 0.69, + "learning_rate": 1.566296056016644e-05, + "loss": 0.1163, + "step": 308110 + }, + { + "epoch": 0.69, + "learning_rate": 1.5661842016957116e-05, + "loss": 0.1109, + "step": 308120 + }, + { + "epoch": 0.69, + "learning_rate": 1.566072347374779e-05, + "loss": 0.1087, + "step": 308130 + }, + { + "epoch": 0.69, + "learning_rate": 1.565960493053847e-05, + "loss": 0.1111, + "step": 308140 + }, + { + "epoch": 0.69, + "learning_rate": 1.5658486387329143e-05, + "loss": 0.1096, + "step": 308150 + }, + { + "epoch": 0.69, + "learning_rate": 1.5657367844119818e-05, + "loss": 0.1079, + "step": 308160 + }, + { + "epoch": 0.69, + "learning_rate": 1.5656249300910496e-05, + "loss": 0.1062, + "step": 308170 + }, + { + "epoch": 0.69, + "learning_rate": 1.565513075770117e-05, + "loss": 0.1096, + "step": 308180 + }, + { + "epoch": 0.69, + "learning_rate": 1.565401221449185e-05, + "loss": 0.1066, + "step": 308190 + }, + { + "epoch": 0.69, + "learning_rate": 1.5652893671282523e-05, + "loss": 0.1126, + "step": 308200 + }, + { + "epoch": 0.69, + "learning_rate": 1.5651775128073197e-05, + "loss": 0.1133, + "step": 308210 + }, + { + "epoch": 0.69, + "learning_rate": 1.5650656584863875e-05, + "loss": 0.1109, + "step": 308220 + }, + { + "epoch": 0.69, + "learning_rate": 1.564953804165455e-05, + "loss": 0.1091, + "step": 308230 + }, + { + "epoch": 0.69, + "learning_rate": 1.5648419498445228e-05, + "loss": 0.1114, + "step": 308240 + }, + { + "epoch": 0.69, + "learning_rate": 1.5647300955235902e-05, + "loss": 0.1054, + "step": 308250 + }, + { + "epoch": 0.69, + "learning_rate": 1.5646182412026577e-05, + "loss": 0.1106, + "step": 308260 + }, + { + "epoch": 0.69, + "learning_rate": 1.564506386881725e-05, + "loss": 0.1108, + "step": 308270 + }, + { + "epoch": 0.69, + "learning_rate": 1.564394532560793e-05, + "loss": 0.109, + "step": 308280 + }, + { + "epoch": 0.69, + "learning_rate": 1.5642826782398604e-05, + "loss": 0.1129, + "step": 308290 + }, + { + "epoch": 0.69, + "learning_rate": 1.5641708239189282e-05, + "loss": 0.1151, + "step": 308300 + }, + { + "epoch": 0.69, + "learning_rate": 1.5640589695979956e-05, + "loss": 0.1075, + "step": 308310 + }, + { + "epoch": 0.69, + "learning_rate": 1.563947115277063e-05, + "loss": 0.1097, + "step": 308320 + }, + { + "epoch": 0.69, + "learning_rate": 1.563835260956131e-05, + "loss": 0.1101, + "step": 308330 + }, + { + "epoch": 0.69, + "learning_rate": 1.5637234066351983e-05, + "loss": 0.1117, + "step": 308340 + }, + { + "epoch": 0.69, + "learning_rate": 1.563611552314266e-05, + "loss": 0.111, + "step": 308350 + }, + { + "epoch": 0.69, + "learning_rate": 1.5634996979933336e-05, + "loss": 0.1093, + "step": 308360 + }, + { + "epoch": 0.69, + "learning_rate": 1.563387843672401e-05, + "loss": 0.11, + "step": 308370 + }, + { + "epoch": 0.69, + "learning_rate": 1.5632759893514688e-05, + "loss": 0.1097, + "step": 308380 + }, + { + "epoch": 0.69, + "learning_rate": 1.5631641350305363e-05, + "loss": 0.1062, + "step": 308390 + }, + { + "epoch": 0.69, + "learning_rate": 1.563052280709604e-05, + "loss": 0.1074, + "step": 308400 + }, + { + "epoch": 0.69, + "learning_rate": 1.5629404263886715e-05, + "loss": 0.1147, + "step": 308410 + }, + { + "epoch": 0.69, + "learning_rate": 1.562828572067739e-05, + "loss": 0.1136, + "step": 308420 + }, + { + "epoch": 0.69, + "learning_rate": 1.5627167177468068e-05, + "loss": 0.1095, + "step": 308430 + }, + { + "epoch": 0.69, + "learning_rate": 1.5626048634258742e-05, + "loss": 0.1176, + "step": 308440 + }, + { + "epoch": 0.69, + "learning_rate": 1.5624930091049417e-05, + "loss": 0.1093, + "step": 308450 + }, + { + "epoch": 0.69, + "learning_rate": 1.5623811547840095e-05, + "loss": 0.1161, + "step": 308460 + }, + { + "epoch": 0.69, + "learning_rate": 1.562269300463077e-05, + "loss": 0.1121, + "step": 308470 + }, + { + "epoch": 0.69, + "learning_rate": 1.5621574461421444e-05, + "loss": 0.1086, + "step": 308480 + }, + { + "epoch": 0.69, + "learning_rate": 1.5620455918212122e-05, + "loss": 0.111, + "step": 308490 + }, + { + "epoch": 0.69, + "learning_rate": 1.5619337375002796e-05, + "loss": 0.113, + "step": 308500 + }, + { + "epoch": 0.69, + "learning_rate": 1.5618218831793474e-05, + "loss": 0.111, + "step": 308510 + }, + { + "epoch": 0.69, + "learning_rate": 1.561710028858415e-05, + "loss": 0.1108, + "step": 308520 + }, + { + "epoch": 0.69, + "learning_rate": 1.5615981745374823e-05, + "loss": 0.1093, + "step": 308530 + }, + { + "epoch": 0.69, + "learning_rate": 1.56148632021655e-05, + "loss": 0.1107, + "step": 308540 + }, + { + "epoch": 0.69, + "learning_rate": 1.5613744658956176e-05, + "loss": 0.1136, + "step": 308550 + }, + { + "epoch": 0.69, + "learning_rate": 1.5612626115746854e-05, + "loss": 0.1091, + "step": 308560 + }, + { + "epoch": 0.69, + "learning_rate": 1.5611507572537528e-05, + "loss": 0.108, + "step": 308570 + }, + { + "epoch": 0.69, + "learning_rate": 1.5610389029328203e-05, + "loss": 0.1106, + "step": 308580 + }, + { + "epoch": 0.69, + "learning_rate": 1.560927048611888e-05, + "loss": 0.1124, + "step": 308590 + }, + { + "epoch": 0.69, + "learning_rate": 1.5608151942909555e-05, + "loss": 0.1103, + "step": 308600 + }, + { + "epoch": 0.69, + "learning_rate": 1.560703339970023e-05, + "loss": 0.1132, + "step": 308610 + }, + { + "epoch": 0.69, + "learning_rate": 1.5605914856490908e-05, + "loss": 0.112, + "step": 308620 + }, + { + "epoch": 0.69, + "learning_rate": 1.5604796313281582e-05, + "loss": 0.1099, + "step": 308630 + }, + { + "epoch": 0.69, + "learning_rate": 1.560367777007226e-05, + "loss": 0.1084, + "step": 308640 + }, + { + "epoch": 0.69, + "learning_rate": 1.5602559226862935e-05, + "loss": 0.1105, + "step": 308650 + }, + { + "epoch": 0.69, + "learning_rate": 1.560144068365361e-05, + "loss": 0.1164, + "step": 308660 + }, + { + "epoch": 0.69, + "learning_rate": 1.5600322140444287e-05, + "loss": 0.1077, + "step": 308670 + }, + { + "epoch": 0.69, + "learning_rate": 1.5599203597234962e-05, + "loss": 0.1139, + "step": 308680 + }, + { + "epoch": 0.69, + "learning_rate": 1.5598085054025636e-05, + "loss": 0.1077, + "step": 308690 + }, + { + "epoch": 0.69, + "learning_rate": 1.5596966510816314e-05, + "loss": 0.1104, + "step": 308700 + }, + { + "epoch": 0.69, + "learning_rate": 1.559584796760699e-05, + "loss": 0.1128, + "step": 308710 + }, + { + "epoch": 0.69, + "learning_rate": 1.5594729424397667e-05, + "loss": 0.1166, + "step": 308720 + }, + { + "epoch": 0.69, + "learning_rate": 1.559361088118834e-05, + "loss": 0.1127, + "step": 308730 + }, + { + "epoch": 0.69, + "learning_rate": 1.5592492337979016e-05, + "loss": 0.1123, + "step": 308740 + }, + { + "epoch": 0.69, + "learning_rate": 1.5591373794769694e-05, + "loss": 0.1091, + "step": 308750 + }, + { + "epoch": 0.69, + "learning_rate": 1.5590255251560368e-05, + "loss": 0.1095, + "step": 308760 + }, + { + "epoch": 0.69, + "learning_rate": 1.5589136708351043e-05, + "loss": 0.1088, + "step": 308770 + }, + { + "epoch": 0.69, + "learning_rate": 1.558801816514172e-05, + "loss": 0.1101, + "step": 308780 + }, + { + "epoch": 0.69, + "learning_rate": 1.5586899621932395e-05, + "loss": 0.1137, + "step": 308790 + }, + { + "epoch": 0.69, + "learning_rate": 1.5585781078723073e-05, + "loss": 0.1086, + "step": 308800 + }, + { + "epoch": 0.69, + "learning_rate": 1.5584774389834682e-05, + "loss": 0.1077, + "step": 308810 + }, + { + "epoch": 0.69, + "learning_rate": 1.5583655846625356e-05, + "loss": 0.1116, + "step": 308820 + }, + { + "epoch": 0.69, + "learning_rate": 1.558253730341603e-05, + "loss": 0.1124, + "step": 308830 + }, + { + "epoch": 0.69, + "learning_rate": 1.5581418760206706e-05, + "loss": 0.1095, + "step": 308840 + }, + { + "epoch": 0.69, + "learning_rate": 1.5580300216997383e-05, + "loss": 0.1122, + "step": 308850 + }, + { + "epoch": 0.69, + "learning_rate": 1.5579181673788058e-05, + "loss": 0.1096, + "step": 308860 + }, + { + "epoch": 0.69, + "learning_rate": 1.5578063130578736e-05, + "loss": 0.1119, + "step": 308870 + }, + { + "epoch": 0.69, + "learning_rate": 1.557694458736941e-05, + "loss": 0.1097, + "step": 308880 + }, + { + "epoch": 0.69, + "learning_rate": 1.5575826044160085e-05, + "loss": 0.1061, + "step": 308890 + }, + { + "epoch": 0.69, + "learning_rate": 1.5574707500950763e-05, + "loss": 0.106, + "step": 308900 + }, + { + "epoch": 0.69, + "learning_rate": 1.5573588957741438e-05, + "loss": 0.1151, + "step": 308910 + }, + { + "epoch": 0.69, + "learning_rate": 1.5572470414532115e-05, + "loss": 0.1133, + "step": 308920 + }, + { + "epoch": 0.69, + "learning_rate": 1.557135187132279e-05, + "loss": 0.1085, + "step": 308930 + }, + { + "epoch": 0.69, + "learning_rate": 1.5570233328113465e-05, + "loss": 0.1146, + "step": 308940 + }, + { + "epoch": 0.69, + "learning_rate": 1.556911478490414e-05, + "loss": 0.1116, + "step": 308950 + }, + { + "epoch": 0.69, + "learning_rate": 1.5567996241694817e-05, + "loss": 0.1077, + "step": 308960 + }, + { + "epoch": 0.69, + "learning_rate": 1.5566877698485495e-05, + "loss": 0.1098, + "step": 308970 + }, + { + "epoch": 0.69, + "learning_rate": 1.556575915527617e-05, + "loss": 0.1095, + "step": 308980 + }, + { + "epoch": 0.69, + "learning_rate": 1.5564640612066844e-05, + "loss": 0.1108, + "step": 308990 + }, + { + "epoch": 0.69, + "learning_rate": 1.556352206885752e-05, + "loss": 0.1072, + "step": 309000 + }, + { + "epoch": 0.69, + "learning_rate": 1.5562403525648196e-05, + "loss": 0.1123, + "step": 309010 + }, + { + "epoch": 0.69, + "learning_rate": 1.5561284982438874e-05, + "loss": 0.1105, + "step": 309020 + }, + { + "epoch": 0.69, + "learning_rate": 1.556016643922955e-05, + "loss": 0.106, + "step": 309030 + }, + { + "epoch": 0.69, + "learning_rate": 1.5559047896020223e-05, + "loss": 0.1108, + "step": 309040 + }, + { + "epoch": 0.69, + "learning_rate": 1.5557929352810898e-05, + "loss": 0.1075, + "step": 309050 + }, + { + "epoch": 0.69, + "learning_rate": 1.5556810809601576e-05, + "loss": 0.1097, + "step": 309060 + }, + { + "epoch": 0.69, + "learning_rate": 1.5555692266392254e-05, + "loss": 0.1117, + "step": 309070 + }, + { + "epoch": 0.69, + "learning_rate": 1.555457372318293e-05, + "loss": 0.1124, + "step": 309080 + }, + { + "epoch": 0.69, + "learning_rate": 1.5553455179973603e-05, + "loss": 0.1113, + "step": 309090 + }, + { + "epoch": 0.69, + "learning_rate": 1.5552336636764277e-05, + "loss": 0.1122, + "step": 309100 + }, + { + "epoch": 0.69, + "learning_rate": 1.5551218093554952e-05, + "loss": 0.1065, + "step": 309110 + }, + { + "epoch": 0.69, + "learning_rate": 1.555009955034563e-05, + "loss": 0.1127, + "step": 309120 + }, + { + "epoch": 0.69, + "learning_rate": 1.5548981007136308e-05, + "loss": 0.1143, + "step": 309130 + }, + { + "epoch": 0.69, + "learning_rate": 1.5547862463926982e-05, + "loss": 0.1093, + "step": 309140 + }, + { + "epoch": 0.69, + "learning_rate": 1.5546743920717657e-05, + "loss": 0.1107, + "step": 309150 + }, + { + "epoch": 0.69, + "learning_rate": 1.554562537750833e-05, + "loss": 0.109, + "step": 309160 + }, + { + "epoch": 0.69, + "learning_rate": 1.554450683429901e-05, + "loss": 0.1071, + "step": 309170 + }, + { + "epoch": 0.69, + "learning_rate": 1.5543388291089687e-05, + "loss": 0.1085, + "step": 309180 + }, + { + "epoch": 0.69, + "learning_rate": 1.5542269747880362e-05, + "loss": 0.1124, + "step": 309190 + }, + { + "epoch": 0.69, + "learning_rate": 1.5541151204671036e-05, + "loss": 0.1103, + "step": 309200 + }, + { + "epoch": 0.69, + "learning_rate": 1.554003266146171e-05, + "loss": 0.1124, + "step": 309210 + }, + { + "epoch": 0.69, + "learning_rate": 1.553891411825239e-05, + "loss": 0.1099, + "step": 309220 + }, + { + "epoch": 0.69, + "learning_rate": 1.5537795575043067e-05, + "loss": 0.1103, + "step": 309230 + }, + { + "epoch": 0.69, + "learning_rate": 1.553667703183374e-05, + "loss": 0.111, + "step": 309240 + }, + { + "epoch": 0.69, + "learning_rate": 1.5535558488624416e-05, + "loss": 0.1106, + "step": 309250 + }, + { + "epoch": 0.69, + "learning_rate": 1.553443994541509e-05, + "loss": 0.1105, + "step": 309260 + }, + { + "epoch": 0.69, + "learning_rate": 1.5533321402205765e-05, + "loss": 0.1092, + "step": 309270 + }, + { + "epoch": 0.69, + "learning_rate": 1.5532202858996446e-05, + "loss": 0.1135, + "step": 309280 + }, + { + "epoch": 0.69, + "learning_rate": 1.553108431578712e-05, + "loss": 0.1123, + "step": 309290 + }, + { + "epoch": 0.69, + "learning_rate": 1.5529965772577795e-05, + "loss": 0.1114, + "step": 309300 + }, + { + "epoch": 0.69, + "learning_rate": 1.552884722936847e-05, + "loss": 0.1146, + "step": 309310 + }, + { + "epoch": 0.69, + "learning_rate": 1.5527728686159144e-05, + "loss": 0.1109, + "step": 309320 + }, + { + "epoch": 0.69, + "learning_rate": 1.5526610142949822e-05, + "loss": 0.113, + "step": 309330 + }, + { + "epoch": 0.69, + "learning_rate": 1.55254915997405e-05, + "loss": 0.1188, + "step": 309340 + }, + { + "epoch": 0.69, + "learning_rate": 1.5524373056531175e-05, + "loss": 0.1115, + "step": 309350 + }, + { + "epoch": 0.69, + "learning_rate": 1.552325451332185e-05, + "loss": 0.1094, + "step": 309360 + }, + { + "epoch": 0.69, + "learning_rate": 1.5522135970112524e-05, + "loss": 0.1116, + "step": 309370 + }, + { + "epoch": 0.69, + "learning_rate": 1.5521017426903202e-05, + "loss": 0.1175, + "step": 309380 + }, + { + "epoch": 0.69, + "learning_rate": 1.551989888369388e-05, + "loss": 0.1143, + "step": 309390 + }, + { + "epoch": 0.69, + "learning_rate": 1.5518780340484554e-05, + "loss": 0.1062, + "step": 309400 + }, + { + "epoch": 0.69, + "learning_rate": 1.551766179727523e-05, + "loss": 0.1082, + "step": 309410 + }, + { + "epoch": 0.69, + "learning_rate": 1.5516543254065903e-05, + "loss": 0.1122, + "step": 309420 + }, + { + "epoch": 0.69, + "learning_rate": 1.551542471085658e-05, + "loss": 0.1094, + "step": 309430 + }, + { + "epoch": 0.69, + "learning_rate": 1.551430616764726e-05, + "loss": 0.1071, + "step": 309440 + }, + { + "epoch": 0.69, + "learning_rate": 1.5513187624437934e-05, + "loss": 0.1095, + "step": 309450 + }, + { + "epoch": 0.69, + "learning_rate": 1.551206908122861e-05, + "loss": 0.1058, + "step": 309460 + }, + { + "epoch": 0.69, + "learning_rate": 1.5510950538019283e-05, + "loss": 0.1131, + "step": 309470 + }, + { + "epoch": 0.69, + "learning_rate": 1.5509831994809957e-05, + "loss": 0.1115, + "step": 309480 + }, + { + "epoch": 0.69, + "learning_rate": 1.550871345160064e-05, + "loss": 0.1092, + "step": 309490 + }, + { + "epoch": 0.69, + "learning_rate": 1.5507594908391313e-05, + "loss": 0.1104, + "step": 309500 + }, + { + "epoch": 0.69, + "learning_rate": 1.5506476365181988e-05, + "loss": 0.1119, + "step": 309510 + }, + { + "epoch": 0.69, + "learning_rate": 1.5505357821972662e-05, + "loss": 0.1132, + "step": 309520 + }, + { + "epoch": 0.69, + "learning_rate": 1.5504239278763337e-05, + "loss": 0.1092, + "step": 309530 + }, + { + "epoch": 0.69, + "learning_rate": 1.5503120735554015e-05, + "loss": 0.1065, + "step": 309540 + }, + { + "epoch": 0.69, + "learning_rate": 1.5502002192344693e-05, + "loss": 0.1106, + "step": 309550 + }, + { + "epoch": 0.69, + "learning_rate": 1.5500883649135367e-05, + "loss": 0.1085, + "step": 309560 + }, + { + "epoch": 0.69, + "learning_rate": 1.5499765105926042e-05, + "loss": 0.1067, + "step": 309570 + }, + { + "epoch": 0.69, + "learning_rate": 1.5498646562716716e-05, + "loss": 0.1094, + "step": 309580 + }, + { + "epoch": 0.69, + "learning_rate": 1.5497528019507394e-05, + "loss": 0.1151, + "step": 309590 + }, + { + "epoch": 0.69, + "learning_rate": 1.5496409476298072e-05, + "loss": 0.1065, + "step": 309600 + }, + { + "epoch": 0.69, + "learning_rate": 1.5495290933088747e-05, + "loss": 0.106, + "step": 309610 + }, + { + "epoch": 0.69, + "learning_rate": 1.549417238987942e-05, + "loss": 0.1132, + "step": 309620 + }, + { + "epoch": 0.69, + "learning_rate": 1.5493053846670096e-05, + "loss": 0.1138, + "step": 309630 + }, + { + "epoch": 0.69, + "learning_rate": 1.5491935303460774e-05, + "loss": 0.1108, + "step": 309640 + }, + { + "epoch": 0.69, + "learning_rate": 1.549081676025145e-05, + "loss": 0.1138, + "step": 309650 + }, + { + "epoch": 0.69, + "learning_rate": 1.5489698217042126e-05, + "loss": 0.1097, + "step": 309660 + }, + { + "epoch": 0.69, + "learning_rate": 1.54885796738328e-05, + "loss": 0.1067, + "step": 309670 + }, + { + "epoch": 0.69, + "learning_rate": 1.5487461130623475e-05, + "loss": 0.1085, + "step": 309680 + }, + { + "epoch": 0.69, + "learning_rate": 1.5486342587414153e-05, + "loss": 0.1096, + "step": 309690 + }, + { + "epoch": 0.69, + "learning_rate": 1.548522404420483e-05, + "loss": 0.1075, + "step": 309700 + }, + { + "epoch": 0.69, + "learning_rate": 1.5484105500995506e-05, + "loss": 0.1116, + "step": 309710 + }, + { + "epoch": 0.69, + "learning_rate": 1.548298695778618e-05, + "loss": 0.1104, + "step": 309720 + }, + { + "epoch": 0.69, + "learning_rate": 1.5481868414576855e-05, + "loss": 0.1135, + "step": 309730 + }, + { + "epoch": 0.69, + "learning_rate": 1.548074987136753e-05, + "loss": 0.1082, + "step": 309740 + }, + { + "epoch": 0.69, + "learning_rate": 1.5479631328158207e-05, + "loss": 0.1115, + "step": 309750 + }, + { + "epoch": 0.69, + "learning_rate": 1.5478512784948885e-05, + "loss": 0.1167, + "step": 309760 + }, + { + "epoch": 0.69, + "learning_rate": 1.547739424173956e-05, + "loss": 0.1079, + "step": 309770 + }, + { + "epoch": 0.69, + "learning_rate": 1.5476275698530234e-05, + "loss": 0.1062, + "step": 309780 + }, + { + "epoch": 0.69, + "learning_rate": 1.547515715532091e-05, + "loss": 0.1095, + "step": 309790 + }, + { + "epoch": 0.69, + "learning_rate": 1.5474038612111587e-05, + "loss": 0.1119, + "step": 309800 + }, + { + "epoch": 0.69, + "learning_rate": 1.5472920068902265e-05, + "loss": 0.1064, + "step": 309810 + }, + { + "epoch": 0.69, + "learning_rate": 1.547180152569294e-05, + "loss": 0.1135, + "step": 309820 + }, + { + "epoch": 0.69, + "learning_rate": 1.5470682982483614e-05, + "loss": 0.1125, + "step": 309830 + }, + { + "epoch": 0.69, + "learning_rate": 1.5469564439274288e-05, + "loss": 0.1119, + "step": 309840 + }, + { + "epoch": 0.69, + "learning_rate": 1.5468445896064966e-05, + "loss": 0.1128, + "step": 309850 + }, + { + "epoch": 0.69, + "learning_rate": 1.5467327352855644e-05, + "loss": 0.109, + "step": 309860 + }, + { + "epoch": 0.69, + "learning_rate": 1.546620880964632e-05, + "loss": 0.112, + "step": 309870 + }, + { + "epoch": 0.69, + "learning_rate": 1.5465090266436993e-05, + "loss": 0.1092, + "step": 309880 + }, + { + "epoch": 0.69, + "learning_rate": 1.5463971723227668e-05, + "loss": 0.1095, + "step": 309890 + }, + { + "epoch": 0.69, + "learning_rate": 1.5462853180018346e-05, + "loss": 0.1104, + "step": 309900 + }, + { + "epoch": 0.69, + "learning_rate": 1.546173463680902e-05, + "loss": 0.1156, + "step": 309910 + }, + { + "epoch": 0.69, + "learning_rate": 1.5460616093599698e-05, + "loss": 0.1109, + "step": 309920 + }, + { + "epoch": 0.69, + "learning_rate": 1.5459497550390373e-05, + "loss": 0.1111, + "step": 309930 + }, + { + "epoch": 0.69, + "learning_rate": 1.5458379007181047e-05, + "loss": 0.1093, + "step": 309940 + }, + { + "epoch": 0.69, + "learning_rate": 1.5457260463971722e-05, + "loss": 0.1109, + "step": 309950 + }, + { + "epoch": 0.69, + "learning_rate": 1.54561419207624e-05, + "loss": 0.107, + "step": 309960 + }, + { + "epoch": 0.69, + "learning_rate": 1.5455023377553078e-05, + "loss": 0.1124, + "step": 309970 + }, + { + "epoch": 0.69, + "learning_rate": 1.5453904834343752e-05, + "loss": 0.109, + "step": 309980 + }, + { + "epoch": 0.69, + "learning_rate": 1.5452786291134427e-05, + "loss": 0.109, + "step": 309990 + }, + { + "epoch": 0.69, + "learning_rate": 1.54516677479251e-05, + "loss": 0.1119, + "step": 310000 + }, + { + "epoch": 0.69, + "learning_rate": 1.545054920471578e-05, + "loss": 0.1049, + "step": 310010 + }, + { + "epoch": 0.69, + "learning_rate": 1.5449430661506457e-05, + "loss": 0.1121, + "step": 310020 + }, + { + "epoch": 0.69, + "learning_rate": 1.544831211829713e-05, + "loss": 0.1047, + "step": 310030 + }, + { + "epoch": 0.69, + "learning_rate": 1.5447193575087806e-05, + "loss": 0.1106, + "step": 310040 + }, + { + "epoch": 0.69, + "learning_rate": 1.544607503187848e-05, + "loss": 0.1074, + "step": 310050 + }, + { + "epoch": 0.69, + "learning_rate": 1.544495648866916e-05, + "loss": 0.1141, + "step": 310060 + }, + { + "epoch": 0.69, + "learning_rate": 1.5443837945459833e-05, + "loss": 0.1106, + "step": 310070 + }, + { + "epoch": 0.69, + "learning_rate": 1.544271940225051e-05, + "loss": 0.1113, + "step": 310080 + }, + { + "epoch": 0.69, + "learning_rate": 1.5441600859041186e-05, + "loss": 0.1084, + "step": 310090 + }, + { + "epoch": 0.69, + "learning_rate": 1.544048231583186e-05, + "loss": 0.1101, + "step": 310100 + }, + { + "epoch": 0.69, + "learning_rate": 1.5439363772622538e-05, + "loss": 0.1121, + "step": 310110 + }, + { + "epoch": 0.69, + "learning_rate": 1.5438245229413213e-05, + "loss": 0.1109, + "step": 310120 + }, + { + "epoch": 0.69, + "learning_rate": 1.543712668620389e-05, + "loss": 0.1107, + "step": 310130 + }, + { + "epoch": 0.69, + "learning_rate": 1.5436008142994565e-05, + "loss": 0.1146, + "step": 310140 + }, + { + "epoch": 0.69, + "learning_rate": 1.543488959978524e-05, + "loss": 0.1126, + "step": 310150 + }, + { + "epoch": 0.69, + "learning_rate": 1.5433771056575914e-05, + "loss": 0.1144, + "step": 310160 + }, + { + "epoch": 0.69, + "learning_rate": 1.5432652513366592e-05, + "loss": 0.1126, + "step": 310170 + }, + { + "epoch": 0.69, + "learning_rate": 1.543153397015727e-05, + "loss": 0.107, + "step": 310180 + }, + { + "epoch": 0.69, + "learning_rate": 1.5430415426947945e-05, + "loss": 0.1096, + "step": 310190 + }, + { + "epoch": 0.69, + "learning_rate": 1.542929688373862e-05, + "loss": 0.1103, + "step": 310200 + }, + { + "epoch": 0.69, + "learning_rate": 1.5428178340529294e-05, + "loss": 0.1093, + "step": 310210 + }, + { + "epoch": 0.69, + "learning_rate": 1.542705979731997e-05, + "loss": 0.1102, + "step": 310220 + }, + { + "epoch": 0.69, + "learning_rate": 1.5425941254110646e-05, + "loss": 0.1082, + "step": 310230 + }, + { + "epoch": 0.69, + "learning_rate": 1.5424822710901324e-05, + "loss": 0.1111, + "step": 310240 + }, + { + "epoch": 0.69, + "learning_rate": 1.5423704167692e-05, + "loss": 0.1084, + "step": 310250 + }, + { + "epoch": 0.69, + "learning_rate": 1.5422585624482673e-05, + "loss": 0.1102, + "step": 310260 + }, + { + "epoch": 0.69, + "learning_rate": 1.542146708127335e-05, + "loss": 0.1153, + "step": 310270 + }, + { + "epoch": 0.69, + "learning_rate": 1.5420348538064026e-05, + "loss": 0.1101, + "step": 310280 + }, + { + "epoch": 0.69, + "learning_rate": 1.5419229994854704e-05, + "loss": 0.107, + "step": 310290 + }, + { + "epoch": 0.69, + "learning_rate": 1.5418111451645378e-05, + "loss": 0.1073, + "step": 310300 + }, + { + "epoch": 0.69, + "learning_rate": 1.5416992908436053e-05, + "loss": 0.1082, + "step": 310310 + }, + { + "epoch": 0.69, + "learning_rate": 1.541587436522673e-05, + "loss": 0.1084, + "step": 310320 + }, + { + "epoch": 0.69, + "learning_rate": 1.5414755822017405e-05, + "loss": 0.1073, + "step": 310330 + }, + { + "epoch": 0.69, + "learning_rate": 1.5413637278808083e-05, + "loss": 0.1094, + "step": 310340 + }, + { + "epoch": 0.69, + "learning_rate": 1.5412518735598758e-05, + "loss": 0.1113, + "step": 310350 + }, + { + "epoch": 0.69, + "learning_rate": 1.5411400192389432e-05, + "loss": 0.1106, + "step": 310360 + }, + { + "epoch": 0.69, + "learning_rate": 1.5410281649180107e-05, + "loss": 0.1123, + "step": 310370 + }, + { + "epoch": 0.69, + "learning_rate": 1.5409163105970785e-05, + "loss": 0.111, + "step": 310380 + }, + { + "epoch": 0.69, + "learning_rate": 1.540804456276146e-05, + "loss": 0.1083, + "step": 310390 + }, + { + "epoch": 0.69, + "learning_rate": 1.5406926019552137e-05, + "loss": 0.1098, + "step": 310400 + }, + { + "epoch": 0.69, + "learning_rate": 1.540580747634281e-05, + "loss": 0.111, + "step": 310410 + }, + { + "epoch": 0.69, + "learning_rate": 1.5404688933133486e-05, + "loss": 0.1093, + "step": 310420 + }, + { + "epoch": 0.69, + "learning_rate": 1.5403570389924164e-05, + "loss": 0.1114, + "step": 310430 + }, + { + "epoch": 0.69, + "learning_rate": 1.540245184671484e-05, + "loss": 0.1069, + "step": 310440 + }, + { + "epoch": 0.69, + "learning_rate": 1.5401333303505516e-05, + "loss": 0.1132, + "step": 310450 + }, + { + "epoch": 0.69, + "learning_rate": 1.540021476029619e-05, + "loss": 0.114, + "step": 310460 + }, + { + "epoch": 0.69, + "learning_rate": 1.5399096217086866e-05, + "loss": 0.11, + "step": 310470 + }, + { + "epoch": 0.69, + "learning_rate": 1.5397977673877544e-05, + "loss": 0.1114, + "step": 310480 + }, + { + "epoch": 0.69, + "learning_rate": 1.5396859130668218e-05, + "loss": 0.1115, + "step": 310490 + }, + { + "epoch": 0.69, + "learning_rate": 1.5395740587458896e-05, + "loss": 0.1108, + "step": 310500 + }, + { + "epoch": 0.69, + "learning_rate": 1.539462204424957e-05, + "loss": 0.1113, + "step": 310510 + }, + { + "epoch": 0.69, + "learning_rate": 1.5393503501040245e-05, + "loss": 0.1108, + "step": 310520 + }, + { + "epoch": 0.69, + "learning_rate": 1.5392384957830923e-05, + "loss": 0.1115, + "step": 310530 + }, + { + "epoch": 0.69, + "learning_rate": 1.5391266414621598e-05, + "loss": 0.113, + "step": 310540 + }, + { + "epoch": 0.69, + "learning_rate": 1.5390147871412272e-05, + "loss": 0.1113, + "step": 310550 + }, + { + "epoch": 0.69, + "learning_rate": 1.538902932820295e-05, + "loss": 0.1106, + "step": 310560 + }, + { + "epoch": 0.69, + "learning_rate": 1.5387910784993625e-05, + "loss": 0.1064, + "step": 310570 + }, + { + "epoch": 0.69, + "learning_rate": 1.5386792241784302e-05, + "loss": 0.1122, + "step": 310580 + }, + { + "epoch": 0.69, + "learning_rate": 1.5385673698574977e-05, + "loss": 0.1141, + "step": 310590 + }, + { + "epoch": 0.69, + "learning_rate": 1.538455515536565e-05, + "loss": 0.1136, + "step": 310600 + }, + { + "epoch": 0.69, + "learning_rate": 1.538343661215633e-05, + "loss": 0.1067, + "step": 310610 + }, + { + "epoch": 0.69, + "learning_rate": 1.5382318068947004e-05, + "loss": 0.1105, + "step": 310620 + }, + { + "epoch": 0.69, + "learning_rate": 1.538119952573768e-05, + "loss": 0.1099, + "step": 310630 + }, + { + "epoch": 0.69, + "learning_rate": 1.5380080982528356e-05, + "loss": 0.1105, + "step": 310640 + }, + { + "epoch": 0.69, + "learning_rate": 1.537896243931903e-05, + "loss": 0.1103, + "step": 310650 + }, + { + "epoch": 0.69, + "learning_rate": 1.537784389610971e-05, + "loss": 0.1155, + "step": 310660 + }, + { + "epoch": 0.69, + "learning_rate": 1.5376725352900383e-05, + "loss": 0.1077, + "step": 310670 + }, + { + "epoch": 0.69, + "learning_rate": 1.5375606809691058e-05, + "loss": 0.1123, + "step": 310680 + }, + { + "epoch": 0.69, + "learning_rate": 1.5374488266481736e-05, + "loss": 0.1093, + "step": 310690 + }, + { + "epoch": 0.69, + "learning_rate": 1.537336972327241e-05, + "loss": 0.1108, + "step": 310700 + }, + { + "epoch": 0.69, + "learning_rate": 1.5372251180063085e-05, + "loss": 0.1131, + "step": 310710 + }, + { + "epoch": 0.69, + "learning_rate": 1.5371132636853763e-05, + "loss": 0.1114, + "step": 310720 + }, + { + "epoch": 0.69, + "learning_rate": 1.5370014093644437e-05, + "loss": 0.1085, + "step": 310730 + }, + { + "epoch": 0.69, + "learning_rate": 1.5368895550435115e-05, + "loss": 0.1077, + "step": 310740 + }, + { + "epoch": 0.69, + "learning_rate": 1.536777700722579e-05, + "loss": 0.1084, + "step": 310750 + }, + { + "epoch": 0.69, + "learning_rate": 1.5366658464016464e-05, + "loss": 0.1081, + "step": 310760 + }, + { + "epoch": 0.69, + "learning_rate": 1.5365539920807142e-05, + "loss": 0.1107, + "step": 310770 + }, + { + "epoch": 0.69, + "learning_rate": 1.5364421377597817e-05, + "loss": 0.1097, + "step": 310780 + }, + { + "epoch": 0.69, + "learning_rate": 1.5363302834388495e-05, + "loss": 0.1147, + "step": 310790 + }, + { + "epoch": 0.69, + "learning_rate": 1.536218429117917e-05, + "loss": 0.1059, + "step": 310800 + }, + { + "epoch": 0.69, + "learning_rate": 1.5361065747969844e-05, + "loss": 0.1124, + "step": 310810 + }, + { + "epoch": 0.69, + "learning_rate": 1.5359947204760522e-05, + "loss": 0.1116, + "step": 310820 + }, + { + "epoch": 0.69, + "learning_rate": 1.5358940515872127e-05, + "loss": 0.1143, + "step": 310830 + }, + { + "epoch": 0.69, + "learning_rate": 1.5357821972662805e-05, + "loss": 0.1102, + "step": 310840 + }, + { + "epoch": 0.69, + "learning_rate": 1.535670342945348e-05, + "loss": 0.1073, + "step": 310850 + }, + { + "epoch": 0.69, + "learning_rate": 1.5355584886244158e-05, + "loss": 0.1102, + "step": 310860 + }, + { + "epoch": 0.69, + "learning_rate": 1.5354466343034832e-05, + "loss": 0.1116, + "step": 310870 + }, + { + "epoch": 0.69, + "learning_rate": 1.5353347799825507e-05, + "loss": 0.1109, + "step": 310880 + }, + { + "epoch": 0.69, + "learning_rate": 1.5352229256616185e-05, + "loss": 0.1109, + "step": 310890 + }, + { + "epoch": 0.69, + "learning_rate": 1.535111071340686e-05, + "loss": 0.1147, + "step": 310900 + }, + { + "epoch": 0.69, + "learning_rate": 1.5349992170197537e-05, + "loss": 0.1115, + "step": 310910 + }, + { + "epoch": 0.69, + "learning_rate": 1.5348873626988212e-05, + "loss": 0.1086, + "step": 310920 + }, + { + "epoch": 0.69, + "learning_rate": 1.5347755083778886e-05, + "loss": 0.1093, + "step": 310930 + }, + { + "epoch": 0.69, + "learning_rate": 1.534663654056956e-05, + "loss": 0.1101, + "step": 310940 + }, + { + "epoch": 0.69, + "learning_rate": 1.534551799736024e-05, + "loss": 0.11, + "step": 310950 + }, + { + "epoch": 0.69, + "learning_rate": 1.5344399454150917e-05, + "loss": 0.112, + "step": 310960 + }, + { + "epoch": 0.69, + "learning_rate": 1.534328091094159e-05, + "loss": 0.1142, + "step": 310970 + }, + { + "epoch": 0.69, + "learning_rate": 1.5342162367732266e-05, + "loss": 0.1085, + "step": 310980 + }, + { + "epoch": 0.69, + "learning_rate": 1.534104382452294e-05, + "loss": 0.1102, + "step": 310990 + }, + { + "epoch": 0.69, + "learning_rate": 1.5339925281313618e-05, + "loss": 0.1093, + "step": 311000 + }, + { + "epoch": 0.69, + "learning_rate": 1.5338806738104293e-05, + "loss": 0.1132, + "step": 311010 + }, + { + "epoch": 0.69, + "learning_rate": 1.533768819489497e-05, + "loss": 0.1054, + "step": 311020 + }, + { + "epoch": 0.69, + "learning_rate": 1.5336569651685645e-05, + "loss": 0.1093, + "step": 311030 + }, + { + "epoch": 0.69, + "learning_rate": 1.533545110847632e-05, + "loss": 0.1115, + "step": 311040 + }, + { + "epoch": 0.69, + "learning_rate": 1.5334332565266998e-05, + "loss": 0.1133, + "step": 311050 + }, + { + "epoch": 0.69, + "learning_rate": 1.5333214022057672e-05, + "loss": 0.1128, + "step": 311060 + }, + { + "epoch": 0.69, + "learning_rate": 1.533209547884835e-05, + "loss": 0.108, + "step": 311070 + }, + { + "epoch": 0.69, + "learning_rate": 1.5330976935639025e-05, + "loss": 0.1097, + "step": 311080 + }, + { + "epoch": 0.69, + "learning_rate": 1.53298583924297e-05, + "loss": 0.1096, + "step": 311090 + }, + { + "epoch": 0.69, + "learning_rate": 1.5328739849220374e-05, + "loss": 0.107, + "step": 311100 + }, + { + "epoch": 0.69, + "learning_rate": 1.532762130601105e-05, + "loss": 0.1126, + "step": 311110 + }, + { + "epoch": 0.69, + "learning_rate": 1.532650276280173e-05, + "loss": 0.1071, + "step": 311120 + }, + { + "epoch": 0.69, + "learning_rate": 1.5325384219592404e-05, + "loss": 0.1073, + "step": 311130 + }, + { + "epoch": 0.69, + "learning_rate": 1.532426567638308e-05, + "loss": 0.1101, + "step": 311140 + }, + { + "epoch": 0.69, + "learning_rate": 1.5323147133173753e-05, + "loss": 0.1092, + "step": 311150 + }, + { + "epoch": 0.69, + "learning_rate": 1.532202858996443e-05, + "loss": 0.1093, + "step": 311160 + }, + { + "epoch": 0.69, + "learning_rate": 1.532091004675511e-05, + "loss": 0.1031, + "step": 311170 + }, + { + "epoch": 0.69, + "learning_rate": 1.5319791503545784e-05, + "loss": 0.1083, + "step": 311180 + }, + { + "epoch": 0.69, + "learning_rate": 1.5318672960336458e-05, + "loss": 0.1044, + "step": 311190 + }, + { + "epoch": 0.69, + "learning_rate": 1.5317554417127133e-05, + "loss": 0.1131, + "step": 311200 + }, + { + "epoch": 0.69, + "learning_rate": 1.531643587391781e-05, + "loss": 0.1091, + "step": 311210 + }, + { + "epoch": 0.69, + "learning_rate": 1.5315317330708485e-05, + "loss": 0.1085, + "step": 311220 + }, + { + "epoch": 0.69, + "learning_rate": 1.5314198787499163e-05, + "loss": 0.113, + "step": 311230 + }, + { + "epoch": 0.69, + "learning_rate": 1.5313080244289838e-05, + "loss": 0.1074, + "step": 311240 + }, + { + "epoch": 0.69, + "learning_rate": 1.5311961701080512e-05, + "loss": 0.1111, + "step": 311250 + }, + { + "epoch": 0.69, + "learning_rate": 1.5310843157871187e-05, + "loss": 0.1119, + "step": 311260 + }, + { + "epoch": 0.69, + "learning_rate": 1.5309724614661865e-05, + "loss": 0.1144, + "step": 311270 + }, + { + "epoch": 0.69, + "learning_rate": 1.5308606071452543e-05, + "loss": 0.1115, + "step": 311280 + }, + { + "epoch": 0.69, + "learning_rate": 1.5307487528243217e-05, + "loss": 0.1072, + "step": 311290 + }, + { + "epoch": 0.69, + "learning_rate": 1.530636898503389e-05, + "loss": 0.1148, + "step": 311300 + }, + { + "epoch": 0.69, + "learning_rate": 1.5305250441824566e-05, + "loss": 0.1108, + "step": 311310 + }, + { + "epoch": 0.69, + "learning_rate": 1.5304131898615244e-05, + "loss": 0.1102, + "step": 311320 + }, + { + "epoch": 0.69, + "learning_rate": 1.5303013355405922e-05, + "loss": 0.1124, + "step": 311330 + }, + { + "epoch": 0.69, + "learning_rate": 1.5301894812196597e-05, + "loss": 0.113, + "step": 311340 + }, + { + "epoch": 0.69, + "learning_rate": 1.530077626898727e-05, + "loss": 0.1069, + "step": 311350 + }, + { + "epoch": 0.69, + "learning_rate": 1.5299657725777946e-05, + "loss": 0.1054, + "step": 311360 + }, + { + "epoch": 0.7, + "learning_rate": 1.5298539182568624e-05, + "loss": 0.1119, + "step": 311370 + }, + { + "epoch": 0.7, + "learning_rate": 1.52974206393593e-05, + "loss": 0.1096, + "step": 311380 + }, + { + "epoch": 0.7, + "learning_rate": 1.5296302096149976e-05, + "loss": 0.1115, + "step": 311390 + }, + { + "epoch": 0.7, + "learning_rate": 1.529518355294065e-05, + "loss": 0.1129, + "step": 311400 + }, + { + "epoch": 0.7, + "learning_rate": 1.5294065009731325e-05, + "loss": 0.1113, + "step": 311410 + }, + { + "epoch": 0.7, + "learning_rate": 1.5292946466522e-05, + "loss": 0.1107, + "step": 311420 + }, + { + "epoch": 0.7, + "learning_rate": 1.529182792331268e-05, + "loss": 0.1077, + "step": 311430 + }, + { + "epoch": 0.7, + "learning_rate": 1.5290709380103356e-05, + "loss": 0.1117, + "step": 311440 + }, + { + "epoch": 0.7, + "learning_rate": 1.528959083689403e-05, + "loss": 0.11, + "step": 311450 + }, + { + "epoch": 0.7, + "learning_rate": 1.5288472293684705e-05, + "loss": 0.108, + "step": 311460 + }, + { + "epoch": 0.7, + "learning_rate": 1.528735375047538e-05, + "loss": 0.1118, + "step": 311470 + }, + { + "epoch": 0.7, + "learning_rate": 1.5286235207266057e-05, + "loss": 0.1076, + "step": 311480 + }, + { + "epoch": 0.7, + "learning_rate": 1.5285116664056735e-05, + "loss": 0.1115, + "step": 311490 + }, + { + "epoch": 0.7, + "learning_rate": 1.528399812084741e-05, + "loss": 0.1113, + "step": 311500 + }, + { + "epoch": 0.7, + "learning_rate": 1.5282879577638084e-05, + "loss": 0.1124, + "step": 311510 + }, + { + "epoch": 0.7, + "learning_rate": 1.528176103442876e-05, + "loss": 0.1096, + "step": 311520 + }, + { + "epoch": 0.7, + "learning_rate": 1.5280642491219437e-05, + "loss": 0.1086, + "step": 311530 + }, + { + "epoch": 0.7, + "learning_rate": 1.5279523948010114e-05, + "loss": 0.1111, + "step": 311540 + }, + { + "epoch": 0.7, + "learning_rate": 1.527840540480079e-05, + "loss": 0.1074, + "step": 311550 + }, + { + "epoch": 0.7, + "learning_rate": 1.5277286861591464e-05, + "loss": 0.1093, + "step": 311560 + }, + { + "epoch": 0.7, + "learning_rate": 1.5276168318382138e-05, + "loss": 0.1114, + "step": 311570 + }, + { + "epoch": 0.7, + "learning_rate": 1.5275049775172816e-05, + "loss": 0.1096, + "step": 311580 + }, + { + "epoch": 0.7, + "learning_rate": 1.5273931231963494e-05, + "loss": 0.1114, + "step": 311590 + }, + { + "epoch": 0.7, + "learning_rate": 1.527281268875417e-05, + "loss": 0.1099, + "step": 311600 + }, + { + "epoch": 0.7, + "learning_rate": 1.5271694145544843e-05, + "loss": 0.1117, + "step": 311610 + }, + { + "epoch": 0.7, + "learning_rate": 1.5270575602335518e-05, + "loss": 0.107, + "step": 311620 + }, + { + "epoch": 0.7, + "learning_rate": 1.5269457059126192e-05, + "loss": 0.1115, + "step": 311630 + }, + { + "epoch": 0.7, + "learning_rate": 1.5268338515916873e-05, + "loss": 0.1166, + "step": 311640 + }, + { + "epoch": 0.7, + "learning_rate": 1.5267219972707548e-05, + "loss": 0.113, + "step": 311650 + }, + { + "epoch": 0.7, + "learning_rate": 1.5266101429498222e-05, + "loss": 0.112, + "step": 311660 + }, + { + "epoch": 0.7, + "learning_rate": 1.5264982886288897e-05, + "loss": 0.1099, + "step": 311670 + }, + { + "epoch": 0.7, + "learning_rate": 1.526386434307957e-05, + "loss": 0.1125, + "step": 311680 + }, + { + "epoch": 0.7, + "learning_rate": 1.526274579987025e-05, + "loss": 0.1099, + "step": 311690 + }, + { + "epoch": 0.7, + "learning_rate": 1.5261627256660927e-05, + "loss": 0.1101, + "step": 311700 + }, + { + "epoch": 0.7, + "learning_rate": 1.5260508713451602e-05, + "loss": 0.1122, + "step": 311710 + }, + { + "epoch": 0.7, + "learning_rate": 1.5259390170242277e-05, + "loss": 0.1111, + "step": 311720 + }, + { + "epoch": 0.7, + "learning_rate": 1.5258271627032953e-05, + "loss": 0.1082, + "step": 311730 + }, + { + "epoch": 0.7, + "learning_rate": 1.5257153083823627e-05, + "loss": 0.1091, + "step": 311740 + }, + { + "epoch": 0.7, + "learning_rate": 1.5256034540614305e-05, + "loss": 0.1079, + "step": 311750 + }, + { + "epoch": 0.7, + "learning_rate": 1.5254915997404981e-05, + "loss": 0.11, + "step": 311760 + }, + { + "epoch": 0.7, + "learning_rate": 1.5253797454195656e-05, + "loss": 0.1083, + "step": 311770 + }, + { + "epoch": 0.7, + "learning_rate": 1.5252678910986332e-05, + "loss": 0.1106, + "step": 311780 + }, + { + "epoch": 0.7, + "learning_rate": 1.5251560367777007e-05, + "loss": 0.1091, + "step": 311790 + }, + { + "epoch": 0.7, + "learning_rate": 1.5250441824567685e-05, + "loss": 0.1115, + "step": 311800 + }, + { + "epoch": 0.7, + "learning_rate": 1.5249323281358361e-05, + "loss": 0.1091, + "step": 311810 + }, + { + "epoch": 0.7, + "learning_rate": 1.5248204738149035e-05, + "loss": 0.1156, + "step": 311820 + }, + { + "epoch": 0.7, + "learning_rate": 1.5247086194939712e-05, + "loss": 0.1122, + "step": 311830 + }, + { + "epoch": 0.7, + "learning_rate": 1.5245967651730386e-05, + "loss": 0.1096, + "step": 311840 + }, + { + "epoch": 0.7, + "learning_rate": 1.524484910852106e-05, + "loss": 0.1096, + "step": 311850 + }, + { + "epoch": 0.7, + "learning_rate": 1.524373056531174e-05, + "loss": 0.109, + "step": 311860 + }, + { + "epoch": 0.7, + "learning_rate": 1.5242612022102415e-05, + "loss": 0.1084, + "step": 311870 + }, + { + "epoch": 0.7, + "learning_rate": 1.524149347889309e-05, + "loss": 0.1068, + "step": 311880 + }, + { + "epoch": 0.7, + "learning_rate": 1.5240374935683766e-05, + "loss": 0.1081, + "step": 311890 + }, + { + "epoch": 0.7, + "learning_rate": 1.523925639247444e-05, + "loss": 0.1155, + "step": 311900 + }, + { + "epoch": 0.7, + "learning_rate": 1.5238137849265118e-05, + "loss": 0.1099, + "step": 311910 + }, + { + "epoch": 0.7, + "learning_rate": 1.5237019306055794e-05, + "loss": 0.109, + "step": 311920 + }, + { + "epoch": 0.7, + "learning_rate": 1.5235900762846469e-05, + "loss": 0.1104, + "step": 311930 + }, + { + "epoch": 0.7, + "learning_rate": 1.5234782219637145e-05, + "loss": 0.1112, + "step": 311940 + }, + { + "epoch": 0.7, + "learning_rate": 1.523366367642782e-05, + "loss": 0.1121, + "step": 311950 + }, + { + "epoch": 0.7, + "learning_rate": 1.5232545133218498e-05, + "loss": 0.106, + "step": 311960 + }, + { + "epoch": 0.7, + "learning_rate": 1.5231426590009174e-05, + "loss": 0.1107, + "step": 311970 + }, + { + "epoch": 0.7, + "learning_rate": 1.5230308046799848e-05, + "loss": 0.1041, + "step": 311980 + }, + { + "epoch": 0.7, + "learning_rate": 1.5229189503590525e-05, + "loss": 0.1111, + "step": 311990 + }, + { + "epoch": 0.7, + "learning_rate": 1.52280709603812e-05, + "loss": 0.1076, + "step": 312000 + }, + { + "epoch": 0.7, + "learning_rate": 1.5226952417171875e-05, + "loss": 0.1088, + "step": 312010 + }, + { + "epoch": 0.7, + "learning_rate": 1.5225833873962553e-05, + "loss": 0.1096, + "step": 312020 + }, + { + "epoch": 0.7, + "learning_rate": 1.5224715330753228e-05, + "loss": 0.1113, + "step": 312030 + }, + { + "epoch": 0.7, + "learning_rate": 1.5223596787543904e-05, + "loss": 0.1118, + "step": 312040 + }, + { + "epoch": 0.7, + "learning_rate": 1.5222478244334579e-05, + "loss": 0.1096, + "step": 312050 + }, + { + "epoch": 0.7, + "learning_rate": 1.5221359701125253e-05, + "loss": 0.1118, + "step": 312060 + }, + { + "epoch": 0.7, + "learning_rate": 1.5220241157915933e-05, + "loss": 0.1126, + "step": 312070 + }, + { + "epoch": 0.7, + "learning_rate": 1.5219122614706607e-05, + "loss": 0.1153, + "step": 312080 + }, + { + "epoch": 0.7, + "learning_rate": 1.5218004071497282e-05, + "loss": 0.1048, + "step": 312090 + }, + { + "epoch": 0.7, + "learning_rate": 1.5216885528287958e-05, + "loss": 0.1062, + "step": 312100 + }, + { + "epoch": 0.7, + "learning_rate": 1.5215766985078633e-05, + "loss": 0.1108, + "step": 312110 + }, + { + "epoch": 0.7, + "learning_rate": 1.521464844186931e-05, + "loss": 0.1085, + "step": 312120 + }, + { + "epoch": 0.7, + "learning_rate": 1.5213529898659987e-05, + "loss": 0.1083, + "step": 312130 + }, + { + "epoch": 0.7, + "learning_rate": 1.5212411355450661e-05, + "loss": 0.1085, + "step": 312140 + }, + { + "epoch": 0.7, + "learning_rate": 1.5211292812241338e-05, + "loss": 0.1112, + "step": 312150 + }, + { + "epoch": 0.7, + "learning_rate": 1.5210174269032012e-05, + "loss": 0.1077, + "step": 312160 + }, + { + "epoch": 0.7, + "learning_rate": 1.5209055725822688e-05, + "loss": 0.1072, + "step": 312170 + }, + { + "epoch": 0.7, + "learning_rate": 1.5207937182613366e-05, + "loss": 0.1105, + "step": 312180 + }, + { + "epoch": 0.7, + "learning_rate": 1.5206818639404041e-05, + "loss": 0.1123, + "step": 312190 + }, + { + "epoch": 0.7, + "learning_rate": 1.5205700096194717e-05, + "loss": 0.108, + "step": 312200 + }, + { + "epoch": 0.7, + "learning_rate": 1.5204581552985392e-05, + "loss": 0.1091, + "step": 312210 + }, + { + "epoch": 0.7, + "learning_rate": 1.5203463009776068e-05, + "loss": 0.1107, + "step": 312220 + }, + { + "epoch": 0.7, + "learning_rate": 1.5202344466566746e-05, + "loss": 0.1036, + "step": 312230 + }, + { + "epoch": 0.7, + "learning_rate": 1.520122592335742e-05, + "loss": 0.1069, + "step": 312240 + }, + { + "epoch": 0.7, + "learning_rate": 1.5200107380148097e-05, + "loss": 0.1115, + "step": 312250 + }, + { + "epoch": 0.7, + "learning_rate": 1.5198988836938771e-05, + "loss": 0.1112, + "step": 312260 + }, + { + "epoch": 0.7, + "learning_rate": 1.5197870293729447e-05, + "loss": 0.1062, + "step": 312270 + }, + { + "epoch": 0.7, + "learning_rate": 1.5196751750520125e-05, + "loss": 0.1125, + "step": 312280 + }, + { + "epoch": 0.7, + "learning_rate": 1.51956332073108e-05, + "loss": 0.1106, + "step": 312290 + }, + { + "epoch": 0.7, + "learning_rate": 1.5194514664101474e-05, + "loss": 0.11, + "step": 312300 + }, + { + "epoch": 0.7, + "learning_rate": 1.519339612089215e-05, + "loss": 0.1118, + "step": 312310 + }, + { + "epoch": 0.7, + "learning_rate": 1.5192277577682825e-05, + "loss": 0.1085, + "step": 312320 + }, + { + "epoch": 0.7, + "learning_rate": 1.5191159034473501e-05, + "loss": 0.1095, + "step": 312330 + }, + { + "epoch": 0.7, + "learning_rate": 1.519004049126418e-05, + "loss": 0.1137, + "step": 312340 + }, + { + "epoch": 0.7, + "learning_rate": 1.5188921948054854e-05, + "loss": 0.1128, + "step": 312350 + }, + { + "epoch": 0.7, + "learning_rate": 1.518780340484553e-05, + "loss": 0.1104, + "step": 312360 + }, + { + "epoch": 0.7, + "learning_rate": 1.5186684861636205e-05, + "loss": 0.1045, + "step": 312370 + }, + { + "epoch": 0.7, + "learning_rate": 1.518556631842688e-05, + "loss": 0.1067, + "step": 312380 + }, + { + "epoch": 0.7, + "learning_rate": 1.5184447775217559e-05, + "loss": 0.1089, + "step": 312390 + }, + { + "epoch": 0.7, + "learning_rate": 1.5183329232008233e-05, + "loss": 0.1118, + "step": 312400 + }, + { + "epoch": 0.7, + "learning_rate": 1.518221068879891e-05, + "loss": 0.1059, + "step": 312410 + }, + { + "epoch": 0.7, + "learning_rate": 1.5181092145589584e-05, + "loss": 0.1079, + "step": 312420 + }, + { + "epoch": 0.7, + "learning_rate": 1.517997360238026e-05, + "loss": 0.1093, + "step": 312430 + }, + { + "epoch": 0.7, + "learning_rate": 1.5178855059170938e-05, + "loss": 0.1091, + "step": 312440 + }, + { + "epoch": 0.7, + "learning_rate": 1.5177736515961613e-05, + "loss": 0.112, + "step": 312450 + }, + { + "epoch": 0.7, + "learning_rate": 1.5176617972752289e-05, + "loss": 0.1056, + "step": 312460 + }, + { + "epoch": 0.7, + "learning_rate": 1.5175499429542964e-05, + "loss": 0.1051, + "step": 312470 + }, + { + "epoch": 0.7, + "learning_rate": 1.517438088633364e-05, + "loss": 0.1084, + "step": 312480 + }, + { + "epoch": 0.7, + "learning_rate": 1.5173262343124314e-05, + "loss": 0.1073, + "step": 312490 + }, + { + "epoch": 0.7, + "learning_rate": 1.5172143799914992e-05, + "loss": 0.1068, + "step": 312500 + }, + { + "epoch": 0.7, + "learning_rate": 1.5171025256705668e-05, + "loss": 0.1056, + "step": 312510 + }, + { + "epoch": 0.7, + "learning_rate": 1.5169906713496343e-05, + "loss": 0.1092, + "step": 312520 + }, + { + "epoch": 0.7, + "learning_rate": 1.5168788170287018e-05, + "loss": 0.1093, + "step": 312530 + }, + { + "epoch": 0.7, + "learning_rate": 1.5167669627077694e-05, + "loss": 0.1062, + "step": 312540 + }, + { + "epoch": 0.7, + "learning_rate": 1.5166551083868372e-05, + "loss": 0.1072, + "step": 312550 + }, + { + "epoch": 0.7, + "learning_rate": 1.5165432540659046e-05, + "loss": 0.1089, + "step": 312560 + }, + { + "epoch": 0.7, + "learning_rate": 1.5164313997449722e-05, + "loss": 0.1091, + "step": 312570 + }, + { + "epoch": 0.7, + "learning_rate": 1.5163195454240397e-05, + "loss": 0.1114, + "step": 312580 + }, + { + "epoch": 0.7, + "learning_rate": 1.5162076911031073e-05, + "loss": 0.1074, + "step": 312590 + }, + { + "epoch": 0.7, + "learning_rate": 1.5160958367821751e-05, + "loss": 0.1114, + "step": 312600 + }, + { + "epoch": 0.7, + "learning_rate": 1.5159839824612426e-05, + "loss": 0.1106, + "step": 312610 + }, + { + "epoch": 0.7, + "learning_rate": 1.5158721281403102e-05, + "loss": 0.108, + "step": 312620 + }, + { + "epoch": 0.7, + "learning_rate": 1.5157602738193776e-05, + "loss": 0.1077, + "step": 312630 + }, + { + "epoch": 0.7, + "learning_rate": 1.5156484194984453e-05, + "loss": 0.112, + "step": 312640 + }, + { + "epoch": 0.7, + "learning_rate": 1.5155365651775127e-05, + "loss": 0.1073, + "step": 312650 + }, + { + "epoch": 0.7, + "learning_rate": 1.5154247108565805e-05, + "loss": 0.1082, + "step": 312660 + }, + { + "epoch": 0.7, + "learning_rate": 1.5153128565356481e-05, + "loss": 0.1044, + "step": 312670 + }, + { + "epoch": 0.7, + "learning_rate": 1.5152010022147156e-05, + "loss": 0.1075, + "step": 312680 + }, + { + "epoch": 0.7, + "learning_rate": 1.5150891478937832e-05, + "loss": 0.112, + "step": 312690 + }, + { + "epoch": 0.7, + "learning_rate": 1.5149772935728507e-05, + "loss": 0.1066, + "step": 312700 + }, + { + "epoch": 0.7, + "learning_rate": 1.5148654392519185e-05, + "loss": 0.1103, + "step": 312710 + }, + { + "epoch": 0.7, + "learning_rate": 1.5147535849309861e-05, + "loss": 0.1103, + "step": 312720 + }, + { + "epoch": 0.7, + "learning_rate": 1.5146417306100535e-05, + "loss": 0.1075, + "step": 312730 + }, + { + "epoch": 0.7, + "learning_rate": 1.514529876289121e-05, + "loss": 0.1077, + "step": 312740 + }, + { + "epoch": 0.7, + "learning_rate": 1.5144180219681886e-05, + "loss": 0.1131, + "step": 312750 + }, + { + "epoch": 0.7, + "learning_rate": 1.5143061676472564e-05, + "loss": 0.1094, + "step": 312760 + }, + { + "epoch": 0.7, + "learning_rate": 1.5141943133263239e-05, + "loss": 0.11, + "step": 312770 + }, + { + "epoch": 0.7, + "learning_rate": 1.5140824590053915e-05, + "loss": 0.1098, + "step": 312780 + }, + { + "epoch": 0.7, + "learning_rate": 1.513970604684459e-05, + "loss": 0.1095, + "step": 312790 + }, + { + "epoch": 0.7, + "learning_rate": 1.5138587503635266e-05, + "loss": 0.1118, + "step": 312800 + }, + { + "epoch": 0.7, + "learning_rate": 1.513746896042594e-05, + "loss": 0.1115, + "step": 312810 + }, + { + "epoch": 0.7, + "learning_rate": 1.5136350417216618e-05, + "loss": 0.1078, + "step": 312820 + }, + { + "epoch": 0.7, + "learning_rate": 1.5135231874007294e-05, + "loss": 0.109, + "step": 312830 + }, + { + "epoch": 0.7, + "learning_rate": 1.5134225185118903e-05, + "loss": 0.1107, + "step": 312840 + }, + { + "epoch": 0.7, + "learning_rate": 1.5133106641909578e-05, + "loss": 0.1078, + "step": 312850 + }, + { + "epoch": 0.7, + "learning_rate": 1.5131988098700254e-05, + "loss": 0.1115, + "step": 312860 + }, + { + "epoch": 0.7, + "learning_rate": 1.5130869555490928e-05, + "loss": 0.1119, + "step": 312870 + }, + { + "epoch": 0.7, + "learning_rate": 1.5129751012281603e-05, + "loss": 0.1096, + "step": 312880 + }, + { + "epoch": 0.7, + "learning_rate": 1.5128632469072283e-05, + "loss": 0.1114, + "step": 312890 + }, + { + "epoch": 0.7, + "learning_rate": 1.5127513925862957e-05, + "loss": 0.1079, + "step": 312900 + }, + { + "epoch": 0.7, + "learning_rate": 1.5126395382653632e-05, + "loss": 0.1055, + "step": 312910 + }, + { + "epoch": 0.7, + "learning_rate": 1.5125276839444308e-05, + "loss": 0.1096, + "step": 312920 + }, + { + "epoch": 0.7, + "learning_rate": 1.5124158296234982e-05, + "loss": 0.108, + "step": 312930 + }, + { + "epoch": 0.7, + "learning_rate": 1.512303975302566e-05, + "loss": 0.1096, + "step": 312940 + }, + { + "epoch": 0.7, + "learning_rate": 1.5121921209816337e-05, + "loss": 0.1091, + "step": 312950 + }, + { + "epoch": 0.7, + "learning_rate": 1.5120802666607011e-05, + "loss": 0.1085, + "step": 312960 + }, + { + "epoch": 0.7, + "learning_rate": 1.5119684123397687e-05, + "loss": 0.1075, + "step": 312970 + }, + { + "epoch": 0.7, + "learning_rate": 1.5118565580188362e-05, + "loss": 0.1094, + "step": 312980 + }, + { + "epoch": 0.7, + "learning_rate": 1.511744703697904e-05, + "loss": 0.1155, + "step": 312990 + }, + { + "epoch": 0.7, + "learning_rate": 1.5116328493769716e-05, + "loss": 0.1119, + "step": 313000 + }, + { + "epoch": 0.7, + "learning_rate": 1.511520995056039e-05, + "loss": 0.1027, + "step": 313010 + }, + { + "epoch": 0.7, + "learning_rate": 1.5114091407351067e-05, + "loss": 0.1114, + "step": 313020 + }, + { + "epoch": 0.7, + "learning_rate": 1.5112972864141741e-05, + "loss": 0.1137, + "step": 313030 + }, + { + "epoch": 0.7, + "learning_rate": 1.5111854320932418e-05, + "loss": 0.1135, + "step": 313040 + }, + { + "epoch": 0.7, + "learning_rate": 1.5110735777723096e-05, + "loss": 0.1102, + "step": 313050 + }, + { + "epoch": 0.7, + "learning_rate": 1.510961723451377e-05, + "loss": 0.1079, + "step": 313060 + }, + { + "epoch": 0.7, + "learning_rate": 1.5108498691304446e-05, + "loss": 0.1117, + "step": 313070 + }, + { + "epoch": 0.7, + "learning_rate": 1.5107380148095121e-05, + "loss": 0.1063, + "step": 313080 + }, + { + "epoch": 0.7, + "learning_rate": 1.5106261604885797e-05, + "loss": 0.1092, + "step": 313090 + }, + { + "epoch": 0.7, + "learning_rate": 1.5105143061676475e-05, + "loss": 0.1088, + "step": 313100 + }, + { + "epoch": 0.7, + "learning_rate": 1.510402451846715e-05, + "loss": 0.1134, + "step": 313110 + }, + { + "epoch": 0.7, + "learning_rate": 1.5102905975257826e-05, + "loss": 0.1061, + "step": 313120 + }, + { + "epoch": 0.7, + "learning_rate": 1.51017874320485e-05, + "loss": 0.106, + "step": 313130 + }, + { + "epoch": 0.7, + "learning_rate": 1.5100668888839175e-05, + "loss": 0.1056, + "step": 313140 + }, + { + "epoch": 0.7, + "learning_rate": 1.5099550345629855e-05, + "loss": 0.1023, + "step": 313150 + }, + { + "epoch": 0.7, + "learning_rate": 1.5098431802420529e-05, + "loss": 0.1091, + "step": 313160 + }, + { + "epoch": 0.7, + "learning_rate": 1.5097313259211204e-05, + "loss": 0.111, + "step": 313170 + }, + { + "epoch": 0.7, + "learning_rate": 1.509619471600188e-05, + "loss": 0.1076, + "step": 313180 + }, + { + "epoch": 0.7, + "learning_rate": 1.5095076172792554e-05, + "loss": 0.109, + "step": 313190 + }, + { + "epoch": 0.7, + "learning_rate": 1.509395762958323e-05, + "loss": 0.109, + "step": 313200 + }, + { + "epoch": 0.7, + "learning_rate": 1.5092839086373909e-05, + "loss": 0.1083, + "step": 313210 + }, + { + "epoch": 0.7, + "learning_rate": 1.5091720543164583e-05, + "loss": 0.105, + "step": 313220 + }, + { + "epoch": 0.7, + "learning_rate": 1.509060199995526e-05, + "loss": 0.1128, + "step": 313230 + }, + { + "epoch": 0.7, + "learning_rate": 1.5089483456745934e-05, + "loss": 0.1043, + "step": 313240 + }, + { + "epoch": 0.7, + "learning_rate": 1.508836491353661e-05, + "loss": 0.1063, + "step": 313250 + }, + { + "epoch": 0.7, + "learning_rate": 1.5087246370327288e-05, + "loss": 0.1129, + "step": 313260 + }, + { + "epoch": 0.7, + "learning_rate": 1.5086127827117963e-05, + "loss": 0.1097, + "step": 313270 + }, + { + "epoch": 0.7, + "learning_rate": 1.5085009283908639e-05, + "loss": 0.1097, + "step": 313280 + }, + { + "epoch": 0.7, + "learning_rate": 1.5083890740699313e-05, + "loss": 0.1044, + "step": 313290 + }, + { + "epoch": 0.7, + "learning_rate": 1.508277219748999e-05, + "loss": 0.11, + "step": 313300 + }, + { + "epoch": 0.7, + "learning_rate": 1.5081653654280668e-05, + "loss": 0.1114, + "step": 313310 + }, + { + "epoch": 0.7, + "learning_rate": 1.5080535111071342e-05, + "loss": 0.1096, + "step": 313320 + }, + { + "epoch": 0.7, + "learning_rate": 1.5079416567862018e-05, + "loss": 0.1113, + "step": 313330 + }, + { + "epoch": 0.7, + "learning_rate": 1.5078298024652693e-05, + "loss": 0.1089, + "step": 313340 + }, + { + "epoch": 0.7, + "learning_rate": 1.5077179481443367e-05, + "loss": 0.1104, + "step": 313350 + }, + { + "epoch": 0.7, + "learning_rate": 1.5076060938234044e-05, + "loss": 0.1098, + "step": 313360 + }, + { + "epoch": 0.7, + "learning_rate": 1.5074942395024722e-05, + "loss": 0.1043, + "step": 313370 + }, + { + "epoch": 0.7, + "learning_rate": 1.5073823851815396e-05, + "loss": 0.1056, + "step": 313380 + }, + { + "epoch": 0.7, + "learning_rate": 1.5072705308606072e-05, + "loss": 0.11, + "step": 313390 + }, + { + "epoch": 0.7, + "learning_rate": 1.5071586765396747e-05, + "loss": 0.1118, + "step": 313400 + }, + { + "epoch": 0.7, + "learning_rate": 1.5070468222187423e-05, + "loss": 0.1107, + "step": 313410 + }, + { + "epoch": 0.7, + "learning_rate": 1.5069349678978101e-05, + "loss": 0.1071, + "step": 313420 + }, + { + "epoch": 0.7, + "learning_rate": 1.5068231135768776e-05, + "loss": 0.1095, + "step": 313430 + }, + { + "epoch": 0.7, + "learning_rate": 1.5067112592559452e-05, + "loss": 0.1127, + "step": 313440 + }, + { + "epoch": 0.7, + "learning_rate": 1.5065994049350126e-05, + "loss": 0.1124, + "step": 313450 + }, + { + "epoch": 0.7, + "learning_rate": 1.5064875506140803e-05, + "loss": 0.112, + "step": 313460 + }, + { + "epoch": 0.7, + "learning_rate": 1.506375696293148e-05, + "loss": 0.1105, + "step": 313470 + }, + { + "epoch": 0.7, + "learning_rate": 1.5062638419722155e-05, + "loss": 0.1123, + "step": 313480 + }, + { + "epoch": 0.7, + "learning_rate": 1.5061519876512831e-05, + "loss": 0.1089, + "step": 313490 + }, + { + "epoch": 0.7, + "learning_rate": 1.5060401333303506e-05, + "loss": 0.1108, + "step": 313500 + }, + { + "epoch": 0.7, + "learning_rate": 1.5059282790094182e-05, + "loss": 0.1092, + "step": 313510 + }, + { + "epoch": 0.7, + "learning_rate": 1.5058164246884857e-05, + "loss": 0.1095, + "step": 313520 + }, + { + "epoch": 0.7, + "learning_rate": 1.5057045703675534e-05, + "loss": 0.1067, + "step": 313530 + }, + { + "epoch": 0.7, + "learning_rate": 1.505592716046621e-05, + "loss": 0.1045, + "step": 313540 + }, + { + "epoch": 0.7, + "learning_rate": 1.5054808617256885e-05, + "loss": 0.1061, + "step": 313550 + }, + { + "epoch": 0.7, + "learning_rate": 1.505369007404756e-05, + "loss": 0.1073, + "step": 313560 + }, + { + "epoch": 0.7, + "learning_rate": 1.5052571530838236e-05, + "loss": 0.1089, + "step": 313570 + }, + { + "epoch": 0.7, + "learning_rate": 1.5051452987628914e-05, + "loss": 0.1132, + "step": 313580 + }, + { + "epoch": 0.7, + "learning_rate": 1.5050334444419589e-05, + "loss": 0.1054, + "step": 313590 + }, + { + "epoch": 0.7, + "learning_rate": 1.5049215901210265e-05, + "loss": 0.1074, + "step": 313600 + }, + { + "epoch": 0.7, + "learning_rate": 1.504809735800094e-05, + "loss": 0.1117, + "step": 313610 + }, + { + "epoch": 0.7, + "learning_rate": 1.5046978814791616e-05, + "loss": 0.1136, + "step": 313620 + }, + { + "epoch": 0.7, + "learning_rate": 1.5045860271582293e-05, + "loss": 0.1133, + "step": 313630 + }, + { + "epoch": 0.7, + "learning_rate": 1.5044741728372968e-05, + "loss": 0.109, + "step": 313640 + }, + { + "epoch": 0.7, + "learning_rate": 1.5043623185163644e-05, + "loss": 0.1068, + "step": 313650 + }, + { + "epoch": 0.7, + "learning_rate": 1.5042504641954319e-05, + "loss": 0.1042, + "step": 313660 + }, + { + "epoch": 0.7, + "learning_rate": 1.5041386098744995e-05, + "loss": 0.1102, + "step": 313670 + }, + { + "epoch": 0.7, + "learning_rate": 1.504026755553567e-05, + "loss": 0.1044, + "step": 313680 + }, + { + "epoch": 0.7, + "learning_rate": 1.5039149012326347e-05, + "loss": 0.1104, + "step": 313690 + }, + { + "epoch": 0.7, + "learning_rate": 1.5038030469117024e-05, + "loss": 0.1113, + "step": 313700 + }, + { + "epoch": 0.7, + "learning_rate": 1.5036911925907698e-05, + "loss": 0.1107, + "step": 313710 + }, + { + "epoch": 0.7, + "learning_rate": 1.5035793382698374e-05, + "loss": 0.108, + "step": 313720 + }, + { + "epoch": 0.7, + "learning_rate": 1.5034674839489049e-05, + "loss": 0.1075, + "step": 313730 + }, + { + "epoch": 0.7, + "learning_rate": 1.5033556296279727e-05, + "loss": 0.1065, + "step": 313740 + }, + { + "epoch": 0.7, + "learning_rate": 1.5032437753070403e-05, + "loss": 0.1085, + "step": 313750 + }, + { + "epoch": 0.7, + "learning_rate": 1.5031319209861078e-05, + "loss": 0.1023, + "step": 313760 + }, + { + "epoch": 0.7, + "learning_rate": 1.5030200666651752e-05, + "loss": 0.1123, + "step": 313770 + }, + { + "epoch": 0.7, + "learning_rate": 1.5029082123442428e-05, + "loss": 0.1112, + "step": 313780 + }, + { + "epoch": 0.7, + "learning_rate": 1.5027963580233106e-05, + "loss": 0.1117, + "step": 313790 + }, + { + "epoch": 0.7, + "learning_rate": 1.5026845037023781e-05, + "loss": 0.1099, + "step": 313800 + }, + { + "epoch": 0.7, + "learning_rate": 1.5025726493814457e-05, + "loss": 0.1088, + "step": 313810 + }, + { + "epoch": 0.7, + "learning_rate": 1.5024607950605132e-05, + "loss": 0.1097, + "step": 313820 + }, + { + "epoch": 0.7, + "learning_rate": 1.5023489407395808e-05, + "loss": 0.1135, + "step": 313830 + }, + { + "epoch": 0.7, + "learning_rate": 1.5022370864186482e-05, + "loss": 0.1083, + "step": 313840 + }, + { + "epoch": 0.7, + "learning_rate": 1.502125232097716e-05, + "loss": 0.1092, + "step": 313850 + }, + { + "epoch": 0.7, + "learning_rate": 1.5020133777767837e-05, + "loss": 0.1099, + "step": 313860 + }, + { + "epoch": 0.7, + "learning_rate": 1.5019015234558511e-05, + "loss": 0.1092, + "step": 313870 + }, + { + "epoch": 0.7, + "learning_rate": 1.5017896691349187e-05, + "loss": 0.1086, + "step": 313880 + }, + { + "epoch": 0.7, + "learning_rate": 1.5016778148139862e-05, + "loss": 0.1146, + "step": 313890 + }, + { + "epoch": 0.7, + "learning_rate": 1.501565960493054e-05, + "loss": 0.1092, + "step": 313900 + }, + { + "epoch": 0.7, + "learning_rate": 1.5014541061721216e-05, + "loss": 0.111, + "step": 313910 + }, + { + "epoch": 0.7, + "learning_rate": 1.501342251851189e-05, + "loss": 0.1098, + "step": 313920 + }, + { + "epoch": 0.7, + "learning_rate": 1.5012303975302567e-05, + "loss": 0.1096, + "step": 313930 + }, + { + "epoch": 0.7, + "learning_rate": 1.5011185432093241e-05, + "loss": 0.1085, + "step": 313940 + }, + { + "epoch": 0.7, + "learning_rate": 1.501006688888392e-05, + "loss": 0.1075, + "step": 313950 + }, + { + "epoch": 0.7, + "learning_rate": 1.5008948345674596e-05, + "loss": 0.1045, + "step": 313960 + }, + { + "epoch": 0.7, + "learning_rate": 1.500782980246527e-05, + "loss": 0.1064, + "step": 313970 + }, + { + "epoch": 0.7, + "learning_rate": 1.5006711259255946e-05, + "loss": 0.1093, + "step": 313980 + }, + { + "epoch": 0.7, + "learning_rate": 1.5005592716046621e-05, + "loss": 0.1106, + "step": 313990 + }, + { + "epoch": 0.7, + "learning_rate": 1.5004474172837295e-05, + "loss": 0.108, + "step": 314000 + }, + { + "epoch": 0.7, + "learning_rate": 1.5003355629627975e-05, + "loss": 0.1097, + "step": 314010 + }, + { + "epoch": 0.7, + "learning_rate": 1.500223708641865e-05, + "loss": 0.1082, + "step": 314020 + }, + { + "epoch": 0.7, + "learning_rate": 1.5001118543209324e-05, + "loss": 0.1055, + "step": 314030 + }, + { + "epoch": 0.7, + "learning_rate": 1.5e-05, + "loss": 0.109, + "step": 314040 + }, + { + "epoch": 0.7, + "learning_rate": 1.4998881456790675e-05, + "loss": 0.1058, + "step": 314050 + }, + { + "epoch": 0.7, + "learning_rate": 1.4997762913581353e-05, + "loss": 0.1098, + "step": 314060 + }, + { + "epoch": 0.7, + "learning_rate": 1.4996644370372029e-05, + "loss": 0.1089, + "step": 314070 + }, + { + "epoch": 0.7, + "learning_rate": 1.4995525827162704e-05, + "loss": 0.1083, + "step": 314080 + }, + { + "epoch": 0.7, + "learning_rate": 1.499440728395338e-05, + "loss": 0.1063, + "step": 314090 + }, + { + "epoch": 0.7, + "learning_rate": 1.4993288740744054e-05, + "loss": 0.1076, + "step": 314100 + }, + { + "epoch": 0.7, + "learning_rate": 1.4992170197534732e-05, + "loss": 0.1101, + "step": 314110 + }, + { + "epoch": 0.7, + "learning_rate": 1.4991051654325409e-05, + "loss": 0.1077, + "step": 314120 + }, + { + "epoch": 0.7, + "learning_rate": 1.4989933111116083e-05, + "loss": 0.1034, + "step": 314130 + }, + { + "epoch": 0.7, + "learning_rate": 1.498881456790676e-05, + "loss": 0.114, + "step": 314140 + }, + { + "epoch": 0.7, + "learning_rate": 1.4987696024697434e-05, + "loss": 0.1119, + "step": 314150 + }, + { + "epoch": 0.7, + "learning_rate": 1.498657748148811e-05, + "loss": 0.1131, + "step": 314160 + }, + { + "epoch": 0.7, + "learning_rate": 1.4985458938278788e-05, + "loss": 0.1047, + "step": 314170 + }, + { + "epoch": 0.7, + "learning_rate": 1.4984340395069463e-05, + "loss": 0.1092, + "step": 314180 + }, + { + "epoch": 0.7, + "learning_rate": 1.4983221851860139e-05, + "loss": 0.11, + "step": 314190 + }, + { + "epoch": 0.7, + "learning_rate": 1.4982103308650813e-05, + "loss": 0.1107, + "step": 314200 + }, + { + "epoch": 0.7, + "learning_rate": 1.4980984765441488e-05, + "loss": 0.1125, + "step": 314210 + }, + { + "epoch": 0.7, + "learning_rate": 1.4979866222232168e-05, + "loss": 0.1079, + "step": 314220 + }, + { + "epoch": 0.7, + "learning_rate": 1.4978747679022842e-05, + "loss": 0.1057, + "step": 314230 + }, + { + "epoch": 0.7, + "learning_rate": 1.4977629135813517e-05, + "loss": 0.1106, + "step": 314240 + }, + { + "epoch": 0.7, + "learning_rate": 1.4976510592604193e-05, + "loss": 0.111, + "step": 314250 + }, + { + "epoch": 0.7, + "learning_rate": 1.4975392049394867e-05, + "loss": 0.1075, + "step": 314260 + }, + { + "epoch": 0.7, + "learning_rate": 1.4974273506185545e-05, + "loss": 0.1069, + "step": 314270 + }, + { + "epoch": 0.7, + "learning_rate": 1.4973154962976222e-05, + "loss": 0.1084, + "step": 314280 + }, + { + "epoch": 0.7, + "learning_rate": 1.4972036419766896e-05, + "loss": 0.1063, + "step": 314290 + }, + { + "epoch": 0.7, + "learning_rate": 1.4970917876557572e-05, + "loss": 0.1118, + "step": 314300 + }, + { + "epoch": 0.7, + "learning_rate": 1.4969799333348247e-05, + "loss": 0.1099, + "step": 314310 + }, + { + "epoch": 0.7, + "learning_rate": 1.4968680790138923e-05, + "loss": 0.1109, + "step": 314320 + }, + { + "epoch": 0.7, + "learning_rate": 1.4967562246929601e-05, + "loss": 0.1065, + "step": 314330 + }, + { + "epoch": 0.7, + "learning_rate": 1.4966443703720276e-05, + "loss": 0.1123, + "step": 314340 + }, + { + "epoch": 0.7, + "learning_rate": 1.4965325160510952e-05, + "loss": 0.108, + "step": 314350 + }, + { + "epoch": 0.7, + "learning_rate": 1.4964206617301626e-05, + "loss": 0.109, + "step": 314360 + }, + { + "epoch": 0.7, + "learning_rate": 1.4963088074092303e-05, + "loss": 0.1122, + "step": 314370 + }, + { + "epoch": 0.7, + "learning_rate": 1.496196953088298e-05, + "loss": 0.1082, + "step": 314380 + }, + { + "epoch": 0.7, + "learning_rate": 1.4960850987673655e-05, + "loss": 0.1108, + "step": 314390 + }, + { + "epoch": 0.7, + "learning_rate": 1.4959732444464331e-05, + "loss": 0.1084, + "step": 314400 + }, + { + "epoch": 0.7, + "learning_rate": 1.4958613901255006e-05, + "loss": 0.1116, + "step": 314410 + }, + { + "epoch": 0.7, + "learning_rate": 1.495749535804568e-05, + "loss": 0.1083, + "step": 314420 + }, + { + "epoch": 0.7, + "learning_rate": 1.495637681483636e-05, + "loss": 0.1104, + "step": 314430 + }, + { + "epoch": 0.7, + "learning_rate": 1.4955258271627034e-05, + "loss": 0.1136, + "step": 314440 + }, + { + "epoch": 0.7, + "learning_rate": 1.4954139728417709e-05, + "loss": 0.1045, + "step": 314450 + }, + { + "epoch": 0.7, + "learning_rate": 1.4953021185208385e-05, + "loss": 0.1101, + "step": 314460 + }, + { + "epoch": 0.7, + "learning_rate": 1.495190264199906e-05, + "loss": 0.108, + "step": 314470 + }, + { + "epoch": 0.7, + "learning_rate": 1.4950784098789736e-05, + "loss": 0.1083, + "step": 314480 + }, + { + "epoch": 0.7, + "learning_rate": 1.4949665555580414e-05, + "loss": 0.1057, + "step": 314490 + }, + { + "epoch": 0.7, + "learning_rate": 1.4948547012371088e-05, + "loss": 0.1134, + "step": 314500 + }, + { + "epoch": 0.7, + "learning_rate": 1.4947428469161765e-05, + "loss": 0.1098, + "step": 314510 + }, + { + "epoch": 0.7, + "learning_rate": 1.494630992595244e-05, + "loss": 0.1038, + "step": 314520 + }, + { + "epoch": 0.7, + "learning_rate": 1.4945191382743115e-05, + "loss": 0.1116, + "step": 314530 + }, + { + "epoch": 0.7, + "learning_rate": 1.4944072839533793e-05, + "loss": 0.1087, + "step": 314540 + }, + { + "epoch": 0.7, + "learning_rate": 1.4942954296324468e-05, + "loss": 0.1123, + "step": 314550 + }, + { + "epoch": 0.7, + "learning_rate": 1.4941835753115144e-05, + "loss": 0.1085, + "step": 314560 + }, + { + "epoch": 0.7, + "learning_rate": 1.4940717209905819e-05, + "loss": 0.109, + "step": 314570 + }, + { + "epoch": 0.7, + "learning_rate": 1.4939598666696495e-05, + "loss": 0.1108, + "step": 314580 + }, + { + "epoch": 0.7, + "learning_rate": 1.4938480123487173e-05, + "loss": 0.1062, + "step": 314590 + }, + { + "epoch": 0.7, + "learning_rate": 1.4937361580277847e-05, + "loss": 0.1047, + "step": 314600 + }, + { + "epoch": 0.7, + "learning_rate": 1.4936243037068524e-05, + "loss": 0.1078, + "step": 314610 + }, + { + "epoch": 0.7, + "learning_rate": 1.4935124493859198e-05, + "loss": 0.1098, + "step": 314620 + }, + { + "epoch": 0.7, + "learning_rate": 1.4934005950649874e-05, + "loss": 0.1095, + "step": 314630 + }, + { + "epoch": 0.7, + "learning_rate": 1.4932887407440549e-05, + "loss": 0.1047, + "step": 314640 + }, + { + "epoch": 0.7, + "learning_rate": 1.4931768864231227e-05, + "loss": 0.1064, + "step": 314650 + }, + { + "epoch": 0.7, + "learning_rate": 1.4930650321021903e-05, + "loss": 0.112, + "step": 314660 + }, + { + "epoch": 0.7, + "learning_rate": 1.4929531777812578e-05, + "loss": 0.1087, + "step": 314670 + }, + { + "epoch": 0.7, + "learning_rate": 1.4928413234603252e-05, + "loss": 0.108, + "step": 314680 + }, + { + "epoch": 0.7, + "learning_rate": 1.4927294691393928e-05, + "loss": 0.112, + "step": 314690 + }, + { + "epoch": 0.7, + "learning_rate": 1.4926176148184606e-05, + "loss": 0.1117, + "step": 314700 + }, + { + "epoch": 0.7, + "learning_rate": 1.4925057604975281e-05, + "loss": 0.1068, + "step": 314710 + }, + { + "epoch": 0.7, + "learning_rate": 1.4923939061765957e-05, + "loss": 0.1058, + "step": 314720 + }, + { + "epoch": 0.7, + "learning_rate": 1.4922820518556632e-05, + "loss": 0.1069, + "step": 314730 + }, + { + "epoch": 0.7, + "learning_rate": 1.4921701975347308e-05, + "loss": 0.1111, + "step": 314740 + }, + { + "epoch": 0.7, + "learning_rate": 1.4920583432137982e-05, + "loss": 0.1093, + "step": 314750 + }, + { + "epoch": 0.7, + "learning_rate": 1.491946488892866e-05, + "loss": 0.1138, + "step": 314760 + }, + { + "epoch": 0.7, + "learning_rate": 1.4918346345719337e-05, + "loss": 0.1034, + "step": 314770 + }, + { + "epoch": 0.7, + "learning_rate": 1.4917227802510011e-05, + "loss": 0.1124, + "step": 314780 + }, + { + "epoch": 0.7, + "learning_rate": 1.4916109259300687e-05, + "loss": 0.1073, + "step": 314790 + }, + { + "epoch": 0.7, + "learning_rate": 1.4914990716091362e-05, + "loss": 0.1054, + "step": 314800 + }, + { + "epoch": 0.7, + "learning_rate": 1.491387217288204e-05, + "loss": 0.11, + "step": 314810 + }, + { + "epoch": 0.7, + "learning_rate": 1.4912753629672716e-05, + "loss": 0.1056, + "step": 314820 + }, + { + "epoch": 0.7, + "learning_rate": 1.491163508646339e-05, + "loss": 0.1089, + "step": 314830 + }, + { + "epoch": 0.7, + "learning_rate": 1.4910516543254067e-05, + "loss": 0.1085, + "step": 314840 + }, + { + "epoch": 0.7, + "learning_rate": 1.4909398000044741e-05, + "loss": 0.1144, + "step": 314850 + }, + { + "epoch": 0.7, + "learning_rate": 1.490839131115635e-05, + "loss": 0.1092, + "step": 314860 + }, + { + "epoch": 0.7, + "learning_rate": 1.4907272767947025e-05, + "loss": 0.1121, + "step": 314870 + }, + { + "epoch": 0.7, + "learning_rate": 1.4906154224737703e-05, + "loss": 0.1088, + "step": 314880 + }, + { + "epoch": 0.7, + "learning_rate": 1.4905035681528379e-05, + "loss": 0.1078, + "step": 314890 + }, + { + "epoch": 0.7, + "learning_rate": 1.4903917138319053e-05, + "loss": 0.1114, + "step": 314900 + }, + { + "epoch": 0.7, + "learning_rate": 1.490279859510973e-05, + "loss": 0.111, + "step": 314910 + }, + { + "epoch": 0.7, + "learning_rate": 1.4901680051900404e-05, + "loss": 0.108, + "step": 314920 + }, + { + "epoch": 0.7, + "learning_rate": 1.4900561508691082e-05, + "loss": 0.1093, + "step": 314930 + }, + { + "epoch": 0.7, + "learning_rate": 1.4899442965481758e-05, + "loss": 0.1038, + "step": 314940 + }, + { + "epoch": 0.7, + "learning_rate": 1.4898324422272433e-05, + "loss": 0.1108, + "step": 314950 + }, + { + "epoch": 0.7, + "learning_rate": 1.4897205879063109e-05, + "loss": 0.1107, + "step": 314960 + }, + { + "epoch": 0.7, + "learning_rate": 1.4896087335853784e-05, + "loss": 0.113, + "step": 314970 + }, + { + "epoch": 0.7, + "learning_rate": 1.489496879264446e-05, + "loss": 0.1102, + "step": 314980 + }, + { + "epoch": 0.7, + "learning_rate": 1.4893850249435138e-05, + "loss": 0.1105, + "step": 314990 + }, + { + "epoch": 0.7, + "learning_rate": 1.4892731706225812e-05, + "loss": 0.1093, + "step": 315000 + }, + { + "epoch": 0.7, + "learning_rate": 1.4891613163016489e-05, + "loss": 0.1054, + "step": 315010 + }, + { + "epoch": 0.7, + "learning_rate": 1.4890494619807163e-05, + "loss": 0.1104, + "step": 315020 + }, + { + "epoch": 0.7, + "learning_rate": 1.4889376076597838e-05, + "loss": 0.108, + "step": 315030 + }, + { + "epoch": 0.7, + "learning_rate": 1.4888257533388517e-05, + "loss": 0.1036, + "step": 315040 + }, + { + "epoch": 0.7, + "learning_rate": 1.4887138990179192e-05, + "loss": 0.114, + "step": 315050 + }, + { + "epoch": 0.7, + "learning_rate": 1.4886020446969866e-05, + "loss": 0.1109, + "step": 315060 + }, + { + "epoch": 0.7, + "learning_rate": 1.4884901903760543e-05, + "loss": 0.1041, + "step": 315070 + }, + { + "epoch": 0.7, + "learning_rate": 1.4883783360551217e-05, + "loss": 0.1072, + "step": 315080 + }, + { + "epoch": 0.7, + "learning_rate": 1.4882664817341895e-05, + "loss": 0.1125, + "step": 315090 + }, + { + "epoch": 0.7, + "learning_rate": 1.4881546274132571e-05, + "loss": 0.1057, + "step": 315100 + }, + { + "epoch": 0.7, + "learning_rate": 1.4880427730923246e-05, + "loss": 0.108, + "step": 315110 + }, + { + "epoch": 0.7, + "learning_rate": 1.4879309187713922e-05, + "loss": 0.1146, + "step": 315120 + }, + { + "epoch": 0.7, + "learning_rate": 1.4878190644504597e-05, + "loss": 0.1075, + "step": 315130 + }, + { + "epoch": 0.7, + "learning_rate": 1.4877072101295273e-05, + "loss": 0.1122, + "step": 315140 + }, + { + "epoch": 0.7, + "learning_rate": 1.487595355808595e-05, + "loss": 0.1126, + "step": 315150 + }, + { + "epoch": 0.7, + "learning_rate": 1.4874835014876625e-05, + "loss": 0.1101, + "step": 315160 + }, + { + "epoch": 0.7, + "learning_rate": 1.4873716471667302e-05, + "loss": 0.11, + "step": 315170 + }, + { + "epoch": 0.7, + "learning_rate": 1.4872597928457976e-05, + "loss": 0.1115, + "step": 315180 + }, + { + "epoch": 0.7, + "learning_rate": 1.4871479385248652e-05, + "loss": 0.1105, + "step": 315190 + }, + { + "epoch": 0.7, + "learning_rate": 1.487036084203933e-05, + "loss": 0.1067, + "step": 315200 + }, + { + "epoch": 0.7, + "learning_rate": 1.4869242298830005e-05, + "loss": 0.1069, + "step": 315210 + }, + { + "epoch": 0.7, + "learning_rate": 1.4868123755620681e-05, + "loss": 0.1063, + "step": 315220 + }, + { + "epoch": 0.7, + "learning_rate": 1.4867005212411356e-05, + "loss": 0.1077, + "step": 315230 + }, + { + "epoch": 0.7, + "learning_rate": 1.4865886669202032e-05, + "loss": 0.1121, + "step": 315240 + }, + { + "epoch": 0.7, + "learning_rate": 1.486476812599271e-05, + "loss": 0.1105, + "step": 315250 + }, + { + "epoch": 0.7, + "learning_rate": 1.4863649582783384e-05, + "loss": 0.107, + "step": 315260 + }, + { + "epoch": 0.7, + "learning_rate": 1.4862531039574059e-05, + "loss": 0.1089, + "step": 315270 + }, + { + "epoch": 0.7, + "learning_rate": 1.4861412496364735e-05, + "loss": 0.1086, + "step": 315280 + }, + { + "epoch": 0.7, + "learning_rate": 1.486029395315541e-05, + "loss": 0.1066, + "step": 315290 + }, + { + "epoch": 0.7, + "learning_rate": 1.4859175409946086e-05, + "loss": 0.1104, + "step": 315300 + }, + { + "epoch": 0.7, + "learning_rate": 1.4858056866736764e-05, + "loss": 0.1113, + "step": 315310 + }, + { + "epoch": 0.7, + "learning_rate": 1.4856938323527438e-05, + "loss": 0.1134, + "step": 315320 + }, + { + "epoch": 0.7, + "learning_rate": 1.4855819780318115e-05, + "loss": 0.109, + "step": 315330 + }, + { + "epoch": 0.7, + "learning_rate": 1.4854701237108789e-05, + "loss": 0.1074, + "step": 315340 + }, + { + "epoch": 0.7, + "learning_rate": 1.4853582693899465e-05, + "loss": 0.1111, + "step": 315350 + }, + { + "epoch": 0.7, + "learning_rate": 1.4852464150690143e-05, + "loss": 0.1104, + "step": 315360 + }, + { + "epoch": 0.7, + "learning_rate": 1.4851345607480818e-05, + "loss": 0.108, + "step": 315370 + }, + { + "epoch": 0.7, + "learning_rate": 1.4850227064271494e-05, + "loss": 0.1136, + "step": 315380 + }, + { + "epoch": 0.7, + "learning_rate": 1.4849108521062169e-05, + "loss": 0.1079, + "step": 315390 + }, + { + "epoch": 0.7, + "learning_rate": 1.4847989977852845e-05, + "loss": 0.1091, + "step": 315400 + }, + { + "epoch": 0.7, + "learning_rate": 1.4846871434643523e-05, + "loss": 0.1084, + "step": 315410 + }, + { + "epoch": 0.7, + "learning_rate": 1.4845752891434197e-05, + "loss": 0.11, + "step": 315420 + }, + { + "epoch": 0.7, + "learning_rate": 1.4844634348224873e-05, + "loss": 0.1086, + "step": 315430 + }, + { + "epoch": 0.7, + "learning_rate": 1.4843515805015548e-05, + "loss": 0.1091, + "step": 315440 + }, + { + "epoch": 0.7, + "learning_rate": 1.4842397261806224e-05, + "loss": 0.1055, + "step": 315450 + }, + { + "epoch": 0.7, + "learning_rate": 1.4841278718596899e-05, + "loss": 0.107, + "step": 315460 + }, + { + "epoch": 0.7, + "learning_rate": 1.4840160175387577e-05, + "loss": 0.106, + "step": 315470 + }, + { + "epoch": 0.7, + "learning_rate": 1.4839041632178253e-05, + "loss": 0.1098, + "step": 315480 + }, + { + "epoch": 0.7, + "learning_rate": 1.4837923088968928e-05, + "loss": 0.1078, + "step": 315490 + }, + { + "epoch": 0.7, + "learning_rate": 1.4836804545759602e-05, + "loss": 0.1063, + "step": 315500 + }, + { + "epoch": 0.7, + "learning_rate": 1.4835686002550278e-05, + "loss": 0.1064, + "step": 315510 + }, + { + "epoch": 0.7, + "learning_rate": 1.4834567459340956e-05, + "loss": 0.1113, + "step": 315520 + }, + { + "epoch": 0.7, + "learning_rate": 1.483344891613163e-05, + "loss": 0.1153, + "step": 315530 + }, + { + "epoch": 0.7, + "learning_rate": 1.4832330372922307e-05, + "loss": 0.1111, + "step": 315540 + }, + { + "epoch": 0.7, + "learning_rate": 1.4831211829712982e-05, + "loss": 0.1119, + "step": 315550 + }, + { + "epoch": 0.7, + "learning_rate": 1.4830093286503658e-05, + "loss": 0.111, + "step": 315560 + }, + { + "epoch": 0.7, + "learning_rate": 1.4828974743294336e-05, + "loss": 0.1076, + "step": 315570 + }, + { + "epoch": 0.7, + "learning_rate": 1.482785620008501e-05, + "loss": 0.108, + "step": 315580 + }, + { + "epoch": 0.7, + "learning_rate": 1.4826737656875686e-05, + "loss": 0.1108, + "step": 315590 + }, + { + "epoch": 0.7, + "learning_rate": 1.4825619113666361e-05, + "loss": 0.1061, + "step": 315600 + }, + { + "epoch": 0.7, + "learning_rate": 1.4824500570457037e-05, + "loss": 0.1083, + "step": 315610 + }, + { + "epoch": 0.7, + "learning_rate": 1.4823382027247712e-05, + "loss": 0.1091, + "step": 315620 + }, + { + "epoch": 0.7, + "learning_rate": 1.482226348403839e-05, + "loss": 0.1094, + "step": 315630 + }, + { + "epoch": 0.7, + "learning_rate": 1.4821144940829066e-05, + "loss": 0.1139, + "step": 315640 + }, + { + "epoch": 0.7, + "learning_rate": 1.482002639761974e-05, + "loss": 0.1083, + "step": 315650 + }, + { + "epoch": 0.7, + "learning_rate": 1.4818907854410417e-05, + "loss": 0.1092, + "step": 315660 + }, + { + "epoch": 0.7, + "learning_rate": 1.4817789311201091e-05, + "loss": 0.108, + "step": 315670 + }, + { + "epoch": 0.7, + "learning_rate": 1.481667076799177e-05, + "loss": 0.1064, + "step": 315680 + }, + { + "epoch": 0.7, + "learning_rate": 1.4815552224782445e-05, + "loss": 0.1081, + "step": 315690 + }, + { + "epoch": 0.7, + "learning_rate": 1.481443368157312e-05, + "loss": 0.1098, + "step": 315700 + }, + { + "epoch": 0.7, + "learning_rate": 1.4813315138363794e-05, + "loss": 0.1111, + "step": 315710 + }, + { + "epoch": 0.7, + "learning_rate": 1.481219659515447e-05, + "loss": 0.1121, + "step": 315720 + }, + { + "epoch": 0.7, + "learning_rate": 1.4811078051945149e-05, + "loss": 0.1095, + "step": 315730 + }, + { + "epoch": 0.7, + "learning_rate": 1.4809959508735823e-05, + "loss": 0.1097, + "step": 315740 + }, + { + "epoch": 0.7, + "learning_rate": 1.48088409655265e-05, + "loss": 0.1087, + "step": 315750 + }, + { + "epoch": 0.7, + "learning_rate": 1.4807722422317174e-05, + "loss": 0.111, + "step": 315760 + }, + { + "epoch": 0.7, + "learning_rate": 1.480660387910785e-05, + "loss": 0.1089, + "step": 315770 + }, + { + "epoch": 0.7, + "learning_rate": 1.4805485335898525e-05, + "loss": 0.1095, + "step": 315780 + }, + { + "epoch": 0.7, + "learning_rate": 1.4804366792689203e-05, + "loss": 0.1131, + "step": 315790 + }, + { + "epoch": 0.7, + "learning_rate": 1.4803248249479879e-05, + "loss": 0.1109, + "step": 315800 + }, + { + "epoch": 0.7, + "learning_rate": 1.4802129706270553e-05, + "loss": 0.113, + "step": 315810 + }, + { + "epoch": 0.7, + "learning_rate": 1.480101116306123e-05, + "loss": 0.1085, + "step": 315820 + }, + { + "epoch": 0.7, + "learning_rate": 1.4799892619851904e-05, + "loss": 0.1066, + "step": 315830 + }, + { + "epoch": 0.7, + "learning_rate": 1.4798774076642582e-05, + "loss": 0.1081, + "step": 315840 + }, + { + "epoch": 0.71, + "learning_rate": 1.4797655533433258e-05, + "loss": 0.1094, + "step": 315850 + }, + { + "epoch": 0.71, + "learning_rate": 1.4796536990223933e-05, + "loss": 0.1098, + "step": 315860 + }, + { + "epoch": 0.71, + "learning_rate": 1.4795418447014609e-05, + "loss": 0.1057, + "step": 315870 + }, + { + "epoch": 0.71, + "learning_rate": 1.4794299903805284e-05, + "loss": 0.1057, + "step": 315880 + }, + { + "epoch": 0.71, + "learning_rate": 1.4793181360595962e-05, + "loss": 0.1101, + "step": 315890 + }, + { + "epoch": 0.71, + "learning_rate": 1.4792062817386638e-05, + "loss": 0.11, + "step": 315900 + }, + { + "epoch": 0.71, + "learning_rate": 1.4790944274177312e-05, + "loss": 0.1094, + "step": 315910 + }, + { + "epoch": 0.71, + "learning_rate": 1.4789825730967987e-05, + "loss": 0.102, + "step": 315920 + }, + { + "epoch": 0.71, + "learning_rate": 1.4788707187758663e-05, + "loss": 0.1088, + "step": 315930 + }, + { + "epoch": 0.71, + "learning_rate": 1.4787588644549338e-05, + "loss": 0.107, + "step": 315940 + }, + { + "epoch": 0.71, + "learning_rate": 1.4786470101340016e-05, + "loss": 0.1118, + "step": 315950 + }, + { + "epoch": 0.71, + "learning_rate": 1.4785351558130692e-05, + "loss": 0.108, + "step": 315960 + }, + { + "epoch": 0.71, + "learning_rate": 1.4784233014921366e-05, + "loss": 0.1087, + "step": 315970 + }, + { + "epoch": 0.71, + "learning_rate": 1.4783114471712043e-05, + "loss": 0.108, + "step": 315980 + }, + { + "epoch": 0.71, + "learning_rate": 1.4781995928502717e-05, + "loss": 0.1073, + "step": 315990 + }, + { + "epoch": 0.71, + "learning_rate": 1.4780877385293395e-05, + "loss": 0.1067, + "step": 316000 + }, + { + "epoch": 0.71, + "learning_rate": 1.4779758842084071e-05, + "loss": 0.1114, + "step": 316010 + }, + { + "epoch": 0.71, + "learning_rate": 1.4778640298874746e-05, + "loss": 0.1056, + "step": 316020 + }, + { + "epoch": 0.71, + "learning_rate": 1.4777521755665422e-05, + "loss": 0.108, + "step": 316030 + }, + { + "epoch": 0.71, + "learning_rate": 1.4776403212456097e-05, + "loss": 0.1129, + "step": 316040 + }, + { + "epoch": 0.71, + "learning_rate": 1.4775284669246775e-05, + "loss": 0.1068, + "step": 316050 + }, + { + "epoch": 0.71, + "learning_rate": 1.477416612603745e-05, + "loss": 0.1079, + "step": 316060 + }, + { + "epoch": 0.71, + "learning_rate": 1.4773047582828125e-05, + "loss": 0.1082, + "step": 316070 + }, + { + "epoch": 0.71, + "learning_rate": 1.4771929039618802e-05, + "loss": 0.1021, + "step": 316080 + }, + { + "epoch": 0.71, + "learning_rate": 1.4770810496409476e-05, + "loss": 0.1072, + "step": 316090 + }, + { + "epoch": 0.71, + "learning_rate": 1.4769691953200152e-05, + "loss": 0.1098, + "step": 316100 + }, + { + "epoch": 0.71, + "learning_rate": 1.476857340999083e-05, + "loss": 0.1116, + "step": 316110 + }, + { + "epoch": 0.71, + "learning_rate": 1.4767454866781505e-05, + "loss": 0.108, + "step": 316120 + }, + { + "epoch": 0.71, + "learning_rate": 1.4766336323572181e-05, + "loss": 0.1096, + "step": 316130 + }, + { + "epoch": 0.71, + "learning_rate": 1.4765217780362856e-05, + "loss": 0.109, + "step": 316140 + }, + { + "epoch": 0.71, + "learning_rate": 1.476409923715353e-05, + "loss": 0.1099, + "step": 316150 + }, + { + "epoch": 0.71, + "learning_rate": 1.476298069394421e-05, + "loss": 0.113, + "step": 316160 + }, + { + "epoch": 0.71, + "learning_rate": 1.4761862150734884e-05, + "loss": 0.1101, + "step": 316170 + }, + { + "epoch": 0.71, + "learning_rate": 1.4760743607525559e-05, + "loss": 0.1097, + "step": 316180 + }, + { + "epoch": 0.71, + "learning_rate": 1.4759625064316235e-05, + "loss": 0.1073, + "step": 316190 + }, + { + "epoch": 0.71, + "learning_rate": 1.475850652110691e-05, + "loss": 0.1105, + "step": 316200 + }, + { + "epoch": 0.71, + "learning_rate": 1.4757387977897588e-05, + "loss": 0.1141, + "step": 316210 + }, + { + "epoch": 0.71, + "learning_rate": 1.4756269434688264e-05, + "loss": 0.1036, + "step": 316220 + }, + { + "epoch": 0.71, + "learning_rate": 1.4755150891478938e-05, + "loss": 0.1066, + "step": 316230 + }, + { + "epoch": 0.71, + "learning_rate": 1.4754032348269615e-05, + "loss": 0.1082, + "step": 316240 + }, + { + "epoch": 0.71, + "learning_rate": 1.4752913805060289e-05, + "loss": 0.1076, + "step": 316250 + }, + { + "epoch": 0.71, + "learning_rate": 1.4751795261850965e-05, + "loss": 0.1106, + "step": 316260 + }, + { + "epoch": 0.71, + "learning_rate": 1.4750676718641643e-05, + "loss": 0.1127, + "step": 316270 + }, + { + "epoch": 0.71, + "learning_rate": 1.4749558175432318e-05, + "loss": 0.1097, + "step": 316280 + }, + { + "epoch": 0.71, + "learning_rate": 1.4748439632222994e-05, + "loss": 0.1096, + "step": 316290 + }, + { + "epoch": 0.71, + "learning_rate": 1.4747321089013669e-05, + "loss": 0.107, + "step": 316300 + }, + { + "epoch": 0.71, + "learning_rate": 1.4746202545804345e-05, + "loss": 0.1106, + "step": 316310 + }, + { + "epoch": 0.71, + "learning_rate": 1.4745084002595023e-05, + "loss": 0.1092, + "step": 316320 + }, + { + "epoch": 0.71, + "learning_rate": 1.4743965459385697e-05, + "loss": 0.1099, + "step": 316330 + }, + { + "epoch": 0.71, + "learning_rate": 1.4742846916176373e-05, + "loss": 0.1113, + "step": 316340 + }, + { + "epoch": 0.71, + "learning_rate": 1.4741728372967048e-05, + "loss": 0.1084, + "step": 316350 + }, + { + "epoch": 0.71, + "learning_rate": 1.4740609829757723e-05, + "loss": 0.1112, + "step": 316360 + }, + { + "epoch": 0.71, + "learning_rate": 1.4739491286548402e-05, + "loss": 0.1091, + "step": 316370 + }, + { + "epoch": 0.71, + "learning_rate": 1.4738372743339077e-05, + "loss": 0.1071, + "step": 316380 + }, + { + "epoch": 0.71, + "learning_rate": 1.4737254200129751e-05, + "loss": 0.1124, + "step": 316390 + }, + { + "epoch": 0.71, + "learning_rate": 1.4736135656920427e-05, + "loss": 0.1104, + "step": 316400 + }, + { + "epoch": 0.71, + "learning_rate": 1.4735017113711102e-05, + "loss": 0.1095, + "step": 316410 + }, + { + "epoch": 0.71, + "learning_rate": 1.4733898570501778e-05, + "loss": 0.109, + "step": 316420 + }, + { + "epoch": 0.71, + "learning_rate": 1.4732780027292456e-05, + "loss": 0.1098, + "step": 316430 + }, + { + "epoch": 0.71, + "learning_rate": 1.473166148408313e-05, + "loss": 0.1116, + "step": 316440 + }, + { + "epoch": 0.71, + "learning_rate": 1.4730542940873807e-05, + "loss": 0.1079, + "step": 316450 + }, + { + "epoch": 0.71, + "learning_rate": 1.4729424397664482e-05, + "loss": 0.1095, + "step": 316460 + }, + { + "epoch": 0.71, + "learning_rate": 1.4728305854455158e-05, + "loss": 0.1085, + "step": 316470 + }, + { + "epoch": 0.71, + "learning_rate": 1.4727187311245836e-05, + "loss": 0.1108, + "step": 316480 + }, + { + "epoch": 0.71, + "learning_rate": 1.472606876803651e-05, + "loss": 0.1088, + "step": 316490 + }, + { + "epoch": 0.71, + "learning_rate": 1.4724950224827186e-05, + "loss": 0.1115, + "step": 316500 + }, + { + "epoch": 0.71, + "learning_rate": 1.4723831681617861e-05, + "loss": 0.1091, + "step": 316510 + }, + { + "epoch": 0.71, + "learning_rate": 1.4722713138408537e-05, + "loss": 0.1079, + "step": 316520 + }, + { + "epoch": 0.71, + "learning_rate": 1.4721594595199215e-05, + "loss": 0.1062, + "step": 316530 + }, + { + "epoch": 0.71, + "learning_rate": 1.472047605198989e-05, + "loss": 0.107, + "step": 316540 + }, + { + "epoch": 0.71, + "learning_rate": 1.4719357508780566e-05, + "loss": 0.1053, + "step": 316550 + }, + { + "epoch": 0.71, + "learning_rate": 1.471823896557124e-05, + "loss": 0.111, + "step": 316560 + }, + { + "epoch": 0.71, + "learning_rate": 1.4717120422361915e-05, + "loss": 0.1079, + "step": 316570 + }, + { + "epoch": 0.71, + "learning_rate": 1.4716001879152591e-05, + "loss": 0.11, + "step": 316580 + }, + { + "epoch": 0.71, + "learning_rate": 1.471488333594327e-05, + "loss": 0.1079, + "step": 316590 + }, + { + "epoch": 0.71, + "learning_rate": 1.4713764792733944e-05, + "loss": 0.1098, + "step": 316600 + }, + { + "epoch": 0.71, + "learning_rate": 1.471264624952462e-05, + "loss": 0.1094, + "step": 316610 + }, + { + "epoch": 0.71, + "learning_rate": 1.4711527706315294e-05, + "loss": 0.1097, + "step": 316620 + }, + { + "epoch": 0.71, + "learning_rate": 1.471040916310597e-05, + "loss": 0.106, + "step": 316630 + }, + { + "epoch": 0.71, + "learning_rate": 1.4709290619896649e-05, + "loss": 0.1096, + "step": 316640 + }, + { + "epoch": 0.71, + "learning_rate": 1.4708172076687323e-05, + "loss": 0.1038, + "step": 316650 + }, + { + "epoch": 0.71, + "learning_rate": 1.4707053533478e-05, + "loss": 0.1086, + "step": 316660 + }, + { + "epoch": 0.71, + "learning_rate": 1.4705934990268674e-05, + "loss": 0.1091, + "step": 316670 + }, + { + "epoch": 0.71, + "learning_rate": 1.470481644705935e-05, + "loss": 0.1092, + "step": 316680 + }, + { + "epoch": 0.71, + "learning_rate": 1.4703697903850028e-05, + "loss": 0.1125, + "step": 316690 + }, + { + "epoch": 0.71, + "learning_rate": 1.4702579360640703e-05, + "loss": 0.1116, + "step": 316700 + }, + { + "epoch": 0.71, + "learning_rate": 1.4701460817431379e-05, + "loss": 0.1127, + "step": 316710 + }, + { + "epoch": 0.71, + "learning_rate": 1.4700342274222053e-05, + "loss": 0.1099, + "step": 316720 + }, + { + "epoch": 0.71, + "learning_rate": 1.469922373101273e-05, + "loss": 0.11, + "step": 316730 + }, + { + "epoch": 0.71, + "learning_rate": 1.4698105187803404e-05, + "loss": 0.1119, + "step": 316740 + }, + { + "epoch": 0.71, + "learning_rate": 1.4696986644594082e-05, + "loss": 0.1083, + "step": 316750 + }, + { + "epoch": 0.71, + "learning_rate": 1.4695868101384758e-05, + "loss": 0.1148, + "step": 316760 + }, + { + "epoch": 0.71, + "learning_rate": 1.4694749558175433e-05, + "loss": 0.112, + "step": 316770 + }, + { + "epoch": 0.71, + "learning_rate": 1.4693631014966107e-05, + "loss": 0.1037, + "step": 316780 + }, + { + "epoch": 0.71, + "learning_rate": 1.4692512471756784e-05, + "loss": 0.1066, + "step": 316790 + }, + { + "epoch": 0.71, + "learning_rate": 1.4691393928547462e-05, + "loss": 0.1058, + "step": 316800 + }, + { + "epoch": 0.71, + "learning_rate": 1.4690275385338136e-05, + "loss": 0.1059, + "step": 316810 + }, + { + "epoch": 0.71, + "learning_rate": 1.4689156842128812e-05, + "loss": 0.108, + "step": 316820 + }, + { + "epoch": 0.71, + "learning_rate": 1.4688038298919487e-05, + "loss": 0.1074, + "step": 316830 + }, + { + "epoch": 0.71, + "learning_rate": 1.4686919755710163e-05, + "loss": 0.1082, + "step": 316840 + }, + { + "epoch": 0.71, + "learning_rate": 1.4685801212500841e-05, + "loss": 0.1071, + "step": 316850 + }, + { + "epoch": 0.71, + "learning_rate": 1.4684682669291516e-05, + "loss": 0.1073, + "step": 316860 + }, + { + "epoch": 0.71, + "learning_rate": 1.4683564126082192e-05, + "loss": 0.1002, + "step": 316870 + }, + { + "epoch": 0.71, + "learning_rate": 1.46825574371938e-05, + "loss": 0.1074, + "step": 316880 + }, + { + "epoch": 0.71, + "learning_rate": 1.4681438893984475e-05, + "loss": 0.111, + "step": 316890 + }, + { + "epoch": 0.71, + "learning_rate": 1.4680320350775151e-05, + "loss": 0.1086, + "step": 316900 + }, + { + "epoch": 0.71, + "learning_rate": 1.4679201807565826e-05, + "loss": 0.1071, + "step": 316910 + }, + { + "epoch": 0.71, + "learning_rate": 1.4678083264356504e-05, + "loss": 0.1147, + "step": 316920 + }, + { + "epoch": 0.71, + "learning_rate": 1.467696472114718e-05, + "loss": 0.1122, + "step": 316930 + }, + { + "epoch": 0.71, + "learning_rate": 1.4675846177937855e-05, + "loss": 0.1095, + "step": 316940 + }, + { + "epoch": 0.71, + "learning_rate": 1.4674727634728531e-05, + "loss": 0.1095, + "step": 316950 + }, + { + "epoch": 0.71, + "learning_rate": 1.4673609091519205e-05, + "loss": 0.1088, + "step": 316960 + }, + { + "epoch": 0.71, + "learning_rate": 1.467249054830988e-05, + "loss": 0.1071, + "step": 316970 + }, + { + "epoch": 0.71, + "learning_rate": 1.467137200510056e-05, + "loss": 0.114, + "step": 316980 + }, + { + "epoch": 0.71, + "learning_rate": 1.4670253461891234e-05, + "loss": 0.111, + "step": 316990 + }, + { + "epoch": 0.71, + "learning_rate": 1.4669134918681909e-05, + "loss": 0.111, + "step": 317000 + }, + { + "epoch": 0.71, + "learning_rate": 1.4668016375472585e-05, + "loss": 0.1125, + "step": 317010 + }, + { + "epoch": 0.71, + "learning_rate": 1.466689783226326e-05, + "loss": 0.1079, + "step": 317020 + }, + { + "epoch": 0.71, + "learning_rate": 1.4665779289053937e-05, + "loss": 0.1095, + "step": 317030 + }, + { + "epoch": 0.71, + "learning_rate": 1.4664660745844614e-05, + "loss": 0.111, + "step": 317040 + }, + { + "epoch": 0.71, + "learning_rate": 1.4663542202635288e-05, + "loss": 0.1105, + "step": 317050 + }, + { + "epoch": 0.71, + "learning_rate": 1.4662423659425964e-05, + "loss": 0.1056, + "step": 317060 + }, + { + "epoch": 0.71, + "learning_rate": 1.4661305116216639e-05, + "loss": 0.1088, + "step": 317070 + }, + { + "epoch": 0.71, + "learning_rate": 1.4660186573007317e-05, + "loss": 0.1074, + "step": 317080 + }, + { + "epoch": 0.71, + "learning_rate": 1.4659068029797993e-05, + "loss": 0.1152, + "step": 317090 + }, + { + "epoch": 0.71, + "learning_rate": 1.4657949486588668e-05, + "loss": 0.1071, + "step": 317100 + }, + { + "epoch": 0.71, + "learning_rate": 1.4656830943379344e-05, + "loss": 0.1126, + "step": 317110 + }, + { + "epoch": 0.71, + "learning_rate": 1.4655712400170018e-05, + "loss": 0.1088, + "step": 317120 + }, + { + "epoch": 0.71, + "learning_rate": 1.4654593856960695e-05, + "loss": 0.1098, + "step": 317130 + }, + { + "epoch": 0.71, + "learning_rate": 1.4653475313751373e-05, + "loss": 0.1097, + "step": 317140 + }, + { + "epoch": 0.71, + "learning_rate": 1.4652356770542047e-05, + "loss": 0.1122, + "step": 317150 + }, + { + "epoch": 0.71, + "learning_rate": 1.4651238227332723e-05, + "loss": 0.1137, + "step": 317160 + }, + { + "epoch": 0.71, + "learning_rate": 1.4650119684123398e-05, + "loss": 0.1079, + "step": 317170 + }, + { + "epoch": 0.71, + "learning_rate": 1.4649001140914072e-05, + "loss": 0.1078, + "step": 317180 + }, + { + "epoch": 0.71, + "learning_rate": 1.4647882597704752e-05, + "loss": 0.1099, + "step": 317190 + }, + { + "epoch": 0.71, + "learning_rate": 1.4646764054495427e-05, + "loss": 0.1023, + "step": 317200 + }, + { + "epoch": 0.71, + "learning_rate": 1.4645645511286101e-05, + "loss": 0.1085, + "step": 317210 + }, + { + "epoch": 0.71, + "learning_rate": 1.4644526968076777e-05, + "loss": 0.1082, + "step": 317220 + }, + { + "epoch": 0.71, + "learning_rate": 1.4643408424867452e-05, + "loss": 0.1104, + "step": 317230 + }, + { + "epoch": 0.71, + "learning_rate": 1.464228988165813e-05, + "loss": 0.1117, + "step": 317240 + }, + { + "epoch": 0.71, + "learning_rate": 1.4641171338448806e-05, + "loss": 0.106, + "step": 317250 + }, + { + "epoch": 0.71, + "learning_rate": 1.464005279523948e-05, + "loss": 0.1104, + "step": 317260 + }, + { + "epoch": 0.71, + "learning_rate": 1.4638934252030157e-05, + "loss": 0.1081, + "step": 317270 + }, + { + "epoch": 0.71, + "learning_rate": 1.4637815708820831e-05, + "loss": 0.1088, + "step": 317280 + }, + { + "epoch": 0.71, + "learning_rate": 1.4636697165611508e-05, + "loss": 0.1083, + "step": 317290 + }, + { + "epoch": 0.71, + "learning_rate": 1.4635578622402185e-05, + "loss": 0.1102, + "step": 317300 + }, + { + "epoch": 0.71, + "learning_rate": 1.463446007919286e-05, + "loss": 0.1048, + "step": 317310 + }, + { + "epoch": 0.71, + "learning_rate": 1.4633341535983536e-05, + "loss": 0.1046, + "step": 317320 + }, + { + "epoch": 0.71, + "learning_rate": 1.463222299277421e-05, + "loss": 0.1087, + "step": 317330 + }, + { + "epoch": 0.71, + "learning_rate": 1.4631104449564887e-05, + "loss": 0.1075, + "step": 317340 + }, + { + "epoch": 0.71, + "learning_rate": 1.4629985906355565e-05, + "loss": 0.1079, + "step": 317350 + }, + { + "epoch": 0.71, + "learning_rate": 1.462886736314624e-05, + "loss": 0.1077, + "step": 317360 + }, + { + "epoch": 0.71, + "learning_rate": 1.4627748819936916e-05, + "loss": 0.1054, + "step": 317370 + }, + { + "epoch": 0.71, + "learning_rate": 1.462663027672759e-05, + "loss": 0.1091, + "step": 317380 + }, + { + "epoch": 0.71, + "learning_rate": 1.4625511733518265e-05, + "loss": 0.1059, + "step": 317390 + }, + { + "epoch": 0.71, + "learning_rate": 1.4624393190308941e-05, + "loss": 0.1092, + "step": 317400 + }, + { + "epoch": 0.71, + "learning_rate": 1.4623274647099619e-05, + "loss": 0.1077, + "step": 317410 + }, + { + "epoch": 0.71, + "learning_rate": 1.4622156103890294e-05, + "loss": 0.1065, + "step": 317420 + }, + { + "epoch": 0.71, + "learning_rate": 1.462103756068097e-05, + "loss": 0.1103, + "step": 317430 + }, + { + "epoch": 0.71, + "learning_rate": 1.4619919017471644e-05, + "loss": 0.1066, + "step": 317440 + }, + { + "epoch": 0.71, + "learning_rate": 1.461880047426232e-05, + "loss": 0.1077, + "step": 317450 + }, + { + "epoch": 0.71, + "learning_rate": 1.4617681931052998e-05, + "loss": 0.1121, + "step": 317460 + }, + { + "epoch": 0.71, + "learning_rate": 1.4616563387843673e-05, + "loss": 0.1079, + "step": 317470 + }, + { + "epoch": 0.71, + "learning_rate": 1.461544484463435e-05, + "loss": 0.1086, + "step": 317480 + }, + { + "epoch": 0.71, + "learning_rate": 1.4614326301425024e-05, + "loss": 0.1075, + "step": 317490 + }, + { + "epoch": 0.71, + "learning_rate": 1.46132077582157e-05, + "loss": 0.1083, + "step": 317500 + }, + { + "epoch": 0.71, + "learning_rate": 1.4612089215006378e-05, + "loss": 0.1053, + "step": 317510 + }, + { + "epoch": 0.71, + "learning_rate": 1.4610970671797052e-05, + "loss": 0.1073, + "step": 317520 + }, + { + "epoch": 0.71, + "learning_rate": 1.4609852128587729e-05, + "loss": 0.1118, + "step": 317530 + }, + { + "epoch": 0.71, + "learning_rate": 1.4608733585378403e-05, + "loss": 0.1114, + "step": 317540 + }, + { + "epoch": 0.71, + "learning_rate": 1.460761504216908e-05, + "loss": 0.1094, + "step": 317550 + }, + { + "epoch": 0.71, + "learning_rate": 1.4606496498959754e-05, + "loss": 0.1114, + "step": 317560 + }, + { + "epoch": 0.71, + "learning_rate": 1.4605377955750432e-05, + "loss": 0.107, + "step": 317570 + }, + { + "epoch": 0.71, + "learning_rate": 1.4604259412541108e-05, + "loss": 0.1093, + "step": 317580 + }, + { + "epoch": 0.71, + "learning_rate": 1.4603140869331783e-05, + "loss": 0.1078, + "step": 317590 + }, + { + "epoch": 0.71, + "learning_rate": 1.4602022326122459e-05, + "loss": 0.1081, + "step": 317600 + }, + { + "epoch": 0.71, + "learning_rate": 1.4600903782913133e-05, + "loss": 0.1052, + "step": 317610 + }, + { + "epoch": 0.71, + "learning_rate": 1.4599785239703811e-05, + "loss": 0.1102, + "step": 317620 + }, + { + "epoch": 0.71, + "learning_rate": 1.4598666696494488e-05, + "loss": 0.1038, + "step": 317630 + }, + { + "epoch": 0.71, + "learning_rate": 1.4597548153285162e-05, + "loss": 0.1088, + "step": 317640 + }, + { + "epoch": 0.71, + "learning_rate": 1.4596429610075837e-05, + "loss": 0.1069, + "step": 317650 + }, + { + "epoch": 0.71, + "learning_rate": 1.4595311066866513e-05, + "loss": 0.1093, + "step": 317660 + }, + { + "epoch": 0.71, + "learning_rate": 1.4594192523657191e-05, + "loss": 0.1111, + "step": 317670 + }, + { + "epoch": 0.71, + "learning_rate": 1.4593073980447865e-05, + "loss": 0.11, + "step": 317680 + }, + { + "epoch": 0.71, + "learning_rate": 1.4591955437238542e-05, + "loss": 0.1071, + "step": 317690 + }, + { + "epoch": 0.71, + "learning_rate": 1.4590836894029216e-05, + "loss": 0.1039, + "step": 317700 + }, + { + "epoch": 0.71, + "learning_rate": 1.4589718350819892e-05, + "loss": 0.1087, + "step": 317710 + }, + { + "epoch": 0.71, + "learning_rate": 1.4588599807610567e-05, + "loss": 0.1095, + "step": 317720 + }, + { + "epoch": 0.71, + "learning_rate": 1.4587481264401245e-05, + "loss": 0.1024, + "step": 317730 + }, + { + "epoch": 0.71, + "learning_rate": 1.4586362721191921e-05, + "loss": 0.1078, + "step": 317740 + }, + { + "epoch": 0.71, + "learning_rate": 1.4585244177982596e-05, + "loss": 0.106, + "step": 317750 + }, + { + "epoch": 0.71, + "learning_rate": 1.4584125634773272e-05, + "loss": 0.1055, + "step": 317760 + }, + { + "epoch": 0.71, + "learning_rate": 1.4583007091563946e-05, + "loss": 0.1084, + "step": 317770 + }, + { + "epoch": 0.71, + "learning_rate": 1.4581888548354624e-05, + "loss": 0.1088, + "step": 317780 + }, + { + "epoch": 0.71, + "learning_rate": 1.45807700051453e-05, + "loss": 0.1048, + "step": 317790 + }, + { + "epoch": 0.71, + "learning_rate": 1.4579651461935975e-05, + "loss": 0.1063, + "step": 317800 + }, + { + "epoch": 0.71, + "learning_rate": 1.4578532918726651e-05, + "loss": 0.1087, + "step": 317810 + }, + { + "epoch": 0.71, + "learning_rate": 1.4577414375517326e-05, + "loss": 0.1091, + "step": 317820 + }, + { + "epoch": 0.71, + "learning_rate": 1.4576295832308004e-05, + "loss": 0.1067, + "step": 317830 + }, + { + "epoch": 0.71, + "learning_rate": 1.457517728909868e-05, + "loss": 0.1075, + "step": 317840 + }, + { + "epoch": 0.71, + "learning_rate": 1.4574058745889355e-05, + "loss": 0.112, + "step": 317850 + }, + { + "epoch": 0.71, + "learning_rate": 1.457294020268003e-05, + "loss": 0.1036, + "step": 317860 + }, + { + "epoch": 0.71, + "learning_rate": 1.4571821659470705e-05, + "loss": 0.1142, + "step": 317870 + }, + { + "epoch": 0.71, + "learning_rate": 1.457070311626138e-05, + "loss": 0.1103, + "step": 317880 + }, + { + "epoch": 0.71, + "learning_rate": 1.4569584573052058e-05, + "loss": 0.1116, + "step": 317890 + }, + { + "epoch": 0.71, + "learning_rate": 1.4568466029842734e-05, + "loss": 0.1098, + "step": 317900 + }, + { + "epoch": 0.71, + "learning_rate": 1.4567347486633409e-05, + "loss": 0.1136, + "step": 317910 + }, + { + "epoch": 0.71, + "learning_rate": 1.4566228943424085e-05, + "loss": 0.1115, + "step": 317920 + }, + { + "epoch": 0.71, + "learning_rate": 1.456511040021476e-05, + "loss": 0.1104, + "step": 317930 + }, + { + "epoch": 0.71, + "learning_rate": 1.4563991857005437e-05, + "loss": 0.1091, + "step": 317940 + }, + { + "epoch": 0.71, + "learning_rate": 1.4562873313796114e-05, + "loss": 0.1107, + "step": 317950 + }, + { + "epoch": 0.71, + "learning_rate": 1.4561754770586788e-05, + "loss": 0.1072, + "step": 317960 + }, + { + "epoch": 0.71, + "learning_rate": 1.4560636227377464e-05, + "loss": 0.1068, + "step": 317970 + }, + { + "epoch": 0.71, + "learning_rate": 1.4559517684168139e-05, + "loss": 0.1048, + "step": 317980 + }, + { + "epoch": 0.71, + "learning_rate": 1.4558399140958817e-05, + "loss": 0.1129, + "step": 317990 + }, + { + "epoch": 0.71, + "learning_rate": 1.4557280597749493e-05, + "loss": 0.1091, + "step": 318000 + }, + { + "epoch": 0.71, + "learning_rate": 1.4556162054540168e-05, + "loss": 0.1079, + "step": 318010 + }, + { + "epoch": 0.71, + "learning_rate": 1.4555043511330844e-05, + "loss": 0.1067, + "step": 318020 + }, + { + "epoch": 0.71, + "learning_rate": 1.4553924968121518e-05, + "loss": 0.1102, + "step": 318030 + }, + { + "epoch": 0.71, + "learning_rate": 1.4552806424912193e-05, + "loss": 0.1048, + "step": 318040 + }, + { + "epoch": 0.71, + "learning_rate": 1.4551687881702873e-05, + "loss": 0.1058, + "step": 318050 + }, + { + "epoch": 0.71, + "learning_rate": 1.4550569338493547e-05, + "loss": 0.106, + "step": 318060 + }, + { + "epoch": 0.71, + "learning_rate": 1.4549450795284222e-05, + "loss": 0.1075, + "step": 318070 + }, + { + "epoch": 0.71, + "learning_rate": 1.4548332252074898e-05, + "loss": 0.1083, + "step": 318080 + }, + { + "epoch": 0.71, + "learning_rate": 1.4547213708865572e-05, + "loss": 0.1087, + "step": 318090 + }, + { + "epoch": 0.71, + "learning_rate": 1.454609516565625e-05, + "loss": 0.1092, + "step": 318100 + }, + { + "epoch": 0.71, + "learning_rate": 1.4544976622446927e-05, + "loss": 0.1069, + "step": 318110 + }, + { + "epoch": 0.71, + "learning_rate": 1.4543858079237601e-05, + "loss": 0.1089, + "step": 318120 + }, + { + "epoch": 0.71, + "learning_rate": 1.4542739536028277e-05, + "loss": 0.1043, + "step": 318130 + }, + { + "epoch": 0.71, + "learning_rate": 1.4541620992818952e-05, + "loss": 0.1114, + "step": 318140 + }, + { + "epoch": 0.71, + "learning_rate": 1.454050244960963e-05, + "loss": 0.1124, + "step": 318150 + }, + { + "epoch": 0.71, + "learning_rate": 1.4539383906400306e-05, + "loss": 0.106, + "step": 318160 + }, + { + "epoch": 0.71, + "learning_rate": 1.453826536319098e-05, + "loss": 0.1081, + "step": 318170 + }, + { + "epoch": 0.71, + "learning_rate": 1.4537146819981657e-05, + "loss": 0.1016, + "step": 318180 + }, + { + "epoch": 0.71, + "learning_rate": 1.4536028276772331e-05, + "loss": 0.111, + "step": 318190 + }, + { + "epoch": 0.71, + "learning_rate": 1.4534909733563008e-05, + "loss": 0.1125, + "step": 318200 + }, + { + "epoch": 0.71, + "learning_rate": 1.4533791190353685e-05, + "loss": 0.1084, + "step": 318210 + }, + { + "epoch": 0.71, + "learning_rate": 1.453267264714436e-05, + "loss": 0.1127, + "step": 318220 + }, + { + "epoch": 0.71, + "learning_rate": 1.4531554103935036e-05, + "loss": 0.1085, + "step": 318230 + }, + { + "epoch": 0.71, + "learning_rate": 1.453043556072571e-05, + "loss": 0.1055, + "step": 318240 + }, + { + "epoch": 0.71, + "learning_rate": 1.4529317017516387e-05, + "loss": 0.1069, + "step": 318250 + }, + { + "epoch": 0.71, + "learning_rate": 1.4528198474307065e-05, + "loss": 0.1111, + "step": 318260 + }, + { + "epoch": 0.71, + "learning_rate": 1.452707993109774e-05, + "loss": 0.11, + "step": 318270 + }, + { + "epoch": 0.71, + "learning_rate": 1.4525961387888414e-05, + "loss": 0.1047, + "step": 318280 + }, + { + "epoch": 0.71, + "learning_rate": 1.452484284467909e-05, + "loss": 0.1048, + "step": 318290 + }, + { + "epoch": 0.71, + "learning_rate": 1.4523724301469765e-05, + "loss": 0.1135, + "step": 318300 + }, + { + "epoch": 0.71, + "learning_rate": 1.4522605758260443e-05, + "loss": 0.1065, + "step": 318310 + }, + { + "epoch": 0.71, + "learning_rate": 1.4521487215051119e-05, + "loss": 0.1034, + "step": 318320 + }, + { + "epoch": 0.71, + "learning_rate": 1.4520368671841794e-05, + "loss": 0.1102, + "step": 318330 + }, + { + "epoch": 0.71, + "learning_rate": 1.451925012863247e-05, + "loss": 0.1052, + "step": 318340 + }, + { + "epoch": 0.71, + "learning_rate": 1.4518131585423144e-05, + "loss": 0.1099, + "step": 318350 + }, + { + "epoch": 0.71, + "learning_rate": 1.451701304221382e-05, + "loss": 0.1083, + "step": 318360 + }, + { + "epoch": 0.71, + "learning_rate": 1.4515894499004498e-05, + "loss": 0.1049, + "step": 318370 + }, + { + "epoch": 0.71, + "learning_rate": 1.4514775955795173e-05, + "loss": 0.1095, + "step": 318380 + }, + { + "epoch": 0.71, + "learning_rate": 1.451365741258585e-05, + "loss": 0.1066, + "step": 318390 + }, + { + "epoch": 0.71, + "learning_rate": 1.4512538869376524e-05, + "loss": 0.1082, + "step": 318400 + }, + { + "epoch": 0.71, + "learning_rate": 1.45114203261672e-05, + "loss": 0.111, + "step": 318410 + }, + { + "epoch": 0.71, + "learning_rate": 1.4510301782957878e-05, + "loss": 0.1075, + "step": 318420 + }, + { + "epoch": 0.71, + "learning_rate": 1.4509183239748552e-05, + "loss": 0.1097, + "step": 318430 + }, + { + "epoch": 0.71, + "learning_rate": 1.4508064696539229e-05, + "loss": 0.1103, + "step": 318440 + }, + { + "epoch": 0.71, + "learning_rate": 1.4506946153329903e-05, + "loss": 0.1077, + "step": 318450 + }, + { + "epoch": 0.71, + "learning_rate": 1.450582761012058e-05, + "loss": 0.1084, + "step": 318460 + }, + { + "epoch": 0.71, + "learning_rate": 1.4504709066911257e-05, + "loss": 0.1095, + "step": 318470 + }, + { + "epoch": 0.71, + "learning_rate": 1.4503590523701932e-05, + "loss": 0.1128, + "step": 318480 + }, + { + "epoch": 0.71, + "learning_rate": 1.4502471980492608e-05, + "loss": 0.1079, + "step": 318490 + }, + { + "epoch": 0.71, + "learning_rate": 1.4501353437283283e-05, + "loss": 0.1092, + "step": 318500 + }, + { + "epoch": 0.71, + "learning_rate": 1.4500234894073957e-05, + "loss": 0.1056, + "step": 318510 + }, + { + "epoch": 0.71, + "learning_rate": 1.4499116350864633e-05, + "loss": 0.1043, + "step": 318520 + }, + { + "epoch": 0.71, + "learning_rate": 1.4497997807655311e-05, + "loss": 0.1041, + "step": 318530 + }, + { + "epoch": 0.71, + "learning_rate": 1.4496879264445986e-05, + "loss": 0.1046, + "step": 318540 + }, + { + "epoch": 0.71, + "learning_rate": 1.4495760721236662e-05, + "loss": 0.1086, + "step": 318550 + }, + { + "epoch": 0.71, + "learning_rate": 1.4494642178027337e-05, + "loss": 0.1111, + "step": 318560 + }, + { + "epoch": 0.71, + "learning_rate": 1.4493523634818013e-05, + "loss": 0.1097, + "step": 318570 + }, + { + "epoch": 0.71, + "learning_rate": 1.4492405091608691e-05, + "loss": 0.1076, + "step": 318580 + }, + { + "epoch": 0.71, + "learning_rate": 1.4491286548399365e-05, + "loss": 0.1063, + "step": 318590 + }, + { + "epoch": 0.71, + "learning_rate": 1.4490168005190042e-05, + "loss": 0.1066, + "step": 318600 + }, + { + "epoch": 0.71, + "learning_rate": 1.4489049461980716e-05, + "loss": 0.1146, + "step": 318610 + }, + { + "epoch": 0.71, + "learning_rate": 1.4487930918771392e-05, + "loss": 0.1123, + "step": 318620 + }, + { + "epoch": 0.71, + "learning_rate": 1.448681237556207e-05, + "loss": 0.1025, + "step": 318630 + }, + { + "epoch": 0.71, + "learning_rate": 1.4485693832352745e-05, + "loss": 0.1047, + "step": 318640 + }, + { + "epoch": 0.71, + "learning_rate": 1.4484575289143421e-05, + "loss": 0.1062, + "step": 318650 + }, + { + "epoch": 0.71, + "learning_rate": 1.4483456745934096e-05, + "loss": 0.1078, + "step": 318660 + }, + { + "epoch": 0.71, + "learning_rate": 1.4482338202724772e-05, + "loss": 0.1049, + "step": 318670 + }, + { + "epoch": 0.71, + "learning_rate": 1.4481219659515446e-05, + "loss": 0.108, + "step": 318680 + }, + { + "epoch": 0.71, + "learning_rate": 1.4480101116306124e-05, + "loss": 0.1074, + "step": 318690 + }, + { + "epoch": 0.71, + "learning_rate": 1.44789825730968e-05, + "loss": 0.1106, + "step": 318700 + }, + { + "epoch": 0.71, + "learning_rate": 1.4477864029887475e-05, + "loss": 0.1097, + "step": 318710 + }, + { + "epoch": 0.71, + "learning_rate": 1.447674548667815e-05, + "loss": 0.1064, + "step": 318720 + }, + { + "epoch": 0.71, + "learning_rate": 1.4475626943468826e-05, + "loss": 0.105, + "step": 318730 + }, + { + "epoch": 0.71, + "learning_rate": 1.4474508400259504e-05, + "loss": 0.1073, + "step": 318740 + }, + { + "epoch": 0.71, + "learning_rate": 1.4473389857050178e-05, + "loss": 0.1145, + "step": 318750 + }, + { + "epoch": 0.71, + "learning_rate": 1.4472271313840855e-05, + "loss": 0.1075, + "step": 318760 + }, + { + "epoch": 0.71, + "learning_rate": 1.447115277063153e-05, + "loss": 0.1072, + "step": 318770 + }, + { + "epoch": 0.71, + "learning_rate": 1.4470034227422205e-05, + "loss": 0.1079, + "step": 318780 + }, + { + "epoch": 0.71, + "learning_rate": 1.4468915684212883e-05, + "loss": 0.1033, + "step": 318790 + }, + { + "epoch": 0.71, + "learning_rate": 1.4467797141003558e-05, + "loss": 0.1076, + "step": 318800 + }, + { + "epoch": 0.71, + "learning_rate": 1.4466678597794234e-05, + "loss": 0.1085, + "step": 318810 + }, + { + "epoch": 0.71, + "learning_rate": 1.4465560054584909e-05, + "loss": 0.1086, + "step": 318820 + }, + { + "epoch": 0.71, + "learning_rate": 1.4464441511375585e-05, + "loss": 0.1049, + "step": 318830 + }, + { + "epoch": 0.71, + "learning_rate": 1.446332296816626e-05, + "loss": 0.105, + "step": 318840 + }, + { + "epoch": 0.71, + "learning_rate": 1.4462204424956937e-05, + "loss": 0.1101, + "step": 318850 + }, + { + "epoch": 0.71, + "learning_rate": 1.4461085881747614e-05, + "loss": 0.111, + "step": 318860 + }, + { + "epoch": 0.71, + "learning_rate": 1.4459967338538288e-05, + "loss": 0.1089, + "step": 318870 + }, + { + "epoch": 0.71, + "learning_rate": 1.4458848795328964e-05, + "loss": 0.1074, + "step": 318880 + }, + { + "epoch": 0.71, + "learning_rate": 1.4457730252119639e-05, + "loss": 0.1127, + "step": 318890 + }, + { + "epoch": 0.71, + "learning_rate": 1.4456723563231248e-05, + "loss": 0.1097, + "step": 318900 + }, + { + "epoch": 0.71, + "learning_rate": 1.4455605020021922e-05, + "loss": 0.1144, + "step": 318910 + }, + { + "epoch": 0.71, + "learning_rate": 1.44544864768126e-05, + "loss": 0.1115, + "step": 318920 + }, + { + "epoch": 0.71, + "learning_rate": 1.4453367933603276e-05, + "loss": 0.1093, + "step": 318930 + }, + { + "epoch": 0.71, + "learning_rate": 1.4452249390393951e-05, + "loss": 0.1129, + "step": 318940 + }, + { + "epoch": 0.71, + "learning_rate": 1.4451130847184627e-05, + "loss": 0.1071, + "step": 318950 + }, + { + "epoch": 0.71, + "learning_rate": 1.4450012303975302e-05, + "loss": 0.1076, + "step": 318960 + }, + { + "epoch": 0.71, + "learning_rate": 1.444889376076598e-05, + "loss": 0.1141, + "step": 318970 + }, + { + "epoch": 0.71, + "learning_rate": 1.4447775217556656e-05, + "loss": 0.1114, + "step": 318980 + }, + { + "epoch": 0.71, + "learning_rate": 1.444665667434733e-05, + "loss": 0.1068, + "step": 318990 + }, + { + "epoch": 0.71, + "learning_rate": 1.4445538131138007e-05, + "loss": 0.105, + "step": 319000 + }, + { + "epoch": 0.71, + "learning_rate": 1.4444419587928681e-05, + "loss": 0.1079, + "step": 319010 + }, + { + "epoch": 0.71, + "learning_rate": 1.4443301044719359e-05, + "loss": 0.1098, + "step": 319020 + }, + { + "epoch": 0.71, + "learning_rate": 1.4442182501510035e-05, + "loss": 0.1097, + "step": 319030 + }, + { + "epoch": 0.71, + "learning_rate": 1.444106395830071e-05, + "loss": 0.1086, + "step": 319040 + }, + { + "epoch": 0.71, + "learning_rate": 1.4439945415091386e-05, + "loss": 0.1041, + "step": 319050 + }, + { + "epoch": 0.71, + "learning_rate": 1.443882687188206e-05, + "loss": 0.1054, + "step": 319060 + }, + { + "epoch": 0.71, + "learning_rate": 1.4437708328672737e-05, + "loss": 0.1096, + "step": 319070 + }, + { + "epoch": 0.71, + "learning_rate": 1.4436589785463415e-05, + "loss": 0.108, + "step": 319080 + }, + { + "epoch": 0.71, + "learning_rate": 1.443547124225409e-05, + "loss": 0.1102, + "step": 319090 + }, + { + "epoch": 0.71, + "learning_rate": 1.4434352699044766e-05, + "loss": 0.1114, + "step": 319100 + }, + { + "epoch": 0.71, + "learning_rate": 1.443323415583544e-05, + "loss": 0.1131, + "step": 319110 + }, + { + "epoch": 0.71, + "learning_rate": 1.4432115612626115e-05, + "loss": 0.1099, + "step": 319120 + }, + { + "epoch": 0.71, + "learning_rate": 1.4430997069416794e-05, + "loss": 0.1093, + "step": 319130 + }, + { + "epoch": 0.71, + "learning_rate": 1.4429878526207469e-05, + "loss": 0.1084, + "step": 319140 + }, + { + "epoch": 0.71, + "learning_rate": 1.4428759982998143e-05, + "loss": 0.1093, + "step": 319150 + }, + { + "epoch": 0.71, + "learning_rate": 1.442764143978882e-05, + "loss": 0.1052, + "step": 319160 + }, + { + "epoch": 0.71, + "learning_rate": 1.4426522896579494e-05, + "loss": 0.1095, + "step": 319170 + }, + { + "epoch": 0.71, + "learning_rate": 1.4425404353370172e-05, + "loss": 0.1076, + "step": 319180 + }, + { + "epoch": 0.71, + "learning_rate": 1.4424285810160848e-05, + "loss": 0.107, + "step": 319190 + }, + { + "epoch": 0.71, + "learning_rate": 1.4423167266951523e-05, + "loss": 0.1107, + "step": 319200 + }, + { + "epoch": 0.71, + "learning_rate": 1.4422048723742199e-05, + "loss": 0.1093, + "step": 319210 + }, + { + "epoch": 0.71, + "learning_rate": 1.4420930180532874e-05, + "loss": 0.1112, + "step": 319220 + }, + { + "epoch": 0.71, + "learning_rate": 1.441981163732355e-05, + "loss": 0.1118, + "step": 319230 + }, + { + "epoch": 0.71, + "learning_rate": 1.4418693094114228e-05, + "loss": 0.1073, + "step": 319240 + }, + { + "epoch": 0.71, + "learning_rate": 1.4417574550904902e-05, + "loss": 0.108, + "step": 319250 + }, + { + "epoch": 0.71, + "learning_rate": 1.4416456007695579e-05, + "loss": 0.1083, + "step": 319260 + }, + { + "epoch": 0.71, + "learning_rate": 1.4415337464486253e-05, + "loss": 0.104, + "step": 319270 + }, + { + "epoch": 0.71, + "learning_rate": 1.441421892127693e-05, + "loss": 0.1093, + "step": 319280 + }, + { + "epoch": 0.71, + "learning_rate": 1.4413100378067607e-05, + "loss": 0.1092, + "step": 319290 + }, + { + "epoch": 0.71, + "learning_rate": 1.4411981834858282e-05, + "loss": 0.1098, + "step": 319300 + }, + { + "epoch": 0.71, + "learning_rate": 1.4410863291648958e-05, + "loss": 0.1064, + "step": 319310 + }, + { + "epoch": 0.71, + "learning_rate": 1.4409744748439633e-05, + "loss": 0.1091, + "step": 319320 + }, + { + "epoch": 0.71, + "learning_rate": 1.4408626205230307e-05, + "loss": 0.1087, + "step": 319330 + }, + { + "epoch": 0.71, + "learning_rate": 1.4407507662020987e-05, + "loss": 0.1057, + "step": 319340 + }, + { + "epoch": 0.71, + "learning_rate": 1.4406389118811661e-05, + "loss": 0.1039, + "step": 319350 + }, + { + "epoch": 0.71, + "learning_rate": 1.4405270575602336e-05, + "loss": 0.1083, + "step": 319360 + }, + { + "epoch": 0.71, + "learning_rate": 1.4404152032393012e-05, + "loss": 0.107, + "step": 319370 + }, + { + "epoch": 0.71, + "learning_rate": 1.4403033489183687e-05, + "loss": 0.1086, + "step": 319380 + }, + { + "epoch": 0.71, + "learning_rate": 1.4401914945974363e-05, + "loss": 0.1081, + "step": 319390 + }, + { + "epoch": 0.71, + "learning_rate": 1.440079640276504e-05, + "loss": 0.1127, + "step": 319400 + }, + { + "epoch": 0.71, + "learning_rate": 1.4399677859555715e-05, + "loss": 0.1079, + "step": 319410 + }, + { + "epoch": 0.71, + "learning_rate": 1.4398559316346391e-05, + "loss": 0.1063, + "step": 319420 + }, + { + "epoch": 0.71, + "learning_rate": 1.4397440773137066e-05, + "loss": 0.1068, + "step": 319430 + }, + { + "epoch": 0.71, + "learning_rate": 1.4396322229927742e-05, + "loss": 0.1055, + "step": 319440 + }, + { + "epoch": 0.71, + "learning_rate": 1.439520368671842e-05, + "loss": 0.1045, + "step": 319450 + }, + { + "epoch": 0.71, + "learning_rate": 1.4394085143509095e-05, + "loss": 0.1028, + "step": 319460 + }, + { + "epoch": 0.71, + "learning_rate": 1.4392966600299771e-05, + "loss": 0.1045, + "step": 319470 + }, + { + "epoch": 0.71, + "learning_rate": 1.4391848057090445e-05, + "loss": 0.1121, + "step": 319480 + }, + { + "epoch": 0.71, + "learning_rate": 1.4390729513881122e-05, + "loss": 0.104, + "step": 319490 + }, + { + "epoch": 0.71, + "learning_rate": 1.43896109706718e-05, + "loss": 0.1114, + "step": 319500 + }, + { + "epoch": 0.71, + "learning_rate": 1.4388492427462474e-05, + "loss": 0.1079, + "step": 319510 + }, + { + "epoch": 0.71, + "learning_rate": 1.438737388425315e-05, + "loss": 0.1116, + "step": 319520 + }, + { + "epoch": 0.71, + "learning_rate": 1.4386255341043825e-05, + "loss": 0.1067, + "step": 319530 + }, + { + "epoch": 0.71, + "learning_rate": 1.43851367978345e-05, + "loss": 0.1077, + "step": 319540 + }, + { + "epoch": 0.71, + "learning_rate": 1.4384018254625176e-05, + "loss": 0.1118, + "step": 319550 + }, + { + "epoch": 0.71, + "learning_rate": 1.4382899711415854e-05, + "loss": 0.1038, + "step": 319560 + }, + { + "epoch": 0.71, + "learning_rate": 1.4381781168206528e-05, + "loss": 0.1111, + "step": 319570 + }, + { + "epoch": 0.71, + "learning_rate": 1.4380662624997204e-05, + "loss": 0.1077, + "step": 319580 + }, + { + "epoch": 0.71, + "learning_rate": 1.4379544081787879e-05, + "loss": 0.1132, + "step": 319590 + }, + { + "epoch": 0.71, + "learning_rate": 1.4378425538578555e-05, + "loss": 0.1156, + "step": 319600 + }, + { + "epoch": 0.71, + "learning_rate": 1.4377306995369233e-05, + "loss": 0.1118, + "step": 319610 + }, + { + "epoch": 0.71, + "learning_rate": 1.4376188452159908e-05, + "loss": 0.1037, + "step": 319620 + }, + { + "epoch": 0.71, + "learning_rate": 1.4375069908950584e-05, + "loss": 0.1105, + "step": 319630 + }, + { + "epoch": 0.71, + "learning_rate": 1.4373951365741258e-05, + "loss": 0.1097, + "step": 319640 + }, + { + "epoch": 0.71, + "learning_rate": 1.4372832822531935e-05, + "loss": 0.1083, + "step": 319650 + }, + { + "epoch": 0.71, + "learning_rate": 1.4371714279322613e-05, + "loss": 0.1089, + "step": 319660 + }, + { + "epoch": 0.71, + "learning_rate": 1.4370595736113287e-05, + "loss": 0.1053, + "step": 319670 + }, + { + "epoch": 0.71, + "learning_rate": 1.4369477192903963e-05, + "loss": 0.1146, + "step": 319680 + }, + { + "epoch": 0.71, + "learning_rate": 1.4368358649694638e-05, + "loss": 0.1106, + "step": 319690 + }, + { + "epoch": 0.71, + "learning_rate": 1.4367240106485314e-05, + "loss": 0.1105, + "step": 319700 + }, + { + "epoch": 0.71, + "learning_rate": 1.4366121563275989e-05, + "loss": 0.1074, + "step": 319710 + }, + { + "epoch": 0.71, + "learning_rate": 1.4365003020066667e-05, + "loss": 0.105, + "step": 319720 + }, + { + "epoch": 0.71, + "learning_rate": 1.4363884476857343e-05, + "loss": 0.1057, + "step": 319730 + }, + { + "epoch": 0.71, + "learning_rate": 1.4362765933648017e-05, + "loss": 0.1068, + "step": 319740 + }, + { + "epoch": 0.71, + "learning_rate": 1.4361647390438692e-05, + "loss": 0.1141, + "step": 319750 + }, + { + "epoch": 0.71, + "learning_rate": 1.4360528847229368e-05, + "loss": 0.1056, + "step": 319760 + }, + { + "epoch": 0.71, + "learning_rate": 1.4359410304020046e-05, + "loss": 0.1058, + "step": 319770 + }, + { + "epoch": 0.71, + "learning_rate": 1.435829176081072e-05, + "loss": 0.107, + "step": 319780 + }, + { + "epoch": 0.71, + "learning_rate": 1.4357173217601397e-05, + "loss": 0.1034, + "step": 319790 + }, + { + "epoch": 0.71, + "learning_rate": 1.4356054674392071e-05, + "loss": 0.1075, + "step": 319800 + }, + { + "epoch": 0.71, + "learning_rate": 1.4354936131182748e-05, + "loss": 0.1079, + "step": 319810 + }, + { + "epoch": 0.71, + "learning_rate": 1.4353817587973426e-05, + "loss": 0.11, + "step": 319820 + }, + { + "epoch": 0.71, + "learning_rate": 1.43526990447641e-05, + "loss": 0.1075, + "step": 319830 + }, + { + "epoch": 0.71, + "learning_rate": 1.4351580501554776e-05, + "loss": 0.1088, + "step": 319840 + }, + { + "epoch": 0.71, + "learning_rate": 1.4350461958345451e-05, + "loss": 0.1101, + "step": 319850 + }, + { + "epoch": 0.71, + "learning_rate": 1.4349343415136127e-05, + "loss": 0.1053, + "step": 319860 + }, + { + "epoch": 0.71, + "learning_rate": 1.4348224871926802e-05, + "loss": 0.1074, + "step": 319870 + }, + { + "epoch": 0.71, + "learning_rate": 1.434710632871748e-05, + "loss": 0.1081, + "step": 319880 + }, + { + "epoch": 0.71, + "learning_rate": 1.4345987785508156e-05, + "loss": 0.109, + "step": 319890 + }, + { + "epoch": 0.71, + "learning_rate": 1.434486924229883e-05, + "loss": 0.1091, + "step": 319900 + }, + { + "epoch": 0.71, + "learning_rate": 1.4343750699089507e-05, + "loss": 0.1092, + "step": 319910 + }, + { + "epoch": 0.71, + "learning_rate": 1.4342632155880181e-05, + "loss": 0.1067, + "step": 319920 + }, + { + "epoch": 0.71, + "learning_rate": 1.4341513612670859e-05, + "loss": 0.1051, + "step": 319930 + }, + { + "epoch": 0.71, + "learning_rate": 1.4340395069461535e-05, + "loss": 0.1044, + "step": 319940 + }, + { + "epoch": 0.71, + "learning_rate": 1.433927652625221e-05, + "loss": 0.1084, + "step": 319950 + }, + { + "epoch": 0.71, + "learning_rate": 1.4338157983042886e-05, + "loss": 0.1078, + "step": 319960 + }, + { + "epoch": 0.71, + "learning_rate": 1.433703943983356e-05, + "loss": 0.106, + "step": 319970 + }, + { + "epoch": 0.71, + "learning_rate": 1.4335920896624239e-05, + "loss": 0.1064, + "step": 319980 + }, + { + "epoch": 0.71, + "learning_rate": 1.4334802353414915e-05, + "loss": 0.1102, + "step": 319990 + }, + { + "epoch": 0.71, + "learning_rate": 1.433368381020559e-05, + "loss": 0.1079, + "step": 320000 + }, + { + "epoch": 0.71, + "eval_NEIMS_canon_smiles": 0.95945, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.22353333333333333, + "eval_NEIMS_daylight_tanimoto_simil": 0.6026459992718832, + "eval_NEIMS_exact_mols": 0.22323333333333334, + "eval_NEIMS_exact_smiles": 0.21845, + "eval_NEIMS_loss": 0.13635511696338654, + "eval_NEIMS_matched_formulas": 0.7373833333333333, + "eval_NEIMS_morgan_tanimoto_simil": 0.5262141911314259, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.22396666666666668, + "eval_NEIMS_runtime": 726.0288, + "eval_NEIMS_samples_per_second": 82.641, + "eval_NEIMS_steps_per_second": 1.292, + "step": 320000 + }, + { + "epoch": 0.71, + "eval_RASSP_canon_smiles": 0.9573246068053561, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.29270043743947644, + "eval_RASSP_daylight_tanimoto_simil": 0.699134387711347, + "eval_RASSP_exact_mols": 0.2919491100945003, + "eval_RASSP_exact_smiles": 0.2854876949277056, + "eval_RASSP_loss": 0.10701441764831543, + "eval_RASSP_matched_formulas": 0.8672488062243296, + "eval_RASSP_morgan_tanimoto_simil": 0.5883433733977457, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.2921160717267172, + "eval_RASSP_runtime": 827.3085, + "eval_RASSP_samples_per_second": 72.396, + "eval_RASSP_steps_per_second": 1.131, + "step": 320000 + }, + { + "epoch": 0.71, + "eval_NEIMS_old_canon_smiles": 0.9601, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2178, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.5997354984801073, + "eval_NEIMS_old_exact_mols": 0.21753333333333333, + "eval_NEIMS_old_exact_smiles": 0.21266666666666667, + "eval_NEIMS_old_loss": 0.1359175592660904, + "eval_NEIMS_old_matched_formulas": 0.7347333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5233337080878555, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.21816666666666668, + "eval_NEIMS_old_runtime": 366.4998, + "eval_NEIMS_old_samples_per_second": 81.855, + "eval_NEIMS_old_steps_per_second": 1.28, + "step": 320000 + }, + { + "epoch": 0.71, + "eval_RASSP_old_canon_smiles": 0.9571862381953482, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.32212099976640973, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7181237207648891, + "eval_RASSP_old_exact_mols": 0.3214535989588547, + "eval_RASSP_old_exact_smiles": 0.3135448993893283, + "eval_RASSP_old_loss": 0.10045062005519867, + "eval_RASSP_old_matched_formulas": 0.8784663129442387, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6125297180777441, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.3217205592818767, + "eval_RASSP_old_runtime": 413.9105, + "eval_RASSP_old_samples_per_second": 72.4, + "eval_RASSP_old_steps_per_second": 1.133, + "step": 320000 + }, + { + "epoch": 0.71, + "eval_NIST_canon_smiles": 0.8731944493736026, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02814352131170813, + "eval_NIST_daylight_tanimoto_simil": 0.3013057679038636, + "eval_NIST_exact_mols": 0.02700784327643113, + "eval_NIST_exact_smiles": 0.025659225609539694, + "eval_NIST_loss": 1.8613232374191284, + "eval_NIST_matched_formulas": 0.12914788657415624, + "eval_NIST_morgan_tanimoto_simil": 0.2519311622414152, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02789509174149129, + "eval_NIST_runtime": 516.4481, + "eval_NIST_samples_per_second": 54.559, + "eval_NIST_steps_per_second": 0.854, + "step": 320000 + }, + { + "epoch": 0.71, + "learning_rate": 1.4332565266996264e-05, + "loss": 0.1084, + "step": 320010 + }, + { + "epoch": 0.71, + "learning_rate": 1.433144672378694e-05, + "loss": 0.1056, + "step": 320020 + }, + { + "epoch": 0.71, + "learning_rate": 1.4330328180577615e-05, + "loss": 0.1093, + "step": 320030 + }, + { + "epoch": 0.71, + "learning_rate": 1.4329209637368293e-05, + "loss": 0.1103, + "step": 320040 + }, + { + "epoch": 0.71, + "learning_rate": 1.4328091094158969e-05, + "loss": 0.1131, + "step": 320050 + }, + { + "epoch": 0.71, + "learning_rate": 1.4326972550949643e-05, + "loss": 0.1066, + "step": 320060 + }, + { + "epoch": 0.71, + "learning_rate": 1.432585400774032e-05, + "loss": 0.1061, + "step": 320070 + }, + { + "epoch": 0.71, + "learning_rate": 1.4324735464530994e-05, + "loss": 0.1041, + "step": 320080 + }, + { + "epoch": 0.71, + "learning_rate": 1.4323616921321672e-05, + "loss": 0.1079, + "step": 320090 + }, + { + "epoch": 0.71, + "learning_rate": 1.4322498378112348e-05, + "loss": 0.1083, + "step": 320100 + }, + { + "epoch": 0.71, + "learning_rate": 1.4321379834903023e-05, + "loss": 0.1119, + "step": 320110 + }, + { + "epoch": 0.71, + "learning_rate": 1.4320261291693699e-05, + "loss": 0.1081, + "step": 320120 + }, + { + "epoch": 0.71, + "learning_rate": 1.4319142748484374e-05, + "loss": 0.108, + "step": 320130 + }, + { + "epoch": 0.71, + "learning_rate": 1.4318024205275051e-05, + "loss": 0.1037, + "step": 320140 + }, + { + "epoch": 0.71, + "learning_rate": 1.4316905662065728e-05, + "loss": 0.11, + "step": 320150 + }, + { + "epoch": 0.71, + "learning_rate": 1.4315787118856402e-05, + "loss": 0.1067, + "step": 320160 + }, + { + "epoch": 0.71, + "learning_rate": 1.4314668575647079e-05, + "loss": 0.1072, + "step": 320170 + }, + { + "epoch": 0.71, + "learning_rate": 1.4313550032437753e-05, + "loss": 0.113, + "step": 320180 + }, + { + "epoch": 0.71, + "learning_rate": 1.4312431489228428e-05, + "loss": 0.1108, + "step": 320190 + }, + { + "epoch": 0.71, + "learning_rate": 1.4311312946019107e-05, + "loss": 0.11, + "step": 320200 + }, + { + "epoch": 0.71, + "learning_rate": 1.4310194402809782e-05, + "loss": 0.105, + "step": 320210 + }, + { + "epoch": 0.71, + "learning_rate": 1.4309075859600456e-05, + "loss": 0.1088, + "step": 320220 + }, + { + "epoch": 0.71, + "learning_rate": 1.4307957316391133e-05, + "loss": 0.1079, + "step": 320230 + }, + { + "epoch": 0.71, + "learning_rate": 1.4306838773181807e-05, + "loss": 0.1071, + "step": 320240 + }, + { + "epoch": 0.71, + "learning_rate": 1.4305720229972485e-05, + "loss": 0.1144, + "step": 320250 + }, + { + "epoch": 0.71, + "learning_rate": 1.4304601686763161e-05, + "loss": 0.109, + "step": 320260 + }, + { + "epoch": 0.71, + "learning_rate": 1.4303483143553836e-05, + "loss": 0.1119, + "step": 320270 + }, + { + "epoch": 0.71, + "learning_rate": 1.4302364600344512e-05, + "loss": 0.1058, + "step": 320280 + }, + { + "epoch": 0.71, + "learning_rate": 1.4301246057135187e-05, + "loss": 0.1112, + "step": 320290 + }, + { + "epoch": 0.71, + "learning_rate": 1.4300127513925864e-05, + "loss": 0.1058, + "step": 320300 + }, + { + "epoch": 0.71, + "learning_rate": 1.429900897071654e-05, + "loss": 0.108, + "step": 320310 + }, + { + "epoch": 0.71, + "learning_rate": 1.4297890427507215e-05, + "loss": 0.112, + "step": 320320 + }, + { + "epoch": 0.72, + "learning_rate": 1.4296771884297891e-05, + "loss": 0.1066, + "step": 320330 + }, + { + "epoch": 0.72, + "learning_rate": 1.4295653341088566e-05, + "loss": 0.1069, + "step": 320340 + }, + { + "epoch": 0.72, + "learning_rate": 1.4294534797879242e-05, + "loss": 0.106, + "step": 320350 + }, + { + "epoch": 0.72, + "learning_rate": 1.429341625466992e-05, + "loss": 0.1044, + "step": 320360 + }, + { + "epoch": 0.72, + "learning_rate": 1.4292297711460595e-05, + "loss": 0.1039, + "step": 320370 + }, + { + "epoch": 0.72, + "learning_rate": 1.4291179168251271e-05, + "loss": 0.1064, + "step": 320380 + }, + { + "epoch": 0.72, + "learning_rate": 1.4290060625041945e-05, + "loss": 0.109, + "step": 320390 + }, + { + "epoch": 0.72, + "learning_rate": 1.428894208183262e-05, + "loss": 0.1051, + "step": 320400 + }, + { + "epoch": 0.72, + "learning_rate": 1.42878235386233e-05, + "loss": 0.1086, + "step": 320410 + }, + { + "epoch": 0.72, + "learning_rate": 1.4286704995413974e-05, + "loss": 0.1097, + "step": 320420 + }, + { + "epoch": 0.72, + "learning_rate": 1.4285586452204649e-05, + "loss": 0.1053, + "step": 320430 + }, + { + "epoch": 0.72, + "learning_rate": 1.4284467908995325e-05, + "loss": 0.1101, + "step": 320440 + }, + { + "epoch": 0.72, + "learning_rate": 1.4283349365786e-05, + "loss": 0.1091, + "step": 320450 + }, + { + "epoch": 0.72, + "learning_rate": 1.4282230822576676e-05, + "loss": 0.1049, + "step": 320460 + }, + { + "epoch": 0.72, + "learning_rate": 1.4281224133688285e-05, + "loss": 0.1101, + "step": 320470 + }, + { + "epoch": 0.72, + "learning_rate": 1.4280105590478962e-05, + "loss": 0.1076, + "step": 320480 + }, + { + "epoch": 0.72, + "learning_rate": 1.4278987047269637e-05, + "loss": 0.1077, + "step": 320490 + }, + { + "epoch": 0.72, + "learning_rate": 1.4277868504060313e-05, + "loss": 0.1063, + "step": 320500 + }, + { + "epoch": 0.72, + "learning_rate": 1.4276749960850988e-05, + "loss": 0.1083, + "step": 320510 + }, + { + "epoch": 0.72, + "learning_rate": 1.4275631417641664e-05, + "loss": 0.1115, + "step": 320520 + }, + { + "epoch": 0.72, + "learning_rate": 1.4274512874432339e-05, + "loss": 0.1068, + "step": 320530 + }, + { + "epoch": 0.72, + "learning_rate": 1.4273394331223016e-05, + "loss": 0.111, + "step": 320540 + }, + { + "epoch": 0.72, + "learning_rate": 1.4272275788013693e-05, + "loss": 0.1062, + "step": 320550 + }, + { + "epoch": 0.72, + "learning_rate": 1.4271157244804367e-05, + "loss": 0.1151, + "step": 320560 + }, + { + "epoch": 0.72, + "learning_rate": 1.4270038701595043e-05, + "loss": 0.1065, + "step": 320570 + }, + { + "epoch": 0.72, + "learning_rate": 1.4268920158385718e-05, + "loss": 0.1027, + "step": 320580 + }, + { + "epoch": 0.72, + "learning_rate": 1.4267801615176396e-05, + "loss": 0.1084, + "step": 320590 + }, + { + "epoch": 0.72, + "learning_rate": 1.4266683071967072e-05, + "loss": 0.1085, + "step": 320600 + }, + { + "epoch": 0.72, + "learning_rate": 1.4265564528757747e-05, + "loss": 0.1112, + "step": 320610 + }, + { + "epoch": 0.72, + "learning_rate": 1.4264445985548421e-05, + "loss": 0.1097, + "step": 320620 + }, + { + "epoch": 0.72, + "learning_rate": 1.4263327442339097e-05, + "loss": 0.1079, + "step": 320630 + }, + { + "epoch": 0.72, + "learning_rate": 1.4262208899129775e-05, + "loss": 0.113, + "step": 320640 + }, + { + "epoch": 0.72, + "learning_rate": 1.426109035592045e-05, + "loss": 0.1149, + "step": 320650 + }, + { + "epoch": 0.72, + "learning_rate": 1.4259971812711126e-05, + "loss": 0.1081, + "step": 320660 + }, + { + "epoch": 0.72, + "learning_rate": 1.42588532695018e-05, + "loss": 0.1083, + "step": 320670 + }, + { + "epoch": 0.72, + "learning_rate": 1.4257734726292477e-05, + "loss": 0.1106, + "step": 320680 + }, + { + "epoch": 0.72, + "learning_rate": 1.4256616183083151e-05, + "loss": 0.108, + "step": 320690 + }, + { + "epoch": 0.72, + "learning_rate": 1.425549763987383e-05, + "loss": 0.1099, + "step": 320700 + }, + { + "epoch": 0.72, + "learning_rate": 1.4254379096664506e-05, + "loss": 0.1077, + "step": 320710 + }, + { + "epoch": 0.72, + "learning_rate": 1.425326055345518e-05, + "loss": 0.1061, + "step": 320720 + }, + { + "epoch": 0.72, + "learning_rate": 1.4252142010245856e-05, + "loss": 0.1084, + "step": 320730 + }, + { + "epoch": 0.72, + "learning_rate": 1.4251023467036531e-05, + "loss": 0.1091, + "step": 320740 + }, + { + "epoch": 0.72, + "learning_rate": 1.4249904923827209e-05, + "loss": 0.1103, + "step": 320750 + }, + { + "epoch": 0.72, + "learning_rate": 1.4248786380617885e-05, + "loss": 0.1062, + "step": 320760 + }, + { + "epoch": 0.72, + "learning_rate": 1.424766783740856e-05, + "loss": 0.1076, + "step": 320770 + }, + { + "epoch": 0.72, + "learning_rate": 1.4246549294199236e-05, + "loss": 0.1099, + "step": 320780 + }, + { + "epoch": 0.72, + "learning_rate": 1.424543075098991e-05, + "loss": 0.1077, + "step": 320790 + }, + { + "epoch": 0.72, + "learning_rate": 1.4244312207780588e-05, + "loss": 0.1072, + "step": 320800 + }, + { + "epoch": 0.72, + "learning_rate": 1.4243193664571265e-05, + "loss": 0.1116, + "step": 320810 + }, + { + "epoch": 0.72, + "learning_rate": 1.4242075121361939e-05, + "loss": 0.1029, + "step": 320820 + }, + { + "epoch": 0.72, + "learning_rate": 1.4240956578152614e-05, + "loss": 0.1114, + "step": 320830 + }, + { + "epoch": 0.72, + "learning_rate": 1.423983803494329e-05, + "loss": 0.1054, + "step": 320840 + }, + { + "epoch": 0.72, + "learning_rate": 1.4238719491733964e-05, + "loss": 0.107, + "step": 320850 + }, + { + "epoch": 0.72, + "learning_rate": 1.4237600948524642e-05, + "loss": 0.112, + "step": 320860 + }, + { + "epoch": 0.72, + "learning_rate": 1.4236482405315319e-05, + "loss": 0.1106, + "step": 320870 + }, + { + "epoch": 0.72, + "learning_rate": 1.4235363862105993e-05, + "loss": 0.1048, + "step": 320880 + }, + { + "epoch": 0.72, + "learning_rate": 1.423424531889667e-05, + "loss": 0.1082, + "step": 320890 + }, + { + "epoch": 0.72, + "learning_rate": 1.4233126775687344e-05, + "loss": 0.1102, + "step": 320900 + }, + { + "epoch": 0.72, + "learning_rate": 1.4232008232478022e-05, + "loss": 0.1062, + "step": 320910 + }, + { + "epoch": 0.72, + "learning_rate": 1.4230889689268698e-05, + "loss": 0.1069, + "step": 320920 + }, + { + "epoch": 0.72, + "learning_rate": 1.4229771146059373e-05, + "loss": 0.1073, + "step": 320930 + }, + { + "epoch": 0.72, + "learning_rate": 1.4228652602850049e-05, + "loss": 0.1065, + "step": 320940 + }, + { + "epoch": 0.72, + "learning_rate": 1.4227534059640723e-05, + "loss": 0.1077, + "step": 320950 + }, + { + "epoch": 0.72, + "learning_rate": 1.4226415516431401e-05, + "loss": 0.1059, + "step": 320960 + }, + { + "epoch": 0.72, + "learning_rate": 1.4225296973222078e-05, + "loss": 0.1073, + "step": 320970 + }, + { + "epoch": 0.72, + "learning_rate": 1.4224178430012752e-05, + "loss": 0.1106, + "step": 320980 + }, + { + "epoch": 0.72, + "learning_rate": 1.4223059886803428e-05, + "loss": 0.109, + "step": 320990 + }, + { + "epoch": 0.72, + "learning_rate": 1.4221941343594103e-05, + "loss": 0.1065, + "step": 321000 + }, + { + "epoch": 0.72, + "learning_rate": 1.4220822800384777e-05, + "loss": 0.1095, + "step": 321010 + }, + { + "epoch": 0.72, + "learning_rate": 1.4219704257175457e-05, + "loss": 0.1122, + "step": 321020 + }, + { + "epoch": 0.72, + "learning_rate": 1.4218585713966132e-05, + "loss": 0.108, + "step": 321030 + }, + { + "epoch": 0.72, + "learning_rate": 1.4217467170756806e-05, + "loss": 0.1066, + "step": 321040 + }, + { + "epoch": 0.72, + "learning_rate": 1.4216348627547482e-05, + "loss": 0.108, + "step": 321050 + }, + { + "epoch": 0.72, + "learning_rate": 1.4215230084338157e-05, + "loss": 0.1087, + "step": 321060 + }, + { + "epoch": 0.72, + "learning_rate": 1.4214111541128835e-05, + "loss": 0.1061, + "step": 321070 + }, + { + "epoch": 0.72, + "learning_rate": 1.4212992997919511e-05, + "loss": 0.1058, + "step": 321080 + }, + { + "epoch": 0.72, + "learning_rate": 1.4211874454710186e-05, + "loss": 0.1079, + "step": 321090 + }, + { + "epoch": 0.72, + "learning_rate": 1.4210755911500862e-05, + "loss": 0.1111, + "step": 321100 + }, + { + "epoch": 0.72, + "learning_rate": 1.4209637368291536e-05, + "loss": 0.1064, + "step": 321110 + }, + { + "epoch": 0.72, + "learning_rate": 1.4208518825082214e-05, + "loss": 0.1072, + "step": 321120 + }, + { + "epoch": 0.72, + "learning_rate": 1.420740028187289e-05, + "loss": 0.1132, + "step": 321130 + }, + { + "epoch": 0.72, + "learning_rate": 1.4206281738663565e-05, + "loss": 0.1077, + "step": 321140 + }, + { + "epoch": 0.72, + "learning_rate": 1.4205163195454241e-05, + "loss": 0.1083, + "step": 321150 + }, + { + "epoch": 0.72, + "learning_rate": 1.4204044652244916e-05, + "loss": 0.1014, + "step": 321160 + }, + { + "epoch": 0.72, + "learning_rate": 1.4202926109035592e-05, + "loss": 0.1052, + "step": 321170 + }, + { + "epoch": 0.72, + "learning_rate": 1.420180756582627e-05, + "loss": 0.1044, + "step": 321180 + }, + { + "epoch": 0.72, + "learning_rate": 1.4200689022616945e-05, + "loss": 0.1106, + "step": 321190 + }, + { + "epoch": 0.72, + "learning_rate": 1.419957047940762e-05, + "loss": 0.1099, + "step": 321200 + }, + { + "epoch": 0.72, + "learning_rate": 1.4198451936198295e-05, + "loss": 0.1083, + "step": 321210 + }, + { + "epoch": 0.72, + "learning_rate": 1.4197333392988972e-05, + "loss": 0.1075, + "step": 321220 + }, + { + "epoch": 0.72, + "learning_rate": 1.419621484977965e-05, + "loss": 0.111, + "step": 321230 + }, + { + "epoch": 0.72, + "learning_rate": 1.4195096306570324e-05, + "loss": 0.1113, + "step": 321240 + }, + { + "epoch": 0.72, + "learning_rate": 1.4193977763360999e-05, + "loss": 0.1035, + "step": 321250 + }, + { + "epoch": 0.72, + "learning_rate": 1.4192859220151675e-05, + "loss": 0.1074, + "step": 321260 + }, + { + "epoch": 0.72, + "learning_rate": 1.419174067694235e-05, + "loss": 0.102, + "step": 321270 + }, + { + "epoch": 0.72, + "learning_rate": 1.4190622133733027e-05, + "loss": 0.1072, + "step": 321280 + }, + { + "epoch": 0.72, + "learning_rate": 1.4189503590523703e-05, + "loss": 0.1065, + "step": 321290 + }, + { + "epoch": 0.72, + "learning_rate": 1.4188385047314378e-05, + "loss": 0.1106, + "step": 321300 + }, + { + "epoch": 0.72, + "learning_rate": 1.4187266504105054e-05, + "loss": 0.1038, + "step": 321310 + }, + { + "epoch": 0.72, + "learning_rate": 1.4186147960895729e-05, + "loss": 0.1084, + "step": 321320 + }, + { + "epoch": 0.72, + "learning_rate": 1.4185029417686405e-05, + "loss": 0.1069, + "step": 321330 + }, + { + "epoch": 0.72, + "learning_rate": 1.4183910874477083e-05, + "loss": 0.1092, + "step": 321340 + }, + { + "epoch": 0.72, + "learning_rate": 1.4182792331267757e-05, + "loss": 0.1072, + "step": 321350 + }, + { + "epoch": 0.72, + "learning_rate": 1.4181673788058434e-05, + "loss": 0.1106, + "step": 321360 + }, + { + "epoch": 0.72, + "learning_rate": 1.4180555244849108e-05, + "loss": 0.1048, + "step": 321370 + }, + { + "epoch": 0.72, + "learning_rate": 1.4179436701639784e-05, + "loss": 0.1069, + "step": 321380 + }, + { + "epoch": 0.72, + "learning_rate": 1.4178318158430462e-05, + "loss": 0.1087, + "step": 321390 + }, + { + "epoch": 0.72, + "learning_rate": 1.4177199615221137e-05, + "loss": 0.1081, + "step": 321400 + }, + { + "epoch": 0.72, + "learning_rate": 1.4176081072011813e-05, + "loss": 0.1064, + "step": 321410 + }, + { + "epoch": 0.72, + "learning_rate": 1.4174962528802488e-05, + "loss": 0.102, + "step": 321420 + }, + { + "epoch": 0.72, + "learning_rate": 1.4173843985593164e-05, + "loss": 0.1102, + "step": 321430 + }, + { + "epoch": 0.72, + "learning_rate": 1.4172725442383842e-05, + "loss": 0.1083, + "step": 321440 + }, + { + "epoch": 0.72, + "learning_rate": 1.4171606899174516e-05, + "loss": 0.1022, + "step": 321450 + }, + { + "epoch": 0.72, + "learning_rate": 1.4170488355965193e-05, + "loss": 0.1063, + "step": 321460 + }, + { + "epoch": 0.72, + "learning_rate": 1.4169369812755867e-05, + "loss": 0.109, + "step": 321470 + }, + { + "epoch": 0.72, + "learning_rate": 1.4168251269546542e-05, + "loss": 0.1051, + "step": 321480 + }, + { + "epoch": 0.72, + "learning_rate": 1.4167132726337218e-05, + "loss": 0.1089, + "step": 321490 + }, + { + "epoch": 0.72, + "learning_rate": 1.4166014183127896e-05, + "loss": 0.1123, + "step": 321500 + }, + { + "epoch": 0.72, + "learning_rate": 1.416489563991857e-05, + "loss": 0.1109, + "step": 321510 + }, + { + "epoch": 0.72, + "learning_rate": 1.4163777096709247e-05, + "loss": 0.1096, + "step": 321520 + }, + { + "epoch": 0.72, + "learning_rate": 1.4162658553499921e-05, + "loss": 0.1067, + "step": 321530 + }, + { + "epoch": 0.72, + "learning_rate": 1.4161540010290597e-05, + "loss": 0.1083, + "step": 321540 + }, + { + "epoch": 0.72, + "learning_rate": 1.4160421467081275e-05, + "loss": 0.1089, + "step": 321550 + }, + { + "epoch": 0.72, + "learning_rate": 1.415930292387195e-05, + "loss": 0.1039, + "step": 321560 + }, + { + "epoch": 0.72, + "learning_rate": 1.4158184380662626e-05, + "loss": 0.1053, + "step": 321570 + }, + { + "epoch": 0.72, + "learning_rate": 1.41570658374533e-05, + "loss": 0.1073, + "step": 321580 + }, + { + "epoch": 0.72, + "learning_rate": 1.4155947294243977e-05, + "loss": 0.1076, + "step": 321590 + }, + { + "epoch": 0.72, + "learning_rate": 1.4154828751034655e-05, + "loss": 0.1059, + "step": 321600 + }, + { + "epoch": 0.72, + "learning_rate": 1.415371020782533e-05, + "loss": 0.1099, + "step": 321610 + }, + { + "epoch": 0.72, + "learning_rate": 1.4152591664616006e-05, + "loss": 0.1075, + "step": 321620 + }, + { + "epoch": 0.72, + "learning_rate": 1.415147312140668e-05, + "loss": 0.1082, + "step": 321630 + }, + { + "epoch": 0.72, + "learning_rate": 1.4150354578197356e-05, + "loss": 0.1109, + "step": 321640 + }, + { + "epoch": 0.72, + "learning_rate": 1.4149236034988031e-05, + "loss": 0.1082, + "step": 321650 + }, + { + "epoch": 0.72, + "learning_rate": 1.4148117491778709e-05, + "loss": 0.1099, + "step": 321660 + }, + { + "epoch": 0.72, + "learning_rate": 1.4146998948569385e-05, + "loss": 0.1081, + "step": 321670 + }, + { + "epoch": 0.72, + "learning_rate": 1.414588040536006e-05, + "loss": 0.1068, + "step": 321680 + }, + { + "epoch": 0.72, + "learning_rate": 1.4144761862150734e-05, + "loss": 0.1026, + "step": 321690 + }, + { + "epoch": 0.72, + "learning_rate": 1.414364331894141e-05, + "loss": 0.104, + "step": 321700 + }, + { + "epoch": 0.72, + "learning_rate": 1.4142524775732088e-05, + "loss": 0.1045, + "step": 321710 + }, + { + "epoch": 0.72, + "learning_rate": 1.4141406232522763e-05, + "loss": 0.1095, + "step": 321720 + }, + { + "epoch": 0.72, + "learning_rate": 1.4140287689313439e-05, + "loss": 0.1073, + "step": 321730 + }, + { + "epoch": 0.72, + "learning_rate": 1.4139169146104114e-05, + "loss": 0.1084, + "step": 321740 + }, + { + "epoch": 0.72, + "learning_rate": 1.413805060289479e-05, + "loss": 0.104, + "step": 321750 + }, + { + "epoch": 0.72, + "learning_rate": 1.4136932059685468e-05, + "loss": 0.1147, + "step": 321760 + }, + { + "epoch": 0.72, + "learning_rate": 1.4135813516476142e-05, + "loss": 0.1081, + "step": 321770 + }, + { + "epoch": 0.72, + "learning_rate": 1.4134694973266819e-05, + "loss": 0.1073, + "step": 321780 + }, + { + "epoch": 0.72, + "learning_rate": 1.4133576430057493e-05, + "loss": 0.1062, + "step": 321790 + }, + { + "epoch": 0.72, + "learning_rate": 1.413245788684817e-05, + "loss": 0.1083, + "step": 321800 + }, + { + "epoch": 0.72, + "learning_rate": 1.4131339343638844e-05, + "loss": 0.1076, + "step": 321810 + }, + { + "epoch": 0.72, + "learning_rate": 1.4130220800429522e-05, + "loss": 0.1085, + "step": 321820 + }, + { + "epoch": 0.72, + "learning_rate": 1.4129102257220198e-05, + "loss": 0.1055, + "step": 321830 + }, + { + "epoch": 0.72, + "learning_rate": 1.4127983714010873e-05, + "loss": 0.1099, + "step": 321840 + }, + { + "epoch": 0.72, + "learning_rate": 1.4126865170801549e-05, + "loss": 0.105, + "step": 321850 + }, + { + "epoch": 0.72, + "learning_rate": 1.4125746627592223e-05, + "loss": 0.1073, + "step": 321860 + }, + { + "epoch": 0.72, + "learning_rate": 1.4124628084382901e-05, + "loss": 0.1056, + "step": 321870 + }, + { + "epoch": 0.72, + "learning_rate": 1.4123509541173578e-05, + "loss": 0.108, + "step": 321880 + }, + { + "epoch": 0.72, + "learning_rate": 1.4122390997964252e-05, + "loss": 0.1107, + "step": 321890 + }, + { + "epoch": 0.72, + "learning_rate": 1.4121272454754927e-05, + "loss": 0.105, + "step": 321900 + }, + { + "epoch": 0.72, + "learning_rate": 1.4120153911545603e-05, + "loss": 0.1059, + "step": 321910 + }, + { + "epoch": 0.72, + "learning_rate": 1.411903536833628e-05, + "loss": 0.1114, + "step": 321920 + }, + { + "epoch": 0.72, + "learning_rate": 1.4117916825126955e-05, + "loss": 0.1105, + "step": 321930 + }, + { + "epoch": 0.72, + "learning_rate": 1.4116798281917632e-05, + "loss": 0.1052, + "step": 321940 + }, + { + "epoch": 0.72, + "learning_rate": 1.4115679738708306e-05, + "loss": 0.1092, + "step": 321950 + }, + { + "epoch": 0.72, + "learning_rate": 1.4114561195498982e-05, + "loss": 0.1092, + "step": 321960 + }, + { + "epoch": 0.72, + "learning_rate": 1.4113442652289657e-05, + "loss": 0.1036, + "step": 321970 + }, + { + "epoch": 0.72, + "learning_rate": 1.4112324109080335e-05, + "loss": 0.1065, + "step": 321980 + }, + { + "epoch": 0.72, + "learning_rate": 1.4111205565871011e-05, + "loss": 0.1091, + "step": 321990 + }, + { + "epoch": 0.72, + "learning_rate": 1.4110087022661686e-05, + "loss": 0.1074, + "step": 322000 + }, + { + "epoch": 0.72, + "learning_rate": 1.4108968479452362e-05, + "loss": 0.1066, + "step": 322010 + }, + { + "epoch": 0.72, + "learning_rate": 1.4107849936243036e-05, + "loss": 0.1064, + "step": 322020 + }, + { + "epoch": 0.72, + "learning_rate": 1.4106731393033714e-05, + "loss": 0.1037, + "step": 322030 + }, + { + "epoch": 0.72, + "learning_rate": 1.410561284982439e-05, + "loss": 0.1102, + "step": 322040 + }, + { + "epoch": 0.72, + "learning_rate": 1.4104494306615065e-05, + "loss": 0.1048, + "step": 322050 + }, + { + "epoch": 0.72, + "learning_rate": 1.4103375763405741e-05, + "loss": 0.1061, + "step": 322060 + }, + { + "epoch": 0.72, + "learning_rate": 1.4102257220196416e-05, + "loss": 0.1093, + "step": 322070 + }, + { + "epoch": 0.72, + "learning_rate": 1.4101138676987094e-05, + "loss": 0.1146, + "step": 322080 + }, + { + "epoch": 0.72, + "learning_rate": 1.410002013377777e-05, + "loss": 0.1037, + "step": 322090 + }, + { + "epoch": 0.72, + "learning_rate": 1.4098901590568445e-05, + "loss": 0.1037, + "step": 322100 + }, + { + "epoch": 0.72, + "learning_rate": 1.409778304735912e-05, + "loss": 0.1078, + "step": 322110 + }, + { + "epoch": 0.72, + "learning_rate": 1.4096664504149795e-05, + "loss": 0.1072, + "step": 322120 + }, + { + "epoch": 0.72, + "learning_rate": 1.409554596094047e-05, + "loss": 0.1042, + "step": 322130 + }, + { + "epoch": 0.72, + "learning_rate": 1.409442741773115e-05, + "loss": 0.1061, + "step": 322140 + }, + { + "epoch": 0.72, + "learning_rate": 1.4093308874521824e-05, + "loss": 0.112, + "step": 322150 + }, + { + "epoch": 0.72, + "learning_rate": 1.4092190331312499e-05, + "loss": 0.1088, + "step": 322160 + }, + { + "epoch": 0.72, + "learning_rate": 1.4091071788103175e-05, + "loss": 0.1081, + "step": 322170 + }, + { + "epoch": 0.72, + "learning_rate": 1.408995324489385e-05, + "loss": 0.1093, + "step": 322180 + }, + { + "epoch": 0.72, + "learning_rate": 1.4088834701684527e-05, + "loss": 0.1062, + "step": 322190 + }, + { + "epoch": 0.72, + "learning_rate": 1.4087716158475203e-05, + "loss": 0.1081, + "step": 322200 + }, + { + "epoch": 0.72, + "learning_rate": 1.4086597615265878e-05, + "loss": 0.113, + "step": 322210 + }, + { + "epoch": 0.72, + "learning_rate": 1.4085479072056554e-05, + "loss": 0.1148, + "step": 322220 + }, + { + "epoch": 0.72, + "learning_rate": 1.4084360528847229e-05, + "loss": 0.1076, + "step": 322230 + }, + { + "epoch": 0.72, + "learning_rate": 1.4083241985637907e-05, + "loss": 0.1065, + "step": 322240 + }, + { + "epoch": 0.72, + "learning_rate": 1.4082123442428583e-05, + "loss": 0.1049, + "step": 322250 + }, + { + "epoch": 0.72, + "learning_rate": 1.4081004899219257e-05, + "loss": 0.1015, + "step": 322260 + }, + { + "epoch": 0.72, + "learning_rate": 1.4079886356009934e-05, + "loss": 0.108, + "step": 322270 + }, + { + "epoch": 0.72, + "learning_rate": 1.4078767812800608e-05, + "loss": 0.1066, + "step": 322280 + }, + { + "epoch": 0.72, + "learning_rate": 1.4077649269591284e-05, + "loss": 0.1076, + "step": 322290 + }, + { + "epoch": 0.72, + "learning_rate": 1.4076530726381962e-05, + "loss": 0.11, + "step": 322300 + }, + { + "epoch": 0.72, + "learning_rate": 1.4075412183172637e-05, + "loss": 0.1099, + "step": 322310 + }, + { + "epoch": 0.72, + "learning_rate": 1.4074293639963313e-05, + "loss": 0.1083, + "step": 322320 + }, + { + "epoch": 0.72, + "learning_rate": 1.4073175096753988e-05, + "loss": 0.109, + "step": 322330 + }, + { + "epoch": 0.72, + "learning_rate": 1.4072056553544662e-05, + "loss": 0.1085, + "step": 322340 + }, + { + "epoch": 0.72, + "learning_rate": 1.4070938010335342e-05, + "loss": 0.1106, + "step": 322350 + }, + { + "epoch": 0.72, + "learning_rate": 1.4069819467126016e-05, + "loss": 0.1123, + "step": 322360 + }, + { + "epoch": 0.72, + "learning_rate": 1.4068700923916691e-05, + "loss": 0.1057, + "step": 322370 + }, + { + "epoch": 0.72, + "learning_rate": 1.4067582380707367e-05, + "loss": 0.1023, + "step": 322380 + }, + { + "epoch": 0.72, + "learning_rate": 1.4066463837498042e-05, + "loss": 0.1044, + "step": 322390 + }, + { + "epoch": 0.72, + "learning_rate": 1.406534529428872e-05, + "loss": 0.1078, + "step": 322400 + }, + { + "epoch": 0.72, + "learning_rate": 1.4064226751079396e-05, + "loss": 0.1056, + "step": 322410 + }, + { + "epoch": 0.72, + "learning_rate": 1.406310820787007e-05, + "loss": 0.1055, + "step": 322420 + }, + { + "epoch": 0.72, + "learning_rate": 1.4061989664660747e-05, + "loss": 0.1047, + "step": 322430 + }, + { + "epoch": 0.72, + "learning_rate": 1.4060871121451421e-05, + "loss": 0.1095, + "step": 322440 + }, + { + "epoch": 0.72, + "learning_rate": 1.4059752578242097e-05, + "loss": 0.1084, + "step": 322450 + }, + { + "epoch": 0.72, + "learning_rate": 1.4058634035032775e-05, + "loss": 0.1097, + "step": 322460 + }, + { + "epoch": 0.72, + "learning_rate": 1.405751549182345e-05, + "loss": 0.1009, + "step": 322470 + }, + { + "epoch": 0.72, + "learning_rate": 1.4056396948614126e-05, + "loss": 0.1079, + "step": 322480 + }, + { + "epoch": 0.72, + "learning_rate": 1.40552784054048e-05, + "loss": 0.1102, + "step": 322490 + }, + { + "epoch": 0.72, + "learning_rate": 1.4054159862195477e-05, + "loss": 0.1061, + "step": 322500 + }, + { + "epoch": 0.72, + "learning_rate": 1.4053041318986155e-05, + "loss": 0.1092, + "step": 322510 + }, + { + "epoch": 0.72, + "learning_rate": 1.405192277577683e-05, + "loss": 0.1049, + "step": 322520 + }, + { + "epoch": 0.72, + "learning_rate": 1.4050804232567506e-05, + "loss": 0.1082, + "step": 322530 + }, + { + "epoch": 0.72, + "learning_rate": 1.404968568935818e-05, + "loss": 0.1084, + "step": 322540 + }, + { + "epoch": 0.72, + "learning_rate": 1.4048567146148855e-05, + "loss": 0.1138, + "step": 322550 + }, + { + "epoch": 0.72, + "learning_rate": 1.4047448602939534e-05, + "loss": 0.1081, + "step": 322560 + }, + { + "epoch": 0.72, + "learning_rate": 1.4046330059730209e-05, + "loss": 0.1075, + "step": 322570 + }, + { + "epoch": 0.72, + "learning_rate": 1.4045211516520883e-05, + "loss": 0.107, + "step": 322580 + }, + { + "epoch": 0.72, + "learning_rate": 1.404409297331156e-05, + "loss": 0.1088, + "step": 322590 + }, + { + "epoch": 0.72, + "learning_rate": 1.4042974430102234e-05, + "loss": 0.1095, + "step": 322600 + }, + { + "epoch": 0.72, + "learning_rate": 1.404185588689291e-05, + "loss": 0.1058, + "step": 322610 + }, + { + "epoch": 0.72, + "learning_rate": 1.4040737343683588e-05, + "loss": 0.1079, + "step": 322620 + }, + { + "epoch": 0.72, + "learning_rate": 1.4039618800474263e-05, + "loss": 0.1074, + "step": 322630 + }, + { + "epoch": 0.72, + "learning_rate": 1.4038500257264939e-05, + "loss": 0.1114, + "step": 322640 + }, + { + "epoch": 0.72, + "learning_rate": 1.4037381714055614e-05, + "loss": 0.1093, + "step": 322650 + }, + { + "epoch": 0.72, + "learning_rate": 1.403626317084629e-05, + "loss": 0.1119, + "step": 322660 + }, + { + "epoch": 0.72, + "learning_rate": 1.4035144627636968e-05, + "loss": 0.1087, + "step": 322670 + }, + { + "epoch": 0.72, + "learning_rate": 1.4034026084427642e-05, + "loss": 0.1076, + "step": 322680 + }, + { + "epoch": 0.72, + "learning_rate": 1.4032907541218319e-05, + "loss": 0.1077, + "step": 322690 + }, + { + "epoch": 0.72, + "learning_rate": 1.4031788998008993e-05, + "loss": 0.1109, + "step": 322700 + }, + { + "epoch": 0.72, + "learning_rate": 1.403067045479967e-05, + "loss": 0.1119, + "step": 322710 + }, + { + "epoch": 0.72, + "learning_rate": 1.4029551911590347e-05, + "loss": 0.1032, + "step": 322720 + }, + { + "epoch": 0.72, + "learning_rate": 1.4028433368381022e-05, + "loss": 0.1138, + "step": 322730 + }, + { + "epoch": 0.72, + "learning_rate": 1.4027314825171698e-05, + "loss": 0.1068, + "step": 322740 + }, + { + "epoch": 0.72, + "learning_rate": 1.4026196281962373e-05, + "loss": 0.1058, + "step": 322750 + }, + { + "epoch": 0.72, + "learning_rate": 1.4025077738753047e-05, + "loss": 0.1073, + "step": 322760 + }, + { + "epoch": 0.72, + "learning_rate": 1.4023959195543723e-05, + "loss": 0.1039, + "step": 322770 + }, + { + "epoch": 0.72, + "learning_rate": 1.4022840652334401e-05, + "loss": 0.1114, + "step": 322780 + }, + { + "epoch": 0.72, + "learning_rate": 1.4021722109125076e-05, + "loss": 0.106, + "step": 322790 + }, + { + "epoch": 0.72, + "learning_rate": 1.4020603565915752e-05, + "loss": 0.1016, + "step": 322800 + }, + { + "epoch": 0.72, + "learning_rate": 1.4019485022706427e-05, + "loss": 0.1108, + "step": 322810 + }, + { + "epoch": 0.72, + "learning_rate": 1.4018366479497103e-05, + "loss": 0.1085, + "step": 322820 + }, + { + "epoch": 0.72, + "learning_rate": 1.401724793628778e-05, + "loss": 0.1091, + "step": 322830 + }, + { + "epoch": 0.72, + "learning_rate": 1.4016129393078455e-05, + "loss": 0.1094, + "step": 322840 + }, + { + "epoch": 0.72, + "learning_rate": 1.4015010849869132e-05, + "loss": 0.1057, + "step": 322850 + }, + { + "epoch": 0.72, + "learning_rate": 1.4013892306659806e-05, + "loss": 0.1056, + "step": 322860 + }, + { + "epoch": 0.72, + "learning_rate": 1.4012773763450482e-05, + "loss": 0.1063, + "step": 322870 + }, + { + "epoch": 0.72, + "learning_rate": 1.401165522024116e-05, + "loss": 0.1105, + "step": 322880 + }, + { + "epoch": 0.72, + "learning_rate": 1.4010536677031835e-05, + "loss": 0.1024, + "step": 322890 + }, + { + "epoch": 0.72, + "learning_rate": 1.4009418133822511e-05, + "loss": 0.115, + "step": 322900 + }, + { + "epoch": 0.72, + "learning_rate": 1.4008299590613186e-05, + "loss": 0.1117, + "step": 322910 + }, + { + "epoch": 0.72, + "learning_rate": 1.4007181047403862e-05, + "loss": 0.1106, + "step": 322920 + }, + { + "epoch": 0.72, + "learning_rate": 1.4006062504194536e-05, + "loss": 0.1087, + "step": 322930 + }, + { + "epoch": 0.72, + "learning_rate": 1.4004943960985214e-05, + "loss": 0.1062, + "step": 322940 + }, + { + "epoch": 0.72, + "learning_rate": 1.400382541777589e-05, + "loss": 0.1072, + "step": 322950 + }, + { + "epoch": 0.72, + "learning_rate": 1.4002706874566565e-05, + "loss": 0.1056, + "step": 322960 + }, + { + "epoch": 0.72, + "learning_rate": 1.4001588331357241e-05, + "loss": 0.1123, + "step": 322970 + }, + { + "epoch": 0.72, + "learning_rate": 1.4000469788147916e-05, + "loss": 0.1061, + "step": 322980 + }, + { + "epoch": 0.72, + "learning_rate": 1.3999351244938594e-05, + "loss": 0.1072, + "step": 322990 + }, + { + "epoch": 0.72, + "learning_rate": 1.399823270172927e-05, + "loss": 0.1103, + "step": 323000 + }, + { + "epoch": 0.72, + "learning_rate": 1.3997114158519945e-05, + "loss": 0.1073, + "step": 323010 + }, + { + "epoch": 0.72, + "learning_rate": 1.3995995615310619e-05, + "loss": 0.1079, + "step": 323020 + }, + { + "epoch": 0.72, + "learning_rate": 1.3994877072101295e-05, + "loss": 0.1064, + "step": 323030 + }, + { + "epoch": 0.72, + "learning_rate": 1.3993758528891973e-05, + "loss": 0.1041, + "step": 323040 + }, + { + "epoch": 0.72, + "learning_rate": 1.3992639985682648e-05, + "loss": 0.1063, + "step": 323050 + }, + { + "epoch": 0.72, + "learning_rate": 1.3991521442473324e-05, + "loss": 0.1084, + "step": 323060 + }, + { + "epoch": 0.72, + "learning_rate": 1.3990402899263999e-05, + "loss": 0.1052, + "step": 323070 + }, + { + "epoch": 0.72, + "learning_rate": 1.3989284356054675e-05, + "loss": 0.1059, + "step": 323080 + }, + { + "epoch": 0.72, + "learning_rate": 1.398816581284535e-05, + "loss": 0.1036, + "step": 323090 + }, + { + "epoch": 0.72, + "learning_rate": 1.3987047269636027e-05, + "loss": 0.1051, + "step": 323100 + }, + { + "epoch": 0.72, + "learning_rate": 1.3985928726426703e-05, + "loss": 0.1068, + "step": 323110 + }, + { + "epoch": 0.72, + "learning_rate": 1.3984810183217378e-05, + "loss": 0.1068, + "step": 323120 + }, + { + "epoch": 0.72, + "learning_rate": 1.3983691640008054e-05, + "loss": 0.1115, + "step": 323130 + }, + { + "epoch": 0.72, + "learning_rate": 1.3982573096798729e-05, + "loss": 0.108, + "step": 323140 + }, + { + "epoch": 0.72, + "learning_rate": 1.3981454553589407e-05, + "loss": 0.1035, + "step": 323150 + }, + { + "epoch": 0.72, + "learning_rate": 1.3980336010380083e-05, + "loss": 0.1067, + "step": 323160 + }, + { + "epoch": 0.72, + "learning_rate": 1.3979217467170757e-05, + "loss": 0.1054, + "step": 323170 + }, + { + "epoch": 0.72, + "learning_rate": 1.3978098923961434e-05, + "loss": 0.1062, + "step": 323180 + }, + { + "epoch": 0.72, + "learning_rate": 1.3976980380752108e-05, + "loss": 0.1058, + "step": 323190 + }, + { + "epoch": 0.72, + "learning_rate": 1.3975861837542786e-05, + "loss": 0.1079, + "step": 323200 + }, + { + "epoch": 0.72, + "learning_rate": 1.3974743294333462e-05, + "loss": 0.1102, + "step": 323210 + }, + { + "epoch": 0.72, + "learning_rate": 1.3973624751124137e-05, + "loss": 0.1051, + "step": 323220 + }, + { + "epoch": 0.72, + "learning_rate": 1.3972506207914811e-05, + "loss": 0.1066, + "step": 323230 + }, + { + "epoch": 0.72, + "learning_rate": 1.3971387664705488e-05, + "loss": 0.1069, + "step": 323240 + }, + { + "epoch": 0.72, + "learning_rate": 1.3970269121496162e-05, + "loss": 0.111, + "step": 323250 + }, + { + "epoch": 0.72, + "learning_rate": 1.396915057828684e-05, + "loss": 0.1045, + "step": 323260 + }, + { + "epoch": 0.72, + "learning_rate": 1.3968032035077516e-05, + "loss": 0.1038, + "step": 323270 + }, + { + "epoch": 0.72, + "learning_rate": 1.3966913491868191e-05, + "loss": 0.1076, + "step": 323280 + }, + { + "epoch": 0.72, + "learning_rate": 1.3965794948658867e-05, + "loss": 0.109, + "step": 323290 + }, + { + "epoch": 0.72, + "learning_rate": 1.3964676405449542e-05, + "loss": 0.1097, + "step": 323300 + }, + { + "epoch": 0.72, + "learning_rate": 1.396355786224022e-05, + "loss": 0.1088, + "step": 323310 + }, + { + "epoch": 0.72, + "learning_rate": 1.3962439319030896e-05, + "loss": 0.1107, + "step": 323320 + }, + { + "epoch": 0.72, + "learning_rate": 1.396132077582157e-05, + "loss": 0.1112, + "step": 323330 + }, + { + "epoch": 0.72, + "learning_rate": 1.3960202232612247e-05, + "loss": 0.1095, + "step": 323340 + }, + { + "epoch": 0.72, + "learning_rate": 1.3959083689402921e-05, + "loss": 0.1066, + "step": 323350 + }, + { + "epoch": 0.72, + "learning_rate": 1.3957965146193597e-05, + "loss": 0.1057, + "step": 323360 + }, + { + "epoch": 0.72, + "learning_rate": 1.3956846602984275e-05, + "loss": 0.1093, + "step": 323370 + }, + { + "epoch": 0.72, + "learning_rate": 1.395572805977495e-05, + "loss": 0.1032, + "step": 323380 + }, + { + "epoch": 0.72, + "learning_rate": 1.3954609516565626e-05, + "loss": 0.1075, + "step": 323390 + }, + { + "epoch": 0.72, + "learning_rate": 1.39534909733563e-05, + "loss": 0.1083, + "step": 323400 + }, + { + "epoch": 0.72, + "learning_rate": 1.3952372430146975e-05, + "loss": 0.1089, + "step": 323410 + }, + { + "epoch": 0.72, + "learning_rate": 1.3951253886937655e-05, + "loss": 0.1089, + "step": 323420 + }, + { + "epoch": 0.72, + "learning_rate": 1.395013534372833e-05, + "loss": 0.1126, + "step": 323430 + }, + { + "epoch": 0.72, + "learning_rate": 1.3949016800519004e-05, + "loss": 0.1101, + "step": 323440 + }, + { + "epoch": 0.72, + "learning_rate": 1.394789825730968e-05, + "loss": 0.1075, + "step": 323450 + }, + { + "epoch": 0.72, + "learning_rate": 1.3946779714100355e-05, + "loss": 0.1095, + "step": 323460 + }, + { + "epoch": 0.72, + "learning_rate": 1.3945661170891033e-05, + "loss": 0.1035, + "step": 323470 + }, + { + "epoch": 0.72, + "learning_rate": 1.3944542627681709e-05, + "loss": 0.1095, + "step": 323480 + }, + { + "epoch": 0.72, + "learning_rate": 1.3943424084472383e-05, + "loss": 0.1104, + "step": 323490 + }, + { + "epoch": 0.72, + "learning_rate": 1.394230554126306e-05, + "loss": 0.1072, + "step": 323500 + }, + { + "epoch": 0.72, + "learning_rate": 1.3941186998053734e-05, + "loss": 0.1135, + "step": 323510 + }, + { + "epoch": 0.72, + "learning_rate": 1.394006845484441e-05, + "loss": 0.1051, + "step": 323520 + }, + { + "epoch": 0.72, + "learning_rate": 1.3938949911635088e-05, + "loss": 0.1062, + "step": 323530 + }, + { + "epoch": 0.72, + "learning_rate": 1.3937831368425763e-05, + "loss": 0.1022, + "step": 323540 + }, + { + "epoch": 0.72, + "learning_rate": 1.3936712825216439e-05, + "loss": 0.1076, + "step": 323550 + }, + { + "epoch": 0.72, + "learning_rate": 1.3935594282007114e-05, + "loss": 0.1031, + "step": 323560 + }, + { + "epoch": 0.72, + "learning_rate": 1.393447573879779e-05, + "loss": 0.1071, + "step": 323570 + }, + { + "epoch": 0.72, + "learning_rate": 1.3933357195588468e-05, + "loss": 0.1106, + "step": 323580 + }, + { + "epoch": 0.72, + "learning_rate": 1.3932238652379142e-05, + "loss": 0.1105, + "step": 323590 + }, + { + "epoch": 0.72, + "learning_rate": 1.3931120109169819e-05, + "loss": 0.1055, + "step": 323600 + }, + { + "epoch": 0.72, + "learning_rate": 1.3930001565960493e-05, + "loss": 0.1059, + "step": 323610 + }, + { + "epoch": 0.72, + "learning_rate": 1.392888302275117e-05, + "loss": 0.1074, + "step": 323620 + }, + { + "epoch": 0.72, + "learning_rate": 1.3927764479541847e-05, + "loss": 0.1042, + "step": 323630 + }, + { + "epoch": 0.72, + "learning_rate": 1.3926645936332522e-05, + "loss": 0.1086, + "step": 323640 + }, + { + "epoch": 0.72, + "learning_rate": 1.3925527393123198e-05, + "loss": 0.1085, + "step": 323650 + }, + { + "epoch": 0.72, + "learning_rate": 1.3924408849913873e-05, + "loss": 0.1074, + "step": 323660 + }, + { + "epoch": 0.72, + "learning_rate": 1.3923290306704547e-05, + "loss": 0.1084, + "step": 323670 + }, + { + "epoch": 0.72, + "learning_rate": 1.3922171763495223e-05, + "loss": 0.1097, + "step": 323680 + }, + { + "epoch": 0.72, + "learning_rate": 1.3921053220285901e-05, + "loss": 0.1057, + "step": 323690 + }, + { + "epoch": 0.72, + "learning_rate": 1.3919934677076576e-05, + "loss": 0.1099, + "step": 323700 + }, + { + "epoch": 0.72, + "learning_rate": 1.3918816133867252e-05, + "loss": 0.1131, + "step": 323710 + }, + { + "epoch": 0.72, + "learning_rate": 1.3917697590657927e-05, + "loss": 0.1096, + "step": 323720 + }, + { + "epoch": 0.72, + "learning_rate": 1.3916579047448603e-05, + "loss": 0.104, + "step": 323730 + }, + { + "epoch": 0.72, + "learning_rate": 1.391546050423928e-05, + "loss": 0.1039, + "step": 323740 + }, + { + "epoch": 0.72, + "learning_rate": 1.3914341961029955e-05, + "loss": 0.1075, + "step": 323750 + }, + { + "epoch": 0.72, + "learning_rate": 1.3913223417820632e-05, + "loss": 0.107, + "step": 323760 + }, + { + "epoch": 0.72, + "learning_rate": 1.3912104874611306e-05, + "loss": 0.1059, + "step": 323770 + }, + { + "epoch": 0.72, + "learning_rate": 1.3910986331401982e-05, + "loss": 0.1118, + "step": 323780 + }, + { + "epoch": 0.72, + "learning_rate": 1.390986778819266e-05, + "loss": 0.1072, + "step": 323790 + }, + { + "epoch": 0.72, + "learning_rate": 1.3908749244983335e-05, + "loss": 0.1075, + "step": 323800 + }, + { + "epoch": 0.72, + "learning_rate": 1.3907630701774011e-05, + "loss": 0.1108, + "step": 323810 + }, + { + "epoch": 0.72, + "learning_rate": 1.3906512158564686e-05, + "loss": 0.1073, + "step": 323820 + }, + { + "epoch": 0.72, + "learning_rate": 1.3905393615355362e-05, + "loss": 0.1071, + "step": 323830 + }, + { + "epoch": 0.72, + "learning_rate": 1.3904275072146036e-05, + "loss": 0.1111, + "step": 323840 + }, + { + "epoch": 0.72, + "learning_rate": 1.3903156528936714e-05, + "loss": 0.1079, + "step": 323850 + }, + { + "epoch": 0.72, + "learning_rate": 1.390203798572739e-05, + "loss": 0.1029, + "step": 323860 + }, + { + "epoch": 0.72, + "learning_rate": 1.3900919442518065e-05, + "loss": 0.1059, + "step": 323870 + }, + { + "epoch": 0.72, + "learning_rate": 1.389980089930874e-05, + "loss": 0.1058, + "step": 323880 + }, + { + "epoch": 0.72, + "learning_rate": 1.3898682356099416e-05, + "loss": 0.1052, + "step": 323890 + }, + { + "epoch": 0.72, + "learning_rate": 1.3897563812890094e-05, + "loss": 0.1123, + "step": 323900 + }, + { + "epoch": 0.72, + "learning_rate": 1.3896445269680768e-05, + "loss": 0.1078, + "step": 323910 + }, + { + "epoch": 0.72, + "learning_rate": 1.3895326726471444e-05, + "loss": 0.104, + "step": 323920 + }, + { + "epoch": 0.72, + "learning_rate": 1.3894208183262119e-05, + "loss": 0.105, + "step": 323930 + }, + { + "epoch": 0.72, + "learning_rate": 1.3893089640052795e-05, + "loss": 0.1076, + "step": 323940 + }, + { + "epoch": 0.72, + "learning_rate": 1.3891971096843473e-05, + "loss": 0.1028, + "step": 323950 + }, + { + "epoch": 0.72, + "learning_rate": 1.3890852553634148e-05, + "loss": 0.1039, + "step": 323960 + }, + { + "epoch": 0.72, + "learning_rate": 1.3889734010424824e-05, + "loss": 0.1058, + "step": 323970 + }, + { + "epoch": 0.72, + "learning_rate": 1.3888615467215499e-05, + "loss": 0.1068, + "step": 323980 + }, + { + "epoch": 0.72, + "learning_rate": 1.3887496924006175e-05, + "loss": 0.1103, + "step": 323990 + }, + { + "epoch": 0.72, + "learning_rate": 1.388637838079685e-05, + "loss": 0.1072, + "step": 324000 + }, + { + "epoch": 0.72, + "learning_rate": 1.3885259837587527e-05, + "loss": 0.1055, + "step": 324010 + }, + { + "epoch": 0.72, + "learning_rate": 1.3884141294378203e-05, + "loss": 0.1061, + "step": 324020 + }, + { + "epoch": 0.72, + "learning_rate": 1.3883022751168878e-05, + "loss": 0.1081, + "step": 324030 + }, + { + "epoch": 0.72, + "learning_rate": 1.3881904207959554e-05, + "loss": 0.1058, + "step": 324040 + }, + { + "epoch": 0.72, + "learning_rate": 1.3880785664750229e-05, + "loss": 0.1075, + "step": 324050 + }, + { + "epoch": 0.72, + "learning_rate": 1.3879667121540907e-05, + "loss": 0.1084, + "step": 324060 + }, + { + "epoch": 0.72, + "learning_rate": 1.3878548578331583e-05, + "loss": 0.1086, + "step": 324070 + }, + { + "epoch": 0.72, + "learning_rate": 1.3877430035122257e-05, + "loss": 0.1103, + "step": 324080 + }, + { + "epoch": 0.72, + "learning_rate": 1.3876311491912932e-05, + "loss": 0.1088, + "step": 324090 + }, + { + "epoch": 0.72, + "learning_rate": 1.3875192948703608e-05, + "loss": 0.1074, + "step": 324100 + }, + { + "epoch": 0.72, + "learning_rate": 1.3874074405494286e-05, + "loss": 0.1088, + "step": 324110 + }, + { + "epoch": 0.72, + "learning_rate": 1.387295586228496e-05, + "loss": 0.1116, + "step": 324120 + }, + { + "epoch": 0.72, + "learning_rate": 1.3871837319075637e-05, + "loss": 0.1066, + "step": 324130 + }, + { + "epoch": 0.72, + "learning_rate": 1.3870718775866311e-05, + "loss": 0.1096, + "step": 324140 + }, + { + "epoch": 0.72, + "learning_rate": 1.3869600232656988e-05, + "loss": 0.1082, + "step": 324150 + }, + { + "epoch": 0.72, + "learning_rate": 1.3868481689447662e-05, + "loss": 0.1064, + "step": 324160 + }, + { + "epoch": 0.72, + "learning_rate": 1.386736314623834e-05, + "loss": 0.1069, + "step": 324170 + }, + { + "epoch": 0.72, + "learning_rate": 1.3866244603029016e-05, + "loss": 0.105, + "step": 324180 + }, + { + "epoch": 0.72, + "learning_rate": 1.3865126059819691e-05, + "loss": 0.105, + "step": 324190 + }, + { + "epoch": 0.72, + "learning_rate": 1.3864007516610367e-05, + "loss": 0.1093, + "step": 324200 + }, + { + "epoch": 0.72, + "learning_rate": 1.3862888973401042e-05, + "loss": 0.1108, + "step": 324210 + }, + { + "epoch": 0.72, + "learning_rate": 1.386177043019172e-05, + "loss": 0.1056, + "step": 324220 + }, + { + "epoch": 0.72, + "learning_rate": 1.3860651886982396e-05, + "loss": 0.1052, + "step": 324230 + }, + { + "epoch": 0.72, + "learning_rate": 1.385953334377307e-05, + "loss": 0.1125, + "step": 324240 + }, + { + "epoch": 0.72, + "learning_rate": 1.3858414800563747e-05, + "loss": 0.1061, + "step": 324250 + }, + { + "epoch": 0.72, + "learning_rate": 1.3857296257354421e-05, + "loss": 0.1083, + "step": 324260 + }, + { + "epoch": 0.72, + "learning_rate": 1.3856177714145099e-05, + "loss": 0.11, + "step": 324270 + }, + { + "epoch": 0.72, + "learning_rate": 1.3855059170935775e-05, + "loss": 0.1088, + "step": 324280 + }, + { + "epoch": 0.72, + "learning_rate": 1.385394062772645e-05, + "loss": 0.1041, + "step": 324290 + }, + { + "epoch": 0.72, + "learning_rate": 1.3852822084517124e-05, + "loss": 0.1047, + "step": 324300 + }, + { + "epoch": 0.72, + "learning_rate": 1.38517035413078e-05, + "loss": 0.1007, + "step": 324310 + }, + { + "epoch": 0.72, + "learning_rate": 1.3850584998098475e-05, + "loss": 0.1113, + "step": 324320 + }, + { + "epoch": 0.72, + "learning_rate": 1.3849466454889153e-05, + "loss": 0.1063, + "step": 324330 + }, + { + "epoch": 0.72, + "learning_rate": 1.384834791167983e-05, + "loss": 0.1099, + "step": 324340 + }, + { + "epoch": 0.72, + "learning_rate": 1.3847229368470504e-05, + "loss": 0.1049, + "step": 324350 + }, + { + "epoch": 0.72, + "learning_rate": 1.384611082526118e-05, + "loss": 0.1091, + "step": 324360 + }, + { + "epoch": 0.72, + "learning_rate": 1.3844992282051855e-05, + "loss": 0.1089, + "step": 324370 + }, + { + "epoch": 0.72, + "learning_rate": 1.3843873738842533e-05, + "loss": 0.1085, + "step": 324380 + }, + { + "epoch": 0.72, + "learning_rate": 1.3842755195633209e-05, + "loss": 0.1111, + "step": 324390 + }, + { + "epoch": 0.72, + "learning_rate": 1.3841636652423883e-05, + "loss": 0.1055, + "step": 324400 + }, + { + "epoch": 0.72, + "learning_rate": 1.384051810921456e-05, + "loss": 0.1042, + "step": 324410 + }, + { + "epoch": 0.72, + "learning_rate": 1.3839399566005234e-05, + "loss": 0.1042, + "step": 324420 + }, + { + "epoch": 0.72, + "learning_rate": 1.3838281022795912e-05, + "loss": 0.1065, + "step": 324430 + }, + { + "epoch": 0.72, + "learning_rate": 1.3837162479586588e-05, + "loss": 0.1042, + "step": 324440 + }, + { + "epoch": 0.72, + "learning_rate": 1.3836043936377263e-05, + "loss": 0.1033, + "step": 324450 + }, + { + "epoch": 0.72, + "learning_rate": 1.3834925393167939e-05, + "loss": 0.111, + "step": 324460 + }, + { + "epoch": 0.72, + "learning_rate": 1.3833806849958614e-05, + "loss": 0.1079, + "step": 324470 + }, + { + "epoch": 0.72, + "learning_rate": 1.383268830674929e-05, + "loss": 0.1043, + "step": 324480 + }, + { + "epoch": 0.72, + "learning_rate": 1.3831681617860897e-05, + "loss": 0.1091, + "step": 324490 + }, + { + "epoch": 0.72, + "learning_rate": 1.3830563074651577e-05, + "loss": 0.1074, + "step": 324500 + }, + { + "epoch": 0.72, + "learning_rate": 1.3829444531442251e-05, + "loss": 0.1129, + "step": 324510 + }, + { + "epoch": 0.72, + "learning_rate": 1.3828325988232926e-05, + "loss": 0.1069, + "step": 324520 + }, + { + "epoch": 0.72, + "learning_rate": 1.3827207445023602e-05, + "loss": 0.1022, + "step": 324530 + }, + { + "epoch": 0.72, + "learning_rate": 1.3826088901814276e-05, + "loss": 0.1072, + "step": 324540 + }, + { + "epoch": 0.72, + "learning_rate": 1.3824970358604953e-05, + "loss": 0.1028, + "step": 324550 + }, + { + "epoch": 0.72, + "learning_rate": 1.382385181539563e-05, + "loss": 0.1054, + "step": 324560 + }, + { + "epoch": 0.72, + "learning_rate": 1.3822733272186305e-05, + "loss": 0.1075, + "step": 324570 + }, + { + "epoch": 0.72, + "learning_rate": 1.3821614728976981e-05, + "loss": 0.1081, + "step": 324580 + }, + { + "epoch": 0.72, + "learning_rate": 1.3820496185767656e-05, + "loss": 0.1093, + "step": 324590 + }, + { + "epoch": 0.72, + "learning_rate": 1.3819377642558332e-05, + "loss": 0.1059, + "step": 324600 + }, + { + "epoch": 0.72, + "learning_rate": 1.381825909934901e-05, + "loss": 0.1094, + "step": 324610 + }, + { + "epoch": 0.72, + "learning_rate": 1.3817140556139685e-05, + "loss": 0.104, + "step": 324620 + }, + { + "epoch": 0.72, + "learning_rate": 1.381602201293036e-05, + "loss": 0.1096, + "step": 324630 + }, + { + "epoch": 0.72, + "learning_rate": 1.3814903469721035e-05, + "loss": 0.1073, + "step": 324640 + }, + { + "epoch": 0.72, + "learning_rate": 1.3813784926511712e-05, + "loss": 0.1054, + "step": 324650 + }, + { + "epoch": 0.72, + "learning_rate": 1.381266638330239e-05, + "loss": 0.106, + "step": 324660 + }, + { + "epoch": 0.72, + "learning_rate": 1.3811547840093064e-05, + "loss": 0.1105, + "step": 324670 + }, + { + "epoch": 0.72, + "learning_rate": 1.381042929688374e-05, + "loss": 0.1101, + "step": 324680 + }, + { + "epoch": 0.72, + "learning_rate": 1.3809310753674415e-05, + "loss": 0.1068, + "step": 324690 + }, + { + "epoch": 0.72, + "learning_rate": 1.380819221046509e-05, + "loss": 0.1081, + "step": 324700 + }, + { + "epoch": 0.72, + "learning_rate": 1.3807073667255766e-05, + "loss": 0.1058, + "step": 324710 + }, + { + "epoch": 0.72, + "learning_rate": 1.3805955124046444e-05, + "loss": 0.1069, + "step": 324720 + }, + { + "epoch": 0.72, + "learning_rate": 1.3804836580837118e-05, + "loss": 0.1014, + "step": 324730 + }, + { + "epoch": 0.72, + "learning_rate": 1.3803718037627794e-05, + "loss": 0.1088, + "step": 324740 + }, + { + "epoch": 0.72, + "learning_rate": 1.3802599494418469e-05, + "loss": 0.1079, + "step": 324750 + }, + { + "epoch": 0.72, + "learning_rate": 1.3801480951209145e-05, + "loss": 0.1079, + "step": 324760 + }, + { + "epoch": 0.72, + "learning_rate": 1.3800362407999823e-05, + "loss": 0.1086, + "step": 324770 + }, + { + "epoch": 0.72, + "learning_rate": 1.3799243864790498e-05, + "loss": 0.1048, + "step": 324780 + }, + { + "epoch": 0.72, + "learning_rate": 1.3798125321581174e-05, + "loss": 0.1048, + "step": 324790 + }, + { + "epoch": 0.72, + "learning_rate": 1.3797006778371848e-05, + "loss": 0.1065, + "step": 324800 + }, + { + "epoch": 0.73, + "learning_rate": 1.3795888235162525e-05, + "loss": 0.1074, + "step": 324810 + }, + { + "epoch": 0.73, + "learning_rate": 1.3794769691953202e-05, + "loss": 0.108, + "step": 324820 + }, + { + "epoch": 0.73, + "learning_rate": 1.3793651148743877e-05, + "loss": 0.1043, + "step": 324830 + }, + { + "epoch": 0.73, + "learning_rate": 1.3792532605534553e-05, + "loss": 0.1063, + "step": 324840 + }, + { + "epoch": 0.73, + "learning_rate": 1.3791414062325228e-05, + "loss": 0.1062, + "step": 324850 + }, + { + "epoch": 0.73, + "learning_rate": 1.3790295519115904e-05, + "loss": 0.1042, + "step": 324860 + }, + { + "epoch": 0.73, + "learning_rate": 1.3789176975906579e-05, + "loss": 0.1036, + "step": 324870 + }, + { + "epoch": 0.73, + "learning_rate": 1.3788058432697257e-05, + "loss": 0.1079, + "step": 324880 + }, + { + "epoch": 0.73, + "learning_rate": 1.3786939889487933e-05, + "loss": 0.1085, + "step": 324890 + }, + { + "epoch": 0.73, + "learning_rate": 1.3785821346278607e-05, + "loss": 0.1019, + "step": 324900 + }, + { + "epoch": 0.73, + "learning_rate": 1.3784702803069282e-05, + "loss": 0.1096, + "step": 324910 + }, + { + "epoch": 0.73, + "learning_rate": 1.3783584259859958e-05, + "loss": 0.1052, + "step": 324920 + }, + { + "epoch": 0.73, + "learning_rate": 1.3782465716650636e-05, + "loss": 0.111, + "step": 324930 + }, + { + "epoch": 0.73, + "learning_rate": 1.378134717344131e-05, + "loss": 0.1059, + "step": 324940 + }, + { + "epoch": 0.73, + "learning_rate": 1.3780228630231987e-05, + "loss": 0.1076, + "step": 324950 + }, + { + "epoch": 0.73, + "learning_rate": 1.3779110087022661e-05, + "loss": 0.1035, + "step": 324960 + }, + { + "epoch": 0.73, + "learning_rate": 1.3777991543813338e-05, + "loss": 0.1056, + "step": 324970 + }, + { + "epoch": 0.73, + "learning_rate": 1.3776873000604015e-05, + "loss": 0.1067, + "step": 324980 + }, + { + "epoch": 0.73, + "learning_rate": 1.377575445739469e-05, + "loss": 0.106, + "step": 324990 + }, + { + "epoch": 0.73, + "learning_rate": 1.3774635914185366e-05, + "loss": 0.104, + "step": 325000 + }, + { + "epoch": 0.73, + "learning_rate": 1.377351737097604e-05, + "loss": 0.1045, + "step": 325010 + }, + { + "epoch": 0.73, + "learning_rate": 1.3772398827766717e-05, + "loss": 0.1033, + "step": 325020 + }, + { + "epoch": 0.73, + "learning_rate": 1.3771280284557392e-05, + "loss": 0.1056, + "step": 325030 + }, + { + "epoch": 0.73, + "learning_rate": 1.377016174134807e-05, + "loss": 0.1036, + "step": 325040 + }, + { + "epoch": 0.73, + "learning_rate": 1.3769043198138746e-05, + "loss": 0.1122, + "step": 325050 + }, + { + "epoch": 0.73, + "learning_rate": 1.376792465492942e-05, + "loss": 0.1083, + "step": 325060 + }, + { + "epoch": 0.73, + "learning_rate": 1.3766806111720096e-05, + "loss": 0.102, + "step": 325070 + }, + { + "epoch": 0.73, + "learning_rate": 1.3765687568510771e-05, + "loss": 0.1109, + "step": 325080 + }, + { + "epoch": 0.73, + "learning_rate": 1.3764569025301449e-05, + "loss": 0.1074, + "step": 325090 + }, + { + "epoch": 0.73, + "learning_rate": 1.3763450482092125e-05, + "loss": 0.11, + "step": 325100 + }, + { + "epoch": 0.73, + "learning_rate": 1.37623319388828e-05, + "loss": 0.1058, + "step": 325110 + }, + { + "epoch": 0.73, + "learning_rate": 1.3761213395673476e-05, + "loss": 0.1046, + "step": 325120 + }, + { + "epoch": 0.73, + "learning_rate": 1.376009485246415e-05, + "loss": 0.1089, + "step": 325130 + }, + { + "epoch": 0.73, + "learning_rate": 1.3758976309254828e-05, + "loss": 0.1039, + "step": 325140 + }, + { + "epoch": 0.73, + "learning_rate": 1.3757857766045505e-05, + "loss": 0.1088, + "step": 325150 + }, + { + "epoch": 0.73, + "learning_rate": 1.375673922283618e-05, + "loss": 0.1076, + "step": 325160 + }, + { + "epoch": 0.73, + "learning_rate": 1.3755620679626854e-05, + "loss": 0.103, + "step": 325170 + }, + { + "epoch": 0.73, + "learning_rate": 1.375450213641753e-05, + "loss": 0.1087, + "step": 325180 + }, + { + "epoch": 0.73, + "learning_rate": 1.3753383593208205e-05, + "loss": 0.1084, + "step": 325190 + }, + { + "epoch": 0.73, + "learning_rate": 1.3752265049998882e-05, + "loss": 0.1086, + "step": 325200 + }, + { + "epoch": 0.73, + "learning_rate": 1.3751146506789559e-05, + "loss": 0.11, + "step": 325210 + }, + { + "epoch": 0.73, + "learning_rate": 1.3750027963580233e-05, + "loss": 0.1035, + "step": 325220 + }, + { + "epoch": 0.73, + "learning_rate": 1.374890942037091e-05, + "loss": 0.1052, + "step": 325230 + }, + { + "epoch": 0.73, + "learning_rate": 1.3747790877161584e-05, + "loss": 0.1062, + "step": 325240 + }, + { + "epoch": 0.73, + "learning_rate": 1.3746672333952262e-05, + "loss": 0.1085, + "step": 325250 + }, + { + "epoch": 0.73, + "learning_rate": 1.3745553790742938e-05, + "loss": 0.1073, + "step": 325260 + }, + { + "epoch": 0.73, + "learning_rate": 1.3744435247533613e-05, + "loss": 0.104, + "step": 325270 + }, + { + "epoch": 0.73, + "learning_rate": 1.3743316704324289e-05, + "loss": 0.1039, + "step": 325280 + }, + { + "epoch": 0.73, + "learning_rate": 1.3742198161114963e-05, + "loss": 0.1103, + "step": 325290 + }, + { + "epoch": 0.73, + "learning_rate": 1.3741079617905641e-05, + "loss": 0.1056, + "step": 325300 + }, + { + "epoch": 0.73, + "learning_rate": 1.3739961074696318e-05, + "loss": 0.1056, + "step": 325310 + }, + { + "epoch": 0.73, + "learning_rate": 1.3738842531486992e-05, + "loss": 0.1096, + "step": 325320 + }, + { + "epoch": 0.73, + "learning_rate": 1.3737723988277668e-05, + "loss": 0.1072, + "step": 325330 + }, + { + "epoch": 0.73, + "learning_rate": 1.3736605445068343e-05, + "loss": 0.1057, + "step": 325340 + }, + { + "epoch": 0.73, + "learning_rate": 1.3735486901859017e-05, + "loss": 0.1066, + "step": 325350 + }, + { + "epoch": 0.73, + "learning_rate": 1.3734368358649697e-05, + "loss": 0.1076, + "step": 325360 + }, + { + "epoch": 0.73, + "learning_rate": 1.3733249815440372e-05, + "loss": 0.1092, + "step": 325370 + }, + { + "epoch": 0.73, + "learning_rate": 1.3732131272231046e-05, + "loss": 0.1113, + "step": 325380 + }, + { + "epoch": 0.73, + "learning_rate": 1.3731012729021722e-05, + "loss": 0.1063, + "step": 325390 + }, + { + "epoch": 0.73, + "learning_rate": 1.3729894185812397e-05, + "loss": 0.1068, + "step": 325400 + }, + { + "epoch": 0.73, + "learning_rate": 1.3728775642603075e-05, + "loss": 0.106, + "step": 325410 + }, + { + "epoch": 0.73, + "learning_rate": 1.3727657099393751e-05, + "loss": 0.1101, + "step": 325420 + }, + { + "epoch": 0.73, + "learning_rate": 1.3726538556184426e-05, + "loss": 0.106, + "step": 325430 + }, + { + "epoch": 0.73, + "learning_rate": 1.3725420012975102e-05, + "loss": 0.1065, + "step": 325440 + }, + { + "epoch": 0.73, + "learning_rate": 1.3724301469765776e-05, + "loss": 0.1061, + "step": 325450 + }, + { + "epoch": 0.73, + "learning_rate": 1.3723182926556454e-05, + "loss": 0.11, + "step": 325460 + }, + { + "epoch": 0.73, + "learning_rate": 1.372206438334713e-05, + "loss": 0.1099, + "step": 325470 + }, + { + "epoch": 0.73, + "learning_rate": 1.3720945840137805e-05, + "loss": 0.109, + "step": 325480 + }, + { + "epoch": 0.73, + "learning_rate": 1.3719827296928481e-05, + "loss": 0.1064, + "step": 325490 + }, + { + "epoch": 0.73, + "learning_rate": 1.3718708753719156e-05, + "loss": 0.1062, + "step": 325500 + }, + { + "epoch": 0.73, + "learning_rate": 1.3717590210509832e-05, + "loss": 0.1097, + "step": 325510 + }, + { + "epoch": 0.73, + "learning_rate": 1.371647166730051e-05, + "loss": 0.1051, + "step": 325520 + }, + { + "epoch": 0.73, + "learning_rate": 1.3715353124091185e-05, + "loss": 0.1075, + "step": 325530 + }, + { + "epoch": 0.73, + "learning_rate": 1.371423458088186e-05, + "loss": 0.1083, + "step": 325540 + }, + { + "epoch": 0.73, + "learning_rate": 1.3713116037672535e-05, + "loss": 0.1051, + "step": 325550 + }, + { + "epoch": 0.73, + "learning_rate": 1.371199749446321e-05, + "loss": 0.1076, + "step": 325560 + }, + { + "epoch": 0.73, + "learning_rate": 1.371087895125389e-05, + "loss": 0.1049, + "step": 325570 + }, + { + "epoch": 0.73, + "learning_rate": 1.3709760408044564e-05, + "loss": 0.1046, + "step": 325580 + }, + { + "epoch": 0.73, + "learning_rate": 1.3708641864835239e-05, + "loss": 0.1105, + "step": 325590 + }, + { + "epoch": 0.73, + "learning_rate": 1.3707523321625915e-05, + "loss": 0.1057, + "step": 325600 + }, + { + "epoch": 0.73, + "learning_rate": 1.370640477841659e-05, + "loss": 0.1048, + "step": 325610 + }, + { + "epoch": 0.73, + "learning_rate": 1.3705286235207267e-05, + "loss": 0.1118, + "step": 325620 + }, + { + "epoch": 0.73, + "learning_rate": 1.3704167691997944e-05, + "loss": 0.1055, + "step": 325630 + }, + { + "epoch": 0.73, + "learning_rate": 1.3703049148788618e-05, + "loss": 0.1086, + "step": 325640 + }, + { + "epoch": 0.73, + "learning_rate": 1.3701930605579294e-05, + "loss": 0.1085, + "step": 325650 + }, + { + "epoch": 0.73, + "learning_rate": 1.3700812062369969e-05, + "loss": 0.1066, + "step": 325660 + }, + { + "epoch": 0.73, + "learning_rate": 1.3699693519160645e-05, + "loss": 0.1036, + "step": 325670 + }, + { + "epoch": 0.73, + "learning_rate": 1.3698574975951323e-05, + "loss": 0.1122, + "step": 325680 + }, + { + "epoch": 0.73, + "learning_rate": 1.3697456432741998e-05, + "loss": 0.1068, + "step": 325690 + }, + { + "epoch": 0.73, + "learning_rate": 1.3696337889532674e-05, + "loss": 0.109, + "step": 325700 + }, + { + "epoch": 0.73, + "learning_rate": 1.3695219346323348e-05, + "loss": 0.1099, + "step": 325710 + }, + { + "epoch": 0.73, + "learning_rate": 1.3694100803114025e-05, + "loss": 0.1095, + "step": 325720 + }, + { + "epoch": 0.73, + "learning_rate": 1.3692982259904702e-05, + "loss": 0.1032, + "step": 325730 + }, + { + "epoch": 0.73, + "learning_rate": 1.3691863716695377e-05, + "loss": 0.1108, + "step": 325740 + }, + { + "epoch": 0.73, + "learning_rate": 1.3690745173486053e-05, + "loss": 0.1072, + "step": 325750 + }, + { + "epoch": 0.73, + "learning_rate": 1.3689626630276728e-05, + "loss": 0.1117, + "step": 325760 + }, + { + "epoch": 0.73, + "learning_rate": 1.3688508087067402e-05, + "loss": 0.1094, + "step": 325770 + }, + { + "epoch": 0.73, + "learning_rate": 1.3687389543858082e-05, + "loss": 0.1089, + "step": 325780 + }, + { + "epoch": 0.73, + "learning_rate": 1.3686271000648756e-05, + "loss": 0.1079, + "step": 325790 + }, + { + "epoch": 0.73, + "learning_rate": 1.3685152457439431e-05, + "loss": 0.1074, + "step": 325800 + }, + { + "epoch": 0.73, + "learning_rate": 1.3684033914230107e-05, + "loss": 0.1092, + "step": 325810 + }, + { + "epoch": 0.73, + "learning_rate": 1.3682915371020782e-05, + "loss": 0.1058, + "step": 325820 + }, + { + "epoch": 0.73, + "learning_rate": 1.3681796827811458e-05, + "loss": 0.1071, + "step": 325830 + }, + { + "epoch": 0.73, + "learning_rate": 1.3680678284602136e-05, + "loss": 0.1034, + "step": 325840 + }, + { + "epoch": 0.73, + "learning_rate": 1.367955974139281e-05, + "loss": 0.1046, + "step": 325850 + }, + { + "epoch": 0.73, + "learning_rate": 1.3678441198183487e-05, + "loss": 0.1093, + "step": 325860 + }, + { + "epoch": 0.73, + "learning_rate": 1.3677322654974161e-05, + "loss": 0.1036, + "step": 325870 + }, + { + "epoch": 0.73, + "learning_rate": 1.3676204111764838e-05, + "loss": 0.104, + "step": 325880 + }, + { + "epoch": 0.73, + "learning_rate": 1.3675085568555515e-05, + "loss": 0.1059, + "step": 325890 + }, + { + "epoch": 0.73, + "learning_rate": 1.367396702534619e-05, + "loss": 0.105, + "step": 325900 + }, + { + "epoch": 0.73, + "learning_rate": 1.3672848482136866e-05, + "loss": 0.1072, + "step": 325910 + }, + { + "epoch": 0.73, + "learning_rate": 1.367172993892754e-05, + "loss": 0.1063, + "step": 325920 + }, + { + "epoch": 0.73, + "learning_rate": 1.3670611395718217e-05, + "loss": 0.1091, + "step": 325930 + }, + { + "epoch": 0.73, + "learning_rate": 1.3669492852508895e-05, + "loss": 0.1037, + "step": 325940 + }, + { + "epoch": 0.73, + "learning_rate": 1.366837430929957e-05, + "loss": 0.1071, + "step": 325950 + }, + { + "epoch": 0.73, + "learning_rate": 1.3667255766090246e-05, + "loss": 0.1057, + "step": 325960 + }, + { + "epoch": 0.73, + "learning_rate": 1.366613722288092e-05, + "loss": 0.106, + "step": 325970 + }, + { + "epoch": 0.73, + "learning_rate": 1.3665018679671596e-05, + "loss": 0.1041, + "step": 325980 + }, + { + "epoch": 0.73, + "learning_rate": 1.3663900136462271e-05, + "loss": 0.1055, + "step": 325990 + }, + { + "epoch": 0.73, + "learning_rate": 1.3662781593252949e-05, + "loss": 0.1047, + "step": 326000 + }, + { + "epoch": 0.73, + "learning_rate": 1.3661663050043625e-05, + "loss": 0.1101, + "step": 326010 + }, + { + "epoch": 0.73, + "learning_rate": 1.36605445068343e-05, + "loss": 0.1062, + "step": 326020 + }, + { + "epoch": 0.73, + "learning_rate": 1.3659425963624974e-05, + "loss": 0.1054, + "step": 326030 + }, + { + "epoch": 0.73, + "learning_rate": 1.365830742041565e-05, + "loss": 0.1102, + "step": 326040 + }, + { + "epoch": 0.73, + "learning_rate": 1.3657188877206328e-05, + "loss": 0.1054, + "step": 326050 + }, + { + "epoch": 0.73, + "learning_rate": 1.3656070333997003e-05, + "loss": 0.108, + "step": 326060 + }, + { + "epoch": 0.73, + "learning_rate": 1.365495179078768e-05, + "loss": 0.1059, + "step": 326070 + }, + { + "epoch": 0.73, + "learning_rate": 1.3653833247578354e-05, + "loss": 0.103, + "step": 326080 + }, + { + "epoch": 0.73, + "learning_rate": 1.365271470436903e-05, + "loss": 0.1104, + "step": 326090 + }, + { + "epoch": 0.73, + "learning_rate": 1.3651596161159708e-05, + "loss": 0.1045, + "step": 326100 + }, + { + "epoch": 0.73, + "learning_rate": 1.3650477617950382e-05, + "loss": 0.1068, + "step": 326110 + }, + { + "epoch": 0.73, + "learning_rate": 1.3649359074741059e-05, + "loss": 0.1075, + "step": 326120 + }, + { + "epoch": 0.73, + "learning_rate": 1.3648240531531733e-05, + "loss": 0.108, + "step": 326130 + }, + { + "epoch": 0.73, + "learning_rate": 1.364712198832241e-05, + "loss": 0.1057, + "step": 326140 + }, + { + "epoch": 0.73, + "learning_rate": 1.3646003445113084e-05, + "loss": 0.1097, + "step": 326150 + }, + { + "epoch": 0.73, + "learning_rate": 1.3644884901903762e-05, + "loss": 0.1077, + "step": 326160 + }, + { + "epoch": 0.73, + "learning_rate": 1.3643766358694438e-05, + "loss": 0.1074, + "step": 326170 + }, + { + "epoch": 0.73, + "learning_rate": 1.3642647815485113e-05, + "loss": 0.1049, + "step": 326180 + }, + { + "epoch": 0.73, + "learning_rate": 1.3641529272275789e-05, + "loss": 0.1068, + "step": 326190 + }, + { + "epoch": 0.73, + "learning_rate": 1.3640410729066463e-05, + "loss": 0.1052, + "step": 326200 + }, + { + "epoch": 0.73, + "learning_rate": 1.3639292185857141e-05, + "loss": 0.1093, + "step": 326210 + }, + { + "epoch": 0.73, + "learning_rate": 1.3638173642647818e-05, + "loss": 0.105, + "step": 326220 + }, + { + "epoch": 0.73, + "learning_rate": 1.3637055099438492e-05, + "loss": 0.1092, + "step": 326230 + }, + { + "epoch": 0.73, + "learning_rate": 1.3635936556229167e-05, + "loss": 0.1061, + "step": 326240 + }, + { + "epoch": 0.73, + "learning_rate": 1.3634818013019843e-05, + "loss": 0.1094, + "step": 326250 + }, + { + "epoch": 0.73, + "learning_rate": 1.363369946981052e-05, + "loss": 0.1066, + "step": 326260 + }, + { + "epoch": 0.73, + "learning_rate": 1.3632580926601195e-05, + "loss": 0.1038, + "step": 326270 + }, + { + "epoch": 0.73, + "learning_rate": 1.3631462383391872e-05, + "loss": 0.1055, + "step": 326280 + }, + { + "epoch": 0.73, + "learning_rate": 1.3630343840182546e-05, + "loss": 0.1086, + "step": 326290 + }, + { + "epoch": 0.73, + "learning_rate": 1.3629225296973222e-05, + "loss": 0.1036, + "step": 326300 + }, + { + "epoch": 0.73, + "learning_rate": 1.3628106753763897e-05, + "loss": 0.109, + "step": 326310 + }, + { + "epoch": 0.73, + "learning_rate": 1.3626988210554575e-05, + "loss": 0.1084, + "step": 326320 + }, + { + "epoch": 0.73, + "learning_rate": 1.3625869667345251e-05, + "loss": 0.1081, + "step": 326330 + }, + { + "epoch": 0.73, + "learning_rate": 1.3624751124135926e-05, + "loss": 0.1103, + "step": 326340 + }, + { + "epoch": 0.73, + "learning_rate": 1.3623632580926602e-05, + "loss": 0.1064, + "step": 326350 + }, + { + "epoch": 0.73, + "learning_rate": 1.3622514037717276e-05, + "loss": 0.1056, + "step": 326360 + }, + { + "epoch": 0.73, + "learning_rate": 1.3621395494507954e-05, + "loss": 0.1065, + "step": 326370 + }, + { + "epoch": 0.73, + "learning_rate": 1.362027695129863e-05, + "loss": 0.1094, + "step": 326380 + }, + { + "epoch": 0.73, + "learning_rate": 1.3619158408089305e-05, + "loss": 0.1075, + "step": 326390 + }, + { + "epoch": 0.73, + "learning_rate": 1.3618039864879981e-05, + "loss": 0.1065, + "step": 326400 + }, + { + "epoch": 0.73, + "learning_rate": 1.3616921321670656e-05, + "loss": 0.1076, + "step": 326410 + }, + { + "epoch": 0.73, + "learning_rate": 1.361580277846133e-05, + "loss": 0.1049, + "step": 326420 + }, + { + "epoch": 0.73, + "learning_rate": 1.361468423525201e-05, + "loss": 0.1063, + "step": 326430 + }, + { + "epoch": 0.73, + "learning_rate": 1.3613565692042685e-05, + "loss": 0.1038, + "step": 326440 + }, + { + "epoch": 0.73, + "learning_rate": 1.3612447148833359e-05, + "loss": 0.1038, + "step": 326450 + }, + { + "epoch": 0.73, + "learning_rate": 1.3611328605624035e-05, + "loss": 0.1065, + "step": 326460 + }, + { + "epoch": 0.73, + "learning_rate": 1.361021006241471e-05, + "loss": 0.1087, + "step": 326470 + }, + { + "epoch": 0.73, + "learning_rate": 1.3609091519205388e-05, + "loss": 0.1062, + "step": 326480 + }, + { + "epoch": 0.73, + "learning_rate": 1.3607972975996064e-05, + "loss": 0.1082, + "step": 326490 + }, + { + "epoch": 0.73, + "learning_rate": 1.3606966287107673e-05, + "loss": 0.1085, + "step": 326500 + }, + { + "epoch": 0.73, + "learning_rate": 1.3605847743898347e-05, + "loss": 0.109, + "step": 326510 + }, + { + "epoch": 0.73, + "learning_rate": 1.3604729200689024e-05, + "loss": 0.1066, + "step": 326520 + }, + { + "epoch": 0.73, + "learning_rate": 1.3603610657479698e-05, + "loss": 0.1038, + "step": 326530 + }, + { + "epoch": 0.73, + "learning_rate": 1.3602492114270374e-05, + "loss": 0.1121, + "step": 326540 + }, + { + "epoch": 0.73, + "learning_rate": 1.3601373571061052e-05, + "loss": 0.1108, + "step": 326550 + }, + { + "epoch": 0.73, + "learning_rate": 1.3600255027851727e-05, + "loss": 0.1058, + "step": 326560 + }, + { + "epoch": 0.73, + "learning_rate": 1.3599136484642403e-05, + "loss": 0.1075, + "step": 326570 + }, + { + "epoch": 0.73, + "learning_rate": 1.3598017941433078e-05, + "loss": 0.1074, + "step": 326580 + }, + { + "epoch": 0.73, + "learning_rate": 1.3596899398223754e-05, + "loss": 0.1041, + "step": 326590 + }, + { + "epoch": 0.73, + "learning_rate": 1.3595780855014432e-05, + "loss": 0.1019, + "step": 326600 + }, + { + "epoch": 0.73, + "learning_rate": 1.3594662311805106e-05, + "loss": 0.1112, + "step": 326610 + }, + { + "epoch": 0.73, + "learning_rate": 1.3593543768595783e-05, + "loss": 0.1064, + "step": 326620 + }, + { + "epoch": 0.73, + "learning_rate": 1.3592425225386457e-05, + "loss": 0.1066, + "step": 326630 + }, + { + "epoch": 0.73, + "learning_rate": 1.3591306682177132e-05, + "loss": 0.1089, + "step": 326640 + }, + { + "epoch": 0.73, + "learning_rate": 1.3590188138967808e-05, + "loss": 0.1045, + "step": 326650 + }, + { + "epoch": 0.73, + "learning_rate": 1.3589069595758486e-05, + "loss": 0.1088, + "step": 326660 + }, + { + "epoch": 0.73, + "learning_rate": 1.358795105254916e-05, + "loss": 0.1041, + "step": 326670 + }, + { + "epoch": 0.73, + "learning_rate": 1.3586832509339837e-05, + "loss": 0.1065, + "step": 326680 + }, + { + "epoch": 0.73, + "learning_rate": 1.3585713966130511e-05, + "loss": 0.1048, + "step": 326690 + }, + { + "epoch": 0.73, + "learning_rate": 1.3584595422921187e-05, + "loss": 0.1118, + "step": 326700 + }, + { + "epoch": 0.73, + "learning_rate": 1.3583476879711865e-05, + "loss": 0.1041, + "step": 326710 + }, + { + "epoch": 0.73, + "learning_rate": 1.358235833650254e-05, + "loss": 0.1055, + "step": 326720 + }, + { + "epoch": 0.73, + "learning_rate": 1.3581239793293216e-05, + "loss": 0.1084, + "step": 326730 + }, + { + "epoch": 0.73, + "learning_rate": 1.358012125008389e-05, + "loss": 0.1055, + "step": 326740 + }, + { + "epoch": 0.73, + "learning_rate": 1.3579002706874567e-05, + "loss": 0.1045, + "step": 326750 + }, + { + "epoch": 0.73, + "learning_rate": 1.3577884163665245e-05, + "loss": 0.1036, + "step": 326760 + }, + { + "epoch": 0.73, + "learning_rate": 1.357676562045592e-05, + "loss": 0.1063, + "step": 326770 + }, + { + "epoch": 0.73, + "learning_rate": 1.3575647077246596e-05, + "loss": 0.1059, + "step": 326780 + }, + { + "epoch": 0.73, + "learning_rate": 1.357452853403727e-05, + "loss": 0.1063, + "step": 326790 + }, + { + "epoch": 0.73, + "learning_rate": 1.3573409990827946e-05, + "loss": 0.1098, + "step": 326800 + }, + { + "epoch": 0.73, + "learning_rate": 1.357229144761862e-05, + "loss": 0.101, + "step": 326810 + }, + { + "epoch": 0.73, + "learning_rate": 1.3571172904409299e-05, + "loss": 0.1072, + "step": 326820 + }, + { + "epoch": 0.73, + "learning_rate": 1.3570054361199975e-05, + "loss": 0.1027, + "step": 326830 + }, + { + "epoch": 0.73, + "learning_rate": 1.356893581799065e-05, + "loss": 0.1085, + "step": 326840 + }, + { + "epoch": 0.73, + "learning_rate": 1.3567817274781324e-05, + "loss": 0.1043, + "step": 326850 + }, + { + "epoch": 0.73, + "learning_rate": 1.3566698731572e-05, + "loss": 0.1056, + "step": 326860 + }, + { + "epoch": 0.73, + "learning_rate": 1.3565580188362678e-05, + "loss": 0.1047, + "step": 326870 + }, + { + "epoch": 0.73, + "learning_rate": 1.3564461645153353e-05, + "loss": 0.1057, + "step": 326880 + }, + { + "epoch": 0.73, + "learning_rate": 1.3563343101944029e-05, + "loss": 0.1032, + "step": 326890 + }, + { + "epoch": 0.73, + "learning_rate": 1.3562224558734704e-05, + "loss": 0.1092, + "step": 326900 + }, + { + "epoch": 0.73, + "learning_rate": 1.356110601552538e-05, + "loss": 0.1088, + "step": 326910 + }, + { + "epoch": 0.73, + "learning_rate": 1.3559987472316058e-05, + "loss": 0.1065, + "step": 326920 + }, + { + "epoch": 0.73, + "learning_rate": 1.3558868929106732e-05, + "loss": 0.108, + "step": 326930 + }, + { + "epoch": 0.73, + "learning_rate": 1.3557750385897408e-05, + "loss": 0.1058, + "step": 326940 + }, + { + "epoch": 0.73, + "learning_rate": 1.3556631842688083e-05, + "loss": 0.1066, + "step": 326950 + }, + { + "epoch": 0.73, + "learning_rate": 1.355551329947876e-05, + "loss": 0.1079, + "step": 326960 + }, + { + "epoch": 0.73, + "learning_rate": 1.3554394756269434e-05, + "loss": 0.1009, + "step": 326970 + }, + { + "epoch": 0.73, + "learning_rate": 1.3553276213060112e-05, + "loss": 0.1061, + "step": 326980 + }, + { + "epoch": 0.73, + "learning_rate": 1.3552157669850788e-05, + "loss": 0.108, + "step": 326990 + }, + { + "epoch": 0.73, + "learning_rate": 1.3551039126641462e-05, + "loss": 0.1038, + "step": 327000 + }, + { + "epoch": 0.73, + "learning_rate": 1.3549920583432139e-05, + "loss": 0.1063, + "step": 327010 + }, + { + "epoch": 0.73, + "learning_rate": 1.3548802040222813e-05, + "loss": 0.109, + "step": 327020 + }, + { + "epoch": 0.73, + "learning_rate": 1.3547683497013491e-05, + "loss": 0.1097, + "step": 327030 + }, + { + "epoch": 0.73, + "learning_rate": 1.3546564953804167e-05, + "loss": 0.1018, + "step": 327040 + }, + { + "epoch": 0.73, + "learning_rate": 1.3545446410594842e-05, + "loss": 0.1019, + "step": 327050 + }, + { + "epoch": 0.73, + "learning_rate": 1.3544327867385517e-05, + "loss": 0.1037, + "step": 327060 + }, + { + "epoch": 0.73, + "learning_rate": 1.3543209324176193e-05, + "loss": 0.1095, + "step": 327070 + }, + { + "epoch": 0.73, + "learning_rate": 1.354209078096687e-05, + "loss": 0.1064, + "step": 327080 + }, + { + "epoch": 0.73, + "learning_rate": 1.3540972237757545e-05, + "loss": 0.1098, + "step": 327090 + }, + { + "epoch": 0.73, + "learning_rate": 1.3539853694548221e-05, + "loss": 0.1029, + "step": 327100 + }, + { + "epoch": 0.73, + "learning_rate": 1.3538735151338896e-05, + "loss": 0.1033, + "step": 327110 + }, + { + "epoch": 0.73, + "learning_rate": 1.3537616608129572e-05, + "loss": 0.1084, + "step": 327120 + }, + { + "epoch": 0.73, + "learning_rate": 1.3536498064920247e-05, + "loss": 0.1065, + "step": 327130 + }, + { + "epoch": 0.73, + "learning_rate": 1.3535379521710925e-05, + "loss": 0.1125, + "step": 327140 + }, + { + "epoch": 0.73, + "learning_rate": 1.3534260978501601e-05, + "loss": 0.102, + "step": 327150 + }, + { + "epoch": 0.73, + "learning_rate": 1.3533142435292275e-05, + "loss": 0.1086, + "step": 327160 + }, + { + "epoch": 0.73, + "learning_rate": 1.3532023892082952e-05, + "loss": 0.1078, + "step": 327170 + }, + { + "epoch": 0.73, + "learning_rate": 1.3530905348873626e-05, + "loss": 0.1071, + "step": 327180 + }, + { + "epoch": 0.73, + "learning_rate": 1.3529786805664304e-05, + "loss": 0.1065, + "step": 327190 + }, + { + "epoch": 0.73, + "learning_rate": 1.352866826245498e-05, + "loss": 0.1046, + "step": 327200 + }, + { + "epoch": 0.73, + "learning_rate": 1.3527549719245655e-05, + "loss": 0.1054, + "step": 327210 + }, + { + "epoch": 0.73, + "learning_rate": 1.3526431176036331e-05, + "loss": 0.1043, + "step": 327220 + }, + { + "epoch": 0.73, + "learning_rate": 1.3525312632827006e-05, + "loss": 0.1049, + "step": 327230 + }, + { + "epoch": 0.73, + "learning_rate": 1.3524194089617684e-05, + "loss": 0.1106, + "step": 327240 + }, + { + "epoch": 0.73, + "learning_rate": 1.352307554640836e-05, + "loss": 0.1024, + "step": 327250 + }, + { + "epoch": 0.73, + "learning_rate": 1.3521957003199034e-05, + "loss": 0.1074, + "step": 327260 + }, + { + "epoch": 0.73, + "learning_rate": 1.3520838459989709e-05, + "loss": 0.1109, + "step": 327270 + }, + { + "epoch": 0.73, + "learning_rate": 1.3519719916780385e-05, + "loss": 0.106, + "step": 327280 + }, + { + "epoch": 0.73, + "learning_rate": 1.351860137357106e-05, + "loss": 0.1068, + "step": 327290 + }, + { + "epoch": 0.73, + "learning_rate": 1.3517482830361738e-05, + "loss": 0.1107, + "step": 327300 + }, + { + "epoch": 0.73, + "learning_rate": 1.3516364287152414e-05, + "loss": 0.103, + "step": 327310 + }, + { + "epoch": 0.73, + "learning_rate": 1.3515245743943088e-05, + "loss": 0.1086, + "step": 327320 + }, + { + "epoch": 0.73, + "learning_rate": 1.3514127200733765e-05, + "loss": 0.1085, + "step": 327330 + }, + { + "epoch": 0.73, + "learning_rate": 1.351300865752444e-05, + "loss": 0.1068, + "step": 327340 + }, + { + "epoch": 0.73, + "learning_rate": 1.3511890114315117e-05, + "loss": 0.1065, + "step": 327350 + }, + { + "epoch": 0.73, + "learning_rate": 1.3510771571105793e-05, + "loss": 0.1051, + "step": 327360 + }, + { + "epoch": 0.73, + "learning_rate": 1.3509653027896468e-05, + "loss": 0.1109, + "step": 327370 + }, + { + "epoch": 0.73, + "learning_rate": 1.3508534484687144e-05, + "loss": 0.1106, + "step": 327380 + }, + { + "epoch": 0.73, + "learning_rate": 1.3507415941477819e-05, + "loss": 0.1047, + "step": 327390 + }, + { + "epoch": 0.73, + "learning_rate": 1.3506297398268497e-05, + "loss": 0.1019, + "step": 327400 + }, + { + "epoch": 0.73, + "learning_rate": 1.3505178855059173e-05, + "loss": 0.106, + "step": 327410 + }, + { + "epoch": 0.73, + "learning_rate": 1.3504060311849847e-05, + "loss": 0.1038, + "step": 327420 + }, + { + "epoch": 0.73, + "learning_rate": 1.3502941768640524e-05, + "loss": 0.1074, + "step": 327430 + }, + { + "epoch": 0.73, + "learning_rate": 1.3501823225431198e-05, + "loss": 0.1041, + "step": 327440 + }, + { + "epoch": 0.73, + "learning_rate": 1.3500704682221874e-05, + "loss": 0.1042, + "step": 327450 + }, + { + "epoch": 0.73, + "learning_rate": 1.3499586139012552e-05, + "loss": 0.1072, + "step": 327460 + }, + { + "epoch": 0.73, + "learning_rate": 1.3498467595803227e-05, + "loss": 0.1051, + "step": 327470 + }, + { + "epoch": 0.73, + "learning_rate": 1.3497349052593903e-05, + "loss": 0.1082, + "step": 327480 + }, + { + "epoch": 0.73, + "learning_rate": 1.3496230509384578e-05, + "loss": 0.106, + "step": 327490 + }, + { + "epoch": 0.73, + "learning_rate": 1.3495111966175252e-05, + "loss": 0.1078, + "step": 327500 + }, + { + "epoch": 0.73, + "learning_rate": 1.3493993422965932e-05, + "loss": 0.1072, + "step": 327510 + }, + { + "epoch": 0.73, + "learning_rate": 1.3492874879756606e-05, + "loss": 0.1091, + "step": 327520 + }, + { + "epoch": 0.73, + "learning_rate": 1.349175633654728e-05, + "loss": 0.1032, + "step": 327530 + }, + { + "epoch": 0.73, + "learning_rate": 1.3490637793337957e-05, + "loss": 0.1086, + "step": 327540 + }, + { + "epoch": 0.73, + "learning_rate": 1.3489519250128632e-05, + "loss": 0.1031, + "step": 327550 + }, + { + "epoch": 0.73, + "learning_rate": 1.348840070691931e-05, + "loss": 0.1036, + "step": 327560 + }, + { + "epoch": 0.73, + "learning_rate": 1.3487282163709986e-05, + "loss": 0.1022, + "step": 327570 + }, + { + "epoch": 0.73, + "learning_rate": 1.348616362050066e-05, + "loss": 0.107, + "step": 327580 + }, + { + "epoch": 0.73, + "learning_rate": 1.3485045077291337e-05, + "loss": 0.1063, + "step": 327590 + }, + { + "epoch": 0.73, + "learning_rate": 1.3483926534082011e-05, + "loss": 0.1081, + "step": 327600 + }, + { + "epoch": 0.73, + "learning_rate": 1.3482807990872687e-05, + "loss": 0.1018, + "step": 327610 + }, + { + "epoch": 0.73, + "learning_rate": 1.3481689447663365e-05, + "loss": 0.1081, + "step": 327620 + }, + { + "epoch": 0.73, + "learning_rate": 1.348057090445404e-05, + "loss": 0.1079, + "step": 327630 + }, + { + "epoch": 0.73, + "learning_rate": 1.3479452361244716e-05, + "loss": 0.1022, + "step": 327640 + }, + { + "epoch": 0.73, + "learning_rate": 1.347833381803539e-05, + "loss": 0.1095, + "step": 327650 + }, + { + "epoch": 0.73, + "learning_rate": 1.3477215274826067e-05, + "loss": 0.1076, + "step": 327660 + }, + { + "epoch": 0.73, + "learning_rate": 1.3476096731616745e-05, + "loss": 0.1076, + "step": 327670 + }, + { + "epoch": 0.73, + "learning_rate": 1.347497818840742e-05, + "loss": 0.1096, + "step": 327680 + }, + { + "epoch": 0.73, + "learning_rate": 1.3473859645198096e-05, + "loss": 0.1057, + "step": 327690 + }, + { + "epoch": 0.73, + "learning_rate": 1.347274110198877e-05, + "loss": 0.1044, + "step": 327700 + }, + { + "epoch": 0.73, + "learning_rate": 1.3471622558779445e-05, + "loss": 0.1052, + "step": 327710 + }, + { + "epoch": 0.73, + "learning_rate": 1.3470504015570124e-05, + "loss": 0.1062, + "step": 327720 + }, + { + "epoch": 0.73, + "learning_rate": 1.3469385472360799e-05, + "loss": 0.1025, + "step": 327730 + }, + { + "epoch": 0.73, + "learning_rate": 1.3468266929151473e-05, + "loss": 0.1102, + "step": 327740 + }, + { + "epoch": 0.73, + "learning_rate": 1.346714838594215e-05, + "loss": 0.1058, + "step": 327750 + }, + { + "epoch": 0.73, + "learning_rate": 1.3466029842732824e-05, + "loss": 0.1065, + "step": 327760 + }, + { + "epoch": 0.73, + "learning_rate": 1.34649112995235e-05, + "loss": 0.1097, + "step": 327770 + }, + { + "epoch": 0.73, + "learning_rate": 1.3463792756314178e-05, + "loss": 0.109, + "step": 327780 + }, + { + "epoch": 0.73, + "learning_rate": 1.3462674213104853e-05, + "loss": 0.1057, + "step": 327790 + }, + { + "epoch": 0.73, + "learning_rate": 1.3461555669895529e-05, + "loss": 0.1074, + "step": 327800 + }, + { + "epoch": 0.73, + "learning_rate": 1.3460437126686204e-05, + "loss": 0.1038, + "step": 327810 + }, + { + "epoch": 0.73, + "learning_rate": 1.345931858347688e-05, + "loss": 0.1057, + "step": 327820 + }, + { + "epoch": 0.73, + "learning_rate": 1.3458200040267558e-05, + "loss": 0.1063, + "step": 327830 + }, + { + "epoch": 0.73, + "learning_rate": 1.3457081497058232e-05, + "loss": 0.1071, + "step": 327840 + }, + { + "epoch": 0.73, + "learning_rate": 1.3455962953848908e-05, + "loss": 0.109, + "step": 327850 + }, + { + "epoch": 0.73, + "learning_rate": 1.3454844410639583e-05, + "loss": 0.111, + "step": 327860 + }, + { + "epoch": 0.73, + "learning_rate": 1.345372586743026e-05, + "loss": 0.1053, + "step": 327870 + }, + { + "epoch": 0.73, + "learning_rate": 1.3452607324220937e-05, + "loss": 0.1042, + "step": 327880 + }, + { + "epoch": 0.73, + "learning_rate": 1.3451488781011612e-05, + "loss": 0.109, + "step": 327890 + }, + { + "epoch": 0.73, + "learning_rate": 1.3450370237802288e-05, + "loss": 0.1066, + "step": 327900 + }, + { + "epoch": 0.73, + "learning_rate": 1.3449251694592962e-05, + "loss": 0.1042, + "step": 327910 + }, + { + "epoch": 0.73, + "learning_rate": 1.3448133151383637e-05, + "loss": 0.1062, + "step": 327920 + }, + { + "epoch": 0.73, + "learning_rate": 1.3447014608174313e-05, + "loss": 0.102, + "step": 327930 + }, + { + "epoch": 0.73, + "learning_rate": 1.3445896064964991e-05, + "loss": 0.1024, + "step": 327940 + }, + { + "epoch": 0.73, + "learning_rate": 1.3444777521755666e-05, + "loss": 0.1044, + "step": 327950 + }, + { + "epoch": 0.73, + "learning_rate": 1.3443658978546342e-05, + "loss": 0.107, + "step": 327960 + }, + { + "epoch": 0.73, + "learning_rate": 1.3442540435337016e-05, + "loss": 0.1103, + "step": 327970 + }, + { + "epoch": 0.73, + "learning_rate": 1.3441421892127693e-05, + "loss": 0.1071, + "step": 327980 + }, + { + "epoch": 0.73, + "learning_rate": 1.344030334891837e-05, + "loss": 0.1064, + "step": 327990 + }, + { + "epoch": 0.73, + "learning_rate": 1.3439184805709045e-05, + "loss": 0.1068, + "step": 328000 + }, + { + "epoch": 0.73, + "learning_rate": 1.3438066262499721e-05, + "loss": 0.108, + "step": 328010 + }, + { + "epoch": 0.73, + "learning_rate": 1.3436947719290396e-05, + "loss": 0.1087, + "step": 328020 + }, + { + "epoch": 0.73, + "learning_rate": 1.3435829176081072e-05, + "loss": 0.1082, + "step": 328030 + }, + { + "epoch": 0.73, + "learning_rate": 1.343471063287175e-05, + "loss": 0.1071, + "step": 328040 + }, + { + "epoch": 0.73, + "learning_rate": 1.3433592089662425e-05, + "loss": 0.1027, + "step": 328050 + }, + { + "epoch": 0.73, + "learning_rate": 1.3432473546453101e-05, + "loss": 0.1055, + "step": 328060 + }, + { + "epoch": 0.73, + "learning_rate": 1.3431355003243775e-05, + "loss": 0.1038, + "step": 328070 + }, + { + "epoch": 0.73, + "learning_rate": 1.3430236460034452e-05, + "loss": 0.1081, + "step": 328080 + }, + { + "epoch": 0.73, + "learning_rate": 1.3429117916825126e-05, + "loss": 0.1054, + "step": 328090 + }, + { + "epoch": 0.73, + "learning_rate": 1.3427999373615804e-05, + "loss": 0.1062, + "step": 328100 + }, + { + "epoch": 0.73, + "learning_rate": 1.342688083040648e-05, + "loss": 0.1109, + "step": 328110 + }, + { + "epoch": 0.73, + "learning_rate": 1.3425762287197155e-05, + "loss": 0.1049, + "step": 328120 + }, + { + "epoch": 0.73, + "learning_rate": 1.3424643743987831e-05, + "loss": 0.1036, + "step": 328130 + }, + { + "epoch": 0.73, + "learning_rate": 1.3423525200778506e-05, + "loss": 0.1079, + "step": 328140 + }, + { + "epoch": 0.73, + "learning_rate": 1.3422406657569184e-05, + "loss": 0.1066, + "step": 328150 + }, + { + "epoch": 0.73, + "learning_rate": 1.3421288114359858e-05, + "loss": 0.1056, + "step": 328160 + }, + { + "epoch": 0.73, + "learning_rate": 1.3420169571150534e-05, + "loss": 0.1095, + "step": 328170 + }, + { + "epoch": 0.73, + "learning_rate": 1.3419051027941209e-05, + "loss": 0.1112, + "step": 328180 + }, + { + "epoch": 0.73, + "learning_rate": 1.3417932484731885e-05, + "loss": 0.1036, + "step": 328190 + }, + { + "epoch": 0.73, + "learning_rate": 1.3416813941522563e-05, + "loss": 0.0998, + "step": 328200 + }, + { + "epoch": 0.73, + "learning_rate": 1.3415695398313238e-05, + "loss": 0.1042, + "step": 328210 + }, + { + "epoch": 0.73, + "learning_rate": 1.3414576855103914e-05, + "loss": 0.1023, + "step": 328220 + }, + { + "epoch": 0.73, + "learning_rate": 1.3413458311894588e-05, + "loss": 0.1049, + "step": 328230 + }, + { + "epoch": 0.73, + "learning_rate": 1.3412339768685265e-05, + "loss": 0.1066, + "step": 328240 + }, + { + "epoch": 0.73, + "learning_rate": 1.341122122547594e-05, + "loss": 0.1071, + "step": 328250 + }, + { + "epoch": 0.73, + "learning_rate": 1.3410102682266617e-05, + "loss": 0.1051, + "step": 328260 + }, + { + "epoch": 0.73, + "learning_rate": 1.3408984139057293e-05, + "loss": 0.1063, + "step": 328270 + }, + { + "epoch": 0.73, + "learning_rate": 1.3407865595847968e-05, + "loss": 0.1023, + "step": 328280 + }, + { + "epoch": 0.73, + "learning_rate": 1.3406747052638644e-05, + "loss": 0.1077, + "step": 328290 + }, + { + "epoch": 0.73, + "learning_rate": 1.3405628509429319e-05, + "loss": 0.1036, + "step": 328300 + }, + { + "epoch": 0.73, + "learning_rate": 1.3404509966219997e-05, + "loss": 0.1066, + "step": 328310 + }, + { + "epoch": 0.73, + "learning_rate": 1.3403391423010673e-05, + "loss": 0.1085, + "step": 328320 + }, + { + "epoch": 0.73, + "learning_rate": 1.3402272879801347e-05, + "loss": 0.109, + "step": 328330 + }, + { + "epoch": 0.73, + "learning_rate": 1.3401154336592024e-05, + "loss": 0.1105, + "step": 328340 + }, + { + "epoch": 0.73, + "learning_rate": 1.3400035793382698e-05, + "loss": 0.1087, + "step": 328350 + }, + { + "epoch": 0.73, + "learning_rate": 1.3398917250173376e-05, + "loss": 0.1077, + "step": 328360 + }, + { + "epoch": 0.73, + "learning_rate": 1.3397798706964052e-05, + "loss": 0.1138, + "step": 328370 + }, + { + "epoch": 0.73, + "learning_rate": 1.3396680163754727e-05, + "loss": 0.1076, + "step": 328380 + }, + { + "epoch": 0.73, + "learning_rate": 1.3395561620545401e-05, + "loss": 0.1101, + "step": 328390 + }, + { + "epoch": 0.73, + "learning_rate": 1.3394443077336078e-05, + "loss": 0.1033, + "step": 328400 + }, + { + "epoch": 0.73, + "learning_rate": 1.3393324534126752e-05, + "loss": 0.1099, + "step": 328410 + }, + { + "epoch": 0.73, + "learning_rate": 1.339220599091743e-05, + "loss": 0.1016, + "step": 328420 + }, + { + "epoch": 0.73, + "learning_rate": 1.3391087447708106e-05, + "loss": 0.109, + "step": 328430 + }, + { + "epoch": 0.73, + "learning_rate": 1.338996890449878e-05, + "loss": 0.1043, + "step": 328440 + }, + { + "epoch": 0.73, + "learning_rate": 1.3388850361289457e-05, + "loss": 0.1095, + "step": 328450 + }, + { + "epoch": 0.73, + "learning_rate": 1.3387731818080132e-05, + "loss": 0.1094, + "step": 328460 + }, + { + "epoch": 0.73, + "learning_rate": 1.338661327487081e-05, + "loss": 0.11, + "step": 328470 + }, + { + "epoch": 0.73, + "learning_rate": 1.3385494731661486e-05, + "loss": 0.1082, + "step": 328480 + }, + { + "epoch": 0.73, + "learning_rate": 1.338437618845216e-05, + "loss": 0.1071, + "step": 328490 + }, + { + "epoch": 0.73, + "learning_rate": 1.3383257645242837e-05, + "loss": 0.1037, + "step": 328500 + }, + { + "epoch": 0.73, + "learning_rate": 1.3382139102033511e-05, + "loss": 0.1058, + "step": 328510 + }, + { + "epoch": 0.73, + "learning_rate": 1.338113241314512e-05, + "loss": 0.1059, + "step": 328520 + }, + { + "epoch": 0.73, + "learning_rate": 1.3380013869935794e-05, + "loss": 0.1052, + "step": 328530 + }, + { + "epoch": 0.73, + "learning_rate": 1.3378895326726474e-05, + "loss": 0.1065, + "step": 328540 + }, + { + "epoch": 0.73, + "learning_rate": 1.3377776783517149e-05, + "loss": 0.1022, + "step": 328550 + }, + { + "epoch": 0.73, + "learning_rate": 1.3376658240307823e-05, + "loss": 0.1053, + "step": 328560 + }, + { + "epoch": 0.73, + "learning_rate": 1.33755396970985e-05, + "loss": 0.1023, + "step": 328570 + }, + { + "epoch": 0.73, + "learning_rate": 1.3374421153889174e-05, + "loss": 0.1043, + "step": 328580 + }, + { + "epoch": 0.73, + "learning_rate": 1.3373302610679852e-05, + "loss": 0.1075, + "step": 328590 + }, + { + "epoch": 0.73, + "learning_rate": 1.3372184067470528e-05, + "loss": 0.1037, + "step": 328600 + }, + { + "epoch": 0.73, + "learning_rate": 1.3371065524261203e-05, + "loss": 0.1046, + "step": 328610 + }, + { + "epoch": 0.73, + "learning_rate": 1.3369946981051879e-05, + "loss": 0.1013, + "step": 328620 + }, + { + "epoch": 0.73, + "learning_rate": 1.3368828437842553e-05, + "loss": 0.1041, + "step": 328630 + }, + { + "epoch": 0.73, + "learning_rate": 1.336770989463323e-05, + "loss": 0.1015, + "step": 328640 + }, + { + "epoch": 0.73, + "learning_rate": 1.3366591351423908e-05, + "loss": 0.1058, + "step": 328650 + }, + { + "epoch": 0.73, + "learning_rate": 1.3365472808214582e-05, + "loss": 0.1015, + "step": 328660 + }, + { + "epoch": 0.73, + "learning_rate": 1.3364354265005258e-05, + "loss": 0.1099, + "step": 328670 + }, + { + "epoch": 0.73, + "learning_rate": 1.3363235721795933e-05, + "loss": 0.1041, + "step": 328680 + }, + { + "epoch": 0.73, + "learning_rate": 1.3362117178586609e-05, + "loss": 0.1068, + "step": 328690 + }, + { + "epoch": 0.73, + "learning_rate": 1.3360998635377287e-05, + "loss": 0.1046, + "step": 328700 + }, + { + "epoch": 0.73, + "learning_rate": 1.3359880092167962e-05, + "loss": 0.1052, + "step": 328710 + }, + { + "epoch": 0.73, + "learning_rate": 1.3358761548958638e-05, + "loss": 0.1106, + "step": 328720 + }, + { + "epoch": 0.73, + "learning_rate": 1.3357643005749312e-05, + "loss": 0.1063, + "step": 328730 + }, + { + "epoch": 0.73, + "learning_rate": 1.3356524462539987e-05, + "loss": 0.1089, + "step": 328740 + }, + { + "epoch": 0.73, + "learning_rate": 1.3355405919330666e-05, + "loss": 0.105, + "step": 328750 + }, + { + "epoch": 0.73, + "learning_rate": 1.3354287376121341e-05, + "loss": 0.1074, + "step": 328760 + }, + { + "epoch": 0.73, + "learning_rate": 1.3353168832912016e-05, + "loss": 0.1059, + "step": 328770 + }, + { + "epoch": 0.73, + "learning_rate": 1.3352050289702692e-05, + "loss": 0.108, + "step": 328780 + }, + { + "epoch": 0.73, + "learning_rate": 1.3350931746493366e-05, + "loss": 0.1034, + "step": 328790 + }, + { + "epoch": 0.73, + "learning_rate": 1.3349813203284043e-05, + "loss": 0.1091, + "step": 328800 + }, + { + "epoch": 0.73, + "learning_rate": 1.334869466007472e-05, + "loss": 0.1058, + "step": 328810 + }, + { + "epoch": 0.73, + "learning_rate": 1.3347576116865395e-05, + "loss": 0.1076, + "step": 328820 + }, + { + "epoch": 0.73, + "learning_rate": 1.3346457573656071e-05, + "loss": 0.1051, + "step": 328830 + }, + { + "epoch": 0.73, + "learning_rate": 1.3345339030446746e-05, + "loss": 0.109, + "step": 328840 + }, + { + "epoch": 0.73, + "learning_rate": 1.3344220487237422e-05, + "loss": 0.1098, + "step": 328850 + }, + { + "epoch": 0.73, + "learning_rate": 1.33431019440281e-05, + "loss": 0.1062, + "step": 328860 + }, + { + "epoch": 0.73, + "learning_rate": 1.3341983400818774e-05, + "loss": 0.1022, + "step": 328870 + }, + { + "epoch": 0.73, + "learning_rate": 1.334086485760945e-05, + "loss": 0.1058, + "step": 328880 + }, + { + "epoch": 0.73, + "learning_rate": 1.3339746314400125e-05, + "loss": 0.1033, + "step": 328890 + }, + { + "epoch": 0.73, + "learning_rate": 1.3338627771190801e-05, + "loss": 0.1102, + "step": 328900 + }, + { + "epoch": 0.73, + "learning_rate": 1.333750922798148e-05, + "loss": 0.1064, + "step": 328910 + }, + { + "epoch": 0.73, + "learning_rate": 1.3336390684772154e-05, + "loss": 0.1093, + "step": 328920 + }, + { + "epoch": 0.73, + "learning_rate": 1.333527214156283e-05, + "loss": 0.1041, + "step": 328930 + }, + { + "epoch": 0.73, + "learning_rate": 1.3334153598353505e-05, + "loss": 0.1081, + "step": 328940 + }, + { + "epoch": 0.73, + "learning_rate": 1.3333035055144181e-05, + "loss": 0.1073, + "step": 328950 + }, + { + "epoch": 0.73, + "learning_rate": 1.3331916511934856e-05, + "loss": 0.1058, + "step": 328960 + }, + { + "epoch": 0.73, + "learning_rate": 1.3330797968725533e-05, + "loss": 0.1007, + "step": 328970 + }, + { + "epoch": 0.73, + "learning_rate": 1.332967942551621e-05, + "loss": 0.1088, + "step": 328980 + }, + { + "epoch": 0.73, + "learning_rate": 1.3328560882306884e-05, + "loss": 0.1071, + "step": 328990 + }, + { + "epoch": 0.73, + "learning_rate": 1.3327442339097559e-05, + "loss": 0.1048, + "step": 329000 + }, + { + "epoch": 0.73, + "learning_rate": 1.3326323795888235e-05, + "loss": 0.1061, + "step": 329010 + }, + { + "epoch": 0.73, + "learning_rate": 1.3325205252678913e-05, + "loss": 0.1057, + "step": 329020 + }, + { + "epoch": 0.73, + "learning_rate": 1.3324086709469587e-05, + "loss": 0.1023, + "step": 329030 + }, + { + "epoch": 0.73, + "learning_rate": 1.3322968166260264e-05, + "loss": 0.103, + "step": 329040 + }, + { + "epoch": 0.73, + "learning_rate": 1.3321849623050938e-05, + "loss": 0.1062, + "step": 329050 + }, + { + "epoch": 0.73, + "learning_rate": 1.3320731079841614e-05, + "loss": 0.1066, + "step": 329060 + }, + { + "epoch": 0.73, + "learning_rate": 1.3319612536632289e-05, + "loss": 0.1086, + "step": 329070 + }, + { + "epoch": 0.73, + "learning_rate": 1.3318493993422967e-05, + "loss": 0.1051, + "step": 329080 + }, + { + "epoch": 0.73, + "learning_rate": 1.3317375450213643e-05, + "loss": 0.1084, + "step": 329090 + }, + { + "epoch": 0.73, + "learning_rate": 1.3316256907004318e-05, + "loss": 0.1062, + "step": 329100 + }, + { + "epoch": 0.73, + "learning_rate": 1.3315138363794994e-05, + "loss": 0.1111, + "step": 329110 + }, + { + "epoch": 0.73, + "learning_rate": 1.3314019820585668e-05, + "loss": 0.1049, + "step": 329120 + }, + { + "epoch": 0.73, + "learning_rate": 1.3312901277376346e-05, + "loss": 0.1085, + "step": 329130 + }, + { + "epoch": 0.73, + "learning_rate": 1.3311782734167023e-05, + "loss": 0.1081, + "step": 329140 + }, + { + "epoch": 0.73, + "learning_rate": 1.3310664190957697e-05, + "loss": 0.1048, + "step": 329150 + }, + { + "epoch": 0.73, + "learning_rate": 1.3309545647748373e-05, + "loss": 0.1094, + "step": 329160 + }, + { + "epoch": 0.73, + "learning_rate": 1.3308427104539048e-05, + "loss": 0.1066, + "step": 329170 + }, + { + "epoch": 0.73, + "learning_rate": 1.3307308561329726e-05, + "loss": 0.1068, + "step": 329180 + }, + { + "epoch": 0.73, + "learning_rate": 1.3306190018120402e-05, + "loss": 0.1035, + "step": 329190 + }, + { + "epoch": 0.73, + "learning_rate": 1.3305071474911077e-05, + "loss": 0.1062, + "step": 329200 + }, + { + "epoch": 0.73, + "learning_rate": 1.3303952931701751e-05, + "loss": 0.1088, + "step": 329210 + }, + { + "epoch": 0.73, + "learning_rate": 1.3302834388492427e-05, + "loss": 0.1013, + "step": 329220 + }, + { + "epoch": 0.73, + "learning_rate": 1.3301715845283102e-05, + "loss": 0.1063, + "step": 329230 + }, + { + "epoch": 0.73, + "learning_rate": 1.330059730207378e-05, + "loss": 0.107, + "step": 329240 + }, + { + "epoch": 0.73, + "learning_rate": 1.3299478758864456e-05, + "loss": 0.106, + "step": 329250 + }, + { + "epoch": 0.73, + "learning_rate": 1.329836021565513e-05, + "loss": 0.1073, + "step": 329260 + }, + { + "epoch": 0.73, + "learning_rate": 1.3297241672445807e-05, + "loss": 0.0997, + "step": 329270 + }, + { + "epoch": 0.73, + "learning_rate": 1.3296123129236481e-05, + "loss": 0.1011, + "step": 329280 + }, + { + "epoch": 0.74, + "learning_rate": 1.329500458602716e-05, + "loss": 0.1094, + "step": 329290 + }, + { + "epoch": 0.74, + "learning_rate": 1.3293886042817836e-05, + "loss": 0.1052, + "step": 329300 + }, + { + "epoch": 0.74, + "learning_rate": 1.329276749960851e-05, + "loss": 0.1088, + "step": 329310 + }, + { + "epoch": 0.74, + "learning_rate": 1.3291648956399186e-05, + "loss": 0.1044, + "step": 329320 + }, + { + "epoch": 0.74, + "learning_rate": 1.3290530413189861e-05, + "loss": 0.1017, + "step": 329330 + }, + { + "epoch": 0.74, + "learning_rate": 1.3289411869980539e-05, + "loss": 0.1009, + "step": 329340 + }, + { + "epoch": 0.74, + "learning_rate": 1.3288293326771215e-05, + "loss": 0.1072, + "step": 329350 + }, + { + "epoch": 0.74, + "learning_rate": 1.328717478356189e-05, + "loss": 0.1063, + "step": 329360 + }, + { + "epoch": 0.74, + "learning_rate": 1.3286056240352566e-05, + "loss": 0.1053, + "step": 329370 + }, + { + "epoch": 0.74, + "learning_rate": 1.328493769714324e-05, + "loss": 0.1112, + "step": 329380 + }, + { + "epoch": 0.74, + "learning_rate": 1.3283819153933915e-05, + "loss": 0.1068, + "step": 329390 + }, + { + "epoch": 0.74, + "learning_rate": 1.3282700610724595e-05, + "loss": 0.108, + "step": 329400 + }, + { + "epoch": 0.74, + "learning_rate": 1.3281582067515269e-05, + "loss": 0.1069, + "step": 329410 + }, + { + "epoch": 0.74, + "learning_rate": 1.3280463524305944e-05, + "loss": 0.1073, + "step": 329420 + }, + { + "epoch": 0.74, + "learning_rate": 1.327934498109662e-05, + "loss": 0.1076, + "step": 329430 + }, + { + "epoch": 0.74, + "learning_rate": 1.3278226437887294e-05, + "loss": 0.1069, + "step": 329440 + }, + { + "epoch": 0.74, + "learning_rate": 1.3277107894677972e-05, + "loss": 0.1109, + "step": 329450 + }, + { + "epoch": 0.74, + "learning_rate": 1.3275989351468649e-05, + "loss": 0.1061, + "step": 329460 + }, + { + "epoch": 0.74, + "learning_rate": 1.3274870808259323e-05, + "loss": 0.1079, + "step": 329470 + }, + { + "epoch": 0.74, + "learning_rate": 1.327375226505e-05, + "loss": 0.107, + "step": 329480 + }, + { + "epoch": 0.74, + "learning_rate": 1.3272633721840674e-05, + "loss": 0.1095, + "step": 329490 + }, + { + "epoch": 0.74, + "learning_rate": 1.3271515178631352e-05, + "loss": 0.1042, + "step": 329500 + }, + { + "epoch": 0.74, + "learning_rate": 1.3270396635422028e-05, + "loss": 0.1065, + "step": 329510 + }, + { + "epoch": 0.74, + "learning_rate": 1.3269278092212703e-05, + "loss": 0.108, + "step": 329520 + }, + { + "epoch": 0.74, + "learning_rate": 1.3268159549003379e-05, + "loss": 0.1093, + "step": 329530 + }, + { + "epoch": 0.74, + "learning_rate": 1.3267041005794053e-05, + "loss": 0.1051, + "step": 329540 + }, + { + "epoch": 0.74, + "learning_rate": 1.326592246258473e-05, + "loss": 0.1026, + "step": 329550 + }, + { + "epoch": 0.74, + "learning_rate": 1.3264803919375408e-05, + "loss": 0.1026, + "step": 329560 + }, + { + "epoch": 0.74, + "learning_rate": 1.3263685376166082e-05, + "loss": 0.1042, + "step": 329570 + }, + { + "epoch": 0.74, + "learning_rate": 1.3262566832956758e-05, + "loss": 0.1058, + "step": 329580 + }, + { + "epoch": 0.74, + "learning_rate": 1.3261448289747433e-05, + "loss": 0.1078, + "step": 329590 + }, + { + "epoch": 0.74, + "learning_rate": 1.3260329746538109e-05, + "loss": 0.1036, + "step": 329600 + }, + { + "epoch": 0.74, + "learning_rate": 1.3259211203328787e-05, + "loss": 0.1079, + "step": 329610 + }, + { + "epoch": 0.74, + "learning_rate": 1.3258092660119462e-05, + "loss": 0.1045, + "step": 329620 + }, + { + "epoch": 0.74, + "learning_rate": 1.3256974116910138e-05, + "loss": 0.1058, + "step": 329630 + }, + { + "epoch": 0.74, + "learning_rate": 1.3255855573700812e-05, + "loss": 0.1073, + "step": 329640 + }, + { + "epoch": 0.74, + "learning_rate": 1.3254737030491487e-05, + "loss": 0.1043, + "step": 329650 + }, + { + "epoch": 0.74, + "learning_rate": 1.3253618487282165e-05, + "loss": 0.1047, + "step": 329660 + }, + { + "epoch": 0.74, + "learning_rate": 1.3252499944072841e-05, + "loss": 0.1051, + "step": 329670 + }, + { + "epoch": 0.74, + "learning_rate": 1.3251381400863516e-05, + "loss": 0.1037, + "step": 329680 + }, + { + "epoch": 0.74, + "learning_rate": 1.3250262857654192e-05, + "loss": 0.1078, + "step": 329690 + }, + { + "epoch": 0.74, + "learning_rate": 1.3249144314444866e-05, + "loss": 0.1044, + "step": 329700 + }, + { + "epoch": 0.74, + "learning_rate": 1.3248025771235543e-05, + "loss": 0.1062, + "step": 329710 + }, + { + "epoch": 0.74, + "learning_rate": 1.324690722802622e-05, + "loss": 0.1027, + "step": 329720 + }, + { + "epoch": 0.74, + "learning_rate": 1.3245788684816895e-05, + "loss": 0.1031, + "step": 329730 + }, + { + "epoch": 0.74, + "learning_rate": 1.3244670141607571e-05, + "loss": 0.1045, + "step": 329740 + }, + { + "epoch": 0.74, + "learning_rate": 1.3243551598398246e-05, + "loss": 0.1077, + "step": 329750 + }, + { + "epoch": 0.74, + "learning_rate": 1.3242433055188922e-05, + "loss": 0.1038, + "step": 329760 + }, + { + "epoch": 0.74, + "learning_rate": 1.32413145119796e-05, + "loss": 0.1062, + "step": 329770 + }, + { + "epoch": 0.74, + "learning_rate": 1.3240195968770274e-05, + "loss": 0.1047, + "step": 329780 + }, + { + "epoch": 0.74, + "learning_rate": 1.323907742556095e-05, + "loss": 0.1022, + "step": 329790 + }, + { + "epoch": 0.74, + "learning_rate": 1.3237958882351625e-05, + "loss": 0.1101, + "step": 329800 + }, + { + "epoch": 0.74, + "learning_rate": 1.3236840339142301e-05, + "loss": 0.1053, + "step": 329810 + }, + { + "epoch": 0.74, + "learning_rate": 1.323572179593298e-05, + "loss": 0.1069, + "step": 329820 + }, + { + "epoch": 0.74, + "learning_rate": 1.3234603252723654e-05, + "loss": 0.1061, + "step": 329830 + }, + { + "epoch": 0.74, + "learning_rate": 1.323348470951433e-05, + "loss": 0.1051, + "step": 329840 + }, + { + "epoch": 0.74, + "learning_rate": 1.3232366166305005e-05, + "loss": 0.105, + "step": 329850 + }, + { + "epoch": 0.74, + "learning_rate": 1.323124762309568e-05, + "loss": 0.1069, + "step": 329860 + }, + { + "epoch": 0.74, + "learning_rate": 1.3230129079886355e-05, + "loss": 0.107, + "step": 329870 + }, + { + "epoch": 0.74, + "learning_rate": 1.3229010536677033e-05, + "loss": 0.1093, + "step": 329880 + }, + { + "epoch": 0.74, + "learning_rate": 1.3227891993467708e-05, + "loss": 0.1051, + "step": 329890 + }, + { + "epoch": 0.74, + "learning_rate": 1.3226773450258384e-05, + "loss": 0.1028, + "step": 329900 + }, + { + "epoch": 0.74, + "learning_rate": 1.3225654907049059e-05, + "loss": 0.1039, + "step": 329910 + }, + { + "epoch": 0.74, + "learning_rate": 1.3224536363839735e-05, + "loss": 0.1075, + "step": 329920 + }, + { + "epoch": 0.74, + "learning_rate": 1.3223417820630413e-05, + "loss": 0.1049, + "step": 329930 + }, + { + "epoch": 0.74, + "learning_rate": 1.3222299277421087e-05, + "loss": 0.107, + "step": 329940 + }, + { + "epoch": 0.74, + "learning_rate": 1.3221180734211764e-05, + "loss": 0.104, + "step": 329950 + }, + { + "epoch": 0.74, + "learning_rate": 1.3220062191002438e-05, + "loss": 0.1028, + "step": 329960 + }, + { + "epoch": 0.74, + "learning_rate": 1.3218943647793114e-05, + "loss": 0.1079, + "step": 329970 + }, + { + "epoch": 0.74, + "learning_rate": 1.3217825104583792e-05, + "loss": 0.1053, + "step": 329980 + }, + { + "epoch": 0.74, + "learning_rate": 1.3216706561374467e-05, + "loss": 0.1074, + "step": 329990 + }, + { + "epoch": 0.74, + "learning_rate": 1.3215588018165143e-05, + "loss": 0.103, + "step": 330000 + }, + { + "epoch": 0.74, + "learning_rate": 1.3214469474955818e-05, + "loss": 0.1065, + "step": 330010 + }, + { + "epoch": 0.74, + "learning_rate": 1.3213350931746494e-05, + "loss": 0.1083, + "step": 330020 + }, + { + "epoch": 0.74, + "learning_rate": 1.3212232388537168e-05, + "loss": 0.1058, + "step": 330030 + }, + { + "epoch": 0.74, + "learning_rate": 1.3211113845327846e-05, + "loss": 0.1102, + "step": 330040 + }, + { + "epoch": 0.74, + "learning_rate": 1.3209995302118523e-05, + "loss": 0.105, + "step": 330050 + }, + { + "epoch": 0.74, + "learning_rate": 1.3208876758909197e-05, + "loss": 0.1088, + "step": 330060 + }, + { + "epoch": 0.74, + "learning_rate": 1.3207758215699872e-05, + "loss": 0.1059, + "step": 330070 + }, + { + "epoch": 0.74, + "learning_rate": 1.3206639672490548e-05, + "loss": 0.1065, + "step": 330080 + }, + { + "epoch": 0.74, + "learning_rate": 1.3205521129281226e-05, + "loss": 0.104, + "step": 330090 + }, + { + "epoch": 0.74, + "learning_rate": 1.32044025860719e-05, + "loss": 0.1078, + "step": 330100 + }, + { + "epoch": 0.74, + "learning_rate": 1.3203284042862577e-05, + "loss": 0.1018, + "step": 330110 + }, + { + "epoch": 0.74, + "learning_rate": 1.3202165499653251e-05, + "loss": 0.1083, + "step": 330120 + }, + { + "epoch": 0.74, + "learning_rate": 1.3201046956443927e-05, + "loss": 0.1098, + "step": 330130 + }, + { + "epoch": 0.74, + "learning_rate": 1.3199928413234605e-05, + "loss": 0.1078, + "step": 330140 + }, + { + "epoch": 0.74, + "learning_rate": 1.319880987002528e-05, + "loss": 0.1034, + "step": 330150 + }, + { + "epoch": 0.74, + "learning_rate": 1.3197691326815956e-05, + "loss": 0.1047, + "step": 330160 + }, + { + "epoch": 0.74, + "learning_rate": 1.319657278360663e-05, + "loss": 0.1124, + "step": 330170 + }, + { + "epoch": 0.74, + "learning_rate": 1.3195454240397307e-05, + "loss": 0.104, + "step": 330180 + }, + { + "epoch": 0.74, + "learning_rate": 1.3194335697187981e-05, + "loss": 0.107, + "step": 330190 + }, + { + "epoch": 0.74, + "learning_rate": 1.319321715397866e-05, + "loss": 0.1038, + "step": 330200 + }, + { + "epoch": 0.74, + "learning_rate": 1.3192098610769336e-05, + "loss": 0.1073, + "step": 330210 + }, + { + "epoch": 0.74, + "learning_rate": 1.319098006756001e-05, + "loss": 0.1046, + "step": 330220 + }, + { + "epoch": 0.74, + "learning_rate": 1.3189861524350686e-05, + "loss": 0.1043, + "step": 330230 + }, + { + "epoch": 0.74, + "learning_rate": 1.3188742981141361e-05, + "loss": 0.1042, + "step": 330240 + }, + { + "epoch": 0.74, + "learning_rate": 1.3187624437932039e-05, + "loss": 0.1057, + "step": 330250 + }, + { + "epoch": 0.74, + "learning_rate": 1.3186505894722715e-05, + "loss": 0.1095, + "step": 330260 + }, + { + "epoch": 0.74, + "learning_rate": 1.318538735151339e-05, + "loss": 0.1048, + "step": 330270 + }, + { + "epoch": 0.74, + "learning_rate": 1.3184268808304064e-05, + "loss": 0.1092, + "step": 330280 + }, + { + "epoch": 0.74, + "learning_rate": 1.318315026509474e-05, + "loss": 0.1068, + "step": 330290 + }, + { + "epoch": 0.74, + "learning_rate": 1.3182031721885418e-05, + "loss": 0.1054, + "step": 330300 + }, + { + "epoch": 0.74, + "learning_rate": 1.3180913178676093e-05, + "loss": 0.1129, + "step": 330310 + }, + { + "epoch": 0.74, + "learning_rate": 1.3179794635466769e-05, + "loss": 0.1089, + "step": 330320 + }, + { + "epoch": 0.74, + "learning_rate": 1.3178676092257444e-05, + "loss": 0.1034, + "step": 330330 + }, + { + "epoch": 0.74, + "learning_rate": 1.317755754904812e-05, + "loss": 0.106, + "step": 330340 + }, + { + "epoch": 0.74, + "learning_rate": 1.3176439005838794e-05, + "loss": 0.104, + "step": 330350 + }, + { + "epoch": 0.74, + "learning_rate": 1.3175320462629472e-05, + "loss": 0.1043, + "step": 330360 + }, + { + "epoch": 0.74, + "learning_rate": 1.3174201919420149e-05, + "loss": 0.1061, + "step": 330370 + }, + { + "epoch": 0.74, + "learning_rate": 1.3173083376210823e-05, + "loss": 0.1104, + "step": 330380 + }, + { + "epoch": 0.74, + "learning_rate": 1.31719648330015e-05, + "loss": 0.1051, + "step": 330390 + }, + { + "epoch": 0.74, + "learning_rate": 1.3170846289792174e-05, + "loss": 0.1091, + "step": 330400 + }, + { + "epoch": 0.74, + "learning_rate": 1.3169727746582852e-05, + "loss": 0.1088, + "step": 330410 + }, + { + "epoch": 0.74, + "learning_rate": 1.3168609203373528e-05, + "loss": 0.1059, + "step": 330420 + }, + { + "epoch": 0.74, + "learning_rate": 1.3167490660164203e-05, + "loss": 0.109, + "step": 330430 + }, + { + "epoch": 0.74, + "learning_rate": 1.3166372116954879e-05, + "loss": 0.1011, + "step": 330440 + }, + { + "epoch": 0.74, + "learning_rate": 1.3165253573745553e-05, + "loss": 0.1016, + "step": 330450 + }, + { + "epoch": 0.74, + "learning_rate": 1.3164135030536231e-05, + "loss": 0.1074, + "step": 330460 + }, + { + "epoch": 0.74, + "learning_rate": 1.3163016487326907e-05, + "loss": 0.1054, + "step": 330470 + }, + { + "epoch": 0.74, + "learning_rate": 1.3161897944117582e-05, + "loss": 0.1074, + "step": 330480 + }, + { + "epoch": 0.74, + "learning_rate": 1.3160779400908258e-05, + "loss": 0.1029, + "step": 330490 + }, + { + "epoch": 0.74, + "learning_rate": 1.3159660857698933e-05, + "loss": 0.0986, + "step": 330500 + }, + { + "epoch": 0.74, + "learning_rate": 1.3158542314489607e-05, + "loss": 0.1006, + "step": 330510 + }, + { + "epoch": 0.74, + "learning_rate": 1.3157423771280287e-05, + "loss": 0.1038, + "step": 330520 + }, + { + "epoch": 0.74, + "learning_rate": 1.3156417082391894e-05, + "loss": 0.105, + "step": 330530 + }, + { + "epoch": 0.74, + "learning_rate": 1.315529853918257e-05, + "loss": 0.1041, + "step": 330540 + }, + { + "epoch": 0.74, + "learning_rate": 1.3154179995973245e-05, + "loss": 0.1057, + "step": 330550 + }, + { + "epoch": 0.74, + "learning_rate": 1.3153061452763921e-05, + "loss": 0.1073, + "step": 330560 + }, + { + "epoch": 0.74, + "learning_rate": 1.3151942909554596e-05, + "loss": 0.1029, + "step": 330570 + }, + { + "epoch": 0.74, + "learning_rate": 1.3150824366345272e-05, + "loss": 0.1038, + "step": 330580 + }, + { + "epoch": 0.74, + "learning_rate": 1.314970582313595e-05, + "loss": 0.1058, + "step": 330590 + }, + { + "epoch": 0.74, + "learning_rate": 1.3148587279926624e-05, + "loss": 0.1047, + "step": 330600 + }, + { + "epoch": 0.74, + "learning_rate": 1.31474687367173e-05, + "loss": 0.1028, + "step": 330610 + }, + { + "epoch": 0.74, + "learning_rate": 1.3146350193507975e-05, + "loss": 0.111, + "step": 330620 + }, + { + "epoch": 0.74, + "learning_rate": 1.3145231650298651e-05, + "loss": 0.1083, + "step": 330630 + }, + { + "epoch": 0.74, + "learning_rate": 1.314411310708933e-05, + "loss": 0.1041, + "step": 330640 + }, + { + "epoch": 0.74, + "learning_rate": 1.3142994563880004e-05, + "loss": 0.1065, + "step": 330650 + }, + { + "epoch": 0.74, + "learning_rate": 1.314187602067068e-05, + "loss": 0.1084, + "step": 330660 + }, + { + "epoch": 0.74, + "learning_rate": 1.3140757477461355e-05, + "loss": 0.105, + "step": 330670 + }, + { + "epoch": 0.74, + "learning_rate": 1.3139638934252029e-05, + "loss": 0.1068, + "step": 330680 + }, + { + "epoch": 0.74, + "learning_rate": 1.3138520391042709e-05, + "loss": 0.1085, + "step": 330690 + }, + { + "epoch": 0.74, + "learning_rate": 1.3137401847833383e-05, + "loss": 0.1123, + "step": 330700 + }, + { + "epoch": 0.74, + "learning_rate": 1.3136283304624058e-05, + "loss": 0.1054, + "step": 330710 + }, + { + "epoch": 0.74, + "learning_rate": 1.3135164761414734e-05, + "loss": 0.1066, + "step": 330720 + }, + { + "epoch": 0.74, + "learning_rate": 1.3134046218205409e-05, + "loss": 0.1052, + "step": 330730 + }, + { + "epoch": 0.74, + "learning_rate": 1.3132927674996085e-05, + "loss": 0.1019, + "step": 330740 + }, + { + "epoch": 0.74, + "learning_rate": 1.3131809131786763e-05, + "loss": 0.1059, + "step": 330750 + }, + { + "epoch": 0.74, + "learning_rate": 1.3130690588577437e-05, + "loss": 0.1079, + "step": 330760 + }, + { + "epoch": 0.74, + "learning_rate": 1.3129572045368113e-05, + "loss": 0.1072, + "step": 330770 + }, + { + "epoch": 0.74, + "learning_rate": 1.3128453502158788e-05, + "loss": 0.1062, + "step": 330780 + }, + { + "epoch": 0.74, + "learning_rate": 1.3127334958949464e-05, + "loss": 0.1107, + "step": 330790 + }, + { + "epoch": 0.74, + "learning_rate": 1.3126216415740142e-05, + "loss": 0.0999, + "step": 330800 + }, + { + "epoch": 0.74, + "learning_rate": 1.3125097872530817e-05, + "loss": 0.1102, + "step": 330810 + }, + { + "epoch": 0.74, + "learning_rate": 1.3123979329321493e-05, + "loss": 0.1049, + "step": 330820 + }, + { + "epoch": 0.74, + "learning_rate": 1.3122860786112168e-05, + "loss": 0.1067, + "step": 330830 + }, + { + "epoch": 0.74, + "learning_rate": 1.3121742242902844e-05, + "loss": 0.1073, + "step": 330840 + }, + { + "epoch": 0.74, + "learning_rate": 1.3120623699693522e-05, + "loss": 0.1074, + "step": 330850 + }, + { + "epoch": 0.74, + "learning_rate": 1.3119505156484196e-05, + "loss": 0.1077, + "step": 330860 + }, + { + "epoch": 0.74, + "learning_rate": 1.3118386613274872e-05, + "loss": 0.1079, + "step": 330870 + }, + { + "epoch": 0.74, + "learning_rate": 1.3117268070065547e-05, + "loss": 0.1103, + "step": 330880 + }, + { + "epoch": 0.74, + "learning_rate": 1.3116149526856222e-05, + "loss": 0.1078, + "step": 330890 + }, + { + "epoch": 0.74, + "learning_rate": 1.3115030983646898e-05, + "loss": 0.1069, + "step": 330900 + }, + { + "epoch": 0.74, + "learning_rate": 1.3113912440437576e-05, + "loss": 0.1036, + "step": 330910 + }, + { + "epoch": 0.74, + "learning_rate": 1.311279389722825e-05, + "loss": 0.1079, + "step": 330920 + }, + { + "epoch": 0.74, + "learning_rate": 1.3111675354018926e-05, + "loss": 0.1051, + "step": 330930 + }, + { + "epoch": 0.74, + "learning_rate": 1.3110556810809601e-05, + "loss": 0.103, + "step": 330940 + }, + { + "epoch": 0.74, + "learning_rate": 1.3109438267600277e-05, + "loss": 0.1049, + "step": 330950 + }, + { + "epoch": 0.74, + "learning_rate": 1.3108319724390955e-05, + "loss": 0.105, + "step": 330960 + }, + { + "epoch": 0.74, + "learning_rate": 1.310720118118163e-05, + "loss": 0.1071, + "step": 330970 + }, + { + "epoch": 0.74, + "learning_rate": 1.3106082637972306e-05, + "loss": 0.1067, + "step": 330980 + }, + { + "epoch": 0.74, + "learning_rate": 1.310496409476298e-05, + "loss": 0.106, + "step": 330990 + }, + { + "epoch": 0.74, + "learning_rate": 1.3103845551553657e-05, + "loss": 0.1053, + "step": 331000 + }, + { + "epoch": 0.74, + "learning_rate": 1.3102727008344335e-05, + "loss": 0.1062, + "step": 331010 + }, + { + "epoch": 0.74, + "learning_rate": 1.310160846513501e-05, + "loss": 0.1076, + "step": 331020 + }, + { + "epoch": 0.74, + "learning_rate": 1.3100489921925685e-05, + "loss": 0.1045, + "step": 331030 + }, + { + "epoch": 0.74, + "learning_rate": 1.309937137871636e-05, + "loss": 0.1055, + "step": 331040 + }, + { + "epoch": 0.74, + "learning_rate": 1.3098252835507036e-05, + "loss": 0.1092, + "step": 331050 + }, + { + "epoch": 0.74, + "learning_rate": 1.309713429229771e-05, + "loss": 0.1058, + "step": 331060 + }, + { + "epoch": 0.74, + "learning_rate": 1.3096015749088389e-05, + "loss": 0.1071, + "step": 331070 + }, + { + "epoch": 0.74, + "learning_rate": 1.3094897205879065e-05, + "loss": 0.1071, + "step": 331080 + }, + { + "epoch": 0.74, + "learning_rate": 1.309377866266974e-05, + "loss": 0.1071, + "step": 331090 + }, + { + "epoch": 0.74, + "learning_rate": 1.3092660119460416e-05, + "loss": 0.1068, + "step": 331100 + }, + { + "epoch": 0.74, + "learning_rate": 1.309154157625109e-05, + "loss": 0.1, + "step": 331110 + }, + { + "epoch": 0.74, + "learning_rate": 1.3090423033041768e-05, + "loss": 0.1114, + "step": 331120 + }, + { + "epoch": 0.74, + "learning_rate": 1.3089304489832444e-05, + "loss": 0.1074, + "step": 331130 + }, + { + "epoch": 0.74, + "learning_rate": 1.3088185946623119e-05, + "loss": 0.1065, + "step": 331140 + }, + { + "epoch": 0.74, + "learning_rate": 1.3087067403413793e-05, + "loss": 0.1035, + "step": 331150 + }, + { + "epoch": 0.74, + "learning_rate": 1.308594886020447e-05, + "loss": 0.1045, + "step": 331160 + }, + { + "epoch": 0.74, + "learning_rate": 1.3084830316995148e-05, + "loss": 0.1013, + "step": 331170 + }, + { + "epoch": 0.74, + "learning_rate": 1.3083711773785822e-05, + "loss": 0.0975, + "step": 331180 + }, + { + "epoch": 0.74, + "learning_rate": 1.3082593230576498e-05, + "loss": 0.1043, + "step": 331190 + }, + { + "epoch": 0.74, + "learning_rate": 1.3081474687367173e-05, + "loss": 0.1059, + "step": 331200 + }, + { + "epoch": 0.74, + "learning_rate": 1.3080356144157849e-05, + "loss": 0.1027, + "step": 331210 + }, + { + "epoch": 0.74, + "learning_rate": 1.3079237600948524e-05, + "loss": 0.1039, + "step": 331220 + }, + { + "epoch": 0.74, + "learning_rate": 1.3078119057739202e-05, + "loss": 0.1083, + "step": 331230 + }, + { + "epoch": 0.74, + "learning_rate": 1.3077000514529878e-05, + "loss": 0.1054, + "step": 331240 + }, + { + "epoch": 0.74, + "learning_rate": 1.3075881971320552e-05, + "loss": 0.1026, + "step": 331250 + }, + { + "epoch": 0.74, + "learning_rate": 1.3074763428111229e-05, + "loss": 0.1056, + "step": 331260 + }, + { + "epoch": 0.74, + "learning_rate": 1.3073644884901903e-05, + "loss": 0.1084, + "step": 331270 + }, + { + "epoch": 0.74, + "learning_rate": 1.3072526341692581e-05, + "loss": 0.1094, + "step": 331280 + }, + { + "epoch": 0.74, + "learning_rate": 1.3071407798483257e-05, + "loss": 0.105, + "step": 331290 + }, + { + "epoch": 0.74, + "learning_rate": 1.3070289255273932e-05, + "loss": 0.1058, + "step": 331300 + }, + { + "epoch": 0.74, + "learning_rate": 1.3069170712064608e-05, + "loss": 0.1089, + "step": 331310 + }, + { + "epoch": 0.74, + "learning_rate": 1.3068052168855283e-05, + "loss": 0.1079, + "step": 331320 + }, + { + "epoch": 0.74, + "learning_rate": 1.306693362564596e-05, + "loss": 0.1024, + "step": 331330 + }, + { + "epoch": 0.74, + "learning_rate": 1.3065815082436637e-05, + "loss": 0.1082, + "step": 331340 + }, + { + "epoch": 0.74, + "learning_rate": 1.3064696539227311e-05, + "loss": 0.1039, + "step": 331350 + }, + { + "epoch": 0.74, + "learning_rate": 1.3063577996017986e-05, + "loss": 0.104, + "step": 331360 + }, + { + "epoch": 0.74, + "learning_rate": 1.3062459452808662e-05, + "loss": 0.1067, + "step": 331370 + }, + { + "epoch": 0.74, + "learning_rate": 1.3061340909599337e-05, + "loss": 0.1026, + "step": 331380 + }, + { + "epoch": 0.74, + "learning_rate": 1.3060222366390015e-05, + "loss": 0.1072, + "step": 331390 + }, + { + "epoch": 0.74, + "learning_rate": 1.305910382318069e-05, + "loss": 0.1054, + "step": 331400 + }, + { + "epoch": 0.74, + "learning_rate": 1.3057985279971365e-05, + "loss": 0.1004, + "step": 331410 + }, + { + "epoch": 0.74, + "learning_rate": 1.3056866736762042e-05, + "loss": 0.1099, + "step": 331420 + }, + { + "epoch": 0.74, + "learning_rate": 1.3055748193552716e-05, + "loss": 0.1057, + "step": 331430 + }, + { + "epoch": 0.74, + "learning_rate": 1.3054629650343394e-05, + "loss": 0.1079, + "step": 331440 + }, + { + "epoch": 0.74, + "learning_rate": 1.305351110713407e-05, + "loss": 0.1006, + "step": 331450 + }, + { + "epoch": 0.74, + "learning_rate": 1.3052392563924745e-05, + "loss": 0.1059, + "step": 331460 + }, + { + "epoch": 0.74, + "learning_rate": 1.3051274020715421e-05, + "loss": 0.102, + "step": 331470 + }, + { + "epoch": 0.74, + "learning_rate": 1.3050155477506096e-05, + "loss": 0.1053, + "step": 331480 + }, + { + "epoch": 0.74, + "learning_rate": 1.3049036934296774e-05, + "loss": 0.1087, + "step": 331490 + }, + { + "epoch": 0.74, + "learning_rate": 1.304791839108745e-05, + "loss": 0.1064, + "step": 331500 + }, + { + "epoch": 0.74, + "learning_rate": 1.3046799847878124e-05, + "loss": 0.11, + "step": 331510 + }, + { + "epoch": 0.74, + "learning_rate": 1.30456813046688e-05, + "loss": 0.1053, + "step": 331520 + }, + { + "epoch": 0.74, + "learning_rate": 1.3044562761459475e-05, + "loss": 0.1034, + "step": 331530 + }, + { + "epoch": 0.74, + "learning_rate": 1.304344421825015e-05, + "loss": 0.0999, + "step": 331540 + }, + { + "epoch": 0.74, + "learning_rate": 1.304232567504083e-05, + "loss": 0.1078, + "step": 331550 + }, + { + "epoch": 0.74, + "learning_rate": 1.3041207131831504e-05, + "loss": 0.1055, + "step": 331560 + }, + { + "epoch": 0.74, + "learning_rate": 1.3040088588622178e-05, + "loss": 0.1004, + "step": 331570 + }, + { + "epoch": 0.74, + "learning_rate": 1.3038970045412855e-05, + "loss": 0.1066, + "step": 331580 + }, + { + "epoch": 0.74, + "learning_rate": 1.3037851502203529e-05, + "loss": 0.1044, + "step": 331590 + }, + { + "epoch": 0.74, + "learning_rate": 1.3036732958994207e-05, + "loss": 0.1064, + "step": 331600 + }, + { + "epoch": 0.74, + "learning_rate": 1.3035614415784883e-05, + "loss": 0.1034, + "step": 331610 + }, + { + "epoch": 0.74, + "learning_rate": 1.3034495872575558e-05, + "loss": 0.1053, + "step": 331620 + }, + { + "epoch": 0.74, + "learning_rate": 1.3033377329366234e-05, + "loss": 0.1044, + "step": 331630 + }, + { + "epoch": 0.74, + "learning_rate": 1.3032258786156909e-05, + "loss": 0.1036, + "step": 331640 + }, + { + "epoch": 0.74, + "learning_rate": 1.3031140242947586e-05, + "loss": 0.104, + "step": 331650 + }, + { + "epoch": 0.74, + "learning_rate": 1.3030021699738263e-05, + "loss": 0.1073, + "step": 331660 + }, + { + "epoch": 0.74, + "learning_rate": 1.3028903156528937e-05, + "loss": 0.1054, + "step": 331670 + }, + { + "epoch": 0.74, + "learning_rate": 1.3027784613319613e-05, + "loss": 0.1074, + "step": 331680 + }, + { + "epoch": 0.74, + "learning_rate": 1.3026666070110288e-05, + "loss": 0.1067, + "step": 331690 + }, + { + "epoch": 0.74, + "learning_rate": 1.3025547526900964e-05, + "loss": 0.1044, + "step": 331700 + }, + { + "epoch": 0.74, + "learning_rate": 1.3024428983691642e-05, + "loss": 0.1029, + "step": 331710 + }, + { + "epoch": 0.74, + "learning_rate": 1.3023310440482317e-05, + "loss": 0.11, + "step": 331720 + }, + { + "epoch": 0.74, + "learning_rate": 1.3022191897272993e-05, + "loss": 0.1048, + "step": 331730 + }, + { + "epoch": 0.74, + "learning_rate": 1.3021073354063667e-05, + "loss": 0.1028, + "step": 331740 + }, + { + "epoch": 0.74, + "learning_rate": 1.3019954810854342e-05, + "loss": 0.1037, + "step": 331750 + }, + { + "epoch": 0.74, + "learning_rate": 1.3018836267645022e-05, + "loss": 0.1044, + "step": 331760 + }, + { + "epoch": 0.74, + "learning_rate": 1.3017717724435696e-05, + "loss": 0.1048, + "step": 331770 + }, + { + "epoch": 0.74, + "learning_rate": 1.301659918122637e-05, + "loss": 0.1086, + "step": 331780 + }, + { + "epoch": 0.74, + "learning_rate": 1.3015480638017047e-05, + "loss": 0.1036, + "step": 331790 + }, + { + "epoch": 0.74, + "learning_rate": 1.3014362094807722e-05, + "loss": 0.1057, + "step": 331800 + }, + { + "epoch": 0.74, + "learning_rate": 1.30132435515984e-05, + "loss": 0.1105, + "step": 331810 + }, + { + "epoch": 0.74, + "learning_rate": 1.3012125008389076e-05, + "loss": 0.1045, + "step": 331820 + }, + { + "epoch": 0.74, + "learning_rate": 1.301100646517975e-05, + "loss": 0.1073, + "step": 331830 + }, + { + "epoch": 0.74, + "learning_rate": 1.3009887921970426e-05, + "loss": 0.1039, + "step": 331840 + }, + { + "epoch": 0.74, + "learning_rate": 1.3008769378761101e-05, + "loss": 0.104, + "step": 331850 + }, + { + "epoch": 0.74, + "learning_rate": 1.3007650835551777e-05, + "loss": 0.106, + "step": 331860 + }, + { + "epoch": 0.74, + "learning_rate": 1.3006532292342455e-05, + "loss": 0.1066, + "step": 331870 + }, + { + "epoch": 0.74, + "learning_rate": 1.300541374913313e-05, + "loss": 0.1011, + "step": 331880 + }, + { + "epoch": 0.74, + "learning_rate": 1.3004295205923806e-05, + "loss": 0.1069, + "step": 331890 + }, + { + "epoch": 0.74, + "learning_rate": 1.300317666271448e-05, + "loss": 0.105, + "step": 331900 + }, + { + "epoch": 0.74, + "learning_rate": 1.3002058119505157e-05, + "loss": 0.1065, + "step": 331910 + }, + { + "epoch": 0.74, + "learning_rate": 1.3000939576295835e-05, + "loss": 0.1034, + "step": 331920 + }, + { + "epoch": 0.74, + "learning_rate": 1.299982103308651e-05, + "loss": 0.1061, + "step": 331930 + }, + { + "epoch": 0.74, + "learning_rate": 1.2998702489877185e-05, + "loss": 0.1045, + "step": 331940 + }, + { + "epoch": 0.74, + "learning_rate": 1.299758394666786e-05, + "loss": 0.1089, + "step": 331950 + }, + { + "epoch": 0.74, + "learning_rate": 1.2996465403458536e-05, + "loss": 0.1062, + "step": 331960 + }, + { + "epoch": 0.74, + "learning_rate": 1.299534686024921e-05, + "loss": 0.1096, + "step": 331970 + }, + { + "epoch": 0.74, + "learning_rate": 1.2994228317039889e-05, + "loss": 0.1007, + "step": 331980 + }, + { + "epoch": 0.74, + "learning_rate": 1.2993109773830565e-05, + "loss": 0.1026, + "step": 331990 + }, + { + "epoch": 0.74, + "learning_rate": 1.299199123062124e-05, + "loss": 0.1018, + "step": 332000 + }, + { + "epoch": 0.74, + "learning_rate": 1.2990872687411914e-05, + "loss": 0.1065, + "step": 332010 + }, + { + "epoch": 0.74, + "learning_rate": 1.298975414420259e-05, + "loss": 0.1101, + "step": 332020 + }, + { + "epoch": 0.74, + "learning_rate": 1.2988635600993268e-05, + "loss": 0.1068, + "step": 332030 + }, + { + "epoch": 0.74, + "learning_rate": 1.2987517057783943e-05, + "loss": 0.1032, + "step": 332040 + }, + { + "epoch": 0.74, + "learning_rate": 1.2986398514574619e-05, + "loss": 0.1012, + "step": 332050 + }, + { + "epoch": 0.74, + "learning_rate": 1.2985279971365293e-05, + "loss": 0.1063, + "step": 332060 + }, + { + "epoch": 0.74, + "learning_rate": 1.298416142815597e-05, + "loss": 0.1023, + "step": 332070 + }, + { + "epoch": 0.74, + "learning_rate": 1.2983042884946648e-05, + "loss": 0.1017, + "step": 332080 + }, + { + "epoch": 0.74, + "learning_rate": 1.2981924341737322e-05, + "loss": 0.1025, + "step": 332090 + }, + { + "epoch": 0.74, + "learning_rate": 1.2980805798527998e-05, + "loss": 0.1072, + "step": 332100 + }, + { + "epoch": 0.74, + "learning_rate": 1.2979687255318673e-05, + "loss": 0.1039, + "step": 332110 + }, + { + "epoch": 0.74, + "learning_rate": 1.2978568712109349e-05, + "loss": 0.1043, + "step": 332120 + }, + { + "epoch": 0.74, + "learning_rate": 1.2977450168900024e-05, + "loss": 0.1096, + "step": 332130 + }, + { + "epoch": 0.74, + "learning_rate": 1.2976331625690702e-05, + "loss": 0.1021, + "step": 332140 + }, + { + "epoch": 0.74, + "learning_rate": 1.2975213082481378e-05, + "loss": 0.106, + "step": 332150 + }, + { + "epoch": 0.74, + "learning_rate": 1.2974094539272052e-05, + "loss": 0.1005, + "step": 332160 + }, + { + "epoch": 0.74, + "learning_rate": 1.2972975996062729e-05, + "loss": 0.1035, + "step": 332170 + }, + { + "epoch": 0.74, + "learning_rate": 1.2971857452853403e-05, + "loss": 0.1082, + "step": 332180 + }, + { + "epoch": 0.74, + "learning_rate": 1.2970738909644081e-05, + "loss": 0.1013, + "step": 332190 + }, + { + "epoch": 0.74, + "learning_rate": 1.2969620366434757e-05, + "loss": 0.1098, + "step": 332200 + }, + { + "epoch": 0.74, + "learning_rate": 1.2968501823225432e-05, + "loss": 0.1025, + "step": 332210 + }, + { + "epoch": 0.74, + "learning_rate": 1.2967383280016106e-05, + "loss": 0.1058, + "step": 332220 + }, + { + "epoch": 0.74, + "learning_rate": 1.2966264736806783e-05, + "loss": 0.1053, + "step": 332230 + }, + { + "epoch": 0.74, + "learning_rate": 1.296514619359746e-05, + "loss": 0.102, + "step": 332240 + }, + { + "epoch": 0.74, + "learning_rate": 1.2964027650388135e-05, + "loss": 0.1064, + "step": 332250 + }, + { + "epoch": 0.74, + "learning_rate": 1.2962909107178811e-05, + "loss": 0.1065, + "step": 332260 + }, + { + "epoch": 0.74, + "learning_rate": 1.2961790563969486e-05, + "loss": 0.101, + "step": 332270 + }, + { + "epoch": 0.74, + "learning_rate": 1.2960672020760162e-05, + "loss": 0.1051, + "step": 332280 + }, + { + "epoch": 0.74, + "learning_rate": 1.2959553477550837e-05, + "loss": 0.1041, + "step": 332290 + }, + { + "epoch": 0.74, + "learning_rate": 1.2958434934341515e-05, + "loss": 0.1007, + "step": 332300 + }, + { + "epoch": 0.74, + "learning_rate": 1.295731639113219e-05, + "loss": 0.1049, + "step": 332310 + }, + { + "epoch": 0.74, + "learning_rate": 1.2956197847922865e-05, + "loss": 0.1054, + "step": 332320 + }, + { + "epoch": 0.74, + "learning_rate": 1.2955079304713542e-05, + "loss": 0.1041, + "step": 332330 + }, + { + "epoch": 0.74, + "learning_rate": 1.2953960761504216e-05, + "loss": 0.1023, + "step": 332340 + }, + { + "epoch": 0.74, + "learning_rate": 1.2952842218294894e-05, + "loss": 0.109, + "step": 332350 + }, + { + "epoch": 0.74, + "learning_rate": 1.295172367508557e-05, + "loss": 0.1066, + "step": 332360 + }, + { + "epoch": 0.74, + "learning_rate": 1.2950605131876245e-05, + "loss": 0.1065, + "step": 332370 + }, + { + "epoch": 0.74, + "learning_rate": 1.2949486588666921e-05, + "loss": 0.1063, + "step": 332380 + }, + { + "epoch": 0.74, + "learning_rate": 1.2948368045457596e-05, + "loss": 0.1057, + "step": 332390 + }, + { + "epoch": 0.74, + "learning_rate": 1.2947249502248274e-05, + "loss": 0.1102, + "step": 332400 + }, + { + "epoch": 0.74, + "learning_rate": 1.294613095903895e-05, + "loss": 0.1024, + "step": 332410 + }, + { + "epoch": 0.74, + "learning_rate": 1.2945012415829624e-05, + "loss": 0.1058, + "step": 332420 + }, + { + "epoch": 0.74, + "learning_rate": 1.2943893872620299e-05, + "loss": 0.1051, + "step": 332430 + }, + { + "epoch": 0.74, + "learning_rate": 1.2942775329410975e-05, + "loss": 0.1069, + "step": 332440 + }, + { + "epoch": 0.74, + "learning_rate": 1.294165678620165e-05, + "loss": 0.1073, + "step": 332450 + }, + { + "epoch": 0.74, + "learning_rate": 1.2940538242992328e-05, + "loss": 0.1073, + "step": 332460 + }, + { + "epoch": 0.74, + "learning_rate": 1.2939419699783004e-05, + "loss": 0.1059, + "step": 332470 + }, + { + "epoch": 0.74, + "learning_rate": 1.2938301156573678e-05, + "loss": 0.1071, + "step": 332480 + }, + { + "epoch": 0.74, + "learning_rate": 1.2937182613364355e-05, + "loss": 0.1, + "step": 332490 + }, + { + "epoch": 0.74, + "learning_rate": 1.2936064070155029e-05, + "loss": 0.1066, + "step": 332500 + }, + { + "epoch": 0.74, + "learning_rate": 1.2934945526945707e-05, + "loss": 0.1033, + "step": 332510 + }, + { + "epoch": 0.74, + "learning_rate": 1.2933826983736383e-05, + "loss": 0.1059, + "step": 332520 + }, + { + "epoch": 0.74, + "learning_rate": 1.2932820294847992e-05, + "loss": 0.1048, + "step": 332530 + }, + { + "epoch": 0.74, + "learning_rate": 1.2931701751638667e-05, + "loss": 0.1037, + "step": 332540 + }, + { + "epoch": 0.74, + "learning_rate": 1.2930583208429343e-05, + "loss": 0.106, + "step": 332550 + }, + { + "epoch": 0.74, + "learning_rate": 1.2929464665220017e-05, + "loss": 0.1066, + "step": 332560 + }, + { + "epoch": 0.74, + "learning_rate": 1.2928346122010694e-05, + "loss": 0.1049, + "step": 332570 + }, + { + "epoch": 0.74, + "learning_rate": 1.2927227578801371e-05, + "loss": 0.1089, + "step": 332580 + }, + { + "epoch": 0.74, + "learning_rate": 1.2926109035592046e-05, + "loss": 0.1044, + "step": 332590 + }, + { + "epoch": 0.74, + "learning_rate": 1.2924990492382722e-05, + "loss": 0.1066, + "step": 332600 + }, + { + "epoch": 0.74, + "learning_rate": 1.2923871949173397e-05, + "loss": 0.107, + "step": 332610 + }, + { + "epoch": 0.74, + "learning_rate": 1.2922753405964071e-05, + "loss": 0.1065, + "step": 332620 + }, + { + "epoch": 0.74, + "learning_rate": 1.292163486275475e-05, + "loss": 0.1042, + "step": 332630 + }, + { + "epoch": 0.74, + "learning_rate": 1.2920516319545425e-05, + "loss": 0.1101, + "step": 332640 + }, + { + "epoch": 0.74, + "learning_rate": 1.29193977763361e-05, + "loss": 0.1035, + "step": 332650 + }, + { + "epoch": 0.74, + "learning_rate": 1.2918279233126776e-05, + "loss": 0.1008, + "step": 332660 + }, + { + "epoch": 0.74, + "learning_rate": 1.291716068991745e-05, + "loss": 0.1077, + "step": 332670 + }, + { + "epoch": 0.74, + "learning_rate": 1.2916042146708127e-05, + "loss": 0.1024, + "step": 332680 + }, + { + "epoch": 0.74, + "learning_rate": 1.2914923603498805e-05, + "loss": 0.108, + "step": 332690 + }, + { + "epoch": 0.74, + "learning_rate": 1.291380506028948e-05, + "loss": 0.1044, + "step": 332700 + }, + { + "epoch": 0.74, + "learning_rate": 1.2912686517080156e-05, + "loss": 0.1052, + "step": 332710 + }, + { + "epoch": 0.74, + "learning_rate": 1.291156797387083e-05, + "loss": 0.1071, + "step": 332720 + }, + { + "epoch": 0.74, + "learning_rate": 1.2910449430661507e-05, + "loss": 0.106, + "step": 332730 + }, + { + "epoch": 0.74, + "learning_rate": 1.2909330887452184e-05, + "loss": 0.1024, + "step": 332740 + }, + { + "epoch": 0.74, + "learning_rate": 1.2908212344242859e-05, + "loss": 0.1025, + "step": 332750 + }, + { + "epoch": 0.74, + "learning_rate": 1.2907093801033535e-05, + "loss": 0.1021, + "step": 332760 + }, + { + "epoch": 0.74, + "learning_rate": 1.290597525782421e-05, + "loss": 0.109, + "step": 332770 + }, + { + "epoch": 0.74, + "learning_rate": 1.2904856714614886e-05, + "loss": 0.1101, + "step": 332780 + }, + { + "epoch": 0.74, + "learning_rate": 1.2903738171405564e-05, + "loss": 0.106, + "step": 332790 + }, + { + "epoch": 0.74, + "learning_rate": 1.2902619628196238e-05, + "loss": 0.1085, + "step": 332800 + }, + { + "epoch": 0.74, + "learning_rate": 1.2901501084986915e-05, + "loss": 0.1054, + "step": 332810 + }, + { + "epoch": 0.74, + "learning_rate": 1.290038254177759e-05, + "loss": 0.1045, + "step": 332820 + }, + { + "epoch": 0.74, + "learning_rate": 1.2899263998568264e-05, + "loss": 0.1105, + "step": 332830 + }, + { + "epoch": 0.74, + "learning_rate": 1.289814545535894e-05, + "loss": 0.1047, + "step": 332840 + }, + { + "epoch": 0.74, + "learning_rate": 1.2897026912149618e-05, + "loss": 0.1073, + "step": 332850 + }, + { + "epoch": 0.74, + "learning_rate": 1.2895908368940292e-05, + "loss": 0.1086, + "step": 332860 + }, + { + "epoch": 0.74, + "learning_rate": 1.2894789825730969e-05, + "loss": 0.1065, + "step": 332870 + }, + { + "epoch": 0.74, + "learning_rate": 1.2893671282521643e-05, + "loss": 0.1083, + "step": 332880 + }, + { + "epoch": 0.74, + "learning_rate": 1.289255273931232e-05, + "loss": 0.1053, + "step": 332890 + }, + { + "epoch": 0.74, + "learning_rate": 1.2891434196102997e-05, + "loss": 0.1068, + "step": 332900 + }, + { + "epoch": 0.74, + "learning_rate": 1.2890315652893672e-05, + "loss": 0.1077, + "step": 332910 + }, + { + "epoch": 0.74, + "learning_rate": 1.2889197109684348e-05, + "loss": 0.107, + "step": 332920 + }, + { + "epoch": 0.74, + "learning_rate": 1.2888078566475023e-05, + "loss": 0.1055, + "step": 332930 + }, + { + "epoch": 0.74, + "learning_rate": 1.2886960023265699e-05, + "loss": 0.1046, + "step": 332940 + }, + { + "epoch": 0.74, + "learning_rate": 1.2885841480056377e-05, + "loss": 0.1053, + "step": 332950 + }, + { + "epoch": 0.74, + "learning_rate": 1.2884722936847051e-05, + "loss": 0.1068, + "step": 332960 + }, + { + "epoch": 0.74, + "learning_rate": 1.2883604393637728e-05, + "loss": 0.1039, + "step": 332970 + }, + { + "epoch": 0.74, + "learning_rate": 1.2882485850428402e-05, + "loss": 0.1044, + "step": 332980 + }, + { + "epoch": 0.74, + "learning_rate": 1.2881367307219078e-05, + "loss": 0.103, + "step": 332990 + }, + { + "epoch": 0.74, + "learning_rate": 1.2880248764009753e-05, + "loss": 0.1046, + "step": 333000 + }, + { + "epoch": 0.74, + "learning_rate": 1.2879130220800431e-05, + "loss": 0.1026, + "step": 333010 + }, + { + "epoch": 0.74, + "learning_rate": 1.2878011677591107e-05, + "loss": 0.104, + "step": 333020 + }, + { + "epoch": 0.74, + "learning_rate": 1.2876893134381782e-05, + "loss": 0.1043, + "step": 333030 + }, + { + "epoch": 0.74, + "learning_rate": 1.2875774591172456e-05, + "loss": 0.1064, + "step": 333040 + }, + { + "epoch": 0.74, + "learning_rate": 1.2874656047963132e-05, + "loss": 0.1052, + "step": 333050 + }, + { + "epoch": 0.74, + "learning_rate": 1.287353750475381e-05, + "loss": 0.1035, + "step": 333060 + }, + { + "epoch": 0.74, + "learning_rate": 1.2872418961544485e-05, + "loss": 0.1071, + "step": 333070 + }, + { + "epoch": 0.74, + "learning_rate": 1.2871300418335161e-05, + "loss": 0.1071, + "step": 333080 + }, + { + "epoch": 0.74, + "learning_rate": 1.2870181875125836e-05, + "loss": 0.1014, + "step": 333090 + }, + { + "epoch": 0.74, + "learning_rate": 1.2869063331916512e-05, + "loss": 0.1071, + "step": 333100 + }, + { + "epoch": 0.74, + "learning_rate": 1.286794478870719e-05, + "loss": 0.1007, + "step": 333110 + }, + { + "epoch": 0.74, + "learning_rate": 1.2866826245497864e-05, + "loss": 0.1047, + "step": 333120 + }, + { + "epoch": 0.74, + "learning_rate": 1.286570770228854e-05, + "loss": 0.1042, + "step": 333130 + }, + { + "epoch": 0.74, + "learning_rate": 1.2864589159079215e-05, + "loss": 0.1099, + "step": 333140 + }, + { + "epoch": 0.74, + "learning_rate": 1.2863470615869891e-05, + "loss": 0.11, + "step": 333150 + }, + { + "epoch": 0.74, + "learning_rate": 1.2862352072660566e-05, + "loss": 0.1038, + "step": 333160 + }, + { + "epoch": 0.74, + "learning_rate": 1.2861233529451244e-05, + "loss": 0.1056, + "step": 333170 + }, + { + "epoch": 0.74, + "learning_rate": 1.286011498624192e-05, + "loss": 0.1096, + "step": 333180 + }, + { + "epoch": 0.74, + "learning_rate": 1.2858996443032595e-05, + "loss": 0.1019, + "step": 333190 + }, + { + "epoch": 0.74, + "learning_rate": 1.2857877899823271e-05, + "loss": 0.1049, + "step": 333200 + }, + { + "epoch": 0.74, + "learning_rate": 1.2856759356613945e-05, + "loss": 0.1064, + "step": 333210 + }, + { + "epoch": 0.74, + "learning_rate": 1.2855640813404623e-05, + "loss": 0.1075, + "step": 333220 + }, + { + "epoch": 0.74, + "learning_rate": 1.28545222701953e-05, + "loss": 0.1014, + "step": 333230 + }, + { + "epoch": 0.74, + "learning_rate": 1.2853403726985974e-05, + "loss": 0.1026, + "step": 333240 + }, + { + "epoch": 0.74, + "learning_rate": 1.2852285183776649e-05, + "loss": 0.1077, + "step": 333250 + }, + { + "epoch": 0.74, + "learning_rate": 1.2851166640567325e-05, + "loss": 0.1073, + "step": 333260 + }, + { + "epoch": 0.74, + "learning_rate": 1.2850048097358003e-05, + "loss": 0.1055, + "step": 333270 + }, + { + "epoch": 0.74, + "learning_rate": 1.2848929554148677e-05, + "loss": 0.107, + "step": 333280 + }, + { + "epoch": 0.74, + "learning_rate": 1.2847811010939354e-05, + "loss": 0.1025, + "step": 333290 + }, + { + "epoch": 0.74, + "learning_rate": 1.2846692467730028e-05, + "loss": 0.1039, + "step": 333300 + }, + { + "epoch": 0.74, + "learning_rate": 1.2845573924520704e-05, + "loss": 0.105, + "step": 333310 + }, + { + "epoch": 0.74, + "learning_rate": 1.2844455381311379e-05, + "loss": 0.1055, + "step": 333320 + }, + { + "epoch": 0.74, + "learning_rate": 1.2843336838102057e-05, + "loss": 0.1049, + "step": 333330 + }, + { + "epoch": 0.74, + "learning_rate": 1.2842218294892733e-05, + "loss": 0.1051, + "step": 333340 + }, + { + "epoch": 0.74, + "learning_rate": 1.2841099751683408e-05, + "loss": 0.108, + "step": 333350 + }, + { + "epoch": 0.74, + "learning_rate": 1.2839981208474084e-05, + "loss": 0.1041, + "step": 333360 + }, + { + "epoch": 0.74, + "learning_rate": 1.2838862665264758e-05, + "loss": 0.1022, + "step": 333370 + }, + { + "epoch": 0.74, + "learning_rate": 1.2837744122055436e-05, + "loss": 0.1044, + "step": 333380 + }, + { + "epoch": 0.74, + "learning_rate": 1.2836625578846113e-05, + "loss": 0.1021, + "step": 333390 + }, + { + "epoch": 0.74, + "learning_rate": 1.2835507035636787e-05, + "loss": 0.106, + "step": 333400 + }, + { + "epoch": 0.74, + "learning_rate": 1.2834388492427463e-05, + "loss": 0.1064, + "step": 333410 + }, + { + "epoch": 0.74, + "learning_rate": 1.2833269949218138e-05, + "loss": 0.1008, + "step": 333420 + }, + { + "epoch": 0.74, + "learning_rate": 1.2832151406008816e-05, + "loss": 0.1035, + "step": 333430 + }, + { + "epoch": 0.74, + "learning_rate": 1.2831032862799492e-05, + "loss": 0.1048, + "step": 333440 + }, + { + "epoch": 0.74, + "learning_rate": 1.2829914319590167e-05, + "loss": 0.1047, + "step": 333450 + }, + { + "epoch": 0.74, + "learning_rate": 1.2828795776380843e-05, + "loss": 0.1059, + "step": 333460 + }, + { + "epoch": 0.74, + "learning_rate": 1.2827677233171517e-05, + "loss": 0.1044, + "step": 333470 + }, + { + "epoch": 0.74, + "learning_rate": 1.2826558689962192e-05, + "loss": 0.1043, + "step": 333480 + }, + { + "epoch": 0.74, + "learning_rate": 1.2825440146752871e-05, + "loss": 0.1064, + "step": 333490 + }, + { + "epoch": 0.74, + "learning_rate": 1.2824321603543546e-05, + "loss": 0.1102, + "step": 333500 + }, + { + "epoch": 0.74, + "learning_rate": 1.282320306033422e-05, + "loss": 0.1036, + "step": 333510 + }, + { + "epoch": 0.74, + "learning_rate": 1.2822084517124897e-05, + "loss": 0.1081, + "step": 333520 + }, + { + "epoch": 0.74, + "learning_rate": 1.2820965973915571e-05, + "loss": 0.1079, + "step": 333530 + }, + { + "epoch": 0.74, + "learning_rate": 1.281984743070625e-05, + "loss": 0.1058, + "step": 333540 + }, + { + "epoch": 0.74, + "learning_rate": 1.2818728887496925e-05, + "loss": 0.1052, + "step": 333550 + }, + { + "epoch": 0.74, + "learning_rate": 1.28176103442876e-05, + "loss": 0.1017, + "step": 333560 + }, + { + "epoch": 0.74, + "learning_rate": 1.2816491801078276e-05, + "loss": 0.104, + "step": 333570 + }, + { + "epoch": 0.74, + "learning_rate": 1.281537325786895e-05, + "loss": 0.1051, + "step": 333580 + }, + { + "epoch": 0.74, + "learning_rate": 1.2814254714659629e-05, + "loss": 0.1073, + "step": 333590 + }, + { + "epoch": 0.74, + "learning_rate": 1.2813136171450305e-05, + "loss": 0.1078, + "step": 333600 + }, + { + "epoch": 0.74, + "learning_rate": 1.281201762824098e-05, + "loss": 0.1038, + "step": 333610 + }, + { + "epoch": 0.74, + "learning_rate": 1.2810899085031656e-05, + "loss": 0.1058, + "step": 333620 + }, + { + "epoch": 0.74, + "learning_rate": 1.280978054182233e-05, + "loss": 0.1037, + "step": 333630 + }, + { + "epoch": 0.74, + "learning_rate": 1.2808661998613007e-05, + "loss": 0.1051, + "step": 333640 + }, + { + "epoch": 0.74, + "learning_rate": 1.2807543455403684e-05, + "loss": 0.1051, + "step": 333650 + }, + { + "epoch": 0.74, + "learning_rate": 1.2806424912194359e-05, + "loss": 0.1074, + "step": 333660 + }, + { + "epoch": 0.74, + "learning_rate": 1.2805306368985035e-05, + "loss": 0.1109, + "step": 333670 + }, + { + "epoch": 0.74, + "learning_rate": 1.280418782577571e-05, + "loss": 0.1066, + "step": 333680 + }, + { + "epoch": 0.74, + "learning_rate": 1.2803069282566384e-05, + "loss": 0.1044, + "step": 333690 + }, + { + "epoch": 0.74, + "learning_rate": 1.2801950739357064e-05, + "loss": 0.1097, + "step": 333700 + }, + { + "epoch": 0.74, + "learning_rate": 1.2800832196147738e-05, + "loss": 0.1048, + "step": 333710 + }, + { + "epoch": 0.74, + "learning_rate": 1.2799713652938413e-05, + "loss": 0.106, + "step": 333720 + }, + { + "epoch": 0.74, + "learning_rate": 1.279859510972909e-05, + "loss": 0.1049, + "step": 333730 + }, + { + "epoch": 0.74, + "learning_rate": 1.2797476566519764e-05, + "loss": 0.1043, + "step": 333740 + }, + { + "epoch": 0.74, + "learning_rate": 1.2796358023310442e-05, + "loss": 0.1055, + "step": 333750 + }, + { + "epoch": 0.74, + "learning_rate": 1.2795239480101118e-05, + "loss": 0.1099, + "step": 333760 + }, + { + "epoch": 0.75, + "learning_rate": 1.2794120936891792e-05, + "loss": 0.1055, + "step": 333770 + }, + { + "epoch": 0.75, + "learning_rate": 1.2793002393682469e-05, + "loss": 0.1077, + "step": 333780 + }, + { + "epoch": 0.75, + "learning_rate": 1.2791883850473143e-05, + "loss": 0.105, + "step": 333790 + }, + { + "epoch": 0.75, + "learning_rate": 1.279076530726382e-05, + "loss": 0.1072, + "step": 333800 + }, + { + "epoch": 0.75, + "learning_rate": 1.2789646764054497e-05, + "loss": 0.1055, + "step": 333810 + }, + { + "epoch": 0.75, + "learning_rate": 1.2788528220845172e-05, + "loss": 0.106, + "step": 333820 + }, + { + "epoch": 0.75, + "learning_rate": 1.2787409677635848e-05, + "loss": 0.105, + "step": 333830 + }, + { + "epoch": 0.75, + "learning_rate": 1.2786291134426523e-05, + "loss": 0.1032, + "step": 333840 + }, + { + "epoch": 0.75, + "learning_rate": 1.2785172591217199e-05, + "loss": 0.1031, + "step": 333850 + }, + { + "epoch": 0.75, + "learning_rate": 1.2784054048007877e-05, + "loss": 0.1078, + "step": 333860 + }, + { + "epoch": 0.75, + "learning_rate": 1.2782935504798551e-05, + "loss": 0.1081, + "step": 333870 + }, + { + "epoch": 0.75, + "learning_rate": 1.2781816961589228e-05, + "loss": 0.1099, + "step": 333880 + }, + { + "epoch": 0.75, + "learning_rate": 1.2780698418379902e-05, + "loss": 0.1048, + "step": 333890 + }, + { + "epoch": 0.75, + "learning_rate": 1.2779579875170577e-05, + "loss": 0.1056, + "step": 333900 + }, + { + "epoch": 0.75, + "learning_rate": 1.2778461331961256e-05, + "loss": 0.1046, + "step": 333910 + }, + { + "epoch": 0.75, + "learning_rate": 1.2777342788751931e-05, + "loss": 0.1099, + "step": 333920 + }, + { + "epoch": 0.75, + "learning_rate": 1.2776224245542605e-05, + "loss": 0.1029, + "step": 333930 + }, + { + "epoch": 0.75, + "learning_rate": 1.2775105702333282e-05, + "loss": 0.1072, + "step": 333940 + }, + { + "epoch": 0.75, + "learning_rate": 1.2773987159123956e-05, + "loss": 0.1045, + "step": 333950 + }, + { + "epoch": 0.75, + "learning_rate": 1.2772868615914632e-05, + "loss": 0.1038, + "step": 333960 + }, + { + "epoch": 0.75, + "learning_rate": 1.277175007270531e-05, + "loss": 0.1051, + "step": 333970 + }, + { + "epoch": 0.75, + "learning_rate": 1.2770631529495985e-05, + "loss": 0.1052, + "step": 333980 + }, + { + "epoch": 0.75, + "learning_rate": 1.2769512986286661e-05, + "loss": 0.1033, + "step": 333990 + }, + { + "epoch": 0.75, + "learning_rate": 1.2768394443077336e-05, + "loss": 0.1025, + "step": 334000 + }, + { + "epoch": 0.75, + "learning_rate": 1.2767275899868012e-05, + "loss": 0.1054, + "step": 334010 + }, + { + "epoch": 0.75, + "learning_rate": 1.276615735665869e-05, + "loss": 0.0989, + "step": 334020 + }, + { + "epoch": 0.75, + "learning_rate": 1.2765038813449364e-05, + "loss": 0.1064, + "step": 334030 + }, + { + "epoch": 0.75, + "learning_rate": 1.276392027024004e-05, + "loss": 0.1046, + "step": 334040 + }, + { + "epoch": 0.75, + "learning_rate": 1.2762801727030715e-05, + "loss": 0.1043, + "step": 334050 + }, + { + "epoch": 0.75, + "learning_rate": 1.2761683183821391e-05, + "loss": 0.1087, + "step": 334060 + }, + { + "epoch": 0.75, + "learning_rate": 1.276056464061207e-05, + "loss": 0.1098, + "step": 334070 + }, + { + "epoch": 0.75, + "learning_rate": 1.2759446097402744e-05, + "loss": 0.1038, + "step": 334080 + }, + { + "epoch": 0.75, + "learning_rate": 1.275832755419342e-05, + "loss": 0.1057, + "step": 334090 + }, + { + "epoch": 0.75, + "learning_rate": 1.2757209010984095e-05, + "loss": 0.1036, + "step": 334100 + }, + { + "epoch": 0.75, + "learning_rate": 1.2756090467774771e-05, + "loss": 0.104, + "step": 334110 + }, + { + "epoch": 0.75, + "learning_rate": 1.2754971924565445e-05, + "loss": 0.0999, + "step": 334120 + }, + { + "epoch": 0.75, + "learning_rate": 1.2753853381356123e-05, + "loss": 0.1067, + "step": 334130 + }, + { + "epoch": 0.75, + "learning_rate": 1.2752734838146798e-05, + "loss": 0.1041, + "step": 334140 + }, + { + "epoch": 0.75, + "learning_rate": 1.2751616294937474e-05, + "loss": 0.1005, + "step": 334150 + }, + { + "epoch": 0.75, + "learning_rate": 1.2750497751728149e-05, + "loss": 0.0995, + "step": 334160 + }, + { + "epoch": 0.75, + "learning_rate": 1.2749379208518825e-05, + "loss": 0.1095, + "step": 334170 + }, + { + "epoch": 0.75, + "learning_rate": 1.2748260665309503e-05, + "loss": 0.1049, + "step": 334180 + }, + { + "epoch": 0.75, + "learning_rate": 1.2747142122100177e-05, + "loss": 0.1043, + "step": 334190 + }, + { + "epoch": 0.75, + "learning_rate": 1.2746023578890854e-05, + "loss": 0.1093, + "step": 334200 + }, + { + "epoch": 0.75, + "learning_rate": 1.2744905035681528e-05, + "loss": 0.105, + "step": 334210 + }, + { + "epoch": 0.75, + "learning_rate": 1.2743786492472204e-05, + "loss": 0.1037, + "step": 334220 + }, + { + "epoch": 0.75, + "learning_rate": 1.2742667949262882e-05, + "loss": 0.105, + "step": 334230 + }, + { + "epoch": 0.75, + "learning_rate": 1.2741549406053557e-05, + "loss": 0.104, + "step": 334240 + }, + { + "epoch": 0.75, + "learning_rate": 1.2740430862844233e-05, + "loss": 0.1071, + "step": 334250 + }, + { + "epoch": 0.75, + "learning_rate": 1.2739312319634908e-05, + "loss": 0.1115, + "step": 334260 + }, + { + "epoch": 0.75, + "learning_rate": 1.2738193776425584e-05, + "loss": 0.1066, + "step": 334270 + }, + { + "epoch": 0.75, + "learning_rate": 1.2737075233216258e-05, + "loss": 0.1002, + "step": 334280 + }, + { + "epoch": 0.75, + "learning_rate": 1.2735956690006936e-05, + "loss": 0.108, + "step": 334290 + }, + { + "epoch": 0.75, + "learning_rate": 1.2734838146797613e-05, + "loss": 0.1074, + "step": 334300 + }, + { + "epoch": 0.75, + "learning_rate": 1.2733719603588287e-05, + "loss": 0.1045, + "step": 334310 + }, + { + "epoch": 0.75, + "learning_rate": 1.2732601060378963e-05, + "loss": 0.1055, + "step": 334320 + }, + { + "epoch": 0.75, + "learning_rate": 1.2731482517169638e-05, + "loss": 0.1026, + "step": 334330 + }, + { + "epoch": 0.75, + "learning_rate": 1.2730363973960316e-05, + "loss": 0.1078, + "step": 334340 + }, + { + "epoch": 0.75, + "learning_rate": 1.2729245430750992e-05, + "loss": 0.1075, + "step": 334350 + }, + { + "epoch": 0.75, + "learning_rate": 1.2728126887541667e-05, + "loss": 0.1049, + "step": 334360 + }, + { + "epoch": 0.75, + "learning_rate": 1.2727008344332341e-05, + "loss": 0.1047, + "step": 334370 + }, + { + "epoch": 0.75, + "learning_rate": 1.2725889801123017e-05, + "loss": 0.1037, + "step": 334380 + }, + { + "epoch": 0.75, + "learning_rate": 1.2724771257913695e-05, + "loss": 0.1074, + "step": 334390 + }, + { + "epoch": 0.75, + "learning_rate": 1.272365271470437e-05, + "loss": 0.1069, + "step": 334400 + }, + { + "epoch": 0.75, + "learning_rate": 1.2722534171495046e-05, + "loss": 0.103, + "step": 334410 + }, + { + "epoch": 0.75, + "learning_rate": 1.272141562828572e-05, + "loss": 0.1086, + "step": 334420 + }, + { + "epoch": 0.75, + "learning_rate": 1.2720297085076397e-05, + "loss": 0.1036, + "step": 334430 + }, + { + "epoch": 0.75, + "learning_rate": 1.2719178541867071e-05, + "loss": 0.1003, + "step": 334440 + }, + { + "epoch": 0.75, + "learning_rate": 1.271805999865775e-05, + "loss": 0.105, + "step": 334450 + }, + { + "epoch": 0.75, + "learning_rate": 1.2716941455448425e-05, + "loss": 0.1048, + "step": 334460 + }, + { + "epoch": 0.75, + "learning_rate": 1.27158229122391e-05, + "loss": 0.1024, + "step": 334470 + }, + { + "epoch": 0.75, + "learning_rate": 1.2714704369029776e-05, + "loss": 0.1061, + "step": 334480 + }, + { + "epoch": 0.75, + "learning_rate": 1.271358582582045e-05, + "loss": 0.1018, + "step": 334490 + }, + { + "epoch": 0.75, + "learning_rate": 1.2712467282611129e-05, + "loss": 0.1046, + "step": 334500 + }, + { + "epoch": 0.75, + "learning_rate": 1.2711348739401805e-05, + "loss": 0.1056, + "step": 334510 + }, + { + "epoch": 0.75, + "learning_rate": 1.271023019619248e-05, + "loss": 0.1057, + "step": 334520 + }, + { + "epoch": 0.75, + "learning_rate": 1.2709111652983156e-05, + "loss": 0.1003, + "step": 334530 + }, + { + "epoch": 0.75, + "learning_rate": 1.2708104964094763e-05, + "loss": 0.1064, + "step": 334540 + }, + { + "epoch": 0.75, + "learning_rate": 1.2706986420885439e-05, + "loss": 0.108, + "step": 334550 + }, + { + "epoch": 0.75, + "learning_rate": 1.2705867877676114e-05, + "loss": 0.1027, + "step": 334560 + }, + { + "epoch": 0.75, + "learning_rate": 1.2704749334466792e-05, + "loss": 0.1018, + "step": 334570 + }, + { + "epoch": 0.75, + "learning_rate": 1.2703630791257468e-05, + "loss": 0.1022, + "step": 334580 + }, + { + "epoch": 0.75, + "learning_rate": 1.2702512248048142e-05, + "loss": 0.0979, + "step": 334590 + }, + { + "epoch": 0.75, + "learning_rate": 1.2701393704838819e-05, + "loss": 0.1083, + "step": 334600 + }, + { + "epoch": 0.75, + "learning_rate": 1.2700275161629493e-05, + "loss": 0.0982, + "step": 334610 + }, + { + "epoch": 0.75, + "learning_rate": 1.269915661842017e-05, + "loss": 0.1031, + "step": 334620 + }, + { + "epoch": 0.75, + "learning_rate": 1.2698038075210847e-05, + "loss": 0.1024, + "step": 334630 + }, + { + "epoch": 0.75, + "learning_rate": 1.2696919532001522e-05, + "loss": 0.1023, + "step": 334640 + }, + { + "epoch": 0.75, + "learning_rate": 1.2695800988792198e-05, + "loss": 0.1064, + "step": 334650 + }, + { + "epoch": 0.75, + "learning_rate": 1.2694682445582873e-05, + "loss": 0.1009, + "step": 334660 + }, + { + "epoch": 0.75, + "learning_rate": 1.2693563902373549e-05, + "loss": 0.1044, + "step": 334670 + }, + { + "epoch": 0.75, + "learning_rate": 1.2692445359164227e-05, + "loss": 0.1052, + "step": 334680 + }, + { + "epoch": 0.75, + "learning_rate": 1.2691326815954901e-05, + "loss": 0.1066, + "step": 334690 + }, + { + "epoch": 0.75, + "learning_rate": 1.2690208272745577e-05, + "loss": 0.1076, + "step": 334700 + }, + { + "epoch": 0.75, + "learning_rate": 1.2689089729536252e-05, + "loss": 0.1009, + "step": 334710 + }, + { + "epoch": 0.75, + "learning_rate": 1.2687971186326927e-05, + "loss": 0.1086, + "step": 334720 + }, + { + "epoch": 0.75, + "learning_rate": 1.2686852643117606e-05, + "loss": 0.1044, + "step": 334730 + }, + { + "epoch": 0.75, + "learning_rate": 1.268573409990828e-05, + "loss": 0.11, + "step": 334740 + }, + { + "epoch": 0.75, + "learning_rate": 1.2684615556698955e-05, + "loss": 0.1061, + "step": 334750 + }, + { + "epoch": 0.75, + "learning_rate": 1.2683497013489631e-05, + "loss": 0.106, + "step": 334760 + }, + { + "epoch": 0.75, + "learning_rate": 1.2682378470280306e-05, + "loss": 0.1061, + "step": 334770 + }, + { + "epoch": 0.75, + "learning_rate": 1.2681259927070982e-05, + "loss": 0.1055, + "step": 334780 + }, + { + "epoch": 0.75, + "learning_rate": 1.268014138386166e-05, + "loss": 0.1089, + "step": 334790 + }, + { + "epoch": 0.75, + "learning_rate": 1.2679022840652335e-05, + "loss": 0.1074, + "step": 334800 + }, + { + "epoch": 0.75, + "learning_rate": 1.2677904297443011e-05, + "loss": 0.1076, + "step": 334810 + }, + { + "epoch": 0.75, + "learning_rate": 1.2676785754233685e-05, + "loss": 0.1069, + "step": 334820 + }, + { + "epoch": 0.75, + "learning_rate": 1.2675667211024362e-05, + "loss": 0.1046, + "step": 334830 + }, + { + "epoch": 0.75, + "learning_rate": 1.267454866781504e-05, + "loss": 0.1047, + "step": 334840 + }, + { + "epoch": 0.75, + "learning_rate": 1.2673430124605714e-05, + "loss": 0.1063, + "step": 334850 + }, + { + "epoch": 0.75, + "learning_rate": 1.267231158139639e-05, + "loss": 0.1049, + "step": 334860 + }, + { + "epoch": 0.75, + "learning_rate": 1.2671193038187065e-05, + "loss": 0.1066, + "step": 334870 + }, + { + "epoch": 0.75, + "learning_rate": 1.2670074494977741e-05, + "loss": 0.104, + "step": 334880 + }, + { + "epoch": 0.75, + "learning_rate": 1.2668955951768419e-05, + "loss": 0.1079, + "step": 334890 + }, + { + "epoch": 0.75, + "learning_rate": 1.2667837408559094e-05, + "loss": 0.1044, + "step": 334900 + }, + { + "epoch": 0.75, + "learning_rate": 1.266671886534977e-05, + "loss": 0.0993, + "step": 334910 + }, + { + "epoch": 0.75, + "learning_rate": 1.2665600322140444e-05, + "loss": 0.1074, + "step": 334920 + }, + { + "epoch": 0.75, + "learning_rate": 1.266448177893112e-05, + "loss": 0.0983, + "step": 334930 + }, + { + "epoch": 0.75, + "learning_rate": 1.2663363235721795e-05, + "loss": 0.1061, + "step": 334940 + }, + { + "epoch": 0.75, + "learning_rate": 1.2662244692512473e-05, + "loss": 0.1013, + "step": 334950 + }, + { + "epoch": 0.75, + "learning_rate": 1.266112614930315e-05, + "loss": 0.1042, + "step": 334960 + }, + { + "epoch": 0.75, + "learning_rate": 1.2660007606093824e-05, + "loss": 0.1094, + "step": 334970 + }, + { + "epoch": 0.75, + "learning_rate": 1.2658889062884498e-05, + "loss": 0.1067, + "step": 334980 + }, + { + "epoch": 0.75, + "learning_rate": 1.2657770519675175e-05, + "loss": 0.1033, + "step": 334990 + }, + { + "epoch": 0.75, + "learning_rate": 1.2656651976465853e-05, + "loss": 0.1052, + "step": 335000 + }, + { + "epoch": 0.75, + "learning_rate": 1.2655533433256527e-05, + "loss": 0.1067, + "step": 335010 + }, + { + "epoch": 0.75, + "learning_rate": 1.2654414890047203e-05, + "loss": 0.1064, + "step": 335020 + }, + { + "epoch": 0.75, + "learning_rate": 1.2653296346837878e-05, + "loss": 0.1048, + "step": 335030 + }, + { + "epoch": 0.75, + "learning_rate": 1.2652177803628554e-05, + "loss": 0.1037, + "step": 335040 + }, + { + "epoch": 0.75, + "learning_rate": 1.2651059260419232e-05, + "loss": 0.104, + "step": 335050 + }, + { + "epoch": 0.75, + "learning_rate": 1.2649940717209907e-05, + "loss": 0.1055, + "step": 335060 + }, + { + "epoch": 0.75, + "learning_rate": 1.2648822174000583e-05, + "loss": 0.1052, + "step": 335070 + }, + { + "epoch": 0.75, + "learning_rate": 1.2647703630791257e-05, + "loss": 0.1044, + "step": 335080 + }, + { + "epoch": 0.75, + "learning_rate": 1.2646585087581934e-05, + "loss": 0.0991, + "step": 335090 + }, + { + "epoch": 0.75, + "learning_rate": 1.2645466544372608e-05, + "loss": 0.1036, + "step": 335100 + }, + { + "epoch": 0.75, + "learning_rate": 1.2644348001163286e-05, + "loss": 0.1047, + "step": 335110 + }, + { + "epoch": 0.75, + "learning_rate": 1.2643229457953962e-05, + "loss": 0.1012, + "step": 335120 + }, + { + "epoch": 0.75, + "learning_rate": 1.2642110914744637e-05, + "loss": 0.1031, + "step": 335130 + }, + { + "epoch": 0.75, + "learning_rate": 1.2640992371535313e-05, + "loss": 0.104, + "step": 335140 + }, + { + "epoch": 0.75, + "learning_rate": 1.2639873828325988e-05, + "loss": 0.1025, + "step": 335150 + }, + { + "epoch": 0.75, + "learning_rate": 1.2638755285116666e-05, + "loss": 0.1035, + "step": 335160 + }, + { + "epoch": 0.75, + "learning_rate": 1.2637636741907342e-05, + "loss": 0.1019, + "step": 335170 + }, + { + "epoch": 0.75, + "learning_rate": 1.2636518198698016e-05, + "loss": 0.1047, + "step": 335180 + }, + { + "epoch": 0.75, + "learning_rate": 1.2635399655488691e-05, + "loss": 0.1043, + "step": 335190 + }, + { + "epoch": 0.75, + "learning_rate": 1.2634281112279367e-05, + "loss": 0.1046, + "step": 335200 + }, + { + "epoch": 0.75, + "learning_rate": 1.2633162569070045e-05, + "loss": 0.1047, + "step": 335210 + }, + { + "epoch": 0.75, + "learning_rate": 1.263204402586072e-05, + "loss": 0.1037, + "step": 335220 + }, + { + "epoch": 0.75, + "learning_rate": 1.2630925482651396e-05, + "loss": 0.105, + "step": 335230 + }, + { + "epoch": 0.75, + "learning_rate": 1.262980693944207e-05, + "loss": 0.1024, + "step": 335240 + }, + { + "epoch": 0.75, + "learning_rate": 1.2628688396232747e-05, + "loss": 0.1069, + "step": 335250 + }, + { + "epoch": 0.75, + "learning_rate": 1.2627569853023421e-05, + "loss": 0.1092, + "step": 335260 + }, + { + "epoch": 0.75, + "learning_rate": 1.2626451309814099e-05, + "loss": 0.1062, + "step": 335270 + }, + { + "epoch": 0.75, + "learning_rate": 1.2625332766604775e-05, + "loss": 0.1079, + "step": 335280 + }, + { + "epoch": 0.75, + "learning_rate": 1.262421422339545e-05, + "loss": 0.1046, + "step": 335290 + }, + { + "epoch": 0.75, + "learning_rate": 1.2623095680186126e-05, + "loss": 0.1047, + "step": 335300 + }, + { + "epoch": 0.75, + "learning_rate": 1.26219771369768e-05, + "loss": 0.1065, + "step": 335310 + }, + { + "epoch": 0.75, + "learning_rate": 1.2620858593767479e-05, + "loss": 0.108, + "step": 335320 + }, + { + "epoch": 0.75, + "learning_rate": 1.2619740050558155e-05, + "loss": 0.1031, + "step": 335330 + }, + { + "epoch": 0.75, + "learning_rate": 1.261862150734883e-05, + "loss": 0.1045, + "step": 335340 + }, + { + "epoch": 0.75, + "learning_rate": 1.2617502964139506e-05, + "loss": 0.1052, + "step": 335350 + }, + { + "epoch": 0.75, + "learning_rate": 1.261638442093018e-05, + "loss": 0.1055, + "step": 335360 + }, + { + "epoch": 0.75, + "learning_rate": 1.2615265877720858e-05, + "loss": 0.1052, + "step": 335370 + }, + { + "epoch": 0.75, + "learning_rate": 1.2614147334511534e-05, + "loss": 0.1039, + "step": 335380 + }, + { + "epoch": 0.75, + "learning_rate": 1.2613028791302209e-05, + "loss": 0.101, + "step": 335390 + }, + { + "epoch": 0.75, + "learning_rate": 1.2611910248092883e-05, + "loss": 0.1019, + "step": 335400 + }, + { + "epoch": 0.75, + "learning_rate": 1.261079170488356e-05, + "loss": 0.1079, + "step": 335410 + }, + { + "epoch": 0.75, + "learning_rate": 1.2609673161674234e-05, + "loss": 0.1038, + "step": 335420 + }, + { + "epoch": 0.75, + "learning_rate": 1.2608554618464912e-05, + "loss": 0.1036, + "step": 335430 + }, + { + "epoch": 0.75, + "learning_rate": 1.2607436075255588e-05, + "loss": 0.1034, + "step": 335440 + }, + { + "epoch": 0.75, + "learning_rate": 1.2606317532046263e-05, + "loss": 0.1042, + "step": 335450 + }, + { + "epoch": 0.75, + "learning_rate": 1.2605198988836939e-05, + "loss": 0.1034, + "step": 335460 + }, + { + "epoch": 0.75, + "learning_rate": 1.2604080445627614e-05, + "loss": 0.1073, + "step": 335470 + }, + { + "epoch": 0.75, + "learning_rate": 1.2602961902418291e-05, + "loss": 0.1063, + "step": 335480 + }, + { + "epoch": 0.75, + "learning_rate": 1.2601843359208968e-05, + "loss": 0.1078, + "step": 335490 + }, + { + "epoch": 0.75, + "learning_rate": 1.2600724815999642e-05, + "loss": 0.1016, + "step": 335500 + }, + { + "epoch": 0.75, + "learning_rate": 1.2599606272790319e-05, + "loss": 0.1052, + "step": 335510 + }, + { + "epoch": 0.75, + "learning_rate": 1.2598487729580993e-05, + "loss": 0.1025, + "step": 335520 + }, + { + "epoch": 0.75, + "learning_rate": 1.2597369186371671e-05, + "loss": 0.1053, + "step": 335530 + }, + { + "epoch": 0.75, + "learning_rate": 1.2596250643162347e-05, + "loss": 0.1044, + "step": 335540 + }, + { + "epoch": 0.75, + "learning_rate": 1.2595132099953022e-05, + "loss": 0.105, + "step": 335550 + }, + { + "epoch": 0.75, + "learning_rate": 1.2594013556743698e-05, + "loss": 0.1038, + "step": 335560 + }, + { + "epoch": 0.75, + "learning_rate": 1.2592895013534373e-05, + "loss": 0.1054, + "step": 335570 + }, + { + "epoch": 0.75, + "learning_rate": 1.2591776470325049e-05, + "loss": 0.1022, + "step": 335580 + }, + { + "epoch": 0.75, + "learning_rate": 1.2590657927115727e-05, + "loss": 0.1071, + "step": 335590 + }, + { + "epoch": 0.75, + "learning_rate": 1.2589539383906401e-05, + "loss": 0.1013, + "step": 335600 + }, + { + "epoch": 0.75, + "learning_rate": 1.2588420840697077e-05, + "loss": 0.1047, + "step": 335610 + }, + { + "epoch": 0.75, + "learning_rate": 1.2587302297487752e-05, + "loss": 0.105, + "step": 335620 + }, + { + "epoch": 0.75, + "learning_rate": 1.2586183754278427e-05, + "loss": 0.1065, + "step": 335630 + }, + { + "epoch": 0.75, + "learning_rate": 1.2585065211069104e-05, + "loss": 0.1077, + "step": 335640 + }, + { + "epoch": 0.75, + "learning_rate": 1.258394666785978e-05, + "loss": 0.1024, + "step": 335650 + }, + { + "epoch": 0.75, + "learning_rate": 1.2582828124650455e-05, + "loss": 0.106, + "step": 335660 + }, + { + "epoch": 0.75, + "learning_rate": 1.2581709581441131e-05, + "loss": 0.1022, + "step": 335670 + }, + { + "epoch": 0.75, + "learning_rate": 1.2580591038231806e-05, + "loss": 0.1062, + "step": 335680 + }, + { + "epoch": 0.75, + "learning_rate": 1.2579472495022484e-05, + "loss": 0.1054, + "step": 335690 + }, + { + "epoch": 0.75, + "learning_rate": 1.257835395181316e-05, + "loss": 0.1086, + "step": 335700 + }, + { + "epoch": 0.75, + "learning_rate": 1.2577235408603835e-05, + "loss": 0.1116, + "step": 335710 + }, + { + "epoch": 0.75, + "learning_rate": 1.2576116865394511e-05, + "loss": 0.1031, + "step": 335720 + }, + { + "epoch": 0.75, + "learning_rate": 1.2574998322185185e-05, + "loss": 0.1057, + "step": 335730 + }, + { + "epoch": 0.75, + "learning_rate": 1.2573879778975862e-05, + "loss": 0.1077, + "step": 335740 + }, + { + "epoch": 0.75, + "learning_rate": 1.257276123576654e-05, + "loss": 0.1108, + "step": 335750 + }, + { + "epoch": 0.75, + "learning_rate": 1.2571642692557214e-05, + "loss": 0.1072, + "step": 335760 + }, + { + "epoch": 0.75, + "learning_rate": 1.257052414934789e-05, + "loss": 0.1049, + "step": 335770 + }, + { + "epoch": 0.75, + "learning_rate": 1.2569405606138565e-05, + "loss": 0.1053, + "step": 335780 + }, + { + "epoch": 0.75, + "learning_rate": 1.2568287062929241e-05, + "loss": 0.1016, + "step": 335790 + }, + { + "epoch": 0.75, + "learning_rate": 1.2567168519719919e-05, + "loss": 0.1043, + "step": 335800 + }, + { + "epoch": 0.75, + "learning_rate": 1.2566049976510594e-05, + "loss": 0.1071, + "step": 335810 + }, + { + "epoch": 0.75, + "learning_rate": 1.256493143330127e-05, + "loss": 0.1, + "step": 335820 + }, + { + "epoch": 0.75, + "learning_rate": 1.2563812890091944e-05, + "loss": 0.105, + "step": 335830 + }, + { + "epoch": 0.75, + "learning_rate": 1.2562694346882619e-05, + "loss": 0.1095, + "step": 335840 + }, + { + "epoch": 0.75, + "learning_rate": 1.2561575803673299e-05, + "loss": 0.1088, + "step": 335850 + }, + { + "epoch": 0.75, + "learning_rate": 1.2560457260463973e-05, + "loss": 0.0997, + "step": 335860 + }, + { + "epoch": 0.75, + "learning_rate": 1.2559338717254648e-05, + "loss": 0.1016, + "step": 335870 + }, + { + "epoch": 0.75, + "learning_rate": 1.2558220174045324e-05, + "loss": 0.1086, + "step": 335880 + }, + { + "epoch": 0.75, + "learning_rate": 1.2557101630835998e-05, + "loss": 0.1006, + "step": 335890 + }, + { + "epoch": 0.75, + "learning_rate": 1.2555983087626675e-05, + "loss": 0.1017, + "step": 335900 + }, + { + "epoch": 0.75, + "learning_rate": 1.2554864544417353e-05, + "loss": 0.0987, + "step": 335910 + }, + { + "epoch": 0.75, + "learning_rate": 1.2553746001208027e-05, + "loss": 0.1047, + "step": 335920 + }, + { + "epoch": 0.75, + "learning_rate": 1.2552627457998703e-05, + "loss": 0.1009, + "step": 335930 + }, + { + "epoch": 0.75, + "learning_rate": 1.2551508914789378e-05, + "loss": 0.1027, + "step": 335940 + }, + { + "epoch": 0.75, + "learning_rate": 1.2550390371580054e-05, + "loss": 0.107, + "step": 335950 + }, + { + "epoch": 0.75, + "learning_rate": 1.2549271828370732e-05, + "loss": 0.108, + "step": 335960 + }, + { + "epoch": 0.75, + "learning_rate": 1.2548153285161407e-05, + "loss": 0.1054, + "step": 335970 + }, + { + "epoch": 0.75, + "learning_rate": 1.2547034741952083e-05, + "loss": 0.1056, + "step": 335980 + }, + { + "epoch": 0.75, + "learning_rate": 1.2545916198742757e-05, + "loss": 0.1044, + "step": 335990 + }, + { + "epoch": 0.75, + "learning_rate": 1.2544797655533434e-05, + "loss": 0.1069, + "step": 336000 + }, + { + "epoch": 0.75, + "eval_NEIMS_canon_smiles": 0.9598, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.23185, + "eval_NEIMS_daylight_tanimoto_simil": 0.6092017483957141, + "eval_NEIMS_exact_mols": 0.23151666666666668, + "eval_NEIMS_exact_smiles": 0.2267, + "eval_NEIMS_loss": 0.13373883068561554, + "eval_NEIMS_matched_formulas": 0.73815, + "eval_NEIMS_morgan_tanimoto_simil": 0.5333237860673729, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.23225, + "eval_NEIMS_runtime": 729.3187, + "eval_NEIMS_samples_per_second": 82.269, + "eval_NEIMS_steps_per_second": 1.286, + "step": 336000 + }, + { + "epoch": 0.75, + "eval_RASSP_canon_smiles": 0.9603299161852606, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.30498881357064145, + "eval_RASSP_daylight_tanimoto_simil": 0.7071594432624524, + "eval_RASSP_exact_mols": 0.304254182388887, + "eval_RASSP_exact_smiles": 0.29777607105887066, + "eval_RASSP_loss": 0.10466679185628891, + "eval_RASSP_matched_formulas": 0.8665642635322403, + "eval_RASSP_morgan_tanimoto_simil": 0.5977567263106323, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.304471232510769, + "eval_RASSP_runtime": 830.0726, + "eval_RASSP_samples_per_second": 72.155, + "eval_RASSP_steps_per_second": 1.128, + "step": 336000 + }, + { + "epoch": 0.75, + "eval_NEIMS_old_canon_smiles": 0.9605666666666667, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.22926666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6060298818317755, + "eval_NEIMS_old_exact_mols": 0.22886666666666666, + "eval_NEIMS_old_exact_smiles": 0.22356666666666666, + "eval_NEIMS_old_loss": 0.13339847326278687, + "eval_NEIMS_old_matched_formulas": 0.7393, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5310999196083058, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2298, + "eval_NEIMS_old_runtime": 365.9707, + "eval_NEIMS_old_samples_per_second": 81.974, + "eval_NEIMS_old_steps_per_second": 1.282, + "step": 336000 + }, + { + "epoch": 0.75, + "eval_RASSP_old_canon_smiles": 0.9602229118697234, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.33279941268728935, + "eval_RASSP_old_daylight_tanimoto_simil": 0.726118264298973, + "eval_RASSP_old_exact_mols": 0.3319651616778456, + "eval_RASSP_old_exact_smiles": 0.3246571228351186, + "eval_RASSP_old_loss": 0.0979069322347641, + "eval_RASSP_old_matched_formulas": 0.8776654319751727, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6210304017155047, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.33203190175860114, + "eval_RASSP_old_runtime": 414.3229, + "eval_RASSP_old_samples_per_second": 72.328, + "eval_RASSP_old_steps_per_second": 1.132, + "step": 336000 + }, + { + "epoch": 0.75, + "eval_NIST_canon_smiles": 0.8715264222592894, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.027646662171274445, + "eval_NIST_daylight_tanimoto_simil": 0.3026209843559768, + "eval_NIST_exact_mols": 0.026617453951804662, + "eval_NIST_exact_smiles": 0.02551726585513007, + "eval_NIST_loss": 1.785333514213562, + "eval_NIST_matched_formulas": 0.12407282535401214, + "eval_NIST_morgan_tanimoto_simil": 0.2538043660016317, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.027433722539660005, + "eval_NIST_runtime": 535.8192, + "eval_NIST_samples_per_second": 52.587, + "eval_NIST_steps_per_second": 0.823, + "step": 336000 + }, + { + "epoch": 0.75, + "learning_rate": 1.2543679112324112e-05, + "loss": 0.1065, + "step": 336010 + }, + { + "epoch": 0.75, + "learning_rate": 1.2542560569114786e-05, + "loss": 0.1083, + "step": 336020 + }, + { + "epoch": 0.75, + "learning_rate": 1.2541442025905462e-05, + "loss": 0.1029, + "step": 336030 + }, + { + "epoch": 0.75, + "learning_rate": 1.2540323482696137e-05, + "loss": 0.103, + "step": 336040 + }, + { + "epoch": 0.75, + "learning_rate": 1.2539204939486811e-05, + "loss": 0.1036, + "step": 336050 + }, + { + "epoch": 0.75, + "learning_rate": 1.2538086396277488e-05, + "loss": 0.1042, + "step": 336060 + }, + { + "epoch": 0.75, + "learning_rate": 1.2536967853068166e-05, + "loss": 0.1084, + "step": 336070 + }, + { + "epoch": 0.75, + "learning_rate": 1.253584930985884e-05, + "loss": 0.1039, + "step": 336080 + }, + { + "epoch": 0.75, + "learning_rate": 1.2534730766649516e-05, + "loss": 0.1031, + "step": 336090 + }, + { + "epoch": 0.75, + "learning_rate": 1.2533612223440191e-05, + "loss": 0.1035, + "step": 336100 + }, + { + "epoch": 0.75, + "learning_rate": 1.2532493680230867e-05, + "loss": 0.1021, + "step": 336110 + }, + { + "epoch": 0.75, + "learning_rate": 1.2531375137021545e-05, + "loss": 0.1024, + "step": 336120 + }, + { + "epoch": 0.75, + "learning_rate": 1.253025659381222e-05, + "loss": 0.1048, + "step": 336130 + }, + { + "epoch": 0.75, + "learning_rate": 1.2529138050602896e-05, + "loss": 0.1036, + "step": 336140 + }, + { + "epoch": 0.75, + "learning_rate": 1.252801950739357e-05, + "loss": 0.1025, + "step": 336150 + }, + { + "epoch": 0.75, + "learning_rate": 1.2526900964184247e-05, + "loss": 0.1028, + "step": 336160 + }, + { + "epoch": 0.75, + "learning_rate": 1.2525782420974925e-05, + "loss": 0.1034, + "step": 336170 + }, + { + "epoch": 0.75, + "learning_rate": 1.2524663877765599e-05, + "loss": 0.1051, + "step": 336180 + }, + { + "epoch": 0.75, + "learning_rate": 1.2523545334556275e-05, + "loss": 0.1047, + "step": 336190 + }, + { + "epoch": 0.75, + "learning_rate": 1.252242679134695e-05, + "loss": 0.1049, + "step": 336200 + }, + { + "epoch": 0.75, + "learning_rate": 1.2521308248137626e-05, + "loss": 0.1011, + "step": 336210 + }, + { + "epoch": 0.75, + "learning_rate": 1.25201897049283e-05, + "loss": 0.1021, + "step": 336220 + }, + { + "epoch": 0.75, + "learning_rate": 1.2519071161718979e-05, + "loss": 0.1021, + "step": 336230 + }, + { + "epoch": 0.75, + "learning_rate": 1.2517952618509655e-05, + "loss": 0.1041, + "step": 336240 + }, + { + "epoch": 0.75, + "learning_rate": 1.251683407530033e-05, + "loss": 0.1045, + "step": 336250 + }, + { + "epoch": 0.75, + "learning_rate": 1.2515715532091004e-05, + "loss": 0.1029, + "step": 336260 + }, + { + "epoch": 0.75, + "learning_rate": 1.251459698888168e-05, + "loss": 0.1038, + "step": 336270 + }, + { + "epoch": 0.75, + "learning_rate": 1.2513478445672358e-05, + "loss": 0.1063, + "step": 336280 + }, + { + "epoch": 0.75, + "learning_rate": 1.2512359902463033e-05, + "loss": 0.104, + "step": 336290 + }, + { + "epoch": 0.75, + "learning_rate": 1.2511241359253709e-05, + "loss": 0.0999, + "step": 336300 + }, + { + "epoch": 0.75, + "learning_rate": 1.2510122816044383e-05, + "loss": 0.103, + "step": 336310 + }, + { + "epoch": 0.75, + "learning_rate": 1.250900427283506e-05, + "loss": 0.1056, + "step": 336320 + }, + { + "epoch": 0.75, + "learning_rate": 1.2507885729625737e-05, + "loss": 0.1027, + "step": 336330 + }, + { + "epoch": 0.75, + "learning_rate": 1.2506767186416412e-05, + "loss": 0.1073, + "step": 336340 + }, + { + "epoch": 0.75, + "learning_rate": 1.2505648643207088e-05, + "loss": 0.1059, + "step": 336350 + }, + { + "epoch": 0.75, + "learning_rate": 1.2504530099997763e-05, + "loss": 0.1016, + "step": 336360 + }, + { + "epoch": 0.75, + "learning_rate": 1.2503411556788439e-05, + "loss": 0.1066, + "step": 336370 + }, + { + "epoch": 0.75, + "learning_rate": 1.2502293013579114e-05, + "loss": 0.1024, + "step": 336380 + }, + { + "epoch": 0.75, + "learning_rate": 1.2501174470369791e-05, + "loss": 0.1049, + "step": 336390 + }, + { + "epoch": 0.75, + "learning_rate": 1.2500055927160468e-05, + "loss": 0.1022, + "step": 336400 + }, + { + "epoch": 0.75, + "learning_rate": 1.2498937383951142e-05, + "loss": 0.106, + "step": 336410 + }, + { + "epoch": 0.75, + "learning_rate": 1.2497818840741818e-05, + "loss": 0.1105, + "step": 336420 + }, + { + "epoch": 0.75, + "learning_rate": 1.2496700297532495e-05, + "loss": 0.1043, + "step": 336430 + }, + { + "epoch": 0.75, + "learning_rate": 1.249558175432317e-05, + "loss": 0.1057, + "step": 336440 + }, + { + "epoch": 0.75, + "learning_rate": 1.2494463211113847e-05, + "loss": 0.1061, + "step": 336450 + }, + { + "epoch": 0.75, + "learning_rate": 1.2493344667904522e-05, + "loss": 0.1022, + "step": 336460 + }, + { + "epoch": 0.75, + "learning_rate": 1.2492226124695198e-05, + "loss": 0.1022, + "step": 336470 + }, + { + "epoch": 0.75, + "learning_rate": 1.2491107581485874e-05, + "loss": 0.1031, + "step": 336480 + }, + { + "epoch": 0.75, + "learning_rate": 1.2489989038276549e-05, + "loss": 0.1078, + "step": 336490 + }, + { + "epoch": 0.75, + "learning_rate": 1.2488870495067225e-05, + "loss": 0.1049, + "step": 336500 + }, + { + "epoch": 0.75, + "learning_rate": 1.2487751951857901e-05, + "loss": 0.1061, + "step": 336510 + }, + { + "epoch": 0.75, + "learning_rate": 1.2486633408648576e-05, + "loss": 0.1059, + "step": 336520 + }, + { + "epoch": 0.75, + "learning_rate": 1.2485514865439254e-05, + "loss": 0.1122, + "step": 336530 + }, + { + "epoch": 0.75, + "learning_rate": 1.2484396322229928e-05, + "loss": 0.1078, + "step": 336540 + }, + { + "epoch": 0.75, + "learning_rate": 1.2483389633341537e-05, + "loss": 0.1041, + "step": 336550 + }, + { + "epoch": 0.75, + "learning_rate": 1.2482271090132212e-05, + "loss": 0.1021, + "step": 336560 + }, + { + "epoch": 0.75, + "learning_rate": 1.2481152546922888e-05, + "loss": 0.1044, + "step": 336570 + }, + { + "epoch": 0.75, + "learning_rate": 1.2480034003713564e-05, + "loss": 0.1025, + "step": 336580 + }, + { + "epoch": 0.75, + "learning_rate": 1.247891546050424e-05, + "loss": 0.1019, + "step": 336590 + }, + { + "epoch": 0.75, + "learning_rate": 1.2477796917294916e-05, + "loss": 0.1044, + "step": 336600 + }, + { + "epoch": 0.75, + "learning_rate": 1.2476678374085591e-05, + "loss": 0.103, + "step": 336610 + }, + { + "epoch": 0.75, + "learning_rate": 1.2475559830876267e-05, + "loss": 0.1052, + "step": 336620 + }, + { + "epoch": 0.75, + "learning_rate": 1.2474441287666943e-05, + "loss": 0.1044, + "step": 336630 + }, + { + "epoch": 0.75, + "learning_rate": 1.247332274445762e-05, + "loss": 0.1022, + "step": 336640 + }, + { + "epoch": 0.75, + "learning_rate": 1.2472204201248294e-05, + "loss": 0.1056, + "step": 336650 + }, + { + "epoch": 0.75, + "learning_rate": 1.247108565803897e-05, + "loss": 0.102, + "step": 336660 + }, + { + "epoch": 0.75, + "learning_rate": 1.2469967114829647e-05, + "loss": 0.1032, + "step": 336670 + }, + { + "epoch": 0.75, + "learning_rate": 1.2468848571620323e-05, + "loss": 0.1011, + "step": 336680 + }, + { + "epoch": 0.75, + "learning_rate": 1.2467730028410997e-05, + "loss": 0.1075, + "step": 336690 + }, + { + "epoch": 0.75, + "learning_rate": 1.2466611485201674e-05, + "loss": 0.1064, + "step": 336700 + }, + { + "epoch": 0.75, + "learning_rate": 1.246549294199235e-05, + "loss": 0.1068, + "step": 336710 + }, + { + "epoch": 0.75, + "learning_rate": 1.2464374398783026e-05, + "loss": 0.1033, + "step": 336720 + }, + { + "epoch": 0.75, + "learning_rate": 1.24632558555737e-05, + "loss": 0.1093, + "step": 336730 + }, + { + "epoch": 0.75, + "learning_rate": 1.2462137312364377e-05, + "loss": 0.1046, + "step": 336740 + }, + { + "epoch": 0.75, + "learning_rate": 1.2461018769155053e-05, + "loss": 0.1065, + "step": 336750 + }, + { + "epoch": 0.75, + "learning_rate": 1.245990022594573e-05, + "loss": 0.1059, + "step": 336760 + }, + { + "epoch": 0.75, + "learning_rate": 1.2458781682736406e-05, + "loss": 0.1076, + "step": 336770 + }, + { + "epoch": 0.75, + "learning_rate": 1.245766313952708e-05, + "loss": 0.1098, + "step": 336780 + }, + { + "epoch": 0.75, + "learning_rate": 1.2456544596317756e-05, + "loss": 0.1056, + "step": 336790 + }, + { + "epoch": 0.75, + "learning_rate": 1.2455426053108433e-05, + "loss": 0.1064, + "step": 336800 + }, + { + "epoch": 0.75, + "learning_rate": 1.2454307509899107e-05, + "loss": 0.1046, + "step": 336810 + }, + { + "epoch": 0.75, + "learning_rate": 1.2453188966689783e-05, + "loss": 0.1075, + "step": 336820 + }, + { + "epoch": 0.75, + "learning_rate": 1.245207042348046e-05, + "loss": 0.1041, + "step": 336830 + }, + { + "epoch": 0.75, + "learning_rate": 1.2450951880271136e-05, + "loss": 0.1063, + "step": 336840 + }, + { + "epoch": 0.75, + "learning_rate": 1.2449833337061812e-05, + "loss": 0.104, + "step": 336850 + }, + { + "epoch": 0.75, + "learning_rate": 1.2448714793852487e-05, + "loss": 0.1062, + "step": 336860 + }, + { + "epoch": 0.75, + "learning_rate": 1.2447596250643163e-05, + "loss": 0.105, + "step": 336870 + }, + { + "epoch": 0.75, + "learning_rate": 1.2446477707433839e-05, + "loss": 0.1032, + "step": 336880 + }, + { + "epoch": 0.75, + "learning_rate": 1.2445359164224514e-05, + "loss": 0.1085, + "step": 336890 + }, + { + "epoch": 0.75, + "learning_rate": 1.244424062101519e-05, + "loss": 0.106, + "step": 336900 + }, + { + "epoch": 0.75, + "learning_rate": 1.2443122077805866e-05, + "loss": 0.1066, + "step": 336910 + }, + { + "epoch": 0.75, + "learning_rate": 1.2442003534596542e-05, + "loss": 0.0992, + "step": 336920 + }, + { + "epoch": 0.75, + "learning_rate": 1.2440884991387219e-05, + "loss": 0.104, + "step": 336930 + }, + { + "epoch": 0.75, + "learning_rate": 1.2439766448177893e-05, + "loss": 0.1071, + "step": 336940 + }, + { + "epoch": 0.75, + "learning_rate": 1.243864790496857e-05, + "loss": 0.1055, + "step": 336950 + }, + { + "epoch": 0.75, + "learning_rate": 1.2437529361759246e-05, + "loss": 0.1079, + "step": 336960 + }, + { + "epoch": 0.75, + "learning_rate": 1.243641081854992e-05, + "loss": 0.1066, + "step": 336970 + }, + { + "epoch": 0.75, + "learning_rate": 1.2435292275340598e-05, + "loss": 0.1065, + "step": 336980 + }, + { + "epoch": 0.75, + "learning_rate": 1.2434173732131273e-05, + "loss": 0.1033, + "step": 336990 + }, + { + "epoch": 0.75, + "learning_rate": 1.2433055188921949e-05, + "loss": 0.1073, + "step": 337000 + }, + { + "epoch": 0.75, + "learning_rate": 1.2431936645712625e-05, + "loss": 0.1102, + "step": 337010 + }, + { + "epoch": 0.75, + "learning_rate": 1.24308181025033e-05, + "loss": 0.104, + "step": 337020 + }, + { + "epoch": 0.75, + "learning_rate": 1.2429699559293976e-05, + "loss": 0.1063, + "step": 337030 + }, + { + "epoch": 0.75, + "learning_rate": 1.2428581016084652e-05, + "loss": 0.1044, + "step": 337040 + }, + { + "epoch": 0.75, + "learning_rate": 1.2427462472875327e-05, + "loss": 0.1034, + "step": 337050 + }, + { + "epoch": 0.75, + "learning_rate": 1.2426343929666005e-05, + "loss": 0.1082, + "step": 337060 + }, + { + "epoch": 0.75, + "learning_rate": 1.2425225386456679e-05, + "loss": 0.1053, + "step": 337070 + }, + { + "epoch": 0.75, + "learning_rate": 1.2424106843247355e-05, + "loss": 0.1041, + "step": 337080 + }, + { + "epoch": 0.75, + "learning_rate": 1.2422988300038032e-05, + "loss": 0.1049, + "step": 337090 + }, + { + "epoch": 0.75, + "learning_rate": 1.2421869756828706e-05, + "loss": 0.1051, + "step": 337100 + }, + { + "epoch": 0.75, + "learning_rate": 1.2420751213619384e-05, + "loss": 0.1043, + "step": 337110 + }, + { + "epoch": 0.75, + "learning_rate": 1.2419632670410059e-05, + "loss": 0.1057, + "step": 337120 + }, + { + "epoch": 0.75, + "learning_rate": 1.2418514127200733e-05, + "loss": 0.1063, + "step": 337130 + }, + { + "epoch": 0.75, + "learning_rate": 1.2417395583991411e-05, + "loss": 0.1047, + "step": 337140 + }, + { + "epoch": 0.75, + "learning_rate": 1.2416277040782086e-05, + "loss": 0.1027, + "step": 337150 + }, + { + "epoch": 0.75, + "learning_rate": 1.2415158497572762e-05, + "loss": 0.1037, + "step": 337160 + }, + { + "epoch": 0.75, + "learning_rate": 1.2414039954363438e-05, + "loss": 0.1017, + "step": 337170 + }, + { + "epoch": 0.75, + "learning_rate": 1.2412921411154113e-05, + "loss": 0.1017, + "step": 337180 + }, + { + "epoch": 0.75, + "learning_rate": 1.241180286794479e-05, + "loss": 0.1037, + "step": 337190 + }, + { + "epoch": 0.75, + "learning_rate": 1.2410684324735465e-05, + "loss": 0.1048, + "step": 337200 + }, + { + "epoch": 0.75, + "learning_rate": 1.240956578152614e-05, + "loss": 0.1028, + "step": 337210 + }, + { + "epoch": 0.75, + "learning_rate": 1.2408447238316818e-05, + "loss": 0.1061, + "step": 337220 + }, + { + "epoch": 0.75, + "learning_rate": 1.2407328695107492e-05, + "loss": 0.1041, + "step": 337230 + }, + { + "epoch": 0.75, + "learning_rate": 1.2406210151898168e-05, + "loss": 0.1011, + "step": 337240 + }, + { + "epoch": 0.75, + "learning_rate": 1.2405091608688845e-05, + "loss": 0.1028, + "step": 337250 + }, + { + "epoch": 0.75, + "learning_rate": 1.2403973065479519e-05, + "loss": 0.103, + "step": 337260 + }, + { + "epoch": 0.75, + "learning_rate": 1.2402854522270197e-05, + "loss": 0.1062, + "step": 337270 + }, + { + "epoch": 0.75, + "learning_rate": 1.2401735979060872e-05, + "loss": 0.1037, + "step": 337280 + }, + { + "epoch": 0.75, + "learning_rate": 1.2400617435851548e-05, + "loss": 0.1084, + "step": 337290 + }, + { + "epoch": 0.75, + "learning_rate": 1.2399498892642224e-05, + "loss": 0.1089, + "step": 337300 + }, + { + "epoch": 0.75, + "learning_rate": 1.2398380349432899e-05, + "loss": 0.1034, + "step": 337310 + }, + { + "epoch": 0.75, + "learning_rate": 1.2397261806223576e-05, + "loss": 0.1047, + "step": 337320 + }, + { + "epoch": 0.75, + "learning_rate": 1.2396143263014251e-05, + "loss": 0.1031, + "step": 337330 + }, + { + "epoch": 0.75, + "learning_rate": 1.2395024719804926e-05, + "loss": 0.1033, + "step": 337340 + }, + { + "epoch": 0.75, + "learning_rate": 1.2393906176595603e-05, + "loss": 0.1015, + "step": 337350 + }, + { + "epoch": 0.75, + "learning_rate": 1.2392787633386278e-05, + "loss": 0.102, + "step": 337360 + }, + { + "epoch": 0.75, + "learning_rate": 1.2391669090176954e-05, + "loss": 0.1035, + "step": 337370 + }, + { + "epoch": 0.75, + "learning_rate": 1.239055054696763e-05, + "loss": 0.1068, + "step": 337380 + }, + { + "epoch": 0.75, + "learning_rate": 1.2389432003758305e-05, + "loss": 0.1051, + "step": 337390 + }, + { + "epoch": 0.75, + "learning_rate": 1.2388313460548983e-05, + "loss": 0.1069, + "step": 337400 + }, + { + "epoch": 0.75, + "learning_rate": 1.2387194917339658e-05, + "loss": 0.1052, + "step": 337410 + }, + { + "epoch": 0.75, + "learning_rate": 1.2386076374130332e-05, + "loss": 0.104, + "step": 337420 + }, + { + "epoch": 0.75, + "learning_rate": 1.238495783092101e-05, + "loss": 0.1052, + "step": 337430 + }, + { + "epoch": 0.75, + "learning_rate": 1.2383839287711685e-05, + "loss": 0.1054, + "step": 337440 + }, + { + "epoch": 0.75, + "learning_rate": 1.238272074450236e-05, + "loss": 0.1055, + "step": 337450 + }, + { + "epoch": 0.75, + "learning_rate": 1.2381602201293037e-05, + "loss": 0.1044, + "step": 337460 + }, + { + "epoch": 0.75, + "learning_rate": 1.2380483658083712e-05, + "loss": 0.1047, + "step": 337470 + }, + { + "epoch": 0.75, + "learning_rate": 1.237936511487439e-05, + "loss": 0.1043, + "step": 337480 + }, + { + "epoch": 0.75, + "learning_rate": 1.2378246571665064e-05, + "loss": 0.1009, + "step": 337490 + }, + { + "epoch": 0.75, + "learning_rate": 1.237712802845574e-05, + "loss": 0.1025, + "step": 337500 + }, + { + "epoch": 0.75, + "learning_rate": 1.2376009485246416e-05, + "loss": 0.1053, + "step": 337510 + }, + { + "epoch": 0.75, + "learning_rate": 1.2374890942037091e-05, + "loss": 0.1052, + "step": 337520 + }, + { + "epoch": 0.75, + "learning_rate": 1.2373772398827767e-05, + "loss": 0.1085, + "step": 337530 + }, + { + "epoch": 0.75, + "learning_rate": 1.2372653855618443e-05, + "loss": 0.107, + "step": 337540 + }, + { + "epoch": 0.75, + "learning_rate": 1.2371535312409118e-05, + "loss": 0.0975, + "step": 337550 + }, + { + "epoch": 0.75, + "learning_rate": 1.2370416769199796e-05, + "loss": 0.1036, + "step": 337560 + }, + { + "epoch": 0.75, + "learning_rate": 1.236929822599047e-05, + "loss": 0.1025, + "step": 337570 + }, + { + "epoch": 0.75, + "learning_rate": 1.2368179682781147e-05, + "loss": 0.1035, + "step": 337580 + }, + { + "epoch": 0.75, + "learning_rate": 1.2367061139571823e-05, + "loss": 0.1073, + "step": 337590 + }, + { + "epoch": 0.75, + "learning_rate": 1.2365942596362497e-05, + "loss": 0.1069, + "step": 337600 + }, + { + "epoch": 0.75, + "learning_rate": 1.2364824053153174e-05, + "loss": 0.1033, + "step": 337610 + }, + { + "epoch": 0.75, + "learning_rate": 1.236370550994385e-05, + "loss": 0.1015, + "step": 337620 + }, + { + "epoch": 0.75, + "learning_rate": 1.2362586966734526e-05, + "loss": 0.1051, + "step": 337630 + }, + { + "epoch": 0.75, + "learning_rate": 1.23614684235252e-05, + "loss": 0.104, + "step": 337640 + }, + { + "epoch": 0.75, + "learning_rate": 1.2360349880315877e-05, + "loss": 0.1054, + "step": 337650 + }, + { + "epoch": 0.75, + "learning_rate": 1.2359231337106553e-05, + "loss": 0.1035, + "step": 337660 + }, + { + "epoch": 0.75, + "learning_rate": 1.235811279389723e-05, + "loss": 0.1063, + "step": 337670 + }, + { + "epoch": 0.75, + "learning_rate": 1.2356994250687904e-05, + "loss": 0.102, + "step": 337680 + }, + { + "epoch": 0.75, + "learning_rate": 1.235587570747858e-05, + "loss": 0.1019, + "step": 337690 + }, + { + "epoch": 0.75, + "learning_rate": 1.2354757164269256e-05, + "loss": 0.1011, + "step": 337700 + }, + { + "epoch": 0.75, + "learning_rate": 1.2353638621059933e-05, + "loss": 0.1035, + "step": 337710 + }, + { + "epoch": 0.75, + "learning_rate": 1.2352520077850607e-05, + "loss": 0.1044, + "step": 337720 + }, + { + "epoch": 0.75, + "learning_rate": 1.2351401534641283e-05, + "loss": 0.1064, + "step": 337730 + }, + { + "epoch": 0.75, + "learning_rate": 1.235028299143196e-05, + "loss": 0.108, + "step": 337740 + }, + { + "epoch": 0.75, + "learning_rate": 1.2349164448222636e-05, + "loss": 0.1077, + "step": 337750 + }, + { + "epoch": 0.75, + "learning_rate": 1.234804590501331e-05, + "loss": 0.1028, + "step": 337760 + }, + { + "epoch": 0.75, + "learning_rate": 1.2346927361803987e-05, + "loss": 0.1014, + "step": 337770 + }, + { + "epoch": 0.75, + "learning_rate": 1.2345808818594663e-05, + "loss": 0.1067, + "step": 337780 + }, + { + "epoch": 0.75, + "learning_rate": 1.2344690275385339e-05, + "loss": 0.1017, + "step": 337790 + }, + { + "epoch": 0.75, + "learning_rate": 1.2343571732176014e-05, + "loss": 0.1028, + "step": 337800 + }, + { + "epoch": 0.75, + "learning_rate": 1.234245318896669e-05, + "loss": 0.1032, + "step": 337810 + }, + { + "epoch": 0.75, + "learning_rate": 1.2341334645757366e-05, + "loss": 0.105, + "step": 337820 + }, + { + "epoch": 0.75, + "learning_rate": 1.2340216102548042e-05, + "loss": 0.1019, + "step": 337830 + }, + { + "epoch": 0.75, + "learning_rate": 1.2339097559338719e-05, + "loss": 0.1056, + "step": 337840 + }, + { + "epoch": 0.75, + "learning_rate": 1.2337979016129393e-05, + "loss": 0.1033, + "step": 337850 + }, + { + "epoch": 0.75, + "learning_rate": 1.233686047292007e-05, + "loss": 0.1037, + "step": 337860 + }, + { + "epoch": 0.75, + "learning_rate": 1.2335741929710746e-05, + "loss": 0.1006, + "step": 337870 + }, + { + "epoch": 0.75, + "learning_rate": 1.233462338650142e-05, + "loss": 0.1068, + "step": 337880 + }, + { + "epoch": 0.75, + "learning_rate": 1.2333504843292096e-05, + "loss": 0.1046, + "step": 337890 + }, + { + "epoch": 0.75, + "learning_rate": 1.2332386300082773e-05, + "loss": 0.1071, + "step": 337900 + }, + { + "epoch": 0.75, + "learning_rate": 1.2331267756873449e-05, + "loss": 0.1068, + "step": 337910 + }, + { + "epoch": 0.75, + "learning_rate": 1.2330149213664125e-05, + "loss": 0.1042, + "step": 337920 + }, + { + "epoch": 0.75, + "learning_rate": 1.23290306704548e-05, + "loss": 0.1067, + "step": 337930 + }, + { + "epoch": 0.75, + "learning_rate": 1.2327912127245476e-05, + "loss": 0.1056, + "step": 337940 + }, + { + "epoch": 0.75, + "learning_rate": 1.2326793584036152e-05, + "loss": 0.1036, + "step": 337950 + }, + { + "epoch": 0.75, + "learning_rate": 1.2325675040826827e-05, + "loss": 0.1039, + "step": 337960 + }, + { + "epoch": 0.75, + "learning_rate": 1.2324556497617505e-05, + "loss": 0.105, + "step": 337970 + }, + { + "epoch": 0.75, + "learning_rate": 1.2323437954408179e-05, + "loss": 0.1018, + "step": 337980 + }, + { + "epoch": 0.75, + "learning_rate": 1.2322319411198855e-05, + "loss": 0.1032, + "step": 337990 + }, + { + "epoch": 0.75, + "learning_rate": 1.2321200867989532e-05, + "loss": 0.1059, + "step": 338000 + }, + { + "epoch": 0.75, + "learning_rate": 1.2320082324780206e-05, + "loss": 0.1006, + "step": 338010 + }, + { + "epoch": 0.75, + "learning_rate": 1.2318963781570882e-05, + "loss": 0.1027, + "step": 338020 + }, + { + "epoch": 0.75, + "learning_rate": 1.2317845238361559e-05, + "loss": 0.1066, + "step": 338030 + }, + { + "epoch": 0.75, + "learning_rate": 1.2316726695152233e-05, + "loss": 0.1023, + "step": 338040 + }, + { + "epoch": 0.75, + "learning_rate": 1.2315608151942911e-05, + "loss": 0.1075, + "step": 338050 + }, + { + "epoch": 0.75, + "learning_rate": 1.2314489608733586e-05, + "loss": 0.1021, + "step": 338060 + }, + { + "epoch": 0.75, + "learning_rate": 1.2313371065524262e-05, + "loss": 0.1026, + "step": 338070 + }, + { + "epoch": 0.75, + "learning_rate": 1.2312252522314938e-05, + "loss": 0.1054, + "step": 338080 + }, + { + "epoch": 0.75, + "learning_rate": 1.2311133979105613e-05, + "loss": 0.103, + "step": 338090 + }, + { + "epoch": 0.75, + "learning_rate": 1.2310015435896289e-05, + "loss": 0.1035, + "step": 338100 + }, + { + "epoch": 0.75, + "learning_rate": 1.2308896892686965e-05, + "loss": 0.1035, + "step": 338110 + }, + { + "epoch": 0.75, + "learning_rate": 1.230777834947764e-05, + "loss": 0.1049, + "step": 338120 + }, + { + "epoch": 0.75, + "learning_rate": 1.2306659806268318e-05, + "loss": 0.1047, + "step": 338130 + }, + { + "epoch": 0.75, + "learning_rate": 1.2305541263058992e-05, + "loss": 0.1012, + "step": 338140 + }, + { + "epoch": 0.75, + "learning_rate": 1.2304422719849668e-05, + "loss": 0.1031, + "step": 338150 + }, + { + "epoch": 0.75, + "learning_rate": 1.2303304176640345e-05, + "loss": 0.1029, + "step": 338160 + }, + { + "epoch": 0.75, + "learning_rate": 1.2302185633431019e-05, + "loss": 0.1055, + "step": 338170 + }, + { + "epoch": 0.75, + "learning_rate": 1.2301067090221697e-05, + "loss": 0.1028, + "step": 338180 + }, + { + "epoch": 0.75, + "learning_rate": 1.2299948547012372e-05, + "loss": 0.099, + "step": 338190 + }, + { + "epoch": 0.75, + "learning_rate": 1.2298830003803046e-05, + "loss": 0.0957, + "step": 338200 + }, + { + "epoch": 0.75, + "learning_rate": 1.2297711460593724e-05, + "loss": 0.1065, + "step": 338210 + }, + { + "epoch": 0.75, + "learning_rate": 1.2296592917384399e-05, + "loss": 0.103, + "step": 338220 + }, + { + "epoch": 0.75, + "learning_rate": 1.2295474374175075e-05, + "loss": 0.1028, + "step": 338230 + }, + { + "epoch": 0.75, + "learning_rate": 1.2294355830965751e-05, + "loss": 0.1008, + "step": 338240 + }, + { + "epoch": 0.76, + "learning_rate": 1.2293237287756426e-05, + "loss": 0.1017, + "step": 338250 + }, + { + "epoch": 0.76, + "learning_rate": 1.2292118744547103e-05, + "loss": 0.1076, + "step": 338260 + }, + { + "epoch": 0.76, + "learning_rate": 1.2291000201337778e-05, + "loss": 0.102, + "step": 338270 + }, + { + "epoch": 0.76, + "learning_rate": 1.2289881658128454e-05, + "loss": 0.1061, + "step": 338280 + }, + { + "epoch": 0.76, + "learning_rate": 1.228876311491913e-05, + "loss": 0.1029, + "step": 338290 + }, + { + "epoch": 0.76, + "learning_rate": 1.2287644571709805e-05, + "loss": 0.103, + "step": 338300 + }, + { + "epoch": 0.76, + "learning_rate": 1.2286526028500483e-05, + "loss": 0.1018, + "step": 338310 + }, + { + "epoch": 0.76, + "learning_rate": 1.2285407485291157e-05, + "loss": 0.1049, + "step": 338320 + }, + { + "epoch": 0.76, + "learning_rate": 1.2284288942081832e-05, + "loss": 0.1146, + "step": 338330 + }, + { + "epoch": 0.76, + "learning_rate": 1.228317039887251e-05, + "loss": 0.0993, + "step": 338340 + }, + { + "epoch": 0.76, + "learning_rate": 1.2282051855663185e-05, + "loss": 0.1056, + "step": 338350 + }, + { + "epoch": 0.76, + "learning_rate": 1.228093331245386e-05, + "loss": 0.1003, + "step": 338360 + }, + { + "epoch": 0.76, + "learning_rate": 1.2279814769244537e-05, + "loss": 0.1084, + "step": 338370 + }, + { + "epoch": 0.76, + "learning_rate": 1.2278696226035212e-05, + "loss": 0.1058, + "step": 338380 + }, + { + "epoch": 0.76, + "learning_rate": 1.227757768282589e-05, + "loss": 0.1016, + "step": 338390 + }, + { + "epoch": 0.76, + "learning_rate": 1.2276459139616564e-05, + "loss": 0.1024, + "step": 338400 + }, + { + "epoch": 0.76, + "learning_rate": 1.2275340596407239e-05, + "loss": 0.107, + "step": 338410 + }, + { + "epoch": 0.76, + "learning_rate": 1.2274222053197916e-05, + "loss": 0.1065, + "step": 338420 + }, + { + "epoch": 0.76, + "learning_rate": 1.2273103509988591e-05, + "loss": 0.1073, + "step": 338430 + }, + { + "epoch": 0.76, + "learning_rate": 1.2271984966779267e-05, + "loss": 0.1083, + "step": 338440 + }, + { + "epoch": 0.76, + "learning_rate": 1.2270866423569943e-05, + "loss": 0.1012, + "step": 338450 + }, + { + "epoch": 0.76, + "learning_rate": 1.2269747880360618e-05, + "loss": 0.104, + "step": 338460 + }, + { + "epoch": 0.76, + "learning_rate": 1.2268629337151296e-05, + "loss": 0.1042, + "step": 338470 + }, + { + "epoch": 0.76, + "learning_rate": 1.226751079394197e-05, + "loss": 0.1073, + "step": 338480 + }, + { + "epoch": 0.76, + "learning_rate": 1.2266392250732647e-05, + "loss": 0.1034, + "step": 338490 + }, + { + "epoch": 0.76, + "learning_rate": 1.2265273707523323e-05, + "loss": 0.1043, + "step": 338500 + }, + { + "epoch": 0.76, + "learning_rate": 1.2264155164313997e-05, + "loss": 0.1107, + "step": 338510 + }, + { + "epoch": 0.76, + "learning_rate": 1.2263036621104674e-05, + "loss": 0.1068, + "step": 338520 + }, + { + "epoch": 0.76, + "learning_rate": 1.226191807789535e-05, + "loss": 0.1014, + "step": 338530 + }, + { + "epoch": 0.76, + "learning_rate": 1.2260799534686024e-05, + "loss": 0.1045, + "step": 338540 + }, + { + "epoch": 0.76, + "learning_rate": 1.2259680991476702e-05, + "loss": 0.1061, + "step": 338550 + }, + { + "epoch": 0.76, + "learning_rate": 1.225867430258831e-05, + "loss": 0.1063, + "step": 338560 + }, + { + "epoch": 0.76, + "learning_rate": 1.2257555759378986e-05, + "loss": 0.1034, + "step": 338570 + }, + { + "epoch": 0.76, + "learning_rate": 1.2256437216169662e-05, + "loss": 0.1047, + "step": 338580 + }, + { + "epoch": 0.76, + "learning_rate": 1.2255318672960336e-05, + "loss": 0.1034, + "step": 338590 + }, + { + "epoch": 0.76, + "learning_rate": 1.2254200129751013e-05, + "loss": 0.1072, + "step": 338600 + }, + { + "epoch": 0.76, + "learning_rate": 1.2253081586541689e-05, + "loss": 0.1037, + "step": 338610 + }, + { + "epoch": 0.76, + "learning_rate": 1.2251963043332365e-05, + "loss": 0.1039, + "step": 338620 + }, + { + "epoch": 0.76, + "learning_rate": 1.225084450012304e-05, + "loss": 0.1056, + "step": 338630 + }, + { + "epoch": 0.76, + "learning_rate": 1.2249725956913716e-05, + "loss": 0.1033, + "step": 338640 + }, + { + "epoch": 0.76, + "learning_rate": 1.2248607413704392e-05, + "loss": 0.1027, + "step": 338650 + }, + { + "epoch": 0.76, + "learning_rate": 1.2247488870495068e-05, + "loss": 0.1103, + "step": 338660 + }, + { + "epoch": 0.76, + "learning_rate": 1.2246370327285743e-05, + "loss": 0.1114, + "step": 338670 + }, + { + "epoch": 0.76, + "learning_rate": 1.224525178407642e-05, + "loss": 0.1068, + "step": 338680 + }, + { + "epoch": 0.76, + "learning_rate": 1.2244133240867095e-05, + "loss": 0.1027, + "step": 338690 + }, + { + "epoch": 0.76, + "learning_rate": 1.2243014697657772e-05, + "loss": 0.1056, + "step": 338700 + }, + { + "epoch": 0.76, + "learning_rate": 1.2241896154448446e-05, + "loss": 0.1033, + "step": 338710 + }, + { + "epoch": 0.76, + "learning_rate": 1.2240777611239122e-05, + "loss": 0.104, + "step": 338720 + }, + { + "epoch": 0.76, + "learning_rate": 1.2239659068029799e-05, + "loss": 0.1024, + "step": 338730 + }, + { + "epoch": 0.76, + "learning_rate": 1.2238540524820475e-05, + "loss": 0.1024, + "step": 338740 + }, + { + "epoch": 0.76, + "learning_rate": 1.223742198161115e-05, + "loss": 0.1015, + "step": 338750 + }, + { + "epoch": 0.76, + "learning_rate": 1.2236303438401826e-05, + "loss": 0.1027, + "step": 338760 + }, + { + "epoch": 0.76, + "learning_rate": 1.2235184895192502e-05, + "loss": 0.103, + "step": 338770 + }, + { + "epoch": 0.76, + "learning_rate": 1.2234066351983178e-05, + "loss": 0.1027, + "step": 338780 + }, + { + "epoch": 0.76, + "learning_rate": 1.2232947808773854e-05, + "loss": 0.1039, + "step": 338790 + }, + { + "epoch": 0.76, + "learning_rate": 1.2231829265564529e-05, + "loss": 0.101, + "step": 338800 + }, + { + "epoch": 0.76, + "learning_rate": 1.2230710722355205e-05, + "loss": 0.1061, + "step": 338810 + }, + { + "epoch": 0.76, + "learning_rate": 1.2229592179145881e-05, + "loss": 0.105, + "step": 338820 + }, + { + "epoch": 0.76, + "learning_rate": 1.2228473635936556e-05, + "loss": 0.1068, + "step": 338830 + }, + { + "epoch": 0.76, + "learning_rate": 1.2227355092727232e-05, + "loss": 0.1051, + "step": 338840 + }, + { + "epoch": 0.76, + "learning_rate": 1.2226236549517908e-05, + "loss": 0.0999, + "step": 338850 + }, + { + "epoch": 0.76, + "learning_rate": 1.2225118006308585e-05, + "loss": 0.1034, + "step": 338860 + }, + { + "epoch": 0.76, + "learning_rate": 1.2223999463099261e-05, + "loss": 0.1025, + "step": 338870 + }, + { + "epoch": 0.76, + "learning_rate": 1.2222880919889935e-05, + "loss": 0.1053, + "step": 338880 + }, + { + "epoch": 0.76, + "learning_rate": 1.2221762376680612e-05, + "loss": 0.1089, + "step": 338890 + }, + { + "epoch": 0.76, + "learning_rate": 1.2220643833471288e-05, + "loss": 0.1045, + "step": 338900 + }, + { + "epoch": 0.76, + "learning_rate": 1.2219525290261962e-05, + "loss": 0.1003, + "step": 338910 + }, + { + "epoch": 0.76, + "learning_rate": 1.2218406747052639e-05, + "loss": 0.1058, + "step": 338920 + }, + { + "epoch": 0.76, + "learning_rate": 1.2217288203843315e-05, + "loss": 0.1079, + "step": 338930 + }, + { + "epoch": 0.76, + "learning_rate": 1.2216169660633991e-05, + "loss": 0.1083, + "step": 338940 + }, + { + "epoch": 0.76, + "learning_rate": 1.2215051117424667e-05, + "loss": 0.101, + "step": 338950 + }, + { + "epoch": 0.76, + "learning_rate": 1.2213932574215342e-05, + "loss": 0.1055, + "step": 338960 + }, + { + "epoch": 0.76, + "learning_rate": 1.2212814031006018e-05, + "loss": 0.1046, + "step": 338970 + }, + { + "epoch": 0.76, + "learning_rate": 1.2211695487796694e-05, + "loss": 0.1031, + "step": 338980 + }, + { + "epoch": 0.76, + "learning_rate": 1.2210576944587369e-05, + "loss": 0.1055, + "step": 338990 + }, + { + "epoch": 0.76, + "learning_rate": 1.2209458401378047e-05, + "loss": 0.1063, + "step": 339000 + }, + { + "epoch": 0.76, + "learning_rate": 1.2208339858168721e-05, + "loss": 0.1064, + "step": 339010 + }, + { + "epoch": 0.76, + "learning_rate": 1.2207221314959398e-05, + "loss": 0.1016, + "step": 339020 + }, + { + "epoch": 0.76, + "learning_rate": 1.2206102771750074e-05, + "loss": 0.1075, + "step": 339030 + }, + { + "epoch": 0.76, + "learning_rate": 1.2204984228540748e-05, + "loss": 0.1019, + "step": 339040 + }, + { + "epoch": 0.76, + "learning_rate": 1.2203865685331425e-05, + "loss": 0.1023, + "step": 339050 + }, + { + "epoch": 0.76, + "learning_rate": 1.22027471421221e-05, + "loss": 0.103, + "step": 339060 + }, + { + "epoch": 0.76, + "learning_rate": 1.2201628598912775e-05, + "loss": 0.1054, + "step": 339070 + }, + { + "epoch": 0.76, + "learning_rate": 1.2200510055703453e-05, + "loss": 0.1044, + "step": 339080 + }, + { + "epoch": 0.76, + "learning_rate": 1.2199391512494128e-05, + "loss": 0.1067, + "step": 339090 + }, + { + "epoch": 0.76, + "learning_rate": 1.2198272969284804e-05, + "loss": 0.108, + "step": 339100 + }, + { + "epoch": 0.76, + "learning_rate": 1.219715442607548e-05, + "loss": 0.1065, + "step": 339110 + }, + { + "epoch": 0.76, + "learning_rate": 1.2196035882866155e-05, + "loss": 0.1015, + "step": 339120 + }, + { + "epoch": 0.76, + "learning_rate": 1.2194917339656833e-05, + "loss": 0.1037, + "step": 339130 + }, + { + "epoch": 0.76, + "learning_rate": 1.2193798796447507e-05, + "loss": 0.1048, + "step": 339140 + }, + { + "epoch": 0.76, + "learning_rate": 1.2192680253238182e-05, + "loss": 0.1012, + "step": 339150 + }, + { + "epoch": 0.76, + "learning_rate": 1.219156171002886e-05, + "loss": 0.1001, + "step": 339160 + }, + { + "epoch": 0.76, + "learning_rate": 1.2190443166819534e-05, + "loss": 0.1054, + "step": 339170 + }, + { + "epoch": 0.76, + "learning_rate": 1.218932462361021e-05, + "loss": 0.1047, + "step": 339180 + }, + { + "epoch": 0.76, + "learning_rate": 1.2188206080400887e-05, + "loss": 0.1004, + "step": 339190 + }, + { + "epoch": 0.76, + "learning_rate": 1.2187087537191561e-05, + "loss": 0.1081, + "step": 339200 + }, + { + "epoch": 0.76, + "learning_rate": 1.218596899398224e-05, + "loss": 0.0999, + "step": 339210 + }, + { + "epoch": 0.76, + "learning_rate": 1.2184850450772914e-05, + "loss": 0.1035, + "step": 339220 + }, + { + "epoch": 0.76, + "learning_rate": 1.2183731907563588e-05, + "loss": 0.1037, + "step": 339230 + }, + { + "epoch": 0.76, + "learning_rate": 1.2182613364354266e-05, + "loss": 0.0991, + "step": 339240 + }, + { + "epoch": 0.76, + "learning_rate": 1.218149482114494e-05, + "loss": 0.1035, + "step": 339250 + }, + { + "epoch": 0.76, + "learning_rate": 1.2180376277935617e-05, + "loss": 0.1009, + "step": 339260 + }, + { + "epoch": 0.76, + "learning_rate": 1.2179257734726293e-05, + "loss": 0.1051, + "step": 339270 + }, + { + "epoch": 0.76, + "learning_rate": 1.2178139191516968e-05, + "loss": 0.1015, + "step": 339280 + }, + { + "epoch": 0.76, + "learning_rate": 1.2177020648307646e-05, + "loss": 0.1037, + "step": 339290 + }, + { + "epoch": 0.76, + "learning_rate": 1.217590210509832e-05, + "loss": 0.1092, + "step": 339300 + }, + { + "epoch": 0.76, + "learning_rate": 1.2174783561888997e-05, + "loss": 0.1035, + "step": 339310 + }, + { + "epoch": 0.76, + "learning_rate": 1.2173665018679673e-05, + "loss": 0.1024, + "step": 339320 + }, + { + "epoch": 0.76, + "learning_rate": 1.2172546475470347e-05, + "loss": 0.1031, + "step": 339330 + }, + { + "epoch": 0.76, + "learning_rate": 1.2171427932261025e-05, + "loss": 0.1044, + "step": 339340 + }, + { + "epoch": 0.76, + "learning_rate": 1.21703093890517e-05, + "loss": 0.1018, + "step": 339350 + }, + { + "epoch": 0.76, + "learning_rate": 1.2169190845842374e-05, + "loss": 0.1027, + "step": 339360 + }, + { + "epoch": 0.76, + "learning_rate": 1.2168072302633052e-05, + "loss": 0.1042, + "step": 339370 + }, + { + "epoch": 0.76, + "learning_rate": 1.2166953759423727e-05, + "loss": 0.1052, + "step": 339380 + }, + { + "epoch": 0.76, + "learning_rate": 1.2165835216214403e-05, + "loss": 0.1045, + "step": 339390 + }, + { + "epoch": 0.76, + "learning_rate": 1.216471667300508e-05, + "loss": 0.1076, + "step": 339400 + }, + { + "epoch": 0.76, + "learning_rate": 1.2163598129795754e-05, + "loss": 0.1015, + "step": 339410 + }, + { + "epoch": 0.76, + "learning_rate": 1.2162479586586432e-05, + "loss": 0.1101, + "step": 339420 + }, + { + "epoch": 0.76, + "learning_rate": 1.2161361043377106e-05, + "loss": 0.1036, + "step": 339430 + }, + { + "epoch": 0.76, + "learning_rate": 1.2160242500167782e-05, + "loss": 0.1042, + "step": 339440 + }, + { + "epoch": 0.76, + "learning_rate": 1.2159123956958459e-05, + "loss": 0.1046, + "step": 339450 + }, + { + "epoch": 0.76, + "learning_rate": 1.2158005413749133e-05, + "loss": 0.1038, + "step": 339460 + }, + { + "epoch": 0.76, + "learning_rate": 1.215688687053981e-05, + "loss": 0.1015, + "step": 339470 + }, + { + "epoch": 0.76, + "learning_rate": 1.2155768327330486e-05, + "loss": 0.1054, + "step": 339480 + }, + { + "epoch": 0.76, + "learning_rate": 1.215464978412116e-05, + "loss": 0.1035, + "step": 339490 + }, + { + "epoch": 0.76, + "learning_rate": 1.2153531240911838e-05, + "loss": 0.1055, + "step": 339500 + }, + { + "epoch": 0.76, + "learning_rate": 1.2152412697702513e-05, + "loss": 0.1092, + "step": 339510 + }, + { + "epoch": 0.76, + "learning_rate": 1.2151294154493189e-05, + "loss": 0.1059, + "step": 339520 + }, + { + "epoch": 0.76, + "learning_rate": 1.2150175611283865e-05, + "loss": 0.1051, + "step": 339530 + }, + { + "epoch": 0.76, + "learning_rate": 1.214905706807454e-05, + "loss": 0.101, + "step": 339540 + }, + { + "epoch": 0.76, + "learning_rate": 1.2147938524865216e-05, + "loss": 0.1066, + "step": 339550 + }, + { + "epoch": 0.76, + "learning_rate": 1.2146819981655892e-05, + "loss": 0.1013, + "step": 339560 + }, + { + "epoch": 0.76, + "learning_rate": 1.2145701438446567e-05, + "loss": 0.1064, + "step": 339570 + }, + { + "epoch": 0.76, + "learning_rate": 1.2144582895237245e-05, + "loss": 0.1059, + "step": 339580 + }, + { + "epoch": 0.76, + "learning_rate": 1.214346435202792e-05, + "loss": 0.1031, + "step": 339590 + }, + { + "epoch": 0.76, + "learning_rate": 1.2142345808818595e-05, + "loss": 0.103, + "step": 339600 + }, + { + "epoch": 0.76, + "learning_rate": 1.2141227265609272e-05, + "loss": 0.1074, + "step": 339610 + }, + { + "epoch": 0.76, + "learning_rate": 1.2140108722399946e-05, + "loss": 0.1051, + "step": 339620 + }, + { + "epoch": 0.76, + "learning_rate": 1.2138990179190622e-05, + "loss": 0.1025, + "step": 339630 + }, + { + "epoch": 0.76, + "learning_rate": 1.2137871635981299e-05, + "loss": 0.1039, + "step": 339640 + }, + { + "epoch": 0.76, + "learning_rate": 1.2136753092771975e-05, + "loss": 0.1009, + "step": 339650 + }, + { + "epoch": 0.76, + "learning_rate": 1.2135634549562651e-05, + "loss": 0.1107, + "step": 339660 + }, + { + "epoch": 0.76, + "learning_rate": 1.2134516006353326e-05, + "loss": 0.1039, + "step": 339670 + }, + { + "epoch": 0.76, + "learning_rate": 1.2133397463144002e-05, + "loss": 0.103, + "step": 339680 + }, + { + "epoch": 0.76, + "learning_rate": 1.2132278919934678e-05, + "loss": 0.1068, + "step": 339690 + }, + { + "epoch": 0.76, + "learning_rate": 1.2131160376725353e-05, + "loss": 0.1013, + "step": 339700 + }, + { + "epoch": 0.76, + "learning_rate": 1.2130041833516029e-05, + "loss": 0.1006, + "step": 339710 + }, + { + "epoch": 0.76, + "learning_rate": 1.2128923290306705e-05, + "loss": 0.1031, + "step": 339720 + }, + { + "epoch": 0.76, + "learning_rate": 1.2127804747097381e-05, + "loss": 0.1006, + "step": 339730 + }, + { + "epoch": 0.76, + "learning_rate": 1.2126686203888058e-05, + "loss": 0.102, + "step": 339740 + }, + { + "epoch": 0.76, + "learning_rate": 1.2125567660678732e-05, + "loss": 0.1041, + "step": 339750 + }, + { + "epoch": 0.76, + "learning_rate": 1.2124449117469408e-05, + "loss": 0.1059, + "step": 339760 + }, + { + "epoch": 0.76, + "learning_rate": 1.2123330574260085e-05, + "loss": 0.1074, + "step": 339770 + }, + { + "epoch": 0.76, + "learning_rate": 1.2122212031050761e-05, + "loss": 0.1021, + "step": 339780 + }, + { + "epoch": 0.76, + "learning_rate": 1.2121093487841435e-05, + "loss": 0.103, + "step": 339790 + }, + { + "epoch": 0.76, + "learning_rate": 1.2119974944632112e-05, + "loss": 0.1077, + "step": 339800 + }, + { + "epoch": 0.76, + "learning_rate": 1.2118856401422788e-05, + "loss": 0.1014, + "step": 339810 + }, + { + "epoch": 0.76, + "learning_rate": 1.2117737858213464e-05, + "loss": 0.102, + "step": 339820 + }, + { + "epoch": 0.76, + "learning_rate": 1.2116619315004139e-05, + "loss": 0.1009, + "step": 339830 + }, + { + "epoch": 0.76, + "learning_rate": 1.2115500771794815e-05, + "loss": 0.1014, + "step": 339840 + }, + { + "epoch": 0.76, + "learning_rate": 1.2114382228585491e-05, + "loss": 0.1004, + "step": 339850 + }, + { + "epoch": 0.76, + "learning_rate": 1.2113263685376167e-05, + "loss": 0.1055, + "step": 339860 + }, + { + "epoch": 0.76, + "learning_rate": 1.2112145142166842e-05, + "loss": 0.1055, + "step": 339870 + }, + { + "epoch": 0.76, + "learning_rate": 1.2111026598957518e-05, + "loss": 0.1006, + "step": 339880 + }, + { + "epoch": 0.76, + "learning_rate": 1.2109908055748194e-05, + "loss": 0.1011, + "step": 339890 + }, + { + "epoch": 0.76, + "learning_rate": 1.210878951253887e-05, + "loss": 0.1042, + "step": 339900 + }, + { + "epoch": 0.76, + "learning_rate": 1.2107670969329545e-05, + "loss": 0.1076, + "step": 339910 + }, + { + "epoch": 0.76, + "learning_rate": 1.2106552426120221e-05, + "loss": 0.1051, + "step": 339920 + }, + { + "epoch": 0.76, + "learning_rate": 1.2105433882910898e-05, + "loss": 0.1038, + "step": 339930 + }, + { + "epoch": 0.76, + "learning_rate": 1.2104315339701574e-05, + "loss": 0.0985, + "step": 339940 + }, + { + "epoch": 0.76, + "learning_rate": 1.2103196796492248e-05, + "loss": 0.1077, + "step": 339950 + }, + { + "epoch": 0.76, + "learning_rate": 1.2102078253282925e-05, + "loss": 0.1057, + "step": 339960 + }, + { + "epoch": 0.76, + "learning_rate": 1.21009597100736e-05, + "loss": 0.1033, + "step": 339970 + }, + { + "epoch": 0.76, + "learning_rate": 1.2099841166864277e-05, + "loss": 0.103, + "step": 339980 + }, + { + "epoch": 0.76, + "learning_rate": 1.2098722623654953e-05, + "loss": 0.1047, + "step": 339990 + }, + { + "epoch": 0.76, + "learning_rate": 1.2097604080445628e-05, + "loss": 0.1047, + "step": 340000 + }, + { + "epoch": 0.76, + "learning_rate": 1.2096485537236304e-05, + "loss": 0.1009, + "step": 340010 + }, + { + "epoch": 0.76, + "learning_rate": 1.209536699402698e-05, + "loss": 0.1024, + "step": 340020 + }, + { + "epoch": 0.76, + "learning_rate": 1.2094248450817655e-05, + "loss": 0.1048, + "step": 340030 + }, + { + "epoch": 0.76, + "learning_rate": 1.2093129907608331e-05, + "loss": 0.1073, + "step": 340040 + }, + { + "epoch": 0.76, + "learning_rate": 1.2092011364399007e-05, + "loss": 0.107, + "step": 340050 + }, + { + "epoch": 0.76, + "learning_rate": 1.2090892821189684e-05, + "loss": 0.1002, + "step": 340060 + }, + { + "epoch": 0.76, + "learning_rate": 1.208977427798036e-05, + "loss": 0.0961, + "step": 340070 + }, + { + "epoch": 0.76, + "learning_rate": 1.2088655734771034e-05, + "loss": 0.1065, + "step": 340080 + }, + { + "epoch": 0.76, + "learning_rate": 1.208753719156171e-05, + "loss": 0.1041, + "step": 340090 + }, + { + "epoch": 0.76, + "learning_rate": 1.2086418648352387e-05, + "loss": 0.1047, + "step": 340100 + }, + { + "epoch": 0.76, + "learning_rate": 1.2085300105143061e-05, + "loss": 0.1055, + "step": 340110 + }, + { + "epoch": 0.76, + "learning_rate": 1.208418156193374e-05, + "loss": 0.1047, + "step": 340120 + }, + { + "epoch": 0.76, + "learning_rate": 1.2083063018724414e-05, + "loss": 0.1014, + "step": 340130 + }, + { + "epoch": 0.76, + "learning_rate": 1.208194447551509e-05, + "loss": 0.1014, + "step": 340140 + }, + { + "epoch": 0.76, + "learning_rate": 1.2080825932305766e-05, + "loss": 0.1007, + "step": 340150 + }, + { + "epoch": 0.76, + "learning_rate": 1.207970738909644e-05, + "loss": 0.1012, + "step": 340160 + }, + { + "epoch": 0.76, + "learning_rate": 1.2078588845887117e-05, + "loss": 0.1018, + "step": 340170 + }, + { + "epoch": 0.76, + "learning_rate": 1.2077470302677793e-05, + "loss": 0.0987, + "step": 340180 + }, + { + "epoch": 0.76, + "learning_rate": 1.2076351759468468e-05, + "loss": 0.1072, + "step": 340190 + }, + { + "epoch": 0.76, + "learning_rate": 1.2075233216259146e-05, + "loss": 0.104, + "step": 340200 + }, + { + "epoch": 0.76, + "learning_rate": 1.207411467304982e-05, + "loss": 0.1055, + "step": 340210 + }, + { + "epoch": 0.76, + "learning_rate": 1.2072996129840497e-05, + "loss": 0.1019, + "step": 340220 + }, + { + "epoch": 0.76, + "learning_rate": 1.2071877586631173e-05, + "loss": 0.1049, + "step": 340230 + }, + { + "epoch": 0.76, + "learning_rate": 1.2070759043421847e-05, + "loss": 0.1036, + "step": 340240 + }, + { + "epoch": 0.76, + "learning_rate": 1.2069640500212524e-05, + "loss": 0.103, + "step": 340250 + }, + { + "epoch": 0.76, + "learning_rate": 1.20685219570032e-05, + "loss": 0.1031, + "step": 340260 + }, + { + "epoch": 0.76, + "learning_rate": 1.2067403413793874e-05, + "loss": 0.1047, + "step": 340270 + }, + { + "epoch": 0.76, + "learning_rate": 1.2066284870584552e-05, + "loss": 0.1018, + "step": 340280 + }, + { + "epoch": 0.76, + "learning_rate": 1.2065166327375227e-05, + "loss": 0.1004, + "step": 340290 + }, + { + "epoch": 0.76, + "learning_rate": 1.2064047784165903e-05, + "loss": 0.1055, + "step": 340300 + }, + { + "epoch": 0.76, + "learning_rate": 1.206292924095658e-05, + "loss": 0.1065, + "step": 340310 + }, + { + "epoch": 0.76, + "learning_rate": 1.2061810697747254e-05, + "loss": 0.1063, + "step": 340320 + }, + { + "epoch": 0.76, + "learning_rate": 1.2060692154537932e-05, + "loss": 0.1039, + "step": 340330 + }, + { + "epoch": 0.76, + "learning_rate": 1.2059573611328606e-05, + "loss": 0.1016, + "step": 340340 + }, + { + "epoch": 0.76, + "learning_rate": 1.205845506811928e-05, + "loss": 0.1059, + "step": 340350 + }, + { + "epoch": 0.76, + "learning_rate": 1.2057336524909959e-05, + "loss": 0.1032, + "step": 340360 + }, + { + "epoch": 0.76, + "learning_rate": 1.2056217981700633e-05, + "loss": 0.106, + "step": 340370 + }, + { + "epoch": 0.76, + "learning_rate": 1.205509943849131e-05, + "loss": 0.1013, + "step": 340380 + }, + { + "epoch": 0.76, + "learning_rate": 1.2053980895281986e-05, + "loss": 0.1061, + "step": 340390 + }, + { + "epoch": 0.76, + "learning_rate": 1.205286235207266e-05, + "loss": 0.1073, + "step": 340400 + }, + { + "epoch": 0.76, + "learning_rate": 1.2051743808863338e-05, + "loss": 0.1008, + "step": 340410 + }, + { + "epoch": 0.76, + "learning_rate": 1.2050625265654013e-05, + "loss": 0.1098, + "step": 340420 + }, + { + "epoch": 0.76, + "learning_rate": 1.2049506722444687e-05, + "loss": 0.1027, + "step": 340430 + }, + { + "epoch": 0.76, + "learning_rate": 1.2048388179235365e-05, + "loss": 0.1036, + "step": 340440 + }, + { + "epoch": 0.76, + "learning_rate": 1.204726963602604e-05, + "loss": 0.1018, + "step": 340450 + }, + { + "epoch": 0.76, + "learning_rate": 1.2046151092816716e-05, + "loss": 0.1052, + "step": 340460 + }, + { + "epoch": 0.76, + "learning_rate": 1.2045032549607392e-05, + "loss": 0.1012, + "step": 340470 + }, + { + "epoch": 0.76, + "learning_rate": 1.2043914006398067e-05, + "loss": 0.1096, + "step": 340480 + }, + { + "epoch": 0.76, + "learning_rate": 1.2042795463188745e-05, + "loss": 0.0987, + "step": 340490 + }, + { + "epoch": 0.76, + "learning_rate": 1.204167691997942e-05, + "loss": 0.1003, + "step": 340500 + }, + { + "epoch": 0.76, + "learning_rate": 1.2040558376770095e-05, + "loss": 0.1034, + "step": 340510 + }, + { + "epoch": 0.76, + "learning_rate": 1.2039439833560772e-05, + "loss": 0.1028, + "step": 340520 + }, + { + "epoch": 0.76, + "learning_rate": 1.2038321290351446e-05, + "loss": 0.0993, + "step": 340530 + }, + { + "epoch": 0.76, + "learning_rate": 1.2037202747142124e-05, + "loss": 0.1014, + "step": 340540 + }, + { + "epoch": 0.76, + "learning_rate": 1.2036084203932799e-05, + "loss": 0.1037, + "step": 340550 + }, + { + "epoch": 0.76, + "learning_rate": 1.2034965660723473e-05, + "loss": 0.1021, + "step": 340560 + }, + { + "epoch": 0.76, + "learning_rate": 1.2033847117514151e-05, + "loss": 0.1043, + "step": 340570 + }, + { + "epoch": 0.76, + "learning_rate": 1.2032728574304826e-05, + "loss": 0.1083, + "step": 340580 + }, + { + "epoch": 0.76, + "learning_rate": 1.2031610031095502e-05, + "loss": 0.1065, + "step": 340590 + }, + { + "epoch": 0.76, + "learning_rate": 1.203060334220711e-05, + "loss": 0.1079, + "step": 340600 + }, + { + "epoch": 0.76, + "learning_rate": 1.2029484798997785e-05, + "loss": 0.1011, + "step": 340610 + }, + { + "epoch": 0.76, + "learning_rate": 1.2028366255788461e-05, + "loss": 0.1064, + "step": 340620 + }, + { + "epoch": 0.76, + "learning_rate": 1.2027247712579138e-05, + "loss": 0.1009, + "step": 340630 + }, + { + "epoch": 0.76, + "learning_rate": 1.2026129169369814e-05, + "loss": 0.1034, + "step": 340640 + }, + { + "epoch": 0.76, + "learning_rate": 1.2025010626160488e-05, + "loss": 0.1044, + "step": 340650 + }, + { + "epoch": 0.76, + "learning_rate": 1.2023892082951165e-05, + "loss": 0.1053, + "step": 340660 + }, + { + "epoch": 0.76, + "learning_rate": 1.2022773539741841e-05, + "loss": 0.1056, + "step": 340670 + }, + { + "epoch": 0.76, + "learning_rate": 1.2021654996532517e-05, + "loss": 0.1036, + "step": 340680 + }, + { + "epoch": 0.76, + "learning_rate": 1.2020536453323192e-05, + "loss": 0.1035, + "step": 340690 + }, + { + "epoch": 0.76, + "learning_rate": 1.2019417910113868e-05, + "loss": 0.1011, + "step": 340700 + }, + { + "epoch": 0.76, + "learning_rate": 1.2018299366904544e-05, + "loss": 0.1041, + "step": 340710 + }, + { + "epoch": 0.76, + "learning_rate": 1.201718082369522e-05, + "loss": 0.1049, + "step": 340720 + }, + { + "epoch": 0.76, + "learning_rate": 1.2016062280485895e-05, + "loss": 0.1063, + "step": 340730 + }, + { + "epoch": 0.76, + "learning_rate": 1.2014943737276571e-05, + "loss": 0.1033, + "step": 340740 + }, + { + "epoch": 0.76, + "learning_rate": 1.2013825194067247e-05, + "loss": 0.1022, + "step": 340750 + }, + { + "epoch": 0.76, + "learning_rate": 1.2012706650857924e-05, + "loss": 0.1061, + "step": 340760 + }, + { + "epoch": 0.76, + "learning_rate": 1.2011588107648598e-05, + "loss": 0.1042, + "step": 340770 + }, + { + "epoch": 0.76, + "learning_rate": 1.2010469564439274e-05, + "loss": 0.1058, + "step": 340780 + }, + { + "epoch": 0.76, + "learning_rate": 1.200935102122995e-05, + "loss": 0.1055, + "step": 340790 + }, + { + "epoch": 0.76, + "learning_rate": 1.2008232478020627e-05, + "loss": 0.1064, + "step": 340800 + }, + { + "epoch": 0.76, + "learning_rate": 1.2007113934811303e-05, + "loss": 0.1033, + "step": 340810 + }, + { + "epoch": 0.76, + "learning_rate": 1.2005995391601978e-05, + "loss": 0.1056, + "step": 340820 + }, + { + "epoch": 0.76, + "learning_rate": 1.2004876848392654e-05, + "loss": 0.1016, + "step": 340830 + }, + { + "epoch": 0.76, + "learning_rate": 1.200375830518333e-05, + "loss": 0.102, + "step": 340840 + }, + { + "epoch": 0.76, + "learning_rate": 1.2002639761974005e-05, + "loss": 0.1014, + "step": 340850 + }, + { + "epoch": 0.76, + "learning_rate": 1.2001521218764681e-05, + "loss": 0.1048, + "step": 340860 + }, + { + "epoch": 0.76, + "learning_rate": 1.2000402675555357e-05, + "loss": 0.107, + "step": 340870 + }, + { + "epoch": 0.76, + "learning_rate": 1.1999284132346033e-05, + "loss": 0.1082, + "step": 340880 + }, + { + "epoch": 0.76, + "learning_rate": 1.199816558913671e-05, + "loss": 0.1011, + "step": 340890 + }, + { + "epoch": 0.76, + "learning_rate": 1.1997047045927384e-05, + "loss": 0.1024, + "step": 340900 + }, + { + "epoch": 0.76, + "learning_rate": 1.199592850271806e-05, + "loss": 0.1022, + "step": 340910 + }, + { + "epoch": 0.76, + "learning_rate": 1.1994809959508737e-05, + "loss": 0.1057, + "step": 340920 + }, + { + "epoch": 0.76, + "learning_rate": 1.1993691416299411e-05, + "loss": 0.106, + "step": 340930 + }, + { + "epoch": 0.76, + "learning_rate": 1.1992572873090089e-05, + "loss": 0.107, + "step": 340940 + }, + { + "epoch": 0.76, + "learning_rate": 1.1991454329880764e-05, + "loss": 0.1023, + "step": 340950 + }, + { + "epoch": 0.76, + "learning_rate": 1.199033578667144e-05, + "loss": 0.1043, + "step": 340960 + }, + { + "epoch": 0.76, + "learning_rate": 1.1989217243462116e-05, + "loss": 0.1031, + "step": 340970 + }, + { + "epoch": 0.76, + "learning_rate": 1.198809870025279e-05, + "loss": 0.1028, + "step": 340980 + }, + { + "epoch": 0.76, + "learning_rate": 1.1986980157043467e-05, + "loss": 0.1018, + "step": 340990 + }, + { + "epoch": 0.76, + "learning_rate": 1.1985861613834143e-05, + "loss": 0.0991, + "step": 341000 + }, + { + "epoch": 0.76, + "learning_rate": 1.1984743070624818e-05, + "loss": 0.0993, + "step": 341010 + }, + { + "epoch": 0.76, + "learning_rate": 1.1983624527415496e-05, + "loss": 0.1094, + "step": 341020 + }, + { + "epoch": 0.76, + "learning_rate": 1.198250598420617e-05, + "loss": 0.103, + "step": 341030 + }, + { + "epoch": 0.76, + "learning_rate": 1.1981387440996846e-05, + "loss": 0.1007, + "step": 341040 + }, + { + "epoch": 0.76, + "learning_rate": 1.1980268897787523e-05, + "loss": 0.102, + "step": 341050 + }, + { + "epoch": 0.76, + "learning_rate": 1.1979150354578197e-05, + "loss": 0.0963, + "step": 341060 + }, + { + "epoch": 0.76, + "learning_rate": 1.1978031811368873e-05, + "loss": 0.1066, + "step": 341070 + }, + { + "epoch": 0.76, + "learning_rate": 1.197691326815955e-05, + "loss": 0.104, + "step": 341080 + }, + { + "epoch": 0.76, + "learning_rate": 1.1975794724950224e-05, + "loss": 0.1008, + "step": 341090 + }, + { + "epoch": 0.76, + "learning_rate": 1.1974676181740902e-05, + "loss": 0.104, + "step": 341100 + }, + { + "epoch": 0.76, + "learning_rate": 1.1973557638531577e-05, + "loss": 0.1025, + "step": 341110 + }, + { + "epoch": 0.76, + "learning_rate": 1.1972439095322253e-05, + "loss": 0.1022, + "step": 341120 + }, + { + "epoch": 0.76, + "learning_rate": 1.1971320552112929e-05, + "loss": 0.1046, + "step": 341130 + }, + { + "epoch": 0.76, + "learning_rate": 1.1970202008903604e-05, + "loss": 0.1077, + "step": 341140 + }, + { + "epoch": 0.76, + "learning_rate": 1.1969083465694282e-05, + "loss": 0.1022, + "step": 341150 + }, + { + "epoch": 0.76, + "learning_rate": 1.1967964922484956e-05, + "loss": 0.0995, + "step": 341160 + }, + { + "epoch": 0.76, + "learning_rate": 1.196684637927563e-05, + "loss": 0.1087, + "step": 341170 + }, + { + "epoch": 0.76, + "learning_rate": 1.1965727836066309e-05, + "loss": 0.108, + "step": 341180 + }, + { + "epoch": 0.76, + "learning_rate": 1.1964609292856983e-05, + "loss": 0.1018, + "step": 341190 + }, + { + "epoch": 0.76, + "learning_rate": 1.196349074964766e-05, + "loss": 0.1017, + "step": 341200 + }, + { + "epoch": 0.76, + "learning_rate": 1.1962372206438336e-05, + "loss": 0.1008, + "step": 341210 + }, + { + "epoch": 0.76, + "learning_rate": 1.196125366322901e-05, + "loss": 0.1049, + "step": 341220 + }, + { + "epoch": 0.76, + "learning_rate": 1.1960135120019688e-05, + "loss": 0.1018, + "step": 341230 + }, + { + "epoch": 0.76, + "learning_rate": 1.1959016576810363e-05, + "loss": 0.1006, + "step": 341240 + }, + { + "epoch": 0.76, + "learning_rate": 1.1957898033601039e-05, + "loss": 0.1063, + "step": 341250 + }, + { + "epoch": 0.76, + "learning_rate": 1.1956779490391715e-05, + "loss": 0.1062, + "step": 341260 + }, + { + "epoch": 0.76, + "learning_rate": 1.195566094718239e-05, + "loss": 0.1054, + "step": 341270 + }, + { + "epoch": 0.76, + "learning_rate": 1.1954542403973067e-05, + "loss": 0.1034, + "step": 341280 + }, + { + "epoch": 0.76, + "learning_rate": 1.1953423860763742e-05, + "loss": 0.1048, + "step": 341290 + }, + { + "epoch": 0.76, + "learning_rate": 1.1952305317554417e-05, + "loss": 0.1034, + "step": 341300 + }, + { + "epoch": 0.76, + "learning_rate": 1.1951186774345094e-05, + "loss": 0.1044, + "step": 341310 + }, + { + "epoch": 0.76, + "learning_rate": 1.1950068231135769e-05, + "loss": 0.1009, + "step": 341320 + }, + { + "epoch": 0.76, + "learning_rate": 1.1948949687926445e-05, + "loss": 0.1045, + "step": 341330 + }, + { + "epoch": 0.76, + "learning_rate": 1.1947831144717121e-05, + "loss": 0.1002, + "step": 341340 + }, + { + "epoch": 0.76, + "learning_rate": 1.1946712601507796e-05, + "loss": 0.1045, + "step": 341350 + }, + { + "epoch": 0.76, + "learning_rate": 1.1945594058298474e-05, + "loss": 0.1065, + "step": 341360 + }, + { + "epoch": 0.76, + "learning_rate": 1.1944475515089148e-05, + "loss": 0.101, + "step": 341370 + }, + { + "epoch": 0.76, + "learning_rate": 1.1943356971879823e-05, + "loss": 0.1027, + "step": 341380 + }, + { + "epoch": 0.76, + "learning_rate": 1.1942238428670501e-05, + "loss": 0.1009, + "step": 341390 + }, + { + "epoch": 0.76, + "learning_rate": 1.1941119885461175e-05, + "loss": 0.1006, + "step": 341400 + }, + { + "epoch": 0.76, + "learning_rate": 1.1940001342251852e-05, + "loss": 0.1097, + "step": 341410 + }, + { + "epoch": 0.76, + "learning_rate": 1.1938882799042528e-05, + "loss": 0.1009, + "step": 341420 + }, + { + "epoch": 0.76, + "learning_rate": 1.1937764255833202e-05, + "loss": 0.1054, + "step": 341430 + }, + { + "epoch": 0.76, + "learning_rate": 1.193664571262388e-05, + "loss": 0.1069, + "step": 341440 + }, + { + "epoch": 0.76, + "learning_rate": 1.1935527169414555e-05, + "loss": 0.1031, + "step": 341450 + }, + { + "epoch": 0.76, + "learning_rate": 1.1934408626205231e-05, + "loss": 0.1045, + "step": 341460 + }, + { + "epoch": 0.76, + "learning_rate": 1.1933290082995907e-05, + "loss": 0.0996, + "step": 341470 + }, + { + "epoch": 0.76, + "learning_rate": 1.1932171539786582e-05, + "loss": 0.1037, + "step": 341480 + }, + { + "epoch": 0.76, + "learning_rate": 1.1931052996577258e-05, + "loss": 0.1043, + "step": 341490 + }, + { + "epoch": 0.76, + "learning_rate": 1.1929934453367934e-05, + "loss": 0.0995, + "step": 341500 + }, + { + "epoch": 0.76, + "learning_rate": 1.1928815910158609e-05, + "loss": 0.1037, + "step": 341510 + }, + { + "epoch": 0.76, + "learning_rate": 1.1927697366949287e-05, + "loss": 0.1035, + "step": 341520 + }, + { + "epoch": 0.76, + "learning_rate": 1.1926578823739961e-05, + "loss": 0.1047, + "step": 341530 + }, + { + "epoch": 0.76, + "learning_rate": 1.1925460280530638e-05, + "loss": 0.0996, + "step": 341540 + }, + { + "epoch": 0.76, + "learning_rate": 1.1924341737321314e-05, + "loss": 0.1052, + "step": 341550 + }, + { + "epoch": 0.76, + "learning_rate": 1.1923223194111988e-05, + "loss": 0.1017, + "step": 341560 + }, + { + "epoch": 0.76, + "learning_rate": 1.1922104650902665e-05, + "loss": 0.1056, + "step": 341570 + }, + { + "epoch": 0.76, + "learning_rate": 1.1920986107693341e-05, + "loss": 0.1035, + "step": 341580 + }, + { + "epoch": 0.76, + "learning_rate": 1.1919867564484017e-05, + "loss": 0.1043, + "step": 341590 + }, + { + "epoch": 0.76, + "learning_rate": 1.1918749021274693e-05, + "loss": 0.1032, + "step": 341600 + }, + { + "epoch": 0.76, + "learning_rate": 1.1917630478065368e-05, + "loss": 0.1043, + "step": 341610 + }, + { + "epoch": 0.76, + "learning_rate": 1.1916511934856044e-05, + "loss": 0.1031, + "step": 341620 + }, + { + "epoch": 0.76, + "learning_rate": 1.191539339164672e-05, + "loss": 0.1074, + "step": 341630 + }, + { + "epoch": 0.76, + "learning_rate": 1.1914274848437395e-05, + "loss": 0.0977, + "step": 341640 + }, + { + "epoch": 0.76, + "learning_rate": 1.1913156305228071e-05, + "loss": 0.1057, + "step": 341650 + }, + { + "epoch": 0.76, + "learning_rate": 1.1912037762018747e-05, + "loss": 0.1068, + "step": 341660 + }, + { + "epoch": 0.76, + "learning_rate": 1.1910919218809424e-05, + "loss": 0.1043, + "step": 341670 + }, + { + "epoch": 0.76, + "learning_rate": 1.19098006756001e-05, + "loss": 0.1012, + "step": 341680 + }, + { + "epoch": 0.76, + "learning_rate": 1.1908682132390774e-05, + "loss": 0.1039, + "step": 341690 + }, + { + "epoch": 0.76, + "learning_rate": 1.190756358918145e-05, + "loss": 0.1065, + "step": 341700 + }, + { + "epoch": 0.76, + "learning_rate": 1.1906445045972127e-05, + "loss": 0.1065, + "step": 341710 + }, + { + "epoch": 0.76, + "learning_rate": 1.1905326502762801e-05, + "loss": 0.1088, + "step": 341720 + }, + { + "epoch": 0.76, + "learning_rate": 1.1904207959553478e-05, + "loss": 0.1045, + "step": 341730 + }, + { + "epoch": 0.76, + "learning_rate": 1.1903089416344154e-05, + "loss": 0.1005, + "step": 341740 + }, + { + "epoch": 0.76, + "learning_rate": 1.190197087313483e-05, + "loss": 0.1061, + "step": 341750 + }, + { + "epoch": 0.76, + "learning_rate": 1.1900852329925506e-05, + "loss": 0.1077, + "step": 341760 + }, + { + "epoch": 0.76, + "learning_rate": 1.1899733786716181e-05, + "loss": 0.1029, + "step": 341770 + }, + { + "epoch": 0.76, + "learning_rate": 1.1898615243506857e-05, + "loss": 0.1053, + "step": 341780 + }, + { + "epoch": 0.76, + "learning_rate": 1.1897496700297533e-05, + "loss": 0.1049, + "step": 341790 + }, + { + "epoch": 0.76, + "learning_rate": 1.189637815708821e-05, + "loss": 0.1036, + "step": 341800 + }, + { + "epoch": 0.76, + "learning_rate": 1.1895259613878884e-05, + "loss": 0.1049, + "step": 341810 + }, + { + "epoch": 0.76, + "learning_rate": 1.189414107066956e-05, + "loss": 0.1029, + "step": 341820 + }, + { + "epoch": 0.76, + "learning_rate": 1.1893022527460237e-05, + "loss": 0.1045, + "step": 341830 + }, + { + "epoch": 0.76, + "learning_rate": 1.1891903984250913e-05, + "loss": 0.1023, + "step": 341840 + }, + { + "epoch": 0.76, + "learning_rate": 1.1890785441041587e-05, + "loss": 0.1059, + "step": 341850 + }, + { + "epoch": 0.76, + "learning_rate": 1.1889666897832264e-05, + "loss": 0.1021, + "step": 341860 + }, + { + "epoch": 0.76, + "learning_rate": 1.188854835462294e-05, + "loss": 0.1044, + "step": 341870 + }, + { + "epoch": 0.76, + "learning_rate": 1.1887429811413616e-05, + "loss": 0.104, + "step": 341880 + }, + { + "epoch": 0.76, + "learning_rate": 1.188631126820429e-05, + "loss": 0.105, + "step": 341890 + }, + { + "epoch": 0.76, + "learning_rate": 1.1885192724994967e-05, + "loss": 0.1029, + "step": 341900 + }, + { + "epoch": 0.76, + "learning_rate": 1.1884074181785643e-05, + "loss": 0.1014, + "step": 341910 + }, + { + "epoch": 0.76, + "learning_rate": 1.188295563857632e-05, + "loss": 0.1056, + "step": 341920 + }, + { + "epoch": 0.76, + "learning_rate": 1.1881837095366994e-05, + "loss": 0.1029, + "step": 341930 + }, + { + "epoch": 0.76, + "learning_rate": 1.188071855215767e-05, + "loss": 0.1013, + "step": 341940 + }, + { + "epoch": 0.76, + "learning_rate": 1.1879600008948346e-05, + "loss": 0.1008, + "step": 341950 + }, + { + "epoch": 0.76, + "learning_rate": 1.1878481465739023e-05, + "loss": 0.1069, + "step": 341960 + }, + { + "epoch": 0.76, + "learning_rate": 1.1877362922529697e-05, + "loss": 0.1079, + "step": 341970 + }, + { + "epoch": 0.76, + "learning_rate": 1.1876244379320373e-05, + "loss": 0.1069, + "step": 341980 + }, + { + "epoch": 0.76, + "learning_rate": 1.187512583611105e-05, + "loss": 0.1082, + "step": 341990 + }, + { + "epoch": 0.76, + "learning_rate": 1.1874007292901726e-05, + "loss": 0.106, + "step": 342000 + }, + { + "epoch": 0.76, + "learning_rate": 1.1872888749692402e-05, + "loss": 0.1021, + "step": 342010 + }, + { + "epoch": 0.76, + "learning_rate": 1.1871770206483077e-05, + "loss": 0.1038, + "step": 342020 + }, + { + "epoch": 0.76, + "learning_rate": 1.1870651663273753e-05, + "loss": 0.1, + "step": 342030 + }, + { + "epoch": 0.76, + "learning_rate": 1.1869533120064429e-05, + "loss": 0.1049, + "step": 342040 + }, + { + "epoch": 0.76, + "learning_rate": 1.1868414576855104e-05, + "loss": 0.1066, + "step": 342050 + }, + { + "epoch": 0.76, + "learning_rate": 1.186729603364578e-05, + "loss": 0.1021, + "step": 342060 + }, + { + "epoch": 0.76, + "learning_rate": 1.1866177490436456e-05, + "loss": 0.1074, + "step": 342070 + }, + { + "epoch": 0.76, + "learning_rate": 1.1865058947227132e-05, + "loss": 0.1057, + "step": 342080 + }, + { + "epoch": 0.76, + "learning_rate": 1.1863940404017809e-05, + "loss": 0.1013, + "step": 342090 + }, + { + "epoch": 0.76, + "learning_rate": 1.1862821860808483e-05, + "loss": 0.1051, + "step": 342100 + }, + { + "epoch": 0.76, + "learning_rate": 1.186170331759916e-05, + "loss": 0.0972, + "step": 342110 + }, + { + "epoch": 0.76, + "learning_rate": 1.1860584774389836e-05, + "loss": 0.1036, + "step": 342120 + }, + { + "epoch": 0.76, + "learning_rate": 1.185946623118051e-05, + "loss": 0.1055, + "step": 342130 + }, + { + "epoch": 0.76, + "learning_rate": 1.1858347687971188e-05, + "loss": 0.105, + "step": 342140 + }, + { + "epoch": 0.76, + "learning_rate": 1.1857229144761863e-05, + "loss": 0.1016, + "step": 342150 + }, + { + "epoch": 0.76, + "learning_rate": 1.1856110601552539e-05, + "loss": 0.1028, + "step": 342160 + }, + { + "epoch": 0.76, + "learning_rate": 1.1854992058343215e-05, + "loss": 0.1016, + "step": 342170 + }, + { + "epoch": 0.76, + "learning_rate": 1.185387351513389e-05, + "loss": 0.112, + "step": 342180 + }, + { + "epoch": 0.76, + "learning_rate": 1.1852754971924566e-05, + "loss": 0.1012, + "step": 342190 + }, + { + "epoch": 0.76, + "learning_rate": 1.1851636428715242e-05, + "loss": 0.1053, + "step": 342200 + }, + { + "epoch": 0.76, + "learning_rate": 1.1850517885505917e-05, + "loss": 0.1007, + "step": 342210 + }, + { + "epoch": 0.76, + "learning_rate": 1.1849399342296594e-05, + "loss": 0.1075, + "step": 342220 + }, + { + "epoch": 0.76, + "learning_rate": 1.1848280799087269e-05, + "loss": 0.0998, + "step": 342230 + }, + { + "epoch": 0.76, + "learning_rate": 1.1847162255877945e-05, + "loss": 0.1013, + "step": 342240 + }, + { + "epoch": 0.76, + "learning_rate": 1.1846043712668621e-05, + "loss": 0.1021, + "step": 342250 + }, + { + "epoch": 0.76, + "learning_rate": 1.1844925169459296e-05, + "loss": 0.1059, + "step": 342260 + }, + { + "epoch": 0.76, + "learning_rate": 1.1843806626249972e-05, + "loss": 0.1095, + "step": 342270 + }, + { + "epoch": 0.76, + "learning_rate": 1.1842688083040648e-05, + "loss": 0.1, + "step": 342280 + }, + { + "epoch": 0.76, + "learning_rate": 1.1841569539831323e-05, + "loss": 0.1008, + "step": 342290 + }, + { + "epoch": 0.76, + "learning_rate": 1.1840450996622001e-05, + "loss": 0.104, + "step": 342300 + }, + { + "epoch": 0.76, + "learning_rate": 1.1839332453412675e-05, + "loss": 0.1035, + "step": 342310 + }, + { + "epoch": 0.76, + "learning_rate": 1.1838213910203352e-05, + "loss": 0.1005, + "step": 342320 + }, + { + "epoch": 0.76, + "learning_rate": 1.1837095366994028e-05, + "loss": 0.1057, + "step": 342330 + }, + { + "epoch": 0.76, + "learning_rate": 1.1835976823784702e-05, + "loss": 0.1, + "step": 342340 + }, + { + "epoch": 0.76, + "learning_rate": 1.183485828057538e-05, + "loss": 0.1051, + "step": 342350 + }, + { + "epoch": 0.76, + "learning_rate": 1.1833739737366055e-05, + "loss": 0.1065, + "step": 342360 + }, + { + "epoch": 0.76, + "learning_rate": 1.183262119415673e-05, + "loss": 0.1055, + "step": 342370 + }, + { + "epoch": 0.76, + "learning_rate": 1.1831502650947407e-05, + "loss": 0.1026, + "step": 342380 + }, + { + "epoch": 0.76, + "learning_rate": 1.1830384107738082e-05, + "loss": 0.1, + "step": 342390 + }, + { + "epoch": 0.76, + "learning_rate": 1.1829265564528758e-05, + "loss": 0.105, + "step": 342400 + }, + { + "epoch": 0.76, + "learning_rate": 1.1828147021319434e-05, + "loss": 0.102, + "step": 342410 + }, + { + "epoch": 0.76, + "learning_rate": 1.1827028478110109e-05, + "loss": 0.1022, + "step": 342420 + }, + { + "epoch": 0.76, + "learning_rate": 1.1825909934900787e-05, + "loss": 0.1021, + "step": 342430 + }, + { + "epoch": 0.76, + "learning_rate": 1.1824791391691461e-05, + "loss": 0.1035, + "step": 342440 + }, + { + "epoch": 0.76, + "learning_rate": 1.1823672848482138e-05, + "loss": 0.1044, + "step": 342450 + }, + { + "epoch": 0.76, + "learning_rate": 1.1822554305272814e-05, + "loss": 0.1051, + "step": 342460 + }, + { + "epoch": 0.76, + "learning_rate": 1.1821435762063488e-05, + "loss": 0.0988, + "step": 342470 + }, + { + "epoch": 0.76, + "learning_rate": 1.1820317218854166e-05, + "loss": 0.1031, + "step": 342480 + }, + { + "epoch": 0.76, + "learning_rate": 1.1819198675644841e-05, + "loss": 0.1034, + "step": 342490 + }, + { + "epoch": 0.76, + "learning_rate": 1.1818080132435515e-05, + "loss": 0.0947, + "step": 342500 + }, + { + "epoch": 0.76, + "learning_rate": 1.1816961589226193e-05, + "loss": 0.1042, + "step": 342510 + }, + { + "epoch": 0.76, + "learning_rate": 1.1815843046016868e-05, + "loss": 0.1014, + "step": 342520 + }, + { + "epoch": 0.76, + "learning_rate": 1.1814724502807544e-05, + "loss": 0.1013, + "step": 342530 + }, + { + "epoch": 0.76, + "learning_rate": 1.181360595959822e-05, + "loss": 0.0998, + "step": 342540 + }, + { + "epoch": 0.76, + "learning_rate": 1.1812487416388895e-05, + "loss": 0.1009, + "step": 342550 + }, + { + "epoch": 0.76, + "learning_rate": 1.1811368873179573e-05, + "loss": 0.1044, + "step": 342560 + }, + { + "epoch": 0.76, + "learning_rate": 1.1810250329970247e-05, + "loss": 0.1022, + "step": 342570 + }, + { + "epoch": 0.76, + "learning_rate": 1.1809131786760922e-05, + "loss": 0.0993, + "step": 342580 + }, + { + "epoch": 0.76, + "learning_rate": 1.18080132435516e-05, + "loss": 0.1024, + "step": 342590 + }, + { + "epoch": 0.76, + "learning_rate": 1.1806894700342274e-05, + "loss": 0.102, + "step": 342600 + }, + { + "epoch": 0.76, + "learning_rate": 1.180577615713295e-05, + "loss": 0.1068, + "step": 342610 + }, + { + "epoch": 0.76, + "learning_rate": 1.180476946824456e-05, + "loss": 0.0993, + "step": 342620 + }, + { + "epoch": 0.76, + "learning_rate": 1.1803650925035236e-05, + "loss": 0.1021, + "step": 342630 + }, + { + "epoch": 0.76, + "learning_rate": 1.180253238182591e-05, + "loss": 0.101, + "step": 342640 + }, + { + "epoch": 0.76, + "learning_rate": 1.1801413838616586e-05, + "loss": 0.1051, + "step": 342650 + }, + { + "epoch": 0.76, + "learning_rate": 1.1800295295407263e-05, + "loss": 0.1057, + "step": 342660 + }, + { + "epoch": 0.76, + "learning_rate": 1.1799176752197937e-05, + "loss": 0.11, + "step": 342670 + }, + { + "epoch": 0.76, + "learning_rate": 1.1798058208988613e-05, + "loss": 0.1004, + "step": 342680 + }, + { + "epoch": 0.76, + "learning_rate": 1.179693966577929e-05, + "loss": 0.1019, + "step": 342690 + }, + { + "epoch": 0.76, + "learning_rate": 1.1795821122569966e-05, + "loss": 0.1053, + "step": 342700 + }, + { + "epoch": 0.76, + "learning_rate": 1.1794702579360642e-05, + "loss": 0.1027, + "step": 342710 + }, + { + "epoch": 0.76, + "learning_rate": 1.1793584036151317e-05, + "loss": 0.1025, + "step": 342720 + }, + { + "epoch": 0.77, + "learning_rate": 1.1792465492941993e-05, + "loss": 0.1011, + "step": 342730 + }, + { + "epoch": 0.77, + "learning_rate": 1.1791346949732669e-05, + "loss": 0.101, + "step": 342740 + }, + { + "epoch": 0.77, + "learning_rate": 1.1790228406523345e-05, + "loss": 0.1033, + "step": 342750 + }, + { + "epoch": 0.77, + "learning_rate": 1.178910986331402e-05, + "loss": 0.0996, + "step": 342760 + }, + { + "epoch": 0.77, + "learning_rate": 1.1787991320104696e-05, + "loss": 0.1052, + "step": 342770 + }, + { + "epoch": 0.77, + "learning_rate": 1.1786872776895372e-05, + "loss": 0.1009, + "step": 342780 + }, + { + "epoch": 0.77, + "learning_rate": 1.1785754233686049e-05, + "loss": 0.1015, + "step": 342790 + }, + { + "epoch": 0.77, + "learning_rate": 1.1784635690476723e-05, + "loss": 0.1035, + "step": 342800 + }, + { + "epoch": 0.77, + "learning_rate": 1.17835171472674e-05, + "loss": 0.1013, + "step": 342810 + }, + { + "epoch": 0.77, + "learning_rate": 1.1782398604058076e-05, + "loss": 0.104, + "step": 342820 + }, + { + "epoch": 0.77, + "learning_rate": 1.1781280060848752e-05, + "loss": 0.1065, + "step": 342830 + }, + { + "epoch": 0.77, + "learning_rate": 1.1780161517639426e-05, + "loss": 0.1048, + "step": 342840 + }, + { + "epoch": 0.77, + "learning_rate": 1.1779042974430103e-05, + "loss": 0.1015, + "step": 342850 + }, + { + "epoch": 0.77, + "learning_rate": 1.1777924431220779e-05, + "loss": 0.1053, + "step": 342860 + }, + { + "epoch": 0.77, + "learning_rate": 1.1776805888011455e-05, + "loss": 0.1018, + "step": 342870 + }, + { + "epoch": 0.77, + "learning_rate": 1.177568734480213e-05, + "loss": 0.0987, + "step": 342880 + }, + { + "epoch": 0.77, + "learning_rate": 1.1774568801592806e-05, + "loss": 0.1085, + "step": 342890 + }, + { + "epoch": 0.77, + "learning_rate": 1.1773450258383482e-05, + "loss": 0.1047, + "step": 342900 + }, + { + "epoch": 0.77, + "learning_rate": 1.1772331715174158e-05, + "loss": 0.1041, + "step": 342910 + }, + { + "epoch": 0.77, + "learning_rate": 1.1771213171964833e-05, + "loss": 0.1058, + "step": 342920 + }, + { + "epoch": 0.77, + "learning_rate": 1.1770094628755509e-05, + "loss": 0.108, + "step": 342930 + }, + { + "epoch": 0.77, + "learning_rate": 1.1768976085546185e-05, + "loss": 0.1077, + "step": 342940 + }, + { + "epoch": 0.77, + "learning_rate": 1.1767857542336862e-05, + "loss": 0.1035, + "step": 342950 + }, + { + "epoch": 0.77, + "learning_rate": 1.1766738999127538e-05, + "loss": 0.1025, + "step": 342960 + }, + { + "epoch": 0.77, + "learning_rate": 1.1765620455918212e-05, + "loss": 0.1023, + "step": 342970 + }, + { + "epoch": 0.77, + "learning_rate": 1.1764501912708889e-05, + "loss": 0.1054, + "step": 342980 + }, + { + "epoch": 0.77, + "learning_rate": 1.1763383369499565e-05, + "loss": 0.1082, + "step": 342990 + }, + { + "epoch": 0.77, + "learning_rate": 1.176226482629024e-05, + "loss": 0.1041, + "step": 343000 + }, + { + "epoch": 0.77, + "learning_rate": 1.1761146283080916e-05, + "loss": 0.1004, + "step": 343010 + }, + { + "epoch": 0.77, + "learning_rate": 1.1760027739871592e-05, + "loss": 0.1079, + "step": 343020 + }, + { + "epoch": 0.77, + "learning_rate": 1.1758909196662268e-05, + "loss": 0.1041, + "step": 343030 + }, + { + "epoch": 0.77, + "learning_rate": 1.1757790653452944e-05, + "loss": 0.1019, + "step": 343040 + }, + { + "epoch": 0.77, + "learning_rate": 1.1756672110243619e-05, + "loss": 0.1037, + "step": 343050 + }, + { + "epoch": 0.77, + "learning_rate": 1.1755553567034295e-05, + "loss": 0.1053, + "step": 343060 + }, + { + "epoch": 0.77, + "learning_rate": 1.1754435023824971e-05, + "loss": 0.1014, + "step": 343070 + }, + { + "epoch": 0.77, + "learning_rate": 1.1753316480615646e-05, + "loss": 0.1018, + "step": 343080 + }, + { + "epoch": 0.77, + "learning_rate": 1.1752197937406324e-05, + "loss": 0.1115, + "step": 343090 + }, + { + "epoch": 0.77, + "learning_rate": 1.1751079394196998e-05, + "loss": 0.0999, + "step": 343100 + }, + { + "epoch": 0.77, + "learning_rate": 1.1749960850987675e-05, + "loss": 0.1043, + "step": 343110 + }, + { + "epoch": 0.77, + "learning_rate": 1.174884230777835e-05, + "loss": 0.1005, + "step": 343120 + }, + { + "epoch": 0.77, + "learning_rate": 1.1747723764569025e-05, + "loss": 0.1049, + "step": 343130 + }, + { + "epoch": 0.77, + "learning_rate": 1.1746605221359702e-05, + "loss": 0.1017, + "step": 343140 + }, + { + "epoch": 0.77, + "learning_rate": 1.1745486678150378e-05, + "loss": 0.1044, + "step": 343150 + }, + { + "epoch": 0.77, + "learning_rate": 1.1744368134941052e-05, + "loss": 0.1034, + "step": 343160 + }, + { + "epoch": 0.77, + "learning_rate": 1.174324959173173e-05, + "loss": 0.1032, + "step": 343170 + }, + { + "epoch": 0.77, + "learning_rate": 1.1742131048522405e-05, + "loss": 0.1077, + "step": 343180 + }, + { + "epoch": 0.77, + "learning_rate": 1.1741012505313081e-05, + "loss": 0.1056, + "step": 343190 + }, + { + "epoch": 0.77, + "learning_rate": 1.1739893962103757e-05, + "loss": 0.1024, + "step": 343200 + }, + { + "epoch": 0.77, + "learning_rate": 1.1738775418894432e-05, + "loss": 0.1059, + "step": 343210 + }, + { + "epoch": 0.77, + "learning_rate": 1.1737656875685108e-05, + "loss": 0.1068, + "step": 343220 + }, + { + "epoch": 0.77, + "learning_rate": 1.1736538332475784e-05, + "loss": 0.1101, + "step": 343230 + }, + { + "epoch": 0.77, + "learning_rate": 1.1735419789266459e-05, + "loss": 0.1034, + "step": 343240 + }, + { + "epoch": 0.77, + "learning_rate": 1.1734301246057137e-05, + "loss": 0.1004, + "step": 343250 + }, + { + "epoch": 0.77, + "learning_rate": 1.1733182702847811e-05, + "loss": 0.1024, + "step": 343260 + }, + { + "epoch": 0.77, + "learning_rate": 1.1732064159638487e-05, + "loss": 0.1035, + "step": 343270 + }, + { + "epoch": 0.77, + "learning_rate": 1.1730945616429164e-05, + "loss": 0.1035, + "step": 343280 + }, + { + "epoch": 0.77, + "learning_rate": 1.1729827073219838e-05, + "loss": 0.0999, + "step": 343290 + }, + { + "epoch": 0.77, + "learning_rate": 1.1728708530010516e-05, + "loss": 0.1023, + "step": 343300 + }, + { + "epoch": 0.77, + "learning_rate": 1.172758998680119e-05, + "loss": 0.1033, + "step": 343310 + }, + { + "epoch": 0.77, + "learning_rate": 1.1726471443591865e-05, + "loss": 0.1015, + "step": 343320 + }, + { + "epoch": 0.77, + "learning_rate": 1.1725352900382543e-05, + "loss": 0.1014, + "step": 343330 + }, + { + "epoch": 0.77, + "learning_rate": 1.1724234357173218e-05, + "loss": 0.104, + "step": 343340 + }, + { + "epoch": 0.77, + "learning_rate": 1.1723115813963894e-05, + "loss": 0.107, + "step": 343350 + }, + { + "epoch": 0.77, + "learning_rate": 1.172199727075457e-05, + "loss": 0.1045, + "step": 343360 + }, + { + "epoch": 0.77, + "learning_rate": 1.1720878727545245e-05, + "loss": 0.0997, + "step": 343370 + }, + { + "epoch": 0.77, + "learning_rate": 1.1719760184335923e-05, + "loss": 0.1051, + "step": 343380 + }, + { + "epoch": 0.77, + "learning_rate": 1.1718641641126597e-05, + "loss": 0.106, + "step": 343390 + }, + { + "epoch": 0.77, + "learning_rate": 1.1717523097917272e-05, + "loss": 0.1017, + "step": 343400 + }, + { + "epoch": 0.77, + "learning_rate": 1.171640455470795e-05, + "loss": 0.1033, + "step": 343410 + }, + { + "epoch": 0.77, + "learning_rate": 1.1715286011498624e-05, + "loss": 0.1023, + "step": 343420 + }, + { + "epoch": 0.77, + "learning_rate": 1.17141674682893e-05, + "loss": 0.104, + "step": 343430 + }, + { + "epoch": 0.77, + "learning_rate": 1.1713048925079977e-05, + "loss": 0.1042, + "step": 343440 + }, + { + "epoch": 0.77, + "learning_rate": 1.1711930381870651e-05, + "loss": 0.106, + "step": 343450 + }, + { + "epoch": 0.77, + "learning_rate": 1.1710811838661329e-05, + "loss": 0.1022, + "step": 343460 + }, + { + "epoch": 0.77, + "learning_rate": 1.1709693295452004e-05, + "loss": 0.1027, + "step": 343470 + }, + { + "epoch": 0.77, + "learning_rate": 1.170857475224268e-05, + "loss": 0.1014, + "step": 343480 + }, + { + "epoch": 0.77, + "learning_rate": 1.1707456209033356e-05, + "loss": 0.1027, + "step": 343490 + }, + { + "epoch": 0.77, + "learning_rate": 1.170633766582403e-05, + "loss": 0.1074, + "step": 343500 + }, + { + "epoch": 0.77, + "learning_rate": 1.1705219122614707e-05, + "loss": 0.1033, + "step": 343510 + }, + { + "epoch": 0.77, + "learning_rate": 1.1704100579405383e-05, + "loss": 0.1027, + "step": 343520 + }, + { + "epoch": 0.77, + "learning_rate": 1.1702982036196058e-05, + "loss": 0.1025, + "step": 343530 + }, + { + "epoch": 0.77, + "learning_rate": 1.1701863492986736e-05, + "loss": 0.1085, + "step": 343540 + }, + { + "epoch": 0.77, + "learning_rate": 1.170074494977741e-05, + "loss": 0.1012, + "step": 343550 + }, + { + "epoch": 0.77, + "learning_rate": 1.1699626406568086e-05, + "loss": 0.0987, + "step": 343560 + }, + { + "epoch": 0.77, + "learning_rate": 1.1698507863358763e-05, + "loss": 0.103, + "step": 343570 + }, + { + "epoch": 0.77, + "learning_rate": 1.1697389320149437e-05, + "loss": 0.0992, + "step": 343580 + }, + { + "epoch": 0.77, + "learning_rate": 1.1696270776940113e-05, + "loss": 0.1019, + "step": 343590 + }, + { + "epoch": 0.77, + "learning_rate": 1.169515223373079e-05, + "loss": 0.1021, + "step": 343600 + }, + { + "epoch": 0.77, + "learning_rate": 1.1694033690521466e-05, + "loss": 0.1058, + "step": 343610 + }, + { + "epoch": 0.77, + "learning_rate": 1.1692915147312142e-05, + "loss": 0.1066, + "step": 343620 + }, + { + "epoch": 0.77, + "learning_rate": 1.1691796604102817e-05, + "loss": 0.1051, + "step": 343630 + }, + { + "epoch": 0.77, + "learning_rate": 1.1690678060893493e-05, + "loss": 0.105, + "step": 343640 + }, + { + "epoch": 0.77, + "learning_rate": 1.1689559517684169e-05, + "loss": 0.1051, + "step": 343650 + }, + { + "epoch": 0.77, + "learning_rate": 1.1688440974474844e-05, + "loss": 0.0988, + "step": 343660 + }, + { + "epoch": 0.77, + "learning_rate": 1.168732243126552e-05, + "loss": 0.1021, + "step": 343670 + }, + { + "epoch": 0.77, + "learning_rate": 1.1686203888056196e-05, + "loss": 0.1031, + "step": 343680 + }, + { + "epoch": 0.77, + "learning_rate": 1.1685085344846872e-05, + "loss": 0.1022, + "step": 343690 + }, + { + "epoch": 0.77, + "learning_rate": 1.1683966801637549e-05, + "loss": 0.105, + "step": 343700 + }, + { + "epoch": 0.77, + "learning_rate": 1.1682848258428223e-05, + "loss": 0.1061, + "step": 343710 + }, + { + "epoch": 0.77, + "learning_rate": 1.16817297152189e-05, + "loss": 0.1038, + "step": 343720 + }, + { + "epoch": 0.77, + "learning_rate": 1.1680611172009576e-05, + "loss": 0.0992, + "step": 343730 + }, + { + "epoch": 0.77, + "learning_rate": 1.167949262880025e-05, + "loss": 0.1021, + "step": 343740 + }, + { + "epoch": 0.77, + "learning_rate": 1.1678374085590926e-05, + "loss": 0.0996, + "step": 343750 + }, + { + "epoch": 0.77, + "learning_rate": 1.1677255542381603e-05, + "loss": 0.1039, + "step": 343760 + }, + { + "epoch": 0.77, + "learning_rate": 1.1676136999172279e-05, + "loss": 0.1017, + "step": 343770 + }, + { + "epoch": 0.77, + "learning_rate": 1.1675018455962955e-05, + "loss": 0.1043, + "step": 343780 + }, + { + "epoch": 0.77, + "learning_rate": 1.167389991275363e-05, + "loss": 0.1049, + "step": 343790 + }, + { + "epoch": 0.77, + "learning_rate": 1.1672781369544306e-05, + "loss": 0.1037, + "step": 343800 + }, + { + "epoch": 0.77, + "learning_rate": 1.1671662826334982e-05, + "loss": 0.0999, + "step": 343810 + }, + { + "epoch": 0.77, + "learning_rate": 1.1670544283125658e-05, + "loss": 0.1008, + "step": 343820 + }, + { + "epoch": 0.77, + "learning_rate": 1.1669425739916333e-05, + "loss": 0.102, + "step": 343830 + }, + { + "epoch": 0.77, + "learning_rate": 1.1668307196707009e-05, + "loss": 0.1044, + "step": 343840 + }, + { + "epoch": 0.77, + "learning_rate": 1.1667188653497685e-05, + "loss": 0.1016, + "step": 343850 + }, + { + "epoch": 0.77, + "learning_rate": 1.1666070110288362e-05, + "loss": 0.1, + "step": 343860 + }, + { + "epoch": 0.77, + "learning_rate": 1.1664951567079036e-05, + "loss": 0.106, + "step": 343870 + }, + { + "epoch": 0.77, + "learning_rate": 1.1663833023869712e-05, + "loss": 0.1014, + "step": 343880 + }, + { + "epoch": 0.77, + "learning_rate": 1.1662714480660389e-05, + "loss": 0.1005, + "step": 343890 + }, + { + "epoch": 0.77, + "learning_rate": 1.1661595937451065e-05, + "loss": 0.1024, + "step": 343900 + }, + { + "epoch": 0.77, + "learning_rate": 1.166047739424174e-05, + "loss": 0.1013, + "step": 343910 + }, + { + "epoch": 0.77, + "learning_rate": 1.1659358851032416e-05, + "loss": 0.102, + "step": 343920 + }, + { + "epoch": 0.77, + "learning_rate": 1.1658240307823092e-05, + "loss": 0.1093, + "step": 343930 + }, + { + "epoch": 0.77, + "learning_rate": 1.1657121764613768e-05, + "loss": 0.1047, + "step": 343940 + }, + { + "epoch": 0.77, + "learning_rate": 1.1656003221404444e-05, + "loss": 0.1017, + "step": 343950 + }, + { + "epoch": 0.77, + "learning_rate": 1.1654884678195119e-05, + "loss": 0.104, + "step": 343960 + }, + { + "epoch": 0.77, + "learning_rate": 1.1653766134985795e-05, + "loss": 0.1016, + "step": 343970 + }, + { + "epoch": 0.77, + "learning_rate": 1.1652647591776471e-05, + "loss": 0.1024, + "step": 343980 + }, + { + "epoch": 0.77, + "learning_rate": 1.1651529048567146e-05, + "loss": 0.109, + "step": 343990 + }, + { + "epoch": 0.77, + "learning_rate": 1.1650410505357822e-05, + "loss": 0.0999, + "step": 344000 + }, + { + "epoch": 0.77, + "learning_rate": 1.1649291962148498e-05, + "loss": 0.1021, + "step": 344010 + }, + { + "epoch": 0.77, + "learning_rate": 1.1648173418939175e-05, + "loss": 0.1001, + "step": 344020 + }, + { + "epoch": 0.77, + "learning_rate": 1.164705487572985e-05, + "loss": 0.0998, + "step": 344030 + }, + { + "epoch": 0.77, + "learning_rate": 1.1645936332520525e-05, + "loss": 0.1026, + "step": 344040 + }, + { + "epoch": 0.77, + "learning_rate": 1.1644817789311202e-05, + "loss": 0.1053, + "step": 344050 + }, + { + "epoch": 0.77, + "learning_rate": 1.1643699246101878e-05, + "loss": 0.1002, + "step": 344060 + }, + { + "epoch": 0.77, + "learning_rate": 1.1642580702892552e-05, + "loss": 0.1032, + "step": 344070 + }, + { + "epoch": 0.77, + "learning_rate": 1.1641462159683229e-05, + "loss": 0.1037, + "step": 344080 + }, + { + "epoch": 0.77, + "learning_rate": 1.1640343616473905e-05, + "loss": 0.1024, + "step": 344090 + }, + { + "epoch": 0.77, + "learning_rate": 1.1639225073264581e-05, + "loss": 0.1062, + "step": 344100 + }, + { + "epoch": 0.77, + "learning_rate": 1.1638106530055257e-05, + "loss": 0.0984, + "step": 344110 + }, + { + "epoch": 0.77, + "learning_rate": 1.1636987986845932e-05, + "loss": 0.0992, + "step": 344120 + }, + { + "epoch": 0.77, + "learning_rate": 1.1635869443636608e-05, + "loss": 0.1011, + "step": 344130 + }, + { + "epoch": 0.77, + "learning_rate": 1.1634750900427284e-05, + "loss": 0.1007, + "step": 344140 + }, + { + "epoch": 0.77, + "learning_rate": 1.1633632357217959e-05, + "loss": 0.106, + "step": 344150 + }, + { + "epoch": 0.77, + "learning_rate": 1.1632513814008637e-05, + "loss": 0.1023, + "step": 344160 + }, + { + "epoch": 0.77, + "learning_rate": 1.1631395270799311e-05, + "loss": 0.1017, + "step": 344170 + }, + { + "epoch": 0.77, + "learning_rate": 1.1630276727589987e-05, + "loss": 0.1018, + "step": 344180 + }, + { + "epoch": 0.77, + "learning_rate": 1.1629158184380664e-05, + "loss": 0.1025, + "step": 344190 + }, + { + "epoch": 0.77, + "learning_rate": 1.1628039641171338e-05, + "loss": 0.1036, + "step": 344200 + }, + { + "epoch": 0.77, + "learning_rate": 1.1626921097962014e-05, + "loss": 0.0997, + "step": 344210 + }, + { + "epoch": 0.77, + "learning_rate": 1.162580255475269e-05, + "loss": 0.1031, + "step": 344220 + }, + { + "epoch": 0.77, + "learning_rate": 1.1624684011543365e-05, + "loss": 0.1032, + "step": 344230 + }, + { + "epoch": 0.77, + "learning_rate": 1.1623565468334043e-05, + "loss": 0.1071, + "step": 344240 + }, + { + "epoch": 0.77, + "learning_rate": 1.1622446925124718e-05, + "loss": 0.1018, + "step": 344250 + }, + { + "epoch": 0.77, + "learning_rate": 1.1621328381915394e-05, + "loss": 0.1039, + "step": 344260 + }, + { + "epoch": 0.77, + "learning_rate": 1.162020983870607e-05, + "loss": 0.1082, + "step": 344270 + }, + { + "epoch": 0.77, + "learning_rate": 1.1619091295496745e-05, + "loss": 0.0988, + "step": 344280 + }, + { + "epoch": 0.77, + "learning_rate": 1.1617972752287423e-05, + "loss": 0.102, + "step": 344290 + }, + { + "epoch": 0.77, + "learning_rate": 1.1616854209078097e-05, + "loss": 0.1012, + "step": 344300 + }, + { + "epoch": 0.77, + "learning_rate": 1.1615735665868772e-05, + "loss": 0.102, + "step": 344310 + }, + { + "epoch": 0.77, + "learning_rate": 1.161461712265945e-05, + "loss": 0.1026, + "step": 344320 + }, + { + "epoch": 0.77, + "learning_rate": 1.1613498579450124e-05, + "loss": 0.1008, + "step": 344330 + }, + { + "epoch": 0.77, + "learning_rate": 1.16123800362408e-05, + "loss": 0.102, + "step": 344340 + }, + { + "epoch": 0.77, + "learning_rate": 1.1611261493031477e-05, + "loss": 0.1078, + "step": 344350 + }, + { + "epoch": 0.77, + "learning_rate": 1.1610142949822151e-05, + "loss": 0.0995, + "step": 344360 + }, + { + "epoch": 0.77, + "learning_rate": 1.1609024406612829e-05, + "loss": 0.1068, + "step": 344370 + }, + { + "epoch": 0.77, + "learning_rate": 1.1607905863403504e-05, + "loss": 0.1056, + "step": 344380 + }, + { + "epoch": 0.77, + "learning_rate": 1.1606787320194178e-05, + "loss": 0.1018, + "step": 344390 + }, + { + "epoch": 0.77, + "learning_rate": 1.1605668776984856e-05, + "loss": 0.1049, + "step": 344400 + }, + { + "epoch": 0.77, + "learning_rate": 1.160455023377553e-05, + "loss": 0.1021, + "step": 344410 + }, + { + "epoch": 0.77, + "learning_rate": 1.1603431690566207e-05, + "loss": 0.1008, + "step": 344420 + }, + { + "epoch": 0.77, + "learning_rate": 1.1602313147356883e-05, + "loss": 0.1076, + "step": 344430 + }, + { + "epoch": 0.77, + "learning_rate": 1.1601194604147558e-05, + "loss": 0.1, + "step": 344440 + }, + { + "epoch": 0.77, + "learning_rate": 1.1600076060938236e-05, + "loss": 0.1025, + "step": 344450 + }, + { + "epoch": 0.77, + "learning_rate": 1.159895751772891e-05, + "loss": 0.1077, + "step": 344460 + }, + { + "epoch": 0.77, + "learning_rate": 1.1597838974519586e-05, + "loss": 0.105, + "step": 344470 + }, + { + "epoch": 0.77, + "learning_rate": 1.1596720431310263e-05, + "loss": 0.1083, + "step": 344480 + }, + { + "epoch": 0.77, + "learning_rate": 1.1595601888100937e-05, + "loss": 0.1008, + "step": 344490 + }, + { + "epoch": 0.77, + "learning_rate": 1.1594483344891615e-05, + "loss": 0.1032, + "step": 344500 + }, + { + "epoch": 0.77, + "learning_rate": 1.159336480168229e-05, + "loss": 0.1019, + "step": 344510 + }, + { + "epoch": 0.77, + "learning_rate": 1.1592246258472964e-05, + "loss": 0.1064, + "step": 344520 + }, + { + "epoch": 0.77, + "learning_rate": 1.1591127715263642e-05, + "loss": 0.1043, + "step": 344530 + }, + { + "epoch": 0.77, + "learning_rate": 1.1590009172054317e-05, + "loss": 0.1061, + "step": 344540 + }, + { + "epoch": 0.77, + "learning_rate": 1.1588890628844993e-05, + "loss": 0.1058, + "step": 344550 + }, + { + "epoch": 0.77, + "learning_rate": 1.1587772085635669e-05, + "loss": 0.1023, + "step": 344560 + }, + { + "epoch": 0.77, + "learning_rate": 1.1586653542426344e-05, + "loss": 0.0983, + "step": 344570 + }, + { + "epoch": 0.77, + "learning_rate": 1.1585534999217022e-05, + "loss": 0.1046, + "step": 344580 + }, + { + "epoch": 0.77, + "learning_rate": 1.1584416456007696e-05, + "loss": 0.1052, + "step": 344590 + }, + { + "epoch": 0.77, + "learning_rate": 1.1583297912798372e-05, + "loss": 0.105, + "step": 344600 + }, + { + "epoch": 0.77, + "learning_rate": 1.1582179369589049e-05, + "loss": 0.1041, + "step": 344610 + }, + { + "epoch": 0.77, + "learning_rate": 1.1581060826379723e-05, + "loss": 0.1056, + "step": 344620 + }, + { + "epoch": 0.77, + "learning_rate": 1.1580054137491332e-05, + "loss": 0.102, + "step": 344630 + }, + { + "epoch": 0.77, + "learning_rate": 1.1578935594282008e-05, + "loss": 0.1048, + "step": 344640 + }, + { + "epoch": 0.77, + "learning_rate": 1.1577817051072684e-05, + "loss": 0.1017, + "step": 344650 + }, + { + "epoch": 0.77, + "learning_rate": 1.1576698507863359e-05, + "loss": 0.0965, + "step": 344660 + }, + { + "epoch": 0.77, + "learning_rate": 1.1575579964654035e-05, + "loss": 0.1043, + "step": 344670 + }, + { + "epoch": 0.77, + "learning_rate": 1.1574461421444711e-05, + "loss": 0.104, + "step": 344680 + }, + { + "epoch": 0.77, + "learning_rate": 1.1573342878235386e-05, + "loss": 0.1003, + "step": 344690 + }, + { + "epoch": 0.77, + "learning_rate": 1.1572224335026062e-05, + "loss": 0.1035, + "step": 344700 + }, + { + "epoch": 0.77, + "learning_rate": 1.1571105791816738e-05, + "loss": 0.1055, + "step": 344710 + }, + { + "epoch": 0.77, + "learning_rate": 1.1569987248607415e-05, + "loss": 0.0996, + "step": 344720 + }, + { + "epoch": 0.77, + "learning_rate": 1.1568868705398091e-05, + "loss": 0.1021, + "step": 344730 + }, + { + "epoch": 0.77, + "learning_rate": 1.1567750162188765e-05, + "loss": 0.1079, + "step": 344740 + }, + { + "epoch": 0.77, + "learning_rate": 1.1566631618979442e-05, + "loss": 0.1013, + "step": 344750 + }, + { + "epoch": 0.77, + "learning_rate": 1.1565513075770118e-05, + "loss": 0.1048, + "step": 344760 + }, + { + "epoch": 0.77, + "learning_rate": 1.1564394532560794e-05, + "loss": 0.1086, + "step": 344770 + }, + { + "epoch": 0.77, + "learning_rate": 1.1563275989351469e-05, + "loss": 0.1035, + "step": 344780 + }, + { + "epoch": 0.77, + "learning_rate": 1.1562157446142145e-05, + "loss": 0.1048, + "step": 344790 + }, + { + "epoch": 0.77, + "learning_rate": 1.1561038902932821e-05, + "loss": 0.0996, + "step": 344800 + }, + { + "epoch": 0.77, + "learning_rate": 1.1559920359723497e-05, + "loss": 0.1007, + "step": 344810 + }, + { + "epoch": 0.77, + "learning_rate": 1.1558801816514172e-05, + "loss": 0.1013, + "step": 344820 + }, + { + "epoch": 0.77, + "learning_rate": 1.1557683273304848e-05, + "loss": 0.1047, + "step": 344830 + }, + { + "epoch": 0.77, + "learning_rate": 1.1556564730095524e-05, + "loss": 0.1, + "step": 344840 + }, + { + "epoch": 0.77, + "learning_rate": 1.15554461868862e-05, + "loss": 0.1071, + "step": 344850 + }, + { + "epoch": 0.77, + "learning_rate": 1.1554327643676875e-05, + "loss": 0.1001, + "step": 344860 + }, + { + "epoch": 0.77, + "learning_rate": 1.1553209100467551e-05, + "loss": 0.1037, + "step": 344870 + }, + { + "epoch": 0.77, + "learning_rate": 1.1552090557258228e-05, + "loss": 0.1009, + "step": 344880 + }, + { + "epoch": 0.77, + "learning_rate": 1.1550972014048904e-05, + "loss": 0.1072, + "step": 344890 + }, + { + "epoch": 0.77, + "learning_rate": 1.1549853470839578e-05, + "loss": 0.1039, + "step": 344900 + }, + { + "epoch": 0.77, + "learning_rate": 1.1548734927630255e-05, + "loss": 0.1061, + "step": 344910 + }, + { + "epoch": 0.77, + "learning_rate": 1.154761638442093e-05, + "loss": 0.0996, + "step": 344920 + }, + { + "epoch": 0.77, + "learning_rate": 1.1546497841211607e-05, + "loss": 0.1009, + "step": 344930 + }, + { + "epoch": 0.77, + "learning_rate": 1.1545379298002282e-05, + "loss": 0.106, + "step": 344940 + }, + { + "epoch": 0.77, + "learning_rate": 1.1544260754792958e-05, + "loss": 0.1008, + "step": 344950 + }, + { + "epoch": 0.77, + "learning_rate": 1.1543142211583634e-05, + "loss": 0.1029, + "step": 344960 + }, + { + "epoch": 0.77, + "learning_rate": 1.154202366837431e-05, + "loss": 0.1031, + "step": 344970 + }, + { + "epoch": 0.77, + "learning_rate": 1.1540905125164987e-05, + "loss": 0.1018, + "step": 344980 + }, + { + "epoch": 0.77, + "learning_rate": 1.1539786581955661e-05, + "loss": 0.1047, + "step": 344990 + }, + { + "epoch": 0.77, + "learning_rate": 1.1538668038746337e-05, + "loss": 0.1027, + "step": 345000 + }, + { + "epoch": 0.77, + "learning_rate": 1.1537549495537014e-05, + "loss": 0.1036, + "step": 345010 + }, + { + "epoch": 0.77, + "learning_rate": 1.1536430952327688e-05, + "loss": 0.1027, + "step": 345020 + }, + { + "epoch": 0.77, + "learning_rate": 1.1535312409118364e-05, + "loss": 0.1049, + "step": 345030 + }, + { + "epoch": 0.77, + "learning_rate": 1.153419386590904e-05, + "loss": 0.1066, + "step": 345040 + }, + { + "epoch": 0.77, + "learning_rate": 1.1533075322699717e-05, + "loss": 0.1024, + "step": 345050 + }, + { + "epoch": 0.77, + "learning_rate": 1.1531956779490393e-05, + "loss": 0.1056, + "step": 345060 + }, + { + "epoch": 0.77, + "learning_rate": 1.1530838236281068e-05, + "loss": 0.1032, + "step": 345070 + }, + { + "epoch": 0.77, + "learning_rate": 1.1529719693071744e-05, + "loss": 0.1011, + "step": 345080 + }, + { + "epoch": 0.77, + "learning_rate": 1.152860114986242e-05, + "loss": 0.1062, + "step": 345090 + }, + { + "epoch": 0.77, + "learning_rate": 1.1527482606653095e-05, + "loss": 0.1023, + "step": 345100 + }, + { + "epoch": 0.77, + "learning_rate": 1.1526364063443772e-05, + "loss": 0.103, + "step": 345110 + }, + { + "epoch": 0.77, + "learning_rate": 1.1525245520234447e-05, + "loss": 0.1048, + "step": 345120 + }, + { + "epoch": 0.77, + "learning_rate": 1.1524126977025123e-05, + "loss": 0.1068, + "step": 345130 + }, + { + "epoch": 0.77, + "learning_rate": 1.15230084338158e-05, + "loss": 0.1032, + "step": 345140 + }, + { + "epoch": 0.77, + "learning_rate": 1.1521889890606474e-05, + "loss": 0.1003, + "step": 345150 + }, + { + "epoch": 0.77, + "learning_rate": 1.152077134739715e-05, + "loss": 0.1055, + "step": 345160 + }, + { + "epoch": 0.77, + "learning_rate": 1.1519652804187826e-05, + "loss": 0.1034, + "step": 345170 + }, + { + "epoch": 0.77, + "learning_rate": 1.1518534260978501e-05, + "loss": 0.0994, + "step": 345180 + }, + { + "epoch": 0.77, + "learning_rate": 1.1517415717769179e-05, + "loss": 0.1033, + "step": 345190 + }, + { + "epoch": 0.77, + "learning_rate": 1.1516297174559854e-05, + "loss": 0.1032, + "step": 345200 + }, + { + "epoch": 0.77, + "learning_rate": 1.151517863135053e-05, + "loss": 0.1009, + "step": 345210 + }, + { + "epoch": 0.77, + "learning_rate": 1.1514060088141206e-05, + "loss": 0.1026, + "step": 345220 + }, + { + "epoch": 0.77, + "learning_rate": 1.151294154493188e-05, + "loss": 0.1055, + "step": 345230 + }, + { + "epoch": 0.77, + "learning_rate": 1.1511823001722557e-05, + "loss": 0.0999, + "step": 345240 + }, + { + "epoch": 0.77, + "learning_rate": 1.1510704458513233e-05, + "loss": 0.1054, + "step": 345250 + }, + { + "epoch": 0.77, + "learning_rate": 1.1509585915303908e-05, + "loss": 0.1069, + "step": 345260 + }, + { + "epoch": 0.77, + "learning_rate": 1.1508467372094585e-05, + "loss": 0.1045, + "step": 345270 + }, + { + "epoch": 0.77, + "learning_rate": 1.150734882888526e-05, + "loss": 0.1001, + "step": 345280 + }, + { + "epoch": 0.77, + "learning_rate": 1.1506230285675936e-05, + "loss": 0.1049, + "step": 345290 + }, + { + "epoch": 0.77, + "learning_rate": 1.1505111742466612e-05, + "loss": 0.0984, + "step": 345300 + }, + { + "epoch": 0.77, + "learning_rate": 1.1503993199257287e-05, + "loss": 0.0995, + "step": 345310 + }, + { + "epoch": 0.77, + "learning_rate": 1.1502874656047965e-05, + "loss": 0.1013, + "step": 345320 + }, + { + "epoch": 0.77, + "learning_rate": 1.150175611283864e-05, + "loss": 0.1, + "step": 345330 + }, + { + "epoch": 0.77, + "learning_rate": 1.1500637569629314e-05, + "loss": 0.1041, + "step": 345340 + }, + { + "epoch": 0.77, + "learning_rate": 1.1499519026419992e-05, + "loss": 0.0975, + "step": 345350 + }, + { + "epoch": 0.77, + "learning_rate": 1.1498400483210666e-05, + "loss": 0.0988, + "step": 345360 + }, + { + "epoch": 0.77, + "learning_rate": 1.1497281940001343e-05, + "loss": 0.1037, + "step": 345370 + }, + { + "epoch": 0.77, + "learning_rate": 1.1496163396792019e-05, + "loss": 0.1011, + "step": 345380 + }, + { + "epoch": 0.77, + "learning_rate": 1.1495044853582693e-05, + "loss": 0.1029, + "step": 345390 + }, + { + "epoch": 0.77, + "learning_rate": 1.1493926310373371e-05, + "loss": 0.1056, + "step": 345400 + }, + { + "epoch": 0.77, + "learning_rate": 1.1492807767164046e-05, + "loss": 0.1044, + "step": 345410 + }, + { + "epoch": 0.77, + "learning_rate": 1.1491689223954722e-05, + "loss": 0.1001, + "step": 345420 + }, + { + "epoch": 0.77, + "learning_rate": 1.1490570680745398e-05, + "loss": 0.0998, + "step": 345430 + }, + { + "epoch": 0.77, + "learning_rate": 1.1489452137536073e-05, + "loss": 0.1034, + "step": 345440 + }, + { + "epoch": 0.77, + "learning_rate": 1.1488333594326751e-05, + "loss": 0.1051, + "step": 345450 + }, + { + "epoch": 0.77, + "learning_rate": 1.1487215051117425e-05, + "loss": 0.1041, + "step": 345460 + }, + { + "epoch": 0.77, + "learning_rate": 1.14860965079081e-05, + "loss": 0.1001, + "step": 345470 + }, + { + "epoch": 0.77, + "learning_rate": 1.1484977964698778e-05, + "loss": 0.1035, + "step": 345480 + }, + { + "epoch": 0.77, + "learning_rate": 1.1483859421489452e-05, + "loss": 0.1028, + "step": 345490 + }, + { + "epoch": 0.77, + "learning_rate": 1.1482740878280129e-05, + "loss": 0.1021, + "step": 345500 + }, + { + "epoch": 0.77, + "learning_rate": 1.1481622335070805e-05, + "loss": 0.0997, + "step": 345510 + }, + { + "epoch": 0.77, + "learning_rate": 1.148050379186148e-05, + "loss": 0.1016, + "step": 345520 + }, + { + "epoch": 0.77, + "learning_rate": 1.1479385248652157e-05, + "loss": 0.1012, + "step": 345530 + }, + { + "epoch": 0.77, + "learning_rate": 1.1478266705442832e-05, + "loss": 0.1022, + "step": 345540 + }, + { + "epoch": 0.77, + "learning_rate": 1.1477148162233506e-05, + "loss": 0.1047, + "step": 345550 + }, + { + "epoch": 0.77, + "learning_rate": 1.1476029619024184e-05, + "loss": 0.104, + "step": 345560 + }, + { + "epoch": 0.77, + "learning_rate": 1.1474911075814859e-05, + "loss": 0.1025, + "step": 345570 + }, + { + "epoch": 0.77, + "learning_rate": 1.1473792532605535e-05, + "loss": 0.1063, + "step": 345580 + }, + { + "epoch": 0.77, + "learning_rate": 1.1472673989396211e-05, + "loss": 0.1061, + "step": 345590 + }, + { + "epoch": 0.77, + "learning_rate": 1.1471555446186886e-05, + "loss": 0.0984, + "step": 345600 + }, + { + "epoch": 0.77, + "learning_rate": 1.1470436902977564e-05, + "loss": 0.1029, + "step": 345610 + }, + { + "epoch": 0.77, + "learning_rate": 1.1469318359768238e-05, + "loss": 0.1038, + "step": 345620 + }, + { + "epoch": 0.77, + "learning_rate": 1.1468199816558915e-05, + "loss": 0.0995, + "step": 345630 + }, + { + "epoch": 0.77, + "learning_rate": 1.146708127334959e-05, + "loss": 0.1048, + "step": 345640 + }, + { + "epoch": 0.77, + "learning_rate": 1.1465962730140265e-05, + "loss": 0.1032, + "step": 345650 + }, + { + "epoch": 0.77, + "learning_rate": 1.1464844186930942e-05, + "loss": 0.1045, + "step": 345660 + }, + { + "epoch": 0.77, + "learning_rate": 1.1463725643721618e-05, + "loss": 0.1027, + "step": 345670 + }, + { + "epoch": 0.77, + "learning_rate": 1.1462607100512292e-05, + "loss": 0.1019, + "step": 345680 + }, + { + "epoch": 0.77, + "learning_rate": 1.146148855730297e-05, + "loss": 0.1053, + "step": 345690 + }, + { + "epoch": 0.77, + "learning_rate": 1.1460370014093645e-05, + "loss": 0.1044, + "step": 345700 + }, + { + "epoch": 0.77, + "learning_rate": 1.1459251470884321e-05, + "loss": 0.1076, + "step": 345710 + }, + { + "epoch": 0.77, + "learning_rate": 1.1458132927674997e-05, + "loss": 0.1052, + "step": 345720 + }, + { + "epoch": 0.77, + "learning_rate": 1.1457014384465672e-05, + "loss": 0.106, + "step": 345730 + }, + { + "epoch": 0.77, + "learning_rate": 1.1455895841256348e-05, + "loss": 0.1036, + "step": 345740 + }, + { + "epoch": 0.77, + "learning_rate": 1.1454777298047024e-05, + "loss": 0.1055, + "step": 345750 + }, + { + "epoch": 0.77, + "learning_rate": 1.14536587548377e-05, + "loss": 0.1078, + "step": 345760 + }, + { + "epoch": 0.77, + "learning_rate": 1.1452540211628377e-05, + "loss": 0.1046, + "step": 345770 + }, + { + "epoch": 0.77, + "learning_rate": 1.1451421668419051e-05, + "loss": 0.1029, + "step": 345780 + }, + { + "epoch": 0.77, + "learning_rate": 1.1450303125209728e-05, + "loss": 0.1016, + "step": 345790 + }, + { + "epoch": 0.77, + "learning_rate": 1.1449184582000404e-05, + "loss": 0.1014, + "step": 345800 + }, + { + "epoch": 0.77, + "learning_rate": 1.1448066038791078e-05, + "loss": 0.1059, + "step": 345810 + }, + { + "epoch": 0.77, + "learning_rate": 1.1446947495581755e-05, + "loss": 0.1024, + "step": 345820 + }, + { + "epoch": 0.77, + "learning_rate": 1.144582895237243e-05, + "loss": 0.1017, + "step": 345830 + }, + { + "epoch": 0.77, + "learning_rate": 1.1444710409163107e-05, + "loss": 0.0977, + "step": 345840 + }, + { + "epoch": 0.77, + "learning_rate": 1.1443591865953783e-05, + "loss": 0.1055, + "step": 345850 + }, + { + "epoch": 0.77, + "learning_rate": 1.1442473322744458e-05, + "loss": 0.1028, + "step": 345860 + }, + { + "epoch": 0.77, + "learning_rate": 1.1441354779535134e-05, + "loss": 0.1064, + "step": 345870 + }, + { + "epoch": 0.77, + "learning_rate": 1.144023623632581e-05, + "loss": 0.101, + "step": 345880 + }, + { + "epoch": 0.77, + "learning_rate": 1.1439117693116485e-05, + "loss": 0.1005, + "step": 345890 + }, + { + "epoch": 0.77, + "learning_rate": 1.1437999149907161e-05, + "loss": 0.1052, + "step": 345900 + }, + { + "epoch": 0.77, + "learning_rate": 1.1436880606697837e-05, + "loss": 0.1033, + "step": 345910 + }, + { + "epoch": 0.77, + "learning_rate": 1.1435762063488514e-05, + "loss": 0.1038, + "step": 345920 + }, + { + "epoch": 0.77, + "learning_rate": 1.143464352027919e-05, + "loss": 0.1054, + "step": 345930 + }, + { + "epoch": 0.77, + "learning_rate": 1.1433524977069864e-05, + "loss": 0.1048, + "step": 345940 + }, + { + "epoch": 0.77, + "learning_rate": 1.143240643386054e-05, + "loss": 0.1057, + "step": 345950 + }, + { + "epoch": 0.77, + "learning_rate": 1.1431287890651217e-05, + "loss": 0.1027, + "step": 345960 + }, + { + "epoch": 0.77, + "learning_rate": 1.1430169347441893e-05, + "loss": 0.0966, + "step": 345970 + }, + { + "epoch": 0.77, + "learning_rate": 1.1429050804232568e-05, + "loss": 0.1033, + "step": 345980 + }, + { + "epoch": 0.77, + "learning_rate": 1.1427932261023244e-05, + "loss": 0.1019, + "step": 345990 + }, + { + "epoch": 0.77, + "learning_rate": 1.142681371781392e-05, + "loss": 0.1047, + "step": 346000 + }, + { + "epoch": 0.77, + "learning_rate": 1.1425695174604596e-05, + "loss": 0.1001, + "step": 346010 + }, + { + "epoch": 0.77, + "learning_rate": 1.142457663139527e-05, + "loss": 0.1091, + "step": 346020 + }, + { + "epoch": 0.77, + "learning_rate": 1.1423458088185947e-05, + "loss": 0.101, + "step": 346030 + }, + { + "epoch": 0.77, + "learning_rate": 1.1422339544976623e-05, + "loss": 0.1, + "step": 346040 + }, + { + "epoch": 0.77, + "learning_rate": 1.14212210017673e-05, + "loss": 0.1047, + "step": 346050 + }, + { + "epoch": 0.77, + "learning_rate": 1.1420102458557974e-05, + "loss": 0.1022, + "step": 346060 + }, + { + "epoch": 0.77, + "learning_rate": 1.141898391534865e-05, + "loss": 0.102, + "step": 346070 + }, + { + "epoch": 0.77, + "learning_rate": 1.1417865372139326e-05, + "loss": 0.1039, + "step": 346080 + }, + { + "epoch": 0.77, + "learning_rate": 1.1416746828930003e-05, + "loss": 0.1014, + "step": 346090 + }, + { + "epoch": 0.77, + "learning_rate": 1.1415628285720679e-05, + "loss": 0.1031, + "step": 346100 + }, + { + "epoch": 0.77, + "learning_rate": 1.1414509742511353e-05, + "loss": 0.1047, + "step": 346110 + }, + { + "epoch": 0.77, + "learning_rate": 1.141339119930203e-05, + "loss": 0.1034, + "step": 346120 + }, + { + "epoch": 0.77, + "learning_rate": 1.1412272656092706e-05, + "loss": 0.1056, + "step": 346130 + }, + { + "epoch": 0.77, + "learning_rate": 1.141115411288338e-05, + "loss": 0.0993, + "step": 346140 + }, + { + "epoch": 0.77, + "learning_rate": 1.1410035569674057e-05, + "loss": 0.1018, + "step": 346150 + }, + { + "epoch": 0.77, + "learning_rate": 1.1408917026464733e-05, + "loss": 0.1051, + "step": 346160 + }, + { + "epoch": 0.77, + "learning_rate": 1.140779848325541e-05, + "loss": 0.102, + "step": 346170 + }, + { + "epoch": 0.77, + "learning_rate": 1.1406679940046085e-05, + "loss": 0.1041, + "step": 346180 + }, + { + "epoch": 0.77, + "learning_rate": 1.140556139683676e-05, + "loss": 0.1008, + "step": 346190 + }, + { + "epoch": 0.77, + "learning_rate": 1.1404442853627436e-05, + "loss": 0.1024, + "step": 346200 + }, + { + "epoch": 0.77, + "learning_rate": 1.1403324310418112e-05, + "loss": 0.1005, + "step": 346210 + }, + { + "epoch": 0.77, + "learning_rate": 1.1402205767208787e-05, + "loss": 0.0987, + "step": 346220 + }, + { + "epoch": 0.77, + "learning_rate": 1.1401087223999463e-05, + "loss": 0.1043, + "step": 346230 + }, + { + "epoch": 0.77, + "learning_rate": 1.139996868079014e-05, + "loss": 0.103, + "step": 346240 + }, + { + "epoch": 0.77, + "learning_rate": 1.1398850137580814e-05, + "loss": 0.0972, + "step": 346250 + }, + { + "epoch": 0.77, + "learning_rate": 1.1397731594371492e-05, + "loss": 0.1008, + "step": 346260 + }, + { + "epoch": 0.77, + "learning_rate": 1.1396613051162166e-05, + "loss": 0.1028, + "step": 346270 + }, + { + "epoch": 0.77, + "learning_rate": 1.1395494507952843e-05, + "loss": 0.1061, + "step": 346280 + }, + { + "epoch": 0.77, + "learning_rate": 1.1394375964743519e-05, + "loss": 0.1006, + "step": 346290 + }, + { + "epoch": 0.77, + "learning_rate": 1.1393257421534193e-05, + "loss": 0.0974, + "step": 346300 + }, + { + "epoch": 0.77, + "learning_rate": 1.1392138878324871e-05, + "loss": 0.098, + "step": 346310 + }, + { + "epoch": 0.77, + "learning_rate": 1.1391020335115546e-05, + "loss": 0.102, + "step": 346320 + }, + { + "epoch": 0.77, + "learning_rate": 1.138990179190622e-05, + "loss": 0.1034, + "step": 346330 + }, + { + "epoch": 0.77, + "learning_rate": 1.1388783248696898e-05, + "loss": 0.1018, + "step": 346340 + }, + { + "epoch": 0.77, + "learning_rate": 1.1387664705487573e-05, + "loss": 0.1006, + "step": 346350 + }, + { + "epoch": 0.77, + "learning_rate": 1.138654616227825e-05, + "loss": 0.1012, + "step": 346360 + }, + { + "epoch": 0.77, + "learning_rate": 1.1385427619068925e-05, + "loss": 0.102, + "step": 346370 + }, + { + "epoch": 0.77, + "learning_rate": 1.13843090758596e-05, + "loss": 0.1043, + "step": 346380 + }, + { + "epoch": 0.77, + "learning_rate": 1.1383190532650278e-05, + "loss": 0.102, + "step": 346390 + }, + { + "epoch": 0.77, + "learning_rate": 1.1382071989440952e-05, + "loss": 0.1026, + "step": 346400 + }, + { + "epoch": 0.77, + "learning_rate": 1.1380953446231627e-05, + "loss": 0.0995, + "step": 346410 + }, + { + "epoch": 0.77, + "learning_rate": 1.1379834903022305e-05, + "loss": 0.1025, + "step": 346420 + }, + { + "epoch": 0.77, + "learning_rate": 1.137871635981298e-05, + "loss": 0.1017, + "step": 346430 + }, + { + "epoch": 0.77, + "learning_rate": 1.1377597816603656e-05, + "loss": 0.1032, + "step": 346440 + }, + { + "epoch": 0.77, + "learning_rate": 1.1376479273394332e-05, + "loss": 0.1037, + "step": 346450 + }, + { + "epoch": 0.77, + "learning_rate": 1.1375360730185006e-05, + "loss": 0.1002, + "step": 346460 + }, + { + "epoch": 0.77, + "learning_rate": 1.1374242186975684e-05, + "loss": 0.1075, + "step": 346470 + }, + { + "epoch": 0.77, + "learning_rate": 1.1373123643766359e-05, + "loss": 0.1025, + "step": 346480 + }, + { + "epoch": 0.77, + "learning_rate": 1.1372005100557035e-05, + "loss": 0.1022, + "step": 346490 + }, + { + "epoch": 0.77, + "learning_rate": 1.1370886557347711e-05, + "loss": 0.1026, + "step": 346500 + }, + { + "epoch": 0.77, + "learning_rate": 1.1369768014138386e-05, + "loss": 0.1036, + "step": 346510 + }, + { + "epoch": 0.77, + "learning_rate": 1.1368649470929064e-05, + "loss": 0.102, + "step": 346520 + }, + { + "epoch": 0.77, + "learning_rate": 1.1367530927719738e-05, + "loss": 0.1006, + "step": 346530 + }, + { + "epoch": 0.77, + "learning_rate": 1.1366412384510413e-05, + "loss": 0.0986, + "step": 346540 + }, + { + "epoch": 0.77, + "learning_rate": 1.136529384130109e-05, + "loss": 0.1021, + "step": 346550 + }, + { + "epoch": 0.77, + "learning_rate": 1.1364175298091765e-05, + "loss": 0.1001, + "step": 346560 + }, + { + "epoch": 0.77, + "learning_rate": 1.1363056754882442e-05, + "loss": 0.1038, + "step": 346570 + }, + { + "epoch": 0.77, + "learning_rate": 1.1361938211673118e-05, + "loss": 0.1047, + "step": 346580 + }, + { + "epoch": 0.77, + "learning_rate": 1.1360819668463792e-05, + "loss": 0.1022, + "step": 346590 + }, + { + "epoch": 0.77, + "learning_rate": 1.135970112525447e-05, + "loss": 0.1054, + "step": 346600 + }, + { + "epoch": 0.77, + "learning_rate": 1.1358582582045145e-05, + "loss": 0.1013, + "step": 346610 + }, + { + "epoch": 0.77, + "learning_rate": 1.1357464038835821e-05, + "loss": 0.101, + "step": 346620 + }, + { + "epoch": 0.77, + "learning_rate": 1.1356345495626497e-05, + "loss": 0.1033, + "step": 346630 + }, + { + "epoch": 0.77, + "learning_rate": 1.1355226952417172e-05, + "loss": 0.1027, + "step": 346640 + }, + { + "epoch": 0.77, + "learning_rate": 1.135422026352878e-05, + "loss": 0.1012, + "step": 346650 + }, + { + "epoch": 0.77, + "learning_rate": 1.1353101720319457e-05, + "loss": 0.1022, + "step": 346660 + }, + { + "epoch": 0.77, + "learning_rate": 1.1351983177110133e-05, + "loss": 0.102, + "step": 346670 + }, + { + "epoch": 0.77, + "learning_rate": 1.1350864633900808e-05, + "loss": 0.1043, + "step": 346680 + }, + { + "epoch": 0.77, + "learning_rate": 1.1349746090691484e-05, + "loss": 0.1021, + "step": 346690 + }, + { + "epoch": 0.77, + "learning_rate": 1.134862754748216e-05, + "loss": 0.1019, + "step": 346700 + }, + { + "epoch": 0.77, + "learning_rate": 1.1347509004272835e-05, + "loss": 0.1007, + "step": 346710 + }, + { + "epoch": 0.77, + "learning_rate": 1.1346390461063511e-05, + "loss": 0.1, + "step": 346720 + }, + { + "epoch": 0.77, + "learning_rate": 1.1345271917854187e-05, + "loss": 0.1032, + "step": 346730 + }, + { + "epoch": 0.77, + "learning_rate": 1.1344153374644863e-05, + "loss": 0.1037, + "step": 346740 + }, + { + "epoch": 0.77, + "learning_rate": 1.134303483143554e-05, + "loss": 0.1033, + "step": 346750 + }, + { + "epoch": 0.77, + "learning_rate": 1.1341916288226214e-05, + "loss": 0.1005, + "step": 346760 + }, + { + "epoch": 0.77, + "learning_rate": 1.134079774501689e-05, + "loss": 0.1036, + "step": 346770 + }, + { + "epoch": 0.77, + "learning_rate": 1.1339679201807567e-05, + "loss": 0.0972, + "step": 346780 + }, + { + "epoch": 0.77, + "learning_rate": 1.1338560658598243e-05, + "loss": 0.0994, + "step": 346790 + }, + { + "epoch": 0.77, + "learning_rate": 1.1337442115388917e-05, + "loss": 0.1032, + "step": 346800 + }, + { + "epoch": 0.77, + "learning_rate": 1.1336323572179594e-05, + "loss": 0.1034, + "step": 346810 + }, + { + "epoch": 0.77, + "learning_rate": 1.133520502897027e-05, + "loss": 0.1023, + "step": 346820 + }, + { + "epoch": 0.77, + "learning_rate": 1.1334086485760946e-05, + "loss": 0.0999, + "step": 346830 + }, + { + "epoch": 0.77, + "learning_rate": 1.133296794255162e-05, + "loss": 0.1016, + "step": 346840 + }, + { + "epoch": 0.77, + "learning_rate": 1.1331849399342297e-05, + "loss": 0.102, + "step": 346850 + }, + { + "epoch": 0.77, + "learning_rate": 1.1330730856132973e-05, + "loss": 0.1059, + "step": 346860 + }, + { + "epoch": 0.77, + "learning_rate": 1.132961231292365e-05, + "loss": 0.1014, + "step": 346870 + }, + { + "epoch": 0.77, + "learning_rate": 1.1328493769714324e-05, + "loss": 0.1035, + "step": 346880 + }, + { + "epoch": 0.77, + "learning_rate": 1.1327375226505e-05, + "loss": 0.1035, + "step": 346890 + }, + { + "epoch": 0.77, + "learning_rate": 1.1326256683295676e-05, + "loss": 0.103, + "step": 346900 + }, + { + "epoch": 0.77, + "learning_rate": 1.1325138140086353e-05, + "loss": 0.1033, + "step": 346910 + }, + { + "epoch": 0.77, + "learning_rate": 1.1324019596877029e-05, + "loss": 0.1055, + "step": 346920 + }, + { + "epoch": 0.77, + "learning_rate": 1.1322901053667703e-05, + "loss": 0.1023, + "step": 346930 + }, + { + "epoch": 0.77, + "learning_rate": 1.132178251045838e-05, + "loss": 0.1055, + "step": 346940 + }, + { + "epoch": 0.77, + "learning_rate": 1.1320663967249056e-05, + "loss": 0.1, + "step": 346950 + }, + { + "epoch": 0.77, + "learning_rate": 1.131954542403973e-05, + "loss": 0.1018, + "step": 346960 + }, + { + "epoch": 0.77, + "learning_rate": 1.1318426880830407e-05, + "loss": 0.1071, + "step": 346970 + }, + { + "epoch": 0.77, + "learning_rate": 1.1317308337621083e-05, + "loss": 0.1024, + "step": 346980 + }, + { + "epoch": 0.77, + "learning_rate": 1.1316189794411759e-05, + "loss": 0.1009, + "step": 346990 + }, + { + "epoch": 0.77, + "learning_rate": 1.1315071251202435e-05, + "loss": 0.1011, + "step": 347000 + }, + { + "epoch": 0.77, + "learning_rate": 1.131395270799311e-05, + "loss": 0.1009, + "step": 347010 + }, + { + "epoch": 0.77, + "learning_rate": 1.1312834164783786e-05, + "loss": 0.1023, + "step": 347020 + }, + { + "epoch": 0.77, + "learning_rate": 1.1311715621574462e-05, + "loss": 0.1009, + "step": 347030 + }, + { + "epoch": 0.77, + "learning_rate": 1.1310597078365137e-05, + "loss": 0.1035, + "step": 347040 + }, + { + "epoch": 0.77, + "learning_rate": 1.1309478535155813e-05, + "loss": 0.1021, + "step": 347050 + }, + { + "epoch": 0.77, + "learning_rate": 1.130835999194649e-05, + "loss": 0.1023, + "step": 347060 + }, + { + "epoch": 0.77, + "learning_rate": 1.1307241448737166e-05, + "loss": 0.1027, + "step": 347070 + }, + { + "epoch": 0.77, + "learning_rate": 1.1306122905527842e-05, + "loss": 0.106, + "step": 347080 + }, + { + "epoch": 0.77, + "learning_rate": 1.1305004362318516e-05, + "loss": 0.1048, + "step": 347090 + }, + { + "epoch": 0.77, + "learning_rate": 1.1303885819109193e-05, + "loss": 0.0987, + "step": 347100 + }, + { + "epoch": 0.77, + "learning_rate": 1.1302767275899869e-05, + "loss": 0.1023, + "step": 347110 + }, + { + "epoch": 0.77, + "learning_rate": 1.1301648732690543e-05, + "loss": 0.1035, + "step": 347120 + }, + { + "epoch": 0.77, + "learning_rate": 1.1300530189481221e-05, + "loss": 0.1048, + "step": 347130 + }, + { + "epoch": 0.77, + "learning_rate": 1.1299411646271896e-05, + "loss": 0.1055, + "step": 347140 + }, + { + "epoch": 0.77, + "learning_rate": 1.1298293103062572e-05, + "loss": 0.1026, + "step": 347150 + }, + { + "epoch": 0.77, + "learning_rate": 1.1297174559853248e-05, + "loss": 0.1015, + "step": 347160 + }, + { + "epoch": 0.77, + "learning_rate": 1.1296056016643923e-05, + "loss": 0.1046, + "step": 347170 + }, + { + "epoch": 0.77, + "learning_rate": 1.1294937473434599e-05, + "loss": 0.1064, + "step": 347180 + }, + { + "epoch": 0.77, + "learning_rate": 1.1293818930225275e-05, + "loss": 0.1042, + "step": 347190 + }, + { + "epoch": 0.77, + "learning_rate": 1.129270038701595e-05, + "loss": 0.1023, + "step": 347200 + }, + { + "epoch": 0.78, + "learning_rate": 1.1291581843806628e-05, + "loss": 0.103, + "step": 347210 + }, + { + "epoch": 0.78, + "learning_rate": 1.1290463300597302e-05, + "loss": 0.1036, + "step": 347220 + }, + { + "epoch": 0.78, + "learning_rate": 1.1289344757387978e-05, + "loss": 0.1, + "step": 347230 + }, + { + "epoch": 0.78, + "learning_rate": 1.1288226214178655e-05, + "loss": 0.1056, + "step": 347240 + }, + { + "epoch": 0.78, + "learning_rate": 1.128710767096933e-05, + "loss": 0.0997, + "step": 347250 + }, + { + "epoch": 0.78, + "learning_rate": 1.1285989127760007e-05, + "loss": 0.103, + "step": 347260 + }, + { + "epoch": 0.78, + "learning_rate": 1.1284870584550682e-05, + "loss": 0.0971, + "step": 347270 + }, + { + "epoch": 0.78, + "learning_rate": 1.1283752041341356e-05, + "loss": 0.1004, + "step": 347280 + }, + { + "epoch": 0.78, + "learning_rate": 1.1282633498132034e-05, + "loss": 0.1032, + "step": 347290 + }, + { + "epoch": 0.78, + "learning_rate": 1.1281514954922709e-05, + "loss": 0.0975, + "step": 347300 + }, + { + "epoch": 0.78, + "learning_rate": 1.1280396411713385e-05, + "loss": 0.0982, + "step": 347310 + }, + { + "epoch": 0.78, + "learning_rate": 1.1279277868504061e-05, + "loss": 0.0989, + "step": 347320 + }, + { + "epoch": 0.78, + "learning_rate": 1.1278159325294736e-05, + "loss": 0.1057, + "step": 347330 + }, + { + "epoch": 0.78, + "learning_rate": 1.1277040782085414e-05, + "loss": 0.1053, + "step": 347340 + }, + { + "epoch": 0.78, + "learning_rate": 1.1275922238876088e-05, + "loss": 0.1076, + "step": 347350 + }, + { + "epoch": 0.78, + "learning_rate": 1.1274803695666763e-05, + "loss": 0.1014, + "step": 347360 + }, + { + "epoch": 0.78, + "learning_rate": 1.127368515245744e-05, + "loss": 0.1001, + "step": 347370 + }, + { + "epoch": 0.78, + "learning_rate": 1.1272566609248115e-05, + "loss": 0.1012, + "step": 347380 + }, + { + "epoch": 0.78, + "learning_rate": 1.1271448066038791e-05, + "loss": 0.102, + "step": 347390 + }, + { + "epoch": 0.78, + "learning_rate": 1.1270329522829468e-05, + "loss": 0.1047, + "step": 347400 + }, + { + "epoch": 0.78, + "learning_rate": 1.1269210979620142e-05, + "loss": 0.1026, + "step": 347410 + }, + { + "epoch": 0.78, + "learning_rate": 1.126809243641082e-05, + "loss": 0.1074, + "step": 347420 + }, + { + "epoch": 0.78, + "learning_rate": 1.1266973893201495e-05, + "loss": 0.0999, + "step": 347430 + }, + { + "epoch": 0.78, + "learning_rate": 1.1265855349992171e-05, + "loss": 0.1041, + "step": 347440 + }, + { + "epoch": 0.78, + "learning_rate": 1.1264736806782847e-05, + "loss": 0.1023, + "step": 347450 + }, + { + "epoch": 0.78, + "learning_rate": 1.1263618263573522e-05, + "loss": 0.1065, + "step": 347460 + }, + { + "epoch": 0.78, + "learning_rate": 1.12624997203642e-05, + "loss": 0.1025, + "step": 347470 + }, + { + "epoch": 0.78, + "learning_rate": 1.1261381177154874e-05, + "loss": 0.0989, + "step": 347480 + }, + { + "epoch": 0.78, + "learning_rate": 1.1260262633945549e-05, + "loss": 0.1001, + "step": 347490 + }, + { + "epoch": 0.78, + "learning_rate": 1.1259144090736227e-05, + "loss": 0.1028, + "step": 347500 + }, + { + "epoch": 0.78, + "learning_rate": 1.1258025547526901e-05, + "loss": 0.1001, + "step": 347510 + }, + { + "epoch": 0.78, + "learning_rate": 1.1256907004317577e-05, + "loss": 0.1019, + "step": 347520 + }, + { + "epoch": 0.78, + "learning_rate": 1.1255788461108254e-05, + "loss": 0.1012, + "step": 347530 + }, + { + "epoch": 0.78, + "learning_rate": 1.1254669917898928e-05, + "loss": 0.1034, + "step": 347540 + }, + { + "epoch": 0.78, + "learning_rate": 1.1253551374689606e-05, + "loss": 0.1023, + "step": 347550 + }, + { + "epoch": 0.78, + "learning_rate": 1.125243283148028e-05, + "loss": 0.102, + "step": 347560 + }, + { + "epoch": 0.78, + "learning_rate": 1.1251314288270957e-05, + "loss": 0.102, + "step": 347570 + }, + { + "epoch": 0.78, + "learning_rate": 1.1250195745061633e-05, + "loss": 0.0953, + "step": 347580 + }, + { + "epoch": 0.78, + "learning_rate": 1.1249077201852308e-05, + "loss": 0.1005, + "step": 347590 + }, + { + "epoch": 0.78, + "learning_rate": 1.1247958658642984e-05, + "loss": 0.1017, + "step": 347600 + }, + { + "epoch": 0.78, + "learning_rate": 1.124684011543366e-05, + "loss": 0.1097, + "step": 347610 + }, + { + "epoch": 0.78, + "learning_rate": 1.1245721572224335e-05, + "loss": 0.1036, + "step": 347620 + }, + { + "epoch": 0.78, + "learning_rate": 1.1244603029015013e-05, + "loss": 0.0994, + "step": 347630 + }, + { + "epoch": 0.78, + "learning_rate": 1.1243484485805687e-05, + "loss": 0.1015, + "step": 347640 + }, + { + "epoch": 0.78, + "learning_rate": 1.1242365942596363e-05, + "loss": 0.1039, + "step": 347650 + }, + { + "epoch": 0.78, + "learning_rate": 1.124124739938704e-05, + "loss": 0.1027, + "step": 347660 + }, + { + "epoch": 0.78, + "learning_rate": 1.1240128856177714e-05, + "loss": 0.0988, + "step": 347670 + }, + { + "epoch": 0.78, + "learning_rate": 1.123901031296839e-05, + "loss": 0.1007, + "step": 347680 + }, + { + "epoch": 0.78, + "learning_rate": 1.1237891769759067e-05, + "loss": 0.1008, + "step": 347690 + }, + { + "epoch": 0.78, + "learning_rate": 1.1236773226549741e-05, + "loss": 0.1061, + "step": 347700 + }, + { + "epoch": 0.78, + "learning_rate": 1.1235654683340419e-05, + "loss": 0.1018, + "step": 347710 + }, + { + "epoch": 0.78, + "learning_rate": 1.1234536140131094e-05, + "loss": 0.1051, + "step": 347720 + }, + { + "epoch": 0.78, + "learning_rate": 1.123341759692177e-05, + "loss": 0.1036, + "step": 347730 + }, + { + "epoch": 0.78, + "learning_rate": 1.1232299053712446e-05, + "loss": 0.1044, + "step": 347740 + }, + { + "epoch": 0.78, + "learning_rate": 1.123118051050312e-05, + "loss": 0.1036, + "step": 347750 + }, + { + "epoch": 0.78, + "learning_rate": 1.1230061967293797e-05, + "loss": 0.1047, + "step": 347760 + }, + { + "epoch": 0.78, + "learning_rate": 1.1228943424084473e-05, + "loss": 0.0958, + "step": 347770 + }, + { + "epoch": 0.78, + "learning_rate": 1.122782488087515e-05, + "loss": 0.1002, + "step": 347780 + }, + { + "epoch": 0.78, + "learning_rate": 1.1226706337665826e-05, + "loss": 0.1051, + "step": 347790 + }, + { + "epoch": 0.78, + "learning_rate": 1.12255877944565e-05, + "loss": 0.1042, + "step": 347800 + }, + { + "epoch": 0.78, + "learning_rate": 1.1224469251247176e-05, + "loss": 0.102, + "step": 347810 + }, + { + "epoch": 0.78, + "learning_rate": 1.1223350708037853e-05, + "loss": 0.1024, + "step": 347820 + }, + { + "epoch": 0.78, + "learning_rate": 1.1222232164828527e-05, + "loss": 0.1011, + "step": 347830 + }, + { + "epoch": 0.78, + "learning_rate": 1.1221113621619203e-05, + "loss": 0.105, + "step": 347840 + }, + { + "epoch": 0.78, + "learning_rate": 1.121999507840988e-05, + "loss": 0.1027, + "step": 347850 + }, + { + "epoch": 0.78, + "learning_rate": 1.1218876535200556e-05, + "loss": 0.1032, + "step": 347860 + }, + { + "epoch": 0.78, + "learning_rate": 1.1217757991991232e-05, + "loss": 0.1038, + "step": 347870 + }, + { + "epoch": 0.78, + "learning_rate": 1.1216639448781907e-05, + "loss": 0.1049, + "step": 347880 + }, + { + "epoch": 0.78, + "learning_rate": 1.1215520905572583e-05, + "loss": 0.1019, + "step": 347890 + }, + { + "epoch": 0.78, + "learning_rate": 1.1214402362363259e-05, + "loss": 0.1018, + "step": 347900 + }, + { + "epoch": 0.78, + "learning_rate": 1.1213283819153934e-05, + "loss": 0.0996, + "step": 347910 + }, + { + "epoch": 0.78, + "learning_rate": 1.121216527594461e-05, + "loss": 0.1018, + "step": 347920 + }, + { + "epoch": 0.78, + "learning_rate": 1.1211046732735286e-05, + "loss": 0.1051, + "step": 347930 + }, + { + "epoch": 0.78, + "learning_rate": 1.1209928189525962e-05, + "loss": 0.1043, + "step": 347940 + }, + { + "epoch": 0.78, + "learning_rate": 1.1208809646316638e-05, + "loss": 0.1012, + "step": 347950 + }, + { + "epoch": 0.78, + "learning_rate": 1.1207691103107313e-05, + "loss": 0.102, + "step": 347960 + }, + { + "epoch": 0.78, + "learning_rate": 1.120657255989799e-05, + "loss": 0.1045, + "step": 347970 + }, + { + "epoch": 0.78, + "learning_rate": 1.1205454016688665e-05, + "loss": 0.1043, + "step": 347980 + }, + { + "epoch": 0.78, + "learning_rate": 1.1204335473479342e-05, + "loss": 0.0982, + "step": 347990 + }, + { + "epoch": 0.78, + "learning_rate": 1.1203216930270016e-05, + "loss": 0.1022, + "step": 348000 + }, + { + "epoch": 0.78, + "learning_rate": 1.1202098387060692e-05, + "loss": 0.099, + "step": 348010 + }, + { + "epoch": 0.78, + "learning_rate": 1.1200979843851369e-05, + "loss": 0.1024, + "step": 348020 + }, + { + "epoch": 0.78, + "learning_rate": 1.1199861300642045e-05, + "loss": 0.1039, + "step": 348030 + }, + { + "epoch": 0.78, + "learning_rate": 1.119874275743272e-05, + "loss": 0.0998, + "step": 348040 + }, + { + "epoch": 0.78, + "learning_rate": 1.1197624214223396e-05, + "loss": 0.1017, + "step": 348050 + }, + { + "epoch": 0.78, + "learning_rate": 1.1196505671014072e-05, + "loss": 0.1042, + "step": 348060 + }, + { + "epoch": 0.78, + "learning_rate": 1.1195387127804748e-05, + "loss": 0.1025, + "step": 348070 + }, + { + "epoch": 0.78, + "learning_rate": 1.1194268584595423e-05, + "loss": 0.106, + "step": 348080 + }, + { + "epoch": 0.78, + "learning_rate": 1.1193150041386099e-05, + "loss": 0.0998, + "step": 348090 + }, + { + "epoch": 0.78, + "learning_rate": 1.1192031498176775e-05, + "loss": 0.1079, + "step": 348100 + }, + { + "epoch": 0.78, + "learning_rate": 1.1190912954967451e-05, + "loss": 0.1063, + "step": 348110 + }, + { + "epoch": 0.78, + "learning_rate": 1.1189794411758128e-05, + "loss": 0.1029, + "step": 348120 + }, + { + "epoch": 0.78, + "learning_rate": 1.1188675868548802e-05, + "loss": 0.1028, + "step": 348130 + }, + { + "epoch": 0.78, + "learning_rate": 1.1187557325339478e-05, + "loss": 0.1047, + "step": 348140 + }, + { + "epoch": 0.78, + "learning_rate": 1.1186438782130155e-05, + "loss": 0.0994, + "step": 348150 + }, + { + "epoch": 0.78, + "learning_rate": 1.118532023892083e-05, + "loss": 0.1028, + "step": 348160 + }, + { + "epoch": 0.78, + "learning_rate": 1.1184201695711505e-05, + "loss": 0.1023, + "step": 348170 + }, + { + "epoch": 0.78, + "learning_rate": 1.1183083152502182e-05, + "loss": 0.1022, + "step": 348180 + }, + { + "epoch": 0.78, + "learning_rate": 1.1181964609292858e-05, + "loss": 0.0979, + "step": 348190 + }, + { + "epoch": 0.78, + "learning_rate": 1.1180846066083534e-05, + "loss": 0.1028, + "step": 348200 + }, + { + "epoch": 0.78, + "learning_rate": 1.1179727522874209e-05, + "loss": 0.1045, + "step": 348210 + }, + { + "epoch": 0.78, + "learning_rate": 1.1178608979664885e-05, + "loss": 0.1039, + "step": 348220 + }, + { + "epoch": 0.78, + "learning_rate": 1.1177490436455561e-05, + "loss": 0.1072, + "step": 348230 + }, + { + "epoch": 0.78, + "learning_rate": 1.1176371893246236e-05, + "loss": 0.1078, + "step": 348240 + }, + { + "epoch": 0.78, + "learning_rate": 1.1175253350036912e-05, + "loss": 0.1025, + "step": 348250 + }, + { + "epoch": 0.78, + "learning_rate": 1.1174134806827588e-05, + "loss": 0.1008, + "step": 348260 + }, + { + "epoch": 0.78, + "learning_rate": 1.1173016263618264e-05, + "loss": 0.1055, + "step": 348270 + }, + { + "epoch": 0.78, + "learning_rate": 1.117189772040894e-05, + "loss": 0.105, + "step": 348280 + }, + { + "epoch": 0.78, + "learning_rate": 1.1170779177199615e-05, + "loss": 0.1043, + "step": 348290 + }, + { + "epoch": 0.78, + "learning_rate": 1.1169660633990291e-05, + "loss": 0.0987, + "step": 348300 + }, + { + "epoch": 0.78, + "learning_rate": 1.1168542090780968e-05, + "loss": 0.1023, + "step": 348310 + }, + { + "epoch": 0.78, + "learning_rate": 1.1167423547571642e-05, + "loss": 0.1012, + "step": 348320 + }, + { + "epoch": 0.78, + "learning_rate": 1.116630500436232e-05, + "loss": 0.097, + "step": 348330 + }, + { + "epoch": 0.78, + "learning_rate": 1.1165186461152995e-05, + "loss": 0.1112, + "step": 348340 + }, + { + "epoch": 0.78, + "learning_rate": 1.1164067917943671e-05, + "loss": 0.101, + "step": 348350 + }, + { + "epoch": 0.78, + "learning_rate": 1.1162949374734347e-05, + "loss": 0.1052, + "step": 348360 + }, + { + "epoch": 0.78, + "learning_rate": 1.1161830831525022e-05, + "loss": 0.1026, + "step": 348370 + }, + { + "epoch": 0.78, + "learning_rate": 1.1160712288315698e-05, + "loss": 0.1034, + "step": 348380 + }, + { + "epoch": 0.78, + "learning_rate": 1.1159593745106374e-05, + "loss": 0.0979, + "step": 348390 + }, + { + "epoch": 0.78, + "learning_rate": 1.1158475201897049e-05, + "loss": 0.1059, + "step": 348400 + }, + { + "epoch": 0.78, + "learning_rate": 1.1157356658687727e-05, + "loss": 0.0993, + "step": 348410 + }, + { + "epoch": 0.78, + "learning_rate": 1.1156238115478401e-05, + "loss": 0.0981, + "step": 348420 + }, + { + "epoch": 0.78, + "learning_rate": 1.1155119572269077e-05, + "loss": 0.1046, + "step": 348430 + }, + { + "epoch": 0.78, + "learning_rate": 1.1154001029059754e-05, + "loss": 0.1015, + "step": 348440 + }, + { + "epoch": 0.78, + "learning_rate": 1.1152882485850428e-05, + "loss": 0.0999, + "step": 348450 + }, + { + "epoch": 0.78, + "learning_rate": 1.1151763942641106e-05, + "loss": 0.1013, + "step": 348460 + }, + { + "epoch": 0.78, + "learning_rate": 1.115064539943178e-05, + "loss": 0.1055, + "step": 348470 + }, + { + "epoch": 0.78, + "learning_rate": 1.1149526856222455e-05, + "loss": 0.1023, + "step": 348480 + }, + { + "epoch": 0.78, + "learning_rate": 1.1148408313013133e-05, + "loss": 0.1034, + "step": 348490 + }, + { + "epoch": 0.78, + "learning_rate": 1.1147289769803808e-05, + "loss": 0.1021, + "step": 348500 + }, + { + "epoch": 0.78, + "learning_rate": 1.1146171226594484e-05, + "loss": 0.1015, + "step": 348510 + }, + { + "epoch": 0.78, + "learning_rate": 1.114505268338516e-05, + "loss": 0.1031, + "step": 348520 + }, + { + "epoch": 0.78, + "learning_rate": 1.1143934140175835e-05, + "loss": 0.1031, + "step": 348530 + }, + { + "epoch": 0.78, + "learning_rate": 1.1142815596966513e-05, + "loss": 0.1048, + "step": 348540 + }, + { + "epoch": 0.78, + "learning_rate": 1.1141697053757187e-05, + "loss": 0.1021, + "step": 348550 + }, + { + "epoch": 0.78, + "learning_rate": 1.1140578510547862e-05, + "loss": 0.1024, + "step": 348560 + }, + { + "epoch": 0.78, + "learning_rate": 1.113945996733854e-05, + "loss": 0.1017, + "step": 348570 + }, + { + "epoch": 0.78, + "learning_rate": 1.1138341424129214e-05, + "loss": 0.0994, + "step": 348580 + }, + { + "epoch": 0.78, + "learning_rate": 1.113722288091989e-05, + "loss": 0.1018, + "step": 348590 + }, + { + "epoch": 0.78, + "learning_rate": 1.1136104337710567e-05, + "loss": 0.1033, + "step": 348600 + }, + { + "epoch": 0.78, + "learning_rate": 1.1134985794501241e-05, + "loss": 0.0981, + "step": 348610 + }, + { + "epoch": 0.78, + "learning_rate": 1.1133867251291919e-05, + "loss": 0.1014, + "step": 348620 + }, + { + "epoch": 0.78, + "learning_rate": 1.1132748708082594e-05, + "loss": 0.104, + "step": 348630 + }, + { + "epoch": 0.78, + "learning_rate": 1.113163016487327e-05, + "loss": 0.1015, + "step": 348640 + }, + { + "epoch": 0.78, + "learning_rate": 1.1130511621663946e-05, + "loss": 0.1032, + "step": 348650 + }, + { + "epoch": 0.78, + "learning_rate": 1.112939307845462e-05, + "loss": 0.1024, + "step": 348660 + }, + { + "epoch": 0.78, + "learning_rate": 1.1128274535245299e-05, + "loss": 0.1029, + "step": 348670 + }, + { + "epoch": 0.78, + "learning_rate": 1.1127155992035973e-05, + "loss": 0.1, + "step": 348680 + }, + { + "epoch": 0.78, + "learning_rate": 1.1126149303147582e-05, + "loss": 0.1015, + "step": 348690 + }, + { + "epoch": 0.78, + "learning_rate": 1.1125030759938256e-05, + "loss": 0.1, + "step": 348700 + }, + { + "epoch": 0.78, + "learning_rate": 1.1123912216728933e-05, + "loss": 0.1019, + "step": 348710 + }, + { + "epoch": 0.78, + "learning_rate": 1.1122793673519609e-05, + "loss": 0.1039, + "step": 348720 + }, + { + "epoch": 0.78, + "learning_rate": 1.1121675130310285e-05, + "loss": 0.1021, + "step": 348730 + }, + { + "epoch": 0.78, + "learning_rate": 1.1120556587100961e-05, + "loss": 0.0993, + "step": 348740 + }, + { + "epoch": 0.78, + "learning_rate": 1.1119438043891636e-05, + "loss": 0.1028, + "step": 348750 + }, + { + "epoch": 0.78, + "learning_rate": 1.1118319500682312e-05, + "loss": 0.1041, + "step": 348760 + }, + { + "epoch": 0.78, + "learning_rate": 1.1117200957472988e-05, + "loss": 0.103, + "step": 348770 + }, + { + "epoch": 0.78, + "learning_rate": 1.1116082414263663e-05, + "loss": 0.1082, + "step": 348780 + }, + { + "epoch": 0.78, + "learning_rate": 1.1114963871054339e-05, + "loss": 0.1047, + "step": 348790 + }, + { + "epoch": 0.78, + "learning_rate": 1.1113845327845015e-05, + "loss": 0.0989, + "step": 348800 + }, + { + "epoch": 0.78, + "learning_rate": 1.1112726784635692e-05, + "loss": 0.0981, + "step": 348810 + }, + { + "epoch": 0.78, + "learning_rate": 1.1111608241426368e-05, + "loss": 0.0999, + "step": 348820 + }, + { + "epoch": 0.78, + "learning_rate": 1.1110489698217042e-05, + "loss": 0.1039, + "step": 348830 + }, + { + "epoch": 0.78, + "learning_rate": 1.1109371155007719e-05, + "loss": 0.1002, + "step": 348840 + }, + { + "epoch": 0.78, + "learning_rate": 1.1108252611798395e-05, + "loss": 0.1009, + "step": 348850 + }, + { + "epoch": 0.78, + "learning_rate": 1.110713406858907e-05, + "loss": 0.1053, + "step": 348860 + }, + { + "epoch": 0.78, + "learning_rate": 1.1106015525379746e-05, + "loss": 0.1065, + "step": 348870 + }, + { + "epoch": 0.78, + "learning_rate": 1.1104896982170422e-05, + "loss": 0.1031, + "step": 348880 + }, + { + "epoch": 0.78, + "learning_rate": 1.1103778438961098e-05, + "loss": 0.1004, + "step": 348890 + }, + { + "epoch": 0.78, + "learning_rate": 1.1102659895751773e-05, + "loss": 0.1025, + "step": 348900 + }, + { + "epoch": 0.78, + "learning_rate": 1.1101541352542449e-05, + "loss": 0.1, + "step": 348910 + }, + { + "epoch": 0.78, + "learning_rate": 1.1100422809333125e-05, + "loss": 0.1025, + "step": 348920 + }, + { + "epoch": 0.78, + "learning_rate": 1.1099304266123801e-05, + "loss": 0.1008, + "step": 348930 + }, + { + "epoch": 0.78, + "learning_rate": 1.1098185722914478e-05, + "loss": 0.0987, + "step": 348940 + }, + { + "epoch": 0.78, + "learning_rate": 1.1097067179705152e-05, + "loss": 0.0982, + "step": 348950 + }, + { + "epoch": 0.78, + "learning_rate": 1.1095948636495828e-05, + "loss": 0.1034, + "step": 348960 + }, + { + "epoch": 0.78, + "learning_rate": 1.1094830093286505e-05, + "loss": 0.103, + "step": 348970 + }, + { + "epoch": 0.78, + "learning_rate": 1.1093711550077179e-05, + "loss": 0.1026, + "step": 348980 + }, + { + "epoch": 0.78, + "learning_rate": 1.1092593006867855e-05, + "loss": 0.1017, + "step": 348990 + }, + { + "epoch": 0.78, + "learning_rate": 1.1091474463658532e-05, + "loss": 0.1093, + "step": 349000 + }, + { + "epoch": 0.78, + "learning_rate": 1.1090355920449208e-05, + "loss": 0.1016, + "step": 349010 + }, + { + "epoch": 0.78, + "learning_rate": 1.1089237377239884e-05, + "loss": 0.1044, + "step": 349020 + }, + { + "epoch": 0.78, + "learning_rate": 1.1088118834030559e-05, + "loss": 0.1032, + "step": 349030 + }, + { + "epoch": 0.78, + "learning_rate": 1.1087000290821235e-05, + "loss": 0.1022, + "step": 349040 + }, + { + "epoch": 0.78, + "learning_rate": 1.1085881747611911e-05, + "loss": 0.1029, + "step": 349050 + }, + { + "epoch": 0.78, + "learning_rate": 1.1084763204402586e-05, + "loss": 0.1035, + "step": 349060 + }, + { + "epoch": 0.78, + "learning_rate": 1.1083644661193263e-05, + "loss": 0.1009, + "step": 349070 + }, + { + "epoch": 0.78, + "learning_rate": 1.1082526117983938e-05, + "loss": 0.1004, + "step": 349080 + }, + { + "epoch": 0.78, + "learning_rate": 1.1081407574774614e-05, + "loss": 0.1024, + "step": 349090 + }, + { + "epoch": 0.78, + "learning_rate": 1.108028903156529e-05, + "loss": 0.1008, + "step": 349100 + }, + { + "epoch": 0.78, + "learning_rate": 1.1079170488355965e-05, + "loss": 0.1005, + "step": 349110 + }, + { + "epoch": 0.78, + "learning_rate": 1.1078051945146641e-05, + "loss": 0.1047, + "step": 349120 + }, + { + "epoch": 0.78, + "learning_rate": 1.1076933401937317e-05, + "loss": 0.1006, + "step": 349130 + }, + { + "epoch": 0.78, + "learning_rate": 1.1075814858727992e-05, + "loss": 0.1051, + "step": 349140 + }, + { + "epoch": 0.78, + "learning_rate": 1.107469631551867e-05, + "loss": 0.1015, + "step": 349150 + }, + { + "epoch": 0.78, + "learning_rate": 1.1073577772309344e-05, + "loss": 0.1073, + "step": 349160 + }, + { + "epoch": 0.78, + "learning_rate": 1.107245922910002e-05, + "loss": 0.1049, + "step": 349170 + }, + { + "epoch": 0.78, + "learning_rate": 1.1071340685890697e-05, + "loss": 0.0993, + "step": 349180 + }, + { + "epoch": 0.78, + "learning_rate": 1.1070222142681371e-05, + "loss": 0.0989, + "step": 349190 + }, + { + "epoch": 0.78, + "learning_rate": 1.1069103599472048e-05, + "loss": 0.1015, + "step": 349200 + }, + { + "epoch": 0.78, + "learning_rate": 1.1067985056262724e-05, + "loss": 0.1017, + "step": 349210 + }, + { + "epoch": 0.78, + "learning_rate": 1.1066866513053398e-05, + "loss": 0.1005, + "step": 349220 + }, + { + "epoch": 0.78, + "learning_rate": 1.1065747969844076e-05, + "loss": 0.1017, + "step": 349230 + }, + { + "epoch": 0.78, + "learning_rate": 1.1064629426634751e-05, + "loss": 0.1012, + "step": 349240 + }, + { + "epoch": 0.78, + "learning_rate": 1.1063510883425427e-05, + "loss": 0.1056, + "step": 349250 + }, + { + "epoch": 0.78, + "learning_rate": 1.1062392340216103e-05, + "loss": 0.1004, + "step": 349260 + }, + { + "epoch": 0.78, + "learning_rate": 1.1061273797006778e-05, + "loss": 0.0972, + "step": 349270 + }, + { + "epoch": 0.78, + "learning_rate": 1.1060155253797456e-05, + "loss": 0.1028, + "step": 349280 + }, + { + "epoch": 0.78, + "learning_rate": 1.105903671058813e-05, + "loss": 0.1044, + "step": 349290 + }, + { + "epoch": 0.78, + "learning_rate": 1.1057918167378805e-05, + "loss": 0.1005, + "step": 349300 + }, + { + "epoch": 0.78, + "learning_rate": 1.1056799624169483e-05, + "loss": 0.1024, + "step": 349310 + }, + { + "epoch": 0.78, + "learning_rate": 1.1055681080960157e-05, + "loss": 0.1018, + "step": 349320 + }, + { + "epoch": 0.78, + "learning_rate": 1.1054562537750834e-05, + "loss": 0.1016, + "step": 349330 + }, + { + "epoch": 0.78, + "learning_rate": 1.105344399454151e-05, + "loss": 0.1064, + "step": 349340 + }, + { + "epoch": 0.78, + "learning_rate": 1.1052325451332184e-05, + "loss": 0.1044, + "step": 349350 + }, + { + "epoch": 0.78, + "learning_rate": 1.1051206908122862e-05, + "loss": 0.1043, + "step": 349360 + }, + { + "epoch": 0.78, + "learning_rate": 1.1050088364913537e-05, + "loss": 0.1064, + "step": 349370 + }, + { + "epoch": 0.78, + "learning_rate": 1.1048969821704211e-05, + "loss": 0.1079, + "step": 349380 + }, + { + "epoch": 0.78, + "learning_rate": 1.104785127849489e-05, + "loss": 0.1067, + "step": 349390 + }, + { + "epoch": 0.78, + "learning_rate": 1.1046732735285564e-05, + "loss": 0.1022, + "step": 349400 + }, + { + "epoch": 0.78, + "learning_rate": 1.104561419207624e-05, + "loss": 0.1042, + "step": 349410 + }, + { + "epoch": 0.78, + "learning_rate": 1.1044495648866916e-05, + "loss": 0.1048, + "step": 349420 + }, + { + "epoch": 0.78, + "learning_rate": 1.1043377105657591e-05, + "loss": 0.0988, + "step": 349430 + }, + { + "epoch": 0.78, + "learning_rate": 1.1042258562448269e-05, + "loss": 0.1023, + "step": 349440 + }, + { + "epoch": 0.78, + "learning_rate": 1.1041140019238943e-05, + "loss": 0.1015, + "step": 349450 + }, + { + "epoch": 0.78, + "learning_rate": 1.104002147602962e-05, + "loss": 0.101, + "step": 349460 + }, + { + "epoch": 0.78, + "learning_rate": 1.1038902932820296e-05, + "loss": 0.0999, + "step": 349470 + }, + { + "epoch": 0.78, + "learning_rate": 1.103778438961097e-05, + "loss": 0.0995, + "step": 349480 + }, + { + "epoch": 0.78, + "learning_rate": 1.1036665846401648e-05, + "loss": 0.1015, + "step": 349490 + }, + { + "epoch": 0.78, + "learning_rate": 1.1035547303192323e-05, + "loss": 0.1033, + "step": 349500 + }, + { + "epoch": 0.78, + "learning_rate": 1.1034428759982997e-05, + "loss": 0.0948, + "step": 349510 + }, + { + "epoch": 0.78, + "learning_rate": 1.1033310216773675e-05, + "loss": 0.1077, + "step": 349520 + }, + { + "epoch": 0.78, + "learning_rate": 1.103219167356435e-05, + "loss": 0.1077, + "step": 349530 + }, + { + "epoch": 0.78, + "learning_rate": 1.1031073130355026e-05, + "loss": 0.1005, + "step": 349540 + }, + { + "epoch": 0.78, + "learning_rate": 1.1029954587145702e-05, + "loss": 0.0996, + "step": 349550 + }, + { + "epoch": 0.78, + "learning_rate": 1.1028836043936377e-05, + "loss": 0.1012, + "step": 349560 + }, + { + "epoch": 0.78, + "learning_rate": 1.1027717500727055e-05, + "loss": 0.0984, + "step": 349570 + }, + { + "epoch": 0.78, + "learning_rate": 1.102659895751773e-05, + "loss": 0.1016, + "step": 349580 + }, + { + "epoch": 0.78, + "learning_rate": 1.1025480414308406e-05, + "loss": 0.0993, + "step": 349590 + }, + { + "epoch": 0.78, + "learning_rate": 1.1024361871099082e-05, + "loss": 0.1042, + "step": 349600 + }, + { + "epoch": 0.78, + "learning_rate": 1.1023243327889756e-05, + "loss": 0.102, + "step": 349610 + }, + { + "epoch": 0.78, + "learning_rate": 1.1022124784680433e-05, + "loss": 0.105, + "step": 349620 + }, + { + "epoch": 0.78, + "learning_rate": 1.1021006241471109e-05, + "loss": 0.1022, + "step": 349630 + }, + { + "epoch": 0.78, + "learning_rate": 1.1019887698261783e-05, + "loss": 0.105, + "step": 349640 + }, + { + "epoch": 0.78, + "learning_rate": 1.1018769155052461e-05, + "loss": 0.1016, + "step": 349650 + }, + { + "epoch": 0.78, + "learning_rate": 1.1017650611843136e-05, + "loss": 0.1024, + "step": 349660 + }, + { + "epoch": 0.78, + "learning_rate": 1.1016532068633812e-05, + "loss": 0.1026, + "step": 349670 + }, + { + "epoch": 0.78, + "learning_rate": 1.1015413525424488e-05, + "loss": 0.1019, + "step": 349680 + }, + { + "epoch": 0.78, + "learning_rate": 1.1014294982215163e-05, + "loss": 0.0971, + "step": 349690 + }, + { + "epoch": 0.78, + "learning_rate": 1.1013176439005839e-05, + "loss": 0.1009, + "step": 349700 + }, + { + "epoch": 0.78, + "learning_rate": 1.1012057895796515e-05, + "loss": 0.1013, + "step": 349710 + }, + { + "epoch": 0.78, + "learning_rate": 1.101093935258719e-05, + "loss": 0.1038, + "step": 349720 + }, + { + "epoch": 0.78, + "learning_rate": 1.1009820809377868e-05, + "loss": 0.103, + "step": 349730 + }, + { + "epoch": 0.78, + "learning_rate": 1.1008702266168542e-05, + "loss": 0.1, + "step": 349740 + }, + { + "epoch": 0.78, + "learning_rate": 1.1007583722959219e-05, + "loss": 0.1046, + "step": 349750 + }, + { + "epoch": 0.78, + "learning_rate": 1.1006465179749895e-05, + "loss": 0.0996, + "step": 349760 + }, + { + "epoch": 0.78, + "learning_rate": 1.100534663654057e-05, + "loss": 0.1032, + "step": 349770 + }, + { + "epoch": 0.78, + "learning_rate": 1.1004228093331246e-05, + "loss": 0.1032, + "step": 349780 + }, + { + "epoch": 0.78, + "learning_rate": 1.1003109550121922e-05, + "loss": 0.1032, + "step": 349790 + }, + { + "epoch": 0.78, + "learning_rate": 1.1001991006912598e-05, + "loss": 0.1018, + "step": 349800 + }, + { + "epoch": 0.78, + "learning_rate": 1.1000872463703274e-05, + "loss": 0.0982, + "step": 349810 + }, + { + "epoch": 0.78, + "learning_rate": 1.0999753920493949e-05, + "loss": 0.0988, + "step": 349820 + }, + { + "epoch": 0.78, + "learning_rate": 1.0998635377284625e-05, + "loss": 0.0987, + "step": 349830 + }, + { + "epoch": 0.78, + "learning_rate": 1.0997516834075301e-05, + "loss": 0.1046, + "step": 349840 + }, + { + "epoch": 0.78, + "learning_rate": 1.0996398290865976e-05, + "loss": 0.1017, + "step": 349850 + }, + { + "epoch": 0.78, + "learning_rate": 1.0995279747656652e-05, + "loss": 0.1032, + "step": 349860 + }, + { + "epoch": 0.78, + "learning_rate": 1.0994161204447328e-05, + "loss": 0.1034, + "step": 349870 + }, + { + "epoch": 0.78, + "learning_rate": 1.0993042661238004e-05, + "loss": 0.0971, + "step": 349880 + }, + { + "epoch": 0.78, + "learning_rate": 1.099192411802868e-05, + "loss": 0.1033, + "step": 349890 + }, + { + "epoch": 0.78, + "learning_rate": 1.0990805574819355e-05, + "loss": 0.1002, + "step": 349900 + }, + { + "epoch": 0.78, + "learning_rate": 1.0989687031610032e-05, + "loss": 0.103, + "step": 349910 + }, + { + "epoch": 0.78, + "learning_rate": 1.0988568488400708e-05, + "loss": 0.1054, + "step": 349920 + }, + { + "epoch": 0.78, + "learning_rate": 1.0987449945191384e-05, + "loss": 0.104, + "step": 349930 + }, + { + "epoch": 0.78, + "learning_rate": 1.0986331401982059e-05, + "loss": 0.0989, + "step": 349940 + }, + { + "epoch": 0.78, + "learning_rate": 1.0985212858772735e-05, + "loss": 0.0956, + "step": 349950 + }, + { + "epoch": 0.78, + "learning_rate": 1.0984094315563411e-05, + "loss": 0.1041, + "step": 349960 + }, + { + "epoch": 0.78, + "learning_rate": 1.0982975772354087e-05, + "loss": 0.1011, + "step": 349970 + }, + { + "epoch": 0.78, + "learning_rate": 1.0981857229144762e-05, + "loss": 0.1018, + "step": 349980 + }, + { + "epoch": 0.78, + "learning_rate": 1.0980738685935438e-05, + "loss": 0.1, + "step": 349990 + }, + { + "epoch": 0.78, + "learning_rate": 1.0979620142726114e-05, + "loss": 0.1052, + "step": 350000 + }, + { + "epoch": 0.78, + "learning_rate": 1.097850159951679e-05, + "loss": 0.1026, + "step": 350010 + }, + { + "epoch": 0.78, + "learning_rate": 1.0977383056307465e-05, + "loss": 0.0955, + "step": 350020 + }, + { + "epoch": 0.78, + "learning_rate": 1.0976264513098141e-05, + "loss": 0.1004, + "step": 350030 + }, + { + "epoch": 0.78, + "learning_rate": 1.0975145969888817e-05, + "loss": 0.1002, + "step": 350040 + }, + { + "epoch": 0.78, + "learning_rate": 1.0974027426679494e-05, + "loss": 0.0998, + "step": 350050 + }, + { + "epoch": 0.78, + "learning_rate": 1.0972908883470168e-05, + "loss": 0.0992, + "step": 350060 + }, + { + "epoch": 0.78, + "learning_rate": 1.0971790340260844e-05, + "loss": 0.0999, + "step": 350070 + }, + { + "epoch": 0.78, + "learning_rate": 1.097067179705152e-05, + "loss": 0.1032, + "step": 350080 + }, + { + "epoch": 0.78, + "learning_rate": 1.0969553253842197e-05, + "loss": 0.1024, + "step": 350090 + }, + { + "epoch": 0.78, + "learning_rate": 1.0968434710632871e-05, + "loss": 0.1024, + "step": 350100 + }, + { + "epoch": 0.78, + "learning_rate": 1.0967316167423548e-05, + "loss": 0.1023, + "step": 350110 + }, + { + "epoch": 0.78, + "learning_rate": 1.0966197624214224e-05, + "loss": 0.1018, + "step": 350120 + }, + { + "epoch": 0.78, + "learning_rate": 1.09650790810049e-05, + "loss": 0.1018, + "step": 350130 + }, + { + "epoch": 0.78, + "learning_rate": 1.0963960537795576e-05, + "loss": 0.098, + "step": 350140 + }, + { + "epoch": 0.78, + "learning_rate": 1.0962841994586251e-05, + "loss": 0.1025, + "step": 350150 + }, + { + "epoch": 0.78, + "learning_rate": 1.0961723451376927e-05, + "loss": 0.1003, + "step": 350160 + }, + { + "epoch": 0.78, + "learning_rate": 1.0960604908167603e-05, + "loss": 0.1071, + "step": 350170 + }, + { + "epoch": 0.78, + "learning_rate": 1.0959486364958278e-05, + "loss": 0.0983, + "step": 350180 + }, + { + "epoch": 0.78, + "learning_rate": 1.0958367821748954e-05, + "loss": 0.1022, + "step": 350190 + }, + { + "epoch": 0.78, + "learning_rate": 1.095724927853963e-05, + "loss": 0.107, + "step": 350200 + }, + { + "epoch": 0.78, + "learning_rate": 1.0956130735330307e-05, + "loss": 0.0991, + "step": 350210 + }, + { + "epoch": 0.78, + "learning_rate": 1.0955012192120983e-05, + "loss": 0.1037, + "step": 350220 + }, + { + "epoch": 0.78, + "learning_rate": 1.0953893648911657e-05, + "loss": 0.1074, + "step": 350230 + }, + { + "epoch": 0.78, + "learning_rate": 1.0952775105702334e-05, + "loss": 0.1046, + "step": 350240 + }, + { + "epoch": 0.78, + "learning_rate": 1.095165656249301e-05, + "loss": 0.1022, + "step": 350250 + }, + { + "epoch": 0.78, + "learning_rate": 1.0950538019283684e-05, + "loss": 0.107, + "step": 350260 + }, + { + "epoch": 0.78, + "learning_rate": 1.0949419476074362e-05, + "loss": 0.1026, + "step": 350270 + }, + { + "epoch": 0.78, + "learning_rate": 1.0948300932865037e-05, + "loss": 0.1015, + "step": 350280 + }, + { + "epoch": 0.78, + "learning_rate": 1.0947182389655713e-05, + "loss": 0.0984, + "step": 350290 + }, + { + "epoch": 0.78, + "learning_rate": 1.094606384644639e-05, + "loss": 0.1042, + "step": 350300 + }, + { + "epoch": 0.78, + "learning_rate": 1.0944945303237064e-05, + "loss": 0.0986, + "step": 350310 + }, + { + "epoch": 0.78, + "learning_rate": 1.094382676002774e-05, + "loss": 0.0999, + "step": 350320 + }, + { + "epoch": 0.78, + "learning_rate": 1.0942708216818416e-05, + "loss": 0.1017, + "step": 350330 + }, + { + "epoch": 0.78, + "learning_rate": 1.0941589673609091e-05, + "loss": 0.1015, + "step": 350340 + }, + { + "epoch": 0.78, + "learning_rate": 1.0940471130399769e-05, + "loss": 0.0998, + "step": 350350 + }, + { + "epoch": 0.78, + "learning_rate": 1.0939352587190443e-05, + "loss": 0.1032, + "step": 350360 + }, + { + "epoch": 0.78, + "learning_rate": 1.093823404398112e-05, + "loss": 0.1002, + "step": 350370 + }, + { + "epoch": 0.78, + "learning_rate": 1.0937115500771796e-05, + "loss": 0.0971, + "step": 350380 + }, + { + "epoch": 0.78, + "learning_rate": 1.093599695756247e-05, + "loss": 0.1017, + "step": 350390 + }, + { + "epoch": 0.78, + "learning_rate": 1.0934878414353147e-05, + "loss": 0.1037, + "step": 350400 + }, + { + "epoch": 0.78, + "learning_rate": 1.0933759871143823e-05, + "loss": 0.1049, + "step": 350410 + }, + { + "epoch": 0.78, + "learning_rate": 1.0932641327934497e-05, + "loss": 0.107, + "step": 350420 + }, + { + "epoch": 0.78, + "learning_rate": 1.0931522784725175e-05, + "loss": 0.101, + "step": 350430 + }, + { + "epoch": 0.78, + "learning_rate": 1.093040424151585e-05, + "loss": 0.1054, + "step": 350440 + }, + { + "epoch": 0.78, + "learning_rate": 1.0929285698306526e-05, + "loss": 0.1013, + "step": 350450 + }, + { + "epoch": 0.78, + "learning_rate": 1.0928167155097202e-05, + "loss": 0.104, + "step": 350460 + }, + { + "epoch": 0.78, + "learning_rate": 1.0927048611887877e-05, + "loss": 0.1027, + "step": 350470 + }, + { + "epoch": 0.78, + "learning_rate": 1.0925930068678555e-05, + "loss": 0.1002, + "step": 350480 + }, + { + "epoch": 0.78, + "learning_rate": 1.092481152546923e-05, + "loss": 0.1027, + "step": 350490 + }, + { + "epoch": 0.78, + "learning_rate": 1.0923692982259904e-05, + "loss": 0.0975, + "step": 350500 + }, + { + "epoch": 0.78, + "learning_rate": 1.0922574439050582e-05, + "loss": 0.1067, + "step": 350510 + }, + { + "epoch": 0.78, + "learning_rate": 1.0921455895841256e-05, + "loss": 0.1022, + "step": 350520 + }, + { + "epoch": 0.78, + "learning_rate": 1.0920337352631933e-05, + "loss": 0.1043, + "step": 350530 + }, + { + "epoch": 0.78, + "learning_rate": 1.0919218809422609e-05, + "loss": 0.0979, + "step": 350540 + }, + { + "epoch": 0.78, + "learning_rate": 1.0918100266213283e-05, + "loss": 0.1028, + "step": 350550 + }, + { + "epoch": 0.78, + "learning_rate": 1.0916981723003961e-05, + "loss": 0.1001, + "step": 350560 + }, + { + "epoch": 0.78, + "learning_rate": 1.0915863179794636e-05, + "loss": 0.101, + "step": 350570 + }, + { + "epoch": 0.78, + "learning_rate": 1.0914744636585312e-05, + "loss": 0.101, + "step": 350580 + }, + { + "epoch": 0.78, + "learning_rate": 1.0913626093375988e-05, + "loss": 0.1065, + "step": 350590 + }, + { + "epoch": 0.78, + "learning_rate": 1.0912507550166663e-05, + "loss": 0.1024, + "step": 350600 + }, + { + "epoch": 0.78, + "learning_rate": 1.0911389006957339e-05, + "loss": 0.0994, + "step": 350610 + }, + { + "epoch": 0.78, + "learning_rate": 1.0910270463748015e-05, + "loss": 0.1002, + "step": 350620 + }, + { + "epoch": 0.78, + "learning_rate": 1.090915192053869e-05, + "loss": 0.1017, + "step": 350630 + }, + { + "epoch": 0.78, + "learning_rate": 1.0908033377329368e-05, + "loss": 0.1022, + "step": 350640 + }, + { + "epoch": 0.78, + "learning_rate": 1.0906914834120042e-05, + "loss": 0.1, + "step": 350650 + }, + { + "epoch": 0.78, + "learning_rate": 1.0905796290910719e-05, + "loss": 0.1073, + "step": 350660 + }, + { + "epoch": 0.78, + "learning_rate": 1.0904677747701395e-05, + "loss": 0.1048, + "step": 350670 + }, + { + "epoch": 0.78, + "learning_rate": 1.090355920449207e-05, + "loss": 0.1028, + "step": 350680 + }, + { + "epoch": 0.78, + "learning_rate": 1.0902552515603678e-05, + "loss": 0.1033, + "step": 350690 + }, + { + "epoch": 0.78, + "learning_rate": 1.0901433972394354e-05, + "loss": 0.1078, + "step": 350700 + }, + { + "epoch": 0.78, + "learning_rate": 1.090031542918503e-05, + "loss": 0.105, + "step": 350710 + }, + { + "epoch": 0.78, + "learning_rate": 1.0899196885975705e-05, + "loss": 0.106, + "step": 350720 + }, + { + "epoch": 0.78, + "learning_rate": 1.0898078342766381e-05, + "loss": 0.1008, + "step": 350730 + }, + { + "epoch": 0.78, + "learning_rate": 1.0896959799557058e-05, + "loss": 0.1005, + "step": 350740 + }, + { + "epoch": 0.78, + "learning_rate": 1.0895841256347734e-05, + "loss": 0.1056, + "step": 350750 + }, + { + "epoch": 0.78, + "learning_rate": 1.089472271313841e-05, + "loss": 0.104, + "step": 350760 + }, + { + "epoch": 0.78, + "learning_rate": 1.0893604169929085e-05, + "loss": 0.1039, + "step": 350770 + }, + { + "epoch": 0.78, + "learning_rate": 1.089248562671976e-05, + "loss": 0.1019, + "step": 350780 + }, + { + "epoch": 0.78, + "learning_rate": 1.0891367083510437e-05, + "loss": 0.1044, + "step": 350790 + }, + { + "epoch": 0.78, + "learning_rate": 1.0890248540301112e-05, + "loss": 0.1029, + "step": 350800 + }, + { + "epoch": 0.78, + "learning_rate": 1.0889129997091788e-05, + "loss": 0.1022, + "step": 350810 + }, + { + "epoch": 0.78, + "learning_rate": 1.0888011453882464e-05, + "loss": 0.1049, + "step": 350820 + }, + { + "epoch": 0.78, + "learning_rate": 1.088689291067314e-05, + "loss": 0.1031, + "step": 350830 + }, + { + "epoch": 0.78, + "learning_rate": 1.0885774367463817e-05, + "loss": 0.1007, + "step": 350840 + }, + { + "epoch": 0.78, + "learning_rate": 1.0884655824254491e-05, + "loss": 0.0975, + "step": 350850 + }, + { + "epoch": 0.78, + "learning_rate": 1.0883537281045167e-05, + "loss": 0.1012, + "step": 350860 + }, + { + "epoch": 0.78, + "learning_rate": 1.0882418737835844e-05, + "loss": 0.1012, + "step": 350870 + }, + { + "epoch": 0.78, + "learning_rate": 1.0881300194626518e-05, + "loss": 0.1023, + "step": 350880 + }, + { + "epoch": 0.78, + "learning_rate": 1.0880181651417194e-05, + "loss": 0.1045, + "step": 350890 + }, + { + "epoch": 0.78, + "learning_rate": 1.087906310820787e-05, + "loss": 0.1032, + "step": 350900 + }, + { + "epoch": 0.78, + "learning_rate": 1.0877944564998547e-05, + "loss": 0.0986, + "step": 350910 + }, + { + "epoch": 0.78, + "learning_rate": 1.0876826021789223e-05, + "loss": 0.1014, + "step": 350920 + }, + { + "epoch": 0.78, + "learning_rate": 1.0875707478579898e-05, + "loss": 0.1039, + "step": 350930 + }, + { + "epoch": 0.78, + "learning_rate": 1.0874588935370574e-05, + "loss": 0.0991, + "step": 350940 + }, + { + "epoch": 0.78, + "learning_rate": 1.087347039216125e-05, + "loss": 0.1006, + "step": 350950 + }, + { + "epoch": 0.78, + "learning_rate": 1.0872351848951926e-05, + "loss": 0.1036, + "step": 350960 + }, + { + "epoch": 0.78, + "learning_rate": 1.08712333057426e-05, + "loss": 0.1026, + "step": 350970 + }, + { + "epoch": 0.78, + "learning_rate": 1.0870114762533277e-05, + "loss": 0.1012, + "step": 350980 + }, + { + "epoch": 0.78, + "learning_rate": 1.0868996219323953e-05, + "loss": 0.1055, + "step": 350990 + }, + { + "epoch": 0.78, + "learning_rate": 1.086787767611463e-05, + "loss": 0.105, + "step": 351000 + }, + { + "epoch": 0.78, + "learning_rate": 1.0866759132905304e-05, + "loss": 0.101, + "step": 351010 + }, + { + "epoch": 0.78, + "learning_rate": 1.086564058969598e-05, + "loss": 0.1001, + "step": 351020 + }, + { + "epoch": 0.78, + "learning_rate": 1.0864522046486656e-05, + "loss": 0.1054, + "step": 351030 + }, + { + "epoch": 0.78, + "learning_rate": 1.0863403503277333e-05, + "loss": 0.0995, + "step": 351040 + }, + { + "epoch": 0.78, + "learning_rate": 1.0862284960068007e-05, + "loss": 0.1023, + "step": 351050 + }, + { + "epoch": 0.78, + "learning_rate": 1.0861166416858683e-05, + "loss": 0.0994, + "step": 351060 + }, + { + "epoch": 0.78, + "learning_rate": 1.086004787364936e-05, + "loss": 0.1025, + "step": 351070 + }, + { + "epoch": 0.78, + "learning_rate": 1.0858929330440036e-05, + "loss": 0.1014, + "step": 351080 + }, + { + "epoch": 0.78, + "learning_rate": 1.0857810787230712e-05, + "loss": 0.0987, + "step": 351090 + }, + { + "epoch": 0.78, + "learning_rate": 1.0856692244021387e-05, + "loss": 0.1014, + "step": 351100 + }, + { + "epoch": 0.78, + "learning_rate": 1.0855573700812063e-05, + "loss": 0.0974, + "step": 351110 + }, + { + "epoch": 0.78, + "learning_rate": 1.085445515760274e-05, + "loss": 0.1047, + "step": 351120 + }, + { + "epoch": 0.78, + "learning_rate": 1.0853336614393414e-05, + "loss": 0.1049, + "step": 351130 + }, + { + "epoch": 0.78, + "learning_rate": 1.085221807118409e-05, + "loss": 0.1065, + "step": 351140 + }, + { + "epoch": 0.78, + "learning_rate": 1.0851099527974766e-05, + "loss": 0.1053, + "step": 351150 + }, + { + "epoch": 0.78, + "learning_rate": 1.0849980984765442e-05, + "loss": 0.0981, + "step": 351160 + }, + { + "epoch": 0.78, + "learning_rate": 1.0848862441556119e-05, + "loss": 0.1036, + "step": 351170 + }, + { + "epoch": 0.78, + "learning_rate": 1.0847743898346793e-05, + "loss": 0.1031, + "step": 351180 + }, + { + "epoch": 0.78, + "learning_rate": 1.084662535513747e-05, + "loss": 0.0976, + "step": 351190 + }, + { + "epoch": 0.78, + "learning_rate": 1.0845506811928146e-05, + "loss": 0.101, + "step": 351200 + }, + { + "epoch": 0.78, + "learning_rate": 1.084438826871882e-05, + "loss": 0.1009, + "step": 351210 + }, + { + "epoch": 0.78, + "learning_rate": 1.0843269725509496e-05, + "loss": 0.1022, + "step": 351220 + }, + { + "epoch": 0.78, + "learning_rate": 1.0842151182300173e-05, + "loss": 0.1021, + "step": 351230 + }, + { + "epoch": 0.78, + "learning_rate": 1.0841032639090849e-05, + "loss": 0.1032, + "step": 351240 + }, + { + "epoch": 0.78, + "learning_rate": 1.0839914095881525e-05, + "loss": 0.1061, + "step": 351250 + }, + { + "epoch": 0.78, + "learning_rate": 1.08387955526722e-05, + "loss": 0.1008, + "step": 351260 + }, + { + "epoch": 0.78, + "learning_rate": 1.0837677009462876e-05, + "loss": 0.1029, + "step": 351270 + }, + { + "epoch": 0.78, + "learning_rate": 1.0836558466253552e-05, + "loss": 0.1001, + "step": 351280 + }, + { + "epoch": 0.78, + "learning_rate": 1.0835439923044227e-05, + "loss": 0.1021, + "step": 351290 + }, + { + "epoch": 0.78, + "learning_rate": 1.0834321379834905e-05, + "loss": 0.1022, + "step": 351300 + }, + { + "epoch": 0.78, + "learning_rate": 1.083320283662558e-05, + "loss": 0.107, + "step": 351310 + }, + { + "epoch": 0.78, + "learning_rate": 1.0832084293416255e-05, + "loss": 0.0988, + "step": 351320 + }, + { + "epoch": 0.78, + "learning_rate": 1.0830965750206932e-05, + "loss": 0.0994, + "step": 351330 + }, + { + "epoch": 0.78, + "learning_rate": 1.0829847206997606e-05, + "loss": 0.1056, + "step": 351340 + }, + { + "epoch": 0.78, + "learning_rate": 1.0828728663788282e-05, + "loss": 0.1049, + "step": 351350 + }, + { + "epoch": 0.78, + "learning_rate": 1.0827610120578959e-05, + "loss": 0.1004, + "step": 351360 + }, + { + "epoch": 0.78, + "learning_rate": 1.0826491577369633e-05, + "loss": 0.0973, + "step": 351370 + }, + { + "epoch": 0.78, + "learning_rate": 1.0825373034160311e-05, + "loss": 0.1051, + "step": 351380 + }, + { + "epoch": 0.78, + "learning_rate": 1.0824254490950986e-05, + "loss": 0.1016, + "step": 351390 + }, + { + "epoch": 0.78, + "learning_rate": 1.0823135947741662e-05, + "loss": 0.0997, + "step": 351400 + }, + { + "epoch": 0.78, + "learning_rate": 1.0822017404532338e-05, + "loss": 0.1009, + "step": 351410 + }, + { + "epoch": 0.78, + "learning_rate": 1.0820898861323013e-05, + "loss": 0.104, + "step": 351420 + }, + { + "epoch": 0.78, + "learning_rate": 1.081978031811369e-05, + "loss": 0.1022, + "step": 351430 + }, + { + "epoch": 0.78, + "learning_rate": 1.0818661774904365e-05, + "loss": 0.1007, + "step": 351440 + }, + { + "epoch": 0.78, + "learning_rate": 1.081754323169504e-05, + "loss": 0.1012, + "step": 351450 + }, + { + "epoch": 0.78, + "learning_rate": 1.0816424688485718e-05, + "loss": 0.1062, + "step": 351460 + }, + { + "epoch": 0.78, + "learning_rate": 1.0815306145276392e-05, + "loss": 0.1012, + "step": 351470 + }, + { + "epoch": 0.78, + "learning_rate": 1.0814187602067068e-05, + "loss": 0.0935, + "step": 351480 + }, + { + "epoch": 0.78, + "learning_rate": 1.0813069058857745e-05, + "loss": 0.1026, + "step": 351490 + }, + { + "epoch": 0.78, + "learning_rate": 1.0811950515648419e-05, + "loss": 0.1037, + "step": 351500 + }, + { + "epoch": 0.78, + "learning_rate": 1.0810831972439097e-05, + "loss": 0.1046, + "step": 351510 + }, + { + "epoch": 0.78, + "learning_rate": 1.0809713429229772e-05, + "loss": 0.1031, + "step": 351520 + }, + { + "epoch": 0.78, + "learning_rate": 1.0808594886020446e-05, + "loss": 0.1031, + "step": 351530 + }, + { + "epoch": 0.78, + "learning_rate": 1.0807476342811124e-05, + "loss": 0.1016, + "step": 351540 + }, + { + "epoch": 0.78, + "learning_rate": 1.0806357799601799e-05, + "loss": 0.0988, + "step": 351550 + }, + { + "epoch": 0.78, + "learning_rate": 1.0805239256392475e-05, + "loss": 0.1058, + "step": 351560 + }, + { + "epoch": 0.78, + "learning_rate": 1.0804120713183151e-05, + "loss": 0.1, + "step": 351570 + }, + { + "epoch": 0.78, + "learning_rate": 1.0803002169973826e-05, + "loss": 0.1002, + "step": 351580 + }, + { + "epoch": 0.78, + "learning_rate": 1.0801883626764504e-05, + "loss": 0.1031, + "step": 351590 + }, + { + "epoch": 0.78, + "learning_rate": 1.0800765083555178e-05, + "loss": 0.1044, + "step": 351600 + }, + { + "epoch": 0.78, + "learning_rate": 1.0799646540345854e-05, + "loss": 0.0983, + "step": 351610 + }, + { + "epoch": 0.78, + "learning_rate": 1.079852799713653e-05, + "loss": 0.1003, + "step": 351620 + }, + { + "epoch": 0.78, + "learning_rate": 1.0797409453927205e-05, + "loss": 0.1036, + "step": 351630 + }, + { + "epoch": 0.78, + "learning_rate": 1.0796290910717883e-05, + "loss": 0.1056, + "step": 351640 + }, + { + "epoch": 0.78, + "learning_rate": 1.0795172367508558e-05, + "loss": 0.1048, + "step": 351650 + }, + { + "epoch": 0.78, + "learning_rate": 1.0794053824299232e-05, + "loss": 0.1024, + "step": 351660 + }, + { + "epoch": 0.78, + "learning_rate": 1.079293528108991e-05, + "loss": 0.096, + "step": 351670 + }, + { + "epoch": 0.78, + "learning_rate": 1.0791816737880585e-05, + "loss": 0.1016, + "step": 351680 + }, + { + "epoch": 0.79, + "learning_rate": 1.079069819467126e-05, + "loss": 0.1013, + "step": 351690 + }, + { + "epoch": 0.79, + "learning_rate": 1.0789579651461937e-05, + "loss": 0.0975, + "step": 351700 + }, + { + "epoch": 0.79, + "learning_rate": 1.0788461108252612e-05, + "loss": 0.1002, + "step": 351710 + }, + { + "epoch": 0.79, + "learning_rate": 1.078734256504329e-05, + "loss": 0.101, + "step": 351720 + }, + { + "epoch": 0.79, + "learning_rate": 1.0786224021833964e-05, + "loss": 0.0989, + "step": 351730 + }, + { + "epoch": 0.79, + "learning_rate": 1.078510547862464e-05, + "loss": 0.1008, + "step": 351740 + }, + { + "epoch": 0.79, + "learning_rate": 1.0783986935415316e-05, + "loss": 0.1036, + "step": 351750 + }, + { + "epoch": 0.79, + "learning_rate": 1.0782868392205991e-05, + "loss": 0.1001, + "step": 351760 + }, + { + "epoch": 0.79, + "learning_rate": 1.0781749848996667e-05, + "loss": 0.1008, + "step": 351770 + }, + { + "epoch": 0.79, + "learning_rate": 1.0780631305787344e-05, + "loss": 0.0987, + "step": 351780 + }, + { + "epoch": 0.79, + "learning_rate": 1.0779512762578018e-05, + "loss": 0.1025, + "step": 351790 + }, + { + "epoch": 0.79, + "learning_rate": 1.0778394219368696e-05, + "loss": 0.1027, + "step": 351800 + }, + { + "epoch": 0.79, + "learning_rate": 1.077727567615937e-05, + "loss": 0.099, + "step": 351810 + }, + { + "epoch": 0.79, + "learning_rate": 1.0776157132950047e-05, + "loss": 0.1013, + "step": 351820 + }, + { + "epoch": 0.79, + "learning_rate": 1.0775038589740723e-05, + "loss": 0.1057, + "step": 351830 + }, + { + "epoch": 0.79, + "learning_rate": 1.0773920046531398e-05, + "loss": 0.1012, + "step": 351840 + }, + { + "epoch": 0.79, + "learning_rate": 1.0772801503322074e-05, + "loss": 0.1052, + "step": 351850 + }, + { + "epoch": 0.79, + "learning_rate": 1.077168296011275e-05, + "loss": 0.1038, + "step": 351860 + }, + { + "epoch": 0.79, + "learning_rate": 1.0770564416903425e-05, + "loss": 0.1078, + "step": 351870 + }, + { + "epoch": 0.79, + "learning_rate": 1.07694458736941e-05, + "loss": 0.101, + "step": 351880 + }, + { + "epoch": 0.79, + "learning_rate": 1.0768327330484777e-05, + "loss": 0.103, + "step": 351890 + }, + { + "epoch": 0.79, + "learning_rate": 1.0767208787275453e-05, + "loss": 0.1029, + "step": 351900 + }, + { + "epoch": 0.79, + "learning_rate": 1.076609024406613e-05, + "loss": 0.1021, + "step": 351910 + }, + { + "epoch": 0.79, + "learning_rate": 1.0764971700856804e-05, + "loss": 0.1021, + "step": 351920 + }, + { + "epoch": 0.79, + "learning_rate": 1.076385315764748e-05, + "loss": 0.1022, + "step": 351930 + }, + { + "epoch": 0.79, + "learning_rate": 1.0762734614438156e-05, + "loss": 0.0996, + "step": 351940 + }, + { + "epoch": 0.79, + "learning_rate": 1.0761616071228833e-05, + "loss": 0.1001, + "step": 351950 + }, + { + "epoch": 0.79, + "learning_rate": 1.0760497528019507e-05, + "loss": 0.0973, + "step": 351960 + }, + { + "epoch": 0.79, + "learning_rate": 1.0759378984810183e-05, + "loss": 0.0999, + "step": 351970 + }, + { + "epoch": 0.79, + "learning_rate": 1.075826044160086e-05, + "loss": 0.1005, + "step": 351980 + }, + { + "epoch": 0.79, + "learning_rate": 1.0757141898391536e-05, + "loss": 0.0954, + "step": 351990 + }, + { + "epoch": 0.79, + "learning_rate": 1.075602335518221e-05, + "loss": 0.1011, + "step": 352000 + }, + { + "epoch": 0.79, + "eval_NEIMS_canon_smiles": 0.9635, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.24231666666666668, + "eval_NEIMS_daylight_tanimoto_simil": 0.6168391877401604, + "eval_NEIMS_exact_mols": 0.24203333333333332, + "eval_NEIMS_exact_smiles": 0.23753333333333335, + "eval_NEIMS_loss": 0.1307661235332489, + "eval_NEIMS_matched_formulas": 0.7527833333333334, + "eval_NEIMS_morgan_tanimoto_simil": 0.5414326811640712, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.24275, + "eval_NEIMS_runtime": 729.6583, + "eval_NEIMS_samples_per_second": 82.23, + "eval_NEIMS_steps_per_second": 1.286, + "step": 352000 + }, + { + "epoch": 0.79, + "eval_RASSP_canon_smiles": 0.9598123351253882, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.3166594316626039, + "eval_RASSP_daylight_tanimoto_simil": 0.714034245857075, + "eval_RASSP_exact_mols": 0.31579123117507596, + "eval_RASSP_exact_smiles": 0.30902928507029087, + "eval_RASSP_loss": 0.10140303522348404, + "eval_RASSP_matched_formulas": 0.8786856780311885, + "eval_RASSP_morgan_tanimoto_simil": 0.6061649105462132, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.31599158513373626, + "eval_RASSP_runtime": 828.7474, + "eval_RASSP_samples_per_second": 72.271, + "eval_RASSP_steps_per_second": 1.129, + "step": 352000 + }, + { + "epoch": 0.79, + "eval_NEIMS_old_canon_smiles": 0.9601333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.23863333333333334, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6134417203174045, + "eval_NEIMS_old_exact_mols": 0.2384, + "eval_NEIMS_old_exact_smiles": 0.23283333333333334, + "eval_NEIMS_old_loss": 0.1302582323551178, + "eval_NEIMS_old_matched_formulas": 0.7505, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5396428143408476, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2392, + "eval_NEIMS_old_runtime": 366.3761, + "eval_NEIMS_old_samples_per_second": 81.883, + "eval_NEIMS_old_steps_per_second": 1.28, + "step": 352000 + }, + { + "epoch": 0.79, + "eval_RASSP_old_canon_smiles": 0.9599225815063236, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.3464477592017886, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7336079133090403, + "eval_RASSP_old_exact_mols": 0.34558013815196714, + "eval_RASSP_old_exact_smiles": 0.3383054693496179, + "eval_RASSP_old_loss": 0.09463747590780258, + "eval_RASSP_old_matched_formulas": 0.8917809590549605, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6303040498359146, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.34578035839423366, + "eval_RASSP_old_runtime": 414.6459, + "eval_RASSP_old_samples_per_second": 72.271, + "eval_RASSP_old_steps_per_second": 1.131, + "step": 352000 + }, + { + "epoch": 0.79, + "eval_NIST_canon_smiles": 0.8713844625048799, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.02785960180288888, + "eval_NIST_daylight_tanimoto_simil": 0.30190372504226337, + "eval_NIST_exact_mols": 0.026865883522021506, + "eval_NIST_exact_smiles": 0.02551726585513007, + "eval_NIST_loss": 1.7991760969161987, + "eval_NIST_matched_formulas": 0.1266281009333854, + "eval_NIST_morgan_tanimoto_simil": 0.25362808095589656, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.027646662171274445, + "eval_NIST_runtime": 560.6419, + "eval_NIST_samples_per_second": 50.258, + "eval_NIST_steps_per_second": 0.787, + "step": 352000 + }, + { + "epoch": 0.79, + "learning_rate": 1.0754904811972887e-05, + "loss": 0.1046, + "step": 352010 + }, + { + "epoch": 0.79, + "learning_rate": 1.0753786268763563e-05, + "loss": 0.0975, + "step": 352020 + }, + { + "epoch": 0.79, + "learning_rate": 1.075266772555424e-05, + "loss": 0.1022, + "step": 352030 + }, + { + "epoch": 0.79, + "learning_rate": 1.0751549182344914e-05, + "loss": 0.1049, + "step": 352040 + }, + { + "epoch": 0.79, + "learning_rate": 1.075043063913559e-05, + "loss": 0.1027, + "step": 352050 + }, + { + "epoch": 0.79, + "learning_rate": 1.0749312095926266e-05, + "loss": 0.1003, + "step": 352060 + }, + { + "epoch": 0.79, + "learning_rate": 1.0748193552716942e-05, + "loss": 0.1018, + "step": 352070 + }, + { + "epoch": 0.79, + "learning_rate": 1.0747075009507619e-05, + "loss": 0.0995, + "step": 352080 + }, + { + "epoch": 0.79, + "learning_rate": 1.0745956466298293e-05, + "loss": 0.0997, + "step": 352090 + }, + { + "epoch": 0.79, + "learning_rate": 1.074483792308897e-05, + "loss": 0.0991, + "step": 352100 + }, + { + "epoch": 0.79, + "learning_rate": 1.0743719379879646e-05, + "loss": 0.1041, + "step": 352110 + }, + { + "epoch": 0.79, + "learning_rate": 1.074260083667032e-05, + "loss": 0.1031, + "step": 352120 + }, + { + "epoch": 0.79, + "learning_rate": 1.0741482293460996e-05, + "loss": 0.1042, + "step": 352130 + }, + { + "epoch": 0.79, + "learning_rate": 1.0740363750251673e-05, + "loss": 0.0978, + "step": 352140 + }, + { + "epoch": 0.79, + "learning_rate": 1.0739245207042349e-05, + "loss": 0.0997, + "step": 352150 + }, + { + "epoch": 0.79, + "learning_rate": 1.0738126663833025e-05, + "loss": 0.1019, + "step": 352160 + }, + { + "epoch": 0.79, + "learning_rate": 1.07370081206237e-05, + "loss": 0.0991, + "step": 352170 + }, + { + "epoch": 0.79, + "learning_rate": 1.0735889577414376e-05, + "loss": 0.1042, + "step": 352180 + }, + { + "epoch": 0.79, + "learning_rate": 1.0734771034205052e-05, + "loss": 0.101, + "step": 352190 + }, + { + "epoch": 0.79, + "learning_rate": 1.0733652490995727e-05, + "loss": 0.0999, + "step": 352200 + }, + { + "epoch": 0.79, + "learning_rate": 1.0732533947786403e-05, + "loss": 0.1023, + "step": 352210 + }, + { + "epoch": 0.79, + "learning_rate": 1.0731415404577079e-05, + "loss": 0.1003, + "step": 352220 + }, + { + "epoch": 0.79, + "learning_rate": 1.0730296861367755e-05, + "loss": 0.1009, + "step": 352230 + }, + { + "epoch": 0.79, + "learning_rate": 1.0729178318158432e-05, + "loss": 0.1006, + "step": 352240 + }, + { + "epoch": 0.79, + "learning_rate": 1.0728059774949106e-05, + "loss": 0.0988, + "step": 352250 + }, + { + "epoch": 0.79, + "learning_rate": 1.0726941231739782e-05, + "loss": 0.099, + "step": 352260 + }, + { + "epoch": 0.79, + "learning_rate": 1.0725822688530459e-05, + "loss": 0.0989, + "step": 352270 + }, + { + "epoch": 0.79, + "learning_rate": 1.0724704145321133e-05, + "loss": 0.1021, + "step": 352280 + }, + { + "epoch": 0.79, + "learning_rate": 1.0723585602111811e-05, + "loss": 0.1006, + "step": 352290 + }, + { + "epoch": 0.79, + "learning_rate": 1.0722467058902486e-05, + "loss": 0.1071, + "step": 352300 + }, + { + "epoch": 0.79, + "learning_rate": 1.0721348515693162e-05, + "loss": 0.0965, + "step": 352310 + }, + { + "epoch": 0.79, + "learning_rate": 1.0720229972483838e-05, + "loss": 0.1001, + "step": 352320 + }, + { + "epoch": 0.79, + "learning_rate": 1.0719111429274513e-05, + "loss": 0.0988, + "step": 352330 + }, + { + "epoch": 0.79, + "learning_rate": 1.0717992886065189e-05, + "loss": 0.1009, + "step": 352340 + }, + { + "epoch": 0.79, + "learning_rate": 1.0716874342855865e-05, + "loss": 0.0961, + "step": 352350 + }, + { + "epoch": 0.79, + "learning_rate": 1.071575579964654e-05, + "loss": 0.1025, + "step": 352360 + }, + { + "epoch": 0.79, + "learning_rate": 1.0714637256437218e-05, + "loss": 0.1041, + "step": 352370 + }, + { + "epoch": 0.79, + "learning_rate": 1.0713518713227892e-05, + "loss": 0.103, + "step": 352380 + }, + { + "epoch": 0.79, + "learning_rate": 1.0712400170018568e-05, + "loss": 0.1017, + "step": 352390 + }, + { + "epoch": 0.79, + "learning_rate": 1.0711281626809245e-05, + "loss": 0.1049, + "step": 352400 + }, + { + "epoch": 0.79, + "learning_rate": 1.0710163083599919e-05, + "loss": 0.1009, + "step": 352410 + }, + { + "epoch": 0.79, + "learning_rate": 1.0709044540390595e-05, + "loss": 0.1014, + "step": 352420 + }, + { + "epoch": 0.79, + "learning_rate": 1.0707925997181272e-05, + "loss": 0.1001, + "step": 352430 + }, + { + "epoch": 0.79, + "learning_rate": 1.0706807453971946e-05, + "loss": 0.1075, + "step": 352440 + }, + { + "epoch": 0.79, + "learning_rate": 1.0705688910762624e-05, + "loss": 0.1051, + "step": 352450 + }, + { + "epoch": 0.79, + "learning_rate": 1.0704570367553299e-05, + "loss": 0.0998, + "step": 352460 + }, + { + "epoch": 0.79, + "learning_rate": 1.0703451824343975e-05, + "loss": 0.1035, + "step": 352470 + }, + { + "epoch": 0.79, + "learning_rate": 1.0702333281134651e-05, + "loss": 0.1045, + "step": 352480 + }, + { + "epoch": 0.79, + "learning_rate": 1.0701214737925326e-05, + "loss": 0.1053, + "step": 352490 + }, + { + "epoch": 0.79, + "learning_rate": 1.0700096194716004e-05, + "loss": 0.0994, + "step": 352500 + }, + { + "epoch": 0.79, + "learning_rate": 1.0698977651506678e-05, + "loss": 0.1035, + "step": 352510 + }, + { + "epoch": 0.79, + "learning_rate": 1.0697859108297353e-05, + "loss": 0.102, + "step": 352520 + }, + { + "epoch": 0.79, + "learning_rate": 1.069674056508803e-05, + "loss": 0.0993, + "step": 352530 + }, + { + "epoch": 0.79, + "learning_rate": 1.0695622021878705e-05, + "loss": 0.0995, + "step": 352540 + }, + { + "epoch": 0.79, + "learning_rate": 1.0694503478669381e-05, + "loss": 0.0999, + "step": 352550 + }, + { + "epoch": 0.79, + "learning_rate": 1.0693384935460058e-05, + "loss": 0.1011, + "step": 352560 + }, + { + "epoch": 0.79, + "learning_rate": 1.0692266392250732e-05, + "loss": 0.1007, + "step": 352570 + }, + { + "epoch": 0.79, + "learning_rate": 1.069114784904141e-05, + "loss": 0.0997, + "step": 352580 + }, + { + "epoch": 0.79, + "learning_rate": 1.0690029305832085e-05, + "loss": 0.1059, + "step": 352590 + }, + { + "epoch": 0.79, + "learning_rate": 1.068891076262276e-05, + "loss": 0.1032, + "step": 352600 + }, + { + "epoch": 0.79, + "learning_rate": 1.0687792219413437e-05, + "loss": 0.1039, + "step": 352610 + }, + { + "epoch": 0.79, + "learning_rate": 1.0686673676204112e-05, + "loss": 0.1023, + "step": 352620 + }, + { + "epoch": 0.79, + "learning_rate": 1.068555513299479e-05, + "loss": 0.0993, + "step": 352630 + }, + { + "epoch": 0.79, + "learning_rate": 1.0684436589785464e-05, + "loss": 0.1011, + "step": 352640 + }, + { + "epoch": 0.79, + "learning_rate": 1.0683318046576139e-05, + "loss": 0.1022, + "step": 352650 + }, + { + "epoch": 0.79, + "learning_rate": 1.0682199503366816e-05, + "loss": 0.1021, + "step": 352660 + }, + { + "epoch": 0.79, + "learning_rate": 1.0681080960157491e-05, + "loss": 0.1059, + "step": 352670 + }, + { + "epoch": 0.79, + "learning_rate": 1.0679962416948167e-05, + "loss": 0.1032, + "step": 352680 + }, + { + "epoch": 0.79, + "learning_rate": 1.0678843873738843e-05, + "loss": 0.1028, + "step": 352690 + }, + { + "epoch": 0.79, + "learning_rate": 1.0677725330529518e-05, + "loss": 0.1037, + "step": 352700 + }, + { + "epoch": 0.79, + "learning_rate": 1.0676606787320196e-05, + "loss": 0.0979, + "step": 352710 + }, + { + "epoch": 0.79, + "learning_rate": 1.067548824411087e-05, + "loss": 0.1041, + "step": 352720 + }, + { + "epoch": 0.79, + "learning_rate": 1.0674369700901545e-05, + "loss": 0.1028, + "step": 352730 + }, + { + "epoch": 0.79, + "learning_rate": 1.0673363012013154e-05, + "loss": 0.0991, + "step": 352740 + }, + { + "epoch": 0.79, + "learning_rate": 1.067224446880383e-05, + "loss": 0.1053, + "step": 352750 + }, + { + "epoch": 0.79, + "learning_rate": 1.0671125925594506e-05, + "loss": 0.104, + "step": 352760 + }, + { + "epoch": 0.79, + "learning_rate": 1.0670007382385183e-05, + "loss": 0.0986, + "step": 352770 + }, + { + "epoch": 0.79, + "learning_rate": 1.0668888839175859e-05, + "loss": 0.1054, + "step": 352780 + }, + { + "epoch": 0.79, + "learning_rate": 1.0667770295966533e-05, + "loss": 0.1018, + "step": 352790 + }, + { + "epoch": 0.79, + "learning_rate": 1.066665175275721e-05, + "loss": 0.1024, + "step": 352800 + }, + { + "epoch": 0.79, + "learning_rate": 1.0665533209547886e-05, + "loss": 0.1036, + "step": 352810 + }, + { + "epoch": 0.79, + "learning_rate": 1.066441466633856e-05, + "loss": 0.1013, + "step": 352820 + }, + { + "epoch": 0.79, + "learning_rate": 1.0663296123129237e-05, + "loss": 0.1005, + "step": 352830 + }, + { + "epoch": 0.79, + "learning_rate": 1.0662177579919913e-05, + "loss": 0.1065, + "step": 352840 + }, + { + "epoch": 0.79, + "learning_rate": 1.0661059036710589e-05, + "loss": 0.0978, + "step": 352850 + }, + { + "epoch": 0.79, + "learning_rate": 1.0659940493501265e-05, + "loss": 0.1032, + "step": 352860 + }, + { + "epoch": 0.79, + "learning_rate": 1.065882195029194e-05, + "loss": 0.0992, + "step": 352870 + }, + { + "epoch": 0.79, + "learning_rate": 1.0657703407082616e-05, + "loss": 0.104, + "step": 352880 + }, + { + "epoch": 0.79, + "learning_rate": 1.0656584863873292e-05, + "loss": 0.1014, + "step": 352890 + }, + { + "epoch": 0.79, + "learning_rate": 1.0655466320663968e-05, + "loss": 0.1005, + "step": 352900 + }, + { + "epoch": 0.79, + "learning_rate": 1.0654347777454643e-05, + "loss": 0.1009, + "step": 352910 + }, + { + "epoch": 0.79, + "learning_rate": 1.065322923424532e-05, + "loss": 0.0993, + "step": 352920 + }, + { + "epoch": 0.79, + "learning_rate": 1.0652110691035995e-05, + "loss": 0.1033, + "step": 352930 + }, + { + "epoch": 0.79, + "learning_rate": 1.0650992147826672e-05, + "loss": 0.0968, + "step": 352940 + }, + { + "epoch": 0.79, + "learning_rate": 1.0649873604617346e-05, + "loss": 0.0999, + "step": 352950 + }, + { + "epoch": 0.79, + "learning_rate": 1.0648755061408022e-05, + "loss": 0.1004, + "step": 352960 + }, + { + "epoch": 0.79, + "learning_rate": 1.0647636518198699e-05, + "loss": 0.104, + "step": 352970 + }, + { + "epoch": 0.79, + "learning_rate": 1.0646517974989375e-05, + "loss": 0.1037, + "step": 352980 + }, + { + "epoch": 0.79, + "learning_rate": 1.064539943178005e-05, + "loss": 0.105, + "step": 352990 + }, + { + "epoch": 0.79, + "learning_rate": 1.0644280888570726e-05, + "loss": 0.1062, + "step": 353000 + }, + { + "epoch": 0.79, + "learning_rate": 1.0643162345361402e-05, + "loss": 0.1018, + "step": 353010 + }, + { + "epoch": 0.79, + "learning_rate": 1.0642043802152078e-05, + "loss": 0.1021, + "step": 353020 + }, + { + "epoch": 0.79, + "learning_rate": 1.0640925258942753e-05, + "loss": 0.1018, + "step": 353030 + }, + { + "epoch": 0.79, + "learning_rate": 1.0639806715733429e-05, + "loss": 0.1032, + "step": 353040 + }, + { + "epoch": 0.79, + "learning_rate": 1.0638688172524105e-05, + "loss": 0.0962, + "step": 353050 + }, + { + "epoch": 0.79, + "learning_rate": 1.0637569629314781e-05, + "loss": 0.0985, + "step": 353060 + }, + { + "epoch": 0.79, + "learning_rate": 1.0636451086105456e-05, + "loss": 0.1028, + "step": 353070 + }, + { + "epoch": 0.79, + "learning_rate": 1.0635332542896132e-05, + "loss": 0.101, + "step": 353080 + }, + { + "epoch": 0.79, + "learning_rate": 1.0634213999686808e-05, + "loss": 0.099, + "step": 353090 + }, + { + "epoch": 0.79, + "learning_rate": 1.0633095456477485e-05, + "loss": 0.104, + "step": 353100 + }, + { + "epoch": 0.79, + "learning_rate": 1.0631976913268161e-05, + "loss": 0.0999, + "step": 353110 + }, + { + "epoch": 0.79, + "learning_rate": 1.0630858370058835e-05, + "loss": 0.1025, + "step": 353120 + }, + { + "epoch": 0.79, + "learning_rate": 1.0629739826849512e-05, + "loss": 0.104, + "step": 353130 + }, + { + "epoch": 0.79, + "learning_rate": 1.0628621283640188e-05, + "loss": 0.1015, + "step": 353140 + }, + { + "epoch": 0.79, + "learning_rate": 1.0627502740430862e-05, + "loss": 0.103, + "step": 353150 + }, + { + "epoch": 0.79, + "learning_rate": 1.0626384197221539e-05, + "loss": 0.1016, + "step": 353160 + }, + { + "epoch": 0.79, + "learning_rate": 1.0625265654012215e-05, + "loss": 0.0994, + "step": 353170 + }, + { + "epoch": 0.79, + "learning_rate": 1.0624147110802891e-05, + "loss": 0.0965, + "step": 353180 + }, + { + "epoch": 0.79, + "learning_rate": 1.0623028567593567e-05, + "loss": 0.0964, + "step": 353190 + }, + { + "epoch": 0.79, + "learning_rate": 1.0621910024384242e-05, + "loss": 0.1, + "step": 353200 + }, + { + "epoch": 0.79, + "learning_rate": 1.0620791481174918e-05, + "loss": 0.1041, + "step": 353210 + }, + { + "epoch": 0.79, + "learning_rate": 1.0619672937965594e-05, + "loss": 0.0985, + "step": 353220 + }, + { + "epoch": 0.79, + "learning_rate": 1.0618554394756269e-05, + "loss": 0.0981, + "step": 353230 + }, + { + "epoch": 0.79, + "learning_rate": 1.0617435851546947e-05, + "loss": 0.0992, + "step": 353240 + }, + { + "epoch": 0.79, + "learning_rate": 1.0616317308337621e-05, + "loss": 0.1031, + "step": 353250 + }, + { + "epoch": 0.79, + "learning_rate": 1.0615198765128298e-05, + "loss": 0.1031, + "step": 353260 + }, + { + "epoch": 0.79, + "learning_rate": 1.0614080221918974e-05, + "loss": 0.1039, + "step": 353270 + }, + { + "epoch": 0.79, + "learning_rate": 1.0612961678709648e-05, + "loss": 0.0989, + "step": 353280 + }, + { + "epoch": 0.79, + "learning_rate": 1.0611843135500325e-05, + "loss": 0.1039, + "step": 353290 + }, + { + "epoch": 0.79, + "learning_rate": 1.0610724592291001e-05, + "loss": 0.1009, + "step": 353300 + }, + { + "epoch": 0.79, + "learning_rate": 1.0609606049081675e-05, + "loss": 0.1043, + "step": 353310 + }, + { + "epoch": 0.79, + "learning_rate": 1.0608487505872353e-05, + "loss": 0.0973, + "step": 353320 + }, + { + "epoch": 0.79, + "learning_rate": 1.0607368962663028e-05, + "loss": 0.102, + "step": 353330 + }, + { + "epoch": 0.79, + "learning_rate": 1.0606250419453704e-05, + "loss": 0.1039, + "step": 353340 + }, + { + "epoch": 0.79, + "learning_rate": 1.060513187624438e-05, + "loss": 0.1043, + "step": 353350 + }, + { + "epoch": 0.79, + "learning_rate": 1.0604013333035055e-05, + "loss": 0.1007, + "step": 353360 + }, + { + "epoch": 0.79, + "learning_rate": 1.0602894789825731e-05, + "loss": 0.103, + "step": 353370 + }, + { + "epoch": 0.79, + "learning_rate": 1.0601776246616407e-05, + "loss": 0.099, + "step": 353380 + }, + { + "epoch": 0.79, + "learning_rate": 1.0600657703407082e-05, + "loss": 0.1027, + "step": 353390 + }, + { + "epoch": 0.79, + "learning_rate": 1.059953916019776e-05, + "loss": 0.098, + "step": 353400 + }, + { + "epoch": 0.79, + "learning_rate": 1.0598420616988434e-05, + "loss": 0.1073, + "step": 353410 + }, + { + "epoch": 0.79, + "learning_rate": 1.059730207377911e-05, + "loss": 0.1027, + "step": 353420 + }, + { + "epoch": 0.79, + "learning_rate": 1.0596183530569787e-05, + "loss": 0.103, + "step": 353430 + }, + { + "epoch": 0.79, + "learning_rate": 1.0595064987360461e-05, + "loss": 0.1028, + "step": 353440 + }, + { + "epoch": 0.79, + "learning_rate": 1.059394644415114e-05, + "loss": 0.1014, + "step": 353450 + }, + { + "epoch": 0.79, + "learning_rate": 1.0592827900941814e-05, + "loss": 0.1069, + "step": 353460 + }, + { + "epoch": 0.79, + "learning_rate": 1.0591709357732488e-05, + "loss": 0.1013, + "step": 353470 + }, + { + "epoch": 0.79, + "learning_rate": 1.0590590814523166e-05, + "loss": 0.1045, + "step": 353480 + }, + { + "epoch": 0.79, + "learning_rate": 1.0589472271313841e-05, + "loss": 0.1031, + "step": 353490 + }, + { + "epoch": 0.79, + "learning_rate": 1.0588353728104517e-05, + "loss": 0.0998, + "step": 353500 + }, + { + "epoch": 0.79, + "learning_rate": 1.0587235184895193e-05, + "loss": 0.1031, + "step": 353510 + }, + { + "epoch": 0.79, + "learning_rate": 1.0586116641685868e-05, + "loss": 0.1018, + "step": 353520 + }, + { + "epoch": 0.79, + "learning_rate": 1.0584998098476546e-05, + "loss": 0.101, + "step": 353530 + }, + { + "epoch": 0.79, + "learning_rate": 1.058387955526722e-05, + "loss": 0.1031, + "step": 353540 + }, + { + "epoch": 0.79, + "learning_rate": 1.0582872866378829e-05, + "loss": 0.101, + "step": 353550 + }, + { + "epoch": 0.79, + "learning_rate": 1.0581754323169504e-05, + "loss": 0.101, + "step": 353560 + }, + { + "epoch": 0.79, + "learning_rate": 1.0580635779960182e-05, + "loss": 0.0998, + "step": 353570 + }, + { + "epoch": 0.79, + "learning_rate": 1.0579517236750856e-05, + "loss": 0.1029, + "step": 353580 + }, + { + "epoch": 0.79, + "learning_rate": 1.0578398693541532e-05, + "loss": 0.1001, + "step": 353590 + }, + { + "epoch": 0.79, + "learning_rate": 1.0577280150332209e-05, + "loss": 0.099, + "step": 353600 + }, + { + "epoch": 0.79, + "learning_rate": 1.0576161607122883e-05, + "loss": 0.1019, + "step": 353610 + }, + { + "epoch": 0.79, + "learning_rate": 1.057504306391356e-05, + "loss": 0.1009, + "step": 353620 + }, + { + "epoch": 0.79, + "learning_rate": 1.0573924520704236e-05, + "loss": 0.0976, + "step": 353630 + }, + { + "epoch": 0.79, + "learning_rate": 1.057280597749491e-05, + "loss": 0.1008, + "step": 353640 + }, + { + "epoch": 0.79, + "learning_rate": 1.0571687434285588e-05, + "loss": 0.1009, + "step": 353650 + }, + { + "epoch": 0.79, + "learning_rate": 1.0570568891076263e-05, + "loss": 0.0998, + "step": 353660 + }, + { + "epoch": 0.79, + "learning_rate": 1.0569450347866939e-05, + "loss": 0.0989, + "step": 353670 + }, + { + "epoch": 0.79, + "learning_rate": 1.0568331804657615e-05, + "loss": 0.1034, + "step": 353680 + }, + { + "epoch": 0.79, + "learning_rate": 1.056721326144829e-05, + "loss": 0.1018, + "step": 353690 + }, + { + "epoch": 0.79, + "learning_rate": 1.0566094718238966e-05, + "loss": 0.1074, + "step": 353700 + }, + { + "epoch": 0.79, + "learning_rate": 1.0564976175029642e-05, + "loss": 0.1006, + "step": 353710 + }, + { + "epoch": 0.79, + "learning_rate": 1.0563857631820318e-05, + "loss": 0.1009, + "step": 353720 + }, + { + "epoch": 0.79, + "learning_rate": 1.0562739088610995e-05, + "loss": 0.0992, + "step": 353730 + }, + { + "epoch": 0.79, + "learning_rate": 1.0561620545401669e-05, + "loss": 0.1033, + "step": 353740 + }, + { + "epoch": 0.79, + "learning_rate": 1.0560502002192345e-05, + "loss": 0.0997, + "step": 353750 + }, + { + "epoch": 0.79, + "learning_rate": 1.0559383458983022e-05, + "loss": 0.0989, + "step": 353760 + }, + { + "epoch": 0.79, + "learning_rate": 1.0558264915773696e-05, + "loss": 0.0989, + "step": 353770 + }, + { + "epoch": 0.79, + "learning_rate": 1.0557146372564372e-05, + "loss": 0.0993, + "step": 353780 + }, + { + "epoch": 0.79, + "learning_rate": 1.0556027829355049e-05, + "loss": 0.1059, + "step": 353790 + }, + { + "epoch": 0.79, + "learning_rate": 1.0554909286145725e-05, + "loss": 0.0987, + "step": 353800 + }, + { + "epoch": 0.79, + "learning_rate": 1.0553790742936401e-05, + "loss": 0.0999, + "step": 353810 + }, + { + "epoch": 0.79, + "learning_rate": 1.0552672199727076e-05, + "loss": 0.099, + "step": 353820 + }, + { + "epoch": 0.79, + "learning_rate": 1.0551553656517752e-05, + "loss": 0.1001, + "step": 353830 + }, + { + "epoch": 0.79, + "learning_rate": 1.0550435113308428e-05, + "loss": 0.1051, + "step": 353840 + }, + { + "epoch": 0.79, + "learning_rate": 1.0549316570099103e-05, + "loss": 0.1, + "step": 353850 + }, + { + "epoch": 0.79, + "learning_rate": 1.0548198026889779e-05, + "loss": 0.1022, + "step": 353860 + }, + { + "epoch": 0.79, + "learning_rate": 1.0547079483680455e-05, + "loss": 0.1009, + "step": 353870 + }, + { + "epoch": 0.79, + "learning_rate": 1.0545960940471131e-05, + "loss": 0.1021, + "step": 353880 + }, + { + "epoch": 0.79, + "learning_rate": 1.0544842397261807e-05, + "loss": 0.1049, + "step": 353890 + }, + { + "epoch": 0.79, + "learning_rate": 1.0543723854052482e-05, + "loss": 0.1025, + "step": 353900 + }, + { + "epoch": 0.79, + "learning_rate": 1.0542605310843158e-05, + "loss": 0.1004, + "step": 353910 + }, + { + "epoch": 0.79, + "learning_rate": 1.0541486767633834e-05, + "loss": 0.1012, + "step": 353920 + }, + { + "epoch": 0.79, + "learning_rate": 1.054036822442451e-05, + "loss": 0.099, + "step": 353930 + }, + { + "epoch": 0.79, + "learning_rate": 1.0539249681215185e-05, + "loss": 0.1011, + "step": 353940 + }, + { + "epoch": 0.79, + "learning_rate": 1.0538131138005862e-05, + "loss": 0.1004, + "step": 353950 + }, + { + "epoch": 0.79, + "learning_rate": 1.0537012594796538e-05, + "loss": 0.1031, + "step": 353960 + }, + { + "epoch": 0.79, + "learning_rate": 1.0535894051587214e-05, + "loss": 0.0982, + "step": 353970 + }, + { + "epoch": 0.79, + "learning_rate": 1.0534775508377889e-05, + "loss": 0.1017, + "step": 353980 + }, + { + "epoch": 0.79, + "learning_rate": 1.0533656965168565e-05, + "loss": 0.1019, + "step": 353990 + }, + { + "epoch": 0.79, + "learning_rate": 1.0532538421959241e-05, + "loss": 0.1038, + "step": 354000 + }, + { + "epoch": 0.79, + "learning_rate": 1.0531419878749917e-05, + "loss": 0.1042, + "step": 354010 + }, + { + "epoch": 0.79, + "learning_rate": 1.0530301335540592e-05, + "loss": 0.1016, + "step": 354020 + }, + { + "epoch": 0.79, + "learning_rate": 1.0529182792331268e-05, + "loss": 0.1031, + "step": 354030 + }, + { + "epoch": 0.79, + "learning_rate": 1.0528064249121944e-05, + "loss": 0.1024, + "step": 354040 + }, + { + "epoch": 0.79, + "learning_rate": 1.052694570591262e-05, + "loss": 0.1018, + "step": 354050 + }, + { + "epoch": 0.79, + "learning_rate": 1.0525827162703297e-05, + "loss": 0.1009, + "step": 354060 + }, + { + "epoch": 0.79, + "learning_rate": 1.0524708619493971e-05, + "loss": 0.1001, + "step": 354070 + }, + { + "epoch": 0.79, + "learning_rate": 1.0523590076284647e-05, + "loss": 0.0976, + "step": 354080 + }, + { + "epoch": 0.79, + "learning_rate": 1.0522471533075324e-05, + "loss": 0.1005, + "step": 354090 + }, + { + "epoch": 0.79, + "learning_rate": 1.0521352989865998e-05, + "loss": 0.1004, + "step": 354100 + }, + { + "epoch": 0.79, + "learning_rate": 1.0520234446656674e-05, + "loss": 0.098, + "step": 354110 + }, + { + "epoch": 0.79, + "learning_rate": 1.051911590344735e-05, + "loss": 0.1032, + "step": 354120 + }, + { + "epoch": 0.79, + "learning_rate": 1.0517997360238027e-05, + "loss": 0.1005, + "step": 354130 + }, + { + "epoch": 0.79, + "learning_rate": 1.0516878817028703e-05, + "loss": 0.1007, + "step": 354140 + }, + { + "epoch": 0.79, + "learning_rate": 1.0515760273819378e-05, + "loss": 0.0997, + "step": 354150 + }, + { + "epoch": 0.79, + "learning_rate": 1.0514641730610054e-05, + "loss": 0.0971, + "step": 354160 + }, + { + "epoch": 0.79, + "learning_rate": 1.051352318740073e-05, + "loss": 0.1028, + "step": 354170 + }, + { + "epoch": 0.79, + "learning_rate": 1.0512404644191405e-05, + "loss": 0.101, + "step": 354180 + }, + { + "epoch": 0.79, + "learning_rate": 1.0511286100982081e-05, + "loss": 0.1008, + "step": 354190 + }, + { + "epoch": 0.79, + "learning_rate": 1.0510167557772757e-05, + "loss": 0.1024, + "step": 354200 + }, + { + "epoch": 0.79, + "learning_rate": 1.0509049014563433e-05, + "loss": 0.1012, + "step": 354210 + }, + { + "epoch": 0.79, + "learning_rate": 1.050793047135411e-05, + "loss": 0.1006, + "step": 354220 + }, + { + "epoch": 0.79, + "learning_rate": 1.0506811928144784e-05, + "loss": 0.1021, + "step": 354230 + }, + { + "epoch": 0.79, + "learning_rate": 1.050569338493546e-05, + "loss": 0.0988, + "step": 354240 + }, + { + "epoch": 0.79, + "learning_rate": 1.0504574841726137e-05, + "loss": 0.1005, + "step": 354250 + }, + { + "epoch": 0.79, + "learning_rate": 1.0503456298516811e-05, + "loss": 0.1028, + "step": 354260 + }, + { + "epoch": 0.79, + "learning_rate": 1.0502337755307489e-05, + "loss": 0.0991, + "step": 354270 + }, + { + "epoch": 0.79, + "learning_rate": 1.0501219212098164e-05, + "loss": 0.101, + "step": 354280 + }, + { + "epoch": 0.79, + "learning_rate": 1.050010066888884e-05, + "loss": 0.1008, + "step": 354290 + }, + { + "epoch": 0.79, + "learning_rate": 1.0498982125679516e-05, + "loss": 0.0989, + "step": 354300 + }, + { + "epoch": 0.79, + "learning_rate": 1.049786358247019e-05, + "loss": 0.1011, + "step": 354310 + }, + { + "epoch": 0.79, + "learning_rate": 1.0496745039260867e-05, + "loss": 0.0985, + "step": 354320 + }, + { + "epoch": 0.79, + "learning_rate": 1.0495626496051543e-05, + "loss": 0.1036, + "step": 354330 + }, + { + "epoch": 0.79, + "learning_rate": 1.0494507952842218e-05, + "loss": 0.102, + "step": 354340 + }, + { + "epoch": 0.79, + "learning_rate": 1.0493389409632896e-05, + "loss": 0.103, + "step": 354350 + }, + { + "epoch": 0.79, + "learning_rate": 1.049227086642357e-05, + "loss": 0.1026, + "step": 354360 + }, + { + "epoch": 0.79, + "learning_rate": 1.0491152323214246e-05, + "loss": 0.1009, + "step": 354370 + }, + { + "epoch": 0.79, + "learning_rate": 1.0490033780004923e-05, + "loss": 0.1, + "step": 354380 + }, + { + "epoch": 0.79, + "learning_rate": 1.0488915236795597e-05, + "loss": 0.1055, + "step": 354390 + }, + { + "epoch": 0.79, + "learning_rate": 1.0487796693586275e-05, + "loss": 0.0966, + "step": 354400 + }, + { + "epoch": 0.79, + "learning_rate": 1.048667815037695e-05, + "loss": 0.1038, + "step": 354410 + }, + { + "epoch": 0.79, + "learning_rate": 1.0485559607167624e-05, + "loss": 0.0984, + "step": 354420 + }, + { + "epoch": 0.79, + "learning_rate": 1.0484441063958302e-05, + "loss": 0.1028, + "step": 354430 + }, + { + "epoch": 0.79, + "learning_rate": 1.0483322520748977e-05, + "loss": 0.1034, + "step": 354440 + }, + { + "epoch": 0.79, + "learning_rate": 1.0482203977539653e-05, + "loss": 0.103, + "step": 354450 + }, + { + "epoch": 0.79, + "learning_rate": 1.0481085434330329e-05, + "loss": 0.1036, + "step": 354460 + }, + { + "epoch": 0.79, + "learning_rate": 1.0479966891121004e-05, + "loss": 0.1003, + "step": 354470 + }, + { + "epoch": 0.79, + "learning_rate": 1.0478848347911682e-05, + "loss": 0.0999, + "step": 354480 + }, + { + "epoch": 0.79, + "learning_rate": 1.0477729804702356e-05, + "loss": 0.104, + "step": 354490 + }, + { + "epoch": 0.79, + "learning_rate": 1.047661126149303e-05, + "loss": 0.1018, + "step": 354500 + }, + { + "epoch": 0.79, + "learning_rate": 1.0475492718283709e-05, + "loss": 0.1036, + "step": 354510 + }, + { + "epoch": 0.79, + "learning_rate": 1.0474374175074383e-05, + "loss": 0.1007, + "step": 354520 + }, + { + "epoch": 0.79, + "learning_rate": 1.047325563186506e-05, + "loss": 0.1015, + "step": 354530 + }, + { + "epoch": 0.79, + "learning_rate": 1.0472137088655736e-05, + "loss": 0.1016, + "step": 354540 + }, + { + "epoch": 0.79, + "learning_rate": 1.047101854544641e-05, + "loss": 0.0978, + "step": 354550 + }, + { + "epoch": 0.79, + "learning_rate": 1.0469900002237088e-05, + "loss": 0.1014, + "step": 354560 + }, + { + "epoch": 0.79, + "learning_rate": 1.0468781459027763e-05, + "loss": 0.1014, + "step": 354570 + }, + { + "epoch": 0.79, + "learning_rate": 1.0467662915818439e-05, + "loss": 0.101, + "step": 354580 + }, + { + "epoch": 0.79, + "learning_rate": 1.0466544372609115e-05, + "loss": 0.1037, + "step": 354590 + }, + { + "epoch": 0.79, + "learning_rate": 1.046542582939979e-05, + "loss": 0.1023, + "step": 354600 + }, + { + "epoch": 0.79, + "learning_rate": 1.0464307286190466e-05, + "loss": 0.0984, + "step": 354610 + }, + { + "epoch": 0.79, + "learning_rate": 1.0463188742981142e-05, + "loss": 0.0999, + "step": 354620 + }, + { + "epoch": 0.79, + "learning_rate": 1.0462070199771817e-05, + "loss": 0.098, + "step": 354630 + }, + { + "epoch": 0.79, + "learning_rate": 1.0460951656562495e-05, + "loss": 0.1001, + "step": 354640 + }, + { + "epoch": 0.79, + "learning_rate": 1.0459833113353169e-05, + "loss": 0.0973, + "step": 354650 + }, + { + "epoch": 0.79, + "learning_rate": 1.0458714570143845e-05, + "loss": 0.1022, + "step": 354660 + }, + { + "epoch": 0.79, + "learning_rate": 1.0457596026934522e-05, + "loss": 0.0981, + "step": 354670 + }, + { + "epoch": 0.79, + "learning_rate": 1.0456477483725196e-05, + "loss": 0.0993, + "step": 354680 + }, + { + "epoch": 0.79, + "learning_rate": 1.0455358940515872e-05, + "loss": 0.1019, + "step": 354690 + }, + { + "epoch": 0.79, + "learning_rate": 1.0454240397306549e-05, + "loss": 0.0984, + "step": 354700 + }, + { + "epoch": 0.79, + "learning_rate": 1.0453121854097225e-05, + "loss": 0.1009, + "step": 354710 + }, + { + "epoch": 0.79, + "learning_rate": 1.0452003310887901e-05, + "loss": 0.0997, + "step": 354720 + }, + { + "epoch": 0.79, + "learning_rate": 1.0450884767678576e-05, + "loss": 0.1009, + "step": 354730 + }, + { + "epoch": 0.79, + "learning_rate": 1.0449766224469252e-05, + "loss": 0.1046, + "step": 354740 + }, + { + "epoch": 0.79, + "learning_rate": 1.0448647681259928e-05, + "loss": 0.1017, + "step": 354750 + }, + { + "epoch": 0.79, + "learning_rate": 1.0447529138050603e-05, + "loss": 0.1051, + "step": 354760 + }, + { + "epoch": 0.79, + "learning_rate": 1.0446410594841279e-05, + "loss": 0.1012, + "step": 354770 + }, + { + "epoch": 0.79, + "learning_rate": 1.0445292051631955e-05, + "loss": 0.0983, + "step": 354780 + }, + { + "epoch": 0.79, + "learning_rate": 1.0444173508422631e-05, + "loss": 0.1035, + "step": 354790 + }, + { + "epoch": 0.79, + "learning_rate": 1.0443054965213307e-05, + "loss": 0.097, + "step": 354800 + }, + { + "epoch": 0.79, + "learning_rate": 1.0441936422003982e-05, + "loss": 0.1018, + "step": 354810 + }, + { + "epoch": 0.79, + "learning_rate": 1.0440817878794658e-05, + "loss": 0.1046, + "step": 354820 + }, + { + "epoch": 0.79, + "learning_rate": 1.0439699335585334e-05, + "loss": 0.1004, + "step": 354830 + }, + { + "epoch": 0.79, + "learning_rate": 1.0438580792376009e-05, + "loss": 0.1054, + "step": 354840 + }, + { + "epoch": 0.79, + "learning_rate": 1.0437462249166685e-05, + "loss": 0.1007, + "step": 354850 + }, + { + "epoch": 0.79, + "learning_rate": 1.0436343705957361e-05, + "loss": 0.1029, + "step": 354860 + }, + { + "epoch": 0.79, + "learning_rate": 1.0435225162748038e-05, + "loss": 0.1002, + "step": 354870 + }, + { + "epoch": 0.79, + "learning_rate": 1.0434106619538714e-05, + "loss": 0.1034, + "step": 354880 + }, + { + "epoch": 0.79, + "learning_rate": 1.0432988076329389e-05, + "loss": 0.0992, + "step": 354890 + }, + { + "epoch": 0.79, + "learning_rate": 1.0431869533120065e-05, + "loss": 0.1024, + "step": 354900 + }, + { + "epoch": 0.79, + "learning_rate": 1.0430750989910741e-05, + "loss": 0.0986, + "step": 354910 + }, + { + "epoch": 0.79, + "learning_rate": 1.0429632446701417e-05, + "loss": 0.1, + "step": 354920 + }, + { + "epoch": 0.79, + "learning_rate": 1.0428513903492092e-05, + "loss": 0.1011, + "step": 354930 + }, + { + "epoch": 0.79, + "learning_rate": 1.0427395360282768e-05, + "loss": 0.0999, + "step": 354940 + }, + { + "epoch": 0.79, + "learning_rate": 1.0426276817073444e-05, + "loss": 0.1052, + "step": 354950 + }, + { + "epoch": 0.79, + "learning_rate": 1.042515827386412e-05, + "loss": 0.1005, + "step": 354960 + }, + { + "epoch": 0.79, + "learning_rate": 1.0424039730654795e-05, + "loss": 0.101, + "step": 354970 + }, + { + "epoch": 0.79, + "learning_rate": 1.0422921187445471e-05, + "loss": 0.1005, + "step": 354980 + }, + { + "epoch": 0.79, + "learning_rate": 1.0421802644236147e-05, + "loss": 0.0984, + "step": 354990 + }, + { + "epoch": 0.79, + "learning_rate": 1.0420684101026824e-05, + "loss": 0.1039, + "step": 355000 + }, + { + "epoch": 0.79, + "learning_rate": 1.0419565557817498e-05, + "loss": 0.1024, + "step": 355010 + }, + { + "epoch": 0.79, + "learning_rate": 1.0418447014608174e-05, + "loss": 0.103, + "step": 355020 + }, + { + "epoch": 0.79, + "learning_rate": 1.041732847139885e-05, + "loss": 0.1009, + "step": 355030 + }, + { + "epoch": 0.79, + "learning_rate": 1.0416209928189527e-05, + "loss": 0.0972, + "step": 355040 + }, + { + "epoch": 0.79, + "learning_rate": 1.0415091384980203e-05, + "loss": 0.0964, + "step": 355050 + }, + { + "epoch": 0.79, + "learning_rate": 1.0413972841770878e-05, + "loss": 0.0971, + "step": 355060 + }, + { + "epoch": 0.79, + "learning_rate": 1.0412854298561554e-05, + "loss": 0.1007, + "step": 355070 + }, + { + "epoch": 0.79, + "learning_rate": 1.041173575535223e-05, + "loss": 0.1022, + "step": 355080 + }, + { + "epoch": 0.79, + "learning_rate": 1.0410617212142905e-05, + "loss": 0.1023, + "step": 355090 + }, + { + "epoch": 0.79, + "learning_rate": 1.0409498668933581e-05, + "loss": 0.1028, + "step": 355100 + }, + { + "epoch": 0.79, + "learning_rate": 1.0408380125724257e-05, + "loss": 0.0961, + "step": 355110 + }, + { + "epoch": 0.79, + "learning_rate": 1.0407261582514933e-05, + "loss": 0.1021, + "step": 355120 + }, + { + "epoch": 0.79, + "learning_rate": 1.040614303930561e-05, + "loss": 0.1002, + "step": 355130 + }, + { + "epoch": 0.79, + "learning_rate": 1.0405024496096284e-05, + "loss": 0.1022, + "step": 355140 + }, + { + "epoch": 0.79, + "learning_rate": 1.040390595288696e-05, + "loss": 0.0982, + "step": 355150 + }, + { + "epoch": 0.79, + "learning_rate": 1.0402787409677637e-05, + "loss": 0.1057, + "step": 355160 + }, + { + "epoch": 0.79, + "learning_rate": 1.0401668866468311e-05, + "loss": 0.0984, + "step": 355170 + }, + { + "epoch": 0.79, + "learning_rate": 1.0400550323258987e-05, + "loss": 0.1057, + "step": 355180 + }, + { + "epoch": 0.79, + "learning_rate": 1.0399431780049664e-05, + "loss": 0.1057, + "step": 355190 + }, + { + "epoch": 0.79, + "learning_rate": 1.039831323684034e-05, + "loss": 0.1029, + "step": 355200 + }, + { + "epoch": 0.79, + "learning_rate": 1.0397194693631016e-05, + "loss": 0.1023, + "step": 355210 + }, + { + "epoch": 0.79, + "learning_rate": 1.039607615042169e-05, + "loss": 0.1023, + "step": 355220 + }, + { + "epoch": 0.79, + "learning_rate": 1.0394957607212367e-05, + "loss": 0.0953, + "step": 355230 + }, + { + "epoch": 0.79, + "learning_rate": 1.0393839064003043e-05, + "loss": 0.1011, + "step": 355240 + }, + { + "epoch": 0.79, + "learning_rate": 1.0392720520793718e-05, + "loss": 0.1026, + "step": 355250 + }, + { + "epoch": 0.79, + "learning_rate": 1.0391601977584396e-05, + "loss": 0.1053, + "step": 355260 + }, + { + "epoch": 0.79, + "learning_rate": 1.039048343437507e-05, + "loss": 0.1024, + "step": 355270 + }, + { + "epoch": 0.79, + "learning_rate": 1.0389364891165746e-05, + "loss": 0.0985, + "step": 355280 + }, + { + "epoch": 0.79, + "learning_rate": 1.0388246347956423e-05, + "loss": 0.0991, + "step": 355290 + }, + { + "epoch": 0.79, + "learning_rate": 1.0387127804747097e-05, + "loss": 0.1012, + "step": 355300 + }, + { + "epoch": 0.79, + "learning_rate": 1.0386009261537773e-05, + "loss": 0.1017, + "step": 355310 + }, + { + "epoch": 0.79, + "learning_rate": 1.038489071832845e-05, + "loss": 0.1003, + "step": 355320 + }, + { + "epoch": 0.79, + "learning_rate": 1.0383772175119124e-05, + "loss": 0.0968, + "step": 355330 + }, + { + "epoch": 0.79, + "learning_rate": 1.0382653631909802e-05, + "loss": 0.1005, + "step": 355340 + }, + { + "epoch": 0.79, + "learning_rate": 1.0381535088700477e-05, + "loss": 0.1044, + "step": 355350 + }, + { + "epoch": 0.79, + "learning_rate": 1.0380416545491153e-05, + "loss": 0.1006, + "step": 355360 + }, + { + "epoch": 0.79, + "learning_rate": 1.0379298002281829e-05, + "loss": 0.1036, + "step": 355370 + }, + { + "epoch": 0.79, + "learning_rate": 1.0378179459072504e-05, + "loss": 0.1057, + "step": 355380 + }, + { + "epoch": 0.79, + "learning_rate": 1.037706091586318e-05, + "loss": 0.1012, + "step": 355390 + }, + { + "epoch": 0.79, + "learning_rate": 1.0375942372653856e-05, + "loss": 0.101, + "step": 355400 + }, + { + "epoch": 0.79, + "learning_rate": 1.037482382944453e-05, + "loss": 0.0966, + "step": 355410 + }, + { + "epoch": 0.79, + "learning_rate": 1.0373705286235209e-05, + "loss": 0.1023, + "step": 355420 + }, + { + "epoch": 0.79, + "learning_rate": 1.0372586743025883e-05, + "loss": 0.1021, + "step": 355430 + }, + { + "epoch": 0.79, + "learning_rate": 1.037146819981656e-05, + "loss": 0.1051, + "step": 355440 + }, + { + "epoch": 0.79, + "learning_rate": 1.0370349656607236e-05, + "loss": 0.1001, + "step": 355450 + }, + { + "epoch": 0.79, + "learning_rate": 1.036923111339791e-05, + "loss": 0.103, + "step": 355460 + }, + { + "epoch": 0.79, + "learning_rate": 1.0368112570188588e-05, + "loss": 0.0993, + "step": 355470 + }, + { + "epoch": 0.79, + "learning_rate": 1.0366994026979263e-05, + "loss": 0.0987, + "step": 355480 + }, + { + "epoch": 0.79, + "learning_rate": 1.0365875483769937e-05, + "loss": 0.1008, + "step": 355490 + }, + { + "epoch": 0.79, + "learning_rate": 1.0364756940560615e-05, + "loss": 0.1051, + "step": 355500 + }, + { + "epoch": 0.79, + "learning_rate": 1.036363839735129e-05, + "loss": 0.0992, + "step": 355510 + }, + { + "epoch": 0.79, + "learning_rate": 1.0362519854141966e-05, + "loss": 0.0968, + "step": 355520 + }, + { + "epoch": 0.79, + "learning_rate": 1.0361401310932642e-05, + "loss": 0.0993, + "step": 355530 + }, + { + "epoch": 0.79, + "learning_rate": 1.0360282767723317e-05, + "loss": 0.099, + "step": 355540 + }, + { + "epoch": 0.79, + "learning_rate": 1.0359164224513995e-05, + "loss": 0.096, + "step": 355550 + }, + { + "epoch": 0.79, + "learning_rate": 1.0358045681304669e-05, + "loss": 0.1023, + "step": 355560 + }, + { + "epoch": 0.79, + "learning_rate": 1.0356927138095345e-05, + "loss": 0.098, + "step": 355570 + }, + { + "epoch": 0.79, + "learning_rate": 1.0355808594886022e-05, + "loss": 0.1034, + "step": 355580 + }, + { + "epoch": 0.79, + "learning_rate": 1.0354690051676696e-05, + "loss": 0.0961, + "step": 355590 + }, + { + "epoch": 0.79, + "learning_rate": 1.0353571508467374e-05, + "loss": 0.1049, + "step": 355600 + }, + { + "epoch": 0.79, + "learning_rate": 1.0352452965258049e-05, + "loss": 0.0988, + "step": 355610 + }, + { + "epoch": 0.79, + "learning_rate": 1.0351334422048723e-05, + "loss": 0.1006, + "step": 355620 + }, + { + "epoch": 0.79, + "learning_rate": 1.0350215878839401e-05, + "loss": 0.0979, + "step": 355630 + }, + { + "epoch": 0.79, + "learning_rate": 1.0349097335630076e-05, + "loss": 0.099, + "step": 355640 + }, + { + "epoch": 0.79, + "learning_rate": 1.0347978792420752e-05, + "loss": 0.0967, + "step": 355650 + }, + { + "epoch": 0.79, + "learning_rate": 1.0346860249211428e-05, + "loss": 0.098, + "step": 355660 + }, + { + "epoch": 0.79, + "learning_rate": 1.0345741706002103e-05, + "loss": 0.1073, + "step": 355670 + }, + { + "epoch": 0.79, + "learning_rate": 1.034462316279278e-05, + "loss": 0.1008, + "step": 355680 + }, + { + "epoch": 0.79, + "learning_rate": 1.0343504619583455e-05, + "loss": 0.102, + "step": 355690 + }, + { + "epoch": 0.79, + "learning_rate": 1.034238607637413e-05, + "loss": 0.1007, + "step": 355700 + }, + { + "epoch": 0.79, + "learning_rate": 1.0341267533164807e-05, + "loss": 0.0993, + "step": 355710 + }, + { + "epoch": 0.79, + "learning_rate": 1.0340148989955482e-05, + "loss": 0.0991, + "step": 355720 + }, + { + "epoch": 0.79, + "learning_rate": 1.0339030446746158e-05, + "loss": 0.1039, + "step": 355730 + }, + { + "epoch": 0.79, + "learning_rate": 1.0337911903536834e-05, + "loss": 0.1002, + "step": 355740 + }, + { + "epoch": 0.79, + "learning_rate": 1.0336793360327509e-05, + "loss": 0.0993, + "step": 355750 + }, + { + "epoch": 0.79, + "learning_rate": 1.0335674817118187e-05, + "loss": 0.1019, + "step": 355760 + }, + { + "epoch": 0.79, + "learning_rate": 1.0334556273908861e-05, + "loss": 0.1091, + "step": 355770 + }, + { + "epoch": 0.79, + "learning_rate": 1.0333437730699538e-05, + "loss": 0.0996, + "step": 355780 + }, + { + "epoch": 0.79, + "learning_rate": 1.0332319187490214e-05, + "loss": 0.1017, + "step": 355790 + }, + { + "epoch": 0.79, + "learning_rate": 1.0331200644280888e-05, + "loss": 0.1013, + "step": 355800 + }, + { + "epoch": 0.79, + "learning_rate": 1.0330082101071565e-05, + "loss": 0.1012, + "step": 355810 + }, + { + "epoch": 0.79, + "learning_rate": 1.0328963557862241e-05, + "loss": 0.1031, + "step": 355820 + }, + { + "epoch": 0.79, + "learning_rate": 1.0327845014652915e-05, + "loss": 0.1037, + "step": 355830 + }, + { + "epoch": 0.79, + "learning_rate": 1.0326726471443593e-05, + "loss": 0.0991, + "step": 355840 + }, + { + "epoch": 0.79, + "learning_rate": 1.0325607928234268e-05, + "loss": 0.1008, + "step": 355850 + }, + { + "epoch": 0.79, + "learning_rate": 1.0324489385024944e-05, + "loss": 0.0986, + "step": 355860 + }, + { + "epoch": 0.79, + "learning_rate": 1.032337084181562e-05, + "loss": 0.1043, + "step": 355870 + }, + { + "epoch": 0.79, + "learning_rate": 1.0322252298606295e-05, + "loss": 0.0966, + "step": 355880 + }, + { + "epoch": 0.79, + "learning_rate": 1.0321133755396971e-05, + "loss": 0.1017, + "step": 355890 + }, + { + "epoch": 0.79, + "learning_rate": 1.0320015212187647e-05, + "loss": 0.0986, + "step": 355900 + }, + { + "epoch": 0.79, + "learning_rate": 1.0318896668978324e-05, + "loss": 0.1068, + "step": 355910 + }, + { + "epoch": 0.79, + "learning_rate": 1.0317778125769e-05, + "loss": 0.0988, + "step": 355920 + }, + { + "epoch": 0.79, + "learning_rate": 1.0316659582559674e-05, + "loss": 0.095, + "step": 355930 + }, + { + "epoch": 0.79, + "learning_rate": 1.031554103935035e-05, + "loss": 0.101, + "step": 355940 + }, + { + "epoch": 0.79, + "learning_rate": 1.0314422496141027e-05, + "loss": 0.1002, + "step": 355950 + }, + { + "epoch": 0.79, + "learning_rate": 1.0313303952931701e-05, + "loss": 0.1022, + "step": 355960 + }, + { + "epoch": 0.79, + "learning_rate": 1.0312185409722378e-05, + "loss": 0.0993, + "step": 355970 + }, + { + "epoch": 0.79, + "learning_rate": 1.0311066866513054e-05, + "loss": 0.096, + "step": 355980 + }, + { + "epoch": 0.79, + "learning_rate": 1.030994832330373e-05, + "loss": 0.1003, + "step": 355990 + }, + { + "epoch": 0.79, + "learning_rate": 1.0308829780094406e-05, + "loss": 0.1066, + "step": 356000 + }, + { + "epoch": 0.79, + "learning_rate": 1.0307711236885081e-05, + "loss": 0.0982, + "step": 356010 + }, + { + "epoch": 0.79, + "learning_rate": 1.0306592693675757e-05, + "loss": 0.0984, + "step": 356020 + }, + { + "epoch": 0.79, + "learning_rate": 1.0305474150466433e-05, + "loss": 0.0986, + "step": 356030 + }, + { + "epoch": 0.79, + "learning_rate": 1.0304355607257108e-05, + "loss": 0.1, + "step": 356040 + }, + { + "epoch": 0.79, + "learning_rate": 1.0303237064047784e-05, + "loss": 0.102, + "step": 356050 + }, + { + "epoch": 0.79, + "learning_rate": 1.030211852083846e-05, + "loss": 0.0986, + "step": 356060 + }, + { + "epoch": 0.79, + "learning_rate": 1.0300999977629137e-05, + "loss": 0.1004, + "step": 356070 + }, + { + "epoch": 0.79, + "learning_rate": 1.0299881434419813e-05, + "loss": 0.1054, + "step": 356080 + }, + { + "epoch": 0.79, + "learning_rate": 1.0298762891210487e-05, + "loss": 0.1014, + "step": 356090 + }, + { + "epoch": 0.79, + "learning_rate": 1.0297644348001164e-05, + "loss": 0.0982, + "step": 356100 + }, + { + "epoch": 0.79, + "learning_rate": 1.029652580479184e-05, + "loss": 0.1064, + "step": 356110 + }, + { + "epoch": 0.79, + "learning_rate": 1.0295407261582516e-05, + "loss": 0.1014, + "step": 356120 + }, + { + "epoch": 0.79, + "learning_rate": 1.029428871837319e-05, + "loss": 0.0961, + "step": 356130 + }, + { + "epoch": 0.79, + "learning_rate": 1.0293170175163867e-05, + "loss": 0.1014, + "step": 356140 + }, + { + "epoch": 0.79, + "learning_rate": 1.0292051631954543e-05, + "loss": 0.1014, + "step": 356150 + }, + { + "epoch": 0.79, + "learning_rate": 1.029093308874522e-05, + "loss": 0.1022, + "step": 356160 + }, + { + "epoch": 0.8, + "learning_rate": 1.0289814545535894e-05, + "loss": 0.1001, + "step": 356170 + }, + { + "epoch": 0.8, + "learning_rate": 1.028869600232657e-05, + "loss": 0.0974, + "step": 356180 + }, + { + "epoch": 0.8, + "learning_rate": 1.0287577459117246e-05, + "loss": 0.1013, + "step": 356190 + }, + { + "epoch": 0.8, + "learning_rate": 1.0286458915907923e-05, + "loss": 0.1015, + "step": 356200 + }, + { + "epoch": 0.8, + "learning_rate": 1.0285340372698597e-05, + "loss": 0.1033, + "step": 356210 + }, + { + "epoch": 0.8, + "learning_rate": 1.0284221829489273e-05, + "loss": 0.1002, + "step": 356220 + }, + { + "epoch": 0.8, + "learning_rate": 1.028310328627995e-05, + "loss": 0.1037, + "step": 356230 + }, + { + "epoch": 0.8, + "learning_rate": 1.0281984743070626e-05, + "loss": 0.0988, + "step": 356240 + }, + { + "epoch": 0.8, + "learning_rate": 1.0280866199861302e-05, + "loss": 0.1031, + "step": 356250 + }, + { + "epoch": 0.8, + "learning_rate": 1.0279747656651977e-05, + "loss": 0.1039, + "step": 356260 + }, + { + "epoch": 0.8, + "learning_rate": 1.0278629113442653e-05, + "loss": 0.0998, + "step": 356270 + }, + { + "epoch": 0.8, + "learning_rate": 1.0277510570233329e-05, + "loss": 0.1023, + "step": 356280 + }, + { + "epoch": 0.8, + "learning_rate": 1.0276392027024004e-05, + "loss": 0.0951, + "step": 356290 + }, + { + "epoch": 0.8, + "learning_rate": 1.027527348381468e-05, + "loss": 0.1016, + "step": 356300 + }, + { + "epoch": 0.8, + "learning_rate": 1.0274154940605356e-05, + "loss": 0.1006, + "step": 356310 + }, + { + "epoch": 0.8, + "learning_rate": 1.0273036397396032e-05, + "loss": 0.103, + "step": 356320 + }, + { + "epoch": 0.8, + "learning_rate": 1.0271917854186709e-05, + "loss": 0.1001, + "step": 356330 + }, + { + "epoch": 0.8, + "learning_rate": 1.0270799310977383e-05, + "loss": 0.1009, + "step": 356340 + }, + { + "epoch": 0.8, + "learning_rate": 1.026968076776806e-05, + "loss": 0.1057, + "step": 356350 + }, + { + "epoch": 0.8, + "learning_rate": 1.0268562224558736e-05, + "loss": 0.1045, + "step": 356360 + }, + { + "epoch": 0.8, + "learning_rate": 1.026744368134941e-05, + "loss": 0.1032, + "step": 356370 + }, + { + "epoch": 0.8, + "learning_rate": 1.0266325138140086e-05, + "loss": 0.0981, + "step": 356380 + }, + { + "epoch": 0.8, + "learning_rate": 1.0265206594930763e-05, + "loss": 0.1038, + "step": 356390 + }, + { + "epoch": 0.8, + "learning_rate": 1.0264088051721439e-05, + "loss": 0.1027, + "step": 356400 + }, + { + "epoch": 0.8, + "learning_rate": 1.0262969508512115e-05, + "loss": 0.1037, + "step": 356410 + }, + { + "epoch": 0.8, + "learning_rate": 1.026185096530279e-05, + "loss": 0.1035, + "step": 356420 + }, + { + "epoch": 0.8, + "learning_rate": 1.0260732422093466e-05, + "loss": 0.0999, + "step": 356430 + }, + { + "epoch": 0.8, + "learning_rate": 1.0259613878884142e-05, + "loss": 0.1058, + "step": 356440 + }, + { + "epoch": 0.8, + "learning_rate": 1.0258495335674817e-05, + "loss": 0.0981, + "step": 356450 + }, + { + "epoch": 0.8, + "learning_rate": 1.0257376792465494e-05, + "loss": 0.1041, + "step": 356460 + }, + { + "epoch": 0.8, + "learning_rate": 1.0256258249256169e-05, + "loss": 0.1003, + "step": 356470 + }, + { + "epoch": 0.8, + "learning_rate": 1.0255139706046845e-05, + "loss": 0.0998, + "step": 356480 + }, + { + "epoch": 0.8, + "learning_rate": 1.0254021162837522e-05, + "loss": 0.0988, + "step": 356490 + }, + { + "epoch": 0.8, + "learning_rate": 1.0252902619628196e-05, + "loss": 0.1017, + "step": 356500 + }, + { + "epoch": 0.8, + "learning_rate": 1.0251784076418872e-05, + "loss": 0.1029, + "step": 356510 + }, + { + "epoch": 0.8, + "learning_rate": 1.0250665533209549e-05, + "loss": 0.1049, + "step": 356520 + }, + { + "epoch": 0.8, + "learning_rate": 1.0249546990000223e-05, + "loss": 0.0984, + "step": 356530 + }, + { + "epoch": 0.8, + "learning_rate": 1.0248428446790901e-05, + "loss": 0.1001, + "step": 356540 + }, + { + "epoch": 0.8, + "learning_rate": 1.0247309903581576e-05, + "loss": 0.1006, + "step": 356550 + }, + { + "epoch": 0.8, + "learning_rate": 1.0246191360372252e-05, + "loss": 0.1015, + "step": 356560 + }, + { + "epoch": 0.8, + "learning_rate": 1.0245072817162928e-05, + "loss": 0.0999, + "step": 356570 + }, + { + "epoch": 0.8, + "learning_rate": 1.0243954273953603e-05, + "loss": 0.1008, + "step": 356580 + }, + { + "epoch": 0.8, + "learning_rate": 1.0242835730744279e-05, + "loss": 0.1011, + "step": 356590 + }, + { + "epoch": 0.8, + "learning_rate": 1.0241717187534955e-05, + "loss": 0.1026, + "step": 356600 + }, + { + "epoch": 0.8, + "learning_rate": 1.024059864432563e-05, + "loss": 0.1035, + "step": 356610 + }, + { + "epoch": 0.8, + "learning_rate": 1.0239480101116307e-05, + "loss": 0.1025, + "step": 356620 + }, + { + "epoch": 0.8, + "learning_rate": 1.0238361557906982e-05, + "loss": 0.1053, + "step": 356630 + }, + { + "epoch": 0.8, + "learning_rate": 1.0237243014697658e-05, + "loss": 0.0999, + "step": 356640 + }, + { + "epoch": 0.8, + "learning_rate": 1.0236124471488334e-05, + "loss": 0.0995, + "step": 356650 + }, + { + "epoch": 0.8, + "learning_rate": 1.0235005928279009e-05, + "loss": 0.0995, + "step": 356660 + }, + { + "epoch": 0.8, + "learning_rate": 1.0233887385069687e-05, + "loss": 0.1025, + "step": 356670 + }, + { + "epoch": 0.8, + "learning_rate": 1.0232768841860361e-05, + "loss": 0.1014, + "step": 356680 + }, + { + "epoch": 0.8, + "learning_rate": 1.0231650298651036e-05, + "loss": 0.1013, + "step": 356690 + }, + { + "epoch": 0.8, + "learning_rate": 1.0230531755441714e-05, + "loss": 0.1017, + "step": 356700 + }, + { + "epoch": 0.8, + "learning_rate": 1.0229413212232388e-05, + "loss": 0.1027, + "step": 356710 + }, + { + "epoch": 0.8, + "learning_rate": 1.0228294669023065e-05, + "loss": 0.1003, + "step": 356720 + }, + { + "epoch": 0.8, + "learning_rate": 1.0227176125813741e-05, + "loss": 0.1007, + "step": 356730 + }, + { + "epoch": 0.8, + "learning_rate": 1.0226057582604415e-05, + "loss": 0.1023, + "step": 356740 + }, + { + "epoch": 0.8, + "learning_rate": 1.0224939039395093e-05, + "loss": 0.1006, + "step": 356750 + }, + { + "epoch": 0.8, + "learning_rate": 1.0223820496185768e-05, + "loss": 0.0985, + "step": 356760 + }, + { + "epoch": 0.8, + "learning_rate": 1.0222701952976444e-05, + "loss": 0.1046, + "step": 356770 + }, + { + "epoch": 0.8, + "learning_rate": 1.022158340976712e-05, + "loss": 0.1002, + "step": 356780 + }, + { + "epoch": 0.8, + "learning_rate": 1.0220464866557795e-05, + "loss": 0.0992, + "step": 356790 + }, + { + "epoch": 0.8, + "learning_rate": 1.0219346323348473e-05, + "loss": 0.0989, + "step": 356800 + }, + { + "epoch": 0.8, + "learning_rate": 1.0218227780139147e-05, + "loss": 0.1013, + "step": 356810 + }, + { + "epoch": 0.8, + "learning_rate": 1.0217109236929822e-05, + "loss": 0.1025, + "step": 356820 + }, + { + "epoch": 0.8, + "learning_rate": 1.02159906937205e-05, + "loss": 0.1023, + "step": 356830 + }, + { + "epoch": 0.8, + "learning_rate": 1.0214872150511174e-05, + "loss": 0.0991, + "step": 356840 + }, + { + "epoch": 0.8, + "learning_rate": 1.021375360730185e-05, + "loss": 0.1005, + "step": 356850 + }, + { + "epoch": 0.8, + "learning_rate": 1.0212635064092527e-05, + "loss": 0.0974, + "step": 356860 + }, + { + "epoch": 0.8, + "learning_rate": 1.0211516520883201e-05, + "loss": 0.1009, + "step": 356870 + }, + { + "epoch": 0.8, + "learning_rate": 1.021039797767388e-05, + "loss": 0.1056, + "step": 356880 + }, + { + "epoch": 0.8, + "learning_rate": 1.0209279434464554e-05, + "loss": 0.1008, + "step": 356890 + }, + { + "epoch": 0.8, + "learning_rate": 1.0208160891255228e-05, + "loss": 0.0992, + "step": 356900 + }, + { + "epoch": 0.8, + "learning_rate": 1.0207042348045906e-05, + "loss": 0.0982, + "step": 356910 + }, + { + "epoch": 0.8, + "learning_rate": 1.0205923804836581e-05, + "loss": 0.1003, + "step": 356920 + }, + { + "epoch": 0.8, + "learning_rate": 1.0204805261627257e-05, + "loss": 0.1016, + "step": 356930 + }, + { + "epoch": 0.8, + "learning_rate": 1.0203686718417933e-05, + "loss": 0.1004, + "step": 356940 + }, + { + "epoch": 0.8, + "learning_rate": 1.0202568175208608e-05, + "loss": 0.0992, + "step": 356950 + }, + { + "epoch": 0.8, + "learning_rate": 1.0201449631999286e-05, + "loss": 0.1025, + "step": 356960 + }, + { + "epoch": 0.8, + "learning_rate": 1.020033108878996e-05, + "loss": 0.1026, + "step": 356970 + }, + { + "epoch": 0.8, + "learning_rate": 1.0199212545580637e-05, + "loss": 0.1066, + "step": 356980 + }, + { + "epoch": 0.8, + "learning_rate": 1.0198094002371313e-05, + "loss": 0.0983, + "step": 356990 + }, + { + "epoch": 0.8, + "learning_rate": 1.0196975459161987e-05, + "loss": 0.1026, + "step": 357000 + }, + { + "epoch": 0.8, + "learning_rate": 1.0195856915952664e-05, + "loss": 0.1072, + "step": 357010 + }, + { + "epoch": 0.8, + "learning_rate": 1.019473837274334e-05, + "loss": 0.1016, + "step": 357020 + }, + { + "epoch": 0.8, + "learning_rate": 1.0193619829534014e-05, + "loss": 0.1028, + "step": 357030 + }, + { + "epoch": 0.8, + "learning_rate": 1.0192501286324692e-05, + "loss": 0.1045, + "step": 357040 + }, + { + "epoch": 0.8, + "learning_rate": 1.0191382743115367e-05, + "loss": 0.1015, + "step": 357050 + }, + { + "epoch": 0.8, + "learning_rate": 1.0190264199906043e-05, + "loss": 0.0988, + "step": 357060 + }, + { + "epoch": 0.8, + "learning_rate": 1.018914565669672e-05, + "loss": 0.0997, + "step": 357070 + }, + { + "epoch": 0.8, + "learning_rate": 1.0188027113487394e-05, + "loss": 0.1059, + "step": 357080 + }, + { + "epoch": 0.8, + "learning_rate": 1.018690857027807e-05, + "loss": 0.1002, + "step": 357090 + }, + { + "epoch": 0.8, + "learning_rate": 1.0185790027068746e-05, + "loss": 0.094, + "step": 357100 + }, + { + "epoch": 0.8, + "learning_rate": 1.0184671483859423e-05, + "loss": 0.1014, + "step": 357110 + }, + { + "epoch": 0.8, + "learning_rate": 1.0183552940650099e-05, + "loss": 0.1058, + "step": 357120 + }, + { + "epoch": 0.8, + "learning_rate": 1.0182434397440773e-05, + "loss": 0.1005, + "step": 357130 + }, + { + "epoch": 0.8, + "learning_rate": 1.018131585423145e-05, + "loss": 0.1008, + "step": 357140 + }, + { + "epoch": 0.8, + "learning_rate": 1.0180197311022126e-05, + "loss": 0.1001, + "step": 357150 + }, + { + "epoch": 0.8, + "learning_rate": 1.01790787678128e-05, + "loss": 0.1014, + "step": 357160 + }, + { + "epoch": 0.8, + "learning_rate": 1.0177960224603477e-05, + "loss": 0.1028, + "step": 357170 + }, + { + "epoch": 0.8, + "learning_rate": 1.0176841681394153e-05, + "loss": 0.1009, + "step": 357180 + }, + { + "epoch": 0.8, + "learning_rate": 1.0175723138184829e-05, + "loss": 0.1007, + "step": 357190 + }, + { + "epoch": 0.8, + "learning_rate": 1.0174604594975505e-05, + "loss": 0.0976, + "step": 357200 + }, + { + "epoch": 0.8, + "learning_rate": 1.017348605176618e-05, + "loss": 0.1056, + "step": 357210 + }, + { + "epoch": 0.8, + "learning_rate": 1.0172367508556856e-05, + "loss": 0.102, + "step": 357220 + }, + { + "epoch": 0.8, + "learning_rate": 1.0171248965347532e-05, + "loss": 0.1013, + "step": 357230 + }, + { + "epoch": 0.8, + "learning_rate": 1.0170130422138207e-05, + "loss": 0.1037, + "step": 357240 + }, + { + "epoch": 0.8, + "learning_rate": 1.0169011878928883e-05, + "loss": 0.1004, + "step": 357250 + }, + { + "epoch": 0.8, + "learning_rate": 1.016789333571956e-05, + "loss": 0.1013, + "step": 357260 + }, + { + "epoch": 0.8, + "learning_rate": 1.0166774792510236e-05, + "loss": 0.102, + "step": 357270 + }, + { + "epoch": 0.8, + "learning_rate": 1.0165656249300912e-05, + "loss": 0.1015, + "step": 357280 + }, + { + "epoch": 0.8, + "learning_rate": 1.0164537706091586e-05, + "loss": 0.1007, + "step": 357290 + }, + { + "epoch": 0.8, + "learning_rate": 1.0163419162882263e-05, + "loss": 0.1037, + "step": 357300 + }, + { + "epoch": 0.8, + "learning_rate": 1.0162300619672939e-05, + "loss": 0.1018, + "step": 357310 + }, + { + "epoch": 0.8, + "learning_rate": 1.0161182076463615e-05, + "loss": 0.1008, + "step": 357320 + }, + { + "epoch": 0.8, + "learning_rate": 1.016006353325429e-05, + "loss": 0.0979, + "step": 357330 + }, + { + "epoch": 0.8, + "learning_rate": 1.0158944990044966e-05, + "loss": 0.0991, + "step": 357340 + }, + { + "epoch": 0.8, + "learning_rate": 1.0157826446835642e-05, + "loss": 0.1023, + "step": 357350 + }, + { + "epoch": 0.8, + "learning_rate": 1.0156707903626318e-05, + "loss": 0.106, + "step": 357360 + }, + { + "epoch": 0.8, + "learning_rate": 1.0155589360416993e-05, + "loss": 0.1008, + "step": 357370 + }, + { + "epoch": 0.8, + "learning_rate": 1.0154470817207669e-05, + "loss": 0.0976, + "step": 357380 + }, + { + "epoch": 0.8, + "learning_rate": 1.0153352273998345e-05, + "loss": 0.0985, + "step": 357390 + }, + { + "epoch": 0.8, + "learning_rate": 1.0152233730789021e-05, + "loss": 0.0995, + "step": 357400 + }, + { + "epoch": 0.8, + "learning_rate": 1.0151115187579696e-05, + "loss": 0.0987, + "step": 357410 + }, + { + "epoch": 0.8, + "learning_rate": 1.0149996644370372e-05, + "loss": 0.0983, + "step": 357420 + }, + { + "epoch": 0.8, + "learning_rate": 1.0148878101161049e-05, + "loss": 0.1024, + "step": 357430 + }, + { + "epoch": 0.8, + "learning_rate": 1.0147759557951725e-05, + "loss": 0.1011, + "step": 357440 + }, + { + "epoch": 0.8, + "learning_rate": 1.0146641014742401e-05, + "loss": 0.103, + "step": 357450 + }, + { + "epoch": 0.8, + "learning_rate": 1.0145522471533076e-05, + "loss": 0.1038, + "step": 357460 + }, + { + "epoch": 0.8, + "learning_rate": 1.0144403928323752e-05, + "loss": 0.0991, + "step": 357470 + }, + { + "epoch": 0.8, + "learning_rate": 1.0143285385114428e-05, + "loss": 0.1054, + "step": 357480 + }, + { + "epoch": 0.8, + "learning_rate": 1.0142166841905103e-05, + "loss": 0.0986, + "step": 357490 + }, + { + "epoch": 0.8, + "learning_rate": 1.0141048298695779e-05, + "loss": 0.1002, + "step": 357500 + }, + { + "epoch": 0.8, + "learning_rate": 1.0139929755486455e-05, + "loss": 0.101, + "step": 357510 + }, + { + "epoch": 0.8, + "learning_rate": 1.0138811212277131e-05, + "loss": 0.0988, + "step": 357520 + }, + { + "epoch": 0.8, + "learning_rate": 1.0137692669067807e-05, + "loss": 0.1016, + "step": 357530 + }, + { + "epoch": 0.8, + "learning_rate": 1.0136574125858482e-05, + "loss": 0.1006, + "step": 357540 + }, + { + "epoch": 0.8, + "learning_rate": 1.0135455582649158e-05, + "loss": 0.0983, + "step": 357550 + }, + { + "epoch": 0.8, + "learning_rate": 1.0134337039439834e-05, + "loss": 0.0998, + "step": 357560 + }, + { + "epoch": 0.8, + "learning_rate": 1.0133218496230509e-05, + "loss": 0.1029, + "step": 357570 + }, + { + "epoch": 0.8, + "learning_rate": 1.0132211807342118e-05, + "loss": 0.0987, + "step": 357580 + }, + { + "epoch": 0.8, + "learning_rate": 1.0131093264132794e-05, + "loss": 0.0998, + "step": 357590 + }, + { + "epoch": 0.8, + "learning_rate": 1.012997472092347e-05, + "loss": 0.0949, + "step": 357600 + }, + { + "epoch": 0.8, + "learning_rate": 1.0128856177714145e-05, + "loss": 0.1009, + "step": 357610 + }, + { + "epoch": 0.8, + "learning_rate": 1.0127737634504823e-05, + "loss": 0.1021, + "step": 357620 + }, + { + "epoch": 0.8, + "learning_rate": 1.0126619091295497e-05, + "loss": 0.1044, + "step": 357630 + }, + { + "epoch": 0.8, + "learning_rate": 1.0125500548086172e-05, + "loss": 0.1035, + "step": 357640 + }, + { + "epoch": 0.8, + "learning_rate": 1.012438200487685e-05, + "loss": 0.102, + "step": 357650 + }, + { + "epoch": 0.8, + "learning_rate": 1.0123263461667524e-05, + "loss": 0.1, + "step": 357660 + }, + { + "epoch": 0.8, + "learning_rate": 1.01221449184582e-05, + "loss": 0.0964, + "step": 357670 + }, + { + "epoch": 0.8, + "learning_rate": 1.0121026375248877e-05, + "loss": 0.1017, + "step": 357680 + }, + { + "epoch": 0.8, + "learning_rate": 1.0119907832039551e-05, + "loss": 0.1046, + "step": 357690 + }, + { + "epoch": 0.8, + "learning_rate": 1.011878928883023e-05, + "loss": 0.1008, + "step": 357700 + }, + { + "epoch": 0.8, + "learning_rate": 1.0117670745620904e-05, + "loss": 0.0987, + "step": 357710 + }, + { + "epoch": 0.8, + "learning_rate": 1.011655220241158e-05, + "loss": 0.1062, + "step": 357720 + }, + { + "epoch": 0.8, + "learning_rate": 1.0115433659202256e-05, + "loss": 0.0981, + "step": 357730 + }, + { + "epoch": 0.8, + "learning_rate": 1.011431511599293e-05, + "loss": 0.1002, + "step": 357740 + }, + { + "epoch": 0.8, + "learning_rate": 1.0113196572783607e-05, + "loss": 0.1048, + "step": 357750 + }, + { + "epoch": 0.8, + "learning_rate": 1.0112078029574283e-05, + "loss": 0.1037, + "step": 357760 + }, + { + "epoch": 0.8, + "learning_rate": 1.0110959486364958e-05, + "loss": 0.1036, + "step": 357770 + }, + { + "epoch": 0.8, + "learning_rate": 1.0109840943155636e-05, + "loss": 0.1017, + "step": 357780 + }, + { + "epoch": 0.8, + "learning_rate": 1.010872239994631e-05, + "loss": 0.102, + "step": 357790 + }, + { + "epoch": 0.8, + "learning_rate": 1.0107603856736986e-05, + "loss": 0.1008, + "step": 357800 + }, + { + "epoch": 0.8, + "learning_rate": 1.0106485313527663e-05, + "loss": 0.0972, + "step": 357810 + }, + { + "epoch": 0.8, + "learning_rate": 1.0105366770318337e-05, + "loss": 0.1018, + "step": 357820 + }, + { + "epoch": 0.8, + "learning_rate": 1.0104248227109013e-05, + "loss": 0.0991, + "step": 357830 + }, + { + "epoch": 0.8, + "learning_rate": 1.010312968389969e-05, + "loss": 0.1022, + "step": 357840 + }, + { + "epoch": 0.8, + "learning_rate": 1.0102011140690364e-05, + "loss": 0.0975, + "step": 357850 + }, + { + "epoch": 0.8, + "learning_rate": 1.0100892597481042e-05, + "loss": 0.0995, + "step": 357860 + }, + { + "epoch": 0.8, + "learning_rate": 1.0099774054271717e-05, + "loss": 0.098, + "step": 357870 + }, + { + "epoch": 0.8, + "learning_rate": 1.0098655511062393e-05, + "loss": 0.1024, + "step": 357880 + }, + { + "epoch": 0.8, + "learning_rate": 1.009753696785307e-05, + "loss": 0.1003, + "step": 357890 + }, + { + "epoch": 0.8, + "learning_rate": 1.0096418424643744e-05, + "loss": 0.1008, + "step": 357900 + }, + { + "epoch": 0.8, + "learning_rate": 1.009529988143442e-05, + "loss": 0.1009, + "step": 357910 + }, + { + "epoch": 0.8, + "learning_rate": 1.0094181338225096e-05, + "loss": 0.0985, + "step": 357920 + }, + { + "epoch": 0.8, + "learning_rate": 1.0093062795015772e-05, + "loss": 0.1002, + "step": 357930 + }, + { + "epoch": 0.8, + "learning_rate": 1.0091944251806449e-05, + "loss": 0.1009, + "step": 357940 + }, + { + "epoch": 0.8, + "learning_rate": 1.0090825708597123e-05, + "loss": 0.0993, + "step": 357950 + }, + { + "epoch": 0.8, + "learning_rate": 1.00897071653878e-05, + "loss": 0.1025, + "step": 357960 + }, + { + "epoch": 0.8, + "learning_rate": 1.0088588622178476e-05, + "loss": 0.1029, + "step": 357970 + }, + { + "epoch": 0.8, + "learning_rate": 1.008747007896915e-05, + "loss": 0.1032, + "step": 357980 + }, + { + "epoch": 0.8, + "learning_rate": 1.0086351535759826e-05, + "loss": 0.0991, + "step": 357990 + }, + { + "epoch": 0.8, + "learning_rate": 1.0085232992550503e-05, + "loss": 0.1001, + "step": 358000 + }, + { + "epoch": 0.8, + "learning_rate": 1.0084114449341179e-05, + "loss": 0.0969, + "step": 358010 + }, + { + "epoch": 0.8, + "learning_rate": 1.0082995906131855e-05, + "loss": 0.0967, + "step": 358020 + }, + { + "epoch": 0.8, + "learning_rate": 1.008187736292253e-05, + "loss": 0.1006, + "step": 358030 + }, + { + "epoch": 0.8, + "learning_rate": 1.0080758819713206e-05, + "loss": 0.0998, + "step": 358040 + }, + { + "epoch": 0.8, + "learning_rate": 1.0079640276503882e-05, + "loss": 0.0977, + "step": 358050 + }, + { + "epoch": 0.8, + "learning_rate": 1.0078521733294558e-05, + "loss": 0.0999, + "step": 358060 + }, + { + "epoch": 0.8, + "learning_rate": 1.0077403190085233e-05, + "loss": 0.1017, + "step": 358070 + }, + { + "epoch": 0.8, + "learning_rate": 1.0076284646875909e-05, + "loss": 0.1054, + "step": 358080 + }, + { + "epoch": 0.8, + "learning_rate": 1.0075166103666585e-05, + "loss": 0.1023, + "step": 358090 + }, + { + "epoch": 0.8, + "learning_rate": 1.0074047560457262e-05, + "loss": 0.1022, + "step": 358100 + }, + { + "epoch": 0.8, + "learning_rate": 1.0072929017247936e-05, + "loss": 0.1026, + "step": 358110 + }, + { + "epoch": 0.8, + "learning_rate": 1.0071810474038612e-05, + "loss": 0.1027, + "step": 358120 + }, + { + "epoch": 0.8, + "learning_rate": 1.0070691930829289e-05, + "loss": 0.1027, + "step": 358130 + }, + { + "epoch": 0.8, + "learning_rate": 1.0069573387619965e-05, + "loss": 0.1, + "step": 358140 + }, + { + "epoch": 0.8, + "learning_rate": 1.006845484441064e-05, + "loss": 0.1025, + "step": 358150 + }, + { + "epoch": 0.8, + "learning_rate": 1.0067336301201316e-05, + "loss": 0.1008, + "step": 358160 + }, + { + "epoch": 0.8, + "learning_rate": 1.0066217757991992e-05, + "loss": 0.0998, + "step": 358170 + }, + { + "epoch": 0.8, + "learning_rate": 1.0065099214782668e-05, + "loss": 0.0982, + "step": 358180 + }, + { + "epoch": 0.8, + "learning_rate": 1.0063980671573343e-05, + "loss": 0.1, + "step": 358190 + }, + { + "epoch": 0.8, + "learning_rate": 1.0062862128364019e-05, + "loss": 0.0993, + "step": 358200 + }, + { + "epoch": 0.8, + "learning_rate": 1.0061743585154695e-05, + "loss": 0.0941, + "step": 358210 + }, + { + "epoch": 0.8, + "learning_rate": 1.0060625041945371e-05, + "loss": 0.1024, + "step": 358220 + }, + { + "epoch": 0.8, + "learning_rate": 1.0059506498736046e-05, + "loss": 0.1037, + "step": 358230 + }, + { + "epoch": 0.8, + "learning_rate": 1.0058387955526722e-05, + "loss": 0.1002, + "step": 358240 + }, + { + "epoch": 0.8, + "learning_rate": 1.0057269412317398e-05, + "loss": 0.0975, + "step": 358250 + }, + { + "epoch": 0.8, + "learning_rate": 1.0056150869108075e-05, + "loss": 0.1023, + "step": 358260 + }, + { + "epoch": 0.8, + "learning_rate": 1.005503232589875e-05, + "loss": 0.0986, + "step": 358270 + }, + { + "epoch": 0.8, + "learning_rate": 1.0053913782689425e-05, + "loss": 0.1022, + "step": 358280 + }, + { + "epoch": 0.8, + "learning_rate": 1.0052795239480102e-05, + "loss": 0.0952, + "step": 358290 + }, + { + "epoch": 0.8, + "learning_rate": 1.0051676696270778e-05, + "loss": 0.1017, + "step": 358300 + }, + { + "epoch": 0.8, + "learning_rate": 1.0050558153061452e-05, + "loss": 0.102, + "step": 358310 + }, + { + "epoch": 0.8, + "learning_rate": 1.0049439609852129e-05, + "loss": 0.1003, + "step": 358320 + }, + { + "epoch": 0.8, + "learning_rate": 1.0048321066642805e-05, + "loss": 0.1049, + "step": 358330 + }, + { + "epoch": 0.8, + "learning_rate": 1.0047202523433481e-05, + "loss": 0.1008, + "step": 358340 + }, + { + "epoch": 0.8, + "learning_rate": 1.0046083980224157e-05, + "loss": 0.1029, + "step": 358350 + }, + { + "epoch": 0.8, + "learning_rate": 1.0044965437014832e-05, + "loss": 0.1032, + "step": 358360 + }, + { + "epoch": 0.8, + "learning_rate": 1.0043846893805508e-05, + "loss": 0.0978, + "step": 358370 + }, + { + "epoch": 0.8, + "learning_rate": 1.0042728350596184e-05, + "loss": 0.0962, + "step": 358380 + }, + { + "epoch": 0.8, + "learning_rate": 1.0041609807386859e-05, + "loss": 0.0972, + "step": 358390 + }, + { + "epoch": 0.8, + "learning_rate": 1.0040491264177535e-05, + "loss": 0.1, + "step": 358400 + }, + { + "epoch": 0.8, + "learning_rate": 1.0039372720968211e-05, + "loss": 0.1019, + "step": 358410 + }, + { + "epoch": 0.8, + "learning_rate": 1.0038254177758888e-05, + "loss": 0.1019, + "step": 358420 + }, + { + "epoch": 0.8, + "learning_rate": 1.0037135634549564e-05, + "loss": 0.0982, + "step": 358430 + }, + { + "epoch": 0.8, + "learning_rate": 1.0036017091340238e-05, + "loss": 0.0998, + "step": 358440 + }, + { + "epoch": 0.8, + "learning_rate": 1.0034898548130915e-05, + "loss": 0.1013, + "step": 358450 + }, + { + "epoch": 0.8, + "learning_rate": 1.003378000492159e-05, + "loss": 0.1017, + "step": 358460 + }, + { + "epoch": 0.8, + "learning_rate": 1.0032661461712265e-05, + "loss": 0.1052, + "step": 358470 + }, + { + "epoch": 0.8, + "learning_rate": 1.0031542918502943e-05, + "loss": 0.105, + "step": 358480 + }, + { + "epoch": 0.8, + "learning_rate": 1.0030424375293618e-05, + "loss": 0.1001, + "step": 358490 + }, + { + "epoch": 0.8, + "learning_rate": 1.0029305832084294e-05, + "loss": 0.104, + "step": 358500 + }, + { + "epoch": 0.8, + "learning_rate": 1.002818728887497e-05, + "loss": 0.0976, + "step": 358510 + }, + { + "epoch": 0.8, + "learning_rate": 1.0027068745665645e-05, + "loss": 0.0983, + "step": 358520 + }, + { + "epoch": 0.8, + "learning_rate": 1.0025950202456321e-05, + "loss": 0.1014, + "step": 358530 + }, + { + "epoch": 0.8, + "learning_rate": 1.0024831659246997e-05, + "loss": 0.1034, + "step": 358540 + }, + { + "epoch": 0.8, + "learning_rate": 1.0023713116037672e-05, + "loss": 0.0989, + "step": 358550 + }, + { + "epoch": 0.8, + "learning_rate": 1.002259457282835e-05, + "loss": 0.0971, + "step": 358560 + }, + { + "epoch": 0.8, + "learning_rate": 1.0021476029619024e-05, + "loss": 0.0996, + "step": 358570 + }, + { + "epoch": 0.8, + "learning_rate": 1.00203574864097e-05, + "loss": 0.0993, + "step": 358580 + }, + { + "epoch": 0.8, + "learning_rate": 1.0019238943200377e-05, + "loss": 0.0951, + "step": 358590 + }, + { + "epoch": 0.8, + "learning_rate": 1.0018120399991051e-05, + "loss": 0.1044, + "step": 358600 + }, + { + "epoch": 0.8, + "learning_rate": 1.001700185678173e-05, + "loss": 0.1012, + "step": 358610 + }, + { + "epoch": 0.8, + "learning_rate": 1.0015883313572404e-05, + "loss": 0.1017, + "step": 358620 + }, + { + "epoch": 0.8, + "learning_rate": 1.0014764770363078e-05, + "loss": 0.1015, + "step": 358630 + }, + { + "epoch": 0.8, + "learning_rate": 1.0013646227153756e-05, + "loss": 0.0987, + "step": 358640 + }, + { + "epoch": 0.8, + "learning_rate": 1.001252768394443e-05, + "loss": 0.1044, + "step": 358650 + }, + { + "epoch": 0.8, + "learning_rate": 1.0011409140735107e-05, + "loss": 0.1008, + "step": 358660 + }, + { + "epoch": 0.8, + "learning_rate": 1.0010290597525783e-05, + "loss": 0.1025, + "step": 358670 + }, + { + "epoch": 0.8, + "learning_rate": 1.0009172054316458e-05, + "loss": 0.1036, + "step": 358680 + }, + { + "epoch": 0.8, + "learning_rate": 1.0008053511107136e-05, + "loss": 0.0998, + "step": 358690 + }, + { + "epoch": 0.8, + "learning_rate": 1.000693496789781e-05, + "loss": 0.1025, + "step": 358700 + }, + { + "epoch": 0.8, + "learning_rate": 1.0005816424688485e-05, + "loss": 0.1048, + "step": 358710 + }, + { + "epoch": 0.8, + "learning_rate": 1.0004697881479163e-05, + "loss": 0.0984, + "step": 358720 + }, + { + "epoch": 0.8, + "learning_rate": 1.0003579338269837e-05, + "loss": 0.1038, + "step": 358730 + }, + { + "epoch": 0.8, + "learning_rate": 1.0002460795060513e-05, + "loss": 0.0975, + "step": 358740 + }, + { + "epoch": 0.8, + "learning_rate": 1.000134225185119e-05, + "loss": 0.0962, + "step": 358750 + }, + { + "epoch": 0.8, + "learning_rate": 1.0000223708641864e-05, + "loss": 0.0979, + "step": 358760 + }, + { + "epoch": 0.8, + "learning_rate": 9.999105165432542e-06, + "loss": 0.1027, + "step": 358770 + }, + { + "epoch": 0.8, + "learning_rate": 9.997986622223217e-06, + "loss": 0.0986, + "step": 358780 + }, + { + "epoch": 0.8, + "learning_rate": 9.996868079013893e-06, + "loss": 0.0971, + "step": 358790 + }, + { + "epoch": 0.8, + "learning_rate": 9.995749535804569e-06, + "loss": 0.1013, + "step": 358800 + }, + { + "epoch": 0.8, + "learning_rate": 9.994630992595244e-06, + "loss": 0.1005, + "step": 358810 + }, + { + "epoch": 0.8, + "learning_rate": 9.993512449385922e-06, + "loss": 0.099, + "step": 358820 + }, + { + "epoch": 0.8, + "learning_rate": 9.992393906176596e-06, + "loss": 0.0985, + "step": 358830 + }, + { + "epoch": 0.8, + "learning_rate": 9.99127536296727e-06, + "loss": 0.0991, + "step": 358840 + }, + { + "epoch": 0.8, + "learning_rate": 9.990156819757949e-06, + "loss": 0.1015, + "step": 358850 + }, + { + "epoch": 0.8, + "learning_rate": 9.989038276548623e-06, + "loss": 0.098, + "step": 358860 + }, + { + "epoch": 0.8, + "learning_rate": 9.9879197333393e-06, + "loss": 0.1039, + "step": 358870 + }, + { + "epoch": 0.8, + "learning_rate": 9.986801190129976e-06, + "loss": 0.1027, + "step": 358880 + }, + { + "epoch": 0.8, + "learning_rate": 9.98568264692065e-06, + "loss": 0.1014, + "step": 358890 + }, + { + "epoch": 0.8, + "learning_rate": 9.984564103711328e-06, + "loss": 0.0994, + "step": 358900 + }, + { + "epoch": 0.8, + "learning_rate": 9.983445560502003e-06, + "loss": 0.0968, + "step": 358910 + }, + { + "epoch": 0.8, + "learning_rate": 9.982327017292679e-06, + "loss": 0.0967, + "step": 358920 + }, + { + "epoch": 0.8, + "learning_rate": 9.981208474083355e-06, + "loss": 0.0979, + "step": 358930 + }, + { + "epoch": 0.8, + "learning_rate": 9.98008993087403e-06, + "loss": 0.1005, + "step": 358940 + }, + { + "epoch": 0.8, + "learning_rate": 9.978971387664706e-06, + "loss": 0.1023, + "step": 358950 + }, + { + "epoch": 0.8, + "learning_rate": 9.977852844455382e-06, + "loss": 0.0995, + "step": 358960 + }, + { + "epoch": 0.8, + "learning_rate": 9.976734301246057e-06, + "loss": 0.1006, + "step": 358970 + }, + { + "epoch": 0.8, + "learning_rate": 9.975615758036735e-06, + "loss": 0.1033, + "step": 358980 + }, + { + "epoch": 0.8, + "learning_rate": 9.974497214827409e-06, + "loss": 0.0985, + "step": 358990 + }, + { + "epoch": 0.8, + "learning_rate": 9.973378671618085e-06, + "loss": 0.1006, + "step": 359000 + }, + { + "epoch": 0.8, + "learning_rate": 9.972260128408762e-06, + "loss": 0.1018, + "step": 359010 + }, + { + "epoch": 0.8, + "learning_rate": 9.971141585199436e-06, + "loss": 0.104, + "step": 359020 + }, + { + "epoch": 0.8, + "learning_rate": 9.970023041990112e-06, + "loss": 0.0985, + "step": 359030 + }, + { + "epoch": 0.8, + "learning_rate": 9.968904498780789e-06, + "loss": 0.0999, + "step": 359040 + }, + { + "epoch": 0.8, + "learning_rate": 9.967785955571463e-06, + "loss": 0.1006, + "step": 359050 + }, + { + "epoch": 0.8, + "learning_rate": 9.966667412362141e-06, + "loss": 0.1024, + "step": 359060 + }, + { + "epoch": 0.8, + "learning_rate": 9.965548869152816e-06, + "loss": 0.0974, + "step": 359070 + }, + { + "epoch": 0.8, + "learning_rate": 9.964430325943492e-06, + "loss": 0.097, + "step": 359080 + }, + { + "epoch": 0.8, + "learning_rate": 9.963311782734168e-06, + "loss": 0.0988, + "step": 359090 + }, + { + "epoch": 0.8, + "learning_rate": 9.962193239524843e-06, + "loss": 0.1012, + "step": 359100 + }, + { + "epoch": 0.8, + "learning_rate": 9.961074696315519e-06, + "loss": 0.1034, + "step": 359110 + }, + { + "epoch": 0.8, + "learning_rate": 9.959956153106195e-06, + "loss": 0.097, + "step": 359120 + }, + { + "epoch": 0.8, + "learning_rate": 9.958837609896871e-06, + "loss": 0.0995, + "step": 359130 + }, + { + "epoch": 0.8, + "learning_rate": 9.957719066687548e-06, + "loss": 0.1024, + "step": 359140 + }, + { + "epoch": 0.8, + "learning_rate": 9.956600523478222e-06, + "loss": 0.0979, + "step": 359150 + }, + { + "epoch": 0.8, + "learning_rate": 9.955481980268898e-06, + "loss": 0.1036, + "step": 359160 + }, + { + "epoch": 0.8, + "learning_rate": 9.954363437059575e-06, + "loss": 0.1004, + "step": 359170 + }, + { + "epoch": 0.8, + "learning_rate": 9.953244893850249e-06, + "loss": 0.0954, + "step": 359180 + }, + { + "epoch": 0.8, + "learning_rate": 9.952126350640925e-06, + "loss": 0.1051, + "step": 359190 + }, + { + "epoch": 0.8, + "learning_rate": 9.951007807431602e-06, + "loss": 0.1024, + "step": 359200 + }, + { + "epoch": 0.8, + "learning_rate": 9.949889264222278e-06, + "loss": 0.1069, + "step": 359210 + }, + { + "epoch": 0.8, + "learning_rate": 9.948770721012954e-06, + "loss": 0.0982, + "step": 359220 + }, + { + "epoch": 0.8, + "learning_rate": 9.947652177803629e-06, + "loss": 0.1015, + "step": 359230 + }, + { + "epoch": 0.8, + "learning_rate": 9.946533634594305e-06, + "loss": 0.1022, + "step": 359240 + }, + { + "epoch": 0.8, + "learning_rate": 9.945415091384981e-06, + "loss": 0.0986, + "step": 359250 + }, + { + "epoch": 0.8, + "learning_rate": 9.944296548175657e-06, + "loss": 0.1024, + "step": 359260 + }, + { + "epoch": 0.8, + "learning_rate": 9.943178004966332e-06, + "loss": 0.0991, + "step": 359270 + }, + { + "epoch": 0.8, + "learning_rate": 9.942059461757008e-06, + "loss": 0.0989, + "step": 359280 + }, + { + "epoch": 0.8, + "learning_rate": 9.940940918547684e-06, + "loss": 0.0994, + "step": 359290 + }, + { + "epoch": 0.8, + "learning_rate": 9.93982237533836e-06, + "loss": 0.0961, + "step": 359300 + }, + { + "epoch": 0.8, + "learning_rate": 9.938703832129035e-06, + "loss": 0.0992, + "step": 359310 + }, + { + "epoch": 0.8, + "learning_rate": 9.937585288919711e-06, + "loss": 0.1054, + "step": 359320 + }, + { + "epoch": 0.8, + "learning_rate": 9.936466745710388e-06, + "loss": 0.1058, + "step": 359330 + }, + { + "epoch": 0.8, + "learning_rate": 9.935348202501064e-06, + "loss": 0.101, + "step": 359340 + }, + { + "epoch": 0.8, + "learning_rate": 9.934229659291738e-06, + "loss": 0.1003, + "step": 359350 + }, + { + "epoch": 0.8, + "learning_rate": 9.933111116082415e-06, + "loss": 0.0986, + "step": 359360 + }, + { + "epoch": 0.8, + "learning_rate": 9.93199257287309e-06, + "loss": 0.1007, + "step": 359370 + }, + { + "epoch": 0.8, + "learning_rate": 9.930874029663767e-06, + "loss": 0.1004, + "step": 359380 + }, + { + "epoch": 0.8, + "learning_rate": 9.929755486454442e-06, + "loss": 0.0998, + "step": 359390 + }, + { + "epoch": 0.8, + "learning_rate": 9.928636943245118e-06, + "loss": 0.1016, + "step": 359400 + }, + { + "epoch": 0.8, + "learning_rate": 9.927518400035794e-06, + "loss": 0.0965, + "step": 359410 + }, + { + "epoch": 0.8, + "learning_rate": 9.92639985682647e-06, + "loss": 0.0982, + "step": 359420 + }, + { + "epoch": 0.8, + "learning_rate": 9.925281313617145e-06, + "loss": 0.1006, + "step": 359430 + }, + { + "epoch": 0.8, + "learning_rate": 9.924162770407821e-06, + "loss": 0.1043, + "step": 359440 + }, + { + "epoch": 0.8, + "learning_rate": 9.923044227198497e-06, + "loss": 0.1007, + "step": 359450 + }, + { + "epoch": 0.8, + "learning_rate": 9.921925683989173e-06, + "loss": 0.1007, + "step": 359460 + }, + { + "epoch": 0.8, + "learning_rate": 9.92080714077985e-06, + "loss": 0.0985, + "step": 359470 + }, + { + "epoch": 0.8, + "learning_rate": 9.919688597570524e-06, + "loss": 0.0987, + "step": 359480 + }, + { + "epoch": 0.8, + "learning_rate": 9.9185700543612e-06, + "loss": 0.1013, + "step": 359490 + }, + { + "epoch": 0.8, + "learning_rate": 9.917451511151877e-06, + "loss": 0.0994, + "step": 359500 + }, + { + "epoch": 0.8, + "learning_rate": 9.916332967942551e-06, + "loss": 0.1, + "step": 359510 + }, + { + "epoch": 0.8, + "learning_rate": 9.915214424733227e-06, + "loss": 0.1014, + "step": 359520 + }, + { + "epoch": 0.8, + "learning_rate": 9.914095881523904e-06, + "loss": 0.1015, + "step": 359530 + }, + { + "epoch": 0.8, + "learning_rate": 9.91297733831458e-06, + "loss": 0.1011, + "step": 359540 + }, + { + "epoch": 0.8, + "learning_rate": 9.911858795105256e-06, + "loss": 0.1018, + "step": 359550 + }, + { + "epoch": 0.8, + "learning_rate": 9.91074025189593e-06, + "loss": 0.1029, + "step": 359560 + }, + { + "epoch": 0.8, + "learning_rate": 9.909621708686607e-06, + "loss": 0.1001, + "step": 359570 + }, + { + "epoch": 0.8, + "learning_rate": 9.908503165477283e-06, + "loss": 0.1019, + "step": 359580 + }, + { + "epoch": 0.8, + "learning_rate": 9.907496476588892e-06, + "loss": 0.1038, + "step": 359590 + }, + { + "epoch": 0.8, + "learning_rate": 9.906377933379567e-06, + "loss": 0.1019, + "step": 359600 + }, + { + "epoch": 0.8, + "learning_rate": 9.905259390170243e-06, + "loss": 0.0991, + "step": 359610 + }, + { + "epoch": 0.8, + "learning_rate": 9.904140846960919e-06, + "loss": 0.1031, + "step": 359620 + }, + { + "epoch": 0.8, + "learning_rate": 9.903022303751594e-06, + "loss": 0.099, + "step": 359630 + }, + { + "epoch": 0.8, + "learning_rate": 9.901903760542271e-06, + "loss": 0.101, + "step": 359640 + }, + { + "epoch": 0.8, + "learning_rate": 9.900785217332946e-06, + "loss": 0.1016, + "step": 359650 + }, + { + "epoch": 0.8, + "learning_rate": 9.89966667412362e-06, + "loss": 0.1007, + "step": 359660 + }, + { + "epoch": 0.8, + "learning_rate": 9.898548130914298e-06, + "loss": 0.1022, + "step": 359670 + }, + { + "epoch": 0.8, + "learning_rate": 9.897429587704973e-06, + "loss": 0.0986, + "step": 359680 + }, + { + "epoch": 0.8, + "learning_rate": 9.89631104449565e-06, + "loss": 0.1026, + "step": 359690 + }, + { + "epoch": 0.8, + "learning_rate": 9.895192501286325e-06, + "loss": 0.1063, + "step": 359700 + }, + { + "epoch": 0.8, + "learning_rate": 9.894073958077e-06, + "loss": 0.1022, + "step": 359710 + }, + { + "epoch": 0.8, + "learning_rate": 9.892955414867678e-06, + "loss": 0.0992, + "step": 359720 + }, + { + "epoch": 0.8, + "learning_rate": 9.891836871658352e-06, + "loss": 0.1012, + "step": 359730 + }, + { + "epoch": 0.8, + "learning_rate": 9.890718328449029e-06, + "loss": 0.0996, + "step": 359740 + }, + { + "epoch": 0.8, + "learning_rate": 9.889599785239705e-06, + "loss": 0.099, + "step": 359750 + }, + { + "epoch": 0.8, + "learning_rate": 9.88848124203038e-06, + "loss": 0.1025, + "step": 359760 + }, + { + "epoch": 0.8, + "learning_rate": 9.887362698821057e-06, + "loss": 0.0992, + "step": 359770 + }, + { + "epoch": 0.8, + "learning_rate": 9.886244155611732e-06, + "loss": 0.1022, + "step": 359780 + }, + { + "epoch": 0.8, + "learning_rate": 9.885125612402406e-06, + "loss": 0.1056, + "step": 359790 + }, + { + "epoch": 0.8, + "learning_rate": 9.884007069193084e-06, + "loss": 0.1009, + "step": 359800 + }, + { + "epoch": 0.8, + "learning_rate": 9.882888525983759e-06, + "loss": 0.1023, + "step": 359810 + }, + { + "epoch": 0.8, + "learning_rate": 9.881769982774435e-06, + "loss": 0.0976, + "step": 359820 + }, + { + "epoch": 0.8, + "learning_rate": 9.880651439565111e-06, + "loss": 0.1011, + "step": 359830 + }, + { + "epoch": 0.8, + "learning_rate": 9.879532896355786e-06, + "loss": 0.0979, + "step": 359840 + }, + { + "epoch": 0.8, + "learning_rate": 9.878414353146464e-06, + "loss": 0.1026, + "step": 359850 + }, + { + "epoch": 0.8, + "learning_rate": 9.877295809937138e-06, + "loss": 0.1036, + "step": 359860 + }, + { + "epoch": 0.8, + "learning_rate": 9.876177266727813e-06, + "loss": 0.1011, + "step": 359870 + }, + { + "epoch": 0.8, + "learning_rate": 9.875058723518491e-06, + "loss": 0.1046, + "step": 359880 + }, + { + "epoch": 0.8, + "learning_rate": 9.873940180309165e-06, + "loss": 0.1008, + "step": 359890 + }, + { + "epoch": 0.8, + "learning_rate": 9.872821637099842e-06, + "loss": 0.1047, + "step": 359900 + }, + { + "epoch": 0.8, + "learning_rate": 9.871703093890518e-06, + "loss": 0.0982, + "step": 359910 + }, + { + "epoch": 0.8, + "learning_rate": 9.870584550681192e-06, + "loss": 0.0999, + "step": 359920 + }, + { + "epoch": 0.8, + "learning_rate": 9.86946600747187e-06, + "loss": 0.0967, + "step": 359930 + }, + { + "epoch": 0.8, + "learning_rate": 9.868347464262545e-06, + "loss": 0.0986, + "step": 359940 + }, + { + "epoch": 0.8, + "learning_rate": 9.867228921053221e-06, + "loss": 0.1042, + "step": 359950 + }, + { + "epoch": 0.8, + "learning_rate": 9.866110377843897e-06, + "loss": 0.0992, + "step": 359960 + }, + { + "epoch": 0.8, + "learning_rate": 9.864991834634572e-06, + "loss": 0.0987, + "step": 359970 + }, + { + "epoch": 0.8, + "learning_rate": 9.863873291425248e-06, + "loss": 0.1023, + "step": 359980 + }, + { + "epoch": 0.8, + "learning_rate": 9.862754748215924e-06, + "loss": 0.098, + "step": 359990 + }, + { + "epoch": 0.8, + "learning_rate": 9.861636205006599e-06, + "loss": 0.0924, + "step": 360000 + }, + { + "epoch": 0.8, + "learning_rate": 9.860517661797277e-06, + "loss": 0.0963, + "step": 360010 + }, + { + "epoch": 0.8, + "learning_rate": 9.859399118587951e-06, + "loss": 0.1017, + "step": 360020 + }, + { + "epoch": 0.8, + "learning_rate": 9.858280575378628e-06, + "loss": 0.1028, + "step": 360030 + }, + { + "epoch": 0.8, + "learning_rate": 9.857162032169304e-06, + "loss": 0.0965, + "step": 360040 + }, + { + "epoch": 0.8, + "learning_rate": 9.856043488959978e-06, + "loss": 0.1065, + "step": 360050 + }, + { + "epoch": 0.8, + "learning_rate": 9.854924945750655e-06, + "loss": 0.1012, + "step": 360060 + }, + { + "epoch": 0.8, + "learning_rate": 9.853806402541331e-06, + "loss": 0.1007, + "step": 360070 + }, + { + "epoch": 0.8, + "learning_rate": 9.852687859332007e-06, + "loss": 0.1047, + "step": 360080 + }, + { + "epoch": 0.8, + "learning_rate": 9.851569316122683e-06, + "loss": 0.1014, + "step": 360090 + }, + { + "epoch": 0.8, + "learning_rate": 9.850450772913358e-06, + "loss": 0.1043, + "step": 360100 + }, + { + "epoch": 0.8, + "learning_rate": 9.849332229704034e-06, + "loss": 0.0975, + "step": 360110 + }, + { + "epoch": 0.8, + "learning_rate": 9.84821368649471e-06, + "loss": 0.0977, + "step": 360120 + }, + { + "epoch": 0.8, + "learning_rate": 9.847095143285385e-06, + "loss": 0.1036, + "step": 360130 + }, + { + "epoch": 0.8, + "learning_rate": 9.845976600076061e-06, + "loss": 0.1052, + "step": 360140 + }, + { + "epoch": 0.8, + "learning_rate": 9.844858056866737e-06, + "loss": 0.096, + "step": 360150 + }, + { + "epoch": 0.8, + "learning_rate": 9.843739513657414e-06, + "loss": 0.1019, + "step": 360160 + }, + { + "epoch": 0.8, + "learning_rate": 9.84262097044809e-06, + "loss": 0.099, + "step": 360170 + }, + { + "epoch": 0.8, + "learning_rate": 9.841502427238764e-06, + "loss": 0.101, + "step": 360180 + }, + { + "epoch": 0.8, + "learning_rate": 9.84038388402944e-06, + "loss": 0.1003, + "step": 360190 + }, + { + "epoch": 0.8, + "learning_rate": 9.839265340820117e-06, + "loss": 0.1027, + "step": 360200 + }, + { + "epoch": 0.8, + "learning_rate": 9.838146797610791e-06, + "loss": 0.0996, + "step": 360210 + }, + { + "epoch": 0.8, + "learning_rate": 9.837028254401468e-06, + "loss": 0.0978, + "step": 360220 + }, + { + "epoch": 0.8, + "learning_rate": 9.835909711192144e-06, + "loss": 0.1041, + "step": 360230 + }, + { + "epoch": 0.8, + "learning_rate": 9.83479116798282e-06, + "loss": 0.094, + "step": 360240 + }, + { + "epoch": 0.8, + "learning_rate": 9.833672624773496e-06, + "loss": 0.0975, + "step": 360250 + }, + { + "epoch": 0.8, + "learning_rate": 9.83255408156417e-06, + "loss": 0.1025, + "step": 360260 + }, + { + "epoch": 0.8, + "learning_rate": 9.831435538354847e-06, + "loss": 0.0997, + "step": 360270 + }, + { + "epoch": 0.8, + "learning_rate": 9.830316995145523e-06, + "loss": 0.1056, + "step": 360280 + }, + { + "epoch": 0.8, + "learning_rate": 9.8291984519362e-06, + "loss": 0.0979, + "step": 360290 + }, + { + "epoch": 0.8, + "learning_rate": 9.828079908726874e-06, + "loss": 0.1027, + "step": 360300 + }, + { + "epoch": 0.8, + "learning_rate": 9.82696136551755e-06, + "loss": 0.0979, + "step": 360310 + }, + { + "epoch": 0.8, + "learning_rate": 9.825842822308227e-06, + "loss": 0.1011, + "step": 360320 + }, + { + "epoch": 0.8, + "learning_rate": 9.824724279098903e-06, + "loss": 0.0991, + "step": 360330 + }, + { + "epoch": 0.8, + "learning_rate": 9.823605735889577e-06, + "loss": 0.0955, + "step": 360340 + }, + { + "epoch": 0.8, + "learning_rate": 9.822487192680254e-06, + "loss": 0.1017, + "step": 360350 + }, + { + "epoch": 0.8, + "learning_rate": 9.82136864947093e-06, + "loss": 0.0999, + "step": 360360 + }, + { + "epoch": 0.8, + "learning_rate": 9.820250106261606e-06, + "loss": 0.0996, + "step": 360370 + }, + { + "epoch": 0.8, + "learning_rate": 9.81913156305228e-06, + "loss": 0.0956, + "step": 360380 + }, + { + "epoch": 0.8, + "learning_rate": 9.818013019842957e-06, + "loss": 0.1012, + "step": 360390 + }, + { + "epoch": 0.8, + "learning_rate": 9.816894476633633e-06, + "loss": 0.0965, + "step": 360400 + }, + { + "epoch": 0.8, + "learning_rate": 9.81577593342431e-06, + "loss": 0.0993, + "step": 360410 + }, + { + "epoch": 0.8, + "learning_rate": 9.814657390214985e-06, + "loss": 0.104, + "step": 360420 + }, + { + "epoch": 0.8, + "learning_rate": 9.81353884700566e-06, + "loss": 0.0987, + "step": 360430 + }, + { + "epoch": 0.8, + "learning_rate": 9.812420303796336e-06, + "loss": 0.0962, + "step": 360440 + }, + { + "epoch": 0.8, + "learning_rate": 9.811413614907943e-06, + "loss": 0.0983, + "step": 360450 + }, + { + "epoch": 0.8, + "learning_rate": 9.810295071698621e-06, + "loss": 0.103, + "step": 360460 + }, + { + "epoch": 0.8, + "learning_rate": 9.809176528489296e-06, + "loss": 0.1034, + "step": 360470 + }, + { + "epoch": 0.8, + "learning_rate": 9.80805798527997e-06, + "loss": 0.1003, + "step": 360480 + }, + { + "epoch": 0.8, + "learning_rate": 9.806939442070648e-06, + "loss": 0.0998, + "step": 360490 + }, + { + "epoch": 0.8, + "learning_rate": 9.805820898861323e-06, + "loss": 0.1021, + "step": 360500 + }, + { + "epoch": 0.8, + "learning_rate": 9.804702355651999e-06, + "loss": 0.1007, + "step": 360510 + }, + { + "epoch": 0.8, + "learning_rate": 9.803583812442675e-06, + "loss": 0.1017, + "step": 360520 + }, + { + "epoch": 0.8, + "learning_rate": 9.80246526923335e-06, + "loss": 0.1051, + "step": 360530 + }, + { + "epoch": 0.8, + "learning_rate": 9.801346726024028e-06, + "loss": 0.0969, + "step": 360540 + }, + { + "epoch": 0.8, + "learning_rate": 9.800228182814702e-06, + "loss": 0.101, + "step": 360550 + }, + { + "epoch": 0.8, + "learning_rate": 9.799109639605379e-06, + "loss": 0.0999, + "step": 360560 + }, + { + "epoch": 0.8, + "learning_rate": 9.797991096396055e-06, + "loss": 0.0971, + "step": 360570 + }, + { + "epoch": 0.8, + "learning_rate": 9.79687255318673e-06, + "loss": 0.1024, + "step": 360580 + }, + { + "epoch": 0.8, + "learning_rate": 9.795754009977407e-06, + "loss": 0.1025, + "step": 360590 + }, + { + "epoch": 0.8, + "learning_rate": 9.794635466768082e-06, + "loss": 0.1027, + "step": 360600 + }, + { + "epoch": 0.8, + "learning_rate": 9.793516923558756e-06, + "loss": 0.1003, + "step": 360610 + }, + { + "epoch": 0.8, + "learning_rate": 9.792398380349434e-06, + "loss": 0.1011, + "step": 360620 + }, + { + "epoch": 0.8, + "learning_rate": 9.791279837140109e-06, + "loss": 0.0995, + "step": 360630 + }, + { + "epoch": 0.8, + "learning_rate": 9.790161293930785e-06, + "loss": 0.1017, + "step": 360640 + }, + { + "epoch": 0.81, + "learning_rate": 9.789042750721461e-06, + "loss": 0.101, + "step": 360650 + }, + { + "epoch": 0.81, + "learning_rate": 9.787924207512136e-06, + "loss": 0.0991, + "step": 360660 + }, + { + "epoch": 0.81, + "learning_rate": 9.786805664302814e-06, + "loss": 0.0971, + "step": 360670 + }, + { + "epoch": 0.81, + "learning_rate": 9.785687121093488e-06, + "loss": 0.1047, + "step": 360680 + }, + { + "epoch": 0.81, + "learning_rate": 9.784568577884164e-06, + "loss": 0.096, + "step": 360690 + }, + { + "epoch": 0.81, + "learning_rate": 9.78345003467484e-06, + "loss": 0.0974, + "step": 360700 + }, + { + "epoch": 0.81, + "learning_rate": 9.782331491465515e-06, + "loss": 0.0991, + "step": 360710 + }, + { + "epoch": 0.81, + "learning_rate": 9.781212948256191e-06, + "loss": 0.1036, + "step": 360720 + }, + { + "epoch": 0.81, + "learning_rate": 9.780094405046868e-06, + "loss": 0.1024, + "step": 360730 + }, + { + "epoch": 0.81, + "learning_rate": 9.778975861837542e-06, + "loss": 0.1022, + "step": 360740 + }, + { + "epoch": 0.81, + "learning_rate": 9.77785731862822e-06, + "loss": 0.0963, + "step": 360750 + }, + { + "epoch": 0.81, + "learning_rate": 9.776738775418895e-06, + "loss": 0.1005, + "step": 360760 + }, + { + "epoch": 0.81, + "learning_rate": 9.775620232209571e-06, + "loss": 0.0957, + "step": 360770 + }, + { + "epoch": 0.81, + "learning_rate": 9.774501689000247e-06, + "loss": 0.0991, + "step": 360780 + }, + { + "epoch": 0.81, + "learning_rate": 9.773383145790922e-06, + "loss": 0.0963, + "step": 360790 + }, + { + "epoch": 0.81, + "learning_rate": 9.772264602581598e-06, + "loss": 0.0967, + "step": 360800 + }, + { + "epoch": 0.81, + "learning_rate": 9.771146059372274e-06, + "loss": 0.0996, + "step": 360810 + }, + { + "epoch": 0.81, + "learning_rate": 9.770027516162949e-06, + "loss": 0.1025, + "step": 360820 + }, + { + "epoch": 0.81, + "learning_rate": 9.768908972953627e-06, + "loss": 0.1027, + "step": 360830 + }, + { + "epoch": 0.81, + "learning_rate": 9.767790429744301e-06, + "loss": 0.0991, + "step": 360840 + }, + { + "epoch": 0.81, + "learning_rate": 9.766671886534977e-06, + "loss": 0.101, + "step": 360850 + }, + { + "epoch": 0.81, + "learning_rate": 9.765553343325654e-06, + "loss": 0.099, + "step": 360860 + }, + { + "epoch": 0.81, + "learning_rate": 9.764434800116328e-06, + "loss": 0.1009, + "step": 360870 + }, + { + "epoch": 0.81, + "learning_rate": 9.763316256907004e-06, + "loss": 0.1, + "step": 360880 + }, + { + "epoch": 0.81, + "learning_rate": 9.76219771369768e-06, + "loss": 0.0967, + "step": 360890 + }, + { + "epoch": 0.81, + "learning_rate": 9.761079170488357e-06, + "loss": 0.1039, + "step": 360900 + }, + { + "epoch": 0.81, + "learning_rate": 9.759960627279033e-06, + "loss": 0.0976, + "step": 360910 + }, + { + "epoch": 0.81, + "learning_rate": 9.758842084069708e-06, + "loss": 0.1028, + "step": 360920 + }, + { + "epoch": 0.81, + "learning_rate": 9.757723540860384e-06, + "loss": 0.1008, + "step": 360930 + }, + { + "epoch": 0.81, + "learning_rate": 9.75660499765106e-06, + "loss": 0.101, + "step": 360940 + }, + { + "epoch": 0.81, + "learning_rate": 9.755486454441735e-06, + "loss": 0.1006, + "step": 360950 + }, + { + "epoch": 0.81, + "learning_rate": 9.754367911232411e-06, + "loss": 0.0976, + "step": 360960 + }, + { + "epoch": 0.81, + "learning_rate": 9.753249368023087e-06, + "loss": 0.1015, + "step": 360970 + }, + { + "epoch": 0.81, + "learning_rate": 9.752130824813763e-06, + "loss": 0.1033, + "step": 360980 + }, + { + "epoch": 0.81, + "learning_rate": 9.75101228160444e-06, + "loss": 0.0994, + "step": 360990 + }, + { + "epoch": 0.81, + "learning_rate": 9.749893738395114e-06, + "loss": 0.098, + "step": 361000 + }, + { + "epoch": 0.81, + "learning_rate": 9.74877519518579e-06, + "loss": 0.1013, + "step": 361010 + }, + { + "epoch": 0.81, + "learning_rate": 9.747656651976467e-06, + "loss": 0.0948, + "step": 361020 + }, + { + "epoch": 0.81, + "learning_rate": 9.746538108767143e-06, + "loss": 0.0983, + "step": 361030 + }, + { + "epoch": 0.81, + "learning_rate": 9.745419565557817e-06, + "loss": 0.1021, + "step": 361040 + }, + { + "epoch": 0.81, + "learning_rate": 9.744301022348494e-06, + "loss": 0.0995, + "step": 361050 + }, + { + "epoch": 0.81, + "learning_rate": 9.74318247913917e-06, + "loss": 0.0993, + "step": 361060 + }, + { + "epoch": 0.81, + "learning_rate": 9.742063935929846e-06, + "loss": 0.0995, + "step": 361070 + }, + { + "epoch": 0.81, + "learning_rate": 9.74094539272052e-06, + "loss": 0.1026, + "step": 361080 + }, + { + "epoch": 0.81, + "learning_rate": 9.739826849511197e-06, + "loss": 0.1024, + "step": 361090 + }, + { + "epoch": 0.81, + "learning_rate": 9.738708306301873e-06, + "loss": 0.0971, + "step": 361100 + }, + { + "epoch": 0.81, + "learning_rate": 9.73758976309255e-06, + "loss": 0.1, + "step": 361110 + }, + { + "epoch": 0.81, + "learning_rate": 9.736471219883224e-06, + "loss": 0.1004, + "step": 361120 + }, + { + "epoch": 0.81, + "learning_rate": 9.7353526766739e-06, + "loss": 0.0981, + "step": 361130 + }, + { + "epoch": 0.81, + "learning_rate": 9.734234133464576e-06, + "loss": 0.1009, + "step": 361140 + }, + { + "epoch": 0.81, + "learning_rate": 9.733115590255253e-06, + "loss": 0.0997, + "step": 361150 + }, + { + "epoch": 0.81, + "learning_rate": 9.731997047045927e-06, + "loss": 0.1001, + "step": 361160 + }, + { + "epoch": 0.81, + "learning_rate": 9.730878503836603e-06, + "loss": 0.1025, + "step": 361170 + }, + { + "epoch": 0.81, + "learning_rate": 9.72975996062728e-06, + "loss": 0.0986, + "step": 361180 + }, + { + "epoch": 0.81, + "learning_rate": 9.728641417417956e-06, + "loss": 0.098, + "step": 361190 + }, + { + "epoch": 0.81, + "learning_rate": 9.72752287420863e-06, + "loss": 0.1026, + "step": 361200 + }, + { + "epoch": 0.81, + "learning_rate": 9.726404330999307e-06, + "loss": 0.1008, + "step": 361210 + }, + { + "epoch": 0.81, + "learning_rate": 9.725285787789983e-06, + "loss": 0.1006, + "step": 361220 + }, + { + "epoch": 0.81, + "learning_rate": 9.724167244580659e-06, + "loss": 0.1027, + "step": 361230 + }, + { + "epoch": 0.81, + "learning_rate": 9.723048701371335e-06, + "loss": 0.0989, + "step": 361240 + }, + { + "epoch": 0.81, + "learning_rate": 9.72193015816201e-06, + "loss": 0.0988, + "step": 361250 + }, + { + "epoch": 0.81, + "learning_rate": 9.720811614952686e-06, + "loss": 0.1009, + "step": 361260 + }, + { + "epoch": 0.81, + "learning_rate": 9.719693071743362e-06, + "loss": 0.1029, + "step": 361270 + }, + { + "epoch": 0.81, + "learning_rate": 9.718574528534037e-06, + "loss": 0.1012, + "step": 361280 + }, + { + "epoch": 0.81, + "learning_rate": 9.717455985324713e-06, + "loss": 0.1002, + "step": 361290 + }, + { + "epoch": 0.81, + "learning_rate": 9.71633744211539e-06, + "loss": 0.0986, + "step": 361300 + }, + { + "epoch": 0.81, + "learning_rate": 9.715218898906066e-06, + "loss": 0.1007, + "step": 361310 + }, + { + "epoch": 0.81, + "learning_rate": 9.714100355696742e-06, + "loss": 0.1007, + "step": 361320 + }, + { + "epoch": 0.81, + "learning_rate": 9.712981812487416e-06, + "loss": 0.0957, + "step": 361330 + }, + { + "epoch": 0.81, + "learning_rate": 9.711863269278093e-06, + "loss": 0.1013, + "step": 361340 + }, + { + "epoch": 0.81, + "learning_rate": 9.710744726068769e-06, + "loss": 0.101, + "step": 361350 + }, + { + "epoch": 0.81, + "learning_rate": 9.709626182859443e-06, + "loss": 0.1016, + "step": 361360 + }, + { + "epoch": 0.81, + "learning_rate": 9.70850763965012e-06, + "loss": 0.0999, + "step": 361370 + }, + { + "epoch": 0.81, + "learning_rate": 9.707389096440796e-06, + "loss": 0.1, + "step": 361380 + }, + { + "epoch": 0.81, + "learning_rate": 9.706270553231472e-06, + "loss": 0.0991, + "step": 361390 + }, + { + "epoch": 0.81, + "learning_rate": 9.705152010022148e-06, + "loss": 0.0988, + "step": 361400 + }, + { + "epoch": 0.81, + "learning_rate": 9.704033466812823e-06, + "loss": 0.097, + "step": 361410 + }, + { + "epoch": 0.81, + "learning_rate": 9.702914923603499e-06, + "loss": 0.1009, + "step": 361420 + }, + { + "epoch": 0.81, + "learning_rate": 9.701796380394175e-06, + "loss": 0.1022, + "step": 361430 + }, + { + "epoch": 0.81, + "learning_rate": 9.70067783718485e-06, + "loss": 0.0981, + "step": 361440 + }, + { + "epoch": 0.81, + "learning_rate": 9.699559293975528e-06, + "loss": 0.1009, + "step": 361450 + }, + { + "epoch": 0.81, + "learning_rate": 9.698440750766202e-06, + "loss": 0.0958, + "step": 361460 + }, + { + "epoch": 0.81, + "learning_rate": 9.697322207556879e-06, + "loss": 0.096, + "step": 361470 + }, + { + "epoch": 0.81, + "learning_rate": 9.696203664347555e-06, + "loss": 0.1005, + "step": 361480 + }, + { + "epoch": 0.81, + "learning_rate": 9.69508512113823e-06, + "loss": 0.099, + "step": 361490 + }, + { + "epoch": 0.81, + "learning_rate": 9.693966577928906e-06, + "loss": 0.1031, + "step": 361500 + }, + { + "epoch": 0.81, + "learning_rate": 9.692848034719582e-06, + "loss": 0.1, + "step": 361510 + }, + { + "epoch": 0.81, + "learning_rate": 9.691729491510256e-06, + "loss": 0.1014, + "step": 361520 + }, + { + "epoch": 0.81, + "learning_rate": 9.690610948300934e-06, + "loss": 0.0967, + "step": 361530 + }, + { + "epoch": 0.81, + "learning_rate": 9.689492405091609e-06, + "loss": 0.1006, + "step": 361540 + }, + { + "epoch": 0.81, + "learning_rate": 9.688373861882285e-06, + "loss": 0.0994, + "step": 361550 + }, + { + "epoch": 0.81, + "learning_rate": 9.687255318672961e-06, + "loss": 0.0999, + "step": 361560 + }, + { + "epoch": 0.81, + "learning_rate": 9.686136775463636e-06, + "loss": 0.1011, + "step": 361570 + }, + { + "epoch": 0.81, + "learning_rate": 9.685018232254314e-06, + "loss": 0.102, + "step": 361580 + }, + { + "epoch": 0.81, + "learning_rate": 9.683899689044988e-06, + "loss": 0.0968, + "step": 361590 + }, + { + "epoch": 0.81, + "learning_rate": 9.682781145835663e-06, + "loss": 0.1026, + "step": 361600 + }, + { + "epoch": 0.81, + "learning_rate": 9.68166260262634e-06, + "loss": 0.1002, + "step": 361610 + }, + { + "epoch": 0.81, + "learning_rate": 9.680544059417015e-06, + "loss": 0.105, + "step": 361620 + }, + { + "epoch": 0.81, + "learning_rate": 9.679425516207691e-06, + "loss": 0.1016, + "step": 361630 + }, + { + "epoch": 0.81, + "learning_rate": 9.678306972998368e-06, + "loss": 0.1019, + "step": 361640 + }, + { + "epoch": 0.81, + "learning_rate": 9.677188429789042e-06, + "loss": 0.1021, + "step": 361650 + }, + { + "epoch": 0.81, + "learning_rate": 9.67606988657972e-06, + "loss": 0.1013, + "step": 361660 + }, + { + "epoch": 0.81, + "learning_rate": 9.674951343370395e-06, + "loss": 0.1018, + "step": 361670 + }, + { + "epoch": 0.81, + "learning_rate": 9.67383280016107e-06, + "loss": 0.1006, + "step": 361680 + }, + { + "epoch": 0.81, + "learning_rate": 9.672714256951747e-06, + "loss": 0.0998, + "step": 361690 + }, + { + "epoch": 0.81, + "learning_rate": 9.671595713742422e-06, + "loss": 0.1014, + "step": 361700 + }, + { + "epoch": 0.81, + "learning_rate": 9.670477170533098e-06, + "loss": 0.0942, + "step": 361710 + }, + { + "epoch": 0.81, + "learning_rate": 9.669358627323774e-06, + "loss": 0.0981, + "step": 361720 + }, + { + "epoch": 0.81, + "learning_rate": 9.668240084114449e-06, + "loss": 0.0988, + "step": 361730 + }, + { + "epoch": 0.81, + "learning_rate": 9.667121540905127e-06, + "loss": 0.0974, + "step": 361740 + }, + { + "epoch": 0.81, + "learning_rate": 9.666002997695801e-06, + "loss": 0.0989, + "step": 361750 + }, + { + "epoch": 0.81, + "learning_rate": 9.664884454486477e-06, + "loss": 0.1034, + "step": 361760 + }, + { + "epoch": 0.81, + "learning_rate": 9.663765911277154e-06, + "loss": 0.0982, + "step": 361770 + }, + { + "epoch": 0.81, + "learning_rate": 9.662647368067828e-06, + "loss": 0.1011, + "step": 361780 + }, + { + "epoch": 0.81, + "learning_rate": 9.661528824858506e-06, + "loss": 0.0958, + "step": 361790 + }, + { + "epoch": 0.81, + "learning_rate": 9.66041028164918e-06, + "loss": 0.1021, + "step": 361800 + }, + { + "epoch": 0.81, + "learning_rate": 9.659291738439855e-06, + "loss": 0.0977, + "step": 361810 + }, + { + "epoch": 0.81, + "learning_rate": 9.658173195230533e-06, + "loss": 0.0966, + "step": 361820 + }, + { + "epoch": 0.81, + "learning_rate": 9.657054652021208e-06, + "loss": 0.098, + "step": 361830 + }, + { + "epoch": 0.81, + "learning_rate": 9.655936108811884e-06, + "loss": 0.1042, + "step": 361840 + }, + { + "epoch": 0.81, + "learning_rate": 9.65481756560256e-06, + "loss": 0.1032, + "step": 361850 + }, + { + "epoch": 0.81, + "learning_rate": 9.653699022393235e-06, + "loss": 0.1029, + "step": 361860 + }, + { + "epoch": 0.81, + "learning_rate": 9.652580479183913e-06, + "loss": 0.0998, + "step": 361870 + }, + { + "epoch": 0.81, + "learning_rate": 9.651461935974587e-06, + "loss": 0.099, + "step": 361880 + }, + { + "epoch": 0.81, + "learning_rate": 9.650343392765263e-06, + "loss": 0.0989, + "step": 361890 + }, + { + "epoch": 0.81, + "learning_rate": 9.64922484955594e-06, + "loss": 0.1022, + "step": 361900 + }, + { + "epoch": 0.81, + "learning_rate": 9.648106306346614e-06, + "loss": 0.1011, + "step": 361910 + }, + { + "epoch": 0.81, + "learning_rate": 9.64698776313729e-06, + "loss": 0.0995, + "step": 361920 + }, + { + "epoch": 0.81, + "learning_rate": 9.645869219927967e-06, + "loss": 0.0967, + "step": 361930 + }, + { + "epoch": 0.81, + "learning_rate": 9.644750676718641e-06, + "loss": 0.0999, + "step": 361940 + }, + { + "epoch": 0.81, + "learning_rate": 9.643632133509319e-06, + "loss": 0.1032, + "step": 361950 + }, + { + "epoch": 0.81, + "learning_rate": 9.642513590299994e-06, + "loss": 0.0987, + "step": 361960 + }, + { + "epoch": 0.81, + "learning_rate": 9.64139504709067e-06, + "loss": 0.0981, + "step": 361970 + }, + { + "epoch": 0.81, + "learning_rate": 9.640276503881346e-06, + "loss": 0.1014, + "step": 361980 + }, + { + "epoch": 0.81, + "learning_rate": 9.63915796067202e-06, + "loss": 0.0988, + "step": 361990 + }, + { + "epoch": 0.81, + "learning_rate": 9.638039417462697e-06, + "loss": 0.0973, + "step": 362000 + }, + { + "epoch": 0.81, + "learning_rate": 9.636920874253373e-06, + "loss": 0.1011, + "step": 362010 + }, + { + "epoch": 0.81, + "learning_rate": 9.635802331044048e-06, + "loss": 0.0958, + "step": 362020 + }, + { + "epoch": 0.81, + "learning_rate": 9.634683787834726e-06, + "loss": 0.103, + "step": 362030 + }, + { + "epoch": 0.81, + "learning_rate": 9.6335652446254e-06, + "loss": 0.1038, + "step": 362040 + }, + { + "epoch": 0.81, + "learning_rate": 9.632446701416076e-06, + "loss": 0.098, + "step": 362050 + }, + { + "epoch": 0.81, + "learning_rate": 9.631328158206753e-06, + "loss": 0.1038, + "step": 362060 + }, + { + "epoch": 0.81, + "learning_rate": 9.630209614997427e-06, + "loss": 0.1049, + "step": 362070 + }, + { + "epoch": 0.81, + "learning_rate": 9.629091071788103e-06, + "loss": 0.1001, + "step": 362080 + }, + { + "epoch": 0.81, + "learning_rate": 9.62797252857878e-06, + "loss": 0.0948, + "step": 362090 + }, + { + "epoch": 0.81, + "learning_rate": 9.626853985369456e-06, + "loss": 0.0979, + "step": 362100 + }, + { + "epoch": 0.81, + "learning_rate": 9.625735442160132e-06, + "loss": 0.0986, + "step": 362110 + }, + { + "epoch": 0.81, + "learning_rate": 9.624616898950807e-06, + "loss": 0.1033, + "step": 362120 + }, + { + "epoch": 0.81, + "learning_rate": 9.623498355741483e-06, + "loss": 0.0977, + "step": 362130 + }, + { + "epoch": 0.81, + "learning_rate": 9.622379812532159e-06, + "loss": 0.1019, + "step": 362140 + }, + { + "epoch": 0.81, + "learning_rate": 9.621261269322834e-06, + "loss": 0.101, + "step": 362150 + }, + { + "epoch": 0.81, + "learning_rate": 9.62014272611351e-06, + "loss": 0.0986, + "step": 362160 + }, + { + "epoch": 0.81, + "learning_rate": 9.619024182904186e-06, + "loss": 0.0981, + "step": 362170 + }, + { + "epoch": 0.81, + "learning_rate": 9.617905639694862e-06, + "loss": 0.1001, + "step": 362180 + }, + { + "epoch": 0.81, + "learning_rate": 9.616787096485539e-06, + "loss": 0.0987, + "step": 362190 + }, + { + "epoch": 0.81, + "learning_rate": 9.615668553276213e-06, + "loss": 0.0994, + "step": 362200 + }, + { + "epoch": 0.81, + "learning_rate": 9.61455001006689e-06, + "loss": 0.0979, + "step": 362210 + }, + { + "epoch": 0.81, + "learning_rate": 9.613431466857566e-06, + "loss": 0.0988, + "step": 362220 + }, + { + "epoch": 0.81, + "learning_rate": 9.612312923648242e-06, + "loss": 0.0987, + "step": 362230 + }, + { + "epoch": 0.81, + "learning_rate": 9.611194380438916e-06, + "loss": 0.0998, + "step": 362240 + }, + { + "epoch": 0.81, + "learning_rate": 9.610075837229593e-06, + "loss": 0.0962, + "step": 362250 + }, + { + "epoch": 0.81, + "learning_rate": 9.608957294020269e-06, + "loss": 0.0958, + "step": 362260 + }, + { + "epoch": 0.81, + "learning_rate": 9.607838750810945e-06, + "loss": 0.1001, + "step": 362270 + }, + { + "epoch": 0.81, + "learning_rate": 9.60672020760162e-06, + "loss": 0.0945, + "step": 362280 + }, + { + "epoch": 0.81, + "learning_rate": 9.605601664392296e-06, + "loss": 0.0984, + "step": 362290 + }, + { + "epoch": 0.81, + "learning_rate": 9.604483121182972e-06, + "loss": 0.099, + "step": 362300 + }, + { + "epoch": 0.81, + "learning_rate": 9.603364577973648e-06, + "loss": 0.1, + "step": 362310 + }, + { + "epoch": 0.81, + "learning_rate": 9.602246034764323e-06, + "loss": 0.097, + "step": 362320 + }, + { + "epoch": 0.81, + "learning_rate": 9.601127491554999e-06, + "loss": 0.0968, + "step": 362330 + }, + { + "epoch": 0.81, + "learning_rate": 9.600008948345675e-06, + "loss": 0.1047, + "step": 362340 + }, + { + "epoch": 0.81, + "learning_rate": 9.598890405136351e-06, + "loss": 0.1057, + "step": 362350 + }, + { + "epoch": 0.81, + "learning_rate": 9.597771861927026e-06, + "loss": 0.1033, + "step": 362360 + }, + { + "epoch": 0.81, + "learning_rate": 9.596653318717702e-06, + "loss": 0.1, + "step": 362370 + }, + { + "epoch": 0.81, + "learning_rate": 9.595534775508378e-06, + "loss": 0.0974, + "step": 362380 + }, + { + "epoch": 0.81, + "learning_rate": 9.594416232299055e-06, + "loss": 0.1002, + "step": 362390 + }, + { + "epoch": 0.81, + "learning_rate": 9.59329768908973e-06, + "loss": 0.0985, + "step": 362400 + }, + { + "epoch": 0.81, + "learning_rate": 9.592179145880406e-06, + "loss": 0.0988, + "step": 362410 + }, + { + "epoch": 0.81, + "learning_rate": 9.591060602671082e-06, + "loss": 0.1016, + "step": 362420 + }, + { + "epoch": 0.81, + "learning_rate": 9.589942059461758e-06, + "loss": 0.1008, + "step": 362430 + }, + { + "epoch": 0.81, + "learning_rate": 9.588823516252434e-06, + "loss": 0.097, + "step": 362440 + }, + { + "epoch": 0.81, + "learning_rate": 9.587704973043109e-06, + "loss": 0.0966, + "step": 362450 + }, + { + "epoch": 0.81, + "learning_rate": 9.586586429833785e-06, + "loss": 0.0995, + "step": 362460 + }, + { + "epoch": 0.81, + "learning_rate": 9.585467886624461e-06, + "loss": 0.1005, + "step": 362470 + }, + { + "epoch": 0.81, + "learning_rate": 9.584349343415136e-06, + "loss": 0.0969, + "step": 362480 + }, + { + "epoch": 0.81, + "learning_rate": 9.583230800205812e-06, + "loss": 0.1043, + "step": 362490 + }, + { + "epoch": 0.81, + "learning_rate": 9.582112256996488e-06, + "loss": 0.0961, + "step": 362500 + }, + { + "epoch": 0.81, + "learning_rate": 9.580993713787164e-06, + "loss": 0.0992, + "step": 362510 + }, + { + "epoch": 0.81, + "learning_rate": 9.57987517057784e-06, + "loss": 0.0988, + "step": 362520 + }, + { + "epoch": 0.81, + "learning_rate": 9.578756627368515e-06, + "loss": 0.1021, + "step": 362530 + }, + { + "epoch": 0.81, + "learning_rate": 9.577638084159191e-06, + "loss": 0.1015, + "step": 362540 + }, + { + "epoch": 0.81, + "learning_rate": 9.576519540949868e-06, + "loss": 0.0983, + "step": 362550 + }, + { + "epoch": 0.81, + "learning_rate": 9.575400997740542e-06, + "loss": 0.1017, + "step": 362560 + }, + { + "epoch": 0.81, + "learning_rate": 9.574282454531218e-06, + "loss": 0.1009, + "step": 362570 + }, + { + "epoch": 0.81, + "learning_rate": 9.573163911321895e-06, + "loss": 0.1044, + "step": 362580 + }, + { + "epoch": 0.81, + "learning_rate": 9.572045368112571e-06, + "loss": 0.101, + "step": 362590 + }, + { + "epoch": 0.81, + "learning_rate": 9.570926824903247e-06, + "loss": 0.0983, + "step": 362600 + }, + { + "epoch": 0.81, + "learning_rate": 9.569808281693922e-06, + "loss": 0.0967, + "step": 362610 + }, + { + "epoch": 0.81, + "learning_rate": 9.568689738484598e-06, + "loss": 0.0911, + "step": 362620 + }, + { + "epoch": 0.81, + "learning_rate": 9.567571195275274e-06, + "loss": 0.1024, + "step": 362630 + }, + { + "epoch": 0.81, + "learning_rate": 9.566452652065949e-06, + "loss": 0.0997, + "step": 362640 + }, + { + "epoch": 0.81, + "learning_rate": 9.565334108856627e-06, + "loss": 0.0975, + "step": 362650 + }, + { + "epoch": 0.81, + "learning_rate": 9.564215565647301e-06, + "loss": 0.1053, + "step": 362660 + }, + { + "epoch": 0.81, + "learning_rate": 9.563097022437977e-06, + "loss": 0.097, + "step": 362670 + }, + { + "epoch": 0.81, + "learning_rate": 9.561978479228654e-06, + "loss": 0.0969, + "step": 362680 + }, + { + "epoch": 0.81, + "learning_rate": 9.560859936019328e-06, + "loss": 0.099, + "step": 362690 + }, + { + "epoch": 0.81, + "learning_rate": 9.559741392810004e-06, + "loss": 0.1033, + "step": 362700 + }, + { + "epoch": 0.81, + "learning_rate": 9.55862284960068e-06, + "loss": 0.0962, + "step": 362710 + }, + { + "epoch": 0.81, + "learning_rate": 9.557504306391355e-06, + "loss": 0.1013, + "step": 362720 + }, + { + "epoch": 0.81, + "learning_rate": 9.556385763182033e-06, + "loss": 0.0992, + "step": 362730 + }, + { + "epoch": 0.81, + "learning_rate": 9.555267219972708e-06, + "loss": 0.1019, + "step": 362740 + }, + { + "epoch": 0.81, + "learning_rate": 9.554148676763384e-06, + "loss": 0.0971, + "step": 362750 + }, + { + "epoch": 0.81, + "learning_rate": 9.55303013355406e-06, + "loss": 0.0983, + "step": 362760 + }, + { + "epoch": 0.81, + "learning_rate": 9.551911590344735e-06, + "loss": 0.0996, + "step": 362770 + }, + { + "epoch": 0.81, + "learning_rate": 9.550793047135413e-06, + "loss": 0.1016, + "step": 362780 + }, + { + "epoch": 0.81, + "learning_rate": 9.549674503926087e-06, + "loss": 0.0997, + "step": 362790 + }, + { + "epoch": 0.81, + "learning_rate": 9.548555960716762e-06, + "loss": 0.1053, + "step": 362800 + }, + { + "epoch": 0.81, + "learning_rate": 9.54743741750744e-06, + "loss": 0.1039, + "step": 362810 + }, + { + "epoch": 0.81, + "learning_rate": 9.546318874298114e-06, + "loss": 0.1014, + "step": 362820 + }, + { + "epoch": 0.81, + "learning_rate": 9.54520033108879e-06, + "loss": 0.099, + "step": 362830 + }, + { + "epoch": 0.81, + "learning_rate": 9.544081787879467e-06, + "loss": 0.1011, + "step": 362840 + }, + { + "epoch": 0.81, + "learning_rate": 9.542963244670141e-06, + "loss": 0.1007, + "step": 362850 + }, + { + "epoch": 0.81, + "learning_rate": 9.541844701460819e-06, + "loss": 0.1002, + "step": 362860 + }, + { + "epoch": 0.81, + "learning_rate": 9.540726158251494e-06, + "loss": 0.1023, + "step": 362870 + }, + { + "epoch": 0.81, + "learning_rate": 9.539607615042168e-06, + "loss": 0.0916, + "step": 362880 + }, + { + "epoch": 0.81, + "learning_rate": 9.538489071832846e-06, + "loss": 0.0978, + "step": 362890 + }, + { + "epoch": 0.81, + "learning_rate": 9.53737052862352e-06, + "loss": 0.1021, + "step": 362900 + }, + { + "epoch": 0.81, + "learning_rate": 9.536251985414197e-06, + "loss": 0.0994, + "step": 362910 + }, + { + "epoch": 0.81, + "learning_rate": 9.535133442204873e-06, + "loss": 0.0957, + "step": 362920 + }, + { + "epoch": 0.81, + "learning_rate": 9.534014898995548e-06, + "loss": 0.0985, + "step": 362930 + }, + { + "epoch": 0.81, + "learning_rate": 9.532896355786226e-06, + "loss": 0.0989, + "step": 362940 + }, + { + "epoch": 0.81, + "learning_rate": 9.5317778125769e-06, + "loss": 0.0999, + "step": 362950 + }, + { + "epoch": 0.81, + "learning_rate": 9.530659269367576e-06, + "loss": 0.1034, + "step": 362960 + }, + { + "epoch": 0.81, + "learning_rate": 9.529540726158253e-06, + "loss": 0.0979, + "step": 362970 + }, + { + "epoch": 0.81, + "learning_rate": 9.528422182948927e-06, + "loss": 0.0989, + "step": 362980 + }, + { + "epoch": 0.81, + "learning_rate": 9.527303639739605e-06, + "loss": 0.1016, + "step": 362990 + }, + { + "epoch": 0.81, + "learning_rate": 9.52618509653028e-06, + "loss": 0.1039, + "step": 363000 + }, + { + "epoch": 0.81, + "learning_rate": 9.525066553320954e-06, + "loss": 0.0972, + "step": 363010 + }, + { + "epoch": 0.81, + "learning_rate": 9.523948010111632e-06, + "loss": 0.1, + "step": 363020 + }, + { + "epoch": 0.81, + "learning_rate": 9.522829466902307e-06, + "loss": 0.1001, + "step": 363030 + }, + { + "epoch": 0.81, + "learning_rate": 9.521710923692983e-06, + "loss": 0.1025, + "step": 363040 + }, + { + "epoch": 0.81, + "learning_rate": 9.520592380483659e-06, + "loss": 0.101, + "step": 363050 + }, + { + "epoch": 0.81, + "learning_rate": 9.519473837274334e-06, + "loss": 0.0992, + "step": 363060 + }, + { + "epoch": 0.81, + "learning_rate": 9.518355294065012e-06, + "loss": 0.1044, + "step": 363070 + }, + { + "epoch": 0.81, + "learning_rate": 9.517236750855686e-06, + "loss": 0.0992, + "step": 363080 + }, + { + "epoch": 0.81, + "learning_rate": 9.516118207646362e-06, + "loss": 0.1008, + "step": 363090 + }, + { + "epoch": 0.81, + "learning_rate": 9.514999664437039e-06, + "loss": 0.105, + "step": 363100 + }, + { + "epoch": 0.81, + "learning_rate": 9.513881121227713e-06, + "loss": 0.098, + "step": 363110 + }, + { + "epoch": 0.81, + "learning_rate": 9.51276257801839e-06, + "loss": 0.1015, + "step": 363120 + }, + { + "epoch": 0.81, + "learning_rate": 9.511644034809066e-06, + "loss": 0.1025, + "step": 363130 + }, + { + "epoch": 0.81, + "learning_rate": 9.51052549159974e-06, + "loss": 0.0983, + "step": 363140 + }, + { + "epoch": 0.81, + "learning_rate": 9.509406948390418e-06, + "loss": 0.1004, + "step": 363150 + }, + { + "epoch": 0.81, + "learning_rate": 9.508288405181093e-06, + "loss": 0.0996, + "step": 363160 + }, + { + "epoch": 0.81, + "learning_rate": 9.507169861971769e-06, + "loss": 0.0989, + "step": 363170 + }, + { + "epoch": 0.81, + "learning_rate": 9.506051318762445e-06, + "loss": 0.0957, + "step": 363180 + }, + { + "epoch": 0.81, + "learning_rate": 9.50493277555312e-06, + "loss": 0.1012, + "step": 363190 + }, + { + "epoch": 0.81, + "learning_rate": 9.503814232343796e-06, + "loss": 0.0981, + "step": 363200 + }, + { + "epoch": 0.81, + "learning_rate": 9.502695689134472e-06, + "loss": 0.1061, + "step": 363210 + }, + { + "epoch": 0.81, + "learning_rate": 9.501577145925147e-06, + "loss": 0.1012, + "step": 363220 + }, + { + "epoch": 0.81, + "learning_rate": 9.500458602715824e-06, + "loss": 0.1027, + "step": 363230 + }, + { + "epoch": 0.81, + "learning_rate": 9.499340059506499e-06, + "loss": 0.1007, + "step": 363240 + }, + { + "epoch": 0.81, + "learning_rate": 9.498221516297175e-06, + "loss": 0.0966, + "step": 363250 + }, + { + "epoch": 0.81, + "learning_rate": 9.497102973087851e-06, + "loss": 0.0986, + "step": 363260 + }, + { + "epoch": 0.81, + "learning_rate": 9.495984429878526e-06, + "loss": 0.1026, + "step": 363270 + }, + { + "epoch": 0.81, + "learning_rate": 9.494865886669202e-06, + "loss": 0.1023, + "step": 363280 + }, + { + "epoch": 0.81, + "learning_rate": 9.493747343459878e-06, + "loss": 0.0994, + "step": 363290 + }, + { + "epoch": 0.81, + "learning_rate": 9.492628800250555e-06, + "loss": 0.0983, + "step": 363300 + }, + { + "epoch": 0.81, + "learning_rate": 9.491510257041231e-06, + "loss": 0.0969, + "step": 363310 + }, + { + "epoch": 0.81, + "learning_rate": 9.490391713831905e-06, + "loss": 0.0985, + "step": 363320 + }, + { + "epoch": 0.81, + "learning_rate": 9.489273170622582e-06, + "loss": 0.1029, + "step": 363330 + }, + { + "epoch": 0.81, + "learning_rate": 9.488154627413258e-06, + "loss": 0.0954, + "step": 363340 + }, + { + "epoch": 0.81, + "learning_rate": 9.487036084203932e-06, + "loss": 0.098, + "step": 363350 + }, + { + "epoch": 0.81, + "learning_rate": 9.485917540994609e-06, + "loss": 0.0972, + "step": 363360 + }, + { + "epoch": 0.81, + "learning_rate": 9.484798997785285e-06, + "loss": 0.0993, + "step": 363370 + }, + { + "epoch": 0.81, + "learning_rate": 9.483680454575961e-06, + "loss": 0.0994, + "step": 363380 + }, + { + "epoch": 0.81, + "learning_rate": 9.482561911366637e-06, + "loss": 0.1012, + "step": 363390 + }, + { + "epoch": 0.81, + "learning_rate": 9.481443368157312e-06, + "loss": 0.0972, + "step": 363400 + }, + { + "epoch": 0.81, + "learning_rate": 9.480324824947988e-06, + "loss": 0.0998, + "step": 363410 + }, + { + "epoch": 0.81, + "learning_rate": 9.479206281738664e-06, + "loss": 0.0966, + "step": 363420 + }, + { + "epoch": 0.81, + "learning_rate": 9.47808773852934e-06, + "loss": 0.0989, + "step": 363430 + }, + { + "epoch": 0.81, + "learning_rate": 9.476969195320015e-06, + "loss": 0.1013, + "step": 363440 + }, + { + "epoch": 0.81, + "learning_rate": 9.475850652110691e-06, + "loss": 0.0979, + "step": 363450 + }, + { + "epoch": 0.81, + "learning_rate": 9.474732108901368e-06, + "loss": 0.0995, + "step": 363460 + }, + { + "epoch": 0.81, + "learning_rate": 9.473613565692042e-06, + "loss": 0.1011, + "step": 363470 + }, + { + "epoch": 0.81, + "learning_rate": 9.472495022482718e-06, + "loss": 0.0969, + "step": 363480 + }, + { + "epoch": 0.81, + "learning_rate": 9.471376479273395e-06, + "loss": 0.0962, + "step": 363490 + }, + { + "epoch": 0.81, + "learning_rate": 9.470257936064071e-06, + "loss": 0.0961, + "step": 363500 + }, + { + "epoch": 0.81, + "learning_rate": 9.469139392854747e-06, + "loss": 0.1001, + "step": 363510 + }, + { + "epoch": 0.81, + "learning_rate": 9.468020849645422e-06, + "loss": 0.0954, + "step": 363520 + }, + { + "epoch": 0.81, + "learning_rate": 9.466902306436098e-06, + "loss": 0.0972, + "step": 363530 + }, + { + "epoch": 0.81, + "learning_rate": 9.465783763226774e-06, + "loss": 0.1039, + "step": 363540 + }, + { + "epoch": 0.81, + "learning_rate": 9.464665220017449e-06, + "loss": 0.0997, + "step": 363550 + }, + { + "epoch": 0.81, + "learning_rate": 9.463546676808125e-06, + "loss": 0.0993, + "step": 363560 + }, + { + "epoch": 0.81, + "learning_rate": 9.462428133598801e-06, + "loss": 0.1014, + "step": 363570 + }, + { + "epoch": 0.81, + "learning_rate": 9.461309590389477e-06, + "loss": 0.1014, + "step": 363580 + }, + { + "epoch": 0.81, + "learning_rate": 9.460191047180154e-06, + "loss": 0.1002, + "step": 363590 + }, + { + "epoch": 0.81, + "learning_rate": 9.459072503970828e-06, + "loss": 0.0998, + "step": 363600 + }, + { + "epoch": 0.81, + "learning_rate": 9.457953960761504e-06, + "loss": 0.0969, + "step": 363610 + }, + { + "epoch": 0.81, + "learning_rate": 9.45683541755218e-06, + "loss": 0.1012, + "step": 363620 + }, + { + "epoch": 0.81, + "learning_rate": 9.455716874342855e-06, + "loss": 0.0985, + "step": 363630 + }, + { + "epoch": 0.81, + "learning_rate": 9.454598331133533e-06, + "loss": 0.0984, + "step": 363640 + }, + { + "epoch": 0.81, + "learning_rate": 9.453479787924208e-06, + "loss": 0.0982, + "step": 363650 + }, + { + "epoch": 0.81, + "learning_rate": 9.452361244714884e-06, + "loss": 0.101, + "step": 363660 + }, + { + "epoch": 0.81, + "learning_rate": 9.45124270150556e-06, + "loss": 0.1018, + "step": 363670 + }, + { + "epoch": 0.81, + "learning_rate": 9.450124158296235e-06, + "loss": 0.0958, + "step": 363680 + }, + { + "epoch": 0.81, + "learning_rate": 9.449005615086911e-06, + "loss": 0.0996, + "step": 363690 + }, + { + "epoch": 0.81, + "learning_rate": 9.447887071877587e-06, + "loss": 0.1033, + "step": 363700 + }, + { + "epoch": 0.81, + "learning_rate": 9.446768528668262e-06, + "loss": 0.0978, + "step": 363710 + }, + { + "epoch": 0.81, + "learning_rate": 9.44564998545894e-06, + "loss": 0.0974, + "step": 363720 + }, + { + "epoch": 0.81, + "learning_rate": 9.444531442249614e-06, + "loss": 0.0963, + "step": 363730 + }, + { + "epoch": 0.81, + "learning_rate": 9.44341289904029e-06, + "loss": 0.0977, + "step": 363740 + }, + { + "epoch": 0.81, + "learning_rate": 9.442294355830967e-06, + "loss": 0.0992, + "step": 363750 + }, + { + "epoch": 0.81, + "learning_rate": 9.441175812621641e-06, + "loss": 0.1018, + "step": 363760 + }, + { + "epoch": 0.81, + "learning_rate": 9.440057269412319e-06, + "loss": 0.0977, + "step": 363770 + }, + { + "epoch": 0.81, + "learning_rate": 9.438938726202994e-06, + "loss": 0.1021, + "step": 363780 + }, + { + "epoch": 0.81, + "learning_rate": 9.437820182993668e-06, + "loss": 0.0959, + "step": 363790 + }, + { + "epoch": 0.81, + "learning_rate": 9.436701639784346e-06, + "loss": 0.0983, + "step": 363800 + }, + { + "epoch": 0.81, + "learning_rate": 9.43558309657502e-06, + "loss": 0.1005, + "step": 363810 + }, + { + "epoch": 0.81, + "learning_rate": 9.434464553365697e-06, + "loss": 0.098, + "step": 363820 + }, + { + "epoch": 0.81, + "learning_rate": 9.433346010156373e-06, + "loss": 0.1054, + "step": 363830 + }, + { + "epoch": 0.81, + "learning_rate": 9.432227466947048e-06, + "loss": 0.0929, + "step": 363840 + }, + { + "epoch": 0.81, + "learning_rate": 9.431108923737726e-06, + "loss": 0.1037, + "step": 363850 + }, + { + "epoch": 0.81, + "learning_rate": 9.4299903805284e-06, + "loss": 0.1007, + "step": 363860 + }, + { + "epoch": 0.81, + "learning_rate": 9.428871837319075e-06, + "loss": 0.0975, + "step": 363870 + }, + { + "epoch": 0.81, + "learning_rate": 9.427753294109753e-06, + "loss": 0.0958, + "step": 363880 + }, + { + "epoch": 0.81, + "learning_rate": 9.426634750900427e-06, + "loss": 0.1009, + "step": 363890 + }, + { + "epoch": 0.81, + "learning_rate": 9.425516207691103e-06, + "loss": 0.0992, + "step": 363900 + }, + { + "epoch": 0.81, + "learning_rate": 9.42439766448178e-06, + "loss": 0.104, + "step": 363910 + }, + { + "epoch": 0.81, + "learning_rate": 9.423279121272454e-06, + "loss": 0.0944, + "step": 363920 + }, + { + "epoch": 0.81, + "learning_rate": 9.422160578063132e-06, + "loss": 0.0963, + "step": 363930 + }, + { + "epoch": 0.81, + "learning_rate": 9.421042034853807e-06, + "loss": 0.0971, + "step": 363940 + }, + { + "epoch": 0.81, + "learning_rate": 9.419923491644483e-06, + "loss": 0.0983, + "step": 363950 + }, + { + "epoch": 0.81, + "learning_rate": 9.418804948435159e-06, + "loss": 0.1006, + "step": 363960 + }, + { + "epoch": 0.81, + "learning_rate": 9.417686405225834e-06, + "loss": 0.1024, + "step": 363970 + }, + { + "epoch": 0.81, + "learning_rate": 9.416567862016511e-06, + "loss": 0.0977, + "step": 363980 + }, + { + "epoch": 0.81, + "learning_rate": 9.415449318807186e-06, + "loss": 0.1026, + "step": 363990 + }, + { + "epoch": 0.81, + "learning_rate": 9.41433077559786e-06, + "loss": 0.1013, + "step": 364000 + }, + { + "epoch": 0.81, + "learning_rate": 9.413212232388539e-06, + "loss": 0.097, + "step": 364010 + }, + { + "epoch": 0.81, + "learning_rate": 9.412093689179213e-06, + "loss": 0.1037, + "step": 364020 + }, + { + "epoch": 0.81, + "learning_rate": 9.41097514596989e-06, + "loss": 0.1025, + "step": 364030 + }, + { + "epoch": 0.81, + "learning_rate": 9.409856602760566e-06, + "loss": 0.0992, + "step": 364040 + }, + { + "epoch": 0.81, + "learning_rate": 9.40873805955124e-06, + "loss": 0.1, + "step": 364050 + }, + { + "epoch": 0.81, + "learning_rate": 9.407619516341918e-06, + "loss": 0.0968, + "step": 364060 + }, + { + "epoch": 0.81, + "learning_rate": 9.406500973132593e-06, + "loss": 0.0967, + "step": 364070 + }, + { + "epoch": 0.81, + "learning_rate": 9.405382429923267e-06, + "loss": 0.1031, + "step": 364080 + }, + { + "epoch": 0.81, + "learning_rate": 9.404263886713945e-06, + "loss": 0.0991, + "step": 364090 + }, + { + "epoch": 0.81, + "learning_rate": 9.40314534350462e-06, + "loss": 0.1009, + "step": 364100 + }, + { + "epoch": 0.81, + "learning_rate": 9.402026800295296e-06, + "loss": 0.1001, + "step": 364110 + }, + { + "epoch": 0.81, + "learning_rate": 9.400908257085972e-06, + "loss": 0.0963, + "step": 364120 + }, + { + "epoch": 0.81, + "learning_rate": 9.399789713876647e-06, + "loss": 0.0992, + "step": 364130 + }, + { + "epoch": 0.81, + "learning_rate": 9.398671170667324e-06, + "loss": 0.0977, + "step": 364140 + }, + { + "epoch": 0.81, + "learning_rate": 9.397552627457999e-06, + "loss": 0.0965, + "step": 364150 + }, + { + "epoch": 0.81, + "learning_rate": 9.396434084248675e-06, + "loss": 0.1012, + "step": 364160 + }, + { + "epoch": 0.81, + "learning_rate": 9.395315541039351e-06, + "loss": 0.0933, + "step": 364170 + }, + { + "epoch": 0.81, + "learning_rate": 9.394196997830026e-06, + "loss": 0.1014, + "step": 364180 + }, + { + "epoch": 0.81, + "learning_rate": 9.393078454620702e-06, + "loss": 0.0979, + "step": 364190 + }, + { + "epoch": 0.81, + "learning_rate": 9.391959911411378e-06, + "loss": 0.0983, + "step": 364200 + }, + { + "epoch": 0.81, + "learning_rate": 9.390841368202053e-06, + "loss": 0.1027, + "step": 364210 + }, + { + "epoch": 0.81, + "learning_rate": 9.389722824992731e-06, + "loss": 0.102, + "step": 364220 + }, + { + "epoch": 0.81, + "learning_rate": 9.388604281783405e-06, + "loss": 0.1009, + "step": 364230 + }, + { + "epoch": 0.81, + "learning_rate": 9.387485738574082e-06, + "loss": 0.0997, + "step": 364240 + }, + { + "epoch": 0.81, + "learning_rate": 9.386367195364758e-06, + "loss": 0.0996, + "step": 364250 + }, + { + "epoch": 0.81, + "learning_rate": 9.385248652155432e-06, + "loss": 0.1002, + "step": 364260 + }, + { + "epoch": 0.81, + "learning_rate": 9.384130108946109e-06, + "loss": 0.0998, + "step": 364270 + }, + { + "epoch": 0.81, + "learning_rate": 9.383011565736785e-06, + "loss": 0.1002, + "step": 364280 + }, + { + "epoch": 0.81, + "learning_rate": 9.381893022527461e-06, + "loss": 0.0968, + "step": 364290 + }, + { + "epoch": 0.81, + "learning_rate": 9.380774479318137e-06, + "loss": 0.0983, + "step": 364300 + }, + { + "epoch": 0.81, + "learning_rate": 9.379655936108812e-06, + "loss": 0.0999, + "step": 364310 + }, + { + "epoch": 0.81, + "learning_rate": 9.378537392899488e-06, + "loss": 0.0966, + "step": 364320 + }, + { + "epoch": 0.81, + "learning_rate": 9.377418849690164e-06, + "loss": 0.0968, + "step": 364330 + }, + { + "epoch": 0.81, + "learning_rate": 9.376300306480839e-06, + "loss": 0.0969, + "step": 364340 + }, + { + "epoch": 0.81, + "learning_rate": 9.375181763271515e-06, + "loss": 0.1, + "step": 364350 + }, + { + "epoch": 0.81, + "learning_rate": 9.374063220062191e-06, + "loss": 0.0988, + "step": 364360 + }, + { + "epoch": 0.81, + "learning_rate": 9.372944676852868e-06, + "loss": 0.0995, + "step": 364370 + }, + { + "epoch": 0.81, + "learning_rate": 9.371826133643544e-06, + "loss": 0.0952, + "step": 364380 + }, + { + "epoch": 0.81, + "learning_rate": 9.370707590434218e-06, + "loss": 0.1003, + "step": 364390 + }, + { + "epoch": 0.81, + "learning_rate": 9.369589047224895e-06, + "loss": 0.1005, + "step": 364400 + }, + { + "epoch": 0.81, + "learning_rate": 9.368470504015571e-06, + "loss": 0.1014, + "step": 364410 + }, + { + "epoch": 0.81, + "learning_rate": 9.367351960806245e-06, + "loss": 0.0971, + "step": 364420 + }, + { + "epoch": 0.81, + "learning_rate": 9.366233417596922e-06, + "loss": 0.1007, + "step": 364430 + }, + { + "epoch": 0.81, + "learning_rate": 9.365114874387598e-06, + "loss": 0.1017, + "step": 364440 + }, + { + "epoch": 0.81, + "learning_rate": 9.363996331178274e-06, + "loss": 0.1002, + "step": 364450 + }, + { + "epoch": 0.81, + "learning_rate": 9.36287778796895e-06, + "loss": 0.0991, + "step": 364460 + }, + { + "epoch": 0.81, + "learning_rate": 9.361759244759625e-06, + "loss": 0.0961, + "step": 364470 + }, + { + "epoch": 0.81, + "learning_rate": 9.360640701550301e-06, + "loss": 0.0967, + "step": 364480 + }, + { + "epoch": 0.81, + "learning_rate": 9.359522158340977e-06, + "loss": 0.0986, + "step": 364490 + }, + { + "epoch": 0.81, + "learning_rate": 9.358403615131654e-06, + "loss": 0.0975, + "step": 364500 + }, + { + "epoch": 0.81, + "learning_rate": 9.357285071922328e-06, + "loss": 0.103, + "step": 364510 + }, + { + "epoch": 0.81, + "learning_rate": 9.356166528713004e-06, + "loss": 0.1008, + "step": 364520 + }, + { + "epoch": 0.81, + "learning_rate": 9.35504798550368e-06, + "loss": 0.1001, + "step": 364530 + }, + { + "epoch": 0.81, + "learning_rate": 9.35404129661529e-06, + "loss": 0.099, + "step": 364540 + }, + { + "epoch": 0.81, + "learning_rate": 9.352922753405964e-06, + "loss": 0.0992, + "step": 364550 + }, + { + "epoch": 0.81, + "learning_rate": 9.35180421019664e-06, + "loss": 0.105, + "step": 364560 + }, + { + "epoch": 0.81, + "learning_rate": 9.350685666987316e-06, + "loss": 0.098, + "step": 364570 + }, + { + "epoch": 0.81, + "learning_rate": 9.349567123777991e-06, + "loss": 0.1043, + "step": 364580 + }, + { + "epoch": 0.81, + "learning_rate": 9.348448580568669e-06, + "loss": 0.0999, + "step": 364590 + }, + { + "epoch": 0.81, + "learning_rate": 9.347330037359343e-06, + "loss": 0.1002, + "step": 364600 + }, + { + "epoch": 0.81, + "learning_rate": 9.34621149415002e-06, + "loss": 0.1033, + "step": 364610 + }, + { + "epoch": 0.81, + "learning_rate": 9.345092950940696e-06, + "loss": 0.098, + "step": 364620 + }, + { + "epoch": 0.81, + "learning_rate": 9.34397440773137e-06, + "loss": 0.0987, + "step": 364630 + }, + { + "epoch": 0.81, + "learning_rate": 9.342855864522047e-06, + "loss": 0.0969, + "step": 364640 + }, + { + "epoch": 0.81, + "learning_rate": 9.341737321312723e-06, + "loss": 0.1012, + "step": 364650 + }, + { + "epoch": 0.81, + "learning_rate": 9.340618778103397e-06, + "loss": 0.0943, + "step": 364660 + }, + { + "epoch": 0.81, + "learning_rate": 9.339500234894075e-06, + "loss": 0.0976, + "step": 364670 + }, + { + "epoch": 0.81, + "learning_rate": 9.33838169168475e-06, + "loss": 0.1022, + "step": 364680 + }, + { + "epoch": 0.81, + "learning_rate": 9.337263148475426e-06, + "loss": 0.1013, + "step": 364690 + }, + { + "epoch": 0.81, + "learning_rate": 9.336144605266102e-06, + "loss": 0.1004, + "step": 364700 + }, + { + "epoch": 0.81, + "learning_rate": 9.335026062056777e-06, + "loss": 0.0973, + "step": 364710 + }, + { + "epoch": 0.81, + "learning_rate": 9.333907518847453e-06, + "loss": 0.105, + "step": 364720 + }, + { + "epoch": 0.81, + "learning_rate": 9.33278897563813e-06, + "loss": 0.0988, + "step": 364730 + }, + { + "epoch": 0.81, + "learning_rate": 9.331670432428804e-06, + "loss": 0.1038, + "step": 364740 + }, + { + "epoch": 0.81, + "learning_rate": 9.330551889219482e-06, + "loss": 0.1003, + "step": 364750 + }, + { + "epoch": 0.81, + "learning_rate": 9.329433346010156e-06, + "loss": 0.0981, + "step": 364760 + }, + { + "epoch": 0.81, + "learning_rate": 9.328314802800833e-06, + "loss": 0.0992, + "step": 364770 + }, + { + "epoch": 0.81, + "learning_rate": 9.327196259591509e-06, + "loss": 0.0977, + "step": 364780 + }, + { + "epoch": 0.81, + "learning_rate": 9.326077716382183e-06, + "loss": 0.0972, + "step": 364790 + }, + { + "epoch": 0.81, + "learning_rate": 9.324959173172861e-06, + "loss": 0.1008, + "step": 364800 + }, + { + "epoch": 0.81, + "learning_rate": 9.323840629963536e-06, + "loss": 0.0958, + "step": 364810 + }, + { + "epoch": 0.81, + "learning_rate": 9.32272208675421e-06, + "loss": 0.0985, + "step": 364820 + }, + { + "epoch": 0.81, + "learning_rate": 9.321603543544888e-06, + "loss": 0.0996, + "step": 364830 + }, + { + "epoch": 0.81, + "learning_rate": 9.320485000335563e-06, + "loss": 0.1012, + "step": 364840 + }, + { + "epoch": 0.81, + "learning_rate": 9.319366457126239e-06, + "loss": 0.1, + "step": 364850 + }, + { + "epoch": 0.81, + "learning_rate": 9.318247913916915e-06, + "loss": 0.101, + "step": 364860 + }, + { + "epoch": 0.81, + "learning_rate": 9.31712937070759e-06, + "loss": 0.1006, + "step": 364870 + }, + { + "epoch": 0.81, + "learning_rate": 9.316010827498268e-06, + "loss": 0.0985, + "step": 364880 + }, + { + "epoch": 0.81, + "learning_rate": 9.314892284288942e-06, + "loss": 0.0962, + "step": 364890 + }, + { + "epoch": 0.81, + "learning_rate": 9.313773741079619e-06, + "loss": 0.1027, + "step": 364900 + }, + { + "epoch": 0.81, + "learning_rate": 9.312655197870295e-06, + "loss": 0.0991, + "step": 364910 + }, + { + "epoch": 0.81, + "learning_rate": 9.31153665466097e-06, + "loss": 0.0982, + "step": 364920 + }, + { + "epoch": 0.81, + "learning_rate": 9.310418111451647e-06, + "loss": 0.1028, + "step": 364930 + }, + { + "epoch": 0.81, + "learning_rate": 9.309299568242322e-06, + "loss": 0.0998, + "step": 364940 + }, + { + "epoch": 0.81, + "learning_rate": 9.308181025032996e-06, + "loss": 0.1012, + "step": 364950 + }, + { + "epoch": 0.81, + "learning_rate": 9.307062481823674e-06, + "loss": 0.0988, + "step": 364960 + }, + { + "epoch": 0.81, + "learning_rate": 9.305943938614349e-06, + "loss": 0.0928, + "step": 364970 + }, + { + "epoch": 0.81, + "learning_rate": 9.304825395405025e-06, + "loss": 0.0961, + "step": 364980 + }, + { + "epoch": 0.81, + "learning_rate": 9.303706852195701e-06, + "loss": 0.0986, + "step": 364990 + }, + { + "epoch": 0.81, + "learning_rate": 9.302588308986376e-06, + "loss": 0.0975, + "step": 365000 + }, + { + "epoch": 0.81, + "learning_rate": 9.301469765777054e-06, + "loss": 0.1002, + "step": 365010 + }, + { + "epoch": 0.81, + "learning_rate": 9.300351222567728e-06, + "loss": 0.0953, + "step": 365020 + }, + { + "epoch": 0.81, + "learning_rate": 9.299232679358403e-06, + "loss": 0.102, + "step": 365030 + }, + { + "epoch": 0.81, + "learning_rate": 9.29811413614908e-06, + "loss": 0.1011, + "step": 365040 + }, + { + "epoch": 0.81, + "learning_rate": 9.296995592939755e-06, + "loss": 0.0982, + "step": 365050 + }, + { + "epoch": 0.81, + "learning_rate": 9.295877049730432e-06, + "loss": 0.0955, + "step": 365060 + }, + { + "epoch": 0.81, + "learning_rate": 9.294758506521108e-06, + "loss": 0.0998, + "step": 365070 + }, + { + "epoch": 0.81, + "learning_rate": 9.293639963311782e-06, + "loss": 0.0986, + "step": 365080 + }, + { + "epoch": 0.81, + "learning_rate": 9.29252142010246e-06, + "loss": 0.1045, + "step": 365090 + }, + { + "epoch": 0.81, + "learning_rate": 9.291402876893135e-06, + "loss": 0.0995, + "step": 365100 + }, + { + "epoch": 0.81, + "learning_rate": 9.290284333683811e-06, + "loss": 0.1003, + "step": 365110 + }, + { + "epoch": 0.81, + "learning_rate": 9.289165790474487e-06, + "loss": 0.1037, + "step": 365120 + }, + { + "epoch": 0.82, + "learning_rate": 9.288047247265162e-06, + "loss": 0.0954, + "step": 365130 + }, + { + "epoch": 0.82, + "learning_rate": 9.286928704055838e-06, + "loss": 0.1017, + "step": 365140 + }, + { + "epoch": 0.82, + "learning_rate": 9.285810160846514e-06, + "loss": 0.0977, + "step": 365150 + }, + { + "epoch": 0.82, + "learning_rate": 9.284691617637189e-06, + "loss": 0.0995, + "step": 365160 + }, + { + "epoch": 0.82, + "learning_rate": 9.283573074427867e-06, + "loss": 0.0964, + "step": 365170 + }, + { + "epoch": 0.82, + "learning_rate": 9.282454531218541e-06, + "loss": 0.0996, + "step": 365180 + }, + { + "epoch": 0.82, + "learning_rate": 9.281335988009217e-06, + "loss": 0.0996, + "step": 365190 + }, + { + "epoch": 0.82, + "learning_rate": 9.280217444799894e-06, + "loss": 0.1039, + "step": 365200 + }, + { + "epoch": 0.82, + "learning_rate": 9.279098901590568e-06, + "loss": 0.1028, + "step": 365210 + }, + { + "epoch": 0.82, + "learning_rate": 9.277980358381244e-06, + "loss": 0.1005, + "step": 365220 + }, + { + "epoch": 0.82, + "learning_rate": 9.27686181517192e-06, + "loss": 0.0959, + "step": 365230 + }, + { + "epoch": 0.82, + "learning_rate": 9.275743271962597e-06, + "loss": 0.1001, + "step": 365240 + }, + { + "epoch": 0.82, + "learning_rate": 9.274624728753273e-06, + "loss": 0.0994, + "step": 365250 + }, + { + "epoch": 0.82, + "learning_rate": 9.273506185543948e-06, + "loss": 0.0981, + "step": 365260 + }, + { + "epoch": 0.82, + "learning_rate": 9.272387642334624e-06, + "loss": 0.1012, + "step": 365270 + }, + { + "epoch": 0.82, + "learning_rate": 9.2712690991253e-06, + "loss": 0.0987, + "step": 365280 + }, + { + "epoch": 0.82, + "learning_rate": 9.270150555915975e-06, + "loss": 0.1032, + "step": 365290 + }, + { + "epoch": 0.82, + "learning_rate": 9.269032012706651e-06, + "loss": 0.0965, + "step": 365300 + }, + { + "epoch": 0.82, + "learning_rate": 9.267913469497327e-06, + "loss": 0.0964, + "step": 365310 + }, + { + "epoch": 0.82, + "learning_rate": 9.266794926288003e-06, + "loss": 0.1029, + "step": 365320 + }, + { + "epoch": 0.82, + "learning_rate": 9.26567638307868e-06, + "loss": 0.0951, + "step": 365330 + }, + { + "epoch": 0.82, + "learning_rate": 9.264557839869354e-06, + "loss": 0.1022, + "step": 365340 + }, + { + "epoch": 0.82, + "learning_rate": 9.26343929666003e-06, + "loss": 0.0983, + "step": 365350 + }, + { + "epoch": 0.82, + "learning_rate": 9.262320753450707e-06, + "loss": 0.1008, + "step": 365360 + }, + { + "epoch": 0.82, + "learning_rate": 9.261202210241381e-06, + "loss": 0.1019, + "step": 365370 + }, + { + "epoch": 0.82, + "learning_rate": 9.260083667032057e-06, + "loss": 0.1027, + "step": 365380 + }, + { + "epoch": 0.82, + "learning_rate": 9.258965123822734e-06, + "loss": 0.1002, + "step": 365390 + }, + { + "epoch": 0.82, + "learning_rate": 9.25784658061341e-06, + "loss": 0.1026, + "step": 365400 + }, + { + "epoch": 0.82, + "learning_rate": 9.256728037404086e-06, + "loss": 0.0997, + "step": 365410 + }, + { + "epoch": 0.82, + "learning_rate": 9.25560949419476e-06, + "loss": 0.0976, + "step": 365420 + }, + { + "epoch": 0.82, + "learning_rate": 9.254490950985437e-06, + "loss": 0.097, + "step": 365430 + }, + { + "epoch": 0.82, + "learning_rate": 9.253372407776113e-06, + "loss": 0.1003, + "step": 365440 + }, + { + "epoch": 0.82, + "learning_rate": 9.25225386456679e-06, + "loss": 0.0977, + "step": 365450 + }, + { + "epoch": 0.82, + "learning_rate": 9.251135321357464e-06, + "loss": 0.0977, + "step": 365460 + }, + { + "epoch": 0.82, + "learning_rate": 9.25001677814814e-06, + "loss": 0.1006, + "step": 365470 + }, + { + "epoch": 0.82, + "learning_rate": 9.248898234938816e-06, + "loss": 0.1004, + "step": 365480 + }, + { + "epoch": 0.82, + "learning_rate": 9.247779691729493e-06, + "loss": 0.0987, + "step": 365490 + }, + { + "epoch": 0.82, + "learning_rate": 9.246661148520167e-06, + "loss": 0.0994, + "step": 365500 + }, + { + "epoch": 0.82, + "learning_rate": 9.245542605310843e-06, + "loss": 0.1008, + "step": 365510 + }, + { + "epoch": 0.82, + "learning_rate": 9.24442406210152e-06, + "loss": 0.0965, + "step": 365520 + }, + { + "epoch": 0.82, + "learning_rate": 9.243305518892196e-06, + "loss": 0.0995, + "step": 365530 + }, + { + "epoch": 0.82, + "learning_rate": 9.24218697568287e-06, + "loss": 0.1005, + "step": 365540 + }, + { + "epoch": 0.82, + "learning_rate": 9.241068432473547e-06, + "loss": 0.1004, + "step": 365550 + }, + { + "epoch": 0.82, + "learning_rate": 9.239949889264223e-06, + "loss": 0.0975, + "step": 365560 + }, + { + "epoch": 0.82, + "learning_rate": 9.238831346054899e-06, + "loss": 0.0999, + "step": 365570 + }, + { + "epoch": 0.82, + "learning_rate": 9.237712802845574e-06, + "loss": 0.1003, + "step": 365580 + }, + { + "epoch": 0.82, + "learning_rate": 9.23659425963625e-06, + "loss": 0.1005, + "step": 365590 + }, + { + "epoch": 0.82, + "learning_rate": 9.235475716426926e-06, + "loss": 0.0956, + "step": 365600 + }, + { + "epoch": 0.82, + "learning_rate": 9.234357173217602e-06, + "loss": 0.0952, + "step": 365610 + }, + { + "epoch": 0.82, + "learning_rate": 9.233238630008277e-06, + "loss": 0.0973, + "step": 365620 + }, + { + "epoch": 0.82, + "learning_rate": 9.232120086798953e-06, + "loss": 0.0998, + "step": 365630 + }, + { + "epoch": 0.82, + "learning_rate": 9.23100154358963e-06, + "loss": 0.1034, + "step": 365640 + }, + { + "epoch": 0.82, + "learning_rate": 9.229883000380306e-06, + "loss": 0.1016, + "step": 365650 + }, + { + "epoch": 0.82, + "learning_rate": 9.228764457170982e-06, + "loss": 0.0996, + "step": 365660 + }, + { + "epoch": 0.82, + "learning_rate": 9.227645913961656e-06, + "loss": 0.1016, + "step": 365670 + }, + { + "epoch": 0.82, + "learning_rate": 9.226527370752333e-06, + "loss": 0.1029, + "step": 365680 + }, + { + "epoch": 0.82, + "learning_rate": 9.225408827543009e-06, + "loss": 0.0947, + "step": 365690 + }, + { + "epoch": 0.82, + "learning_rate": 9.224290284333683e-06, + "loss": 0.1046, + "step": 365700 + }, + { + "epoch": 0.82, + "learning_rate": 9.22317174112436e-06, + "loss": 0.1002, + "step": 365710 + }, + { + "epoch": 0.82, + "learning_rate": 9.222053197915036e-06, + "loss": 0.1015, + "step": 365720 + }, + { + "epoch": 0.82, + "learning_rate": 9.220934654705712e-06, + "loss": 0.0983, + "step": 365730 + }, + { + "epoch": 0.82, + "learning_rate": 9.219816111496388e-06, + "loss": 0.101, + "step": 365740 + }, + { + "epoch": 0.82, + "learning_rate": 9.218697568287063e-06, + "loss": 0.0994, + "step": 365750 + }, + { + "epoch": 0.82, + "learning_rate": 9.217579025077739e-06, + "loss": 0.0972, + "step": 365760 + }, + { + "epoch": 0.82, + "learning_rate": 9.216460481868415e-06, + "loss": 0.1013, + "step": 365770 + }, + { + "epoch": 0.82, + "learning_rate": 9.21534193865909e-06, + "loss": 0.1006, + "step": 365780 + }, + { + "epoch": 0.82, + "learning_rate": 9.214223395449768e-06, + "loss": 0.1017, + "step": 365790 + }, + { + "epoch": 0.82, + "learning_rate": 9.213104852240442e-06, + "loss": 0.1009, + "step": 365800 + }, + { + "epoch": 0.82, + "learning_rate": 9.211986309031119e-06, + "loss": 0.0997, + "step": 365810 + }, + { + "epoch": 0.82, + "learning_rate": 9.210867765821795e-06, + "loss": 0.0968, + "step": 365820 + }, + { + "epoch": 0.82, + "learning_rate": 9.20974922261247e-06, + "loss": 0.0995, + "step": 365830 + }, + { + "epoch": 0.82, + "learning_rate": 9.208630679403146e-06, + "loss": 0.1023, + "step": 365840 + }, + { + "epoch": 0.82, + "learning_rate": 9.207512136193822e-06, + "loss": 0.1012, + "step": 365850 + }, + { + "epoch": 0.82, + "learning_rate": 9.206393592984496e-06, + "loss": 0.0992, + "step": 365860 + }, + { + "epoch": 0.82, + "learning_rate": 9.205275049775174e-06, + "loss": 0.0988, + "step": 365870 + }, + { + "epoch": 0.82, + "learning_rate": 9.204156506565849e-06, + "loss": 0.098, + "step": 365880 + }, + { + "epoch": 0.82, + "learning_rate": 9.203037963356525e-06, + "loss": 0.0962, + "step": 365890 + }, + { + "epoch": 0.82, + "learning_rate": 9.201919420147201e-06, + "loss": 0.0963, + "step": 365900 + }, + { + "epoch": 0.82, + "learning_rate": 9.200800876937876e-06, + "loss": 0.0998, + "step": 365910 + }, + { + "epoch": 0.82, + "learning_rate": 9.199682333728552e-06, + "loss": 0.0963, + "step": 365920 + }, + { + "epoch": 0.82, + "learning_rate": 9.198563790519228e-06, + "loss": 0.0932, + "step": 365930 + }, + { + "epoch": 0.82, + "learning_rate": 9.197445247309903e-06, + "loss": 0.0991, + "step": 365940 + }, + { + "epoch": 0.82, + "learning_rate": 9.19632670410058e-06, + "loss": 0.0998, + "step": 365950 + }, + { + "epoch": 0.82, + "learning_rate": 9.195208160891255e-06, + "loss": 0.0986, + "step": 365960 + }, + { + "epoch": 0.82, + "learning_rate": 9.194089617681932e-06, + "loss": 0.0967, + "step": 365970 + }, + { + "epoch": 0.82, + "learning_rate": 9.192971074472608e-06, + "loss": 0.0976, + "step": 365980 + }, + { + "epoch": 0.82, + "learning_rate": 9.191852531263282e-06, + "loss": 0.0975, + "step": 365990 + }, + { + "epoch": 0.82, + "learning_rate": 9.19073398805396e-06, + "loss": 0.1007, + "step": 366000 + }, + { + "epoch": 0.82, + "learning_rate": 9.189615444844635e-06, + "loss": 0.0996, + "step": 366010 + }, + { + "epoch": 0.82, + "learning_rate": 9.18849690163531e-06, + "loss": 0.0989, + "step": 366020 + }, + { + "epoch": 0.82, + "learning_rate": 9.187378358425987e-06, + "loss": 0.0954, + "step": 366030 + }, + { + "epoch": 0.82, + "learning_rate": 9.186259815216662e-06, + "loss": 0.0904, + "step": 366040 + }, + { + "epoch": 0.82, + "learning_rate": 9.185141272007338e-06, + "loss": 0.1011, + "step": 366050 + }, + { + "epoch": 0.82, + "learning_rate": 9.184022728798014e-06, + "loss": 0.1017, + "step": 366060 + }, + { + "epoch": 0.82, + "learning_rate": 9.182904185588689e-06, + "loss": 0.0991, + "step": 366070 + }, + { + "epoch": 0.82, + "learning_rate": 9.181785642379367e-06, + "loss": 0.0988, + "step": 366080 + }, + { + "epoch": 0.82, + "learning_rate": 9.180667099170041e-06, + "loss": 0.102, + "step": 366090 + }, + { + "epoch": 0.82, + "learning_rate": 9.179548555960717e-06, + "loss": 0.1033, + "step": 366100 + }, + { + "epoch": 0.82, + "learning_rate": 9.178430012751394e-06, + "loss": 0.0948, + "step": 366110 + }, + { + "epoch": 0.82, + "learning_rate": 9.177311469542068e-06, + "loss": 0.0965, + "step": 366120 + }, + { + "epoch": 0.82, + "learning_rate": 9.176192926332746e-06, + "loss": 0.0977, + "step": 366130 + }, + { + "epoch": 0.82, + "learning_rate": 9.17507438312342e-06, + "loss": 0.0991, + "step": 366140 + }, + { + "epoch": 0.82, + "learning_rate": 9.173955839914095e-06, + "loss": 0.0946, + "step": 366150 + }, + { + "epoch": 0.82, + "learning_rate": 9.172837296704773e-06, + "loss": 0.0989, + "step": 366160 + }, + { + "epoch": 0.82, + "learning_rate": 9.171718753495448e-06, + "loss": 0.0965, + "step": 366170 + }, + { + "epoch": 0.82, + "learning_rate": 9.170600210286124e-06, + "loss": 0.097, + "step": 366180 + }, + { + "epoch": 0.82, + "learning_rate": 9.1694816670768e-06, + "loss": 0.0966, + "step": 366190 + }, + { + "epoch": 0.82, + "learning_rate": 9.168363123867475e-06, + "loss": 0.0989, + "step": 366200 + }, + { + "epoch": 0.82, + "learning_rate": 9.167244580658153e-06, + "loss": 0.0971, + "step": 366210 + }, + { + "epoch": 0.82, + "learning_rate": 9.166126037448827e-06, + "loss": 0.1014, + "step": 366220 + }, + { + "epoch": 0.82, + "learning_rate": 9.165007494239502e-06, + "loss": 0.1018, + "step": 366230 + }, + { + "epoch": 0.82, + "learning_rate": 9.16388895103018e-06, + "loss": 0.1002, + "step": 366240 + }, + { + "epoch": 0.82, + "learning_rate": 9.162770407820854e-06, + "loss": 0.1018, + "step": 366250 + }, + { + "epoch": 0.82, + "learning_rate": 9.16165186461153e-06, + "loss": 0.1009, + "step": 366260 + }, + { + "epoch": 0.82, + "learning_rate": 9.160533321402207e-06, + "loss": 0.0962, + "step": 366270 + }, + { + "epoch": 0.82, + "learning_rate": 9.159414778192881e-06, + "loss": 0.1011, + "step": 366280 + }, + { + "epoch": 0.82, + "learning_rate": 9.158296234983559e-06, + "loss": 0.0973, + "step": 366290 + }, + { + "epoch": 0.82, + "learning_rate": 9.157177691774234e-06, + "loss": 0.0929, + "step": 366300 + }, + { + "epoch": 0.82, + "learning_rate": 9.15605914856491e-06, + "loss": 0.1, + "step": 366310 + }, + { + "epoch": 0.82, + "learning_rate": 9.154940605355586e-06, + "loss": 0.1007, + "step": 366320 + }, + { + "epoch": 0.82, + "learning_rate": 9.15382206214626e-06, + "loss": 0.1007, + "step": 366330 + }, + { + "epoch": 0.82, + "learning_rate": 9.152703518936937e-06, + "loss": 0.0988, + "step": 366340 + }, + { + "epoch": 0.82, + "learning_rate": 9.151584975727613e-06, + "loss": 0.1004, + "step": 366350 + }, + { + "epoch": 0.82, + "learning_rate": 9.150466432518288e-06, + "loss": 0.1013, + "step": 366360 + }, + { + "epoch": 0.82, + "learning_rate": 9.149347889308966e-06, + "loss": 0.0989, + "step": 366370 + }, + { + "epoch": 0.82, + "learning_rate": 9.14822934609964e-06, + "loss": 0.0987, + "step": 366380 + }, + { + "epoch": 0.82, + "learning_rate": 9.147110802890316e-06, + "loss": 0.0986, + "step": 366390 + }, + { + "epoch": 0.82, + "learning_rate": 9.145992259680993e-06, + "loss": 0.1002, + "step": 366400 + }, + { + "epoch": 0.82, + "learning_rate": 9.144873716471667e-06, + "loss": 0.1008, + "step": 366410 + }, + { + "epoch": 0.82, + "learning_rate": 9.143755173262343e-06, + "loss": 0.0972, + "step": 366420 + }, + { + "epoch": 0.82, + "learning_rate": 9.14263663005302e-06, + "loss": 0.0973, + "step": 366430 + }, + { + "epoch": 0.82, + "learning_rate": 9.141518086843696e-06, + "loss": 0.1023, + "step": 366440 + }, + { + "epoch": 0.82, + "learning_rate": 9.14039954363437e-06, + "loss": 0.1001, + "step": 366450 + }, + { + "epoch": 0.82, + "learning_rate": 9.139281000425047e-06, + "loss": 0.0984, + "step": 366460 + }, + { + "epoch": 0.82, + "learning_rate": 9.138162457215723e-06, + "loss": 0.0984, + "step": 366470 + }, + { + "epoch": 0.82, + "learning_rate": 9.137043914006399e-06, + "loss": 0.1021, + "step": 366480 + }, + { + "epoch": 0.82, + "learning_rate": 9.135925370797074e-06, + "loss": 0.0984, + "step": 366490 + }, + { + "epoch": 0.82, + "learning_rate": 9.13480682758775e-06, + "loss": 0.1, + "step": 366500 + }, + { + "epoch": 0.82, + "learning_rate": 9.133688284378426e-06, + "loss": 0.0963, + "step": 366510 + }, + { + "epoch": 0.82, + "learning_rate": 9.132569741169102e-06, + "loss": 0.0974, + "step": 366520 + }, + { + "epoch": 0.82, + "learning_rate": 9.131451197959777e-06, + "loss": 0.1059, + "step": 366530 + }, + { + "epoch": 0.82, + "learning_rate": 9.130332654750453e-06, + "loss": 0.1008, + "step": 366540 + }, + { + "epoch": 0.82, + "learning_rate": 9.129325965862062e-06, + "loss": 0.1003, + "step": 366550 + }, + { + "epoch": 0.82, + "learning_rate": 9.128207422652738e-06, + "loss": 0.0978, + "step": 366560 + }, + { + "epoch": 0.82, + "learning_rate": 9.127088879443413e-06, + "loss": 0.0955, + "step": 366570 + }, + { + "epoch": 0.82, + "learning_rate": 9.125970336234089e-06, + "loss": 0.1036, + "step": 366580 + }, + { + "epoch": 0.82, + "learning_rate": 9.124851793024765e-06, + "loss": 0.1032, + "step": 366590 + }, + { + "epoch": 0.82, + "learning_rate": 9.12373324981544e-06, + "loss": 0.096, + "step": 366600 + }, + { + "epoch": 0.82, + "learning_rate": 9.122614706606118e-06, + "loss": 0.0994, + "step": 366610 + }, + { + "epoch": 0.82, + "learning_rate": 9.121496163396792e-06, + "loss": 0.0956, + "step": 366620 + }, + { + "epoch": 0.82, + "learning_rate": 9.120377620187468e-06, + "loss": 0.0966, + "step": 366630 + }, + { + "epoch": 0.82, + "learning_rate": 9.119259076978145e-06, + "loss": 0.0966, + "step": 366640 + }, + { + "epoch": 0.82, + "learning_rate": 9.11814053376882e-06, + "loss": 0.1032, + "step": 366650 + }, + { + "epoch": 0.82, + "learning_rate": 9.117021990559495e-06, + "loss": 0.1007, + "step": 366660 + }, + { + "epoch": 0.82, + "learning_rate": 9.115903447350172e-06, + "loss": 0.1035, + "step": 366670 + }, + { + "epoch": 0.82, + "learning_rate": 9.114784904140846e-06, + "loss": 0.0986, + "step": 366680 + }, + { + "epoch": 0.82, + "learning_rate": 9.113666360931524e-06, + "loss": 0.096, + "step": 366690 + }, + { + "epoch": 0.82, + "learning_rate": 9.112547817722199e-06, + "loss": 0.1014, + "step": 366700 + }, + { + "epoch": 0.82, + "learning_rate": 9.111429274512875e-06, + "loss": 0.0982, + "step": 366710 + }, + { + "epoch": 0.82, + "learning_rate": 9.110310731303551e-06, + "loss": 0.1012, + "step": 366720 + }, + { + "epoch": 0.82, + "learning_rate": 9.109192188094226e-06, + "loss": 0.0951, + "step": 366730 + }, + { + "epoch": 0.82, + "learning_rate": 9.108073644884904e-06, + "loss": 0.1018, + "step": 366740 + }, + { + "epoch": 0.82, + "learning_rate": 9.106955101675578e-06, + "loss": 0.0992, + "step": 366750 + }, + { + "epoch": 0.82, + "learning_rate": 9.105836558466253e-06, + "loss": 0.1005, + "step": 366760 + }, + { + "epoch": 0.82, + "learning_rate": 9.10471801525693e-06, + "loss": 0.0961, + "step": 366770 + }, + { + "epoch": 0.82, + "learning_rate": 9.103599472047605e-06, + "loss": 0.0945, + "step": 366780 + }, + { + "epoch": 0.82, + "learning_rate": 9.102480928838281e-06, + "loss": 0.0939, + "step": 366790 + }, + { + "epoch": 0.82, + "learning_rate": 9.101362385628958e-06, + "loss": 0.0978, + "step": 366800 + }, + { + "epoch": 0.82, + "learning_rate": 9.100243842419632e-06, + "loss": 0.0927, + "step": 366810 + }, + { + "epoch": 0.82, + "learning_rate": 9.09912529921031e-06, + "loss": 0.0966, + "step": 366820 + }, + { + "epoch": 0.82, + "learning_rate": 9.098006756000985e-06, + "loss": 0.0951, + "step": 366830 + }, + { + "epoch": 0.82, + "learning_rate": 9.096888212791659e-06, + "loss": 0.0982, + "step": 366840 + }, + { + "epoch": 0.82, + "learning_rate": 9.095769669582337e-06, + "loss": 0.0987, + "step": 366850 + }, + { + "epoch": 0.82, + "learning_rate": 9.094651126373012e-06, + "loss": 0.099, + "step": 366860 + }, + { + "epoch": 0.82, + "learning_rate": 9.093532583163688e-06, + "loss": 0.0946, + "step": 366870 + }, + { + "epoch": 0.82, + "learning_rate": 9.092414039954364e-06, + "loss": 0.1009, + "step": 366880 + }, + { + "epoch": 0.82, + "learning_rate": 9.091295496745039e-06, + "loss": 0.0936, + "step": 366890 + }, + { + "epoch": 0.82, + "learning_rate": 9.090176953535717e-06, + "loss": 0.0972, + "step": 366900 + }, + { + "epoch": 0.82, + "learning_rate": 9.089058410326391e-06, + "loss": 0.0945, + "step": 366910 + }, + { + "epoch": 0.82, + "learning_rate": 9.087939867117067e-06, + "loss": 0.1013, + "step": 366920 + }, + { + "epoch": 0.82, + "learning_rate": 9.086821323907744e-06, + "loss": 0.0931, + "step": 366930 + }, + { + "epoch": 0.82, + "learning_rate": 9.085702780698418e-06, + "loss": 0.0977, + "step": 366940 + }, + { + "epoch": 0.82, + "learning_rate": 9.084584237489096e-06, + "loss": 0.1022, + "step": 366950 + }, + { + "epoch": 0.82, + "learning_rate": 9.08346569427977e-06, + "loss": 0.098, + "step": 366960 + }, + { + "epoch": 0.82, + "learning_rate": 9.082347151070445e-06, + "loss": 0.0977, + "step": 366970 + }, + { + "epoch": 0.82, + "learning_rate": 9.081228607861123e-06, + "loss": 0.0983, + "step": 366980 + }, + { + "epoch": 0.82, + "learning_rate": 9.080110064651798e-06, + "loss": 0.098, + "step": 366990 + }, + { + "epoch": 0.82, + "learning_rate": 9.078991521442474e-06, + "loss": 0.0964, + "step": 367000 + }, + { + "epoch": 0.82, + "learning_rate": 9.077984832554083e-06, + "loss": 0.0979, + "step": 367010 + }, + { + "epoch": 0.82, + "learning_rate": 9.076866289344759e-06, + "loss": 0.1054, + "step": 367020 + }, + { + "epoch": 0.82, + "learning_rate": 9.075747746135433e-06, + "loss": 0.0972, + "step": 367030 + }, + { + "epoch": 0.82, + "learning_rate": 9.07462920292611e-06, + "loss": 0.1039, + "step": 367040 + }, + { + "epoch": 0.82, + "learning_rate": 9.073510659716786e-06, + "loss": 0.0993, + "step": 367050 + }, + { + "epoch": 0.82, + "learning_rate": 9.07239211650746e-06, + "loss": 0.0969, + "step": 367060 + }, + { + "epoch": 0.82, + "learning_rate": 9.071273573298137e-06, + "loss": 0.0994, + "step": 367070 + }, + { + "epoch": 0.82, + "learning_rate": 9.070155030088813e-06, + "loss": 0.1016, + "step": 367080 + }, + { + "epoch": 0.82, + "learning_rate": 9.069036486879489e-06, + "loss": 0.0956, + "step": 367090 + }, + { + "epoch": 0.82, + "learning_rate": 9.067917943670165e-06, + "loss": 0.0995, + "step": 367100 + }, + { + "epoch": 0.82, + "learning_rate": 9.06679940046084e-06, + "loss": 0.0995, + "step": 367110 + }, + { + "epoch": 0.82, + "learning_rate": 9.065680857251516e-06, + "loss": 0.0975, + "step": 367120 + }, + { + "epoch": 0.82, + "learning_rate": 9.064562314042192e-06, + "loss": 0.0993, + "step": 367130 + }, + { + "epoch": 0.82, + "learning_rate": 9.063443770832867e-06, + "loss": 0.1, + "step": 367140 + }, + { + "epoch": 0.82, + "learning_rate": 9.062325227623543e-06, + "loss": 0.0956, + "step": 367150 + }, + { + "epoch": 0.82, + "learning_rate": 9.06120668441422e-06, + "loss": 0.102, + "step": 367160 + }, + { + "epoch": 0.82, + "learning_rate": 9.060088141204896e-06, + "loss": 0.0988, + "step": 367170 + }, + { + "epoch": 0.82, + "learning_rate": 9.058969597995572e-06, + "loss": 0.0974, + "step": 367180 + }, + { + "epoch": 0.82, + "learning_rate": 9.057851054786246e-06, + "loss": 0.0974, + "step": 367190 + }, + { + "epoch": 0.82, + "learning_rate": 9.056732511576923e-06, + "loss": 0.0988, + "step": 367200 + }, + { + "epoch": 0.82, + "learning_rate": 9.055613968367599e-06, + "loss": 0.1024, + "step": 367210 + }, + { + "epoch": 0.82, + "learning_rate": 9.054495425158275e-06, + "loss": 0.0972, + "step": 367220 + }, + { + "epoch": 0.82, + "learning_rate": 9.05337688194895e-06, + "loss": 0.1019, + "step": 367230 + }, + { + "epoch": 0.82, + "learning_rate": 9.052258338739626e-06, + "loss": 0.096, + "step": 367240 + }, + { + "epoch": 0.82, + "learning_rate": 9.051139795530302e-06, + "loss": 0.0982, + "step": 367250 + }, + { + "epoch": 0.82, + "learning_rate": 9.050021252320978e-06, + "loss": 0.0941, + "step": 367260 + }, + { + "epoch": 0.82, + "learning_rate": 9.048902709111653e-06, + "loss": 0.1019, + "step": 367270 + }, + { + "epoch": 0.82, + "learning_rate": 9.047784165902329e-06, + "loss": 0.0971, + "step": 367280 + }, + { + "epoch": 0.82, + "learning_rate": 9.046665622693005e-06, + "loss": 0.0963, + "step": 367290 + }, + { + "epoch": 0.82, + "learning_rate": 9.045547079483681e-06, + "loss": 0.0981, + "step": 367300 + }, + { + "epoch": 0.82, + "learning_rate": 9.044428536274356e-06, + "loss": 0.1005, + "step": 367310 + }, + { + "epoch": 0.82, + "learning_rate": 9.043309993065032e-06, + "loss": 0.0978, + "step": 367320 + }, + { + "epoch": 0.82, + "learning_rate": 9.042191449855708e-06, + "loss": 0.0956, + "step": 367330 + }, + { + "epoch": 0.82, + "learning_rate": 9.041072906646385e-06, + "loss": 0.0972, + "step": 367340 + }, + { + "epoch": 0.82, + "learning_rate": 9.03995436343706e-06, + "loss": 0.096, + "step": 367350 + }, + { + "epoch": 0.82, + "learning_rate": 9.038835820227735e-06, + "loss": 0.0994, + "step": 367360 + }, + { + "epoch": 0.82, + "learning_rate": 9.037717277018412e-06, + "loss": 0.0965, + "step": 367370 + }, + { + "epoch": 0.82, + "learning_rate": 9.036598733809088e-06, + "loss": 0.0948, + "step": 367380 + }, + { + "epoch": 0.82, + "learning_rate": 9.035480190599762e-06, + "loss": 0.1031, + "step": 367390 + }, + { + "epoch": 0.82, + "learning_rate": 9.034361647390439e-06, + "loss": 0.0994, + "step": 367400 + }, + { + "epoch": 0.82, + "learning_rate": 9.033243104181115e-06, + "loss": 0.1003, + "step": 367410 + }, + { + "epoch": 0.82, + "learning_rate": 9.032124560971791e-06, + "loss": 0.101, + "step": 367420 + }, + { + "epoch": 0.82, + "learning_rate": 9.031006017762467e-06, + "loss": 0.1003, + "step": 367430 + }, + { + "epoch": 0.82, + "learning_rate": 9.029887474553142e-06, + "loss": 0.0976, + "step": 367440 + }, + { + "epoch": 0.82, + "learning_rate": 9.028768931343818e-06, + "loss": 0.0951, + "step": 367450 + }, + { + "epoch": 0.82, + "learning_rate": 9.027650388134494e-06, + "loss": 0.098, + "step": 367460 + }, + { + "epoch": 0.82, + "learning_rate": 9.026531844925169e-06, + "loss": 0.1022, + "step": 367470 + }, + { + "epoch": 0.82, + "learning_rate": 9.025413301715845e-06, + "loss": 0.095, + "step": 367480 + }, + { + "epoch": 0.82, + "learning_rate": 9.024294758506521e-06, + "loss": 0.1008, + "step": 367490 + }, + { + "epoch": 0.82, + "learning_rate": 9.023176215297198e-06, + "loss": 0.0973, + "step": 367500 + }, + { + "epoch": 0.82, + "learning_rate": 9.022057672087874e-06, + "loss": 0.1011, + "step": 367510 + }, + { + "epoch": 0.82, + "learning_rate": 9.020939128878548e-06, + "loss": 0.0972, + "step": 367520 + }, + { + "epoch": 0.82, + "learning_rate": 9.019820585669225e-06, + "loss": 0.1007, + "step": 367530 + }, + { + "epoch": 0.82, + "learning_rate": 9.018702042459901e-06, + "loss": 0.0966, + "step": 367540 + }, + { + "epoch": 0.82, + "learning_rate": 9.017583499250575e-06, + "loss": 0.095, + "step": 367550 + }, + { + "epoch": 0.82, + "learning_rate": 9.016464956041253e-06, + "loss": 0.0953, + "step": 367560 + }, + { + "epoch": 0.82, + "learning_rate": 9.015346412831928e-06, + "loss": 0.0975, + "step": 367570 + }, + { + "epoch": 0.82, + "learning_rate": 9.014227869622604e-06, + "loss": 0.0976, + "step": 367580 + }, + { + "epoch": 0.82, + "learning_rate": 9.01310932641328e-06, + "loss": 0.097, + "step": 367590 + }, + { + "epoch": 0.82, + "learning_rate": 9.011990783203955e-06, + "loss": 0.0973, + "step": 367600 + }, + { + "epoch": 0.82, + "learning_rate": 9.010872239994631e-06, + "loss": 0.1036, + "step": 367610 + }, + { + "epoch": 0.82, + "learning_rate": 9.009753696785307e-06, + "loss": 0.0986, + "step": 367620 + }, + { + "epoch": 0.82, + "learning_rate": 9.008635153575982e-06, + "loss": 0.0963, + "step": 367630 + }, + { + "epoch": 0.82, + "learning_rate": 9.00751661036666e-06, + "loss": 0.0962, + "step": 367640 + }, + { + "epoch": 0.82, + "learning_rate": 9.006398067157334e-06, + "loss": 0.095, + "step": 367650 + }, + { + "epoch": 0.82, + "learning_rate": 9.00527952394801e-06, + "loss": 0.1005, + "step": 367660 + }, + { + "epoch": 0.82, + "learning_rate": 9.004160980738687e-06, + "loss": 0.0968, + "step": 367670 + }, + { + "epoch": 0.82, + "learning_rate": 9.003042437529361e-06, + "loss": 0.0959, + "step": 367680 + }, + { + "epoch": 0.82, + "learning_rate": 9.001923894320038e-06, + "loss": 0.0999, + "step": 367690 + }, + { + "epoch": 0.82, + "learning_rate": 9.000805351110714e-06, + "loss": 0.0984, + "step": 367700 + }, + { + "epoch": 0.82, + "learning_rate": 8.999686807901388e-06, + "loss": 0.1005, + "step": 367710 + }, + { + "epoch": 0.82, + "learning_rate": 8.998568264692066e-06, + "loss": 0.0973, + "step": 367720 + }, + { + "epoch": 0.82, + "learning_rate": 8.997449721482741e-06, + "loss": 0.0971, + "step": 367730 + }, + { + "epoch": 0.82, + "learning_rate": 8.996331178273417e-06, + "loss": 0.0977, + "step": 367740 + }, + { + "epoch": 0.82, + "learning_rate": 8.995212635064093e-06, + "loss": 0.0972, + "step": 367750 + }, + { + "epoch": 0.82, + "learning_rate": 8.994094091854768e-06, + "loss": 0.1005, + "step": 367760 + }, + { + "epoch": 0.82, + "learning_rate": 8.992975548645446e-06, + "loss": 0.098, + "step": 367770 + }, + { + "epoch": 0.82, + "learning_rate": 8.99185700543612e-06, + "loss": 0.0989, + "step": 367780 + }, + { + "epoch": 0.82, + "learning_rate": 8.990738462226795e-06, + "loss": 0.0983, + "step": 367790 + }, + { + "epoch": 0.82, + "learning_rate": 8.989619919017473e-06, + "loss": 0.102, + "step": 367800 + }, + { + "epoch": 0.82, + "learning_rate": 8.988501375808147e-06, + "loss": 0.1, + "step": 367810 + }, + { + "epoch": 0.82, + "learning_rate": 8.987382832598824e-06, + "loss": 0.0979, + "step": 367820 + }, + { + "epoch": 0.82, + "learning_rate": 8.9862642893895e-06, + "loss": 0.0984, + "step": 367830 + }, + { + "epoch": 0.82, + "learning_rate": 8.985145746180174e-06, + "loss": 0.1036, + "step": 367840 + }, + { + "epoch": 0.82, + "learning_rate": 8.984027202970852e-06, + "loss": 0.0987, + "step": 367850 + }, + { + "epoch": 0.82, + "learning_rate": 8.982908659761527e-06, + "loss": 0.0946, + "step": 367860 + }, + { + "epoch": 0.82, + "learning_rate": 8.981790116552203e-06, + "loss": 0.0998, + "step": 367870 + }, + { + "epoch": 0.82, + "learning_rate": 8.98067157334288e-06, + "loss": 0.1025, + "step": 367880 + }, + { + "epoch": 0.82, + "learning_rate": 8.979553030133554e-06, + "loss": 0.0949, + "step": 367890 + }, + { + "epoch": 0.82, + "learning_rate": 8.978434486924232e-06, + "loss": 0.1022, + "step": 367900 + }, + { + "epoch": 0.82, + "learning_rate": 8.977315943714906e-06, + "loss": 0.0998, + "step": 367910 + }, + { + "epoch": 0.82, + "learning_rate": 8.976197400505581e-06, + "loss": 0.1015, + "step": 367920 + }, + { + "epoch": 0.82, + "learning_rate": 8.975078857296259e-06, + "loss": 0.0972, + "step": 367930 + }, + { + "epoch": 0.82, + "learning_rate": 8.973960314086933e-06, + "loss": 0.0972, + "step": 367940 + }, + { + "epoch": 0.82, + "learning_rate": 8.97284177087761e-06, + "loss": 0.0994, + "step": 367950 + }, + { + "epoch": 0.82, + "learning_rate": 8.971723227668286e-06, + "loss": 0.101, + "step": 367960 + }, + { + "epoch": 0.82, + "learning_rate": 8.97060468445896e-06, + "loss": 0.0986, + "step": 367970 + }, + { + "epoch": 0.82, + "learning_rate": 8.969486141249638e-06, + "loss": 0.0977, + "step": 367980 + }, + { + "epoch": 0.82, + "learning_rate": 8.968367598040313e-06, + "loss": 0.097, + "step": 367990 + }, + { + "epoch": 0.82, + "learning_rate": 8.967249054830987e-06, + "loss": 0.1001, + "step": 368000 + }, + { + "epoch": 0.82, + "eval_NEIMS_canon_smiles": 0.9604166666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.2511333333333333, + "eval_NEIMS_daylight_tanimoto_simil": 0.6216905711984301, + "eval_NEIMS_exact_mols": 0.2508166666666667, + "eval_NEIMS_exact_smiles": 0.24565, + "eval_NEIMS_loss": 0.12716229259967804, + "eval_NEIMS_matched_formulas": 0.7599666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.5481367598972201, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.2515833333333333, + "eval_NEIMS_runtime": 723.9674, + "eval_NEIMS_samples_per_second": 82.877, + "eval_NEIMS_steps_per_second": 1.296, + "step": 368000 + }, + { + "epoch": 0.82, + "eval_RASSP_canon_smiles": 0.9590276154539686, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.3293986042007547, + "eval_RASSP_daylight_tanimoto_simil": 0.7214638698502331, + "eval_RASSP_exact_mols": 0.32868066918222194, + "eval_RASSP_exact_smiles": 0.32126757271179085, + "eval_RASSP_loss": 0.09796497225761414, + "eval_RASSP_matched_formulas": 0.8874177713961332, + "eval_RASSP_morgan_tanimoto_simil": 0.6153958957101399, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.32883093465121715, + "eval_RASSP_runtime": 827.7225, + "eval_RASSP_samples_per_second": 72.36, + "eval_RASSP_steps_per_second": 1.131, + "step": 368000 + }, + { + "epoch": 0.82, + "eval_NEIMS_old_canon_smiles": 0.9569, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.24716666666666667, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6181070945950397, + "eval_NEIMS_old_exact_mols": 0.24676666666666666, + "eval_NEIMS_old_exact_smiles": 0.24113333333333334, + "eval_NEIMS_old_loss": 0.12702243030071259, + "eval_NEIMS_old_matched_formulas": 0.7590333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5451388567322556, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2478, + "eval_NEIMS_old_runtime": 364.6671, + "eval_NEIMS_old_samples_per_second": 82.267, + "eval_NEIMS_old_steps_per_second": 1.286, + "step": 368000 + }, + { + "epoch": 0.82, + "eval_RASSP_old_canon_smiles": 0.9600226916274569, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.3614642773717756, + "eval_RASSP_old_daylight_tanimoto_simil": 0.739538803028277, + "eval_RASSP_old_exact_mols": 0.36066339640270967, + "eval_RASSP_old_exact_smiles": 0.35242099642940566, + "eval_RASSP_old_loss": 0.09185847640037537, + "eval_RASSP_old_matched_formulas": 0.8995895485033537, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6392512733680792, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.3609637267661094, + "eval_RASSP_old_runtime": 410.1978, + "eval_RASSP_old_samples_per_second": 73.055, + "eval_RASSP_old_steps_per_second": 1.143, + "step": 368000 + }, + { + "epoch": 0.82, + "eval_NIST_canon_smiles": 0.8670192000567839, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.028108031373105725, + "eval_NIST_daylight_tanimoto_simil": 0.30182903118124116, + "eval_NIST_exact_mols": 0.027185292969443164, + "eval_NIST_exact_smiles": 0.026014124995563756, + "eval_NIST_loss": 1.8104623556137085, + "eval_NIST_matched_formulas": 0.12797671860027682, + "eval_NIST_morgan_tanimoto_simil": 0.25419116396637087, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.02768215210987685, + "eval_NIST_runtime": 506.5442, + "eval_NIST_samples_per_second": 55.626, + "eval_NIST_steps_per_second": 0.871, + "step": 368000 + }, + { + "epoch": 0.82, + "learning_rate": 8.966130511621665e-06, + "loss": 0.0973, + "step": 368010 + }, + { + "epoch": 0.82, + "learning_rate": 8.96501196841234e-06, + "loss": 0.0988, + "step": 368020 + }, + { + "epoch": 0.82, + "learning_rate": 8.963893425203016e-06, + "loss": 0.0962, + "step": 368030 + }, + { + "epoch": 0.82, + "learning_rate": 8.962774881993692e-06, + "loss": 0.0976, + "step": 368040 + }, + { + "epoch": 0.82, + "learning_rate": 8.961656338784367e-06, + "loss": 0.0969, + "step": 368050 + }, + { + "epoch": 0.82, + "learning_rate": 8.960537795575045e-06, + "loss": 0.0997, + "step": 368060 + }, + { + "epoch": 0.82, + "learning_rate": 8.95941925236572e-06, + "loss": 0.0999, + "step": 368070 + }, + { + "epoch": 0.82, + "learning_rate": 8.958300709156396e-06, + "loss": 0.095, + "step": 368080 + }, + { + "epoch": 0.82, + "learning_rate": 8.957182165947072e-06, + "loss": 0.0981, + "step": 368090 + }, + { + "epoch": 0.82, + "learning_rate": 8.956063622737746e-06, + "loss": 0.1013, + "step": 368100 + }, + { + "epoch": 0.82, + "learning_rate": 8.954945079528423e-06, + "loss": 0.1014, + "step": 368110 + }, + { + "epoch": 0.82, + "learning_rate": 8.953826536319099e-06, + "loss": 0.0983, + "step": 368120 + }, + { + "epoch": 0.82, + "learning_rate": 8.952707993109773e-06, + "loss": 0.1006, + "step": 368130 + }, + { + "epoch": 0.82, + "learning_rate": 8.951589449900451e-06, + "loss": 0.0995, + "step": 368140 + }, + { + "epoch": 0.82, + "learning_rate": 8.950470906691126e-06, + "loss": 0.0973, + "step": 368150 + }, + { + "epoch": 0.82, + "learning_rate": 8.949352363481802e-06, + "loss": 0.0956, + "step": 368160 + }, + { + "epoch": 0.82, + "learning_rate": 8.948233820272478e-06, + "loss": 0.0962, + "step": 368170 + }, + { + "epoch": 0.82, + "learning_rate": 8.947115277063153e-06, + "loss": 0.1015, + "step": 368180 + }, + { + "epoch": 0.82, + "learning_rate": 8.945996733853829e-06, + "loss": 0.0988, + "step": 368190 + }, + { + "epoch": 0.82, + "learning_rate": 8.944878190644505e-06, + "loss": 0.0982, + "step": 368200 + }, + { + "epoch": 0.82, + "learning_rate": 8.943759647435181e-06, + "loss": 0.0954, + "step": 368210 + }, + { + "epoch": 0.82, + "learning_rate": 8.942641104225858e-06, + "loss": 0.0965, + "step": 368220 + }, + { + "epoch": 0.82, + "learning_rate": 8.941522561016532e-06, + "loss": 0.0965, + "step": 368230 + }, + { + "epoch": 0.82, + "learning_rate": 8.940404017807208e-06, + "loss": 0.0978, + "step": 368240 + }, + { + "epoch": 0.82, + "learning_rate": 8.939285474597885e-06, + "loss": 0.1024, + "step": 368250 + }, + { + "epoch": 0.82, + "learning_rate": 8.93816693138856e-06, + "loss": 0.0926, + "step": 368260 + }, + { + "epoch": 0.82, + "learning_rate": 8.937048388179235e-06, + "loss": 0.1042, + "step": 368270 + }, + { + "epoch": 0.82, + "learning_rate": 8.935929844969912e-06, + "loss": 0.0938, + "step": 368280 + }, + { + "epoch": 0.82, + "learning_rate": 8.934811301760588e-06, + "loss": 0.0952, + "step": 368290 + }, + { + "epoch": 0.82, + "learning_rate": 8.933692758551264e-06, + "loss": 0.0959, + "step": 368300 + }, + { + "epoch": 0.82, + "learning_rate": 8.932574215341939e-06, + "loss": 0.0955, + "step": 368310 + }, + { + "epoch": 0.82, + "learning_rate": 8.931455672132615e-06, + "loss": 0.0984, + "step": 368320 + }, + { + "epoch": 0.82, + "learning_rate": 8.930337128923291e-06, + "loss": 0.0974, + "step": 368330 + }, + { + "epoch": 0.82, + "learning_rate": 8.929218585713966e-06, + "loss": 0.0958, + "step": 368340 + }, + { + "epoch": 0.82, + "learning_rate": 8.928100042504642e-06, + "loss": 0.0975, + "step": 368350 + }, + { + "epoch": 0.82, + "learning_rate": 8.926981499295318e-06, + "loss": 0.0977, + "step": 368360 + }, + { + "epoch": 0.82, + "learning_rate": 8.925862956085994e-06, + "loss": 0.0993, + "step": 368370 + }, + { + "epoch": 0.82, + "learning_rate": 8.92474441287667e-06, + "loss": 0.0966, + "step": 368380 + }, + { + "epoch": 0.82, + "learning_rate": 8.923625869667345e-06, + "loss": 0.0933, + "step": 368390 + }, + { + "epoch": 0.82, + "learning_rate": 8.922507326458021e-06, + "loss": 0.0956, + "step": 368400 + }, + { + "epoch": 0.82, + "learning_rate": 8.921388783248698e-06, + "loss": 0.096, + "step": 368410 + }, + { + "epoch": 0.82, + "learning_rate": 8.920270240039374e-06, + "loss": 0.1023, + "step": 368420 + }, + { + "epoch": 0.82, + "learning_rate": 8.919151696830048e-06, + "loss": 0.0947, + "step": 368430 + }, + { + "epoch": 0.82, + "learning_rate": 8.918033153620725e-06, + "loss": 0.0942, + "step": 368440 + }, + { + "epoch": 0.82, + "learning_rate": 8.916914610411401e-06, + "loss": 0.1006, + "step": 368450 + }, + { + "epoch": 0.82, + "learning_rate": 8.915796067202077e-06, + "loss": 0.0959, + "step": 368460 + }, + { + "epoch": 0.82, + "learning_rate": 8.914677523992752e-06, + "loss": 0.0974, + "step": 368470 + }, + { + "epoch": 0.82, + "learning_rate": 8.913558980783428e-06, + "loss": 0.1005, + "step": 368480 + }, + { + "epoch": 0.82, + "learning_rate": 8.912440437574104e-06, + "loss": 0.1039, + "step": 368490 + }, + { + "epoch": 0.82, + "learning_rate": 8.91132189436478e-06, + "loss": 0.1052, + "step": 368500 + }, + { + "epoch": 0.82, + "learning_rate": 8.910203351155455e-06, + "loss": 0.097, + "step": 368510 + }, + { + "epoch": 0.82, + "learning_rate": 8.909084807946131e-06, + "loss": 0.1004, + "step": 368520 + }, + { + "epoch": 0.82, + "learning_rate": 8.907966264736807e-06, + "loss": 0.1003, + "step": 368530 + }, + { + "epoch": 0.82, + "learning_rate": 8.906847721527484e-06, + "loss": 0.095, + "step": 368540 + }, + { + "epoch": 0.82, + "learning_rate": 8.905729178318158e-06, + "loss": 0.1005, + "step": 368550 + }, + { + "epoch": 0.82, + "learning_rate": 8.904610635108834e-06, + "loss": 0.099, + "step": 368560 + }, + { + "epoch": 0.82, + "learning_rate": 8.90349209189951e-06, + "loss": 0.0942, + "step": 368570 + }, + { + "epoch": 0.82, + "learning_rate": 8.902373548690187e-06, + "loss": 0.0975, + "step": 368580 + }, + { + "epoch": 0.82, + "learning_rate": 8.901255005480861e-06, + "loss": 0.0935, + "step": 368590 + }, + { + "epoch": 0.82, + "learning_rate": 8.900136462271538e-06, + "loss": 0.0996, + "step": 368600 + }, + { + "epoch": 0.82, + "learning_rate": 8.899017919062214e-06, + "loss": 0.0974, + "step": 368610 + }, + { + "epoch": 0.82, + "learning_rate": 8.89789937585289e-06, + "loss": 0.0985, + "step": 368620 + }, + { + "epoch": 0.82, + "learning_rate": 8.896780832643566e-06, + "loss": 0.098, + "step": 368630 + }, + { + "epoch": 0.82, + "learning_rate": 8.895662289434241e-06, + "loss": 0.0941, + "step": 368640 + }, + { + "epoch": 0.82, + "learning_rate": 8.894543746224917e-06, + "loss": 0.1007, + "step": 368650 + }, + { + "epoch": 0.82, + "learning_rate": 8.893425203015593e-06, + "loss": 0.0983, + "step": 368660 + }, + { + "epoch": 0.82, + "learning_rate": 8.892306659806268e-06, + "loss": 0.0985, + "step": 368670 + }, + { + "epoch": 0.82, + "learning_rate": 8.891188116596944e-06, + "loss": 0.0971, + "step": 368680 + }, + { + "epoch": 0.82, + "learning_rate": 8.89006957338762e-06, + "loss": 0.1025, + "step": 368690 + }, + { + "epoch": 0.82, + "learning_rate": 8.888951030178297e-06, + "loss": 0.0917, + "step": 368700 + }, + { + "epoch": 0.82, + "learning_rate": 8.887832486968973e-06, + "loss": 0.099, + "step": 368710 + }, + { + "epoch": 0.82, + "learning_rate": 8.886713943759647e-06, + "loss": 0.1012, + "step": 368720 + }, + { + "epoch": 0.82, + "learning_rate": 8.885595400550324e-06, + "loss": 0.0992, + "step": 368730 + }, + { + "epoch": 0.82, + "learning_rate": 8.884476857341e-06, + "loss": 0.0988, + "step": 368740 + }, + { + "epoch": 0.82, + "learning_rate": 8.883358314131674e-06, + "loss": 0.1021, + "step": 368750 + }, + { + "epoch": 0.82, + "learning_rate": 8.882239770922352e-06, + "loss": 0.1031, + "step": 368760 + }, + { + "epoch": 0.82, + "learning_rate": 8.881121227713027e-06, + "loss": 0.1013, + "step": 368770 + }, + { + "epoch": 0.82, + "learning_rate": 8.880002684503703e-06, + "loss": 0.0993, + "step": 368780 + }, + { + "epoch": 0.82, + "learning_rate": 8.87888414129438e-06, + "loss": 0.0941, + "step": 368790 + }, + { + "epoch": 0.82, + "learning_rate": 8.877765598085054e-06, + "loss": 0.0979, + "step": 368800 + }, + { + "epoch": 0.82, + "learning_rate": 8.87664705487573e-06, + "loss": 0.1034, + "step": 368810 + }, + { + "epoch": 0.82, + "learning_rate": 8.875528511666406e-06, + "loss": 0.0955, + "step": 368820 + }, + { + "epoch": 0.82, + "learning_rate": 8.87440996845708e-06, + "loss": 0.1007, + "step": 368830 + }, + { + "epoch": 0.82, + "learning_rate": 8.873291425247759e-06, + "loss": 0.0988, + "step": 368840 + }, + { + "epoch": 0.82, + "learning_rate": 8.872172882038433e-06, + "loss": 0.0999, + "step": 368850 + }, + { + "epoch": 0.82, + "learning_rate": 8.87105433882911e-06, + "loss": 0.0973, + "step": 368860 + }, + { + "epoch": 0.82, + "learning_rate": 8.869935795619786e-06, + "loss": 0.103, + "step": 368870 + }, + { + "epoch": 0.82, + "learning_rate": 8.86881725241046e-06, + "loss": 0.0993, + "step": 368880 + }, + { + "epoch": 0.82, + "learning_rate": 8.867698709201137e-06, + "loss": 0.0946, + "step": 368890 + }, + { + "epoch": 0.82, + "learning_rate": 8.866580165991813e-06, + "loss": 0.0983, + "step": 368900 + }, + { + "epoch": 0.82, + "learning_rate": 8.865461622782487e-06, + "loss": 0.1002, + "step": 368910 + }, + { + "epoch": 0.82, + "learning_rate": 8.864343079573165e-06, + "loss": 0.0956, + "step": 368920 + }, + { + "epoch": 0.82, + "learning_rate": 8.86322453636384e-06, + "loss": 0.0957, + "step": 368930 + }, + { + "epoch": 0.82, + "learning_rate": 8.862105993154516e-06, + "loss": 0.1021, + "step": 368940 + }, + { + "epoch": 0.82, + "learning_rate": 8.860987449945192e-06, + "loss": 0.1006, + "step": 368950 + }, + { + "epoch": 0.82, + "learning_rate": 8.859868906735867e-06, + "loss": 0.1024, + "step": 368960 + }, + { + "epoch": 0.82, + "learning_rate": 8.858750363526545e-06, + "loss": 0.0977, + "step": 368970 + }, + { + "epoch": 0.82, + "learning_rate": 8.85763182031722e-06, + "loss": 0.0986, + "step": 368980 + }, + { + "epoch": 0.82, + "learning_rate": 8.856513277107894e-06, + "loss": 0.0978, + "step": 368990 + }, + { + "epoch": 0.82, + "learning_rate": 8.855394733898572e-06, + "loss": 0.0949, + "step": 369000 + }, + { + "epoch": 0.82, + "learning_rate": 8.854276190689246e-06, + "loss": 0.0993, + "step": 369010 + }, + { + "epoch": 0.82, + "learning_rate": 8.853157647479923e-06, + "loss": 0.0986, + "step": 369020 + }, + { + "epoch": 0.82, + "learning_rate": 8.852039104270599e-06, + "loss": 0.0954, + "step": 369030 + }, + { + "epoch": 0.82, + "learning_rate": 8.850920561061273e-06, + "loss": 0.0979, + "step": 369040 + }, + { + "epoch": 0.82, + "learning_rate": 8.849802017851951e-06, + "loss": 0.0993, + "step": 369050 + }, + { + "epoch": 0.82, + "learning_rate": 8.848683474642626e-06, + "loss": 0.1023, + "step": 369060 + }, + { + "epoch": 0.82, + "learning_rate": 8.847564931433302e-06, + "loss": 0.0969, + "step": 369070 + }, + { + "epoch": 0.82, + "learning_rate": 8.846446388223978e-06, + "loss": 0.1009, + "step": 369080 + }, + { + "epoch": 0.82, + "learning_rate": 8.845327845014653e-06, + "loss": 0.0988, + "step": 369090 + }, + { + "epoch": 0.82, + "learning_rate": 8.844209301805329e-06, + "loss": 0.1009, + "step": 369100 + }, + { + "epoch": 0.82, + "learning_rate": 8.843090758596005e-06, + "loss": 0.0972, + "step": 369110 + }, + { + "epoch": 0.82, + "learning_rate": 8.84197221538668e-06, + "loss": 0.0969, + "step": 369120 + }, + { + "epoch": 0.82, + "learning_rate": 8.840853672177358e-06, + "loss": 0.0985, + "step": 369130 + }, + { + "epoch": 0.82, + "learning_rate": 8.839735128968032e-06, + "loss": 0.0964, + "step": 369140 + }, + { + "epoch": 0.82, + "learning_rate": 8.838616585758708e-06, + "loss": 0.1001, + "step": 369150 + }, + { + "epoch": 0.82, + "learning_rate": 8.837498042549385e-06, + "loss": 0.0997, + "step": 369160 + }, + { + "epoch": 0.82, + "learning_rate": 8.83637949934006e-06, + "loss": 0.098, + "step": 369170 + }, + { + "epoch": 0.82, + "learning_rate": 8.835260956130735e-06, + "loss": 0.0975, + "step": 369180 + }, + { + "epoch": 0.82, + "learning_rate": 8.834142412921412e-06, + "loss": 0.0975, + "step": 369190 + }, + { + "epoch": 0.82, + "learning_rate": 8.833023869712086e-06, + "loss": 0.1003, + "step": 369200 + }, + { + "epoch": 0.82, + "learning_rate": 8.831905326502764e-06, + "loss": 0.0992, + "step": 369210 + }, + { + "epoch": 0.82, + "learning_rate": 8.830786783293439e-06, + "loss": 0.0973, + "step": 369220 + }, + { + "epoch": 0.82, + "learning_rate": 8.829668240084115e-06, + "loss": 0.1057, + "step": 369230 + }, + { + "epoch": 0.82, + "learning_rate": 8.828549696874791e-06, + "loss": 0.0976, + "step": 369240 + }, + { + "epoch": 0.82, + "learning_rate": 8.827431153665466e-06, + "loss": 0.101, + "step": 369250 + }, + { + "epoch": 0.82, + "learning_rate": 8.826312610456142e-06, + "loss": 0.1001, + "step": 369260 + }, + { + "epoch": 0.82, + "learning_rate": 8.825194067246818e-06, + "loss": 0.0965, + "step": 369270 + }, + { + "epoch": 0.82, + "learning_rate": 8.824075524037494e-06, + "loss": 0.0993, + "step": 369280 + }, + { + "epoch": 0.82, + "learning_rate": 8.82295698082817e-06, + "loss": 0.1011, + "step": 369290 + }, + { + "epoch": 0.82, + "learning_rate": 8.821838437618845e-06, + "loss": 0.0972, + "step": 369300 + }, + { + "epoch": 0.82, + "learning_rate": 8.820719894409521e-06, + "loss": 0.0997, + "step": 369310 + }, + { + "epoch": 0.82, + "learning_rate": 8.819601351200198e-06, + "loss": 0.0996, + "step": 369320 + }, + { + "epoch": 0.82, + "learning_rate": 8.818482807990872e-06, + "loss": 0.1017, + "step": 369330 + }, + { + "epoch": 0.82, + "learning_rate": 8.817364264781548e-06, + "loss": 0.1035, + "step": 369340 + }, + { + "epoch": 0.82, + "learning_rate": 8.816245721572225e-06, + "loss": 0.0949, + "step": 369350 + }, + { + "epoch": 0.82, + "learning_rate": 8.815127178362901e-06, + "loss": 0.0979, + "step": 369360 + }, + { + "epoch": 0.82, + "learning_rate": 8.814008635153577e-06, + "loss": 0.0971, + "step": 369370 + }, + { + "epoch": 0.82, + "learning_rate": 8.812890091944252e-06, + "loss": 0.0983, + "step": 369380 + }, + { + "epoch": 0.82, + "learning_rate": 8.811771548734928e-06, + "loss": 0.1001, + "step": 369390 + }, + { + "epoch": 0.82, + "learning_rate": 8.810653005525604e-06, + "loss": 0.1037, + "step": 369400 + }, + { + "epoch": 0.82, + "learning_rate": 8.80953446231628e-06, + "loss": 0.0956, + "step": 369410 + }, + { + "epoch": 0.82, + "learning_rate": 8.808415919106955e-06, + "loss": 0.0999, + "step": 369420 + }, + { + "epoch": 0.82, + "learning_rate": 8.807297375897631e-06, + "loss": 0.0987, + "step": 369430 + }, + { + "epoch": 0.82, + "learning_rate": 8.806178832688307e-06, + "loss": 0.1001, + "step": 369440 + }, + { + "epoch": 0.82, + "learning_rate": 8.805060289478984e-06, + "loss": 0.0955, + "step": 369450 + }, + { + "epoch": 0.82, + "learning_rate": 8.803941746269658e-06, + "loss": 0.096, + "step": 369460 + }, + { + "epoch": 0.82, + "learning_rate": 8.802823203060334e-06, + "loss": 0.0972, + "step": 369470 + }, + { + "epoch": 0.82, + "learning_rate": 8.80170465985101e-06, + "loss": 0.093, + "step": 369480 + }, + { + "epoch": 0.82, + "learning_rate": 8.800586116641687e-06, + "loss": 0.099, + "step": 369490 + }, + { + "epoch": 0.82, + "learning_rate": 8.799467573432361e-06, + "loss": 0.0969, + "step": 369500 + }, + { + "epoch": 0.82, + "learning_rate": 8.798349030223038e-06, + "loss": 0.0987, + "step": 369510 + }, + { + "epoch": 0.82, + "learning_rate": 8.797230487013714e-06, + "loss": 0.0971, + "step": 369520 + }, + { + "epoch": 0.82, + "learning_rate": 8.79611194380439e-06, + "loss": 0.0948, + "step": 369530 + }, + { + "epoch": 0.82, + "learning_rate": 8.794993400595065e-06, + "loss": 0.0979, + "step": 369540 + }, + { + "epoch": 0.82, + "learning_rate": 8.793874857385741e-06, + "loss": 0.0963, + "step": 369550 + }, + { + "epoch": 0.82, + "learning_rate": 8.792756314176417e-06, + "loss": 0.1005, + "step": 369560 + }, + { + "epoch": 0.82, + "learning_rate": 8.791637770967093e-06, + "loss": 0.0977, + "step": 369570 + }, + { + "epoch": 0.82, + "learning_rate": 8.790519227757768e-06, + "loss": 0.1002, + "step": 369580 + }, + { + "epoch": 0.82, + "learning_rate": 8.789400684548444e-06, + "loss": 0.095, + "step": 369590 + }, + { + "epoch": 0.82, + "learning_rate": 8.78828214133912e-06, + "loss": 0.1046, + "step": 369600 + }, + { + "epoch": 0.83, + "learning_rate": 8.787163598129797e-06, + "loss": 0.0988, + "step": 369610 + }, + { + "epoch": 0.83, + "learning_rate": 8.786045054920473e-06, + "loss": 0.0973, + "step": 369620 + }, + { + "epoch": 0.83, + "learning_rate": 8.784926511711147e-06, + "loss": 0.0974, + "step": 369630 + }, + { + "epoch": 0.83, + "learning_rate": 8.783807968501824e-06, + "loss": 0.0968, + "step": 369640 + }, + { + "epoch": 0.83, + "learning_rate": 8.7826894252925e-06, + "loss": 0.095, + "step": 369650 + }, + { + "epoch": 0.83, + "learning_rate": 8.781570882083174e-06, + "loss": 0.0972, + "step": 369660 + }, + { + "epoch": 0.83, + "learning_rate": 8.78045233887385e-06, + "loss": 0.0979, + "step": 369670 + }, + { + "epoch": 0.83, + "learning_rate": 8.779333795664527e-06, + "loss": 0.0968, + "step": 369680 + }, + { + "epoch": 0.83, + "learning_rate": 8.778215252455203e-06, + "loss": 0.1011, + "step": 369690 + }, + { + "epoch": 0.83, + "learning_rate": 8.77709670924588e-06, + "loss": 0.0993, + "step": 369700 + }, + { + "epoch": 0.83, + "learning_rate": 8.775978166036554e-06, + "loss": 0.1012, + "step": 369710 + }, + { + "epoch": 0.83, + "learning_rate": 8.77485962282723e-06, + "loss": 0.1004, + "step": 369720 + }, + { + "epoch": 0.83, + "learning_rate": 8.773741079617906e-06, + "loss": 0.0969, + "step": 369730 + }, + { + "epoch": 0.83, + "learning_rate": 8.77262253640858e-06, + "loss": 0.0998, + "step": 369740 + }, + { + "epoch": 0.83, + "learning_rate": 8.771503993199259e-06, + "loss": 0.0942, + "step": 369750 + }, + { + "epoch": 0.83, + "learning_rate": 8.770385449989933e-06, + "loss": 0.0966, + "step": 369760 + }, + { + "epoch": 0.83, + "learning_rate": 8.76926690678061e-06, + "loss": 0.0961, + "step": 369770 + }, + { + "epoch": 0.83, + "learning_rate": 8.768148363571286e-06, + "loss": 0.0955, + "step": 369780 + }, + { + "epoch": 0.83, + "learning_rate": 8.76702982036196e-06, + "loss": 0.098, + "step": 369790 + }, + { + "epoch": 0.83, + "learning_rate": 8.765911277152637e-06, + "loss": 0.1044, + "step": 369800 + }, + { + "epoch": 0.83, + "learning_rate": 8.764792733943313e-06, + "loss": 0.1058, + "step": 369810 + }, + { + "epoch": 0.83, + "learning_rate": 8.763674190733987e-06, + "loss": 0.0983, + "step": 369820 + }, + { + "epoch": 0.83, + "learning_rate": 8.762555647524665e-06, + "loss": 0.1018, + "step": 369830 + }, + { + "epoch": 0.83, + "learning_rate": 8.76143710431534e-06, + "loss": 0.0994, + "step": 369840 + }, + { + "epoch": 0.83, + "learning_rate": 8.760318561106016e-06, + "loss": 0.097, + "step": 369850 + }, + { + "epoch": 0.83, + "learning_rate": 8.759200017896692e-06, + "loss": 0.1, + "step": 369860 + }, + { + "epoch": 0.83, + "learning_rate": 8.758081474687367e-06, + "loss": 0.0979, + "step": 369870 + }, + { + "epoch": 0.83, + "learning_rate": 8.756962931478043e-06, + "loss": 0.0989, + "step": 369880 + }, + { + "epoch": 0.83, + "learning_rate": 8.75584438826872e-06, + "loss": 0.0993, + "step": 369890 + }, + { + "epoch": 0.83, + "learning_rate": 8.754725845059394e-06, + "loss": 0.099, + "step": 369900 + }, + { + "epoch": 0.83, + "learning_rate": 8.753607301850072e-06, + "loss": 0.0972, + "step": 369910 + }, + { + "epoch": 0.83, + "learning_rate": 8.752488758640746e-06, + "loss": 0.0969, + "step": 369920 + }, + { + "epoch": 0.83, + "learning_rate": 8.751370215431422e-06, + "loss": 0.0998, + "step": 369930 + }, + { + "epoch": 0.83, + "learning_rate": 8.750251672222099e-06, + "loss": 0.0969, + "step": 369940 + }, + { + "epoch": 0.83, + "learning_rate": 8.749133129012773e-06, + "loss": 0.1012, + "step": 369950 + }, + { + "epoch": 0.83, + "learning_rate": 8.748014585803451e-06, + "loss": 0.0983, + "step": 369960 + }, + { + "epoch": 0.83, + "learning_rate": 8.746896042594126e-06, + "loss": 0.1013, + "step": 369970 + }, + { + "epoch": 0.83, + "learning_rate": 8.7457774993848e-06, + "loss": 0.1007, + "step": 369980 + }, + { + "epoch": 0.83, + "learning_rate": 8.744658956175478e-06, + "loss": 0.0954, + "step": 369990 + }, + { + "epoch": 0.83, + "learning_rate": 8.743540412966153e-06, + "loss": 0.0944, + "step": 370000 + }, + { + "epoch": 0.83, + "learning_rate": 8.742421869756829e-06, + "loss": 0.0977, + "step": 370010 + }, + { + "epoch": 0.83, + "learning_rate": 8.741303326547505e-06, + "loss": 0.0978, + "step": 370020 + }, + { + "epoch": 0.83, + "learning_rate": 8.74018478333818e-06, + "loss": 0.0977, + "step": 370030 + }, + { + "epoch": 0.83, + "learning_rate": 8.739066240128858e-06, + "loss": 0.0993, + "step": 370040 + }, + { + "epoch": 0.83, + "learning_rate": 8.737947696919532e-06, + "loss": 0.1019, + "step": 370050 + }, + { + "epoch": 0.83, + "learning_rate": 8.736829153710207e-06, + "loss": 0.0995, + "step": 370060 + }, + { + "epoch": 0.83, + "learning_rate": 8.735710610500885e-06, + "loss": 0.0939, + "step": 370070 + }, + { + "epoch": 0.83, + "learning_rate": 8.73459206729156e-06, + "loss": 0.0991, + "step": 370080 + }, + { + "epoch": 0.83, + "learning_rate": 8.733473524082235e-06, + "loss": 0.0991, + "step": 370090 + }, + { + "epoch": 0.83, + "learning_rate": 8.732354980872912e-06, + "loss": 0.101, + "step": 370100 + }, + { + "epoch": 0.83, + "learning_rate": 8.731236437663586e-06, + "loss": 0.1013, + "step": 370110 + }, + { + "epoch": 0.83, + "learning_rate": 8.730117894454264e-06, + "loss": 0.0976, + "step": 370120 + }, + { + "epoch": 0.83, + "learning_rate": 8.728999351244939e-06, + "loss": 0.0986, + "step": 370130 + }, + { + "epoch": 0.83, + "learning_rate": 8.727880808035615e-06, + "loss": 0.0952, + "step": 370140 + }, + { + "epoch": 0.83, + "learning_rate": 8.726762264826291e-06, + "loss": 0.0939, + "step": 370150 + }, + { + "epoch": 0.83, + "learning_rate": 8.725643721616966e-06, + "loss": 0.0945, + "step": 370160 + }, + { + "epoch": 0.83, + "learning_rate": 8.724525178407644e-06, + "loss": 0.097, + "step": 370170 + }, + { + "epoch": 0.83, + "learning_rate": 8.723406635198318e-06, + "loss": 0.0978, + "step": 370180 + }, + { + "epoch": 0.83, + "learning_rate": 8.722288091988993e-06, + "loss": 0.0994, + "step": 370190 + }, + { + "epoch": 0.83, + "learning_rate": 8.72116954877967e-06, + "loss": 0.0981, + "step": 370200 + }, + { + "epoch": 0.83, + "learning_rate": 8.720051005570345e-06, + "loss": 0.1006, + "step": 370210 + }, + { + "epoch": 0.83, + "learning_rate": 8.718932462361021e-06, + "loss": 0.0984, + "step": 370220 + }, + { + "epoch": 0.83, + "learning_rate": 8.717813919151698e-06, + "loss": 0.0995, + "step": 370230 + }, + { + "epoch": 0.83, + "learning_rate": 8.716695375942372e-06, + "loss": 0.0939, + "step": 370240 + }, + { + "epoch": 0.83, + "learning_rate": 8.71557683273305e-06, + "loss": 0.1014, + "step": 370250 + }, + { + "epoch": 0.83, + "learning_rate": 8.714458289523725e-06, + "loss": 0.097, + "step": 370260 + }, + { + "epoch": 0.83, + "learning_rate": 8.713339746314401e-06, + "loss": 0.0988, + "step": 370270 + }, + { + "epoch": 0.83, + "learning_rate": 8.712221203105077e-06, + "loss": 0.0968, + "step": 370280 + }, + { + "epoch": 0.83, + "learning_rate": 8.711102659895752e-06, + "loss": 0.0989, + "step": 370290 + }, + { + "epoch": 0.83, + "learning_rate": 8.709984116686428e-06, + "loss": 0.0964, + "step": 370300 + }, + { + "epoch": 0.83, + "learning_rate": 8.708865573477104e-06, + "loss": 0.094, + "step": 370310 + }, + { + "epoch": 0.83, + "learning_rate": 8.707747030267779e-06, + "loss": 0.0974, + "step": 370320 + }, + { + "epoch": 0.83, + "learning_rate": 8.706628487058457e-06, + "loss": 0.0978, + "step": 370330 + }, + { + "epoch": 0.83, + "learning_rate": 8.705509943849131e-06, + "loss": 0.1026, + "step": 370340 + }, + { + "epoch": 0.83, + "learning_rate": 8.704391400639807e-06, + "loss": 0.0969, + "step": 370350 + }, + { + "epoch": 0.83, + "learning_rate": 8.703272857430484e-06, + "loss": 0.0981, + "step": 370360 + }, + { + "epoch": 0.83, + "learning_rate": 8.702154314221158e-06, + "loss": 0.099, + "step": 370370 + }, + { + "epoch": 0.83, + "learning_rate": 8.701035771011834e-06, + "loss": 0.0928, + "step": 370380 + }, + { + "epoch": 0.83, + "learning_rate": 8.69991722780251e-06, + "loss": 0.0922, + "step": 370390 + }, + { + "epoch": 0.83, + "learning_rate": 8.698798684593185e-06, + "loss": 0.097, + "step": 370400 + }, + { + "epoch": 0.83, + "learning_rate": 8.697680141383863e-06, + "loss": 0.1004, + "step": 370410 + }, + { + "epoch": 0.83, + "learning_rate": 8.696561598174538e-06, + "loss": 0.0983, + "step": 370420 + }, + { + "epoch": 0.83, + "learning_rate": 8.695443054965214e-06, + "loss": 0.099, + "step": 370430 + }, + { + "epoch": 0.83, + "learning_rate": 8.69432451175589e-06, + "loss": 0.0958, + "step": 370440 + }, + { + "epoch": 0.83, + "learning_rate": 8.693205968546565e-06, + "loss": 0.1005, + "step": 370450 + }, + { + "epoch": 0.83, + "learning_rate": 8.692087425337241e-06, + "loss": 0.1015, + "step": 370460 + }, + { + "epoch": 0.83, + "learning_rate": 8.690968882127917e-06, + "loss": 0.0997, + "step": 370470 + }, + { + "epoch": 0.83, + "learning_rate": 8.689850338918593e-06, + "loss": 0.1046, + "step": 370480 + }, + { + "epoch": 0.83, + "learning_rate": 8.68873179570927e-06, + "loss": 0.1007, + "step": 370490 + }, + { + "epoch": 0.83, + "learning_rate": 8.687613252499944e-06, + "loss": 0.0991, + "step": 370500 + }, + { + "epoch": 0.83, + "learning_rate": 8.68649470929062e-06, + "loss": 0.0949, + "step": 370510 + }, + { + "epoch": 0.83, + "learning_rate": 8.685376166081297e-06, + "loss": 0.0961, + "step": 370520 + }, + { + "epoch": 0.83, + "learning_rate": 8.684257622871971e-06, + "loss": 0.1029, + "step": 370530 + }, + { + "epoch": 0.83, + "learning_rate": 8.683139079662647e-06, + "loss": 0.0955, + "step": 370540 + }, + { + "epoch": 0.83, + "learning_rate": 8.682020536453324e-06, + "loss": 0.0998, + "step": 370550 + }, + { + "epoch": 0.83, + "learning_rate": 8.680901993244e-06, + "loss": 0.099, + "step": 370560 + }, + { + "epoch": 0.83, + "learning_rate": 8.679783450034676e-06, + "loss": 0.0967, + "step": 370570 + }, + { + "epoch": 0.83, + "learning_rate": 8.67866490682535e-06, + "loss": 0.0961, + "step": 370580 + }, + { + "epoch": 0.83, + "learning_rate": 8.677546363616027e-06, + "loss": 0.0981, + "step": 370590 + }, + { + "epoch": 0.83, + "learning_rate": 8.676427820406703e-06, + "loss": 0.0986, + "step": 370600 + }, + { + "epoch": 0.83, + "learning_rate": 8.67530927719738e-06, + "loss": 0.094, + "step": 370610 + }, + { + "epoch": 0.83, + "learning_rate": 8.674190733988054e-06, + "loss": 0.1023, + "step": 370620 + }, + { + "epoch": 0.83, + "learning_rate": 8.67307219077873e-06, + "loss": 0.0995, + "step": 370630 + }, + { + "epoch": 0.83, + "learning_rate": 8.671953647569406e-06, + "loss": 0.0975, + "step": 370640 + }, + { + "epoch": 0.83, + "learning_rate": 8.670835104360083e-06, + "loss": 0.0997, + "step": 370650 + }, + { + "epoch": 0.83, + "learning_rate": 8.669716561150757e-06, + "loss": 0.0984, + "step": 370660 + }, + { + "epoch": 0.83, + "learning_rate": 8.668598017941433e-06, + "loss": 0.0978, + "step": 370670 + }, + { + "epoch": 0.83, + "learning_rate": 8.66747947473211e-06, + "loss": 0.0985, + "step": 370680 + }, + { + "epoch": 0.83, + "learning_rate": 8.666360931522786e-06, + "loss": 0.0965, + "step": 370690 + }, + { + "epoch": 0.83, + "learning_rate": 8.66524238831346e-06, + "loss": 0.0948, + "step": 370700 + }, + { + "epoch": 0.83, + "learning_rate": 8.664123845104137e-06, + "loss": 0.0991, + "step": 370710 + }, + { + "epoch": 0.83, + "learning_rate": 8.663005301894813e-06, + "loss": 0.0936, + "step": 370720 + }, + { + "epoch": 0.83, + "learning_rate": 8.661886758685489e-06, + "loss": 0.0985, + "step": 370730 + }, + { + "epoch": 0.83, + "learning_rate": 8.660768215476164e-06, + "loss": 0.0948, + "step": 370740 + }, + { + "epoch": 0.83, + "learning_rate": 8.65964967226684e-06, + "loss": 0.0979, + "step": 370750 + }, + { + "epoch": 0.83, + "learning_rate": 8.658531129057516e-06, + "loss": 0.1002, + "step": 370760 + }, + { + "epoch": 0.83, + "learning_rate": 8.657412585848192e-06, + "loss": 0.0987, + "step": 370770 + }, + { + "epoch": 0.83, + "learning_rate": 8.656294042638867e-06, + "loss": 0.0962, + "step": 370780 + }, + { + "epoch": 0.83, + "learning_rate": 8.655175499429543e-06, + "loss": 0.0979, + "step": 370790 + }, + { + "epoch": 0.83, + "learning_rate": 8.65405695622022e-06, + "loss": 0.0989, + "step": 370800 + }, + { + "epoch": 0.83, + "learning_rate": 8.652938413010895e-06, + "loss": 0.0969, + "step": 370810 + }, + { + "epoch": 0.83, + "learning_rate": 8.651819869801572e-06, + "loss": 0.1037, + "step": 370820 + }, + { + "epoch": 0.83, + "learning_rate": 8.650701326592246e-06, + "loss": 0.0997, + "step": 370830 + }, + { + "epoch": 0.83, + "learning_rate": 8.649582783382922e-06, + "loss": 0.1023, + "step": 370840 + }, + { + "epoch": 0.83, + "learning_rate": 8.648464240173599e-06, + "loss": 0.1007, + "step": 370850 + }, + { + "epoch": 0.83, + "learning_rate": 8.647345696964273e-06, + "loss": 0.0981, + "step": 370860 + }, + { + "epoch": 0.83, + "learning_rate": 8.64622715375495e-06, + "loss": 0.1005, + "step": 370870 + }, + { + "epoch": 0.83, + "learning_rate": 8.645108610545626e-06, + "loss": 0.0997, + "step": 370880 + }, + { + "epoch": 0.83, + "learning_rate": 8.643990067336302e-06, + "loss": 0.0989, + "step": 370890 + }, + { + "epoch": 0.83, + "learning_rate": 8.642871524126978e-06, + "loss": 0.1001, + "step": 370900 + }, + { + "epoch": 0.83, + "learning_rate": 8.641752980917653e-06, + "loss": 0.0977, + "step": 370910 + }, + { + "epoch": 0.83, + "learning_rate": 8.640634437708329e-06, + "loss": 0.0991, + "step": 370920 + }, + { + "epoch": 0.83, + "learning_rate": 8.639515894499005e-06, + "loss": 0.0993, + "step": 370930 + }, + { + "epoch": 0.83, + "learning_rate": 8.63839735128968e-06, + "loss": 0.1009, + "step": 370940 + }, + { + "epoch": 0.83, + "learning_rate": 8.637278808080358e-06, + "loss": 0.0999, + "step": 370950 + }, + { + "epoch": 0.83, + "learning_rate": 8.636160264871032e-06, + "loss": 0.0981, + "step": 370960 + }, + { + "epoch": 0.83, + "learning_rate": 8.635041721661708e-06, + "loss": 0.1002, + "step": 370970 + }, + { + "epoch": 0.83, + "learning_rate": 8.633923178452385e-06, + "loss": 0.0967, + "step": 370980 + }, + { + "epoch": 0.83, + "learning_rate": 8.63280463524306e-06, + "loss": 0.0957, + "step": 370990 + }, + { + "epoch": 0.83, + "learning_rate": 8.631686092033735e-06, + "loss": 0.0959, + "step": 371000 + }, + { + "epoch": 0.83, + "learning_rate": 8.630567548824412e-06, + "loss": 0.0975, + "step": 371010 + }, + { + "epoch": 0.83, + "learning_rate": 8.62956085993602e-06, + "loss": 0.1036, + "step": 371020 + }, + { + "epoch": 0.83, + "learning_rate": 8.628442316726695e-06, + "loss": 0.1004, + "step": 371030 + }, + { + "epoch": 0.83, + "learning_rate": 8.627323773517371e-06, + "loss": 0.0978, + "step": 371040 + }, + { + "epoch": 0.83, + "learning_rate": 8.626205230308047e-06, + "loss": 0.1002, + "step": 371050 + }, + { + "epoch": 0.83, + "learning_rate": 8.625086687098722e-06, + "loss": 0.0992, + "step": 371060 + }, + { + "epoch": 0.83, + "learning_rate": 8.6239681438894e-06, + "loss": 0.1004, + "step": 371070 + }, + { + "epoch": 0.83, + "learning_rate": 8.622849600680074e-06, + "loss": 0.0937, + "step": 371080 + }, + { + "epoch": 0.83, + "learning_rate": 8.62173105747075e-06, + "loss": 0.1006, + "step": 371090 + }, + { + "epoch": 0.83, + "learning_rate": 8.620612514261427e-06, + "loss": 0.098, + "step": 371100 + }, + { + "epoch": 0.83, + "learning_rate": 8.619493971052101e-06, + "loss": 0.0975, + "step": 371110 + }, + { + "epoch": 0.83, + "learning_rate": 8.61837542784278e-06, + "loss": 0.0942, + "step": 371120 + }, + { + "epoch": 0.83, + "learning_rate": 8.617256884633454e-06, + "loss": 0.0972, + "step": 371130 + }, + { + "epoch": 0.83, + "learning_rate": 8.616138341424128e-06, + "loss": 0.0967, + "step": 371140 + }, + { + "epoch": 0.83, + "learning_rate": 8.615019798214806e-06, + "loss": 0.1011, + "step": 371150 + }, + { + "epoch": 0.83, + "learning_rate": 8.613901255005481e-06, + "loss": 0.0998, + "step": 371160 + }, + { + "epoch": 0.83, + "learning_rate": 8.612782711796157e-06, + "loss": 0.1017, + "step": 371170 + }, + { + "epoch": 0.83, + "learning_rate": 8.611664168586833e-06, + "loss": 0.1024, + "step": 371180 + }, + { + "epoch": 0.83, + "learning_rate": 8.610545625377508e-06, + "loss": 0.0978, + "step": 371190 + }, + { + "epoch": 0.83, + "learning_rate": 8.609427082168186e-06, + "loss": 0.0961, + "step": 371200 + }, + { + "epoch": 0.83, + "learning_rate": 8.60830853895886e-06, + "loss": 0.1028, + "step": 371210 + }, + { + "epoch": 0.83, + "learning_rate": 8.607189995749537e-06, + "loss": 0.0995, + "step": 371220 + }, + { + "epoch": 0.83, + "learning_rate": 8.606071452540213e-06, + "loss": 0.0977, + "step": 371230 + }, + { + "epoch": 0.83, + "learning_rate": 8.604952909330887e-06, + "loss": 0.0969, + "step": 371240 + }, + { + "epoch": 0.83, + "learning_rate": 8.603834366121564e-06, + "loss": 0.0978, + "step": 371250 + }, + { + "epoch": 0.83, + "learning_rate": 8.60271582291224e-06, + "loss": 0.0995, + "step": 371260 + }, + { + "epoch": 0.83, + "learning_rate": 8.601597279702914e-06, + "loss": 0.0976, + "step": 371270 + }, + { + "epoch": 0.83, + "learning_rate": 8.600478736493592e-06, + "loss": 0.0974, + "step": 371280 + }, + { + "epoch": 0.83, + "learning_rate": 8.599360193284267e-06, + "loss": 0.101, + "step": 371290 + }, + { + "epoch": 0.83, + "learning_rate": 8.598241650074943e-06, + "loss": 0.0986, + "step": 371300 + }, + { + "epoch": 0.83, + "learning_rate": 8.59712310686562e-06, + "loss": 0.1005, + "step": 371310 + }, + { + "epoch": 0.83, + "learning_rate": 8.596004563656294e-06, + "loss": 0.0952, + "step": 371320 + }, + { + "epoch": 0.83, + "learning_rate": 8.59488602044697e-06, + "loss": 0.1024, + "step": 371330 + }, + { + "epoch": 0.83, + "learning_rate": 8.593767477237646e-06, + "loss": 0.0943, + "step": 371340 + }, + { + "epoch": 0.83, + "learning_rate": 8.592648934028321e-06, + "loss": 0.0979, + "step": 371350 + }, + { + "epoch": 0.83, + "learning_rate": 8.591530390818999e-06, + "loss": 0.0977, + "step": 371360 + }, + { + "epoch": 0.83, + "learning_rate": 8.590411847609673e-06, + "loss": 0.0963, + "step": 371370 + }, + { + "epoch": 0.83, + "learning_rate": 8.58929330440035e-06, + "loss": 0.0978, + "step": 371380 + }, + { + "epoch": 0.83, + "learning_rate": 8.588174761191026e-06, + "loss": 0.0958, + "step": 371390 + }, + { + "epoch": 0.83, + "learning_rate": 8.5870562179817e-06, + "loss": 0.0952, + "step": 371400 + }, + { + "epoch": 0.83, + "learning_rate": 8.585937674772377e-06, + "loss": 0.1018, + "step": 371410 + }, + { + "epoch": 0.83, + "learning_rate": 8.584819131563053e-06, + "loss": 0.0962, + "step": 371420 + }, + { + "epoch": 0.83, + "learning_rate": 8.583700588353729e-06, + "loss": 0.1011, + "step": 371430 + }, + { + "epoch": 0.83, + "learning_rate": 8.582582045144405e-06, + "loss": 0.1024, + "step": 371440 + }, + { + "epoch": 0.83, + "learning_rate": 8.58146350193508e-06, + "loss": 0.0924, + "step": 371450 + }, + { + "epoch": 0.83, + "learning_rate": 8.580344958725756e-06, + "loss": 0.0985, + "step": 371460 + }, + { + "epoch": 0.83, + "learning_rate": 8.579226415516432e-06, + "loss": 0.098, + "step": 371470 + }, + { + "epoch": 0.83, + "learning_rate": 8.578107872307107e-06, + "loss": 0.0954, + "step": 371480 + }, + { + "epoch": 0.83, + "learning_rate": 8.576989329097783e-06, + "loss": 0.1003, + "step": 371490 + }, + { + "epoch": 0.83, + "learning_rate": 8.57587078588846e-06, + "loss": 0.1005, + "step": 371500 + }, + { + "epoch": 0.83, + "learning_rate": 8.574752242679136e-06, + "loss": 0.1002, + "step": 371510 + }, + { + "epoch": 0.83, + "learning_rate": 8.573633699469812e-06, + "loss": 0.1024, + "step": 371520 + }, + { + "epoch": 0.83, + "learning_rate": 8.572515156260486e-06, + "loss": 0.0967, + "step": 371530 + }, + { + "epoch": 0.83, + "learning_rate": 8.571396613051163e-06, + "loss": 0.0964, + "step": 371540 + }, + { + "epoch": 0.83, + "learning_rate": 8.570278069841839e-06, + "loss": 0.0927, + "step": 371550 + }, + { + "epoch": 0.83, + "learning_rate": 8.569159526632513e-06, + "loss": 0.0968, + "step": 371560 + }, + { + "epoch": 0.83, + "learning_rate": 8.56804098342319e-06, + "loss": 0.095, + "step": 371570 + }, + { + "epoch": 0.83, + "learning_rate": 8.566922440213866e-06, + "loss": 0.0969, + "step": 371580 + }, + { + "epoch": 0.83, + "learning_rate": 8.565803897004542e-06, + "loss": 0.0982, + "step": 371590 + }, + { + "epoch": 0.83, + "learning_rate": 8.564685353795218e-06, + "loss": 0.0985, + "step": 371600 + }, + { + "epoch": 0.83, + "learning_rate": 8.563566810585893e-06, + "loss": 0.0976, + "step": 371610 + }, + { + "epoch": 0.83, + "learning_rate": 8.562448267376569e-06, + "loss": 0.0972, + "step": 371620 + }, + { + "epoch": 0.83, + "learning_rate": 8.561329724167245e-06, + "loss": 0.0963, + "step": 371630 + }, + { + "epoch": 0.83, + "learning_rate": 8.560211180957922e-06, + "loss": 0.0926, + "step": 371640 + }, + { + "epoch": 0.83, + "learning_rate": 8.559092637748596e-06, + "loss": 0.0986, + "step": 371650 + }, + { + "epoch": 0.83, + "learning_rate": 8.557974094539272e-06, + "loss": 0.0934, + "step": 371660 + }, + { + "epoch": 0.83, + "learning_rate": 8.556855551329949e-06, + "loss": 0.0982, + "step": 371670 + }, + { + "epoch": 0.83, + "learning_rate": 8.555737008120625e-06, + "loss": 0.0979, + "step": 371680 + }, + { + "epoch": 0.83, + "learning_rate": 8.5546184649113e-06, + "loss": 0.0986, + "step": 371690 + }, + { + "epoch": 0.83, + "learning_rate": 8.553499921701976e-06, + "loss": 0.0999, + "step": 371700 + }, + { + "epoch": 0.83, + "learning_rate": 8.552381378492652e-06, + "loss": 0.0998, + "step": 371710 + }, + { + "epoch": 0.83, + "learning_rate": 8.551262835283328e-06, + "loss": 0.098, + "step": 371720 + }, + { + "epoch": 0.83, + "learning_rate": 8.550144292074003e-06, + "loss": 0.0972, + "step": 371730 + }, + { + "epoch": 0.83, + "learning_rate": 8.549025748864679e-06, + "loss": 0.095, + "step": 371740 + }, + { + "epoch": 0.83, + "learning_rate": 8.547907205655355e-06, + "loss": 0.0976, + "step": 371750 + }, + { + "epoch": 0.83, + "learning_rate": 8.546788662446031e-06, + "loss": 0.0983, + "step": 371760 + }, + { + "epoch": 0.83, + "learning_rate": 8.545670119236707e-06, + "loss": 0.1029, + "step": 371770 + }, + { + "epoch": 0.83, + "learning_rate": 8.544551576027382e-06, + "loss": 0.1005, + "step": 371780 + }, + { + "epoch": 0.83, + "learning_rate": 8.543433032818058e-06, + "loss": 0.0993, + "step": 371790 + }, + { + "epoch": 0.83, + "learning_rate": 8.542314489608734e-06, + "loss": 0.1012, + "step": 371800 + }, + { + "epoch": 0.83, + "learning_rate": 8.541195946399409e-06, + "loss": 0.0999, + "step": 371810 + }, + { + "epoch": 0.83, + "learning_rate": 8.540077403190085e-06, + "loss": 0.0971, + "step": 371820 + }, + { + "epoch": 0.83, + "learning_rate": 8.538958859980762e-06, + "loss": 0.0994, + "step": 371830 + }, + { + "epoch": 0.83, + "learning_rate": 8.537840316771438e-06, + "loss": 0.0948, + "step": 371840 + }, + { + "epoch": 0.83, + "learning_rate": 8.536721773562114e-06, + "loss": 0.1006, + "step": 371850 + }, + { + "epoch": 0.83, + "learning_rate": 8.535603230352789e-06, + "loss": 0.1017, + "step": 371860 + }, + { + "epoch": 0.83, + "learning_rate": 8.534484687143465e-06, + "loss": 0.1047, + "step": 371870 + }, + { + "epoch": 0.83, + "learning_rate": 8.533366143934141e-06, + "loss": 0.0966, + "step": 371880 + }, + { + "epoch": 0.83, + "learning_rate": 8.532247600724816e-06, + "loss": 0.0965, + "step": 371890 + }, + { + "epoch": 0.83, + "learning_rate": 8.531129057515492e-06, + "loss": 0.0939, + "step": 371900 + }, + { + "epoch": 0.83, + "learning_rate": 8.530010514306168e-06, + "loss": 0.0981, + "step": 371910 + }, + { + "epoch": 0.83, + "learning_rate": 8.528891971096844e-06, + "loss": 0.0981, + "step": 371920 + }, + { + "epoch": 0.83, + "learning_rate": 8.52777342788752e-06, + "loss": 0.1043, + "step": 371930 + }, + { + "epoch": 0.83, + "learning_rate": 8.526654884678195e-06, + "loss": 0.0969, + "step": 371940 + }, + { + "epoch": 0.83, + "learning_rate": 8.525536341468871e-06, + "loss": 0.095, + "step": 371950 + }, + { + "epoch": 0.83, + "learning_rate": 8.524417798259547e-06, + "loss": 0.0946, + "step": 371960 + }, + { + "epoch": 0.83, + "learning_rate": 8.523299255050222e-06, + "loss": 0.0983, + "step": 371970 + }, + { + "epoch": 0.83, + "learning_rate": 8.5221807118409e-06, + "loss": 0.1014, + "step": 371980 + }, + { + "epoch": 0.83, + "learning_rate": 8.521062168631574e-06, + "loss": 0.0983, + "step": 371990 + }, + { + "epoch": 0.83, + "learning_rate": 8.51994362542225e-06, + "loss": 0.0957, + "step": 372000 + }, + { + "epoch": 0.83, + "learning_rate": 8.518825082212927e-06, + "loss": 0.0986, + "step": 372010 + }, + { + "epoch": 0.83, + "learning_rate": 8.517706539003601e-06, + "loss": 0.0955, + "step": 372020 + }, + { + "epoch": 0.83, + "learning_rate": 8.516587995794278e-06, + "loss": 0.0986, + "step": 372030 + }, + { + "epoch": 0.83, + "learning_rate": 8.515469452584954e-06, + "loss": 0.0937, + "step": 372040 + }, + { + "epoch": 0.83, + "learning_rate": 8.514350909375628e-06, + "loss": 0.0979, + "step": 372050 + }, + { + "epoch": 0.83, + "learning_rate": 8.513232366166306e-06, + "loss": 0.0999, + "step": 372060 + }, + { + "epoch": 0.83, + "learning_rate": 8.512113822956981e-06, + "loss": 0.0939, + "step": 372070 + }, + { + "epoch": 0.83, + "learning_rate": 8.510995279747657e-06, + "loss": 0.0967, + "step": 372080 + }, + { + "epoch": 0.83, + "learning_rate": 8.509876736538333e-06, + "loss": 0.1008, + "step": 372090 + }, + { + "epoch": 0.83, + "learning_rate": 8.508758193329008e-06, + "loss": 0.0965, + "step": 372100 + }, + { + "epoch": 0.83, + "learning_rate": 8.507639650119686e-06, + "loss": 0.099, + "step": 372110 + }, + { + "epoch": 0.83, + "learning_rate": 8.50652110691036e-06, + "loss": 0.0971, + "step": 372120 + }, + { + "epoch": 0.83, + "learning_rate": 8.505402563701035e-06, + "loss": 0.0975, + "step": 372130 + }, + { + "epoch": 0.83, + "learning_rate": 8.504284020491713e-06, + "loss": 0.0978, + "step": 372140 + }, + { + "epoch": 0.83, + "learning_rate": 8.503165477282387e-06, + "loss": 0.0971, + "step": 372150 + }, + { + "epoch": 0.83, + "learning_rate": 8.502046934073064e-06, + "loss": 0.0978, + "step": 372160 + }, + { + "epoch": 0.83, + "learning_rate": 8.50092839086374e-06, + "loss": 0.0981, + "step": 372170 + }, + { + "epoch": 0.83, + "learning_rate": 8.499809847654414e-06, + "loss": 0.0992, + "step": 372180 + }, + { + "epoch": 0.83, + "learning_rate": 8.498691304445092e-06, + "loss": 0.1016, + "step": 372190 + }, + { + "epoch": 0.83, + "learning_rate": 8.497572761235767e-06, + "loss": 0.101, + "step": 372200 + }, + { + "epoch": 0.83, + "learning_rate": 8.496454218026441e-06, + "loss": 0.0959, + "step": 372210 + }, + { + "epoch": 0.83, + "learning_rate": 8.49533567481712e-06, + "loss": 0.1038, + "step": 372220 + }, + { + "epoch": 0.83, + "learning_rate": 8.494217131607794e-06, + "loss": 0.0967, + "step": 372230 + }, + { + "epoch": 0.83, + "learning_rate": 8.49309858839847e-06, + "loss": 0.0976, + "step": 372240 + }, + { + "epoch": 0.83, + "learning_rate": 8.491980045189146e-06, + "loss": 0.1002, + "step": 372250 + }, + { + "epoch": 0.83, + "learning_rate": 8.490861501979821e-06, + "loss": 0.0965, + "step": 372260 + }, + { + "epoch": 0.83, + "learning_rate": 8.489742958770499e-06, + "loss": 0.098, + "step": 372270 + }, + { + "epoch": 0.83, + "learning_rate": 8.488624415561173e-06, + "loss": 0.0987, + "step": 372280 + }, + { + "epoch": 0.83, + "learning_rate": 8.48750587235185e-06, + "loss": 0.0981, + "step": 372290 + }, + { + "epoch": 0.83, + "learning_rate": 8.486387329142526e-06, + "loss": 0.0965, + "step": 372300 + }, + { + "epoch": 0.83, + "learning_rate": 8.4852687859332e-06, + "loss": 0.0947, + "step": 372310 + }, + { + "epoch": 0.83, + "learning_rate": 8.484150242723877e-06, + "loss": 0.0981, + "step": 372320 + }, + { + "epoch": 0.83, + "learning_rate": 8.483031699514553e-06, + "loss": 0.0982, + "step": 372330 + }, + { + "epoch": 0.83, + "learning_rate": 8.481913156305227e-06, + "loss": 0.0995, + "step": 372340 + }, + { + "epoch": 0.83, + "learning_rate": 8.480794613095905e-06, + "loss": 0.1008, + "step": 372350 + }, + { + "epoch": 0.83, + "learning_rate": 8.47967606988658e-06, + "loss": 0.1007, + "step": 372360 + }, + { + "epoch": 0.83, + "learning_rate": 8.478557526677256e-06, + "loss": 0.0939, + "step": 372370 + }, + { + "epoch": 0.83, + "learning_rate": 8.477438983467932e-06, + "loss": 0.1023, + "step": 372380 + }, + { + "epoch": 0.83, + "learning_rate": 8.476320440258607e-06, + "loss": 0.0972, + "step": 372390 + }, + { + "epoch": 0.83, + "learning_rate": 8.475201897049283e-06, + "loss": 0.0956, + "step": 372400 + }, + { + "epoch": 0.83, + "learning_rate": 8.47408335383996e-06, + "loss": 0.0965, + "step": 372410 + }, + { + "epoch": 0.83, + "learning_rate": 8.472964810630636e-06, + "loss": 0.0997, + "step": 372420 + }, + { + "epoch": 0.83, + "learning_rate": 8.471846267421312e-06, + "loss": 0.0979, + "step": 372430 + }, + { + "epoch": 0.83, + "learning_rate": 8.470727724211986e-06, + "loss": 0.0964, + "step": 372440 + }, + { + "epoch": 0.83, + "learning_rate": 8.469609181002663e-06, + "loss": 0.1001, + "step": 372450 + }, + { + "epoch": 0.83, + "learning_rate": 8.468490637793339e-06, + "loss": 0.0968, + "step": 372460 + }, + { + "epoch": 0.83, + "learning_rate": 8.467372094584013e-06, + "loss": 0.0979, + "step": 372470 + }, + { + "epoch": 0.83, + "learning_rate": 8.46625355137469e-06, + "loss": 0.0981, + "step": 372480 + }, + { + "epoch": 0.83, + "learning_rate": 8.465135008165366e-06, + "loss": 0.097, + "step": 372490 + }, + { + "epoch": 0.83, + "learning_rate": 8.464016464956042e-06, + "loss": 0.097, + "step": 372500 + }, + { + "epoch": 0.83, + "learning_rate": 8.462897921746718e-06, + "loss": 0.0969, + "step": 372510 + }, + { + "epoch": 0.83, + "learning_rate": 8.461779378537393e-06, + "loss": 0.0952, + "step": 372520 + }, + { + "epoch": 0.83, + "learning_rate": 8.460660835328069e-06, + "loss": 0.0963, + "step": 372530 + }, + { + "epoch": 0.83, + "learning_rate": 8.459542292118745e-06, + "loss": 0.0991, + "step": 372540 + }, + { + "epoch": 0.83, + "learning_rate": 8.45842374890942e-06, + "loss": 0.0988, + "step": 372550 + }, + { + "epoch": 0.83, + "learning_rate": 8.457305205700096e-06, + "loss": 0.0984, + "step": 372560 + }, + { + "epoch": 0.83, + "learning_rate": 8.456186662490772e-06, + "loss": 0.0978, + "step": 372570 + }, + { + "epoch": 0.83, + "learning_rate": 8.455068119281449e-06, + "loss": 0.0957, + "step": 372580 + }, + { + "epoch": 0.83, + "learning_rate": 8.453949576072125e-06, + "loss": 0.0973, + "step": 372590 + }, + { + "epoch": 0.83, + "learning_rate": 8.4528310328628e-06, + "loss": 0.0968, + "step": 372600 + }, + { + "epoch": 0.83, + "learning_rate": 8.451712489653476e-06, + "loss": 0.0969, + "step": 372610 + }, + { + "epoch": 0.83, + "learning_rate": 8.450593946444152e-06, + "loss": 0.0987, + "step": 372620 + }, + { + "epoch": 0.83, + "learning_rate": 8.449475403234828e-06, + "loss": 0.0959, + "step": 372630 + }, + { + "epoch": 0.83, + "learning_rate": 8.448356860025503e-06, + "loss": 0.0987, + "step": 372640 + }, + { + "epoch": 0.83, + "learning_rate": 8.447238316816179e-06, + "loss": 0.0938, + "step": 372650 + }, + { + "epoch": 0.83, + "learning_rate": 8.446119773606855e-06, + "loss": 0.0954, + "step": 372660 + }, + { + "epoch": 0.83, + "learning_rate": 8.445001230397531e-06, + "loss": 0.0969, + "step": 372670 + }, + { + "epoch": 0.83, + "learning_rate": 8.443882687188206e-06, + "loss": 0.0954, + "step": 372680 + }, + { + "epoch": 0.83, + "learning_rate": 8.442764143978882e-06, + "loss": 0.0977, + "step": 372690 + }, + { + "epoch": 0.83, + "learning_rate": 8.441645600769558e-06, + "loss": 0.0984, + "step": 372700 + }, + { + "epoch": 0.83, + "learning_rate": 8.440527057560234e-06, + "loss": 0.1012, + "step": 372710 + }, + { + "epoch": 0.83, + "learning_rate": 8.439408514350909e-06, + "loss": 0.0985, + "step": 372720 + }, + { + "epoch": 0.83, + "learning_rate": 8.438289971141585e-06, + "loss": 0.0967, + "step": 372730 + }, + { + "epoch": 0.83, + "learning_rate": 8.437171427932261e-06, + "loss": 0.0962, + "step": 372740 + }, + { + "epoch": 0.83, + "learning_rate": 8.436052884722938e-06, + "loss": 0.0991, + "step": 372750 + }, + { + "epoch": 0.83, + "learning_rate": 8.434934341513612e-06, + "loss": 0.0972, + "step": 372760 + }, + { + "epoch": 0.83, + "learning_rate": 8.433815798304289e-06, + "loss": 0.0946, + "step": 372770 + }, + { + "epoch": 0.83, + "learning_rate": 8.432697255094965e-06, + "loss": 0.0996, + "step": 372780 + }, + { + "epoch": 0.83, + "learning_rate": 8.431578711885641e-06, + "loss": 0.0973, + "step": 372790 + }, + { + "epoch": 0.83, + "learning_rate": 8.430460168676316e-06, + "loss": 0.0971, + "step": 372800 + }, + { + "epoch": 0.83, + "learning_rate": 8.429341625466992e-06, + "loss": 0.0983, + "step": 372810 + }, + { + "epoch": 0.83, + "learning_rate": 8.428223082257668e-06, + "loss": 0.1013, + "step": 372820 + }, + { + "epoch": 0.83, + "learning_rate": 8.427104539048344e-06, + "loss": 0.1012, + "step": 372830 + }, + { + "epoch": 0.83, + "learning_rate": 8.42598599583902e-06, + "loss": 0.0975, + "step": 372840 + }, + { + "epoch": 0.83, + "learning_rate": 8.424867452629695e-06, + "loss": 0.0953, + "step": 372850 + }, + { + "epoch": 0.83, + "learning_rate": 8.423748909420371e-06, + "loss": 0.0965, + "step": 372860 + }, + { + "epoch": 0.83, + "learning_rate": 8.422630366211047e-06, + "loss": 0.1007, + "step": 372870 + }, + { + "epoch": 0.83, + "learning_rate": 8.421511823001722e-06, + "loss": 0.0982, + "step": 372880 + }, + { + "epoch": 0.83, + "learning_rate": 8.420393279792398e-06, + "loss": 0.1014, + "step": 372890 + }, + { + "epoch": 0.83, + "learning_rate": 8.419274736583074e-06, + "loss": 0.0974, + "step": 372900 + }, + { + "epoch": 0.83, + "learning_rate": 8.41815619337375e-06, + "loss": 0.1, + "step": 372910 + }, + { + "epoch": 0.83, + "learning_rate": 8.417037650164427e-06, + "loss": 0.1007, + "step": 372920 + }, + { + "epoch": 0.83, + "learning_rate": 8.415919106955101e-06, + "loss": 0.0962, + "step": 372930 + }, + { + "epoch": 0.83, + "learning_rate": 8.414800563745778e-06, + "loss": 0.0983, + "step": 372940 + }, + { + "epoch": 0.83, + "learning_rate": 8.413682020536454e-06, + "loss": 0.0974, + "step": 372950 + }, + { + "epoch": 0.83, + "learning_rate": 8.412563477327128e-06, + "loss": 0.094, + "step": 372960 + }, + { + "epoch": 0.83, + "learning_rate": 8.411444934117806e-06, + "loss": 0.0959, + "step": 372970 + }, + { + "epoch": 0.83, + "learning_rate": 8.410326390908481e-06, + "loss": 0.1011, + "step": 372980 + }, + { + "epoch": 0.83, + "learning_rate": 8.409207847699157e-06, + "loss": 0.1002, + "step": 372990 + }, + { + "epoch": 0.83, + "learning_rate": 8.408089304489833e-06, + "loss": 0.0993, + "step": 373000 + }, + { + "epoch": 0.83, + "learning_rate": 8.406970761280508e-06, + "loss": 0.0938, + "step": 373010 + }, + { + "epoch": 0.83, + "learning_rate": 8.405852218071184e-06, + "loss": 0.0999, + "step": 373020 + }, + { + "epoch": 0.83, + "learning_rate": 8.40473367486186e-06, + "loss": 0.0947, + "step": 373030 + }, + { + "epoch": 0.83, + "learning_rate": 8.403615131652535e-06, + "loss": 0.0975, + "step": 373040 + }, + { + "epoch": 0.83, + "learning_rate": 8.402496588443213e-06, + "loss": 0.0966, + "step": 373050 + }, + { + "epoch": 0.83, + "learning_rate": 8.40148989955482e-06, + "loss": 0.0949, + "step": 373060 + }, + { + "epoch": 0.83, + "learning_rate": 8.400371356345496e-06, + "loss": 0.099, + "step": 373070 + }, + { + "epoch": 0.83, + "learning_rate": 8.39925281313617e-06, + "loss": 0.1002, + "step": 373080 + }, + { + "epoch": 0.83, + "learning_rate": 8.398134269926849e-06, + "loss": 0.0975, + "step": 373090 + }, + { + "epoch": 0.83, + "learning_rate": 8.397015726717523e-06, + "loss": 0.0955, + "step": 373100 + }, + { + "epoch": 0.83, + "learning_rate": 8.3958971835082e-06, + "loss": 0.0984, + "step": 373110 + }, + { + "epoch": 0.83, + "learning_rate": 8.394778640298876e-06, + "loss": 0.0969, + "step": 373120 + }, + { + "epoch": 0.83, + "learning_rate": 8.39366009708955e-06, + "loss": 0.0994, + "step": 373130 + }, + { + "epoch": 0.83, + "learning_rate": 8.392541553880228e-06, + "loss": 0.0963, + "step": 373140 + }, + { + "epoch": 0.83, + "learning_rate": 8.391423010670903e-06, + "loss": 0.097, + "step": 373150 + }, + { + "epoch": 0.83, + "learning_rate": 8.390304467461577e-06, + "loss": 0.1003, + "step": 373160 + }, + { + "epoch": 0.83, + "learning_rate": 8.389185924252255e-06, + "loss": 0.1016, + "step": 373170 + }, + { + "epoch": 0.83, + "learning_rate": 8.38806738104293e-06, + "loss": 0.0936, + "step": 373180 + }, + { + "epoch": 0.83, + "learning_rate": 8.386948837833606e-06, + "loss": 0.0985, + "step": 373190 + }, + { + "epoch": 0.83, + "learning_rate": 8.385830294624282e-06, + "loss": 0.1016, + "step": 373200 + }, + { + "epoch": 0.83, + "learning_rate": 8.384711751414957e-06, + "loss": 0.0996, + "step": 373210 + }, + { + "epoch": 0.83, + "learning_rate": 8.383593208205635e-06, + "loss": 0.0972, + "step": 373220 + }, + { + "epoch": 0.83, + "learning_rate": 8.38247466499631e-06, + "loss": 0.0978, + "step": 373230 + }, + { + "epoch": 0.83, + "learning_rate": 8.381356121786985e-06, + "loss": 0.0935, + "step": 373240 + }, + { + "epoch": 0.83, + "learning_rate": 8.380237578577662e-06, + "loss": 0.0981, + "step": 373250 + }, + { + "epoch": 0.83, + "learning_rate": 8.379119035368336e-06, + "loss": 0.0981, + "step": 373260 + }, + { + "epoch": 0.83, + "learning_rate": 8.378000492159012e-06, + "loss": 0.0986, + "step": 373270 + }, + { + "epoch": 0.83, + "learning_rate": 8.376881948949689e-06, + "loss": 0.1027, + "step": 373280 + }, + { + "epoch": 0.83, + "learning_rate": 8.375763405740363e-06, + "loss": 0.0997, + "step": 373290 + }, + { + "epoch": 0.83, + "learning_rate": 8.374644862531041e-06, + "loss": 0.0966, + "step": 373300 + }, + { + "epoch": 0.83, + "learning_rate": 8.373526319321716e-06, + "loss": 0.0986, + "step": 373310 + }, + { + "epoch": 0.83, + "learning_rate": 8.372407776112392e-06, + "loss": 0.0969, + "step": 373320 + }, + { + "epoch": 0.83, + "learning_rate": 8.371289232903068e-06, + "loss": 0.1009, + "step": 373330 + }, + { + "epoch": 0.83, + "learning_rate": 8.370170689693743e-06, + "loss": 0.0978, + "step": 373340 + }, + { + "epoch": 0.83, + "learning_rate": 8.369052146484419e-06, + "loss": 0.098, + "step": 373350 + }, + { + "epoch": 0.83, + "learning_rate": 8.367933603275095e-06, + "loss": 0.0985, + "step": 373360 + }, + { + "epoch": 0.83, + "learning_rate": 8.36681506006577e-06, + "loss": 0.0948, + "step": 373370 + }, + { + "epoch": 0.83, + "learning_rate": 8.365696516856448e-06, + "loss": 0.0989, + "step": 373380 + }, + { + "epoch": 0.83, + "learning_rate": 8.364577973647122e-06, + "loss": 0.0932, + "step": 373390 + }, + { + "epoch": 0.83, + "learning_rate": 8.363459430437798e-06, + "loss": 0.0965, + "step": 373400 + }, + { + "epoch": 0.83, + "learning_rate": 8.362340887228475e-06, + "loss": 0.0979, + "step": 373410 + }, + { + "epoch": 0.83, + "learning_rate": 8.361222344019149e-06, + "loss": 0.0966, + "step": 373420 + }, + { + "epoch": 0.83, + "learning_rate": 8.360103800809825e-06, + "loss": 0.0977, + "step": 373430 + }, + { + "epoch": 0.83, + "learning_rate": 8.358985257600502e-06, + "loss": 0.0983, + "step": 373440 + }, + { + "epoch": 0.83, + "learning_rate": 8.357866714391178e-06, + "loss": 0.0982, + "step": 373450 + }, + { + "epoch": 0.83, + "learning_rate": 8.356748171181854e-06, + "loss": 0.0972, + "step": 373460 + }, + { + "epoch": 0.83, + "learning_rate": 8.355629627972529e-06, + "loss": 0.1001, + "step": 373470 + }, + { + "epoch": 0.83, + "learning_rate": 8.354511084763205e-06, + "loss": 0.0974, + "step": 373480 + }, + { + "epoch": 0.83, + "learning_rate": 8.353392541553881e-06, + "loss": 0.0967, + "step": 373490 + }, + { + "epoch": 0.83, + "learning_rate": 8.352273998344556e-06, + "loss": 0.0952, + "step": 373500 + }, + { + "epoch": 0.83, + "learning_rate": 8.351155455135232e-06, + "loss": 0.0979, + "step": 373510 + }, + { + "epoch": 0.83, + "learning_rate": 8.350036911925908e-06, + "loss": 0.1006, + "step": 373520 + }, + { + "epoch": 0.83, + "learning_rate": 8.348918368716584e-06, + "loss": 0.0946, + "step": 373530 + }, + { + "epoch": 0.83, + "learning_rate": 8.34779982550726e-06, + "loss": 0.0989, + "step": 373540 + }, + { + "epoch": 0.83, + "learning_rate": 8.346681282297935e-06, + "loss": 0.0983, + "step": 373550 + }, + { + "epoch": 0.83, + "learning_rate": 8.345562739088611e-06, + "loss": 0.0991, + "step": 373560 + }, + { + "epoch": 0.83, + "learning_rate": 8.344444195879288e-06, + "loss": 0.1001, + "step": 373570 + }, + { + "epoch": 0.83, + "learning_rate": 8.343325652669964e-06, + "loss": 0.0968, + "step": 373580 + }, + { + "epoch": 0.83, + "learning_rate": 8.342207109460638e-06, + "loss": 0.0961, + "step": 373590 + }, + { + "epoch": 0.83, + "learning_rate": 8.341088566251315e-06, + "loss": 0.0985, + "step": 373600 + }, + { + "epoch": 0.83, + "learning_rate": 8.33997002304199e-06, + "loss": 0.0955, + "step": 373610 + }, + { + "epoch": 0.83, + "learning_rate": 8.338851479832667e-06, + "loss": 0.1007, + "step": 373620 + }, + { + "epoch": 0.83, + "learning_rate": 8.337732936623342e-06, + "loss": 0.0921, + "step": 373630 + }, + { + "epoch": 0.83, + "learning_rate": 8.336614393414018e-06, + "loss": 0.0981, + "step": 373640 + }, + { + "epoch": 0.83, + "learning_rate": 8.335495850204694e-06, + "loss": 0.1002, + "step": 373650 + }, + { + "epoch": 0.83, + "learning_rate": 8.33437730699537e-06, + "loss": 0.1008, + "step": 373660 + }, + { + "epoch": 0.83, + "learning_rate": 8.333258763786045e-06, + "loss": 0.1007, + "step": 373670 + }, + { + "epoch": 0.83, + "learning_rate": 8.332140220576721e-06, + "loss": 0.0938, + "step": 373680 + }, + { + "epoch": 0.83, + "learning_rate": 8.331021677367397e-06, + "loss": 0.0958, + "step": 373690 + }, + { + "epoch": 0.83, + "learning_rate": 8.329903134158074e-06, + "loss": 0.0968, + "step": 373700 + }, + { + "epoch": 0.83, + "learning_rate": 8.328784590948748e-06, + "loss": 0.1003, + "step": 373710 + }, + { + "epoch": 0.83, + "learning_rate": 8.327666047739424e-06, + "loss": 0.0964, + "step": 373720 + }, + { + "epoch": 0.83, + "learning_rate": 8.3265475045301e-06, + "loss": 0.0947, + "step": 373730 + }, + { + "epoch": 0.83, + "learning_rate": 8.325428961320777e-06, + "loss": 0.0941, + "step": 373740 + }, + { + "epoch": 0.83, + "learning_rate": 8.324310418111451e-06, + "loss": 0.0941, + "step": 373750 + }, + { + "epoch": 0.83, + "learning_rate": 8.323191874902128e-06, + "loss": 0.0958, + "step": 373760 + }, + { + "epoch": 0.83, + "learning_rate": 8.322073331692804e-06, + "loss": 0.0951, + "step": 373770 + }, + { + "epoch": 0.83, + "learning_rate": 8.32095478848348e-06, + "loss": 0.094, + "step": 373780 + }, + { + "epoch": 0.83, + "learning_rate": 8.319836245274156e-06, + "loss": 0.0976, + "step": 373790 + }, + { + "epoch": 0.83, + "learning_rate": 8.31871770206483e-06, + "loss": 0.097, + "step": 373800 + }, + { + "epoch": 0.83, + "learning_rate": 8.317599158855507e-06, + "loss": 0.0985, + "step": 373810 + }, + { + "epoch": 0.83, + "learning_rate": 8.316480615646183e-06, + "loss": 0.0973, + "step": 373820 + }, + { + "epoch": 0.83, + "learning_rate": 8.315362072436858e-06, + "loss": 0.0977, + "step": 373830 + }, + { + "epoch": 0.83, + "learning_rate": 8.314243529227534e-06, + "loss": 0.0962, + "step": 373840 + }, + { + "epoch": 0.83, + "learning_rate": 8.31312498601821e-06, + "loss": 0.0967, + "step": 373850 + }, + { + "epoch": 0.83, + "learning_rate": 8.312006442808886e-06, + "loss": 0.0962, + "step": 373860 + }, + { + "epoch": 0.83, + "learning_rate": 8.310887899599563e-06, + "loss": 0.0993, + "step": 373870 + }, + { + "epoch": 0.83, + "learning_rate": 8.309769356390237e-06, + "loss": 0.0938, + "step": 373880 + }, + { + "epoch": 0.83, + "learning_rate": 8.308650813180913e-06, + "loss": 0.097, + "step": 373890 + }, + { + "epoch": 0.83, + "learning_rate": 8.30753226997159e-06, + "loss": 0.1006, + "step": 373900 + }, + { + "epoch": 0.83, + "learning_rate": 8.306413726762264e-06, + "loss": 0.0929, + "step": 373910 + }, + { + "epoch": 0.83, + "learning_rate": 8.305295183552942e-06, + "loss": 0.103, + "step": 373920 + }, + { + "epoch": 0.83, + "learning_rate": 8.304176640343617e-06, + "loss": 0.0981, + "step": 373930 + }, + { + "epoch": 0.83, + "learning_rate": 8.303058097134293e-06, + "loss": 0.0966, + "step": 373940 + }, + { + "epoch": 0.83, + "learning_rate": 8.30193955392497e-06, + "loss": 0.0963, + "step": 373950 + }, + { + "epoch": 0.83, + "learning_rate": 8.300821010715644e-06, + "loss": 0.0971, + "step": 373960 + }, + { + "epoch": 0.83, + "learning_rate": 8.29970246750632e-06, + "loss": 0.1, + "step": 373970 + }, + { + "epoch": 0.83, + "learning_rate": 8.298583924296996e-06, + "loss": 0.0979, + "step": 373980 + }, + { + "epoch": 0.83, + "learning_rate": 8.29746538108767e-06, + "loss": 0.0982, + "step": 373990 + }, + { + "epoch": 0.83, + "learning_rate": 8.296346837878349e-06, + "loss": 0.0981, + "step": 374000 + }, + { + "epoch": 0.83, + "learning_rate": 8.295228294669023e-06, + "loss": 0.0999, + "step": 374010 + }, + { + "epoch": 0.83, + "learning_rate": 8.2941097514597e-06, + "loss": 0.0961, + "step": 374020 + }, + { + "epoch": 0.83, + "learning_rate": 8.292991208250376e-06, + "loss": 0.0951, + "step": 374030 + }, + { + "epoch": 0.83, + "learning_rate": 8.29187266504105e-06, + "loss": 0.0946, + "step": 374040 + }, + { + "epoch": 0.83, + "learning_rate": 8.290754121831726e-06, + "loss": 0.0971, + "step": 374050 + }, + { + "epoch": 0.83, + "learning_rate": 8.289635578622403e-06, + "loss": 0.1002, + "step": 374060 + }, + { + "epoch": 0.83, + "learning_rate": 8.288517035413077e-06, + "loss": 0.099, + "step": 374070 + }, + { + "epoch": 0.83, + "learning_rate": 8.287398492203755e-06, + "loss": 0.0953, + "step": 374080 + }, + { + "epoch": 0.84, + "learning_rate": 8.28627994899443e-06, + "loss": 0.0975, + "step": 374090 + }, + { + "epoch": 0.84, + "learning_rate": 8.285161405785106e-06, + "loss": 0.099, + "step": 374100 + }, + { + "epoch": 0.84, + "learning_rate": 8.284042862575782e-06, + "loss": 0.0977, + "step": 374110 + }, + { + "epoch": 0.84, + "learning_rate": 8.282924319366457e-06, + "loss": 0.0987, + "step": 374120 + }, + { + "epoch": 0.84, + "learning_rate": 8.281805776157135e-06, + "loss": 0.0966, + "step": 374130 + }, + { + "epoch": 0.84, + "learning_rate": 8.280687232947809e-06, + "loss": 0.1021, + "step": 374140 + }, + { + "epoch": 0.84, + "learning_rate": 8.279568689738484e-06, + "loss": 0.0988, + "step": 374150 + }, + { + "epoch": 0.84, + "learning_rate": 8.278450146529162e-06, + "loss": 0.1025, + "step": 374160 + }, + { + "epoch": 0.84, + "learning_rate": 8.277331603319836e-06, + "loss": 0.0965, + "step": 374170 + }, + { + "epoch": 0.84, + "learning_rate": 8.276213060110512e-06, + "loss": 0.0923, + "step": 374180 + }, + { + "epoch": 0.84, + "learning_rate": 8.275094516901189e-06, + "loss": 0.0957, + "step": 374190 + }, + { + "epoch": 0.84, + "learning_rate": 8.273975973691863e-06, + "loss": 0.1004, + "step": 374200 + }, + { + "epoch": 0.84, + "learning_rate": 8.272857430482541e-06, + "loss": 0.0961, + "step": 374210 + }, + { + "epoch": 0.84, + "learning_rate": 8.271738887273216e-06, + "loss": 0.0989, + "step": 374220 + }, + { + "epoch": 0.84, + "learning_rate": 8.270620344063892e-06, + "loss": 0.1021, + "step": 374230 + }, + { + "epoch": 0.84, + "learning_rate": 8.269501800854568e-06, + "loss": 0.0983, + "step": 374240 + }, + { + "epoch": 0.84, + "learning_rate": 8.268383257645243e-06, + "loss": 0.0956, + "step": 374250 + }, + { + "epoch": 0.84, + "learning_rate": 8.267264714435919e-06, + "loss": 0.1003, + "step": 374260 + }, + { + "epoch": 0.84, + "learning_rate": 8.266146171226595e-06, + "loss": 0.0947, + "step": 374270 + }, + { + "epoch": 0.84, + "learning_rate": 8.26502762801727e-06, + "loss": 0.0977, + "step": 374280 + }, + { + "epoch": 0.84, + "learning_rate": 8.263909084807948e-06, + "loss": 0.0979, + "step": 374290 + }, + { + "epoch": 0.84, + "learning_rate": 8.262790541598622e-06, + "loss": 0.1002, + "step": 374300 + }, + { + "epoch": 0.84, + "learning_rate": 8.261671998389298e-06, + "loss": 0.0969, + "step": 374310 + }, + { + "epoch": 0.84, + "learning_rate": 8.260553455179975e-06, + "loss": 0.0973, + "step": 374320 + }, + { + "epoch": 0.84, + "learning_rate": 8.259434911970649e-06, + "loss": 0.0962, + "step": 374330 + }, + { + "epoch": 0.84, + "learning_rate": 8.258316368761327e-06, + "loss": 0.0979, + "step": 374340 + }, + { + "epoch": 0.84, + "learning_rate": 8.257197825552002e-06, + "loss": 0.0958, + "step": 374350 + }, + { + "epoch": 0.84, + "learning_rate": 8.256079282342676e-06, + "loss": 0.1001, + "step": 374360 + }, + { + "epoch": 0.84, + "learning_rate": 8.254960739133354e-06, + "loss": 0.095, + "step": 374370 + }, + { + "epoch": 0.84, + "learning_rate": 8.253842195924029e-06, + "loss": 0.0962, + "step": 374380 + }, + { + "epoch": 0.84, + "learning_rate": 8.252723652714705e-06, + "loss": 0.0963, + "step": 374390 + }, + { + "epoch": 0.84, + "learning_rate": 8.251605109505381e-06, + "loss": 0.0965, + "step": 374400 + }, + { + "epoch": 0.84, + "learning_rate": 8.250486566296056e-06, + "loss": 0.1004, + "step": 374410 + }, + { + "epoch": 0.84, + "learning_rate": 8.249368023086734e-06, + "loss": 0.0966, + "step": 374420 + }, + { + "epoch": 0.84, + "learning_rate": 8.248249479877408e-06, + "loss": 0.0976, + "step": 374430 + }, + { + "epoch": 0.84, + "learning_rate": 8.247130936668084e-06, + "loss": 0.0995, + "step": 374440 + }, + { + "epoch": 0.84, + "learning_rate": 8.24601239345876e-06, + "loss": 0.1024, + "step": 374450 + }, + { + "epoch": 0.84, + "learning_rate": 8.244893850249435e-06, + "loss": 0.0948, + "step": 374460 + }, + { + "epoch": 0.84, + "learning_rate": 8.243775307040111e-06, + "loss": 0.0979, + "step": 374470 + }, + { + "epoch": 0.84, + "learning_rate": 8.242656763830788e-06, + "loss": 0.0919, + "step": 374480 + }, + { + "epoch": 0.84, + "learning_rate": 8.241538220621462e-06, + "loss": 0.0983, + "step": 374490 + }, + { + "epoch": 0.84, + "learning_rate": 8.24041967741214e-06, + "loss": 0.0999, + "step": 374500 + }, + { + "epoch": 0.84, + "learning_rate": 8.239301134202815e-06, + "loss": 0.095, + "step": 374510 + }, + { + "epoch": 0.84, + "learning_rate": 8.23818259099349e-06, + "loss": 0.0921, + "step": 374520 + }, + { + "epoch": 0.84, + "learning_rate": 8.237064047784167e-06, + "loss": 0.1005, + "step": 374530 + }, + { + "epoch": 0.84, + "learning_rate": 8.235945504574842e-06, + "loss": 0.099, + "step": 374540 + }, + { + "epoch": 0.84, + "learning_rate": 8.234826961365518e-06, + "loss": 0.0958, + "step": 374550 + }, + { + "epoch": 0.84, + "learning_rate": 8.233708418156194e-06, + "loss": 0.099, + "step": 374560 + }, + { + "epoch": 0.84, + "learning_rate": 8.232589874946869e-06, + "loss": 0.0972, + "step": 374570 + }, + { + "epoch": 0.84, + "learning_rate": 8.231471331737546e-06, + "loss": 0.0954, + "step": 374580 + }, + { + "epoch": 0.84, + "learning_rate": 8.230352788528221e-06, + "loss": 0.1006, + "step": 374590 + }, + { + "epoch": 0.84, + "learning_rate": 8.229234245318897e-06, + "loss": 0.0997, + "step": 374600 + }, + { + "epoch": 0.84, + "learning_rate": 8.228115702109573e-06, + "loss": 0.0935, + "step": 374610 + }, + { + "epoch": 0.84, + "learning_rate": 8.226997158900248e-06, + "loss": 0.0974, + "step": 374620 + }, + { + "epoch": 0.84, + "learning_rate": 8.225878615690924e-06, + "loss": 0.0996, + "step": 374630 + }, + { + "epoch": 0.84, + "learning_rate": 8.2247600724816e-06, + "loss": 0.0991, + "step": 374640 + }, + { + "epoch": 0.84, + "learning_rate": 8.223641529272277e-06, + "loss": 0.0992, + "step": 374650 + }, + { + "epoch": 0.84, + "learning_rate": 8.222522986062953e-06, + "loss": 0.0974, + "step": 374660 + }, + { + "epoch": 0.84, + "learning_rate": 8.221404442853628e-06, + "loss": 0.1016, + "step": 374670 + }, + { + "epoch": 0.84, + "learning_rate": 8.220285899644304e-06, + "loss": 0.0996, + "step": 374680 + }, + { + "epoch": 0.84, + "learning_rate": 8.21916735643498e-06, + "loss": 0.099, + "step": 374690 + }, + { + "epoch": 0.84, + "learning_rate": 8.218048813225655e-06, + "loss": 0.0962, + "step": 374700 + }, + { + "epoch": 0.84, + "learning_rate": 8.21693027001633e-06, + "loss": 0.0994, + "step": 374710 + }, + { + "epoch": 0.84, + "learning_rate": 8.215811726807007e-06, + "loss": 0.0954, + "step": 374720 + }, + { + "epoch": 0.84, + "learning_rate": 8.214693183597683e-06, + "loss": 0.0994, + "step": 374730 + }, + { + "epoch": 0.84, + "learning_rate": 8.21357464038836e-06, + "loss": 0.099, + "step": 374740 + }, + { + "epoch": 0.84, + "learning_rate": 8.212456097179034e-06, + "loss": 0.0965, + "step": 374750 + }, + { + "epoch": 0.84, + "learning_rate": 8.21133755396971e-06, + "loss": 0.0967, + "step": 374760 + }, + { + "epoch": 0.84, + "learning_rate": 8.210219010760386e-06, + "loss": 0.1001, + "step": 374770 + }, + { + "epoch": 0.84, + "learning_rate": 8.209100467551063e-06, + "loss": 0.0986, + "step": 374780 + }, + { + "epoch": 0.84, + "learning_rate": 8.207981924341737e-06, + "loss": 0.0985, + "step": 374790 + }, + { + "epoch": 0.84, + "learning_rate": 8.206863381132413e-06, + "loss": 0.0963, + "step": 374800 + }, + { + "epoch": 0.84, + "learning_rate": 8.20574483792309e-06, + "loss": 0.0985, + "step": 374810 + }, + { + "epoch": 0.84, + "learning_rate": 8.204626294713766e-06, + "loss": 0.097, + "step": 374820 + }, + { + "epoch": 0.84, + "learning_rate": 8.20350775150444e-06, + "loss": 0.0971, + "step": 374830 + }, + { + "epoch": 0.84, + "learning_rate": 8.202389208295117e-06, + "loss": 0.0955, + "step": 374840 + }, + { + "epoch": 0.84, + "learning_rate": 8.201270665085793e-06, + "loss": 0.0996, + "step": 374850 + }, + { + "epoch": 0.84, + "learning_rate": 8.20015212187647e-06, + "loss": 0.0985, + "step": 374860 + }, + { + "epoch": 0.84, + "learning_rate": 8.199033578667144e-06, + "loss": 0.0978, + "step": 374870 + }, + { + "epoch": 0.84, + "learning_rate": 8.19791503545782e-06, + "loss": 0.1016, + "step": 374880 + }, + { + "epoch": 0.84, + "learning_rate": 8.196796492248496e-06, + "loss": 0.1012, + "step": 374890 + }, + { + "epoch": 0.84, + "learning_rate": 8.195677949039172e-06, + "loss": 0.0987, + "step": 374900 + }, + { + "epoch": 0.84, + "learning_rate": 8.194559405829847e-06, + "loss": 0.0984, + "step": 374910 + }, + { + "epoch": 0.84, + "learning_rate": 8.193440862620523e-06, + "loss": 0.096, + "step": 374920 + }, + { + "epoch": 0.84, + "learning_rate": 8.1923223194112e-06, + "loss": 0.0986, + "step": 374930 + }, + { + "epoch": 0.84, + "learning_rate": 8.191203776201876e-06, + "loss": 0.0974, + "step": 374940 + }, + { + "epoch": 0.84, + "learning_rate": 8.19008523299255e-06, + "loss": 0.0968, + "step": 374950 + }, + { + "epoch": 0.84, + "learning_rate": 8.188966689783226e-06, + "loss": 0.0962, + "step": 374960 + }, + { + "epoch": 0.84, + "learning_rate": 8.187848146573903e-06, + "loss": 0.0967, + "step": 374970 + }, + { + "epoch": 0.84, + "learning_rate": 8.186729603364579e-06, + "loss": 0.0932, + "step": 374980 + }, + { + "epoch": 0.84, + "learning_rate": 8.185611060155255e-06, + "loss": 0.0962, + "step": 374990 + }, + { + "epoch": 0.84, + "learning_rate": 8.18449251694593e-06, + "loss": 0.0975, + "step": 375000 + }, + { + "epoch": 0.84, + "learning_rate": 8.183373973736606e-06, + "loss": 0.0976, + "step": 375010 + }, + { + "epoch": 0.84, + "learning_rate": 8.182255430527282e-06, + "loss": 0.0953, + "step": 375020 + }, + { + "epoch": 0.84, + "learning_rate": 8.181136887317957e-06, + "loss": 0.0955, + "step": 375030 + }, + { + "epoch": 0.84, + "learning_rate": 8.180018344108633e-06, + "loss": 0.0993, + "step": 375040 + }, + { + "epoch": 0.84, + "learning_rate": 8.178899800899309e-06, + "loss": 0.0971, + "step": 375050 + }, + { + "epoch": 0.84, + "learning_rate": 8.177781257689984e-06, + "loss": 0.1014, + "step": 375060 + }, + { + "epoch": 0.84, + "learning_rate": 8.176662714480662e-06, + "loss": 0.0979, + "step": 375070 + }, + { + "epoch": 0.84, + "learning_rate": 8.175544171271336e-06, + "loss": 0.0946, + "step": 375080 + }, + { + "epoch": 0.84, + "learning_rate": 8.174425628062012e-06, + "loss": 0.0986, + "step": 375090 + }, + { + "epoch": 0.84, + "learning_rate": 8.173307084852689e-06, + "loss": 0.0955, + "step": 375100 + }, + { + "epoch": 0.84, + "learning_rate": 8.172188541643363e-06, + "loss": 0.0968, + "step": 375110 + }, + { + "epoch": 0.84, + "learning_rate": 8.171181852754972e-06, + "loss": 0.096, + "step": 375120 + }, + { + "epoch": 0.84, + "learning_rate": 8.170063309545648e-06, + "loss": 0.0966, + "step": 375130 + }, + { + "epoch": 0.84, + "learning_rate": 8.168944766336324e-06, + "loss": 0.097, + "step": 375140 + }, + { + "epoch": 0.84, + "learning_rate": 8.167826223126999e-06, + "loss": 0.0939, + "step": 375150 + }, + { + "epoch": 0.84, + "learning_rate": 8.166707679917677e-06, + "loss": 0.0965, + "step": 375160 + }, + { + "epoch": 0.84, + "learning_rate": 8.165589136708351e-06, + "loss": 0.095, + "step": 375170 + }, + { + "epoch": 0.84, + "learning_rate": 8.164470593499026e-06, + "loss": 0.0975, + "step": 375180 + }, + { + "epoch": 0.84, + "learning_rate": 8.163352050289704e-06, + "loss": 0.0951, + "step": 375190 + }, + { + "epoch": 0.84, + "learning_rate": 8.162233507080378e-06, + "loss": 0.0996, + "step": 375200 + }, + { + "epoch": 0.84, + "learning_rate": 8.161114963871055e-06, + "loss": 0.0987, + "step": 375210 + }, + { + "epoch": 0.84, + "learning_rate": 8.159996420661731e-06, + "loss": 0.0951, + "step": 375220 + }, + { + "epoch": 0.84, + "learning_rate": 8.158877877452405e-06, + "loss": 0.0962, + "step": 375230 + }, + { + "epoch": 0.84, + "learning_rate": 8.157759334243083e-06, + "loss": 0.0951, + "step": 375240 + }, + { + "epoch": 0.84, + "learning_rate": 8.156640791033758e-06, + "loss": 0.0952, + "step": 375250 + }, + { + "epoch": 0.84, + "learning_rate": 8.155522247824434e-06, + "loss": 0.0952, + "step": 375260 + }, + { + "epoch": 0.84, + "learning_rate": 8.15440370461511e-06, + "loss": 0.0974, + "step": 375270 + }, + { + "epoch": 0.84, + "learning_rate": 8.153285161405785e-06, + "loss": 0.0973, + "step": 375280 + }, + { + "epoch": 0.84, + "learning_rate": 8.152166618196461e-06, + "loss": 0.102, + "step": 375290 + }, + { + "epoch": 0.84, + "learning_rate": 8.151048074987137e-06, + "loss": 0.1026, + "step": 375300 + }, + { + "epoch": 0.84, + "learning_rate": 8.149929531777812e-06, + "loss": 0.0981, + "step": 375310 + }, + { + "epoch": 0.84, + "learning_rate": 8.14881098856849e-06, + "loss": 0.0948, + "step": 375320 + }, + { + "epoch": 0.84, + "learning_rate": 8.147692445359164e-06, + "loss": 0.0969, + "step": 375330 + }, + { + "epoch": 0.84, + "learning_rate": 8.14657390214984e-06, + "loss": 0.0983, + "step": 375340 + }, + { + "epoch": 0.84, + "learning_rate": 8.145455358940517e-06, + "loss": 0.0963, + "step": 375350 + }, + { + "epoch": 0.84, + "learning_rate": 8.144336815731191e-06, + "loss": 0.096, + "step": 375360 + }, + { + "epoch": 0.84, + "learning_rate": 8.143218272521868e-06, + "loss": 0.0983, + "step": 375370 + }, + { + "epoch": 0.84, + "learning_rate": 8.142099729312544e-06, + "loss": 0.0974, + "step": 375380 + }, + { + "epoch": 0.84, + "learning_rate": 8.14098118610322e-06, + "loss": 0.0961, + "step": 375390 + }, + { + "epoch": 0.84, + "learning_rate": 8.139862642893896e-06, + "loss": 0.0971, + "step": 375400 + }, + { + "epoch": 0.84, + "learning_rate": 8.138744099684571e-06, + "loss": 0.0971, + "step": 375410 + }, + { + "epoch": 0.84, + "learning_rate": 8.137625556475247e-06, + "loss": 0.0983, + "step": 375420 + }, + { + "epoch": 0.84, + "learning_rate": 8.136507013265923e-06, + "loss": 0.0977, + "step": 375430 + }, + { + "epoch": 0.84, + "learning_rate": 8.135388470056598e-06, + "loss": 0.0948, + "step": 375440 + }, + { + "epoch": 0.84, + "learning_rate": 8.134269926847274e-06, + "loss": 0.0976, + "step": 375450 + }, + { + "epoch": 0.84, + "learning_rate": 8.13315138363795e-06, + "loss": 0.0957, + "step": 375460 + }, + { + "epoch": 0.84, + "learning_rate": 8.132032840428627e-06, + "loss": 0.0987, + "step": 375470 + }, + { + "epoch": 0.84, + "learning_rate": 8.130914297219303e-06, + "loss": 0.0989, + "step": 375480 + }, + { + "epoch": 0.84, + "learning_rate": 8.129795754009977e-06, + "loss": 0.0991, + "step": 375490 + }, + { + "epoch": 0.84, + "learning_rate": 8.128677210800654e-06, + "loss": 0.096, + "step": 375500 + }, + { + "epoch": 0.84, + "learning_rate": 8.12755866759133e-06, + "loss": 0.0966, + "step": 375510 + }, + { + "epoch": 0.84, + "learning_rate": 8.126440124382004e-06, + "loss": 0.0966, + "step": 375520 + }, + { + "epoch": 0.84, + "learning_rate": 8.12532158117268e-06, + "loss": 0.0982, + "step": 375530 + }, + { + "epoch": 0.84, + "learning_rate": 8.124203037963357e-06, + "loss": 0.0988, + "step": 375540 + }, + { + "epoch": 0.84, + "learning_rate": 8.123084494754033e-06, + "loss": 0.0965, + "step": 375550 + }, + { + "epoch": 0.84, + "learning_rate": 8.12196595154471e-06, + "loss": 0.0965, + "step": 375560 + }, + { + "epoch": 0.84, + "learning_rate": 8.120847408335384e-06, + "loss": 0.1016, + "step": 375570 + }, + { + "epoch": 0.84, + "learning_rate": 8.11972886512606e-06, + "loss": 0.0963, + "step": 375580 + }, + { + "epoch": 0.84, + "learning_rate": 8.118610321916736e-06, + "loss": 0.0965, + "step": 375590 + }, + { + "epoch": 0.84, + "learning_rate": 8.117491778707413e-06, + "loss": 0.1028, + "step": 375600 + }, + { + "epoch": 0.84, + "learning_rate": 8.116373235498087e-06, + "loss": 0.1016, + "step": 375610 + }, + { + "epoch": 0.84, + "learning_rate": 8.115254692288763e-06, + "loss": 0.0936, + "step": 375620 + }, + { + "epoch": 0.84, + "learning_rate": 8.11413614907944e-06, + "loss": 0.0929, + "step": 375630 + }, + { + "epoch": 0.84, + "learning_rate": 8.113017605870116e-06, + "loss": 0.1008, + "step": 375640 + }, + { + "epoch": 0.84, + "learning_rate": 8.11189906266079e-06, + "loss": 0.0943, + "step": 375650 + }, + { + "epoch": 0.84, + "learning_rate": 8.110780519451467e-06, + "loss": 0.0952, + "step": 375660 + }, + { + "epoch": 0.84, + "learning_rate": 8.109661976242143e-06, + "loss": 0.0947, + "step": 375670 + }, + { + "epoch": 0.84, + "learning_rate": 8.108543433032819e-06, + "loss": 0.0938, + "step": 375680 + }, + { + "epoch": 0.84, + "learning_rate": 8.107424889823494e-06, + "loss": 0.097, + "step": 375690 + }, + { + "epoch": 0.84, + "learning_rate": 8.10630634661417e-06, + "loss": 0.0957, + "step": 375700 + }, + { + "epoch": 0.84, + "learning_rate": 8.105187803404846e-06, + "loss": 0.0949, + "step": 375710 + }, + { + "epoch": 0.84, + "learning_rate": 8.104069260195522e-06, + "loss": 0.1009, + "step": 375720 + }, + { + "epoch": 0.84, + "learning_rate": 8.102950716986198e-06, + "loss": 0.0957, + "step": 375730 + }, + { + "epoch": 0.84, + "learning_rate": 8.101832173776873e-06, + "loss": 0.0966, + "step": 375740 + }, + { + "epoch": 0.84, + "learning_rate": 8.10071363056755e-06, + "loss": 0.0965, + "step": 375750 + }, + { + "epoch": 0.84, + "learning_rate": 8.099595087358225e-06, + "loss": 0.0968, + "step": 375760 + }, + { + "epoch": 0.84, + "learning_rate": 8.0984765441489e-06, + "loss": 0.0941, + "step": 375770 + }, + { + "epoch": 0.84, + "learning_rate": 8.097358000939576e-06, + "loss": 0.0947, + "step": 375780 + }, + { + "epoch": 0.84, + "learning_rate": 8.096239457730252e-06, + "loss": 0.0969, + "step": 375790 + }, + { + "epoch": 0.84, + "learning_rate": 8.095120914520929e-06, + "loss": 0.0971, + "step": 375800 + }, + { + "epoch": 0.84, + "learning_rate": 8.094002371311605e-06, + "loss": 0.0944, + "step": 375810 + }, + { + "epoch": 0.84, + "learning_rate": 8.09288382810228e-06, + "loss": 0.0994, + "step": 375820 + }, + { + "epoch": 0.84, + "learning_rate": 8.091765284892956e-06, + "loss": 0.0948, + "step": 375830 + }, + { + "epoch": 0.84, + "learning_rate": 8.090646741683632e-06, + "loss": 0.1001, + "step": 375840 + }, + { + "epoch": 0.84, + "learning_rate": 8.089528198474306e-06, + "loss": 0.0979, + "step": 375850 + }, + { + "epoch": 0.84, + "learning_rate": 8.088409655264983e-06, + "loss": 0.0966, + "step": 375860 + }, + { + "epoch": 0.84, + "learning_rate": 8.087291112055659e-06, + "loss": 0.1015, + "step": 375870 + }, + { + "epoch": 0.84, + "learning_rate": 8.086172568846335e-06, + "loss": 0.0974, + "step": 375880 + }, + { + "epoch": 0.84, + "learning_rate": 8.085054025637011e-06, + "loss": 0.0985, + "step": 375890 + }, + { + "epoch": 0.84, + "learning_rate": 8.083935482427686e-06, + "loss": 0.0987, + "step": 375900 + }, + { + "epoch": 0.84, + "learning_rate": 8.082816939218362e-06, + "loss": 0.0996, + "step": 375910 + }, + { + "epoch": 0.84, + "learning_rate": 8.081698396009038e-06, + "loss": 0.0974, + "step": 375920 + }, + { + "epoch": 0.84, + "learning_rate": 8.080579852799713e-06, + "loss": 0.0961, + "step": 375930 + }, + { + "epoch": 0.84, + "learning_rate": 8.079461309590391e-06, + "loss": 0.0959, + "step": 375940 + }, + { + "epoch": 0.84, + "learning_rate": 8.078342766381065e-06, + "loss": 0.1015, + "step": 375950 + }, + { + "epoch": 0.84, + "learning_rate": 8.077224223171742e-06, + "loss": 0.0952, + "step": 375960 + }, + { + "epoch": 0.84, + "learning_rate": 8.076105679962418e-06, + "loss": 0.0991, + "step": 375970 + }, + { + "epoch": 0.84, + "learning_rate": 8.074987136753092e-06, + "loss": 0.098, + "step": 375980 + }, + { + "epoch": 0.84, + "learning_rate": 8.073868593543769e-06, + "loss": 0.0955, + "step": 375990 + }, + { + "epoch": 0.84, + "learning_rate": 8.072750050334445e-06, + "loss": 0.0976, + "step": 376000 + }, + { + "epoch": 0.84, + "learning_rate": 8.07163150712512e-06, + "loss": 0.0981, + "step": 376010 + }, + { + "epoch": 0.84, + "learning_rate": 8.070512963915797e-06, + "loss": 0.1008, + "step": 376020 + }, + { + "epoch": 0.84, + "learning_rate": 8.069394420706472e-06, + "loss": 0.0969, + "step": 376030 + }, + { + "epoch": 0.84, + "learning_rate": 8.068275877497148e-06, + "loss": 0.0977, + "step": 376040 + }, + { + "epoch": 0.84, + "learning_rate": 8.067157334287824e-06, + "loss": 0.1005, + "step": 376050 + }, + { + "epoch": 0.84, + "learning_rate": 8.066038791078499e-06, + "loss": 0.0978, + "step": 376060 + }, + { + "epoch": 0.84, + "learning_rate": 8.064920247869175e-06, + "loss": 0.0953, + "step": 376070 + }, + { + "epoch": 0.84, + "learning_rate": 8.063801704659851e-06, + "loss": 0.0937, + "step": 376080 + }, + { + "epoch": 0.84, + "learning_rate": 8.062683161450526e-06, + "loss": 0.0886, + "step": 376090 + }, + { + "epoch": 0.84, + "learning_rate": 8.061564618241204e-06, + "loss": 0.095, + "step": 376100 + }, + { + "epoch": 0.84, + "learning_rate": 8.060446075031878e-06, + "loss": 0.0959, + "step": 376110 + }, + { + "epoch": 0.84, + "learning_rate": 8.059327531822555e-06, + "loss": 0.0932, + "step": 376120 + }, + { + "epoch": 0.84, + "learning_rate": 8.058208988613231e-06, + "loss": 0.0998, + "step": 376130 + }, + { + "epoch": 0.84, + "learning_rate": 8.057090445403905e-06, + "loss": 0.0989, + "step": 376140 + }, + { + "epoch": 0.84, + "learning_rate": 8.055971902194583e-06, + "loss": 0.0997, + "step": 376150 + }, + { + "epoch": 0.84, + "learning_rate": 8.054853358985258e-06, + "loss": 0.1006, + "step": 376160 + }, + { + "epoch": 0.84, + "learning_rate": 8.053734815775932e-06, + "loss": 0.1, + "step": 376170 + }, + { + "epoch": 0.84, + "learning_rate": 8.05261627256661e-06, + "loss": 0.0976, + "step": 376180 + }, + { + "epoch": 0.84, + "learning_rate": 8.051497729357285e-06, + "loss": 0.0967, + "step": 376190 + }, + { + "epoch": 0.84, + "learning_rate": 8.050379186147961e-06, + "loss": 0.0974, + "step": 376200 + }, + { + "epoch": 0.84, + "learning_rate": 8.049260642938637e-06, + "loss": 0.0954, + "step": 376210 + }, + { + "epoch": 0.84, + "learning_rate": 8.048142099729312e-06, + "loss": 0.0985, + "step": 376220 + }, + { + "epoch": 0.84, + "learning_rate": 8.04702355651999e-06, + "loss": 0.0994, + "step": 376230 + }, + { + "epoch": 0.84, + "learning_rate": 8.045905013310664e-06, + "loss": 0.1001, + "step": 376240 + }, + { + "epoch": 0.84, + "learning_rate": 8.04478647010134e-06, + "loss": 0.0954, + "step": 376250 + }, + { + "epoch": 0.84, + "learning_rate": 8.043667926892017e-06, + "loss": 0.097, + "step": 376260 + }, + { + "epoch": 0.84, + "learning_rate": 8.042549383682691e-06, + "loss": 0.0941, + "step": 376270 + }, + { + "epoch": 0.84, + "learning_rate": 8.04143084047337e-06, + "loss": 0.0956, + "step": 376280 + }, + { + "epoch": 0.84, + "learning_rate": 8.040312297264044e-06, + "loss": 0.0979, + "step": 376290 + }, + { + "epoch": 0.84, + "learning_rate": 8.039193754054718e-06, + "loss": 0.1004, + "step": 376300 + }, + { + "epoch": 0.84, + "learning_rate": 8.038075210845396e-06, + "loss": 0.1009, + "step": 376310 + }, + { + "epoch": 0.84, + "learning_rate": 8.03695666763607e-06, + "loss": 0.0948, + "step": 376320 + }, + { + "epoch": 0.84, + "learning_rate": 8.035838124426747e-06, + "loss": 0.0948, + "step": 376330 + }, + { + "epoch": 0.84, + "learning_rate": 8.034719581217423e-06, + "loss": 0.0996, + "step": 376340 + }, + { + "epoch": 0.84, + "learning_rate": 8.033601038008098e-06, + "loss": 0.0966, + "step": 376350 + }, + { + "epoch": 0.84, + "learning_rate": 8.032482494798776e-06, + "loss": 0.0992, + "step": 376360 + }, + { + "epoch": 0.84, + "learning_rate": 8.03136395158945e-06, + "loss": 0.096, + "step": 376370 + }, + { + "epoch": 0.84, + "learning_rate": 8.030245408380125e-06, + "loss": 0.0953, + "step": 376380 + }, + { + "epoch": 0.84, + "learning_rate": 8.029126865170803e-06, + "loss": 0.0974, + "step": 376390 + }, + { + "epoch": 0.84, + "learning_rate": 8.028008321961477e-06, + "loss": 0.0997, + "step": 376400 + }, + { + "epoch": 0.84, + "learning_rate": 8.026889778752154e-06, + "loss": 0.0977, + "step": 376410 + }, + { + "epoch": 0.84, + "learning_rate": 8.02577123554283e-06, + "loss": 0.1005, + "step": 376420 + }, + { + "epoch": 0.84, + "learning_rate": 8.024652692333504e-06, + "loss": 0.0989, + "step": 376430 + }, + { + "epoch": 0.84, + "learning_rate": 8.023534149124182e-06, + "loss": 0.0942, + "step": 376440 + }, + { + "epoch": 0.84, + "learning_rate": 8.022415605914857e-06, + "loss": 0.0979, + "step": 376450 + }, + { + "epoch": 0.84, + "learning_rate": 8.021297062705533e-06, + "loss": 0.0995, + "step": 376460 + }, + { + "epoch": 0.84, + "learning_rate": 8.02017851949621e-06, + "loss": 0.0942, + "step": 376470 + }, + { + "epoch": 0.84, + "learning_rate": 8.019059976286884e-06, + "loss": 0.1, + "step": 376480 + }, + { + "epoch": 0.84, + "learning_rate": 8.01794143307756e-06, + "loss": 0.099, + "step": 376490 + }, + { + "epoch": 0.84, + "learning_rate": 8.016822889868236e-06, + "loss": 0.0975, + "step": 376500 + }, + { + "epoch": 0.84, + "learning_rate": 8.01570434665891e-06, + "loss": 0.0964, + "step": 376510 + }, + { + "epoch": 0.84, + "learning_rate": 8.014585803449589e-06, + "loss": 0.0978, + "step": 376520 + }, + { + "epoch": 0.84, + "learning_rate": 8.013467260240263e-06, + "loss": 0.0989, + "step": 376530 + }, + { + "epoch": 0.84, + "learning_rate": 8.01234871703094e-06, + "loss": 0.0974, + "step": 376540 + }, + { + "epoch": 0.84, + "learning_rate": 8.011230173821616e-06, + "loss": 0.0941, + "step": 376550 + }, + { + "epoch": 0.84, + "learning_rate": 8.01011163061229e-06, + "loss": 0.0975, + "step": 376560 + }, + { + "epoch": 0.84, + "learning_rate": 8.008993087402967e-06, + "loss": 0.0975, + "step": 376570 + }, + { + "epoch": 0.84, + "learning_rate": 8.007874544193643e-06, + "loss": 0.1001, + "step": 376580 + }, + { + "epoch": 0.84, + "learning_rate": 8.006756000984319e-06, + "loss": 0.097, + "step": 376590 + }, + { + "epoch": 0.84, + "learning_rate": 8.005637457774995e-06, + "loss": 0.0969, + "step": 376600 + }, + { + "epoch": 0.84, + "learning_rate": 8.00451891456567e-06, + "loss": 0.1, + "step": 376610 + }, + { + "epoch": 0.84, + "learning_rate": 8.003400371356346e-06, + "loss": 0.0962, + "step": 376620 + }, + { + "epoch": 0.84, + "learning_rate": 8.002281828147022e-06, + "loss": 0.1026, + "step": 376630 + }, + { + "epoch": 0.84, + "learning_rate": 8.001163284937697e-06, + "loss": 0.0958, + "step": 376640 + }, + { + "epoch": 0.84, + "learning_rate": 8.000044741728373e-06, + "loss": 0.0984, + "step": 376650 + }, + { + "epoch": 0.84, + "learning_rate": 7.99892619851905e-06, + "loss": 0.0975, + "step": 376660 + }, + { + "epoch": 0.84, + "learning_rate": 7.997807655309725e-06, + "loss": 0.0993, + "step": 376670 + }, + { + "epoch": 0.84, + "learning_rate": 7.996689112100402e-06, + "loss": 0.1006, + "step": 376680 + }, + { + "epoch": 0.84, + "learning_rate": 7.995570568891076e-06, + "loss": 0.0973, + "step": 376690 + }, + { + "epoch": 0.84, + "learning_rate": 7.994452025681752e-06, + "loss": 0.0991, + "step": 376700 + }, + { + "epoch": 0.84, + "learning_rate": 7.993333482472429e-06, + "loss": 0.0966, + "step": 376710 + }, + { + "epoch": 0.84, + "learning_rate": 7.992214939263103e-06, + "loss": 0.0934, + "step": 376720 + }, + { + "epoch": 0.84, + "learning_rate": 7.99109639605378e-06, + "loss": 0.0956, + "step": 376730 + }, + { + "epoch": 0.84, + "learning_rate": 7.989977852844456e-06, + "loss": 0.1014, + "step": 376740 + }, + { + "epoch": 0.84, + "learning_rate": 7.988859309635132e-06, + "loss": 0.0945, + "step": 376750 + }, + { + "epoch": 0.84, + "learning_rate": 7.987740766425808e-06, + "loss": 0.0959, + "step": 376760 + }, + { + "epoch": 0.84, + "learning_rate": 7.986622223216483e-06, + "loss": 0.0962, + "step": 376770 + }, + { + "epoch": 0.84, + "learning_rate": 7.985503680007159e-06, + "loss": 0.0981, + "step": 376780 + }, + { + "epoch": 0.84, + "learning_rate": 7.984385136797835e-06, + "loss": 0.0968, + "step": 376790 + }, + { + "epoch": 0.84, + "learning_rate": 7.983266593588511e-06, + "loss": 0.101, + "step": 376800 + }, + { + "epoch": 0.84, + "learning_rate": 7.982148050379186e-06, + "loss": 0.0981, + "step": 376810 + }, + { + "epoch": 0.84, + "learning_rate": 7.981029507169862e-06, + "loss": 0.0969, + "step": 376820 + }, + { + "epoch": 0.84, + "learning_rate": 7.979910963960538e-06, + "loss": 0.0976, + "step": 376830 + }, + { + "epoch": 0.84, + "learning_rate": 7.978792420751215e-06, + "loss": 0.0976, + "step": 376840 + }, + { + "epoch": 0.84, + "learning_rate": 7.97767387754189e-06, + "loss": 0.1005, + "step": 376850 + }, + { + "epoch": 0.84, + "learning_rate": 7.976555334332565e-06, + "loss": 0.0945, + "step": 376860 + }, + { + "epoch": 0.84, + "learning_rate": 7.975436791123242e-06, + "loss": 0.1014, + "step": 376870 + }, + { + "epoch": 0.84, + "learning_rate": 7.974318247913918e-06, + "loss": 0.0945, + "step": 376880 + }, + { + "epoch": 0.84, + "learning_rate": 7.973199704704592e-06, + "loss": 0.0992, + "step": 376890 + }, + { + "epoch": 0.84, + "learning_rate": 7.972081161495269e-06, + "loss": 0.0964, + "step": 376900 + }, + { + "epoch": 0.84, + "learning_rate": 7.970962618285945e-06, + "loss": 0.0992, + "step": 376910 + }, + { + "epoch": 0.84, + "learning_rate": 7.969844075076621e-06, + "loss": 0.0939, + "step": 376920 + }, + { + "epoch": 0.84, + "learning_rate": 7.968725531867297e-06, + "loss": 0.1016, + "step": 376930 + }, + { + "epoch": 0.84, + "learning_rate": 7.967606988657972e-06, + "loss": 0.0952, + "step": 376940 + }, + { + "epoch": 0.84, + "learning_rate": 7.966488445448648e-06, + "loss": 0.0994, + "step": 376950 + }, + { + "epoch": 0.84, + "learning_rate": 7.965369902239324e-06, + "loss": 0.0992, + "step": 376960 + }, + { + "epoch": 0.84, + "learning_rate": 7.964251359029999e-06, + "loss": 0.0977, + "step": 376970 + }, + { + "epoch": 0.84, + "learning_rate": 7.963132815820675e-06, + "loss": 0.0973, + "step": 376980 + }, + { + "epoch": 0.84, + "learning_rate": 7.962014272611351e-06, + "loss": 0.0979, + "step": 376990 + }, + { + "epoch": 0.84, + "learning_rate": 7.960895729402028e-06, + "loss": 0.0958, + "step": 377000 + }, + { + "epoch": 0.84, + "learning_rate": 7.959777186192704e-06, + "loss": 0.0977, + "step": 377010 + }, + { + "epoch": 0.84, + "learning_rate": 7.958658642983378e-06, + "loss": 0.0991, + "step": 377020 + }, + { + "epoch": 0.84, + "learning_rate": 7.957540099774055e-06, + "loss": 0.0929, + "step": 377030 + }, + { + "epoch": 0.84, + "learning_rate": 7.956421556564731e-06, + "loss": 0.0971, + "step": 377040 + }, + { + "epoch": 0.84, + "learning_rate": 7.955303013355405e-06, + "loss": 0.0996, + "step": 377050 + }, + { + "epoch": 0.84, + "learning_rate": 7.954184470146082e-06, + "loss": 0.0962, + "step": 377060 + }, + { + "epoch": 0.84, + "learning_rate": 7.953065926936758e-06, + "loss": 0.0972, + "step": 377070 + }, + { + "epoch": 0.84, + "learning_rate": 7.951947383727434e-06, + "loss": 0.0943, + "step": 377080 + }, + { + "epoch": 0.84, + "learning_rate": 7.95082884051811e-06, + "loss": 0.0966, + "step": 377090 + }, + { + "epoch": 0.84, + "learning_rate": 7.949710297308785e-06, + "loss": 0.1009, + "step": 377100 + }, + { + "epoch": 0.84, + "learning_rate": 7.948591754099461e-06, + "loss": 0.0933, + "step": 377110 + }, + { + "epoch": 0.84, + "learning_rate": 7.947473210890137e-06, + "loss": 0.0975, + "step": 377120 + }, + { + "epoch": 0.84, + "learning_rate": 7.946354667680812e-06, + "loss": 0.0955, + "step": 377130 + }, + { + "epoch": 0.84, + "learning_rate": 7.94523612447149e-06, + "loss": 0.0991, + "step": 377140 + }, + { + "epoch": 0.84, + "learning_rate": 7.944117581262164e-06, + "loss": 0.0998, + "step": 377150 + }, + { + "epoch": 0.84, + "learning_rate": 7.94299903805284e-06, + "loss": 0.0932, + "step": 377160 + }, + { + "epoch": 0.84, + "learning_rate": 7.941880494843517e-06, + "loss": 0.1004, + "step": 377170 + }, + { + "epoch": 0.84, + "learning_rate": 7.940873805955126e-06, + "loss": 0.0981, + "step": 377180 + }, + { + "epoch": 0.84, + "learning_rate": 7.9397552627458e-06, + "loss": 0.0951, + "step": 377190 + }, + { + "epoch": 0.84, + "learning_rate": 7.938636719536476e-06, + "loss": 0.0981, + "step": 377200 + }, + { + "epoch": 0.84, + "learning_rate": 7.937518176327153e-06, + "loss": 0.0936, + "step": 377210 + }, + { + "epoch": 0.84, + "learning_rate": 7.936399633117827e-06, + "loss": 0.1026, + "step": 377220 + }, + { + "epoch": 0.84, + "learning_rate": 7.935281089908503e-06, + "loss": 0.0958, + "step": 377230 + }, + { + "epoch": 0.84, + "learning_rate": 7.93416254669918e-06, + "loss": 0.0993, + "step": 377240 + }, + { + "epoch": 0.84, + "learning_rate": 7.933044003489854e-06, + "loss": 0.1003, + "step": 377250 + }, + { + "epoch": 0.84, + "learning_rate": 7.931925460280532e-06, + "loss": 0.0972, + "step": 377260 + }, + { + "epoch": 0.84, + "learning_rate": 7.930806917071207e-06, + "loss": 0.0992, + "step": 377270 + }, + { + "epoch": 0.84, + "learning_rate": 7.929688373861883e-06, + "loss": 0.0996, + "step": 377280 + }, + { + "epoch": 0.84, + "learning_rate": 7.928569830652559e-06, + "loss": 0.0968, + "step": 377290 + }, + { + "epoch": 0.84, + "learning_rate": 7.927451287443234e-06, + "loss": 0.097, + "step": 377300 + }, + { + "epoch": 0.84, + "learning_rate": 7.926332744233912e-06, + "loss": 0.0999, + "step": 377310 + }, + { + "epoch": 0.84, + "learning_rate": 7.925214201024586e-06, + "loss": 0.0979, + "step": 377320 + }, + { + "epoch": 0.84, + "learning_rate": 7.92409565781526e-06, + "loss": 0.1008, + "step": 377330 + }, + { + "epoch": 0.84, + "learning_rate": 7.922977114605939e-06, + "loss": 0.0961, + "step": 377340 + }, + { + "epoch": 0.84, + "learning_rate": 7.921858571396613e-06, + "loss": 0.0955, + "step": 377350 + }, + { + "epoch": 0.84, + "learning_rate": 7.92074002818729e-06, + "loss": 0.0975, + "step": 377360 + }, + { + "epoch": 0.84, + "learning_rate": 7.919621484977966e-06, + "loss": 0.0966, + "step": 377370 + }, + { + "epoch": 0.84, + "learning_rate": 7.91850294176864e-06, + "loss": 0.1004, + "step": 377380 + }, + { + "epoch": 0.84, + "learning_rate": 7.917384398559318e-06, + "loss": 0.0961, + "step": 377390 + }, + { + "epoch": 0.84, + "learning_rate": 7.916265855349993e-06, + "loss": 0.0992, + "step": 377400 + }, + { + "epoch": 0.84, + "learning_rate": 7.915147312140669e-06, + "loss": 0.0982, + "step": 377410 + }, + { + "epoch": 0.84, + "learning_rate": 7.914028768931345e-06, + "loss": 0.0972, + "step": 377420 + }, + { + "epoch": 0.84, + "learning_rate": 7.91291022572202e-06, + "loss": 0.0941, + "step": 377430 + }, + { + "epoch": 0.84, + "learning_rate": 7.911791682512696e-06, + "loss": 0.0994, + "step": 377440 + }, + { + "epoch": 0.84, + "learning_rate": 7.910673139303372e-06, + "loss": 0.0968, + "step": 377450 + }, + { + "epoch": 0.84, + "learning_rate": 7.909554596094047e-06, + "loss": 0.0972, + "step": 377460 + }, + { + "epoch": 0.84, + "learning_rate": 7.908436052884725e-06, + "loss": 0.0962, + "step": 377470 + }, + { + "epoch": 0.84, + "learning_rate": 7.907317509675399e-06, + "loss": 0.0961, + "step": 377480 + }, + { + "epoch": 0.84, + "learning_rate": 7.906198966466075e-06, + "loss": 0.0957, + "step": 377490 + }, + { + "epoch": 0.84, + "learning_rate": 7.905080423256752e-06, + "loss": 0.097, + "step": 377500 + }, + { + "epoch": 0.84, + "learning_rate": 7.903961880047426e-06, + "loss": 0.0947, + "step": 377510 + }, + { + "epoch": 0.84, + "learning_rate": 7.902843336838102e-06, + "loss": 0.098, + "step": 377520 + }, + { + "epoch": 0.84, + "learning_rate": 7.901724793628779e-06, + "loss": 0.1004, + "step": 377530 + }, + { + "epoch": 0.84, + "learning_rate": 7.900606250419453e-06, + "loss": 0.0943, + "step": 377540 + }, + { + "epoch": 0.84, + "learning_rate": 7.899487707210131e-06, + "loss": 0.1021, + "step": 377550 + }, + { + "epoch": 0.84, + "learning_rate": 7.898369164000806e-06, + "loss": 0.0974, + "step": 377560 + }, + { + "epoch": 0.84, + "learning_rate": 7.897250620791482e-06, + "loss": 0.0962, + "step": 377570 + }, + { + "epoch": 0.84, + "learning_rate": 7.896132077582158e-06, + "loss": 0.0928, + "step": 377580 + }, + { + "epoch": 0.84, + "learning_rate": 7.895013534372833e-06, + "loss": 0.0998, + "step": 377590 + }, + { + "epoch": 0.84, + "learning_rate": 7.893894991163509e-06, + "loss": 0.1, + "step": 377600 + }, + { + "epoch": 0.84, + "learning_rate": 7.892776447954185e-06, + "loss": 0.0973, + "step": 377610 + }, + { + "epoch": 0.84, + "learning_rate": 7.891657904744861e-06, + "loss": 0.0961, + "step": 377620 + }, + { + "epoch": 0.84, + "learning_rate": 7.890539361535537e-06, + "loss": 0.0978, + "step": 377630 + }, + { + "epoch": 0.84, + "learning_rate": 7.889420818326212e-06, + "loss": 0.097, + "step": 377640 + }, + { + "epoch": 0.84, + "learning_rate": 7.888302275116888e-06, + "loss": 0.0983, + "step": 377650 + }, + { + "epoch": 0.84, + "learning_rate": 7.887183731907564e-06, + "loss": 0.0922, + "step": 377660 + }, + { + "epoch": 0.84, + "learning_rate": 7.886065188698239e-06, + "loss": 0.0974, + "step": 377670 + }, + { + "epoch": 0.84, + "learning_rate": 7.884946645488915e-06, + "loss": 0.0948, + "step": 377680 + }, + { + "epoch": 0.84, + "learning_rate": 7.883828102279591e-06, + "loss": 0.094, + "step": 377690 + }, + { + "epoch": 0.84, + "learning_rate": 7.882709559070268e-06, + "loss": 0.0948, + "step": 377700 + }, + { + "epoch": 0.84, + "learning_rate": 7.881591015860942e-06, + "loss": 0.0982, + "step": 377710 + }, + { + "epoch": 0.84, + "learning_rate": 7.880472472651618e-06, + "loss": 0.0959, + "step": 377720 + }, + { + "epoch": 0.84, + "learning_rate": 7.879353929442295e-06, + "loss": 0.0934, + "step": 377730 + }, + { + "epoch": 0.84, + "learning_rate": 7.878235386232971e-06, + "loss": 0.0954, + "step": 377740 + }, + { + "epoch": 0.84, + "learning_rate": 7.877116843023647e-06, + "loss": 0.0964, + "step": 377750 + }, + { + "epoch": 0.84, + "learning_rate": 7.875998299814322e-06, + "loss": 0.0954, + "step": 377760 + }, + { + "epoch": 0.84, + "learning_rate": 7.874879756604998e-06, + "loss": 0.1015, + "step": 377770 + }, + { + "epoch": 0.84, + "learning_rate": 7.873761213395674e-06, + "loss": 0.0928, + "step": 377780 + }, + { + "epoch": 0.84, + "learning_rate": 7.872642670186349e-06, + "loss": 0.0974, + "step": 377790 + }, + { + "epoch": 0.84, + "learning_rate": 7.871524126977025e-06, + "loss": 0.0979, + "step": 377800 + }, + { + "epoch": 0.84, + "learning_rate": 7.870405583767701e-06, + "loss": 0.1015, + "step": 377810 + }, + { + "epoch": 0.84, + "learning_rate": 7.869287040558377e-06, + "loss": 0.0951, + "step": 377820 + }, + { + "epoch": 0.84, + "learning_rate": 7.868168497349054e-06, + "loss": 0.0972, + "step": 377830 + }, + { + "epoch": 0.84, + "learning_rate": 7.867049954139728e-06, + "loss": 0.099, + "step": 377840 + }, + { + "epoch": 0.84, + "learning_rate": 7.865931410930404e-06, + "loss": 0.0953, + "step": 377850 + }, + { + "epoch": 0.84, + "learning_rate": 7.86481286772108e-06, + "loss": 0.0964, + "step": 377860 + }, + { + "epoch": 0.84, + "learning_rate": 7.863694324511755e-06, + "loss": 0.0962, + "step": 377870 + }, + { + "epoch": 0.84, + "learning_rate": 7.862575781302431e-06, + "loss": 0.0974, + "step": 377880 + }, + { + "epoch": 0.84, + "learning_rate": 7.861457238093108e-06, + "loss": 0.0998, + "step": 377890 + }, + { + "epoch": 0.84, + "learning_rate": 7.860338694883784e-06, + "loss": 0.1006, + "step": 377900 + }, + { + "epoch": 0.84, + "learning_rate": 7.85922015167446e-06, + "loss": 0.1012, + "step": 377910 + }, + { + "epoch": 0.84, + "learning_rate": 7.858101608465135e-06, + "loss": 0.0998, + "step": 377920 + }, + { + "epoch": 0.84, + "learning_rate": 7.856983065255811e-06, + "loss": 0.09, + "step": 377930 + }, + { + "epoch": 0.84, + "learning_rate": 7.855864522046487e-06, + "loss": 0.0925, + "step": 377940 + }, + { + "epoch": 0.84, + "learning_rate": 7.854745978837162e-06, + "loss": 0.1022, + "step": 377950 + }, + { + "epoch": 0.84, + "learning_rate": 7.85362743562784e-06, + "loss": 0.0991, + "step": 377960 + }, + { + "epoch": 0.84, + "learning_rate": 7.852508892418514e-06, + "loss": 0.0982, + "step": 377970 + }, + { + "epoch": 0.84, + "learning_rate": 7.85139034920919e-06, + "loss": 0.0965, + "step": 377980 + }, + { + "epoch": 0.84, + "learning_rate": 7.850271805999867e-06, + "loss": 0.0965, + "step": 377990 + }, + { + "epoch": 0.84, + "learning_rate": 7.849153262790541e-06, + "loss": 0.0965, + "step": 378000 + }, + { + "epoch": 0.84, + "learning_rate": 7.848034719581217e-06, + "loss": 0.0963, + "step": 378010 + }, + { + "epoch": 0.84, + "learning_rate": 7.846916176371894e-06, + "loss": 0.1022, + "step": 378020 + }, + { + "epoch": 0.84, + "learning_rate": 7.845797633162568e-06, + "loss": 0.0971, + "step": 378030 + }, + { + "epoch": 0.84, + "learning_rate": 7.844679089953246e-06, + "loss": 0.0979, + "step": 378040 + }, + { + "epoch": 0.84, + "learning_rate": 7.84356054674392e-06, + "loss": 0.0965, + "step": 378050 + }, + { + "epoch": 0.84, + "learning_rate": 7.842442003534597e-06, + "loss": 0.0965, + "step": 378060 + }, + { + "epoch": 0.84, + "learning_rate": 7.841323460325273e-06, + "loss": 0.0961, + "step": 378070 + }, + { + "epoch": 0.84, + "learning_rate": 7.840204917115948e-06, + "loss": 0.0959, + "step": 378080 + }, + { + "epoch": 0.84, + "learning_rate": 7.839086373906626e-06, + "loss": 0.0927, + "step": 378090 + }, + { + "epoch": 0.84, + "learning_rate": 7.8379678306973e-06, + "loss": 0.0992, + "step": 378100 + }, + { + "epoch": 0.84, + "learning_rate": 7.836849287487975e-06, + "loss": 0.0961, + "step": 378110 + }, + { + "epoch": 0.84, + "learning_rate": 7.835730744278653e-06, + "loss": 0.0994, + "step": 378120 + }, + { + "epoch": 0.84, + "learning_rate": 7.834612201069327e-06, + "loss": 0.1016, + "step": 378130 + }, + { + "epoch": 0.84, + "learning_rate": 7.833493657860003e-06, + "loss": 0.0979, + "step": 378140 + }, + { + "epoch": 0.84, + "learning_rate": 7.83237511465068e-06, + "loss": 0.0992, + "step": 378150 + }, + { + "epoch": 0.84, + "learning_rate": 7.831256571441354e-06, + "loss": 0.0958, + "step": 378160 + }, + { + "epoch": 0.84, + "learning_rate": 7.830138028232032e-06, + "loss": 0.0972, + "step": 378170 + }, + { + "epoch": 0.84, + "learning_rate": 7.829019485022707e-06, + "loss": 0.0971, + "step": 378180 + }, + { + "epoch": 0.84, + "learning_rate": 7.827900941813381e-06, + "loss": 0.0951, + "step": 378190 + }, + { + "epoch": 0.84, + "learning_rate": 7.826782398604059e-06, + "loss": 0.1001, + "step": 378200 + }, + { + "epoch": 0.84, + "learning_rate": 7.825663855394734e-06, + "loss": 0.0952, + "step": 378210 + }, + { + "epoch": 0.84, + "learning_rate": 7.82454531218541e-06, + "loss": 0.0976, + "step": 378220 + }, + { + "epoch": 0.84, + "learning_rate": 7.823426768976086e-06, + "loss": 0.0942, + "step": 378230 + }, + { + "epoch": 0.84, + "learning_rate": 7.82230822576676e-06, + "loss": 0.0943, + "step": 378240 + }, + { + "epoch": 0.84, + "learning_rate": 7.821189682557439e-06, + "loss": 0.099, + "step": 378250 + }, + { + "epoch": 0.84, + "learning_rate": 7.820071139348113e-06, + "loss": 0.0997, + "step": 378260 + }, + { + "epoch": 0.84, + "learning_rate": 7.81895259613879e-06, + "loss": 0.0978, + "step": 378270 + }, + { + "epoch": 0.84, + "learning_rate": 7.817834052929466e-06, + "loss": 0.1022, + "step": 378280 + }, + { + "epoch": 0.84, + "learning_rate": 7.81671550972014e-06, + "loss": 0.0947, + "step": 378290 + }, + { + "epoch": 0.84, + "learning_rate": 7.815596966510818e-06, + "loss": 0.0949, + "step": 378300 + }, + { + "epoch": 0.84, + "learning_rate": 7.814478423301493e-06, + "loss": 0.0977, + "step": 378310 + }, + { + "epoch": 0.84, + "learning_rate": 7.813359880092167e-06, + "loss": 0.1007, + "step": 378320 + }, + { + "epoch": 0.84, + "learning_rate": 7.812241336882845e-06, + "loss": 0.0949, + "step": 378330 + }, + { + "epoch": 0.84, + "learning_rate": 7.81112279367352e-06, + "loss": 0.095, + "step": 378340 + }, + { + "epoch": 0.84, + "learning_rate": 7.810004250464196e-06, + "loss": 0.1021, + "step": 378350 + }, + { + "epoch": 0.84, + "learning_rate": 7.808885707254872e-06, + "loss": 0.0935, + "step": 378360 + }, + { + "epoch": 0.84, + "learning_rate": 7.807767164045547e-06, + "loss": 0.0967, + "step": 378370 + }, + { + "epoch": 0.84, + "learning_rate": 7.806648620836225e-06, + "loss": 0.0977, + "step": 378380 + }, + { + "epoch": 0.84, + "learning_rate": 7.805530077626899e-06, + "loss": 0.0982, + "step": 378390 + }, + { + "epoch": 0.84, + "learning_rate": 7.804411534417575e-06, + "loss": 0.0982, + "step": 378400 + }, + { + "epoch": 0.84, + "learning_rate": 7.803292991208252e-06, + "loss": 0.0987, + "step": 378410 + }, + { + "epoch": 0.84, + "learning_rate": 7.802174447998926e-06, + "loss": 0.0997, + "step": 378420 + }, + { + "epoch": 0.84, + "learning_rate": 7.801055904789602e-06, + "loss": 0.1025, + "step": 378430 + }, + { + "epoch": 0.84, + "learning_rate": 7.799937361580279e-06, + "loss": 0.0985, + "step": 378440 + }, + { + "epoch": 0.84, + "learning_rate": 7.798818818370953e-06, + "loss": 0.0961, + "step": 378450 + }, + { + "epoch": 0.84, + "learning_rate": 7.797700275161631e-06, + "loss": 0.1023, + "step": 378460 + }, + { + "epoch": 0.84, + "learning_rate": 7.796581731952306e-06, + "loss": 0.1008, + "step": 378470 + }, + { + "epoch": 0.84, + "learning_rate": 7.795463188742982e-06, + "loss": 0.0969, + "step": 378480 + }, + { + "epoch": 0.84, + "learning_rate": 7.794344645533658e-06, + "loss": 0.0978, + "step": 378490 + }, + { + "epoch": 0.84, + "learning_rate": 7.793226102324333e-06, + "loss": 0.0943, + "step": 378500 + }, + { + "epoch": 0.84, + "learning_rate": 7.792107559115009e-06, + "loss": 0.0988, + "step": 378510 + }, + { + "epoch": 0.84, + "learning_rate": 7.790989015905685e-06, + "loss": 0.0933, + "step": 378520 + }, + { + "epoch": 0.84, + "learning_rate": 7.78987047269636e-06, + "loss": 0.0932, + "step": 378530 + }, + { + "epoch": 0.84, + "learning_rate": 7.788751929487037e-06, + "loss": 0.0978, + "step": 378540 + }, + { + "epoch": 0.84, + "learning_rate": 7.787633386277712e-06, + "loss": 0.0925, + "step": 378550 + }, + { + "epoch": 0.84, + "learning_rate": 7.786514843068388e-06, + "loss": 0.0933, + "step": 378560 + }, + { + "epoch": 0.85, + "learning_rate": 7.785396299859064e-06, + "loss": 0.0944, + "step": 378570 + }, + { + "epoch": 0.85, + "learning_rate": 7.784277756649739e-06, + "loss": 0.0969, + "step": 378580 + }, + { + "epoch": 0.85, + "learning_rate": 7.783159213440415e-06, + "loss": 0.1022, + "step": 378590 + }, + { + "epoch": 0.85, + "learning_rate": 7.782040670231091e-06, + "loss": 0.098, + "step": 378600 + }, + { + "epoch": 0.85, + "learning_rate": 7.780922127021768e-06, + "loss": 0.0966, + "step": 378610 + }, + { + "epoch": 0.85, + "learning_rate": 7.779803583812444e-06, + "loss": 0.0996, + "step": 378620 + }, + { + "epoch": 0.85, + "learning_rate": 7.778685040603118e-06, + "loss": 0.0945, + "step": 378630 + }, + { + "epoch": 0.85, + "learning_rate": 7.777566497393795e-06, + "loss": 0.0959, + "step": 378640 + }, + { + "epoch": 0.85, + "learning_rate": 7.776447954184471e-06, + "loss": 0.0943, + "step": 378650 + }, + { + "epoch": 0.85, + "learning_rate": 7.775329410975145e-06, + "loss": 0.0973, + "step": 378660 + }, + { + "epoch": 0.85, + "learning_rate": 7.774210867765822e-06, + "loss": 0.0977, + "step": 378670 + }, + { + "epoch": 0.85, + "learning_rate": 7.773092324556498e-06, + "loss": 0.0974, + "step": 378680 + }, + { + "epoch": 0.85, + "learning_rate": 7.771973781347174e-06, + "loss": 0.1008, + "step": 378690 + }, + { + "epoch": 0.85, + "learning_rate": 7.77085523813785e-06, + "loss": 0.0944, + "step": 378700 + }, + { + "epoch": 0.85, + "learning_rate": 7.769736694928525e-06, + "loss": 0.0966, + "step": 378710 + }, + { + "epoch": 0.85, + "learning_rate": 7.768618151719201e-06, + "loss": 0.0962, + "step": 378720 + }, + { + "epoch": 0.85, + "learning_rate": 7.767499608509877e-06, + "loss": 0.0968, + "step": 378730 + }, + { + "epoch": 0.85, + "learning_rate": 7.766381065300552e-06, + "loss": 0.0999, + "step": 378740 + }, + { + "epoch": 0.85, + "learning_rate": 7.765262522091228e-06, + "loss": 0.0967, + "step": 378750 + }, + { + "epoch": 0.85, + "learning_rate": 7.764143978881904e-06, + "loss": 0.0988, + "step": 378760 + }, + { + "epoch": 0.85, + "learning_rate": 7.76302543567258e-06, + "loss": 0.0986, + "step": 378770 + }, + { + "epoch": 0.85, + "learning_rate": 7.761906892463257e-06, + "loss": 0.0955, + "step": 378780 + }, + { + "epoch": 0.85, + "learning_rate": 7.760788349253931e-06, + "loss": 0.0952, + "step": 378790 + }, + { + "epoch": 0.85, + "learning_rate": 7.759669806044608e-06, + "loss": 0.0952, + "step": 378800 + }, + { + "epoch": 0.85, + "learning_rate": 7.758551262835284e-06, + "loss": 0.0997, + "step": 378810 + }, + { + "epoch": 0.85, + "learning_rate": 7.75743271962596e-06, + "loss": 0.0919, + "step": 378820 + }, + { + "epoch": 0.85, + "learning_rate": 7.756314176416635e-06, + "loss": 0.0983, + "step": 378830 + }, + { + "epoch": 0.85, + "learning_rate": 7.755195633207311e-06, + "loss": 0.0958, + "step": 378840 + }, + { + "epoch": 0.85, + "learning_rate": 7.754077089997987e-06, + "loss": 0.0985, + "step": 378850 + }, + { + "epoch": 0.85, + "learning_rate": 7.752958546788663e-06, + "loss": 0.097, + "step": 378860 + }, + { + "epoch": 0.85, + "learning_rate": 7.751840003579338e-06, + "loss": 0.0925, + "step": 378870 + }, + { + "epoch": 0.85, + "learning_rate": 7.750721460370014e-06, + "loss": 0.0952, + "step": 378880 + }, + { + "epoch": 0.85, + "learning_rate": 7.74960291716069e-06, + "loss": 0.0946, + "step": 378890 + }, + { + "epoch": 0.85, + "learning_rate": 7.748484373951367e-06, + "loss": 0.0966, + "step": 378900 + }, + { + "epoch": 0.85, + "learning_rate": 7.747365830742041e-06, + "loss": 0.094, + "step": 378910 + }, + { + "epoch": 0.85, + "learning_rate": 7.746247287532717e-06, + "loss": 0.0967, + "step": 378920 + }, + { + "epoch": 0.85, + "learning_rate": 7.745128744323394e-06, + "loss": 0.0957, + "step": 378930 + }, + { + "epoch": 0.85, + "learning_rate": 7.74401020111407e-06, + "loss": 0.0981, + "step": 378940 + }, + { + "epoch": 0.85, + "learning_rate": 7.742891657904746e-06, + "loss": 0.0985, + "step": 378950 + }, + { + "epoch": 0.85, + "learning_rate": 7.74177311469542e-06, + "loss": 0.099, + "step": 378960 + }, + { + "epoch": 0.85, + "learning_rate": 7.740654571486097e-06, + "loss": 0.1012, + "step": 378970 + }, + { + "epoch": 0.85, + "learning_rate": 7.739536028276773e-06, + "loss": 0.0929, + "step": 378980 + }, + { + "epoch": 0.85, + "learning_rate": 7.738417485067448e-06, + "loss": 0.0956, + "step": 378990 + }, + { + "epoch": 0.85, + "learning_rate": 7.737298941858124e-06, + "loss": 0.0943, + "step": 379000 + }, + { + "epoch": 0.85, + "learning_rate": 7.7361803986488e-06, + "loss": 0.1, + "step": 379010 + }, + { + "epoch": 0.85, + "learning_rate": 7.735061855439476e-06, + "loss": 0.0974, + "step": 379020 + }, + { + "epoch": 0.85, + "learning_rate": 7.733943312230153e-06, + "loss": 0.0969, + "step": 379030 + }, + { + "epoch": 0.85, + "learning_rate": 7.732824769020827e-06, + "loss": 0.0976, + "step": 379040 + }, + { + "epoch": 0.85, + "learning_rate": 7.731706225811503e-06, + "loss": 0.0972, + "step": 379050 + }, + { + "epoch": 0.85, + "learning_rate": 7.73058768260218e-06, + "loss": 0.099, + "step": 379060 + }, + { + "epoch": 0.85, + "learning_rate": 7.729469139392854e-06, + "loss": 0.0997, + "step": 379070 + }, + { + "epoch": 0.85, + "learning_rate": 7.72835059618353e-06, + "loss": 0.1011, + "step": 379080 + }, + { + "epoch": 0.85, + "learning_rate": 7.727232052974207e-06, + "loss": 0.0951, + "step": 379090 + }, + { + "epoch": 0.85, + "learning_rate": 7.726113509764883e-06, + "loss": 0.0956, + "step": 379100 + }, + { + "epoch": 0.85, + "learning_rate": 7.724994966555559e-06, + "loss": 0.0956, + "step": 379110 + }, + { + "epoch": 0.85, + "learning_rate": 7.723876423346234e-06, + "loss": 0.0964, + "step": 379120 + }, + { + "epoch": 0.85, + "learning_rate": 7.72275788013691e-06, + "loss": 0.1002, + "step": 379130 + }, + { + "epoch": 0.85, + "learning_rate": 7.721639336927586e-06, + "loss": 0.0976, + "step": 379140 + }, + { + "epoch": 0.85, + "learning_rate": 7.72052079371826e-06, + "loss": 0.0941, + "step": 379150 + }, + { + "epoch": 0.85, + "learning_rate": 7.719402250508939e-06, + "loss": 0.1006, + "step": 379160 + }, + { + "epoch": 0.85, + "learning_rate": 7.718283707299613e-06, + "loss": 0.0958, + "step": 379170 + }, + { + "epoch": 0.85, + "learning_rate": 7.71716516409029e-06, + "loss": 0.0997, + "step": 379180 + }, + { + "epoch": 0.85, + "learning_rate": 7.716046620880966e-06, + "loss": 0.0966, + "step": 379190 + }, + { + "epoch": 0.85, + "learning_rate": 7.715039931992574e-06, + "loss": 0.0921, + "step": 379200 + }, + { + "epoch": 0.85, + "learning_rate": 7.713921388783249e-06, + "loss": 0.1006, + "step": 379210 + }, + { + "epoch": 0.85, + "learning_rate": 7.712802845573925e-06, + "loss": 0.0962, + "step": 379220 + }, + { + "epoch": 0.85, + "learning_rate": 7.711684302364601e-06, + "loss": 0.0926, + "step": 379230 + }, + { + "epoch": 0.85, + "learning_rate": 7.710565759155276e-06, + "loss": 0.0962, + "step": 379240 + }, + { + "epoch": 0.85, + "learning_rate": 7.709447215945954e-06, + "loss": 0.0963, + "step": 379250 + }, + { + "epoch": 0.85, + "learning_rate": 7.708328672736628e-06, + "loss": 0.0979, + "step": 379260 + }, + { + "epoch": 0.85, + "learning_rate": 7.707210129527303e-06, + "loss": 0.1005, + "step": 379270 + }, + { + "epoch": 0.85, + "learning_rate": 7.70609158631798e-06, + "loss": 0.0991, + "step": 379280 + }, + { + "epoch": 0.85, + "learning_rate": 7.704973043108655e-06, + "loss": 0.1007, + "step": 379290 + }, + { + "epoch": 0.85, + "learning_rate": 7.703854499899332e-06, + "loss": 0.0978, + "step": 379300 + }, + { + "epoch": 0.85, + "learning_rate": 7.702735956690008e-06, + "loss": 0.095, + "step": 379310 + }, + { + "epoch": 0.85, + "learning_rate": 7.701617413480682e-06, + "loss": 0.094, + "step": 379320 + }, + { + "epoch": 0.85, + "learning_rate": 7.70049887027136e-06, + "loss": 0.0966, + "step": 379330 + }, + { + "epoch": 0.85, + "learning_rate": 7.699380327062035e-06, + "loss": 0.0986, + "step": 379340 + }, + { + "epoch": 0.85, + "learning_rate": 7.69826178385271e-06, + "loss": 0.0971, + "step": 379350 + }, + { + "epoch": 0.85, + "learning_rate": 7.697143240643387e-06, + "loss": 0.0984, + "step": 379360 + }, + { + "epoch": 0.85, + "learning_rate": 7.696024697434062e-06, + "loss": 0.095, + "step": 379370 + }, + { + "epoch": 0.85, + "learning_rate": 7.694906154224738e-06, + "loss": 0.098, + "step": 379380 + }, + { + "epoch": 0.85, + "learning_rate": 7.693787611015414e-06, + "loss": 0.099, + "step": 379390 + }, + { + "epoch": 0.85, + "learning_rate": 7.692669067806089e-06, + "loss": 0.0985, + "step": 379400 + }, + { + "epoch": 0.85, + "learning_rate": 7.691550524596767e-06, + "loss": 0.0975, + "step": 379410 + }, + { + "epoch": 0.85, + "learning_rate": 7.690431981387441e-06, + "loss": 0.1, + "step": 379420 + }, + { + "epoch": 0.85, + "learning_rate": 7.689313438178118e-06, + "loss": 0.0977, + "step": 379430 + }, + { + "epoch": 0.85, + "learning_rate": 7.688194894968794e-06, + "loss": 0.0943, + "step": 379440 + }, + { + "epoch": 0.85, + "learning_rate": 7.687076351759468e-06, + "loss": 0.093, + "step": 379450 + }, + { + "epoch": 0.85, + "learning_rate": 7.685957808550145e-06, + "loss": 0.0978, + "step": 379460 + }, + { + "epoch": 0.85, + "learning_rate": 7.68483926534082e-06, + "loss": 0.0975, + "step": 379470 + }, + { + "epoch": 0.85, + "learning_rate": 7.683720722131495e-06, + "loss": 0.094, + "step": 379480 + }, + { + "epoch": 0.85, + "learning_rate": 7.682602178922173e-06, + "loss": 0.0967, + "step": 379490 + }, + { + "epoch": 0.85, + "learning_rate": 7.681483635712848e-06, + "loss": 0.1012, + "step": 379500 + }, + { + "epoch": 0.85, + "learning_rate": 7.680365092503524e-06, + "loss": 0.0974, + "step": 379510 + }, + { + "epoch": 0.85, + "learning_rate": 7.6792465492942e-06, + "loss": 0.0937, + "step": 379520 + }, + { + "epoch": 0.85, + "learning_rate": 7.678128006084875e-06, + "loss": 0.0945, + "step": 379530 + }, + { + "epoch": 0.85, + "learning_rate": 7.677009462875551e-06, + "loss": 0.0943, + "step": 379540 + }, + { + "epoch": 0.85, + "learning_rate": 7.675890919666227e-06, + "loss": 0.0936, + "step": 379550 + }, + { + "epoch": 0.85, + "learning_rate": 7.674772376456903e-06, + "loss": 0.0939, + "step": 379560 + }, + { + "epoch": 0.85, + "learning_rate": 7.67365383324758e-06, + "loss": 0.1, + "step": 379570 + }, + { + "epoch": 0.85, + "learning_rate": 7.672535290038254e-06, + "loss": 0.0944, + "step": 379580 + }, + { + "epoch": 0.85, + "learning_rate": 7.67141674682893e-06, + "loss": 0.0984, + "step": 379590 + }, + { + "epoch": 0.85, + "learning_rate": 7.670298203619607e-06, + "loss": 0.0971, + "step": 379600 + }, + { + "epoch": 0.85, + "learning_rate": 7.669179660410281e-06, + "loss": 0.0934, + "step": 379610 + }, + { + "epoch": 0.85, + "learning_rate": 7.668061117200957e-06, + "loss": 0.0962, + "step": 379620 + }, + { + "epoch": 0.85, + "learning_rate": 7.666942573991634e-06, + "loss": 0.0987, + "step": 379630 + }, + { + "epoch": 0.85, + "learning_rate": 7.66582403078231e-06, + "loss": 0.097, + "step": 379640 + }, + { + "epoch": 0.85, + "learning_rate": 7.664705487572986e-06, + "loss": 0.0968, + "step": 379650 + }, + { + "epoch": 0.85, + "learning_rate": 7.66358694436366e-06, + "loss": 0.0931, + "step": 379660 + }, + { + "epoch": 0.85, + "learning_rate": 7.662468401154337e-06, + "loss": 0.093, + "step": 379670 + }, + { + "epoch": 0.85, + "learning_rate": 7.661349857945013e-06, + "loss": 0.0967, + "step": 379680 + }, + { + "epoch": 0.85, + "learning_rate": 7.660231314735688e-06, + "loss": 0.098, + "step": 379690 + }, + { + "epoch": 0.85, + "learning_rate": 7.659112771526364e-06, + "loss": 0.0957, + "step": 379700 + }, + { + "epoch": 0.85, + "learning_rate": 7.65799422831704e-06, + "loss": 0.0977, + "step": 379710 + }, + { + "epoch": 0.85, + "learning_rate": 7.656875685107716e-06, + "loss": 0.0947, + "step": 379720 + }, + { + "epoch": 0.85, + "learning_rate": 7.655757141898393e-06, + "loss": 0.0966, + "step": 379730 + }, + { + "epoch": 0.85, + "learning_rate": 7.654638598689067e-06, + "loss": 0.0939, + "step": 379740 + }, + { + "epoch": 0.85, + "learning_rate": 7.653520055479743e-06, + "loss": 0.0979, + "step": 379750 + }, + { + "epoch": 0.85, + "learning_rate": 7.65240151227042e-06, + "loss": 0.0963, + "step": 379760 + }, + { + "epoch": 0.85, + "learning_rate": 7.651282969061096e-06, + "loss": 0.0964, + "step": 379770 + }, + { + "epoch": 0.85, + "learning_rate": 7.65016442585177e-06, + "loss": 0.0972, + "step": 379780 + }, + { + "epoch": 0.85, + "learning_rate": 7.649045882642447e-06, + "loss": 0.0945, + "step": 379790 + }, + { + "epoch": 0.85, + "learning_rate": 7.647927339433123e-06, + "loss": 0.098, + "step": 379800 + }, + { + "epoch": 0.85, + "learning_rate": 7.6468087962238e-06, + "loss": 0.0943, + "step": 379810 + }, + { + "epoch": 0.85, + "learning_rate": 7.645690253014474e-06, + "loss": 0.0956, + "step": 379820 + }, + { + "epoch": 0.85, + "learning_rate": 7.64457170980515e-06, + "loss": 0.0976, + "step": 379830 + }, + { + "epoch": 0.85, + "learning_rate": 7.643453166595826e-06, + "loss": 0.0973, + "step": 379840 + }, + { + "epoch": 0.85, + "learning_rate": 7.642334623386502e-06, + "loss": 0.0967, + "step": 379850 + }, + { + "epoch": 0.85, + "learning_rate": 7.641216080177177e-06, + "loss": 0.098, + "step": 379860 + }, + { + "epoch": 0.85, + "learning_rate": 7.640097536967853e-06, + "loss": 0.0985, + "step": 379870 + }, + { + "epoch": 0.85, + "learning_rate": 7.63897899375853e-06, + "loss": 0.0971, + "step": 379880 + }, + { + "epoch": 0.85, + "learning_rate": 7.637860450549206e-06, + "loss": 0.0962, + "step": 379890 + }, + { + "epoch": 0.85, + "learning_rate": 7.636741907339882e-06, + "loss": 0.0942, + "step": 379900 + }, + { + "epoch": 0.85, + "learning_rate": 7.635623364130556e-06, + "loss": 0.0967, + "step": 379910 + }, + { + "epoch": 0.85, + "learning_rate": 7.634504820921233e-06, + "loss": 0.0939, + "step": 379920 + }, + { + "epoch": 0.85, + "learning_rate": 7.633386277711909e-06, + "loss": 0.0954, + "step": 379930 + }, + { + "epoch": 0.85, + "learning_rate": 7.632267734502583e-06, + "loss": 0.0973, + "step": 379940 + }, + { + "epoch": 0.85, + "learning_rate": 7.63114919129326e-06, + "loss": 0.0913, + "step": 379950 + }, + { + "epoch": 0.85, + "learning_rate": 7.630030648083936e-06, + "loss": 0.0949, + "step": 379960 + }, + { + "epoch": 0.85, + "learning_rate": 7.628912104874612e-06, + "loss": 0.0967, + "step": 379970 + }, + { + "epoch": 0.85, + "learning_rate": 7.6277935616652875e-06, + "loss": 0.0977, + "step": 379980 + }, + { + "epoch": 0.85, + "learning_rate": 7.626675018455963e-06, + "loss": 0.0988, + "step": 379990 + }, + { + "epoch": 0.85, + "learning_rate": 7.62555647524664e-06, + "loss": 0.0947, + "step": 380000 + }, + { + "epoch": 0.85, + "learning_rate": 7.6244379320373145e-06, + "loss": 0.0955, + "step": 380010 + }, + { + "epoch": 0.85, + "learning_rate": 7.62331938882799e-06, + "loss": 0.0997, + "step": 380020 + }, + { + "epoch": 0.85, + "learning_rate": 7.622200845618667e-06, + "loss": 0.1006, + "step": 380030 + }, + { + "epoch": 0.85, + "learning_rate": 7.621082302409342e-06, + "loss": 0.0955, + "step": 380040 + }, + { + "epoch": 0.85, + "learning_rate": 7.619963759200019e-06, + "loss": 0.096, + "step": 380050 + }, + { + "epoch": 0.85, + "learning_rate": 7.618845215990694e-06, + "loss": 0.096, + "step": 380060 + }, + { + "epoch": 0.85, + "learning_rate": 7.617726672781369e-06, + "loss": 0.099, + "step": 380070 + }, + { + "epoch": 0.85, + "learning_rate": 7.6166081295720465e-06, + "loss": 0.0968, + "step": 380080 + }, + { + "epoch": 0.85, + "learning_rate": 7.615489586362722e-06, + "loss": 0.099, + "step": 380090 + }, + { + "epoch": 0.85, + "learning_rate": 7.614371043153397e-06, + "loss": 0.0925, + "step": 380100 + }, + { + "epoch": 0.85, + "learning_rate": 7.6132524999440735e-06, + "loss": 0.0978, + "step": 380110 + }, + { + "epoch": 0.85, + "learning_rate": 7.612133956734749e-06, + "loss": 0.0933, + "step": 380120 + }, + { + "epoch": 0.85, + "learning_rate": 7.611015413525426e-06, + "loss": 0.0987, + "step": 380130 + }, + { + "epoch": 0.85, + "learning_rate": 7.6098968703161005e-06, + "loss": 0.0983, + "step": 380140 + }, + { + "epoch": 0.85, + "learning_rate": 7.608778327106776e-06, + "loss": 0.1009, + "step": 380150 + }, + { + "epoch": 0.85, + "learning_rate": 7.607659783897453e-06, + "loss": 0.0968, + "step": 380160 + }, + { + "epoch": 0.85, + "learning_rate": 7.606541240688128e-06, + "loss": 0.093, + "step": 380170 + }, + { + "epoch": 0.85, + "learning_rate": 7.605422697478804e-06, + "loss": 0.0973, + "step": 380180 + }, + { + "epoch": 0.85, + "learning_rate": 7.60430415426948e-06, + "loss": 0.0963, + "step": 380190 + }, + { + "epoch": 0.85, + "learning_rate": 7.603185611060155e-06, + "loss": 0.0993, + "step": 380200 + }, + { + "epoch": 0.85, + "learning_rate": 7.602067067850832e-06, + "loss": 0.0953, + "step": 380210 + }, + { + "epoch": 0.85, + "learning_rate": 7.600948524641508e-06, + "loss": 0.0952, + "step": 380220 + }, + { + "epoch": 0.85, + "learning_rate": 7.599829981432182e-06, + "loss": 0.0972, + "step": 380230 + }, + { + "epoch": 0.85, + "learning_rate": 7.598711438222859e-06, + "loss": 0.0951, + "step": 380240 + }, + { + "epoch": 0.85, + "learning_rate": 7.597592895013535e-06, + "loss": 0.0978, + "step": 380250 + }, + { + "epoch": 0.85, + "learning_rate": 7.59647435180421e-06, + "loss": 0.0952, + "step": 380260 + }, + { + "epoch": 0.85, + "learning_rate": 7.5953558085948864e-06, + "loss": 0.0955, + "step": 380270 + }, + { + "epoch": 0.85, + "learning_rate": 7.594237265385562e-06, + "loss": 0.1029, + "step": 380280 + }, + { + "epoch": 0.85, + "learning_rate": 7.593118722176239e-06, + "loss": 0.0994, + "step": 380290 + }, + { + "epoch": 0.85, + "learning_rate": 7.592000178966914e-06, + "loss": 0.0947, + "step": 380300 + }, + { + "epoch": 0.85, + "learning_rate": 7.59088163575759e-06, + "loss": 0.0944, + "step": 380310 + }, + { + "epoch": 0.85, + "learning_rate": 7.589763092548266e-06, + "loss": 0.0951, + "step": 380320 + }, + { + "epoch": 0.85, + "learning_rate": 7.588644549338941e-06, + "loss": 0.0944, + "step": 380330 + }, + { + "epoch": 0.85, + "learning_rate": 7.587526006129617e-06, + "loss": 0.0918, + "step": 380340 + }, + { + "epoch": 0.85, + "learning_rate": 7.586407462920293e-06, + "loss": 0.0972, + "step": 380350 + }, + { + "epoch": 0.85, + "learning_rate": 7.585288919710968e-06, + "loss": 0.0934, + "step": 380360 + }, + { + "epoch": 0.85, + "learning_rate": 7.584170376501645e-06, + "loss": 0.0979, + "step": 380370 + }, + { + "epoch": 0.85, + "learning_rate": 7.583051833292321e-06, + "loss": 0.0938, + "step": 380380 + }, + { + "epoch": 0.85, + "learning_rate": 7.581933290082996e-06, + "loss": 0.0983, + "step": 380390 + }, + { + "epoch": 0.85, + "learning_rate": 7.580814746873672e-06, + "loss": 0.0954, + "step": 380400 + }, + { + "epoch": 0.85, + "learning_rate": 7.579696203664348e-06, + "loss": 0.0985, + "step": 380410 + }, + { + "epoch": 0.85, + "learning_rate": 7.578577660455023e-06, + "loss": 0.0962, + "step": 380420 + }, + { + "epoch": 0.85, + "learning_rate": 7.5774591172457e-06, + "loss": 0.096, + "step": 380430 + }, + { + "epoch": 0.85, + "learning_rate": 7.576340574036376e-06, + "loss": 0.0979, + "step": 380440 + }, + { + "epoch": 0.85, + "learning_rate": 7.575222030827052e-06, + "loss": 0.0974, + "step": 380450 + }, + { + "epoch": 0.85, + "learning_rate": 7.574103487617727e-06, + "loss": 0.0953, + "step": 380460 + }, + { + "epoch": 0.85, + "learning_rate": 7.572984944408403e-06, + "loss": 0.0929, + "step": 380470 + }, + { + "epoch": 0.85, + "learning_rate": 7.571866401199079e-06, + "loss": 0.1006, + "step": 380480 + }, + { + "epoch": 0.85, + "learning_rate": 7.570747857989754e-06, + "loss": 0.0966, + "step": 380490 + }, + { + "epoch": 0.85, + "learning_rate": 7.56962931478043e-06, + "loss": 0.0977, + "step": 380500 + }, + { + "epoch": 0.85, + "learning_rate": 7.568510771571107e-06, + "loss": 0.098, + "step": 380510 + }, + { + "epoch": 0.85, + "learning_rate": 7.567392228361782e-06, + "loss": 0.0987, + "step": 380520 + }, + { + "epoch": 0.85, + "learning_rate": 7.566273685152458e-06, + "loss": 0.0988, + "step": 380530 + }, + { + "epoch": 0.85, + "learning_rate": 7.565155141943134e-06, + "loss": 0.0954, + "step": 380540 + }, + { + "epoch": 0.85, + "learning_rate": 7.564036598733809e-06, + "loss": 0.0962, + "step": 380550 + }, + { + "epoch": 0.85, + "learning_rate": 7.562918055524486e-06, + "loss": 0.0989, + "step": 380560 + }, + { + "epoch": 0.85, + "learning_rate": 7.561799512315161e-06, + "loss": 0.0978, + "step": 380570 + }, + { + "epoch": 0.85, + "learning_rate": 7.560680969105836e-06, + "loss": 0.0949, + "step": 380580 + }, + { + "epoch": 0.85, + "learning_rate": 7.559562425896513e-06, + "loss": 0.0975, + "step": 380590 + }, + { + "epoch": 0.85, + "learning_rate": 7.558443882687189e-06, + "loss": 0.0944, + "step": 380600 + }, + { + "epoch": 0.85, + "learning_rate": 7.557325339477865e-06, + "loss": 0.0923, + "step": 380610 + }, + { + "epoch": 0.85, + "learning_rate": 7.55620679626854e-06, + "loss": 0.0902, + "step": 380620 + }, + { + "epoch": 0.85, + "learning_rate": 7.555088253059216e-06, + "loss": 0.0963, + "step": 380630 + }, + { + "epoch": 0.85, + "learning_rate": 7.553969709849893e-06, + "loss": 0.0979, + "step": 380640 + }, + { + "epoch": 0.85, + "learning_rate": 7.552851166640568e-06, + "loss": 0.0975, + "step": 380650 + }, + { + "epoch": 0.85, + "learning_rate": 7.551732623431243e-06, + "loss": 0.1031, + "step": 380660 + }, + { + "epoch": 0.85, + "learning_rate": 7.55061408022192e-06, + "loss": 0.0976, + "step": 380670 + }, + { + "epoch": 0.85, + "learning_rate": 7.549495537012595e-06, + "loss": 0.0971, + "step": 380680 + }, + { + "epoch": 0.85, + "learning_rate": 7.5483769938032705e-06, + "loss": 0.0999, + "step": 380690 + }, + { + "epoch": 0.85, + "learning_rate": 7.547258450593947e-06, + "loss": 0.1011, + "step": 380700 + }, + { + "epoch": 0.85, + "learning_rate": 7.546139907384622e-06, + "loss": 0.097, + "step": 380710 + }, + { + "epoch": 0.85, + "learning_rate": 7.545021364175299e-06, + "loss": 0.0996, + "step": 380720 + }, + { + "epoch": 0.85, + "learning_rate": 7.5439028209659745e-06, + "loss": 0.097, + "step": 380730 + }, + { + "epoch": 0.85, + "learning_rate": 7.54278427775665e-06, + "loss": 0.0964, + "step": 380740 + }, + { + "epoch": 0.85, + "learning_rate": 7.541665734547326e-06, + "loss": 0.0952, + "step": 380750 + }, + { + "epoch": 0.85, + "learning_rate": 7.5405471913380015e-06, + "loss": 0.0947, + "step": 380760 + }, + { + "epoch": 0.85, + "learning_rate": 7.539428648128677e-06, + "loss": 0.0982, + "step": 380770 + }, + { + "epoch": 0.85, + "learning_rate": 7.538310104919353e-06, + "loss": 0.0974, + "step": 380780 + }, + { + "epoch": 0.85, + "learning_rate": 7.5371915617100286e-06, + "loss": 0.0994, + "step": 380790 + }, + { + "epoch": 0.85, + "learning_rate": 7.536073018500706e-06, + "loss": 0.1017, + "step": 380800 + }, + { + "epoch": 0.85, + "learning_rate": 7.534954475291381e-06, + "loss": 0.0962, + "step": 380810 + }, + { + "epoch": 0.85, + "learning_rate": 7.533835932082056e-06, + "loss": 0.0981, + "step": 380820 + }, + { + "epoch": 0.85, + "learning_rate": 7.532717388872733e-06, + "loss": 0.0965, + "step": 380830 + }, + { + "epoch": 0.85, + "learning_rate": 7.531598845663408e-06, + "loss": 0.0961, + "step": 380840 + }, + { + "epoch": 0.85, + "learning_rate": 7.530480302454083e-06, + "loss": 0.0928, + "step": 380850 + }, + { + "epoch": 0.85, + "learning_rate": 7.5293617592447605e-06, + "loss": 0.0971, + "step": 380860 + }, + { + "epoch": 0.85, + "learning_rate": 7.528243216035436e-06, + "loss": 0.0993, + "step": 380870 + }, + { + "epoch": 0.85, + "learning_rate": 7.527124672826112e-06, + "loss": 0.0947, + "step": 380880 + }, + { + "epoch": 0.85, + "learning_rate": 7.5260061296167875e-06, + "loss": 0.0948, + "step": 380890 + }, + { + "epoch": 0.85, + "learning_rate": 7.524887586407463e-06, + "loss": 0.0971, + "step": 380900 + }, + { + "epoch": 0.85, + "learning_rate": 7.523769043198139e-06, + "loss": 0.098, + "step": 380910 + }, + { + "epoch": 0.85, + "learning_rate": 7.5226504999888145e-06, + "loss": 0.1043, + "step": 380920 + }, + { + "epoch": 0.85, + "learning_rate": 7.52153195677949e-06, + "loss": 0.0945, + "step": 380930 + }, + { + "epoch": 0.85, + "learning_rate": 7.520413413570167e-06, + "loss": 0.0998, + "step": 380940 + }, + { + "epoch": 0.85, + "learning_rate": 7.519294870360842e-06, + "loss": 0.0969, + "step": 380950 + }, + { + "epoch": 0.85, + "learning_rate": 7.518176327151519e-06, + "loss": 0.0946, + "step": 380960 + }, + { + "epoch": 0.85, + "learning_rate": 7.517057783942194e-06, + "loss": 0.0949, + "step": 380970 + }, + { + "epoch": 0.85, + "learning_rate": 7.515939240732869e-06, + "loss": 0.0975, + "step": 380980 + }, + { + "epoch": 0.85, + "learning_rate": 7.5148206975235464e-06, + "loss": 0.1005, + "step": 380990 + }, + { + "epoch": 0.85, + "learning_rate": 7.513702154314221e-06, + "loss": 0.098, + "step": 381000 + }, + { + "epoch": 0.85, + "learning_rate": 7.512583611104896e-06, + "loss": 0.0948, + "step": 381010 + }, + { + "epoch": 0.85, + "learning_rate": 7.5114650678955735e-06, + "loss": 0.1012, + "step": 381020 + }, + { + "epoch": 0.85, + "learning_rate": 7.510346524686249e-06, + "loss": 0.0986, + "step": 381030 + }, + { + "epoch": 0.85, + "learning_rate": 7.509227981476925e-06, + "loss": 0.0929, + "step": 381040 + }, + { + "epoch": 0.85, + "learning_rate": 7.5081094382676005e-06, + "loss": 0.0971, + "step": 381050 + }, + { + "epoch": 0.85, + "learning_rate": 7.506990895058276e-06, + "loss": 0.0969, + "step": 381060 + }, + { + "epoch": 0.85, + "learning_rate": 7.505872351848953e-06, + "loss": 0.0952, + "step": 381070 + }, + { + "epoch": 0.85, + "learning_rate": 7.504753808639628e-06, + "loss": 0.0977, + "step": 381080 + }, + { + "epoch": 0.85, + "learning_rate": 7.503635265430303e-06, + "loss": 0.0963, + "step": 381090 + }, + { + "epoch": 0.85, + "learning_rate": 7.50251672222098e-06, + "loss": 0.0998, + "step": 381100 + }, + { + "epoch": 0.85, + "learning_rate": 7.501398179011655e-06, + "loss": 0.0949, + "step": 381110 + }, + { + "epoch": 0.85, + "learning_rate": 7.5002796358023316e-06, + "loss": 0.093, + "step": 381120 + }, + { + "epoch": 0.85, + "learning_rate": 7.499161092593007e-06, + "loss": 0.0949, + "step": 381130 + }, + { + "epoch": 0.85, + "learning_rate": 7.498042549383682e-06, + "loss": 0.0974, + "step": 381140 + }, + { + "epoch": 0.85, + "learning_rate": 7.496924006174359e-06, + "loss": 0.0971, + "step": 381150 + }, + { + "epoch": 0.85, + "learning_rate": 7.495805462965035e-06, + "loss": 0.0943, + "step": 381160 + }, + { + "epoch": 0.85, + "learning_rate": 7.49468691975571e-06, + "loss": 0.0922, + "step": 381170 + }, + { + "epoch": 0.85, + "learning_rate": 7.493568376546386e-06, + "loss": 0.0934, + "step": 381180 + }, + { + "epoch": 0.85, + "learning_rate": 7.492449833337062e-06, + "loss": 0.0989, + "step": 381190 + }, + { + "epoch": 0.85, + "learning_rate": 7.491331290127739e-06, + "loss": 0.0945, + "step": 381200 + }, + { + "epoch": 0.85, + "learning_rate": 7.490212746918414e-06, + "loss": 0.0963, + "step": 381210 + }, + { + "epoch": 0.85, + "learning_rate": 7.489094203709089e-06, + "loss": 0.0928, + "step": 381220 + }, + { + "epoch": 0.85, + "learning_rate": 7.487975660499766e-06, + "loss": 0.0992, + "step": 381230 + }, + { + "epoch": 0.85, + "learning_rate": 7.486857117290441e-06, + "loss": 0.0958, + "step": 381240 + }, + { + "epoch": 0.85, + "learning_rate": 7.485738574081117e-06, + "loss": 0.0945, + "step": 381250 + }, + { + "epoch": 0.85, + "learning_rate": 7.4847318851927254e-06, + "loss": 0.0972, + "step": 381260 + }, + { + "epoch": 0.85, + "learning_rate": 7.483613341983402e-06, + "loss": 0.0962, + "step": 381270 + }, + { + "epoch": 0.85, + "learning_rate": 7.482494798774077e-06, + "loss": 0.0999, + "step": 381280 + }, + { + "epoch": 0.85, + "learning_rate": 7.4813762555647524e-06, + "loss": 0.097, + "step": 381290 + }, + { + "epoch": 0.85, + "learning_rate": 7.480257712355429e-06, + "loss": 0.0945, + "step": 381300 + }, + { + "epoch": 0.85, + "learning_rate": 7.479139169146104e-06, + "loss": 0.0957, + "step": 381310 + }, + { + "epoch": 0.85, + "learning_rate": 7.4780206259367795e-06, + "loss": 0.0958, + "step": 381320 + }, + { + "epoch": 0.85, + "learning_rate": 7.4769020827274565e-06, + "loss": 0.097, + "step": 381330 + }, + { + "epoch": 0.85, + "learning_rate": 7.475783539518132e-06, + "loss": 0.0954, + "step": 381340 + }, + { + "epoch": 0.85, + "learning_rate": 7.474664996308808e-06, + "loss": 0.0949, + "step": 381350 + }, + { + "epoch": 0.85, + "learning_rate": 7.4735464530994835e-06, + "loss": 0.0968, + "step": 381360 + }, + { + "epoch": 0.85, + "learning_rate": 7.472427909890159e-06, + "loss": 0.0972, + "step": 381370 + }, + { + "epoch": 0.85, + "learning_rate": 7.471309366680836e-06, + "loss": 0.0987, + "step": 381380 + }, + { + "epoch": 0.85, + "learning_rate": 7.4701908234715106e-06, + "loss": 0.0976, + "step": 381390 + }, + { + "epoch": 0.85, + "learning_rate": 7.469072280262186e-06, + "loss": 0.0911, + "step": 381400 + }, + { + "epoch": 0.85, + "learning_rate": 7.467953737052863e-06, + "loss": 0.0962, + "step": 381410 + }, + { + "epoch": 0.85, + "learning_rate": 7.466835193843538e-06, + "loss": 0.094, + "step": 381420 + }, + { + "epoch": 0.85, + "learning_rate": 7.465716650634215e-06, + "loss": 0.0951, + "step": 381430 + }, + { + "epoch": 0.85, + "learning_rate": 7.46459810742489e-06, + "loss": 0.1033, + "step": 381440 + }, + { + "epoch": 0.85, + "learning_rate": 7.463479564215565e-06, + "loss": 0.0972, + "step": 381450 + }, + { + "epoch": 0.85, + "learning_rate": 7.4623610210062425e-06, + "loss": 0.0955, + "step": 381460 + }, + { + "epoch": 0.85, + "learning_rate": 7.461242477796918e-06, + "loss": 0.0958, + "step": 381470 + }, + { + "epoch": 0.85, + "learning_rate": 7.460123934587593e-06, + "loss": 0.0954, + "step": 381480 + }, + { + "epoch": 0.85, + "learning_rate": 7.4590053913782695e-06, + "loss": 0.0984, + "step": 381490 + }, + { + "epoch": 0.85, + "learning_rate": 7.457886848168945e-06, + "loss": 0.0971, + "step": 381500 + }, + { + "epoch": 0.85, + "learning_rate": 7.456768304959621e-06, + "loss": 0.0942, + "step": 381510 + }, + { + "epoch": 0.85, + "learning_rate": 7.4556497617502965e-06, + "loss": 0.0986, + "step": 381520 + }, + { + "epoch": 0.85, + "learning_rate": 7.454531218540972e-06, + "loss": 0.0955, + "step": 381530 + }, + { + "epoch": 0.85, + "learning_rate": 7.453412675331649e-06, + "loss": 0.0948, + "step": 381540 + }, + { + "epoch": 0.85, + "learning_rate": 7.452294132122324e-06, + "loss": 0.0981, + "step": 381550 + }, + { + "epoch": 0.85, + "learning_rate": 7.451175588913e-06, + "loss": 0.0977, + "step": 381560 + }, + { + "epoch": 0.85, + "learning_rate": 7.450057045703676e-06, + "loss": 0.0995, + "step": 381570 + }, + { + "epoch": 0.85, + "learning_rate": 7.448938502494351e-06, + "loss": 0.099, + "step": 381580 + }, + { + "epoch": 0.85, + "learning_rate": 7.4478199592850284e-06, + "loss": 0.0942, + "step": 381590 + }, + { + "epoch": 0.85, + "learning_rate": 7.446701416075704e-06, + "loss": 0.0973, + "step": 381600 + }, + { + "epoch": 0.85, + "learning_rate": 7.445582872866378e-06, + "loss": 0.0976, + "step": 381610 + }, + { + "epoch": 0.85, + "learning_rate": 7.4444643296570555e-06, + "loss": 0.0953, + "step": 381620 + }, + { + "epoch": 0.85, + "learning_rate": 7.443345786447731e-06, + "loss": 0.0962, + "step": 381630 + }, + { + "epoch": 0.85, + "learning_rate": 7.442227243238406e-06, + "loss": 0.0943, + "step": 381640 + }, + { + "epoch": 0.85, + "learning_rate": 7.4411087000290825e-06, + "loss": 0.0998, + "step": 381650 + }, + { + "epoch": 0.85, + "learning_rate": 7.439990156819758e-06, + "loss": 0.0947, + "step": 381660 + }, + { + "epoch": 0.85, + "learning_rate": 7.438871613610435e-06, + "loss": 0.0978, + "step": 381670 + }, + { + "epoch": 0.85, + "learning_rate": 7.43775307040111e-06, + "loss": 0.0948, + "step": 381680 + }, + { + "epoch": 0.85, + "learning_rate": 7.436634527191786e-06, + "loss": 0.0959, + "step": 381690 + }, + { + "epoch": 0.85, + "learning_rate": 7.435515983982462e-06, + "loss": 0.0966, + "step": 381700 + }, + { + "epoch": 0.85, + "learning_rate": 7.434397440773137e-06, + "loss": 0.0963, + "step": 381710 + }, + { + "epoch": 0.85, + "learning_rate": 7.433278897563813e-06, + "loss": 0.0965, + "step": 381720 + }, + { + "epoch": 0.85, + "learning_rate": 7.432160354354489e-06, + "loss": 0.0992, + "step": 381730 + }, + { + "epoch": 0.85, + "learning_rate": 7.431041811145164e-06, + "loss": 0.0975, + "step": 381740 + }, + { + "epoch": 0.85, + "learning_rate": 7.429923267935841e-06, + "loss": 0.0934, + "step": 381750 + }, + { + "epoch": 0.85, + "learning_rate": 7.428804724726517e-06, + "loss": 0.0961, + "step": 381760 + }, + { + "epoch": 0.85, + "learning_rate": 7.427686181517192e-06, + "loss": 0.0964, + "step": 381770 + }, + { + "epoch": 0.85, + "learning_rate": 7.426567638307868e-06, + "loss": 0.102, + "step": 381780 + }, + { + "epoch": 0.85, + "learning_rate": 7.425449095098544e-06, + "loss": 0.098, + "step": 381790 + }, + { + "epoch": 0.85, + "learning_rate": 7.424330551889219e-06, + "loss": 0.0962, + "step": 381800 + }, + { + "epoch": 0.85, + "learning_rate": 7.423212008679896e-06, + "loss": 0.0985, + "step": 381810 + }, + { + "epoch": 0.85, + "learning_rate": 7.422093465470571e-06, + "loss": 0.0997, + "step": 381820 + }, + { + "epoch": 0.85, + "learning_rate": 7.420974922261248e-06, + "loss": 0.0976, + "step": 381830 + }, + { + "epoch": 0.85, + "learning_rate": 7.419856379051923e-06, + "loss": 0.0955, + "step": 381840 + }, + { + "epoch": 0.85, + "learning_rate": 7.418737835842599e-06, + "loss": 0.0977, + "step": 381850 + }, + { + "epoch": 0.85, + "learning_rate": 7.417619292633275e-06, + "loss": 0.0945, + "step": 381860 + }, + { + "epoch": 0.85, + "learning_rate": 7.41650074942395e-06, + "loss": 0.0955, + "step": 381870 + }, + { + "epoch": 0.85, + "learning_rate": 7.415382206214626e-06, + "loss": 0.0924, + "step": 381880 + }, + { + "epoch": 0.85, + "learning_rate": 7.414263663005303e-06, + "loss": 0.0952, + "step": 381890 + }, + { + "epoch": 0.85, + "learning_rate": 7.413145119795978e-06, + "loss": 0.0948, + "step": 381900 + }, + { + "epoch": 0.85, + "learning_rate": 7.412026576586654e-06, + "loss": 0.0976, + "step": 381910 + }, + { + "epoch": 0.85, + "learning_rate": 7.41090803337733e-06, + "loss": 0.0964, + "step": 381920 + }, + { + "epoch": 0.85, + "learning_rate": 7.409789490168005e-06, + "loss": 0.0939, + "step": 381930 + }, + { + "epoch": 0.85, + "learning_rate": 7.408670946958682e-06, + "loss": 0.0974, + "step": 381940 + }, + { + "epoch": 0.85, + "learning_rate": 7.407552403749357e-06, + "loss": 0.0961, + "step": 381950 + }, + { + "epoch": 0.85, + "learning_rate": 7.406433860540032e-06, + "loss": 0.1005, + "step": 381960 + }, + { + "epoch": 0.85, + "learning_rate": 7.405315317330709e-06, + "loss": 0.0953, + "step": 381970 + }, + { + "epoch": 0.85, + "learning_rate": 7.404196774121385e-06, + "loss": 0.0965, + "step": 381980 + }, + { + "epoch": 0.85, + "learning_rate": 7.403078230912061e-06, + "loss": 0.0982, + "step": 381990 + }, + { + "epoch": 0.85, + "learning_rate": 7.401959687702736e-06, + "loss": 0.0978, + "step": 382000 + }, + { + "epoch": 0.85, + "learning_rate": 7.400841144493412e-06, + "loss": 0.0994, + "step": 382010 + }, + { + "epoch": 0.85, + "learning_rate": 7.399722601284089e-06, + "loss": 0.0954, + "step": 382020 + }, + { + "epoch": 0.85, + "learning_rate": 7.398604058074764e-06, + "loss": 0.0965, + "step": 382030 + }, + { + "epoch": 0.85, + "learning_rate": 7.397485514865439e-06, + "loss": 0.0941, + "step": 382040 + }, + { + "epoch": 0.85, + "learning_rate": 7.396366971656116e-06, + "loss": 0.0987, + "step": 382050 + }, + { + "epoch": 0.85, + "learning_rate": 7.395248428446791e-06, + "loss": 0.0934, + "step": 382060 + }, + { + "epoch": 0.85, + "learning_rate": 7.394129885237467e-06, + "loss": 0.098, + "step": 382070 + }, + { + "epoch": 0.85, + "learning_rate": 7.393011342028143e-06, + "loss": 0.094, + "step": 382080 + }, + { + "epoch": 0.85, + "learning_rate": 7.391892798818818e-06, + "loss": 0.0943, + "step": 382090 + }, + { + "epoch": 0.85, + "learning_rate": 7.390774255609495e-06, + "loss": 0.0957, + "step": 382100 + }, + { + "epoch": 0.85, + "learning_rate": 7.3896557124001706e-06, + "loss": 0.0957, + "step": 382110 + }, + { + "epoch": 0.85, + "learning_rate": 7.388537169190846e-06, + "loss": 0.0971, + "step": 382120 + }, + { + "epoch": 0.85, + "learning_rate": 7.387418625981522e-06, + "loss": 0.0993, + "step": 382130 + }, + { + "epoch": 0.85, + "learning_rate": 7.386300082772198e-06, + "loss": 0.0945, + "step": 382140 + }, + { + "epoch": 0.85, + "learning_rate": 7.385181539562875e-06, + "loss": 0.093, + "step": 382150 + }, + { + "epoch": 0.85, + "learning_rate": 7.384062996353549e-06, + "loss": 0.0964, + "step": 382160 + }, + { + "epoch": 0.85, + "learning_rate": 7.382944453144225e-06, + "loss": 0.0993, + "step": 382170 + }, + { + "epoch": 0.85, + "learning_rate": 7.381825909934902e-06, + "loss": 0.0947, + "step": 382180 + }, + { + "epoch": 0.85, + "learning_rate": 7.380707366725577e-06, + "loss": 0.0969, + "step": 382190 + }, + { + "epoch": 0.85, + "learning_rate": 7.3795888235162524e-06, + "loss": 0.0958, + "step": 382200 + }, + { + "epoch": 0.85, + "learning_rate": 7.378470280306929e-06, + "loss": 0.0969, + "step": 382210 + }, + { + "epoch": 0.85, + "learning_rate": 7.377351737097604e-06, + "loss": 0.0956, + "step": 382220 + }, + { + "epoch": 0.85, + "learning_rate": 7.376233193888281e-06, + "loss": 0.0969, + "step": 382230 + }, + { + "epoch": 0.85, + "learning_rate": 7.3751146506789565e-06, + "loss": 0.0988, + "step": 382240 + }, + { + "epoch": 0.85, + "learning_rate": 7.373996107469631e-06, + "loss": 0.0958, + "step": 382250 + }, + { + "epoch": 0.85, + "learning_rate": 7.372877564260308e-06, + "loss": 0.0947, + "step": 382260 + }, + { + "epoch": 0.85, + "learning_rate": 7.3717590210509835e-06, + "loss": 0.0987, + "step": 382270 + }, + { + "epoch": 0.85, + "learning_rate": 7.370640477841659e-06, + "loss": 0.0951, + "step": 382280 + }, + { + "epoch": 0.85, + "learning_rate": 7.369521934632335e-06, + "loss": 0.0976, + "step": 382290 + }, + { + "epoch": 0.85, + "learning_rate": 7.3684033914230105e-06, + "loss": 0.0971, + "step": 382300 + }, + { + "epoch": 0.85, + "learning_rate": 7.367284848213688e-06, + "loss": 0.096, + "step": 382310 + }, + { + "epoch": 0.85, + "learning_rate": 7.366166305004363e-06, + "loss": 0.1012, + "step": 382320 + }, + { + "epoch": 0.85, + "learning_rate": 7.365047761795038e-06, + "loss": 0.0949, + "step": 382330 + }, + { + "epoch": 0.85, + "learning_rate": 7.363929218585715e-06, + "loss": 0.099, + "step": 382340 + }, + { + "epoch": 0.85, + "learning_rate": 7.36281067537639e-06, + "loss": 0.1015, + "step": 382350 + }, + { + "epoch": 0.85, + "learning_rate": 7.361692132167065e-06, + "loss": 0.0966, + "step": 382360 + }, + { + "epoch": 0.85, + "learning_rate": 7.3605735889577425e-06, + "loss": 0.0968, + "step": 382370 + }, + { + "epoch": 0.85, + "learning_rate": 7.359455045748417e-06, + "loss": 0.0979, + "step": 382380 + }, + { + "epoch": 0.85, + "learning_rate": 7.358336502539094e-06, + "loss": 0.0977, + "step": 382390 + }, + { + "epoch": 0.85, + "learning_rate": 7.3572179593297695e-06, + "loss": 0.0923, + "step": 382400 + }, + { + "epoch": 0.85, + "learning_rate": 7.356099416120445e-06, + "loss": 0.0923, + "step": 382410 + }, + { + "epoch": 0.85, + "learning_rate": 7.354980872911121e-06, + "loss": 0.0993, + "step": 382420 + }, + { + "epoch": 0.85, + "learning_rate": 7.3538623297017965e-06, + "loss": 0.0976, + "step": 382430 + }, + { + "epoch": 0.85, + "learning_rate": 7.352743786492472e-06, + "loss": 0.0976, + "step": 382440 + }, + { + "epoch": 0.85, + "learning_rate": 7.351625243283149e-06, + "loss": 0.093, + "step": 382450 + }, + { + "epoch": 0.85, + "learning_rate": 7.350506700073824e-06, + "loss": 0.0942, + "step": 382460 + }, + { + "epoch": 0.85, + "learning_rate": 7.349388156864501e-06, + "loss": 0.1004, + "step": 382470 + }, + { + "epoch": 0.85, + "learning_rate": 7.348269613655176e-06, + "loss": 0.0945, + "step": 382480 + }, + { + "epoch": 0.85, + "learning_rate": 7.347151070445851e-06, + "loss": 0.0912, + "step": 382490 + }, + { + "epoch": 0.85, + "learning_rate": 7.346032527236528e-06, + "loss": 0.0985, + "step": 382500 + }, + { + "epoch": 0.85, + "learning_rate": 7.344913984027203e-06, + "loss": 0.1008, + "step": 382510 + }, + { + "epoch": 0.85, + "learning_rate": 7.343795440817878e-06, + "loss": 0.0997, + "step": 382520 + }, + { + "epoch": 0.85, + "learning_rate": 7.3426768976085554e-06, + "loss": 0.0971, + "step": 382530 + }, + { + "epoch": 0.85, + "learning_rate": 7.341558354399231e-06, + "loss": 0.0927, + "step": 382540 + }, + { + "epoch": 0.85, + "learning_rate": 7.340439811189907e-06, + "loss": 0.098, + "step": 382550 + }, + { + "epoch": 0.85, + "learning_rate": 7.3393212679805824e-06, + "loss": 0.0989, + "step": 382560 + }, + { + "epoch": 0.85, + "learning_rate": 7.338202724771258e-06, + "loss": 0.0944, + "step": 382570 + }, + { + "epoch": 0.85, + "learning_rate": 7.337084181561935e-06, + "loss": 0.0904, + "step": 382580 + }, + { + "epoch": 0.85, + "learning_rate": 7.3359656383526095e-06, + "loss": 0.0976, + "step": 382590 + }, + { + "epoch": 0.85, + "learning_rate": 7.334847095143285e-06, + "loss": 0.095, + "step": 382600 + }, + { + "epoch": 0.85, + "learning_rate": 7.333728551933962e-06, + "loss": 0.0979, + "step": 382610 + }, + { + "epoch": 0.85, + "learning_rate": 7.332610008724637e-06, + "loss": 0.0947, + "step": 382620 + }, + { + "epoch": 0.85, + "learning_rate": 7.3314914655153135e-06, + "loss": 0.0931, + "step": 382630 + }, + { + "epoch": 0.85, + "learning_rate": 7.330372922305989e-06, + "loss": 0.099, + "step": 382640 + }, + { + "epoch": 0.85, + "learning_rate": 7.329254379096664e-06, + "loss": 0.0949, + "step": 382650 + }, + { + "epoch": 0.85, + "learning_rate": 7.328135835887341e-06, + "loss": 0.0985, + "step": 382660 + }, + { + "epoch": 0.85, + "learning_rate": 7.327017292678017e-06, + "loss": 0.0943, + "step": 382670 + }, + { + "epoch": 0.85, + "learning_rate": 7.325898749468692e-06, + "loss": 0.0975, + "step": 382680 + }, + { + "epoch": 0.85, + "learning_rate": 7.324780206259368e-06, + "loss": 0.0973, + "step": 382690 + }, + { + "epoch": 0.85, + "learning_rate": 7.323661663050044e-06, + "loss": 0.0905, + "step": 382700 + }, + { + "epoch": 0.85, + "learning_rate": 7.32254311984072e-06, + "loss": 0.0924, + "step": 382710 + }, + { + "epoch": 0.85, + "learning_rate": 7.321424576631395e-06, + "loss": 0.1021, + "step": 382720 + }, + { + "epoch": 0.85, + "learning_rate": 7.320306033422071e-06, + "loss": 0.1032, + "step": 382730 + }, + { + "epoch": 0.85, + "learning_rate": 7.319187490212748e-06, + "loss": 0.0989, + "step": 382740 + }, + { + "epoch": 0.85, + "learning_rate": 7.318068947003423e-06, + "loss": 0.0996, + "step": 382750 + }, + { + "epoch": 0.85, + "learning_rate": 7.316950403794099e-06, + "loss": 0.0952, + "step": 382760 + }, + { + "epoch": 0.85, + "learning_rate": 7.315831860584775e-06, + "loss": 0.0974, + "step": 382770 + }, + { + "epoch": 0.85, + "learning_rate": 7.31471331737545e-06, + "loss": 0.0921, + "step": 382780 + }, + { + "epoch": 0.85, + "learning_rate": 7.313594774166127e-06, + "loss": 0.0947, + "step": 382790 + }, + { + "epoch": 0.85, + "learning_rate": 7.312476230956803e-06, + "loss": 0.0943, + "step": 382800 + }, + { + "epoch": 0.85, + "learning_rate": 7.311357687747477e-06, + "loss": 0.1002, + "step": 382810 + }, + { + "epoch": 0.85, + "learning_rate": 7.310239144538154e-06, + "loss": 0.0936, + "step": 382820 + }, + { + "epoch": 0.85, + "learning_rate": 7.30912060132883e-06, + "loss": 0.0965, + "step": 382830 + }, + { + "epoch": 0.85, + "learning_rate": 7.308002058119505e-06, + "loss": 0.0927, + "step": 382840 + }, + { + "epoch": 0.85, + "learning_rate": 7.306883514910181e-06, + "loss": 0.0968, + "step": 382850 + }, + { + "epoch": 0.85, + "learning_rate": 7.305764971700857e-06, + "loss": 0.0951, + "step": 382860 + }, + { + "epoch": 0.85, + "learning_rate": 7.304646428491534e-06, + "loss": 0.0942, + "step": 382870 + }, + { + "epoch": 0.85, + "learning_rate": 7.303527885282209e-06, + "loss": 0.1006, + "step": 382880 + }, + { + "epoch": 0.85, + "learning_rate": 7.302409342072885e-06, + "loss": 0.1017, + "step": 382890 + }, + { + "epoch": 0.85, + "learning_rate": 7.301290798863561e-06, + "loss": 0.0966, + "step": 382900 + }, + { + "epoch": 0.85, + "learning_rate": 7.300172255654236e-06, + "loss": 0.0934, + "step": 382910 + }, + { + "epoch": 0.85, + "learning_rate": 7.299053712444912e-06, + "loss": 0.0956, + "step": 382920 + }, + { + "epoch": 0.85, + "learning_rate": 7.297935169235588e-06, + "loss": 0.0945, + "step": 382930 + }, + { + "epoch": 0.85, + "learning_rate": 7.296816626026263e-06, + "loss": 0.0999, + "step": 382940 + }, + { + "epoch": 0.85, + "learning_rate": 7.29569808281694e-06, + "loss": 0.0978, + "step": 382950 + }, + { + "epoch": 0.85, + "learning_rate": 7.294579539607616e-06, + "loss": 0.0931, + "step": 382960 + }, + { + "epoch": 0.85, + "learning_rate": 7.293460996398291e-06, + "loss": 0.0999, + "step": 382970 + }, + { + "epoch": 0.85, + "learning_rate": 7.292342453188967e-06, + "loss": 0.0943, + "step": 382980 + }, + { + "epoch": 0.85, + "learning_rate": 7.291223909979643e-06, + "loss": 0.0987, + "step": 382990 + }, + { + "epoch": 0.85, + "learning_rate": 7.290105366770318e-06, + "loss": 0.0966, + "step": 383000 + }, + { + "epoch": 0.85, + "learning_rate": 7.288986823560995e-06, + "loss": 0.0973, + "step": 383010 + }, + { + "epoch": 0.85, + "learning_rate": 7.28786828035167e-06, + "loss": 0.0958, + "step": 383020 + }, + { + "epoch": 0.85, + "learning_rate": 7.286749737142347e-06, + "loss": 0.0972, + "step": 383030 + }, + { + "epoch": 0.85, + "learning_rate": 7.285631193933022e-06, + "loss": 0.0973, + "step": 383040 + }, + { + "epoch": 0.86, + "learning_rate": 7.2845126507236976e-06, + "loss": 0.0951, + "step": 383050 + }, + { + "epoch": 0.86, + "learning_rate": 7.283394107514374e-06, + "loss": 0.095, + "step": 383060 + }, + { + "epoch": 0.86, + "learning_rate": 7.282275564305049e-06, + "loss": 0.0982, + "step": 383070 + }, + { + "epoch": 0.86, + "learning_rate": 7.2811570210957246e-06, + "loss": 0.0983, + "step": 383080 + }, + { + "epoch": 0.86, + "learning_rate": 7.280038477886402e-06, + "loss": 0.0951, + "step": 383090 + }, + { + "epoch": 0.86, + "learning_rate": 7.278919934677077e-06, + "loss": 0.0954, + "step": 383100 + }, + { + "epoch": 0.86, + "learning_rate": 7.277801391467753e-06, + "loss": 0.0984, + "step": 383110 + }, + { + "epoch": 0.86, + "learning_rate": 7.276682848258429e-06, + "loss": 0.0997, + "step": 383120 + }, + { + "epoch": 0.86, + "learning_rate": 7.275564305049104e-06, + "loss": 0.0988, + "step": 383130 + }, + { + "epoch": 0.86, + "learning_rate": 7.274445761839781e-06, + "loss": 0.0964, + "step": 383140 + }, + { + "epoch": 0.86, + "learning_rate": 7.273327218630456e-06, + "loss": 0.0941, + "step": 383150 + }, + { + "epoch": 0.86, + "learning_rate": 7.272208675421131e-06, + "loss": 0.0961, + "step": 383160 + }, + { + "epoch": 0.86, + "learning_rate": 7.271090132211808e-06, + "loss": 0.1003, + "step": 383170 + }, + { + "epoch": 0.86, + "learning_rate": 7.2699715890024835e-06, + "loss": 0.0954, + "step": 383180 + }, + { + "epoch": 0.86, + "learning_rate": 7.26885304579316e-06, + "loss": 0.0906, + "step": 383190 + }, + { + "epoch": 0.86, + "learning_rate": 7.267734502583835e-06, + "loss": 0.0983, + "step": 383200 + }, + { + "epoch": 0.86, + "learning_rate": 7.2666159593745105e-06, + "loss": 0.0984, + "step": 383210 + }, + { + "epoch": 0.86, + "learning_rate": 7.265497416165188e-06, + "loss": 0.0997, + "step": 383220 + }, + { + "epoch": 0.86, + "learning_rate": 7.264378872955863e-06, + "loss": 0.0983, + "step": 383230 + }, + { + "epoch": 0.86, + "learning_rate": 7.2632603297465375e-06, + "loss": 0.1012, + "step": 383240 + }, + { + "epoch": 0.86, + "learning_rate": 7.262141786537215e-06, + "loss": 0.0984, + "step": 383250 + }, + { + "epoch": 0.86, + "learning_rate": 7.26102324332789e-06, + "loss": 0.0946, + "step": 383260 + }, + { + "epoch": 0.86, + "learning_rate": 7.259904700118566e-06, + "loss": 0.0963, + "step": 383270 + }, + { + "epoch": 0.86, + "learning_rate": 7.258786156909242e-06, + "loss": 0.0965, + "step": 383280 + }, + { + "epoch": 0.86, + "learning_rate": 7.257667613699917e-06, + "loss": 0.0958, + "step": 383290 + }, + { + "epoch": 0.86, + "learning_rate": 7.256549070490594e-06, + "loss": 0.0964, + "step": 383300 + }, + { + "epoch": 0.86, + "learning_rate": 7.2554305272812695e-06, + "loss": 0.0975, + "step": 383310 + }, + { + "epoch": 0.86, + "learning_rate": 7.254311984071945e-06, + "loss": 0.0952, + "step": 383320 + }, + { + "epoch": 0.86, + "learning_rate": 7.253305295183553e-06, + "loss": 0.0998, + "step": 383330 + }, + { + "epoch": 0.86, + "learning_rate": 7.252186751974228e-06, + "loss": 0.0977, + "step": 383340 + }, + { + "epoch": 0.86, + "learning_rate": 7.251068208764905e-06, + "loss": 0.0981, + "step": 383350 + }, + { + "epoch": 0.86, + "learning_rate": 7.249949665555581e-06, + "loss": 0.0953, + "step": 383360 + }, + { + "epoch": 0.86, + "learning_rate": 7.248831122346257e-06, + "loss": 0.0952, + "step": 383370 + }, + { + "epoch": 0.86, + "learning_rate": 7.247712579136932e-06, + "loss": 0.0971, + "step": 383380 + }, + { + "epoch": 0.86, + "learning_rate": 7.246594035927608e-06, + "loss": 0.0983, + "step": 383390 + }, + { + "epoch": 0.86, + "learning_rate": 7.245475492718285e-06, + "loss": 0.0973, + "step": 383400 + }, + { + "epoch": 0.86, + "learning_rate": 7.24435694950896e-06, + "loss": 0.0964, + "step": 383410 + }, + { + "epoch": 0.86, + "learning_rate": 7.243238406299635e-06, + "loss": 0.0942, + "step": 383420 + }, + { + "epoch": 0.86, + "learning_rate": 7.242119863090312e-06, + "loss": 0.0973, + "step": 383430 + }, + { + "epoch": 0.86, + "learning_rate": 7.241001319880987e-06, + "loss": 0.098, + "step": 383440 + }, + { + "epoch": 0.86, + "learning_rate": 7.239882776671663e-06, + "loss": 0.0998, + "step": 383450 + }, + { + "epoch": 0.86, + "learning_rate": 7.238764233462339e-06, + "loss": 0.0922, + "step": 383460 + }, + { + "epoch": 0.86, + "learning_rate": 7.237645690253014e-06, + "loss": 0.0936, + "step": 383470 + }, + { + "epoch": 0.86, + "learning_rate": 7.236527147043691e-06, + "loss": 0.0964, + "step": 383480 + }, + { + "epoch": 0.86, + "learning_rate": 7.235408603834367e-06, + "loss": 0.0989, + "step": 383490 + }, + { + "epoch": 0.86, + "learning_rate": 7.234290060625042e-06, + "loss": 0.0988, + "step": 383500 + }, + { + "epoch": 0.86, + "learning_rate": 7.233171517415718e-06, + "loss": 0.0963, + "step": 383510 + }, + { + "epoch": 0.86, + "learning_rate": 7.232052974206394e-06, + "loss": 0.0963, + "step": 383520 + }, + { + "epoch": 0.86, + "learning_rate": 7.230934430997071e-06, + "loss": 0.0978, + "step": 383530 + }, + { + "epoch": 0.86, + "learning_rate": 7.229815887787745e-06, + "loss": 0.0954, + "step": 383540 + }, + { + "epoch": 0.86, + "learning_rate": 7.228697344578421e-06, + "loss": 0.0938, + "step": 383550 + }, + { + "epoch": 0.86, + "learning_rate": 7.227578801369098e-06, + "loss": 0.1, + "step": 383560 + }, + { + "epoch": 0.86, + "learning_rate": 7.226460258159773e-06, + "loss": 0.0965, + "step": 383570 + }, + { + "epoch": 0.86, + "learning_rate": 7.2253417149504485e-06, + "loss": 0.0956, + "step": 383580 + }, + { + "epoch": 0.86, + "learning_rate": 7.224223171741125e-06, + "loss": 0.1003, + "step": 383590 + }, + { + "epoch": 0.86, + "learning_rate": 7.2231046285318e-06, + "loss": 0.0953, + "step": 383600 + }, + { + "epoch": 0.86, + "learning_rate": 7.221986085322477e-06, + "loss": 0.099, + "step": 383610 + }, + { + "epoch": 0.86, + "learning_rate": 7.2208675421131526e-06, + "loss": 0.0918, + "step": 383620 + }, + { + "epoch": 0.86, + "learning_rate": 7.219748998903827e-06, + "loss": 0.1002, + "step": 383630 + }, + { + "epoch": 0.86, + "learning_rate": 7.218630455694504e-06, + "loss": 0.0926, + "step": 383640 + }, + { + "epoch": 0.86, + "learning_rate": 7.2175119124851796e-06, + "loss": 0.099, + "step": 383650 + }, + { + "epoch": 0.86, + "learning_rate": 7.216393369275855e-06, + "loss": 0.0975, + "step": 383660 + }, + { + "epoch": 0.86, + "learning_rate": 7.215274826066531e-06, + "loss": 0.0988, + "step": 383670 + }, + { + "epoch": 0.86, + "learning_rate": 7.2141562828572066e-06, + "loss": 0.0977, + "step": 383680 + }, + { + "epoch": 0.86, + "learning_rate": 7.213037739647884e-06, + "loss": 0.0976, + "step": 383690 + }, + { + "epoch": 0.86, + "learning_rate": 7.211919196438559e-06, + "loss": 0.0962, + "step": 383700 + }, + { + "epoch": 0.86, + "learning_rate": 7.2108006532292344e-06, + "loss": 0.0933, + "step": 383710 + }, + { + "epoch": 0.86, + "learning_rate": 7.209682110019911e-06, + "loss": 0.0939, + "step": 383720 + }, + { + "epoch": 0.86, + "learning_rate": 7.208563566810586e-06, + "loss": 0.0935, + "step": 383730 + }, + { + "epoch": 0.86, + "learning_rate": 7.2074450236012614e-06, + "loss": 0.0938, + "step": 383740 + }, + { + "epoch": 0.86, + "learning_rate": 7.206326480391938e-06, + "loss": 0.0978, + "step": 383750 + }, + { + "epoch": 0.86, + "learning_rate": 7.205207937182613e-06, + "loss": 0.0957, + "step": 383760 + }, + { + "epoch": 0.86, + "learning_rate": 7.20408939397329e-06, + "loss": 0.0965, + "step": 383770 + }, + { + "epoch": 0.86, + "learning_rate": 7.2029708507639655e-06, + "loss": 0.0967, + "step": 383780 + }, + { + "epoch": 0.86, + "learning_rate": 7.201852307554641e-06, + "loss": 0.0914, + "step": 383790 + }, + { + "epoch": 0.86, + "learning_rate": 7.200733764345317e-06, + "loss": 0.0971, + "step": 383800 + }, + { + "epoch": 0.86, + "learning_rate": 7.1996152211359925e-06, + "loss": 0.098, + "step": 383810 + }, + { + "epoch": 0.86, + "learning_rate": 7.198496677926668e-06, + "loss": 0.1023, + "step": 383820 + }, + { + "epoch": 0.86, + "learning_rate": 7.197378134717345e-06, + "loss": 0.0989, + "step": 383830 + }, + { + "epoch": 0.86, + "learning_rate": 7.19625959150802e-06, + "loss": 0.096, + "step": 383840 + }, + { + "epoch": 0.86, + "learning_rate": 7.195141048298697e-06, + "loss": 0.0941, + "step": 383850 + }, + { + "epoch": 0.86, + "learning_rate": 7.194022505089372e-06, + "loss": 0.0957, + "step": 383860 + }, + { + "epoch": 0.86, + "learning_rate": 7.192903961880047e-06, + "loss": 0.0959, + "step": 383870 + }, + { + "epoch": 0.86, + "learning_rate": 7.191785418670724e-06, + "loss": 0.0971, + "step": 383880 + }, + { + "epoch": 0.86, + "learning_rate": 7.190666875461399e-06, + "loss": 0.0958, + "step": 383890 + }, + { + "epoch": 0.86, + "learning_rate": 7.189548332252074e-06, + "loss": 0.094, + "step": 383900 + }, + { + "epoch": 0.86, + "learning_rate": 7.1884297890427515e-06, + "loss": 0.1003, + "step": 383910 + }, + { + "epoch": 0.86, + "learning_rate": 7.187311245833427e-06, + "loss": 0.0931, + "step": 383920 + }, + { + "epoch": 0.86, + "learning_rate": 7.186192702624103e-06, + "loss": 0.0946, + "step": 383930 + }, + { + "epoch": 0.86, + "learning_rate": 7.1850741594147785e-06, + "loss": 0.0985, + "step": 383940 + }, + { + "epoch": 0.86, + "learning_rate": 7.183955616205454e-06, + "loss": 0.0939, + "step": 383950 + }, + { + "epoch": 0.86, + "learning_rate": 7.182837072996131e-06, + "loss": 0.0981, + "step": 383960 + }, + { + "epoch": 0.86, + "learning_rate": 7.1817185297868055e-06, + "loss": 0.0958, + "step": 383970 + }, + { + "epoch": 0.86, + "learning_rate": 7.180599986577481e-06, + "loss": 0.0997, + "step": 383980 + }, + { + "epoch": 0.86, + "learning_rate": 7.179481443368158e-06, + "loss": 0.0954, + "step": 383990 + }, + { + "epoch": 0.86, + "learning_rate": 7.178362900158833e-06, + "loss": 0.0967, + "step": 384000 + }, + { + "epoch": 0.86, + "eval_NEIMS_canon_smiles": 0.9607833333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.25933333333333336, + "eval_NEIMS_daylight_tanimoto_simil": 0.6267563233740708, + "eval_NEIMS_exact_mols": 0.25903333333333334, + "eval_NEIMS_exact_smiles": 0.2536, + "eval_NEIMS_loss": 0.12484291940927505, + "eval_NEIMS_matched_formulas": 0.7617, + "eval_NEIMS_morgan_tanimoto_simil": 0.5537638786876777, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.2597333333333333, + "eval_NEIMS_runtime": 719.2732, + "eval_NEIMS_samples_per_second": 83.418, + "eval_NEIMS_steps_per_second": 1.304, + "step": 384000 + }, + { + "epoch": 0.86, + "eval_RASSP_canon_smiles": 0.9588773499849734, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.33893211340034063, + "eval_RASSP_daylight_tanimoto_simil": 0.7259697438813308, + "eval_RASSP_exact_mols": 0.3379136474438174, + "eval_RASSP_exact_smiles": 0.3304671586469429, + "eval_RASSP_loss": 0.0959290936589241, + "eval_RASSP_matched_formulas": 0.886666444051157, + "eval_RASSP_morgan_tanimoto_simil": 0.6220087404547321, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.3380806090760343, + "eval_RASSP_runtime": 820.4667, + "eval_RASSP_samples_per_second": 73.0, + "eval_RASSP_steps_per_second": 1.141, + "step": 384000 + }, + { + "epoch": 0.86, + "eval_NEIMS_old_canon_smiles": 0.9624333333333334, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2599, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6267138465153401, + "eval_NEIMS_old_exact_mols": 0.25956666666666667, + "eval_NEIMS_old_exact_smiles": 0.2537333333333333, + "eval_NEIMS_old_loss": 0.12479431927204132, + "eval_NEIMS_old_matched_formulas": 0.7629666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5545085504008672, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2603, + "eval_NEIMS_old_runtime": 361.8958, + "eval_NEIMS_old_samples_per_second": 82.897, + "eval_NEIMS_old_steps_per_second": 1.296, + "step": 384000 + }, + { + "epoch": 0.86, + "eval_RASSP_old_canon_smiles": 0.9591217005372576, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.37007374778923485, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7438813181554336, + "eval_RASSP_old_exact_mols": 0.36910601661828013, + "eval_RASSP_old_exact_smiles": 0.36029632595855443, + "eval_RASSP_old_loss": 0.09004275500774384, + "eval_RASSP_old_matched_formulas": 0.8961524343444456, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6454019288548613, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.36927286682016885, + "eval_RASSP_old_runtime": 408.227, + "eval_RASSP_old_samples_per_second": 73.408, + "eval_RASSP_old_steps_per_second": 1.149, + "step": 384000 + }, + { + "epoch": 0.86, + "eval_NIST_canon_smiles": 0.8686162472938922, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.029314689285587534, + "eval_NIST_daylight_tanimoto_simil": 0.3041194723038319, + "eval_NIST_exact_mols": 0.02835646094332257, + "eval_NIST_exact_smiles": 0.026972353337828724, + "eval_NIST_loss": 1.751615285873413, + "eval_NIST_matched_formulas": 0.13085140362707173, + "eval_NIST_morgan_tanimoto_simil": 0.25491791360787763, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.028959789899563475, + "eval_NIST_runtime": 550.6393, + "eval_NIST_samples_per_second": 51.171, + "eval_NIST_steps_per_second": 0.801, + "step": 384000 + }, + { + "epoch": 0.86, + "learning_rate": 7.17724435694951e-06, + "loss": 0.0999, + "step": 384010 + }, + { + "epoch": 0.86, + "learning_rate": 7.176125813740185e-06, + "loss": 0.0969, + "step": 384020 + }, + { + "epoch": 0.86, + "learning_rate": 7.17500727053086e-06, + "loss": 0.0965, + "step": 384030 + }, + { + "epoch": 0.86, + "learning_rate": 7.1738887273215374e-06, + "loss": 0.0969, + "step": 384040 + }, + { + "epoch": 0.86, + "learning_rate": 7.172770184112213e-06, + "loss": 0.0947, + "step": 384050 + }, + { + "epoch": 0.86, + "learning_rate": 7.171651640902887e-06, + "loss": 0.0989, + "step": 384060 + }, + { + "epoch": 0.86, + "learning_rate": 7.1705330976935644e-06, + "loss": 0.0948, + "step": 384070 + }, + { + "epoch": 0.86, + "learning_rate": 7.16941455448424e-06, + "loss": 0.0945, + "step": 384080 + }, + { + "epoch": 0.86, + "learning_rate": 7.168296011274916e-06, + "loss": 0.0913, + "step": 384090 + }, + { + "epoch": 0.86, + "learning_rate": 7.1671774680655914e-06, + "loss": 0.0969, + "step": 384100 + }, + { + "epoch": 0.86, + "learning_rate": 7.166058924856267e-06, + "loss": 0.0944, + "step": 384110 + }, + { + "epoch": 0.86, + "learning_rate": 7.164940381646944e-06, + "loss": 0.097, + "step": 384120 + }, + { + "epoch": 0.86, + "learning_rate": 7.163821838437619e-06, + "loss": 0.0936, + "step": 384130 + }, + { + "epoch": 0.86, + "learning_rate": 7.162703295228295e-06, + "loss": 0.0963, + "step": 384140 + }, + { + "epoch": 0.86, + "learning_rate": 7.161584752018971e-06, + "loss": 0.0974, + "step": 384150 + }, + { + "epoch": 0.86, + "learning_rate": 7.160466208809646e-06, + "loss": 0.0947, + "step": 384160 + }, + { + "epoch": 0.86, + "learning_rate": 7.159347665600323e-06, + "loss": 0.0918, + "step": 384170 + }, + { + "epoch": 0.86, + "learning_rate": 7.158229122390999e-06, + "loss": 0.0989, + "step": 384180 + }, + { + "epoch": 0.86, + "learning_rate": 7.157110579181673e-06, + "loss": 0.0954, + "step": 384190 + }, + { + "epoch": 0.86, + "learning_rate": 7.15599203597235e-06, + "loss": 0.0953, + "step": 384200 + }, + { + "epoch": 0.86, + "learning_rate": 7.154873492763026e-06, + "loss": 0.0992, + "step": 384210 + }, + { + "epoch": 0.86, + "learning_rate": 7.153754949553701e-06, + "loss": 0.0936, + "step": 384220 + }, + { + "epoch": 0.86, + "learning_rate": 7.152636406344377e-06, + "loss": 0.0938, + "step": 384230 + }, + { + "epoch": 0.86, + "learning_rate": 7.151517863135053e-06, + "loss": 0.0969, + "step": 384240 + }, + { + "epoch": 0.86, + "learning_rate": 7.15039931992573e-06, + "loss": 0.0972, + "step": 384250 + }, + { + "epoch": 0.86, + "learning_rate": 7.149280776716405e-06, + "loss": 0.0927, + "step": 384260 + }, + { + "epoch": 0.86, + "learning_rate": 7.148162233507081e-06, + "loss": 0.0991, + "step": 384270 + }, + { + "epoch": 0.86, + "learning_rate": 7.147043690297757e-06, + "loss": 0.1012, + "step": 384280 + }, + { + "epoch": 0.86, + "learning_rate": 7.145925147088432e-06, + "loss": 0.0893, + "step": 384290 + }, + { + "epoch": 0.86, + "learning_rate": 7.144806603879108e-06, + "loss": 0.0967, + "step": 384300 + }, + { + "epoch": 0.86, + "learning_rate": 7.143688060669784e-06, + "loss": 0.0972, + "step": 384310 + }, + { + "epoch": 0.86, + "learning_rate": 7.142569517460459e-06, + "loss": 0.0987, + "step": 384320 + }, + { + "epoch": 0.86, + "learning_rate": 7.141450974251136e-06, + "loss": 0.0972, + "step": 384330 + }, + { + "epoch": 0.86, + "learning_rate": 7.140332431041812e-06, + "loss": 0.0943, + "step": 384340 + }, + { + "epoch": 0.86, + "learning_rate": 7.139213887832487e-06, + "loss": 0.0974, + "step": 384350 + }, + { + "epoch": 0.86, + "learning_rate": 7.138095344623163e-06, + "loss": 0.0938, + "step": 384360 + }, + { + "epoch": 0.86, + "learning_rate": 7.136976801413839e-06, + "loss": 0.0971, + "step": 384370 + }, + { + "epoch": 0.86, + "learning_rate": 7.135858258204514e-06, + "loss": 0.0989, + "step": 384380 + }, + { + "epoch": 0.86, + "learning_rate": 7.134739714995191e-06, + "loss": 0.0979, + "step": 384390 + }, + { + "epoch": 0.86, + "learning_rate": 7.133621171785866e-06, + "loss": 0.0946, + "step": 384400 + }, + { + "epoch": 0.86, + "learning_rate": 7.132502628576543e-06, + "loss": 0.1008, + "step": 384410 + }, + { + "epoch": 0.86, + "learning_rate": 7.131384085367218e-06, + "loss": 0.096, + "step": 384420 + }, + { + "epoch": 0.86, + "learning_rate": 7.130265542157894e-06, + "loss": 0.1002, + "step": 384430 + }, + { + "epoch": 0.86, + "learning_rate": 7.12914699894857e-06, + "loss": 0.0949, + "step": 384440 + }, + { + "epoch": 0.86, + "learning_rate": 7.128028455739245e-06, + "loss": 0.0988, + "step": 384450 + }, + { + "epoch": 0.86, + "learning_rate": 7.126909912529921e-06, + "loss": 0.097, + "step": 384460 + }, + { + "epoch": 0.86, + "learning_rate": 7.125791369320598e-06, + "loss": 0.0934, + "step": 384470 + }, + { + "epoch": 0.86, + "learning_rate": 7.124672826111273e-06, + "loss": 0.0947, + "step": 384480 + }, + { + "epoch": 0.86, + "learning_rate": 7.123554282901949e-06, + "loss": 0.0945, + "step": 384490 + }, + { + "epoch": 0.86, + "learning_rate": 7.122435739692625e-06, + "loss": 0.0955, + "step": 384500 + }, + { + "epoch": 0.86, + "learning_rate": 7.1213171964833e-06, + "loss": 0.0945, + "step": 384510 + }, + { + "epoch": 0.86, + "learning_rate": 7.120198653273976e-06, + "loss": 0.0963, + "step": 384520 + }, + { + "epoch": 0.86, + "learning_rate": 7.119080110064652e-06, + "loss": 0.093, + "step": 384530 + }, + { + "epoch": 0.86, + "learning_rate": 7.117961566855327e-06, + "loss": 0.0983, + "step": 384540 + }, + { + "epoch": 0.86, + "learning_rate": 7.116843023646004e-06, + "loss": 0.0957, + "step": 384550 + }, + { + "epoch": 0.86, + "learning_rate": 7.1157244804366796e-06, + "loss": 0.0944, + "step": 384560 + }, + { + "epoch": 0.86, + "learning_rate": 7.114605937227356e-06, + "loss": 0.0972, + "step": 384570 + }, + { + "epoch": 0.86, + "learning_rate": 7.113487394018031e-06, + "loss": 0.096, + "step": 384580 + }, + { + "epoch": 0.86, + "learning_rate": 7.1123688508087066e-06, + "loss": 0.0963, + "step": 384590 + }, + { + "epoch": 0.86, + "learning_rate": 7.111250307599384e-06, + "loss": 0.0973, + "step": 384600 + }, + { + "epoch": 0.86, + "learning_rate": 7.110131764390059e-06, + "loss": 0.0974, + "step": 384610 + }, + { + "epoch": 0.86, + "learning_rate": 7.1090132211807336e-06, + "loss": 0.0993, + "step": 384620 + }, + { + "epoch": 0.86, + "learning_rate": 7.107894677971411e-06, + "loss": 0.0929, + "step": 384630 + }, + { + "epoch": 0.86, + "learning_rate": 7.106776134762086e-06, + "loss": 0.0959, + "step": 384640 + }, + { + "epoch": 0.86, + "learning_rate": 7.105657591552762e-06, + "loss": 0.0919, + "step": 384650 + }, + { + "epoch": 0.86, + "learning_rate": 7.104539048343438e-06, + "loss": 0.0919, + "step": 384660 + }, + { + "epoch": 0.86, + "learning_rate": 7.103420505134113e-06, + "loss": 0.094, + "step": 384670 + }, + { + "epoch": 0.86, + "learning_rate": 7.10230196192479e-06, + "loss": 0.0974, + "step": 384680 + }, + { + "epoch": 0.86, + "learning_rate": 7.1011834187154655e-06, + "loss": 0.099, + "step": 384690 + }, + { + "epoch": 0.86, + "learning_rate": 7.100064875506141e-06, + "loss": 0.0966, + "step": 384700 + }, + { + "epoch": 0.86, + "learning_rate": 7.098946332296817e-06, + "loss": 0.0974, + "step": 384710 + }, + { + "epoch": 0.86, + "learning_rate": 7.0978277890874925e-06, + "loss": 0.0993, + "step": 384720 + }, + { + "epoch": 0.86, + "learning_rate": 7.09670924587817e-06, + "loss": 0.0981, + "step": 384730 + }, + { + "epoch": 0.86, + "learning_rate": 7.095590702668844e-06, + "loss": 0.0983, + "step": 384740 + }, + { + "epoch": 0.86, + "learning_rate": 7.0944721594595195e-06, + "loss": 0.0986, + "step": 384750 + }, + { + "epoch": 0.86, + "learning_rate": 7.093353616250197e-06, + "loss": 0.1002, + "step": 384760 + }, + { + "epoch": 0.86, + "learning_rate": 7.092235073040872e-06, + "loss": 0.094, + "step": 384770 + }, + { + "epoch": 0.86, + "learning_rate": 7.091116529831547e-06, + "loss": 0.1002, + "step": 384780 + }, + { + "epoch": 0.86, + "learning_rate": 7.089997986622224e-06, + "loss": 0.0953, + "step": 384790 + }, + { + "epoch": 0.86, + "learning_rate": 7.088879443412899e-06, + "loss": 0.0959, + "step": 384800 + }, + { + "epoch": 0.86, + "learning_rate": 7.087760900203576e-06, + "loss": 0.1006, + "step": 384810 + }, + { + "epoch": 0.86, + "learning_rate": 7.0866423569942515e-06, + "loss": 0.1004, + "step": 384820 + }, + { + "epoch": 0.86, + "learning_rate": 7.085523813784926e-06, + "loss": 0.098, + "step": 384830 + }, + { + "epoch": 0.86, + "learning_rate": 7.084405270575603e-06, + "loss": 0.0965, + "step": 384840 + }, + { + "epoch": 0.86, + "learning_rate": 7.0832867273662785e-06, + "loss": 0.0941, + "step": 384850 + }, + { + "epoch": 0.86, + "learning_rate": 7.082168184156954e-06, + "loss": 0.0943, + "step": 384860 + }, + { + "epoch": 0.86, + "learning_rate": 7.08104964094763e-06, + "loss": 0.0965, + "step": 384870 + }, + { + "epoch": 0.86, + "learning_rate": 7.0799310977383055e-06, + "loss": 0.0981, + "step": 384880 + }, + { + "epoch": 0.86, + "learning_rate": 7.0788125545289826e-06, + "loss": 0.0954, + "step": 384890 + }, + { + "epoch": 0.86, + "learning_rate": 7.077694011319658e-06, + "loss": 0.095, + "step": 384900 + }, + { + "epoch": 0.86, + "learning_rate": 7.076575468110333e-06, + "loss": 0.0918, + "step": 384910 + }, + { + "epoch": 0.86, + "learning_rate": 7.0754569249010096e-06, + "loss": 0.0989, + "step": 384920 + }, + { + "epoch": 0.86, + "learning_rate": 7.074338381691685e-06, + "loss": 0.0991, + "step": 384930 + }, + { + "epoch": 0.86, + "learning_rate": 7.07321983848236e-06, + "loss": 0.0979, + "step": 384940 + }, + { + "epoch": 0.86, + "learning_rate": 7.0721012952730366e-06, + "loss": 0.0946, + "step": 384950 + }, + { + "epoch": 0.86, + "learning_rate": 7.070982752063712e-06, + "loss": 0.094, + "step": 384960 + }, + { + "epoch": 0.86, + "learning_rate": 7.069864208854389e-06, + "loss": 0.0944, + "step": 384970 + }, + { + "epoch": 0.86, + "learning_rate": 7.0687456656450644e-06, + "loss": 0.1013, + "step": 384980 + }, + { + "epoch": 0.86, + "learning_rate": 7.06762712243574e-06, + "loss": 0.0982, + "step": 384990 + }, + { + "epoch": 0.86, + "learning_rate": 7.066508579226416e-06, + "loss": 0.1049, + "step": 385000 + }, + { + "epoch": 0.86, + "learning_rate": 7.0653900360170914e-06, + "loss": 0.1001, + "step": 385010 + }, + { + "epoch": 0.86, + "learning_rate": 7.064271492807767e-06, + "loss": 0.0931, + "step": 385020 + }, + { + "epoch": 0.86, + "learning_rate": 7.063152949598444e-06, + "loss": 0.0947, + "step": 385030 + }, + { + "epoch": 0.86, + "learning_rate": 7.062034406389119e-06, + "loss": 0.096, + "step": 385040 + }, + { + "epoch": 0.86, + "learning_rate": 7.0609158631797955e-06, + "loss": 0.0936, + "step": 385050 + }, + { + "epoch": 0.86, + "learning_rate": 7.059797319970471e-06, + "loss": 0.0944, + "step": 385060 + }, + { + "epoch": 0.86, + "learning_rate": 7.058678776761146e-06, + "loss": 0.0969, + "step": 385070 + }, + { + "epoch": 0.86, + "learning_rate": 7.0575602335518225e-06, + "loss": 0.0929, + "step": 385080 + }, + { + "epoch": 0.86, + "learning_rate": 7.056441690342498e-06, + "loss": 0.0967, + "step": 385090 + }, + { + "epoch": 0.86, + "learning_rate": 7.055323147133173e-06, + "loss": 0.0991, + "step": 385100 + }, + { + "epoch": 0.86, + "learning_rate": 7.05420460392385e-06, + "loss": 0.0956, + "step": 385110 + }, + { + "epoch": 0.86, + "learning_rate": 7.053086060714526e-06, + "loss": 0.0989, + "step": 385120 + }, + { + "epoch": 0.86, + "learning_rate": 7.051967517505202e-06, + "loss": 0.0923, + "step": 385130 + }, + { + "epoch": 0.86, + "learning_rate": 7.050848974295877e-06, + "loss": 0.0981, + "step": 385140 + }, + { + "epoch": 0.86, + "learning_rate": 7.049730431086553e-06, + "loss": 0.0964, + "step": 385150 + }, + { + "epoch": 0.86, + "learning_rate": 7.04861188787723e-06, + "loss": 0.0933, + "step": 385160 + }, + { + "epoch": 0.86, + "learning_rate": 7.047493344667904e-06, + "loss": 0.0954, + "step": 385170 + }, + { + "epoch": 0.86, + "learning_rate": 7.04637480145858e-06, + "loss": 0.094, + "step": 385180 + }, + { + "epoch": 0.86, + "learning_rate": 7.045256258249257e-06, + "loss": 0.0971, + "step": 385190 + }, + { + "epoch": 0.86, + "learning_rate": 7.044137715039932e-06, + "loss": 0.099, + "step": 385200 + }, + { + "epoch": 0.86, + "learning_rate": 7.0430191718306085e-06, + "loss": 0.0985, + "step": 385210 + }, + { + "epoch": 0.86, + "learning_rate": 7.041900628621284e-06, + "loss": 0.0971, + "step": 385220 + }, + { + "epoch": 0.86, + "learning_rate": 7.040782085411959e-06, + "loss": 0.1006, + "step": 385230 + }, + { + "epoch": 0.86, + "learning_rate": 7.039663542202636e-06, + "loss": 0.0951, + "step": 385240 + }, + { + "epoch": 0.86, + "learning_rate": 7.038544998993312e-06, + "loss": 0.0952, + "step": 385250 + }, + { + "epoch": 0.86, + "learning_rate": 7.037426455783986e-06, + "loss": 0.096, + "step": 385260 + }, + { + "epoch": 0.86, + "learning_rate": 7.036307912574663e-06, + "loss": 0.0965, + "step": 385270 + }, + { + "epoch": 0.86, + "learning_rate": 7.035189369365339e-06, + "loss": 0.095, + "step": 385280 + }, + { + "epoch": 0.86, + "learning_rate": 7.034070826156015e-06, + "loss": 0.094, + "step": 385290 + }, + { + "epoch": 0.86, + "learning_rate": 7.03295228294669e-06, + "loss": 0.0969, + "step": 385300 + }, + { + "epoch": 0.86, + "learning_rate": 7.031833739737366e-06, + "loss": 0.0945, + "step": 385310 + }, + { + "epoch": 0.86, + "learning_rate": 7.030715196528043e-06, + "loss": 0.0975, + "step": 385320 + }, + { + "epoch": 0.86, + "learning_rate": 7.029596653318718e-06, + "loss": 0.0962, + "step": 385330 + }, + { + "epoch": 0.86, + "learning_rate": 7.028478110109394e-06, + "loss": 0.0908, + "step": 385340 + }, + { + "epoch": 0.86, + "learning_rate": 7.02735956690007e-06, + "loss": 0.0968, + "step": 385350 + }, + { + "epoch": 0.86, + "learning_rate": 7.026241023690745e-06, + "loss": 0.0973, + "step": 385360 + }, + { + "epoch": 0.86, + "learning_rate": 7.025122480481422e-06, + "loss": 0.0947, + "step": 385370 + }, + { + "epoch": 0.86, + "learning_rate": 7.024115791593029e-06, + "loss": 0.0976, + "step": 385380 + }, + { + "epoch": 0.86, + "learning_rate": 7.022997248383706e-06, + "loss": 0.0988, + "step": 385390 + }, + { + "epoch": 0.86, + "learning_rate": 7.021878705174381e-06, + "loss": 0.0985, + "step": 385400 + }, + { + "epoch": 0.86, + "learning_rate": 7.020760161965056e-06, + "loss": 0.0954, + "step": 385410 + }, + { + "epoch": 0.86, + "learning_rate": 7.0196416187557335e-06, + "loss": 0.0962, + "step": 385420 + }, + { + "epoch": 0.86, + "learning_rate": 7.018523075546409e-06, + "loss": 0.0953, + "step": 385430 + }, + { + "epoch": 0.86, + "learning_rate": 7.017404532337085e-06, + "loss": 0.0934, + "step": 385440 + }, + { + "epoch": 0.86, + "learning_rate": 7.0162859891277605e-06, + "loss": 0.0948, + "step": 385450 + }, + { + "epoch": 0.86, + "learning_rate": 7.015167445918436e-06, + "loss": 0.0972, + "step": 385460 + }, + { + "epoch": 0.86, + "learning_rate": 7.014048902709112e-06, + "loss": 0.0971, + "step": 385470 + }, + { + "epoch": 0.86, + "learning_rate": 7.0129303594997875e-06, + "loss": 0.0971, + "step": 385480 + }, + { + "epoch": 0.86, + "learning_rate": 7.011811816290463e-06, + "loss": 0.0945, + "step": 385490 + }, + { + "epoch": 0.86, + "learning_rate": 7.01069327308114e-06, + "loss": 0.0936, + "step": 385500 + }, + { + "epoch": 0.86, + "learning_rate": 7.009574729871815e-06, + "loss": 0.097, + "step": 385510 + }, + { + "epoch": 0.86, + "learning_rate": 7.0084561866624916e-06, + "loss": 0.0953, + "step": 385520 + }, + { + "epoch": 0.86, + "learning_rate": 7.007337643453167e-06, + "loss": 0.0945, + "step": 385530 + }, + { + "epoch": 0.86, + "learning_rate": 7.006219100243842e-06, + "loss": 0.1031, + "step": 385540 + }, + { + "epoch": 0.86, + "learning_rate": 7.005100557034519e-06, + "loss": 0.0972, + "step": 385550 + }, + { + "epoch": 0.86, + "learning_rate": 7.003982013825194e-06, + "loss": 0.0935, + "step": 385560 + }, + { + "epoch": 0.86, + "learning_rate": 7.002863470615869e-06, + "loss": 0.0969, + "step": 385570 + }, + { + "epoch": 0.86, + "learning_rate": 7.0017449274065464e-06, + "loss": 0.0969, + "step": 385580 + }, + { + "epoch": 0.86, + "learning_rate": 7.000626384197222e-06, + "loss": 0.0934, + "step": 385590 + }, + { + "epoch": 0.86, + "learning_rate": 6.999507840987898e-06, + "loss": 0.0944, + "step": 385600 + }, + { + "epoch": 0.86, + "learning_rate": 6.9983892977785734e-06, + "loss": 0.0959, + "step": 385610 + }, + { + "epoch": 0.86, + "learning_rate": 6.997270754569249e-06, + "loss": 0.0926, + "step": 385620 + }, + { + "epoch": 0.86, + "learning_rate": 6.996152211359926e-06, + "loss": 0.0974, + "step": 385630 + }, + { + "epoch": 0.86, + "learning_rate": 6.995033668150601e-06, + "loss": 0.0973, + "step": 385640 + }, + { + "epoch": 0.86, + "learning_rate": 6.993915124941277e-06, + "loss": 0.098, + "step": 385650 + }, + { + "epoch": 0.86, + "learning_rate": 6.992796581731953e-06, + "loss": 0.0976, + "step": 385660 + }, + { + "epoch": 0.86, + "learning_rate": 6.991678038522628e-06, + "loss": 0.0924, + "step": 385670 + }, + { + "epoch": 0.86, + "learning_rate": 6.9905594953133045e-06, + "loss": 0.0983, + "step": 385680 + }, + { + "epoch": 0.86, + "learning_rate": 6.98944095210398e-06, + "loss": 0.0976, + "step": 385690 + }, + { + "epoch": 0.86, + "learning_rate": 6.988322408894655e-06, + "loss": 0.0982, + "step": 385700 + }, + { + "epoch": 0.86, + "learning_rate": 6.987203865685332e-06, + "loss": 0.0982, + "step": 385710 + }, + { + "epoch": 0.86, + "learning_rate": 6.986085322476008e-06, + "loss": 0.0931, + "step": 385720 + }, + { + "epoch": 0.86, + "learning_rate": 6.984966779266683e-06, + "loss": 0.0951, + "step": 385730 + }, + { + "epoch": 0.86, + "learning_rate": 6.983848236057359e-06, + "loss": 0.0939, + "step": 385740 + }, + { + "epoch": 0.86, + "learning_rate": 6.982729692848035e-06, + "loss": 0.0904, + "step": 385750 + }, + { + "epoch": 0.86, + "learning_rate": 6.981611149638712e-06, + "loss": 0.0951, + "step": 385760 + }, + { + "epoch": 0.86, + "learning_rate": 6.980492606429387e-06, + "loss": 0.0971, + "step": 385770 + }, + { + "epoch": 0.86, + "learning_rate": 6.979374063220062e-06, + "loss": 0.0967, + "step": 385780 + }, + { + "epoch": 0.86, + "learning_rate": 6.978255520010739e-06, + "loss": 0.0967, + "step": 385790 + }, + { + "epoch": 0.86, + "learning_rate": 6.977136976801414e-06, + "loss": 0.0958, + "step": 385800 + }, + { + "epoch": 0.86, + "learning_rate": 6.97601843359209e-06, + "loss": 0.0972, + "step": 385810 + }, + { + "epoch": 0.86, + "learning_rate": 6.974899890382766e-06, + "loss": 0.0921, + "step": 385820 + }, + { + "epoch": 0.86, + "learning_rate": 6.973781347173441e-06, + "loss": 0.0948, + "step": 385830 + }, + { + "epoch": 0.86, + "learning_rate": 6.972662803964118e-06, + "loss": 0.0937, + "step": 385840 + }, + { + "epoch": 0.86, + "learning_rate": 6.971544260754794e-06, + "loss": 0.0935, + "step": 385850 + }, + { + "epoch": 0.86, + "learning_rate": 6.970425717545469e-06, + "loss": 0.0955, + "step": 385860 + }, + { + "epoch": 0.86, + "learning_rate": 6.969307174336145e-06, + "loss": 0.0966, + "step": 385870 + }, + { + "epoch": 0.86, + "learning_rate": 6.968188631126821e-06, + "loss": 0.0937, + "step": 385880 + }, + { + "epoch": 0.86, + "learning_rate": 6.967070087917496e-06, + "loss": 0.0943, + "step": 385890 + }, + { + "epoch": 0.86, + "learning_rate": 6.965951544708172e-06, + "loss": 0.0975, + "step": 385900 + }, + { + "epoch": 0.86, + "learning_rate": 6.964833001498848e-06, + "loss": 0.0981, + "step": 385910 + }, + { + "epoch": 0.86, + "learning_rate": 6.963714458289525e-06, + "loss": 0.0901, + "step": 385920 + }, + { + "epoch": 0.86, + "learning_rate": 6.9625959150802e-06, + "loss": 0.0966, + "step": 385930 + }, + { + "epoch": 0.86, + "learning_rate": 6.961477371870876e-06, + "loss": 0.0931, + "step": 385940 + }, + { + "epoch": 0.86, + "learning_rate": 6.960358828661552e-06, + "loss": 0.0959, + "step": 385950 + }, + { + "epoch": 0.86, + "learning_rate": 6.959240285452227e-06, + "loss": 0.0949, + "step": 385960 + }, + { + "epoch": 0.86, + "learning_rate": 6.958121742242903e-06, + "loss": 0.0967, + "step": 385970 + }, + { + "epoch": 0.86, + "learning_rate": 6.95700319903358e-06, + "loss": 0.0932, + "step": 385980 + }, + { + "epoch": 0.86, + "learning_rate": 6.955884655824254e-06, + "loss": 0.0951, + "step": 385990 + }, + { + "epoch": 0.86, + "learning_rate": 6.954766112614931e-06, + "loss": 0.1, + "step": 386000 + }, + { + "epoch": 0.86, + "learning_rate": 6.953647569405607e-06, + "loss": 0.0939, + "step": 386010 + }, + { + "epoch": 0.86, + "learning_rate": 6.952529026196282e-06, + "loss": 0.0975, + "step": 386020 + }, + { + "epoch": 0.86, + "learning_rate": 6.951410482986958e-06, + "loss": 0.0941, + "step": 386030 + }, + { + "epoch": 0.86, + "learning_rate": 6.950291939777634e-06, + "loss": 0.096, + "step": 386040 + }, + { + "epoch": 0.86, + "learning_rate": 6.949173396568309e-06, + "loss": 0.0954, + "step": 386050 + }, + { + "epoch": 0.86, + "learning_rate": 6.948054853358986e-06, + "loss": 0.1006, + "step": 386060 + }, + { + "epoch": 0.86, + "learning_rate": 6.9469363101496615e-06, + "loss": 0.0938, + "step": 386070 + }, + { + "epoch": 0.86, + "learning_rate": 6.945817766940338e-06, + "loss": 0.0969, + "step": 386080 + }, + { + "epoch": 0.86, + "learning_rate": 6.944699223731013e-06, + "loss": 0.0949, + "step": 386090 + }, + { + "epoch": 0.86, + "learning_rate": 6.9435806805216886e-06, + "loss": 0.0943, + "step": 386100 + }, + { + "epoch": 0.86, + "learning_rate": 6.942462137312366e-06, + "loss": 0.0975, + "step": 386110 + }, + { + "epoch": 0.86, + "learning_rate": 6.94134359410304e-06, + "loss": 0.0951, + "step": 386120 + }, + { + "epoch": 0.86, + "learning_rate": 6.9402250508937156e-06, + "loss": 0.0922, + "step": 386130 + }, + { + "epoch": 0.86, + "learning_rate": 6.939106507684393e-06, + "loss": 0.0922, + "step": 386140 + }, + { + "epoch": 0.86, + "learning_rate": 6.937987964475068e-06, + "loss": 0.0947, + "step": 386150 + }, + { + "epoch": 0.86, + "learning_rate": 6.936869421265744e-06, + "loss": 0.0952, + "step": 386160 + }, + { + "epoch": 0.86, + "learning_rate": 6.93575087805642e-06, + "loss": 0.098, + "step": 386170 + }, + { + "epoch": 0.86, + "learning_rate": 6.934632334847095e-06, + "loss": 0.0954, + "step": 386180 + }, + { + "epoch": 0.86, + "learning_rate": 6.933513791637772e-06, + "loss": 0.0971, + "step": 386190 + }, + { + "epoch": 0.86, + "learning_rate": 6.9323952484284475e-06, + "loss": 0.0947, + "step": 386200 + }, + { + "epoch": 0.86, + "learning_rate": 6.931276705219122e-06, + "loss": 0.098, + "step": 386210 + }, + { + "epoch": 0.86, + "learning_rate": 6.930158162009799e-06, + "loss": 0.0966, + "step": 386220 + }, + { + "epoch": 0.86, + "learning_rate": 6.9290396188004745e-06, + "loss": 0.0931, + "step": 386230 + }, + { + "epoch": 0.86, + "learning_rate": 6.927921075591151e-06, + "loss": 0.0961, + "step": 386240 + }, + { + "epoch": 0.86, + "learning_rate": 6.926802532381826e-06, + "loss": 0.096, + "step": 386250 + }, + { + "epoch": 0.86, + "learning_rate": 6.9256839891725015e-06, + "loss": 0.093, + "step": 386260 + }, + { + "epoch": 0.86, + "learning_rate": 6.924565445963179e-06, + "loss": 0.0974, + "step": 386270 + }, + { + "epoch": 0.86, + "learning_rate": 6.923446902753854e-06, + "loss": 0.0944, + "step": 386280 + }, + { + "epoch": 0.86, + "learning_rate": 6.922328359544529e-06, + "loss": 0.0982, + "step": 386290 + }, + { + "epoch": 0.86, + "learning_rate": 6.921209816335206e-06, + "loss": 0.0996, + "step": 386300 + }, + { + "epoch": 0.86, + "learning_rate": 6.920091273125881e-06, + "loss": 0.0927, + "step": 386310 + }, + { + "epoch": 0.86, + "learning_rate": 6.918972729916556e-06, + "loss": 0.0908, + "step": 386320 + }, + { + "epoch": 0.86, + "learning_rate": 6.917854186707233e-06, + "loss": 0.0933, + "step": 386330 + }, + { + "epoch": 0.86, + "learning_rate": 6.916735643497908e-06, + "loss": 0.0915, + "step": 386340 + }, + { + "epoch": 0.86, + "learning_rate": 6.915617100288585e-06, + "loss": 0.0967, + "step": 386350 + }, + { + "epoch": 0.86, + "learning_rate": 6.9144985570792605e-06, + "loss": 0.0935, + "step": 386360 + }, + { + "epoch": 0.86, + "learning_rate": 6.913380013869936e-06, + "loss": 0.0924, + "step": 386370 + }, + { + "epoch": 0.86, + "learning_rate": 6.912261470660612e-06, + "loss": 0.0941, + "step": 386380 + }, + { + "epoch": 0.86, + "learning_rate": 6.9111429274512875e-06, + "loss": 0.096, + "step": 386390 + }, + { + "epoch": 0.86, + "learning_rate": 6.910024384241963e-06, + "loss": 0.0997, + "step": 386400 + }, + { + "epoch": 0.86, + "learning_rate": 6.90890584103264e-06, + "loss": 0.0965, + "step": 386410 + }, + { + "epoch": 0.86, + "learning_rate": 6.907787297823315e-06, + "loss": 0.0973, + "step": 386420 + }, + { + "epoch": 0.86, + "learning_rate": 6.9066687546139916e-06, + "loss": 0.1036, + "step": 386430 + }, + { + "epoch": 0.86, + "learning_rate": 6.905550211404667e-06, + "loss": 0.0964, + "step": 386440 + }, + { + "epoch": 0.86, + "learning_rate": 6.904431668195342e-06, + "loss": 0.094, + "step": 386450 + }, + { + "epoch": 0.86, + "learning_rate": 6.9033131249860186e-06, + "loss": 0.0971, + "step": 386460 + }, + { + "epoch": 0.86, + "learning_rate": 6.902194581776694e-06, + "loss": 0.0987, + "step": 386470 + }, + { + "epoch": 0.86, + "learning_rate": 6.901076038567369e-06, + "loss": 0.0965, + "step": 386480 + }, + { + "epoch": 0.86, + "learning_rate": 6.899957495358046e-06, + "loss": 0.0999, + "step": 386490 + }, + { + "epoch": 0.86, + "learning_rate": 6.898838952148722e-06, + "loss": 0.0994, + "step": 386500 + }, + { + "epoch": 0.86, + "learning_rate": 6.897720408939398e-06, + "loss": 0.0932, + "step": 386510 + }, + { + "epoch": 0.86, + "learning_rate": 6.8966018657300734e-06, + "loss": 0.094, + "step": 386520 + }, + { + "epoch": 0.86, + "learning_rate": 6.895483322520749e-06, + "loss": 0.0971, + "step": 386530 + }, + { + "epoch": 0.86, + "learning_rate": 6.894364779311426e-06, + "loss": 0.095, + "step": 386540 + }, + { + "epoch": 0.86, + "learning_rate": 6.8932462361021004e-06, + "loss": 0.0942, + "step": 386550 + }, + { + "epoch": 0.86, + "learning_rate": 6.892127692892776e-06, + "loss": 0.0953, + "step": 386560 + }, + { + "epoch": 0.86, + "learning_rate": 6.891009149683453e-06, + "loss": 0.0952, + "step": 386570 + }, + { + "epoch": 0.86, + "learning_rate": 6.889890606474128e-06, + "loss": 0.0944, + "step": 386580 + }, + { + "epoch": 0.86, + "learning_rate": 6.8887720632648045e-06, + "loss": 0.0997, + "step": 386590 + }, + { + "epoch": 0.86, + "learning_rate": 6.88765352005548e-06, + "loss": 0.0968, + "step": 386600 + }, + { + "epoch": 0.86, + "learning_rate": 6.886534976846155e-06, + "loss": 0.0958, + "step": 386610 + }, + { + "epoch": 0.86, + "learning_rate": 6.885416433636832e-06, + "loss": 0.0929, + "step": 386620 + }, + { + "epoch": 0.86, + "learning_rate": 6.884297890427508e-06, + "loss": 0.0947, + "step": 386630 + }, + { + "epoch": 0.86, + "learning_rate": 6.883179347218182e-06, + "loss": 0.0932, + "step": 386640 + }, + { + "epoch": 0.86, + "learning_rate": 6.882060804008859e-06, + "loss": 0.0963, + "step": 386650 + }, + { + "epoch": 0.86, + "learning_rate": 6.880942260799535e-06, + "loss": 0.0937, + "step": 386660 + }, + { + "epoch": 0.86, + "learning_rate": 6.879823717590211e-06, + "loss": 0.0971, + "step": 386670 + }, + { + "epoch": 0.86, + "learning_rate": 6.878705174380886e-06, + "loss": 0.0979, + "step": 386680 + }, + { + "epoch": 0.86, + "learning_rate": 6.877586631171562e-06, + "loss": 0.0946, + "step": 386690 + }, + { + "epoch": 0.86, + "learning_rate": 6.876468087962239e-06, + "loss": 0.0985, + "step": 386700 + }, + { + "epoch": 0.86, + "learning_rate": 6.875349544752914e-06, + "loss": 0.0993, + "step": 386710 + }, + { + "epoch": 0.86, + "learning_rate": 6.87423100154359e-06, + "loss": 0.1029, + "step": 386720 + }, + { + "epoch": 0.86, + "learning_rate": 6.873112458334266e-06, + "loss": 0.0942, + "step": 386730 + }, + { + "epoch": 0.86, + "learning_rate": 6.871993915124941e-06, + "loss": 0.0938, + "step": 386740 + }, + { + "epoch": 0.86, + "learning_rate": 6.870875371915618e-06, + "loss": 0.0937, + "step": 386750 + }, + { + "epoch": 0.86, + "learning_rate": 6.869756828706293e-06, + "loss": 0.0948, + "step": 386760 + }, + { + "epoch": 0.86, + "learning_rate": 6.868638285496968e-06, + "loss": 0.0954, + "step": 386770 + }, + { + "epoch": 0.86, + "learning_rate": 6.867519742287645e-06, + "loss": 0.095, + "step": 386780 + }, + { + "epoch": 0.86, + "learning_rate": 6.866401199078321e-06, + "loss": 0.0976, + "step": 386790 + }, + { + "epoch": 0.86, + "learning_rate": 6.865282655868996e-06, + "loss": 0.1006, + "step": 386800 + }, + { + "epoch": 0.86, + "learning_rate": 6.864164112659672e-06, + "loss": 0.0982, + "step": 386810 + }, + { + "epoch": 0.86, + "learning_rate": 6.863045569450348e-06, + "loss": 0.0912, + "step": 386820 + }, + { + "epoch": 0.86, + "learning_rate": 6.861927026241025e-06, + "loss": 0.0974, + "step": 386830 + }, + { + "epoch": 0.86, + "learning_rate": 6.8608084830317e-06, + "loss": 0.0965, + "step": 386840 + }, + { + "epoch": 0.86, + "learning_rate": 6.859689939822376e-06, + "loss": 0.0964, + "step": 386850 + }, + { + "epoch": 0.86, + "learning_rate": 6.858571396613052e-06, + "loss": 0.0965, + "step": 386860 + }, + { + "epoch": 0.86, + "learning_rate": 6.857452853403727e-06, + "loss": 0.095, + "step": 386870 + }, + { + "epoch": 0.86, + "learning_rate": 6.856334310194403e-06, + "loss": 0.0962, + "step": 386880 + }, + { + "epoch": 0.86, + "learning_rate": 6.855215766985079e-06, + "loss": 0.0935, + "step": 386890 + }, + { + "epoch": 0.86, + "learning_rate": 6.854097223775754e-06, + "loss": 0.0961, + "step": 386900 + }, + { + "epoch": 0.86, + "learning_rate": 6.852978680566431e-06, + "loss": 0.0957, + "step": 386910 + }, + { + "epoch": 0.86, + "learning_rate": 6.851860137357107e-06, + "loss": 0.0939, + "step": 386920 + }, + { + "epoch": 0.86, + "learning_rate": 6.850741594147782e-06, + "loss": 0.096, + "step": 386930 + }, + { + "epoch": 0.86, + "learning_rate": 6.849623050938458e-06, + "loss": 0.094, + "step": 386940 + }, + { + "epoch": 0.86, + "learning_rate": 6.848504507729134e-06, + "loss": 0.0931, + "step": 386950 + }, + { + "epoch": 0.86, + "learning_rate": 6.847385964519809e-06, + "loss": 0.0956, + "step": 386960 + }, + { + "epoch": 0.86, + "learning_rate": 6.846267421310486e-06, + "loss": 0.0976, + "step": 386970 + }, + { + "epoch": 0.86, + "learning_rate": 6.845148878101161e-06, + "loss": 0.095, + "step": 386980 + }, + { + "epoch": 0.86, + "learning_rate": 6.844030334891838e-06, + "loss": 0.0931, + "step": 386990 + }, + { + "epoch": 0.86, + "learning_rate": 6.842911791682513e-06, + "loss": 0.0958, + "step": 387000 + }, + { + "epoch": 0.86, + "learning_rate": 6.8417932484731885e-06, + "loss": 0.0966, + "step": 387010 + }, + { + "epoch": 0.86, + "learning_rate": 6.840674705263865e-06, + "loss": 0.0932, + "step": 387020 + }, + { + "epoch": 0.86, + "learning_rate": 6.83955616205454e-06, + "loss": 0.0933, + "step": 387030 + }, + { + "epoch": 0.86, + "learning_rate": 6.8384376188452155e-06, + "loss": 0.098, + "step": 387040 + }, + { + "epoch": 0.86, + "learning_rate": 6.837319075635893e-06, + "loss": 0.093, + "step": 387050 + }, + { + "epoch": 0.86, + "learning_rate": 6.836200532426568e-06, + "loss": 0.095, + "step": 387060 + }, + { + "epoch": 0.86, + "learning_rate": 6.835081989217244e-06, + "loss": 0.0968, + "step": 387070 + }, + { + "epoch": 0.86, + "learning_rate": 6.83396344600792e-06, + "loss": 0.0895, + "step": 387080 + }, + { + "epoch": 0.86, + "learning_rate": 6.832844902798595e-06, + "loss": 0.0948, + "step": 387090 + }, + { + "epoch": 0.86, + "learning_rate": 6.831726359589271e-06, + "loss": 0.1015, + "step": 387100 + }, + { + "epoch": 0.86, + "learning_rate": 6.830607816379947e-06, + "loss": 0.0974, + "step": 387110 + }, + { + "epoch": 0.86, + "learning_rate": 6.829489273170622e-06, + "loss": 0.0921, + "step": 387120 + }, + { + "epoch": 0.86, + "learning_rate": 6.828370729961299e-06, + "loss": 0.0935, + "step": 387130 + }, + { + "epoch": 0.86, + "learning_rate": 6.8272521867519745e-06, + "loss": 0.0948, + "step": 387140 + }, + { + "epoch": 0.86, + "learning_rate": 6.826133643542651e-06, + "loss": 0.092, + "step": 387150 + }, + { + "epoch": 0.86, + "learning_rate": 6.825015100333326e-06, + "loss": 0.0981, + "step": 387160 + }, + { + "epoch": 0.86, + "learning_rate": 6.8238965571240015e-06, + "loss": 0.0942, + "step": 387170 + }, + { + "epoch": 0.86, + "learning_rate": 6.822778013914679e-06, + "loss": 0.0936, + "step": 387180 + }, + { + "epoch": 0.86, + "learning_rate": 6.821659470705354e-06, + "loss": 0.097, + "step": 387190 + }, + { + "epoch": 0.86, + "learning_rate": 6.8205409274960285e-06, + "loss": 0.0942, + "step": 387200 + }, + { + "epoch": 0.86, + "learning_rate": 6.819422384286706e-06, + "loss": 0.0942, + "step": 387210 + }, + { + "epoch": 0.86, + "learning_rate": 6.818303841077381e-06, + "loss": 0.0941, + "step": 387220 + }, + { + "epoch": 0.86, + "learning_rate": 6.817185297868057e-06, + "loss": 0.0965, + "step": 387230 + }, + { + "epoch": 0.86, + "learning_rate": 6.816066754658733e-06, + "loss": 0.0976, + "step": 387240 + }, + { + "epoch": 0.86, + "learning_rate": 6.814948211449408e-06, + "loss": 0.097, + "step": 387250 + }, + { + "epoch": 0.86, + "learning_rate": 6.813829668240085e-06, + "loss": 0.0976, + "step": 387260 + }, + { + "epoch": 0.86, + "learning_rate": 6.8127111250307605e-06, + "loss": 0.0921, + "step": 387270 + }, + { + "epoch": 0.86, + "learning_rate": 6.811592581821436e-06, + "loss": 0.1013, + "step": 387280 + }, + { + "epoch": 0.86, + "learning_rate": 6.810474038612112e-06, + "loss": 0.0952, + "step": 387290 + }, + { + "epoch": 0.86, + "learning_rate": 6.8093554954027875e-06, + "loss": 0.0928, + "step": 387300 + }, + { + "epoch": 0.86, + "learning_rate": 6.8082369521934645e-06, + "loss": 0.0946, + "step": 387310 + }, + { + "epoch": 0.86, + "learning_rate": 6.807118408984139e-06, + "loss": 0.0948, + "step": 387320 + }, + { + "epoch": 0.86, + "learning_rate": 6.8059998657748145e-06, + "loss": 0.0906, + "step": 387330 + }, + { + "epoch": 0.86, + "learning_rate": 6.8048813225654915e-06, + "loss": 0.1004, + "step": 387340 + }, + { + "epoch": 0.86, + "learning_rate": 6.803762779356167e-06, + "loss": 0.0942, + "step": 387350 + }, + { + "epoch": 0.86, + "learning_rate": 6.802644236146842e-06, + "loss": 0.1013, + "step": 387360 + }, + { + "epoch": 0.86, + "learning_rate": 6.8015256929375186e-06, + "loss": 0.0972, + "step": 387370 + }, + { + "epoch": 0.86, + "learning_rate": 6.800407149728194e-06, + "loss": 0.095, + "step": 387380 + }, + { + "epoch": 0.86, + "learning_rate": 6.799288606518871e-06, + "loss": 0.0996, + "step": 387390 + }, + { + "epoch": 0.86, + "learning_rate": 6.798281917630478e-06, + "loss": 0.0963, + "step": 387400 + }, + { + "epoch": 0.86, + "learning_rate": 6.797163374421154e-06, + "loss": 0.0954, + "step": 387410 + }, + { + "epoch": 0.86, + "learning_rate": 6.79604483121183e-06, + "loss": 0.0946, + "step": 387420 + }, + { + "epoch": 0.86, + "learning_rate": 6.794926288002505e-06, + "loss": 0.0939, + "step": 387430 + }, + { + "epoch": 0.86, + "learning_rate": 6.793807744793182e-06, + "loss": 0.0932, + "step": 387440 + }, + { + "epoch": 0.86, + "learning_rate": 6.792689201583858e-06, + "loss": 0.0937, + "step": 387450 + }, + { + "epoch": 0.86, + "learning_rate": 6.791570658374534e-06, + "loss": 0.0988, + "step": 387460 + }, + { + "epoch": 0.86, + "learning_rate": 6.790452115165209e-06, + "loss": 0.0954, + "step": 387470 + }, + { + "epoch": 0.86, + "learning_rate": 6.789333571955885e-06, + "loss": 0.0954, + "step": 387480 + }, + { + "epoch": 0.86, + "learning_rate": 6.788215028746561e-06, + "loss": 0.0956, + "step": 387490 + }, + { + "epoch": 0.86, + "learning_rate": 6.787096485537236e-06, + "loss": 0.098, + "step": 387500 + }, + { + "epoch": 0.86, + "learning_rate": 6.785977942327912e-06, + "loss": 0.0948, + "step": 387510 + }, + { + "epoch": 0.86, + "learning_rate": 6.784859399118589e-06, + "loss": 0.0992, + "step": 387520 + }, + { + "epoch": 0.87, + "learning_rate": 6.783740855909264e-06, + "loss": 0.0959, + "step": 387530 + }, + { + "epoch": 0.87, + "learning_rate": 6.78262231269994e-06, + "loss": 0.0932, + "step": 387540 + }, + { + "epoch": 0.87, + "learning_rate": 6.781503769490616e-06, + "loss": 0.0962, + "step": 387550 + }, + { + "epoch": 0.87, + "learning_rate": 6.780385226281291e-06, + "loss": 0.0946, + "step": 387560 + }, + { + "epoch": 0.87, + "learning_rate": 6.779266683071968e-06, + "loss": 0.0941, + "step": 387570 + }, + { + "epoch": 0.87, + "learning_rate": 6.7781481398626435e-06, + "loss": 0.0935, + "step": 387580 + }, + { + "epoch": 0.87, + "learning_rate": 6.777029596653318e-06, + "loss": 0.0951, + "step": 387590 + }, + { + "epoch": 0.87, + "learning_rate": 6.775911053443995e-06, + "loss": 0.0982, + "step": 387600 + }, + { + "epoch": 0.87, + "learning_rate": 6.7747925102346705e-06, + "loss": 0.1011, + "step": 387610 + }, + { + "epoch": 0.87, + "learning_rate": 6.773673967025347e-06, + "loss": 0.0997, + "step": 387620 + }, + { + "epoch": 0.87, + "learning_rate": 6.772555423816022e-06, + "loss": 0.0968, + "step": 387630 + }, + { + "epoch": 0.87, + "learning_rate": 6.7714368806066975e-06, + "loss": 0.0948, + "step": 387640 + }, + { + "epoch": 0.87, + "learning_rate": 6.770318337397375e-06, + "loss": 0.096, + "step": 387650 + }, + { + "epoch": 0.87, + "learning_rate": 6.76919979418805e-06, + "loss": 0.0953, + "step": 387660 + }, + { + "epoch": 0.87, + "learning_rate": 6.768081250978725e-06, + "loss": 0.0928, + "step": 387670 + }, + { + "epoch": 0.87, + "learning_rate": 6.766962707769402e-06, + "loss": 0.094, + "step": 387680 + }, + { + "epoch": 0.87, + "learning_rate": 6.765844164560077e-06, + "loss": 0.0924, + "step": 387690 + }, + { + "epoch": 0.87, + "learning_rate": 6.764725621350754e-06, + "loss": 0.0993, + "step": 387700 + }, + { + "epoch": 0.87, + "learning_rate": 6.763607078141429e-06, + "loss": 0.0965, + "step": 387710 + }, + { + "epoch": 0.87, + "learning_rate": 6.762488534932104e-06, + "loss": 0.0909, + "step": 387720 + }, + { + "epoch": 0.87, + "learning_rate": 6.761369991722781e-06, + "loss": 0.0959, + "step": 387730 + }, + { + "epoch": 0.87, + "learning_rate": 6.7602514485134565e-06, + "loss": 0.0959, + "step": 387740 + }, + { + "epoch": 0.87, + "learning_rate": 6.759132905304132e-06, + "loss": 0.0922, + "step": 387750 + }, + { + "epoch": 0.87, + "learning_rate": 6.758014362094808e-06, + "loss": 0.1023, + "step": 387760 + }, + { + "epoch": 0.87, + "learning_rate": 6.7568958188854835e-06, + "loss": 0.096, + "step": 387770 + }, + { + "epoch": 0.87, + "learning_rate": 6.755777275676161e-06, + "loss": 0.0942, + "step": 387780 + }, + { + "epoch": 0.87, + "learning_rate": 6.754658732466836e-06, + "loss": 0.0964, + "step": 387790 + }, + { + "epoch": 0.87, + "learning_rate": 6.7535401892575105e-06, + "loss": 0.0958, + "step": 387800 + }, + { + "epoch": 0.87, + "learning_rate": 6.752421646048188e-06, + "loss": 0.1, + "step": 387810 + }, + { + "epoch": 0.87, + "learning_rate": 6.751303102838863e-06, + "loss": 0.1024, + "step": 387820 + }, + { + "epoch": 0.87, + "learning_rate": 6.750184559629538e-06, + "loss": 0.0978, + "step": 387830 + }, + { + "epoch": 0.87, + "learning_rate": 6.749066016420215e-06, + "loss": 0.0951, + "step": 387840 + }, + { + "epoch": 0.87, + "learning_rate": 6.74794747321089e-06, + "loss": 0.0944, + "step": 387850 + }, + { + "epoch": 0.87, + "learning_rate": 6.746828930001567e-06, + "loss": 0.0974, + "step": 387860 + }, + { + "epoch": 0.87, + "learning_rate": 6.7457103867922425e-06, + "loss": 0.0952, + "step": 387870 + }, + { + "epoch": 0.87, + "learning_rate": 6.744591843582918e-06, + "loss": 0.0929, + "step": 387880 + }, + { + "epoch": 0.87, + "learning_rate": 6.743473300373594e-06, + "loss": 0.0956, + "step": 387890 + }, + { + "epoch": 0.87, + "learning_rate": 6.7423547571642695e-06, + "loss": 0.0976, + "step": 387900 + }, + { + "epoch": 0.87, + "learning_rate": 6.741236213954945e-06, + "loss": 0.0926, + "step": 387910 + }, + { + "epoch": 0.87, + "learning_rate": 6.740117670745622e-06, + "loss": 0.0946, + "step": 387920 + }, + { + "epoch": 0.87, + "learning_rate": 6.7389991275362965e-06, + "loss": 0.0971, + "step": 387930 + }, + { + "epoch": 0.87, + "learning_rate": 6.7378805843269735e-06, + "loss": 0.0938, + "step": 387940 + }, + { + "epoch": 0.87, + "learning_rate": 6.736762041117649e-06, + "loss": 0.0965, + "step": 387950 + }, + { + "epoch": 0.87, + "learning_rate": 6.735643497908324e-06, + "loss": 0.0923, + "step": 387960 + }, + { + "epoch": 0.87, + "learning_rate": 6.7345249546990006e-06, + "loss": 0.0942, + "step": 387970 + }, + { + "epoch": 0.87, + "learning_rate": 6.733406411489676e-06, + "loss": 0.0945, + "step": 387980 + }, + { + "epoch": 0.87, + "learning_rate": 6.732287868280351e-06, + "loss": 0.0992, + "step": 387990 + }, + { + "epoch": 0.87, + "learning_rate": 6.731169325071028e-06, + "loss": 0.0977, + "step": 388000 + }, + { + "epoch": 0.87, + "learning_rate": 6.730050781861704e-06, + "loss": 0.0954, + "step": 388010 + }, + { + "epoch": 0.87, + "learning_rate": 6.72893223865238e-06, + "loss": 0.0933, + "step": 388020 + }, + { + "epoch": 0.87, + "learning_rate": 6.727813695443055e-06, + "loss": 0.094, + "step": 388030 + }, + { + "epoch": 0.87, + "learning_rate": 6.726695152233731e-06, + "loss": 0.0941, + "step": 388040 + }, + { + "epoch": 0.87, + "learning_rate": 6.725576609024407e-06, + "loss": 0.0979, + "step": 388050 + }, + { + "epoch": 0.87, + "learning_rate": 6.724458065815082e-06, + "loss": 0.0971, + "step": 388060 + }, + { + "epoch": 0.87, + "learning_rate": 6.723339522605758e-06, + "loss": 0.0969, + "step": 388070 + }, + { + "epoch": 0.87, + "learning_rate": 6.722220979396435e-06, + "loss": 0.0971, + "step": 388080 + }, + { + "epoch": 0.87, + "learning_rate": 6.72110243618711e-06, + "loss": 0.0967, + "step": 388090 + }, + { + "epoch": 0.87, + "learning_rate": 6.7199838929777865e-06, + "loss": 0.0955, + "step": 388100 + }, + { + "epoch": 0.87, + "learning_rate": 6.718865349768462e-06, + "loss": 0.0966, + "step": 388110 + }, + { + "epoch": 0.87, + "learning_rate": 6.717746806559137e-06, + "loss": 0.0946, + "step": 388120 + }, + { + "epoch": 0.87, + "learning_rate": 6.716628263349814e-06, + "loss": 0.0956, + "step": 388130 + }, + { + "epoch": 0.87, + "learning_rate": 6.715509720140489e-06, + "loss": 0.0947, + "step": 388140 + }, + { + "epoch": 0.87, + "learning_rate": 6.714391176931164e-06, + "loss": 0.0987, + "step": 388150 + }, + { + "epoch": 0.87, + "learning_rate": 6.713272633721841e-06, + "loss": 0.1, + "step": 388160 + }, + { + "epoch": 0.87, + "learning_rate": 6.712154090512517e-06, + "loss": 0.0935, + "step": 388170 + }, + { + "epoch": 0.87, + "learning_rate": 6.711035547303193e-06, + "loss": 0.0972, + "step": 388180 + }, + { + "epoch": 0.87, + "learning_rate": 6.709917004093868e-06, + "loss": 0.0938, + "step": 388190 + }, + { + "epoch": 0.87, + "learning_rate": 6.708798460884544e-06, + "loss": 0.0993, + "step": 388200 + }, + { + "epoch": 0.87, + "learning_rate": 6.707679917675221e-06, + "loss": 0.0956, + "step": 388210 + }, + { + "epoch": 0.87, + "learning_rate": 6.706561374465896e-06, + "loss": 0.0932, + "step": 388220 + }, + { + "epoch": 0.87, + "learning_rate": 6.705442831256571e-06, + "loss": 0.0933, + "step": 388230 + }, + { + "epoch": 0.87, + "learning_rate": 6.704324288047248e-06, + "loss": 0.0956, + "step": 388240 + }, + { + "epoch": 0.87, + "learning_rate": 6.703205744837923e-06, + "loss": 0.0946, + "step": 388250 + }, + { + "epoch": 0.87, + "learning_rate": 6.7020872016285995e-06, + "loss": 0.0991, + "step": 388260 + }, + { + "epoch": 0.87, + "learning_rate": 6.700968658419275e-06, + "loss": 0.0935, + "step": 388270 + }, + { + "epoch": 0.87, + "learning_rate": 6.69985011520995e-06, + "loss": 0.0963, + "step": 388280 + }, + { + "epoch": 0.87, + "learning_rate": 6.698731572000627e-06, + "loss": 0.0971, + "step": 388290 + }, + { + "epoch": 0.87, + "learning_rate": 6.697613028791303e-06, + "loss": 0.0989, + "step": 388300 + }, + { + "epoch": 0.87, + "learning_rate": 6.696494485581978e-06, + "loss": 0.0919, + "step": 388310 + }, + { + "epoch": 0.87, + "learning_rate": 6.695375942372654e-06, + "loss": 0.0955, + "step": 388320 + }, + { + "epoch": 0.87, + "learning_rate": 6.69425739916333e-06, + "loss": 0.0948, + "step": 388330 + }, + { + "epoch": 0.87, + "learning_rate": 6.693138855954007e-06, + "loss": 0.0988, + "step": 388340 + }, + { + "epoch": 0.87, + "learning_rate": 6.692020312744682e-06, + "loss": 0.0973, + "step": 388350 + }, + { + "epoch": 0.87, + "learning_rate": 6.690901769535357e-06, + "loss": 0.0954, + "step": 388360 + }, + { + "epoch": 0.87, + "learning_rate": 6.689783226326034e-06, + "loss": 0.1002, + "step": 388370 + }, + { + "epoch": 0.87, + "learning_rate": 6.688664683116709e-06, + "loss": 0.0965, + "step": 388380 + }, + { + "epoch": 0.87, + "learning_rate": 6.6875461399073846e-06, + "loss": 0.0986, + "step": 388390 + }, + { + "epoch": 0.87, + "learning_rate": 6.686427596698061e-06, + "loss": 0.0973, + "step": 388400 + }, + { + "epoch": 0.87, + "learning_rate": 6.685309053488736e-06, + "loss": 0.0977, + "step": 388410 + }, + { + "epoch": 0.87, + "learning_rate": 6.684190510279413e-06, + "loss": 0.096, + "step": 388420 + }, + { + "epoch": 0.87, + "learning_rate": 6.683071967070089e-06, + "loss": 0.0957, + "step": 388430 + }, + { + "epoch": 0.87, + "learning_rate": 6.681953423860764e-06, + "loss": 0.0968, + "step": 388440 + }, + { + "epoch": 0.87, + "learning_rate": 6.68083488065144e-06, + "loss": 0.0945, + "step": 388450 + }, + { + "epoch": 0.87, + "learning_rate": 6.679716337442116e-06, + "loss": 0.0962, + "step": 388460 + }, + { + "epoch": 0.87, + "learning_rate": 6.678597794232791e-06, + "loss": 0.0934, + "step": 388470 + }, + { + "epoch": 0.87, + "learning_rate": 6.677479251023467e-06, + "loss": 0.0928, + "step": 388480 + }, + { + "epoch": 0.87, + "learning_rate": 6.676360707814143e-06, + "loss": 0.0997, + "step": 388490 + }, + { + "epoch": 0.87, + "learning_rate": 6.67524216460482e-06, + "loss": 0.0975, + "step": 388500 + }, + { + "epoch": 0.87, + "learning_rate": 6.674123621395495e-06, + "loss": 0.0949, + "step": 388510 + }, + { + "epoch": 0.87, + "learning_rate": 6.6730050781861705e-06, + "loss": 0.0949, + "step": 388520 + }, + { + "epoch": 0.87, + "learning_rate": 6.671886534976847e-06, + "loss": 0.0929, + "step": 388530 + }, + { + "epoch": 0.87, + "learning_rate": 6.670767991767522e-06, + "loss": 0.0973, + "step": 388540 + }, + { + "epoch": 0.87, + "learning_rate": 6.6696494485581975e-06, + "loss": 0.0953, + "step": 388550 + }, + { + "epoch": 0.87, + "learning_rate": 6.668530905348875e-06, + "loss": 0.0934, + "step": 388560 + }, + { + "epoch": 0.87, + "learning_rate": 6.667412362139549e-06, + "loss": 0.0977, + "step": 388570 + }, + { + "epoch": 0.87, + "learning_rate": 6.666293818930226e-06, + "loss": 0.0967, + "step": 388580 + }, + { + "epoch": 0.87, + "learning_rate": 6.665175275720902e-06, + "loss": 0.0984, + "step": 388590 + }, + { + "epoch": 0.87, + "learning_rate": 6.664056732511577e-06, + "loss": 0.0929, + "step": 388600 + }, + { + "epoch": 0.87, + "learning_rate": 6.662938189302253e-06, + "loss": 0.0914, + "step": 388610 + }, + { + "epoch": 0.87, + "learning_rate": 6.661819646092929e-06, + "loss": 0.0954, + "step": 388620 + }, + { + "epoch": 0.87, + "learning_rate": 6.660701102883604e-06, + "loss": 0.0969, + "step": 388630 + }, + { + "epoch": 0.87, + "learning_rate": 6.659582559674281e-06, + "loss": 0.0938, + "step": 388640 + }, + { + "epoch": 0.87, + "learning_rate": 6.6584640164649565e-06, + "loss": 0.0972, + "step": 388650 + }, + { + "epoch": 0.87, + "learning_rate": 6.657345473255633e-06, + "loss": 0.0991, + "step": 388660 + }, + { + "epoch": 0.87, + "learning_rate": 6.656226930046308e-06, + "loss": 0.098, + "step": 388670 + }, + { + "epoch": 0.87, + "learning_rate": 6.6551083868369835e-06, + "loss": 0.0945, + "step": 388680 + }, + { + "epoch": 0.87, + "learning_rate": 6.65398984362766e-06, + "loss": 0.0948, + "step": 388690 + }, + { + "epoch": 0.87, + "learning_rate": 6.652871300418335e-06, + "loss": 0.0972, + "step": 388700 + }, + { + "epoch": 0.87, + "learning_rate": 6.6517527572090105e-06, + "loss": 0.0938, + "step": 388710 + }, + { + "epoch": 0.87, + "learning_rate": 6.650634213999688e-06, + "loss": 0.0914, + "step": 388720 + }, + { + "epoch": 0.87, + "learning_rate": 6.649515670790363e-06, + "loss": 0.0955, + "step": 388730 + }, + { + "epoch": 0.87, + "learning_rate": 6.648397127581039e-06, + "loss": 0.0927, + "step": 388740 + }, + { + "epoch": 0.87, + "learning_rate": 6.647278584371715e-06, + "loss": 0.0912, + "step": 388750 + }, + { + "epoch": 0.87, + "learning_rate": 6.64616004116239e-06, + "loss": 0.096, + "step": 388760 + }, + { + "epoch": 0.87, + "learning_rate": 6.645041497953067e-06, + "loss": 0.0944, + "step": 388770 + }, + { + "epoch": 0.87, + "learning_rate": 6.6439229547437424e-06, + "loss": 0.0899, + "step": 388780 + }, + { + "epoch": 0.87, + "learning_rate": 6.642804411534417e-06, + "loss": 0.0958, + "step": 388790 + }, + { + "epoch": 0.87, + "learning_rate": 6.641685868325094e-06, + "loss": 0.098, + "step": 388800 + }, + { + "epoch": 0.87, + "learning_rate": 6.6405673251157694e-06, + "loss": 0.0957, + "step": 388810 + }, + { + "epoch": 0.87, + "learning_rate": 6.639448781906446e-06, + "loss": 0.0932, + "step": 388820 + }, + { + "epoch": 0.87, + "learning_rate": 6.638330238697121e-06, + "loss": 0.0933, + "step": 388830 + }, + { + "epoch": 0.87, + "learning_rate": 6.6372116954877965e-06, + "loss": 0.0959, + "step": 388840 + }, + { + "epoch": 0.87, + "learning_rate": 6.6360931522784735e-06, + "loss": 0.0956, + "step": 388850 + }, + { + "epoch": 0.87, + "learning_rate": 6.634974609069149e-06, + "loss": 0.097, + "step": 388860 + }, + { + "epoch": 0.87, + "learning_rate": 6.633856065859824e-06, + "loss": 0.0968, + "step": 388870 + }, + { + "epoch": 0.87, + "learning_rate": 6.6327375226505005e-06, + "loss": 0.0951, + "step": 388880 + }, + { + "epoch": 0.87, + "learning_rate": 6.631618979441176e-06, + "loss": 0.0968, + "step": 388890 + }, + { + "epoch": 0.87, + "learning_rate": 6.630500436231853e-06, + "loss": 0.0971, + "step": 388900 + }, + { + "epoch": 0.87, + "learning_rate": 6.6293818930225275e-06, + "loss": 0.0935, + "step": 388910 + }, + { + "epoch": 0.87, + "learning_rate": 6.628263349813203e-06, + "loss": 0.1018, + "step": 388920 + }, + { + "epoch": 0.87, + "learning_rate": 6.62714480660388e-06, + "loss": 0.0942, + "step": 388930 + }, + { + "epoch": 0.87, + "learning_rate": 6.626026263394555e-06, + "loss": 0.0989, + "step": 388940 + }, + { + "epoch": 0.87, + "learning_rate": 6.624907720185231e-06, + "loss": 0.0953, + "step": 388950 + }, + { + "epoch": 0.87, + "learning_rate": 6.623789176975907e-06, + "loss": 0.0955, + "step": 388960 + }, + { + "epoch": 0.87, + "learning_rate": 6.622670633766582e-06, + "loss": 0.0954, + "step": 388970 + }, + { + "epoch": 0.87, + "learning_rate": 6.6215520905572595e-06, + "loss": 0.0988, + "step": 388980 + }, + { + "epoch": 0.87, + "learning_rate": 6.620433547347935e-06, + "loss": 0.096, + "step": 388990 + }, + { + "epoch": 0.87, + "learning_rate": 6.619315004138609e-06, + "loss": 0.0966, + "step": 389000 + }, + { + "epoch": 0.87, + "learning_rate": 6.6181964609292865e-06, + "loss": 0.0949, + "step": 389010 + }, + { + "epoch": 0.87, + "learning_rate": 6.617077917719962e-06, + "loss": 0.0951, + "step": 389020 + }, + { + "epoch": 0.87, + "learning_rate": 6.615959374510637e-06, + "loss": 0.0887, + "step": 389030 + }, + { + "epoch": 0.87, + "learning_rate": 6.6148408313013135e-06, + "loss": 0.094, + "step": 389040 + }, + { + "epoch": 0.87, + "learning_rate": 6.613722288091989e-06, + "loss": 0.0968, + "step": 389050 + }, + { + "epoch": 0.87, + "learning_rate": 6.612603744882666e-06, + "loss": 0.0936, + "step": 389060 + }, + { + "epoch": 0.87, + "learning_rate": 6.611485201673341e-06, + "loss": 0.0978, + "step": 389070 + }, + { + "epoch": 0.87, + "learning_rate": 6.610366658464017e-06, + "loss": 0.0964, + "step": 389080 + }, + { + "epoch": 0.87, + "learning_rate": 6.609248115254693e-06, + "loss": 0.0955, + "step": 389090 + }, + { + "epoch": 0.87, + "learning_rate": 6.608129572045368e-06, + "loss": 0.0975, + "step": 389100 + }, + { + "epoch": 0.87, + "learning_rate": 6.607011028836044e-06, + "loss": 0.094, + "step": 389110 + }, + { + "epoch": 0.87, + "learning_rate": 6.605892485626721e-06, + "loss": 0.0935, + "step": 389120 + }, + { + "epoch": 0.87, + "learning_rate": 6.604773942417395e-06, + "loss": 0.0976, + "step": 389130 + }, + { + "epoch": 0.87, + "learning_rate": 6.6036553992080725e-06, + "loss": 0.0958, + "step": 389140 + }, + { + "epoch": 0.87, + "learning_rate": 6.602536855998748e-06, + "loss": 0.0989, + "step": 389150 + }, + { + "epoch": 0.87, + "learning_rate": 6.601418312789423e-06, + "loss": 0.0918, + "step": 389160 + }, + { + "epoch": 0.87, + "learning_rate": 6.6002997695800995e-06, + "loss": 0.0977, + "step": 389170 + }, + { + "epoch": 0.87, + "learning_rate": 6.599181226370775e-06, + "loss": 0.0945, + "step": 389180 + }, + { + "epoch": 0.87, + "learning_rate": 6.59806268316145e-06, + "loss": 0.0947, + "step": 389190 + }, + { + "epoch": 0.87, + "learning_rate": 6.596944139952127e-06, + "loss": 0.0959, + "step": 389200 + }, + { + "epoch": 0.87, + "learning_rate": 6.595825596742803e-06, + "loss": 0.0932, + "step": 389210 + }, + { + "epoch": 0.87, + "learning_rate": 6.594707053533479e-06, + "loss": 0.0937, + "step": 389220 + }, + { + "epoch": 0.87, + "learning_rate": 6.593588510324154e-06, + "loss": 0.0984, + "step": 389230 + }, + { + "epoch": 0.87, + "learning_rate": 6.59246996711483e-06, + "loss": 0.0997, + "step": 389240 + }, + { + "epoch": 0.87, + "learning_rate": 6.591351423905506e-06, + "loss": 0.0928, + "step": 389250 + }, + { + "epoch": 0.87, + "learning_rate": 6.590232880696181e-06, + "loss": 0.099, + "step": 389260 + }, + { + "epoch": 0.87, + "learning_rate": 6.589114337486857e-06, + "loss": 0.0987, + "step": 389270 + }, + { + "epoch": 0.87, + "learning_rate": 6.587995794277534e-06, + "loss": 0.0966, + "step": 389280 + }, + { + "epoch": 0.87, + "learning_rate": 6.586877251068209e-06, + "loss": 0.0958, + "step": 389290 + }, + { + "epoch": 0.87, + "learning_rate": 6.5857587078588846e-06, + "loss": 0.0939, + "step": 389300 + }, + { + "epoch": 0.87, + "learning_rate": 6.584640164649561e-06, + "loss": 0.0942, + "step": 389310 + }, + { + "epoch": 0.87, + "learning_rate": 6.583521621440236e-06, + "loss": 0.0953, + "step": 389320 + }, + { + "epoch": 0.87, + "learning_rate": 6.582403078230913e-06, + "loss": 0.0975, + "step": 389330 + }, + { + "epoch": 0.87, + "learning_rate": 6.581284535021588e-06, + "loss": 0.0937, + "step": 389340 + }, + { + "epoch": 0.87, + "learning_rate": 6.580165991812263e-06, + "loss": 0.0946, + "step": 389350 + }, + { + "epoch": 0.87, + "learning_rate": 6.57904744860294e-06, + "loss": 0.0979, + "step": 389360 + }, + { + "epoch": 0.87, + "learning_rate": 6.577928905393616e-06, + "loss": 0.1002, + "step": 389370 + }, + { + "epoch": 0.87, + "learning_rate": 6.576810362184291e-06, + "loss": 0.0941, + "step": 389380 + }, + { + "epoch": 0.87, + "learning_rate": 6.575691818974967e-06, + "loss": 0.0993, + "step": 389390 + }, + { + "epoch": 0.87, + "learning_rate": 6.574573275765643e-06, + "loss": 0.0939, + "step": 389400 + }, + { + "epoch": 0.87, + "learning_rate": 6.57345473255632e-06, + "loss": 0.0963, + "step": 389410 + }, + { + "epoch": 0.87, + "learning_rate": 6.572336189346995e-06, + "loss": 0.0948, + "step": 389420 + }, + { + "epoch": 0.87, + "learning_rate": 6.5712176461376705e-06, + "loss": 0.0945, + "step": 389430 + }, + { + "epoch": 0.87, + "learning_rate": 6.570099102928347e-06, + "loss": 0.097, + "step": 389440 + }, + { + "epoch": 0.87, + "learning_rate": 6.568980559719022e-06, + "loss": 0.0938, + "step": 389450 + }, + { + "epoch": 0.87, + "learning_rate": 6.5678620165096975e-06, + "loss": 0.0968, + "step": 389460 + }, + { + "epoch": 0.87, + "learning_rate": 6.566743473300374e-06, + "loss": 0.094, + "step": 389470 + }, + { + "epoch": 0.87, + "learning_rate": 6.565624930091049e-06, + "loss": 0.0961, + "step": 389480 + }, + { + "epoch": 0.87, + "learning_rate": 6.564506386881726e-06, + "loss": 0.0957, + "step": 389490 + }, + { + "epoch": 0.87, + "learning_rate": 6.563387843672402e-06, + "loss": 0.0958, + "step": 389500 + }, + { + "epoch": 0.87, + "learning_rate": 6.562269300463077e-06, + "loss": 0.0972, + "step": 389510 + }, + { + "epoch": 0.87, + "learning_rate": 6.561150757253753e-06, + "loss": 0.096, + "step": 389520 + }, + { + "epoch": 0.87, + "learning_rate": 6.56014406836536e-06, + "loss": 0.0911, + "step": 389530 + }, + { + "epoch": 0.87, + "learning_rate": 6.559025525156037e-06, + "loss": 0.0939, + "step": 389540 + }, + { + "epoch": 0.87, + "learning_rate": 6.557906981946713e-06, + "loss": 0.0971, + "step": 389550 + }, + { + "epoch": 0.87, + "learning_rate": 6.556788438737389e-06, + "loss": 0.0961, + "step": 389560 + }, + { + "epoch": 0.87, + "learning_rate": 6.555669895528064e-06, + "loss": 0.0956, + "step": 389570 + }, + { + "epoch": 0.87, + "learning_rate": 6.55455135231874e-06, + "loss": 0.0924, + "step": 389580 + }, + { + "epoch": 0.87, + "learning_rate": 6.553432809109417e-06, + "loss": 0.0937, + "step": 389590 + }, + { + "epoch": 0.87, + "learning_rate": 6.552314265900092e-06, + "loss": 0.0942, + "step": 389600 + }, + { + "epoch": 0.87, + "learning_rate": 6.551195722690767e-06, + "loss": 0.0987, + "step": 389610 + }, + { + "epoch": 0.87, + "learning_rate": 6.550077179481444e-06, + "loss": 0.0967, + "step": 389620 + }, + { + "epoch": 0.87, + "learning_rate": 6.548958636272119e-06, + "loss": 0.0968, + "step": 389630 + }, + { + "epoch": 0.87, + "learning_rate": 6.5478400930627955e-06, + "loss": 0.0953, + "step": 389640 + }, + { + "epoch": 0.87, + "learning_rate": 6.546721549853471e-06, + "loss": 0.0946, + "step": 389650 + }, + { + "epoch": 0.87, + "learning_rate": 6.545603006644146e-06, + "loss": 0.097, + "step": 389660 + }, + { + "epoch": 0.87, + "learning_rate": 6.544484463434823e-06, + "loss": 0.0978, + "step": 389670 + }, + { + "epoch": 0.87, + "learning_rate": 6.543365920225499e-06, + "loss": 0.0929, + "step": 389680 + }, + { + "epoch": 0.87, + "learning_rate": 6.542247377016174e-06, + "loss": 0.0951, + "step": 389690 + }, + { + "epoch": 0.87, + "learning_rate": 6.54112883380685e-06, + "loss": 0.0908, + "step": 389700 + }, + { + "epoch": 0.87, + "learning_rate": 6.540010290597526e-06, + "loss": 0.0955, + "step": 389710 + }, + { + "epoch": 0.87, + "learning_rate": 6.538891747388203e-06, + "loss": 0.0961, + "step": 389720 + }, + { + "epoch": 0.87, + "learning_rate": 6.537773204178877e-06, + "loss": 0.0945, + "step": 389730 + }, + { + "epoch": 0.87, + "learning_rate": 6.536654660969553e-06, + "loss": 0.0946, + "step": 389740 + }, + { + "epoch": 0.87, + "learning_rate": 6.53553611776023e-06, + "loss": 0.0936, + "step": 389750 + }, + { + "epoch": 0.87, + "learning_rate": 6.534417574550905e-06, + "loss": 0.1002, + "step": 389760 + }, + { + "epoch": 0.87, + "learning_rate": 6.533299031341581e-06, + "loss": 0.0976, + "step": 389770 + }, + { + "epoch": 0.87, + "learning_rate": 6.532180488132257e-06, + "loss": 0.098, + "step": 389780 + }, + { + "epoch": 0.87, + "learning_rate": 6.531061944922932e-06, + "loss": 0.0996, + "step": 389790 + }, + { + "epoch": 0.87, + "learning_rate": 6.529943401713609e-06, + "loss": 0.0993, + "step": 389800 + }, + { + "epoch": 0.87, + "learning_rate": 6.528824858504285e-06, + "loss": 0.0947, + "step": 389810 + }, + { + "epoch": 0.87, + "learning_rate": 6.52770631529496e-06, + "loss": 0.0933, + "step": 389820 + }, + { + "epoch": 0.87, + "learning_rate": 6.526587772085636e-06, + "loss": 0.0938, + "step": 389830 + }, + { + "epoch": 0.87, + "learning_rate": 6.525469228876312e-06, + "loss": 0.0972, + "step": 389840 + }, + { + "epoch": 0.87, + "learning_rate": 6.524350685666987e-06, + "loss": 0.0935, + "step": 389850 + }, + { + "epoch": 0.87, + "learning_rate": 6.523232142457663e-06, + "loss": 0.0957, + "step": 389860 + }, + { + "epoch": 0.87, + "learning_rate": 6.522113599248339e-06, + "loss": 0.0975, + "step": 389870 + }, + { + "epoch": 0.87, + "learning_rate": 6.520995056039016e-06, + "loss": 0.0965, + "step": 389880 + }, + { + "epoch": 0.87, + "learning_rate": 6.519876512829691e-06, + "loss": 0.0944, + "step": 389890 + }, + { + "epoch": 0.87, + "learning_rate": 6.5187579696203666e-06, + "loss": 0.0987, + "step": 389900 + }, + { + "epoch": 0.87, + "learning_rate": 6.517639426411043e-06, + "loss": 0.0966, + "step": 389910 + }, + { + "epoch": 0.87, + "learning_rate": 6.516520883201718e-06, + "loss": 0.0943, + "step": 389920 + }, + { + "epoch": 0.87, + "learning_rate": 6.5154023399923936e-06, + "loss": 0.0915, + "step": 389930 + }, + { + "epoch": 0.87, + "learning_rate": 6.514283796783071e-06, + "loss": 0.0987, + "step": 389940 + }, + { + "epoch": 0.87, + "learning_rate": 6.513165253573745e-06, + "loss": 0.0967, + "step": 389950 + }, + { + "epoch": 0.87, + "learning_rate": 6.512046710364422e-06, + "loss": 0.0971, + "step": 389960 + }, + { + "epoch": 0.87, + "learning_rate": 6.510928167155098e-06, + "loss": 0.0937, + "step": 389970 + }, + { + "epoch": 0.87, + "learning_rate": 6.509809623945773e-06, + "loss": 0.0971, + "step": 389980 + }, + { + "epoch": 0.87, + "learning_rate": 6.508691080736449e-06, + "loss": 0.0999, + "step": 389990 + }, + { + "epoch": 0.87, + "learning_rate": 6.507572537527125e-06, + "loss": 0.0917, + "step": 390000 + }, + { + "epoch": 0.87, + "learning_rate": 6.5064539943178e-06, + "loss": 0.0962, + "step": 390010 + }, + { + "epoch": 0.87, + "learning_rate": 6.505335451108477e-06, + "loss": 0.0955, + "step": 390020 + }, + { + "epoch": 0.87, + "learning_rate": 6.5042169078991525e-06, + "loss": 0.0947, + "step": 390030 + }, + { + "epoch": 0.87, + "learning_rate": 6.503098364689829e-06, + "loss": 0.0939, + "step": 390040 + }, + { + "epoch": 0.87, + "learning_rate": 6.501979821480504e-06, + "loss": 0.0927, + "step": 390050 + }, + { + "epoch": 0.87, + "learning_rate": 6.5008612782711795e-06, + "loss": 0.0951, + "step": 390060 + }, + { + "epoch": 0.87, + "learning_rate": 6.499742735061856e-06, + "loss": 0.0952, + "step": 390070 + }, + { + "epoch": 0.87, + "learning_rate": 6.498624191852531e-06, + "loss": 0.0944, + "step": 390080 + }, + { + "epoch": 0.87, + "learning_rate": 6.4975056486432065e-06, + "loss": 0.0964, + "step": 390090 + }, + { + "epoch": 0.87, + "learning_rate": 6.496387105433884e-06, + "loss": 0.0929, + "step": 390100 + }, + { + "epoch": 0.87, + "learning_rate": 6.495268562224559e-06, + "loss": 0.0936, + "step": 390110 + }, + { + "epoch": 0.87, + "learning_rate": 6.494150019015235e-06, + "loss": 0.0975, + "step": 390120 + }, + { + "epoch": 0.87, + "learning_rate": 6.493031475805911e-06, + "loss": 0.0973, + "step": 390130 + }, + { + "epoch": 0.87, + "learning_rate": 6.491912932596586e-06, + "loss": 0.0952, + "step": 390140 + }, + { + "epoch": 0.87, + "learning_rate": 6.490794389387263e-06, + "loss": 0.0981, + "step": 390150 + }, + { + "epoch": 0.87, + "learning_rate": 6.4896758461779385e-06, + "loss": 0.0975, + "step": 390160 + }, + { + "epoch": 0.87, + "learning_rate": 6.488557302968613e-06, + "loss": 0.0933, + "step": 390170 + }, + { + "epoch": 0.87, + "learning_rate": 6.48743875975929e-06, + "loss": 0.0956, + "step": 390180 + }, + { + "epoch": 0.87, + "learning_rate": 6.4863202165499655e-06, + "loss": 0.0981, + "step": 390190 + }, + { + "epoch": 0.87, + "learning_rate": 6.485201673340642e-06, + "loss": 0.0994, + "step": 390200 + }, + { + "epoch": 0.87, + "learning_rate": 6.484083130131317e-06, + "loss": 0.0979, + "step": 390210 + }, + { + "epoch": 0.87, + "learning_rate": 6.4829645869219925e-06, + "loss": 0.0984, + "step": 390220 + }, + { + "epoch": 0.87, + "learning_rate": 6.4818460437126696e-06, + "loss": 0.0937, + "step": 390230 + }, + { + "epoch": 0.87, + "learning_rate": 6.480727500503345e-06, + "loss": 0.0981, + "step": 390240 + }, + { + "epoch": 0.87, + "learning_rate": 6.47960895729402e-06, + "loss": 0.0936, + "step": 390250 + }, + { + "epoch": 0.87, + "learning_rate": 6.4784904140846966e-06, + "loss": 0.0896, + "step": 390260 + }, + { + "epoch": 0.87, + "learning_rate": 6.477371870875372e-06, + "loss": 0.0896, + "step": 390270 + }, + { + "epoch": 0.87, + "learning_rate": 6.476253327666049e-06, + "loss": 0.0956, + "step": 390280 + }, + { + "epoch": 0.87, + "learning_rate": 6.475134784456724e-06, + "loss": 0.094, + "step": 390290 + }, + { + "epoch": 0.87, + "learning_rate": 6.474016241247399e-06, + "loss": 0.0968, + "step": 390300 + }, + { + "epoch": 0.87, + "learning_rate": 6.472897698038076e-06, + "loss": 0.0933, + "step": 390310 + }, + { + "epoch": 0.87, + "learning_rate": 6.4717791548287514e-06, + "loss": 0.0916, + "step": 390320 + }, + { + "epoch": 0.87, + "learning_rate": 6.470660611619427e-06, + "loss": 0.0935, + "step": 390330 + }, + { + "epoch": 0.87, + "learning_rate": 6.469542068410103e-06, + "loss": 0.0944, + "step": 390340 + }, + { + "epoch": 0.87, + "learning_rate": 6.4684235252007784e-06, + "loss": 0.1026, + "step": 390350 + }, + { + "epoch": 0.87, + "learning_rate": 6.4673049819914555e-06, + "loss": 0.0955, + "step": 390360 + }, + { + "epoch": 0.87, + "learning_rate": 6.466186438782131e-06, + "loss": 0.0999, + "step": 390370 + }, + { + "epoch": 0.87, + "learning_rate": 6.4650678955728055e-06, + "loss": 0.098, + "step": 390380 + }, + { + "epoch": 0.87, + "learning_rate": 6.4639493523634825e-06, + "loss": 0.0943, + "step": 390390 + }, + { + "epoch": 0.87, + "learning_rate": 6.462830809154158e-06, + "loss": 0.0967, + "step": 390400 + }, + { + "epoch": 0.87, + "learning_rate": 6.461712265944833e-06, + "loss": 0.0945, + "step": 390410 + }, + { + "epoch": 0.87, + "learning_rate": 6.4605937227355095e-06, + "loss": 0.0965, + "step": 390420 + }, + { + "epoch": 0.87, + "learning_rate": 6.459475179526185e-06, + "loss": 0.0914, + "step": 390430 + }, + { + "epoch": 0.87, + "learning_rate": 6.458356636316862e-06, + "loss": 0.0931, + "step": 390440 + }, + { + "epoch": 0.87, + "learning_rate": 6.457238093107537e-06, + "loss": 0.0951, + "step": 390450 + }, + { + "epoch": 0.87, + "learning_rate": 6.456119549898213e-06, + "loss": 0.0979, + "step": 390460 + }, + { + "epoch": 0.87, + "learning_rate": 6.455001006688889e-06, + "loss": 0.0919, + "step": 390470 + }, + { + "epoch": 0.87, + "learning_rate": 6.453882463479564e-06, + "loss": 0.0937, + "step": 390480 + }, + { + "epoch": 0.87, + "learning_rate": 6.45276392027024e-06, + "loss": 0.0946, + "step": 390490 + }, + { + "epoch": 0.87, + "learning_rate": 6.451645377060916e-06, + "loss": 0.0991, + "step": 390500 + }, + { + "epoch": 0.87, + "learning_rate": 6.450526833851591e-06, + "loss": 0.0978, + "step": 390510 + }, + { + "epoch": 0.87, + "learning_rate": 6.4494082906422685e-06, + "loss": 0.0972, + "step": 390520 + }, + { + "epoch": 0.87, + "learning_rate": 6.448289747432944e-06, + "loss": 0.095, + "step": 390530 + }, + { + "epoch": 0.87, + "learning_rate": 6.447171204223619e-06, + "loss": 0.0923, + "step": 390540 + }, + { + "epoch": 0.87, + "learning_rate": 6.4460526610142955e-06, + "loss": 0.0986, + "step": 390550 + }, + { + "epoch": 0.87, + "learning_rate": 6.444934117804971e-06, + "loss": 0.0948, + "step": 390560 + }, + { + "epoch": 0.87, + "learning_rate": 6.443815574595646e-06, + "loss": 0.0953, + "step": 390570 + }, + { + "epoch": 0.87, + "learning_rate": 6.442697031386323e-06, + "loss": 0.0977, + "step": 390580 + }, + { + "epoch": 0.87, + "learning_rate": 6.441578488176999e-06, + "loss": 0.0968, + "step": 390590 + }, + { + "epoch": 0.87, + "learning_rate": 6.440459944967675e-06, + "loss": 0.0938, + "step": 390600 + }, + { + "epoch": 0.87, + "learning_rate": 6.43934140175835e-06, + "loss": 0.0917, + "step": 390610 + }, + { + "epoch": 0.87, + "learning_rate": 6.438222858549026e-06, + "loss": 0.1016, + "step": 390620 + }, + { + "epoch": 0.87, + "learning_rate": 6.437104315339702e-06, + "loss": 0.0941, + "step": 390630 + }, + { + "epoch": 0.87, + "learning_rate": 6.435985772130377e-06, + "loss": 0.0939, + "step": 390640 + }, + { + "epoch": 0.87, + "learning_rate": 6.434867228921053e-06, + "loss": 0.0914, + "step": 390650 + }, + { + "epoch": 0.87, + "learning_rate": 6.43374868571173e-06, + "loss": 0.092, + "step": 390660 + }, + { + "epoch": 0.87, + "learning_rate": 6.432630142502405e-06, + "loss": 0.0942, + "step": 390670 + }, + { + "epoch": 0.87, + "learning_rate": 6.4315115992930814e-06, + "loss": 0.0986, + "step": 390680 + }, + { + "epoch": 0.87, + "learning_rate": 6.430393056083757e-06, + "loss": 0.1, + "step": 390690 + }, + { + "epoch": 0.87, + "learning_rate": 6.429274512874432e-06, + "loss": 0.0933, + "step": 390700 + }, + { + "epoch": 0.87, + "learning_rate": 6.428155969665109e-06, + "loss": 0.0957, + "step": 390710 + }, + { + "epoch": 0.87, + "learning_rate": 6.427037426455784e-06, + "loss": 0.0952, + "step": 390720 + }, + { + "epoch": 0.87, + "learning_rate": 6.425918883246459e-06, + "loss": 0.0975, + "step": 390730 + }, + { + "epoch": 0.87, + "learning_rate": 6.424800340037136e-06, + "loss": 0.0939, + "step": 390740 + }, + { + "epoch": 0.87, + "learning_rate": 6.423681796827812e-06, + "loss": 0.0925, + "step": 390750 + }, + { + "epoch": 0.87, + "learning_rate": 6.422563253618488e-06, + "loss": 0.0938, + "step": 390760 + }, + { + "epoch": 0.87, + "learning_rate": 6.421444710409163e-06, + "loss": 0.0977, + "step": 390770 + }, + { + "epoch": 0.87, + "learning_rate": 6.420326167199839e-06, + "loss": 0.0962, + "step": 390780 + }, + { + "epoch": 0.87, + "learning_rate": 6.419207623990516e-06, + "loss": 0.095, + "step": 390790 + }, + { + "epoch": 0.87, + "learning_rate": 6.418089080781191e-06, + "loss": 0.0978, + "step": 390800 + }, + { + "epoch": 0.87, + "learning_rate": 6.416970537571866e-06, + "loss": 0.0949, + "step": 390810 + }, + { + "epoch": 0.87, + "learning_rate": 6.415851994362543e-06, + "loss": 0.0971, + "step": 390820 + }, + { + "epoch": 0.87, + "learning_rate": 6.414733451153218e-06, + "loss": 0.0968, + "step": 390830 + }, + { + "epoch": 0.87, + "learning_rate": 6.413614907943894e-06, + "loss": 0.0951, + "step": 390840 + }, + { + "epoch": 0.87, + "learning_rate": 6.41249636473457e-06, + "loss": 0.1, + "step": 390850 + }, + { + "epoch": 0.87, + "learning_rate": 6.411377821525245e-06, + "loss": 0.0948, + "step": 390860 + }, + { + "epoch": 0.87, + "learning_rate": 6.410259278315922e-06, + "loss": 0.0971, + "step": 390870 + }, + { + "epoch": 0.87, + "learning_rate": 6.409140735106598e-06, + "loss": 0.0971, + "step": 390880 + }, + { + "epoch": 0.87, + "learning_rate": 6.408022191897273e-06, + "loss": 0.0949, + "step": 390890 + }, + { + "epoch": 0.87, + "learning_rate": 6.406903648687949e-06, + "loss": 0.0944, + "step": 390900 + }, + { + "epoch": 0.87, + "learning_rate": 6.405785105478625e-06, + "loss": 0.0864, + "step": 390910 + }, + { + "epoch": 0.87, + "learning_rate": 6.404666562269302e-06, + "loss": 0.0939, + "step": 390920 + }, + { + "epoch": 0.87, + "learning_rate": 6.403548019059976e-06, + "loss": 0.0935, + "step": 390930 + }, + { + "epoch": 0.87, + "learning_rate": 6.402429475850652e-06, + "loss": 0.0992, + "step": 390940 + }, + { + "epoch": 0.87, + "learning_rate": 6.401310932641329e-06, + "loss": 0.0941, + "step": 390950 + }, + { + "epoch": 0.87, + "learning_rate": 6.400192389432004e-06, + "loss": 0.096, + "step": 390960 + }, + { + "epoch": 0.87, + "learning_rate": 6.3990738462226795e-06, + "loss": 0.0934, + "step": 390970 + }, + { + "epoch": 0.87, + "learning_rate": 6.397955303013356e-06, + "loss": 0.0962, + "step": 390980 + }, + { + "epoch": 0.87, + "learning_rate": 6.396836759804031e-06, + "loss": 0.0939, + "step": 390990 + }, + { + "epoch": 0.87, + "learning_rate": 6.395718216594708e-06, + "loss": 0.0928, + "step": 391000 + }, + { + "epoch": 0.87, + "learning_rate": 6.394599673385384e-06, + "loss": 0.0947, + "step": 391010 + }, + { + "epoch": 0.87, + "learning_rate": 6.393481130176059e-06, + "loss": 0.0977, + "step": 391020 + }, + { + "epoch": 0.87, + "learning_rate": 6.392362586966735e-06, + "loss": 0.1005, + "step": 391030 + }, + { + "epoch": 0.87, + "learning_rate": 6.391244043757411e-06, + "loss": 0.0924, + "step": 391040 + }, + { + "epoch": 0.87, + "learning_rate": 6.390125500548086e-06, + "loss": 0.0959, + "step": 391050 + }, + { + "epoch": 0.87, + "learning_rate": 6.389006957338762e-06, + "loss": 0.0912, + "step": 391060 + }, + { + "epoch": 0.87, + "learning_rate": 6.387888414129438e-06, + "loss": 0.0963, + "step": 391070 + }, + { + "epoch": 0.87, + "learning_rate": 6.386769870920115e-06, + "loss": 0.0951, + "step": 391080 + }, + { + "epoch": 0.87, + "learning_rate": 6.38565132771079e-06, + "loss": 0.0966, + "step": 391090 + }, + { + "epoch": 0.87, + "learning_rate": 6.3845327845014655e-06, + "loss": 0.0931, + "step": 391100 + }, + { + "epoch": 0.87, + "learning_rate": 6.383414241292142e-06, + "loss": 0.0918, + "step": 391110 + }, + { + "epoch": 0.87, + "learning_rate": 6.382295698082817e-06, + "loss": 0.0932, + "step": 391120 + }, + { + "epoch": 0.87, + "learning_rate": 6.3811771548734925e-06, + "loss": 0.0953, + "step": 391130 + }, + { + "epoch": 0.87, + "learning_rate": 6.3800586116641696e-06, + "loss": 0.0939, + "step": 391140 + }, + { + "epoch": 0.87, + "learning_rate": 6.378940068454844e-06, + "loss": 0.0976, + "step": 391150 + }, + { + "epoch": 0.87, + "learning_rate": 6.377821525245521e-06, + "loss": 0.0951, + "step": 391160 + }, + { + "epoch": 0.87, + "learning_rate": 6.3767029820361966e-06, + "loss": 0.0973, + "step": 391170 + }, + { + "epoch": 0.87, + "learning_rate": 6.375584438826872e-06, + "loss": 0.0909, + "step": 391180 + }, + { + "epoch": 0.87, + "learning_rate": 6.374465895617548e-06, + "loss": 0.0938, + "step": 391190 + }, + { + "epoch": 0.87, + "learning_rate": 6.3733473524082236e-06, + "loss": 0.0995, + "step": 391200 + }, + { + "epoch": 0.87, + "learning_rate": 6.372228809198899e-06, + "loss": 0.0962, + "step": 391210 + }, + { + "epoch": 0.87, + "learning_rate": 6.371110265989576e-06, + "loss": 0.0996, + "step": 391220 + }, + { + "epoch": 0.87, + "learning_rate": 6.3699917227802514e-06, + "loss": 0.0971, + "step": 391230 + }, + { + "epoch": 0.87, + "learning_rate": 6.368873179570928e-06, + "loss": 0.0954, + "step": 391240 + }, + { + "epoch": 0.87, + "learning_rate": 6.367754636361603e-06, + "loss": 0.0953, + "step": 391250 + }, + { + "epoch": 0.87, + "learning_rate": 6.3666360931522784e-06, + "loss": 0.0969, + "step": 391260 + }, + { + "epoch": 0.87, + "learning_rate": 6.365517549942955e-06, + "loss": 0.0932, + "step": 391270 + }, + { + "epoch": 0.87, + "learning_rate": 6.36439900673363e-06, + "loss": 0.0954, + "step": 391280 + }, + { + "epoch": 0.87, + "learning_rate": 6.3632804635243054e-06, + "loss": 0.0933, + "step": 391290 + }, + { + "epoch": 0.87, + "learning_rate": 6.3621619203149825e-06, + "loss": 0.093, + "step": 391300 + }, + { + "epoch": 0.87, + "learning_rate": 6.361043377105658e-06, + "loss": 0.0946, + "step": 391310 + }, + { + "epoch": 0.87, + "learning_rate": 6.359924833896334e-06, + "loss": 0.0912, + "step": 391320 + }, + { + "epoch": 0.87, + "learning_rate": 6.3588062906870095e-06, + "loss": 0.0909, + "step": 391330 + }, + { + "epoch": 0.87, + "learning_rate": 6.357687747477685e-06, + "loss": 0.0951, + "step": 391340 + }, + { + "epoch": 0.87, + "learning_rate": 6.356569204268362e-06, + "loss": 0.0909, + "step": 391350 + }, + { + "epoch": 0.87, + "learning_rate": 6.355450661059037e-06, + "loss": 0.0944, + "step": 391360 + }, + { + "epoch": 0.87, + "learning_rate": 6.354332117849712e-06, + "loss": 0.0929, + "step": 391370 + }, + { + "epoch": 0.87, + "learning_rate": 6.353213574640389e-06, + "loss": 0.0971, + "step": 391380 + }, + { + "epoch": 0.87, + "learning_rate": 6.352095031431064e-06, + "loss": 0.096, + "step": 391390 + }, + { + "epoch": 0.87, + "learning_rate": 6.350976488221741e-06, + "loss": 0.0914, + "step": 391400 + }, + { + "epoch": 0.87, + "learning_rate": 6.349857945012416e-06, + "loss": 0.0906, + "step": 391410 + }, + { + "epoch": 0.87, + "learning_rate": 6.348739401803091e-06, + "loss": 0.0944, + "step": 391420 + }, + { + "epoch": 0.87, + "learning_rate": 6.3476208585937685e-06, + "loss": 0.0987, + "step": 391430 + }, + { + "epoch": 0.87, + "learning_rate": 6.346502315384444e-06, + "loss": 0.0976, + "step": 391440 + }, + { + "epoch": 0.87, + "learning_rate": 6.345383772175119e-06, + "loss": 0.0921, + "step": 391450 + }, + { + "epoch": 0.87, + "learning_rate": 6.3442652289657955e-06, + "loss": 0.0957, + "step": 391460 + }, + { + "epoch": 0.87, + "learning_rate": 6.343146685756471e-06, + "loss": 0.0925, + "step": 391470 + }, + { + "epoch": 0.87, + "learning_rate": 6.342028142547148e-06, + "loss": 0.0917, + "step": 391480 + }, + { + "epoch": 0.87, + "learning_rate": 6.3409095993378225e-06, + "loss": 0.0972, + "step": 391490 + }, + { + "epoch": 0.87, + "learning_rate": 6.339791056128498e-06, + "loss": 0.0956, + "step": 391500 + }, + { + "epoch": 0.87, + "learning_rate": 6.338672512919175e-06, + "loss": 0.0956, + "step": 391510 + }, + { + "epoch": 0.87, + "learning_rate": 6.33755396970985e-06, + "loss": 0.0959, + "step": 391520 + }, + { + "epoch": 0.87, + "learning_rate": 6.336547280821459e-06, + "loss": 0.0941, + "step": 391530 + }, + { + "epoch": 0.87, + "learning_rate": 6.335428737612134e-06, + "loss": 0.0936, + "step": 391540 + }, + { + "epoch": 0.87, + "learning_rate": 6.334310194402811e-06, + "loss": 0.0928, + "step": 391550 + }, + { + "epoch": 0.87, + "learning_rate": 6.333191651193486e-06, + "loss": 0.0947, + "step": 391560 + }, + { + "epoch": 0.87, + "learning_rate": 6.3320731079841615e-06, + "loss": 0.0933, + "step": 391570 + }, + { + "epoch": 0.87, + "learning_rate": 6.330954564774838e-06, + "loss": 0.0966, + "step": 391580 + }, + { + "epoch": 0.87, + "learning_rate": 6.329836021565513e-06, + "loss": 0.0938, + "step": 391590 + }, + { + "epoch": 0.87, + "learning_rate": 6.3287174783561885e-06, + "loss": 0.0929, + "step": 391600 + }, + { + "epoch": 0.87, + "learning_rate": 6.327598935146866e-06, + "loss": 0.0948, + "step": 391610 + }, + { + "epoch": 0.87, + "learning_rate": 6.326480391937541e-06, + "loss": 0.0957, + "step": 391620 + }, + { + "epoch": 0.87, + "learning_rate": 6.325361848728217e-06, + "loss": 0.0943, + "step": 391630 + }, + { + "epoch": 0.87, + "learning_rate": 6.324243305518893e-06, + "loss": 0.0934, + "step": 391640 + }, + { + "epoch": 0.87, + "learning_rate": 6.323124762309568e-06, + "loss": 0.0966, + "step": 391650 + }, + { + "epoch": 0.87, + "learning_rate": 6.322006219100245e-06, + "loss": 0.0956, + "step": 391660 + }, + { + "epoch": 0.87, + "learning_rate": 6.32088767589092e-06, + "loss": 0.0937, + "step": 391670 + }, + { + "epoch": 0.87, + "learning_rate": 6.319769132681595e-06, + "loss": 0.0944, + "step": 391680 + }, + { + "epoch": 0.87, + "learning_rate": 6.318650589472272e-06, + "loss": 0.0958, + "step": 391690 + }, + { + "epoch": 0.87, + "learning_rate": 6.3175320462629475e-06, + "loss": 0.0954, + "step": 391700 + }, + { + "epoch": 0.87, + "learning_rate": 6.316413503053624e-06, + "loss": 0.0935, + "step": 391710 + }, + { + "epoch": 0.87, + "learning_rate": 6.315294959844299e-06, + "loss": 0.0913, + "step": 391720 + }, + { + "epoch": 0.87, + "learning_rate": 6.3141764166349745e-06, + "loss": 0.0942, + "step": 391730 + }, + { + "epoch": 0.87, + "learning_rate": 6.3130578734256516e-06, + "loss": 0.0952, + "step": 391740 + }, + { + "epoch": 0.87, + "learning_rate": 6.311939330216327e-06, + "loss": 0.0915, + "step": 391750 + }, + { + "epoch": 0.87, + "learning_rate": 6.3108207870070015e-06, + "loss": 0.0924, + "step": 391760 + }, + { + "epoch": 0.87, + "learning_rate": 6.3097022437976786e-06, + "loss": 0.0979, + "step": 391770 + }, + { + "epoch": 0.87, + "learning_rate": 6.308583700588354e-06, + "loss": 0.0898, + "step": 391780 + }, + { + "epoch": 0.87, + "learning_rate": 6.30746515737903e-06, + "loss": 0.0899, + "step": 391790 + }, + { + "epoch": 0.87, + "learning_rate": 6.3063466141697056e-06, + "loss": 0.0908, + "step": 391800 + }, + { + "epoch": 0.87, + "learning_rate": 6.305228070960381e-06, + "loss": 0.0953, + "step": 391810 + }, + { + "epoch": 0.87, + "learning_rate": 6.304109527751058e-06, + "loss": 0.0934, + "step": 391820 + }, + { + "epoch": 0.87, + "learning_rate": 6.3029909845417334e-06, + "loss": 0.0942, + "step": 391830 + }, + { + "epoch": 0.87, + "learning_rate": 6.301872441332409e-06, + "loss": 0.098, + "step": 391840 + }, + { + "epoch": 0.87, + "learning_rate": 6.300753898123085e-06, + "loss": 0.0952, + "step": 391850 + }, + { + "epoch": 0.87, + "learning_rate": 6.2996353549137604e-06, + "loss": 0.0982, + "step": 391860 + }, + { + "epoch": 0.87, + "learning_rate": 6.2985168117044375e-06, + "loss": 0.0938, + "step": 391870 + }, + { + "epoch": 0.87, + "learning_rate": 6.297398268495112e-06, + "loss": 0.0909, + "step": 391880 + }, + { + "epoch": 0.87, + "learning_rate": 6.2962797252857874e-06, + "loss": 0.0937, + "step": 391890 + }, + { + "epoch": 0.87, + "learning_rate": 6.2951611820764645e-06, + "loss": 0.0957, + "step": 391900 + }, + { + "epoch": 0.87, + "learning_rate": 6.29404263886714e-06, + "loss": 0.0981, + "step": 391910 + }, + { + "epoch": 0.87, + "learning_rate": 6.292924095657815e-06, + "loss": 0.093, + "step": 391920 + }, + { + "epoch": 0.87, + "learning_rate": 6.2918055524484915e-06, + "loss": 0.0922, + "step": 391930 + }, + { + "epoch": 0.87, + "learning_rate": 6.290687009239167e-06, + "loss": 0.0959, + "step": 391940 + }, + { + "epoch": 0.87, + "learning_rate": 6.289568466029842e-06, + "loss": 0.0914, + "step": 391950 + }, + { + "epoch": 0.87, + "learning_rate": 6.288449922820519e-06, + "loss": 0.0916, + "step": 391960 + }, + { + "epoch": 0.87, + "learning_rate": 6.287331379611194e-06, + "loss": 0.0943, + "step": 391970 + }, + { + "epoch": 0.87, + "learning_rate": 6.286212836401871e-06, + "loss": 0.0921, + "step": 391980 + }, + { + "epoch": 0.87, + "learning_rate": 6.285094293192546e-06, + "loss": 0.0913, + "step": 391990 + }, + { + "epoch": 0.87, + "learning_rate": 6.283975749983222e-06, + "loss": 0.0961, + "step": 392000 + }, + { + "epoch": 0.88, + "learning_rate": 6.282857206773898e-06, + "loss": 0.0981, + "step": 392010 + }, + { + "epoch": 0.88, + "learning_rate": 6.281738663564573e-06, + "loss": 0.0976, + "step": 392020 + }, + { + "epoch": 0.88, + "learning_rate": 6.280620120355249e-06, + "loss": 0.0918, + "step": 392030 + }, + { + "epoch": 0.88, + "learning_rate": 6.279501577145926e-06, + "loss": 0.0983, + "step": 392040 + }, + { + "epoch": 0.88, + "learning_rate": 6.278383033936601e-06, + "loss": 0.09, + "step": 392050 + }, + { + "epoch": 0.88, + "learning_rate": 6.2772644907272775e-06, + "loss": 0.0911, + "step": 392060 + }, + { + "epoch": 0.88, + "learning_rate": 6.276145947517953e-06, + "loss": 0.0913, + "step": 392070 + }, + { + "epoch": 0.88, + "learning_rate": 6.275027404308628e-06, + "loss": 0.0996, + "step": 392080 + }, + { + "epoch": 0.88, + "learning_rate": 6.273908861099305e-06, + "loss": 0.0976, + "step": 392090 + }, + { + "epoch": 0.88, + "learning_rate": 6.27279031788998e-06, + "loss": 0.0968, + "step": 392100 + }, + { + "epoch": 0.88, + "learning_rate": 6.271671774680655e-06, + "loss": 0.0992, + "step": 392110 + }, + { + "epoch": 0.88, + "learning_rate": 6.270553231471332e-06, + "loss": 0.097, + "step": 392120 + }, + { + "epoch": 0.88, + "learning_rate": 6.269434688262008e-06, + "loss": 0.0951, + "step": 392130 + }, + { + "epoch": 0.88, + "learning_rate": 6.268316145052684e-06, + "loss": 0.0969, + "step": 392140 + }, + { + "epoch": 0.88, + "learning_rate": 6.267197601843359e-06, + "loss": 0.0929, + "step": 392150 + }, + { + "epoch": 0.88, + "learning_rate": 6.266079058634035e-06, + "loss": 0.097, + "step": 392160 + }, + { + "epoch": 0.88, + "learning_rate": 6.264960515424712e-06, + "loss": 0.088, + "step": 392170 + }, + { + "epoch": 0.88, + "learning_rate": 6.263841972215387e-06, + "loss": 0.095, + "step": 392180 + }, + { + "epoch": 0.88, + "learning_rate": 6.262723429006062e-06, + "loss": 0.0925, + "step": 392190 + }, + { + "epoch": 0.88, + "learning_rate": 6.261604885796739e-06, + "loss": 0.0959, + "step": 392200 + }, + { + "epoch": 0.88, + "learning_rate": 6.260486342587414e-06, + "loss": 0.0959, + "step": 392210 + }, + { + "epoch": 0.88, + "learning_rate": 6.2593677993780904e-06, + "loss": 0.0943, + "step": 392220 + }, + { + "epoch": 0.88, + "learning_rate": 6.258249256168766e-06, + "loss": 0.0912, + "step": 392230 + }, + { + "epoch": 0.88, + "learning_rate": 6.257130712959441e-06, + "loss": 0.0934, + "step": 392240 + }, + { + "epoch": 0.88, + "learning_rate": 6.256012169750118e-06, + "loss": 0.0994, + "step": 392250 + }, + { + "epoch": 0.88, + "learning_rate": 6.254893626540794e-06, + "loss": 0.0914, + "step": 392260 + }, + { + "epoch": 0.88, + "learning_rate": 6.253775083331469e-06, + "loss": 0.0913, + "step": 392270 + }, + { + "epoch": 0.88, + "learning_rate": 6.252656540122145e-06, + "loss": 0.0952, + "step": 392280 + }, + { + "epoch": 0.88, + "learning_rate": 6.251537996912821e-06, + "loss": 0.0938, + "step": 392290 + }, + { + "epoch": 0.88, + "learning_rate": 6.250419453703498e-06, + "loss": 0.0933, + "step": 392300 + }, + { + "epoch": 0.88, + "learning_rate": 6.249300910494172e-06, + "loss": 0.0941, + "step": 392310 + }, + { + "epoch": 0.88, + "learning_rate": 6.2481823672848485e-06, + "loss": 0.0929, + "step": 392320 + }, + { + "epoch": 0.88, + "learning_rate": 6.247063824075524e-06, + "loss": 0.0959, + "step": 392330 + }, + { + "epoch": 0.88, + "learning_rate": 6.2459452808662e-06, + "loss": 0.0947, + "step": 392340 + }, + { + "epoch": 0.88, + "learning_rate": 6.244826737656876e-06, + "loss": 0.0902, + "step": 392350 + }, + { + "epoch": 0.88, + "learning_rate": 6.243708194447552e-06, + "loss": 0.0935, + "step": 392360 + }, + { + "epoch": 0.88, + "learning_rate": 6.242589651238227e-06, + "loss": 0.0964, + "step": 392370 + }, + { + "epoch": 0.88, + "learning_rate": 6.241471108028903e-06, + "loss": 0.0994, + "step": 392380 + }, + { + "epoch": 0.88, + "learning_rate": 6.24035256481958e-06, + "loss": 0.0889, + "step": 392390 + }, + { + "epoch": 0.88, + "learning_rate": 6.239234021610255e-06, + "loss": 0.0913, + "step": 392400 + }, + { + "epoch": 0.88, + "learning_rate": 6.23811547840093e-06, + "loss": 0.0939, + "step": 392410 + }, + { + "epoch": 0.88, + "learning_rate": 6.236996935191607e-06, + "loss": 0.0977, + "step": 392420 + }, + { + "epoch": 0.88, + "learning_rate": 6.235878391982283e-06, + "loss": 0.0967, + "step": 392430 + }, + { + "epoch": 0.88, + "learning_rate": 6.234759848772958e-06, + "loss": 0.0958, + "step": 392440 + }, + { + "epoch": 0.88, + "learning_rate": 6.233641305563634e-06, + "loss": 0.0937, + "step": 392450 + }, + { + "epoch": 0.88, + "learning_rate": 6.23252276235431e-06, + "loss": 0.0921, + "step": 392460 + }, + { + "epoch": 0.88, + "learning_rate": 6.231404219144986e-06, + "loss": 0.0954, + "step": 392470 + }, + { + "epoch": 0.88, + "learning_rate": 6.2302856759356615e-06, + "loss": 0.093, + "step": 392480 + }, + { + "epoch": 0.88, + "learning_rate": 6.229167132726337e-06, + "loss": 0.0941, + "step": 392490 + }, + { + "epoch": 0.88, + "learning_rate": 6.228048589517013e-06, + "loss": 0.0977, + "step": 392500 + }, + { + "epoch": 0.88, + "learning_rate": 6.226930046307689e-06, + "loss": 0.0956, + "step": 392510 + }, + { + "epoch": 0.88, + "learning_rate": 6.225811503098366e-06, + "loss": 0.0945, + "step": 392520 + }, + { + "epoch": 0.88, + "learning_rate": 6.22469295988904e-06, + "loss": 0.0964, + "step": 392530 + }, + { + "epoch": 0.88, + "learning_rate": 6.223574416679716e-06, + "loss": 0.0969, + "step": 392540 + }, + { + "epoch": 0.88, + "learning_rate": 6.222455873470393e-06, + "loss": 0.0938, + "step": 392550 + }, + { + "epoch": 0.88, + "learning_rate": 6.221337330261069e-06, + "loss": 0.0967, + "step": 392560 + }, + { + "epoch": 0.88, + "learning_rate": 6.220218787051743e-06, + "loss": 0.0921, + "step": 392570 + }, + { + "epoch": 0.88, + "learning_rate": 6.21910024384242e-06, + "loss": 0.0996, + "step": 392580 + }, + { + "epoch": 0.88, + "learning_rate": 6.217981700633096e-06, + "loss": 0.0966, + "step": 392590 + }, + { + "epoch": 0.88, + "learning_rate": 6.216863157423772e-06, + "loss": 0.0939, + "step": 392600 + }, + { + "epoch": 0.88, + "learning_rate": 6.2157446142144475e-06, + "loss": 0.0958, + "step": 392610 + }, + { + "epoch": 0.88, + "learning_rate": 6.214626071005123e-06, + "loss": 0.0935, + "step": 392620 + }, + { + "epoch": 0.88, + "learning_rate": 6.213507527795799e-06, + "loss": 0.0971, + "step": 392630 + }, + { + "epoch": 0.88, + "learning_rate": 6.212388984586475e-06, + "loss": 0.0944, + "step": 392640 + }, + { + "epoch": 0.88, + "learning_rate": 6.211270441377151e-06, + "loss": 0.0976, + "step": 392650 + }, + { + "epoch": 0.88, + "learning_rate": 6.210151898167826e-06, + "loss": 0.0987, + "step": 392660 + }, + { + "epoch": 0.88, + "learning_rate": 6.209033354958502e-06, + "loss": 0.0963, + "step": 392670 + }, + { + "epoch": 0.88, + "learning_rate": 6.2079148117491786e-06, + "loss": 0.0997, + "step": 392680 + }, + { + "epoch": 0.88, + "learning_rate": 6.206796268539854e-06, + "loss": 0.0913, + "step": 392690 + }, + { + "epoch": 0.88, + "learning_rate": 6.205677725330529e-06, + "loss": 0.0975, + "step": 392700 + }, + { + "epoch": 0.88, + "learning_rate": 6.2045591821212056e-06, + "loss": 0.0906, + "step": 392710 + }, + { + "epoch": 0.88, + "learning_rate": 6.203440638911882e-06, + "loss": 0.095, + "step": 392720 + }, + { + "epoch": 0.88, + "learning_rate": 6.202322095702557e-06, + "loss": 0.0981, + "step": 392730 + }, + { + "epoch": 0.88, + "learning_rate": 6.2012035524932326e-06, + "loss": 0.0928, + "step": 392740 + }, + { + "epoch": 0.88, + "learning_rate": 6.200085009283909e-06, + "loss": 0.0942, + "step": 392750 + }, + { + "epoch": 0.88, + "learning_rate": 6.198966466074585e-06, + "loss": 0.0943, + "step": 392760 + }, + { + "epoch": 0.88, + "learning_rate": 6.19784792286526e-06, + "loss": 0.0945, + "step": 392770 + }, + { + "epoch": 0.88, + "learning_rate": 6.196729379655937e-06, + "loss": 0.0938, + "step": 392780 + }, + { + "epoch": 0.88, + "learning_rate": 6.195610836446612e-06, + "loss": 0.0935, + "step": 392790 + }, + { + "epoch": 0.88, + "learning_rate": 6.194492293237288e-06, + "loss": 0.0965, + "step": 392800 + }, + { + "epoch": 0.88, + "learning_rate": 6.193373750027964e-06, + "loss": 0.0938, + "step": 392810 + }, + { + "epoch": 0.88, + "learning_rate": 6.19225520681864e-06, + "loss": 0.0926, + "step": 392820 + }, + { + "epoch": 0.88, + "learning_rate": 6.191136663609315e-06, + "loss": 0.0934, + "step": 392830 + }, + { + "epoch": 0.88, + "learning_rate": 6.1900181203999915e-06, + "loss": 0.09, + "step": 392840 + }, + { + "epoch": 0.88, + "learning_rate": 6.188899577190667e-06, + "loss": 0.0974, + "step": 392850 + }, + { + "epoch": 0.88, + "learning_rate": 6.187781033981343e-06, + "loss": 0.0967, + "step": 392860 + }, + { + "epoch": 0.88, + "learning_rate": 6.1866624907720185e-06, + "loss": 0.0978, + "step": 392870 + }, + { + "epoch": 0.88, + "learning_rate": 6.185543947562695e-06, + "loss": 0.0948, + "step": 392880 + }, + { + "epoch": 0.88, + "learning_rate": 6.18442540435337e-06, + "loss": 0.0953, + "step": 392890 + }, + { + "epoch": 0.88, + "learning_rate": 6.183306861144046e-06, + "loss": 0.0944, + "step": 392900 + }, + { + "epoch": 0.88, + "learning_rate": 6.182188317934722e-06, + "loss": 0.0922, + "step": 392910 + }, + { + "epoch": 0.88, + "learning_rate": 6.181069774725398e-06, + "loss": 0.0941, + "step": 392920 + }, + { + "epoch": 0.88, + "learning_rate": 6.179951231516073e-06, + "loss": 0.0987, + "step": 392930 + }, + { + "epoch": 0.88, + "learning_rate": 6.17883268830675e-06, + "loss": 0.0937, + "step": 392940 + }, + { + "epoch": 0.88, + "learning_rate": 6.177714145097426e-06, + "loss": 0.0915, + "step": 392950 + }, + { + "epoch": 0.88, + "learning_rate": 6.176595601888101e-06, + "loss": 0.0944, + "step": 392960 + }, + { + "epoch": 0.88, + "learning_rate": 6.175477058678777e-06, + "loss": 0.0938, + "step": 392970 + }, + { + "epoch": 0.88, + "learning_rate": 6.174358515469453e-06, + "loss": 0.0953, + "step": 392980 + }, + { + "epoch": 0.88, + "learning_rate": 6.173239972260129e-06, + "loss": 0.0926, + "step": 392990 + }, + { + "epoch": 0.88, + "learning_rate": 6.1721214290508045e-06, + "loss": 0.0941, + "step": 393000 + }, + { + "epoch": 0.88, + "learning_rate": 6.17100288584148e-06, + "loss": 0.0976, + "step": 393010 + }, + { + "epoch": 0.88, + "learning_rate": 6.169884342632156e-06, + "loss": 0.0977, + "step": 393020 + }, + { + "epoch": 0.88, + "learning_rate": 6.168765799422832e-06, + "loss": 0.0907, + "step": 393030 + }, + { + "epoch": 0.88, + "learning_rate": 6.167647256213508e-06, + "loss": 0.0941, + "step": 393040 + }, + { + "epoch": 0.88, + "learning_rate": 6.166528713004183e-06, + "loss": 0.0904, + "step": 393050 + }, + { + "epoch": 0.88, + "learning_rate": 6.165410169794859e-06, + "loss": 0.0919, + "step": 393060 + }, + { + "epoch": 0.88, + "learning_rate": 6.1642916265855356e-06, + "loss": 0.0952, + "step": 393070 + }, + { + "epoch": 0.88, + "learning_rate": 6.163173083376211e-06, + "loss": 0.0901, + "step": 393080 + }, + { + "epoch": 0.88, + "learning_rate": 6.162054540166886e-06, + "loss": 0.0957, + "step": 393090 + }, + { + "epoch": 0.88, + "learning_rate": 6.160935996957563e-06, + "loss": 0.0934, + "step": 393100 + }, + { + "epoch": 0.88, + "learning_rate": 6.159817453748239e-06, + "loss": 0.0935, + "step": 393110 + }, + { + "epoch": 0.88, + "learning_rate": 6.158698910538915e-06, + "loss": 0.0915, + "step": 393120 + }, + { + "epoch": 0.88, + "learning_rate": 6.15758036732959e-06, + "loss": 0.0973, + "step": 393130 + }, + { + "epoch": 0.88, + "learning_rate": 6.156461824120266e-06, + "loss": 0.098, + "step": 393140 + }, + { + "epoch": 0.88, + "learning_rate": 6.155343280910942e-06, + "loss": 0.0916, + "step": 393150 + }, + { + "epoch": 0.88, + "learning_rate": 6.154224737701618e-06, + "loss": 0.0959, + "step": 393160 + }, + { + "epoch": 0.88, + "learning_rate": 6.153106194492294e-06, + "loss": 0.0942, + "step": 393170 + }, + { + "epoch": 0.88, + "learning_rate": 6.151987651282969e-06, + "loss": 0.0947, + "step": 393180 + }, + { + "epoch": 0.88, + "learning_rate": 6.150869108073645e-06, + "loss": 0.0934, + "step": 393190 + }, + { + "epoch": 0.88, + "learning_rate": 6.1497505648643215e-06, + "loss": 0.0954, + "step": 393200 + }, + { + "epoch": 0.88, + "learning_rate": 6.148632021654997e-06, + "loss": 0.0938, + "step": 393210 + }, + { + "epoch": 0.88, + "learning_rate": 6.147513478445672e-06, + "loss": 0.0953, + "step": 393220 + }, + { + "epoch": 0.88, + "learning_rate": 6.1463949352363485e-06, + "loss": 0.0928, + "step": 393230 + }, + { + "epoch": 0.88, + "learning_rate": 6.145276392027025e-06, + "loss": 0.0912, + "step": 393240 + }, + { + "epoch": 0.88, + "learning_rate": 6.1441578488177e-06, + "loss": 0.0951, + "step": 393250 + }, + { + "epoch": 0.88, + "learning_rate": 6.1430393056083755e-06, + "loss": 0.0935, + "step": 393260 + }, + { + "epoch": 0.88, + "learning_rate": 6.141920762399052e-06, + "loss": 0.0929, + "step": 393270 + }, + { + "epoch": 0.88, + "learning_rate": 6.140802219189728e-06, + "loss": 0.0949, + "step": 393280 + }, + { + "epoch": 0.88, + "learning_rate": 6.139683675980403e-06, + "loss": 0.0896, + "step": 393290 + }, + { + "epoch": 0.88, + "learning_rate": 6.138565132771079e-06, + "loss": 0.0899, + "step": 393300 + }, + { + "epoch": 0.88, + "learning_rate": 6.137446589561755e-06, + "loss": 0.0945, + "step": 393310 + }, + { + "epoch": 0.88, + "learning_rate": 6.136328046352431e-06, + "loss": 0.0961, + "step": 393320 + }, + { + "epoch": 0.88, + "learning_rate": 6.135209503143107e-06, + "loss": 0.0902, + "step": 393330 + }, + { + "epoch": 0.88, + "learning_rate": 6.134090959933782e-06, + "loss": 0.099, + "step": 393340 + }, + { + "epoch": 0.88, + "learning_rate": 6.132972416724458e-06, + "loss": 0.0976, + "step": 393350 + }, + { + "epoch": 0.88, + "learning_rate": 6.1318538735151345e-06, + "loss": 0.0917, + "step": 393360 + }, + { + "epoch": 0.88, + "learning_rate": 6.13073533030581e-06, + "loss": 0.0984, + "step": 393370 + }, + { + "epoch": 0.88, + "learning_rate": 6.129616787096486e-06, + "loss": 0.092, + "step": 393380 + }, + { + "epoch": 0.88, + "learning_rate": 6.1284982438871615e-06, + "loss": 0.099, + "step": 393390 + }, + { + "epoch": 0.88, + "learning_rate": 6.127379700677838e-06, + "loss": 0.0967, + "step": 393400 + }, + { + "epoch": 0.88, + "learning_rate": 6.126261157468513e-06, + "loss": 0.0947, + "step": 393410 + }, + { + "epoch": 0.88, + "learning_rate": 6.125142614259189e-06, + "loss": 0.0958, + "step": 393420 + }, + { + "epoch": 0.88, + "learning_rate": 6.124024071049865e-06, + "loss": 0.0922, + "step": 393430 + }, + { + "epoch": 0.88, + "learning_rate": 6.122905527840541e-06, + "loss": 0.0954, + "step": 393440 + }, + { + "epoch": 0.88, + "learning_rate": 6.121786984631216e-06, + "loss": 0.092, + "step": 393450 + }, + { + "epoch": 0.88, + "learning_rate": 6.120668441421893e-06, + "loss": 0.0931, + "step": 393460 + }, + { + "epoch": 0.88, + "learning_rate": 6.119549898212568e-06, + "loss": 0.093, + "step": 393470 + }, + { + "epoch": 0.88, + "learning_rate": 6.118431355003244e-06, + "loss": 0.089, + "step": 393480 + }, + { + "epoch": 0.88, + "learning_rate": 6.11731281179392e-06, + "loss": 0.095, + "step": 393490 + }, + { + "epoch": 0.88, + "learning_rate": 6.116194268584596e-06, + "loss": 0.0927, + "step": 393500 + }, + { + "epoch": 0.88, + "learning_rate": 6.115075725375271e-06, + "loss": 0.0939, + "step": 393510 + }, + { + "epoch": 0.88, + "learning_rate": 6.1139571821659475e-06, + "loss": 0.0934, + "step": 393520 + }, + { + "epoch": 0.88, + "learning_rate": 6.112838638956623e-06, + "loss": 0.0917, + "step": 393530 + }, + { + "epoch": 0.88, + "learning_rate": 6.111720095747299e-06, + "loss": 0.0938, + "step": 393540 + }, + { + "epoch": 0.88, + "learning_rate": 6.110601552537975e-06, + "loss": 0.0922, + "step": 393550 + }, + { + "epoch": 0.88, + "learning_rate": 6.109483009328651e-06, + "loss": 0.0937, + "step": 393560 + }, + { + "epoch": 0.88, + "learning_rate": 6.108476320440259e-06, + "loss": 0.0911, + "step": 393570 + }, + { + "epoch": 0.88, + "learning_rate": 6.107357777230935e-06, + "loss": 0.0981, + "step": 393580 + }, + { + "epoch": 0.88, + "learning_rate": 6.106239234021611e-06, + "loss": 0.0906, + "step": 393590 + }, + { + "epoch": 0.88, + "learning_rate": 6.1051206908122865e-06, + "loss": 0.091, + "step": 393600 + }, + { + "epoch": 0.88, + "learning_rate": 6.104002147602962e-06, + "loss": 0.0943, + "step": 393610 + }, + { + "epoch": 0.88, + "learning_rate": 6.102883604393638e-06, + "loss": 0.0932, + "step": 393620 + }, + { + "epoch": 0.88, + "learning_rate": 6.101765061184314e-06, + "loss": 0.0888, + "step": 393630 + }, + { + "epoch": 0.88, + "learning_rate": 6.10064651797499e-06, + "loss": 0.092, + "step": 393640 + }, + { + "epoch": 0.88, + "learning_rate": 6.099527974765665e-06, + "loss": 0.0939, + "step": 393650 + }, + { + "epoch": 0.88, + "learning_rate": 6.098409431556341e-06, + "loss": 0.0952, + "step": 393660 + }, + { + "epoch": 0.88, + "learning_rate": 6.0972908883470176e-06, + "loss": 0.0988, + "step": 393670 + }, + { + "epoch": 0.88, + "learning_rate": 6.096172345137693e-06, + "loss": 0.0945, + "step": 393680 + }, + { + "epoch": 0.88, + "learning_rate": 6.095053801928368e-06, + "loss": 0.0958, + "step": 393690 + }, + { + "epoch": 0.88, + "learning_rate": 6.093935258719045e-06, + "loss": 0.0923, + "step": 393700 + }, + { + "epoch": 0.88, + "learning_rate": 6.092816715509721e-06, + "loss": 0.0894, + "step": 393710 + }, + { + "epoch": 0.88, + "learning_rate": 6.091698172300396e-06, + "loss": 0.0934, + "step": 393720 + }, + { + "epoch": 0.88, + "learning_rate": 6.0905796290910724e-06, + "loss": 0.0907, + "step": 393730 + }, + { + "epoch": 0.88, + "learning_rate": 6.089461085881748e-06, + "loss": 0.095, + "step": 393740 + }, + { + "epoch": 0.88, + "learning_rate": 6.088342542672424e-06, + "loss": 0.0886, + "step": 393750 + }, + { + "epoch": 0.88, + "learning_rate": 6.0872239994630994e-06, + "loss": 0.091, + "step": 393760 + }, + { + "epoch": 0.88, + "learning_rate": 6.086105456253776e-06, + "loss": 0.0901, + "step": 393770 + }, + { + "epoch": 0.88, + "learning_rate": 6.084986913044451e-06, + "loss": 0.0871, + "step": 393780 + }, + { + "epoch": 0.88, + "learning_rate": 6.083868369835127e-06, + "loss": 0.0965, + "step": 393790 + }, + { + "epoch": 0.88, + "learning_rate": 6.082749826625803e-06, + "loss": 0.0956, + "step": 393800 + }, + { + "epoch": 0.88, + "learning_rate": 6.081631283416479e-06, + "loss": 0.0936, + "step": 393810 + }, + { + "epoch": 0.88, + "learning_rate": 6.080512740207154e-06, + "loss": 0.0944, + "step": 393820 + }, + { + "epoch": 0.88, + "learning_rate": 6.0793941969978305e-06, + "loss": 0.0964, + "step": 393830 + }, + { + "epoch": 0.88, + "learning_rate": 6.078275653788506e-06, + "loss": 0.0956, + "step": 393840 + }, + { + "epoch": 0.88, + "learning_rate": 6.077157110579182e-06, + "loss": 0.0923, + "step": 393850 + }, + { + "epoch": 0.88, + "learning_rate": 6.0760385673698575e-06, + "loss": 0.0964, + "step": 393860 + }, + { + "epoch": 0.88, + "learning_rate": 6.074920024160534e-06, + "loss": 0.0978, + "step": 393870 + }, + { + "epoch": 0.88, + "learning_rate": 6.073801480951209e-06, + "loss": 0.0962, + "step": 393880 + }, + { + "epoch": 0.88, + "learning_rate": 6.072682937741885e-06, + "loss": 0.0939, + "step": 393890 + }, + { + "epoch": 0.88, + "learning_rate": 6.071564394532562e-06, + "loss": 0.0914, + "step": 393900 + }, + { + "epoch": 0.88, + "learning_rate": 6.070445851323237e-06, + "loss": 0.0952, + "step": 393910 + }, + { + "epoch": 0.88, + "learning_rate": 6.069327308113912e-06, + "loss": 0.0921, + "step": 393920 + }, + { + "epoch": 0.88, + "learning_rate": 6.068208764904589e-06, + "loss": 0.0915, + "step": 393930 + }, + { + "epoch": 0.88, + "learning_rate": 6.067090221695265e-06, + "loss": 0.0952, + "step": 393940 + }, + { + "epoch": 0.88, + "learning_rate": 6.06597167848594e-06, + "loss": 0.0915, + "step": 393950 + }, + { + "epoch": 0.88, + "learning_rate": 6.064853135276616e-06, + "loss": 0.09, + "step": 393960 + }, + { + "epoch": 0.88, + "learning_rate": 6.063734592067292e-06, + "loss": 0.0958, + "step": 393970 + }, + { + "epoch": 0.88, + "learning_rate": 6.062616048857968e-06, + "loss": 0.0935, + "step": 393980 + }, + { + "epoch": 0.88, + "learning_rate": 6.0614975056486435e-06, + "loss": 0.092, + "step": 393990 + }, + { + "epoch": 0.88, + "learning_rate": 6.060378962439319e-06, + "loss": 0.091, + "step": 394000 + }, + { + "epoch": 0.88, + "learning_rate": 6.059260419229995e-06, + "loss": 0.0878, + "step": 394010 + }, + { + "epoch": 0.88, + "learning_rate": 6.058141876020671e-06, + "loss": 0.0946, + "step": 394020 + }, + { + "epoch": 0.88, + "learning_rate": 6.057023332811347e-06, + "loss": 0.0909, + "step": 394030 + }, + { + "epoch": 0.88, + "learning_rate": 6.055904789602022e-06, + "loss": 0.0989, + "step": 394040 + }, + { + "epoch": 0.88, + "learning_rate": 6.054786246392698e-06, + "loss": 0.0928, + "step": 394050 + }, + { + "epoch": 0.88, + "learning_rate": 6.053667703183375e-06, + "loss": 0.0947, + "step": 394060 + }, + { + "epoch": 0.88, + "learning_rate": 6.05254915997405e-06, + "loss": 0.0956, + "step": 394070 + }, + { + "epoch": 0.88, + "learning_rate": 6.051430616764725e-06, + "loss": 0.0927, + "step": 394080 + }, + { + "epoch": 0.88, + "learning_rate": 6.050312073555402e-06, + "loss": 0.0916, + "step": 394090 + }, + { + "epoch": 0.88, + "learning_rate": 6.049193530346078e-06, + "loss": 0.094, + "step": 394100 + }, + { + "epoch": 0.88, + "learning_rate": 6.048074987136754e-06, + "loss": 0.0941, + "step": 394110 + }, + { + "epoch": 0.88, + "learning_rate": 6.046956443927429e-06, + "loss": 0.0928, + "step": 394120 + }, + { + "epoch": 0.88, + "learning_rate": 6.045837900718105e-06, + "loss": 0.0953, + "step": 394130 + }, + { + "epoch": 0.88, + "learning_rate": 6.044719357508781e-06, + "loss": 0.0927, + "step": 394140 + }, + { + "epoch": 0.88, + "learning_rate": 6.043600814299457e-06, + "loss": 0.0915, + "step": 394150 + }, + { + "epoch": 0.88, + "learning_rate": 6.042482271090133e-06, + "loss": 0.0941, + "step": 394160 + }, + { + "epoch": 0.88, + "learning_rate": 6.041363727880808e-06, + "loss": 0.0924, + "step": 394170 + }, + { + "epoch": 0.88, + "learning_rate": 6.040245184671484e-06, + "loss": 0.0895, + "step": 394180 + }, + { + "epoch": 0.88, + "learning_rate": 6.0391266414621605e-06, + "loss": 0.0938, + "step": 394190 + }, + { + "epoch": 0.88, + "learning_rate": 6.038008098252836e-06, + "loss": 0.0942, + "step": 394200 + }, + { + "epoch": 0.88, + "learning_rate": 6.036889555043511e-06, + "loss": 0.0919, + "step": 394210 + }, + { + "epoch": 0.88, + "learning_rate": 6.0357710118341876e-06, + "loss": 0.0908, + "step": 394220 + }, + { + "epoch": 0.88, + "learning_rate": 6.034652468624864e-06, + "loss": 0.0939, + "step": 394230 + }, + { + "epoch": 0.88, + "learning_rate": 6.033533925415539e-06, + "loss": 0.0917, + "step": 394240 + }, + { + "epoch": 0.88, + "learning_rate": 6.0324153822062146e-06, + "loss": 0.0956, + "step": 394250 + }, + { + "epoch": 0.88, + "learning_rate": 6.031296838996891e-06, + "loss": 0.0883, + "step": 394260 + }, + { + "epoch": 0.88, + "learning_rate": 6.030178295787567e-06, + "loss": 0.0979, + "step": 394270 + }, + { + "epoch": 0.88, + "learning_rate": 6.029059752578242e-06, + "loss": 0.0944, + "step": 394280 + }, + { + "epoch": 0.88, + "learning_rate": 6.027941209368918e-06, + "loss": 0.0922, + "step": 394290 + }, + { + "epoch": 0.88, + "learning_rate": 6.026822666159594e-06, + "loss": 0.0933, + "step": 394300 + }, + { + "epoch": 0.88, + "learning_rate": 6.02570412295027e-06, + "loss": 0.0964, + "step": 394310 + }, + { + "epoch": 0.88, + "learning_rate": 6.024585579740946e-06, + "loss": 0.0905, + "step": 394320 + }, + { + "epoch": 0.88, + "learning_rate": 6.023467036531622e-06, + "loss": 0.0921, + "step": 394330 + }, + { + "epoch": 0.88, + "learning_rate": 6.022348493322297e-06, + "loss": 0.0956, + "step": 394340 + }, + { + "epoch": 0.88, + "learning_rate": 6.0212299501129735e-06, + "loss": 0.0921, + "step": 394350 + }, + { + "epoch": 0.88, + "learning_rate": 6.020111406903649e-06, + "loss": 0.0944, + "step": 394360 + }, + { + "epoch": 0.88, + "learning_rate": 6.018992863694325e-06, + "loss": 0.0945, + "step": 394370 + }, + { + "epoch": 0.88, + "learning_rate": 6.0178743204850005e-06, + "loss": 0.0889, + "step": 394380 + }, + { + "epoch": 0.88, + "learning_rate": 6.016755777275677e-06, + "loss": 0.0933, + "step": 394390 + }, + { + "epoch": 0.88, + "learning_rate": 6.015637234066352e-06, + "loss": 0.0952, + "step": 394400 + }, + { + "epoch": 0.88, + "learning_rate": 6.014518690857028e-06, + "loss": 0.0929, + "step": 394410 + }, + { + "epoch": 0.88, + "learning_rate": 6.013400147647704e-06, + "loss": 0.1018, + "step": 394420 + }, + { + "epoch": 0.88, + "learning_rate": 6.01228160443838e-06, + "loss": 0.0977, + "step": 394430 + }, + { + "epoch": 0.88, + "learning_rate": 6.011163061229055e-06, + "loss": 0.0925, + "step": 394440 + }, + { + "epoch": 0.88, + "learning_rate": 6.010044518019732e-06, + "loss": 0.0974, + "step": 394450 + }, + { + "epoch": 0.88, + "learning_rate": 6.008925974810407e-06, + "loss": 0.0963, + "step": 394460 + }, + { + "epoch": 0.88, + "learning_rate": 6.007807431601083e-06, + "loss": 0.0953, + "step": 394470 + }, + { + "epoch": 0.88, + "learning_rate": 6.006688888391759e-06, + "loss": 0.0941, + "step": 394480 + }, + { + "epoch": 0.88, + "learning_rate": 6.005570345182435e-06, + "loss": 0.0967, + "step": 394490 + }, + { + "epoch": 0.88, + "learning_rate": 6.004451801973111e-06, + "loss": 0.0953, + "step": 394500 + }, + { + "epoch": 0.88, + "learning_rate": 6.0033332587637865e-06, + "loss": 0.098, + "step": 394510 + }, + { + "epoch": 0.88, + "learning_rate": 6.002214715554462e-06, + "loss": 0.097, + "step": 394520 + }, + { + "epoch": 0.88, + "learning_rate": 6.001096172345138e-06, + "loss": 0.0969, + "step": 394530 + }, + { + "epoch": 0.88, + "learning_rate": 5.999977629135814e-06, + "loss": 0.0998, + "step": 394540 + }, + { + "epoch": 0.88, + "learning_rate": 5.99885908592649e-06, + "loss": 0.1001, + "step": 394550 + }, + { + "epoch": 0.88, + "learning_rate": 5.997740542717165e-06, + "loss": 0.091, + "step": 394560 + }, + { + "epoch": 0.88, + "learning_rate": 5.996621999507841e-06, + "loss": 0.0955, + "step": 394570 + }, + { + "epoch": 0.88, + "learning_rate": 5.9955034562985176e-06, + "loss": 0.0934, + "step": 394580 + }, + { + "epoch": 0.88, + "learning_rate": 5.994384913089193e-06, + "loss": 0.0974, + "step": 394590 + }, + { + "epoch": 0.88, + "learning_rate": 5.993266369879868e-06, + "loss": 0.0947, + "step": 394600 + }, + { + "epoch": 0.88, + "learning_rate": 5.9921478266705446e-06, + "loss": 0.097, + "step": 394610 + }, + { + "epoch": 0.88, + "learning_rate": 5.991029283461221e-06, + "loss": 0.0965, + "step": 394620 + }, + { + "epoch": 0.88, + "learning_rate": 5.989910740251896e-06, + "loss": 0.0924, + "step": 394630 + }, + { + "epoch": 0.88, + "learning_rate": 5.9887921970425716e-06, + "loss": 0.0923, + "step": 394640 + }, + { + "epoch": 0.88, + "learning_rate": 5.987673653833248e-06, + "loss": 0.0947, + "step": 394650 + }, + { + "epoch": 0.88, + "learning_rate": 5.986555110623924e-06, + "loss": 0.0952, + "step": 394660 + }, + { + "epoch": 0.88, + "learning_rate": 5.9854365674145994e-06, + "loss": 0.0968, + "step": 394670 + }, + { + "epoch": 0.88, + "learning_rate": 5.984318024205275e-06, + "loss": 0.0933, + "step": 394680 + }, + { + "epoch": 0.88, + "learning_rate": 5.983199480995951e-06, + "loss": 0.093, + "step": 394690 + }, + { + "epoch": 0.88, + "learning_rate": 5.982080937786627e-06, + "loss": 0.0965, + "step": 394700 + }, + { + "epoch": 0.88, + "learning_rate": 5.9809623945773035e-06, + "loss": 0.0979, + "step": 394710 + }, + { + "epoch": 0.88, + "learning_rate": 5.979843851367978e-06, + "loss": 0.0914, + "step": 394720 + }, + { + "epoch": 0.88, + "learning_rate": 5.978725308158654e-06, + "loss": 0.0915, + "step": 394730 + }, + { + "epoch": 0.88, + "learning_rate": 5.9776067649493305e-06, + "loss": 0.0935, + "step": 394740 + }, + { + "epoch": 0.88, + "learning_rate": 5.976488221740007e-06, + "loss": 0.0962, + "step": 394750 + }, + { + "epoch": 0.88, + "learning_rate": 5.975369678530682e-06, + "loss": 0.092, + "step": 394760 + }, + { + "epoch": 0.88, + "learning_rate": 5.9742511353213575e-06, + "loss": 0.0949, + "step": 394770 + }, + { + "epoch": 0.88, + "learning_rate": 5.973132592112034e-06, + "loss": 0.0975, + "step": 394780 + }, + { + "epoch": 0.88, + "learning_rate": 5.97201404890271e-06, + "loss": 0.0952, + "step": 394790 + }, + { + "epoch": 0.88, + "learning_rate": 5.970895505693385e-06, + "loss": 0.0933, + "step": 394800 + }, + { + "epoch": 0.88, + "learning_rate": 5.969776962484061e-06, + "loss": 0.093, + "step": 394810 + }, + { + "epoch": 0.88, + "learning_rate": 5.968658419274737e-06, + "loss": 0.0993, + "step": 394820 + }, + { + "epoch": 0.88, + "learning_rate": 5.967539876065413e-06, + "loss": 0.0958, + "step": 394830 + }, + { + "epoch": 0.88, + "learning_rate": 5.966421332856089e-06, + "loss": 0.0918, + "step": 394840 + }, + { + "epoch": 0.88, + "learning_rate": 5.965302789646764e-06, + "loss": 0.0924, + "step": 394850 + }, + { + "epoch": 0.88, + "learning_rate": 5.96418424643744e-06, + "loss": 0.0996, + "step": 394860 + }, + { + "epoch": 0.88, + "learning_rate": 5.9630657032281165e-06, + "loss": 0.0919, + "step": 394870 + }, + { + "epoch": 0.88, + "learning_rate": 5.961947160018792e-06, + "loss": 0.0921, + "step": 394880 + }, + { + "epoch": 0.88, + "learning_rate": 5.960828616809467e-06, + "loss": 0.0953, + "step": 394890 + }, + { + "epoch": 0.88, + "learning_rate": 5.9597100736001435e-06, + "loss": 0.0915, + "step": 394900 + }, + { + "epoch": 0.88, + "learning_rate": 5.958591530390819e-06, + "loss": 0.0944, + "step": 394910 + }, + { + "epoch": 0.88, + "learning_rate": 5.957472987181495e-06, + "loss": 0.0941, + "step": 394920 + }, + { + "epoch": 0.88, + "learning_rate": 5.956354443972171e-06, + "loss": 0.0946, + "step": 394930 + }, + { + "epoch": 0.88, + "learning_rate": 5.955235900762847e-06, + "loss": 0.0961, + "step": 394940 + }, + { + "epoch": 0.88, + "learning_rate": 5.954117357553522e-06, + "loss": 0.0912, + "step": 394950 + }, + { + "epoch": 0.88, + "learning_rate": 5.952998814344198e-06, + "loss": 0.0973, + "step": 394960 + }, + { + "epoch": 0.88, + "learning_rate": 5.951880271134875e-06, + "loss": 0.0963, + "step": 394970 + }, + { + "epoch": 0.88, + "learning_rate": 5.95076172792555e-06, + "loss": 0.0972, + "step": 394980 + }, + { + "epoch": 0.88, + "learning_rate": 5.949643184716225e-06, + "loss": 0.0952, + "step": 394990 + }, + { + "epoch": 0.88, + "learning_rate": 5.948524641506902e-06, + "loss": 0.0951, + "step": 395000 + }, + { + "epoch": 0.88, + "learning_rate": 5.947406098297578e-06, + "loss": 0.093, + "step": 395010 + }, + { + "epoch": 0.88, + "learning_rate": 5.946287555088253e-06, + "loss": 0.0906, + "step": 395020 + }, + { + "epoch": 0.88, + "learning_rate": 5.945169011878929e-06, + "loss": 0.0965, + "step": 395030 + }, + { + "epoch": 0.88, + "learning_rate": 5.944050468669605e-06, + "loss": 0.0993, + "step": 395040 + }, + { + "epoch": 0.88, + "learning_rate": 5.942931925460281e-06, + "loss": 0.0983, + "step": 395050 + }, + { + "epoch": 0.88, + "learning_rate": 5.9418133822509564e-06, + "loss": 0.0944, + "step": 395060 + }, + { + "epoch": 0.88, + "learning_rate": 5.940694839041632e-06, + "loss": 0.0995, + "step": 395070 + }, + { + "epoch": 0.88, + "learning_rate": 5.939576295832308e-06, + "loss": 0.0954, + "step": 395080 + }, + { + "epoch": 0.88, + "learning_rate": 5.938457752622984e-06, + "loss": 0.0978, + "step": 395090 + }, + { + "epoch": 0.88, + "learning_rate": 5.9373392094136605e-06, + "loss": 0.0993, + "step": 395100 + }, + { + "epoch": 0.88, + "learning_rate": 5.936220666204335e-06, + "loss": 0.0955, + "step": 395110 + }, + { + "epoch": 0.88, + "learning_rate": 5.935102122995011e-06, + "loss": 0.0964, + "step": 395120 + }, + { + "epoch": 0.88, + "learning_rate": 5.9339835797856875e-06, + "loss": 0.097, + "step": 395130 + }, + { + "epoch": 0.88, + "learning_rate": 5.932865036576364e-06, + "loss": 0.096, + "step": 395140 + }, + { + "epoch": 0.88, + "learning_rate": 5.931746493367038e-06, + "loss": 0.0934, + "step": 395150 + }, + { + "epoch": 0.88, + "learning_rate": 5.9306279501577145e-06, + "loss": 0.0955, + "step": 395160 + }, + { + "epoch": 0.88, + "learning_rate": 5.929509406948391e-06, + "loss": 0.0938, + "step": 395170 + }, + { + "epoch": 0.88, + "learning_rate": 5.928390863739067e-06, + "loss": 0.0968, + "step": 395180 + }, + { + "epoch": 0.88, + "learning_rate": 5.927272320529742e-06, + "loss": 0.0955, + "step": 395190 + }, + { + "epoch": 0.88, + "learning_rate": 5.926153777320418e-06, + "loss": 0.099, + "step": 395200 + }, + { + "epoch": 0.88, + "learning_rate": 5.925035234111094e-06, + "loss": 0.0931, + "step": 395210 + }, + { + "epoch": 0.88, + "learning_rate": 5.92391669090177e-06, + "loss": 0.0963, + "step": 395220 + }, + { + "epoch": 0.88, + "learning_rate": 5.922798147692446e-06, + "loss": 0.0962, + "step": 395230 + }, + { + "epoch": 0.88, + "learning_rate": 5.921679604483121e-06, + "loss": 0.0925, + "step": 395240 + }, + { + "epoch": 0.88, + "learning_rate": 5.920561061273797e-06, + "loss": 0.0955, + "step": 395250 + }, + { + "epoch": 0.88, + "learning_rate": 5.9194425180644735e-06, + "loss": 0.095, + "step": 395260 + }, + { + "epoch": 0.88, + "learning_rate": 5.918323974855149e-06, + "loss": 0.0962, + "step": 395270 + }, + { + "epoch": 0.88, + "learning_rate": 5.917205431645824e-06, + "loss": 0.0966, + "step": 395280 + }, + { + "epoch": 0.88, + "learning_rate": 5.9160868884365005e-06, + "loss": 0.0984, + "step": 395290 + }, + { + "epoch": 0.88, + "learning_rate": 5.914968345227177e-06, + "loss": 0.0982, + "step": 395300 + }, + { + "epoch": 0.88, + "learning_rate": 5.913849802017852e-06, + "loss": 0.0946, + "step": 395310 + }, + { + "epoch": 0.88, + "learning_rate": 5.9127312588085275e-06, + "loss": 0.095, + "step": 395320 + }, + { + "epoch": 0.88, + "learning_rate": 5.911612715599204e-06, + "loss": 0.0961, + "step": 395330 + }, + { + "epoch": 0.88, + "learning_rate": 5.91049417238988e-06, + "loss": 0.0976, + "step": 395340 + }, + { + "epoch": 0.88, + "learning_rate": 5.909375629180555e-06, + "loss": 0.0939, + "step": 395350 + }, + { + "epoch": 0.88, + "learning_rate": 5.908257085971232e-06, + "loss": 0.0974, + "step": 395360 + }, + { + "epoch": 0.88, + "learning_rate": 5.907138542761907e-06, + "loss": 0.0945, + "step": 395370 + }, + { + "epoch": 0.88, + "learning_rate": 5.906019999552583e-06, + "loss": 0.0957, + "step": 395380 + }, + { + "epoch": 0.88, + "learning_rate": 5.904901456343259e-06, + "loss": 0.0958, + "step": 395390 + }, + { + "epoch": 0.88, + "learning_rate": 5.903782913133935e-06, + "loss": 0.0989, + "step": 395400 + }, + { + "epoch": 0.88, + "learning_rate": 5.90266436992461e-06, + "loss": 0.0982, + "step": 395410 + }, + { + "epoch": 0.88, + "learning_rate": 5.9015458267152865e-06, + "loss": 0.096, + "step": 395420 + }, + { + "epoch": 0.88, + "learning_rate": 5.900427283505962e-06, + "loss": 0.0942, + "step": 395430 + }, + { + "epoch": 0.88, + "learning_rate": 5.899308740296638e-06, + "loss": 0.0937, + "step": 395440 + }, + { + "epoch": 0.88, + "learning_rate": 5.8981901970873135e-06, + "loss": 0.0936, + "step": 395450 + }, + { + "epoch": 0.88, + "learning_rate": 5.89707165387799e-06, + "loss": 0.0961, + "step": 395460 + }, + { + "epoch": 0.88, + "learning_rate": 5.895953110668665e-06, + "loss": 0.0947, + "step": 395470 + }, + { + "epoch": 0.88, + "learning_rate": 5.894834567459341e-06, + "loss": 0.0975, + "step": 395480 + }, + { + "epoch": 0.88, + "learning_rate": 5.893716024250017e-06, + "loss": 0.0935, + "step": 395490 + }, + { + "epoch": 0.88, + "learning_rate": 5.892597481040693e-06, + "loss": 0.0949, + "step": 395500 + }, + { + "epoch": 0.88, + "learning_rate": 5.891478937831368e-06, + "loss": 0.0939, + "step": 395510 + }, + { + "epoch": 0.88, + "learning_rate": 5.8903603946220446e-06, + "loss": 0.0963, + "step": 395520 + }, + { + "epoch": 0.88, + "learning_rate": 5.889241851412721e-06, + "loss": 0.0936, + "step": 395530 + }, + { + "epoch": 0.88, + "learning_rate": 5.888123308203396e-06, + "loss": 0.0949, + "step": 395540 + }, + { + "epoch": 0.88, + "learning_rate": 5.8870047649940716e-06, + "loss": 0.0939, + "step": 395550 + }, + { + "epoch": 0.88, + "learning_rate": 5.885886221784748e-06, + "loss": 0.0942, + "step": 395560 + }, + { + "epoch": 0.88, + "learning_rate": 5.884767678575424e-06, + "loss": 0.0964, + "step": 395570 + }, + { + "epoch": 0.88, + "learning_rate": 5.883649135366099e-06, + "loss": 0.0983, + "step": 395580 + }, + { + "epoch": 0.88, + "learning_rate": 5.882530592156775e-06, + "loss": 0.0953, + "step": 395590 + }, + { + "epoch": 0.88, + "learning_rate": 5.881412048947451e-06, + "loss": 0.0951, + "step": 395600 + }, + { + "epoch": 0.88, + "learning_rate": 5.880293505738127e-06, + "loss": 0.0988, + "step": 395610 + }, + { + "epoch": 0.88, + "learning_rate": 5.879174962528803e-06, + "loss": 0.0956, + "step": 395620 + }, + { + "epoch": 0.88, + "learning_rate": 5.878056419319478e-06, + "loss": 0.0984, + "step": 395630 + }, + { + "epoch": 0.88, + "learning_rate": 5.877049730431087e-06, + "loss": 0.0997, + "step": 395640 + }, + { + "epoch": 0.88, + "learning_rate": 5.875931187221763e-06, + "loss": 0.0986, + "step": 395650 + }, + { + "epoch": 0.88, + "learning_rate": 5.8748126440124384e-06, + "loss": 0.0978, + "step": 395660 + }, + { + "epoch": 0.88, + "learning_rate": 5.873694100803114e-06, + "loss": 0.0972, + "step": 395670 + }, + { + "epoch": 0.88, + "learning_rate": 5.87257555759379e-06, + "loss": 0.0979, + "step": 395680 + }, + { + "epoch": 0.88, + "learning_rate": 5.871457014384466e-06, + "loss": 0.0944, + "step": 395690 + }, + { + "epoch": 0.88, + "learning_rate": 5.870338471175142e-06, + "loss": 0.0956, + "step": 395700 + }, + { + "epoch": 0.88, + "learning_rate": 5.869219927965817e-06, + "loss": 0.0957, + "step": 395710 + }, + { + "epoch": 0.88, + "learning_rate": 5.868101384756493e-06, + "loss": 0.0936, + "step": 395720 + }, + { + "epoch": 0.88, + "learning_rate": 5.8669828415471695e-06, + "loss": 0.0997, + "step": 395730 + }, + { + "epoch": 0.88, + "learning_rate": 5.865864298337845e-06, + "loss": 0.1015, + "step": 395740 + }, + { + "epoch": 0.88, + "learning_rate": 5.864745755128521e-06, + "loss": 0.0983, + "step": 395750 + }, + { + "epoch": 0.88, + "learning_rate": 5.8636272119191965e-06, + "loss": 0.0938, + "step": 395760 + }, + { + "epoch": 0.88, + "learning_rate": 5.862508668709873e-06, + "loss": 0.1009, + "step": 395770 + }, + { + "epoch": 0.88, + "learning_rate": 5.861390125500548e-06, + "loss": 0.0954, + "step": 395780 + }, + { + "epoch": 0.88, + "learning_rate": 5.860271582291224e-06, + "loss": 0.0974, + "step": 395790 + }, + { + "epoch": 0.88, + "learning_rate": 5.8591530390819e-06, + "loss": 0.0947, + "step": 395800 + }, + { + "epoch": 0.88, + "learning_rate": 5.858034495872576e-06, + "loss": 0.0962, + "step": 395810 + }, + { + "epoch": 0.88, + "learning_rate": 5.856915952663251e-06, + "loss": 0.0921, + "step": 395820 + }, + { + "epoch": 0.88, + "learning_rate": 5.855797409453928e-06, + "loss": 0.0944, + "step": 395830 + }, + { + "epoch": 0.88, + "learning_rate": 5.854678866244603e-06, + "loss": 0.0942, + "step": 395840 + }, + { + "epoch": 0.88, + "learning_rate": 5.853560323035279e-06, + "loss": 0.0978, + "step": 395850 + }, + { + "epoch": 0.88, + "learning_rate": 5.852441779825955e-06, + "loss": 0.0935, + "step": 395860 + }, + { + "epoch": 0.88, + "learning_rate": 5.851323236616631e-06, + "loss": 0.0951, + "step": 395870 + }, + { + "epoch": 0.88, + "learning_rate": 5.850204693407306e-06, + "loss": 0.0952, + "step": 395880 + }, + { + "epoch": 0.88, + "learning_rate": 5.8490861501979825e-06, + "loss": 0.0953, + "step": 395890 + }, + { + "epoch": 0.88, + "learning_rate": 5.847967606988658e-06, + "loss": 0.0931, + "step": 395900 + }, + { + "epoch": 0.88, + "learning_rate": 5.846849063779334e-06, + "loss": 0.0972, + "step": 395910 + }, + { + "epoch": 0.88, + "learning_rate": 5.84573052057001e-06, + "loss": 0.0953, + "step": 395920 + }, + { + "epoch": 0.88, + "learning_rate": 5.844611977360686e-06, + "loss": 0.094, + "step": 395930 + }, + { + "epoch": 0.88, + "learning_rate": 5.843493434151361e-06, + "loss": 0.0943, + "step": 395940 + }, + { + "epoch": 0.88, + "learning_rate": 5.842374890942037e-06, + "loss": 0.0961, + "step": 395950 + }, + { + "epoch": 0.88, + "learning_rate": 5.841256347732714e-06, + "loss": 0.0995, + "step": 395960 + }, + { + "epoch": 0.88, + "learning_rate": 5.840137804523389e-06, + "loss": 0.0968, + "step": 395970 + }, + { + "epoch": 0.88, + "learning_rate": 5.839019261314064e-06, + "loss": 0.0971, + "step": 395980 + }, + { + "epoch": 0.88, + "learning_rate": 5.837900718104741e-06, + "loss": 0.097, + "step": 395990 + }, + { + "epoch": 0.88, + "learning_rate": 5.836782174895417e-06, + "loss": 0.0951, + "step": 396000 + }, + { + "epoch": 0.88, + "learning_rate": 5.835663631686092e-06, + "loss": 0.0946, + "step": 396010 + }, + { + "epoch": 0.88, + "learning_rate": 5.834545088476768e-06, + "loss": 0.1009, + "step": 396020 + }, + { + "epoch": 0.88, + "learning_rate": 5.833426545267444e-06, + "loss": 0.0911, + "step": 396030 + }, + { + "epoch": 0.88, + "learning_rate": 5.83230800205812e-06, + "loss": 0.094, + "step": 396040 + }, + { + "epoch": 0.88, + "learning_rate": 5.8311894588487955e-06, + "loss": 0.097, + "step": 396050 + }, + { + "epoch": 0.88, + "learning_rate": 5.830070915639471e-06, + "loss": 0.0979, + "step": 396060 + }, + { + "epoch": 0.88, + "learning_rate": 5.828952372430147e-06, + "loss": 0.0975, + "step": 396070 + }, + { + "epoch": 0.88, + "learning_rate": 5.827833829220823e-06, + "loss": 0.0932, + "step": 396080 + }, + { + "epoch": 0.88, + "learning_rate": 5.8267152860114995e-06, + "loss": 0.0937, + "step": 396090 + }, + { + "epoch": 0.88, + "learning_rate": 5.825596742802174e-06, + "loss": 0.0957, + "step": 396100 + }, + { + "epoch": 0.88, + "learning_rate": 5.82447819959285e-06, + "loss": 0.0975, + "step": 396110 + }, + { + "epoch": 0.88, + "learning_rate": 5.8233596563835266e-06, + "loss": 0.0967, + "step": 396120 + }, + { + "epoch": 0.88, + "learning_rate": 5.822241113174203e-06, + "loss": 0.093, + "step": 396130 + }, + { + "epoch": 0.88, + "learning_rate": 5.821122569964878e-06, + "loss": 0.0969, + "step": 396140 + }, + { + "epoch": 0.88, + "learning_rate": 5.8200040267555536e-06, + "loss": 0.0926, + "step": 396150 + }, + { + "epoch": 0.88, + "learning_rate": 5.81888548354623e-06, + "loss": 0.0963, + "step": 396160 + }, + { + "epoch": 0.88, + "learning_rate": 5.817766940336906e-06, + "loss": 0.096, + "step": 396170 + }, + { + "epoch": 0.88, + "learning_rate": 5.816648397127581e-06, + "loss": 0.0943, + "step": 396180 + }, + { + "epoch": 0.88, + "learning_rate": 5.815529853918257e-06, + "loss": 0.0946, + "step": 396190 + }, + { + "epoch": 0.88, + "learning_rate": 5.814411310708933e-06, + "loss": 0.0971, + "step": 396200 + }, + { + "epoch": 0.88, + "learning_rate": 5.813292767499609e-06, + "loss": 0.0947, + "step": 396210 + }, + { + "epoch": 0.88, + "learning_rate": 5.812174224290285e-06, + "loss": 0.0974, + "step": 396220 + }, + { + "epoch": 0.88, + "learning_rate": 5.81105568108096e-06, + "loss": 0.0935, + "step": 396230 + }, + { + "epoch": 0.88, + "learning_rate": 5.809937137871636e-06, + "loss": 0.0907, + "step": 396240 + }, + { + "epoch": 0.88, + "learning_rate": 5.8088185946623125e-06, + "loss": 0.0943, + "step": 396250 + }, + { + "epoch": 0.88, + "learning_rate": 5.807700051452988e-06, + "loss": 0.0958, + "step": 396260 + }, + { + "epoch": 0.88, + "learning_rate": 5.806581508243663e-06, + "loss": 0.0947, + "step": 396270 + }, + { + "epoch": 0.88, + "learning_rate": 5.8054629650343395e-06, + "loss": 0.098, + "step": 396280 + }, + { + "epoch": 0.88, + "learning_rate": 5.804344421825016e-06, + "loss": 0.0925, + "step": 396290 + }, + { + "epoch": 0.88, + "learning_rate": 5.803225878615691e-06, + "loss": 0.0919, + "step": 396300 + }, + { + "epoch": 0.88, + "learning_rate": 5.8021073354063665e-06, + "loss": 0.0955, + "step": 396310 + }, + { + "epoch": 0.88, + "learning_rate": 5.800988792197043e-06, + "loss": 0.0926, + "step": 396320 + }, + { + "epoch": 0.88, + "learning_rate": 5.799870248987719e-06, + "loss": 0.0987, + "step": 396330 + }, + { + "epoch": 0.88, + "learning_rate": 5.798751705778394e-06, + "loss": 0.0926, + "step": 396340 + }, + { + "epoch": 0.88, + "learning_rate": 5.797633162569071e-06, + "loss": 0.0964, + "step": 396350 + }, + { + "epoch": 0.88, + "learning_rate": 5.796514619359746e-06, + "loss": 0.0967, + "step": 396360 + }, + { + "epoch": 0.88, + "learning_rate": 5.795396076150422e-06, + "loss": 0.0971, + "step": 396370 + }, + { + "epoch": 0.88, + "learning_rate": 5.794277532941098e-06, + "loss": 0.0902, + "step": 396380 + }, + { + "epoch": 0.88, + "learning_rate": 5.793158989731774e-06, + "loss": 0.0905, + "step": 396390 + }, + { + "epoch": 0.88, + "learning_rate": 5.792040446522449e-06, + "loss": 0.0946, + "step": 396400 + }, + { + "epoch": 0.88, + "learning_rate": 5.7909219033131255e-06, + "loss": 0.0984, + "step": 396410 + }, + { + "epoch": 0.88, + "learning_rate": 5.789803360103801e-06, + "loss": 0.0972, + "step": 396420 + }, + { + "epoch": 0.88, + "learning_rate": 5.788684816894477e-06, + "loss": 0.0932, + "step": 396430 + }, + { + "epoch": 0.88, + "learning_rate": 5.7875662736851525e-06, + "loss": 0.0932, + "step": 396440 + }, + { + "epoch": 0.88, + "learning_rate": 5.786447730475829e-06, + "loss": 0.0967, + "step": 396450 + }, + { + "epoch": 0.88, + "learning_rate": 5.785329187266504e-06, + "loss": 0.0974, + "step": 396460 + }, + { + "epoch": 0.88, + "learning_rate": 5.78421064405718e-06, + "loss": 0.098, + "step": 396470 + }, + { + "epoch": 0.88, + "learning_rate": 5.783092100847856e-06, + "loss": 0.0912, + "step": 396480 + }, + { + "epoch": 0.89, + "learning_rate": 5.781973557638532e-06, + "loss": 0.0944, + "step": 396490 + }, + { + "epoch": 0.89, + "learning_rate": 5.780855014429207e-06, + "loss": 0.0953, + "step": 396500 + }, + { + "epoch": 0.89, + "learning_rate": 5.7797364712198836e-06, + "loss": 0.1014, + "step": 396510 + }, + { + "epoch": 0.89, + "learning_rate": 5.77861792801056e-06, + "loss": 0.0949, + "step": 396520 + }, + { + "epoch": 0.89, + "learning_rate": 5.777499384801235e-06, + "loss": 0.0959, + "step": 396530 + }, + { + "epoch": 0.89, + "learning_rate": 5.776380841591911e-06, + "loss": 0.0971, + "step": 396540 + }, + { + "epoch": 0.89, + "learning_rate": 5.775262298382587e-06, + "loss": 0.0984, + "step": 396550 + }, + { + "epoch": 0.89, + "learning_rate": 5.774143755173263e-06, + "loss": 0.0936, + "step": 396560 + }, + { + "epoch": 0.89, + "learning_rate": 5.7730252119639384e-06, + "loss": 0.0947, + "step": 396570 + }, + { + "epoch": 0.89, + "learning_rate": 5.771906668754614e-06, + "loss": 0.0943, + "step": 396580 + }, + { + "epoch": 0.89, + "learning_rate": 5.77078812554529e-06, + "loss": 0.0917, + "step": 396590 + }, + { + "epoch": 0.89, + "learning_rate": 5.769669582335966e-06, + "loss": 0.0933, + "step": 396600 + }, + { + "epoch": 0.89, + "learning_rate": 5.768551039126642e-06, + "loss": 0.0949, + "step": 396610 + }, + { + "epoch": 0.89, + "learning_rate": 5.767432495917317e-06, + "loss": 0.0947, + "step": 396620 + }, + { + "epoch": 0.89, + "learning_rate": 5.766313952707993e-06, + "loss": 0.0944, + "step": 396630 + }, + { + "epoch": 0.89, + "learning_rate": 5.7651954094986695e-06, + "loss": 0.0972, + "step": 396640 + }, + { + "epoch": 0.89, + "learning_rate": 5.764076866289345e-06, + "loss": 0.0964, + "step": 396650 + }, + { + "epoch": 0.89, + "learning_rate": 5.76295832308002e-06, + "loss": 0.0982, + "step": 396660 + }, + { + "epoch": 0.89, + "learning_rate": 5.7618397798706965e-06, + "loss": 0.0951, + "step": 396670 + }, + { + "epoch": 0.89, + "learning_rate": 5.760721236661373e-06, + "loss": 0.0971, + "step": 396680 + }, + { + "epoch": 0.89, + "learning_rate": 5.759602693452049e-06, + "loss": 0.0959, + "step": 396690 + }, + { + "epoch": 0.89, + "learning_rate": 5.7584841502427235e-06, + "loss": 0.0948, + "step": 396700 + }, + { + "epoch": 0.89, + "learning_rate": 5.7573656070334e-06, + "loss": 0.0953, + "step": 396710 + }, + { + "epoch": 0.89, + "learning_rate": 5.756247063824076e-06, + "loss": 0.0981, + "step": 396720 + }, + { + "epoch": 0.89, + "learning_rate": 5.755128520614752e-06, + "loss": 0.0955, + "step": 396730 + }, + { + "epoch": 0.89, + "learning_rate": 5.754009977405428e-06, + "loss": 0.0906, + "step": 396740 + }, + { + "epoch": 0.89, + "learning_rate": 5.752891434196103e-06, + "loss": 0.1002, + "step": 396750 + }, + { + "epoch": 0.89, + "learning_rate": 5.751772890986779e-06, + "loss": 0.0935, + "step": 396760 + }, + { + "epoch": 0.89, + "learning_rate": 5.7506543477774555e-06, + "loss": 0.1007, + "step": 396770 + }, + { + "epoch": 0.89, + "learning_rate": 5.749535804568131e-06, + "loss": 0.0928, + "step": 396780 + }, + { + "epoch": 0.89, + "learning_rate": 5.748417261358806e-06, + "loss": 0.1, + "step": 396790 + }, + { + "epoch": 0.89, + "learning_rate": 5.7472987181494825e-06, + "loss": 0.0926, + "step": 396800 + }, + { + "epoch": 0.89, + "learning_rate": 5.746180174940159e-06, + "loss": 0.0935, + "step": 396810 + }, + { + "epoch": 0.89, + "learning_rate": 5.745061631730834e-06, + "loss": 0.096, + "step": 396820 + }, + { + "epoch": 0.89, + "learning_rate": 5.7439430885215095e-06, + "loss": 0.1009, + "step": 396830 + }, + { + "epoch": 0.89, + "learning_rate": 5.742824545312186e-06, + "loss": 0.0952, + "step": 396840 + }, + { + "epoch": 0.89, + "learning_rate": 5.741706002102862e-06, + "loss": 0.0976, + "step": 396850 + }, + { + "epoch": 0.89, + "learning_rate": 5.740587458893537e-06, + "loss": 0.0949, + "step": 396860 + }, + { + "epoch": 0.89, + "learning_rate": 5.739468915684213e-06, + "loss": 0.0962, + "step": 396870 + }, + { + "epoch": 0.89, + "learning_rate": 5.738350372474889e-06, + "loss": 0.0901, + "step": 396880 + }, + { + "epoch": 0.89, + "learning_rate": 5.737231829265565e-06, + "loss": 0.0987, + "step": 396890 + }, + { + "epoch": 0.89, + "learning_rate": 5.736113286056241e-06, + "loss": 0.0964, + "step": 396900 + }, + { + "epoch": 0.89, + "learning_rate": 5.734994742846917e-06, + "loss": 0.091, + "step": 396910 + }, + { + "epoch": 0.89, + "learning_rate": 5.733876199637592e-06, + "loss": 0.0928, + "step": 396920 + }, + { + "epoch": 0.89, + "learning_rate": 5.7327576564282684e-06, + "loss": 0.0932, + "step": 396930 + }, + { + "epoch": 0.89, + "learning_rate": 5.731639113218944e-06, + "loss": 0.0946, + "step": 396940 + }, + { + "epoch": 0.89, + "learning_rate": 5.73052057000962e-06, + "loss": 0.0965, + "step": 396950 + }, + { + "epoch": 0.89, + "learning_rate": 5.7294020268002955e-06, + "loss": 0.0934, + "step": 396960 + }, + { + "epoch": 0.89, + "learning_rate": 5.728283483590972e-06, + "loss": 0.0971, + "step": 396970 + }, + { + "epoch": 0.89, + "learning_rate": 5.727164940381647e-06, + "loss": 0.0921, + "step": 396980 + }, + { + "epoch": 0.89, + "learning_rate": 5.726046397172323e-06, + "loss": 0.0913, + "step": 396990 + }, + { + "epoch": 0.89, + "learning_rate": 5.724927853962999e-06, + "loss": 0.0958, + "step": 397000 + }, + { + "epoch": 0.89, + "learning_rate": 5.723809310753675e-06, + "loss": 0.0883, + "step": 397010 + }, + { + "epoch": 0.89, + "learning_rate": 5.72269076754435e-06, + "loss": 0.0961, + "step": 397020 + }, + { + "epoch": 0.89, + "learning_rate": 5.7215722243350265e-06, + "loss": 0.0934, + "step": 397030 + }, + { + "epoch": 0.89, + "learning_rate": 5.720453681125702e-06, + "loss": 0.0934, + "step": 397040 + }, + { + "epoch": 0.89, + "learning_rate": 5.719335137916378e-06, + "loss": 0.0931, + "step": 397050 + }, + { + "epoch": 0.89, + "learning_rate": 5.7182165947070536e-06, + "loss": 0.0999, + "step": 397060 + }, + { + "epoch": 0.89, + "learning_rate": 5.71709805149773e-06, + "loss": 0.0907, + "step": 397070 + }, + { + "epoch": 0.89, + "learning_rate": 5.715979508288405e-06, + "loss": 0.0953, + "step": 397080 + }, + { + "epoch": 0.89, + "learning_rate": 5.714860965079081e-06, + "loss": 0.0991, + "step": 397090 + }, + { + "epoch": 0.89, + "learning_rate": 5.713742421869757e-06, + "loss": 0.0952, + "step": 397100 + }, + { + "epoch": 0.89, + "learning_rate": 5.712623878660433e-06, + "loss": 0.0951, + "step": 397110 + }, + { + "epoch": 0.89, + "learning_rate": 5.711505335451109e-06, + "loss": 0.0954, + "step": 397120 + }, + { + "epoch": 0.89, + "learning_rate": 5.710386792241785e-06, + "loss": 0.0935, + "step": 397130 + }, + { + "epoch": 0.89, + "learning_rate": 5.70926824903246e-06, + "loss": 0.0954, + "step": 397140 + }, + { + "epoch": 0.89, + "learning_rate": 5.708149705823136e-06, + "loss": 0.0945, + "step": 397150 + }, + { + "epoch": 0.89, + "learning_rate": 5.7070311626138125e-06, + "loss": 0.0948, + "step": 397160 + }, + { + "epoch": 0.89, + "learning_rate": 5.705912619404488e-06, + "loss": 0.0946, + "step": 397170 + }, + { + "epoch": 0.89, + "learning_rate": 5.704794076195163e-06, + "loss": 0.0949, + "step": 397180 + }, + { + "epoch": 0.89, + "learning_rate": 5.7036755329858395e-06, + "loss": 0.0977, + "step": 397190 + }, + { + "epoch": 0.89, + "learning_rate": 5.702556989776516e-06, + "loss": 0.0952, + "step": 397200 + }, + { + "epoch": 0.89, + "learning_rate": 5.701438446567191e-06, + "loss": 0.0964, + "step": 397210 + }, + { + "epoch": 0.89, + "learning_rate": 5.7003199033578665e-06, + "loss": 0.0971, + "step": 397220 + }, + { + "epoch": 0.89, + "learning_rate": 5.699201360148543e-06, + "loss": 0.095, + "step": 397230 + }, + { + "epoch": 0.89, + "learning_rate": 5.698082816939219e-06, + "loss": 0.096, + "step": 397240 + }, + { + "epoch": 0.89, + "learning_rate": 5.696964273729894e-06, + "loss": 0.0946, + "step": 397250 + }, + { + "epoch": 0.89, + "learning_rate": 5.69584573052057e-06, + "loss": 0.0911, + "step": 397260 + }, + { + "epoch": 0.89, + "learning_rate": 5.694727187311246e-06, + "loss": 0.0961, + "step": 397270 + }, + { + "epoch": 0.89, + "learning_rate": 5.693608644101922e-06, + "loss": 0.0938, + "step": 397280 + }, + { + "epoch": 0.89, + "learning_rate": 5.6924901008925985e-06, + "loss": 0.0974, + "step": 397290 + }, + { + "epoch": 0.89, + "learning_rate": 5.691371557683273e-06, + "loss": 0.0924, + "step": 397300 + }, + { + "epoch": 0.89, + "learning_rate": 5.690253014473949e-06, + "loss": 0.0948, + "step": 397310 + }, + { + "epoch": 0.89, + "learning_rate": 5.6891344712646255e-06, + "loss": 0.0939, + "step": 397320 + }, + { + "epoch": 0.89, + "learning_rate": 5.688015928055302e-06, + "loss": 0.0996, + "step": 397330 + }, + { + "epoch": 0.89, + "learning_rate": 5.686897384845977e-06, + "loss": 0.0931, + "step": 397340 + }, + { + "epoch": 0.89, + "learning_rate": 5.6857788416366525e-06, + "loss": 0.0898, + "step": 397350 + }, + { + "epoch": 0.89, + "learning_rate": 5.684660298427329e-06, + "loss": 0.0992, + "step": 397360 + }, + { + "epoch": 0.89, + "learning_rate": 5.683541755218005e-06, + "loss": 0.0933, + "step": 397370 + }, + { + "epoch": 0.89, + "learning_rate": 5.68242321200868e-06, + "loss": 0.0952, + "step": 397380 + }, + { + "epoch": 0.89, + "learning_rate": 5.681304668799356e-06, + "loss": 0.095, + "step": 397390 + }, + { + "epoch": 0.89, + "learning_rate": 5.680186125590032e-06, + "loss": 0.0955, + "step": 397400 + }, + { + "epoch": 0.89, + "learning_rate": 5.679067582380708e-06, + "loss": 0.0974, + "step": 397410 + }, + { + "epoch": 0.89, + "learning_rate": 5.6779490391713836e-06, + "loss": 0.0949, + "step": 397420 + }, + { + "epoch": 0.89, + "learning_rate": 5.676830495962059e-06, + "loss": 0.0973, + "step": 397430 + }, + { + "epoch": 0.89, + "learning_rate": 5.675711952752735e-06, + "loss": 0.0968, + "step": 397440 + }, + { + "epoch": 0.89, + "learning_rate": 5.674593409543411e-06, + "loss": 0.0978, + "step": 397450 + }, + { + "epoch": 0.89, + "learning_rate": 5.673474866334087e-06, + "loss": 0.0937, + "step": 397460 + }, + { + "epoch": 0.89, + "learning_rate": 5.672356323124762e-06, + "loss": 0.0968, + "step": 397470 + }, + { + "epoch": 0.89, + "learning_rate": 5.6712377799154384e-06, + "loss": 0.0949, + "step": 397480 + }, + { + "epoch": 0.89, + "learning_rate": 5.670119236706115e-06, + "loss": 0.091, + "step": 397490 + }, + { + "epoch": 0.89, + "learning_rate": 5.66900069349679e-06, + "loss": 0.0971, + "step": 397500 + }, + { + "epoch": 0.89, + "learning_rate": 5.667882150287466e-06, + "loss": 0.0957, + "step": 397510 + }, + { + "epoch": 0.89, + "learning_rate": 5.666763607078142e-06, + "loss": 0.0947, + "step": 397520 + }, + { + "epoch": 0.89, + "learning_rate": 5.665645063868818e-06, + "loss": 0.0917, + "step": 397530 + }, + { + "epoch": 0.89, + "learning_rate": 5.664526520659493e-06, + "loss": 0.0946, + "step": 397540 + }, + { + "epoch": 0.89, + "learning_rate": 5.6634079774501695e-06, + "loss": 0.0928, + "step": 397550 + }, + { + "epoch": 0.89, + "learning_rate": 5.662289434240845e-06, + "loss": 0.0928, + "step": 397560 + }, + { + "epoch": 0.89, + "learning_rate": 5.661170891031521e-06, + "loss": 0.094, + "step": 397570 + }, + { + "epoch": 0.89, + "learning_rate": 5.6600523478221965e-06, + "loss": 0.0976, + "step": 397580 + }, + { + "epoch": 0.89, + "learning_rate": 5.658933804612873e-06, + "loss": 0.0946, + "step": 397590 + }, + { + "epoch": 0.89, + "learning_rate": 5.657815261403548e-06, + "loss": 0.0959, + "step": 397600 + }, + { + "epoch": 0.89, + "learning_rate": 5.656696718194224e-06, + "loss": 0.0904, + "step": 397610 + }, + { + "epoch": 0.89, + "learning_rate": 5.6555781749849e-06, + "loss": 0.0938, + "step": 397620 + }, + { + "epoch": 0.89, + "learning_rate": 5.654459631775576e-06, + "loss": 0.0965, + "step": 397630 + }, + { + "epoch": 0.89, + "learning_rate": 5.653452942887184e-06, + "loss": 0.0965, + "step": 397640 + }, + { + "epoch": 0.89, + "learning_rate": 5.652334399677859e-06, + "loss": 0.0945, + "step": 397650 + }, + { + "epoch": 0.89, + "learning_rate": 5.6512158564685356e-06, + "loss": 0.096, + "step": 397660 + }, + { + "epoch": 0.89, + "learning_rate": 5.650097313259212e-06, + "loss": 0.0928, + "step": 397670 + }, + { + "epoch": 0.89, + "learning_rate": 5.648978770049887e-06, + "loss": 0.1026, + "step": 397680 + }, + { + "epoch": 0.89, + "learning_rate": 5.6478602268405626e-06, + "loss": 0.0907, + "step": 397690 + }, + { + "epoch": 0.89, + "learning_rate": 5.646741683631239e-06, + "loss": 0.0968, + "step": 397700 + }, + { + "epoch": 0.89, + "learning_rate": 5.645623140421915e-06, + "loss": 0.0943, + "step": 397710 + }, + { + "epoch": 0.89, + "learning_rate": 5.64450459721259e-06, + "loss": 0.0909, + "step": 397720 + }, + { + "epoch": 0.89, + "learning_rate": 5.643386054003267e-06, + "loss": 0.0971, + "step": 397730 + }, + { + "epoch": 0.89, + "learning_rate": 5.642267510793942e-06, + "loss": 0.0941, + "step": 397740 + }, + { + "epoch": 0.89, + "learning_rate": 5.641148967584618e-06, + "loss": 0.0908, + "step": 397750 + }, + { + "epoch": 0.89, + "learning_rate": 5.640030424375294e-06, + "loss": 0.0924, + "step": 397760 + }, + { + "epoch": 0.89, + "learning_rate": 5.63891188116597e-06, + "loss": 0.0924, + "step": 397770 + }, + { + "epoch": 0.89, + "learning_rate": 5.637793337956645e-06, + "loss": 0.0955, + "step": 397780 + }, + { + "epoch": 0.89, + "learning_rate": 5.6366747947473215e-06, + "loss": 0.1003, + "step": 397790 + }, + { + "epoch": 0.89, + "learning_rate": 5.635556251537997e-06, + "loss": 0.0969, + "step": 397800 + }, + { + "epoch": 0.89, + "learning_rate": 5.634437708328673e-06, + "loss": 0.0959, + "step": 397810 + }, + { + "epoch": 0.89, + "learning_rate": 5.6333191651193485e-06, + "loss": 0.0983, + "step": 397820 + }, + { + "epoch": 0.89, + "learning_rate": 5.632200621910025e-06, + "loss": 0.0965, + "step": 397830 + }, + { + "epoch": 0.89, + "learning_rate": 5.6310820787007e-06, + "loss": 0.0913, + "step": 397840 + }, + { + "epoch": 0.89, + "learning_rate": 5.629963535491376e-06, + "loss": 0.0931, + "step": 397850 + }, + { + "epoch": 0.89, + "learning_rate": 5.628844992282052e-06, + "loss": 0.0975, + "step": 397860 + }, + { + "epoch": 0.89, + "learning_rate": 5.627726449072728e-06, + "loss": 0.0958, + "step": 397870 + }, + { + "epoch": 0.89, + "learning_rate": 5.626607905863403e-06, + "loss": 0.0964, + "step": 397880 + }, + { + "epoch": 0.89, + "learning_rate": 5.62548936265408e-06, + "loss": 0.0978, + "step": 397890 + }, + { + "epoch": 0.89, + "learning_rate": 5.624370819444756e-06, + "loss": 0.0922, + "step": 397900 + }, + { + "epoch": 0.89, + "learning_rate": 5.623252276235431e-06, + "loss": 0.094, + "step": 397910 + }, + { + "epoch": 0.89, + "learning_rate": 5.622133733026107e-06, + "loss": 0.092, + "step": 397920 + }, + { + "epoch": 0.89, + "learning_rate": 5.621015189816783e-06, + "loss": 0.096, + "step": 397930 + }, + { + "epoch": 0.89, + "learning_rate": 5.619896646607459e-06, + "loss": 0.0903, + "step": 397940 + }, + { + "epoch": 0.89, + "learning_rate": 5.6187781033981345e-06, + "loss": 0.0967, + "step": 397950 + }, + { + "epoch": 0.89, + "learning_rate": 5.61765956018881e-06, + "loss": 0.0919, + "step": 397960 + }, + { + "epoch": 0.89, + "learning_rate": 5.616541016979486e-06, + "loss": 0.1003, + "step": 397970 + }, + { + "epoch": 0.89, + "learning_rate": 5.615422473770162e-06, + "loss": 0.0976, + "step": 397980 + }, + { + "epoch": 0.89, + "learning_rate": 5.614303930560838e-06, + "loss": 0.0949, + "step": 397990 + }, + { + "epoch": 0.89, + "learning_rate": 5.613185387351513e-06, + "loss": 0.093, + "step": 398000 + }, + { + "epoch": 0.89, + "learning_rate": 5.612066844142189e-06, + "loss": 0.0952, + "step": 398010 + }, + { + "epoch": 0.89, + "learning_rate": 5.6109483009328656e-06, + "loss": 0.097, + "step": 398020 + }, + { + "epoch": 0.89, + "learning_rate": 5.609829757723541e-06, + "loss": 0.0928, + "step": 398030 + }, + { + "epoch": 0.89, + "learning_rate": 5.608711214514216e-06, + "loss": 0.0929, + "step": 398040 + }, + { + "epoch": 0.89, + "learning_rate": 5.6075926713048926e-06, + "loss": 0.092, + "step": 398050 + }, + { + "epoch": 0.89, + "learning_rate": 5.606474128095569e-06, + "loss": 0.0902, + "step": 398060 + }, + { + "epoch": 0.89, + "learning_rate": 5.605355584886245e-06, + "loss": 0.0915, + "step": 398070 + }, + { + "epoch": 0.89, + "learning_rate": 5.6042370416769196e-06, + "loss": 0.0923, + "step": 398080 + }, + { + "epoch": 0.89, + "learning_rate": 5.603118498467596e-06, + "loss": 0.0949, + "step": 398090 + }, + { + "epoch": 0.89, + "learning_rate": 5.601999955258272e-06, + "loss": 0.0917, + "step": 398100 + }, + { + "epoch": 0.89, + "learning_rate": 5.600881412048948e-06, + "loss": 0.0951, + "step": 398110 + }, + { + "epoch": 0.89, + "learning_rate": 5.599762868839623e-06, + "loss": 0.0932, + "step": 398120 + }, + { + "epoch": 0.89, + "learning_rate": 5.598644325630299e-06, + "loss": 0.0923, + "step": 398130 + }, + { + "epoch": 0.89, + "learning_rate": 5.597525782420975e-06, + "loss": 0.0931, + "step": 398140 + }, + { + "epoch": 0.89, + "learning_rate": 5.5964072392116515e-06, + "loss": 0.0953, + "step": 398150 + }, + { + "epoch": 0.89, + "learning_rate": 5.595288696002327e-06, + "loss": 0.0943, + "step": 398160 + }, + { + "epoch": 0.89, + "learning_rate": 5.594170152793002e-06, + "loss": 0.0963, + "step": 398170 + }, + { + "epoch": 0.89, + "learning_rate": 5.5930516095836785e-06, + "loss": 0.0923, + "step": 398180 + }, + { + "epoch": 0.89, + "learning_rate": 5.591933066374355e-06, + "loss": 0.0933, + "step": 398190 + }, + { + "epoch": 0.89, + "learning_rate": 5.59081452316503e-06, + "loss": 0.0954, + "step": 398200 + }, + { + "epoch": 0.89, + "learning_rate": 5.5896959799557055e-06, + "loss": 0.0904, + "step": 398210 + }, + { + "epoch": 0.89, + "learning_rate": 5.588577436746382e-06, + "loss": 0.0919, + "step": 398220 + }, + { + "epoch": 0.89, + "learning_rate": 5.587458893537058e-06, + "loss": 0.0975, + "step": 398230 + }, + { + "epoch": 0.89, + "learning_rate": 5.586340350327733e-06, + "loss": 0.0918, + "step": 398240 + }, + { + "epoch": 0.89, + "learning_rate": 5.585221807118409e-06, + "loss": 0.0925, + "step": 398250 + }, + { + "epoch": 0.89, + "learning_rate": 5.584103263909085e-06, + "loss": 0.0947, + "step": 398260 + }, + { + "epoch": 0.89, + "learning_rate": 5.582984720699761e-06, + "loss": 0.0926, + "step": 398270 + }, + { + "epoch": 0.89, + "learning_rate": 5.581866177490437e-06, + "loss": 0.0939, + "step": 398280 + }, + { + "epoch": 0.89, + "learning_rate": 5.580747634281112e-06, + "loss": 0.0869, + "step": 398290 + }, + { + "epoch": 0.89, + "learning_rate": 5.579629091071788e-06, + "loss": 0.0955, + "step": 398300 + }, + { + "epoch": 0.89, + "learning_rate": 5.5785105478624645e-06, + "loss": 0.0974, + "step": 398310 + }, + { + "epoch": 0.89, + "learning_rate": 5.57739200465314e-06, + "loss": 0.095, + "step": 398320 + }, + { + "epoch": 0.89, + "learning_rate": 5.576273461443816e-06, + "loss": 0.0964, + "step": 398330 + }, + { + "epoch": 0.89, + "learning_rate": 5.5751549182344915e-06, + "loss": 0.0946, + "step": 398340 + }, + { + "epoch": 0.89, + "learning_rate": 5.574036375025168e-06, + "loss": 0.0933, + "step": 398350 + }, + { + "epoch": 0.89, + "learning_rate": 5.572917831815843e-06, + "loss": 0.0966, + "step": 398360 + }, + { + "epoch": 0.89, + "learning_rate": 5.571799288606519e-06, + "loss": 0.0926, + "step": 398370 + }, + { + "epoch": 0.89, + "learning_rate": 5.570680745397195e-06, + "loss": 0.0975, + "step": 398380 + }, + { + "epoch": 0.89, + "learning_rate": 5.569562202187871e-06, + "loss": 0.093, + "step": 398390 + }, + { + "epoch": 0.89, + "learning_rate": 5.568443658978546e-06, + "loss": 0.0985, + "step": 398400 + }, + { + "epoch": 0.89, + "learning_rate": 5.567325115769223e-06, + "loss": 0.0969, + "step": 398410 + }, + { + "epoch": 0.89, + "learning_rate": 5.566206572559898e-06, + "loss": 0.0932, + "step": 398420 + }, + { + "epoch": 0.89, + "learning_rate": 5.565088029350574e-06, + "loss": 0.0953, + "step": 398430 + }, + { + "epoch": 0.89, + "learning_rate": 5.56396948614125e-06, + "loss": 0.0959, + "step": 398440 + }, + { + "epoch": 0.89, + "learning_rate": 5.562850942931926e-06, + "loss": 0.0934, + "step": 398450 + }, + { + "epoch": 0.89, + "learning_rate": 5.561732399722601e-06, + "loss": 0.0973, + "step": 398460 + }, + { + "epoch": 0.89, + "learning_rate": 5.5606138565132774e-06, + "loss": 0.0931, + "step": 398470 + }, + { + "epoch": 0.89, + "learning_rate": 5.559495313303953e-06, + "loss": 0.0963, + "step": 398480 + }, + { + "epoch": 0.89, + "learning_rate": 5.558376770094629e-06, + "loss": 0.0933, + "step": 398490 + }, + { + "epoch": 0.89, + "learning_rate": 5.557258226885305e-06, + "loss": 0.0948, + "step": 398500 + }, + { + "epoch": 0.89, + "learning_rate": 5.556139683675981e-06, + "loss": 0.0956, + "step": 398510 + }, + { + "epoch": 0.89, + "learning_rate": 5.555021140466656e-06, + "loss": 0.0925, + "step": 398520 + }, + { + "epoch": 0.89, + "learning_rate": 5.553902597257332e-06, + "loss": 0.0976, + "step": 398530 + }, + { + "epoch": 0.89, + "learning_rate": 5.5527840540480085e-06, + "loss": 0.0897, + "step": 398540 + }, + { + "epoch": 0.89, + "learning_rate": 5.551665510838684e-06, + "loss": 0.0973, + "step": 398550 + }, + { + "epoch": 0.89, + "learning_rate": 5.550546967629359e-06, + "loss": 0.0966, + "step": 398560 + }, + { + "epoch": 0.89, + "learning_rate": 5.5494284244200355e-06, + "loss": 0.0957, + "step": 398570 + }, + { + "epoch": 0.89, + "learning_rate": 5.548309881210712e-06, + "loss": 0.0923, + "step": 398580 + }, + { + "epoch": 0.89, + "learning_rate": 5.547191338001387e-06, + "loss": 0.0936, + "step": 398590 + }, + { + "epoch": 0.89, + "learning_rate": 5.5460727947920625e-06, + "loss": 0.0935, + "step": 398600 + }, + { + "epoch": 0.89, + "learning_rate": 5.544954251582739e-06, + "loss": 0.0961, + "step": 398610 + }, + { + "epoch": 0.89, + "learning_rate": 5.543835708373415e-06, + "loss": 0.0965, + "step": 398620 + }, + { + "epoch": 0.89, + "learning_rate": 5.54271716516409e-06, + "loss": 0.0935, + "step": 398630 + }, + { + "epoch": 0.89, + "learning_rate": 5.541598621954766e-06, + "loss": 0.0946, + "step": 398640 + }, + { + "epoch": 0.89, + "learning_rate": 5.540480078745442e-06, + "loss": 0.1, + "step": 398650 + }, + { + "epoch": 0.89, + "learning_rate": 5.539361535536118e-06, + "loss": 0.0931, + "step": 398660 + }, + { + "epoch": 0.89, + "learning_rate": 5.5382429923267945e-06, + "loss": 0.0914, + "step": 398670 + }, + { + "epoch": 0.89, + "learning_rate": 5.537124449117469e-06, + "loss": 0.0876, + "step": 398680 + }, + { + "epoch": 0.89, + "learning_rate": 5.536005905908145e-06, + "loss": 0.0951, + "step": 398690 + }, + { + "epoch": 0.89, + "learning_rate": 5.5348873626988215e-06, + "loss": 0.0912, + "step": 398700 + }, + { + "epoch": 0.89, + "learning_rate": 5.533768819489498e-06, + "loss": 0.0949, + "step": 398710 + }, + { + "epoch": 0.89, + "learning_rate": 5.532650276280172e-06, + "loss": 0.097, + "step": 398720 + }, + { + "epoch": 0.89, + "learning_rate": 5.5315317330708485e-06, + "loss": 0.0953, + "step": 398730 + }, + { + "epoch": 0.89, + "learning_rate": 5.530413189861525e-06, + "loss": 0.0966, + "step": 398740 + }, + { + "epoch": 0.89, + "learning_rate": 5.529294646652201e-06, + "loss": 0.0961, + "step": 398750 + }, + { + "epoch": 0.89, + "learning_rate": 5.528176103442876e-06, + "loss": 0.0936, + "step": 398760 + }, + { + "epoch": 0.89, + "learning_rate": 5.527057560233552e-06, + "loss": 0.097, + "step": 398770 + }, + { + "epoch": 0.89, + "learning_rate": 5.525939017024228e-06, + "loss": 0.0947, + "step": 398780 + }, + { + "epoch": 0.89, + "learning_rate": 5.524820473814904e-06, + "loss": 0.0939, + "step": 398790 + }, + { + "epoch": 0.89, + "learning_rate": 5.52370193060558e-06, + "loss": 0.0913, + "step": 398800 + }, + { + "epoch": 0.89, + "learning_rate": 5.522583387396255e-06, + "loss": 0.0959, + "step": 398810 + }, + { + "epoch": 0.89, + "learning_rate": 5.521464844186931e-06, + "loss": 0.0923, + "step": 398820 + }, + { + "epoch": 0.89, + "learning_rate": 5.5203463009776075e-06, + "loss": 0.0966, + "step": 398830 + }, + { + "epoch": 0.89, + "learning_rate": 5.519227757768283e-06, + "loss": 0.0946, + "step": 398840 + }, + { + "epoch": 0.89, + "learning_rate": 5.518109214558958e-06, + "loss": 0.0959, + "step": 398850 + }, + { + "epoch": 0.89, + "learning_rate": 5.5169906713496345e-06, + "loss": 0.0909, + "step": 398860 + }, + { + "epoch": 0.89, + "learning_rate": 5.515872128140311e-06, + "loss": 0.0904, + "step": 398870 + }, + { + "epoch": 0.89, + "learning_rate": 5.514753584930986e-06, + "loss": 0.0919, + "step": 398880 + }, + { + "epoch": 0.89, + "learning_rate": 5.5136350417216615e-06, + "loss": 0.0926, + "step": 398890 + }, + { + "epoch": 0.89, + "learning_rate": 5.512516498512338e-06, + "loss": 0.0932, + "step": 398900 + }, + { + "epoch": 0.89, + "learning_rate": 5.511397955303014e-06, + "loss": 0.0955, + "step": 398910 + }, + { + "epoch": 0.89, + "learning_rate": 5.510279412093689e-06, + "loss": 0.0999, + "step": 398920 + }, + { + "epoch": 0.89, + "learning_rate": 5.5091608688843656e-06, + "loss": 0.0952, + "step": 398930 + }, + { + "epoch": 0.89, + "learning_rate": 5.508042325675041e-06, + "loss": 0.0937, + "step": 398940 + }, + { + "epoch": 0.89, + "learning_rate": 5.506923782465717e-06, + "loss": 0.0939, + "step": 398950 + }, + { + "epoch": 0.89, + "learning_rate": 5.5058052392563926e-06, + "loss": 0.0934, + "step": 398960 + }, + { + "epoch": 0.89, + "learning_rate": 5.504686696047069e-06, + "loss": 0.0943, + "step": 398970 + }, + { + "epoch": 0.89, + "learning_rate": 5.503568152837744e-06, + "loss": 0.0911, + "step": 398980 + }, + { + "epoch": 0.89, + "learning_rate": 5.50244960962842e-06, + "loss": 0.0942, + "step": 398990 + }, + { + "epoch": 0.89, + "learning_rate": 5.501331066419096e-06, + "loss": 0.0968, + "step": 399000 + }, + { + "epoch": 0.89, + "learning_rate": 5.500212523209772e-06, + "loss": 0.0935, + "step": 399010 + }, + { + "epoch": 0.89, + "learning_rate": 5.499093980000447e-06, + "loss": 0.0942, + "step": 399020 + }, + { + "epoch": 0.89, + "learning_rate": 5.497975436791124e-06, + "loss": 0.0925, + "step": 399030 + }, + { + "epoch": 0.89, + "learning_rate": 5.496856893581799e-06, + "loss": 0.0917, + "step": 399040 + }, + { + "epoch": 0.89, + "learning_rate": 5.495738350372475e-06, + "loss": 0.0912, + "step": 399050 + }, + { + "epoch": 0.89, + "learning_rate": 5.494619807163151e-06, + "loss": 0.0978, + "step": 399060 + }, + { + "epoch": 0.89, + "learning_rate": 5.493501263953827e-06, + "loss": 0.0952, + "step": 399070 + }, + { + "epoch": 0.89, + "learning_rate": 5.492382720744502e-06, + "loss": 0.0955, + "step": 399080 + }, + { + "epoch": 0.89, + "learning_rate": 5.4912641775351785e-06, + "loss": 0.0923, + "step": 399090 + }, + { + "epoch": 0.89, + "learning_rate": 5.490145634325855e-06, + "loss": 0.0955, + "step": 399100 + }, + { + "epoch": 0.89, + "learning_rate": 5.48902709111653e-06, + "loss": 0.0911, + "step": 399110 + }, + { + "epoch": 0.89, + "learning_rate": 5.4879085479072055e-06, + "loss": 0.0966, + "step": 399120 + }, + { + "epoch": 0.89, + "learning_rate": 5.486790004697882e-06, + "loss": 0.0926, + "step": 399130 + }, + { + "epoch": 0.89, + "learning_rate": 5.485671461488558e-06, + "loss": 0.0899, + "step": 399140 + }, + { + "epoch": 0.89, + "learning_rate": 5.484552918279233e-06, + "loss": 0.096, + "step": 399150 + }, + { + "epoch": 0.89, + "learning_rate": 5.483434375069909e-06, + "loss": 0.0937, + "step": 399160 + }, + { + "epoch": 0.89, + "learning_rate": 5.482315831860585e-06, + "loss": 0.0913, + "step": 399170 + }, + { + "epoch": 0.89, + "learning_rate": 5.481197288651261e-06, + "loss": 0.0967, + "step": 399180 + }, + { + "epoch": 0.89, + "learning_rate": 5.480078745441937e-06, + "loss": 0.0954, + "step": 399190 + }, + { + "epoch": 0.89, + "learning_rate": 5.478960202232612e-06, + "loss": 0.0913, + "step": 399200 + }, + { + "epoch": 0.89, + "learning_rate": 5.477841659023288e-06, + "loss": 0.0971, + "step": 399210 + }, + { + "epoch": 0.89, + "learning_rate": 5.4767231158139645e-06, + "loss": 0.0915, + "step": 399220 + }, + { + "epoch": 0.89, + "learning_rate": 5.47560457260464e-06, + "loss": 0.0947, + "step": 399230 + }, + { + "epoch": 0.89, + "learning_rate": 5.474486029395315e-06, + "loss": 0.0958, + "step": 399240 + }, + { + "epoch": 0.89, + "learning_rate": 5.4733674861859915e-06, + "loss": 0.0973, + "step": 399250 + }, + { + "epoch": 0.89, + "learning_rate": 5.472248942976668e-06, + "loss": 0.0932, + "step": 399260 + }, + { + "epoch": 0.89, + "learning_rate": 5.471130399767344e-06, + "loss": 0.0964, + "step": 399270 + }, + { + "epoch": 0.89, + "learning_rate": 5.4700118565580185e-06, + "loss": 0.0924, + "step": 399280 + }, + { + "epoch": 0.89, + "learning_rate": 5.468893313348695e-06, + "loss": 0.0944, + "step": 399290 + }, + { + "epoch": 0.89, + "learning_rate": 5.467774770139371e-06, + "loss": 0.0965, + "step": 399300 + }, + { + "epoch": 0.89, + "learning_rate": 5.466656226930047e-06, + "loss": 0.096, + "step": 399310 + }, + { + "epoch": 0.89, + "learning_rate": 5.465537683720722e-06, + "loss": 0.0908, + "step": 399320 + }, + { + "epoch": 0.89, + "learning_rate": 5.464419140511398e-06, + "loss": 0.0926, + "step": 399330 + }, + { + "epoch": 0.89, + "learning_rate": 5.463300597302074e-06, + "loss": 0.0947, + "step": 399340 + }, + { + "epoch": 0.89, + "learning_rate": 5.4621820540927504e-06, + "loss": 0.098, + "step": 399350 + }, + { + "epoch": 0.89, + "learning_rate": 5.461063510883426e-06, + "loss": 0.0936, + "step": 399360 + }, + { + "epoch": 0.89, + "learning_rate": 5.459944967674101e-06, + "loss": 0.0941, + "step": 399370 + }, + { + "epoch": 0.89, + "learning_rate": 5.4588264244647774e-06, + "loss": 0.0968, + "step": 399380 + }, + { + "epoch": 0.89, + "learning_rate": 5.457707881255454e-06, + "loss": 0.0923, + "step": 399390 + }, + { + "epoch": 0.89, + "learning_rate": 5.456589338046129e-06, + "loss": 0.0961, + "step": 399400 + }, + { + "epoch": 0.89, + "learning_rate": 5.4554707948368044e-06, + "loss": 0.0961, + "step": 399410 + }, + { + "epoch": 0.89, + "learning_rate": 5.454352251627481e-06, + "loss": 0.0938, + "step": 399420 + }, + { + "epoch": 0.89, + "learning_rate": 5.453233708418157e-06, + "loss": 0.0943, + "step": 399430 + }, + { + "epoch": 0.89, + "learning_rate": 5.452115165208832e-06, + "loss": 0.0942, + "step": 399440 + }, + { + "epoch": 0.89, + "learning_rate": 5.450996621999508e-06, + "loss": 0.0966, + "step": 399450 + }, + { + "epoch": 0.89, + "learning_rate": 5.449878078790184e-06, + "loss": 0.0918, + "step": 399460 + }, + { + "epoch": 0.89, + "learning_rate": 5.44875953558086e-06, + "loss": 0.0933, + "step": 399470 + }, + { + "epoch": 0.89, + "learning_rate": 5.4476409923715355e-06, + "loss": 0.0972, + "step": 399480 + }, + { + "epoch": 0.89, + "learning_rate": 5.446522449162211e-06, + "loss": 0.0926, + "step": 399490 + }, + { + "epoch": 0.89, + "learning_rate": 5.445403905952887e-06, + "loss": 0.0937, + "step": 399500 + }, + { + "epoch": 0.89, + "learning_rate": 5.444285362743563e-06, + "loss": 0.0954, + "step": 399510 + }, + { + "epoch": 0.89, + "learning_rate": 5.443166819534239e-06, + "loss": 0.0919, + "step": 399520 + }, + { + "epoch": 0.89, + "learning_rate": 5.442048276324915e-06, + "loss": 0.0956, + "step": 399530 + }, + { + "epoch": 0.89, + "learning_rate": 5.44092973311559e-06, + "loss": 0.0918, + "step": 399540 + }, + { + "epoch": 0.89, + "learning_rate": 5.439811189906267e-06, + "loss": 0.0932, + "step": 399550 + }, + { + "epoch": 0.89, + "learning_rate": 5.438692646696942e-06, + "loss": 0.092, + "step": 399560 + }, + { + "epoch": 0.89, + "learning_rate": 5.437574103487618e-06, + "loss": 0.1007, + "step": 399570 + }, + { + "epoch": 0.89, + "learning_rate": 5.436455560278294e-06, + "loss": 0.0923, + "step": 399580 + }, + { + "epoch": 0.89, + "learning_rate": 5.43533701706897e-06, + "loss": 0.0894, + "step": 399590 + }, + { + "epoch": 0.89, + "learning_rate": 5.434218473859645e-06, + "loss": 0.0954, + "step": 399600 + }, + { + "epoch": 0.89, + "learning_rate": 5.4330999306503215e-06, + "loss": 0.0907, + "step": 399610 + }, + { + "epoch": 0.89, + "learning_rate": 5.431981387440997e-06, + "loss": 0.0927, + "step": 399620 + }, + { + "epoch": 0.89, + "learning_rate": 5.430862844231673e-06, + "loss": 0.0971, + "step": 399630 + }, + { + "epoch": 0.89, + "learning_rate": 5.4297443010223485e-06, + "loss": 0.0907, + "step": 399640 + }, + { + "epoch": 0.89, + "learning_rate": 5.428737612133957e-06, + "loss": 0.0916, + "step": 399650 + }, + { + "epoch": 0.89, + "learning_rate": 5.4276190689246335e-06, + "loss": 0.0931, + "step": 399660 + }, + { + "epoch": 0.89, + "learning_rate": 5.426500525715308e-06, + "loss": 0.0914, + "step": 399670 + }, + { + "epoch": 0.89, + "learning_rate": 5.425381982505984e-06, + "loss": 0.0928, + "step": 399680 + }, + { + "epoch": 0.89, + "learning_rate": 5.4242634392966605e-06, + "loss": 0.0917, + "step": 399690 + }, + { + "epoch": 0.89, + "learning_rate": 5.423144896087337e-06, + "loss": 0.0952, + "step": 399700 + }, + { + "epoch": 0.89, + "learning_rate": 5.422026352878012e-06, + "loss": 0.09, + "step": 399710 + }, + { + "epoch": 0.89, + "learning_rate": 5.4209078096686875e-06, + "loss": 0.0972, + "step": 399720 + }, + { + "epoch": 0.89, + "learning_rate": 5.419789266459364e-06, + "loss": 0.0949, + "step": 399730 + }, + { + "epoch": 0.89, + "learning_rate": 5.41867072325004e-06, + "loss": 0.0958, + "step": 399740 + }, + { + "epoch": 0.89, + "learning_rate": 5.417552180040715e-06, + "loss": 0.0913, + "step": 399750 + }, + { + "epoch": 0.89, + "learning_rate": 5.416433636831391e-06, + "loss": 0.0963, + "step": 399760 + }, + { + "epoch": 0.89, + "learning_rate": 5.415315093622067e-06, + "loss": 0.0917, + "step": 399770 + }, + { + "epoch": 0.89, + "learning_rate": 5.414196550412743e-06, + "loss": 0.0888, + "step": 399780 + }, + { + "epoch": 0.89, + "learning_rate": 5.413078007203419e-06, + "loss": 0.0957, + "step": 399790 + }, + { + "epoch": 0.89, + "learning_rate": 5.411959463994094e-06, + "loss": 0.0981, + "step": 399800 + }, + { + "epoch": 0.89, + "learning_rate": 5.41084092078477e-06, + "loss": 0.0944, + "step": 399810 + }, + { + "epoch": 0.89, + "learning_rate": 5.4097223775754465e-06, + "loss": 0.0954, + "step": 399820 + }, + { + "epoch": 0.89, + "learning_rate": 5.408603834366122e-06, + "loss": 0.0963, + "step": 399830 + }, + { + "epoch": 0.89, + "learning_rate": 5.407485291156797e-06, + "loss": 0.0954, + "step": 399840 + }, + { + "epoch": 0.89, + "learning_rate": 5.4063667479474735e-06, + "loss": 0.0958, + "step": 399850 + }, + { + "epoch": 0.89, + "learning_rate": 5.40524820473815e-06, + "loss": 0.0946, + "step": 399860 + }, + { + "epoch": 0.89, + "learning_rate": 5.404129661528825e-06, + "loss": 0.0958, + "step": 399870 + }, + { + "epoch": 0.89, + "learning_rate": 5.403011118319501e-06, + "loss": 0.0984, + "step": 399880 + }, + { + "epoch": 0.89, + "learning_rate": 5.401892575110177e-06, + "loss": 0.0967, + "step": 399890 + }, + { + "epoch": 0.89, + "learning_rate": 5.400774031900853e-06, + "loss": 0.0952, + "step": 399900 + }, + { + "epoch": 0.89, + "learning_rate": 5.399655488691528e-06, + "loss": 0.0925, + "step": 399910 + }, + { + "epoch": 0.89, + "learning_rate": 5.3985369454822046e-06, + "loss": 0.094, + "step": 399920 + }, + { + "epoch": 0.89, + "learning_rate": 5.39741840227288e-06, + "loss": 0.0949, + "step": 399930 + }, + { + "epoch": 0.89, + "learning_rate": 5.396299859063556e-06, + "loss": 0.0981, + "step": 399940 + }, + { + "epoch": 0.89, + "learning_rate": 5.3951813158542316e-06, + "loss": 0.0943, + "step": 399950 + }, + { + "epoch": 0.89, + "learning_rate": 5.394062772644908e-06, + "loss": 0.0925, + "step": 399960 + }, + { + "epoch": 0.89, + "learning_rate": 5.392944229435583e-06, + "loss": 0.0939, + "step": 399970 + }, + { + "epoch": 0.89, + "learning_rate": 5.3918256862262594e-06, + "loss": 0.0948, + "step": 399980 + }, + { + "epoch": 0.89, + "learning_rate": 5.390707143016935e-06, + "loss": 0.0916, + "step": 399990 + }, + { + "epoch": 0.89, + "learning_rate": 5.389588599807611e-06, + "loss": 0.0945, + "step": 400000 + }, + { + "epoch": 0.89, + "eval_NEIMS_canon_smiles": 0.9604666666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.26916666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.6317138256914245, + "eval_NEIMS_exact_mols": 0.26886666666666664, + "eval_NEIMS_exact_smiles": 0.2634, + "eval_NEIMS_loss": 0.12200460582971573, + "eval_NEIMS_matched_formulas": 0.7696666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.5601760319966, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.2696, + "eval_NEIMS_runtime": 717.7505, + "eval_NEIMS_samples_per_second": 83.595, + "eval_NEIMS_steps_per_second": 1.307, + "step": 400000 + }, + { + "epoch": 0.89, + "eval_RASSP_canon_smiles": 0.9600293852472702, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.3487494573746953, + "eval_RASSP_daylight_tanimoto_simil": 0.731491784508703, + "eval_RASSP_exact_mols": 0.3478645607239456, + "eval_RASSP_exact_smiles": 0.3400674524994156, + "eval_RASSP_loss": 0.0940130427479744, + "eval_RASSP_matched_formulas": 0.892844024443183, + "eval_RASSP_morgan_tanimoto_simil": 0.6291179843342122, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.3480482185193842, + "eval_RASSP_runtime": 819.1039, + "eval_RASSP_samples_per_second": 73.121, + "eval_RASSP_steps_per_second": 1.143, + "step": 400000 + }, + { + "epoch": 0.89, + "eval_NEIMS_old_canon_smiles": 0.9599333333333333, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2655, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6300964134758967, + "eval_NEIMS_old_exact_mols": 0.26516666666666666, + "eval_NEIMS_old_exact_smiles": 0.25983333333333336, + "eval_NEIMS_old_loss": 0.12217695266008377, + "eval_NEIMS_old_matched_formulas": 0.7700333333333333, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5587830024758467, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2659666666666667, + "eval_NEIMS_old_runtime": 360.7666, + "eval_NEIMS_old_samples_per_second": 83.156, + "eval_NEIMS_old_steps_per_second": 1.3, + "step": 400000 + }, + { + "epoch": 0.89, + "eval_RASSP_old_canon_smiles": 0.9606233523542563, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.37918376881236027, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7507246593989962, + "eval_RASSP_old_exact_mols": 0.3779824473587613, + "eval_RASSP_old_exact_smiles": 0.3693396069009244, + "eval_RASSP_old_loss": 0.08790504932403564, + "eval_RASSP_old_matched_formulas": 0.9023592618547068, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6518403809194248, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.3781159275202723, + "eval_RASSP_old_runtime": 408.4502, + "eval_RASSP_old_samples_per_second": 73.368, + "eval_RASSP_old_steps_per_second": 1.148, + "step": 400000 + }, + { + "epoch": 0.89, + "eval_NIST_canon_smiles": 0.8621215885296518, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.031018206338503034, + "eval_NIST_daylight_tanimoto_simil": 0.3072165098672645, + "eval_NIST_exact_mols": 0.02927919934698513, + "eval_NIST_exact_smiles": 0.0279660716186961, + "eval_NIST_loss": 1.7723655700683594, + "eval_NIST_matched_formulas": 0.13315824963622813, + "eval_NIST_morgan_tanimoto_simil": 0.2580450071508804, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.030521347198069346, + "eval_NIST_runtime": 614.5024, + "eval_NIST_samples_per_second": 45.853, + "eval_NIST_steps_per_second": 0.718, + "step": 400000 + }, + { + "epoch": 0.89, + "learning_rate": 5.3884700565982864e-06, + "loss": 0.0947, + "step": 400010 + }, + { + "epoch": 0.89, + "learning_rate": 5.387351513388963e-06, + "loss": 0.0921, + "step": 400020 + }, + { + "epoch": 0.89, + "learning_rate": 5.386232970179638e-06, + "loss": 0.0946, + "step": 400030 + }, + { + "epoch": 0.89, + "learning_rate": 5.385114426970314e-06, + "loss": 0.0969, + "step": 400040 + }, + { + "epoch": 0.89, + "learning_rate": 5.38399588376099e-06, + "loss": 0.0931, + "step": 400050 + }, + { + "epoch": 0.89, + "learning_rate": 5.382877340551666e-06, + "loss": 0.0911, + "step": 400060 + }, + { + "epoch": 0.89, + "learning_rate": 5.381758797342341e-06, + "loss": 0.0911, + "step": 400070 + }, + { + "epoch": 0.89, + "learning_rate": 5.3806402541330175e-06, + "loss": 0.0951, + "step": 400080 + }, + { + "epoch": 0.89, + "learning_rate": 5.379521710923694e-06, + "loss": 0.0934, + "step": 400090 + }, + { + "epoch": 0.89, + "learning_rate": 5.378403167714369e-06, + "loss": 0.0942, + "step": 400100 + }, + { + "epoch": 0.89, + "learning_rate": 5.3772846245050445e-06, + "loss": 0.0974, + "step": 400110 + }, + { + "epoch": 0.89, + "learning_rate": 5.376166081295721e-06, + "loss": 0.0934, + "step": 400120 + }, + { + "epoch": 0.89, + "learning_rate": 5.375047538086397e-06, + "loss": 0.0928, + "step": 400130 + }, + { + "epoch": 0.89, + "learning_rate": 5.373928994877072e-06, + "loss": 0.0966, + "step": 400140 + }, + { + "epoch": 0.89, + "learning_rate": 5.372810451667748e-06, + "loss": 0.0955, + "step": 400150 + }, + { + "epoch": 0.89, + "learning_rate": 5.371691908458424e-06, + "loss": 0.0973, + "step": 400160 + }, + { + "epoch": 0.89, + "learning_rate": 5.3705733652491e-06, + "loss": 0.0909, + "step": 400170 + }, + { + "epoch": 0.89, + "learning_rate": 5.369454822039776e-06, + "loss": 0.0924, + "step": 400180 + }, + { + "epoch": 0.89, + "learning_rate": 5.368336278830451e-06, + "loss": 0.094, + "step": 400190 + }, + { + "epoch": 0.89, + "learning_rate": 5.367217735621127e-06, + "loss": 0.0936, + "step": 400200 + }, + { + "epoch": 0.89, + "learning_rate": 5.3660991924118035e-06, + "loss": 0.0935, + "step": 400210 + }, + { + "epoch": 0.89, + "learning_rate": 5.364980649202479e-06, + "loss": 0.0962, + "step": 400220 + }, + { + "epoch": 0.89, + "learning_rate": 5.363862105993154e-06, + "loss": 0.0944, + "step": 400230 + }, + { + "epoch": 0.89, + "learning_rate": 5.3627435627838305e-06, + "loss": 0.0926, + "step": 400240 + }, + { + "epoch": 0.89, + "learning_rate": 5.361625019574507e-06, + "loss": 0.0949, + "step": 400250 + }, + { + "epoch": 0.89, + "learning_rate": 5.360506476365183e-06, + "loss": 0.0963, + "step": 400260 + }, + { + "epoch": 0.89, + "learning_rate": 5.3593879331558575e-06, + "loss": 0.0943, + "step": 400270 + }, + { + "epoch": 0.89, + "learning_rate": 5.358269389946534e-06, + "loss": 0.0953, + "step": 400280 + }, + { + "epoch": 0.89, + "learning_rate": 5.35715084673721e-06, + "loss": 0.0982, + "step": 400290 + }, + { + "epoch": 0.89, + "learning_rate": 5.356032303527886e-06, + "loss": 0.093, + "step": 400300 + }, + { + "epoch": 0.89, + "learning_rate": 5.354913760318562e-06, + "loss": 0.0898, + "step": 400310 + }, + { + "epoch": 0.89, + "learning_rate": 5.353795217109237e-06, + "loss": 0.0983, + "step": 400320 + }, + { + "epoch": 0.89, + "learning_rate": 5.352676673899913e-06, + "loss": 0.091, + "step": 400330 + }, + { + "epoch": 0.89, + "learning_rate": 5.3515581306905894e-06, + "loss": 0.0929, + "step": 400340 + }, + { + "epoch": 0.89, + "learning_rate": 5.350439587481265e-06, + "loss": 0.0957, + "step": 400350 + }, + { + "epoch": 0.89, + "learning_rate": 5.34932104427194e-06, + "loss": 0.0914, + "step": 400360 + }, + { + "epoch": 0.89, + "learning_rate": 5.3482025010626164e-06, + "loss": 0.0983, + "step": 400370 + }, + { + "epoch": 0.89, + "learning_rate": 5.347083957853293e-06, + "loss": 0.0935, + "step": 400380 + }, + { + "epoch": 0.89, + "learning_rate": 5.345965414643968e-06, + "loss": 0.0944, + "step": 400390 + }, + { + "epoch": 0.89, + "learning_rate": 5.3448468714346435e-06, + "loss": 0.0921, + "step": 400400 + }, + { + "epoch": 0.89, + "learning_rate": 5.34372832822532e-06, + "loss": 0.0896, + "step": 400410 + }, + { + "epoch": 0.89, + "learning_rate": 5.342609785015996e-06, + "loss": 0.0912, + "step": 400420 + }, + { + "epoch": 0.89, + "learning_rate": 5.341491241806671e-06, + "loss": 0.0941, + "step": 400430 + }, + { + "epoch": 0.89, + "learning_rate": 5.340372698597347e-06, + "loss": 0.0952, + "step": 400440 + }, + { + "epoch": 0.89, + "learning_rate": 5.339254155388023e-06, + "loss": 0.0952, + "step": 400450 + }, + { + "epoch": 0.89, + "learning_rate": 5.338135612178699e-06, + "loss": 0.097, + "step": 400460 + }, + { + "epoch": 0.89, + "learning_rate": 5.3370170689693745e-06, + "loss": 0.0914, + "step": 400470 + }, + { + "epoch": 0.89, + "learning_rate": 5.335898525760051e-06, + "loss": 0.0928, + "step": 400480 + }, + { + "epoch": 0.89, + "learning_rate": 5.334779982550726e-06, + "loss": 0.0928, + "step": 400490 + }, + { + "epoch": 0.89, + "learning_rate": 5.333661439341402e-06, + "loss": 0.0995, + "step": 400500 + }, + { + "epoch": 0.89, + "learning_rate": 5.332542896132078e-06, + "loss": 0.0961, + "step": 400510 + }, + { + "epoch": 0.89, + "learning_rate": 5.331424352922754e-06, + "loss": 0.0953, + "step": 400520 + }, + { + "epoch": 0.89, + "learning_rate": 5.330305809713429e-06, + "loss": 0.0942, + "step": 400530 + }, + { + "epoch": 0.89, + "learning_rate": 5.329187266504105e-06, + "loss": 0.0978, + "step": 400540 + }, + { + "epoch": 0.89, + "learning_rate": 5.328068723294781e-06, + "loss": 0.0963, + "step": 400550 + }, + { + "epoch": 0.89, + "learning_rate": 5.326950180085457e-06, + "loss": 0.0939, + "step": 400560 + }, + { + "epoch": 0.89, + "learning_rate": 5.325831636876133e-06, + "loss": 0.0957, + "step": 400570 + }, + { + "epoch": 0.89, + "learning_rate": 5.324713093666808e-06, + "loss": 0.0934, + "step": 400580 + }, + { + "epoch": 0.89, + "learning_rate": 5.323594550457484e-06, + "loss": 0.0934, + "step": 400590 + }, + { + "epoch": 0.89, + "learning_rate": 5.3224760072481605e-06, + "loss": 0.0999, + "step": 400600 + }, + { + "epoch": 0.89, + "learning_rate": 5.321357464038836e-06, + "loss": 0.0929, + "step": 400610 + }, + { + "epoch": 0.89, + "learning_rate": 5.320238920829511e-06, + "loss": 0.093, + "step": 400620 + }, + { + "epoch": 0.89, + "learning_rate": 5.3191203776201875e-06, + "loss": 0.0908, + "step": 400630 + }, + { + "epoch": 0.89, + "learning_rate": 5.318001834410864e-06, + "loss": 0.0911, + "step": 400640 + }, + { + "epoch": 0.89, + "learning_rate": 5.316883291201539e-06, + "loss": 0.098, + "step": 400650 + }, + { + "epoch": 0.89, + "learning_rate": 5.3157647479922145e-06, + "loss": 0.0961, + "step": 400660 + }, + { + "epoch": 0.89, + "learning_rate": 5.314646204782891e-06, + "loss": 0.095, + "step": 400670 + }, + { + "epoch": 0.89, + "learning_rate": 5.313527661573567e-06, + "loss": 0.0952, + "step": 400680 + }, + { + "epoch": 0.89, + "learning_rate": 5.312409118364243e-06, + "loss": 0.0931, + "step": 400690 + }, + { + "epoch": 0.89, + "learning_rate": 5.311290575154918e-06, + "loss": 0.0917, + "step": 400700 + }, + { + "epoch": 0.89, + "learning_rate": 5.310172031945594e-06, + "loss": 0.0971, + "step": 400710 + }, + { + "epoch": 0.89, + "learning_rate": 5.30905348873627e-06, + "loss": 0.0955, + "step": 400720 + }, + { + "epoch": 0.89, + "learning_rate": 5.3079349455269465e-06, + "loss": 0.0938, + "step": 400730 + }, + { + "epoch": 0.89, + "learning_rate": 5.306816402317622e-06, + "loss": 0.0975, + "step": 400740 + }, + { + "epoch": 0.89, + "learning_rate": 5.305697859108297e-06, + "loss": 0.0948, + "step": 400750 + }, + { + "epoch": 0.89, + "learning_rate": 5.3045793158989735e-06, + "loss": 0.0966, + "step": 400760 + }, + { + "epoch": 0.89, + "learning_rate": 5.30346077268965e-06, + "loss": 0.0932, + "step": 400770 + }, + { + "epoch": 0.89, + "learning_rate": 5.302342229480325e-06, + "loss": 0.0955, + "step": 400780 + }, + { + "epoch": 0.89, + "learning_rate": 5.3012236862710005e-06, + "loss": 0.0891, + "step": 400790 + }, + { + "epoch": 0.89, + "learning_rate": 5.300105143061677e-06, + "loss": 0.0936, + "step": 400800 + }, + { + "epoch": 0.89, + "learning_rate": 5.298986599852353e-06, + "loss": 0.0875, + "step": 400810 + }, + { + "epoch": 0.89, + "learning_rate": 5.297868056643028e-06, + "loss": 0.0963, + "step": 400820 + }, + { + "epoch": 0.89, + "learning_rate": 5.296749513433704e-06, + "loss": 0.0949, + "step": 400830 + }, + { + "epoch": 0.89, + "learning_rate": 5.29563097022438e-06, + "loss": 0.0926, + "step": 400840 + }, + { + "epoch": 0.89, + "learning_rate": 5.294512427015056e-06, + "loss": 0.0946, + "step": 400850 + }, + { + "epoch": 0.89, + "learning_rate": 5.2933938838057316e-06, + "loss": 0.0958, + "step": 400860 + }, + { + "epoch": 0.89, + "learning_rate": 5.292275340596407e-06, + "loss": 0.0904, + "step": 400870 + }, + { + "epoch": 0.89, + "learning_rate": 5.291156797387083e-06, + "loss": 0.0971, + "step": 400880 + }, + { + "epoch": 0.89, + "learning_rate": 5.290038254177759e-06, + "loss": 0.0986, + "step": 400890 + }, + { + "epoch": 0.89, + "learning_rate": 5.288919710968435e-06, + "loss": 0.0962, + "step": 400900 + }, + { + "epoch": 0.89, + "learning_rate": 5.287801167759111e-06, + "loss": 0.0927, + "step": 400910 + }, + { + "epoch": 0.89, + "learning_rate": 5.2866826245497864e-06, + "loss": 0.091, + "step": 400920 + }, + { + "epoch": 0.89, + "learning_rate": 5.285564081340463e-06, + "loss": 0.0907, + "step": 400930 + }, + { + "epoch": 0.89, + "learning_rate": 5.284445538131138e-06, + "loss": 0.095, + "step": 400940 + }, + { + "epoch": 0.89, + "learning_rate": 5.283326994921814e-06, + "loss": 0.0964, + "step": 400950 + }, + { + "epoch": 0.89, + "learning_rate": 5.28220845171249e-06, + "loss": 0.0953, + "step": 400960 + }, + { + "epoch": 0.9, + "learning_rate": 5.281089908503166e-06, + "loss": 0.0969, + "step": 400970 + }, + { + "epoch": 0.9, + "learning_rate": 5.279971365293841e-06, + "loss": 0.0923, + "step": 400980 + }, + { + "epoch": 0.9, + "learning_rate": 5.2788528220845175e-06, + "loss": 0.0942, + "step": 400990 + }, + { + "epoch": 0.9, + "learning_rate": 5.277734278875193e-06, + "loss": 0.0936, + "step": 401000 + }, + { + "epoch": 0.9, + "learning_rate": 5.276615735665869e-06, + "loss": 0.0933, + "step": 401010 + }, + { + "epoch": 0.9, + "learning_rate": 5.2754971924565445e-06, + "loss": 0.098, + "step": 401020 + }, + { + "epoch": 0.9, + "learning_rate": 5.274378649247221e-06, + "loss": 0.0922, + "step": 401030 + }, + { + "epoch": 0.9, + "learning_rate": 5.273260106037896e-06, + "loss": 0.0947, + "step": 401040 + }, + { + "epoch": 0.9, + "learning_rate": 5.272141562828572e-06, + "loss": 0.0999, + "step": 401050 + }, + { + "epoch": 0.9, + "learning_rate": 5.271023019619248e-06, + "loss": 0.0951, + "step": 401060 + }, + { + "epoch": 0.9, + "learning_rate": 5.269904476409924e-06, + "loss": 0.0954, + "step": 401070 + }, + { + "epoch": 0.9, + "learning_rate": 5.2687859332006e-06, + "loss": 0.0904, + "step": 401080 + }, + { + "epoch": 0.9, + "learning_rate": 5.267667389991276e-06, + "loss": 0.0956, + "step": 401090 + }, + { + "epoch": 0.9, + "learning_rate": 5.266548846781951e-06, + "loss": 0.0922, + "step": 401100 + }, + { + "epoch": 0.9, + "learning_rate": 5.265430303572627e-06, + "loss": 0.0968, + "step": 401110 + }, + { + "epoch": 0.9, + "learning_rate": 5.2643117603633035e-06, + "loss": 0.0983, + "step": 401120 + }, + { + "epoch": 0.9, + "learning_rate": 5.263193217153979e-06, + "loss": 0.0939, + "step": 401130 + }, + { + "epoch": 0.9, + "learning_rate": 5.262074673944654e-06, + "loss": 0.0931, + "step": 401140 + }, + { + "epoch": 0.9, + "learning_rate": 5.2609561307353305e-06, + "loss": 0.094, + "step": 401150 + }, + { + "epoch": 0.9, + "learning_rate": 5.259837587526007e-06, + "loss": 0.0942, + "step": 401160 + }, + { + "epoch": 0.9, + "learning_rate": 5.258719044316682e-06, + "loss": 0.0929, + "step": 401170 + }, + { + "epoch": 0.9, + "learning_rate": 5.2576005011073575e-06, + "loss": 0.0973, + "step": 401180 + }, + { + "epoch": 0.9, + "learning_rate": 5.256481957898034e-06, + "loss": 0.0917, + "step": 401190 + }, + { + "epoch": 0.9, + "learning_rate": 5.25536341468871e-06, + "loss": 0.0945, + "step": 401200 + }, + { + "epoch": 0.9, + "learning_rate": 5.254244871479385e-06, + "loss": 0.0921, + "step": 401210 + }, + { + "epoch": 0.9, + "learning_rate": 5.253126328270061e-06, + "loss": 0.0971, + "step": 401220 + }, + { + "epoch": 0.9, + "learning_rate": 5.252007785060737e-06, + "loss": 0.0962, + "step": 401230 + }, + { + "epoch": 0.9, + "learning_rate": 5.250889241851413e-06, + "loss": 0.0945, + "step": 401240 + }, + { + "epoch": 0.9, + "learning_rate": 5.2497706986420894e-06, + "loss": 0.0982, + "step": 401250 + }, + { + "epoch": 0.9, + "learning_rate": 5.248652155432764e-06, + "loss": 0.094, + "step": 401260 + }, + { + "epoch": 0.9, + "learning_rate": 5.24753361222344e-06, + "loss": 0.0928, + "step": 401270 + }, + { + "epoch": 0.9, + "learning_rate": 5.2464150690141164e-06, + "loss": 0.0934, + "step": 401280 + }, + { + "epoch": 0.9, + "learning_rate": 5.245296525804793e-06, + "loss": 0.0949, + "step": 401290 + }, + { + "epoch": 0.9, + "learning_rate": 5.244177982595467e-06, + "loss": 0.0934, + "step": 401300 + }, + { + "epoch": 0.9, + "learning_rate": 5.2430594393861434e-06, + "loss": 0.0954, + "step": 401310 + }, + { + "epoch": 0.9, + "learning_rate": 5.24194089617682e-06, + "loss": 0.093, + "step": 401320 + }, + { + "epoch": 0.9, + "learning_rate": 5.240822352967496e-06, + "loss": 0.095, + "step": 401330 + }, + { + "epoch": 0.9, + "learning_rate": 5.239703809758171e-06, + "loss": 0.0924, + "step": 401340 + }, + { + "epoch": 0.9, + "learning_rate": 5.238585266548847e-06, + "loss": 0.0959, + "step": 401350 + }, + { + "epoch": 0.9, + "learning_rate": 5.237466723339523e-06, + "loss": 0.0932, + "step": 401360 + }, + { + "epoch": 0.9, + "learning_rate": 5.236348180130199e-06, + "loss": 0.0944, + "step": 401370 + }, + { + "epoch": 0.9, + "learning_rate": 5.2352296369208745e-06, + "loss": 0.0928, + "step": 401380 + }, + { + "epoch": 0.9, + "learning_rate": 5.23411109371155e-06, + "loss": 0.0933, + "step": 401390 + }, + { + "epoch": 0.9, + "learning_rate": 5.232992550502226e-06, + "loss": 0.0913, + "step": 401400 + }, + { + "epoch": 0.9, + "learning_rate": 5.231874007292902e-06, + "loss": 0.0939, + "step": 401410 + }, + { + "epoch": 0.9, + "learning_rate": 5.230755464083578e-06, + "loss": 0.0965, + "step": 401420 + }, + { + "epoch": 0.9, + "learning_rate": 5.229636920874253e-06, + "loss": 0.0936, + "step": 401430 + }, + { + "epoch": 0.9, + "learning_rate": 5.228518377664929e-06, + "loss": 0.0906, + "step": 401440 + }, + { + "epoch": 0.9, + "learning_rate": 5.227399834455606e-06, + "loss": 0.0938, + "step": 401450 + }, + { + "epoch": 0.9, + "learning_rate": 5.226281291246281e-06, + "loss": 0.0939, + "step": 401460 + }, + { + "epoch": 0.9, + "learning_rate": 5.225162748036956e-06, + "loss": 0.0927, + "step": 401470 + }, + { + "epoch": 0.9, + "learning_rate": 5.224044204827633e-06, + "loss": 0.0948, + "step": 401480 + }, + { + "epoch": 0.9, + "learning_rate": 5.222925661618309e-06, + "loss": 0.0963, + "step": 401490 + }, + { + "epoch": 0.9, + "learning_rate": 5.221807118408984e-06, + "loss": 0.0939, + "step": 401500 + }, + { + "epoch": 0.9, + "learning_rate": 5.2206885751996605e-06, + "loss": 0.0914, + "step": 401510 + }, + { + "epoch": 0.9, + "learning_rate": 5.219570031990336e-06, + "loss": 0.0892, + "step": 401520 + }, + { + "epoch": 0.9, + "learning_rate": 5.218451488781012e-06, + "loss": 0.0959, + "step": 401530 + }, + { + "epoch": 0.9, + "learning_rate": 5.2173329455716875e-06, + "loss": 0.0929, + "step": 401540 + }, + { + "epoch": 0.9, + "learning_rate": 5.216214402362364e-06, + "loss": 0.0936, + "step": 401550 + }, + { + "epoch": 0.9, + "learning_rate": 5.215095859153039e-06, + "loss": 0.0963, + "step": 401560 + }, + { + "epoch": 0.9, + "learning_rate": 5.213977315943715e-06, + "loss": 0.0983, + "step": 401570 + }, + { + "epoch": 0.9, + "learning_rate": 5.212858772734391e-06, + "loss": 0.0926, + "step": 401580 + }, + { + "epoch": 0.9, + "learning_rate": 5.211740229525067e-06, + "loss": 0.0952, + "step": 401590 + }, + { + "epoch": 0.9, + "learning_rate": 5.210621686315742e-06, + "loss": 0.0933, + "step": 401600 + }, + { + "epoch": 0.9, + "learning_rate": 5.209503143106419e-06, + "loss": 0.0907, + "step": 401610 + }, + { + "epoch": 0.9, + "learning_rate": 5.208384599897094e-06, + "loss": 0.0932, + "step": 401620 + }, + { + "epoch": 0.9, + "learning_rate": 5.20726605668777e-06, + "loss": 0.0911, + "step": 401630 + }, + { + "epoch": 0.9, + "learning_rate": 5.206147513478446e-06, + "loss": 0.0905, + "step": 401640 + }, + { + "epoch": 0.9, + "learning_rate": 5.205028970269122e-06, + "loss": 0.0936, + "step": 401650 + }, + { + "epoch": 0.9, + "learning_rate": 5.203910427059797e-06, + "loss": 0.0929, + "step": 401660 + }, + { + "epoch": 0.9, + "learning_rate": 5.2027918838504735e-06, + "loss": 0.0953, + "step": 401670 + }, + { + "epoch": 0.9, + "learning_rate": 5.20167334064115e-06, + "loss": 0.0942, + "step": 401680 + }, + { + "epoch": 0.9, + "learning_rate": 5.200554797431825e-06, + "loss": 0.0919, + "step": 401690 + }, + { + "epoch": 0.9, + "learning_rate": 5.1994362542225005e-06, + "loss": 0.0925, + "step": 401700 + }, + { + "epoch": 0.9, + "learning_rate": 5.198317711013177e-06, + "loss": 0.0961, + "step": 401710 + }, + { + "epoch": 0.9, + "learning_rate": 5.1973110221247855e-06, + "loss": 0.098, + "step": 401720 + }, + { + "epoch": 0.9, + "learning_rate": 5.196192478915461e-06, + "loss": 0.0965, + "step": 401730 + }, + { + "epoch": 0.9, + "learning_rate": 5.195073935706136e-06, + "loss": 0.0952, + "step": 401740 + }, + { + "epoch": 0.9, + "learning_rate": 5.1939553924968125e-06, + "loss": 0.0935, + "step": 401750 + }, + { + "epoch": 0.9, + "learning_rate": 5.192836849287489e-06, + "loss": 0.097, + "step": 401760 + }, + { + "epoch": 0.9, + "learning_rate": 5.191718306078164e-06, + "loss": 0.0918, + "step": 401770 + }, + { + "epoch": 0.9, + "learning_rate": 5.1905997628688395e-06, + "loss": 0.0927, + "step": 401780 + }, + { + "epoch": 0.9, + "learning_rate": 5.189481219659516e-06, + "loss": 0.0998, + "step": 401790 + }, + { + "epoch": 0.9, + "learning_rate": 5.188362676450192e-06, + "loss": 0.0943, + "step": 401800 + }, + { + "epoch": 0.9, + "learning_rate": 5.187244133240867e-06, + "loss": 0.0965, + "step": 401810 + }, + { + "epoch": 0.9, + "learning_rate": 5.186125590031543e-06, + "loss": 0.0946, + "step": 401820 + }, + { + "epoch": 0.9, + "learning_rate": 5.185007046822219e-06, + "loss": 0.0958, + "step": 401830 + }, + { + "epoch": 0.9, + "learning_rate": 5.183888503612895e-06, + "loss": 0.0912, + "step": 401840 + }, + { + "epoch": 0.9, + "learning_rate": 5.182769960403571e-06, + "loss": 0.095, + "step": 401850 + }, + { + "epoch": 0.9, + "learning_rate": 5.181651417194246e-06, + "loss": 0.0899, + "step": 401860 + }, + { + "epoch": 0.9, + "learning_rate": 5.180532873984922e-06, + "loss": 0.0948, + "step": 401870 + }, + { + "epoch": 0.9, + "learning_rate": 5.1794143307755984e-06, + "loss": 0.0952, + "step": 401880 + }, + { + "epoch": 0.9, + "learning_rate": 5.178295787566274e-06, + "loss": 0.0976, + "step": 401890 + }, + { + "epoch": 0.9, + "learning_rate": 5.17717724435695e-06, + "loss": 0.0931, + "step": 401900 + }, + { + "epoch": 0.9, + "learning_rate": 5.1760587011476254e-06, + "loss": 0.0941, + "step": 401910 + }, + { + "epoch": 0.9, + "learning_rate": 5.174940157938302e-06, + "loss": 0.0947, + "step": 401920 + }, + { + "epoch": 0.9, + "learning_rate": 5.173821614728977e-06, + "loss": 0.0949, + "step": 401930 + }, + { + "epoch": 0.9, + "learning_rate": 5.172703071519653e-06, + "loss": 0.0866, + "step": 401940 + }, + { + "epoch": 0.9, + "learning_rate": 5.171584528310329e-06, + "loss": 0.0957, + "step": 401950 + }, + { + "epoch": 0.9, + "learning_rate": 5.170465985101005e-06, + "loss": 0.0946, + "step": 401960 + }, + { + "epoch": 0.9, + "learning_rate": 5.16934744189168e-06, + "loss": 0.0955, + "step": 401970 + }, + { + "epoch": 0.9, + "learning_rate": 5.1682288986823565e-06, + "loss": 0.0993, + "step": 401980 + }, + { + "epoch": 0.9, + "learning_rate": 5.167110355473032e-06, + "loss": 0.0921, + "step": 401990 + }, + { + "epoch": 0.9, + "learning_rate": 5.165991812263708e-06, + "loss": 0.0928, + "step": 402000 + }, + { + "epoch": 0.9, + "learning_rate": 5.1648732690543835e-06, + "loss": 0.097, + "step": 402010 + }, + { + "epoch": 0.9, + "learning_rate": 5.16375472584506e-06, + "loss": 0.0948, + "step": 402020 + }, + { + "epoch": 0.9, + "learning_rate": 5.162636182635735e-06, + "loss": 0.094, + "step": 402030 + }, + { + "epoch": 0.9, + "learning_rate": 5.161517639426411e-06, + "loss": 0.0957, + "step": 402040 + }, + { + "epoch": 0.9, + "learning_rate": 5.160399096217087e-06, + "loss": 0.0971, + "step": 402050 + }, + { + "epoch": 0.9, + "learning_rate": 5.159280553007763e-06, + "loss": 0.0936, + "step": 402060 + }, + { + "epoch": 0.9, + "learning_rate": 5.158162009798439e-06, + "loss": 0.092, + "step": 402070 + }, + { + "epoch": 0.9, + "learning_rate": 5.157043466589115e-06, + "loss": 0.0954, + "step": 402080 + }, + { + "epoch": 0.9, + "learning_rate": 5.15592492337979e-06, + "loss": 0.0918, + "step": 402090 + }, + { + "epoch": 0.9, + "learning_rate": 5.154806380170466e-06, + "loss": 0.0946, + "step": 402100 + }, + { + "epoch": 0.9, + "learning_rate": 5.1536878369611425e-06, + "loss": 0.0978, + "step": 402110 + }, + { + "epoch": 0.9, + "learning_rate": 5.152569293751818e-06, + "loss": 0.0909, + "step": 402120 + }, + { + "epoch": 0.9, + "learning_rate": 5.151450750542493e-06, + "loss": 0.093, + "step": 402130 + }, + { + "epoch": 0.9, + "learning_rate": 5.1503322073331695e-06, + "loss": 0.0947, + "step": 402140 + }, + { + "epoch": 0.9, + "learning_rate": 5.149213664123846e-06, + "loss": 0.0932, + "step": 402150 + }, + { + "epoch": 0.9, + "learning_rate": 5.148095120914521e-06, + "loss": 0.0941, + "step": 402160 + }, + { + "epoch": 0.9, + "learning_rate": 5.1469765777051965e-06, + "loss": 0.0924, + "step": 402170 + }, + { + "epoch": 0.9, + "learning_rate": 5.145858034495873e-06, + "loss": 0.0958, + "step": 402180 + }, + { + "epoch": 0.9, + "learning_rate": 5.144739491286549e-06, + "loss": 0.0912, + "step": 402190 + }, + { + "epoch": 0.9, + "learning_rate": 5.143620948077224e-06, + "loss": 0.095, + "step": 402200 + }, + { + "epoch": 0.9, + "learning_rate": 5.1425024048679e-06, + "loss": 0.0959, + "step": 402210 + }, + { + "epoch": 0.9, + "learning_rate": 5.141383861658576e-06, + "loss": 0.0914, + "step": 402220 + }, + { + "epoch": 0.9, + "learning_rate": 5.140265318449252e-06, + "loss": 0.091, + "step": 402230 + }, + { + "epoch": 0.9, + "learning_rate": 5.1391467752399284e-06, + "loss": 0.0973, + "step": 402240 + }, + { + "epoch": 0.9, + "learning_rate": 5.138028232030603e-06, + "loss": 0.0953, + "step": 402250 + }, + { + "epoch": 0.9, + "learning_rate": 5.136909688821279e-06, + "loss": 0.0938, + "step": 402260 + }, + { + "epoch": 0.9, + "learning_rate": 5.1357911456119555e-06, + "loss": 0.1014, + "step": 402270 + }, + { + "epoch": 0.9, + "learning_rate": 5.134672602402632e-06, + "loss": 0.0952, + "step": 402280 + }, + { + "epoch": 0.9, + "learning_rate": 5.133554059193306e-06, + "loss": 0.0927, + "step": 402290 + }, + { + "epoch": 0.9, + "learning_rate": 5.1324355159839825e-06, + "loss": 0.0927, + "step": 402300 + }, + { + "epoch": 0.9, + "learning_rate": 5.131316972774659e-06, + "loss": 0.0933, + "step": 402310 + }, + { + "epoch": 0.9, + "learning_rate": 5.130198429565335e-06, + "loss": 0.1004, + "step": 402320 + }, + { + "epoch": 0.9, + "learning_rate": 5.12907988635601e-06, + "loss": 0.0927, + "step": 402330 + }, + { + "epoch": 0.9, + "learning_rate": 5.127961343146686e-06, + "loss": 0.0946, + "step": 402340 + }, + { + "epoch": 0.9, + "learning_rate": 5.126842799937362e-06, + "loss": 0.0941, + "step": 402350 + }, + { + "epoch": 0.9, + "learning_rate": 5.125724256728038e-06, + "loss": 0.0918, + "step": 402360 + }, + { + "epoch": 0.9, + "learning_rate": 5.1246057135187136e-06, + "loss": 0.0978, + "step": 402370 + }, + { + "epoch": 0.9, + "learning_rate": 5.123487170309389e-06, + "loss": 0.0908, + "step": 402380 + }, + { + "epoch": 0.9, + "learning_rate": 5.122368627100065e-06, + "loss": 0.0965, + "step": 402390 + }, + { + "epoch": 0.9, + "learning_rate": 5.121250083890741e-06, + "loss": 0.0902, + "step": 402400 + }, + { + "epoch": 0.9, + "learning_rate": 5.120131540681417e-06, + "loss": 0.0942, + "step": 402410 + }, + { + "epoch": 0.9, + "learning_rate": 5.119012997472092e-06, + "loss": 0.0921, + "step": 402420 + }, + { + "epoch": 0.9, + "learning_rate": 5.117894454262768e-06, + "loss": 0.0965, + "step": 402430 + }, + { + "epoch": 0.9, + "learning_rate": 5.116775911053445e-06, + "loss": 0.0935, + "step": 402440 + }, + { + "epoch": 0.9, + "learning_rate": 5.11565736784412e-06, + "loss": 0.0932, + "step": 402450 + }, + { + "epoch": 0.9, + "learning_rate": 5.114538824634795e-06, + "loss": 0.0961, + "step": 402460 + }, + { + "epoch": 0.9, + "learning_rate": 5.113420281425472e-06, + "loss": 0.0934, + "step": 402470 + }, + { + "epoch": 0.9, + "learning_rate": 5.112301738216148e-06, + "loss": 0.0965, + "step": 402480 + }, + { + "epoch": 0.9, + "learning_rate": 5.111183195006823e-06, + "loss": 0.0938, + "step": 402490 + }, + { + "epoch": 0.9, + "learning_rate": 5.1100646517974995e-06, + "loss": 0.0897, + "step": 402500 + }, + { + "epoch": 0.9, + "learning_rate": 5.108946108588175e-06, + "loss": 0.0939, + "step": 402510 + }, + { + "epoch": 0.9, + "learning_rate": 5.107827565378851e-06, + "loss": 0.0931, + "step": 402520 + }, + { + "epoch": 0.9, + "learning_rate": 5.1067090221695265e-06, + "loss": 0.0916, + "step": 402530 + }, + { + "epoch": 0.9, + "learning_rate": 5.105590478960203e-06, + "loss": 0.0912, + "step": 402540 + }, + { + "epoch": 0.9, + "learning_rate": 5.104471935750878e-06, + "loss": 0.0896, + "step": 402550 + }, + { + "epoch": 0.9, + "learning_rate": 5.103353392541554e-06, + "loss": 0.0903, + "step": 402560 + }, + { + "epoch": 0.9, + "learning_rate": 5.10223484933223e-06, + "loss": 0.0876, + "step": 402570 + }, + { + "epoch": 0.9, + "learning_rate": 5.101116306122906e-06, + "loss": 0.0959, + "step": 402580 + }, + { + "epoch": 0.9, + "learning_rate": 5.099997762913581e-06, + "loss": 0.0938, + "step": 402590 + }, + { + "epoch": 0.9, + "learning_rate": 5.098879219704258e-06, + "loss": 0.095, + "step": 402600 + }, + { + "epoch": 0.9, + "learning_rate": 5.097760676494933e-06, + "loss": 0.0968, + "step": 402610 + }, + { + "epoch": 0.9, + "learning_rate": 5.096642133285609e-06, + "loss": 0.0943, + "step": 402620 + }, + { + "epoch": 0.9, + "learning_rate": 5.095523590076285e-06, + "loss": 0.0938, + "step": 402630 + }, + { + "epoch": 0.9, + "learning_rate": 5.094405046866961e-06, + "loss": 0.0915, + "step": 402640 + }, + { + "epoch": 0.9, + "learning_rate": 5.093286503657636e-06, + "loss": 0.0918, + "step": 402650 + }, + { + "epoch": 0.9, + "learning_rate": 5.0921679604483125e-06, + "loss": 0.091, + "step": 402660 + }, + { + "epoch": 0.9, + "learning_rate": 5.091049417238989e-06, + "loss": 0.0946, + "step": 402670 + }, + { + "epoch": 0.9, + "learning_rate": 5.089930874029664e-06, + "loss": 0.0958, + "step": 402680 + }, + { + "epoch": 0.9, + "learning_rate": 5.0888123308203395e-06, + "loss": 0.0926, + "step": 402690 + }, + { + "epoch": 0.9, + "learning_rate": 5.087693787611016e-06, + "loss": 0.0932, + "step": 402700 + }, + { + "epoch": 0.9, + "learning_rate": 5.086575244401692e-06, + "loss": 0.092, + "step": 402710 + }, + { + "epoch": 0.9, + "learning_rate": 5.085456701192367e-06, + "loss": 0.0938, + "step": 402720 + }, + { + "epoch": 0.9, + "learning_rate": 5.084338157983043e-06, + "loss": 0.0935, + "step": 402730 + }, + { + "epoch": 0.9, + "learning_rate": 5.083219614773719e-06, + "loss": 0.0945, + "step": 402740 + }, + { + "epoch": 0.9, + "learning_rate": 5.082101071564395e-06, + "loss": 0.0998, + "step": 402750 + }, + { + "epoch": 0.9, + "learning_rate": 5.0809825283550706e-06, + "loss": 0.0904, + "step": 402760 + }, + { + "epoch": 0.9, + "learning_rate": 5.079863985145746e-06, + "loss": 0.0984, + "step": 402770 + }, + { + "epoch": 0.9, + "learning_rate": 5.078745441936422e-06, + "loss": 0.095, + "step": 402780 + }, + { + "epoch": 0.9, + "learning_rate": 5.0776268987270984e-06, + "loss": 0.0964, + "step": 402790 + }, + { + "epoch": 0.9, + "learning_rate": 5.076508355517774e-06, + "loss": 0.0912, + "step": 402800 + }, + { + "epoch": 0.9, + "learning_rate": 5.075389812308449e-06, + "loss": 0.0934, + "step": 402810 + }, + { + "epoch": 0.9, + "learning_rate": 5.0742712690991254e-06, + "loss": 0.0926, + "step": 402820 + }, + { + "epoch": 0.9, + "learning_rate": 5.073152725889802e-06, + "loss": 0.0966, + "step": 402830 + }, + { + "epoch": 0.9, + "learning_rate": 5.072034182680478e-06, + "loss": 0.0933, + "step": 402840 + }, + { + "epoch": 0.9, + "learning_rate": 5.0709156394711524e-06, + "loss": 0.0925, + "step": 402850 + }, + { + "epoch": 0.9, + "learning_rate": 5.069797096261829e-06, + "loss": 0.0929, + "step": 402860 + }, + { + "epoch": 0.9, + "learning_rate": 5.068678553052505e-06, + "loss": 0.0911, + "step": 402870 + }, + { + "epoch": 0.9, + "learning_rate": 5.067560009843181e-06, + "loss": 0.0905, + "step": 402880 + }, + { + "epoch": 0.9, + "learning_rate": 5.0664414666338565e-06, + "loss": 0.093, + "step": 402890 + }, + { + "epoch": 0.9, + "learning_rate": 5.065322923424532e-06, + "loss": 0.0902, + "step": 402900 + }, + { + "epoch": 0.9, + "learning_rate": 5.064204380215208e-06, + "loss": 0.0941, + "step": 402910 + }, + { + "epoch": 0.9, + "learning_rate": 5.063085837005884e-06, + "loss": 0.0896, + "step": 402920 + }, + { + "epoch": 0.9, + "learning_rate": 5.06196729379656e-06, + "loss": 0.0962, + "step": 402930 + }, + { + "epoch": 0.9, + "learning_rate": 5.060848750587235e-06, + "loss": 0.0981, + "step": 402940 + }, + { + "epoch": 0.9, + "learning_rate": 5.059730207377911e-06, + "loss": 0.0915, + "step": 402950 + }, + { + "epoch": 0.9, + "learning_rate": 5.058611664168588e-06, + "loss": 0.0939, + "step": 402960 + }, + { + "epoch": 0.9, + "learning_rate": 5.057493120959263e-06, + "loss": 0.0961, + "step": 402970 + }, + { + "epoch": 0.9, + "learning_rate": 5.056374577749938e-06, + "loss": 0.0951, + "step": 402980 + }, + { + "epoch": 0.9, + "learning_rate": 5.055256034540615e-06, + "loss": 0.0947, + "step": 402990 + }, + { + "epoch": 0.9, + "learning_rate": 5.054137491331291e-06, + "loss": 0.0897, + "step": 403000 + }, + { + "epoch": 0.9, + "learning_rate": 5.053018948121966e-06, + "loss": 0.0963, + "step": 403010 + }, + { + "epoch": 0.9, + "learning_rate": 5.051900404912642e-06, + "loss": 0.095, + "step": 403020 + }, + { + "epoch": 0.9, + "learning_rate": 5.050781861703318e-06, + "loss": 0.0968, + "step": 403030 + }, + { + "epoch": 0.9, + "learning_rate": 5.049663318493994e-06, + "loss": 0.0971, + "step": 403040 + }, + { + "epoch": 0.9, + "learning_rate": 5.0485447752846695e-06, + "loss": 0.0962, + "step": 403050 + }, + { + "epoch": 0.9, + "learning_rate": 5.047426232075345e-06, + "loss": 0.0925, + "step": 403060 + }, + { + "epoch": 0.9, + "learning_rate": 5.046307688866021e-06, + "loss": 0.0936, + "step": 403070 + }, + { + "epoch": 0.9, + "learning_rate": 5.045189145656697e-06, + "loss": 0.1006, + "step": 403080 + }, + { + "epoch": 0.9, + "learning_rate": 5.044070602447373e-06, + "loss": 0.0925, + "step": 403090 + }, + { + "epoch": 0.9, + "learning_rate": 5.042952059238049e-06, + "loss": 0.0995, + "step": 403100 + }, + { + "epoch": 0.9, + "learning_rate": 5.041833516028724e-06, + "loss": 0.0897, + "step": 403110 + }, + { + "epoch": 0.9, + "learning_rate": 5.040714972819401e-06, + "loss": 0.0977, + "step": 403120 + }, + { + "epoch": 0.9, + "learning_rate": 5.039596429610076e-06, + "loss": 0.0972, + "step": 403130 + }, + { + "epoch": 0.9, + "learning_rate": 5.038477886400752e-06, + "loss": 0.0965, + "step": 403140 + }, + { + "epoch": 0.9, + "learning_rate": 5.037359343191428e-06, + "loss": 0.0922, + "step": 403150 + }, + { + "epoch": 0.9, + "learning_rate": 5.036240799982104e-06, + "loss": 0.0917, + "step": 403160 + }, + { + "epoch": 0.9, + "learning_rate": 5.035122256772779e-06, + "loss": 0.0927, + "step": 403170 + }, + { + "epoch": 0.9, + "learning_rate": 5.0340037135634554e-06, + "loss": 0.0941, + "step": 403180 + }, + { + "epoch": 0.9, + "learning_rate": 5.032885170354131e-06, + "loss": 0.0898, + "step": 403190 + }, + { + "epoch": 0.9, + "learning_rate": 5.031766627144807e-06, + "loss": 0.0926, + "step": 403200 + }, + { + "epoch": 0.9, + "learning_rate": 5.0306480839354824e-06, + "loss": 0.0934, + "step": 403210 + }, + { + "epoch": 0.9, + "learning_rate": 5.029529540726159e-06, + "loss": 0.0919, + "step": 403220 + }, + { + "epoch": 0.9, + "learning_rate": 5.028410997516834e-06, + "loss": 0.0904, + "step": 403230 + }, + { + "epoch": 0.9, + "learning_rate": 5.02729245430751e-06, + "loss": 0.0939, + "step": 403240 + }, + { + "epoch": 0.9, + "learning_rate": 5.026173911098186e-06, + "loss": 0.0934, + "step": 403250 + }, + { + "epoch": 0.9, + "learning_rate": 5.025055367888862e-06, + "loss": 0.0938, + "step": 403260 + }, + { + "epoch": 0.9, + "learning_rate": 5.023936824679538e-06, + "loss": 0.0912, + "step": 403270 + }, + { + "epoch": 0.9, + "learning_rate": 5.0228182814702135e-06, + "loss": 0.0979, + "step": 403280 + }, + { + "epoch": 0.9, + "learning_rate": 5.021699738260889e-06, + "loss": 0.0924, + "step": 403290 + }, + { + "epoch": 0.9, + "learning_rate": 5.020581195051565e-06, + "loss": 0.0961, + "step": 403300 + }, + { + "epoch": 0.9, + "learning_rate": 5.019462651842241e-06, + "loss": 0.0971, + "step": 403310 + }, + { + "epoch": 0.9, + "learning_rate": 5.018344108632917e-06, + "loss": 0.095, + "step": 403320 + }, + { + "epoch": 0.9, + "learning_rate": 5.017225565423592e-06, + "loss": 0.0927, + "step": 403330 + }, + { + "epoch": 0.9, + "learning_rate": 5.016107022214268e-06, + "loss": 0.0981, + "step": 403340 + }, + { + "epoch": 0.9, + "learning_rate": 5.014988479004945e-06, + "loss": 0.0993, + "step": 403350 + }, + { + "epoch": 0.9, + "learning_rate": 5.01386993579562e-06, + "loss": 0.0897, + "step": 403360 + }, + { + "epoch": 0.9, + "learning_rate": 5.012751392586295e-06, + "loss": 0.0953, + "step": 403370 + }, + { + "epoch": 0.9, + "learning_rate": 5.011632849376972e-06, + "loss": 0.0948, + "step": 403380 + }, + { + "epoch": 0.9, + "learning_rate": 5.010514306167648e-06, + "loss": 0.0962, + "step": 403390 + }, + { + "epoch": 0.9, + "learning_rate": 5.009395762958323e-06, + "loss": 0.0961, + "step": 403400 + }, + { + "epoch": 0.9, + "learning_rate": 5.008277219748999e-06, + "loss": 0.0947, + "step": 403410 + }, + { + "epoch": 0.9, + "learning_rate": 5.007158676539675e-06, + "loss": 0.0901, + "step": 403420 + }, + { + "epoch": 0.9, + "learning_rate": 5.006040133330351e-06, + "loss": 0.0929, + "step": 403430 + }, + { + "epoch": 0.9, + "learning_rate": 5.004921590121027e-06, + "loss": 0.0968, + "step": 403440 + }, + { + "epoch": 0.9, + "learning_rate": 5.003803046911702e-06, + "loss": 0.0967, + "step": 403450 + }, + { + "epoch": 0.9, + "learning_rate": 5.002684503702378e-06, + "loss": 0.0915, + "step": 403460 + }, + { + "epoch": 0.9, + "learning_rate": 5.001565960493054e-06, + "loss": 0.0922, + "step": 403470 + }, + { + "epoch": 0.9, + "learning_rate": 5.000447417283731e-06, + "loss": 0.0957, + "step": 403480 + }, + { + "epoch": 0.9, + "learning_rate": 4.999328874074406e-06, + "loss": 0.0934, + "step": 403490 + }, + { + "epoch": 0.9, + "learning_rate": 4.998210330865081e-06, + "loss": 0.0952, + "step": 403500 + }, + { + "epoch": 0.9, + "learning_rate": 4.997091787655758e-06, + "loss": 0.0945, + "step": 403510 + }, + { + "epoch": 0.9, + "learning_rate": 4.995973244446433e-06, + "loss": 0.0968, + "step": 403520 + }, + { + "epoch": 0.9, + "learning_rate": 4.994854701237109e-06, + "loss": 0.0935, + "step": 403530 + }, + { + "epoch": 0.9, + "learning_rate": 4.993736158027785e-06, + "loss": 0.0942, + "step": 403540 + }, + { + "epoch": 0.9, + "learning_rate": 4.992617614818461e-06, + "loss": 0.0918, + "step": 403550 + }, + { + "epoch": 0.9, + "learning_rate": 4.991499071609136e-06, + "loss": 0.0928, + "step": 403560 + }, + { + "epoch": 0.9, + "learning_rate": 4.9903805283998125e-06, + "loss": 0.0936, + "step": 403570 + }, + { + "epoch": 0.9, + "learning_rate": 4.989261985190488e-06, + "loss": 0.0962, + "step": 403580 + }, + { + "epoch": 0.9, + "learning_rate": 4.988143441981164e-06, + "loss": 0.0955, + "step": 403590 + }, + { + "epoch": 0.9, + "learning_rate": 4.9870248987718395e-06, + "loss": 0.0952, + "step": 403600 + }, + { + "epoch": 0.9, + "learning_rate": 4.985906355562516e-06, + "loss": 0.0945, + "step": 403610 + }, + { + "epoch": 0.9, + "learning_rate": 4.984787812353191e-06, + "loss": 0.0951, + "step": 403620 + }, + { + "epoch": 0.9, + "learning_rate": 4.983669269143867e-06, + "loss": 0.0919, + "step": 403630 + }, + { + "epoch": 0.9, + "learning_rate": 4.982550725934543e-06, + "loss": 0.0943, + "step": 403640 + }, + { + "epoch": 0.9, + "learning_rate": 4.981432182725219e-06, + "loss": 0.0915, + "step": 403650 + }, + { + "epoch": 0.9, + "learning_rate": 4.980313639515894e-06, + "loss": 0.0929, + "step": 403660 + }, + { + "epoch": 0.9, + "learning_rate": 4.9791950963065706e-06, + "loss": 0.093, + "step": 403670 + }, + { + "epoch": 0.9, + "learning_rate": 4.978076553097246e-06, + "loss": 0.0934, + "step": 403680 + }, + { + "epoch": 0.9, + "learning_rate": 4.976958009887922e-06, + "loss": 0.0927, + "step": 403690 + }, + { + "epoch": 0.9, + "learning_rate": 4.975839466678598e-06, + "loss": 0.0952, + "step": 403700 + }, + { + "epoch": 0.9, + "learning_rate": 4.974720923469274e-06, + "loss": 0.0961, + "step": 403710 + }, + { + "epoch": 0.9, + "learning_rate": 4.973602380259949e-06, + "loss": 0.091, + "step": 403720 + }, + { + "epoch": 0.9, + "learning_rate": 4.972483837050625e-06, + "loss": 0.0939, + "step": 403730 + }, + { + "epoch": 0.9, + "learning_rate": 4.971477148162234e-06, + "loss": 0.0954, + "step": 403740 + }, + { + "epoch": 0.9, + "learning_rate": 4.97035860495291e-06, + "loss": 0.0936, + "step": 403750 + }, + { + "epoch": 0.9, + "learning_rate": 4.969240061743585e-06, + "loss": 0.0916, + "step": 403760 + }, + { + "epoch": 0.9, + "learning_rate": 4.968121518534261e-06, + "loss": 0.093, + "step": 403770 + }, + { + "epoch": 0.9, + "learning_rate": 4.9670029753249374e-06, + "loss": 0.0958, + "step": 403780 + }, + { + "epoch": 0.9, + "learning_rate": 4.965884432115613e-06, + "loss": 0.0928, + "step": 403790 + }, + { + "epoch": 0.9, + "learning_rate": 4.964765888906288e-06, + "loss": 0.0931, + "step": 403800 + }, + { + "epoch": 0.9, + "learning_rate": 4.9636473456969644e-06, + "loss": 0.0894, + "step": 403810 + }, + { + "epoch": 0.9, + "learning_rate": 4.962528802487641e-06, + "loss": 0.093, + "step": 403820 + }, + { + "epoch": 0.9, + "learning_rate": 4.961410259278316e-06, + "loss": 0.0926, + "step": 403830 + }, + { + "epoch": 0.9, + "learning_rate": 4.9602917160689915e-06, + "loss": 0.0954, + "step": 403840 + }, + { + "epoch": 0.9, + "learning_rate": 4.959173172859668e-06, + "loss": 0.0925, + "step": 403850 + }, + { + "epoch": 0.9, + "learning_rate": 4.958054629650344e-06, + "loss": 0.0955, + "step": 403860 + }, + { + "epoch": 0.9, + "learning_rate": 4.956936086441019e-06, + "loss": 0.0986, + "step": 403870 + }, + { + "epoch": 0.9, + "learning_rate": 4.9558175432316955e-06, + "loss": 0.0954, + "step": 403880 + }, + { + "epoch": 0.9, + "learning_rate": 4.954699000022371e-06, + "loss": 0.0929, + "step": 403890 + }, + { + "epoch": 0.9, + "learning_rate": 4.953580456813047e-06, + "loss": 0.0943, + "step": 403900 + }, + { + "epoch": 0.9, + "learning_rate": 4.9524619136037226e-06, + "loss": 0.0923, + "step": 403910 + }, + { + "epoch": 0.9, + "learning_rate": 4.951343370394399e-06, + "loss": 0.0955, + "step": 403920 + }, + { + "epoch": 0.9, + "learning_rate": 4.950224827185074e-06, + "loss": 0.0914, + "step": 403930 + }, + { + "epoch": 0.9, + "learning_rate": 4.94910628397575e-06, + "loss": 0.0958, + "step": 403940 + }, + { + "epoch": 0.9, + "learning_rate": 4.947987740766426e-06, + "loss": 0.0951, + "step": 403950 + }, + { + "epoch": 0.9, + "learning_rate": 4.946869197557102e-06, + "loss": 0.0909, + "step": 403960 + }, + { + "epoch": 0.9, + "learning_rate": 4.945750654347777e-06, + "loss": 0.092, + "step": 403970 + }, + { + "epoch": 0.9, + "learning_rate": 4.944632111138454e-06, + "loss": 0.0922, + "step": 403980 + }, + { + "epoch": 0.9, + "learning_rate": 4.943513567929129e-06, + "loss": 0.091, + "step": 403990 + }, + { + "epoch": 0.9, + "learning_rate": 4.942395024719805e-06, + "loss": 0.0941, + "step": 404000 + }, + { + "epoch": 0.9, + "learning_rate": 4.941276481510481e-06, + "loss": 0.091, + "step": 404010 + }, + { + "epoch": 0.9, + "learning_rate": 4.940157938301157e-06, + "loss": 0.099, + "step": 404020 + }, + { + "epoch": 0.9, + "learning_rate": 4.939039395091832e-06, + "loss": 0.0953, + "step": 404030 + }, + { + "epoch": 0.9, + "learning_rate": 4.9379208518825085e-06, + "loss": 0.0975, + "step": 404040 + }, + { + "epoch": 0.9, + "learning_rate": 4.936802308673185e-06, + "loss": 0.094, + "step": 404050 + }, + { + "epoch": 0.9, + "learning_rate": 4.93568376546386e-06, + "loss": 0.0934, + "step": 404060 + }, + { + "epoch": 0.9, + "learning_rate": 4.9345652222545355e-06, + "loss": 0.0924, + "step": 404070 + }, + { + "epoch": 0.9, + "learning_rate": 4.933446679045212e-06, + "loss": 0.0938, + "step": 404080 + }, + { + "epoch": 0.9, + "learning_rate": 4.932328135835888e-06, + "loss": 0.0937, + "step": 404090 + }, + { + "epoch": 0.9, + "learning_rate": 4.931209592626563e-06, + "loss": 0.093, + "step": 404100 + }, + { + "epoch": 0.9, + "learning_rate": 4.930091049417239e-06, + "loss": 0.0957, + "step": 404110 + }, + { + "epoch": 0.9, + "learning_rate": 4.928972506207915e-06, + "loss": 0.0937, + "step": 404120 + }, + { + "epoch": 0.9, + "learning_rate": 4.927853962998591e-06, + "loss": 0.0952, + "step": 404130 + }, + { + "epoch": 0.9, + "learning_rate": 4.926735419789267e-06, + "loss": 0.0946, + "step": 404140 + }, + { + "epoch": 0.9, + "learning_rate": 4.925616876579942e-06, + "loss": 0.0904, + "step": 404150 + }, + { + "epoch": 0.9, + "learning_rate": 4.924498333370618e-06, + "loss": 0.093, + "step": 404160 + }, + { + "epoch": 0.9, + "learning_rate": 4.9233797901612945e-06, + "loss": 0.0938, + "step": 404170 + }, + { + "epoch": 0.9, + "learning_rate": 4.92226124695197e-06, + "loss": 0.0917, + "step": 404180 + }, + { + "epoch": 0.9, + "learning_rate": 4.921142703742645e-06, + "loss": 0.0941, + "step": 404190 + }, + { + "epoch": 0.9, + "learning_rate": 4.9200241605333215e-06, + "loss": 0.0902, + "step": 404200 + }, + { + "epoch": 0.9, + "learning_rate": 4.918905617323998e-06, + "loss": 0.0961, + "step": 404210 + }, + { + "epoch": 0.9, + "learning_rate": 4.917787074114674e-06, + "loss": 0.0926, + "step": 404220 + }, + { + "epoch": 0.9, + "learning_rate": 4.9166685309053485e-06, + "loss": 0.0917, + "step": 404230 + }, + { + "epoch": 0.9, + "learning_rate": 4.915549987696025e-06, + "loss": 0.0942, + "step": 404240 + }, + { + "epoch": 0.9, + "learning_rate": 4.914431444486701e-06, + "loss": 0.0949, + "step": 404250 + }, + { + "epoch": 0.9, + "learning_rate": 4.913312901277377e-06, + "loss": 0.0948, + "step": 404260 + }, + { + "epoch": 0.9, + "learning_rate": 4.912194358068052e-06, + "loss": 0.0938, + "step": 404270 + }, + { + "epoch": 0.9, + "learning_rate": 4.911075814858728e-06, + "loss": 0.0939, + "step": 404280 + }, + { + "epoch": 0.9, + "learning_rate": 4.909957271649404e-06, + "loss": 0.0951, + "step": 404290 + }, + { + "epoch": 0.9, + "learning_rate": 4.90883872844008e-06, + "loss": 0.0928, + "step": 404300 + }, + { + "epoch": 0.9, + "learning_rate": 4.907720185230756e-06, + "loss": 0.0952, + "step": 404310 + }, + { + "epoch": 0.9, + "learning_rate": 4.906601642021431e-06, + "loss": 0.0939, + "step": 404320 + }, + { + "epoch": 0.9, + "learning_rate": 4.905483098812107e-06, + "loss": 0.0939, + "step": 404330 + }, + { + "epoch": 0.9, + "learning_rate": 4.904364555602784e-06, + "loss": 0.0953, + "step": 404340 + }, + { + "epoch": 0.9, + "learning_rate": 4.903246012393459e-06, + "loss": 0.0956, + "step": 404350 + }, + { + "epoch": 0.9, + "learning_rate": 4.9021274691841344e-06, + "loss": 0.0903, + "step": 404360 + }, + { + "epoch": 0.9, + "learning_rate": 4.901008925974811e-06, + "loss": 0.0945, + "step": 404370 + }, + { + "epoch": 0.9, + "learning_rate": 4.899890382765487e-06, + "loss": 0.0916, + "step": 404380 + }, + { + "epoch": 0.9, + "learning_rate": 4.898771839556162e-06, + "loss": 0.0923, + "step": 404390 + }, + { + "epoch": 0.9, + "learning_rate": 4.897653296346838e-06, + "loss": 0.094, + "step": 404400 + }, + { + "epoch": 0.9, + "learning_rate": 4.896534753137514e-06, + "loss": 0.093, + "step": 404410 + }, + { + "epoch": 0.9, + "learning_rate": 4.89541620992819e-06, + "loss": 0.0951, + "step": 404420 + }, + { + "epoch": 0.9, + "learning_rate": 4.8942976667188655e-06, + "loss": 0.0919, + "step": 404430 + }, + { + "epoch": 0.9, + "learning_rate": 4.893179123509541e-06, + "loss": 0.0907, + "step": 404440 + }, + { + "epoch": 0.9, + "learning_rate": 4.892060580300217e-06, + "loss": 0.0937, + "step": 404450 + }, + { + "epoch": 0.9, + "learning_rate": 4.890942037090893e-06, + "loss": 0.0937, + "step": 404460 + }, + { + "epoch": 0.9, + "learning_rate": 4.889823493881569e-06, + "loss": 0.0944, + "step": 404470 + }, + { + "epoch": 0.9, + "learning_rate": 4.888704950672245e-06, + "loss": 0.0916, + "step": 404480 + }, + { + "epoch": 0.9, + "learning_rate": 4.88758640746292e-06, + "loss": 0.0887, + "step": 404490 + }, + { + "epoch": 0.9, + "learning_rate": 4.886467864253597e-06, + "loss": 0.0945, + "step": 404500 + }, + { + "epoch": 0.9, + "learning_rate": 4.885349321044272e-06, + "loss": 0.0943, + "step": 404510 + }, + { + "epoch": 0.9, + "learning_rate": 4.884230777834948e-06, + "loss": 0.096, + "step": 404520 + }, + { + "epoch": 0.9, + "learning_rate": 4.883112234625624e-06, + "loss": 0.094, + "step": 404530 + }, + { + "epoch": 0.9, + "learning_rate": 4.8819936914163e-06, + "loss": 0.0927, + "step": 404540 + }, + { + "epoch": 0.9, + "learning_rate": 4.880875148206975e-06, + "loss": 0.0957, + "step": 404550 + }, + { + "epoch": 0.9, + "learning_rate": 4.8797566049976515e-06, + "loss": 0.094, + "step": 404560 + }, + { + "epoch": 0.9, + "learning_rate": 4.878638061788327e-06, + "loss": 0.0966, + "step": 404570 + }, + { + "epoch": 0.9, + "learning_rate": 4.877519518579003e-06, + "loss": 0.0978, + "step": 404580 + }, + { + "epoch": 0.9, + "learning_rate": 4.8764009753696785e-06, + "loss": 0.0899, + "step": 404590 + }, + { + "epoch": 0.9, + "learning_rate": 4.875282432160355e-06, + "loss": 0.0954, + "step": 404600 + }, + { + "epoch": 0.9, + "learning_rate": 4.87416388895103e-06, + "loss": 0.0947, + "step": 404610 + }, + { + "epoch": 0.9, + "learning_rate": 4.873045345741706e-06, + "loss": 0.0919, + "step": 404620 + }, + { + "epoch": 0.9, + "learning_rate": 4.871926802532382e-06, + "loss": 0.088, + "step": 404630 + }, + { + "epoch": 0.9, + "learning_rate": 4.870808259323058e-06, + "loss": 0.0949, + "step": 404640 + }, + { + "epoch": 0.9, + "learning_rate": 4.869689716113734e-06, + "loss": 0.093, + "step": 404650 + }, + { + "epoch": 0.9, + "learning_rate": 4.86857117290441e-06, + "loss": 0.0917, + "step": 404660 + }, + { + "epoch": 0.9, + "learning_rate": 4.867452629695085e-06, + "loss": 0.0941, + "step": 404670 + }, + { + "epoch": 0.9, + "learning_rate": 4.866334086485761e-06, + "loss": 0.0904, + "step": 404680 + }, + { + "epoch": 0.9, + "learning_rate": 4.8652155432764374e-06, + "loss": 0.0939, + "step": 404690 + }, + { + "epoch": 0.9, + "learning_rate": 4.864097000067113e-06, + "loss": 0.0925, + "step": 404700 + }, + { + "epoch": 0.9, + "learning_rate": 4.862978456857788e-06, + "loss": 0.0955, + "step": 404710 + }, + { + "epoch": 0.9, + "learning_rate": 4.8618599136484644e-06, + "loss": 0.0932, + "step": 404720 + }, + { + "epoch": 0.9, + "learning_rate": 4.860741370439141e-06, + "loss": 0.0988, + "step": 404730 + }, + { + "epoch": 0.9, + "learning_rate": 4.859622827229816e-06, + "loss": 0.096, + "step": 404740 + }, + { + "epoch": 0.9, + "learning_rate": 4.8585042840204914e-06, + "loss": 0.0941, + "step": 404750 + }, + { + "epoch": 0.9, + "learning_rate": 4.857385740811168e-06, + "loss": 0.0902, + "step": 404760 + }, + { + "epoch": 0.9, + "learning_rate": 4.856267197601844e-06, + "loss": 0.0923, + "step": 404770 + }, + { + "epoch": 0.9, + "learning_rate": 4.855148654392519e-06, + "loss": 0.0968, + "step": 404780 + }, + { + "epoch": 0.9, + "learning_rate": 4.854030111183195e-06, + "loss": 0.0944, + "step": 404790 + }, + { + "epoch": 0.9, + "learning_rate": 4.852911567973871e-06, + "loss": 0.0968, + "step": 404800 + }, + { + "epoch": 0.9, + "learning_rate": 4.851793024764547e-06, + "loss": 0.0934, + "step": 404810 + }, + { + "epoch": 0.9, + "learning_rate": 4.850674481555223e-06, + "loss": 0.0882, + "step": 404820 + }, + { + "epoch": 0.9, + "learning_rate": 4.849555938345898e-06, + "loss": 0.0948, + "step": 404830 + }, + { + "epoch": 0.9, + "learning_rate": 4.848437395136574e-06, + "loss": 0.0918, + "step": 404840 + }, + { + "epoch": 0.9, + "learning_rate": 4.84731885192725e-06, + "loss": 0.0949, + "step": 404850 + }, + { + "epoch": 0.9, + "learning_rate": 4.846200308717927e-06, + "loss": 0.0912, + "step": 404860 + }, + { + "epoch": 0.9, + "learning_rate": 4.845081765508601e-06, + "loss": 0.0971, + "step": 404870 + }, + { + "epoch": 0.9, + "learning_rate": 4.843963222299277e-06, + "loss": 0.0926, + "step": 404880 + }, + { + "epoch": 0.9, + "learning_rate": 4.842844679089954e-06, + "loss": 0.0921, + "step": 404890 + }, + { + "epoch": 0.9, + "learning_rate": 4.84172613588063e-06, + "loss": 0.0932, + "step": 404900 + }, + { + "epoch": 0.9, + "learning_rate": 4.840607592671305e-06, + "loss": 0.0905, + "step": 404910 + }, + { + "epoch": 0.9, + "learning_rate": 4.839489049461981e-06, + "loss": 0.095, + "step": 404920 + }, + { + "epoch": 0.9, + "learning_rate": 4.838370506252657e-06, + "loss": 0.0928, + "step": 404930 + }, + { + "epoch": 0.9, + "learning_rate": 4.837251963043333e-06, + "loss": 0.0935, + "step": 404940 + }, + { + "epoch": 0.9, + "learning_rate": 4.8361334198340085e-06, + "loss": 0.0878, + "step": 404950 + }, + { + "epoch": 0.9, + "learning_rate": 4.835014876624684e-06, + "loss": 0.0953, + "step": 404960 + }, + { + "epoch": 0.9, + "learning_rate": 4.83389633341536e-06, + "loss": 0.0952, + "step": 404970 + }, + { + "epoch": 0.9, + "learning_rate": 4.832777790206036e-06, + "loss": 0.0895, + "step": 404980 + }, + { + "epoch": 0.9, + "learning_rate": 4.831659246996712e-06, + "loss": 0.0966, + "step": 404990 + }, + { + "epoch": 0.9, + "learning_rate": 4.830540703787387e-06, + "loss": 0.0919, + "step": 405000 + }, + { + "epoch": 0.9, + "learning_rate": 4.829422160578063e-06, + "loss": 0.0922, + "step": 405010 + }, + { + "epoch": 0.9, + "learning_rate": 4.82830361736874e-06, + "loss": 0.0972, + "step": 405020 + }, + { + "epoch": 0.9, + "learning_rate": 4.827185074159415e-06, + "loss": 0.0911, + "step": 405030 + }, + { + "epoch": 0.9, + "learning_rate": 4.82606653095009e-06, + "loss": 0.0935, + "step": 405040 + }, + { + "epoch": 0.9, + "learning_rate": 4.824947987740767e-06, + "loss": 0.0936, + "step": 405050 + }, + { + "epoch": 0.9, + "learning_rate": 4.823829444531443e-06, + "loss": 0.0978, + "step": 405060 + }, + { + "epoch": 0.9, + "learning_rate": 4.822710901322118e-06, + "loss": 0.0924, + "step": 405070 + }, + { + "epoch": 0.9, + "learning_rate": 4.8215923581127944e-06, + "loss": 0.095, + "step": 405080 + }, + { + "epoch": 0.9, + "learning_rate": 4.82047381490347e-06, + "loss": 0.0953, + "step": 405090 + }, + { + "epoch": 0.9, + "learning_rate": 4.819355271694146e-06, + "loss": 0.0959, + "step": 405100 + }, + { + "epoch": 0.9, + "learning_rate": 4.8182367284848215e-06, + "loss": 0.0964, + "step": 405110 + }, + { + "epoch": 0.9, + "learning_rate": 4.817118185275498e-06, + "loss": 0.0967, + "step": 405120 + }, + { + "epoch": 0.9, + "learning_rate": 4.815999642066173e-06, + "loss": 0.0928, + "step": 405130 + }, + { + "epoch": 0.9, + "learning_rate": 4.814881098856849e-06, + "loss": 0.0928, + "step": 405140 + }, + { + "epoch": 0.9, + "learning_rate": 4.813762555647525e-06, + "loss": 0.0973, + "step": 405150 + }, + { + "epoch": 0.9, + "learning_rate": 4.812644012438201e-06, + "loss": 0.0977, + "step": 405160 + }, + { + "epoch": 0.9, + "learning_rate": 4.811525469228876e-06, + "loss": 0.0908, + "step": 405170 + }, + { + "epoch": 0.9, + "learning_rate": 4.8104069260195526e-06, + "loss": 0.0947, + "step": 405180 + }, + { + "epoch": 0.9, + "learning_rate": 4.809288382810228e-06, + "loss": 0.0923, + "step": 405190 + }, + { + "epoch": 0.9, + "learning_rate": 4.808169839600904e-06, + "loss": 0.0904, + "step": 405200 + }, + { + "epoch": 0.9, + "learning_rate": 4.8070512963915796e-06, + "loss": 0.0939, + "step": 405210 + }, + { + "epoch": 0.9, + "learning_rate": 4.805932753182256e-06, + "loss": 0.0947, + "step": 405220 + }, + { + "epoch": 0.9, + "learning_rate": 4.804814209972931e-06, + "loss": 0.0965, + "step": 405230 + }, + { + "epoch": 0.9, + "learning_rate": 4.803695666763607e-06, + "loss": 0.0933, + "step": 405240 + }, + { + "epoch": 0.9, + "learning_rate": 4.802577123554284e-06, + "loss": 0.0907, + "step": 405250 + }, + { + "epoch": 0.9, + "learning_rate": 4.801458580344959e-06, + "loss": 0.09, + "step": 405260 + }, + { + "epoch": 0.9, + "learning_rate": 4.800340037135634e-06, + "loss": 0.0932, + "step": 405270 + }, + { + "epoch": 0.9, + "learning_rate": 4.799221493926311e-06, + "loss": 0.0954, + "step": 405280 + }, + { + "epoch": 0.9, + "learning_rate": 4.798102950716987e-06, + "loss": 0.0975, + "step": 405290 + }, + { + "epoch": 0.9, + "learning_rate": 4.796984407507662e-06, + "loss": 0.0968, + "step": 405300 + }, + { + "epoch": 0.9, + "learning_rate": 4.795865864298338e-06, + "loss": 0.0936, + "step": 405310 + }, + { + "epoch": 0.9, + "learning_rate": 4.794747321089014e-06, + "loss": 0.0944, + "step": 405320 + }, + { + "epoch": 0.9, + "learning_rate": 4.79362877787969e-06, + "loss": 0.0926, + "step": 405330 + }, + { + "epoch": 0.9, + "learning_rate": 4.7925102346703655e-06, + "loss": 0.091, + "step": 405340 + }, + { + "epoch": 0.9, + "learning_rate": 4.791391691461041e-06, + "loss": 0.0921, + "step": 405350 + }, + { + "epoch": 0.9, + "learning_rate": 4.790273148251717e-06, + "loss": 0.0951, + "step": 405360 + }, + { + "epoch": 0.9, + "learning_rate": 4.789154605042393e-06, + "loss": 0.0993, + "step": 405370 + }, + { + "epoch": 0.9, + "learning_rate": 4.788036061833069e-06, + "loss": 0.0909, + "step": 405380 + }, + { + "epoch": 0.9, + "learning_rate": 4.786917518623744e-06, + "loss": 0.0946, + "step": 405390 + }, + { + "epoch": 0.9, + "learning_rate": 4.78579897541442e-06, + "loss": 0.0905, + "step": 405400 + }, + { + "epoch": 0.9, + "learning_rate": 4.784680432205097e-06, + "loss": 0.094, + "step": 405410 + }, + { + "epoch": 0.9, + "learning_rate": 4.783561888995773e-06, + "loss": 0.0951, + "step": 405420 + }, + { + "epoch": 0.9, + "learning_rate": 4.782443345786447e-06, + "loss": 0.094, + "step": 405430 + }, + { + "epoch": 0.9, + "learning_rate": 4.781324802577124e-06, + "loss": 0.0975, + "step": 405440 + }, + { + "epoch": 0.91, + "learning_rate": 4.7802062593678e-06, + "loss": 0.094, + "step": 405450 + }, + { + "epoch": 0.91, + "learning_rate": 4.779087716158476e-06, + "loss": 0.0985, + "step": 405460 + }, + { + "epoch": 0.91, + "learning_rate": 4.777969172949151e-06, + "loss": 0.0911, + "step": 405470 + }, + { + "epoch": 0.91, + "learning_rate": 4.776850629739827e-06, + "loss": 0.0911, + "step": 405480 + }, + { + "epoch": 0.91, + "learning_rate": 4.775732086530503e-06, + "loss": 0.0965, + "step": 405490 + }, + { + "epoch": 0.91, + "learning_rate": 4.774613543321179e-06, + "loss": 0.0937, + "step": 405500 + }, + { + "epoch": 0.91, + "learning_rate": 4.773495000111855e-06, + "loss": 0.0899, + "step": 405510 + }, + { + "epoch": 0.91, + "learning_rate": 4.77237645690253e-06, + "loss": 0.091, + "step": 405520 + }, + { + "epoch": 0.91, + "learning_rate": 4.771257913693206e-06, + "loss": 0.0936, + "step": 405530 + }, + { + "epoch": 0.91, + "learning_rate": 4.7701393704838826e-06, + "loss": 0.096, + "step": 405540 + }, + { + "epoch": 0.91, + "learning_rate": 4.769020827274558e-06, + "loss": 0.0937, + "step": 405550 + }, + { + "epoch": 0.91, + "learning_rate": 4.767902284065233e-06, + "loss": 0.0936, + "step": 405560 + }, + { + "epoch": 0.91, + "learning_rate": 4.7667837408559096e-06, + "loss": 0.093, + "step": 405570 + }, + { + "epoch": 0.91, + "learning_rate": 4.765665197646586e-06, + "loss": 0.0924, + "step": 405580 + }, + { + "epoch": 0.91, + "learning_rate": 4.764546654437261e-06, + "loss": 0.0904, + "step": 405590 + }, + { + "epoch": 0.91, + "learning_rate": 4.7634281112279366e-06, + "loss": 0.0938, + "step": 405600 + }, + { + "epoch": 0.91, + "learning_rate": 4.762309568018613e-06, + "loss": 0.0953, + "step": 405610 + }, + { + "epoch": 0.91, + "learning_rate": 4.761191024809289e-06, + "loss": 0.0924, + "step": 405620 + }, + { + "epoch": 0.91, + "learning_rate": 4.7600724815999644e-06, + "loss": 0.0908, + "step": 405630 + }, + { + "epoch": 0.91, + "learning_rate": 4.75895393839064e-06, + "loss": 0.0916, + "step": 405640 + }, + { + "epoch": 0.91, + "learning_rate": 4.757835395181316e-06, + "loss": 0.0907, + "step": 405650 + }, + { + "epoch": 0.91, + "learning_rate": 4.756716851971992e-06, + "loss": 0.095, + "step": 405660 + }, + { + "epoch": 0.91, + "learning_rate": 4.755598308762668e-06, + "loss": 0.0963, + "step": 405670 + }, + { + "epoch": 0.91, + "learning_rate": 4.754479765553344e-06, + "loss": 0.0935, + "step": 405680 + }, + { + "epoch": 0.91, + "learning_rate": 4.753361222344019e-06, + "loss": 0.0896, + "step": 405690 + }, + { + "epoch": 0.91, + "learning_rate": 4.7522426791346955e-06, + "loss": 0.0949, + "step": 405700 + }, + { + "epoch": 0.91, + "learning_rate": 4.751124135925371e-06, + "loss": 0.0904, + "step": 405710 + }, + { + "epoch": 0.91, + "learning_rate": 4.750005592716047e-06, + "loss": 0.0948, + "step": 405720 + }, + { + "epoch": 0.91, + "learning_rate": 4.7488870495067225e-06, + "loss": 0.0957, + "step": 405730 + }, + { + "epoch": 0.91, + "learning_rate": 4.747768506297399e-06, + "loss": 0.0897, + "step": 405740 + }, + { + "epoch": 0.91, + "learning_rate": 4.746649963088074e-06, + "loss": 0.0935, + "step": 405750 + }, + { + "epoch": 0.91, + "learning_rate": 4.74553141987875e-06, + "loss": 0.0965, + "step": 405760 + }, + { + "epoch": 0.91, + "learning_rate": 4.744412876669426e-06, + "loss": 0.0931, + "step": 405770 + }, + { + "epoch": 0.91, + "learning_rate": 4.743294333460102e-06, + "loss": 0.094, + "step": 405780 + }, + { + "epoch": 0.91, + "learning_rate": 4.74228764457171e-06, + "loss": 0.094, + "step": 405790 + }, + { + "epoch": 0.91, + "learning_rate": 4.741169101362386e-06, + "loss": 0.0937, + "step": 405800 + }, + { + "epoch": 0.91, + "learning_rate": 4.740050558153062e-06, + "loss": 0.0929, + "step": 405810 + }, + { + "epoch": 0.91, + "learning_rate": 4.738932014943737e-06, + "loss": 0.0933, + "step": 405820 + }, + { + "epoch": 0.91, + "learning_rate": 4.737813471734413e-06, + "loss": 0.094, + "step": 405830 + }, + { + "epoch": 0.91, + "learning_rate": 4.736694928525089e-06, + "loss": 0.0929, + "step": 405840 + }, + { + "epoch": 0.91, + "learning_rate": 4.735576385315766e-06, + "loss": 0.0889, + "step": 405850 + }, + { + "epoch": 0.91, + "learning_rate": 4.734457842106441e-06, + "loss": 0.0891, + "step": 405860 + }, + { + "epoch": 0.91, + "learning_rate": 4.733339298897116e-06, + "loss": 0.095, + "step": 405870 + }, + { + "epoch": 0.91, + "learning_rate": 4.732220755687793e-06, + "loss": 0.096, + "step": 405880 + }, + { + "epoch": 0.91, + "learning_rate": 4.731102212478469e-06, + "loss": 0.0951, + "step": 405890 + }, + { + "epoch": 0.91, + "learning_rate": 4.729983669269144e-06, + "loss": 0.0913, + "step": 405900 + }, + { + "epoch": 0.91, + "learning_rate": 4.72886512605982e-06, + "loss": 0.0925, + "step": 405910 + }, + { + "epoch": 0.91, + "learning_rate": 4.727746582850496e-06, + "loss": 0.0936, + "step": 405920 + }, + { + "epoch": 0.91, + "learning_rate": 4.726628039641172e-06, + "loss": 0.093, + "step": 405930 + }, + { + "epoch": 0.91, + "learning_rate": 4.7255094964318475e-06, + "loss": 0.0888, + "step": 405940 + }, + { + "epoch": 0.91, + "learning_rate": 4.724390953222523e-06, + "loss": 0.0967, + "step": 405950 + }, + { + "epoch": 0.91, + "learning_rate": 4.723272410013199e-06, + "loss": 0.0919, + "step": 405960 + }, + { + "epoch": 0.91, + "learning_rate": 4.722153866803875e-06, + "loss": 0.0905, + "step": 405970 + }, + { + "epoch": 0.91, + "learning_rate": 4.721035323594551e-06, + "loss": 0.0935, + "step": 405980 + }, + { + "epoch": 0.91, + "learning_rate": 4.719916780385226e-06, + "loss": 0.0945, + "step": 405990 + }, + { + "epoch": 0.91, + "learning_rate": 4.718798237175902e-06, + "loss": 0.0923, + "step": 406000 + }, + { + "epoch": 0.91, + "learning_rate": 4.717679693966579e-06, + "loss": 0.091, + "step": 406010 + }, + { + "epoch": 0.91, + "learning_rate": 4.716561150757254e-06, + "loss": 0.0937, + "step": 406020 + }, + { + "epoch": 0.91, + "learning_rate": 4.715442607547929e-06, + "loss": 0.0987, + "step": 406030 + }, + { + "epoch": 0.91, + "learning_rate": 4.714324064338606e-06, + "loss": 0.096, + "step": 406040 + }, + { + "epoch": 0.91, + "learning_rate": 4.713205521129282e-06, + "loss": 0.0935, + "step": 406050 + }, + { + "epoch": 0.91, + "learning_rate": 4.712086977919957e-06, + "loss": 0.0965, + "step": 406060 + }, + { + "epoch": 0.91, + "learning_rate": 4.7109684347106335e-06, + "loss": 0.0943, + "step": 406070 + }, + { + "epoch": 0.91, + "learning_rate": 4.709849891501309e-06, + "loss": 0.0972, + "step": 406080 + }, + { + "epoch": 0.91, + "learning_rate": 4.708731348291985e-06, + "loss": 0.0955, + "step": 406090 + }, + { + "epoch": 0.91, + "learning_rate": 4.7076128050826605e-06, + "loss": 0.0919, + "step": 406100 + }, + { + "epoch": 0.91, + "learning_rate": 4.706494261873337e-06, + "loss": 0.0926, + "step": 406110 + }, + { + "epoch": 0.91, + "learning_rate": 4.705375718664012e-06, + "loss": 0.0921, + "step": 406120 + }, + { + "epoch": 0.91, + "learning_rate": 4.704257175454688e-06, + "loss": 0.0923, + "step": 406130 + }, + { + "epoch": 0.91, + "learning_rate": 4.703138632245364e-06, + "loss": 0.0943, + "step": 406140 + }, + { + "epoch": 0.91, + "learning_rate": 4.70202008903604e-06, + "loss": 0.0933, + "step": 406150 + }, + { + "epoch": 0.91, + "learning_rate": 4.700901545826715e-06, + "loss": 0.0975, + "step": 406160 + }, + { + "epoch": 0.91, + "learning_rate": 4.699783002617391e-06, + "loss": 0.0933, + "step": 406170 + }, + { + "epoch": 0.91, + "learning_rate": 4.698664459408067e-06, + "loss": 0.0929, + "step": 406180 + }, + { + "epoch": 0.91, + "learning_rate": 4.697545916198743e-06, + "loss": 0.0991, + "step": 406190 + }, + { + "epoch": 0.91, + "learning_rate": 4.6964273729894186e-06, + "loss": 0.0908, + "step": 406200 + }, + { + "epoch": 0.91, + "learning_rate": 4.695308829780094e-06, + "loss": 0.0948, + "step": 406210 + }, + { + "epoch": 0.91, + "learning_rate": 4.69419028657077e-06, + "loss": 0.0979, + "step": 406220 + }, + { + "epoch": 0.91, + "learning_rate": 4.6930717433614464e-06, + "loss": 0.0952, + "step": 406230 + }, + { + "epoch": 0.91, + "learning_rate": 4.691953200152123e-06, + "loss": 0.0957, + "step": 406240 + }, + { + "epoch": 0.91, + "learning_rate": 4.690834656942797e-06, + "loss": 0.0897, + "step": 406250 + }, + { + "epoch": 0.91, + "learning_rate": 4.6897161137334734e-06, + "loss": 0.0944, + "step": 406260 + }, + { + "epoch": 0.91, + "learning_rate": 4.68859757052415e-06, + "loss": 0.0946, + "step": 406270 + }, + { + "epoch": 0.91, + "learning_rate": 4.687479027314826e-06, + "loss": 0.0921, + "step": 406280 + }, + { + "epoch": 0.91, + "learning_rate": 4.686360484105501e-06, + "loss": 0.0995, + "step": 406290 + }, + { + "epoch": 0.91, + "learning_rate": 4.685241940896177e-06, + "loss": 0.097, + "step": 406300 + }, + { + "epoch": 0.91, + "learning_rate": 4.684123397686853e-06, + "loss": 0.0926, + "step": 406310 + }, + { + "epoch": 0.91, + "learning_rate": 4.683004854477529e-06, + "loss": 0.0959, + "step": 406320 + }, + { + "epoch": 0.91, + "learning_rate": 4.6818863112682045e-06, + "loss": 0.0891, + "step": 406330 + }, + { + "epoch": 0.91, + "learning_rate": 4.68076776805888e-06, + "loss": 0.094, + "step": 406340 + }, + { + "epoch": 0.91, + "learning_rate": 4.679649224849556e-06, + "loss": 0.0944, + "step": 406350 + }, + { + "epoch": 0.91, + "learning_rate": 4.678530681640232e-06, + "loss": 0.0954, + "step": 406360 + }, + { + "epoch": 0.91, + "learning_rate": 4.677412138430908e-06, + "loss": 0.0942, + "step": 406370 + }, + { + "epoch": 0.91, + "learning_rate": 4.676293595221583e-06, + "loss": 0.0959, + "step": 406380 + }, + { + "epoch": 0.91, + "learning_rate": 4.675175052012259e-06, + "loss": 0.0946, + "step": 406390 + }, + { + "epoch": 0.91, + "learning_rate": 4.674056508802936e-06, + "loss": 0.0911, + "step": 406400 + }, + { + "epoch": 0.91, + "learning_rate": 4.672937965593611e-06, + "loss": 0.094, + "step": 406410 + }, + { + "epoch": 0.91, + "learning_rate": 4.671819422384286e-06, + "loss": 0.0924, + "step": 406420 + }, + { + "epoch": 0.91, + "learning_rate": 4.670700879174963e-06, + "loss": 0.0968, + "step": 406430 + }, + { + "epoch": 0.91, + "learning_rate": 4.669582335965639e-06, + "loss": 0.0939, + "step": 406440 + }, + { + "epoch": 0.91, + "learning_rate": 4.668463792756314e-06, + "loss": 0.0951, + "step": 406450 + }, + { + "epoch": 0.91, + "learning_rate": 4.6673452495469905e-06, + "loss": 0.0904, + "step": 406460 + }, + { + "epoch": 0.91, + "learning_rate": 4.666226706337666e-06, + "loss": 0.0922, + "step": 406470 + }, + { + "epoch": 0.91, + "learning_rate": 4.665108163128342e-06, + "loss": 0.0937, + "step": 406480 + }, + { + "epoch": 0.91, + "learning_rate": 4.6639896199190175e-06, + "loss": 0.091, + "step": 406490 + }, + { + "epoch": 0.91, + "learning_rate": 4.662871076709694e-06, + "loss": 0.0944, + "step": 406500 + }, + { + "epoch": 0.91, + "learning_rate": 4.661752533500369e-06, + "loss": 0.0941, + "step": 406510 + }, + { + "epoch": 0.91, + "learning_rate": 4.660633990291045e-06, + "loss": 0.095, + "step": 406520 + }, + { + "epoch": 0.91, + "learning_rate": 4.659515447081721e-06, + "loss": 0.0943, + "step": 406530 + }, + { + "epoch": 0.91, + "learning_rate": 4.658396903872397e-06, + "loss": 0.0896, + "step": 406540 + }, + { + "epoch": 0.91, + "learning_rate": 4.657278360663072e-06, + "loss": 0.0883, + "step": 406550 + }, + { + "epoch": 0.91, + "learning_rate": 4.656159817453749e-06, + "loss": 0.0883, + "step": 406560 + }, + { + "epoch": 0.91, + "learning_rate": 4.655041274244424e-06, + "loss": 0.0928, + "step": 406570 + }, + { + "epoch": 0.91, + "learning_rate": 4.6539227310351e-06, + "loss": 0.0916, + "step": 406580 + }, + { + "epoch": 0.91, + "learning_rate": 4.652804187825776e-06, + "loss": 0.0885, + "step": 406590 + }, + { + "epoch": 0.91, + "learning_rate": 4.651685644616452e-06, + "loss": 0.0944, + "step": 406600 + }, + { + "epoch": 0.91, + "learning_rate": 4.650567101407127e-06, + "loss": 0.0898, + "step": 406610 + }, + { + "epoch": 0.91, + "learning_rate": 4.6494485581978034e-06, + "loss": 0.0912, + "step": 406620 + }, + { + "epoch": 0.91, + "learning_rate": 4.648330014988479e-06, + "loss": 0.091, + "step": 406630 + }, + { + "epoch": 0.91, + "learning_rate": 4.647211471779155e-06, + "loss": 0.0894, + "step": 406640 + }, + { + "epoch": 0.91, + "learning_rate": 4.6460929285698305e-06, + "loss": 0.0926, + "step": 406650 + }, + { + "epoch": 0.91, + "learning_rate": 4.644974385360507e-06, + "loss": 0.0922, + "step": 406660 + }, + { + "epoch": 0.91, + "learning_rate": 4.643855842151183e-06, + "loss": 0.0927, + "step": 406670 + }, + { + "epoch": 0.91, + "learning_rate": 4.642737298941858e-06, + "loss": 0.0926, + "step": 406680 + }, + { + "epoch": 0.91, + "learning_rate": 4.641618755732534e-06, + "loss": 0.0895, + "step": 406690 + }, + { + "epoch": 0.91, + "learning_rate": 4.64050021252321e-06, + "loss": 0.0925, + "step": 406700 + }, + { + "epoch": 0.91, + "learning_rate": 4.639381669313886e-06, + "loss": 0.0959, + "step": 406710 + }, + { + "epoch": 0.91, + "learning_rate": 4.6382631261045615e-06, + "loss": 0.0946, + "step": 406720 + }, + { + "epoch": 0.91, + "learning_rate": 4.637144582895237e-06, + "loss": 0.0932, + "step": 406730 + }, + { + "epoch": 0.91, + "learning_rate": 4.636026039685913e-06, + "loss": 0.0951, + "step": 406740 + }, + { + "epoch": 0.91, + "learning_rate": 4.634907496476589e-06, + "loss": 0.0921, + "step": 406750 + }, + { + "epoch": 0.91, + "learning_rate": 4.633788953267265e-06, + "loss": 0.0897, + "step": 406760 + }, + { + "epoch": 0.91, + "learning_rate": 4.63267041005794e-06, + "loss": 0.0927, + "step": 406770 + }, + { + "epoch": 0.91, + "learning_rate": 4.631551866848616e-06, + "loss": 0.0942, + "step": 406780 + }, + { + "epoch": 0.91, + "learning_rate": 4.630433323639293e-06, + "loss": 0.0954, + "step": 406790 + }, + { + "epoch": 0.91, + "learning_rate": 4.629314780429968e-06, + "loss": 0.0927, + "step": 406800 + }, + { + "epoch": 0.91, + "learning_rate": 4.628196237220643e-06, + "loss": 0.0874, + "step": 406810 + }, + { + "epoch": 0.91, + "learning_rate": 4.62707769401132e-06, + "loss": 0.0929, + "step": 406820 + }, + { + "epoch": 0.91, + "learning_rate": 4.625959150801996e-06, + "loss": 0.0893, + "step": 406830 + }, + { + "epoch": 0.91, + "learning_rate": 4.624840607592672e-06, + "loss": 0.0929, + "step": 406840 + }, + { + "epoch": 0.91, + "learning_rate": 4.623722064383347e-06, + "loss": 0.0893, + "step": 406850 + }, + { + "epoch": 0.91, + "learning_rate": 4.622603521174023e-06, + "loss": 0.092, + "step": 406860 + }, + { + "epoch": 0.91, + "learning_rate": 4.621484977964699e-06, + "loss": 0.0932, + "step": 406870 + }, + { + "epoch": 0.91, + "learning_rate": 4.620366434755375e-06, + "loss": 0.0951, + "step": 406880 + }, + { + "epoch": 0.91, + "learning_rate": 4.619247891546051e-06, + "loss": 0.0891, + "step": 406890 + }, + { + "epoch": 0.91, + "learning_rate": 4.618129348336726e-06, + "loss": 0.0943, + "step": 406900 + }, + { + "epoch": 0.91, + "learning_rate": 4.617010805127402e-06, + "loss": 0.0922, + "step": 406910 + }, + { + "epoch": 0.91, + "learning_rate": 4.615892261918079e-06, + "loss": 0.093, + "step": 406920 + }, + { + "epoch": 0.91, + "learning_rate": 4.614773718708754e-06, + "loss": 0.0928, + "step": 406930 + }, + { + "epoch": 0.91, + "learning_rate": 4.613655175499429e-06, + "loss": 0.0932, + "step": 406940 + }, + { + "epoch": 0.91, + "learning_rate": 4.612536632290106e-06, + "loss": 0.0926, + "step": 406950 + }, + { + "epoch": 0.91, + "learning_rate": 4.611418089080782e-06, + "loss": 0.0966, + "step": 406960 + }, + { + "epoch": 0.91, + "learning_rate": 4.610299545871457e-06, + "loss": 0.0923, + "step": 406970 + }, + { + "epoch": 0.91, + "learning_rate": 4.609181002662133e-06, + "loss": 0.0932, + "step": 406980 + }, + { + "epoch": 0.91, + "learning_rate": 4.608062459452809e-06, + "loss": 0.0898, + "step": 406990 + }, + { + "epoch": 0.91, + "learning_rate": 4.606943916243485e-06, + "loss": 0.0904, + "step": 407000 + }, + { + "epoch": 0.91, + "learning_rate": 4.6058253730341605e-06, + "loss": 0.0942, + "step": 407010 + }, + { + "epoch": 0.91, + "learning_rate": 4.604706829824836e-06, + "loss": 0.0916, + "step": 407020 + }, + { + "epoch": 0.91, + "learning_rate": 4.603588286615512e-06, + "loss": 0.0943, + "step": 407030 + }, + { + "epoch": 0.91, + "learning_rate": 4.602469743406188e-06, + "loss": 0.0942, + "step": 407040 + }, + { + "epoch": 0.91, + "learning_rate": 4.601351200196864e-06, + "loss": 0.0987, + "step": 407050 + }, + { + "epoch": 0.91, + "learning_rate": 4.60023265698754e-06, + "loss": 0.0907, + "step": 407060 + }, + { + "epoch": 0.91, + "learning_rate": 4.599114113778215e-06, + "loss": 0.0923, + "step": 407070 + }, + { + "epoch": 0.91, + "learning_rate": 4.5979955705688916e-06, + "loss": 0.0919, + "step": 407080 + }, + { + "epoch": 0.91, + "learning_rate": 4.596877027359567e-06, + "loss": 0.0942, + "step": 407090 + }, + { + "epoch": 0.91, + "learning_rate": 4.595758484150243e-06, + "loss": 0.0884, + "step": 407100 + }, + { + "epoch": 0.91, + "learning_rate": 4.5946399409409186e-06, + "loss": 0.0895, + "step": 407110 + }, + { + "epoch": 0.91, + "learning_rate": 4.593521397731595e-06, + "loss": 0.0953, + "step": 407120 + }, + { + "epoch": 0.91, + "learning_rate": 4.59240285452227e-06, + "loss": 0.0946, + "step": 407130 + }, + { + "epoch": 0.91, + "learning_rate": 4.591284311312946e-06, + "loss": 0.0931, + "step": 407140 + }, + { + "epoch": 0.91, + "learning_rate": 4.590165768103622e-06, + "loss": 0.0928, + "step": 407150 + }, + { + "epoch": 0.91, + "learning_rate": 4.589047224894298e-06, + "loss": 0.0912, + "step": 407160 + }, + { + "epoch": 0.91, + "learning_rate": 4.5879286816849734e-06, + "loss": 0.0934, + "step": 407170 + }, + { + "epoch": 0.91, + "learning_rate": 4.58681013847565e-06, + "loss": 0.0954, + "step": 407180 + }, + { + "epoch": 0.91, + "learning_rate": 4.585691595266325e-06, + "loss": 0.0923, + "step": 407190 + }, + { + "epoch": 0.91, + "learning_rate": 4.584573052057001e-06, + "loss": 0.0936, + "step": 407200 + }, + { + "epoch": 0.91, + "learning_rate": 4.583454508847677e-06, + "loss": 0.092, + "step": 407210 + }, + { + "epoch": 0.91, + "learning_rate": 4.582335965638353e-06, + "loss": 0.0939, + "step": 407220 + }, + { + "epoch": 0.91, + "learning_rate": 4.581217422429029e-06, + "loss": 0.0927, + "step": 407230 + }, + { + "epoch": 0.91, + "learning_rate": 4.5800988792197045e-06, + "loss": 0.0906, + "step": 407240 + }, + { + "epoch": 0.91, + "learning_rate": 4.57898033601038e-06, + "loss": 0.0913, + "step": 407250 + }, + { + "epoch": 0.91, + "learning_rate": 4.577861792801056e-06, + "loss": 0.0916, + "step": 407260 + }, + { + "epoch": 0.91, + "learning_rate": 4.576743249591732e-06, + "loss": 0.092, + "step": 407270 + }, + { + "epoch": 0.91, + "learning_rate": 4.575624706382408e-06, + "loss": 0.0922, + "step": 407280 + }, + { + "epoch": 0.91, + "learning_rate": 4.574506163173083e-06, + "loss": 0.0892, + "step": 407290 + }, + { + "epoch": 0.91, + "learning_rate": 4.573387619963759e-06, + "loss": 0.095, + "step": 407300 + }, + { + "epoch": 0.91, + "learning_rate": 4.572269076754436e-06, + "loss": 0.0914, + "step": 407310 + }, + { + "epoch": 0.91, + "learning_rate": 4.571150533545111e-06, + "loss": 0.0907, + "step": 407320 + }, + { + "epoch": 0.91, + "learning_rate": 4.570031990335786e-06, + "loss": 0.0911, + "step": 407330 + }, + { + "epoch": 0.91, + "learning_rate": 4.568913447126463e-06, + "loss": 0.0939, + "step": 407340 + }, + { + "epoch": 0.91, + "learning_rate": 4.567794903917139e-06, + "loss": 0.0966, + "step": 407350 + }, + { + "epoch": 0.91, + "learning_rate": 4.566676360707814e-06, + "loss": 0.0958, + "step": 407360 + }, + { + "epoch": 0.91, + "learning_rate": 4.56555781749849e-06, + "loss": 0.0898, + "step": 407370 + }, + { + "epoch": 0.91, + "learning_rate": 4.564439274289166e-06, + "loss": 0.0873, + "step": 407380 + }, + { + "epoch": 0.91, + "learning_rate": 4.563320731079842e-06, + "loss": 0.0938, + "step": 407390 + }, + { + "epoch": 0.91, + "learning_rate": 4.5622021878705175e-06, + "loss": 0.0913, + "step": 407400 + }, + { + "epoch": 0.91, + "learning_rate": 4.561083644661193e-06, + "loss": 0.0915, + "step": 407410 + }, + { + "epoch": 0.91, + "learning_rate": 4.559965101451869e-06, + "loss": 0.0903, + "step": 407420 + }, + { + "epoch": 0.91, + "learning_rate": 4.558846558242545e-06, + "loss": 0.092, + "step": 407430 + }, + { + "epoch": 0.91, + "learning_rate": 4.5577280150332216e-06, + "loss": 0.094, + "step": 407440 + }, + { + "epoch": 0.91, + "learning_rate": 4.556609471823896e-06, + "loss": 0.0893, + "step": 407450 + }, + { + "epoch": 0.91, + "learning_rate": 4.555490928614572e-06, + "loss": 0.0921, + "step": 407460 + }, + { + "epoch": 0.91, + "learning_rate": 4.5543723854052486e-06, + "loss": 0.0911, + "step": 407470 + }, + { + "epoch": 0.91, + "learning_rate": 4.553253842195925e-06, + "loss": 0.0895, + "step": 407480 + }, + { + "epoch": 0.91, + "learning_rate": 4.5521352989866e-06, + "loss": 0.0951, + "step": 407490 + }, + { + "epoch": 0.91, + "learning_rate": 4.551016755777276e-06, + "loss": 0.0911, + "step": 407500 + }, + { + "epoch": 0.91, + "learning_rate": 4.549898212567952e-06, + "loss": 0.0909, + "step": 407510 + }, + { + "epoch": 0.91, + "learning_rate": 4.548779669358628e-06, + "loss": 0.0922, + "step": 407520 + }, + { + "epoch": 0.91, + "learning_rate": 4.5476611261493034e-06, + "loss": 0.0889, + "step": 407530 + }, + { + "epoch": 0.91, + "learning_rate": 4.546542582939979e-06, + "loss": 0.0882, + "step": 407540 + }, + { + "epoch": 0.91, + "learning_rate": 4.545424039730655e-06, + "loss": 0.0945, + "step": 407550 + }, + { + "epoch": 0.91, + "learning_rate": 4.544305496521331e-06, + "loss": 0.0909, + "step": 407560 + }, + { + "epoch": 0.91, + "learning_rate": 4.543186953312007e-06, + "loss": 0.0923, + "step": 407570 + }, + { + "epoch": 0.91, + "learning_rate": 4.542068410102682e-06, + "loss": 0.0912, + "step": 407580 + }, + { + "epoch": 0.91, + "learning_rate": 4.540949866893358e-06, + "loss": 0.095, + "step": 407590 + }, + { + "epoch": 0.91, + "learning_rate": 4.5398313236840345e-06, + "loss": 0.0912, + "step": 407600 + }, + { + "epoch": 0.91, + "learning_rate": 4.53871278047471e-06, + "loss": 0.0898, + "step": 407610 + }, + { + "epoch": 0.91, + "learning_rate": 4.537594237265385e-06, + "loss": 0.0938, + "step": 407620 + }, + { + "epoch": 0.91, + "learning_rate": 4.5364756940560615e-06, + "loss": 0.0963, + "step": 407630 + }, + { + "epoch": 0.91, + "learning_rate": 4.535357150846738e-06, + "loss": 0.092, + "step": 407640 + }, + { + "epoch": 0.91, + "learning_rate": 4.534238607637413e-06, + "loss": 0.0901, + "step": 407650 + }, + { + "epoch": 0.91, + "learning_rate": 4.533120064428089e-06, + "loss": 0.095, + "step": 407660 + }, + { + "epoch": 0.91, + "learning_rate": 4.532001521218765e-06, + "loss": 0.0858, + "step": 407670 + }, + { + "epoch": 0.91, + "learning_rate": 4.530882978009441e-06, + "loss": 0.0904, + "step": 407680 + }, + { + "epoch": 0.91, + "learning_rate": 4.529764434800116e-06, + "loss": 0.0912, + "step": 407690 + }, + { + "epoch": 0.91, + "learning_rate": 4.528645891590793e-06, + "loss": 0.0936, + "step": 407700 + }, + { + "epoch": 0.91, + "learning_rate": 4.527527348381468e-06, + "loss": 0.0914, + "step": 407710 + }, + { + "epoch": 0.91, + "learning_rate": 4.526408805172144e-06, + "loss": 0.0931, + "step": 407720 + }, + { + "epoch": 0.91, + "learning_rate": 4.52529026196282e-06, + "loss": 0.0917, + "step": 407730 + }, + { + "epoch": 0.91, + "learning_rate": 4.524171718753496e-06, + "loss": 0.0972, + "step": 407740 + }, + { + "epoch": 0.91, + "learning_rate": 4.523053175544171e-06, + "loss": 0.0942, + "step": 407750 + }, + { + "epoch": 0.91, + "learning_rate": 4.5219346323348475e-06, + "loss": 0.0915, + "step": 407760 + }, + { + "epoch": 0.91, + "learning_rate": 4.520816089125523e-06, + "loss": 0.0943, + "step": 407770 + }, + { + "epoch": 0.91, + "learning_rate": 4.519697545916199e-06, + "loss": 0.092, + "step": 407780 + }, + { + "epoch": 0.91, + "learning_rate": 4.5185790027068745e-06, + "loss": 0.0885, + "step": 407790 + }, + { + "epoch": 0.91, + "learning_rate": 4.5175723138184824e-06, + "loss": 0.0912, + "step": 407800 + }, + { + "epoch": 0.91, + "learning_rate": 4.516453770609159e-06, + "loss": 0.092, + "step": 407810 + }, + { + "epoch": 0.91, + "learning_rate": 4.515335227399835e-06, + "loss": 0.0907, + "step": 407820 + }, + { + "epoch": 0.91, + "learning_rate": 4.514216684190511e-06, + "loss": 0.0916, + "step": 407830 + }, + { + "epoch": 0.91, + "learning_rate": 4.513098140981186e-06, + "loss": 0.09, + "step": 407840 + }, + { + "epoch": 0.91, + "learning_rate": 4.511979597771862e-06, + "loss": 0.0917, + "step": 407850 + }, + { + "epoch": 0.91, + "learning_rate": 4.510861054562538e-06, + "loss": 0.094, + "step": 407860 + }, + { + "epoch": 0.91, + "learning_rate": 4.509742511353214e-06, + "loss": 0.0931, + "step": 407870 + }, + { + "epoch": 0.91, + "learning_rate": 4.50862396814389e-06, + "loss": 0.0913, + "step": 407880 + }, + { + "epoch": 0.91, + "learning_rate": 4.507505424934565e-06, + "loss": 0.0885, + "step": 407890 + }, + { + "epoch": 0.91, + "learning_rate": 4.506386881725241e-06, + "loss": 0.0945, + "step": 407900 + }, + { + "epoch": 0.91, + "learning_rate": 4.505268338515918e-06, + "loss": 0.0905, + "step": 407910 + }, + { + "epoch": 0.91, + "learning_rate": 4.504149795306593e-06, + "loss": 0.0923, + "step": 407920 + }, + { + "epoch": 0.91, + "learning_rate": 4.503031252097268e-06, + "loss": 0.0875, + "step": 407930 + }, + { + "epoch": 0.91, + "learning_rate": 4.501912708887945e-06, + "loss": 0.0918, + "step": 407940 + }, + { + "epoch": 0.91, + "learning_rate": 4.500794165678621e-06, + "loss": 0.0908, + "step": 407950 + }, + { + "epoch": 0.91, + "learning_rate": 4.499675622469296e-06, + "loss": 0.0904, + "step": 407960 + }, + { + "epoch": 0.91, + "learning_rate": 4.498557079259972e-06, + "loss": 0.0861, + "step": 407970 + }, + { + "epoch": 0.91, + "learning_rate": 4.497438536050648e-06, + "loss": 0.0909, + "step": 407980 + }, + { + "epoch": 0.91, + "learning_rate": 4.496319992841324e-06, + "loss": 0.0915, + "step": 407990 + }, + { + "epoch": 0.91, + "learning_rate": 4.4952014496319995e-06, + "loss": 0.0971, + "step": 408000 + }, + { + "epoch": 0.91, + "learning_rate": 4.494082906422675e-06, + "loss": 0.0948, + "step": 408010 + }, + { + "epoch": 0.91, + "learning_rate": 4.492964363213351e-06, + "loss": 0.0897, + "step": 408020 + }, + { + "epoch": 0.91, + "learning_rate": 4.491845820004027e-06, + "loss": 0.0885, + "step": 408030 + }, + { + "epoch": 0.91, + "learning_rate": 4.490727276794703e-06, + "loss": 0.0926, + "step": 408040 + }, + { + "epoch": 0.91, + "learning_rate": 4.489608733585379e-06, + "loss": 0.0891, + "step": 408050 + }, + { + "epoch": 0.91, + "learning_rate": 4.488490190376054e-06, + "loss": 0.0907, + "step": 408060 + }, + { + "epoch": 0.91, + "learning_rate": 4.4873716471667306e-06, + "loss": 0.092, + "step": 408070 + }, + { + "epoch": 0.91, + "learning_rate": 4.486253103957406e-06, + "loss": 0.0938, + "step": 408080 + }, + { + "epoch": 0.91, + "learning_rate": 4.485134560748082e-06, + "loss": 0.0944, + "step": 408090 + }, + { + "epoch": 0.91, + "learning_rate": 4.484016017538758e-06, + "loss": 0.0906, + "step": 408100 + }, + { + "epoch": 0.91, + "learning_rate": 4.482897474329434e-06, + "loss": 0.0955, + "step": 408110 + }, + { + "epoch": 0.91, + "learning_rate": 4.481778931120109e-06, + "loss": 0.0943, + "step": 408120 + }, + { + "epoch": 0.91, + "learning_rate": 4.4806603879107854e-06, + "loss": 0.0919, + "step": 408130 + }, + { + "epoch": 0.91, + "learning_rate": 4.479541844701461e-06, + "loss": 0.0913, + "step": 408140 + }, + { + "epoch": 0.91, + "learning_rate": 4.478423301492137e-06, + "loss": 0.0907, + "step": 408150 + }, + { + "epoch": 0.91, + "learning_rate": 4.4773047582828124e-06, + "loss": 0.0914, + "step": 408160 + }, + { + "epoch": 0.91, + "learning_rate": 4.476186215073489e-06, + "loss": 0.0921, + "step": 408170 + }, + { + "epoch": 0.91, + "learning_rate": 4.475067671864164e-06, + "loss": 0.0922, + "step": 408180 + }, + { + "epoch": 0.91, + "learning_rate": 4.47394912865484e-06, + "loss": 0.0906, + "step": 408190 + }, + { + "epoch": 0.91, + "learning_rate": 4.472830585445516e-06, + "loss": 0.0929, + "step": 408200 + }, + { + "epoch": 0.91, + "learning_rate": 4.471712042236192e-06, + "loss": 0.0943, + "step": 408210 + }, + { + "epoch": 0.91, + "learning_rate": 4.470593499026868e-06, + "loss": 0.0912, + "step": 408220 + }, + { + "epoch": 0.91, + "learning_rate": 4.4694749558175435e-06, + "loss": 0.0936, + "step": 408230 + }, + { + "epoch": 0.91, + "learning_rate": 4.468356412608219e-06, + "loss": 0.0881, + "step": 408240 + }, + { + "epoch": 0.91, + "learning_rate": 4.467237869398895e-06, + "loss": 0.0928, + "step": 408250 + }, + { + "epoch": 0.91, + "learning_rate": 4.466119326189571e-06, + "loss": 0.0898, + "step": 408260 + }, + { + "epoch": 0.91, + "learning_rate": 4.465000782980247e-06, + "loss": 0.0918, + "step": 408270 + }, + { + "epoch": 0.91, + "learning_rate": 4.463882239770922e-06, + "loss": 0.0904, + "step": 408280 + }, + { + "epoch": 0.91, + "learning_rate": 4.462763696561598e-06, + "loss": 0.0918, + "step": 408290 + }, + { + "epoch": 0.91, + "learning_rate": 4.461645153352275e-06, + "loss": 0.0941, + "step": 408300 + }, + { + "epoch": 0.91, + "learning_rate": 4.46052661014295e-06, + "loss": 0.0944, + "step": 408310 + }, + { + "epoch": 0.91, + "learning_rate": 4.459408066933625e-06, + "loss": 0.0931, + "step": 408320 + }, + { + "epoch": 0.91, + "learning_rate": 4.458289523724302e-06, + "loss": 0.0899, + "step": 408330 + }, + { + "epoch": 0.91, + "learning_rate": 4.457170980514978e-06, + "loss": 0.095, + "step": 408340 + }, + { + "epoch": 0.91, + "learning_rate": 4.456052437305653e-06, + "loss": 0.0906, + "step": 408350 + }, + { + "epoch": 0.91, + "learning_rate": 4.454933894096329e-06, + "loss": 0.0941, + "step": 408360 + }, + { + "epoch": 0.91, + "learning_rate": 4.453815350887005e-06, + "loss": 0.0954, + "step": 408370 + }, + { + "epoch": 0.91, + "learning_rate": 4.452696807677681e-06, + "loss": 0.0916, + "step": 408380 + }, + { + "epoch": 0.91, + "learning_rate": 4.451578264468357e-06, + "loss": 0.0933, + "step": 408390 + }, + { + "epoch": 0.91, + "learning_rate": 4.450459721259032e-06, + "loss": 0.0919, + "step": 408400 + }, + { + "epoch": 0.91, + "learning_rate": 4.449341178049708e-06, + "loss": 0.0948, + "step": 408410 + }, + { + "epoch": 0.91, + "learning_rate": 4.448222634840384e-06, + "loss": 0.0914, + "step": 408420 + }, + { + "epoch": 0.91, + "learning_rate": 4.447104091631061e-06, + "loss": 0.0891, + "step": 408430 + }, + { + "epoch": 0.91, + "learning_rate": 4.445985548421735e-06, + "loss": 0.0925, + "step": 408440 + }, + { + "epoch": 0.91, + "learning_rate": 4.444867005212411e-06, + "loss": 0.0911, + "step": 408450 + }, + { + "epoch": 0.91, + "learning_rate": 4.443748462003088e-06, + "loss": 0.0929, + "step": 408460 + }, + { + "epoch": 0.91, + "learning_rate": 4.442629918793764e-06, + "loss": 0.0882, + "step": 408470 + }, + { + "epoch": 0.91, + "learning_rate": 4.441511375584439e-06, + "loss": 0.0906, + "step": 408480 + }, + { + "epoch": 0.91, + "learning_rate": 4.440392832375115e-06, + "loss": 0.0931, + "step": 408490 + }, + { + "epoch": 0.91, + "learning_rate": 4.439274289165791e-06, + "loss": 0.0875, + "step": 408500 + }, + { + "epoch": 0.91, + "learning_rate": 4.438155745956467e-06, + "loss": 0.0941, + "step": 408510 + }, + { + "epoch": 0.91, + "learning_rate": 4.4370372027471425e-06, + "loss": 0.0903, + "step": 408520 + }, + { + "epoch": 0.91, + "learning_rate": 4.435918659537818e-06, + "loss": 0.0934, + "step": 408530 + }, + { + "epoch": 0.91, + "learning_rate": 4.434800116328494e-06, + "loss": 0.0896, + "step": 408540 + }, + { + "epoch": 0.91, + "learning_rate": 4.43368157311917e-06, + "loss": 0.0908, + "step": 408550 + }, + { + "epoch": 0.91, + "learning_rate": 4.432563029909846e-06, + "loss": 0.0937, + "step": 408560 + }, + { + "epoch": 0.91, + "learning_rate": 4.431444486700521e-06, + "loss": 0.0916, + "step": 408570 + }, + { + "epoch": 0.91, + "learning_rate": 4.430325943491197e-06, + "loss": 0.0931, + "step": 408580 + }, + { + "epoch": 0.91, + "learning_rate": 4.4292074002818735e-06, + "loss": 0.0927, + "step": 408590 + }, + { + "epoch": 0.91, + "learning_rate": 4.428088857072549e-06, + "loss": 0.0925, + "step": 408600 + }, + { + "epoch": 0.91, + "learning_rate": 4.426970313863224e-06, + "loss": 0.0921, + "step": 408610 + }, + { + "epoch": 0.91, + "learning_rate": 4.4258517706539006e-06, + "loss": 0.0925, + "step": 408620 + }, + { + "epoch": 0.91, + "learning_rate": 4.424733227444577e-06, + "loss": 0.0896, + "step": 408630 + }, + { + "epoch": 0.91, + "learning_rate": 4.423614684235252e-06, + "loss": 0.092, + "step": 408640 + }, + { + "epoch": 0.91, + "learning_rate": 4.422496141025928e-06, + "loss": 0.089, + "step": 408650 + }, + { + "epoch": 0.91, + "learning_rate": 4.421377597816604e-06, + "loss": 0.0885, + "step": 408660 + }, + { + "epoch": 0.91, + "learning_rate": 4.42025905460728e-06, + "loss": 0.0944, + "step": 408670 + }, + { + "epoch": 0.91, + "learning_rate": 4.419140511397955e-06, + "loss": 0.0915, + "step": 408680 + }, + { + "epoch": 0.91, + "learning_rate": 4.418021968188632e-06, + "loss": 0.0923, + "step": 408690 + }, + { + "epoch": 0.91, + "learning_rate": 4.416903424979307e-06, + "loss": 0.0928, + "step": 408700 + }, + { + "epoch": 0.91, + "learning_rate": 4.415784881769983e-06, + "loss": 0.0908, + "step": 408710 + }, + { + "epoch": 0.91, + "learning_rate": 4.414666338560659e-06, + "loss": 0.0896, + "step": 408720 + }, + { + "epoch": 0.91, + "learning_rate": 4.413547795351335e-06, + "loss": 0.091, + "step": 408730 + }, + { + "epoch": 0.91, + "learning_rate": 4.41242925214201e-06, + "loss": 0.0909, + "step": 408740 + }, + { + "epoch": 0.91, + "learning_rate": 4.4113107089326865e-06, + "loss": 0.0971, + "step": 408750 + }, + { + "epoch": 0.91, + "learning_rate": 4.410192165723362e-06, + "loss": 0.0938, + "step": 408760 + }, + { + "epoch": 0.91, + "learning_rate": 4.409073622514038e-06, + "loss": 0.09, + "step": 408770 + }, + { + "epoch": 0.91, + "learning_rate": 4.4079550793047135e-06, + "loss": 0.0906, + "step": 408780 + }, + { + "epoch": 0.91, + "learning_rate": 4.40683653609539e-06, + "loss": 0.093, + "step": 408790 + }, + { + "epoch": 0.91, + "learning_rate": 4.405717992886065e-06, + "loss": 0.0925, + "step": 408800 + }, + { + "epoch": 0.91, + "learning_rate": 4.404599449676741e-06, + "loss": 0.0922, + "step": 408810 + }, + { + "epoch": 0.91, + "learning_rate": 4.403480906467418e-06, + "loss": 0.0935, + "step": 408820 + }, + { + "epoch": 0.91, + "learning_rate": 4.402362363258093e-06, + "loss": 0.0931, + "step": 408830 + }, + { + "epoch": 0.91, + "learning_rate": 4.401243820048768e-06, + "loss": 0.0908, + "step": 408840 + }, + { + "epoch": 0.91, + "learning_rate": 4.400125276839445e-06, + "loss": 0.0926, + "step": 408850 + }, + { + "epoch": 0.91, + "learning_rate": 4.399006733630121e-06, + "loss": 0.0911, + "step": 408860 + }, + { + "epoch": 0.91, + "learning_rate": 4.397888190420796e-06, + "loss": 0.092, + "step": 408870 + }, + { + "epoch": 0.91, + "learning_rate": 4.396769647211472e-06, + "loss": 0.089, + "step": 408880 + }, + { + "epoch": 0.91, + "learning_rate": 4.395651104002148e-06, + "loss": 0.0911, + "step": 408890 + }, + { + "epoch": 0.91, + "learning_rate": 4.394532560792824e-06, + "loss": 0.0893, + "step": 408900 + }, + { + "epoch": 0.91, + "learning_rate": 4.3934140175834995e-06, + "loss": 0.0883, + "step": 408910 + }, + { + "epoch": 0.91, + "learning_rate": 4.392295474374175e-06, + "loss": 0.0932, + "step": 408920 + }, + { + "epoch": 0.91, + "learning_rate": 4.391176931164851e-06, + "loss": 0.09, + "step": 408930 + }, + { + "epoch": 0.91, + "learning_rate": 4.390058387955527e-06, + "loss": 0.0903, + "step": 408940 + }, + { + "epoch": 0.91, + "learning_rate": 4.388939844746203e-06, + "loss": 0.0948, + "step": 408950 + }, + { + "epoch": 0.91, + "learning_rate": 4.387821301536878e-06, + "loss": 0.0942, + "step": 408960 + }, + { + "epoch": 0.91, + "learning_rate": 4.386702758327554e-06, + "loss": 0.0933, + "step": 408970 + }, + { + "epoch": 0.91, + "learning_rate": 4.3855842151182306e-06, + "loss": 0.0893, + "step": 408980 + }, + { + "epoch": 0.91, + "learning_rate": 4.384465671908907e-06, + "loss": 0.0876, + "step": 408990 + }, + { + "epoch": 0.91, + "learning_rate": 4.383347128699581e-06, + "loss": 0.0855, + "step": 409000 + }, + { + "epoch": 0.91, + "learning_rate": 4.3822285854902576e-06, + "loss": 0.0911, + "step": 409010 + }, + { + "epoch": 0.91, + "learning_rate": 4.381110042280934e-06, + "loss": 0.0886, + "step": 409020 + }, + { + "epoch": 0.91, + "learning_rate": 4.37999149907161e-06, + "loss": 0.0958, + "step": 409030 + }, + { + "epoch": 0.91, + "learning_rate": 4.378872955862285e-06, + "loss": 0.0924, + "step": 409040 + }, + { + "epoch": 0.91, + "learning_rate": 4.377754412652961e-06, + "loss": 0.0906, + "step": 409050 + }, + { + "epoch": 0.91, + "learning_rate": 4.376635869443637e-06, + "loss": 0.0948, + "step": 409060 + }, + { + "epoch": 0.91, + "learning_rate": 4.375517326234313e-06, + "loss": 0.0906, + "step": 409070 + }, + { + "epoch": 0.91, + "learning_rate": 4.374398783024989e-06, + "loss": 0.0894, + "step": 409080 + }, + { + "epoch": 0.91, + "learning_rate": 4.373280239815664e-06, + "loss": 0.0928, + "step": 409090 + }, + { + "epoch": 0.91, + "learning_rate": 4.37216169660634e-06, + "loss": 0.0928, + "step": 409100 + }, + { + "epoch": 0.91, + "learning_rate": 4.3710431533970165e-06, + "loss": 0.0924, + "step": 409110 + }, + { + "epoch": 0.91, + "learning_rate": 4.369924610187692e-06, + "loss": 0.0892, + "step": 409120 + }, + { + "epoch": 0.91, + "learning_rate": 4.368806066978367e-06, + "loss": 0.0915, + "step": 409130 + }, + { + "epoch": 0.91, + "learning_rate": 4.3676875237690435e-06, + "loss": 0.0902, + "step": 409140 + }, + { + "epoch": 0.91, + "learning_rate": 4.366568980559719e-06, + "loss": 0.095, + "step": 409150 + }, + { + "epoch": 0.91, + "learning_rate": 4.365450437350395e-06, + "loss": 0.0935, + "step": 409160 + }, + { + "epoch": 0.91, + "learning_rate": 4.3643318941410705e-06, + "loss": 0.0899, + "step": 409170 + }, + { + "epoch": 0.91, + "learning_rate": 4.363213350931747e-06, + "loss": 0.0898, + "step": 409180 + }, + { + "epoch": 0.91, + "learning_rate": 4.362094807722422e-06, + "loss": 0.0951, + "step": 409190 + }, + { + "epoch": 0.91, + "learning_rate": 4.360976264513098e-06, + "loss": 0.0895, + "step": 409200 + }, + { + "epoch": 0.91, + "learning_rate": 4.359857721303774e-06, + "loss": 0.0913, + "step": 409210 + }, + { + "epoch": 0.91, + "learning_rate": 4.35873917809445e-06, + "loss": 0.0946, + "step": 409220 + }, + { + "epoch": 0.91, + "learning_rate": 4.357620634885125e-06, + "loss": 0.0951, + "step": 409230 + }, + { + "epoch": 0.91, + "learning_rate": 4.356502091675802e-06, + "loss": 0.0937, + "step": 409240 + }, + { + "epoch": 0.91, + "learning_rate": 4.355383548466478e-06, + "loss": 0.093, + "step": 409250 + }, + { + "epoch": 0.91, + "learning_rate": 4.354265005257153e-06, + "loss": 0.0971, + "step": 409260 + }, + { + "epoch": 0.91, + "learning_rate": 4.353146462047829e-06, + "loss": 0.0926, + "step": 409270 + }, + { + "epoch": 0.91, + "learning_rate": 4.352027918838505e-06, + "loss": 0.0955, + "step": 409280 + }, + { + "epoch": 0.91, + "learning_rate": 4.350909375629181e-06, + "loss": 0.0925, + "step": 409290 + }, + { + "epoch": 0.91, + "learning_rate": 4.3497908324198565e-06, + "loss": 0.0965, + "step": 409300 + }, + { + "epoch": 0.91, + "learning_rate": 4.348672289210532e-06, + "loss": 0.0953, + "step": 409310 + }, + { + "epoch": 0.91, + "learning_rate": 4.347553746001208e-06, + "loss": 0.097, + "step": 409320 + }, + { + "epoch": 0.91, + "learning_rate": 4.346435202791884e-06, + "loss": 0.0916, + "step": 409330 + }, + { + "epoch": 0.91, + "learning_rate": 4.34531665958256e-06, + "loss": 0.0947, + "step": 409340 + }, + { + "epoch": 0.91, + "learning_rate": 4.344198116373235e-06, + "loss": 0.0968, + "step": 409350 + }, + { + "epoch": 0.91, + "learning_rate": 4.343079573163911e-06, + "loss": 0.0923, + "step": 409360 + }, + { + "epoch": 0.91, + "learning_rate": 4.341961029954588e-06, + "loss": 0.0935, + "step": 409370 + }, + { + "epoch": 0.91, + "learning_rate": 4.340842486745263e-06, + "loss": 0.0941, + "step": 409380 + }, + { + "epoch": 0.91, + "learning_rate": 4.339723943535938e-06, + "loss": 0.0906, + "step": 409390 + }, + { + "epoch": 0.91, + "learning_rate": 4.338605400326615e-06, + "loss": 0.0942, + "step": 409400 + }, + { + "epoch": 0.91, + "learning_rate": 4.337486857117291e-06, + "loss": 0.0934, + "step": 409410 + }, + { + "epoch": 0.91, + "learning_rate": 4.336368313907967e-06, + "loss": 0.0974, + "step": 409420 + }, + { + "epoch": 0.91, + "learning_rate": 4.335249770698642e-06, + "loss": 0.0957, + "step": 409430 + }, + { + "epoch": 0.91, + "learning_rate": 4.334131227489318e-06, + "loss": 0.095, + "step": 409440 + }, + { + "epoch": 0.91, + "learning_rate": 4.333012684279994e-06, + "loss": 0.0928, + "step": 409450 + }, + { + "epoch": 0.91, + "learning_rate": 4.33189414107067e-06, + "loss": 0.0944, + "step": 409460 + }, + { + "epoch": 0.91, + "learning_rate": 4.330775597861346e-06, + "loss": 0.0935, + "step": 409470 + }, + { + "epoch": 0.91, + "learning_rate": 4.329657054652021e-06, + "loss": 0.1002, + "step": 409480 + }, + { + "epoch": 0.91, + "learning_rate": 4.328538511442697e-06, + "loss": 0.0945, + "step": 409490 + }, + { + "epoch": 0.91, + "learning_rate": 4.3274199682333735e-06, + "loss": 0.0974, + "step": 409500 + }, + { + "epoch": 0.91, + "learning_rate": 4.326301425024049e-06, + "loss": 0.0971, + "step": 409510 + }, + { + "epoch": 0.91, + "learning_rate": 4.325182881814724e-06, + "loss": 0.0916, + "step": 409520 + }, + { + "epoch": 0.91, + "learning_rate": 4.3240643386054005e-06, + "loss": 0.0955, + "step": 409530 + }, + { + "epoch": 0.91, + "learning_rate": 4.322945795396077e-06, + "loss": 0.0953, + "step": 409540 + }, + { + "epoch": 0.91, + "learning_rate": 4.321827252186752e-06, + "loss": 0.0946, + "step": 409550 + }, + { + "epoch": 0.91, + "learning_rate": 4.3207087089774275e-06, + "loss": 0.0983, + "step": 409560 + }, + { + "epoch": 0.91, + "learning_rate": 4.319590165768104e-06, + "loss": 0.0946, + "step": 409570 + }, + { + "epoch": 0.91, + "learning_rate": 4.31847162255878e-06, + "loss": 0.099, + "step": 409580 + }, + { + "epoch": 0.91, + "learning_rate": 4.317353079349455e-06, + "loss": 0.0942, + "step": 409590 + }, + { + "epoch": 0.91, + "learning_rate": 4.316234536140131e-06, + "loss": 0.0934, + "step": 409600 + }, + { + "epoch": 0.91, + "learning_rate": 4.315115992930807e-06, + "loss": 0.0917, + "step": 409610 + }, + { + "epoch": 0.91, + "learning_rate": 4.313997449721483e-06, + "loss": 0.0938, + "step": 409620 + }, + { + "epoch": 0.91, + "learning_rate": 4.312878906512159e-06, + "loss": 0.0969, + "step": 409630 + }, + { + "epoch": 0.91, + "learning_rate": 4.311760363302834e-06, + "loss": 0.0934, + "step": 409640 + }, + { + "epoch": 0.91, + "learning_rate": 4.31064182009351e-06, + "loss": 0.093, + "step": 409650 + }, + { + "epoch": 0.91, + "learning_rate": 4.3095232768841865e-06, + "loss": 0.0909, + "step": 409660 + }, + { + "epoch": 0.91, + "learning_rate": 4.308404733674862e-06, + "loss": 0.0948, + "step": 409670 + }, + { + "epoch": 0.91, + "learning_rate": 4.307286190465538e-06, + "loss": 0.0956, + "step": 409680 + }, + { + "epoch": 0.91, + "learning_rate": 4.3061676472562135e-06, + "loss": 0.0904, + "step": 409690 + }, + { + "epoch": 0.91, + "learning_rate": 4.30504910404689e-06, + "loss": 0.0915, + "step": 409700 + }, + { + "epoch": 0.91, + "learning_rate": 4.303930560837565e-06, + "loss": 0.0936, + "step": 409710 + }, + { + "epoch": 0.91, + "learning_rate": 4.302812017628241e-06, + "loss": 0.0947, + "step": 409720 + }, + { + "epoch": 0.91, + "learning_rate": 4.301693474418917e-06, + "loss": 0.0932, + "step": 409730 + }, + { + "epoch": 0.91, + "learning_rate": 4.300574931209593e-06, + "loss": 0.0912, + "step": 409740 + }, + { + "epoch": 0.91, + "learning_rate": 4.299456388000268e-06, + "loss": 0.097, + "step": 409750 + }, + { + "epoch": 0.91, + "learning_rate": 4.298337844790945e-06, + "loss": 0.0941, + "step": 409760 + }, + { + "epoch": 0.91, + "learning_rate": 4.29721930158162e-06, + "loss": 0.0915, + "step": 409770 + }, + { + "epoch": 0.91, + "learning_rate": 4.296100758372296e-06, + "loss": 0.0926, + "step": 409780 + }, + { + "epoch": 0.91, + "learning_rate": 4.294982215162972e-06, + "loss": 0.0928, + "step": 409790 + }, + { + "epoch": 0.91, + "learning_rate": 4.293863671953648e-06, + "loss": 0.0935, + "step": 409800 + }, + { + "epoch": 0.91, + "learning_rate": 4.292745128744323e-06, + "loss": 0.0958, + "step": 409810 + }, + { + "epoch": 0.91, + "learning_rate": 4.2916265855349995e-06, + "loss": 0.094, + "step": 409820 + }, + { + "epoch": 0.91, + "learning_rate": 4.290508042325675e-06, + "loss": 0.0959, + "step": 409830 + }, + { + "epoch": 0.91, + "learning_rate": 4.289389499116351e-06, + "loss": 0.0907, + "step": 409840 + }, + { + "epoch": 0.91, + "learning_rate": 4.288270955907027e-06, + "loss": 0.0913, + "step": 409850 + }, + { + "epoch": 0.91, + "learning_rate": 4.287152412697703e-06, + "loss": 0.0953, + "step": 409860 + }, + { + "epoch": 0.91, + "learning_rate": 4.286033869488378e-06, + "loss": 0.0945, + "step": 409870 + }, + { + "epoch": 0.91, + "learning_rate": 4.284915326279054e-06, + "loss": 0.0939, + "step": 409880 + }, + { + "epoch": 0.91, + "learning_rate": 4.2837967830697306e-06, + "loss": 0.092, + "step": 409890 + }, + { + "epoch": 0.91, + "learning_rate": 4.2827900941813385e-06, + "loss": 0.0944, + "step": 409900 + }, + { + "epoch": 0.91, + "learning_rate": 4.281671550972014e-06, + "loss": 0.0952, + "step": 409910 + }, + { + "epoch": 0.91, + "learning_rate": 4.28055300776269e-06, + "loss": 0.0967, + "step": 409920 + }, + { + "epoch": 0.92, + "learning_rate": 4.279434464553366e-06, + "loss": 0.0925, + "step": 409930 + }, + { + "epoch": 0.92, + "learning_rate": 4.278315921344042e-06, + "loss": 0.0961, + "step": 409940 + }, + { + "epoch": 0.92, + "learning_rate": 4.277197378134717e-06, + "loss": 0.0921, + "step": 409950 + }, + { + "epoch": 0.92, + "learning_rate": 4.276078834925393e-06, + "loss": 0.0948, + "step": 409960 + }, + { + "epoch": 0.92, + "learning_rate": 4.27496029171607e-06, + "loss": 0.0962, + "step": 409970 + }, + { + "epoch": 0.92, + "learning_rate": 4.273841748506745e-06, + "loss": 0.0943, + "step": 409980 + }, + { + "epoch": 0.92, + "learning_rate": 4.27272320529742e-06, + "loss": 0.0955, + "step": 409990 + }, + { + "epoch": 0.92, + "learning_rate": 4.271604662088097e-06, + "loss": 0.0952, + "step": 410000 + }, + { + "epoch": 0.92, + "learning_rate": 4.270486118878773e-06, + "loss": 0.0955, + "step": 410010 + }, + { + "epoch": 0.92, + "learning_rate": 4.269367575669448e-06, + "loss": 0.0946, + "step": 410020 + }, + { + "epoch": 0.92, + "learning_rate": 4.2682490324601244e-06, + "loss": 0.0929, + "step": 410030 + }, + { + "epoch": 0.92, + "learning_rate": 4.2671304892508e-06, + "loss": 0.0929, + "step": 410040 + }, + { + "epoch": 0.92, + "learning_rate": 4.266011946041476e-06, + "loss": 0.095, + "step": 410050 + }, + { + "epoch": 0.92, + "learning_rate": 4.2648934028321514e-06, + "loss": 0.0949, + "step": 410060 + }, + { + "epoch": 0.92, + "learning_rate": 4.263774859622828e-06, + "loss": 0.0926, + "step": 410070 + }, + { + "epoch": 0.92, + "learning_rate": 4.262656316413503e-06, + "loss": 0.0908, + "step": 410080 + }, + { + "epoch": 0.92, + "learning_rate": 4.261537773204179e-06, + "loss": 0.0954, + "step": 410090 + }, + { + "epoch": 0.92, + "learning_rate": 4.260419229994855e-06, + "loss": 0.0988, + "step": 410100 + }, + { + "epoch": 0.92, + "learning_rate": 4.259300686785531e-06, + "loss": 0.0911, + "step": 410110 + }, + { + "epoch": 0.92, + "learning_rate": 4.258182143576206e-06, + "loss": 0.0945, + "step": 410120 + }, + { + "epoch": 0.92, + "learning_rate": 4.2570636003668825e-06, + "loss": 0.0928, + "step": 410130 + }, + { + "epoch": 0.92, + "learning_rate": 4.255945057157558e-06, + "loss": 0.0966, + "step": 410140 + }, + { + "epoch": 0.92, + "learning_rate": 4.254826513948234e-06, + "loss": 0.0889, + "step": 410150 + }, + { + "epoch": 0.92, + "learning_rate": 4.2537079707389095e-06, + "loss": 0.0952, + "step": 410160 + }, + { + "epoch": 0.92, + "learning_rate": 4.252589427529586e-06, + "loss": 0.0973, + "step": 410170 + }, + { + "epoch": 0.92, + "learning_rate": 4.251470884320261e-06, + "loss": 0.0897, + "step": 410180 + }, + { + "epoch": 0.92, + "learning_rate": 4.250352341110937e-06, + "loss": 0.0929, + "step": 410190 + }, + { + "epoch": 0.92, + "learning_rate": 4.249233797901614e-06, + "loss": 0.0941, + "step": 410200 + }, + { + "epoch": 0.92, + "learning_rate": 4.248115254692289e-06, + "loss": 0.0919, + "step": 410210 + }, + { + "epoch": 0.92, + "learning_rate": 4.246996711482964e-06, + "loss": 0.0906, + "step": 410220 + }, + { + "epoch": 0.92, + "learning_rate": 4.245878168273641e-06, + "loss": 0.0964, + "step": 410230 + }, + { + "epoch": 0.92, + "learning_rate": 4.244759625064317e-06, + "loss": 0.0942, + "step": 410240 + }, + { + "epoch": 0.92, + "learning_rate": 4.243641081854992e-06, + "loss": 0.0917, + "step": 410250 + }, + { + "epoch": 0.92, + "learning_rate": 4.242522538645668e-06, + "loss": 0.0897, + "step": 410260 + }, + { + "epoch": 0.92, + "learning_rate": 4.241403995436344e-06, + "loss": 0.0975, + "step": 410270 + }, + { + "epoch": 0.92, + "learning_rate": 4.24028545222702e-06, + "loss": 0.0938, + "step": 410280 + }, + { + "epoch": 0.92, + "learning_rate": 4.2391669090176955e-06, + "loss": 0.0977, + "step": 410290 + }, + { + "epoch": 0.92, + "learning_rate": 4.238048365808371e-06, + "loss": 0.0957, + "step": 410300 + }, + { + "epoch": 0.92, + "learning_rate": 4.236929822599047e-06, + "loss": 0.0895, + "step": 410310 + }, + { + "epoch": 0.92, + "learning_rate": 4.235811279389723e-06, + "loss": 0.093, + "step": 410320 + }, + { + "epoch": 0.92, + "learning_rate": 4.234692736180399e-06, + "loss": 0.0922, + "step": 410330 + }, + { + "epoch": 0.92, + "learning_rate": 4.233574192971074e-06, + "loss": 0.0919, + "step": 410340 + }, + { + "epoch": 0.92, + "learning_rate": 4.23245564976175e-06, + "loss": 0.0977, + "step": 410350 + }, + { + "epoch": 0.92, + "learning_rate": 4.231337106552427e-06, + "loss": 0.0928, + "step": 410360 + }, + { + "epoch": 0.92, + "learning_rate": 4.230218563343102e-06, + "loss": 0.0941, + "step": 410370 + }, + { + "epoch": 0.92, + "learning_rate": 4.229100020133777e-06, + "loss": 0.0964, + "step": 410380 + }, + { + "epoch": 0.92, + "learning_rate": 4.227981476924454e-06, + "loss": 0.0926, + "step": 410390 + }, + { + "epoch": 0.92, + "learning_rate": 4.22686293371513e-06, + "loss": 0.0935, + "step": 410400 + }, + { + "epoch": 0.92, + "learning_rate": 4.225744390505806e-06, + "loss": 0.0934, + "step": 410410 + }, + { + "epoch": 0.92, + "learning_rate": 4.224625847296481e-06, + "loss": 0.0929, + "step": 410420 + }, + { + "epoch": 0.92, + "learning_rate": 4.223507304087157e-06, + "loss": 0.092, + "step": 410430 + }, + { + "epoch": 0.92, + "learning_rate": 4.222388760877833e-06, + "loss": 0.0953, + "step": 410440 + }, + { + "epoch": 0.92, + "learning_rate": 4.221270217668509e-06, + "loss": 0.092, + "step": 410450 + }, + { + "epoch": 0.92, + "learning_rate": 4.220151674459185e-06, + "loss": 0.0948, + "step": 410460 + }, + { + "epoch": 0.92, + "learning_rate": 4.21903313124986e-06, + "loss": 0.0921, + "step": 410470 + }, + { + "epoch": 0.92, + "learning_rate": 4.217914588040536e-06, + "loss": 0.0936, + "step": 410480 + }, + { + "epoch": 0.92, + "learning_rate": 4.2167960448312126e-06, + "loss": 0.0916, + "step": 410490 + }, + { + "epoch": 0.92, + "learning_rate": 4.215677501621888e-06, + "loss": 0.0918, + "step": 410500 + }, + { + "epoch": 0.92, + "learning_rate": 4.214558958412563e-06, + "loss": 0.0937, + "step": 410510 + }, + { + "epoch": 0.92, + "learning_rate": 4.2134404152032396e-06, + "loss": 0.0935, + "step": 410520 + }, + { + "epoch": 0.92, + "learning_rate": 4.212321871993916e-06, + "loss": 0.0937, + "step": 410530 + }, + { + "epoch": 0.92, + "learning_rate": 4.211203328784591e-06, + "loss": 0.0938, + "step": 410540 + }, + { + "epoch": 0.92, + "learning_rate": 4.2100847855752666e-06, + "loss": 0.0928, + "step": 410550 + }, + { + "epoch": 0.92, + "learning_rate": 4.208966242365943e-06, + "loss": 0.0949, + "step": 410560 + }, + { + "epoch": 0.92, + "learning_rate": 4.207847699156619e-06, + "loss": 0.0917, + "step": 410570 + }, + { + "epoch": 0.92, + "learning_rate": 4.206729155947294e-06, + "loss": 0.0937, + "step": 410580 + }, + { + "epoch": 0.92, + "learning_rate": 4.20561061273797e-06, + "loss": 0.0941, + "step": 410590 + }, + { + "epoch": 0.92, + "learning_rate": 4.204492069528646e-06, + "loss": 0.0962, + "step": 410600 + }, + { + "epoch": 0.92, + "learning_rate": 4.203373526319322e-06, + "loss": 0.0892, + "step": 410610 + }, + { + "epoch": 0.92, + "learning_rate": 4.202254983109998e-06, + "loss": 0.0944, + "step": 410620 + }, + { + "epoch": 0.92, + "learning_rate": 4.201136439900674e-06, + "loss": 0.0907, + "step": 410630 + }, + { + "epoch": 0.92, + "learning_rate": 4.200017896691349e-06, + "loss": 0.0937, + "step": 410640 + }, + { + "epoch": 0.92, + "learning_rate": 4.1988993534820255e-06, + "loss": 0.0927, + "step": 410650 + }, + { + "epoch": 0.92, + "learning_rate": 4.197780810272701e-06, + "loss": 0.0937, + "step": 410660 + }, + { + "epoch": 0.92, + "learning_rate": 4.196662267063377e-06, + "loss": 0.0906, + "step": 410670 + }, + { + "epoch": 0.92, + "learning_rate": 4.1955437238540525e-06, + "loss": 0.0948, + "step": 410680 + }, + { + "epoch": 0.92, + "learning_rate": 4.194425180644729e-06, + "loss": 0.0948, + "step": 410690 + }, + { + "epoch": 0.92, + "learning_rate": 4.193306637435404e-06, + "loss": 0.0937, + "step": 410700 + }, + { + "epoch": 0.92, + "learning_rate": 4.19218809422608e-06, + "loss": 0.0899, + "step": 410710 + }, + { + "epoch": 0.92, + "learning_rate": 4.191069551016756e-06, + "loss": 0.0939, + "step": 410720 + }, + { + "epoch": 0.92, + "learning_rate": 4.189951007807432e-06, + "loss": 0.0975, + "step": 410730 + }, + { + "epoch": 0.92, + "learning_rate": 4.188832464598107e-06, + "loss": 0.0939, + "step": 410740 + }, + { + "epoch": 0.92, + "learning_rate": 4.187713921388784e-06, + "loss": 0.0931, + "step": 410750 + }, + { + "epoch": 0.92, + "learning_rate": 4.186595378179459e-06, + "loss": 0.0953, + "step": 410760 + }, + { + "epoch": 0.92, + "learning_rate": 4.185476834970135e-06, + "loss": 0.0912, + "step": 410770 + }, + { + "epoch": 0.92, + "learning_rate": 4.184358291760811e-06, + "loss": 0.0986, + "step": 410780 + }, + { + "epoch": 0.92, + "learning_rate": 4.183239748551487e-06, + "loss": 0.0971, + "step": 410790 + }, + { + "epoch": 0.92, + "learning_rate": 4.182121205342163e-06, + "loss": 0.091, + "step": 410800 + }, + { + "epoch": 0.92, + "learning_rate": 4.1810026621328385e-06, + "loss": 0.0934, + "step": 410810 + }, + { + "epoch": 0.92, + "learning_rate": 4.179884118923514e-06, + "loss": 0.0891, + "step": 410820 + }, + { + "epoch": 0.92, + "learning_rate": 4.17876557571419e-06, + "loss": 0.093, + "step": 410830 + }, + { + "epoch": 0.92, + "learning_rate": 4.177647032504866e-06, + "loss": 0.0916, + "step": 410840 + }, + { + "epoch": 0.92, + "learning_rate": 4.176528489295542e-06, + "loss": 0.0922, + "step": 410850 + }, + { + "epoch": 0.92, + "learning_rate": 4.175409946086217e-06, + "loss": 0.0928, + "step": 410860 + }, + { + "epoch": 0.92, + "learning_rate": 4.174291402876893e-06, + "loss": 0.0944, + "step": 410870 + }, + { + "epoch": 0.92, + "learning_rate": 4.1731728596675696e-06, + "loss": 0.092, + "step": 410880 + }, + { + "epoch": 0.92, + "learning_rate": 4.172054316458245e-06, + "loss": 0.0956, + "step": 410890 + }, + { + "epoch": 0.92, + "learning_rate": 4.17093577324892e-06, + "loss": 0.0889, + "step": 410900 + }, + { + "epoch": 0.92, + "learning_rate": 4.1698172300395966e-06, + "loss": 0.0919, + "step": 410910 + }, + { + "epoch": 0.92, + "learning_rate": 4.168698686830273e-06, + "loss": 0.094, + "step": 410920 + }, + { + "epoch": 0.92, + "learning_rate": 4.167580143620948e-06, + "loss": 0.0942, + "step": 410930 + }, + { + "epoch": 0.92, + "learning_rate": 4.166461600411624e-06, + "loss": 0.091, + "step": 410940 + }, + { + "epoch": 0.92, + "learning_rate": 4.1653430572023e-06, + "loss": 0.0914, + "step": 410950 + }, + { + "epoch": 0.92, + "learning_rate": 4.164224513992976e-06, + "loss": 0.0918, + "step": 410960 + }, + { + "epoch": 0.92, + "learning_rate": 4.1631059707836514e-06, + "loss": 0.0917, + "step": 410970 + }, + { + "epoch": 0.92, + "learning_rate": 4.161987427574327e-06, + "loss": 0.0938, + "step": 410980 + }, + { + "epoch": 0.92, + "learning_rate": 4.160868884365003e-06, + "loss": 0.0928, + "step": 410990 + }, + { + "epoch": 0.92, + "learning_rate": 4.159750341155679e-06, + "loss": 0.0977, + "step": 411000 + }, + { + "epoch": 0.92, + "learning_rate": 4.1586317979463555e-06, + "loss": 0.094, + "step": 411010 + }, + { + "epoch": 0.92, + "learning_rate": 4.15751325473703e-06, + "loss": 0.0939, + "step": 411020 + }, + { + "epoch": 0.92, + "learning_rate": 4.156394711527706e-06, + "loss": 0.0924, + "step": 411030 + }, + { + "epoch": 0.92, + "learning_rate": 4.1552761683183825e-06, + "loss": 0.0954, + "step": 411040 + }, + { + "epoch": 0.92, + "learning_rate": 4.154157625109059e-06, + "loss": 0.0932, + "step": 411050 + }, + { + "epoch": 0.92, + "learning_rate": 4.153039081899734e-06, + "loss": 0.0898, + "step": 411060 + }, + { + "epoch": 0.92, + "learning_rate": 4.1519205386904095e-06, + "loss": 0.095, + "step": 411070 + }, + { + "epoch": 0.92, + "learning_rate": 4.150801995481086e-06, + "loss": 0.096, + "step": 411080 + }, + { + "epoch": 0.92, + "learning_rate": 4.149683452271762e-06, + "loss": 0.0993, + "step": 411090 + }, + { + "epoch": 0.92, + "learning_rate": 4.148564909062437e-06, + "loss": 0.0915, + "step": 411100 + }, + { + "epoch": 0.92, + "learning_rate": 4.147446365853113e-06, + "loss": 0.0955, + "step": 411110 + }, + { + "epoch": 0.92, + "learning_rate": 4.146327822643789e-06, + "loss": 0.091, + "step": 411120 + }, + { + "epoch": 0.92, + "learning_rate": 4.145209279434465e-06, + "loss": 0.0938, + "step": 411130 + }, + { + "epoch": 0.92, + "learning_rate": 4.144090736225141e-06, + "loss": 0.09, + "step": 411140 + }, + { + "epoch": 0.92, + "learning_rate": 4.142972193015816e-06, + "loss": 0.0916, + "step": 411150 + }, + { + "epoch": 0.92, + "learning_rate": 4.141853649806492e-06, + "loss": 0.0923, + "step": 411160 + }, + { + "epoch": 0.92, + "learning_rate": 4.1407351065971685e-06, + "loss": 0.0952, + "step": 411170 + }, + { + "epoch": 0.92, + "learning_rate": 4.139616563387844e-06, + "loss": 0.0926, + "step": 411180 + }, + { + "epoch": 0.92, + "learning_rate": 4.138498020178519e-06, + "loss": 0.0951, + "step": 411190 + }, + { + "epoch": 0.92, + "learning_rate": 4.1373794769691955e-06, + "loss": 0.0949, + "step": 411200 + }, + { + "epoch": 0.92, + "learning_rate": 4.136260933759872e-06, + "loss": 0.094, + "step": 411210 + }, + { + "epoch": 0.92, + "learning_rate": 4.135142390550547e-06, + "loss": 0.0919, + "step": 411220 + }, + { + "epoch": 0.92, + "learning_rate": 4.134023847341223e-06, + "loss": 0.0938, + "step": 411230 + }, + { + "epoch": 0.92, + "learning_rate": 4.132905304131899e-06, + "loss": 0.0962, + "step": 411240 + }, + { + "epoch": 0.92, + "learning_rate": 4.131786760922575e-06, + "loss": 0.0897, + "step": 411250 + }, + { + "epoch": 0.92, + "learning_rate": 4.13066821771325e-06, + "loss": 0.0925, + "step": 411260 + }, + { + "epoch": 0.92, + "learning_rate": 4.129549674503927e-06, + "loss": 0.0947, + "step": 411270 + }, + { + "epoch": 0.92, + "learning_rate": 4.128431131294602e-06, + "loss": 0.0967, + "step": 411280 + }, + { + "epoch": 0.92, + "learning_rate": 4.127312588085278e-06, + "loss": 0.0921, + "step": 411290 + }, + { + "epoch": 0.92, + "learning_rate": 4.126194044875954e-06, + "loss": 0.093, + "step": 411300 + }, + { + "epoch": 0.92, + "learning_rate": 4.12507550166663e-06, + "loss": 0.0929, + "step": 411310 + }, + { + "epoch": 0.92, + "learning_rate": 4.123956958457305e-06, + "loss": 0.0963, + "step": 411320 + }, + { + "epoch": 0.92, + "learning_rate": 4.1228384152479814e-06, + "loss": 0.0904, + "step": 411330 + }, + { + "epoch": 0.92, + "learning_rate": 4.121719872038657e-06, + "loss": 0.0909, + "step": 411340 + }, + { + "epoch": 0.92, + "learning_rate": 4.120601328829333e-06, + "loss": 0.0965, + "step": 411350 + }, + { + "epoch": 0.92, + "learning_rate": 4.1194827856200085e-06, + "loss": 0.0913, + "step": 411360 + }, + { + "epoch": 0.92, + "learning_rate": 4.118364242410685e-06, + "loss": 0.0876, + "step": 411370 + }, + { + "epoch": 0.92, + "learning_rate": 4.11724569920136e-06, + "loss": 0.0955, + "step": 411380 + }, + { + "epoch": 0.92, + "learning_rate": 4.116127155992036e-06, + "loss": 0.0892, + "step": 411390 + }, + { + "epoch": 0.92, + "learning_rate": 4.1150086127827125e-06, + "loss": 0.093, + "step": 411400 + }, + { + "epoch": 0.92, + "learning_rate": 4.113890069573388e-06, + "loss": 0.0923, + "step": 411410 + }, + { + "epoch": 0.92, + "learning_rate": 4.112771526364063e-06, + "loss": 0.0937, + "step": 411420 + }, + { + "epoch": 0.92, + "learning_rate": 4.1116529831547395e-06, + "loss": 0.093, + "step": 411430 + }, + { + "epoch": 0.92, + "learning_rate": 4.110534439945416e-06, + "loss": 0.0956, + "step": 411440 + }, + { + "epoch": 0.92, + "learning_rate": 4.109415896736091e-06, + "loss": 0.0932, + "step": 411450 + }, + { + "epoch": 0.92, + "learning_rate": 4.1082973535267666e-06, + "loss": 0.0956, + "step": 411460 + }, + { + "epoch": 0.92, + "learning_rate": 4.107178810317443e-06, + "loss": 0.0931, + "step": 411470 + }, + { + "epoch": 0.92, + "learning_rate": 4.106060267108119e-06, + "loss": 0.0972, + "step": 411480 + }, + { + "epoch": 0.92, + "learning_rate": 4.104941723898794e-06, + "loss": 0.0926, + "step": 411490 + }, + { + "epoch": 0.92, + "learning_rate": 4.10382318068947e-06, + "loss": 0.0971, + "step": 411500 + }, + { + "epoch": 0.92, + "learning_rate": 4.102704637480146e-06, + "loss": 0.0932, + "step": 411510 + }, + { + "epoch": 0.92, + "learning_rate": 4.101586094270822e-06, + "loss": 0.0923, + "step": 411520 + }, + { + "epoch": 0.92, + "learning_rate": 4.100467551061498e-06, + "loss": 0.0921, + "step": 411530 + }, + { + "epoch": 0.92, + "learning_rate": 4.099349007852173e-06, + "loss": 0.0917, + "step": 411540 + }, + { + "epoch": 0.92, + "learning_rate": 4.098230464642849e-06, + "loss": 0.0942, + "step": 411550 + }, + { + "epoch": 0.92, + "learning_rate": 4.0971119214335255e-06, + "loss": 0.0945, + "step": 411560 + }, + { + "epoch": 0.92, + "learning_rate": 4.095993378224202e-06, + "loss": 0.101, + "step": 411570 + }, + { + "epoch": 0.92, + "learning_rate": 4.094874835014876e-06, + "loss": 0.0915, + "step": 411580 + }, + { + "epoch": 0.92, + "learning_rate": 4.0937562918055525e-06, + "loss": 0.0931, + "step": 411590 + }, + { + "epoch": 0.92, + "learning_rate": 4.092637748596229e-06, + "loss": 0.0957, + "step": 411600 + }, + { + "epoch": 0.92, + "learning_rate": 4.091519205386905e-06, + "loss": 0.0893, + "step": 411610 + }, + { + "epoch": 0.92, + "learning_rate": 4.0904006621775795e-06, + "loss": 0.0927, + "step": 411620 + }, + { + "epoch": 0.92, + "learning_rate": 4.089282118968256e-06, + "loss": 0.0889, + "step": 411630 + }, + { + "epoch": 0.92, + "learning_rate": 4.088163575758932e-06, + "loss": 0.0897, + "step": 411640 + }, + { + "epoch": 0.92, + "learning_rate": 4.087045032549608e-06, + "loss": 0.0927, + "step": 411650 + }, + { + "epoch": 0.92, + "learning_rate": 4.085926489340284e-06, + "loss": 0.0871, + "step": 411660 + }, + { + "epoch": 0.92, + "learning_rate": 4.084807946130959e-06, + "loss": 0.0919, + "step": 411670 + }, + { + "epoch": 0.92, + "learning_rate": 4.083689402921635e-06, + "loss": 0.0846, + "step": 411680 + }, + { + "epoch": 0.92, + "learning_rate": 4.0825708597123115e-06, + "loss": 0.0928, + "step": 411690 + }, + { + "epoch": 0.92, + "learning_rate": 4.081452316502987e-06, + "loss": 0.0919, + "step": 411700 + }, + { + "epoch": 0.92, + "learning_rate": 4.080333773293662e-06, + "loss": 0.0947, + "step": 411710 + }, + { + "epoch": 0.92, + "learning_rate": 4.0792152300843385e-06, + "loss": 0.0908, + "step": 411720 + }, + { + "epoch": 0.92, + "learning_rate": 4.078096686875015e-06, + "loss": 0.0981, + "step": 411730 + }, + { + "epoch": 0.92, + "learning_rate": 4.07697814366569e-06, + "loss": 0.0926, + "step": 411740 + }, + { + "epoch": 0.92, + "learning_rate": 4.0758596004563655e-06, + "loss": 0.0969, + "step": 411750 + }, + { + "epoch": 0.92, + "learning_rate": 4.074741057247042e-06, + "loss": 0.0945, + "step": 411760 + }, + { + "epoch": 0.92, + "learning_rate": 4.073622514037718e-06, + "loss": 0.0927, + "step": 411770 + }, + { + "epoch": 0.92, + "learning_rate": 4.072503970828393e-06, + "loss": 0.0903, + "step": 411780 + }, + { + "epoch": 0.92, + "learning_rate": 4.071385427619069e-06, + "loss": 0.0951, + "step": 411790 + }, + { + "epoch": 0.92, + "learning_rate": 4.070266884409745e-06, + "loss": 0.0958, + "step": 411800 + }, + { + "epoch": 0.92, + "learning_rate": 4.069148341200421e-06, + "loss": 0.0917, + "step": 411810 + }, + { + "epoch": 0.92, + "learning_rate": 4.0680297979910966e-06, + "loss": 0.0931, + "step": 411820 + }, + { + "epoch": 0.92, + "learning_rate": 4.066911254781773e-06, + "loss": 0.0945, + "step": 411830 + }, + { + "epoch": 0.92, + "learning_rate": 4.065792711572448e-06, + "loss": 0.093, + "step": 411840 + }, + { + "epoch": 0.92, + "learning_rate": 4.064674168363124e-06, + "loss": 0.0866, + "step": 411850 + }, + { + "epoch": 0.92, + "learning_rate": 4.0635556251538e-06, + "loss": 0.0946, + "step": 411860 + }, + { + "epoch": 0.92, + "learning_rate": 4.062437081944476e-06, + "loss": 0.0902, + "step": 411870 + }, + { + "epoch": 0.92, + "learning_rate": 4.0613185387351514e-06, + "loss": 0.0929, + "step": 411880 + }, + { + "epoch": 0.92, + "learning_rate": 4.060199995525828e-06, + "loss": 0.093, + "step": 411890 + }, + { + "epoch": 0.92, + "learning_rate": 4.059081452316503e-06, + "loss": 0.0929, + "step": 411900 + }, + { + "epoch": 0.92, + "learning_rate": 4.057962909107179e-06, + "loss": 0.0924, + "step": 411910 + }, + { + "epoch": 0.92, + "learning_rate": 4.056844365897855e-06, + "loss": 0.0908, + "step": 411920 + }, + { + "epoch": 0.92, + "learning_rate": 4.055725822688531e-06, + "loss": 0.0909, + "step": 411930 + }, + { + "epoch": 0.92, + "learning_rate": 4.054607279479206e-06, + "loss": 0.094, + "step": 411940 + }, + { + "epoch": 0.92, + "learning_rate": 4.0534887362698825e-06, + "loss": 0.0936, + "step": 411950 + }, + { + "epoch": 0.92, + "learning_rate": 4.0524820473814905e-06, + "loss": 0.0897, + "step": 411960 + }, + { + "epoch": 0.92, + "learning_rate": 4.051363504172166e-06, + "loss": 0.0942, + "step": 411970 + }, + { + "epoch": 0.92, + "learning_rate": 4.050244960962842e-06, + "loss": 0.0912, + "step": 411980 + }, + { + "epoch": 0.92, + "learning_rate": 4.049126417753518e-06, + "loss": 0.092, + "step": 411990 + }, + { + "epoch": 0.92, + "learning_rate": 4.048007874544194e-06, + "loss": 0.0976, + "step": 412000 + }, + { + "epoch": 0.92, + "learning_rate": 4.046889331334869e-06, + "loss": 0.097, + "step": 412010 + }, + { + "epoch": 0.92, + "learning_rate": 4.045770788125545e-06, + "loss": 0.094, + "step": 412020 + }, + { + "epoch": 0.92, + "learning_rate": 4.0446522449162215e-06, + "loss": 0.0895, + "step": 412030 + }, + { + "epoch": 0.92, + "learning_rate": 4.043533701706897e-06, + "loss": 0.0959, + "step": 412040 + }, + { + "epoch": 0.92, + "learning_rate": 4.042415158497573e-06, + "loss": 0.0938, + "step": 412050 + }, + { + "epoch": 0.92, + "learning_rate": 4.0412966152882486e-06, + "loss": 0.0959, + "step": 412060 + }, + { + "epoch": 0.92, + "learning_rate": 4.040178072078925e-06, + "loss": 0.0938, + "step": 412070 + }, + { + "epoch": 0.92, + "learning_rate": 4.0390595288696e-06, + "loss": 0.0935, + "step": 412080 + }, + { + "epoch": 0.92, + "learning_rate": 4.037940985660276e-06, + "loss": 0.0914, + "step": 412090 + }, + { + "epoch": 0.92, + "learning_rate": 4.036822442450952e-06, + "loss": 0.0926, + "step": 412100 + }, + { + "epoch": 0.92, + "learning_rate": 4.035703899241628e-06, + "loss": 0.0932, + "step": 412110 + }, + { + "epoch": 0.92, + "learning_rate": 4.034585356032303e-06, + "loss": 0.0898, + "step": 412120 + }, + { + "epoch": 0.92, + "learning_rate": 4.03346681282298e-06, + "loss": 0.0932, + "step": 412130 + }, + { + "epoch": 0.92, + "learning_rate": 4.032348269613655e-06, + "loss": 0.093, + "step": 412140 + }, + { + "epoch": 0.92, + "learning_rate": 4.031229726404331e-06, + "loss": 0.0922, + "step": 412150 + }, + { + "epoch": 0.92, + "learning_rate": 4.030111183195007e-06, + "loss": 0.0883, + "step": 412160 + }, + { + "epoch": 0.92, + "learning_rate": 4.028992639985683e-06, + "loss": 0.0967, + "step": 412170 + }, + { + "epoch": 0.92, + "learning_rate": 4.027874096776358e-06, + "loss": 0.0945, + "step": 412180 + }, + { + "epoch": 0.92, + "learning_rate": 4.0267555535670345e-06, + "loss": 0.093, + "step": 412190 + }, + { + "epoch": 0.92, + "learning_rate": 4.02563701035771e-06, + "loss": 0.0907, + "step": 412200 + }, + { + "epoch": 0.92, + "learning_rate": 4.024518467148386e-06, + "loss": 0.0964, + "step": 412210 + }, + { + "epoch": 0.92, + "learning_rate": 4.023399923939062e-06, + "loss": 0.098, + "step": 412220 + }, + { + "epoch": 0.92, + "learning_rate": 4.022281380729738e-06, + "loss": 0.0927, + "step": 412230 + }, + { + "epoch": 0.92, + "learning_rate": 4.021162837520413e-06, + "loss": 0.0923, + "step": 412240 + }, + { + "epoch": 0.92, + "learning_rate": 4.020044294311089e-06, + "loss": 0.0943, + "step": 412250 + }, + { + "epoch": 0.92, + "learning_rate": 4.018925751101766e-06, + "loss": 0.095, + "step": 412260 + }, + { + "epoch": 0.92, + "learning_rate": 4.017807207892441e-06, + "loss": 0.0957, + "step": 412270 + }, + { + "epoch": 0.92, + "learning_rate": 4.016688664683116e-06, + "loss": 0.0932, + "step": 412280 + }, + { + "epoch": 0.92, + "learning_rate": 4.015570121473793e-06, + "loss": 0.0955, + "step": 412290 + }, + { + "epoch": 0.92, + "learning_rate": 4.014451578264469e-06, + "loss": 0.0967, + "step": 412300 + }, + { + "epoch": 0.92, + "learning_rate": 4.013333035055144e-06, + "loss": 0.0942, + "step": 412310 + }, + { + "epoch": 0.92, + "learning_rate": 4.01221449184582e-06, + "loss": 0.091, + "step": 412320 + }, + { + "epoch": 0.92, + "learning_rate": 4.011095948636496e-06, + "loss": 0.0955, + "step": 412330 + }, + { + "epoch": 0.92, + "learning_rate": 4.009977405427172e-06, + "loss": 0.0913, + "step": 412340 + }, + { + "epoch": 0.92, + "learning_rate": 4.0088588622178475e-06, + "loss": 0.0922, + "step": 412350 + }, + { + "epoch": 0.92, + "learning_rate": 4.007740319008523e-06, + "loss": 0.0917, + "step": 412360 + }, + { + "epoch": 0.92, + "learning_rate": 4.006621775799199e-06, + "loss": 0.0902, + "step": 412370 + }, + { + "epoch": 0.92, + "learning_rate": 4.005503232589875e-06, + "loss": 0.09, + "step": 412380 + }, + { + "epoch": 0.92, + "learning_rate": 4.0043846893805516e-06, + "loss": 0.0949, + "step": 412390 + }, + { + "epoch": 0.92, + "learning_rate": 4.003266146171226e-06, + "loss": 0.0915, + "step": 412400 + }, + { + "epoch": 0.92, + "learning_rate": 4.002147602961902e-06, + "loss": 0.0895, + "step": 412410 + }, + { + "epoch": 0.92, + "learning_rate": 4.0010290597525786e-06, + "loss": 0.0903, + "step": 412420 + }, + { + "epoch": 0.92, + "learning_rate": 3.999910516543255e-06, + "loss": 0.0897, + "step": 412430 + }, + { + "epoch": 0.92, + "learning_rate": 3.99879197333393e-06, + "loss": 0.0935, + "step": 412440 + }, + { + "epoch": 0.92, + "learning_rate": 3.9976734301246056e-06, + "loss": 0.0929, + "step": 412450 + }, + { + "epoch": 0.92, + "learning_rate": 3.996554886915282e-06, + "loss": 0.0936, + "step": 412460 + }, + { + "epoch": 0.92, + "learning_rate": 3.995436343705958e-06, + "loss": 0.0885, + "step": 412470 + }, + { + "epoch": 0.92, + "learning_rate": 3.9943178004966334e-06, + "loss": 0.0892, + "step": 412480 + }, + { + "epoch": 0.92, + "learning_rate": 3.993199257287309e-06, + "loss": 0.093, + "step": 412490 + }, + { + "epoch": 0.92, + "learning_rate": 3.992080714077985e-06, + "loss": 0.0931, + "step": 412500 + }, + { + "epoch": 0.92, + "learning_rate": 3.990962170868661e-06, + "loss": 0.0897, + "step": 412510 + }, + { + "epoch": 0.92, + "learning_rate": 3.989843627659337e-06, + "loss": 0.0967, + "step": 412520 + }, + { + "epoch": 0.92, + "learning_rate": 3.988725084450012e-06, + "loss": 0.0902, + "step": 412530 + }, + { + "epoch": 0.92, + "learning_rate": 3.987606541240688e-06, + "loss": 0.0903, + "step": 412540 + }, + { + "epoch": 0.92, + "learning_rate": 3.9864879980313645e-06, + "loss": 0.0917, + "step": 412550 + }, + { + "epoch": 0.92, + "learning_rate": 3.98536945482204e-06, + "loss": 0.0915, + "step": 412560 + }, + { + "epoch": 0.92, + "learning_rate": 3.984250911612715e-06, + "loss": 0.0931, + "step": 412570 + }, + { + "epoch": 0.92, + "learning_rate": 3.9831323684033915e-06, + "loss": 0.092, + "step": 412580 + }, + { + "epoch": 0.92, + "learning_rate": 3.982013825194068e-06, + "loss": 0.0942, + "step": 412590 + }, + { + "epoch": 0.92, + "learning_rate": 3.980895281984743e-06, + "loss": 0.094, + "step": 412600 + }, + { + "epoch": 0.92, + "learning_rate": 3.9797767387754185e-06, + "loss": 0.0909, + "step": 412610 + }, + { + "epoch": 0.92, + "learning_rate": 3.978658195566095e-06, + "loss": 0.0909, + "step": 412620 + }, + { + "epoch": 0.92, + "learning_rate": 3.977539652356771e-06, + "loss": 0.0947, + "step": 412630 + }, + { + "epoch": 0.92, + "learning_rate": 3.976421109147446e-06, + "loss": 0.0938, + "step": 412640 + }, + { + "epoch": 0.92, + "learning_rate": 3.975302565938123e-06, + "loss": 0.0934, + "step": 412650 + }, + { + "epoch": 0.92, + "learning_rate": 3.974184022728798e-06, + "loss": 0.0965, + "step": 412660 + }, + { + "epoch": 0.92, + "learning_rate": 3.973065479519474e-06, + "loss": 0.0937, + "step": 412670 + }, + { + "epoch": 0.92, + "learning_rate": 3.97194693631015e-06, + "loss": 0.0906, + "step": 412680 + }, + { + "epoch": 0.92, + "learning_rate": 3.970828393100826e-06, + "loss": 0.0923, + "step": 412690 + }, + { + "epoch": 0.92, + "learning_rate": 3.969709849891501e-06, + "loss": 0.091, + "step": 412700 + }, + { + "epoch": 0.92, + "learning_rate": 3.9685913066821775e-06, + "loss": 0.0936, + "step": 412710 + }, + { + "epoch": 0.92, + "learning_rate": 3.967472763472853e-06, + "loss": 0.0946, + "step": 412720 + }, + { + "epoch": 0.92, + "learning_rate": 3.966354220263529e-06, + "loss": 0.0925, + "step": 412730 + }, + { + "epoch": 0.92, + "learning_rate": 3.9652356770542045e-06, + "loss": 0.0887, + "step": 412740 + }, + { + "epoch": 0.92, + "learning_rate": 3.964117133844881e-06, + "loss": 0.0906, + "step": 412750 + }, + { + "epoch": 0.92, + "learning_rate": 3.962998590635556e-06, + "loss": 0.093, + "step": 412760 + }, + { + "epoch": 0.92, + "learning_rate": 3.961880047426232e-06, + "loss": 0.0929, + "step": 412770 + }, + { + "epoch": 0.92, + "learning_rate": 3.960761504216908e-06, + "loss": 0.0948, + "step": 412780 + }, + { + "epoch": 0.92, + "learning_rate": 3.959642961007584e-06, + "loss": 0.0918, + "step": 412790 + }, + { + "epoch": 0.92, + "learning_rate": 3.958524417798259e-06, + "loss": 0.0976, + "step": 412800 + }, + { + "epoch": 0.92, + "learning_rate": 3.957405874588936e-06, + "loss": 0.0952, + "step": 412810 + }, + { + "epoch": 0.92, + "learning_rate": 3.956287331379612e-06, + "loss": 0.0906, + "step": 412820 + }, + { + "epoch": 0.92, + "learning_rate": 3.955168788170287e-06, + "loss": 0.0901, + "step": 412830 + }, + { + "epoch": 0.92, + "learning_rate": 3.954050244960963e-06, + "loss": 0.0936, + "step": 412840 + }, + { + "epoch": 0.92, + "learning_rate": 3.952931701751639e-06, + "loss": 0.0914, + "step": 412850 + }, + { + "epoch": 0.92, + "learning_rate": 3.951813158542315e-06, + "loss": 0.0927, + "step": 412860 + }, + { + "epoch": 0.92, + "learning_rate": 3.9506946153329904e-06, + "loss": 0.0951, + "step": 412870 + }, + { + "epoch": 0.92, + "learning_rate": 3.949576072123666e-06, + "loss": 0.094, + "step": 412880 + }, + { + "epoch": 0.92, + "learning_rate": 3.948457528914342e-06, + "loss": 0.0912, + "step": 412890 + }, + { + "epoch": 0.92, + "learning_rate": 3.947338985705018e-06, + "loss": 0.0911, + "step": 412900 + }, + { + "epoch": 0.92, + "learning_rate": 3.946220442495694e-06, + "loss": 0.0933, + "step": 412910 + }, + { + "epoch": 0.92, + "learning_rate": 3.945101899286369e-06, + "loss": 0.0945, + "step": 412920 + }, + { + "epoch": 0.92, + "learning_rate": 3.943983356077045e-06, + "loss": 0.0895, + "step": 412930 + }, + { + "epoch": 0.92, + "learning_rate": 3.9428648128677215e-06, + "loss": 0.0921, + "step": 412940 + }, + { + "epoch": 0.92, + "learning_rate": 3.941746269658397e-06, + "loss": 0.0946, + "step": 412950 + }, + { + "epoch": 0.92, + "learning_rate": 3.940627726449072e-06, + "loss": 0.0931, + "step": 412960 + }, + { + "epoch": 0.92, + "learning_rate": 3.9395091832397485e-06, + "loss": 0.0934, + "step": 412970 + }, + { + "epoch": 0.92, + "learning_rate": 3.938390640030425e-06, + "loss": 0.0927, + "step": 412980 + }, + { + "epoch": 0.92, + "learning_rate": 3.937272096821101e-06, + "loss": 0.0946, + "step": 412990 + }, + { + "epoch": 0.92, + "learning_rate": 3.9361535536117756e-06, + "loss": 0.0935, + "step": 413000 + }, + { + "epoch": 0.92, + "learning_rate": 3.935035010402452e-06, + "loss": 0.0921, + "step": 413010 + }, + { + "epoch": 0.92, + "learning_rate": 3.933916467193128e-06, + "loss": 0.0906, + "step": 413020 + }, + { + "epoch": 0.92, + "learning_rate": 3.932797923983804e-06, + "loss": 0.0905, + "step": 413030 + }, + { + "epoch": 0.92, + "learning_rate": 3.93167938077448e-06, + "loss": 0.0914, + "step": 413040 + }, + { + "epoch": 0.92, + "learning_rate": 3.930560837565155e-06, + "loss": 0.0946, + "step": 413050 + }, + { + "epoch": 0.92, + "learning_rate": 3.929442294355831e-06, + "loss": 0.0922, + "step": 413060 + }, + { + "epoch": 0.92, + "learning_rate": 3.9283237511465075e-06, + "loss": 0.0936, + "step": 413070 + }, + { + "epoch": 0.92, + "learning_rate": 3.927205207937183e-06, + "loss": 0.0968, + "step": 413080 + }, + { + "epoch": 0.92, + "learning_rate": 3.926086664727858e-06, + "loss": 0.0945, + "step": 413090 + }, + { + "epoch": 0.92, + "learning_rate": 3.9249681215185345e-06, + "loss": 0.0903, + "step": 413100 + }, + { + "epoch": 0.92, + "learning_rate": 3.923849578309211e-06, + "loss": 0.0917, + "step": 413110 + }, + { + "epoch": 0.92, + "learning_rate": 3.922731035099886e-06, + "loss": 0.092, + "step": 413120 + }, + { + "epoch": 0.92, + "learning_rate": 3.9216124918905615e-06, + "loss": 0.0922, + "step": 413130 + }, + { + "epoch": 0.92, + "learning_rate": 3.920493948681238e-06, + "loss": 0.0889, + "step": 413140 + }, + { + "epoch": 0.92, + "learning_rate": 3.919375405471914e-06, + "loss": 0.0893, + "step": 413150 + }, + { + "epoch": 0.92, + "learning_rate": 3.918256862262589e-06, + "loss": 0.0963, + "step": 413160 + }, + { + "epoch": 0.92, + "learning_rate": 3.917138319053265e-06, + "loss": 0.0965, + "step": 413170 + }, + { + "epoch": 0.92, + "learning_rate": 3.916019775843941e-06, + "loss": 0.0966, + "step": 413180 + }, + { + "epoch": 0.92, + "learning_rate": 3.914901232634617e-06, + "loss": 0.0969, + "step": 413190 + }, + { + "epoch": 0.92, + "learning_rate": 3.913782689425293e-06, + "loss": 0.0937, + "step": 413200 + }, + { + "epoch": 0.92, + "learning_rate": 3.912664146215969e-06, + "loss": 0.0902, + "step": 413210 + }, + { + "epoch": 0.92, + "learning_rate": 3.911545603006644e-06, + "loss": 0.0929, + "step": 413220 + }, + { + "epoch": 0.92, + "learning_rate": 3.9104270597973205e-06, + "loss": 0.0927, + "step": 413230 + }, + { + "epoch": 0.92, + "learning_rate": 3.909308516587996e-06, + "loss": 0.0924, + "step": 413240 + }, + { + "epoch": 0.92, + "learning_rate": 3.908189973378672e-06, + "loss": 0.0902, + "step": 413250 + }, + { + "epoch": 0.92, + "learning_rate": 3.9070714301693475e-06, + "loss": 0.0913, + "step": 413260 + }, + { + "epoch": 0.92, + "learning_rate": 3.905952886960024e-06, + "loss": 0.0956, + "step": 413270 + }, + { + "epoch": 0.92, + "learning_rate": 3.904834343750699e-06, + "loss": 0.0906, + "step": 413280 + }, + { + "epoch": 0.92, + "learning_rate": 3.903715800541375e-06, + "loss": 0.0905, + "step": 413290 + }, + { + "epoch": 0.92, + "learning_rate": 3.902597257332051e-06, + "loss": 0.0911, + "step": 413300 + }, + { + "epoch": 0.92, + "learning_rate": 3.901478714122727e-06, + "loss": 0.0897, + "step": 413310 + }, + { + "epoch": 0.92, + "learning_rate": 3.900360170913402e-06, + "loss": 0.0908, + "step": 413320 + }, + { + "epoch": 0.92, + "learning_rate": 3.8992416277040786e-06, + "loss": 0.0947, + "step": 413330 + }, + { + "epoch": 0.92, + "learning_rate": 3.898123084494754e-06, + "loss": 0.0917, + "step": 413340 + }, + { + "epoch": 0.92, + "learning_rate": 3.89700454128543e-06, + "loss": 0.0924, + "step": 413350 + }, + { + "epoch": 0.92, + "learning_rate": 3.8958859980761056e-06, + "loss": 0.0926, + "step": 413360 + }, + { + "epoch": 0.92, + "learning_rate": 3.894767454866782e-06, + "loss": 0.0931, + "step": 413370 + }, + { + "epoch": 0.92, + "learning_rate": 3.893648911657457e-06, + "loss": 0.0902, + "step": 413380 + }, + { + "epoch": 0.92, + "learning_rate": 3.892530368448133e-06, + "loss": 0.0899, + "step": 413390 + }, + { + "epoch": 0.92, + "learning_rate": 3.891411825238809e-06, + "loss": 0.0902, + "step": 413400 + }, + { + "epoch": 0.92, + "learning_rate": 3.890293282029485e-06, + "loss": 0.0931, + "step": 413410 + }, + { + "epoch": 0.92, + "learning_rate": 3.889174738820161e-06, + "loss": 0.0945, + "step": 413420 + }, + { + "epoch": 0.92, + "learning_rate": 3.888056195610837e-06, + "loss": 0.093, + "step": 413430 + }, + { + "epoch": 0.92, + "learning_rate": 3.886937652401512e-06, + "loss": 0.0926, + "step": 413440 + }, + { + "epoch": 0.92, + "learning_rate": 3.885819109192188e-06, + "loss": 0.093, + "step": 413450 + }, + { + "epoch": 0.92, + "learning_rate": 3.8847005659828645e-06, + "loss": 0.0941, + "step": 413460 + }, + { + "epoch": 0.92, + "learning_rate": 3.88358202277354e-06, + "loss": 0.0924, + "step": 413470 + }, + { + "epoch": 0.92, + "learning_rate": 3.882463479564215e-06, + "loss": 0.0961, + "step": 413480 + }, + { + "epoch": 0.92, + "learning_rate": 3.8813449363548915e-06, + "loss": 0.0901, + "step": 413490 + }, + { + "epoch": 0.92, + "learning_rate": 3.880226393145568e-06, + "loss": 0.0951, + "step": 413500 + }, + { + "epoch": 0.92, + "learning_rate": 3.879107849936243e-06, + "loss": 0.0884, + "step": 413510 + }, + { + "epoch": 0.92, + "learning_rate": 3.8779893067269185e-06, + "loss": 0.0983, + "step": 413520 + }, + { + "epoch": 0.92, + "learning_rate": 3.876870763517595e-06, + "loss": 0.0931, + "step": 413530 + }, + { + "epoch": 0.92, + "learning_rate": 3.875752220308271e-06, + "loss": 0.09, + "step": 413540 + }, + { + "epoch": 0.92, + "learning_rate": 3.874633677098946e-06, + "loss": 0.0939, + "step": 413550 + }, + { + "epoch": 0.92, + "learning_rate": 3.873515133889622e-06, + "loss": 0.0928, + "step": 413560 + }, + { + "epoch": 0.92, + "learning_rate": 3.872396590680298e-06, + "loss": 0.0913, + "step": 413570 + }, + { + "epoch": 0.92, + "learning_rate": 3.871278047470974e-06, + "loss": 0.0908, + "step": 413580 + }, + { + "epoch": 0.92, + "learning_rate": 3.8701595042616505e-06, + "loss": 0.09, + "step": 413590 + }, + { + "epoch": 0.92, + "learning_rate": 3.869040961052325e-06, + "loss": 0.0911, + "step": 413600 + }, + { + "epoch": 0.92, + "learning_rate": 3.867922417843001e-06, + "loss": 0.0979, + "step": 413610 + }, + { + "epoch": 0.92, + "learning_rate": 3.8668038746336775e-06, + "loss": 0.0916, + "step": 413620 + }, + { + "epoch": 0.92, + "learning_rate": 3.865685331424354e-06, + "loss": 0.0949, + "step": 413630 + }, + { + "epoch": 0.92, + "learning_rate": 3.864566788215029e-06, + "loss": 0.094, + "step": 413640 + }, + { + "epoch": 0.92, + "learning_rate": 3.8634482450057045e-06, + "loss": 0.093, + "step": 413650 + }, + { + "epoch": 0.92, + "learning_rate": 3.862329701796381e-06, + "loss": 0.0914, + "step": 413660 + }, + { + "epoch": 0.92, + "learning_rate": 3.861211158587057e-06, + "loss": 0.0922, + "step": 413670 + }, + { + "epoch": 0.92, + "learning_rate": 3.860092615377732e-06, + "loss": 0.0906, + "step": 413680 + }, + { + "epoch": 0.92, + "learning_rate": 3.858974072168408e-06, + "loss": 0.0939, + "step": 413690 + }, + { + "epoch": 0.92, + "learning_rate": 3.857855528959084e-06, + "loss": 0.0906, + "step": 413700 + }, + { + "epoch": 0.92, + "learning_rate": 3.85673698574976e-06, + "loss": 0.0881, + "step": 413710 + }, + { + "epoch": 0.92, + "learning_rate": 3.8556184425404356e-06, + "loss": 0.0868, + "step": 413720 + }, + { + "epoch": 0.92, + "learning_rate": 3.854499899331111e-06, + "loss": 0.0926, + "step": 413730 + }, + { + "epoch": 0.92, + "learning_rate": 3.853381356121787e-06, + "loss": 0.0924, + "step": 413740 + }, + { + "epoch": 0.92, + "learning_rate": 3.8522628129124634e-06, + "loss": 0.0933, + "step": 413750 + }, + { + "epoch": 0.92, + "learning_rate": 3.851144269703139e-06, + "loss": 0.0942, + "step": 413760 + }, + { + "epoch": 0.92, + "learning_rate": 3.850025726493814e-06, + "loss": 0.0906, + "step": 413770 + }, + { + "epoch": 0.92, + "learning_rate": 3.8489071832844904e-06, + "loss": 0.0876, + "step": 413780 + }, + { + "epoch": 0.92, + "learning_rate": 3.847788640075167e-06, + "loss": 0.0938, + "step": 413790 + }, + { + "epoch": 0.92, + "learning_rate": 3.846670096865842e-06, + "loss": 0.0904, + "step": 413800 + }, + { + "epoch": 0.92, + "learning_rate": 3.845551553656518e-06, + "loss": 0.0927, + "step": 413810 + }, + { + "epoch": 0.92, + "learning_rate": 3.844433010447194e-06, + "loss": 0.0914, + "step": 413820 + }, + { + "epoch": 0.92, + "learning_rate": 3.84331446723787e-06, + "loss": 0.0942, + "step": 413830 + }, + { + "epoch": 0.92, + "learning_rate": 3.842195924028545e-06, + "loss": 0.0927, + "step": 413840 + }, + { + "epoch": 0.92, + "learning_rate": 3.8410773808192215e-06, + "loss": 0.0893, + "step": 413850 + }, + { + "epoch": 0.92, + "learning_rate": 3.839958837609897e-06, + "loss": 0.0944, + "step": 413860 + }, + { + "epoch": 0.92, + "learning_rate": 3.838840294400573e-06, + "loss": 0.0952, + "step": 413870 + }, + { + "epoch": 0.92, + "learning_rate": 3.8377217511912485e-06, + "loss": 0.0887, + "step": 413880 + }, + { + "epoch": 0.92, + "learning_rate": 3.836603207981925e-06, + "loss": 0.0913, + "step": 413890 + }, + { + "epoch": 0.92, + "learning_rate": 3.8354846647726e-06, + "loss": 0.09, + "step": 413900 + }, + { + "epoch": 0.92, + "learning_rate": 3.834366121563276e-06, + "loss": 0.095, + "step": 413910 + }, + { + "epoch": 0.92, + "learning_rate": 3.833247578353952e-06, + "loss": 0.0945, + "step": 413920 + }, + { + "epoch": 0.92, + "learning_rate": 3.832129035144628e-06, + "loss": 0.0904, + "step": 413930 + }, + { + "epoch": 0.92, + "learning_rate": 3.831010491935303e-06, + "loss": 0.0936, + "step": 413940 + }, + { + "epoch": 0.92, + "learning_rate": 3.82989194872598e-06, + "loss": 0.092, + "step": 413950 + }, + { + "epoch": 0.92, + "learning_rate": 3.828773405516655e-06, + "loss": 0.0933, + "step": 413960 + }, + { + "epoch": 0.92, + "learning_rate": 3.827654862307331e-06, + "loss": 0.0908, + "step": 413970 + }, + { + "epoch": 0.92, + "learning_rate": 3.826536319098007e-06, + "loss": 0.0933, + "step": 413980 + }, + { + "epoch": 0.92, + "learning_rate": 3.825417775888683e-06, + "loss": 0.0914, + "step": 413990 + }, + { + "epoch": 0.92, + "learning_rate": 3.824299232679358e-06, + "loss": 0.0911, + "step": 414000 + }, + { + "epoch": 0.92, + "learning_rate": 3.823292543790967e-06, + "loss": 0.091, + "step": 414010 + }, + { + "epoch": 0.92, + "learning_rate": 3.822174000581643e-06, + "loss": 0.0902, + "step": 414020 + }, + { + "epoch": 0.92, + "learning_rate": 3.821055457372319e-06, + "loss": 0.0944, + "step": 414030 + }, + { + "epoch": 0.92, + "learning_rate": 3.819936914162994e-06, + "loss": 0.0941, + "step": 414040 + }, + { + "epoch": 0.92, + "learning_rate": 3.81881837095367e-06, + "loss": 0.0953, + "step": 414050 + }, + { + "epoch": 0.92, + "learning_rate": 3.8176998277443465e-06, + "loss": 0.0911, + "step": 414060 + }, + { + "epoch": 0.92, + "learning_rate": 3.816581284535022e-06, + "loss": 0.091, + "step": 414070 + }, + { + "epoch": 0.92, + "learning_rate": 3.815462741325697e-06, + "loss": 0.0922, + "step": 414080 + }, + { + "epoch": 0.92, + "learning_rate": 3.8143441981163735e-06, + "loss": 0.09, + "step": 414090 + }, + { + "epoch": 0.92, + "learning_rate": 3.8132256549070497e-06, + "loss": 0.0967, + "step": 414100 + }, + { + "epoch": 0.92, + "learning_rate": 3.8121071116977247e-06, + "loss": 0.0898, + "step": 414110 + }, + { + "epoch": 0.92, + "learning_rate": 3.810988568488401e-06, + "loss": 0.0942, + "step": 414120 + }, + { + "epoch": 0.92, + "learning_rate": 3.8098700252790768e-06, + "loss": 0.0926, + "step": 414130 + }, + { + "epoch": 0.92, + "learning_rate": 3.808751482069753e-06, + "loss": 0.0933, + "step": 414140 + }, + { + "epoch": 0.92, + "learning_rate": 3.807632938860428e-06, + "loss": 0.0938, + "step": 414150 + }, + { + "epoch": 0.92, + "learning_rate": 3.806514395651104e-06, + "loss": 0.0879, + "step": 414160 + }, + { + "epoch": 0.92, + "learning_rate": 3.80539585244178e-06, + "loss": 0.091, + "step": 414170 + }, + { + "epoch": 0.92, + "learning_rate": 3.8042773092324562e-06, + "loss": 0.0967, + "step": 414180 + }, + { + "epoch": 0.92, + "learning_rate": 3.8031587660231316e-06, + "loss": 0.0885, + "step": 414190 + }, + { + "epoch": 0.92, + "learning_rate": 3.8020402228138074e-06, + "loss": 0.0918, + "step": 414200 + }, + { + "epoch": 0.92, + "learning_rate": 3.8009216796044837e-06, + "loss": 0.0914, + "step": 414210 + }, + { + "epoch": 0.92, + "learning_rate": 3.7998031363951595e-06, + "loss": 0.0881, + "step": 414220 + }, + { + "epoch": 0.92, + "learning_rate": 3.798684593185835e-06, + "loss": 0.0983, + "step": 414230 + }, + { + "epoch": 0.92, + "learning_rate": 3.7975660499765107e-06, + "loss": 0.0926, + "step": 414240 + }, + { + "epoch": 0.92, + "learning_rate": 3.796447506767187e-06, + "loss": 0.0949, + "step": 414250 + }, + { + "epoch": 0.92, + "learning_rate": 3.7953289635578627e-06, + "loss": 0.091, + "step": 414260 + }, + { + "epoch": 0.92, + "learning_rate": 3.794210420348538e-06, + "loss": 0.0917, + "step": 414270 + }, + { + "epoch": 0.92, + "learning_rate": 3.793091877139214e-06, + "loss": 0.0963, + "step": 414280 + }, + { + "epoch": 0.92, + "learning_rate": 3.79197333392989e-06, + "loss": 0.0921, + "step": 414290 + }, + { + "epoch": 0.92, + "learning_rate": 3.790854790720566e-06, + "loss": 0.0936, + "step": 414300 + }, + { + "epoch": 0.92, + "learning_rate": 3.7897362475112413e-06, + "loss": 0.0937, + "step": 414310 + }, + { + "epoch": 0.92, + "learning_rate": 3.788617704301917e-06, + "loss": 0.0899, + "step": 414320 + }, + { + "epoch": 0.92, + "learning_rate": 3.7874991610925934e-06, + "loss": 0.0972, + "step": 414330 + }, + { + "epoch": 0.92, + "learning_rate": 3.786380617883269e-06, + "loss": 0.0904, + "step": 414340 + }, + { + "epoch": 0.92, + "learning_rate": 3.7852620746739446e-06, + "loss": 0.0956, + "step": 414350 + }, + { + "epoch": 0.92, + "learning_rate": 3.784143531464621e-06, + "loss": 0.0906, + "step": 414360 + }, + { + "epoch": 0.92, + "learning_rate": 3.7830249882552966e-06, + "loss": 0.0945, + "step": 414370 + }, + { + "epoch": 0.92, + "learning_rate": 3.7819064450459724e-06, + "loss": 0.0909, + "step": 414380 + }, + { + "epoch": 0.92, + "learning_rate": 3.780787901836648e-06, + "loss": 0.0919, + "step": 414390 + }, + { + "epoch": 0.92, + "learning_rate": 3.779669358627324e-06, + "loss": 0.0907, + "step": 414400 + }, + { + "epoch": 0.93, + "learning_rate": 3.778550815418e-06, + "loss": 0.0986, + "step": 414410 + }, + { + "epoch": 0.93, + "learning_rate": 3.777432272208676e-06, + "loss": 0.0921, + "step": 414420 + }, + { + "epoch": 0.93, + "learning_rate": 3.776313728999351e-06, + "loss": 0.0944, + "step": 414430 + }, + { + "epoch": 0.93, + "learning_rate": 3.7751951857900273e-06, + "loss": 0.0961, + "step": 414440 + }, + { + "epoch": 0.93, + "learning_rate": 3.774076642580703e-06, + "loss": 0.0924, + "step": 414450 + }, + { + "epoch": 0.93, + "learning_rate": 3.7729580993713793e-06, + "loss": 0.0918, + "step": 414460 + }, + { + "epoch": 0.93, + "learning_rate": 3.7718395561620547e-06, + "loss": 0.0914, + "step": 414470 + }, + { + "epoch": 0.93, + "learning_rate": 3.7707210129527305e-06, + "loss": 0.0936, + "step": 414480 + }, + { + "epoch": 0.93, + "learning_rate": 3.7696024697434063e-06, + "loss": 0.095, + "step": 414490 + }, + { + "epoch": 0.93, + "learning_rate": 3.7684839265340826e-06, + "loss": 0.0891, + "step": 414500 + }, + { + "epoch": 0.93, + "learning_rate": 3.767365383324758e-06, + "loss": 0.0915, + "step": 414510 + }, + { + "epoch": 0.93, + "learning_rate": 3.7662468401154338e-06, + "loss": 0.0886, + "step": 414520 + }, + { + "epoch": 0.93, + "learning_rate": 3.76512829690611e-06, + "loss": 0.0938, + "step": 414530 + }, + { + "epoch": 0.93, + "learning_rate": 3.764009753696786e-06, + "loss": 0.0952, + "step": 414540 + }, + { + "epoch": 0.93, + "learning_rate": 3.762891210487461e-06, + "loss": 0.0939, + "step": 414550 + }, + { + "epoch": 0.93, + "learning_rate": 3.761772667278137e-06, + "loss": 0.0933, + "step": 414560 + }, + { + "epoch": 0.93, + "learning_rate": 3.7606541240688132e-06, + "loss": 0.0952, + "step": 414570 + }, + { + "epoch": 0.93, + "learning_rate": 3.759535580859489e-06, + "loss": 0.0893, + "step": 414580 + }, + { + "epoch": 0.93, + "learning_rate": 3.7584170376501644e-06, + "loss": 0.0887, + "step": 414590 + }, + { + "epoch": 0.93, + "learning_rate": 3.7572984944408403e-06, + "loss": 0.0915, + "step": 414600 + }, + { + "epoch": 0.93, + "learning_rate": 3.7561799512315165e-06, + "loss": 0.0935, + "step": 414610 + }, + { + "epoch": 0.93, + "learning_rate": 3.7550614080221923e-06, + "loss": 0.0926, + "step": 414620 + }, + { + "epoch": 0.93, + "learning_rate": 3.7539428648128677e-06, + "loss": 0.089, + "step": 414630 + }, + { + "epoch": 0.93, + "learning_rate": 3.752824321603544e-06, + "loss": 0.0934, + "step": 414640 + }, + { + "epoch": 0.93, + "learning_rate": 3.7517057783942197e-06, + "loss": 0.0933, + "step": 414650 + }, + { + "epoch": 0.93, + "learning_rate": 3.7505872351848955e-06, + "loss": 0.0944, + "step": 414660 + }, + { + "epoch": 0.93, + "learning_rate": 3.749468691975571e-06, + "loss": 0.0932, + "step": 414670 + }, + { + "epoch": 0.93, + "learning_rate": 3.748350148766247e-06, + "loss": 0.0901, + "step": 414680 + }, + { + "epoch": 0.93, + "learning_rate": 3.747231605556923e-06, + "loss": 0.0898, + "step": 414690 + }, + { + "epoch": 0.93, + "learning_rate": 3.746113062347599e-06, + "loss": 0.094, + "step": 414700 + }, + { + "epoch": 0.93, + "learning_rate": 3.744994519138274e-06, + "loss": 0.0899, + "step": 414710 + }, + { + "epoch": 0.93, + "learning_rate": 3.7438759759289504e-06, + "loss": 0.0947, + "step": 414720 + }, + { + "epoch": 0.93, + "learning_rate": 3.742757432719626e-06, + "loss": 0.0919, + "step": 414730 + }, + { + "epoch": 0.93, + "learning_rate": 3.7416388895103024e-06, + "loss": 0.0889, + "step": 414740 + }, + { + "epoch": 0.93, + "learning_rate": 3.7405203463009774e-06, + "loss": 0.0937, + "step": 414750 + }, + { + "epoch": 0.93, + "learning_rate": 3.7394018030916536e-06, + "loss": 0.0876, + "step": 414760 + }, + { + "epoch": 0.93, + "learning_rate": 3.7382832598823294e-06, + "loss": 0.0958, + "step": 414770 + }, + { + "epoch": 0.93, + "learning_rate": 3.737164716673005e-06, + "loss": 0.0882, + "step": 414780 + }, + { + "epoch": 0.93, + "learning_rate": 3.736046173463681e-06, + "loss": 0.0913, + "step": 414790 + }, + { + "epoch": 0.93, + "learning_rate": 3.734927630254357e-06, + "loss": 0.0918, + "step": 414800 + }, + { + "epoch": 0.93, + "learning_rate": 3.733809087045033e-06, + "loss": 0.0888, + "step": 414810 + }, + { + "epoch": 0.93, + "learning_rate": 3.732690543835708e-06, + "loss": 0.0901, + "step": 414820 + }, + { + "epoch": 0.93, + "learning_rate": 3.7315720006263843e-06, + "loss": 0.0944, + "step": 414830 + }, + { + "epoch": 0.93, + "learning_rate": 3.73045345741706e-06, + "loss": 0.091, + "step": 414840 + }, + { + "epoch": 0.93, + "learning_rate": 3.7293349142077364e-06, + "loss": 0.0922, + "step": 414850 + }, + { + "epoch": 0.93, + "learning_rate": 3.7282163709984113e-06, + "loss": 0.0925, + "step": 414860 + }, + { + "epoch": 0.93, + "learning_rate": 3.7270978277890876e-06, + "loss": 0.0891, + "step": 414870 + }, + { + "epoch": 0.93, + "learning_rate": 3.7259792845797634e-06, + "loss": 0.0928, + "step": 414880 + }, + { + "epoch": 0.93, + "learning_rate": 3.7248607413704396e-06, + "loss": 0.0915, + "step": 414890 + }, + { + "epoch": 0.93, + "learning_rate": 3.723742198161115e-06, + "loss": 0.0914, + "step": 414900 + }, + { + "epoch": 0.93, + "learning_rate": 3.722623654951791e-06, + "loss": 0.0914, + "step": 414910 + }, + { + "epoch": 0.93, + "learning_rate": 3.7215051117424666e-06, + "loss": 0.0904, + "step": 414920 + }, + { + "epoch": 0.93, + "learning_rate": 3.720386568533143e-06, + "loss": 0.0932, + "step": 414930 + }, + { + "epoch": 0.93, + "learning_rate": 3.7192680253238182e-06, + "loss": 0.0913, + "step": 414940 + }, + { + "epoch": 0.93, + "learning_rate": 3.718149482114494e-06, + "loss": 0.0945, + "step": 414950 + }, + { + "epoch": 0.93, + "learning_rate": 3.7170309389051703e-06, + "loss": 0.089, + "step": 414960 + }, + { + "epoch": 0.93, + "learning_rate": 3.715912395695846e-06, + "loss": 0.0926, + "step": 414970 + }, + { + "epoch": 0.93, + "learning_rate": 3.7147938524865215e-06, + "loss": 0.0913, + "step": 414980 + }, + { + "epoch": 0.93, + "learning_rate": 3.7136753092771973e-06, + "loss": 0.0886, + "step": 414990 + }, + { + "epoch": 0.93, + "learning_rate": 3.7125567660678735e-06, + "loss": 0.0901, + "step": 415000 + }, + { + "epoch": 0.93, + "learning_rate": 3.7114382228585493e-06, + "loss": 0.0925, + "step": 415010 + }, + { + "epoch": 0.93, + "learning_rate": 3.7103196796492247e-06, + "loss": 0.0899, + "step": 415020 + }, + { + "epoch": 0.93, + "learning_rate": 3.7092011364399005e-06, + "loss": 0.0915, + "step": 415030 + }, + { + "epoch": 0.93, + "learning_rate": 3.7080825932305767e-06, + "loss": 0.0872, + "step": 415040 + }, + { + "epoch": 0.93, + "learning_rate": 3.7069640500212526e-06, + "loss": 0.09, + "step": 415050 + }, + { + "epoch": 0.93, + "learning_rate": 3.705845506811928e-06, + "loss": 0.0928, + "step": 415060 + }, + { + "epoch": 0.93, + "learning_rate": 3.704726963602604e-06, + "loss": 0.0924, + "step": 415070 + }, + { + "epoch": 0.93, + "learning_rate": 3.70360842039328e-06, + "loss": 0.0925, + "step": 415080 + }, + { + "epoch": 0.93, + "learning_rate": 3.702489877183956e-06, + "loss": 0.0955, + "step": 415090 + }, + { + "epoch": 0.93, + "learning_rate": 3.701371333974631e-06, + "loss": 0.0958, + "step": 415100 + }, + { + "epoch": 0.93, + "learning_rate": 3.7002527907653074e-06, + "loss": 0.0946, + "step": 415110 + }, + { + "epoch": 0.93, + "learning_rate": 3.6991342475559832e-06, + "loss": 0.0919, + "step": 415120 + }, + { + "epoch": 0.93, + "learning_rate": 3.6980157043466595e-06, + "loss": 0.0956, + "step": 415130 + }, + { + "epoch": 0.93, + "learning_rate": 3.6968971611373344e-06, + "loss": 0.0944, + "step": 415140 + }, + { + "epoch": 0.93, + "learning_rate": 3.6957786179280107e-06, + "loss": 0.0923, + "step": 415150 + }, + { + "epoch": 0.93, + "learning_rate": 3.6946600747186865e-06, + "loss": 0.0954, + "step": 415160 + }, + { + "epoch": 0.93, + "learning_rate": 3.6935415315093627e-06, + "loss": 0.0933, + "step": 415170 + }, + { + "epoch": 0.93, + "learning_rate": 3.692422988300038e-06, + "loss": 0.0943, + "step": 415180 + }, + { + "epoch": 0.93, + "learning_rate": 3.691304445090714e-06, + "loss": 0.0933, + "step": 415190 + }, + { + "epoch": 0.93, + "learning_rate": 3.6901859018813897e-06, + "loss": 0.0933, + "step": 415200 + }, + { + "epoch": 0.93, + "learning_rate": 3.689067358672066e-06, + "loss": 0.0893, + "step": 415210 + }, + { + "epoch": 0.93, + "learning_rate": 3.6879488154627413e-06, + "loss": 0.092, + "step": 415220 + }, + { + "epoch": 0.93, + "learning_rate": 3.686830272253417e-06, + "loss": 0.0953, + "step": 415230 + }, + { + "epoch": 0.93, + "learning_rate": 3.6857117290440934e-06, + "loss": 0.0899, + "step": 415240 + }, + { + "epoch": 0.93, + "learning_rate": 3.684593185834769e-06, + "loss": 0.0928, + "step": 415250 + }, + { + "epoch": 0.93, + "learning_rate": 3.6834746426254446e-06, + "loss": 0.093, + "step": 415260 + }, + { + "epoch": 0.93, + "learning_rate": 3.6823560994161204e-06, + "loss": 0.091, + "step": 415270 + }, + { + "epoch": 0.93, + "learning_rate": 3.6812375562067966e-06, + "loss": 0.0886, + "step": 415280 + }, + { + "epoch": 0.93, + "learning_rate": 3.6801190129974724e-06, + "loss": 0.0916, + "step": 415290 + }, + { + "epoch": 0.93, + "learning_rate": 3.679000469788148e-06, + "loss": 0.0955, + "step": 415300 + }, + { + "epoch": 0.93, + "learning_rate": 3.6778819265788236e-06, + "loss": 0.092, + "step": 415310 + }, + { + "epoch": 0.93, + "learning_rate": 3.6767633833695e-06, + "loss": 0.0956, + "step": 415320 + }, + { + "epoch": 0.93, + "learning_rate": 3.6756448401601757e-06, + "loss": 0.0891, + "step": 415330 + }, + { + "epoch": 0.93, + "learning_rate": 3.674526296950851e-06, + "loss": 0.0912, + "step": 415340 + }, + { + "epoch": 0.93, + "learning_rate": 3.673407753741527e-06, + "loss": 0.0921, + "step": 415350 + }, + { + "epoch": 0.93, + "learning_rate": 3.672289210532203e-06, + "loss": 0.091, + "step": 415360 + }, + { + "epoch": 0.93, + "learning_rate": 3.671170667322879e-06, + "loss": 0.0918, + "step": 415370 + }, + { + "epoch": 0.93, + "learning_rate": 3.6700521241135543e-06, + "loss": 0.0909, + "step": 415380 + }, + { + "epoch": 0.93, + "learning_rate": 3.6689335809042305e-06, + "loss": 0.0924, + "step": 415390 + }, + { + "epoch": 0.93, + "learning_rate": 3.6678150376949063e-06, + "loss": 0.0897, + "step": 415400 + }, + { + "epoch": 0.93, + "learning_rate": 3.6666964944855826e-06, + "loss": 0.0928, + "step": 415410 + }, + { + "epoch": 0.93, + "learning_rate": 3.6655779512762575e-06, + "loss": 0.0927, + "step": 415420 + }, + { + "epoch": 0.93, + "learning_rate": 3.6644594080669338e-06, + "loss": 0.0919, + "step": 415430 + }, + { + "epoch": 0.93, + "learning_rate": 3.6633408648576096e-06, + "loss": 0.0937, + "step": 415440 + }, + { + "epoch": 0.93, + "learning_rate": 3.662222321648286e-06, + "loss": 0.0939, + "step": 415450 + }, + { + "epoch": 0.93, + "learning_rate": 3.6611037784389608e-06, + "loss": 0.0938, + "step": 415460 + }, + { + "epoch": 0.93, + "learning_rate": 3.659985235229637e-06, + "loss": 0.0927, + "step": 415470 + }, + { + "epoch": 0.93, + "learning_rate": 3.658866692020313e-06, + "loss": 0.0961, + "step": 415480 + }, + { + "epoch": 0.93, + "learning_rate": 3.657748148810989e-06, + "loss": 0.0968, + "step": 415490 + }, + { + "epoch": 0.93, + "learning_rate": 3.6566296056016644e-06, + "loss": 0.0972, + "step": 415500 + }, + { + "epoch": 0.93, + "learning_rate": 3.6555110623923402e-06, + "loss": 0.0915, + "step": 415510 + }, + { + "epoch": 0.93, + "learning_rate": 3.654392519183016e-06, + "loss": 0.0921, + "step": 415520 + }, + { + "epoch": 0.93, + "learning_rate": 3.6532739759736923e-06, + "loss": 0.093, + "step": 415530 + }, + { + "epoch": 0.93, + "learning_rate": 3.6521554327643677e-06, + "loss": 0.0971, + "step": 415540 + }, + { + "epoch": 0.93, + "learning_rate": 3.6510368895550435e-06, + "loss": 0.0916, + "step": 415550 + }, + { + "epoch": 0.93, + "learning_rate": 3.6499183463457197e-06, + "loss": 0.0909, + "step": 415560 + }, + { + "epoch": 0.93, + "learning_rate": 3.6487998031363955e-06, + "loss": 0.0931, + "step": 415570 + }, + { + "epoch": 0.93, + "learning_rate": 3.647681259927071e-06, + "loss": 0.0954, + "step": 415580 + }, + { + "epoch": 0.93, + "learning_rate": 3.6465627167177467e-06, + "loss": 0.0878, + "step": 415590 + }, + { + "epoch": 0.93, + "learning_rate": 3.645444173508423e-06, + "loss": 0.0949, + "step": 415600 + }, + { + "epoch": 0.93, + "learning_rate": 3.6443256302990988e-06, + "loss": 0.092, + "step": 415610 + }, + { + "epoch": 0.93, + "learning_rate": 3.643207087089774e-06, + "loss": 0.0941, + "step": 415620 + }, + { + "epoch": 0.93, + "learning_rate": 3.64208854388045e-06, + "loss": 0.0893, + "step": 415630 + }, + { + "epoch": 0.93, + "learning_rate": 3.640970000671126e-06, + "loss": 0.0902, + "step": 415640 + }, + { + "epoch": 0.93, + "learning_rate": 3.639851457461802e-06, + "loss": 0.0944, + "step": 415650 + }, + { + "epoch": 0.93, + "learning_rate": 3.6387329142524774e-06, + "loss": 0.0876, + "step": 415660 + }, + { + "epoch": 0.93, + "learning_rate": 3.6376143710431536e-06, + "loss": 0.093, + "step": 415670 + }, + { + "epoch": 0.93, + "learning_rate": 3.6364958278338294e-06, + "loss": 0.0889, + "step": 415680 + }, + { + "epoch": 0.93, + "learning_rate": 3.6353772846245052e-06, + "loss": 0.0957, + "step": 415690 + }, + { + "epoch": 0.93, + "learning_rate": 3.6342587414151806e-06, + "loss": 0.0916, + "step": 415700 + }, + { + "epoch": 0.93, + "learning_rate": 3.633140198205857e-06, + "loss": 0.094, + "step": 415710 + }, + { + "epoch": 0.93, + "learning_rate": 3.6320216549965327e-06, + "loss": 0.0893, + "step": 415720 + }, + { + "epoch": 0.93, + "learning_rate": 3.630903111787209e-06, + "loss": 0.0921, + "step": 415730 + }, + { + "epoch": 0.93, + "learning_rate": 3.629784568577884e-06, + "loss": 0.0936, + "step": 415740 + }, + { + "epoch": 0.93, + "learning_rate": 3.62866602536856e-06, + "loss": 0.0907, + "step": 415750 + }, + { + "epoch": 0.93, + "learning_rate": 3.627547482159236e-06, + "loss": 0.0903, + "step": 415760 + }, + { + "epoch": 0.93, + "learning_rate": 3.626428938949912e-06, + "loss": 0.0885, + "step": 415770 + }, + { + "epoch": 0.93, + "learning_rate": 3.6253103957405875e-06, + "loss": 0.0919, + "step": 415780 + }, + { + "epoch": 0.93, + "learning_rate": 3.6241918525312634e-06, + "loss": 0.0904, + "step": 415790 + }, + { + "epoch": 0.93, + "learning_rate": 3.623073309321939e-06, + "loss": 0.0954, + "step": 415800 + }, + { + "epoch": 0.93, + "learning_rate": 3.6219547661126154e-06, + "loss": 0.09, + "step": 415810 + }, + { + "epoch": 0.93, + "learning_rate": 3.6208362229032908e-06, + "loss": 0.0965, + "step": 415820 + }, + { + "epoch": 0.93, + "learning_rate": 3.6197176796939666e-06, + "loss": 0.0938, + "step": 415830 + }, + { + "epoch": 0.93, + "learning_rate": 3.618599136484643e-06, + "loss": 0.0923, + "step": 415840 + }, + { + "epoch": 0.93, + "learning_rate": 3.6174805932753186e-06, + "loss": 0.094, + "step": 415850 + }, + { + "epoch": 0.93, + "learning_rate": 3.616362050065994e-06, + "loss": 0.0892, + "step": 415860 + }, + { + "epoch": 0.93, + "learning_rate": 3.61524350685667e-06, + "loss": 0.0907, + "step": 415870 + }, + { + "epoch": 0.93, + "learning_rate": 3.614124963647346e-06, + "loss": 0.0898, + "step": 415880 + }, + { + "epoch": 0.93, + "learning_rate": 3.613006420438022e-06, + "loss": 0.0898, + "step": 415890 + }, + { + "epoch": 0.93, + "learning_rate": 3.6118878772286973e-06, + "loss": 0.0929, + "step": 415900 + }, + { + "epoch": 0.93, + "learning_rate": 3.610769334019373e-06, + "loss": 0.0935, + "step": 415910 + }, + { + "epoch": 0.93, + "learning_rate": 3.6096507908100493e-06, + "loss": 0.0946, + "step": 415920 + }, + { + "epoch": 0.93, + "learning_rate": 3.608532247600725e-06, + "loss": 0.0898, + "step": 415930 + }, + { + "epoch": 0.93, + "learning_rate": 3.6074137043914005e-06, + "loss": 0.0989, + "step": 415940 + }, + { + "epoch": 0.93, + "learning_rate": 3.6062951611820767e-06, + "loss": 0.0903, + "step": 415950 + }, + { + "epoch": 0.93, + "learning_rate": 3.6051766179727525e-06, + "loss": 0.0944, + "step": 415960 + }, + { + "epoch": 0.93, + "learning_rate": 3.6040580747634284e-06, + "loss": 0.0942, + "step": 415970 + }, + { + "epoch": 0.93, + "learning_rate": 3.6029395315541037e-06, + "loss": 0.0906, + "step": 415980 + }, + { + "epoch": 0.93, + "learning_rate": 3.60182098834478e-06, + "loss": 0.0909, + "step": 415990 + }, + { + "epoch": 0.93, + "learning_rate": 3.6007024451354558e-06, + "loss": 0.0904, + "step": 416000 + }, + { + "epoch": 0.93, + "eval_NEIMS_canon_smiles": 0.9624666666666667, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.2750666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.6371111906214365, + "eval_NEIMS_exact_mols": 0.2747, + "eval_NEIMS_exact_smiles": 0.26936666666666664, + "eval_NEIMS_loss": 0.11969273537397385, + "eval_NEIMS_matched_formulas": 0.7757166666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.5660433149519205, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.27545, + "eval_NEIMS_runtime": 719.1351, + "eval_NEIMS_samples_per_second": 83.434, + "eval_NEIMS_steps_per_second": 1.304, + "step": 416000 + }, + { + "epoch": 0.93, + "eval_RASSP_canon_smiles": 0.9618993555280997, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.3591678632250309, + "eval_RASSP_daylight_tanimoto_simil": 0.7373454884679993, + "eval_RASSP_exact_mols": 0.3582328780846162, + "eval_RASSP_exact_smiles": 0.3507529969612983, + "eval_RASSP_loss": 0.09156587719917297, + "eval_RASSP_matched_formulas": 0.8974521654923698, + "eval_RASSP_morgan_tanimoto_simil": 0.6360392286168532, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.3583330550639463, + "eval_RASSP_runtime": 822.0191, + "eval_RASSP_samples_per_second": 72.862, + "eval_RASSP_steps_per_second": 1.139, + "step": 416000 + }, + { + "epoch": 0.93, + "eval_NEIMS_old_canon_smiles": 0.9609666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2737, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6360609580727021, + "eval_NEIMS_old_exact_mols": 0.2733333333333333, + "eval_NEIMS_old_exact_smiles": 0.26753333333333335, + "eval_NEIMS_old_loss": 0.11973420530557632, + "eval_NEIMS_old_matched_formulas": 0.7747333333333334, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5656519533604796, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.27423333333333333, + "eval_NEIMS_old_runtime": 361.5457, + "eval_NEIMS_old_samples_per_second": 82.977, + "eval_NEIMS_old_steps_per_second": 1.297, + "step": 416000 + }, + { + "epoch": 0.93, + "eval_RASSP_old_canon_smiles": 0.9604565021523676, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.3906630627023059, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7553457264259706, + "eval_RASSP_old_exact_mols": 0.38949511128908465, + "eval_RASSP_old_exact_smiles": 0.38021824006407046, + "eval_RASSP_old_loss": 0.0857519656419754, + "eval_RASSP_old_matched_formulas": 0.9081656488804352, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6592790715363493, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.38966196149097343, + "eval_RASSP_old_runtime": 409.6739, + "eval_RASSP_old_samples_per_second": 73.148, + "eval_RASSP_old_steps_per_second": 1.145, + "step": 416000 + }, + { + "epoch": 0.93, + "eval_NIST_canon_smiles": 0.8661674415303261, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.03087624658409341, + "eval_NIST_daylight_tanimoto_simil": 0.30508954105288427, + "eval_NIST_exact_mols": 0.029634098733009193, + "eval_NIST_exact_smiles": 0.028462930759129788, + "eval_NIST_loss": 1.8143688440322876, + "eval_NIST_matched_formulas": 0.1352166660751677, + "eval_NIST_morgan_tanimoto_simil": 0.25456425299800667, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.030663306952478972, + "eval_NIST_runtime": 568.221, + "eval_NIST_samples_per_second": 49.588, + "eval_NIST_steps_per_second": 0.776, + "step": 416000 + }, + { + "epoch": 0.93, + "learning_rate": 3.599583901926132e-06, + "loss": 0.0891, + "step": 416010 + }, + { + "epoch": 0.93, + "learning_rate": 3.598465358716807e-06, + "loss": 0.0936, + "step": 416020 + }, + { + "epoch": 0.93, + "learning_rate": 3.5973468155074832e-06, + "loss": 0.0902, + "step": 416030 + }, + { + "epoch": 0.93, + "learning_rate": 3.5963401266190916e-06, + "loss": 0.0942, + "step": 416040 + }, + { + "epoch": 0.93, + "learning_rate": 3.595221583409767e-06, + "loss": 0.0935, + "step": 416050 + }, + { + "epoch": 0.93, + "learning_rate": 3.594103040200443e-06, + "loss": 0.0913, + "step": 416060 + }, + { + "epoch": 0.93, + "learning_rate": 3.592984496991119e-06, + "loss": 0.0937, + "step": 416070 + }, + { + "epoch": 0.93, + "learning_rate": 3.591865953781795e-06, + "loss": 0.0917, + "step": 416080 + }, + { + "epoch": 0.93, + "learning_rate": 3.59074741057247e-06, + "loss": 0.0956, + "step": 416090 + }, + { + "epoch": 0.93, + "learning_rate": 3.5896288673631464e-06, + "loss": 0.0932, + "step": 416100 + }, + { + "epoch": 0.93, + "learning_rate": 3.5885103241538222e-06, + "loss": 0.0915, + "step": 416110 + }, + { + "epoch": 0.93, + "learning_rate": 3.5873917809444985e-06, + "loss": 0.0903, + "step": 416120 + }, + { + "epoch": 0.93, + "learning_rate": 3.5862732377351734e-06, + "loss": 0.0898, + "step": 416130 + }, + { + "epoch": 0.93, + "learning_rate": 3.5851546945258497e-06, + "loss": 0.0959, + "step": 416140 + }, + { + "epoch": 0.93, + "learning_rate": 3.5840361513165255e-06, + "loss": 0.0909, + "step": 416150 + }, + { + "epoch": 0.93, + "learning_rate": 3.5829176081072017e-06, + "loss": 0.0928, + "step": 416160 + }, + { + "epoch": 0.93, + "learning_rate": 3.581799064897877e-06, + "loss": 0.0915, + "step": 416170 + }, + { + "epoch": 0.93, + "learning_rate": 3.580680521688553e-06, + "loss": 0.0909, + "step": 416180 + }, + { + "epoch": 0.93, + "learning_rate": 3.5795619784792287e-06, + "loss": 0.0903, + "step": 416190 + }, + { + "epoch": 0.93, + "learning_rate": 3.578443435269905e-06, + "loss": 0.0909, + "step": 416200 + }, + { + "epoch": 0.93, + "learning_rate": 3.5773248920605803e-06, + "loss": 0.0888, + "step": 416210 + }, + { + "epoch": 0.93, + "learning_rate": 3.576206348851256e-06, + "loss": 0.0927, + "step": 416220 + }, + { + "epoch": 0.93, + "learning_rate": 3.5750878056419324e-06, + "loss": 0.0914, + "step": 416230 + }, + { + "epoch": 0.93, + "learning_rate": 3.573969262432608e-06, + "loss": 0.0917, + "step": 416240 + }, + { + "epoch": 0.93, + "learning_rate": 3.5728507192232836e-06, + "loss": 0.094, + "step": 416250 + }, + { + "epoch": 0.93, + "learning_rate": 3.5717321760139594e-06, + "loss": 0.0908, + "step": 416260 + }, + { + "epoch": 0.93, + "learning_rate": 3.5706136328046356e-06, + "loss": 0.0952, + "step": 416270 + }, + { + "epoch": 0.93, + "learning_rate": 3.5694950895953114e-06, + "loss": 0.0913, + "step": 416280 + }, + { + "epoch": 0.93, + "learning_rate": 3.568376546385987e-06, + "loss": 0.0917, + "step": 416290 + }, + { + "epoch": 0.93, + "learning_rate": 3.5672580031766626e-06, + "loss": 0.0907, + "step": 416300 + }, + { + "epoch": 0.93, + "learning_rate": 3.566139459967339e-06, + "loss": 0.0919, + "step": 416310 + }, + { + "epoch": 0.93, + "learning_rate": 3.5650209167580147e-06, + "loss": 0.0882, + "step": 416320 + }, + { + "epoch": 0.93, + "learning_rate": 3.56390237354869e-06, + "loss": 0.0946, + "step": 416330 + }, + { + "epoch": 0.93, + "learning_rate": 3.5627838303393663e-06, + "loss": 0.093, + "step": 416340 + }, + { + "epoch": 0.93, + "learning_rate": 3.561665287130042e-06, + "loss": 0.0956, + "step": 416350 + }, + { + "epoch": 0.93, + "learning_rate": 3.560546743920718e-06, + "loss": 0.098, + "step": 416360 + }, + { + "epoch": 0.93, + "learning_rate": 3.5594282007113933e-06, + "loss": 0.0914, + "step": 416370 + }, + { + "epoch": 0.93, + "learning_rate": 3.5583096575020695e-06, + "loss": 0.0943, + "step": 416380 + }, + { + "epoch": 0.93, + "learning_rate": 3.5571911142927453e-06, + "loss": 0.0906, + "step": 416390 + }, + { + "epoch": 0.93, + "learning_rate": 3.5560725710834216e-06, + "loss": 0.091, + "step": 416400 + }, + { + "epoch": 0.93, + "learning_rate": 3.5549540278740965e-06, + "loss": 0.0896, + "step": 416410 + }, + { + "epoch": 0.93, + "learning_rate": 3.5538354846647728e-06, + "loss": 0.0924, + "step": 416420 + }, + { + "epoch": 0.93, + "learning_rate": 3.5527169414554486e-06, + "loss": 0.095, + "step": 416430 + }, + { + "epoch": 0.93, + "learning_rate": 3.551598398246125e-06, + "loss": 0.0958, + "step": 416440 + }, + { + "epoch": 0.93, + "learning_rate": 3.5504798550368e-06, + "loss": 0.0947, + "step": 416450 + }, + { + "epoch": 0.93, + "learning_rate": 3.549361311827476e-06, + "loss": 0.0868, + "step": 416460 + }, + { + "epoch": 0.93, + "learning_rate": 3.548242768618152e-06, + "loss": 0.0942, + "step": 416470 + }, + { + "epoch": 0.93, + "learning_rate": 3.547124225408828e-06, + "loss": 0.0936, + "step": 416480 + }, + { + "epoch": 0.93, + "learning_rate": 3.5460056821995035e-06, + "loss": 0.091, + "step": 416490 + }, + { + "epoch": 0.93, + "learning_rate": 3.5448871389901793e-06, + "loss": 0.095, + "step": 416500 + }, + { + "epoch": 0.93, + "learning_rate": 3.5437685957808555e-06, + "loss": 0.0897, + "step": 416510 + }, + { + "epoch": 0.93, + "learning_rate": 3.5426500525715313e-06, + "loss": 0.0938, + "step": 416520 + }, + { + "epoch": 0.93, + "learning_rate": 3.5415315093622067e-06, + "loss": 0.0931, + "step": 416530 + }, + { + "epoch": 0.93, + "learning_rate": 3.5404129661528825e-06, + "loss": 0.0936, + "step": 416540 + }, + { + "epoch": 0.93, + "learning_rate": 3.5392944229435587e-06, + "loss": 0.0899, + "step": 416550 + }, + { + "epoch": 0.93, + "learning_rate": 3.5381758797342345e-06, + "loss": 0.093, + "step": 416560 + }, + { + "epoch": 0.93, + "learning_rate": 3.53705733652491e-06, + "loss": 0.0912, + "step": 416570 + }, + { + "epoch": 0.93, + "learning_rate": 3.5359387933155857e-06, + "loss": 0.0906, + "step": 416580 + }, + { + "epoch": 0.93, + "learning_rate": 3.534820250106262e-06, + "loss": 0.0888, + "step": 416590 + }, + { + "epoch": 0.93, + "learning_rate": 3.5337017068969378e-06, + "loss": 0.0907, + "step": 416600 + }, + { + "epoch": 0.93, + "learning_rate": 3.532583163687613e-06, + "loss": 0.0931, + "step": 416610 + }, + { + "epoch": 0.93, + "learning_rate": 3.531464620478289e-06, + "loss": 0.0958, + "step": 416620 + }, + { + "epoch": 0.93, + "learning_rate": 3.5303460772689652e-06, + "loss": 0.0938, + "step": 416630 + }, + { + "epoch": 0.93, + "learning_rate": 3.529227534059641e-06, + "loss": 0.0974, + "step": 416640 + }, + { + "epoch": 0.93, + "learning_rate": 3.5281089908503164e-06, + "loss": 0.0882, + "step": 416650 + }, + { + "epoch": 0.93, + "learning_rate": 3.5269904476409926e-06, + "loss": 0.0938, + "step": 416660 + }, + { + "epoch": 0.93, + "learning_rate": 3.5258719044316685e-06, + "loss": 0.0898, + "step": 416670 + }, + { + "epoch": 0.93, + "learning_rate": 3.5247533612223447e-06, + "loss": 0.091, + "step": 416680 + }, + { + "epoch": 0.93, + "learning_rate": 3.5236348180130197e-06, + "loss": 0.0914, + "step": 416690 + }, + { + "epoch": 0.93, + "learning_rate": 3.522516274803696e-06, + "loss": 0.0899, + "step": 416700 + }, + { + "epoch": 0.93, + "learning_rate": 3.5213977315943717e-06, + "loss": 0.0903, + "step": 416710 + }, + { + "epoch": 0.93, + "learning_rate": 3.520279188385048e-06, + "loss": 0.095, + "step": 416720 + }, + { + "epoch": 0.93, + "learning_rate": 3.519160645175723e-06, + "loss": 0.0927, + "step": 416730 + }, + { + "epoch": 0.93, + "learning_rate": 3.518042101966399e-06, + "loss": 0.092, + "step": 416740 + }, + { + "epoch": 0.93, + "learning_rate": 3.516923558757075e-06, + "loss": 0.0947, + "step": 416750 + }, + { + "epoch": 0.93, + "learning_rate": 3.515805015547751e-06, + "loss": 0.093, + "step": 416760 + }, + { + "epoch": 0.93, + "learning_rate": 3.5146864723384266e-06, + "loss": 0.0933, + "step": 416770 + }, + { + "epoch": 0.93, + "learning_rate": 3.5135679291291024e-06, + "loss": 0.0879, + "step": 416780 + }, + { + "epoch": 0.93, + "learning_rate": 3.512449385919778e-06, + "loss": 0.0891, + "step": 416790 + }, + { + "epoch": 0.93, + "learning_rate": 3.5113308427104544e-06, + "loss": 0.0904, + "step": 416800 + }, + { + "epoch": 0.93, + "learning_rate": 3.51021229950113e-06, + "loss": 0.0916, + "step": 416810 + }, + { + "epoch": 0.93, + "learning_rate": 3.5090937562918056e-06, + "loss": 0.0941, + "step": 416820 + }, + { + "epoch": 0.93, + "learning_rate": 3.507975213082482e-06, + "loss": 0.0965, + "step": 416830 + }, + { + "epoch": 0.93, + "learning_rate": 3.5068566698731577e-06, + "loss": 0.0938, + "step": 416840 + }, + { + "epoch": 0.93, + "learning_rate": 3.505738126663833e-06, + "loss": 0.0924, + "step": 416850 + }, + { + "epoch": 0.93, + "learning_rate": 3.504619583454509e-06, + "loss": 0.092, + "step": 416860 + }, + { + "epoch": 0.93, + "learning_rate": 3.503501040245185e-06, + "loss": 0.0906, + "step": 416870 + }, + { + "epoch": 0.93, + "learning_rate": 3.502382497035861e-06, + "loss": 0.0938, + "step": 416880 + }, + { + "epoch": 0.93, + "learning_rate": 3.5012639538265363e-06, + "loss": 0.0936, + "step": 416890 + }, + { + "epoch": 0.93, + "learning_rate": 3.500145410617212e-06, + "loss": 0.0916, + "step": 416900 + }, + { + "epoch": 0.93, + "learning_rate": 3.4990268674078883e-06, + "loss": 0.0926, + "step": 416910 + }, + { + "epoch": 0.93, + "learning_rate": 3.497908324198564e-06, + "loss": 0.094, + "step": 416920 + }, + { + "epoch": 0.93, + "learning_rate": 3.4967897809892395e-06, + "loss": 0.0932, + "step": 416930 + }, + { + "epoch": 0.93, + "learning_rate": 3.4956712377799158e-06, + "loss": 0.0941, + "step": 416940 + }, + { + "epoch": 0.93, + "learning_rate": 3.4945526945705916e-06, + "loss": 0.0937, + "step": 416950 + }, + { + "epoch": 0.93, + "learning_rate": 3.4934341513612674e-06, + "loss": 0.0921, + "step": 416960 + }, + { + "epoch": 0.93, + "learning_rate": 3.4923156081519428e-06, + "loss": 0.0933, + "step": 416970 + }, + { + "epoch": 0.93, + "learning_rate": 3.491197064942619e-06, + "loss": 0.0937, + "step": 416980 + }, + { + "epoch": 0.93, + "learning_rate": 3.490078521733295e-06, + "loss": 0.0914, + "step": 416990 + }, + { + "epoch": 0.93, + "learning_rate": 3.488959978523971e-06, + "loss": 0.0884, + "step": 417000 + }, + { + "epoch": 0.93, + "learning_rate": 3.487841435314646e-06, + "loss": 0.0971, + "step": 417010 + }, + { + "epoch": 0.93, + "learning_rate": 3.4867228921053222e-06, + "loss": 0.0937, + "step": 417020 + }, + { + "epoch": 0.93, + "learning_rate": 3.485604348895998e-06, + "loss": 0.0917, + "step": 417030 + }, + { + "epoch": 0.93, + "learning_rate": 3.4844858056866743e-06, + "loss": 0.0914, + "step": 417040 + }, + { + "epoch": 0.93, + "learning_rate": 3.4833672624773497e-06, + "loss": 0.0908, + "step": 417050 + }, + { + "epoch": 0.93, + "learning_rate": 3.4822487192680255e-06, + "loss": 0.0929, + "step": 417060 + }, + { + "epoch": 0.93, + "learning_rate": 3.4811301760587013e-06, + "loss": 0.0914, + "step": 417070 + }, + { + "epoch": 0.93, + "learning_rate": 3.4800116328493775e-06, + "loss": 0.0933, + "step": 417080 + }, + { + "epoch": 0.93, + "learning_rate": 3.478893089640053e-06, + "loss": 0.0934, + "step": 417090 + }, + { + "epoch": 0.93, + "learning_rate": 3.4777745464307287e-06, + "loss": 0.0909, + "step": 417100 + }, + { + "epoch": 0.93, + "learning_rate": 3.476656003221405e-06, + "loss": 0.091, + "step": 417110 + }, + { + "epoch": 0.93, + "learning_rate": 3.4755374600120808e-06, + "loss": 0.0924, + "step": 417120 + }, + { + "epoch": 0.93, + "learning_rate": 3.474418916802756e-06, + "loss": 0.0939, + "step": 417130 + }, + { + "epoch": 0.93, + "learning_rate": 3.473300373593432e-06, + "loss": 0.1001, + "step": 417140 + }, + { + "epoch": 0.93, + "learning_rate": 3.472181830384108e-06, + "loss": 0.0873, + "step": 417150 + }, + { + "epoch": 0.93, + "learning_rate": 3.471063287174784e-06, + "loss": 0.0943, + "step": 417160 + }, + { + "epoch": 0.93, + "learning_rate": 3.4699447439654594e-06, + "loss": 0.0943, + "step": 417170 + }, + { + "epoch": 0.93, + "learning_rate": 3.468826200756135e-06, + "loss": 0.0846, + "step": 417180 + }, + { + "epoch": 0.93, + "learning_rate": 3.4677076575468114e-06, + "loss": 0.0905, + "step": 417190 + }, + { + "epoch": 0.93, + "learning_rate": 3.4665891143374872e-06, + "loss": 0.0921, + "step": 417200 + }, + { + "epoch": 0.93, + "learning_rate": 3.4654705711281626e-06, + "loss": 0.0903, + "step": 417210 + }, + { + "epoch": 0.93, + "learning_rate": 3.4643520279188384e-06, + "loss": 0.0919, + "step": 417220 + }, + { + "epoch": 0.93, + "learning_rate": 3.4632334847095147e-06, + "loss": 0.0923, + "step": 417230 + }, + { + "epoch": 0.93, + "learning_rate": 3.4621149415001905e-06, + "loss": 0.0959, + "step": 417240 + }, + { + "epoch": 0.93, + "learning_rate": 3.460996398290866e-06, + "loss": 0.0894, + "step": 417250 + }, + { + "epoch": 0.93, + "learning_rate": 3.459877855081542e-06, + "loss": 0.0887, + "step": 417260 + }, + { + "epoch": 0.93, + "learning_rate": 3.458759311872218e-06, + "loss": 0.0921, + "step": 417270 + }, + { + "epoch": 0.93, + "learning_rate": 3.457640768662894e-06, + "loss": 0.0916, + "step": 417280 + }, + { + "epoch": 0.93, + "learning_rate": 3.456522225453569e-06, + "loss": 0.0881, + "step": 417290 + }, + { + "epoch": 0.93, + "learning_rate": 3.4554036822442453e-06, + "loss": 0.0916, + "step": 417300 + }, + { + "epoch": 0.93, + "learning_rate": 3.454285139034921e-06, + "loss": 0.0924, + "step": 417310 + }, + { + "epoch": 0.93, + "learning_rate": 3.4531665958255974e-06, + "loss": 0.0961, + "step": 417320 + }, + { + "epoch": 0.93, + "learning_rate": 3.4520480526162723e-06, + "loss": 0.0888, + "step": 417330 + }, + { + "epoch": 0.93, + "learning_rate": 3.4509295094069486e-06, + "loss": 0.0939, + "step": 417340 + }, + { + "epoch": 0.93, + "learning_rate": 3.4498109661976244e-06, + "loss": 0.0949, + "step": 417350 + }, + { + "epoch": 0.93, + "learning_rate": 3.4486924229883006e-06, + "loss": 0.0905, + "step": 417360 + }, + { + "epoch": 0.93, + "learning_rate": 3.447573879778976e-06, + "loss": 0.0898, + "step": 417370 + }, + { + "epoch": 0.93, + "learning_rate": 3.446455336569652e-06, + "loss": 0.094, + "step": 417380 + }, + { + "epoch": 0.93, + "learning_rate": 3.4453367933603276e-06, + "loss": 0.0936, + "step": 417390 + }, + { + "epoch": 0.93, + "learning_rate": 3.444218250151004e-06, + "loss": 0.0898, + "step": 417400 + }, + { + "epoch": 0.93, + "learning_rate": 3.4430997069416793e-06, + "loss": 0.0924, + "step": 417410 + }, + { + "epoch": 0.93, + "learning_rate": 3.441981163732355e-06, + "loss": 0.0906, + "step": 417420 + }, + { + "epoch": 0.93, + "learning_rate": 3.4408626205230313e-06, + "loss": 0.0936, + "step": 417430 + }, + { + "epoch": 0.93, + "learning_rate": 3.439744077313707e-06, + "loss": 0.0887, + "step": 417440 + }, + { + "epoch": 0.93, + "learning_rate": 3.4386255341043825e-06, + "loss": 0.0881, + "step": 417450 + }, + { + "epoch": 0.93, + "learning_rate": 3.4375069908950583e-06, + "loss": 0.0915, + "step": 417460 + }, + { + "epoch": 0.93, + "learning_rate": 3.4363884476857345e-06, + "loss": 0.0951, + "step": 417470 + }, + { + "epoch": 0.93, + "learning_rate": 3.4352699044764103e-06, + "loss": 0.0916, + "step": 417480 + }, + { + "epoch": 0.93, + "learning_rate": 3.4341513612670857e-06, + "loss": 0.0924, + "step": 417490 + }, + { + "epoch": 0.93, + "learning_rate": 3.4330328180577615e-06, + "loss": 0.0917, + "step": 417500 + }, + { + "epoch": 0.93, + "learning_rate": 3.4319142748484378e-06, + "loss": 0.0921, + "step": 417510 + }, + { + "epoch": 0.93, + "learning_rate": 3.4307957316391136e-06, + "loss": 0.0912, + "step": 417520 + }, + { + "epoch": 0.93, + "learning_rate": 3.429677188429789e-06, + "loss": 0.0908, + "step": 417530 + }, + { + "epoch": 0.93, + "learning_rate": 3.428558645220465e-06, + "loss": 0.0902, + "step": 417540 + }, + { + "epoch": 0.93, + "learning_rate": 3.427440102011141e-06, + "loss": 0.0915, + "step": 417550 + }, + { + "epoch": 0.93, + "learning_rate": 3.426321558801817e-06, + "loss": 0.0931, + "step": 417560 + }, + { + "epoch": 0.93, + "learning_rate": 3.425203015592492e-06, + "loss": 0.0907, + "step": 417570 + }, + { + "epoch": 0.93, + "learning_rate": 3.4240844723831684e-06, + "loss": 0.0915, + "step": 417580 + }, + { + "epoch": 0.93, + "learning_rate": 3.4229659291738443e-06, + "loss": 0.091, + "step": 417590 + }, + { + "epoch": 0.93, + "learning_rate": 3.4218473859645205e-06, + "loss": 0.0921, + "step": 417600 + }, + { + "epoch": 0.93, + "learning_rate": 3.4207288427551955e-06, + "loss": 0.0915, + "step": 417610 + }, + { + "epoch": 0.93, + "learning_rate": 3.4196102995458717e-06, + "loss": 0.0898, + "step": 417620 + }, + { + "epoch": 0.93, + "learning_rate": 3.4184917563365475e-06, + "loss": 0.0922, + "step": 417630 + }, + { + "epoch": 0.93, + "learning_rate": 3.4173732131272237e-06, + "loss": 0.0934, + "step": 417640 + }, + { + "epoch": 0.93, + "learning_rate": 3.416254669917899e-06, + "loss": 0.0944, + "step": 417650 + }, + { + "epoch": 0.93, + "learning_rate": 3.415136126708575e-06, + "loss": 0.0981, + "step": 417660 + }, + { + "epoch": 0.93, + "learning_rate": 3.4140175834992507e-06, + "loss": 0.0927, + "step": 417670 + }, + { + "epoch": 0.93, + "learning_rate": 3.412899040289927e-06, + "loss": 0.0918, + "step": 417680 + }, + { + "epoch": 0.93, + "learning_rate": 3.4117804970806024e-06, + "loss": 0.0909, + "step": 417690 + }, + { + "epoch": 0.93, + "learning_rate": 3.410661953871278e-06, + "loss": 0.0892, + "step": 417700 + }, + { + "epoch": 0.93, + "learning_rate": 3.4095434106619544e-06, + "loss": 0.0937, + "step": 417710 + }, + { + "epoch": 0.93, + "learning_rate": 3.40842486745263e-06, + "loss": 0.0939, + "step": 417720 + }, + { + "epoch": 0.93, + "learning_rate": 3.4073063242433056e-06, + "loss": 0.0899, + "step": 417730 + }, + { + "epoch": 0.93, + "learning_rate": 3.4061877810339814e-06, + "loss": 0.0854, + "step": 417740 + }, + { + "epoch": 0.93, + "learning_rate": 3.4050692378246576e-06, + "loss": 0.0945, + "step": 417750 + }, + { + "epoch": 0.93, + "learning_rate": 3.4039506946153326e-06, + "loss": 0.0904, + "step": 417760 + }, + { + "epoch": 0.93, + "learning_rate": 3.402832151406009e-06, + "loss": 0.0869, + "step": 417770 + }, + { + "epoch": 0.93, + "learning_rate": 3.4017136081966846e-06, + "loss": 0.0934, + "step": 417780 + }, + { + "epoch": 0.93, + "learning_rate": 3.400595064987361e-06, + "loss": 0.0897, + "step": 417790 + }, + { + "epoch": 0.93, + "learning_rate": 3.3994765217780363e-06, + "loss": 0.0906, + "step": 417800 + }, + { + "epoch": 0.93, + "learning_rate": 3.398357978568712e-06, + "loss": 0.0905, + "step": 417810 + }, + { + "epoch": 0.93, + "learning_rate": 3.3972394353593883e-06, + "loss": 0.0932, + "step": 417820 + }, + { + "epoch": 0.93, + "learning_rate": 3.396120892150064e-06, + "loss": 0.0904, + "step": 417830 + }, + { + "epoch": 0.93, + "learning_rate": 3.3950023489407395e-06, + "loss": 0.0901, + "step": 417840 + }, + { + "epoch": 0.93, + "learning_rate": 3.3938838057314153e-06, + "loss": 0.0934, + "step": 417850 + }, + { + "epoch": 0.93, + "learning_rate": 3.3927652625220916e-06, + "loss": 0.0935, + "step": 417860 + }, + { + "epoch": 0.93, + "learning_rate": 3.3916467193127674e-06, + "loss": 0.0919, + "step": 417870 + }, + { + "epoch": 0.93, + "learning_rate": 3.3905281761034427e-06, + "loss": 0.0941, + "step": 417880 + }, + { + "epoch": 0.93, + "learning_rate": 3.3894096328941186e-06, + "loss": 0.0948, + "step": 417890 + }, + { + "epoch": 0.93, + "learning_rate": 3.388291089684795e-06, + "loss": 0.0913, + "step": 417900 + }, + { + "epoch": 0.93, + "learning_rate": 3.3871725464754706e-06, + "loss": 0.093, + "step": 417910 + }, + { + "epoch": 0.93, + "learning_rate": 3.386054003266146e-06, + "loss": 0.0953, + "step": 417920 + }, + { + "epoch": 0.93, + "learning_rate": 3.384935460056822e-06, + "loss": 0.0843, + "step": 417930 + }, + { + "epoch": 0.93, + "learning_rate": 3.383816916847498e-06, + "loss": 0.0887, + "step": 417940 + }, + { + "epoch": 0.93, + "learning_rate": 3.382698373638174e-06, + "loss": 0.0892, + "step": 417950 + }, + { + "epoch": 0.93, + "learning_rate": 3.3815798304288492e-06, + "loss": 0.0975, + "step": 417960 + }, + { + "epoch": 0.93, + "learning_rate": 3.3804612872195255e-06, + "loss": 0.0909, + "step": 417970 + }, + { + "epoch": 0.93, + "learning_rate": 3.3793427440102013e-06, + "loss": 0.0904, + "step": 417980 + }, + { + "epoch": 0.93, + "learning_rate": 3.378224200800877e-06, + "loss": 0.0888, + "step": 417990 + }, + { + "epoch": 0.93, + "learning_rate": 3.3771056575915525e-06, + "loss": 0.0892, + "step": 418000 + }, + { + "epoch": 0.93, + "learning_rate": 3.3759871143822287e-06, + "loss": 0.0928, + "step": 418010 + }, + { + "epoch": 0.93, + "learning_rate": 3.3748685711729045e-06, + "loss": 0.094, + "step": 418020 + }, + { + "epoch": 0.93, + "learning_rate": 3.3737500279635807e-06, + "loss": 0.0945, + "step": 418030 + }, + { + "epoch": 0.93, + "learning_rate": 3.3726314847542557e-06, + "loss": 0.0921, + "step": 418040 + }, + { + "epoch": 0.93, + "learning_rate": 3.371512941544932e-06, + "loss": 0.09, + "step": 418050 + }, + { + "epoch": 0.93, + "learning_rate": 3.3703943983356078e-06, + "loss": 0.0921, + "step": 418060 + }, + { + "epoch": 0.93, + "learning_rate": 3.3693877094472157e-06, + "loss": 0.0908, + "step": 418070 + }, + { + "epoch": 0.93, + "learning_rate": 3.368269166237892e-06, + "loss": 0.0926, + "step": 418080 + }, + { + "epoch": 0.93, + "learning_rate": 3.3671506230285677e-06, + "loss": 0.0938, + "step": 418090 + }, + { + "epoch": 0.93, + "learning_rate": 3.366032079819244e-06, + "loss": 0.092, + "step": 418100 + }, + { + "epoch": 0.93, + "learning_rate": 3.364913536609919e-06, + "loss": 0.0957, + "step": 418110 + }, + { + "epoch": 0.93, + "learning_rate": 3.363794993400595e-06, + "loss": 0.0919, + "step": 418120 + }, + { + "epoch": 0.93, + "learning_rate": 3.362676450191271e-06, + "loss": 0.0946, + "step": 418130 + }, + { + "epoch": 0.93, + "learning_rate": 3.361557906981947e-06, + "loss": 0.0874, + "step": 418140 + }, + { + "epoch": 0.93, + "learning_rate": 3.3604393637726226e-06, + "loss": 0.0894, + "step": 418150 + }, + { + "epoch": 0.93, + "learning_rate": 3.3593208205632984e-06, + "loss": 0.0915, + "step": 418160 + }, + { + "epoch": 0.93, + "learning_rate": 3.358202277353974e-06, + "loss": 0.0946, + "step": 418170 + }, + { + "epoch": 0.93, + "learning_rate": 3.3570837341446504e-06, + "loss": 0.0889, + "step": 418180 + }, + { + "epoch": 0.93, + "learning_rate": 3.355965190935326e-06, + "loss": 0.0886, + "step": 418190 + }, + { + "epoch": 0.93, + "learning_rate": 3.3548466477260016e-06, + "loss": 0.0948, + "step": 418200 + }, + { + "epoch": 0.93, + "learning_rate": 3.353728104516678e-06, + "loss": 0.0948, + "step": 418210 + }, + { + "epoch": 0.93, + "learning_rate": 3.3526095613073537e-06, + "loss": 0.0946, + "step": 418220 + }, + { + "epoch": 0.93, + "learning_rate": 3.351491018098029e-06, + "loss": 0.0937, + "step": 418230 + }, + { + "epoch": 0.93, + "learning_rate": 3.350372474888705e-06, + "loss": 0.0944, + "step": 418240 + }, + { + "epoch": 0.93, + "learning_rate": 3.349253931679381e-06, + "loss": 0.0919, + "step": 418250 + }, + { + "epoch": 0.93, + "learning_rate": 3.348135388470057e-06, + "loss": 0.0931, + "step": 418260 + }, + { + "epoch": 0.93, + "learning_rate": 3.3470168452607323e-06, + "loss": 0.089, + "step": 418270 + }, + { + "epoch": 0.93, + "learning_rate": 3.345898302051408e-06, + "loss": 0.0936, + "step": 418280 + }, + { + "epoch": 0.93, + "learning_rate": 3.3447797588420844e-06, + "loss": 0.0964, + "step": 418290 + }, + { + "epoch": 0.93, + "learning_rate": 3.34366121563276e-06, + "loss": 0.0892, + "step": 418300 + }, + { + "epoch": 0.93, + "learning_rate": 3.3425426724234356e-06, + "loss": 0.0896, + "step": 418310 + }, + { + "epoch": 0.93, + "learning_rate": 3.3414241292141118e-06, + "loss": 0.0934, + "step": 418320 + }, + { + "epoch": 0.93, + "learning_rate": 3.3403055860047876e-06, + "loss": 0.0937, + "step": 418330 + }, + { + "epoch": 0.93, + "learning_rate": 3.3391870427954634e-06, + "loss": 0.0877, + "step": 418340 + }, + { + "epoch": 0.93, + "learning_rate": 3.338068499586139e-06, + "loss": 0.0958, + "step": 418350 + }, + { + "epoch": 0.93, + "learning_rate": 3.336949956376815e-06, + "loss": 0.0942, + "step": 418360 + }, + { + "epoch": 0.93, + "learning_rate": 3.335831413167491e-06, + "loss": 0.0885, + "step": 418370 + }, + { + "epoch": 0.93, + "learning_rate": 3.334712869958167e-06, + "loss": 0.096, + "step": 418380 + }, + { + "epoch": 0.93, + "learning_rate": 3.333594326748842e-06, + "loss": 0.0938, + "step": 418390 + }, + { + "epoch": 0.93, + "learning_rate": 3.3324757835395183e-06, + "loss": 0.09, + "step": 418400 + }, + { + "epoch": 0.93, + "learning_rate": 3.331357240330194e-06, + "loss": 0.0928, + "step": 418410 + }, + { + "epoch": 0.93, + "learning_rate": 3.3302386971208703e-06, + "loss": 0.0934, + "step": 418420 + }, + { + "epoch": 0.93, + "learning_rate": 3.3291201539115453e-06, + "loss": 0.0898, + "step": 418430 + }, + { + "epoch": 0.93, + "learning_rate": 3.3280016107022215e-06, + "loss": 0.0923, + "step": 418440 + }, + { + "epoch": 0.93, + "learning_rate": 3.3268830674928973e-06, + "loss": 0.0923, + "step": 418450 + }, + { + "epoch": 0.93, + "learning_rate": 3.3257645242835736e-06, + "loss": 0.0906, + "step": 418460 + }, + { + "epoch": 0.93, + "learning_rate": 3.324645981074249e-06, + "loss": 0.094, + "step": 418470 + }, + { + "epoch": 0.93, + "learning_rate": 3.3235274378649247e-06, + "loss": 0.0931, + "step": 418480 + }, + { + "epoch": 0.93, + "learning_rate": 3.3224088946556006e-06, + "loss": 0.0936, + "step": 418490 + }, + { + "epoch": 0.93, + "learning_rate": 3.321290351446277e-06, + "loss": 0.0921, + "step": 418500 + }, + { + "epoch": 0.93, + "learning_rate": 3.320171808236952e-06, + "loss": 0.0868, + "step": 418510 + }, + { + "epoch": 0.93, + "learning_rate": 3.319053265027628e-06, + "loss": 0.0902, + "step": 418520 + }, + { + "epoch": 0.93, + "learning_rate": 3.3179347218183042e-06, + "loss": 0.0945, + "step": 418530 + }, + { + "epoch": 0.93, + "learning_rate": 3.31681617860898e-06, + "loss": 0.093, + "step": 418540 + }, + { + "epoch": 0.93, + "learning_rate": 3.3156976353996554e-06, + "loss": 0.0932, + "step": 418550 + }, + { + "epoch": 0.93, + "learning_rate": 3.3145790921903312e-06, + "loss": 0.098, + "step": 418560 + }, + { + "epoch": 0.93, + "learning_rate": 3.3134605489810075e-06, + "loss": 0.0915, + "step": 418570 + }, + { + "epoch": 0.93, + "learning_rate": 3.3123420057716833e-06, + "loss": 0.0939, + "step": 418580 + }, + { + "epoch": 0.93, + "learning_rate": 3.3112234625623587e-06, + "loss": 0.0939, + "step": 418590 + }, + { + "epoch": 0.93, + "learning_rate": 3.3101049193530345e-06, + "loss": 0.0907, + "step": 418600 + }, + { + "epoch": 0.93, + "learning_rate": 3.3089863761437107e-06, + "loss": 0.0963, + "step": 418610 + }, + { + "epoch": 0.93, + "learning_rate": 3.3078678329343865e-06, + "loss": 0.091, + "step": 418620 + }, + { + "epoch": 0.93, + "learning_rate": 3.306749289725062e-06, + "loss": 0.0941, + "step": 418630 + }, + { + "epoch": 0.93, + "learning_rate": 3.305630746515738e-06, + "loss": 0.0949, + "step": 418640 + }, + { + "epoch": 0.93, + "learning_rate": 3.304512203306414e-06, + "loss": 0.0908, + "step": 418650 + }, + { + "epoch": 0.93, + "learning_rate": 3.3033936600970898e-06, + "loss": 0.0923, + "step": 418660 + }, + { + "epoch": 0.93, + "learning_rate": 3.302275116887765e-06, + "loss": 0.0918, + "step": 418670 + }, + { + "epoch": 0.93, + "learning_rate": 3.3011565736784414e-06, + "loss": 0.0938, + "step": 418680 + }, + { + "epoch": 0.93, + "learning_rate": 3.300038030469117e-06, + "loss": 0.0897, + "step": 418690 + }, + { + "epoch": 0.93, + "learning_rate": 3.2989194872597934e-06, + "loss": 0.0913, + "step": 418700 + }, + { + "epoch": 0.93, + "learning_rate": 3.2978009440504684e-06, + "loss": 0.0932, + "step": 418710 + }, + { + "epoch": 0.93, + "learning_rate": 3.2966824008411446e-06, + "loss": 0.0887, + "step": 418720 + }, + { + "epoch": 0.93, + "learning_rate": 3.2955638576318204e-06, + "loss": 0.0932, + "step": 418730 + }, + { + "epoch": 0.93, + "learning_rate": 3.2944453144224967e-06, + "loss": 0.0959, + "step": 418740 + }, + { + "epoch": 0.93, + "learning_rate": 3.293326771213172e-06, + "loss": 0.0984, + "step": 418750 + }, + { + "epoch": 0.93, + "learning_rate": 3.292208228003848e-06, + "loss": 0.0938, + "step": 418760 + }, + { + "epoch": 0.93, + "learning_rate": 3.2910896847945237e-06, + "loss": 0.0938, + "step": 418770 + }, + { + "epoch": 0.93, + "learning_rate": 3.2899711415852e-06, + "loss": 0.0895, + "step": 418780 + }, + { + "epoch": 0.93, + "learning_rate": 3.2888525983758753e-06, + "loss": 0.0914, + "step": 418790 + }, + { + "epoch": 0.93, + "learning_rate": 3.287734055166551e-06, + "loss": 0.093, + "step": 418800 + }, + { + "epoch": 0.93, + "learning_rate": 3.2866155119572273e-06, + "loss": 0.0942, + "step": 418810 + }, + { + "epoch": 0.93, + "learning_rate": 3.285496968747903e-06, + "loss": 0.0893, + "step": 418820 + }, + { + "epoch": 0.93, + "learning_rate": 3.2843784255385785e-06, + "loss": 0.0959, + "step": 418830 + }, + { + "epoch": 0.93, + "learning_rate": 3.2832598823292543e-06, + "loss": 0.0914, + "step": 418840 + }, + { + "epoch": 0.93, + "learning_rate": 3.2821413391199306e-06, + "loss": 0.0961, + "step": 418850 + }, + { + "epoch": 0.93, + "learning_rate": 3.2810227959106064e-06, + "loss": 0.0925, + "step": 418860 + }, + { + "epoch": 0.93, + "learning_rate": 3.2799042527012818e-06, + "loss": 0.0905, + "step": 418870 + }, + { + "epoch": 0.93, + "learning_rate": 3.2787857094919576e-06, + "loss": 0.0898, + "step": 418880 + }, + { + "epoch": 0.94, + "learning_rate": 3.277667166282634e-06, + "loss": 0.0903, + "step": 418890 + }, + { + "epoch": 0.94, + "learning_rate": 3.2765486230733096e-06, + "loss": 0.0919, + "step": 418900 + }, + { + "epoch": 0.94, + "learning_rate": 3.275430079863985e-06, + "loss": 0.0904, + "step": 418910 + }, + { + "epoch": 0.94, + "learning_rate": 3.2743115366546612e-06, + "loss": 0.0906, + "step": 418920 + }, + { + "epoch": 0.94, + "learning_rate": 3.273192993445337e-06, + "loss": 0.0933, + "step": 418930 + }, + { + "epoch": 0.94, + "learning_rate": 3.272074450236013e-06, + "loss": 0.0944, + "step": 418940 + }, + { + "epoch": 0.94, + "learning_rate": 3.2709559070266882e-06, + "loss": 0.0921, + "step": 418950 + }, + { + "epoch": 0.94, + "learning_rate": 3.2698373638173645e-06, + "loss": 0.0931, + "step": 418960 + }, + { + "epoch": 0.94, + "learning_rate": 3.2687188206080403e-06, + "loss": 0.0919, + "step": 418970 + }, + { + "epoch": 0.94, + "learning_rate": 3.2676002773987165e-06, + "loss": 0.098, + "step": 418980 + }, + { + "epoch": 0.94, + "learning_rate": 3.2664817341893915e-06, + "loss": 0.0913, + "step": 418990 + }, + { + "epoch": 0.94, + "learning_rate": 3.2653631909800677e-06, + "loss": 0.0945, + "step": 419000 + }, + { + "epoch": 0.94, + "learning_rate": 3.2642446477707435e-06, + "loss": 0.0913, + "step": 419010 + }, + { + "epoch": 0.94, + "learning_rate": 3.2631261045614198e-06, + "loss": 0.0922, + "step": 419020 + }, + { + "epoch": 0.94, + "learning_rate": 3.2620075613520947e-06, + "loss": 0.0922, + "step": 419030 + }, + { + "epoch": 0.94, + "learning_rate": 3.260889018142771e-06, + "loss": 0.0903, + "step": 419040 + }, + { + "epoch": 0.94, + "learning_rate": 3.2597704749334468e-06, + "loss": 0.0933, + "step": 419050 + }, + { + "epoch": 0.94, + "learning_rate": 3.258651931724123e-06, + "loss": 0.0926, + "step": 419060 + }, + { + "epoch": 0.94, + "learning_rate": 3.2575333885147984e-06, + "loss": 0.0908, + "step": 419070 + }, + { + "epoch": 0.94, + "learning_rate": 3.256414845305474e-06, + "loss": 0.096, + "step": 419080 + }, + { + "epoch": 0.94, + "learning_rate": 3.25529630209615e-06, + "loss": 0.0926, + "step": 419090 + }, + { + "epoch": 0.94, + "learning_rate": 3.2541777588868262e-06, + "loss": 0.0915, + "step": 419100 + }, + { + "epoch": 0.94, + "learning_rate": 3.2530592156775016e-06, + "loss": 0.0894, + "step": 419110 + }, + { + "epoch": 0.94, + "learning_rate": 3.2519406724681774e-06, + "loss": 0.0916, + "step": 419120 + }, + { + "epoch": 0.94, + "learning_rate": 3.2508221292588537e-06, + "loss": 0.0923, + "step": 419130 + }, + { + "epoch": 0.94, + "learning_rate": 3.2497035860495295e-06, + "loss": 0.0962, + "step": 419140 + }, + { + "epoch": 0.94, + "learning_rate": 3.248585042840205e-06, + "loss": 0.0922, + "step": 419150 + }, + { + "epoch": 0.94, + "learning_rate": 3.2474664996308807e-06, + "loss": 0.0901, + "step": 419160 + }, + { + "epoch": 0.94, + "learning_rate": 3.246347956421557e-06, + "loss": 0.0911, + "step": 419170 + }, + { + "epoch": 0.94, + "learning_rate": 3.2452294132122327e-06, + "loss": 0.0926, + "step": 419180 + }, + { + "epoch": 0.94, + "learning_rate": 3.244110870002908e-06, + "loss": 0.0917, + "step": 419190 + }, + { + "epoch": 0.94, + "learning_rate": 3.242992326793584e-06, + "loss": 0.0959, + "step": 419200 + }, + { + "epoch": 0.94, + "learning_rate": 3.24187378358426e-06, + "loss": 0.0904, + "step": 419210 + }, + { + "epoch": 0.94, + "learning_rate": 3.240755240374936e-06, + "loss": 0.0892, + "step": 419220 + }, + { + "epoch": 0.94, + "learning_rate": 3.2396366971656114e-06, + "loss": 0.0948, + "step": 419230 + }, + { + "epoch": 0.94, + "learning_rate": 3.2385181539562876e-06, + "loss": 0.0961, + "step": 419240 + }, + { + "epoch": 0.94, + "learning_rate": 3.2373996107469634e-06, + "loss": 0.0947, + "step": 419250 + }, + { + "epoch": 0.94, + "learning_rate": 3.236281067537639e-06, + "loss": 0.0883, + "step": 419260 + }, + { + "epoch": 0.94, + "learning_rate": 3.2351625243283146e-06, + "loss": 0.0925, + "step": 419270 + }, + { + "epoch": 0.94, + "learning_rate": 3.234043981118991e-06, + "loss": 0.0936, + "step": 419280 + }, + { + "epoch": 0.94, + "learning_rate": 3.2329254379096666e-06, + "loss": 0.0917, + "step": 419290 + }, + { + "epoch": 0.94, + "learning_rate": 3.231806894700343e-06, + "loss": 0.0874, + "step": 419300 + }, + { + "epoch": 0.94, + "learning_rate": 3.230688351491018e-06, + "loss": 0.0942, + "step": 419310 + }, + { + "epoch": 0.94, + "learning_rate": 3.229569808281694e-06, + "loss": 0.0938, + "step": 419320 + }, + { + "epoch": 0.94, + "learning_rate": 3.22845126507237e-06, + "loss": 0.0887, + "step": 419330 + }, + { + "epoch": 0.94, + "learning_rate": 3.227332721863046e-06, + "loss": 0.0977, + "step": 419340 + }, + { + "epoch": 0.94, + "learning_rate": 3.2262141786537215e-06, + "loss": 0.0879, + "step": 419350 + }, + { + "epoch": 0.94, + "learning_rate": 3.2250956354443973e-06, + "loss": 0.0915, + "step": 419360 + }, + { + "epoch": 0.94, + "learning_rate": 3.223977092235073e-06, + "loss": 0.0932, + "step": 419370 + }, + { + "epoch": 0.94, + "learning_rate": 3.2228585490257494e-06, + "loss": 0.094, + "step": 419380 + }, + { + "epoch": 0.94, + "learning_rate": 3.2217400058164247e-06, + "loss": 0.0914, + "step": 419390 + }, + { + "epoch": 0.94, + "learning_rate": 3.2206214626071005e-06, + "loss": 0.0922, + "step": 419400 + }, + { + "epoch": 0.94, + "learning_rate": 3.2195029193977768e-06, + "loss": 0.0926, + "step": 419410 + }, + { + "epoch": 0.94, + "learning_rate": 3.2183843761884526e-06, + "loss": 0.0911, + "step": 419420 + }, + { + "epoch": 0.94, + "learning_rate": 3.217265832979128e-06, + "loss": 0.0907, + "step": 419430 + }, + { + "epoch": 0.94, + "learning_rate": 3.2161472897698038e-06, + "loss": 0.092, + "step": 419440 + }, + { + "epoch": 0.94, + "learning_rate": 3.21502874656048e-06, + "loss": 0.0914, + "step": 419450 + }, + { + "epoch": 0.94, + "learning_rate": 3.213910203351156e-06, + "loss": 0.0954, + "step": 419460 + }, + { + "epoch": 0.94, + "learning_rate": 3.2127916601418312e-06, + "loss": 0.093, + "step": 419470 + }, + { + "epoch": 0.94, + "learning_rate": 3.211673116932507e-06, + "loss": 0.0943, + "step": 419480 + }, + { + "epoch": 0.94, + "learning_rate": 3.2105545737231833e-06, + "loss": 0.0881, + "step": 419490 + }, + { + "epoch": 0.94, + "learning_rate": 3.209436030513859e-06, + "loss": 0.0953, + "step": 419500 + }, + { + "epoch": 0.94, + "learning_rate": 3.2083174873045345e-06, + "loss": 0.0882, + "step": 419510 + }, + { + "epoch": 0.94, + "learning_rate": 3.2071989440952107e-06, + "loss": 0.0963, + "step": 419520 + }, + { + "epoch": 0.94, + "learning_rate": 3.2060804008858865e-06, + "loss": 0.0923, + "step": 419530 + }, + { + "epoch": 0.94, + "learning_rate": 3.2049618576765623e-06, + "loss": 0.0925, + "step": 419540 + }, + { + "epoch": 0.94, + "learning_rate": 3.2038433144672377e-06, + "loss": 0.0908, + "step": 419550 + }, + { + "epoch": 0.94, + "learning_rate": 3.202724771257914e-06, + "loss": 0.0904, + "step": 419560 + }, + { + "epoch": 0.94, + "learning_rate": 3.2016062280485897e-06, + "loss": 0.0923, + "step": 419570 + }, + { + "epoch": 0.94, + "learning_rate": 3.200487684839266e-06, + "loss": 0.0943, + "step": 419580 + }, + { + "epoch": 0.94, + "learning_rate": 3.199369141629941e-06, + "loss": 0.0926, + "step": 419590 + }, + { + "epoch": 0.94, + "learning_rate": 3.198250598420617e-06, + "loss": 0.0904, + "step": 419600 + }, + { + "epoch": 0.94, + "learning_rate": 3.197132055211293e-06, + "loss": 0.092, + "step": 419610 + }, + { + "epoch": 0.94, + "learning_rate": 3.1960135120019692e-06, + "loss": 0.0933, + "step": 419620 + }, + { + "epoch": 0.94, + "learning_rate": 3.194894968792644e-06, + "loss": 0.0918, + "step": 419630 + }, + { + "epoch": 0.94, + "learning_rate": 3.1937764255833204e-06, + "loss": 0.0955, + "step": 419640 + }, + { + "epoch": 0.94, + "learning_rate": 3.1926578823739962e-06, + "loss": 0.0926, + "step": 419650 + }, + { + "epoch": 0.94, + "learning_rate": 3.1915393391646725e-06, + "loss": 0.0934, + "step": 419660 + }, + { + "epoch": 0.94, + "learning_rate": 3.190420795955348e-06, + "loss": 0.0876, + "step": 419670 + }, + { + "epoch": 0.94, + "learning_rate": 3.1893022527460237e-06, + "loss": 0.089, + "step": 419680 + }, + { + "epoch": 0.94, + "learning_rate": 3.1881837095366995e-06, + "loss": 0.0932, + "step": 419690 + }, + { + "epoch": 0.94, + "learning_rate": 3.1870651663273757e-06, + "loss": 0.0942, + "step": 419700 + }, + { + "epoch": 0.94, + "learning_rate": 3.185946623118051e-06, + "loss": 0.088, + "step": 419710 + }, + { + "epoch": 0.94, + "learning_rate": 3.184828079908727e-06, + "loss": 0.0928, + "step": 419720 + }, + { + "epoch": 0.94, + "learning_rate": 3.183709536699403e-06, + "loss": 0.0933, + "step": 419730 + }, + { + "epoch": 0.94, + "learning_rate": 3.182590993490079e-06, + "loss": 0.0901, + "step": 419740 + }, + { + "epoch": 0.94, + "learning_rate": 3.1814724502807543e-06, + "loss": 0.0888, + "step": 419750 + }, + { + "epoch": 0.94, + "learning_rate": 3.18035390707143e-06, + "loss": 0.0941, + "step": 419760 + }, + { + "epoch": 0.94, + "learning_rate": 3.1792353638621064e-06, + "loss": 0.0886, + "step": 419770 + }, + { + "epoch": 0.94, + "learning_rate": 3.178116820652782e-06, + "loss": 0.0924, + "step": 419780 + }, + { + "epoch": 0.94, + "learning_rate": 3.1769982774434576e-06, + "loss": 0.0949, + "step": 419790 + }, + { + "epoch": 0.94, + "learning_rate": 3.1758797342341334e-06, + "loss": 0.089, + "step": 419800 + }, + { + "epoch": 0.94, + "learning_rate": 3.1747611910248096e-06, + "loss": 0.0916, + "step": 419810 + }, + { + "epoch": 0.94, + "learning_rate": 3.1736426478154854e-06, + "loss": 0.0962, + "step": 419820 + }, + { + "epoch": 0.94, + "learning_rate": 3.172524104606161e-06, + "loss": 0.0931, + "step": 419830 + }, + { + "epoch": 0.94, + "learning_rate": 3.171405561396837e-06, + "loss": 0.0899, + "step": 419840 + }, + { + "epoch": 0.94, + "learning_rate": 3.170287018187513e-06, + "loss": 0.098, + "step": 419850 + }, + { + "epoch": 0.94, + "learning_rate": 3.1691684749781887e-06, + "loss": 0.0932, + "step": 419860 + }, + { + "epoch": 0.94, + "learning_rate": 3.168049931768864e-06, + "loss": 0.0891, + "step": 419870 + }, + { + "epoch": 0.94, + "learning_rate": 3.1669313885595403e-06, + "loss": 0.0903, + "step": 419880 + }, + { + "epoch": 0.94, + "learning_rate": 3.165812845350216e-06, + "loss": 0.0929, + "step": 419890 + }, + { + "epoch": 0.94, + "learning_rate": 3.1646943021408923e-06, + "loss": 0.0926, + "step": 419900 + }, + { + "epoch": 0.94, + "learning_rate": 3.1635757589315673e-06, + "loss": 0.0926, + "step": 419910 + }, + { + "epoch": 0.94, + "learning_rate": 3.1624572157222435e-06, + "loss": 0.0933, + "step": 419920 + }, + { + "epoch": 0.94, + "learning_rate": 3.1613386725129193e-06, + "loss": 0.0922, + "step": 419930 + }, + { + "epoch": 0.94, + "learning_rate": 3.1602201293035956e-06, + "loss": 0.092, + "step": 419940 + }, + { + "epoch": 0.94, + "learning_rate": 3.159101586094271e-06, + "loss": 0.0943, + "step": 419950 + }, + { + "epoch": 0.94, + "learning_rate": 3.1579830428849468e-06, + "loss": 0.0944, + "step": 419960 + }, + { + "epoch": 0.94, + "learning_rate": 3.1568644996756226e-06, + "loss": 0.0932, + "step": 419970 + }, + { + "epoch": 0.94, + "learning_rate": 3.155745956466299e-06, + "loss": 0.0921, + "step": 419980 + }, + { + "epoch": 0.94, + "learning_rate": 3.154627413256974e-06, + "loss": 0.0972, + "step": 419990 + }, + { + "epoch": 0.94, + "learning_rate": 3.15350887004765e-06, + "loss": 0.0928, + "step": 420000 + }, + { + "epoch": 0.94, + "learning_rate": 3.1523903268383262e-06, + "loss": 0.0915, + "step": 420010 + }, + { + "epoch": 0.94, + "learning_rate": 3.151271783629002e-06, + "loss": 0.0918, + "step": 420020 + }, + { + "epoch": 0.94, + "learning_rate": 3.1501532404196774e-06, + "loss": 0.0888, + "step": 420030 + }, + { + "epoch": 0.94, + "learning_rate": 3.1490346972103532e-06, + "loss": 0.0909, + "step": 420040 + }, + { + "epoch": 0.94, + "learning_rate": 3.1479161540010295e-06, + "loss": 0.0966, + "step": 420050 + }, + { + "epoch": 0.94, + "learning_rate": 3.1467976107917053e-06, + "loss": 0.0929, + "step": 420060 + }, + { + "epoch": 0.94, + "learning_rate": 3.1456790675823807e-06, + "loss": 0.0938, + "step": 420070 + }, + { + "epoch": 0.94, + "learning_rate": 3.1445605243730565e-06, + "loss": 0.0924, + "step": 420080 + }, + { + "epoch": 0.94, + "learning_rate": 3.1435538354846653e-06, + "loss": 0.0913, + "step": 420090 + }, + { + "epoch": 0.94, + "learning_rate": 3.1424352922753406e-06, + "loss": 0.0954, + "step": 420100 + }, + { + "epoch": 0.94, + "learning_rate": 3.1413167490660165e-06, + "loss": 0.0898, + "step": 420110 + }, + { + "epoch": 0.94, + "learning_rate": 3.1401982058566927e-06, + "loss": 0.0934, + "step": 420120 + }, + { + "epoch": 0.94, + "learning_rate": 3.1390796626473685e-06, + "loss": 0.0929, + "step": 420130 + }, + { + "epoch": 0.94, + "learning_rate": 3.137961119438044e-06, + "loss": 0.0965, + "step": 420140 + }, + { + "epoch": 0.94, + "learning_rate": 3.1368425762287197e-06, + "loss": 0.0861, + "step": 420150 + }, + { + "epoch": 0.94, + "learning_rate": 3.135724033019396e-06, + "loss": 0.0899, + "step": 420160 + }, + { + "epoch": 0.94, + "learning_rate": 3.1346054898100717e-06, + "loss": 0.0966, + "step": 420170 + }, + { + "epoch": 0.94, + "learning_rate": 3.133486946600747e-06, + "loss": 0.0914, + "step": 420180 + }, + { + "epoch": 0.94, + "learning_rate": 3.1323684033914234e-06, + "loss": 0.0905, + "step": 420190 + }, + { + "epoch": 0.94, + "learning_rate": 3.131249860182099e-06, + "loss": 0.0934, + "step": 420200 + }, + { + "epoch": 0.94, + "learning_rate": 3.130131316972775e-06, + "loss": 0.0958, + "step": 420210 + }, + { + "epoch": 0.94, + "learning_rate": 3.1290127737634504e-06, + "loss": 0.0915, + "step": 420220 + }, + { + "epoch": 0.94, + "learning_rate": 3.1278942305541266e-06, + "loss": 0.0939, + "step": 420230 + }, + { + "epoch": 0.94, + "learning_rate": 3.1267756873448024e-06, + "loss": 0.0964, + "step": 420240 + }, + { + "epoch": 0.94, + "learning_rate": 3.1256571441354786e-06, + "loss": 0.0921, + "step": 420250 + }, + { + "epoch": 0.94, + "learning_rate": 3.124538600926154e-06, + "loss": 0.0942, + "step": 420260 + }, + { + "epoch": 0.94, + "learning_rate": 3.12342005771683e-06, + "loss": 0.0941, + "step": 420270 + }, + { + "epoch": 0.94, + "learning_rate": 3.1223015145075057e-06, + "loss": 0.0936, + "step": 420280 + }, + { + "epoch": 0.94, + "learning_rate": 3.1211829712981815e-06, + "loss": 0.0911, + "step": 420290 + }, + { + "epoch": 0.94, + "learning_rate": 3.1200644280888573e-06, + "loss": 0.0923, + "step": 420300 + }, + { + "epoch": 0.94, + "learning_rate": 3.118945884879533e-06, + "loss": 0.0936, + "step": 420310 + }, + { + "epoch": 0.94, + "learning_rate": 3.117827341670209e-06, + "loss": 0.0903, + "step": 420320 + }, + { + "epoch": 0.94, + "learning_rate": 3.1167087984608847e-06, + "loss": 0.0889, + "step": 420330 + }, + { + "epoch": 0.94, + "learning_rate": 3.1155902552515605e-06, + "loss": 0.0927, + "step": 420340 + }, + { + "epoch": 0.94, + "learning_rate": 3.1144717120422363e-06, + "loss": 0.0941, + "step": 420350 + }, + { + "epoch": 0.94, + "learning_rate": 3.113353168832912e-06, + "loss": 0.0888, + "step": 420360 + }, + { + "epoch": 0.94, + "learning_rate": 3.112234625623588e-06, + "loss": 0.0898, + "step": 420370 + }, + { + "epoch": 0.94, + "learning_rate": 3.111116082414264e-06, + "loss": 0.0897, + "step": 420380 + }, + { + "epoch": 0.94, + "learning_rate": 3.1099975392049396e-06, + "loss": 0.0929, + "step": 420390 + }, + { + "epoch": 0.94, + "learning_rate": 3.1088789959956154e-06, + "loss": 0.0918, + "step": 420400 + }, + { + "epoch": 0.94, + "learning_rate": 3.107760452786291e-06, + "loss": 0.0915, + "step": 420410 + }, + { + "epoch": 0.94, + "learning_rate": 3.106641909576967e-06, + "loss": 0.0952, + "step": 420420 + }, + { + "epoch": 0.94, + "learning_rate": 3.105523366367643e-06, + "loss": 0.095, + "step": 420430 + }, + { + "epoch": 0.94, + "learning_rate": 3.1044048231583186e-06, + "loss": 0.0924, + "step": 420440 + }, + { + "epoch": 0.94, + "learning_rate": 3.1032862799489944e-06, + "loss": 0.0933, + "step": 420450 + }, + { + "epoch": 0.94, + "learning_rate": 3.1021677367396702e-06, + "loss": 0.0922, + "step": 420460 + }, + { + "epoch": 0.94, + "learning_rate": 3.101049193530346e-06, + "loss": 0.0988, + "step": 420470 + }, + { + "epoch": 0.94, + "learning_rate": 3.099930650321022e-06, + "loss": 0.0948, + "step": 420480 + }, + { + "epoch": 0.94, + "learning_rate": 3.098812107111698e-06, + "loss": 0.0942, + "step": 420490 + }, + { + "epoch": 0.94, + "learning_rate": 3.0976935639023735e-06, + "loss": 0.0916, + "step": 420500 + }, + { + "epoch": 0.94, + "learning_rate": 3.0965750206930497e-06, + "loss": 0.0905, + "step": 420510 + }, + { + "epoch": 0.94, + "learning_rate": 3.095456477483725e-06, + "loss": 0.0956, + "step": 420520 + }, + { + "epoch": 0.94, + "learning_rate": 3.0943379342744013e-06, + "loss": 0.0874, + "step": 420530 + }, + { + "epoch": 0.94, + "learning_rate": 3.0932193910650767e-06, + "loss": 0.0888, + "step": 420540 + }, + { + "epoch": 0.94, + "learning_rate": 3.092100847855753e-06, + "loss": 0.092, + "step": 420550 + }, + { + "epoch": 0.94, + "learning_rate": 3.0909823046464283e-06, + "loss": 0.0929, + "step": 420560 + }, + { + "epoch": 0.94, + "learning_rate": 3.0898637614371046e-06, + "loss": 0.0875, + "step": 420570 + }, + { + "epoch": 0.94, + "learning_rate": 3.08874521822778e-06, + "loss": 0.0933, + "step": 420580 + }, + { + "epoch": 0.94, + "learning_rate": 3.087626675018456e-06, + "loss": 0.0946, + "step": 420590 + }, + { + "epoch": 0.94, + "learning_rate": 3.0865081318091316e-06, + "loss": 0.0961, + "step": 420600 + }, + { + "epoch": 0.94, + "learning_rate": 3.085389588599808e-06, + "loss": 0.0943, + "step": 420610 + }, + { + "epoch": 0.94, + "learning_rate": 3.0842710453904836e-06, + "loss": 0.0939, + "step": 420620 + }, + { + "epoch": 0.94, + "learning_rate": 3.0831525021811594e-06, + "loss": 0.0942, + "step": 420630 + }, + { + "epoch": 0.94, + "learning_rate": 3.0820339589718352e-06, + "loss": 0.0894, + "step": 420640 + }, + { + "epoch": 0.94, + "learning_rate": 3.080915415762511e-06, + "loss": 0.0931, + "step": 420650 + }, + { + "epoch": 0.94, + "learning_rate": 3.079796872553187e-06, + "loss": 0.0926, + "step": 420660 + }, + { + "epoch": 0.94, + "learning_rate": 3.0786783293438627e-06, + "loss": 0.0921, + "step": 420670 + }, + { + "epoch": 0.94, + "learning_rate": 3.0775597861345385e-06, + "loss": 0.0885, + "step": 420680 + }, + { + "epoch": 0.94, + "learning_rate": 3.0764412429252143e-06, + "loss": 0.0927, + "step": 420690 + }, + { + "epoch": 0.94, + "learning_rate": 3.07532269971589e-06, + "loss": 0.0926, + "step": 420700 + }, + { + "epoch": 0.94, + "learning_rate": 3.074204156506566e-06, + "loss": 0.0979, + "step": 420710 + }, + { + "epoch": 0.94, + "learning_rate": 3.0730856132972417e-06, + "loss": 0.0953, + "step": 420720 + }, + { + "epoch": 0.94, + "learning_rate": 3.0719670700879175e-06, + "loss": 0.0912, + "step": 420730 + }, + { + "epoch": 0.94, + "learning_rate": 3.0708485268785933e-06, + "loss": 0.0965, + "step": 420740 + }, + { + "epoch": 0.94, + "learning_rate": 3.069729983669269e-06, + "loss": 0.0903, + "step": 420750 + }, + { + "epoch": 0.94, + "learning_rate": 3.068611440459945e-06, + "loss": 0.0956, + "step": 420760 + }, + { + "epoch": 0.94, + "learning_rate": 3.0674928972506208e-06, + "loss": 0.091, + "step": 420770 + }, + { + "epoch": 0.94, + "learning_rate": 3.0663743540412966e-06, + "loss": 0.0895, + "step": 420780 + }, + { + "epoch": 0.94, + "learning_rate": 3.065255810831973e-06, + "loss": 0.0894, + "step": 420790 + }, + { + "epoch": 0.94, + "learning_rate": 3.064137267622648e-06, + "loss": 0.0896, + "step": 420800 + }, + { + "epoch": 0.94, + "learning_rate": 3.0630187244133244e-06, + "loss": 0.0967, + "step": 420810 + }, + { + "epoch": 0.94, + "learning_rate": 3.061900181204e-06, + "loss": 0.0913, + "step": 420820 + }, + { + "epoch": 0.94, + "learning_rate": 3.060781637994676e-06, + "loss": 0.0917, + "step": 420830 + }, + { + "epoch": 0.94, + "learning_rate": 3.0596630947853514e-06, + "loss": 0.0951, + "step": 420840 + }, + { + "epoch": 0.94, + "learning_rate": 3.0585445515760277e-06, + "loss": 0.0907, + "step": 420850 + }, + { + "epoch": 0.94, + "learning_rate": 3.057426008366703e-06, + "loss": 0.0908, + "step": 420860 + }, + { + "epoch": 0.94, + "learning_rate": 3.0563074651573793e-06, + "loss": 0.0985, + "step": 420870 + }, + { + "epoch": 0.94, + "learning_rate": 3.0551889219480547e-06, + "loss": 0.0954, + "step": 420880 + }, + { + "epoch": 0.94, + "learning_rate": 3.054070378738731e-06, + "loss": 0.0912, + "step": 420890 + }, + { + "epoch": 0.94, + "learning_rate": 3.0529518355294063e-06, + "loss": 0.0918, + "step": 420900 + }, + { + "epoch": 0.94, + "learning_rate": 3.0518332923200825e-06, + "loss": 0.0904, + "step": 420910 + }, + { + "epoch": 0.94, + "learning_rate": 3.0507147491107583e-06, + "loss": 0.0925, + "step": 420920 + }, + { + "epoch": 0.94, + "learning_rate": 3.049596205901434e-06, + "loss": 0.0939, + "step": 420930 + }, + { + "epoch": 0.94, + "learning_rate": 3.04847766269211e-06, + "loss": 0.0913, + "step": 420940 + }, + { + "epoch": 0.94, + "learning_rate": 3.0473591194827858e-06, + "loss": 0.094, + "step": 420950 + }, + { + "epoch": 0.94, + "learning_rate": 3.0462405762734616e-06, + "loss": 0.0905, + "step": 420960 + }, + { + "epoch": 0.94, + "learning_rate": 3.0451220330641374e-06, + "loss": 0.0981, + "step": 420970 + }, + { + "epoch": 0.94, + "learning_rate": 3.044003489854813e-06, + "loss": 0.0964, + "step": 420980 + }, + { + "epoch": 0.94, + "learning_rate": 3.042884946645489e-06, + "loss": 0.0928, + "step": 420990 + }, + { + "epoch": 0.94, + "learning_rate": 3.041766403436165e-06, + "loss": 0.0926, + "step": 421000 + }, + { + "epoch": 0.94, + "learning_rate": 3.0406478602268406e-06, + "loss": 0.0911, + "step": 421010 + }, + { + "epoch": 0.94, + "learning_rate": 3.0395293170175164e-06, + "loss": 0.0944, + "step": 421020 + }, + { + "epoch": 0.94, + "learning_rate": 3.0384107738081923e-06, + "loss": 0.0935, + "step": 421030 + }, + { + "epoch": 0.94, + "learning_rate": 3.037292230598868e-06, + "loss": 0.0953, + "step": 421040 + }, + { + "epoch": 0.94, + "learning_rate": 3.036173687389544e-06, + "loss": 0.0961, + "step": 421050 + }, + { + "epoch": 0.94, + "learning_rate": 3.0350551441802197e-06, + "loss": 0.0912, + "step": 421060 + }, + { + "epoch": 0.94, + "learning_rate": 3.0339366009708955e-06, + "loss": 0.0928, + "step": 421070 + }, + { + "epoch": 0.94, + "learning_rate": 3.0328180577615713e-06, + "loss": 0.0917, + "step": 421080 + }, + { + "epoch": 0.94, + "learning_rate": 3.0316995145522475e-06, + "loss": 0.0959, + "step": 421090 + }, + { + "epoch": 0.94, + "learning_rate": 3.030580971342923e-06, + "loss": 0.0899, + "step": 421100 + }, + { + "epoch": 0.94, + "learning_rate": 3.029462428133599e-06, + "loss": 0.0937, + "step": 421110 + }, + { + "epoch": 0.94, + "learning_rate": 3.0283438849242745e-06, + "loss": 0.093, + "step": 421120 + }, + { + "epoch": 0.94, + "learning_rate": 3.0272253417149508e-06, + "loss": 0.095, + "step": 421130 + }, + { + "epoch": 0.94, + "learning_rate": 3.026106798505626e-06, + "loss": 0.0883, + "step": 421140 + }, + { + "epoch": 0.94, + "learning_rate": 3.0249882552963024e-06, + "loss": 0.0951, + "step": 421150 + }, + { + "epoch": 0.94, + "learning_rate": 3.023869712086978e-06, + "loss": 0.0896, + "step": 421160 + }, + { + "epoch": 0.94, + "learning_rate": 3.022751168877654e-06, + "loss": 0.0919, + "step": 421170 + }, + { + "epoch": 0.94, + "learning_rate": 3.0216326256683294e-06, + "loss": 0.0895, + "step": 421180 + }, + { + "epoch": 0.94, + "learning_rate": 3.0205140824590056e-06, + "loss": 0.0891, + "step": 421190 + }, + { + "epoch": 0.94, + "learning_rate": 3.019395539249681e-06, + "loss": 0.0895, + "step": 421200 + }, + { + "epoch": 0.94, + "learning_rate": 3.0182769960403573e-06, + "loss": 0.0898, + "step": 421210 + }, + { + "epoch": 0.94, + "learning_rate": 3.017158452831033e-06, + "loss": 0.0922, + "step": 421220 + }, + { + "epoch": 0.94, + "learning_rate": 3.016039909621709e-06, + "loss": 0.0911, + "step": 421230 + }, + { + "epoch": 0.94, + "learning_rate": 3.0149213664123847e-06, + "loss": 0.0933, + "step": 421240 + }, + { + "epoch": 0.94, + "learning_rate": 3.0138028232030605e-06, + "loss": 0.0969, + "step": 421250 + }, + { + "epoch": 0.94, + "learning_rate": 3.0126842799937363e-06, + "loss": 0.0934, + "step": 421260 + }, + { + "epoch": 0.94, + "learning_rate": 3.011565736784412e-06, + "loss": 0.0915, + "step": 421270 + }, + { + "epoch": 0.94, + "learning_rate": 3.010447193575088e-06, + "loss": 0.0937, + "step": 421280 + }, + { + "epoch": 0.94, + "learning_rate": 3.0093286503657637e-06, + "loss": 0.0916, + "step": 421290 + }, + { + "epoch": 0.94, + "learning_rate": 3.0082101071564396e-06, + "loss": 0.0883, + "step": 421300 + }, + { + "epoch": 0.94, + "learning_rate": 3.0070915639471154e-06, + "loss": 0.0904, + "step": 421310 + }, + { + "epoch": 0.94, + "learning_rate": 3.005973020737791e-06, + "loss": 0.0908, + "step": 421320 + }, + { + "epoch": 0.94, + "learning_rate": 3.004854477528467e-06, + "loss": 0.0912, + "step": 421330 + }, + { + "epoch": 0.94, + "learning_rate": 3.003735934319143e-06, + "loss": 0.0928, + "step": 421340 + }, + { + "epoch": 0.94, + "learning_rate": 3.0026173911098186e-06, + "loss": 0.0902, + "step": 421350 + }, + { + "epoch": 0.94, + "learning_rate": 3.0014988479004944e-06, + "loss": 0.0926, + "step": 421360 + }, + { + "epoch": 0.94, + "learning_rate": 3.0003803046911702e-06, + "loss": 0.088, + "step": 421370 + }, + { + "epoch": 0.94, + "learning_rate": 2.999261761481846e-06, + "loss": 0.091, + "step": 421380 + }, + { + "epoch": 0.94, + "learning_rate": 2.9981432182725223e-06, + "loss": 0.0942, + "step": 421390 + }, + { + "epoch": 0.94, + "learning_rate": 2.9970246750631977e-06, + "loss": 0.0921, + "step": 421400 + }, + { + "epoch": 0.94, + "learning_rate": 2.995906131853874e-06, + "loss": 0.0907, + "step": 421410 + }, + { + "epoch": 0.94, + "learning_rate": 2.9947875886445493e-06, + "loss": 0.0921, + "step": 421420 + }, + { + "epoch": 0.94, + "learning_rate": 2.9936690454352255e-06, + "loss": 0.095, + "step": 421430 + }, + { + "epoch": 0.94, + "learning_rate": 2.992550502225901e-06, + "loss": 0.0877, + "step": 421440 + }, + { + "epoch": 0.94, + "learning_rate": 2.991431959016577e-06, + "loss": 0.0934, + "step": 421450 + }, + { + "epoch": 0.94, + "learning_rate": 2.9903134158072525e-06, + "loss": 0.0915, + "step": 421460 + }, + { + "epoch": 0.94, + "learning_rate": 2.9891948725979287e-06, + "loss": 0.0901, + "step": 421470 + }, + { + "epoch": 0.94, + "learning_rate": 2.988076329388604e-06, + "loss": 0.0954, + "step": 421480 + }, + { + "epoch": 0.94, + "learning_rate": 2.9869577861792804e-06, + "loss": 0.098, + "step": 421490 + }, + { + "epoch": 0.94, + "learning_rate": 2.9858392429699558e-06, + "loss": 0.0888, + "step": 421500 + }, + { + "epoch": 0.94, + "learning_rate": 2.984720699760632e-06, + "loss": 0.0922, + "step": 421510 + }, + { + "epoch": 0.94, + "learning_rate": 2.983602156551308e-06, + "loss": 0.0883, + "step": 421520 + }, + { + "epoch": 0.94, + "learning_rate": 2.9824836133419836e-06, + "loss": 0.0942, + "step": 421530 + }, + { + "epoch": 0.94, + "learning_rate": 2.9813650701326594e-06, + "loss": 0.0921, + "step": 421540 + }, + { + "epoch": 0.94, + "learning_rate": 2.9802465269233352e-06, + "loss": 0.095, + "step": 421550 + }, + { + "epoch": 0.94, + "learning_rate": 2.979127983714011e-06, + "loss": 0.0872, + "step": 421560 + }, + { + "epoch": 0.94, + "learning_rate": 2.978009440504687e-06, + "loss": 0.0945, + "step": 421570 + }, + { + "epoch": 0.94, + "learning_rate": 2.9768908972953627e-06, + "loss": 0.0964, + "step": 421580 + }, + { + "epoch": 0.94, + "learning_rate": 2.9757723540860385e-06, + "loss": 0.094, + "step": 421590 + }, + { + "epoch": 0.94, + "learning_rate": 2.9746538108767143e-06, + "loss": 0.0904, + "step": 421600 + }, + { + "epoch": 0.94, + "learning_rate": 2.97353526766739e-06, + "loss": 0.0959, + "step": 421610 + }, + { + "epoch": 0.94, + "learning_rate": 2.972416724458066e-06, + "loss": 0.0936, + "step": 421620 + }, + { + "epoch": 0.94, + "learning_rate": 2.9712981812487417e-06, + "loss": 0.0926, + "step": 421630 + }, + { + "epoch": 0.94, + "learning_rate": 2.9701796380394175e-06, + "loss": 0.0905, + "step": 421640 + }, + { + "epoch": 0.94, + "learning_rate": 2.9690610948300933e-06, + "loss": 0.0929, + "step": 421650 + }, + { + "epoch": 0.94, + "learning_rate": 2.967942551620769e-06, + "loss": 0.0936, + "step": 421660 + }, + { + "epoch": 0.94, + "learning_rate": 2.966824008411445e-06, + "loss": 0.091, + "step": 421670 + }, + { + "epoch": 0.94, + "learning_rate": 2.9657054652021208e-06, + "loss": 0.0905, + "step": 421680 + }, + { + "epoch": 0.94, + "learning_rate": 2.964586921992797e-06, + "loss": 0.0886, + "step": 421690 + }, + { + "epoch": 0.94, + "learning_rate": 2.9634683787834724e-06, + "loss": 0.0918, + "step": 421700 + }, + { + "epoch": 0.94, + "learning_rate": 2.9623498355741486e-06, + "loss": 0.0872, + "step": 421710 + }, + { + "epoch": 0.94, + "learning_rate": 2.961231292364824e-06, + "loss": 0.088, + "step": 421720 + }, + { + "epoch": 0.94, + "learning_rate": 2.9601127491555002e-06, + "loss": 0.0921, + "step": 421730 + }, + { + "epoch": 0.94, + "learning_rate": 2.9589942059461756e-06, + "loss": 0.0914, + "step": 421740 + }, + { + "epoch": 0.94, + "learning_rate": 2.957875662736852e-06, + "loss": 0.0909, + "step": 421750 + }, + { + "epoch": 0.94, + "learning_rate": 2.9567571195275272e-06, + "loss": 0.0913, + "step": 421760 + }, + { + "epoch": 0.94, + "learning_rate": 2.9556385763182035e-06, + "loss": 0.088, + "step": 421770 + }, + { + "epoch": 0.94, + "learning_rate": 2.954520033108879e-06, + "loss": 0.0908, + "step": 421780 + }, + { + "epoch": 0.94, + "learning_rate": 2.953401489899555e-06, + "loss": 0.0896, + "step": 421790 + }, + { + "epoch": 0.94, + "learning_rate": 2.9522829466902305e-06, + "loss": 0.097, + "step": 421800 + }, + { + "epoch": 0.94, + "learning_rate": 2.9511644034809067e-06, + "loss": 0.0929, + "step": 421810 + }, + { + "epoch": 0.94, + "learning_rate": 2.9500458602715825e-06, + "loss": 0.0905, + "step": 421820 + }, + { + "epoch": 0.94, + "learning_rate": 2.9489273170622583e-06, + "loss": 0.0947, + "step": 421830 + }, + { + "epoch": 0.94, + "learning_rate": 2.947808773852934e-06, + "loss": 0.0895, + "step": 421840 + }, + { + "epoch": 0.94, + "learning_rate": 2.94669023064361e-06, + "loss": 0.091, + "step": 421850 + }, + { + "epoch": 0.94, + "learning_rate": 2.9455716874342858e-06, + "loss": 0.0904, + "step": 421860 + }, + { + "epoch": 0.94, + "learning_rate": 2.9444531442249616e-06, + "loss": 0.0912, + "step": 421870 + }, + { + "epoch": 0.94, + "learning_rate": 2.9433346010156374e-06, + "loss": 0.0905, + "step": 421880 + }, + { + "epoch": 0.94, + "learning_rate": 2.942216057806313e-06, + "loss": 0.0894, + "step": 421890 + }, + { + "epoch": 0.94, + "learning_rate": 2.941097514596989e-06, + "loss": 0.0975, + "step": 421900 + }, + { + "epoch": 0.94, + "learning_rate": 2.939978971387665e-06, + "loss": 0.0966, + "step": 421910 + }, + { + "epoch": 0.94, + "learning_rate": 2.9388604281783406e-06, + "loss": 0.0913, + "step": 421920 + }, + { + "epoch": 0.94, + "learning_rate": 2.9377418849690164e-06, + "loss": 0.0909, + "step": 421930 + }, + { + "epoch": 0.94, + "learning_rate": 2.9366233417596922e-06, + "loss": 0.0931, + "step": 421940 + }, + { + "epoch": 0.94, + "learning_rate": 2.935504798550368e-06, + "loss": 0.0901, + "step": 421950 + }, + { + "epoch": 0.94, + "learning_rate": 2.934386255341044e-06, + "loss": 0.0953, + "step": 421960 + }, + { + "epoch": 0.94, + "learning_rate": 2.9332677121317197e-06, + "loss": 0.0942, + "step": 421970 + }, + { + "epoch": 0.94, + "learning_rate": 2.9321491689223955e-06, + "loss": 0.0928, + "step": 421980 + }, + { + "epoch": 0.94, + "learning_rate": 2.9310306257130717e-06, + "loss": 0.089, + "step": 421990 + }, + { + "epoch": 0.94, + "learning_rate": 2.929912082503747e-06, + "loss": 0.0934, + "step": 422000 + }, + { + "epoch": 0.94, + "learning_rate": 2.9287935392944233e-06, + "loss": 0.0874, + "step": 422010 + }, + { + "epoch": 0.94, + "learning_rate": 2.9276749960850987e-06, + "loss": 0.0889, + "step": 422020 + }, + { + "epoch": 0.94, + "learning_rate": 2.926556452875775e-06, + "loss": 0.0909, + "step": 422030 + }, + { + "epoch": 0.94, + "learning_rate": 2.9254379096664503e-06, + "loss": 0.0927, + "step": 422040 + }, + { + "epoch": 0.94, + "learning_rate": 2.9243193664571266e-06, + "loss": 0.094, + "step": 422050 + }, + { + "epoch": 0.94, + "learning_rate": 2.923200823247802e-06, + "loss": 0.0902, + "step": 422060 + }, + { + "epoch": 0.94, + "learning_rate": 2.922082280038478e-06, + "loss": 0.09, + "step": 422070 + }, + { + "epoch": 0.94, + "learning_rate": 2.9209637368291536e-06, + "loss": 0.0959, + "step": 422080 + }, + { + "epoch": 0.94, + "learning_rate": 2.91984519361983e-06, + "loss": 0.0932, + "step": 422090 + }, + { + "epoch": 0.94, + "learning_rate": 2.918838504731438e-06, + "loss": 0.0907, + "step": 422100 + }, + { + "epoch": 0.94, + "learning_rate": 2.9177199615221136e-06, + "loss": 0.0948, + "step": 422110 + }, + { + "epoch": 0.94, + "learning_rate": 2.91660141831279e-06, + "loss": 0.0932, + "step": 422120 + }, + { + "epoch": 0.94, + "learning_rate": 2.915482875103465e-06, + "loss": 0.0917, + "step": 422130 + }, + { + "epoch": 0.94, + "learning_rate": 2.9143643318941414e-06, + "loss": 0.0856, + "step": 422140 + }, + { + "epoch": 0.94, + "learning_rate": 2.913245788684817e-06, + "loss": 0.0908, + "step": 422150 + }, + { + "epoch": 0.94, + "learning_rate": 2.912127245475493e-06, + "loss": 0.0926, + "step": 422160 + }, + { + "epoch": 0.94, + "learning_rate": 2.9110087022661684e-06, + "loss": 0.0905, + "step": 422170 + }, + { + "epoch": 0.94, + "learning_rate": 2.9098901590568447e-06, + "loss": 0.0923, + "step": 422180 + }, + { + "epoch": 0.94, + "learning_rate": 2.9087716158475205e-06, + "loss": 0.0952, + "step": 422190 + }, + { + "epoch": 0.94, + "learning_rate": 2.9076530726381963e-06, + "loss": 0.0911, + "step": 422200 + }, + { + "epoch": 0.94, + "learning_rate": 2.906534529428872e-06, + "loss": 0.0867, + "step": 422210 + }, + { + "epoch": 0.94, + "learning_rate": 2.905415986219548e-06, + "loss": 0.0934, + "step": 422220 + }, + { + "epoch": 0.94, + "learning_rate": 2.9042974430102237e-06, + "loss": 0.092, + "step": 422230 + }, + { + "epoch": 0.94, + "learning_rate": 2.9031788998008995e-06, + "loss": 0.0906, + "step": 422240 + }, + { + "epoch": 0.94, + "learning_rate": 2.9020603565915753e-06, + "loss": 0.0882, + "step": 422250 + }, + { + "epoch": 0.94, + "learning_rate": 2.900941813382251e-06, + "loss": 0.0899, + "step": 422260 + }, + { + "epoch": 0.94, + "learning_rate": 2.899823270172927e-06, + "loss": 0.0868, + "step": 422270 + }, + { + "epoch": 0.94, + "learning_rate": 2.8987047269636028e-06, + "loss": 0.0942, + "step": 422280 + }, + { + "epoch": 0.94, + "learning_rate": 2.8975861837542786e-06, + "loss": 0.0895, + "step": 422290 + }, + { + "epoch": 0.94, + "learning_rate": 2.8964676405449544e-06, + "loss": 0.0881, + "step": 422300 + }, + { + "epoch": 0.94, + "learning_rate": 2.89534909733563e-06, + "loss": 0.0932, + "step": 422310 + }, + { + "epoch": 0.94, + "learning_rate": 2.894230554126306e-06, + "loss": 0.0904, + "step": 422320 + }, + { + "epoch": 0.94, + "learning_rate": 2.893112010916982e-06, + "loss": 0.0916, + "step": 422330 + }, + { + "epoch": 0.94, + "learning_rate": 2.8919934677076576e-06, + "loss": 0.0903, + "step": 422340 + }, + { + "epoch": 0.94, + "learning_rate": 2.8908749244983334e-06, + "loss": 0.0896, + "step": 422350 + }, + { + "epoch": 0.94, + "learning_rate": 2.8897563812890097e-06, + "loss": 0.0919, + "step": 422360 + }, + { + "epoch": 0.94, + "learning_rate": 2.888637838079685e-06, + "loss": 0.0951, + "step": 422370 + }, + { + "epoch": 0.94, + "learning_rate": 2.8875192948703613e-06, + "loss": 0.0903, + "step": 422380 + }, + { + "epoch": 0.94, + "learning_rate": 2.8864007516610367e-06, + "loss": 0.091, + "step": 422390 + }, + { + "epoch": 0.94, + "learning_rate": 2.885282208451713e-06, + "loss": 0.0913, + "step": 422400 + }, + { + "epoch": 0.94, + "learning_rate": 2.8841636652423883e-06, + "loss": 0.0908, + "step": 422410 + }, + { + "epoch": 0.94, + "learning_rate": 2.8830451220330645e-06, + "loss": 0.0902, + "step": 422420 + }, + { + "epoch": 0.94, + "learning_rate": 2.88192657882374e-06, + "loss": 0.0906, + "step": 422430 + }, + { + "epoch": 0.94, + "learning_rate": 2.880808035614416e-06, + "loss": 0.0904, + "step": 422440 + }, + { + "epoch": 0.94, + "learning_rate": 2.8796894924050915e-06, + "loss": 0.0902, + "step": 422450 + }, + { + "epoch": 0.94, + "learning_rate": 2.8785709491957678e-06, + "loss": 0.0939, + "step": 422460 + }, + { + "epoch": 0.94, + "learning_rate": 2.877452405986443e-06, + "loss": 0.0902, + "step": 422470 + }, + { + "epoch": 0.94, + "learning_rate": 2.8763338627771194e-06, + "loss": 0.0934, + "step": 422480 + }, + { + "epoch": 0.94, + "learning_rate": 2.875215319567795e-06, + "loss": 0.0919, + "step": 422490 + }, + { + "epoch": 0.94, + "learning_rate": 2.874096776358471e-06, + "loss": 0.0912, + "step": 422500 + }, + { + "epoch": 0.94, + "learning_rate": 2.872978233149147e-06, + "loss": 0.0907, + "step": 422510 + }, + { + "epoch": 0.94, + "learning_rate": 2.8718596899398226e-06, + "loss": 0.0921, + "step": 422520 + }, + { + "epoch": 0.94, + "learning_rate": 2.8707411467304984e-06, + "loss": 0.0921, + "step": 422530 + }, + { + "epoch": 0.94, + "learning_rate": 2.8696226035211742e-06, + "loss": 0.0925, + "step": 422540 + }, + { + "epoch": 0.94, + "learning_rate": 2.86850406031185e-06, + "loss": 0.0908, + "step": 422550 + }, + { + "epoch": 0.94, + "learning_rate": 2.867385517102526e-06, + "loss": 0.0886, + "step": 422560 + }, + { + "epoch": 0.94, + "learning_rate": 2.8662669738932017e-06, + "loss": 0.0945, + "step": 422570 + }, + { + "epoch": 0.94, + "learning_rate": 2.8651484306838775e-06, + "loss": 0.0928, + "step": 422580 + }, + { + "epoch": 0.94, + "learning_rate": 2.8640298874745533e-06, + "loss": 0.0916, + "step": 422590 + }, + { + "epoch": 0.94, + "learning_rate": 2.862911344265229e-06, + "loss": 0.0895, + "step": 422600 + }, + { + "epoch": 0.94, + "learning_rate": 2.861792801055905e-06, + "loss": 0.0927, + "step": 422610 + }, + { + "epoch": 0.94, + "learning_rate": 2.8606742578465807e-06, + "loss": 0.0916, + "step": 422620 + }, + { + "epoch": 0.94, + "learning_rate": 2.8595557146372565e-06, + "loss": 0.0951, + "step": 422630 + }, + { + "epoch": 0.94, + "learning_rate": 2.8584371714279323e-06, + "loss": 0.0938, + "step": 422640 + }, + { + "epoch": 0.94, + "learning_rate": 2.857318628218608e-06, + "loss": 0.0909, + "step": 422650 + }, + { + "epoch": 0.94, + "learning_rate": 2.8562000850092844e-06, + "loss": 0.089, + "step": 422660 + }, + { + "epoch": 0.94, + "learning_rate": 2.8550815417999598e-06, + "loss": 0.0944, + "step": 422670 + }, + { + "epoch": 0.94, + "learning_rate": 2.853962998590636e-06, + "loss": 0.0907, + "step": 422680 + }, + { + "epoch": 0.94, + "learning_rate": 2.8528444553813114e-06, + "loss": 0.093, + "step": 422690 + }, + { + "epoch": 0.94, + "learning_rate": 2.8517259121719876e-06, + "loss": 0.0922, + "step": 422700 + }, + { + "epoch": 0.94, + "learning_rate": 2.850607368962663e-06, + "loss": 0.0905, + "step": 422710 + }, + { + "epoch": 0.94, + "learning_rate": 2.8494888257533393e-06, + "loss": 0.0913, + "step": 422720 + }, + { + "epoch": 0.94, + "learning_rate": 2.8483702825440146e-06, + "loss": 0.0895, + "step": 422730 + }, + { + "epoch": 0.94, + "learning_rate": 2.847251739334691e-06, + "loss": 0.0922, + "step": 422740 + }, + { + "epoch": 0.94, + "learning_rate": 2.8461331961253663e-06, + "loss": 0.0923, + "step": 422750 + }, + { + "epoch": 0.94, + "learning_rate": 2.8450146529160425e-06, + "loss": 0.0942, + "step": 422760 + }, + { + "epoch": 0.94, + "learning_rate": 2.843896109706718e-06, + "loss": 0.091, + "step": 422770 + }, + { + "epoch": 0.94, + "learning_rate": 2.842777566497394e-06, + "loss": 0.0905, + "step": 422780 + }, + { + "epoch": 0.94, + "learning_rate": 2.84165902328807e-06, + "loss": 0.0905, + "step": 422790 + }, + { + "epoch": 0.94, + "learning_rate": 2.8405404800787457e-06, + "loss": 0.0913, + "step": 422800 + }, + { + "epoch": 0.94, + "learning_rate": 2.8394219368694215e-06, + "loss": 0.0887, + "step": 422810 + }, + { + "epoch": 0.94, + "learning_rate": 2.8383033936600974e-06, + "loss": 0.0883, + "step": 422820 + }, + { + "epoch": 0.94, + "learning_rate": 2.837184850450773e-06, + "loss": 0.0931, + "step": 422830 + }, + { + "epoch": 0.94, + "learning_rate": 2.836066307241449e-06, + "loss": 0.0889, + "step": 422840 + }, + { + "epoch": 0.94, + "learning_rate": 2.8349477640321248e-06, + "loss": 0.092, + "step": 422850 + }, + { + "epoch": 0.94, + "learning_rate": 2.8338292208228006e-06, + "loss": 0.093, + "step": 422860 + }, + { + "epoch": 0.94, + "learning_rate": 2.8327106776134764e-06, + "loss": 0.088, + "step": 422870 + }, + { + "epoch": 0.94, + "learning_rate": 2.8315921344041522e-06, + "loss": 0.0919, + "step": 422880 + }, + { + "epoch": 0.94, + "learning_rate": 2.830473591194828e-06, + "loss": 0.0964, + "step": 422890 + }, + { + "epoch": 0.94, + "learning_rate": 2.829355047985504e-06, + "loss": 0.094, + "step": 422900 + }, + { + "epoch": 0.94, + "learning_rate": 2.8282365047761796e-06, + "loss": 0.0874, + "step": 422910 + }, + { + "epoch": 0.94, + "learning_rate": 2.8271179615668555e-06, + "loss": 0.0933, + "step": 422920 + }, + { + "epoch": 0.94, + "learning_rate": 2.8259994183575313e-06, + "loss": 0.0903, + "step": 422930 + }, + { + "epoch": 0.94, + "learning_rate": 2.824880875148207e-06, + "loss": 0.0918, + "step": 422940 + }, + { + "epoch": 0.94, + "learning_rate": 2.823762331938883e-06, + "loss": 0.0853, + "step": 422950 + }, + { + "epoch": 0.94, + "learning_rate": 2.822643788729559e-06, + "loss": 0.0906, + "step": 422960 + }, + { + "epoch": 0.94, + "learning_rate": 2.8215252455202345e-06, + "loss": 0.0928, + "step": 422970 + }, + { + "epoch": 0.94, + "learning_rate": 2.8204067023109107e-06, + "loss": 0.0931, + "step": 422980 + }, + { + "epoch": 0.94, + "learning_rate": 2.819288159101586e-06, + "loss": 0.0943, + "step": 422990 + }, + { + "epoch": 0.94, + "learning_rate": 2.8181696158922624e-06, + "loss": 0.0923, + "step": 423000 + }, + { + "epoch": 0.94, + "learning_rate": 2.8170510726829377e-06, + "loss": 0.0916, + "step": 423010 + }, + { + "epoch": 0.94, + "learning_rate": 2.815932529473614e-06, + "loss": 0.0913, + "step": 423020 + }, + { + "epoch": 0.94, + "learning_rate": 2.8148139862642894e-06, + "loss": 0.0888, + "step": 423030 + }, + { + "epoch": 0.94, + "learning_rate": 2.8136954430549656e-06, + "loss": 0.0893, + "step": 423040 + }, + { + "epoch": 0.94, + "learning_rate": 2.812576899845641e-06, + "loss": 0.0897, + "step": 423050 + }, + { + "epoch": 0.94, + "learning_rate": 2.8114583566363172e-06, + "loss": 0.0946, + "step": 423060 + }, + { + "epoch": 0.94, + "learning_rate": 2.8103398134269926e-06, + "loss": 0.0919, + "step": 423070 + }, + { + "epoch": 0.94, + "learning_rate": 2.809221270217669e-06, + "loss": 0.0937, + "step": 423080 + }, + { + "epoch": 0.94, + "learning_rate": 2.8081027270083446e-06, + "loss": 0.0918, + "step": 423090 + }, + { + "epoch": 0.94, + "learning_rate": 2.8069841837990205e-06, + "loss": 0.0964, + "step": 423100 + }, + { + "epoch": 0.94, + "learning_rate": 2.8058656405896963e-06, + "loss": 0.0906, + "step": 423110 + }, + { + "epoch": 0.94, + "learning_rate": 2.804747097380372e-06, + "loss": 0.0953, + "step": 423120 + }, + { + "epoch": 0.94, + "learning_rate": 2.803628554171048e-06, + "loss": 0.0911, + "step": 423130 + }, + { + "epoch": 0.94, + "learning_rate": 2.8025100109617237e-06, + "loss": 0.0889, + "step": 423140 + }, + { + "epoch": 0.94, + "learning_rate": 2.8013914677523995e-06, + "loss": 0.0948, + "step": 423150 + }, + { + "epoch": 0.94, + "learning_rate": 2.8002729245430753e-06, + "loss": 0.0918, + "step": 423160 + }, + { + "epoch": 0.94, + "learning_rate": 2.799154381333751e-06, + "loss": 0.0907, + "step": 423170 + }, + { + "epoch": 0.94, + "learning_rate": 2.798035838124427e-06, + "loss": 0.0899, + "step": 423180 + }, + { + "epoch": 0.94, + "learning_rate": 2.7969172949151027e-06, + "loss": 0.0901, + "step": 423190 + }, + { + "epoch": 0.94, + "learning_rate": 2.7957987517057786e-06, + "loss": 0.0893, + "step": 423200 + }, + { + "epoch": 0.94, + "learning_rate": 2.7946802084964544e-06, + "loss": 0.0965, + "step": 423210 + }, + { + "epoch": 0.94, + "learning_rate": 2.79356166528713e-06, + "loss": 0.0928, + "step": 423220 + }, + { + "epoch": 0.94, + "learning_rate": 2.792443122077806e-06, + "loss": 0.0912, + "step": 423230 + }, + { + "epoch": 0.94, + "learning_rate": 2.791324578868482e-06, + "loss": 0.089, + "step": 423240 + }, + { + "epoch": 0.94, + "learning_rate": 2.7902060356591576e-06, + "loss": 0.0931, + "step": 423250 + }, + { + "epoch": 0.94, + "learning_rate": 2.789087492449834e-06, + "loss": 0.0881, + "step": 423260 + }, + { + "epoch": 0.94, + "learning_rate": 2.7879689492405092e-06, + "loss": 0.0863, + "step": 423270 + }, + { + "epoch": 0.94, + "learning_rate": 2.7868504060311855e-06, + "loss": 0.0902, + "step": 423280 + }, + { + "epoch": 0.94, + "learning_rate": 2.785731862821861e-06, + "loss": 0.0925, + "step": 423290 + }, + { + "epoch": 0.94, + "learning_rate": 2.784613319612537e-06, + "loss": 0.0871, + "step": 423300 + }, + { + "epoch": 0.94, + "learning_rate": 2.7834947764032125e-06, + "loss": 0.0921, + "step": 423310 + }, + { + "epoch": 0.94, + "learning_rate": 2.7823762331938887e-06, + "loss": 0.0915, + "step": 423320 + }, + { + "epoch": 0.94, + "learning_rate": 2.781257689984564e-06, + "loss": 0.0902, + "step": 423330 + }, + { + "epoch": 0.94, + "learning_rate": 2.7801391467752403e-06, + "loss": 0.0944, + "step": 423340 + }, + { + "epoch": 0.94, + "learning_rate": 2.7790206035659157e-06, + "loss": 0.0941, + "step": 423350 + }, + { + "epoch": 0.94, + "learning_rate": 2.777902060356592e-06, + "loss": 0.0922, + "step": 423360 + }, + { + "epoch": 0.95, + "learning_rate": 2.7767835171472673e-06, + "loss": 0.0955, + "step": 423370 + }, + { + "epoch": 0.95, + "learning_rate": 2.775664973937943e-06, + "loss": 0.0916, + "step": 423380 + }, + { + "epoch": 0.95, + "learning_rate": 2.7745464307286194e-06, + "loss": 0.092, + "step": 423390 + }, + { + "epoch": 0.95, + "learning_rate": 2.7734278875192948e-06, + "loss": 0.0901, + "step": 423400 + }, + { + "epoch": 0.95, + "learning_rate": 2.772309344309971e-06, + "loss": 0.095, + "step": 423410 + }, + { + "epoch": 0.95, + "learning_rate": 2.7711908011006464e-06, + "loss": 0.0872, + "step": 423420 + }, + { + "epoch": 0.95, + "learning_rate": 2.7700722578913226e-06, + "loss": 0.0888, + "step": 423430 + }, + { + "epoch": 0.95, + "learning_rate": 2.768953714681998e-06, + "loss": 0.0966, + "step": 423440 + }, + { + "epoch": 0.95, + "learning_rate": 2.7678351714726742e-06, + "loss": 0.0892, + "step": 423450 + }, + { + "epoch": 0.95, + "learning_rate": 2.7667166282633496e-06, + "loss": 0.092, + "step": 423460 + }, + { + "epoch": 0.95, + "learning_rate": 2.765598085054026e-06, + "loss": 0.0893, + "step": 423470 + }, + { + "epoch": 0.95, + "learning_rate": 2.7644795418447012e-06, + "loss": 0.0887, + "step": 423480 + }, + { + "epoch": 0.95, + "learning_rate": 2.7633609986353775e-06, + "loss": 0.0941, + "step": 423490 + }, + { + "epoch": 0.95, + "learning_rate": 2.762242455426053e-06, + "loss": 0.0904, + "step": 423500 + }, + { + "epoch": 0.95, + "learning_rate": 2.761123912216729e-06, + "loss": 0.0905, + "step": 423510 + }, + { + "epoch": 0.95, + "learning_rate": 2.760005369007405e-06, + "loss": 0.09, + "step": 423520 + }, + { + "epoch": 0.95, + "learning_rate": 2.7588868257980807e-06, + "loss": 0.0932, + "step": 423530 + }, + { + "epoch": 0.95, + "learning_rate": 2.7577682825887565e-06, + "loss": 0.09, + "step": 423540 + }, + { + "epoch": 0.95, + "learning_rate": 2.7566497393794323e-06, + "loss": 0.0899, + "step": 423550 + }, + { + "epoch": 0.95, + "learning_rate": 2.755531196170108e-06, + "loss": 0.0929, + "step": 423560 + }, + { + "epoch": 0.95, + "learning_rate": 2.754412652960784e-06, + "loss": 0.0905, + "step": 423570 + }, + { + "epoch": 0.95, + "learning_rate": 2.7532941097514598e-06, + "loss": 0.0911, + "step": 423580 + }, + { + "epoch": 0.95, + "learning_rate": 2.7521755665421356e-06, + "loss": 0.0934, + "step": 423590 + }, + { + "epoch": 0.95, + "learning_rate": 2.7510570233328114e-06, + "loss": 0.096, + "step": 423600 + }, + { + "epoch": 0.95, + "learning_rate": 2.749938480123487e-06, + "loss": 0.0881, + "step": 423610 + }, + { + "epoch": 0.95, + "learning_rate": 2.748819936914163e-06, + "loss": 0.0935, + "step": 423620 + }, + { + "epoch": 0.95, + "learning_rate": 2.747701393704839e-06, + "loss": 0.0901, + "step": 423630 + }, + { + "epoch": 0.95, + "learning_rate": 2.7465828504955146e-06, + "loss": 0.0946, + "step": 423640 + }, + { + "epoch": 0.95, + "learning_rate": 2.7454643072861904e-06, + "loss": 0.0926, + "step": 423650 + }, + { + "epoch": 0.95, + "learning_rate": 2.7443457640768662e-06, + "loss": 0.0919, + "step": 423660 + }, + { + "epoch": 0.95, + "learning_rate": 2.743227220867542e-06, + "loss": 0.0918, + "step": 423670 + }, + { + "epoch": 0.95, + "learning_rate": 2.742108677658218e-06, + "loss": 0.0947, + "step": 423680 + }, + { + "epoch": 0.95, + "learning_rate": 2.740990134448894e-06, + "loss": 0.0893, + "step": 423690 + }, + { + "epoch": 0.95, + "learning_rate": 2.7398715912395695e-06, + "loss": 0.0911, + "step": 423700 + }, + { + "epoch": 0.95, + "learning_rate": 2.7387530480302457e-06, + "loss": 0.0865, + "step": 423710 + }, + { + "epoch": 0.95, + "learning_rate": 2.737634504820921e-06, + "loss": 0.0936, + "step": 423720 + }, + { + "epoch": 0.95, + "learning_rate": 2.7365159616115973e-06, + "loss": 0.0918, + "step": 423730 + }, + { + "epoch": 0.95, + "learning_rate": 2.7353974184022727e-06, + "loss": 0.0929, + "step": 423740 + }, + { + "epoch": 0.95, + "learning_rate": 2.734278875192949e-06, + "loss": 0.0928, + "step": 423750 + }, + { + "epoch": 0.95, + "learning_rate": 2.7331603319836243e-06, + "loss": 0.0888, + "step": 423760 + }, + { + "epoch": 0.95, + "learning_rate": 2.7320417887743006e-06, + "loss": 0.0908, + "step": 423770 + }, + { + "epoch": 0.95, + "learning_rate": 2.730923245564976e-06, + "loss": 0.0965, + "step": 423780 + }, + { + "epoch": 0.95, + "learning_rate": 2.729804702355652e-06, + "loss": 0.0924, + "step": 423790 + }, + { + "epoch": 0.95, + "learning_rate": 2.728686159146328e-06, + "loss": 0.0943, + "step": 423800 + }, + { + "epoch": 0.95, + "learning_rate": 2.727567615937004e-06, + "loss": 0.0899, + "step": 423810 + }, + { + "epoch": 0.95, + "learning_rate": 2.7264490727276796e-06, + "loss": 0.0899, + "step": 423820 + }, + { + "epoch": 0.95, + "learning_rate": 2.7253305295183554e-06, + "loss": 0.089, + "step": 423830 + }, + { + "epoch": 0.95, + "learning_rate": 2.7242119863090313e-06, + "loss": 0.0918, + "step": 423840 + }, + { + "epoch": 0.95, + "learning_rate": 2.723093443099707e-06, + "loss": 0.0903, + "step": 423850 + }, + { + "epoch": 0.95, + "learning_rate": 2.721974899890383e-06, + "loss": 0.0911, + "step": 423860 + }, + { + "epoch": 0.95, + "learning_rate": 2.7208563566810587e-06, + "loss": 0.0912, + "step": 423870 + }, + { + "epoch": 0.95, + "learning_rate": 2.7197378134717345e-06, + "loss": 0.0897, + "step": 423880 + }, + { + "epoch": 0.95, + "learning_rate": 2.7186192702624103e-06, + "loss": 0.0955, + "step": 423890 + }, + { + "epoch": 0.95, + "learning_rate": 2.717500727053086e-06, + "loss": 0.0946, + "step": 423900 + }, + { + "epoch": 0.95, + "learning_rate": 2.716382183843762e-06, + "loss": 0.0899, + "step": 423910 + }, + { + "epoch": 0.95, + "learning_rate": 2.7152636406344377e-06, + "loss": 0.0906, + "step": 423920 + }, + { + "epoch": 0.95, + "learning_rate": 2.7141450974251135e-06, + "loss": 0.0898, + "step": 423930 + }, + { + "epoch": 0.95, + "learning_rate": 2.7130265542157894e-06, + "loss": 0.0904, + "step": 423940 + }, + { + "epoch": 0.95, + "learning_rate": 2.711908011006465e-06, + "loss": 0.0906, + "step": 423950 + }, + { + "epoch": 0.95, + "learning_rate": 2.710789467797141e-06, + "loss": 0.0891, + "step": 423960 + }, + { + "epoch": 0.95, + "learning_rate": 2.7096709245878168e-06, + "loss": 0.0922, + "step": 423970 + }, + { + "epoch": 0.95, + "learning_rate": 2.7085523813784926e-06, + "loss": 0.0928, + "step": 423980 + }, + { + "epoch": 0.95, + "learning_rate": 2.707433838169169e-06, + "loss": 0.0896, + "step": 423990 + }, + { + "epoch": 0.95, + "learning_rate": 2.7063152949598442e-06, + "loss": 0.0893, + "step": 424000 + }, + { + "epoch": 0.95, + "learning_rate": 2.7051967517505204e-06, + "loss": 0.0919, + "step": 424010 + }, + { + "epoch": 0.95, + "learning_rate": 2.704078208541196e-06, + "loss": 0.0981, + "step": 424020 + }, + { + "epoch": 0.95, + "learning_rate": 2.702959665331872e-06, + "loss": 0.0947, + "step": 424030 + }, + { + "epoch": 0.95, + "learning_rate": 2.7018411221225475e-06, + "loss": 0.0944, + "step": 424040 + }, + { + "epoch": 0.95, + "learning_rate": 2.7007225789132237e-06, + "loss": 0.0961, + "step": 424050 + }, + { + "epoch": 0.95, + "learning_rate": 2.699604035703899e-06, + "loss": 0.089, + "step": 424060 + }, + { + "epoch": 0.95, + "learning_rate": 2.6984854924945753e-06, + "loss": 0.0911, + "step": 424070 + }, + { + "epoch": 0.95, + "learning_rate": 2.6973669492852507e-06, + "loss": 0.0964, + "step": 424080 + }, + { + "epoch": 0.95, + "learning_rate": 2.696248406075927e-06, + "loss": 0.0887, + "step": 424090 + }, + { + "epoch": 0.95, + "learning_rate": 2.6951298628666027e-06, + "loss": 0.091, + "step": 424100 + }, + { + "epoch": 0.95, + "learning_rate": 2.6941231739782107e-06, + "loss": 0.0931, + "step": 424110 + }, + { + "epoch": 0.95, + "learning_rate": 2.693004630768887e-06, + "loss": 0.0876, + "step": 424120 + }, + { + "epoch": 0.95, + "learning_rate": 2.6918860875595623e-06, + "loss": 0.0909, + "step": 424130 + }, + { + "epoch": 0.95, + "learning_rate": 2.6907675443502385e-06, + "loss": 0.0899, + "step": 424140 + }, + { + "epoch": 0.95, + "learning_rate": 2.689649001140914e-06, + "loss": 0.0939, + "step": 424150 + }, + { + "epoch": 0.95, + "learning_rate": 2.68853045793159e-06, + "loss": 0.0894, + "step": 424160 + }, + { + "epoch": 0.95, + "learning_rate": 2.6874119147222655e-06, + "loss": 0.0951, + "step": 424170 + }, + { + "epoch": 0.95, + "learning_rate": 2.6862933715129418e-06, + "loss": 0.0934, + "step": 424180 + }, + { + "epoch": 0.95, + "learning_rate": 2.6851748283036176e-06, + "loss": 0.0924, + "step": 424190 + }, + { + "epoch": 0.95, + "learning_rate": 2.6840562850942934e-06, + "loss": 0.0957, + "step": 424200 + }, + { + "epoch": 0.95, + "learning_rate": 2.682937741884969e-06, + "loss": 0.0876, + "step": 424210 + }, + { + "epoch": 0.95, + "learning_rate": 2.681819198675645e-06, + "loss": 0.0921, + "step": 424220 + }, + { + "epoch": 0.95, + "learning_rate": 2.680700655466321e-06, + "loss": 0.0923, + "step": 424230 + }, + { + "epoch": 0.95, + "learning_rate": 2.6795821122569966e-06, + "loss": 0.0968, + "step": 424240 + }, + { + "epoch": 0.95, + "learning_rate": 2.6784635690476724e-06, + "loss": 0.0944, + "step": 424250 + }, + { + "epoch": 0.95, + "learning_rate": 2.6773450258383482e-06, + "loss": 0.0888, + "step": 424260 + }, + { + "epoch": 0.95, + "learning_rate": 2.676226482629024e-06, + "loss": 0.0912, + "step": 424270 + }, + { + "epoch": 0.95, + "learning_rate": 2.6751079394197e-06, + "loss": 0.0913, + "step": 424280 + }, + { + "epoch": 0.95, + "learning_rate": 2.6739893962103757e-06, + "loss": 0.0933, + "step": 424290 + }, + { + "epoch": 0.95, + "learning_rate": 2.6728708530010515e-06, + "loss": 0.0894, + "step": 424300 + }, + { + "epoch": 0.95, + "learning_rate": 2.6717523097917273e-06, + "loss": 0.0926, + "step": 424310 + }, + { + "epoch": 0.95, + "learning_rate": 2.670633766582403e-06, + "loss": 0.0909, + "step": 424320 + }, + { + "epoch": 0.95, + "learning_rate": 2.669515223373079e-06, + "loss": 0.0888, + "step": 424330 + }, + { + "epoch": 0.95, + "learning_rate": 2.6683966801637547e-06, + "loss": 0.0884, + "step": 424340 + }, + { + "epoch": 0.95, + "learning_rate": 2.6672781369544305e-06, + "loss": 0.0924, + "step": 424350 + }, + { + "epoch": 0.95, + "learning_rate": 2.6661595937451068e-06, + "loss": 0.0916, + "step": 424360 + }, + { + "epoch": 0.95, + "learning_rate": 2.665041050535782e-06, + "loss": 0.0926, + "step": 424370 + }, + { + "epoch": 0.95, + "learning_rate": 2.6639225073264584e-06, + "loss": 0.0921, + "step": 424380 + }, + { + "epoch": 0.95, + "learning_rate": 2.6628039641171338e-06, + "loss": 0.0917, + "step": 424390 + }, + { + "epoch": 0.95, + "learning_rate": 2.66168542090781e-06, + "loss": 0.0918, + "step": 424400 + }, + { + "epoch": 0.95, + "learning_rate": 2.6605668776984854e-06, + "loss": 0.0904, + "step": 424410 + }, + { + "epoch": 0.95, + "learning_rate": 2.6594483344891616e-06, + "loss": 0.0897, + "step": 424420 + }, + { + "epoch": 0.95, + "learning_rate": 2.658329791279837e-06, + "loss": 0.0918, + "step": 424430 + }, + { + "epoch": 0.95, + "learning_rate": 2.6572112480705133e-06, + "loss": 0.0894, + "step": 424440 + }, + { + "epoch": 0.95, + "learning_rate": 2.6560927048611886e-06, + "loss": 0.0919, + "step": 424450 + }, + { + "epoch": 0.95, + "learning_rate": 2.654974161651865e-06, + "loss": 0.0938, + "step": 424460 + }, + { + "epoch": 0.95, + "learning_rate": 2.6538556184425403e-06, + "loss": 0.0925, + "step": 424470 + }, + { + "epoch": 0.95, + "learning_rate": 2.6527370752332165e-06, + "loss": 0.0889, + "step": 424480 + }, + { + "epoch": 0.95, + "learning_rate": 2.6516185320238923e-06, + "loss": 0.0909, + "step": 424490 + }, + { + "epoch": 0.95, + "learning_rate": 2.650499988814568e-06, + "loss": 0.0928, + "step": 424500 + }, + { + "epoch": 0.95, + "learning_rate": 2.649381445605244e-06, + "loss": 0.0926, + "step": 424510 + }, + { + "epoch": 0.95, + "learning_rate": 2.6482629023959197e-06, + "loss": 0.0915, + "step": 424520 + }, + { + "epoch": 0.95, + "learning_rate": 2.6471443591865955e-06, + "loss": 0.0874, + "step": 424530 + }, + { + "epoch": 0.95, + "learning_rate": 2.6460258159772714e-06, + "loss": 0.0914, + "step": 424540 + }, + { + "epoch": 0.95, + "learning_rate": 2.644907272767947e-06, + "loss": 0.0897, + "step": 424550 + }, + { + "epoch": 0.95, + "learning_rate": 2.643788729558623e-06, + "loss": 0.0883, + "step": 424560 + }, + { + "epoch": 0.95, + "learning_rate": 2.6426701863492988e-06, + "loss": 0.0982, + "step": 424570 + }, + { + "epoch": 0.95, + "learning_rate": 2.6415516431399746e-06, + "loss": 0.0938, + "step": 424580 + }, + { + "epoch": 0.95, + "learning_rate": 2.6404330999306504e-06, + "loss": 0.0904, + "step": 424590 + }, + { + "epoch": 0.95, + "learning_rate": 2.6393145567213262e-06, + "loss": 0.09, + "step": 424600 + }, + { + "epoch": 0.95, + "learning_rate": 2.638196013512002e-06, + "loss": 0.0914, + "step": 424610 + }, + { + "epoch": 0.95, + "learning_rate": 2.637077470302678e-06, + "loss": 0.0853, + "step": 424620 + }, + { + "epoch": 0.95, + "learning_rate": 2.6359589270933536e-06, + "loss": 0.088, + "step": 424630 + }, + { + "epoch": 0.95, + "learning_rate": 2.6348403838840295e-06, + "loss": 0.0958, + "step": 424640 + }, + { + "epoch": 0.95, + "learning_rate": 2.6337218406747053e-06, + "loss": 0.0887, + "step": 424650 + }, + { + "epoch": 0.95, + "learning_rate": 2.6326032974653815e-06, + "loss": 0.0898, + "step": 424660 + }, + { + "epoch": 0.95, + "learning_rate": 2.631484754256057e-06, + "loss": 0.0936, + "step": 424670 + }, + { + "epoch": 0.95, + "learning_rate": 2.630366211046733e-06, + "loss": 0.0923, + "step": 424680 + }, + { + "epoch": 0.95, + "learning_rate": 2.6292476678374085e-06, + "loss": 0.0918, + "step": 424690 + }, + { + "epoch": 0.95, + "learning_rate": 2.6281291246280847e-06, + "loss": 0.0921, + "step": 424700 + }, + { + "epoch": 0.95, + "learning_rate": 2.62701058141876e-06, + "loss": 0.0929, + "step": 424710 + }, + { + "epoch": 0.95, + "learning_rate": 2.6258920382094364e-06, + "loss": 0.0933, + "step": 424720 + }, + { + "epoch": 0.95, + "learning_rate": 2.6247734950001117e-06, + "loss": 0.0909, + "step": 424730 + }, + { + "epoch": 0.95, + "learning_rate": 2.623654951790788e-06, + "loss": 0.0924, + "step": 424740 + }, + { + "epoch": 0.95, + "learning_rate": 2.6225364085814634e-06, + "loss": 0.0969, + "step": 424750 + }, + { + "epoch": 0.95, + "learning_rate": 2.6214178653721396e-06, + "loss": 0.092, + "step": 424760 + }, + { + "epoch": 0.95, + "learning_rate": 2.620299322162815e-06, + "loss": 0.0944, + "step": 424770 + }, + { + "epoch": 0.95, + "learning_rate": 2.6191807789534912e-06, + "loss": 0.0958, + "step": 424780 + }, + { + "epoch": 0.95, + "learning_rate": 2.618062235744167e-06, + "loss": 0.0943, + "step": 424790 + }, + { + "epoch": 0.95, + "learning_rate": 2.616943692534843e-06, + "loss": 0.0917, + "step": 424800 + }, + { + "epoch": 0.95, + "learning_rate": 2.6158251493255186e-06, + "loss": 0.091, + "step": 424810 + }, + { + "epoch": 0.95, + "learning_rate": 2.6147066061161945e-06, + "loss": 0.0877, + "step": 424820 + }, + { + "epoch": 0.95, + "learning_rate": 2.6135880629068703e-06, + "loss": 0.0934, + "step": 424830 + }, + { + "epoch": 0.95, + "learning_rate": 2.612469519697546e-06, + "loss": 0.0936, + "step": 424840 + }, + { + "epoch": 0.95, + "learning_rate": 2.611350976488222e-06, + "loss": 0.0895, + "step": 424850 + }, + { + "epoch": 0.95, + "learning_rate": 2.6102324332788977e-06, + "loss": 0.0917, + "step": 424860 + }, + { + "epoch": 0.95, + "learning_rate": 2.6091138900695735e-06, + "loss": 0.088, + "step": 424870 + }, + { + "epoch": 0.95, + "learning_rate": 2.6079953468602493e-06, + "loss": 0.0902, + "step": 424880 + }, + { + "epoch": 0.95, + "learning_rate": 2.606876803650925e-06, + "loss": 0.0908, + "step": 424890 + }, + { + "epoch": 0.95, + "learning_rate": 2.605758260441601e-06, + "loss": 0.0898, + "step": 424900 + }, + { + "epoch": 0.95, + "learning_rate": 2.6046397172322768e-06, + "loss": 0.095, + "step": 424910 + }, + { + "epoch": 0.95, + "learning_rate": 2.6035211740229526e-06, + "loss": 0.0904, + "step": 424920 + }, + { + "epoch": 0.95, + "learning_rate": 2.6024026308136284e-06, + "loss": 0.0926, + "step": 424930 + }, + { + "epoch": 0.95, + "learning_rate": 2.601284087604304e-06, + "loss": 0.0919, + "step": 424940 + }, + { + "epoch": 0.95, + "learning_rate": 2.60016554439498e-06, + "loss": 0.0934, + "step": 424950 + }, + { + "epoch": 0.95, + "learning_rate": 2.5990470011856562e-06, + "loss": 0.0906, + "step": 424960 + }, + { + "epoch": 0.95, + "learning_rate": 2.5979284579763316e-06, + "loss": 0.0929, + "step": 424970 + }, + { + "epoch": 0.95, + "learning_rate": 2.596809914767008e-06, + "loss": 0.0923, + "step": 424980 + }, + { + "epoch": 0.95, + "learning_rate": 2.5956913715576832e-06, + "loss": 0.0925, + "step": 424990 + }, + { + "epoch": 0.95, + "learning_rate": 2.5945728283483595e-06, + "loss": 0.0888, + "step": 425000 + }, + { + "epoch": 0.95, + "learning_rate": 2.593454285139035e-06, + "loss": 0.092, + "step": 425010 + }, + { + "epoch": 0.95, + "learning_rate": 2.592335741929711e-06, + "loss": 0.0903, + "step": 425020 + }, + { + "epoch": 0.95, + "learning_rate": 2.5912171987203865e-06, + "loss": 0.0901, + "step": 425030 + }, + { + "epoch": 0.95, + "learning_rate": 2.5900986555110627e-06, + "loss": 0.0931, + "step": 425040 + }, + { + "epoch": 0.95, + "learning_rate": 2.588980112301738e-06, + "loss": 0.0935, + "step": 425050 + }, + { + "epoch": 0.95, + "learning_rate": 2.5878615690924143e-06, + "loss": 0.0901, + "step": 425060 + }, + { + "epoch": 0.95, + "learning_rate": 2.5867430258830897e-06, + "loss": 0.0882, + "step": 425070 + }, + { + "epoch": 0.95, + "learning_rate": 2.585624482673766e-06, + "loss": 0.095, + "step": 425080 + }, + { + "epoch": 0.95, + "learning_rate": 2.5845059394644418e-06, + "loss": 0.0918, + "step": 425090 + }, + { + "epoch": 0.95, + "learning_rate": 2.5833873962551176e-06, + "loss": 0.0908, + "step": 425100 + }, + { + "epoch": 0.95, + "learning_rate": 2.5822688530457934e-06, + "loss": 0.0908, + "step": 425110 + }, + { + "epoch": 0.95, + "learning_rate": 2.581150309836469e-06, + "loss": 0.093, + "step": 425120 + }, + { + "epoch": 0.95, + "learning_rate": 2.580031766627145e-06, + "loss": 0.0925, + "step": 425130 + }, + { + "epoch": 0.95, + "learning_rate": 2.578913223417821e-06, + "loss": 0.0911, + "step": 425140 + }, + { + "epoch": 0.95, + "learning_rate": 2.5777946802084966e-06, + "loss": 0.0906, + "step": 425150 + }, + { + "epoch": 0.95, + "learning_rate": 2.5766761369991724e-06, + "loss": 0.089, + "step": 425160 + }, + { + "epoch": 0.95, + "learning_rate": 2.5755575937898482e-06, + "loss": 0.0886, + "step": 425170 + }, + { + "epoch": 0.95, + "learning_rate": 2.574439050580524e-06, + "loss": 0.0891, + "step": 425180 + }, + { + "epoch": 0.95, + "learning_rate": 2.5733205073712e-06, + "loss": 0.0926, + "step": 425190 + }, + { + "epoch": 0.95, + "learning_rate": 2.5722019641618757e-06, + "loss": 0.0924, + "step": 425200 + }, + { + "epoch": 0.95, + "learning_rate": 2.5710834209525515e-06, + "loss": 0.0909, + "step": 425210 + }, + { + "epoch": 0.95, + "learning_rate": 2.5699648777432273e-06, + "loss": 0.0911, + "step": 425220 + }, + { + "epoch": 0.95, + "learning_rate": 2.568846334533903e-06, + "loss": 0.0942, + "step": 425230 + }, + { + "epoch": 0.95, + "learning_rate": 2.567727791324579e-06, + "loss": 0.0969, + "step": 425240 + }, + { + "epoch": 0.95, + "learning_rate": 2.5666092481152547e-06, + "loss": 0.0933, + "step": 425250 + }, + { + "epoch": 0.95, + "learning_rate": 2.565490704905931e-06, + "loss": 0.0951, + "step": 425260 + }, + { + "epoch": 0.95, + "learning_rate": 2.5643721616966063e-06, + "loss": 0.091, + "step": 425270 + }, + { + "epoch": 0.95, + "learning_rate": 2.5632536184872826e-06, + "loss": 0.0907, + "step": 425280 + }, + { + "epoch": 0.95, + "learning_rate": 2.562135075277958e-06, + "loss": 0.0867, + "step": 425290 + }, + { + "epoch": 0.95, + "learning_rate": 2.561016532068634e-06, + "loss": 0.0935, + "step": 425300 + }, + { + "epoch": 0.95, + "learning_rate": 2.5598979888593096e-06, + "loss": 0.0904, + "step": 425310 + }, + { + "epoch": 0.95, + "learning_rate": 2.558779445649986e-06, + "loss": 0.0916, + "step": 425320 + }, + { + "epoch": 0.95, + "learning_rate": 2.557660902440661e-06, + "loss": 0.092, + "step": 425330 + }, + { + "epoch": 0.95, + "learning_rate": 2.5565423592313374e-06, + "loss": 0.0928, + "step": 425340 + }, + { + "epoch": 0.95, + "learning_rate": 2.555423816022013e-06, + "loss": 0.0934, + "step": 425350 + }, + { + "epoch": 0.95, + "learning_rate": 2.554305272812689e-06, + "loss": 0.0925, + "step": 425360 + }, + { + "epoch": 0.95, + "learning_rate": 2.5531867296033644e-06, + "loss": 0.0912, + "step": 425370 + }, + { + "epoch": 0.95, + "learning_rate": 2.5520681863940407e-06, + "loss": 0.0967, + "step": 425380 + }, + { + "epoch": 0.95, + "learning_rate": 2.5509496431847165e-06, + "loss": 0.0894, + "step": 425390 + }, + { + "epoch": 0.95, + "learning_rate": 2.5498310999753923e-06, + "loss": 0.091, + "step": 425400 + }, + { + "epoch": 0.95, + "learning_rate": 2.548712556766068e-06, + "loss": 0.091, + "step": 425410 + }, + { + "epoch": 0.95, + "learning_rate": 2.547594013556744e-06, + "loss": 0.0926, + "step": 425420 + }, + { + "epoch": 0.95, + "learning_rate": 2.5464754703474197e-06, + "loss": 0.0974, + "step": 425430 + }, + { + "epoch": 0.95, + "learning_rate": 2.5453569271380955e-06, + "loss": 0.093, + "step": 425440 + }, + { + "epoch": 0.95, + "learning_rate": 2.5442383839287713e-06, + "loss": 0.0951, + "step": 425450 + }, + { + "epoch": 0.95, + "learning_rate": 2.543119840719447e-06, + "loss": 0.098, + "step": 425460 + }, + { + "epoch": 0.95, + "learning_rate": 2.542001297510123e-06, + "loss": 0.09, + "step": 425470 + }, + { + "epoch": 0.95, + "learning_rate": 2.5408827543007988e-06, + "loss": 0.0911, + "step": 425480 + }, + { + "epoch": 0.95, + "learning_rate": 2.5397642110914746e-06, + "loss": 0.0913, + "step": 425490 + }, + { + "epoch": 0.95, + "learning_rate": 2.5386456678821504e-06, + "loss": 0.0925, + "step": 425500 + }, + { + "epoch": 0.95, + "learning_rate": 2.537527124672826e-06, + "loss": 0.0947, + "step": 425510 + }, + { + "epoch": 0.95, + "learning_rate": 2.536408581463502e-06, + "loss": 0.0917, + "step": 425520 + }, + { + "epoch": 0.95, + "learning_rate": 2.535290038254178e-06, + "loss": 0.0911, + "step": 425530 + }, + { + "epoch": 0.95, + "learning_rate": 2.5341714950448536e-06, + "loss": 0.096, + "step": 425540 + }, + { + "epoch": 0.95, + "learning_rate": 2.5330529518355294e-06, + "loss": 0.0874, + "step": 425550 + }, + { + "epoch": 0.95, + "learning_rate": 2.5319344086262057e-06, + "loss": 0.0951, + "step": 425560 + }, + { + "epoch": 0.95, + "learning_rate": 2.530815865416881e-06, + "loss": 0.0921, + "step": 425570 + }, + { + "epoch": 0.95, + "learning_rate": 2.5296973222075573e-06, + "loss": 0.0901, + "step": 425580 + }, + { + "epoch": 0.95, + "learning_rate": 2.5285787789982327e-06, + "loss": 0.0927, + "step": 425590 + }, + { + "epoch": 0.95, + "learning_rate": 2.527460235788909e-06, + "loss": 0.0961, + "step": 425600 + }, + { + "epoch": 0.95, + "learning_rate": 2.5263416925795843e-06, + "loss": 0.0938, + "step": 425610 + }, + { + "epoch": 0.95, + "learning_rate": 2.5252231493702605e-06, + "loss": 0.0898, + "step": 425620 + }, + { + "epoch": 0.95, + "learning_rate": 2.524104606160936e-06, + "loss": 0.093, + "step": 425630 + }, + { + "epoch": 0.95, + "learning_rate": 2.522986062951612e-06, + "loss": 0.0962, + "step": 425640 + }, + { + "epoch": 0.95, + "learning_rate": 2.5218675197422875e-06, + "loss": 0.0903, + "step": 425650 + }, + { + "epoch": 0.95, + "learning_rate": 2.5207489765329638e-06, + "loss": 0.0941, + "step": 425660 + }, + { + "epoch": 0.95, + "learning_rate": 2.5196304333236396e-06, + "loss": 0.0912, + "step": 425670 + }, + { + "epoch": 0.95, + "learning_rate": 2.5185118901143154e-06, + "loss": 0.0898, + "step": 425680 + }, + { + "epoch": 0.95, + "learning_rate": 2.517393346904991e-06, + "loss": 0.0944, + "step": 425690 + }, + { + "epoch": 0.95, + "learning_rate": 2.516274803695667e-06, + "loss": 0.091, + "step": 425700 + }, + { + "epoch": 0.95, + "learning_rate": 2.515156260486343e-06, + "loss": 0.0961, + "step": 425710 + }, + { + "epoch": 0.95, + "learning_rate": 2.5140377172770186e-06, + "loss": 0.0917, + "step": 425720 + }, + { + "epoch": 0.95, + "learning_rate": 2.5129191740676944e-06, + "loss": 0.0889, + "step": 425730 + }, + { + "epoch": 0.95, + "learning_rate": 2.5118006308583703e-06, + "loss": 0.0904, + "step": 425740 + }, + { + "epoch": 0.95, + "learning_rate": 2.510682087649046e-06, + "loss": 0.0911, + "step": 425750 + }, + { + "epoch": 0.95, + "learning_rate": 2.509563544439722e-06, + "loss": 0.0941, + "step": 425760 + }, + { + "epoch": 0.95, + "learning_rate": 2.5084450012303977e-06, + "loss": 0.0932, + "step": 425770 + }, + { + "epoch": 0.95, + "learning_rate": 2.5073264580210735e-06, + "loss": 0.0922, + "step": 425780 + }, + { + "epoch": 0.95, + "learning_rate": 2.5062079148117493e-06, + "loss": 0.0895, + "step": 425790 + }, + { + "epoch": 0.95, + "learning_rate": 2.505089371602425e-06, + "loss": 0.0957, + "step": 425800 + }, + { + "epoch": 0.95, + "learning_rate": 2.503970828393101e-06, + "loss": 0.0931, + "step": 425810 + }, + { + "epoch": 0.95, + "learning_rate": 2.5028522851837767e-06, + "loss": 0.088, + "step": 425820 + }, + { + "epoch": 0.95, + "learning_rate": 2.5017337419744526e-06, + "loss": 0.0897, + "step": 425830 + }, + { + "epoch": 0.95, + "learning_rate": 2.5006151987651284e-06, + "loss": 0.0917, + "step": 425840 + }, + { + "epoch": 0.95, + "learning_rate": 2.499496655555804e-06, + "loss": 0.0894, + "step": 425850 + }, + { + "epoch": 0.95, + "learning_rate": 2.4983781123464804e-06, + "loss": 0.0886, + "step": 425860 + }, + { + "epoch": 0.95, + "learning_rate": 2.497259569137156e-06, + "loss": 0.093, + "step": 425870 + }, + { + "epoch": 0.95, + "learning_rate": 2.496141025927832e-06, + "loss": 0.0921, + "step": 425880 + }, + { + "epoch": 0.95, + "learning_rate": 2.4950224827185074e-06, + "loss": 0.093, + "step": 425890 + }, + { + "epoch": 0.95, + "learning_rate": 2.4939039395091836e-06, + "loss": 0.0898, + "step": 425900 + }, + { + "epoch": 0.95, + "learning_rate": 2.492785396299859e-06, + "loss": 0.0889, + "step": 425910 + }, + { + "epoch": 0.95, + "learning_rate": 2.4916668530905353e-06, + "loss": 0.0905, + "step": 425920 + }, + { + "epoch": 0.95, + "learning_rate": 2.4905483098812107e-06, + "loss": 0.0901, + "step": 425930 + }, + { + "epoch": 0.95, + "learning_rate": 2.489429766671887e-06, + "loss": 0.0881, + "step": 425940 + }, + { + "epoch": 0.95, + "learning_rate": 2.4883112234625623e-06, + "loss": 0.0886, + "step": 425950 + }, + { + "epoch": 0.95, + "learning_rate": 2.4871926802532385e-06, + "loss": 0.0901, + "step": 425960 + }, + { + "epoch": 0.95, + "learning_rate": 2.4860741370439143e-06, + "loss": 0.0875, + "step": 425970 + }, + { + "epoch": 0.95, + "learning_rate": 2.48495559383459e-06, + "loss": 0.0945, + "step": 425980 + }, + { + "epoch": 0.95, + "learning_rate": 2.483837050625266e-06, + "loss": 0.0914, + "step": 425990 + }, + { + "epoch": 0.95, + "learning_rate": 2.4827185074159417e-06, + "loss": 0.092, + "step": 426000 + }, + { + "epoch": 0.95, + "learning_rate": 2.4815999642066176e-06, + "loss": 0.0933, + "step": 426010 + }, + { + "epoch": 0.95, + "learning_rate": 2.4804814209972934e-06, + "loss": 0.0896, + "step": 426020 + }, + { + "epoch": 0.95, + "learning_rate": 2.479362877787969e-06, + "loss": 0.0957, + "step": 426030 + }, + { + "epoch": 0.95, + "learning_rate": 2.478244334578645e-06, + "loss": 0.096, + "step": 426040 + }, + { + "epoch": 0.95, + "learning_rate": 2.477125791369321e-06, + "loss": 0.0927, + "step": 426050 + }, + { + "epoch": 0.95, + "learning_rate": 2.4760072481599966e-06, + "loss": 0.0911, + "step": 426060 + }, + { + "epoch": 0.95, + "learning_rate": 2.4748887049506724e-06, + "loss": 0.0906, + "step": 426070 + }, + { + "epoch": 0.95, + "learning_rate": 2.4737701617413482e-06, + "loss": 0.0937, + "step": 426080 + }, + { + "epoch": 0.95, + "learning_rate": 2.472651618532024e-06, + "loss": 0.0938, + "step": 426090 + }, + { + "epoch": 0.95, + "learning_rate": 2.4715330753227e-06, + "loss": 0.0951, + "step": 426100 + }, + { + "epoch": 0.95, + "learning_rate": 2.4704145321133757e-06, + "loss": 0.0916, + "step": 426110 + }, + { + "epoch": 0.95, + "learning_rate": 2.469407843224984e-06, + "loss": 0.0896, + "step": 426120 + }, + { + "epoch": 0.95, + "learning_rate": 2.4682893000156594e-06, + "loss": 0.0895, + "step": 426130 + }, + { + "epoch": 0.95, + "learning_rate": 2.4671707568063356e-06, + "loss": 0.0903, + "step": 426140 + }, + { + "epoch": 0.95, + "learning_rate": 2.466052213597011e-06, + "loss": 0.0893, + "step": 426150 + }, + { + "epoch": 0.95, + "learning_rate": 2.4649336703876873e-06, + "loss": 0.0918, + "step": 426160 + }, + { + "epoch": 0.95, + "learning_rate": 2.463815127178363e-06, + "loss": 0.0946, + "step": 426170 + }, + { + "epoch": 0.95, + "learning_rate": 2.462696583969039e-06, + "loss": 0.0922, + "step": 426180 + }, + { + "epoch": 0.95, + "learning_rate": 2.4615780407597147e-06, + "loss": 0.0908, + "step": 426190 + }, + { + "epoch": 0.95, + "learning_rate": 2.4604594975503905e-06, + "loss": 0.0975, + "step": 426200 + }, + { + "epoch": 0.95, + "learning_rate": 2.4593409543410663e-06, + "loss": 0.0907, + "step": 426210 + }, + { + "epoch": 0.95, + "learning_rate": 2.458222411131742e-06, + "loss": 0.0923, + "step": 426220 + }, + { + "epoch": 0.95, + "learning_rate": 2.457103867922418e-06, + "loss": 0.0889, + "step": 426230 + }, + { + "epoch": 0.95, + "learning_rate": 2.4559853247130937e-06, + "loss": 0.0909, + "step": 426240 + }, + { + "epoch": 0.95, + "learning_rate": 2.4548667815037695e-06, + "loss": 0.095, + "step": 426250 + }, + { + "epoch": 0.95, + "learning_rate": 2.4537482382944454e-06, + "loss": 0.0898, + "step": 426260 + }, + { + "epoch": 0.95, + "learning_rate": 2.452629695085121e-06, + "loss": 0.0917, + "step": 426270 + }, + { + "epoch": 0.95, + "learning_rate": 2.451511151875797e-06, + "loss": 0.0876, + "step": 426280 + }, + { + "epoch": 0.95, + "learning_rate": 2.4503926086664728e-06, + "loss": 0.0929, + "step": 426290 + }, + { + "epoch": 0.95, + "learning_rate": 2.4492740654571486e-06, + "loss": 0.0896, + "step": 426300 + }, + { + "epoch": 0.95, + "learning_rate": 2.4481555222478244e-06, + "loss": 0.089, + "step": 426310 + }, + { + "epoch": 0.95, + "learning_rate": 2.4470369790385002e-06, + "loss": 0.0934, + "step": 426320 + }, + { + "epoch": 0.95, + "learning_rate": 2.445918435829176e-06, + "loss": 0.0941, + "step": 426330 + }, + { + "epoch": 0.95, + "learning_rate": 2.444799892619852e-06, + "loss": 0.0924, + "step": 426340 + }, + { + "epoch": 0.95, + "learning_rate": 2.4436813494105276e-06, + "loss": 0.0924, + "step": 426350 + }, + { + "epoch": 0.95, + "learning_rate": 2.442562806201204e-06, + "loss": 0.0953, + "step": 426360 + }, + { + "epoch": 0.95, + "learning_rate": 2.4414442629918793e-06, + "loss": 0.0903, + "step": 426370 + }, + { + "epoch": 0.95, + "learning_rate": 2.4403257197825555e-06, + "loss": 0.0926, + "step": 426380 + }, + { + "epoch": 0.95, + "learning_rate": 2.439207176573231e-06, + "loss": 0.0946, + "step": 426390 + }, + { + "epoch": 0.95, + "learning_rate": 2.438088633363907e-06, + "loss": 0.0909, + "step": 426400 + }, + { + "epoch": 0.95, + "learning_rate": 2.4369700901545825e-06, + "loss": 0.0902, + "step": 426410 + }, + { + "epoch": 0.95, + "learning_rate": 2.4358515469452587e-06, + "loss": 0.0933, + "step": 426420 + }, + { + "epoch": 0.95, + "learning_rate": 2.434733003735934e-06, + "loss": 0.092, + "step": 426430 + }, + { + "epoch": 0.95, + "learning_rate": 2.4336144605266104e-06, + "loss": 0.0899, + "step": 426440 + }, + { + "epoch": 0.95, + "learning_rate": 2.4324959173172857e-06, + "loss": 0.0902, + "step": 426450 + }, + { + "epoch": 0.95, + "learning_rate": 2.431377374107962e-06, + "loss": 0.089, + "step": 426460 + }, + { + "epoch": 0.95, + "learning_rate": 2.430258830898638e-06, + "loss": 0.0912, + "step": 426470 + }, + { + "epoch": 0.95, + "learning_rate": 2.4291402876893136e-06, + "loss": 0.091, + "step": 426480 + }, + { + "epoch": 0.95, + "learning_rate": 2.4280217444799894e-06, + "loss": 0.0887, + "step": 426490 + }, + { + "epoch": 0.95, + "learning_rate": 2.4269032012706652e-06, + "loss": 0.0941, + "step": 426500 + }, + { + "epoch": 0.95, + "learning_rate": 2.425784658061341e-06, + "loss": 0.0882, + "step": 426510 + }, + { + "epoch": 0.95, + "learning_rate": 2.424666114852017e-06, + "loss": 0.0926, + "step": 426520 + }, + { + "epoch": 0.95, + "learning_rate": 2.4235475716426927e-06, + "loss": 0.0934, + "step": 426530 + }, + { + "epoch": 0.95, + "learning_rate": 2.4224290284333685e-06, + "loss": 0.0886, + "step": 426540 + }, + { + "epoch": 0.95, + "learning_rate": 2.4213104852240443e-06, + "loss": 0.0926, + "step": 426550 + }, + { + "epoch": 0.95, + "learning_rate": 2.42019194201472e-06, + "loss": 0.0908, + "step": 426560 + }, + { + "epoch": 0.95, + "learning_rate": 2.419073398805396e-06, + "loss": 0.0983, + "step": 426570 + }, + { + "epoch": 0.95, + "learning_rate": 2.4179548555960717e-06, + "loss": 0.0914, + "step": 426580 + }, + { + "epoch": 0.95, + "learning_rate": 2.4168363123867475e-06, + "loss": 0.0914, + "step": 426590 + }, + { + "epoch": 0.95, + "learning_rate": 2.4157177691774233e-06, + "loss": 0.0898, + "step": 426600 + }, + { + "epoch": 0.95, + "learning_rate": 2.414599225968099e-06, + "loss": 0.0921, + "step": 426610 + }, + { + "epoch": 0.95, + "learning_rate": 2.413480682758775e-06, + "loss": 0.0886, + "step": 426620 + }, + { + "epoch": 0.95, + "learning_rate": 2.4123621395494508e-06, + "loss": 0.0916, + "step": 426630 + }, + { + "epoch": 0.95, + "learning_rate": 2.4112435963401266e-06, + "loss": 0.0902, + "step": 426640 + }, + { + "epoch": 0.95, + "learning_rate": 2.4101250531308024e-06, + "loss": 0.0935, + "step": 426650 + }, + { + "epoch": 0.95, + "learning_rate": 2.4090065099214786e-06, + "loss": 0.0937, + "step": 426660 + }, + { + "epoch": 0.95, + "learning_rate": 2.407887966712154e-06, + "loss": 0.0912, + "step": 426670 + }, + { + "epoch": 0.95, + "learning_rate": 2.4067694235028302e-06, + "loss": 0.0932, + "step": 426680 + }, + { + "epoch": 0.95, + "learning_rate": 2.4056508802935056e-06, + "loss": 0.0929, + "step": 426690 + }, + { + "epoch": 0.95, + "learning_rate": 2.404532337084182e-06, + "loss": 0.0901, + "step": 426700 + }, + { + "epoch": 0.95, + "learning_rate": 2.4034137938748572e-06, + "loss": 0.0966, + "step": 426710 + }, + { + "epoch": 0.95, + "learning_rate": 2.4022952506655335e-06, + "loss": 0.0904, + "step": 426720 + }, + { + "epoch": 0.95, + "learning_rate": 2.401176707456209e-06, + "loss": 0.0895, + "step": 426730 + }, + { + "epoch": 0.95, + "learning_rate": 2.400058164246885e-06, + "loss": 0.0918, + "step": 426740 + }, + { + "epoch": 0.95, + "learning_rate": 2.3989396210375605e-06, + "loss": 0.0891, + "step": 426750 + }, + { + "epoch": 0.95, + "learning_rate": 2.3978210778282367e-06, + "loss": 0.0906, + "step": 426760 + }, + { + "epoch": 0.95, + "learning_rate": 2.3967025346189125e-06, + "loss": 0.0945, + "step": 426770 + }, + { + "epoch": 0.95, + "learning_rate": 2.3955839914095883e-06, + "loss": 0.0967, + "step": 426780 + }, + { + "epoch": 0.95, + "learning_rate": 2.394465448200264e-06, + "loss": 0.0918, + "step": 426790 + }, + { + "epoch": 0.95, + "learning_rate": 2.39334690499094e-06, + "loss": 0.0931, + "step": 426800 + }, + { + "epoch": 0.95, + "learning_rate": 2.3922283617816158e-06, + "loss": 0.0943, + "step": 426810 + }, + { + "epoch": 0.95, + "learning_rate": 2.3911098185722916e-06, + "loss": 0.089, + "step": 426820 + }, + { + "epoch": 0.95, + "learning_rate": 2.3899912753629674e-06, + "loss": 0.0942, + "step": 426830 + }, + { + "epoch": 0.95, + "learning_rate": 2.388872732153643e-06, + "loss": 0.092, + "step": 426840 + }, + { + "epoch": 0.95, + "learning_rate": 2.387754188944319e-06, + "loss": 0.0901, + "step": 426850 + }, + { + "epoch": 0.95, + "learning_rate": 2.386635645734995e-06, + "loss": 0.0919, + "step": 426860 + }, + { + "epoch": 0.95, + "learning_rate": 2.3855171025256706e-06, + "loss": 0.0922, + "step": 426870 + }, + { + "epoch": 0.95, + "learning_rate": 2.3843985593163464e-06, + "loss": 0.091, + "step": 426880 + }, + { + "epoch": 0.95, + "learning_rate": 2.3832800161070222e-06, + "loss": 0.0932, + "step": 426890 + }, + { + "epoch": 0.95, + "learning_rate": 2.382161472897698e-06, + "loss": 0.0904, + "step": 426900 + }, + { + "epoch": 0.95, + "learning_rate": 2.381042929688374e-06, + "loss": 0.0904, + "step": 426910 + }, + { + "epoch": 0.95, + "learning_rate": 2.3799243864790497e-06, + "loss": 0.0925, + "step": 426920 + }, + { + "epoch": 0.95, + "learning_rate": 2.3788058432697255e-06, + "loss": 0.0931, + "step": 426930 + }, + { + "epoch": 0.95, + "learning_rate": 2.3776873000604013e-06, + "loss": 0.0949, + "step": 426940 + }, + { + "epoch": 0.95, + "learning_rate": 2.376568756851077e-06, + "loss": 0.0898, + "step": 426950 + }, + { + "epoch": 0.95, + "learning_rate": 2.3754502136417533e-06, + "loss": 0.0907, + "step": 426960 + }, + { + "epoch": 0.95, + "learning_rate": 2.3743316704324287e-06, + "loss": 0.0928, + "step": 426970 + }, + { + "epoch": 0.95, + "learning_rate": 2.373213127223105e-06, + "loss": 0.0888, + "step": 426980 + }, + { + "epoch": 0.95, + "learning_rate": 2.3720945840137803e-06, + "loss": 0.0916, + "step": 426990 + }, + { + "epoch": 0.95, + "learning_rate": 2.3709760408044566e-06, + "loss": 0.0937, + "step": 427000 + }, + { + "epoch": 0.95, + "learning_rate": 2.369857497595132e-06, + "loss": 0.0898, + "step": 427010 + }, + { + "epoch": 0.95, + "learning_rate": 2.368738954385808e-06, + "loss": 0.0916, + "step": 427020 + }, + { + "epoch": 0.95, + "learning_rate": 2.3676204111764836e-06, + "loss": 0.0895, + "step": 427030 + }, + { + "epoch": 0.95, + "learning_rate": 2.36650186796716e-06, + "loss": 0.0899, + "step": 427040 + }, + { + "epoch": 0.95, + "learning_rate": 2.365383324757835e-06, + "loss": 0.0887, + "step": 427050 + }, + { + "epoch": 0.95, + "learning_rate": 2.3642647815485114e-06, + "loss": 0.088, + "step": 427060 + }, + { + "epoch": 0.95, + "learning_rate": 2.3631462383391872e-06, + "loss": 0.0846, + "step": 427070 + }, + { + "epoch": 0.95, + "learning_rate": 2.362027695129863e-06, + "loss": 0.0896, + "step": 427080 + }, + { + "epoch": 0.95, + "learning_rate": 2.360909151920539e-06, + "loss": 0.0974, + "step": 427090 + }, + { + "epoch": 0.95, + "learning_rate": 2.3597906087112147e-06, + "loss": 0.0951, + "step": 427100 + }, + { + "epoch": 0.95, + "learning_rate": 2.3586720655018905e-06, + "loss": 0.0907, + "step": 427110 + }, + { + "epoch": 0.95, + "learning_rate": 2.3575535222925663e-06, + "loss": 0.0948, + "step": 427120 + }, + { + "epoch": 0.95, + "learning_rate": 2.356434979083242e-06, + "loss": 0.0925, + "step": 427130 + }, + { + "epoch": 0.95, + "learning_rate": 2.355316435873918e-06, + "loss": 0.0868, + "step": 427140 + }, + { + "epoch": 0.95, + "learning_rate": 2.3541978926645937e-06, + "loss": 0.0895, + "step": 427150 + }, + { + "epoch": 0.95, + "learning_rate": 2.3530793494552695e-06, + "loss": 0.0924, + "step": 427160 + }, + { + "epoch": 0.95, + "learning_rate": 2.3519608062459453e-06, + "loss": 0.0885, + "step": 427170 + }, + { + "epoch": 0.95, + "learning_rate": 2.350842263036621e-06, + "loss": 0.0876, + "step": 427180 + }, + { + "epoch": 0.95, + "learning_rate": 2.349723719827297e-06, + "loss": 0.0905, + "step": 427190 + }, + { + "epoch": 0.95, + "learning_rate": 2.3486051766179728e-06, + "loss": 0.0928, + "step": 427200 + }, + { + "epoch": 0.95, + "learning_rate": 2.3474866334086486e-06, + "loss": 0.0914, + "step": 427210 + }, + { + "epoch": 0.95, + "learning_rate": 2.3463680901993244e-06, + "loss": 0.0913, + "step": 427220 + }, + { + "epoch": 0.95, + "learning_rate": 2.34524954699e-06, + "loss": 0.0904, + "step": 427230 + }, + { + "epoch": 0.95, + "learning_rate": 2.344131003780676e-06, + "loss": 0.0938, + "step": 427240 + }, + { + "epoch": 0.95, + "learning_rate": 2.343012460571352e-06, + "loss": 0.0909, + "step": 427250 + }, + { + "epoch": 0.95, + "learning_rate": 2.341893917362028e-06, + "loss": 0.0924, + "step": 427260 + }, + { + "epoch": 0.95, + "learning_rate": 2.3407753741527034e-06, + "loss": 0.0905, + "step": 427270 + }, + { + "epoch": 0.95, + "learning_rate": 2.3396568309433797e-06, + "loss": 0.0892, + "step": 427280 + }, + { + "epoch": 0.95, + "learning_rate": 2.338538287734055e-06, + "loss": 0.0916, + "step": 427290 + }, + { + "epoch": 0.95, + "learning_rate": 2.3374197445247313e-06, + "loss": 0.0868, + "step": 427300 + }, + { + "epoch": 0.95, + "learning_rate": 2.3363012013154067e-06, + "loss": 0.0915, + "step": 427310 + }, + { + "epoch": 0.95, + "learning_rate": 2.335182658106083e-06, + "loss": 0.0917, + "step": 427320 + }, + { + "epoch": 0.95, + "learning_rate": 2.3340641148967583e-06, + "loss": 0.0938, + "step": 427330 + }, + { + "epoch": 0.95, + "learning_rate": 2.3329455716874345e-06, + "loss": 0.0935, + "step": 427340 + }, + { + "epoch": 0.95, + "learning_rate": 2.33182702847811e-06, + "loss": 0.0876, + "step": 427350 + }, + { + "epoch": 0.95, + "learning_rate": 2.330708485268786e-06, + "loss": 0.0917, + "step": 427360 + }, + { + "epoch": 0.95, + "learning_rate": 2.329589942059462e-06, + "loss": 0.0919, + "step": 427370 + }, + { + "epoch": 0.95, + "learning_rate": 2.3284713988501378e-06, + "loss": 0.0898, + "step": 427380 + }, + { + "epoch": 0.95, + "learning_rate": 2.3273528556408136e-06, + "loss": 0.0904, + "step": 427390 + }, + { + "epoch": 0.95, + "learning_rate": 2.3262343124314894e-06, + "loss": 0.0921, + "step": 427400 + }, + { + "epoch": 0.95, + "learning_rate": 2.325115769222165e-06, + "loss": 0.095, + "step": 427410 + }, + { + "epoch": 0.95, + "learning_rate": 2.323997226012841e-06, + "loss": 0.0929, + "step": 427420 + }, + { + "epoch": 0.95, + "learning_rate": 2.322878682803517e-06, + "loss": 0.0942, + "step": 427430 + }, + { + "epoch": 0.95, + "learning_rate": 2.3217601395941926e-06, + "loss": 0.0913, + "step": 427440 + }, + { + "epoch": 0.95, + "learning_rate": 2.3206415963848685e-06, + "loss": 0.09, + "step": 427450 + }, + { + "epoch": 0.95, + "learning_rate": 2.3195230531755443e-06, + "loss": 0.0904, + "step": 427460 + }, + { + "epoch": 0.95, + "learning_rate": 2.31840450996622e-06, + "loss": 0.0895, + "step": 427470 + }, + { + "epoch": 0.95, + "learning_rate": 2.317285966756896e-06, + "loss": 0.0916, + "step": 427480 + }, + { + "epoch": 0.95, + "learning_rate": 2.3161674235475717e-06, + "loss": 0.0932, + "step": 427490 + }, + { + "epoch": 0.95, + "learning_rate": 2.3150488803382475e-06, + "loss": 0.0925, + "step": 427500 + }, + { + "epoch": 0.95, + "learning_rate": 2.3139303371289233e-06, + "loss": 0.0872, + "step": 427510 + }, + { + "epoch": 0.95, + "learning_rate": 2.312811793919599e-06, + "loss": 0.0887, + "step": 427520 + }, + { + "epoch": 0.95, + "learning_rate": 2.311693250710275e-06, + "loss": 0.0913, + "step": 427530 + }, + { + "epoch": 0.95, + "learning_rate": 2.3105747075009507e-06, + "loss": 0.0897, + "step": 427540 + }, + { + "epoch": 0.95, + "learning_rate": 2.3094561642916266e-06, + "loss": 0.085, + "step": 427550 + }, + { + "epoch": 0.95, + "learning_rate": 2.3083376210823028e-06, + "loss": 0.0907, + "step": 427560 + }, + { + "epoch": 0.95, + "learning_rate": 2.307219077872978e-06, + "loss": 0.0916, + "step": 427570 + }, + { + "epoch": 0.95, + "learning_rate": 2.3061005346636544e-06, + "loss": 0.0874, + "step": 427580 + }, + { + "epoch": 0.95, + "learning_rate": 2.30498199145433e-06, + "loss": 0.0971, + "step": 427590 + }, + { + "epoch": 0.95, + "learning_rate": 2.303863448245006e-06, + "loss": 0.0891, + "step": 427600 + }, + { + "epoch": 0.95, + "learning_rate": 2.3027449050356814e-06, + "loss": 0.0884, + "step": 427610 + }, + { + "epoch": 0.95, + "learning_rate": 2.3016263618263576e-06, + "loss": 0.0925, + "step": 427620 + }, + { + "epoch": 0.95, + "learning_rate": 2.300507818617033e-06, + "loss": 0.0912, + "step": 427630 + }, + { + "epoch": 0.95, + "learning_rate": 2.2993892754077093e-06, + "loss": 0.0878, + "step": 427640 + }, + { + "epoch": 0.95, + "learning_rate": 2.2982707321983847e-06, + "loss": 0.0838, + "step": 427650 + }, + { + "epoch": 0.95, + "learning_rate": 2.297152188989061e-06, + "loss": 0.0915, + "step": 427660 + }, + { + "epoch": 0.95, + "learning_rate": 2.2960336457797367e-06, + "loss": 0.0921, + "step": 427670 + }, + { + "epoch": 0.95, + "learning_rate": 2.2949151025704125e-06, + "loss": 0.0951, + "step": 427680 + }, + { + "epoch": 0.95, + "learning_rate": 2.2937965593610883e-06, + "loss": 0.0899, + "step": 427690 + }, + { + "epoch": 0.95, + "learning_rate": 2.292678016151764e-06, + "loss": 0.0944, + "step": 427700 + }, + { + "epoch": 0.95, + "learning_rate": 2.29155947294244e-06, + "loss": 0.0921, + "step": 427710 + }, + { + "epoch": 0.95, + "learning_rate": 2.2904409297331157e-06, + "loss": 0.0935, + "step": 427720 + }, + { + "epoch": 0.95, + "learning_rate": 2.2893223865237916e-06, + "loss": 0.0896, + "step": 427730 + }, + { + "epoch": 0.95, + "learning_rate": 2.2882038433144674e-06, + "loss": 0.0919, + "step": 427740 + }, + { + "epoch": 0.95, + "learning_rate": 2.287085300105143e-06, + "loss": 0.095, + "step": 427750 + }, + { + "epoch": 0.95, + "learning_rate": 2.285966756895819e-06, + "loss": 0.0889, + "step": 427760 + }, + { + "epoch": 0.95, + "learning_rate": 2.284848213686495e-06, + "loss": 0.0906, + "step": 427770 + }, + { + "epoch": 0.95, + "learning_rate": 2.2837296704771706e-06, + "loss": 0.0952, + "step": 427780 + }, + { + "epoch": 0.95, + "learning_rate": 2.2826111272678464e-06, + "loss": 0.0892, + "step": 427790 + }, + { + "epoch": 0.95, + "learning_rate": 2.2814925840585222e-06, + "loss": 0.092, + "step": 427800 + }, + { + "epoch": 0.95, + "learning_rate": 2.280374040849198e-06, + "loss": 0.089, + "step": 427810 + }, + { + "epoch": 0.95, + "learning_rate": 2.279255497639874e-06, + "loss": 0.0919, + "step": 427820 + }, + { + "epoch": 0.95, + "learning_rate": 2.2781369544305497e-06, + "loss": 0.0959, + "step": 427830 + }, + { + "epoch": 0.95, + "learning_rate": 2.277018411221226e-06, + "loss": 0.0905, + "step": 427840 + }, + { + "epoch": 0.96, + "learning_rate": 2.2758998680119013e-06, + "loss": 0.0922, + "step": 427850 + }, + { + "epoch": 0.96, + "learning_rate": 2.2747813248025775e-06, + "loss": 0.0862, + "step": 427860 + }, + { + "epoch": 0.96, + "learning_rate": 2.273662781593253e-06, + "loss": 0.0889, + "step": 427870 + }, + { + "epoch": 0.96, + "learning_rate": 2.272544238383929e-06, + "loss": 0.0943, + "step": 427880 + }, + { + "epoch": 0.96, + "learning_rate": 2.2714256951746045e-06, + "loss": 0.0919, + "step": 427890 + }, + { + "epoch": 0.96, + "learning_rate": 2.2703071519652808e-06, + "loss": 0.0915, + "step": 427900 + }, + { + "epoch": 0.96, + "learning_rate": 2.269188608755956e-06, + "loss": 0.0887, + "step": 427910 + }, + { + "epoch": 0.96, + "learning_rate": 2.2680700655466324e-06, + "loss": 0.0919, + "step": 427920 + }, + { + "epoch": 0.96, + "learning_rate": 2.2669515223373078e-06, + "loss": 0.0895, + "step": 427930 + }, + { + "epoch": 0.96, + "learning_rate": 2.265832979127984e-06, + "loss": 0.0905, + "step": 427940 + }, + { + "epoch": 0.96, + "learning_rate": 2.2647144359186594e-06, + "loss": 0.0893, + "step": 427950 + }, + { + "epoch": 0.96, + "learning_rate": 2.2635958927093356e-06, + "loss": 0.0907, + "step": 427960 + }, + { + "epoch": 0.96, + "learning_rate": 2.2624773495000114e-06, + "loss": 0.0895, + "step": 427970 + }, + { + "epoch": 0.96, + "learning_rate": 2.2613588062906872e-06, + "loss": 0.0882, + "step": 427980 + }, + { + "epoch": 0.96, + "learning_rate": 2.260240263081363e-06, + "loss": 0.0872, + "step": 427990 + }, + { + "epoch": 0.96, + "learning_rate": 2.259121719872039e-06, + "loss": 0.0908, + "step": 428000 + }, + { + "epoch": 0.96, + "learning_rate": 2.2580031766627147e-06, + "loss": 0.0901, + "step": 428010 + }, + { + "epoch": 0.96, + "learning_rate": 2.2568846334533905e-06, + "loss": 0.0883, + "step": 428020 + }, + { + "epoch": 0.96, + "learning_rate": 2.2557660902440663e-06, + "loss": 0.0943, + "step": 428030 + }, + { + "epoch": 0.96, + "learning_rate": 2.254647547034742e-06, + "loss": 0.0904, + "step": 428040 + }, + { + "epoch": 0.96, + "learning_rate": 2.253529003825418e-06, + "loss": 0.0917, + "step": 428050 + }, + { + "epoch": 0.96, + "learning_rate": 2.2524104606160937e-06, + "loss": 0.0907, + "step": 428060 + }, + { + "epoch": 0.96, + "learning_rate": 2.2512919174067695e-06, + "loss": 0.0938, + "step": 428070 + }, + { + "epoch": 0.96, + "learning_rate": 2.2501733741974453e-06, + "loss": 0.0884, + "step": 428080 + }, + { + "epoch": 0.96, + "learning_rate": 2.249054830988121e-06, + "loss": 0.0891, + "step": 428090 + }, + { + "epoch": 0.96, + "learning_rate": 2.247936287778797e-06, + "loss": 0.0919, + "step": 428100 + }, + { + "epoch": 0.96, + "learning_rate": 2.2468177445694728e-06, + "loss": 0.0918, + "step": 428110 + }, + { + "epoch": 0.96, + "learning_rate": 2.2456992013601486e-06, + "loss": 0.0912, + "step": 428120 + }, + { + "epoch": 0.96, + "learning_rate": 2.2445806581508244e-06, + "loss": 0.0979, + "step": 428130 + }, + { + "epoch": 0.96, + "learning_rate": 2.2434621149415006e-06, + "loss": 0.0917, + "step": 428140 + }, + { + "epoch": 0.96, + "learning_rate": 2.242343571732176e-06, + "loss": 0.0881, + "step": 428150 + }, + { + "epoch": 0.96, + "learning_rate": 2.2413368828437844e-06, + "loss": 0.0967, + "step": 428160 + }, + { + "epoch": 0.96, + "learning_rate": 2.24021833963446e-06, + "loss": 0.0936, + "step": 428170 + }, + { + "epoch": 0.96, + "learning_rate": 2.239099796425136e-06, + "loss": 0.0922, + "step": 428180 + }, + { + "epoch": 0.96, + "learning_rate": 2.237981253215812e-06, + "loss": 0.0914, + "step": 428190 + }, + { + "epoch": 0.96, + "learning_rate": 2.2368627100064876e-06, + "loss": 0.0892, + "step": 428200 + }, + { + "epoch": 0.96, + "learning_rate": 2.2357441667971634e-06, + "loss": 0.0893, + "step": 428210 + }, + { + "epoch": 0.96, + "learning_rate": 2.2346256235878392e-06, + "loss": 0.0921, + "step": 428220 + }, + { + "epoch": 0.96, + "learning_rate": 2.2335070803785155e-06, + "loss": 0.0891, + "step": 428230 + }, + { + "epoch": 0.96, + "learning_rate": 2.232388537169191e-06, + "loss": 0.0912, + "step": 428240 + }, + { + "epoch": 0.96, + "learning_rate": 2.231269993959867e-06, + "loss": 0.091, + "step": 428250 + }, + { + "epoch": 0.96, + "learning_rate": 2.2301514507505425e-06, + "loss": 0.0869, + "step": 428260 + }, + { + "epoch": 0.96, + "learning_rate": 2.2290329075412187e-06, + "loss": 0.0897, + "step": 428270 + }, + { + "epoch": 0.96, + "learning_rate": 2.227914364331894e-06, + "loss": 0.0983, + "step": 428280 + }, + { + "epoch": 0.96, + "learning_rate": 2.2267958211225703e-06, + "loss": 0.0894, + "step": 428290 + }, + { + "epoch": 0.96, + "learning_rate": 2.2256772779132457e-06, + "loss": 0.0907, + "step": 428300 + }, + { + "epoch": 0.96, + "learning_rate": 2.224558734703922e-06, + "loss": 0.0938, + "step": 428310 + }, + { + "epoch": 0.96, + "learning_rate": 2.2234401914945973e-06, + "loss": 0.0905, + "step": 428320 + }, + { + "epoch": 0.96, + "learning_rate": 2.2223216482852736e-06, + "loss": 0.0976, + "step": 428330 + }, + { + "epoch": 0.96, + "learning_rate": 2.2212031050759494e-06, + "loss": 0.0938, + "step": 428340 + }, + { + "epoch": 0.96, + "learning_rate": 2.220084561866625e-06, + "loss": 0.0975, + "step": 428350 + }, + { + "epoch": 0.96, + "learning_rate": 2.218966018657301e-06, + "loss": 0.0937, + "step": 428360 + }, + { + "epoch": 0.96, + "learning_rate": 2.217847475447977e-06, + "loss": 0.0945, + "step": 428370 + }, + { + "epoch": 0.96, + "learning_rate": 2.2167289322386526e-06, + "loss": 0.0921, + "step": 428380 + }, + { + "epoch": 0.96, + "learning_rate": 2.2156103890293284e-06, + "loss": 0.0932, + "step": 428390 + }, + { + "epoch": 0.96, + "learning_rate": 2.2144918458200042e-06, + "loss": 0.0932, + "step": 428400 + }, + { + "epoch": 0.96, + "learning_rate": 2.21337330261068e-06, + "loss": 0.0897, + "step": 428410 + }, + { + "epoch": 0.96, + "learning_rate": 2.212254759401356e-06, + "loss": 0.0941, + "step": 428420 + }, + { + "epoch": 0.96, + "learning_rate": 2.2111362161920317e-06, + "loss": 0.0961, + "step": 428430 + }, + { + "epoch": 0.96, + "learning_rate": 2.2100176729827075e-06, + "loss": 0.09, + "step": 428440 + }, + { + "epoch": 0.96, + "learning_rate": 2.2088991297733833e-06, + "loss": 0.0899, + "step": 428450 + }, + { + "epoch": 0.96, + "learning_rate": 2.207780586564059e-06, + "loss": 0.0923, + "step": 428460 + }, + { + "epoch": 0.96, + "learning_rate": 2.206662043354735e-06, + "loss": 0.0925, + "step": 428470 + }, + { + "epoch": 0.96, + "learning_rate": 2.2055435001454107e-06, + "loss": 0.0933, + "step": 428480 + }, + { + "epoch": 0.96, + "learning_rate": 2.2044249569360865e-06, + "loss": 0.0923, + "step": 428490 + }, + { + "epoch": 0.96, + "learning_rate": 2.2033064137267623e-06, + "loss": 0.0931, + "step": 428500 + }, + { + "epoch": 0.96, + "learning_rate": 2.202187870517438e-06, + "loss": 0.0888, + "step": 428510 + }, + { + "epoch": 0.96, + "learning_rate": 2.201069327308114e-06, + "loss": 0.089, + "step": 428520 + }, + { + "epoch": 0.96, + "learning_rate": 2.19995078409879e-06, + "loss": 0.0922, + "step": 428530 + }, + { + "epoch": 0.96, + "learning_rate": 2.1988322408894656e-06, + "loss": 0.0918, + "step": 428540 + }, + { + "epoch": 0.96, + "learning_rate": 2.197713697680142e-06, + "loss": 0.09, + "step": 428550 + }, + { + "epoch": 0.96, + "learning_rate": 2.196595154470817e-06, + "loss": 0.0891, + "step": 428560 + }, + { + "epoch": 0.96, + "learning_rate": 2.1954766112614934e-06, + "loss": 0.0915, + "step": 428570 + }, + { + "epoch": 0.96, + "learning_rate": 2.194358068052169e-06, + "loss": 0.0884, + "step": 428580 + }, + { + "epoch": 0.96, + "learning_rate": 2.193239524842845e-06, + "loss": 0.0904, + "step": 428590 + }, + { + "epoch": 0.96, + "learning_rate": 2.1921209816335204e-06, + "loss": 0.091, + "step": 428600 + }, + { + "epoch": 0.96, + "learning_rate": 2.1910024384241967e-06, + "loss": 0.0932, + "step": 428610 + }, + { + "epoch": 0.96, + "learning_rate": 2.189883895214872e-06, + "loss": 0.0928, + "step": 428620 + }, + { + "epoch": 0.96, + "learning_rate": 2.1887653520055483e-06, + "loss": 0.0909, + "step": 428630 + }, + { + "epoch": 0.96, + "learning_rate": 2.187646808796224e-06, + "loss": 0.0918, + "step": 428640 + }, + { + "epoch": 0.96, + "learning_rate": 2.1865282655869e-06, + "loss": 0.0916, + "step": 428650 + }, + { + "epoch": 0.96, + "learning_rate": 2.1854097223775757e-06, + "loss": 0.0925, + "step": 428660 + }, + { + "epoch": 0.96, + "learning_rate": 2.1842911791682515e-06, + "loss": 0.0863, + "step": 428670 + }, + { + "epoch": 0.96, + "learning_rate": 2.1831726359589273e-06, + "loss": 0.0915, + "step": 428680 + }, + { + "epoch": 0.96, + "learning_rate": 2.182054092749603e-06, + "loss": 0.0944, + "step": 428690 + }, + { + "epoch": 0.96, + "learning_rate": 2.180935549540279e-06, + "loss": 0.0903, + "step": 428700 + }, + { + "epoch": 0.96, + "learning_rate": 2.1798170063309548e-06, + "loss": 0.0885, + "step": 428710 + }, + { + "epoch": 0.96, + "learning_rate": 2.1786984631216306e-06, + "loss": 0.0962, + "step": 428720 + }, + { + "epoch": 0.96, + "learning_rate": 2.1775799199123064e-06, + "loss": 0.0914, + "step": 428730 + }, + { + "epoch": 0.96, + "learning_rate": 2.176461376702982e-06, + "loss": 0.0903, + "step": 428740 + }, + { + "epoch": 0.96, + "learning_rate": 2.175342833493658e-06, + "loss": 0.0894, + "step": 428750 + }, + { + "epoch": 0.96, + "learning_rate": 2.174224290284334e-06, + "loss": 0.0959, + "step": 428760 + }, + { + "epoch": 0.96, + "learning_rate": 2.1731057470750096e-06, + "loss": 0.0909, + "step": 428770 + }, + { + "epoch": 0.96, + "learning_rate": 2.1719872038656854e-06, + "loss": 0.0921, + "step": 428780 + }, + { + "epoch": 0.96, + "learning_rate": 2.1708686606563612e-06, + "loss": 0.0917, + "step": 428790 + }, + { + "epoch": 0.96, + "learning_rate": 2.169750117447037e-06, + "loss": 0.0936, + "step": 428800 + }, + { + "epoch": 0.96, + "learning_rate": 2.168631574237713e-06, + "loss": 0.09, + "step": 428810 + }, + { + "epoch": 0.96, + "learning_rate": 2.1675130310283887e-06, + "loss": 0.0895, + "step": 428820 + }, + { + "epoch": 0.96, + "learning_rate": 2.166394487819065e-06, + "loss": 0.0923, + "step": 428830 + }, + { + "epoch": 0.96, + "learning_rate": 2.1652759446097403e-06, + "loss": 0.0895, + "step": 428840 + }, + { + "epoch": 0.96, + "learning_rate": 2.1641574014004165e-06, + "loss": 0.0922, + "step": 428850 + }, + { + "epoch": 0.96, + "learning_rate": 2.163038858191092e-06, + "loss": 0.0906, + "step": 428860 + }, + { + "epoch": 0.96, + "learning_rate": 2.161920314981768e-06, + "loss": 0.0927, + "step": 428870 + }, + { + "epoch": 0.96, + "learning_rate": 2.1608017717724435e-06, + "loss": 0.0903, + "step": 428880 + }, + { + "epoch": 0.96, + "learning_rate": 2.1596832285631198e-06, + "loss": 0.0911, + "step": 428890 + }, + { + "epoch": 0.96, + "learning_rate": 2.158564685353795e-06, + "loss": 0.0886, + "step": 428900 + }, + { + "epoch": 0.96, + "learning_rate": 2.1574461421444714e-06, + "loss": 0.0939, + "step": 428910 + }, + { + "epoch": 0.96, + "learning_rate": 2.1563275989351468e-06, + "loss": 0.0967, + "step": 428920 + }, + { + "epoch": 0.96, + "learning_rate": 2.155209055725823e-06, + "loss": 0.0963, + "step": 428930 + }, + { + "epoch": 0.96, + "learning_rate": 2.154090512516499e-06, + "loss": 0.0908, + "step": 428940 + }, + { + "epoch": 0.96, + "learning_rate": 2.1529719693071746e-06, + "loss": 0.0873, + "step": 428950 + }, + { + "epoch": 0.96, + "learning_rate": 2.1518534260978504e-06, + "loss": 0.0896, + "step": 428960 + }, + { + "epoch": 0.96, + "learning_rate": 2.1507348828885262e-06, + "loss": 0.0909, + "step": 428970 + }, + { + "epoch": 0.96, + "learning_rate": 2.149616339679202e-06, + "loss": 0.091, + "step": 428980 + }, + { + "epoch": 0.96, + "learning_rate": 2.148497796469878e-06, + "loss": 0.093, + "step": 428990 + }, + { + "epoch": 0.96, + "learning_rate": 2.1473792532605537e-06, + "loss": 0.0941, + "step": 429000 + }, + { + "epoch": 0.96, + "learning_rate": 2.146260710051229e-06, + "loss": 0.0904, + "step": 429010 + }, + { + "epoch": 0.96, + "learning_rate": 2.1451421668419053e-06, + "loss": 0.0885, + "step": 429020 + }, + { + "epoch": 0.96, + "learning_rate": 2.1440236236325807e-06, + "loss": 0.0968, + "step": 429030 + }, + { + "epoch": 0.96, + "learning_rate": 2.142905080423257e-06, + "loss": 0.0865, + "step": 429040 + }, + { + "epoch": 0.96, + "learning_rate": 2.1417865372139323e-06, + "loss": 0.0896, + "step": 429050 + }, + { + "epoch": 0.96, + "learning_rate": 2.1406679940046085e-06, + "loss": 0.0911, + "step": 429060 + }, + { + "epoch": 0.96, + "learning_rate": 2.1395494507952844e-06, + "loss": 0.0905, + "step": 429070 + }, + { + "epoch": 0.96, + "learning_rate": 2.13843090758596e-06, + "loss": 0.0918, + "step": 429080 + }, + { + "epoch": 0.96, + "learning_rate": 2.137312364376636e-06, + "loss": 0.0913, + "step": 429090 + }, + { + "epoch": 0.96, + "learning_rate": 2.1361938211673118e-06, + "loss": 0.0912, + "step": 429100 + }, + { + "epoch": 0.96, + "learning_rate": 2.1350752779579876e-06, + "loss": 0.0914, + "step": 429110 + }, + { + "epoch": 0.96, + "learning_rate": 2.1339567347486634e-06, + "loss": 0.0926, + "step": 429120 + }, + { + "epoch": 0.96, + "learning_rate": 2.132838191539339e-06, + "loss": 0.0877, + "step": 429130 + }, + { + "epoch": 0.96, + "learning_rate": 2.131719648330015e-06, + "loss": 0.0909, + "step": 429140 + }, + { + "epoch": 0.96, + "learning_rate": 2.130601105120691e-06, + "loss": 0.0866, + "step": 429150 + }, + { + "epoch": 0.96, + "learning_rate": 2.1294825619113666e-06, + "loss": 0.0878, + "step": 429160 + }, + { + "epoch": 0.96, + "learning_rate": 2.1283640187020425e-06, + "loss": 0.0931, + "step": 429170 + }, + { + "epoch": 0.96, + "learning_rate": 2.1272454754927183e-06, + "loss": 0.09, + "step": 429180 + }, + { + "epoch": 0.96, + "learning_rate": 2.126126932283394e-06, + "loss": 0.0889, + "step": 429190 + }, + { + "epoch": 0.96, + "learning_rate": 2.12500838907407e-06, + "loss": 0.0917, + "step": 429200 + }, + { + "epoch": 0.96, + "learning_rate": 2.1238898458647457e-06, + "loss": 0.0925, + "step": 429210 + }, + { + "epoch": 0.96, + "learning_rate": 2.1227713026554215e-06, + "loss": 0.0941, + "step": 429220 + }, + { + "epoch": 0.96, + "learning_rate": 2.1216527594460973e-06, + "loss": 0.0924, + "step": 429230 + }, + { + "epoch": 0.96, + "learning_rate": 2.1205342162367735e-06, + "loss": 0.0938, + "step": 429240 + }, + { + "epoch": 0.96, + "learning_rate": 2.119415673027449e-06, + "loss": 0.0933, + "step": 429250 + }, + { + "epoch": 0.96, + "learning_rate": 2.118297129818125e-06, + "loss": 0.0941, + "step": 429260 + }, + { + "epoch": 0.96, + "learning_rate": 2.1171785866088006e-06, + "loss": 0.0947, + "step": 429270 + }, + { + "epoch": 0.96, + "learning_rate": 2.1160600433994768e-06, + "loss": 0.0936, + "step": 429280 + }, + { + "epoch": 0.96, + "learning_rate": 2.114941500190152e-06, + "loss": 0.0958, + "step": 429290 + }, + { + "epoch": 0.96, + "learning_rate": 2.1138229569808284e-06, + "loss": 0.0885, + "step": 429300 + }, + { + "epoch": 0.96, + "learning_rate": 2.112704413771504e-06, + "loss": 0.0922, + "step": 429310 + }, + { + "epoch": 0.96, + "learning_rate": 2.11158587056218e-06, + "loss": 0.0937, + "step": 429320 + }, + { + "epoch": 0.96, + "learning_rate": 2.1104673273528554e-06, + "loss": 0.092, + "step": 429330 + }, + { + "epoch": 0.96, + "learning_rate": 2.1093487841435316e-06, + "loss": 0.0901, + "step": 429340 + }, + { + "epoch": 0.96, + "learning_rate": 2.108230240934207e-06, + "loss": 0.0907, + "step": 429350 + }, + { + "epoch": 0.96, + "learning_rate": 2.1071116977248833e-06, + "loss": 0.0916, + "step": 429360 + }, + { + "epoch": 0.96, + "learning_rate": 2.105993154515559e-06, + "loss": 0.0906, + "step": 429370 + }, + { + "epoch": 0.96, + "learning_rate": 2.104874611306235e-06, + "loss": 0.0913, + "step": 429380 + }, + { + "epoch": 0.96, + "learning_rate": 2.1037560680969107e-06, + "loss": 0.0888, + "step": 429390 + }, + { + "epoch": 0.96, + "learning_rate": 2.1026375248875865e-06, + "loss": 0.088, + "step": 429400 + }, + { + "epoch": 0.96, + "learning_rate": 2.1015189816782623e-06, + "loss": 0.0889, + "step": 429410 + }, + { + "epoch": 0.96, + "learning_rate": 2.100400438468938e-06, + "loss": 0.0882, + "step": 429420 + }, + { + "epoch": 0.96, + "learning_rate": 2.099281895259614e-06, + "loss": 0.0945, + "step": 429430 + }, + { + "epoch": 0.96, + "learning_rate": 2.0981633520502897e-06, + "loss": 0.0934, + "step": 429440 + }, + { + "epoch": 0.96, + "learning_rate": 2.0970448088409656e-06, + "loss": 0.0883, + "step": 429450 + }, + { + "epoch": 0.96, + "learning_rate": 2.0959262656316414e-06, + "loss": 0.0915, + "step": 429460 + }, + { + "epoch": 0.96, + "learning_rate": 2.094807722422317e-06, + "loss": 0.0903, + "step": 429470 + }, + { + "epoch": 0.96, + "learning_rate": 2.093689179212993e-06, + "loss": 0.0888, + "step": 429480 + }, + { + "epoch": 0.96, + "learning_rate": 2.092570636003669e-06, + "loss": 0.0937, + "step": 429490 + }, + { + "epoch": 0.96, + "learning_rate": 2.0914520927943446e-06, + "loss": 0.0929, + "step": 429500 + }, + { + "epoch": 0.96, + "learning_rate": 2.0903335495850204e-06, + "loss": 0.0947, + "step": 429510 + }, + { + "epoch": 0.96, + "learning_rate": 2.0892150063756962e-06, + "loss": 0.0878, + "step": 429520 + }, + { + "epoch": 0.96, + "learning_rate": 2.088096463166372e-06, + "loss": 0.0897, + "step": 429530 + }, + { + "epoch": 0.96, + "learning_rate": 2.0869779199570483e-06, + "loss": 0.0907, + "step": 429540 + }, + { + "epoch": 0.96, + "learning_rate": 2.0858593767477237e-06, + "loss": 0.0873, + "step": 429550 + }, + { + "epoch": 0.96, + "learning_rate": 2.0847408335384e-06, + "loss": 0.0871, + "step": 429560 + }, + { + "epoch": 0.96, + "learning_rate": 2.0836222903290753e-06, + "loss": 0.089, + "step": 429570 + }, + { + "epoch": 0.96, + "learning_rate": 2.0825037471197515e-06, + "loss": 0.0931, + "step": 429580 + }, + { + "epoch": 0.96, + "learning_rate": 2.081385203910427e-06, + "loss": 0.0908, + "step": 429590 + }, + { + "epoch": 0.96, + "learning_rate": 2.080266660701103e-06, + "loss": 0.0903, + "step": 429600 + }, + { + "epoch": 0.96, + "learning_rate": 2.0791481174917785e-06, + "loss": 0.091, + "step": 429610 + }, + { + "epoch": 0.96, + "learning_rate": 2.0780295742824548e-06, + "loss": 0.088, + "step": 429620 + }, + { + "epoch": 0.96, + "learning_rate": 2.07691103107313e-06, + "loss": 0.0906, + "step": 429630 + }, + { + "epoch": 0.96, + "learning_rate": 2.0757924878638064e-06, + "loss": 0.092, + "step": 429640 + }, + { + "epoch": 0.96, + "learning_rate": 2.0746739446544818e-06, + "loss": 0.0927, + "step": 429650 + }, + { + "epoch": 0.96, + "learning_rate": 2.073555401445158e-06, + "loss": 0.0936, + "step": 429660 + }, + { + "epoch": 0.96, + "learning_rate": 2.072436858235834e-06, + "loss": 0.0923, + "step": 429670 + }, + { + "epoch": 0.96, + "learning_rate": 2.0713183150265096e-06, + "loss": 0.0912, + "step": 429680 + }, + { + "epoch": 0.96, + "learning_rate": 2.0701997718171854e-06, + "loss": 0.0933, + "step": 429690 + }, + { + "epoch": 0.96, + "learning_rate": 2.0690812286078612e-06, + "loss": 0.0922, + "step": 429700 + }, + { + "epoch": 0.96, + "learning_rate": 2.067962685398537e-06, + "loss": 0.0904, + "step": 429710 + }, + { + "epoch": 0.96, + "learning_rate": 2.066844142189213e-06, + "loss": 0.0887, + "step": 429720 + }, + { + "epoch": 0.96, + "learning_rate": 2.0657255989798887e-06, + "loss": 0.0884, + "step": 429730 + }, + { + "epoch": 0.96, + "learning_rate": 2.0646070557705645e-06, + "loss": 0.0938, + "step": 429740 + }, + { + "epoch": 0.96, + "learning_rate": 2.0634885125612403e-06, + "loss": 0.0903, + "step": 429750 + }, + { + "epoch": 0.96, + "learning_rate": 2.062369969351916e-06, + "loss": 0.0905, + "step": 429760 + }, + { + "epoch": 0.96, + "learning_rate": 2.061251426142592e-06, + "loss": 0.0929, + "step": 429770 + }, + { + "epoch": 0.96, + "learning_rate": 2.0601328829332677e-06, + "loss": 0.0905, + "step": 429780 + }, + { + "epoch": 0.96, + "learning_rate": 2.0590143397239435e-06, + "loss": 0.0902, + "step": 429790 + }, + { + "epoch": 0.96, + "learning_rate": 2.0578957965146193e-06, + "loss": 0.0985, + "step": 429800 + }, + { + "epoch": 0.96, + "learning_rate": 2.056777253305295e-06, + "loss": 0.0917, + "step": 429810 + }, + { + "epoch": 0.96, + "learning_rate": 2.055658710095971e-06, + "loss": 0.0927, + "step": 429820 + }, + { + "epoch": 0.96, + "learning_rate": 2.0545401668866468e-06, + "loss": 0.0929, + "step": 429830 + }, + { + "epoch": 0.96, + "learning_rate": 2.053421623677323e-06, + "loss": 0.0899, + "step": 429840 + }, + { + "epoch": 0.96, + "learning_rate": 2.0523030804679984e-06, + "loss": 0.09, + "step": 429850 + }, + { + "epoch": 0.96, + "learning_rate": 2.0511845372586746e-06, + "loss": 0.0921, + "step": 429860 + }, + { + "epoch": 0.96, + "learning_rate": 2.05006599404935e-06, + "loss": 0.0923, + "step": 429870 + }, + { + "epoch": 0.96, + "learning_rate": 2.0489474508400262e-06, + "loss": 0.0938, + "step": 429880 + }, + { + "epoch": 0.96, + "learning_rate": 2.0478289076307016e-06, + "loss": 0.092, + "step": 429890 + }, + { + "epoch": 0.96, + "learning_rate": 2.046710364421378e-06, + "loss": 0.0926, + "step": 429900 + }, + { + "epoch": 0.96, + "learning_rate": 2.0455918212120532e-06, + "loss": 0.0887, + "step": 429910 + }, + { + "epoch": 0.96, + "learning_rate": 2.0444732780027295e-06, + "loss": 0.0892, + "step": 429920 + }, + { + "epoch": 0.96, + "learning_rate": 2.043354734793405e-06, + "loss": 0.0895, + "step": 429930 + }, + { + "epoch": 0.96, + "learning_rate": 2.042236191584081e-06, + "loss": 0.0898, + "step": 429940 + }, + { + "epoch": 0.96, + "learning_rate": 2.0411176483747565e-06, + "loss": 0.0909, + "step": 429950 + }, + { + "epoch": 0.96, + "learning_rate": 2.0399991051654327e-06, + "loss": 0.0905, + "step": 429960 + }, + { + "epoch": 0.96, + "learning_rate": 2.0388805619561085e-06, + "loss": 0.0962, + "step": 429970 + }, + { + "epoch": 0.96, + "learning_rate": 2.0377620187467843e-06, + "loss": 0.0911, + "step": 429980 + }, + { + "epoch": 0.96, + "learning_rate": 2.03664347553746e-06, + "loss": 0.0906, + "step": 429990 + }, + { + "epoch": 0.96, + "learning_rate": 2.035524932328136e-06, + "loss": 0.0935, + "step": 430000 + }, + { + "epoch": 0.96, + "learning_rate": 2.0344063891188118e-06, + "loss": 0.0904, + "step": 430010 + }, + { + "epoch": 0.96, + "learning_rate": 2.0332878459094876e-06, + "loss": 0.0925, + "step": 430020 + }, + { + "epoch": 0.96, + "learning_rate": 2.0321693027001634e-06, + "loss": 0.0902, + "step": 430030 + }, + { + "epoch": 0.96, + "learning_rate": 2.031050759490839e-06, + "loss": 0.0899, + "step": 430040 + }, + { + "epoch": 0.96, + "learning_rate": 2.029932216281515e-06, + "loss": 0.088, + "step": 430050 + }, + { + "epoch": 0.96, + "learning_rate": 2.028813673072191e-06, + "loss": 0.0902, + "step": 430060 + }, + { + "epoch": 0.96, + "learning_rate": 2.0276951298628666e-06, + "loss": 0.0898, + "step": 430070 + }, + { + "epoch": 0.96, + "learning_rate": 2.0265765866535424e-06, + "loss": 0.0908, + "step": 430080 + }, + { + "epoch": 0.96, + "learning_rate": 2.0254580434442183e-06, + "loss": 0.0889, + "step": 430090 + }, + { + "epoch": 0.96, + "learning_rate": 2.024339500234894e-06, + "loss": 0.0914, + "step": 430100 + }, + { + "epoch": 0.96, + "learning_rate": 2.02322095702557e-06, + "loss": 0.0905, + "step": 430110 + }, + { + "epoch": 0.96, + "learning_rate": 2.0221024138162457e-06, + "loss": 0.092, + "step": 430120 + }, + { + "epoch": 0.96, + "learning_rate": 2.0209838706069215e-06, + "loss": 0.093, + "step": 430130 + }, + { + "epoch": 0.96, + "learning_rate": 2.0198653273975977e-06, + "loss": 0.0919, + "step": 430140 + }, + { + "epoch": 0.96, + "learning_rate": 2.018746784188273e-06, + "loss": 0.0914, + "step": 430150 + }, + { + "epoch": 0.96, + "learning_rate": 2.0176282409789493e-06, + "loss": 0.0887, + "step": 430160 + }, + { + "epoch": 0.96, + "learning_rate": 2.0165096977696247e-06, + "loss": 0.092, + "step": 430170 + }, + { + "epoch": 0.96, + "learning_rate": 2.015391154560301e-06, + "loss": 0.0944, + "step": 430180 + }, + { + "epoch": 0.96, + "learning_rate": 2.014384465671909e-06, + "loss": 0.0918, + "step": 430190 + }, + { + "epoch": 0.96, + "learning_rate": 2.0132659224625847e-06, + "loss": 0.0908, + "step": 430200 + }, + { + "epoch": 0.96, + "learning_rate": 2.012147379253261e-06, + "loss": 0.0895, + "step": 430210 + }, + { + "epoch": 0.96, + "learning_rate": 2.0110288360439363e-06, + "loss": 0.0894, + "step": 430220 + }, + { + "epoch": 0.96, + "learning_rate": 2.0099102928346126e-06, + "loss": 0.0959, + "step": 430230 + }, + { + "epoch": 0.96, + "learning_rate": 2.008791749625288e-06, + "loss": 0.0855, + "step": 430240 + }, + { + "epoch": 0.96, + "learning_rate": 2.007673206415964e-06, + "loss": 0.0929, + "step": 430250 + }, + { + "epoch": 0.96, + "learning_rate": 2.0065546632066396e-06, + "loss": 0.0931, + "step": 430260 + }, + { + "epoch": 0.96, + "learning_rate": 2.005436119997316e-06, + "loss": 0.0907, + "step": 430270 + }, + { + "epoch": 0.96, + "learning_rate": 2.004317576787991e-06, + "loss": 0.0877, + "step": 430280 + }, + { + "epoch": 0.96, + "learning_rate": 2.0031990335786674e-06, + "loss": 0.0933, + "step": 430290 + }, + { + "epoch": 0.96, + "learning_rate": 2.002080490369343e-06, + "loss": 0.0882, + "step": 430300 + }, + { + "epoch": 0.96, + "learning_rate": 2.000961947160019e-06, + "loss": 0.0912, + "step": 430310 + }, + { + "epoch": 0.96, + "learning_rate": 1.9998434039506944e-06, + "loss": 0.0968, + "step": 430320 + }, + { + "epoch": 0.96, + "learning_rate": 1.9987248607413707e-06, + "loss": 0.0912, + "step": 430330 + }, + { + "epoch": 0.96, + "learning_rate": 1.9976063175320465e-06, + "loss": 0.0888, + "step": 430340 + }, + { + "epoch": 0.96, + "learning_rate": 1.9964877743227223e-06, + "loss": 0.0901, + "step": 430350 + }, + { + "epoch": 0.96, + "learning_rate": 1.995369231113398e-06, + "loss": 0.0939, + "step": 430360 + }, + { + "epoch": 0.96, + "learning_rate": 1.994250687904074e-06, + "loss": 0.0929, + "step": 430370 + }, + { + "epoch": 0.96, + "learning_rate": 1.9931321446947497e-06, + "loss": 0.0889, + "step": 430380 + }, + { + "epoch": 0.96, + "learning_rate": 1.9920136014854255e-06, + "loss": 0.0902, + "step": 430390 + }, + { + "epoch": 0.96, + "learning_rate": 1.9908950582761013e-06, + "loss": 0.0916, + "step": 430400 + }, + { + "epoch": 0.96, + "learning_rate": 1.989776515066777e-06, + "loss": 0.089, + "step": 430410 + }, + { + "epoch": 0.96, + "learning_rate": 1.988657971857453e-06, + "loss": 0.088, + "step": 430420 + }, + { + "epoch": 0.96, + "learning_rate": 1.9875394286481288e-06, + "loss": 0.0911, + "step": 430430 + }, + { + "epoch": 0.96, + "learning_rate": 1.9864208854388046e-06, + "loss": 0.0922, + "step": 430440 + }, + { + "epoch": 0.96, + "learning_rate": 1.9853023422294804e-06, + "loss": 0.0888, + "step": 430450 + }, + { + "epoch": 0.96, + "learning_rate": 1.984183799020156e-06, + "loss": 0.0895, + "step": 430460 + }, + { + "epoch": 0.96, + "learning_rate": 1.983065255810832e-06, + "loss": 0.0921, + "step": 430470 + }, + { + "epoch": 0.96, + "learning_rate": 1.981946712601508e-06, + "loss": 0.0896, + "step": 430480 + }, + { + "epoch": 0.96, + "learning_rate": 1.9808281693921836e-06, + "loss": 0.0925, + "step": 430490 + }, + { + "epoch": 0.96, + "learning_rate": 1.9797096261828594e-06, + "loss": 0.0934, + "step": 430500 + }, + { + "epoch": 0.96, + "learning_rate": 1.9785910829735357e-06, + "loss": 0.088, + "step": 430510 + }, + { + "epoch": 0.96, + "learning_rate": 1.977472539764211e-06, + "loss": 0.092, + "step": 430520 + }, + { + "epoch": 0.96, + "learning_rate": 1.9763539965548873e-06, + "loss": 0.0879, + "step": 430530 + }, + { + "epoch": 0.96, + "learning_rate": 1.9752354533455627e-06, + "loss": 0.0968, + "step": 430540 + }, + { + "epoch": 0.96, + "learning_rate": 1.974116910136239e-06, + "loss": 0.0914, + "step": 430550 + }, + { + "epoch": 0.96, + "learning_rate": 1.9729983669269143e-06, + "loss": 0.0899, + "step": 430560 + }, + { + "epoch": 0.96, + "learning_rate": 1.9718798237175905e-06, + "loss": 0.0883, + "step": 430570 + }, + { + "epoch": 0.96, + "learning_rate": 1.970761280508266e-06, + "loss": 0.0917, + "step": 430580 + }, + { + "epoch": 0.96, + "learning_rate": 1.969642737298942e-06, + "loss": 0.0922, + "step": 430590 + }, + { + "epoch": 0.96, + "learning_rate": 1.9685241940896175e-06, + "loss": 0.0942, + "step": 430600 + }, + { + "epoch": 0.96, + "learning_rate": 1.9674056508802938e-06, + "loss": 0.0905, + "step": 430610 + }, + { + "epoch": 0.96, + "learning_rate": 1.966287107670969e-06, + "loss": 0.0913, + "step": 430620 + }, + { + "epoch": 0.96, + "learning_rate": 1.9651685644616454e-06, + "loss": 0.0893, + "step": 430630 + }, + { + "epoch": 0.96, + "learning_rate": 1.964050021252321e-06, + "loss": 0.0942, + "step": 430640 + }, + { + "epoch": 0.96, + "learning_rate": 1.962931478042997e-06, + "loss": 0.0949, + "step": 430650 + }, + { + "epoch": 0.96, + "learning_rate": 1.961812934833673e-06, + "loss": 0.0894, + "step": 430660 + }, + { + "epoch": 0.96, + "learning_rate": 1.9606943916243486e-06, + "loss": 0.0945, + "step": 430670 + }, + { + "epoch": 0.96, + "learning_rate": 1.9595758484150244e-06, + "loss": 0.0926, + "step": 430680 + }, + { + "epoch": 0.96, + "learning_rate": 1.9584573052057003e-06, + "loss": 0.0891, + "step": 430690 + }, + { + "epoch": 0.96, + "learning_rate": 1.957338761996376e-06, + "loss": 0.0918, + "step": 430700 + }, + { + "epoch": 0.96, + "learning_rate": 1.956220218787052e-06, + "loss": 0.0916, + "step": 430710 + }, + { + "epoch": 0.96, + "learning_rate": 1.9551016755777277e-06, + "loss": 0.0895, + "step": 430720 + }, + { + "epoch": 0.96, + "learning_rate": 1.9539831323684035e-06, + "loss": 0.0884, + "step": 430730 + }, + { + "epoch": 0.96, + "learning_rate": 1.9528645891590793e-06, + "loss": 0.0906, + "step": 430740 + }, + { + "epoch": 0.96, + "learning_rate": 1.951746045949755e-06, + "loss": 0.0962, + "step": 430750 + }, + { + "epoch": 0.96, + "learning_rate": 1.950627502740431e-06, + "loss": 0.0947, + "step": 430760 + }, + { + "epoch": 0.96, + "learning_rate": 1.9495089595311067e-06, + "loss": 0.0934, + "step": 430770 + }, + { + "epoch": 0.96, + "learning_rate": 1.9483904163217825e-06, + "loss": 0.0884, + "step": 430780 + }, + { + "epoch": 0.96, + "learning_rate": 1.9472718731124584e-06, + "loss": 0.0899, + "step": 430790 + }, + { + "epoch": 0.96, + "learning_rate": 1.946153329903134e-06, + "loss": 0.0932, + "step": 430800 + }, + { + "epoch": 0.96, + "learning_rate": 1.9450347866938104e-06, + "loss": 0.0905, + "step": 430810 + }, + { + "epoch": 0.96, + "learning_rate": 1.9439162434844858e-06, + "loss": 0.0922, + "step": 430820 + }, + { + "epoch": 0.96, + "learning_rate": 1.942797700275162e-06, + "loss": 0.0846, + "step": 430830 + }, + { + "epoch": 0.96, + "learning_rate": 1.9416791570658374e-06, + "loss": 0.0941, + "step": 430840 + }, + { + "epoch": 0.96, + "learning_rate": 1.9405606138565136e-06, + "loss": 0.0874, + "step": 430850 + }, + { + "epoch": 0.96, + "learning_rate": 1.939442070647189e-06, + "loss": 0.0944, + "step": 430860 + }, + { + "epoch": 0.96, + "learning_rate": 1.9383235274378653e-06, + "loss": 0.0926, + "step": 430870 + }, + { + "epoch": 0.96, + "learning_rate": 1.9372049842285406e-06, + "loss": 0.0909, + "step": 430880 + }, + { + "epoch": 0.96, + "learning_rate": 1.936086441019217e-06, + "loss": 0.0903, + "step": 430890 + }, + { + "epoch": 0.96, + "learning_rate": 1.9349678978098923e-06, + "loss": 0.0891, + "step": 430900 + }, + { + "epoch": 0.96, + "learning_rate": 1.9338493546005685e-06, + "loss": 0.0895, + "step": 430910 + }, + { + "epoch": 0.96, + "learning_rate": 1.932730811391244e-06, + "loss": 0.0926, + "step": 430920 + }, + { + "epoch": 0.96, + "learning_rate": 1.93161226818192e-06, + "loss": 0.0898, + "step": 430930 + }, + { + "epoch": 0.96, + "learning_rate": 1.930493724972596e-06, + "loss": 0.0867, + "step": 430940 + }, + { + "epoch": 0.96, + "learning_rate": 1.9293751817632717e-06, + "loss": 0.0892, + "step": 430950 + }, + { + "epoch": 0.96, + "learning_rate": 1.9282566385539475e-06, + "loss": 0.0908, + "step": 430960 + }, + { + "epoch": 0.96, + "learning_rate": 1.9271380953446234e-06, + "loss": 0.0859, + "step": 430970 + }, + { + "epoch": 0.96, + "learning_rate": 1.926019552135299e-06, + "loss": 0.0884, + "step": 430980 + }, + { + "epoch": 0.96, + "learning_rate": 1.924901008925975e-06, + "loss": 0.0909, + "step": 430990 + }, + { + "epoch": 0.96, + "learning_rate": 1.9237824657166508e-06, + "loss": 0.0893, + "step": 431000 + }, + { + "epoch": 0.96, + "learning_rate": 1.9226639225073266e-06, + "loss": 0.088, + "step": 431010 + }, + { + "epoch": 0.96, + "learning_rate": 1.9215453792980024e-06, + "loss": 0.0923, + "step": 431020 + }, + { + "epoch": 0.96, + "learning_rate": 1.9204268360886782e-06, + "loss": 0.0923, + "step": 431030 + }, + { + "epoch": 0.96, + "learning_rate": 1.919308292879354e-06, + "loss": 0.0905, + "step": 431040 + }, + { + "epoch": 0.96, + "learning_rate": 1.91818974967003e-06, + "loss": 0.0959, + "step": 431050 + }, + { + "epoch": 0.96, + "learning_rate": 1.9170712064607056e-06, + "loss": 0.0899, + "step": 431060 + }, + { + "epoch": 0.96, + "learning_rate": 1.9159526632513815e-06, + "loss": 0.0929, + "step": 431070 + }, + { + "epoch": 0.96, + "learning_rate": 1.9148341200420573e-06, + "loss": 0.0925, + "step": 431080 + }, + { + "epoch": 0.96, + "learning_rate": 1.913715576832733e-06, + "loss": 0.0917, + "step": 431090 + }, + { + "epoch": 0.96, + "learning_rate": 1.912597033623409e-06, + "loss": 0.0917, + "step": 431100 + }, + { + "epoch": 0.96, + "learning_rate": 1.911478490414085e-06, + "loss": 0.0958, + "step": 431110 + }, + { + "epoch": 0.96, + "learning_rate": 1.9103599472047605e-06, + "loss": 0.089, + "step": 431120 + }, + { + "epoch": 0.96, + "learning_rate": 1.9092414039954367e-06, + "loss": 0.091, + "step": 431130 + }, + { + "epoch": 0.96, + "learning_rate": 1.908122860786112e-06, + "loss": 0.0962, + "step": 431140 + }, + { + "epoch": 0.96, + "learning_rate": 1.9070043175767882e-06, + "loss": 0.0893, + "step": 431150 + }, + { + "epoch": 0.96, + "learning_rate": 1.905885774367464e-06, + "loss": 0.0888, + "step": 431160 + }, + { + "epoch": 0.96, + "learning_rate": 1.9047672311581398e-06, + "loss": 0.0903, + "step": 431170 + }, + { + "epoch": 0.96, + "learning_rate": 1.9036486879488156e-06, + "loss": 0.0895, + "step": 431180 + }, + { + "epoch": 0.96, + "learning_rate": 1.9025301447394916e-06, + "loss": 0.0899, + "step": 431190 + }, + { + "epoch": 0.96, + "learning_rate": 1.9014116015301672e-06, + "loss": 0.0932, + "step": 431200 + }, + { + "epoch": 0.96, + "learning_rate": 1.9002930583208432e-06, + "loss": 0.0887, + "step": 431210 + }, + { + "epoch": 0.96, + "learning_rate": 1.8991745151115188e-06, + "loss": 0.087, + "step": 431220 + }, + { + "epoch": 0.96, + "learning_rate": 1.8980559719021948e-06, + "loss": 0.0893, + "step": 431230 + }, + { + "epoch": 0.96, + "learning_rate": 1.8969374286928704e-06, + "loss": 0.0917, + "step": 431240 + }, + { + "epoch": 0.96, + "learning_rate": 1.8958188854835465e-06, + "loss": 0.0879, + "step": 431250 + }, + { + "epoch": 0.96, + "learning_rate": 1.894700342274222e-06, + "loss": 0.0902, + "step": 431260 + }, + { + "epoch": 0.96, + "learning_rate": 1.893581799064898e-06, + "loss": 0.0921, + "step": 431270 + }, + { + "epoch": 0.96, + "learning_rate": 1.8924632558555737e-06, + "loss": 0.0883, + "step": 431280 + }, + { + "epoch": 0.96, + "learning_rate": 1.8913447126462497e-06, + "loss": 0.0914, + "step": 431290 + }, + { + "epoch": 0.96, + "learning_rate": 1.8902261694369253e-06, + "loss": 0.0907, + "step": 431300 + }, + { + "epoch": 0.96, + "learning_rate": 1.8891076262276013e-06, + "loss": 0.0891, + "step": 431310 + }, + { + "epoch": 0.96, + "learning_rate": 1.8879890830182771e-06, + "loss": 0.0927, + "step": 431320 + }, + { + "epoch": 0.96, + "learning_rate": 1.8868705398089532e-06, + "loss": 0.0867, + "step": 431330 + }, + { + "epoch": 0.96, + "learning_rate": 1.8857519965996288e-06, + "loss": 0.0923, + "step": 431340 + }, + { + "epoch": 0.96, + "learning_rate": 1.8846334533903048e-06, + "loss": 0.0913, + "step": 431350 + }, + { + "epoch": 0.96, + "learning_rate": 1.8835149101809804e-06, + "loss": 0.0944, + "step": 431360 + }, + { + "epoch": 0.96, + "learning_rate": 1.8823963669716564e-06, + "loss": 0.0894, + "step": 431370 + }, + { + "epoch": 0.96, + "learning_rate": 1.881277823762332e-06, + "loss": 0.0909, + "step": 431380 + }, + { + "epoch": 0.96, + "learning_rate": 1.880159280553008e-06, + "loss": 0.0904, + "step": 431390 + }, + { + "epoch": 0.96, + "learning_rate": 1.8790407373436836e-06, + "loss": 0.0889, + "step": 431400 + }, + { + "epoch": 0.96, + "learning_rate": 1.8779221941343596e-06, + "loss": 0.0939, + "step": 431410 + }, + { + "epoch": 0.96, + "learning_rate": 1.8768036509250352e-06, + "loss": 0.0875, + "step": 431420 + }, + { + "epoch": 0.96, + "learning_rate": 1.8756851077157113e-06, + "loss": 0.0847, + "step": 431430 + }, + { + "epoch": 0.96, + "learning_rate": 1.8745665645063869e-06, + "loss": 0.0926, + "step": 431440 + }, + { + "epoch": 0.96, + "learning_rate": 1.8734480212970629e-06, + "loss": 0.0907, + "step": 431450 + }, + { + "epoch": 0.96, + "learning_rate": 1.8723294780877387e-06, + "loss": 0.0923, + "step": 431460 + }, + { + "epoch": 0.96, + "learning_rate": 1.8712109348784145e-06, + "loss": 0.0874, + "step": 431470 + }, + { + "epoch": 0.96, + "learning_rate": 1.8700923916690903e-06, + "loss": 0.0924, + "step": 431480 + }, + { + "epoch": 0.96, + "learning_rate": 1.8689738484597663e-06, + "loss": 0.09, + "step": 431490 + }, + { + "epoch": 0.96, + "learning_rate": 1.867855305250442e-06, + "loss": 0.0946, + "step": 431500 + }, + { + "epoch": 0.96, + "learning_rate": 1.866736762041118e-06, + "loss": 0.0933, + "step": 431510 + }, + { + "epoch": 0.96, + "learning_rate": 1.8656182188317935e-06, + "loss": 0.0942, + "step": 431520 + }, + { + "epoch": 0.96, + "learning_rate": 1.8644996756224696e-06, + "loss": 0.0896, + "step": 431530 + }, + { + "epoch": 0.96, + "learning_rate": 1.8633811324131452e-06, + "loss": 0.0896, + "step": 431540 + }, + { + "epoch": 0.96, + "learning_rate": 1.8622625892038212e-06, + "loss": 0.0904, + "step": 431550 + }, + { + "epoch": 0.96, + "learning_rate": 1.8611440459944968e-06, + "loss": 0.0902, + "step": 431560 + }, + { + "epoch": 0.96, + "learning_rate": 1.8600255027851728e-06, + "loss": 0.0923, + "step": 431570 + }, + { + "epoch": 0.96, + "learning_rate": 1.8589069595758484e-06, + "loss": 0.0922, + "step": 431580 + }, + { + "epoch": 0.96, + "learning_rate": 1.8577884163665244e-06, + "loss": 0.092, + "step": 431590 + }, + { + "epoch": 0.96, + "learning_rate": 1.8566698731572e-06, + "loss": 0.0892, + "step": 431600 + }, + { + "epoch": 0.96, + "learning_rate": 1.855551329947876e-06, + "loss": 0.0932, + "step": 431610 + }, + { + "epoch": 0.96, + "learning_rate": 1.8544327867385519e-06, + "loss": 0.0933, + "step": 431620 + }, + { + "epoch": 0.96, + "learning_rate": 1.8533142435292279e-06, + "loss": 0.0934, + "step": 431630 + }, + { + "epoch": 0.96, + "learning_rate": 1.8521957003199035e-06, + "loss": 0.0952, + "step": 431640 + }, + { + "epoch": 0.96, + "learning_rate": 1.8510771571105795e-06, + "loss": 0.0898, + "step": 431650 + }, + { + "epoch": 0.96, + "learning_rate": 1.849958613901255e-06, + "loss": 0.095, + "step": 431660 + }, + { + "epoch": 0.96, + "learning_rate": 1.8488400706919311e-06, + "loss": 0.0933, + "step": 431670 + }, + { + "epoch": 0.96, + "learning_rate": 1.8477215274826067e-06, + "loss": 0.0883, + "step": 431680 + }, + { + "epoch": 0.96, + "learning_rate": 1.8466029842732827e-06, + "loss": 0.0909, + "step": 431690 + }, + { + "epoch": 0.96, + "learning_rate": 1.8454844410639583e-06, + "loss": 0.0894, + "step": 431700 + }, + { + "epoch": 0.96, + "learning_rate": 1.8443658978546344e-06, + "loss": 0.0924, + "step": 431710 + }, + { + "epoch": 0.96, + "learning_rate": 1.84324735464531e-06, + "loss": 0.0897, + "step": 431720 + }, + { + "epoch": 0.96, + "learning_rate": 1.842128811435986e-06, + "loss": 0.0936, + "step": 431730 + }, + { + "epoch": 0.96, + "learning_rate": 1.8410102682266616e-06, + "loss": 0.0918, + "step": 431740 + }, + { + "epoch": 0.96, + "learning_rate": 1.8398917250173376e-06, + "loss": 0.0936, + "step": 431750 + }, + { + "epoch": 0.96, + "learning_rate": 1.8387731818080134e-06, + "loss": 0.0917, + "step": 431760 + }, + { + "epoch": 0.96, + "learning_rate": 1.8376546385986892e-06, + "loss": 0.0908, + "step": 431770 + }, + { + "epoch": 0.96, + "learning_rate": 1.836536095389365e-06, + "loss": 0.091, + "step": 431780 + }, + { + "epoch": 0.96, + "learning_rate": 1.835417552180041e-06, + "loss": 0.0917, + "step": 431790 + }, + { + "epoch": 0.96, + "learning_rate": 1.8342990089707167e-06, + "loss": 0.0882, + "step": 431800 + }, + { + "epoch": 0.96, + "learning_rate": 1.8331804657613927e-06, + "loss": 0.0889, + "step": 431810 + }, + { + "epoch": 0.96, + "learning_rate": 1.8320619225520683e-06, + "loss": 0.0908, + "step": 431820 + }, + { + "epoch": 0.96, + "learning_rate": 1.8309433793427443e-06, + "loss": 0.0892, + "step": 431830 + }, + { + "epoch": 0.96, + "learning_rate": 1.82982483613342e-06, + "loss": 0.0896, + "step": 431840 + }, + { + "epoch": 0.96, + "learning_rate": 1.828706292924096e-06, + "loss": 0.0891, + "step": 431850 + }, + { + "epoch": 0.96, + "learning_rate": 1.8275877497147715e-06, + "loss": 0.0925, + "step": 431860 + }, + { + "epoch": 0.96, + "learning_rate": 1.8264692065054475e-06, + "loss": 0.0849, + "step": 431870 + }, + { + "epoch": 0.96, + "learning_rate": 1.8253506632961231e-06, + "loss": 0.093, + "step": 431880 + }, + { + "epoch": 0.96, + "learning_rate": 1.8242321200867992e-06, + "loss": 0.0909, + "step": 431890 + }, + { + "epoch": 0.96, + "learning_rate": 1.8231135768774748e-06, + "loss": 0.0928, + "step": 431900 + }, + { + "epoch": 0.96, + "learning_rate": 1.8219950336681508e-06, + "loss": 0.096, + "step": 431910 + }, + { + "epoch": 0.96, + "learning_rate": 1.8208764904588266e-06, + "loss": 0.0899, + "step": 431920 + }, + { + "epoch": 0.96, + "learning_rate": 1.8197579472495026e-06, + "loss": 0.093, + "step": 431930 + }, + { + "epoch": 0.96, + "learning_rate": 1.8186394040401782e-06, + "loss": 0.0912, + "step": 431940 + }, + { + "epoch": 0.96, + "learning_rate": 1.8175208608308542e-06, + "loss": 0.0947, + "step": 431950 + }, + { + "epoch": 0.96, + "learning_rate": 1.8164023176215298e-06, + "loss": 0.0897, + "step": 431960 + }, + { + "epoch": 0.96, + "learning_rate": 1.8152837744122058e-06, + "loss": 0.09, + "step": 431970 + }, + { + "epoch": 0.96, + "learning_rate": 1.8141652312028814e-06, + "loss": 0.0877, + "step": 431980 + }, + { + "epoch": 0.96, + "learning_rate": 1.813046687993557e-06, + "loss": 0.089, + "step": 431990 + }, + { + "epoch": 0.96, + "learning_rate": 1.811928144784233e-06, + "loss": 0.0909, + "step": 432000 + }, + { + "epoch": 0.96, + "eval_NEIMS_canon_smiles": 0.9620666666666666, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.2841666666666667, + "eval_NEIMS_daylight_tanimoto_simil": 0.6417334171649136, + "eval_NEIMS_exact_mols": 0.2838333333333333, + "eval_NEIMS_exact_smiles": 0.27853333333333335, + "eval_NEIMS_loss": 0.11754453182220459, + "eval_NEIMS_matched_formulas": 0.7818166666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.5716279272819861, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.2846, + "eval_NEIMS_runtime": 719.4803, + "eval_NEIMS_samples_per_second": 83.394, + "eval_NEIMS_steps_per_second": 1.304, + "step": 432000 + }, + { + "epoch": 0.96, + "eval_RASSP_canon_smiles": 0.9612815974888971, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.366146859451698, + "eval_RASSP_daylight_tanimoto_simil": 0.7411713289672043, + "eval_RASSP_exact_mols": 0.3651450896583965, + "eval_RASSP_exact_smiles": 0.35718101980164957, + "eval_RASSP_loss": 0.08970693498849869, + "eval_RASSP_matched_formulas": 0.9014258523391324, + "eval_RASSP_morgan_tanimoto_simil": 0.6407572360684114, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.36527865896417006, + "eval_RASSP_runtime": 820.3425, + "eval_RASSP_samples_per_second": 73.011, + "eval_RASSP_steps_per_second": 1.141, + "step": 432000 + }, + { + "epoch": 0.96, + "eval_NEIMS_old_canon_smiles": 0.9588666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2799, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6399654244611078, + "eval_NEIMS_old_exact_mols": 0.2795, + "eval_NEIMS_old_exact_smiles": 0.2735, + "eval_NEIMS_old_loss": 0.11762527376413345, + "eval_NEIMS_old_matched_formulas": 0.7788666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.5702291241093846, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2804, + "eval_NEIMS_old_runtime": 360.1919, + "eval_NEIMS_old_samples_per_second": 83.289, + "eval_NEIMS_old_steps_per_second": 1.302, + "step": 432000 + }, + { + "epoch": 0.96, + "eval_RASSP_old_canon_smiles": 0.9617579337270998, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.39973971368505357, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7596048394195266, + "eval_RASSP_old_exact_mols": 0.39863850235258785, + "eval_RASSP_old_exact_smiles": 0.3901958821370174, + "eval_RASSP_old_loss": 0.0836544781923294, + "eval_RASSP_old_matched_formulas": 0.9108686221510328, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6643308793868389, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.39883872259485437, + "eval_RASSP_old_runtime": 408.3337, + "eval_RASSP_old_samples_per_second": 73.388, + "eval_RASSP_old_steps_per_second": 1.149, + "step": 432000 + }, + { + "epoch": 0.96, + "eval_NIST_canon_smiles": 0.8678709585832417, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.03069879689108138, + "eval_NIST_daylight_tanimoto_simil": 0.30647892744969973, + "eval_NIST_exact_mols": 0.029527628917201974, + "eval_NIST_exact_smiles": 0.028214501188912944, + "eval_NIST_loss": 1.797825574874878, + "eval_NIST_matched_formulas": 0.1364943038648543, + "eval_NIST_morgan_tanimoto_simil": 0.257120358642337, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.03059232707527416, + "eval_NIST_runtime": 576.7618, + "eval_NIST_samples_per_second": 48.854, + "eval_NIST_steps_per_second": 0.765, + "step": 432000 + }, + { + "epoch": 0.96, + "learning_rate": 1.8108096015749087e-06, + "loss": 0.0942, + "step": 432010 + }, + { + "epoch": 0.96, + "learning_rate": 1.8096910583655847e-06, + "loss": 0.0906, + "step": 432020 + }, + { + "epoch": 0.96, + "learning_rate": 1.8085725151562605e-06, + "loss": 0.0921, + "step": 432030 + }, + { + "epoch": 0.96, + "learning_rate": 1.8074539719469363e-06, + "loss": 0.095, + "step": 432040 + }, + { + "epoch": 0.96, + "learning_rate": 1.8063354287376121e-06, + "loss": 0.091, + "step": 432050 + }, + { + "epoch": 0.96, + "learning_rate": 1.8052168855282881e-06, + "loss": 0.0891, + "step": 432060 + }, + { + "epoch": 0.96, + "learning_rate": 1.8040983423189637e-06, + "loss": 0.0912, + "step": 432070 + }, + { + "epoch": 0.96, + "learning_rate": 1.8029797991096398e-06, + "loss": 0.0898, + "step": 432080 + }, + { + "epoch": 0.96, + "learning_rate": 1.8018612559003154e-06, + "loss": 0.09, + "step": 432090 + }, + { + "epoch": 0.96, + "learning_rate": 1.8007427126909914e-06, + "loss": 0.0882, + "step": 432100 + }, + { + "epoch": 0.96, + "learning_rate": 1.799624169481667e-06, + "loss": 0.0937, + "step": 432110 + }, + { + "epoch": 0.96, + "learning_rate": 1.798505626272343e-06, + "loss": 0.0935, + "step": 432120 + }, + { + "epoch": 0.96, + "learning_rate": 1.7973870830630186e-06, + "loss": 0.0913, + "step": 432130 + }, + { + "epoch": 0.96, + "learning_rate": 1.7962685398536946e-06, + "loss": 0.0874, + "step": 432140 + }, + { + "epoch": 0.96, + "learning_rate": 1.7951499966443702e-06, + "loss": 0.0909, + "step": 432150 + }, + { + "epoch": 0.96, + "learning_rate": 1.7940314534350462e-06, + "loss": 0.0939, + "step": 432160 + }, + { + "epoch": 0.96, + "learning_rate": 1.7929129102257218e-06, + "loss": 0.0906, + "step": 432170 + }, + { + "epoch": 0.96, + "learning_rate": 1.7917943670163979e-06, + "loss": 0.0896, + "step": 432180 + }, + { + "epoch": 0.96, + "learning_rate": 1.7906758238070737e-06, + "loss": 0.0911, + "step": 432190 + }, + { + "epoch": 0.96, + "learning_rate": 1.7896691349186818e-06, + "loss": 0.0915, + "step": 432200 + }, + { + "epoch": 0.96, + "learning_rate": 1.7885505917093578e-06, + "loss": 0.0873, + "step": 432210 + }, + { + "epoch": 0.96, + "learning_rate": 1.7874320485000334e-06, + "loss": 0.0946, + "step": 432220 + }, + { + "epoch": 0.96, + "learning_rate": 1.7863135052907095e-06, + "loss": 0.091, + "step": 432230 + }, + { + "epoch": 0.96, + "learning_rate": 1.785194962081385e-06, + "loss": 0.0885, + "step": 432240 + }, + { + "epoch": 0.96, + "learning_rate": 1.784076418872061e-06, + "loss": 0.0903, + "step": 432250 + }, + { + "epoch": 0.96, + "learning_rate": 1.7829578756627369e-06, + "loss": 0.0933, + "step": 432260 + }, + { + "epoch": 0.96, + "learning_rate": 1.7818393324534127e-06, + "loss": 0.0872, + "step": 432270 + }, + { + "epoch": 0.96, + "learning_rate": 1.7807207892440885e-06, + "loss": 0.0921, + "step": 432280 + }, + { + "epoch": 0.96, + "learning_rate": 1.7796022460347645e-06, + "loss": 0.0928, + "step": 432290 + }, + { + "epoch": 0.96, + "learning_rate": 1.7784837028254401e-06, + "loss": 0.0955, + "step": 432300 + }, + { + "epoch": 0.96, + "learning_rate": 1.7773651596161162e-06, + "loss": 0.0908, + "step": 432310 + }, + { + "epoch": 0.96, + "learning_rate": 1.7762466164067917e-06, + "loss": 0.0941, + "step": 432320 + }, + { + "epoch": 0.97, + "learning_rate": 1.7751280731974678e-06, + "loss": 0.0919, + "step": 432330 + }, + { + "epoch": 0.97, + "learning_rate": 1.7740095299881434e-06, + "loss": 0.0956, + "step": 432340 + }, + { + "epoch": 0.97, + "learning_rate": 1.7728909867788194e-06, + "loss": 0.0951, + "step": 432350 + }, + { + "epoch": 0.97, + "learning_rate": 1.771772443569495e-06, + "loss": 0.0925, + "step": 432360 + }, + { + "epoch": 0.97, + "learning_rate": 1.770653900360171e-06, + "loss": 0.097, + "step": 432370 + }, + { + "epoch": 0.97, + "learning_rate": 1.7695353571508466e-06, + "loss": 0.0948, + "step": 432380 + }, + { + "epoch": 0.97, + "learning_rate": 1.7684168139415226e-06, + "loss": 0.0922, + "step": 432390 + }, + { + "epoch": 0.97, + "learning_rate": 1.7672982707321984e-06, + "loss": 0.0951, + "step": 432400 + }, + { + "epoch": 0.97, + "learning_rate": 1.7661797275228743e-06, + "loss": 0.0923, + "step": 432410 + }, + { + "epoch": 0.97, + "learning_rate": 1.76506118431355e-06, + "loss": 0.0892, + "step": 432420 + }, + { + "epoch": 0.97, + "learning_rate": 1.763942641104226e-06, + "loss": 0.091, + "step": 432430 + }, + { + "epoch": 0.97, + "learning_rate": 1.7628240978949017e-06, + "loss": 0.0897, + "step": 432440 + }, + { + "epoch": 0.97, + "learning_rate": 1.7617055546855777e-06, + "loss": 0.0914, + "step": 432450 + }, + { + "epoch": 0.97, + "learning_rate": 1.7605870114762533e-06, + "loss": 0.093, + "step": 432460 + }, + { + "epoch": 0.97, + "learning_rate": 1.7594684682669293e-06, + "loss": 0.087, + "step": 432470 + }, + { + "epoch": 0.97, + "learning_rate": 1.758349925057605e-06, + "loss": 0.0896, + "step": 432480 + }, + { + "epoch": 0.97, + "learning_rate": 1.757231381848281e-06, + "loss": 0.0916, + "step": 432490 + }, + { + "epoch": 0.97, + "learning_rate": 1.7561128386389565e-06, + "loss": 0.0912, + "step": 432500 + }, + { + "epoch": 0.97, + "learning_rate": 1.7549942954296326e-06, + "loss": 0.0896, + "step": 432510 + }, + { + "epoch": 0.97, + "learning_rate": 1.7538757522203082e-06, + "loss": 0.0923, + "step": 432520 + }, + { + "epoch": 0.97, + "learning_rate": 1.7527572090109842e-06, + "loss": 0.0865, + "step": 432530 + }, + { + "epoch": 0.97, + "learning_rate": 1.7516386658016598e-06, + "loss": 0.0953, + "step": 432540 + }, + { + "epoch": 0.97, + "learning_rate": 1.7505201225923358e-06, + "loss": 0.0885, + "step": 432550 + }, + { + "epoch": 0.97, + "learning_rate": 1.7494015793830116e-06, + "loss": 0.0932, + "step": 432560 + }, + { + "epoch": 0.97, + "learning_rate": 1.7482830361736874e-06, + "loss": 0.0902, + "step": 432570 + }, + { + "epoch": 0.97, + "learning_rate": 1.7471644929643632e-06, + "loss": 0.088, + "step": 432580 + }, + { + "epoch": 0.97, + "learning_rate": 1.7460459497550393e-06, + "loss": 0.0923, + "step": 432590 + }, + { + "epoch": 0.97, + "learning_rate": 1.7449274065457149e-06, + "loss": 0.09, + "step": 432600 + }, + { + "epoch": 0.97, + "learning_rate": 1.7438088633363909e-06, + "loss": 0.0874, + "step": 432610 + }, + { + "epoch": 0.97, + "learning_rate": 1.7426903201270665e-06, + "loss": 0.0903, + "step": 432620 + }, + { + "epoch": 0.97, + "learning_rate": 1.7415717769177425e-06, + "loss": 0.0959, + "step": 432630 + }, + { + "epoch": 0.97, + "learning_rate": 1.740453233708418e-06, + "loss": 0.0906, + "step": 432640 + }, + { + "epoch": 0.97, + "learning_rate": 1.7393346904990941e-06, + "loss": 0.0934, + "step": 432650 + }, + { + "epoch": 0.97, + "learning_rate": 1.7382161472897697e-06, + "loss": 0.0894, + "step": 432660 + }, + { + "epoch": 0.97, + "learning_rate": 1.7370976040804457e-06, + "loss": 0.0895, + "step": 432670 + }, + { + "epoch": 0.97, + "learning_rate": 1.7359790608711213e-06, + "loss": 0.0887, + "step": 432680 + }, + { + "epoch": 0.97, + "learning_rate": 1.7348605176617974e-06, + "loss": 0.0945, + "step": 432690 + }, + { + "epoch": 0.97, + "learning_rate": 1.7337419744524732e-06, + "loss": 0.0888, + "step": 432700 + }, + { + "epoch": 0.97, + "learning_rate": 1.732623431243149e-06, + "loss": 0.0887, + "step": 432710 + }, + { + "epoch": 0.97, + "learning_rate": 1.7315048880338248e-06, + "loss": 0.091, + "step": 432720 + }, + { + "epoch": 0.97, + "learning_rate": 1.7303863448245008e-06, + "loss": 0.0894, + "step": 432730 + }, + { + "epoch": 0.97, + "learning_rate": 1.7292678016151764e-06, + "loss": 0.0892, + "step": 432740 + }, + { + "epoch": 0.97, + "learning_rate": 1.7281492584058524e-06, + "loss": 0.0928, + "step": 432750 + }, + { + "epoch": 0.97, + "learning_rate": 1.727030715196528e-06, + "loss": 0.0908, + "step": 432760 + }, + { + "epoch": 0.97, + "learning_rate": 1.725912171987204e-06, + "loss": 0.0931, + "step": 432770 + }, + { + "epoch": 0.97, + "learning_rate": 1.7247936287778796e-06, + "loss": 0.0933, + "step": 432780 + }, + { + "epoch": 0.97, + "learning_rate": 1.7236750855685557e-06, + "loss": 0.0899, + "step": 432790 + }, + { + "epoch": 0.97, + "learning_rate": 1.7225565423592313e-06, + "loss": 0.0892, + "step": 432800 + }, + { + "epoch": 0.97, + "learning_rate": 1.7214379991499073e-06, + "loss": 0.0977, + "step": 432810 + }, + { + "epoch": 0.97, + "learning_rate": 1.7203194559405829e-06, + "loss": 0.0913, + "step": 432820 + }, + { + "epoch": 0.97, + "learning_rate": 1.719200912731259e-06, + "loss": 0.0916, + "step": 432830 + }, + { + "epoch": 0.97, + "learning_rate": 1.7180823695219345e-06, + "loss": 0.0915, + "step": 432840 + }, + { + "epoch": 0.97, + "learning_rate": 1.7169638263126105e-06, + "loss": 0.0928, + "step": 432850 + }, + { + "epoch": 0.97, + "learning_rate": 1.7158452831032863e-06, + "loss": 0.0866, + "step": 432860 + }, + { + "epoch": 0.97, + "learning_rate": 1.7147267398939622e-06, + "loss": 0.0912, + "step": 432870 + }, + { + "epoch": 0.97, + "learning_rate": 1.713608196684638e-06, + "loss": 0.0875, + "step": 432880 + }, + { + "epoch": 0.97, + "learning_rate": 1.712489653475314e-06, + "loss": 0.0883, + "step": 432890 + }, + { + "epoch": 0.97, + "learning_rate": 1.7113711102659896e-06, + "loss": 0.0913, + "step": 432900 + }, + { + "epoch": 0.97, + "learning_rate": 1.7102525670566656e-06, + "loss": 0.0911, + "step": 432910 + }, + { + "epoch": 0.97, + "learning_rate": 1.7091340238473412e-06, + "loss": 0.0914, + "step": 432920 + }, + { + "epoch": 0.97, + "learning_rate": 1.7080154806380172e-06, + "loss": 0.0913, + "step": 432930 + }, + { + "epoch": 0.97, + "learning_rate": 1.7068969374286928e-06, + "loss": 0.0923, + "step": 432940 + }, + { + "epoch": 0.97, + "learning_rate": 1.7057783942193688e-06, + "loss": 0.0889, + "step": 432950 + }, + { + "epoch": 0.97, + "learning_rate": 1.7046598510100444e-06, + "loss": 0.0898, + "step": 432960 + }, + { + "epoch": 0.97, + "learning_rate": 1.7035413078007205e-06, + "loss": 0.0962, + "step": 432970 + }, + { + "epoch": 0.97, + "learning_rate": 1.702422764591396e-06, + "loss": 0.0908, + "step": 432980 + }, + { + "epoch": 0.97, + "learning_rate": 1.701304221382072e-06, + "loss": 0.0948, + "step": 432990 + }, + { + "epoch": 0.97, + "learning_rate": 1.700185678172748e-06, + "loss": 0.0934, + "step": 433000 + }, + { + "epoch": 0.97, + "learning_rate": 1.6990671349634237e-06, + "loss": 0.0887, + "step": 433010 + }, + { + "epoch": 0.97, + "learning_rate": 1.6979485917540995e-06, + "loss": 0.0934, + "step": 433020 + }, + { + "epoch": 0.97, + "learning_rate": 1.6968300485447755e-06, + "loss": 0.0949, + "step": 433030 + }, + { + "epoch": 0.97, + "learning_rate": 1.6957115053354511e-06, + "loss": 0.0858, + "step": 433040 + }, + { + "epoch": 0.97, + "learning_rate": 1.6945929621261272e-06, + "loss": 0.0926, + "step": 433050 + }, + { + "epoch": 0.97, + "learning_rate": 1.6934744189168028e-06, + "loss": 0.0891, + "step": 433060 + }, + { + "epoch": 0.97, + "learning_rate": 1.6923558757074788e-06, + "loss": 0.0878, + "step": 433070 + }, + { + "epoch": 0.97, + "learning_rate": 1.6912373324981544e-06, + "loss": 0.0884, + "step": 433080 + }, + { + "epoch": 0.97, + "learning_rate": 1.6901187892888304e-06, + "loss": 0.0918, + "step": 433090 + }, + { + "epoch": 0.97, + "learning_rate": 1.689000246079506e-06, + "loss": 0.0929, + "step": 433100 + }, + { + "epoch": 0.97, + "learning_rate": 1.687881702870182e-06, + "loss": 0.0879, + "step": 433110 + }, + { + "epoch": 0.97, + "learning_rate": 1.6867631596608576e-06, + "loss": 0.0899, + "step": 433120 + }, + { + "epoch": 0.97, + "learning_rate": 1.6856446164515336e-06, + "loss": 0.0899, + "step": 433130 + }, + { + "epoch": 0.97, + "learning_rate": 1.6845260732422092e-06, + "loss": 0.0885, + "step": 433140 + }, + { + "epoch": 0.97, + "learning_rate": 1.6834075300328853e-06, + "loss": 0.0906, + "step": 433150 + }, + { + "epoch": 0.97, + "learning_rate": 1.682288986823561e-06, + "loss": 0.0933, + "step": 433160 + }, + { + "epoch": 0.97, + "learning_rate": 1.6811704436142369e-06, + "loss": 0.0963, + "step": 433170 + }, + { + "epoch": 0.97, + "learning_rate": 1.6800519004049127e-06, + "loss": 0.0866, + "step": 433180 + }, + { + "epoch": 0.97, + "learning_rate": 1.6789333571955887e-06, + "loss": 0.0908, + "step": 433190 + }, + { + "epoch": 0.97, + "learning_rate": 1.6778148139862643e-06, + "loss": 0.0862, + "step": 433200 + }, + { + "epoch": 0.97, + "learning_rate": 1.6766962707769403e-06, + "loss": 0.0869, + "step": 433210 + }, + { + "epoch": 0.97, + "learning_rate": 1.675577727567616e-06, + "loss": 0.0886, + "step": 433220 + }, + { + "epoch": 0.97, + "learning_rate": 1.674459184358292e-06, + "loss": 0.089, + "step": 433230 + }, + { + "epoch": 0.97, + "learning_rate": 1.6733406411489675e-06, + "loss": 0.0915, + "step": 433240 + }, + { + "epoch": 0.97, + "learning_rate": 1.6722220979396436e-06, + "loss": 0.0948, + "step": 433250 + }, + { + "epoch": 0.97, + "learning_rate": 1.6711035547303192e-06, + "loss": 0.0887, + "step": 433260 + }, + { + "epoch": 0.97, + "learning_rate": 1.6699850115209952e-06, + "loss": 0.0965, + "step": 433270 + }, + { + "epoch": 0.97, + "learning_rate": 1.6688664683116708e-06, + "loss": 0.0899, + "step": 433280 + }, + { + "epoch": 0.97, + "learning_rate": 1.6677479251023468e-06, + "loss": 0.0928, + "step": 433290 + }, + { + "epoch": 0.97, + "learning_rate": 1.6666293818930226e-06, + "loss": 0.0923, + "step": 433300 + }, + { + "epoch": 0.97, + "learning_rate": 1.6655108386836984e-06, + "loss": 0.0915, + "step": 433310 + }, + { + "epoch": 0.97, + "learning_rate": 1.6643922954743742e-06, + "loss": 0.093, + "step": 433320 + }, + { + "epoch": 0.97, + "learning_rate": 1.6632737522650503e-06, + "loss": 0.0911, + "step": 433330 + }, + { + "epoch": 0.97, + "learning_rate": 1.6621552090557259e-06, + "loss": 0.0925, + "step": 433340 + }, + { + "epoch": 0.97, + "learning_rate": 1.6610366658464019e-06, + "loss": 0.0927, + "step": 433350 + }, + { + "epoch": 0.97, + "learning_rate": 1.6599181226370775e-06, + "loss": 0.0915, + "step": 433360 + }, + { + "epoch": 0.97, + "learning_rate": 1.6587995794277535e-06, + "loss": 0.0919, + "step": 433370 + }, + { + "epoch": 0.97, + "learning_rate": 1.657681036218429e-06, + "loss": 0.0916, + "step": 433380 + }, + { + "epoch": 0.97, + "learning_rate": 1.6565624930091051e-06, + "loss": 0.0873, + "step": 433390 + }, + { + "epoch": 0.97, + "learning_rate": 1.6554439497997807e-06, + "loss": 0.0911, + "step": 433400 + }, + { + "epoch": 0.97, + "learning_rate": 1.6543254065904567e-06, + "loss": 0.0908, + "step": 433410 + }, + { + "epoch": 0.97, + "learning_rate": 1.6532068633811323e-06, + "loss": 0.0869, + "step": 433420 + }, + { + "epoch": 0.97, + "learning_rate": 1.6520883201718084e-06, + "loss": 0.092, + "step": 433430 + }, + { + "epoch": 0.97, + "learning_rate": 1.650969776962484e-06, + "loss": 0.0854, + "step": 433440 + }, + { + "epoch": 0.97, + "learning_rate": 1.64985123375316e-06, + "loss": 0.089, + "step": 433450 + }, + { + "epoch": 0.97, + "learning_rate": 1.6487326905438358e-06, + "loss": 0.0968, + "step": 433460 + }, + { + "epoch": 0.97, + "learning_rate": 1.6476141473345116e-06, + "loss": 0.0887, + "step": 433470 + }, + { + "epoch": 0.97, + "learning_rate": 1.6464956041251874e-06, + "loss": 0.088, + "step": 433480 + }, + { + "epoch": 0.97, + "learning_rate": 1.6453770609158634e-06, + "loss": 0.092, + "step": 433490 + }, + { + "epoch": 0.97, + "learning_rate": 1.644258517706539e-06, + "loss": 0.0871, + "step": 433500 + }, + { + "epoch": 0.97, + "learning_rate": 1.643139974497215e-06, + "loss": 0.0898, + "step": 433510 + }, + { + "epoch": 0.97, + "learning_rate": 1.6420214312878907e-06, + "loss": 0.092, + "step": 433520 + }, + { + "epoch": 0.97, + "learning_rate": 1.6409028880785667e-06, + "loss": 0.0916, + "step": 433530 + }, + { + "epoch": 0.97, + "learning_rate": 1.6397843448692423e-06, + "loss": 0.0908, + "step": 433540 + }, + { + "epoch": 0.97, + "learning_rate": 1.6386658016599183e-06, + "loss": 0.0905, + "step": 433550 + }, + { + "epoch": 0.97, + "learning_rate": 1.637547258450594e-06, + "loss": 0.0928, + "step": 433560 + }, + { + "epoch": 0.97, + "learning_rate": 1.63642871524127e-06, + "loss": 0.0904, + "step": 433570 + }, + { + "epoch": 0.97, + "learning_rate": 1.6353101720319455e-06, + "loss": 0.0899, + "step": 433580 + }, + { + "epoch": 0.97, + "learning_rate": 1.6341916288226215e-06, + "loss": 0.0913, + "step": 433590 + }, + { + "epoch": 0.97, + "learning_rate": 1.6330730856132973e-06, + "loss": 0.0879, + "step": 433600 + }, + { + "epoch": 0.97, + "learning_rate": 1.6319545424039732e-06, + "loss": 0.0845, + "step": 433610 + }, + { + "epoch": 0.97, + "learning_rate": 1.630835999194649e-06, + "loss": 0.0907, + "step": 433620 + }, + { + "epoch": 0.97, + "learning_rate": 1.629717455985325e-06, + "loss": 0.0936, + "step": 433630 + }, + { + "epoch": 0.97, + "learning_rate": 1.6285989127760006e-06, + "loss": 0.091, + "step": 433640 + }, + { + "epoch": 0.97, + "learning_rate": 1.6274803695666766e-06, + "loss": 0.0904, + "step": 433650 + }, + { + "epoch": 0.97, + "learning_rate": 1.6263618263573522e-06, + "loss": 0.0916, + "step": 433660 + }, + { + "epoch": 0.97, + "learning_rate": 1.6252432831480282e-06, + "loss": 0.0886, + "step": 433670 + }, + { + "epoch": 0.97, + "learning_rate": 1.6241247399387038e-06, + "loss": 0.0913, + "step": 433680 + }, + { + "epoch": 0.97, + "learning_rate": 1.6230061967293799e-06, + "loss": 0.0884, + "step": 433690 + }, + { + "epoch": 0.97, + "learning_rate": 1.6218876535200554e-06, + "loss": 0.0924, + "step": 433700 + }, + { + "epoch": 0.97, + "learning_rate": 1.6207691103107315e-06, + "loss": 0.0904, + "step": 433710 + }, + { + "epoch": 0.97, + "learning_rate": 1.619650567101407e-06, + "loss": 0.0929, + "step": 433720 + }, + { + "epoch": 0.97, + "learning_rate": 1.618532023892083e-06, + "loss": 0.0899, + "step": 433730 + }, + { + "epoch": 0.97, + "learning_rate": 1.6174134806827587e-06, + "loss": 0.0908, + "step": 433740 + }, + { + "epoch": 0.97, + "learning_rate": 1.6162949374734347e-06, + "loss": 0.0927, + "step": 433750 + }, + { + "epoch": 0.97, + "learning_rate": 1.6151763942641105e-06, + "loss": 0.0888, + "step": 433760 + }, + { + "epoch": 0.97, + "learning_rate": 1.6140578510547863e-06, + "loss": 0.098, + "step": 433770 + }, + { + "epoch": 0.97, + "learning_rate": 1.6129393078454621e-06, + "loss": 0.0916, + "step": 433780 + }, + { + "epoch": 0.97, + "learning_rate": 1.6118207646361382e-06, + "loss": 0.087, + "step": 433790 + }, + { + "epoch": 0.97, + "learning_rate": 1.6107022214268138e-06, + "loss": 0.0912, + "step": 433800 + }, + { + "epoch": 0.97, + "learning_rate": 1.6095836782174898e-06, + "loss": 0.0895, + "step": 433810 + }, + { + "epoch": 0.97, + "learning_rate": 1.6084651350081654e-06, + "loss": 0.0894, + "step": 433820 + }, + { + "epoch": 0.97, + "learning_rate": 1.6073465917988414e-06, + "loss": 0.0952, + "step": 433830 + }, + { + "epoch": 0.97, + "learning_rate": 1.606228048589517e-06, + "loss": 0.0913, + "step": 433840 + }, + { + "epoch": 0.97, + "learning_rate": 1.605109505380193e-06, + "loss": 0.0909, + "step": 433850 + }, + { + "epoch": 0.97, + "learning_rate": 1.6039909621708686e-06, + "loss": 0.0865, + "step": 433860 + }, + { + "epoch": 0.97, + "learning_rate": 1.6028724189615446e-06, + "loss": 0.0926, + "step": 433870 + }, + { + "epoch": 0.97, + "learning_rate": 1.6017538757522202e-06, + "loss": 0.0887, + "step": 433880 + }, + { + "epoch": 0.97, + "learning_rate": 1.6006353325428963e-06, + "loss": 0.0859, + "step": 433890 + }, + { + "epoch": 0.97, + "learning_rate": 1.599516789333572e-06, + "loss": 0.093, + "step": 433900 + }, + { + "epoch": 0.97, + "learning_rate": 1.5983982461242479e-06, + "loss": 0.0877, + "step": 433910 + }, + { + "epoch": 0.97, + "learning_rate": 1.5972797029149237e-06, + "loss": 0.0917, + "step": 433920 + }, + { + "epoch": 0.97, + "learning_rate": 1.5961611597055997e-06, + "loss": 0.0897, + "step": 433930 + }, + { + "epoch": 0.97, + "learning_rate": 1.5950426164962753e-06, + "loss": 0.0889, + "step": 433940 + }, + { + "epoch": 0.97, + "learning_rate": 1.5939240732869513e-06, + "loss": 0.0936, + "step": 433950 + }, + { + "epoch": 0.97, + "learning_rate": 1.592805530077627e-06, + "loss": 0.0915, + "step": 433960 + }, + { + "epoch": 0.97, + "learning_rate": 1.591686986868303e-06, + "loss": 0.0925, + "step": 433970 + }, + { + "epoch": 0.97, + "learning_rate": 1.5905684436589786e-06, + "loss": 0.0903, + "step": 433980 + }, + { + "epoch": 0.97, + "learning_rate": 1.5894499004496546e-06, + "loss": 0.0907, + "step": 433990 + }, + { + "epoch": 0.97, + "learning_rate": 1.5883313572403302e-06, + "loss": 0.0923, + "step": 434000 + }, + { + "epoch": 0.97, + "learning_rate": 1.5872128140310062e-06, + "loss": 0.0931, + "step": 434010 + }, + { + "epoch": 0.97, + "learning_rate": 1.5860942708216818e-06, + "loss": 0.0929, + "step": 434020 + }, + { + "epoch": 0.97, + "learning_rate": 1.5849757276123578e-06, + "loss": 0.0931, + "step": 434030 + }, + { + "epoch": 0.97, + "learning_rate": 1.5838571844030334e-06, + "loss": 0.0894, + "step": 434040 + }, + { + "epoch": 0.97, + "learning_rate": 1.5827386411937094e-06, + "loss": 0.0888, + "step": 434050 + }, + { + "epoch": 0.97, + "learning_rate": 1.5816200979843852e-06, + "loss": 0.0923, + "step": 434060 + }, + { + "epoch": 0.97, + "learning_rate": 1.5805015547750613e-06, + "loss": 0.0888, + "step": 434070 + }, + { + "epoch": 0.97, + "learning_rate": 1.5793830115657369e-06, + "loss": 0.0912, + "step": 434080 + }, + { + "epoch": 0.97, + "learning_rate": 1.5782644683564129e-06, + "loss": 0.0907, + "step": 434090 + }, + { + "epoch": 0.97, + "learning_rate": 1.5771459251470885e-06, + "loss": 0.0939, + "step": 434100 + }, + { + "epoch": 0.97, + "learning_rate": 1.5760273819377645e-06, + "loss": 0.0891, + "step": 434110 + }, + { + "epoch": 0.97, + "learning_rate": 1.5749088387284401e-06, + "loss": 0.089, + "step": 434120 + }, + { + "epoch": 0.97, + "learning_rate": 1.5737902955191161e-06, + "loss": 0.0891, + "step": 434130 + }, + { + "epoch": 0.97, + "learning_rate": 1.5726717523097917e-06, + "loss": 0.0915, + "step": 434140 + }, + { + "epoch": 0.97, + "learning_rate": 1.5715532091004678e-06, + "loss": 0.0917, + "step": 434150 + }, + { + "epoch": 0.97, + "learning_rate": 1.5704346658911433e-06, + "loss": 0.0867, + "step": 434160 + }, + { + "epoch": 0.97, + "learning_rate": 1.5693161226818194e-06, + "loss": 0.0897, + "step": 434170 + }, + { + "epoch": 0.97, + "learning_rate": 1.568197579472495e-06, + "loss": 0.09, + "step": 434180 + }, + { + "epoch": 0.97, + "learning_rate": 1.567079036263171e-06, + "loss": 0.0922, + "step": 434190 + }, + { + "epoch": 0.97, + "learning_rate": 1.5659604930538468e-06, + "loss": 0.0904, + "step": 434200 + }, + { + "epoch": 0.97, + "learning_rate": 1.5648419498445226e-06, + "loss": 0.0879, + "step": 434210 + }, + { + "epoch": 0.97, + "learning_rate": 1.5637234066351984e-06, + "loss": 0.0929, + "step": 434220 + }, + { + "epoch": 0.97, + "learning_rate": 1.5626048634258744e-06, + "loss": 0.0882, + "step": 434230 + }, + { + "epoch": 0.97, + "learning_rate": 1.56148632021655e-06, + "loss": 0.0891, + "step": 434240 + }, + { + "epoch": 0.97, + "learning_rate": 1.5603677770072259e-06, + "loss": 0.0881, + "step": 434250 + }, + { + "epoch": 0.97, + "learning_rate": 1.559361088118834e-06, + "loss": 0.0933, + "step": 434260 + }, + { + "epoch": 0.97, + "learning_rate": 1.5582425449095098e-06, + "loss": 0.0936, + "step": 434270 + }, + { + "epoch": 0.97, + "learning_rate": 1.5571240017001858e-06, + "loss": 0.0917, + "step": 434280 + }, + { + "epoch": 0.97, + "learning_rate": 1.5560054584908616e-06, + "loss": 0.092, + "step": 434290 + }, + { + "epoch": 0.97, + "learning_rate": 1.5548869152815374e-06, + "loss": 0.0898, + "step": 434300 + }, + { + "epoch": 0.97, + "learning_rate": 1.5537683720722133e-06, + "loss": 0.0928, + "step": 434310 + }, + { + "epoch": 0.97, + "learning_rate": 1.552649828862889e-06, + "loss": 0.0958, + "step": 434320 + }, + { + "epoch": 0.97, + "learning_rate": 1.5515312856535649e-06, + "loss": 0.0924, + "step": 434330 + }, + { + "epoch": 0.97, + "learning_rate": 1.5504127424442407e-06, + "loss": 0.0934, + "step": 434340 + }, + { + "epoch": 0.97, + "learning_rate": 1.5492941992349165e-06, + "loss": 0.0946, + "step": 434350 + }, + { + "epoch": 0.97, + "learning_rate": 1.5481756560255923e-06, + "loss": 0.0907, + "step": 434360 + }, + { + "epoch": 0.97, + "learning_rate": 1.5470571128162681e-06, + "loss": 0.0902, + "step": 434370 + }, + { + "epoch": 0.97, + "learning_rate": 1.545938569606944e-06, + "loss": 0.0892, + "step": 434380 + }, + { + "epoch": 0.97, + "learning_rate": 1.5448200263976197e-06, + "loss": 0.0911, + "step": 434390 + }, + { + "epoch": 0.97, + "learning_rate": 1.5437014831882955e-06, + "loss": 0.0943, + "step": 434400 + }, + { + "epoch": 0.97, + "learning_rate": 1.5425829399789714e-06, + "loss": 0.0893, + "step": 434410 + }, + { + "epoch": 0.97, + "learning_rate": 1.5414643967696472e-06, + "loss": 0.0955, + "step": 434420 + }, + { + "epoch": 0.97, + "learning_rate": 1.5403458535603232e-06, + "loss": 0.0883, + "step": 434430 + }, + { + "epoch": 0.97, + "learning_rate": 1.539227310350999e-06, + "loss": 0.0922, + "step": 434440 + }, + { + "epoch": 0.97, + "learning_rate": 1.5381087671416748e-06, + "loss": 0.0906, + "step": 434450 + }, + { + "epoch": 0.97, + "learning_rate": 1.5369902239323506e-06, + "loss": 0.0944, + "step": 434460 + }, + { + "epoch": 0.97, + "learning_rate": 1.5358716807230264e-06, + "loss": 0.0932, + "step": 434470 + }, + { + "epoch": 0.97, + "learning_rate": 1.5347531375137022e-06, + "loss": 0.0925, + "step": 434480 + }, + { + "epoch": 0.97, + "learning_rate": 1.533634594304378e-06, + "loss": 0.0925, + "step": 434490 + }, + { + "epoch": 0.97, + "learning_rate": 1.5325160510950539e-06, + "loss": 0.0913, + "step": 434500 + }, + { + "epoch": 0.97, + "learning_rate": 1.5313975078857297e-06, + "loss": 0.0907, + "step": 434510 + }, + { + "epoch": 0.97, + "learning_rate": 1.5302789646764055e-06, + "loss": 0.0887, + "step": 434520 + }, + { + "epoch": 0.97, + "learning_rate": 1.5291604214670813e-06, + "loss": 0.0928, + "step": 434530 + }, + { + "epoch": 0.97, + "learning_rate": 1.528041878257757e-06, + "loss": 0.0881, + "step": 434540 + }, + { + "epoch": 0.97, + "learning_rate": 1.526923335048433e-06, + "loss": 0.0893, + "step": 434550 + }, + { + "epoch": 0.97, + "learning_rate": 1.5258047918391087e-06, + "loss": 0.0871, + "step": 434560 + }, + { + "epoch": 0.97, + "learning_rate": 1.5246862486297847e-06, + "loss": 0.0913, + "step": 434570 + }, + { + "epoch": 0.97, + "learning_rate": 1.5235677054204606e-06, + "loss": 0.0883, + "step": 434580 + }, + { + "epoch": 0.97, + "learning_rate": 1.5224491622111364e-06, + "loss": 0.0916, + "step": 434590 + }, + { + "epoch": 0.97, + "learning_rate": 1.5213306190018122e-06, + "loss": 0.0885, + "step": 434600 + }, + { + "epoch": 0.97, + "learning_rate": 1.520212075792488e-06, + "loss": 0.0902, + "step": 434610 + }, + { + "epoch": 0.97, + "learning_rate": 1.5190935325831638e-06, + "loss": 0.0914, + "step": 434620 + }, + { + "epoch": 0.97, + "learning_rate": 1.5179749893738396e-06, + "loss": 0.0902, + "step": 434630 + }, + { + "epoch": 0.97, + "learning_rate": 1.5168564461645154e-06, + "loss": 0.0895, + "step": 434640 + }, + { + "epoch": 0.97, + "learning_rate": 1.5157379029551912e-06, + "loss": 0.0941, + "step": 434650 + }, + { + "epoch": 0.97, + "learning_rate": 1.514619359745867e-06, + "loss": 0.0883, + "step": 434660 + }, + { + "epoch": 0.97, + "learning_rate": 1.5135008165365428e-06, + "loss": 0.0864, + "step": 434670 + }, + { + "epoch": 0.97, + "learning_rate": 1.5123822733272187e-06, + "loss": 0.0926, + "step": 434680 + }, + { + "epoch": 0.97, + "learning_rate": 1.5112637301178945e-06, + "loss": 0.0902, + "step": 434690 + }, + { + "epoch": 0.97, + "learning_rate": 1.5101451869085703e-06, + "loss": 0.0924, + "step": 434700 + }, + { + "epoch": 0.97, + "learning_rate": 1.509026643699246e-06, + "loss": 0.0884, + "step": 434710 + }, + { + "epoch": 0.97, + "learning_rate": 1.5079081004899221e-06, + "loss": 0.0911, + "step": 434720 + }, + { + "epoch": 0.97, + "learning_rate": 1.506789557280598e-06, + "loss": 0.0911, + "step": 434730 + }, + { + "epoch": 0.97, + "learning_rate": 1.5056710140712737e-06, + "loss": 0.0913, + "step": 434740 + }, + { + "epoch": 0.97, + "learning_rate": 1.5045524708619495e-06, + "loss": 0.0926, + "step": 434750 + }, + { + "epoch": 0.97, + "learning_rate": 1.5034339276526253e-06, + "loss": 0.0904, + "step": 434760 + }, + { + "epoch": 0.97, + "learning_rate": 1.5023153844433012e-06, + "loss": 0.0957, + "step": 434770 + }, + { + "epoch": 0.97, + "learning_rate": 1.501196841233977e-06, + "loss": 0.0903, + "step": 434780 + }, + { + "epoch": 0.97, + "learning_rate": 1.5000782980246528e-06, + "loss": 0.0914, + "step": 434790 + }, + { + "epoch": 0.97, + "learning_rate": 1.4989597548153286e-06, + "loss": 0.0893, + "step": 434800 + }, + { + "epoch": 0.97, + "learning_rate": 1.4978412116060044e-06, + "loss": 0.0915, + "step": 434810 + }, + { + "epoch": 0.97, + "learning_rate": 1.4967226683966802e-06, + "loss": 0.088, + "step": 434820 + }, + { + "epoch": 0.97, + "learning_rate": 1.495604125187356e-06, + "loss": 0.0925, + "step": 434830 + }, + { + "epoch": 0.97, + "learning_rate": 1.4944855819780318e-06, + "loss": 0.0916, + "step": 434840 + }, + { + "epoch": 0.97, + "learning_rate": 1.4933670387687076e-06, + "loss": 0.0897, + "step": 434850 + }, + { + "epoch": 0.97, + "learning_rate": 1.4922484955593834e-06, + "loss": 0.0939, + "step": 434860 + }, + { + "epoch": 0.97, + "learning_rate": 1.4911299523500595e-06, + "loss": 0.0899, + "step": 434870 + }, + { + "epoch": 0.97, + "learning_rate": 1.4900114091407353e-06, + "loss": 0.0889, + "step": 434880 + }, + { + "epoch": 0.97, + "learning_rate": 1.488892865931411e-06, + "loss": 0.0948, + "step": 434890 + }, + { + "epoch": 0.97, + "learning_rate": 1.487774322722087e-06, + "loss": 0.0943, + "step": 434900 + }, + { + "epoch": 0.97, + "learning_rate": 1.4866557795127627e-06, + "loss": 0.0925, + "step": 434910 + }, + { + "epoch": 0.97, + "learning_rate": 1.4855372363034385e-06, + "loss": 0.0899, + "step": 434920 + }, + { + "epoch": 0.97, + "learning_rate": 1.4844186930941143e-06, + "loss": 0.0937, + "step": 434930 + }, + { + "epoch": 0.97, + "learning_rate": 1.4833001498847901e-06, + "loss": 0.0943, + "step": 434940 + }, + { + "epoch": 0.97, + "learning_rate": 1.482181606675466e-06, + "loss": 0.09, + "step": 434950 + }, + { + "epoch": 0.97, + "learning_rate": 1.4810630634661418e-06, + "loss": 0.0892, + "step": 434960 + }, + { + "epoch": 0.97, + "learning_rate": 1.4799445202568176e-06, + "loss": 0.0915, + "step": 434970 + }, + { + "epoch": 0.97, + "learning_rate": 1.4788259770474934e-06, + "loss": 0.0892, + "step": 434980 + }, + { + "epoch": 0.97, + "learning_rate": 1.4777074338381692e-06, + "loss": 0.0914, + "step": 434990 + }, + { + "epoch": 0.97, + "learning_rate": 1.476588890628845e-06, + "loss": 0.0896, + "step": 435000 + }, + { + "epoch": 0.97, + "learning_rate": 1.4754703474195208e-06, + "loss": 0.0908, + "step": 435010 + }, + { + "epoch": 0.97, + "learning_rate": 1.4743518042101968e-06, + "loss": 0.0968, + "step": 435020 + }, + { + "epoch": 0.97, + "learning_rate": 1.4732332610008726e-06, + "loss": 0.0858, + "step": 435030 + }, + { + "epoch": 0.97, + "learning_rate": 1.4721147177915485e-06, + "loss": 0.0897, + "step": 435040 + }, + { + "epoch": 0.97, + "learning_rate": 1.4709961745822243e-06, + "loss": 0.0875, + "step": 435050 + }, + { + "epoch": 0.97, + "learning_rate": 1.4698776313729e-06, + "loss": 0.0915, + "step": 435060 + }, + { + "epoch": 0.97, + "learning_rate": 1.4687590881635759e-06, + "loss": 0.0918, + "step": 435070 + }, + { + "epoch": 0.97, + "learning_rate": 1.4676405449542517e-06, + "loss": 0.0912, + "step": 435080 + }, + { + "epoch": 0.97, + "learning_rate": 1.4665220017449275e-06, + "loss": 0.0903, + "step": 435090 + }, + { + "epoch": 0.97, + "learning_rate": 1.4654034585356033e-06, + "loss": 0.0879, + "step": 435100 + }, + { + "epoch": 0.97, + "learning_rate": 1.4642849153262791e-06, + "loss": 0.0909, + "step": 435110 + }, + { + "epoch": 0.97, + "learning_rate": 1.463166372116955e-06, + "loss": 0.0936, + "step": 435120 + }, + { + "epoch": 0.97, + "learning_rate": 1.4620478289076307e-06, + "loss": 0.0919, + "step": 435130 + }, + { + "epoch": 0.97, + "learning_rate": 1.4609292856983066e-06, + "loss": 0.0905, + "step": 435140 + }, + { + "epoch": 0.97, + "learning_rate": 1.4598107424889824e-06, + "loss": 0.0869, + "step": 435150 + }, + { + "epoch": 0.97, + "learning_rate": 1.4586921992796582e-06, + "loss": 0.0872, + "step": 435160 + }, + { + "epoch": 0.97, + "learning_rate": 1.4575736560703342e-06, + "loss": 0.0907, + "step": 435170 + }, + { + "epoch": 0.97, + "learning_rate": 1.45645511286101e-06, + "loss": 0.0926, + "step": 435180 + }, + { + "epoch": 0.97, + "learning_rate": 1.4553365696516858e-06, + "loss": 0.0905, + "step": 435190 + }, + { + "epoch": 0.97, + "learning_rate": 1.4542180264423616e-06, + "loss": 0.0942, + "step": 435200 + }, + { + "epoch": 0.97, + "learning_rate": 1.4530994832330374e-06, + "loss": 0.0902, + "step": 435210 + }, + { + "epoch": 0.97, + "learning_rate": 1.4519809400237132e-06, + "loss": 0.0893, + "step": 435220 + }, + { + "epoch": 0.97, + "learning_rate": 1.450862396814389e-06, + "loss": 0.0922, + "step": 435230 + }, + { + "epoch": 0.97, + "learning_rate": 1.4497438536050649e-06, + "loss": 0.0903, + "step": 435240 + }, + { + "epoch": 0.97, + "learning_rate": 1.4486253103957407e-06, + "loss": 0.0936, + "step": 435250 + }, + { + "epoch": 0.97, + "learning_rate": 1.4475067671864165e-06, + "loss": 0.0901, + "step": 435260 + }, + { + "epoch": 0.97, + "learning_rate": 1.4463882239770923e-06, + "loss": 0.0945, + "step": 435270 + }, + { + "epoch": 0.97, + "learning_rate": 1.4452696807677681e-06, + "loss": 0.0916, + "step": 435280 + }, + { + "epoch": 0.97, + "learning_rate": 1.444151137558444e-06, + "loss": 0.0882, + "step": 435290 + }, + { + "epoch": 0.97, + "learning_rate": 1.4430325943491197e-06, + "loss": 0.0918, + "step": 435300 + }, + { + "epoch": 0.97, + "learning_rate": 1.4419140511397955e-06, + "loss": 0.0924, + "step": 435310 + }, + { + "epoch": 0.97, + "learning_rate": 1.4407955079304716e-06, + "loss": 0.0871, + "step": 435320 + }, + { + "epoch": 0.97, + "learning_rate": 1.4396769647211474e-06, + "loss": 0.093, + "step": 435330 + }, + { + "epoch": 0.97, + "learning_rate": 1.4385584215118232e-06, + "loss": 0.0898, + "step": 435340 + }, + { + "epoch": 0.97, + "learning_rate": 1.437439878302499e-06, + "loss": 0.0909, + "step": 435350 + }, + { + "epoch": 0.97, + "learning_rate": 1.4363213350931748e-06, + "loss": 0.0935, + "step": 435360 + }, + { + "epoch": 0.97, + "learning_rate": 1.4352027918838506e-06, + "loss": 0.0894, + "step": 435370 + }, + { + "epoch": 0.97, + "learning_rate": 1.4340842486745264e-06, + "loss": 0.0926, + "step": 435380 + }, + { + "epoch": 0.97, + "learning_rate": 1.4329657054652022e-06, + "loss": 0.0942, + "step": 435390 + }, + { + "epoch": 0.97, + "learning_rate": 1.431847162255878e-06, + "loss": 0.0905, + "step": 435400 + }, + { + "epoch": 0.97, + "learning_rate": 1.4307286190465539e-06, + "loss": 0.0946, + "step": 435410 + }, + { + "epoch": 0.97, + "learning_rate": 1.4296100758372297e-06, + "loss": 0.0887, + "step": 435420 + }, + { + "epoch": 0.97, + "learning_rate": 1.4284915326279055e-06, + "loss": 0.0924, + "step": 435430 + }, + { + "epoch": 0.97, + "learning_rate": 1.4273729894185813e-06, + "loss": 0.0939, + "step": 435440 + }, + { + "epoch": 0.97, + "learning_rate": 1.426254446209257e-06, + "loss": 0.0905, + "step": 435450 + }, + { + "epoch": 0.97, + "learning_rate": 1.425135902999933e-06, + "loss": 0.0892, + "step": 435460 + }, + { + "epoch": 0.97, + "learning_rate": 1.424017359790609e-06, + "loss": 0.0875, + "step": 435470 + }, + { + "epoch": 0.97, + "learning_rate": 1.4228988165812847e-06, + "loss": 0.0931, + "step": 435480 + }, + { + "epoch": 0.97, + "learning_rate": 1.4217802733719605e-06, + "loss": 0.0969, + "step": 435490 + }, + { + "epoch": 0.97, + "learning_rate": 1.4206617301626364e-06, + "loss": 0.092, + "step": 435500 + }, + { + "epoch": 0.97, + "learning_rate": 1.4195431869533122e-06, + "loss": 0.0889, + "step": 435510 + }, + { + "epoch": 0.97, + "learning_rate": 1.418424643743988e-06, + "loss": 0.0917, + "step": 435520 + }, + { + "epoch": 0.97, + "learning_rate": 1.4173061005346638e-06, + "loss": 0.0896, + "step": 435530 + }, + { + "epoch": 0.97, + "learning_rate": 1.4161875573253396e-06, + "loss": 0.0893, + "step": 435540 + }, + { + "epoch": 0.97, + "learning_rate": 1.4150690141160154e-06, + "loss": 0.0913, + "step": 435550 + }, + { + "epoch": 0.97, + "learning_rate": 1.4139504709066912e-06, + "loss": 0.0929, + "step": 435560 + }, + { + "epoch": 0.97, + "learning_rate": 1.412831927697367e-06, + "loss": 0.0917, + "step": 435570 + }, + { + "epoch": 0.97, + "learning_rate": 1.4117133844880428e-06, + "loss": 0.0909, + "step": 435580 + }, + { + "epoch": 0.97, + "learning_rate": 1.4105948412787186e-06, + "loss": 0.0938, + "step": 435590 + }, + { + "epoch": 0.97, + "learning_rate": 1.4094762980693945e-06, + "loss": 0.0891, + "step": 435600 + }, + { + "epoch": 0.97, + "learning_rate": 1.4083577548600703e-06, + "loss": 0.0905, + "step": 435610 + }, + { + "epoch": 0.97, + "learning_rate": 1.4072392116507463e-06, + "loss": 0.0881, + "step": 435620 + }, + { + "epoch": 0.97, + "learning_rate": 1.406120668441422e-06, + "loss": 0.0882, + "step": 435630 + }, + { + "epoch": 0.97, + "learning_rate": 1.405002125232098e-06, + "loss": 0.0908, + "step": 435640 + }, + { + "epoch": 0.97, + "learning_rate": 1.4038835820227737e-06, + "loss": 0.0937, + "step": 435650 + }, + { + "epoch": 0.97, + "learning_rate": 1.4027650388134495e-06, + "loss": 0.0911, + "step": 435660 + }, + { + "epoch": 0.97, + "learning_rate": 1.4016464956041253e-06, + "loss": 0.0939, + "step": 435670 + }, + { + "epoch": 0.97, + "learning_rate": 1.4005279523948011e-06, + "loss": 0.0933, + "step": 435680 + }, + { + "epoch": 0.97, + "learning_rate": 1.399409409185477e-06, + "loss": 0.0893, + "step": 435690 + }, + { + "epoch": 0.97, + "learning_rate": 1.3982908659761528e-06, + "loss": 0.0864, + "step": 435700 + }, + { + "epoch": 0.97, + "learning_rate": 1.3971723227668286e-06, + "loss": 0.0864, + "step": 435710 + }, + { + "epoch": 0.97, + "learning_rate": 1.3960537795575044e-06, + "loss": 0.0845, + "step": 435720 + }, + { + "epoch": 0.97, + "learning_rate": 1.3949352363481802e-06, + "loss": 0.0908, + "step": 435730 + }, + { + "epoch": 0.97, + "learning_rate": 1.393816693138856e-06, + "loss": 0.0893, + "step": 435740 + }, + { + "epoch": 0.97, + "learning_rate": 1.3926981499295318e-06, + "loss": 0.0874, + "step": 435750 + }, + { + "epoch": 0.97, + "learning_rate": 1.3915796067202076e-06, + "loss": 0.0918, + "step": 435760 + }, + { + "epoch": 0.97, + "learning_rate": 1.3904610635108837e-06, + "loss": 0.0889, + "step": 435770 + }, + { + "epoch": 0.97, + "learning_rate": 1.3893425203015595e-06, + "loss": 0.0889, + "step": 435780 + }, + { + "epoch": 0.97, + "learning_rate": 1.3882239770922353e-06, + "loss": 0.092, + "step": 435790 + }, + { + "epoch": 0.97, + "learning_rate": 1.387105433882911e-06, + "loss": 0.0919, + "step": 435800 + }, + { + "epoch": 0.97, + "learning_rate": 1.3859868906735869e-06, + "loss": 0.0931, + "step": 435810 + }, + { + "epoch": 0.97, + "learning_rate": 1.3848683474642627e-06, + "loss": 0.0926, + "step": 435820 + }, + { + "epoch": 0.97, + "learning_rate": 1.3837498042549385e-06, + "loss": 0.0911, + "step": 435830 + }, + { + "epoch": 0.97, + "learning_rate": 1.3826312610456143e-06, + "loss": 0.0959, + "step": 435840 + }, + { + "epoch": 0.97, + "learning_rate": 1.3815127178362901e-06, + "loss": 0.0903, + "step": 435850 + }, + { + "epoch": 0.97, + "learning_rate": 1.380394174626966e-06, + "loss": 0.0921, + "step": 435860 + }, + { + "epoch": 0.97, + "learning_rate": 1.3792756314176418e-06, + "loss": 0.0879, + "step": 435870 + }, + { + "epoch": 0.97, + "learning_rate": 1.3781570882083176e-06, + "loss": 0.0914, + "step": 435880 + }, + { + "epoch": 0.97, + "learning_rate": 1.3770385449989934e-06, + "loss": 0.0937, + "step": 435890 + }, + { + "epoch": 0.97, + "learning_rate": 1.3759200017896692e-06, + "loss": 0.0925, + "step": 435900 + }, + { + "epoch": 0.97, + "learning_rate": 1.374801458580345e-06, + "loss": 0.0932, + "step": 435910 + }, + { + "epoch": 0.97, + "learning_rate": 1.373682915371021e-06, + "loss": 0.0862, + "step": 435920 + }, + { + "epoch": 0.97, + "learning_rate": 1.3725643721616968e-06, + "loss": 0.0914, + "step": 435930 + }, + { + "epoch": 0.97, + "learning_rate": 1.3714458289523726e-06, + "loss": 0.0887, + "step": 435940 + }, + { + "epoch": 0.97, + "learning_rate": 1.3703272857430484e-06, + "loss": 0.0919, + "step": 435950 + }, + { + "epoch": 0.97, + "learning_rate": 1.3692087425337243e-06, + "loss": 0.0895, + "step": 435960 + }, + { + "epoch": 0.97, + "learning_rate": 1.3680901993244e-06, + "loss": 0.0901, + "step": 435970 + }, + { + "epoch": 0.97, + "learning_rate": 1.3669716561150759e-06, + "loss": 0.0921, + "step": 435980 + }, + { + "epoch": 0.97, + "learning_rate": 1.3658531129057517e-06, + "loss": 0.0901, + "step": 435990 + }, + { + "epoch": 0.97, + "learning_rate": 1.3647345696964275e-06, + "loss": 0.0941, + "step": 436000 + }, + { + "epoch": 0.97, + "learning_rate": 1.3636160264871033e-06, + "loss": 0.0927, + "step": 436010 + }, + { + "epoch": 0.97, + "learning_rate": 1.3624974832777791e-06, + "loss": 0.0876, + "step": 436020 + }, + { + "epoch": 0.97, + "learning_rate": 1.361378940068455e-06, + "loss": 0.0889, + "step": 436030 + }, + { + "epoch": 0.97, + "learning_rate": 1.3602603968591307e-06, + "loss": 0.0895, + "step": 436040 + }, + { + "epoch": 0.97, + "learning_rate": 1.3591418536498065e-06, + "loss": 0.0948, + "step": 436050 + }, + { + "epoch": 0.97, + "learning_rate": 1.3580233104404824e-06, + "loss": 0.0871, + "step": 436060 + }, + { + "epoch": 0.97, + "learning_rate": 1.3569047672311584e-06, + "loss": 0.088, + "step": 436070 + }, + { + "epoch": 0.97, + "learning_rate": 1.3557862240218342e-06, + "loss": 0.0927, + "step": 436080 + }, + { + "epoch": 0.97, + "learning_rate": 1.35466768081251e-06, + "loss": 0.0911, + "step": 436090 + }, + { + "epoch": 0.97, + "learning_rate": 1.3535491376031858e-06, + "loss": 0.0901, + "step": 436100 + }, + { + "epoch": 0.97, + "learning_rate": 1.3524305943938616e-06, + "loss": 0.0891, + "step": 436110 + }, + { + "epoch": 0.97, + "learning_rate": 1.3513120511845374e-06, + "loss": 0.0904, + "step": 436120 + }, + { + "epoch": 0.97, + "learning_rate": 1.3501935079752132e-06, + "loss": 0.0917, + "step": 436130 + }, + { + "epoch": 0.97, + "learning_rate": 1.349074964765889e-06, + "loss": 0.0909, + "step": 436140 + }, + { + "epoch": 0.97, + "learning_rate": 1.3479564215565649e-06, + "loss": 0.0886, + "step": 436150 + }, + { + "epoch": 0.97, + "learning_rate": 1.3468378783472407e-06, + "loss": 0.0918, + "step": 436160 + }, + { + "epoch": 0.97, + "learning_rate": 1.3457193351379165e-06, + "loss": 0.0945, + "step": 436170 + }, + { + "epoch": 0.97, + "learning_rate": 1.3446007919285923e-06, + "loss": 0.0917, + "step": 436180 + }, + { + "epoch": 0.97, + "learning_rate": 1.343482248719268e-06, + "loss": 0.0903, + "step": 436190 + }, + { + "epoch": 0.97, + "learning_rate": 1.342363705509944e-06, + "loss": 0.093, + "step": 436200 + }, + { + "epoch": 0.97, + "learning_rate": 1.3412451623006197e-06, + "loss": 0.0907, + "step": 436210 + }, + { + "epoch": 0.97, + "learning_rate": 1.3401266190912957e-06, + "loss": 0.0889, + "step": 436220 + }, + { + "epoch": 0.97, + "learning_rate": 1.3390080758819715e-06, + "loss": 0.092, + "step": 436230 + }, + { + "epoch": 0.97, + "learning_rate": 1.3378895326726474e-06, + "loss": 0.0926, + "step": 436240 + }, + { + "epoch": 0.97, + "learning_rate": 1.3367709894633232e-06, + "loss": 0.0933, + "step": 436250 + }, + { + "epoch": 0.97, + "learning_rate": 1.335652446253999e-06, + "loss": 0.0943, + "step": 436260 + }, + { + "epoch": 0.97, + "learning_rate": 1.3345339030446748e-06, + "loss": 0.0934, + "step": 436270 + }, + { + "epoch": 0.97, + "learning_rate": 1.3334153598353506e-06, + "loss": 0.0915, + "step": 436280 + }, + { + "epoch": 0.97, + "learning_rate": 1.3322968166260262e-06, + "loss": 0.0882, + "step": 436290 + }, + { + "epoch": 0.97, + "learning_rate": 1.3312901277376346e-06, + "loss": 0.0895, + "step": 436300 + }, + { + "epoch": 0.97, + "learning_rate": 1.3301715845283104e-06, + "loss": 0.0901, + "step": 436310 + }, + { + "epoch": 0.97, + "learning_rate": 1.3290530413189862e-06, + "loss": 0.0923, + "step": 436320 + }, + { + "epoch": 0.97, + "learning_rate": 1.327934498109662e-06, + "loss": 0.0934, + "step": 436330 + }, + { + "epoch": 0.97, + "learning_rate": 1.3268159549003378e-06, + "loss": 0.0984, + "step": 436340 + }, + { + "epoch": 0.97, + "learning_rate": 1.3256974116910136e-06, + "loss": 0.0921, + "step": 436350 + }, + { + "epoch": 0.97, + "learning_rate": 1.3245788684816894e-06, + "loss": 0.0882, + "step": 436360 + }, + { + "epoch": 0.97, + "learning_rate": 1.3234603252723652e-06, + "loss": 0.0938, + "step": 436370 + }, + { + "epoch": 0.97, + "learning_rate": 1.322341782063041e-06, + "loss": 0.0912, + "step": 436380 + }, + { + "epoch": 0.97, + "learning_rate": 1.3212232388537168e-06, + "loss": 0.0912, + "step": 436390 + }, + { + "epoch": 0.97, + "learning_rate": 1.3201046956443927e-06, + "loss": 0.0899, + "step": 436400 + }, + { + "epoch": 0.97, + "learning_rate": 1.3189861524350685e-06, + "loss": 0.0922, + "step": 436410 + }, + { + "epoch": 0.97, + "learning_rate": 1.3178676092257445e-06, + "loss": 0.0868, + "step": 436420 + }, + { + "epoch": 0.97, + "learning_rate": 1.3167490660164203e-06, + "loss": 0.0943, + "step": 436430 + }, + { + "epoch": 0.97, + "learning_rate": 1.3156305228070961e-06, + "loss": 0.0884, + "step": 436440 + }, + { + "epoch": 0.97, + "learning_rate": 1.314511979597772e-06, + "loss": 0.0941, + "step": 436450 + }, + { + "epoch": 0.97, + "learning_rate": 1.3133934363884477e-06, + "loss": 0.0888, + "step": 436460 + }, + { + "epoch": 0.97, + "learning_rate": 1.3122748931791235e-06, + "loss": 0.0902, + "step": 436470 + }, + { + "epoch": 0.97, + "learning_rate": 1.3111563499697993e-06, + "loss": 0.0876, + "step": 436480 + }, + { + "epoch": 0.97, + "learning_rate": 1.3100378067604752e-06, + "loss": 0.0892, + "step": 436490 + }, + { + "epoch": 0.97, + "learning_rate": 1.308919263551151e-06, + "loss": 0.0922, + "step": 436500 + }, + { + "epoch": 0.97, + "learning_rate": 1.3078007203418268e-06, + "loss": 0.0873, + "step": 436510 + }, + { + "epoch": 0.97, + "learning_rate": 1.3066821771325026e-06, + "loss": 0.095, + "step": 436520 + }, + { + "epoch": 0.97, + "learning_rate": 1.3055636339231784e-06, + "loss": 0.0896, + "step": 436530 + }, + { + "epoch": 0.97, + "learning_rate": 1.3044450907138542e-06, + "loss": 0.0924, + "step": 436540 + }, + { + "epoch": 0.97, + "learning_rate": 1.30332654750453e-06, + "loss": 0.0895, + "step": 436550 + }, + { + "epoch": 0.97, + "learning_rate": 1.3022080042952058e-06, + "loss": 0.0891, + "step": 436560 + }, + { + "epoch": 0.97, + "learning_rate": 1.3010894610858819e-06, + "loss": 0.0908, + "step": 436570 + }, + { + "epoch": 0.97, + "learning_rate": 1.2999709178765577e-06, + "loss": 0.0908, + "step": 436580 + }, + { + "epoch": 0.97, + "learning_rate": 1.2988523746672335e-06, + "loss": 0.0929, + "step": 436590 + }, + { + "epoch": 0.97, + "learning_rate": 1.2977338314579093e-06, + "loss": 0.0872, + "step": 436600 + }, + { + "epoch": 0.97, + "learning_rate": 1.296615288248585e-06, + "loss": 0.0931, + "step": 436610 + }, + { + "epoch": 0.97, + "learning_rate": 1.295496745039261e-06, + "loss": 0.0863, + "step": 436620 + }, + { + "epoch": 0.97, + "learning_rate": 1.2943782018299367e-06, + "loss": 0.0888, + "step": 436630 + }, + { + "epoch": 0.97, + "learning_rate": 1.2932596586206125e-06, + "loss": 0.0883, + "step": 436640 + }, + { + "epoch": 0.97, + "learning_rate": 1.2921411154112883e-06, + "loss": 0.0896, + "step": 436650 + }, + { + "epoch": 0.97, + "learning_rate": 1.2910225722019641e-06, + "loss": 0.0901, + "step": 436660 + }, + { + "epoch": 0.97, + "learning_rate": 1.28990402899264e-06, + "loss": 0.089, + "step": 436670 + }, + { + "epoch": 0.97, + "learning_rate": 1.2887854857833158e-06, + "loss": 0.0889, + "step": 436680 + }, + { + "epoch": 0.97, + "learning_rate": 1.2876669425739916e-06, + "loss": 0.0912, + "step": 436690 + }, + { + "epoch": 0.97, + "learning_rate": 1.2865483993646674e-06, + "loss": 0.0912, + "step": 436700 + }, + { + "epoch": 0.97, + "learning_rate": 1.2854298561553432e-06, + "loss": 0.0912, + "step": 436710 + }, + { + "epoch": 0.97, + "learning_rate": 1.2843113129460192e-06, + "loss": 0.0861, + "step": 436720 + }, + { + "epoch": 0.97, + "learning_rate": 1.283192769736695e-06, + "loss": 0.0898, + "step": 436730 + }, + { + "epoch": 0.97, + "learning_rate": 1.2820742265273708e-06, + "loss": 0.0934, + "step": 436740 + }, + { + "epoch": 0.97, + "learning_rate": 1.2809556833180466e-06, + "loss": 0.092, + "step": 436750 + }, + { + "epoch": 0.97, + "learning_rate": 1.2798371401087225e-06, + "loss": 0.0878, + "step": 436760 + }, + { + "epoch": 0.97, + "learning_rate": 1.2787185968993983e-06, + "loss": 0.0914, + "step": 436770 + }, + { + "epoch": 0.97, + "learning_rate": 1.277600053690074e-06, + "loss": 0.0902, + "step": 436780 + }, + { + "epoch": 0.97, + "learning_rate": 1.2764815104807499e-06, + "loss": 0.0918, + "step": 436790 + }, + { + "epoch": 0.97, + "learning_rate": 1.2753629672714257e-06, + "loss": 0.0877, + "step": 436800 + }, + { + "epoch": 0.98, + "learning_rate": 1.2742444240621015e-06, + "loss": 0.0932, + "step": 436810 + }, + { + "epoch": 0.98, + "learning_rate": 1.2731258808527773e-06, + "loss": 0.0925, + "step": 436820 + }, + { + "epoch": 0.98, + "learning_rate": 1.2720073376434531e-06, + "loss": 0.0915, + "step": 436830 + }, + { + "epoch": 0.98, + "learning_rate": 1.270888794434129e-06, + "loss": 0.0945, + "step": 436840 + }, + { + "epoch": 0.98, + "learning_rate": 1.2697702512248047e-06, + "loss": 0.092, + "step": 436850 + }, + { + "epoch": 0.98, + "learning_rate": 1.2686517080154806e-06, + "loss": 0.0929, + "step": 436860 + }, + { + "epoch": 0.98, + "learning_rate": 1.2675331648061566e-06, + "loss": 0.0916, + "step": 436870 + }, + { + "epoch": 0.98, + "learning_rate": 1.2664146215968324e-06, + "loss": 0.0939, + "step": 436880 + }, + { + "epoch": 0.98, + "learning_rate": 1.2652960783875082e-06, + "loss": 0.0888, + "step": 436890 + }, + { + "epoch": 0.98, + "learning_rate": 1.264177535178184e-06, + "loss": 0.0919, + "step": 436900 + }, + { + "epoch": 0.98, + "learning_rate": 1.2630589919688598e-06, + "loss": 0.0958, + "step": 436910 + }, + { + "epoch": 0.98, + "learning_rate": 1.2619404487595356e-06, + "loss": 0.0922, + "step": 436920 + }, + { + "epoch": 0.98, + "learning_rate": 1.2608219055502114e-06, + "loss": 0.0904, + "step": 436930 + }, + { + "epoch": 0.98, + "learning_rate": 1.2597033623408872e-06, + "loss": 0.0909, + "step": 436940 + }, + { + "epoch": 0.98, + "learning_rate": 1.258584819131563e-06, + "loss": 0.0925, + "step": 436950 + }, + { + "epoch": 0.98, + "learning_rate": 1.2574662759222389e-06, + "loss": 0.087, + "step": 436960 + }, + { + "epoch": 0.98, + "learning_rate": 1.2563477327129147e-06, + "loss": 0.0887, + "step": 436970 + }, + { + "epoch": 0.98, + "learning_rate": 1.2552291895035905e-06, + "loss": 0.092, + "step": 436980 + }, + { + "epoch": 0.98, + "learning_rate": 1.2541106462942663e-06, + "loss": 0.0893, + "step": 436990 + }, + { + "epoch": 0.98, + "learning_rate": 1.2529921030849421e-06, + "loss": 0.0887, + "step": 437000 + }, + { + "epoch": 0.98, + "learning_rate": 1.251873559875618e-06, + "loss": 0.0881, + "step": 437010 + }, + { + "epoch": 0.98, + "learning_rate": 1.250755016666294e-06, + "loss": 0.0897, + "step": 437020 + }, + { + "epoch": 0.98, + "learning_rate": 1.2496364734569698e-06, + "loss": 0.0915, + "step": 437030 + }, + { + "epoch": 0.98, + "learning_rate": 1.2485179302476456e-06, + "loss": 0.0934, + "step": 437040 + }, + { + "epoch": 0.98, + "learning_rate": 1.2473993870383214e-06, + "loss": 0.0924, + "step": 437050 + }, + { + "epoch": 0.98, + "learning_rate": 1.2462808438289972e-06, + "loss": 0.0915, + "step": 437060 + }, + { + "epoch": 0.98, + "learning_rate": 1.245162300619673e-06, + "loss": 0.0923, + "step": 437070 + }, + { + "epoch": 0.98, + "learning_rate": 1.2440437574103488e-06, + "loss": 0.0902, + "step": 437080 + }, + { + "epoch": 0.98, + "learning_rate": 1.2429252142010246e-06, + "loss": 0.0955, + "step": 437090 + }, + { + "epoch": 0.98, + "learning_rate": 1.2418066709917004e-06, + "loss": 0.0886, + "step": 437100 + }, + { + "epoch": 0.98, + "learning_rate": 1.2406881277823762e-06, + "loss": 0.0931, + "step": 437110 + }, + { + "epoch": 0.98, + "learning_rate": 1.239569584573052e-06, + "loss": 0.0895, + "step": 437120 + }, + { + "epoch": 0.98, + "learning_rate": 1.2384510413637279e-06, + "loss": 0.0933, + "step": 437130 + }, + { + "epoch": 0.98, + "learning_rate": 1.2373324981544037e-06, + "loss": 0.0882, + "step": 437140 + }, + { + "epoch": 0.98, + "learning_rate": 1.2362139549450795e-06, + "loss": 0.0922, + "step": 437150 + }, + { + "epoch": 0.98, + "learning_rate": 1.2350954117357553e-06, + "loss": 0.0921, + "step": 437160 + }, + { + "epoch": 0.98, + "learning_rate": 1.2339768685264313e-06, + "loss": 0.0904, + "step": 437170 + }, + { + "epoch": 0.98, + "learning_rate": 1.2328583253171071e-06, + "loss": 0.0901, + "step": 437180 + }, + { + "epoch": 0.98, + "learning_rate": 1.231739782107783e-06, + "loss": 0.0886, + "step": 437190 + }, + { + "epoch": 0.98, + "learning_rate": 1.2306212388984587e-06, + "loss": 0.0892, + "step": 437200 + }, + { + "epoch": 0.98, + "learning_rate": 1.2295026956891345e-06, + "loss": 0.0874, + "step": 437210 + }, + { + "epoch": 0.98, + "learning_rate": 1.2283841524798104e-06, + "loss": 0.088, + "step": 437220 + }, + { + "epoch": 0.98, + "learning_rate": 1.2272656092704862e-06, + "loss": 0.0851, + "step": 437230 + }, + { + "epoch": 0.98, + "learning_rate": 1.226147066061162e-06, + "loss": 0.0885, + "step": 437240 + }, + { + "epoch": 0.98, + "learning_rate": 1.2250285228518378e-06, + "loss": 0.0903, + "step": 437250 + }, + { + "epoch": 0.98, + "learning_rate": 1.2239099796425136e-06, + "loss": 0.0941, + "step": 437260 + }, + { + "epoch": 0.98, + "learning_rate": 1.2227914364331894e-06, + "loss": 0.0927, + "step": 437270 + }, + { + "epoch": 0.98, + "learning_rate": 1.2216728932238652e-06, + "loss": 0.0927, + "step": 437280 + }, + { + "epoch": 0.98, + "learning_rate": 1.220554350014541e-06, + "loss": 0.0905, + "step": 437290 + }, + { + "epoch": 0.98, + "learning_rate": 1.2194358068052168e-06, + "loss": 0.0919, + "step": 437300 + }, + { + "epoch": 0.98, + "learning_rate": 1.2183172635958929e-06, + "loss": 0.0919, + "step": 437310 + }, + { + "epoch": 0.98, + "learning_rate": 1.2171987203865687e-06, + "loss": 0.0899, + "step": 437320 + }, + { + "epoch": 0.98, + "learning_rate": 1.2160801771772445e-06, + "loss": 0.0888, + "step": 437330 + }, + { + "epoch": 0.98, + "learning_rate": 1.2149616339679203e-06, + "loss": 0.0928, + "step": 437340 + }, + { + "epoch": 0.98, + "learning_rate": 1.213843090758596e-06, + "loss": 0.09, + "step": 437350 + }, + { + "epoch": 0.98, + "learning_rate": 1.212724547549272e-06, + "loss": 0.0933, + "step": 437360 + }, + { + "epoch": 0.98, + "learning_rate": 1.2116060043399477e-06, + "loss": 0.0913, + "step": 437370 + }, + { + "epoch": 0.98, + "learning_rate": 1.2104874611306235e-06, + "loss": 0.0896, + "step": 437380 + }, + { + "epoch": 0.98, + "learning_rate": 1.2093689179212993e-06, + "loss": 0.0947, + "step": 437390 + }, + { + "epoch": 0.98, + "learning_rate": 1.2082503747119751e-06, + "loss": 0.0924, + "step": 437400 + }, + { + "epoch": 0.98, + "learning_rate": 1.207131831502651e-06, + "loss": 0.0877, + "step": 437410 + }, + { + "epoch": 0.98, + "learning_rate": 1.2060132882933268e-06, + "loss": 0.0907, + "step": 437420 + }, + { + "epoch": 0.98, + "learning_rate": 1.2048947450840026e-06, + "loss": 0.0943, + "step": 437430 + }, + { + "epoch": 0.98, + "learning_rate": 1.2037762018746784e-06, + "loss": 0.0895, + "step": 437440 + }, + { + "epoch": 0.98, + "learning_rate": 1.2026576586653542e-06, + "loss": 0.0893, + "step": 437450 + }, + { + "epoch": 0.98, + "learning_rate": 1.2015391154560302e-06, + "loss": 0.093, + "step": 437460 + }, + { + "epoch": 0.98, + "learning_rate": 1.200420572246706e-06, + "loss": 0.0908, + "step": 437470 + }, + { + "epoch": 0.98, + "learning_rate": 1.1993020290373818e-06, + "loss": 0.0907, + "step": 437480 + }, + { + "epoch": 0.98, + "learning_rate": 1.1981834858280577e-06, + "loss": 0.0937, + "step": 437490 + }, + { + "epoch": 0.98, + "learning_rate": 1.1970649426187335e-06, + "loss": 0.0885, + "step": 437500 + }, + { + "epoch": 0.98, + "learning_rate": 1.1959463994094093e-06, + "loss": 0.0857, + "step": 437510 + }, + { + "epoch": 0.98, + "learning_rate": 1.194827856200085e-06, + "loss": 0.0925, + "step": 437520 + }, + { + "epoch": 0.98, + "learning_rate": 1.1937093129907609e-06, + "loss": 0.0905, + "step": 437530 + }, + { + "epoch": 0.98, + "learning_rate": 1.1925907697814367e-06, + "loss": 0.091, + "step": 437540 + }, + { + "epoch": 0.98, + "learning_rate": 1.1914722265721125e-06, + "loss": 0.0892, + "step": 437550 + }, + { + "epoch": 0.98, + "learning_rate": 1.1903536833627883e-06, + "loss": 0.0933, + "step": 437560 + }, + { + "epoch": 0.98, + "learning_rate": 1.1892351401534641e-06, + "loss": 0.0869, + "step": 437570 + }, + { + "epoch": 0.98, + "learning_rate": 1.18811659694414e-06, + "loss": 0.0922, + "step": 437580 + }, + { + "epoch": 0.98, + "learning_rate": 1.1869980537348158e-06, + "loss": 0.0902, + "step": 437590 + }, + { + "epoch": 0.98, + "learning_rate": 1.1858795105254916e-06, + "loss": 0.0875, + "step": 437600 + }, + { + "epoch": 0.98, + "learning_rate": 1.1847609673161676e-06, + "loss": 0.0929, + "step": 437610 + }, + { + "epoch": 0.98, + "learning_rate": 1.1836424241068434e-06, + "loss": 0.0931, + "step": 437620 + }, + { + "epoch": 0.98, + "learning_rate": 1.1825238808975192e-06, + "loss": 0.0902, + "step": 437630 + }, + { + "epoch": 0.98, + "learning_rate": 1.181405337688195e-06, + "loss": 0.0966, + "step": 437640 + }, + { + "epoch": 0.98, + "learning_rate": 1.1802867944788708e-06, + "loss": 0.0898, + "step": 437650 + }, + { + "epoch": 0.98, + "learning_rate": 1.1791682512695466e-06, + "loss": 0.0908, + "step": 437660 + }, + { + "epoch": 0.98, + "learning_rate": 1.1780497080602224e-06, + "loss": 0.0874, + "step": 437670 + }, + { + "epoch": 0.98, + "learning_rate": 1.1769311648508983e-06, + "loss": 0.093, + "step": 437680 + }, + { + "epoch": 0.98, + "learning_rate": 1.175812621641574e-06, + "loss": 0.0895, + "step": 437690 + }, + { + "epoch": 0.98, + "learning_rate": 1.1746940784322499e-06, + "loss": 0.0893, + "step": 437700 + }, + { + "epoch": 0.98, + "learning_rate": 1.1735755352229257e-06, + "loss": 0.0913, + "step": 437710 + }, + { + "epoch": 0.98, + "learning_rate": 1.1724569920136015e-06, + "loss": 0.0915, + "step": 437720 + }, + { + "epoch": 0.98, + "learning_rate": 1.1713384488042773e-06, + "loss": 0.0906, + "step": 437730 + }, + { + "epoch": 0.98, + "learning_rate": 1.1702199055949531e-06, + "loss": 0.0888, + "step": 437740 + }, + { + "epoch": 0.98, + "learning_rate": 1.169101362385629e-06, + "loss": 0.0897, + "step": 437750 + }, + { + "epoch": 0.98, + "learning_rate": 1.167982819176305e-06, + "loss": 0.0865, + "step": 437760 + }, + { + "epoch": 0.98, + "learning_rate": 1.1668642759669808e-06, + "loss": 0.0879, + "step": 437770 + }, + { + "epoch": 0.98, + "learning_rate": 1.1657457327576566e-06, + "loss": 0.0931, + "step": 437780 + }, + { + "epoch": 0.98, + "learning_rate": 1.1646271895483324e-06, + "loss": 0.088, + "step": 437790 + }, + { + "epoch": 0.98, + "learning_rate": 1.1635086463390082e-06, + "loss": 0.0918, + "step": 437800 + }, + { + "epoch": 0.98, + "learning_rate": 1.162390103129684e-06, + "loss": 0.0897, + "step": 437810 + }, + { + "epoch": 0.98, + "learning_rate": 1.1612715599203598e-06, + "loss": 0.0905, + "step": 437820 + }, + { + "epoch": 0.98, + "learning_rate": 1.1601530167110356e-06, + "loss": 0.0881, + "step": 437830 + }, + { + "epoch": 0.98, + "learning_rate": 1.1590344735017114e-06, + "loss": 0.0886, + "step": 437840 + }, + { + "epoch": 0.98, + "learning_rate": 1.1579159302923872e-06, + "loss": 0.0866, + "step": 437850 + }, + { + "epoch": 0.98, + "learning_rate": 1.156797387083063e-06, + "loss": 0.0944, + "step": 437860 + }, + { + "epoch": 0.98, + "learning_rate": 1.1556788438737389e-06, + "loss": 0.0924, + "step": 437870 + }, + { + "epoch": 0.98, + "learning_rate": 1.1545603006644147e-06, + "loss": 0.0879, + "step": 437880 + }, + { + "epoch": 0.98, + "learning_rate": 1.1534417574550905e-06, + "loss": 0.0991, + "step": 437890 + }, + { + "epoch": 0.98, + "learning_rate": 1.1523232142457663e-06, + "loss": 0.089, + "step": 437900 + }, + { + "epoch": 0.98, + "learning_rate": 1.1512046710364423e-06, + "loss": 0.0931, + "step": 437910 + }, + { + "epoch": 0.98, + "learning_rate": 1.1500861278271181e-06, + "loss": 0.0883, + "step": 437920 + }, + { + "epoch": 0.98, + "learning_rate": 1.148967584617794e-06, + "loss": 0.0892, + "step": 437930 + }, + { + "epoch": 0.98, + "learning_rate": 1.1478490414084697e-06, + "loss": 0.0925, + "step": 437940 + }, + { + "epoch": 0.98, + "learning_rate": 1.1467304981991456e-06, + "loss": 0.0911, + "step": 437950 + }, + { + "epoch": 0.98, + "learning_rate": 1.1456119549898214e-06, + "loss": 0.093, + "step": 437960 + }, + { + "epoch": 0.98, + "learning_rate": 1.1444934117804972e-06, + "loss": 0.0917, + "step": 437970 + }, + { + "epoch": 0.98, + "learning_rate": 1.143374868571173e-06, + "loss": 0.0929, + "step": 437980 + }, + { + "epoch": 0.98, + "learning_rate": 1.1422563253618488e-06, + "loss": 0.0869, + "step": 437990 + }, + { + "epoch": 0.98, + "learning_rate": 1.1411377821525246e-06, + "loss": 0.0949, + "step": 438000 + }, + { + "epoch": 0.98, + "learning_rate": 1.1400192389432004e-06, + "loss": 0.094, + "step": 438010 + }, + { + "epoch": 0.98, + "learning_rate": 1.1389006957338762e-06, + "loss": 0.0917, + "step": 438020 + }, + { + "epoch": 0.98, + "learning_rate": 1.137782152524552e-06, + "loss": 0.0884, + "step": 438030 + }, + { + "epoch": 0.98, + "learning_rate": 1.1366636093152278e-06, + "loss": 0.0894, + "step": 438040 + }, + { + "epoch": 0.98, + "learning_rate": 1.1355450661059037e-06, + "loss": 0.0906, + "step": 438050 + }, + { + "epoch": 0.98, + "learning_rate": 1.1344265228965797e-06, + "loss": 0.0916, + "step": 438060 + }, + { + "epoch": 0.98, + "learning_rate": 1.1333079796872555e-06, + "loss": 0.0883, + "step": 438070 + }, + { + "epoch": 0.98, + "learning_rate": 1.1321894364779313e-06, + "loss": 0.09, + "step": 438080 + }, + { + "epoch": 0.98, + "learning_rate": 1.131070893268607e-06, + "loss": 0.0912, + "step": 438090 + }, + { + "epoch": 0.98, + "learning_rate": 1.129952350059283e-06, + "loss": 0.0946, + "step": 438100 + }, + { + "epoch": 0.98, + "learning_rate": 1.1288338068499587e-06, + "loss": 0.0904, + "step": 438110 + }, + { + "epoch": 0.98, + "learning_rate": 1.1277152636406345e-06, + "loss": 0.0889, + "step": 438120 + }, + { + "epoch": 0.98, + "learning_rate": 1.1265967204313103e-06, + "loss": 0.0889, + "step": 438130 + }, + { + "epoch": 0.98, + "learning_rate": 1.1254781772219862e-06, + "loss": 0.0913, + "step": 438140 + }, + { + "epoch": 0.98, + "learning_rate": 1.124359634012662e-06, + "loss": 0.0945, + "step": 438150 + }, + { + "epoch": 0.98, + "learning_rate": 1.1232410908033378e-06, + "loss": 0.0862, + "step": 438160 + }, + { + "epoch": 0.98, + "learning_rate": 1.1221225475940136e-06, + "loss": 0.0892, + "step": 438170 + }, + { + "epoch": 0.98, + "learning_rate": 1.1210040043846894e-06, + "loss": 0.0909, + "step": 438180 + }, + { + "epoch": 0.98, + "learning_rate": 1.1198854611753652e-06, + "loss": 0.0881, + "step": 438190 + }, + { + "epoch": 0.98, + "learning_rate": 1.118766917966041e-06, + "loss": 0.0909, + "step": 438200 + }, + { + "epoch": 0.98, + "learning_rate": 1.117648374756717e-06, + "loss": 0.0923, + "step": 438210 + }, + { + "epoch": 0.98, + "learning_rate": 1.1165298315473928e-06, + "loss": 0.0926, + "step": 438220 + }, + { + "epoch": 0.98, + "learning_rate": 1.1154112883380687e-06, + "loss": 0.0909, + "step": 438230 + }, + { + "epoch": 0.98, + "learning_rate": 1.1142927451287445e-06, + "loss": 0.0961, + "step": 438240 + }, + { + "epoch": 0.98, + "learning_rate": 1.1131742019194203e-06, + "loss": 0.0931, + "step": 438250 + }, + { + "epoch": 0.98, + "learning_rate": 1.112055658710096e-06, + "loss": 0.0883, + "step": 438260 + }, + { + "epoch": 0.98, + "learning_rate": 1.110937115500772e-06, + "loss": 0.09, + "step": 438270 + }, + { + "epoch": 0.98, + "learning_rate": 1.1098185722914477e-06, + "loss": 0.0921, + "step": 438280 + }, + { + "epoch": 0.98, + "learning_rate": 1.1087000290821235e-06, + "loss": 0.093, + "step": 438290 + }, + { + "epoch": 0.98, + "learning_rate": 1.1075814858727993e-06, + "loss": 0.0886, + "step": 438300 + }, + { + "epoch": 0.98, + "learning_rate": 1.1064629426634751e-06, + "loss": 0.0915, + "step": 438310 + }, + { + "epoch": 0.98, + "learning_rate": 1.105344399454151e-06, + "loss": 0.0874, + "step": 438320 + }, + { + "epoch": 0.98, + "learning_rate": 1.1043377105657593e-06, + "loss": 0.0952, + "step": 438330 + }, + { + "epoch": 0.98, + "learning_rate": 1.1032191673564351e-06, + "loss": 0.0903, + "step": 438340 + }, + { + "epoch": 0.98, + "learning_rate": 1.102100624147111e-06, + "loss": 0.0896, + "step": 438350 + }, + { + "epoch": 0.98, + "learning_rate": 1.1009820809377867e-06, + "loss": 0.0913, + "step": 438360 + }, + { + "epoch": 0.98, + "learning_rate": 1.0998635377284625e-06, + "loss": 0.0899, + "step": 438370 + }, + { + "epoch": 0.98, + "learning_rate": 1.0987449945191384e-06, + "loss": 0.089, + "step": 438380 + }, + { + "epoch": 0.98, + "learning_rate": 1.0976264513098142e-06, + "loss": 0.0915, + "step": 438390 + }, + { + "epoch": 0.98, + "learning_rate": 1.09650790810049e-06, + "loss": 0.0919, + "step": 438400 + }, + { + "epoch": 0.98, + "learning_rate": 1.0953893648911658e-06, + "loss": 0.0927, + "step": 438410 + }, + { + "epoch": 0.98, + "learning_rate": 1.0942708216818416e-06, + "loss": 0.0931, + "step": 438420 + }, + { + "epoch": 0.98, + "learning_rate": 1.0931522784725174e-06, + "loss": 0.09, + "step": 438430 + }, + { + "epoch": 0.98, + "learning_rate": 1.0920337352631934e-06, + "loss": 0.0979, + "step": 438440 + }, + { + "epoch": 0.98, + "learning_rate": 1.0909151920538692e-06, + "loss": 0.0936, + "step": 438450 + }, + { + "epoch": 0.98, + "learning_rate": 1.089796648844545e-06, + "loss": 0.0872, + "step": 438460 + }, + { + "epoch": 0.98, + "learning_rate": 1.0886781056352209e-06, + "loss": 0.0854, + "step": 438470 + }, + { + "epoch": 0.98, + "learning_rate": 1.0875595624258967e-06, + "loss": 0.0932, + "step": 438480 + }, + { + "epoch": 0.98, + "learning_rate": 1.0864410192165725e-06, + "loss": 0.0884, + "step": 438490 + }, + { + "epoch": 0.98, + "learning_rate": 1.0853224760072483e-06, + "loss": 0.0863, + "step": 438500 + }, + { + "epoch": 0.98, + "learning_rate": 1.084203932797924e-06, + "loss": 0.0918, + "step": 438510 + }, + { + "epoch": 0.98, + "learning_rate": 1.0830853895886e-06, + "loss": 0.0912, + "step": 438520 + }, + { + "epoch": 0.98, + "learning_rate": 1.0819668463792757e-06, + "loss": 0.0928, + "step": 438530 + }, + { + "epoch": 0.98, + "learning_rate": 1.0808483031699515e-06, + "loss": 0.0895, + "step": 438540 + }, + { + "epoch": 0.98, + "learning_rate": 1.0797297599606273e-06, + "loss": 0.0879, + "step": 438550 + }, + { + "epoch": 0.98, + "learning_rate": 1.0786112167513031e-06, + "loss": 0.093, + "step": 438560 + }, + { + "epoch": 0.98, + "learning_rate": 1.077492673541979e-06, + "loss": 0.0922, + "step": 438570 + }, + { + "epoch": 0.98, + "learning_rate": 1.0763741303326548e-06, + "loss": 0.0946, + "step": 438580 + }, + { + "epoch": 0.98, + "learning_rate": 1.0752555871233308e-06, + "loss": 0.0917, + "step": 438590 + }, + { + "epoch": 0.98, + "learning_rate": 1.0741370439140066e-06, + "loss": 0.0957, + "step": 438600 + }, + { + "epoch": 0.98, + "learning_rate": 1.0730185007046824e-06, + "loss": 0.0939, + "step": 438610 + }, + { + "epoch": 0.98, + "learning_rate": 1.0718999574953582e-06, + "loss": 0.0894, + "step": 438620 + }, + { + "epoch": 0.98, + "learning_rate": 1.070781414286034e-06, + "loss": 0.0918, + "step": 438630 + }, + { + "epoch": 0.98, + "learning_rate": 1.0696628710767098e-06, + "loss": 0.091, + "step": 438640 + }, + { + "epoch": 0.98, + "learning_rate": 1.0685443278673857e-06, + "loss": 0.0923, + "step": 438650 + }, + { + "epoch": 0.98, + "learning_rate": 1.0674257846580615e-06, + "loss": 0.0864, + "step": 438660 + }, + { + "epoch": 0.98, + "learning_rate": 1.0663072414487373e-06, + "loss": 0.0912, + "step": 438670 + }, + { + "epoch": 0.98, + "learning_rate": 1.065188698239413e-06, + "loss": 0.0932, + "step": 438680 + }, + { + "epoch": 0.98, + "learning_rate": 1.0640701550300889e-06, + "loss": 0.0901, + "step": 438690 + }, + { + "epoch": 0.98, + "learning_rate": 1.0629516118207647e-06, + "loss": 0.0926, + "step": 438700 + }, + { + "epoch": 0.98, + "learning_rate": 1.0618330686114405e-06, + "loss": 0.0895, + "step": 438710 + }, + { + "epoch": 0.98, + "learning_rate": 1.0607145254021163e-06, + "loss": 0.095, + "step": 438720 + }, + { + "epoch": 0.98, + "learning_rate": 1.0595959821927921e-06, + "loss": 0.0877, + "step": 438730 + }, + { + "epoch": 0.98, + "learning_rate": 1.0584774389834682e-06, + "loss": 0.0895, + "step": 438740 + }, + { + "epoch": 0.98, + "learning_rate": 1.057358895774144e-06, + "loss": 0.0913, + "step": 438750 + }, + { + "epoch": 0.98, + "learning_rate": 1.0562403525648198e-06, + "loss": 0.0857, + "step": 438760 + }, + { + "epoch": 0.98, + "learning_rate": 1.0551218093554956e-06, + "loss": 0.0855, + "step": 438770 + }, + { + "epoch": 0.98, + "learning_rate": 1.0540032661461714e-06, + "loss": 0.0914, + "step": 438780 + }, + { + "epoch": 0.98, + "learning_rate": 1.0528847229368472e-06, + "loss": 0.0931, + "step": 438790 + }, + { + "epoch": 0.98, + "learning_rate": 1.051766179727523e-06, + "loss": 0.0947, + "step": 438800 + }, + { + "epoch": 0.98, + "learning_rate": 1.0506476365181988e-06, + "loss": 0.0867, + "step": 438810 + }, + { + "epoch": 0.98, + "learning_rate": 1.0495290933088746e-06, + "loss": 0.0948, + "step": 438820 + }, + { + "epoch": 0.98, + "learning_rate": 1.0484105500995504e-06, + "loss": 0.0911, + "step": 438830 + }, + { + "epoch": 0.98, + "learning_rate": 1.0472920068902263e-06, + "loss": 0.095, + "step": 438840 + }, + { + "epoch": 0.98, + "learning_rate": 1.046173463680902e-06, + "loss": 0.0873, + "step": 438850 + }, + { + "epoch": 0.98, + "learning_rate": 1.0450549204715779e-06, + "loss": 0.0927, + "step": 438860 + }, + { + "epoch": 0.98, + "learning_rate": 1.0439363772622537e-06, + "loss": 0.0907, + "step": 438870 + }, + { + "epoch": 0.98, + "learning_rate": 1.0428178340529295e-06, + "loss": 0.092, + "step": 438880 + }, + { + "epoch": 0.98, + "learning_rate": 1.0416992908436055e-06, + "loss": 0.0867, + "step": 438890 + }, + { + "epoch": 0.98, + "learning_rate": 1.0405807476342813e-06, + "loss": 0.0883, + "step": 438900 + }, + { + "epoch": 0.98, + "learning_rate": 1.0394622044249571e-06, + "loss": 0.091, + "step": 438910 + }, + { + "epoch": 0.98, + "learning_rate": 1.038343661215633e-06, + "loss": 0.0877, + "step": 438920 + }, + { + "epoch": 0.98, + "learning_rate": 1.0372251180063088e-06, + "loss": 0.0833, + "step": 438930 + }, + { + "epoch": 0.98, + "learning_rate": 1.0361065747969844e-06, + "loss": 0.0915, + "step": 438940 + }, + { + "epoch": 0.98, + "learning_rate": 1.0349880315876602e-06, + "loss": 0.0895, + "step": 438950 + }, + { + "epoch": 0.98, + "learning_rate": 1.033869488378336e-06, + "loss": 0.0917, + "step": 438960 + }, + { + "epoch": 0.98, + "learning_rate": 1.0327509451690118e-06, + "loss": 0.0921, + "step": 438970 + }, + { + "epoch": 0.98, + "learning_rate": 1.0316324019596876e-06, + "loss": 0.0956, + "step": 438980 + }, + { + "epoch": 0.98, + "learning_rate": 1.0305138587503634e-06, + "loss": 0.0918, + "step": 438990 + }, + { + "epoch": 0.98, + "learning_rate": 1.0293953155410392e-06, + "loss": 0.0889, + "step": 439000 + }, + { + "epoch": 0.98, + "learning_rate": 1.0282767723317152e-06, + "loss": 0.0924, + "step": 439010 + }, + { + "epoch": 0.98, + "learning_rate": 1.027158229122391e-06, + "loss": 0.0898, + "step": 439020 + }, + { + "epoch": 0.98, + "learning_rate": 1.0260396859130669e-06, + "loss": 0.0901, + "step": 439030 + }, + { + "epoch": 0.98, + "learning_rate": 1.0249211427037427e-06, + "loss": 0.0863, + "step": 439040 + }, + { + "epoch": 0.98, + "learning_rate": 1.0238025994944185e-06, + "loss": 0.0915, + "step": 439050 + }, + { + "epoch": 0.98, + "learning_rate": 1.0226840562850943e-06, + "loss": 0.0896, + "step": 439060 + }, + { + "epoch": 0.98, + "learning_rate": 1.02156551307577e-06, + "loss": 0.0861, + "step": 439070 + }, + { + "epoch": 0.98, + "learning_rate": 1.020446969866446e-06, + "loss": 0.0925, + "step": 439080 + }, + { + "epoch": 0.98, + "learning_rate": 1.0193284266571217e-06, + "loss": 0.0938, + "step": 439090 + }, + { + "epoch": 0.98, + "learning_rate": 1.0182098834477975e-06, + "loss": 0.0892, + "step": 439100 + }, + { + "epoch": 0.98, + "learning_rate": 1.0170913402384733e-06, + "loss": 0.0939, + "step": 439110 + }, + { + "epoch": 0.98, + "learning_rate": 1.0159727970291491e-06, + "loss": 0.0905, + "step": 439120 + }, + { + "epoch": 0.98, + "learning_rate": 1.014854253819825e-06, + "loss": 0.089, + "step": 439130 + }, + { + "epoch": 0.98, + "learning_rate": 1.0137357106105008e-06, + "loss": 0.0893, + "step": 439140 + }, + { + "epoch": 0.98, + "learning_rate": 1.0126171674011766e-06, + "loss": 0.0929, + "step": 439150 + }, + { + "epoch": 0.98, + "learning_rate": 1.0114986241918526e-06, + "loss": 0.0907, + "step": 439160 + }, + { + "epoch": 0.98, + "learning_rate": 1.0103800809825284e-06, + "loss": 0.0918, + "step": 439170 + }, + { + "epoch": 0.98, + "learning_rate": 1.0092615377732042e-06, + "loss": 0.0897, + "step": 439180 + }, + { + "epoch": 0.98, + "learning_rate": 1.00814299456388e-06, + "loss": 0.0908, + "step": 439190 + }, + { + "epoch": 0.98, + "learning_rate": 1.0070244513545558e-06, + "loss": 0.0917, + "step": 439200 + }, + { + "epoch": 0.98, + "learning_rate": 1.0059059081452317e-06, + "loss": 0.0912, + "step": 439210 + }, + { + "epoch": 0.98, + "learning_rate": 1.0047873649359075e-06, + "loss": 0.0886, + "step": 439220 + }, + { + "epoch": 0.98, + "learning_rate": 1.0036688217265833e-06, + "loss": 0.0872, + "step": 439230 + }, + { + "epoch": 0.98, + "learning_rate": 1.002550278517259e-06, + "loss": 0.0905, + "step": 439240 + }, + { + "epoch": 0.98, + "learning_rate": 1.0014317353079349e-06, + "loss": 0.0914, + "step": 439250 + }, + { + "epoch": 0.98, + "learning_rate": 1.0003131920986107e-06, + "loss": 0.0917, + "step": 439260 + }, + { + "epoch": 0.98, + "learning_rate": 9.991946488892865e-07, + "loss": 0.0911, + "step": 439270 + }, + { + "epoch": 0.98, + "learning_rate": 9.980761056799623e-07, + "loss": 0.0897, + "step": 439280 + }, + { + "epoch": 0.98, + "learning_rate": 9.969575624706381e-07, + "loss": 0.0915, + "step": 439290 + }, + { + "epoch": 0.98, + "learning_rate": 9.95839019261314e-07, + "loss": 0.0917, + "step": 439300 + }, + { + "epoch": 0.98, + "learning_rate": 9.9472047605199e-07, + "loss": 0.0853, + "step": 439310 + }, + { + "epoch": 0.98, + "learning_rate": 9.936019328426658e-07, + "loss": 0.094, + "step": 439320 + }, + { + "epoch": 0.98, + "learning_rate": 9.924833896333416e-07, + "loss": 0.0948, + "step": 439330 + }, + { + "epoch": 0.98, + "learning_rate": 9.913648464240174e-07, + "loss": 0.0962, + "step": 439340 + }, + { + "epoch": 0.98, + "learning_rate": 9.902463032146932e-07, + "loss": 0.0892, + "step": 439350 + }, + { + "epoch": 0.98, + "learning_rate": 9.89127760005369e-07, + "loss": 0.0938, + "step": 439360 + }, + { + "epoch": 0.98, + "learning_rate": 9.880092167960448e-07, + "loss": 0.0874, + "step": 439370 + }, + { + "epoch": 0.98, + "learning_rate": 9.868906735867206e-07, + "loss": 0.0975, + "step": 439380 + }, + { + "epoch": 0.98, + "learning_rate": 9.857721303773964e-07, + "loss": 0.0903, + "step": 439390 + }, + { + "epoch": 0.98, + "learning_rate": 9.846535871680723e-07, + "loss": 0.0887, + "step": 439400 + }, + { + "epoch": 0.98, + "learning_rate": 9.83535043958748e-07, + "loss": 0.0932, + "step": 439410 + }, + { + "epoch": 0.98, + "learning_rate": 9.824165007494239e-07, + "loss": 0.092, + "step": 439420 + }, + { + "epoch": 0.98, + "learning_rate": 9.812979575400997e-07, + "loss": 0.0885, + "step": 439430 + }, + { + "epoch": 0.98, + "learning_rate": 9.801794143307755e-07, + "loss": 0.0902, + "step": 439440 + }, + { + "epoch": 0.98, + "learning_rate": 9.790608711214513e-07, + "loss": 0.0881, + "step": 439450 + }, + { + "epoch": 0.98, + "learning_rate": 9.779423279121273e-07, + "loss": 0.087, + "step": 439460 + }, + { + "epoch": 0.98, + "learning_rate": 9.768237847028031e-07, + "loss": 0.0897, + "step": 439470 + }, + { + "epoch": 0.98, + "learning_rate": 9.75705241493479e-07, + "loss": 0.0925, + "step": 439480 + }, + { + "epoch": 0.98, + "learning_rate": 9.745866982841548e-07, + "loss": 0.0933, + "step": 439490 + }, + { + "epoch": 0.98, + "learning_rate": 9.734681550748306e-07, + "loss": 0.0921, + "step": 439500 + }, + { + "epoch": 0.98, + "learning_rate": 9.723496118655064e-07, + "loss": 0.0973, + "step": 439510 + }, + { + "epoch": 0.98, + "learning_rate": 9.712310686561822e-07, + "loss": 0.0943, + "step": 439520 + }, + { + "epoch": 0.98, + "learning_rate": 9.70112525446858e-07, + "loss": 0.0906, + "step": 439530 + }, + { + "epoch": 0.98, + "learning_rate": 9.689939822375338e-07, + "loss": 0.09, + "step": 439540 + }, + { + "epoch": 0.98, + "learning_rate": 9.678754390282096e-07, + "loss": 0.0939, + "step": 439550 + }, + { + "epoch": 0.98, + "learning_rate": 9.667568958188854e-07, + "loss": 0.0914, + "step": 439560 + }, + { + "epoch": 0.98, + "learning_rate": 9.656383526095612e-07, + "loss": 0.0928, + "step": 439570 + }, + { + "epoch": 0.98, + "learning_rate": 9.64519809400237e-07, + "loss": 0.0868, + "step": 439580 + }, + { + "epoch": 0.98, + "learning_rate": 9.634012661909129e-07, + "loss": 0.0906, + "step": 439590 + }, + { + "epoch": 0.98, + "learning_rate": 9.622827229815887e-07, + "loss": 0.0894, + "step": 439600 + }, + { + "epoch": 0.98, + "learning_rate": 9.611641797722647e-07, + "loss": 0.0896, + "step": 439610 + }, + { + "epoch": 0.98, + "learning_rate": 9.600456365629405e-07, + "loss": 0.0894, + "step": 439620 + }, + { + "epoch": 0.98, + "learning_rate": 9.589270933536163e-07, + "loss": 0.0942, + "step": 439630 + }, + { + "epoch": 0.98, + "learning_rate": 9.578085501442921e-07, + "loss": 0.0907, + "step": 439640 + }, + { + "epoch": 0.98, + "learning_rate": 9.56690006934968e-07, + "loss": 0.092, + "step": 439650 + }, + { + "epoch": 0.98, + "learning_rate": 9.555714637256437e-07, + "loss": 0.0923, + "step": 439660 + }, + { + "epoch": 0.98, + "learning_rate": 9.544529205163196e-07, + "loss": 0.0898, + "step": 439670 + }, + { + "epoch": 0.98, + "learning_rate": 9.533343773069954e-07, + "loss": 0.0928, + "step": 439680 + }, + { + "epoch": 0.98, + "learning_rate": 9.522158340976712e-07, + "loss": 0.0875, + "step": 439690 + }, + { + "epoch": 0.98, + "learning_rate": 9.51097290888347e-07, + "loss": 0.0881, + "step": 439700 + }, + { + "epoch": 0.98, + "learning_rate": 9.499787476790228e-07, + "loss": 0.0894, + "step": 439710 + }, + { + "epoch": 0.98, + "learning_rate": 9.488602044696987e-07, + "loss": 0.0926, + "step": 439720 + }, + { + "epoch": 0.98, + "learning_rate": 9.477416612603745e-07, + "loss": 0.0875, + "step": 439730 + }, + { + "epoch": 0.98, + "learning_rate": 9.466231180510503e-07, + "loss": 0.0903, + "step": 439740 + }, + { + "epoch": 0.98, + "learning_rate": 9.455045748417261e-07, + "loss": 0.0887, + "step": 439750 + }, + { + "epoch": 0.98, + "learning_rate": 9.44386031632402e-07, + "loss": 0.0909, + "step": 439760 + }, + { + "epoch": 0.98, + "learning_rate": 9.432674884230778e-07, + "loss": 0.0914, + "step": 439770 + }, + { + "epoch": 0.98, + "learning_rate": 9.421489452137536e-07, + "loss": 0.0913, + "step": 439780 + }, + { + "epoch": 0.98, + "learning_rate": 9.410304020044295e-07, + "loss": 0.0886, + "step": 439790 + }, + { + "epoch": 0.98, + "learning_rate": 9.399118587951053e-07, + "loss": 0.0909, + "step": 439800 + }, + { + "epoch": 0.98, + "learning_rate": 9.387933155857811e-07, + "loss": 0.0915, + "step": 439810 + }, + { + "epoch": 0.98, + "learning_rate": 9.376747723764569e-07, + "loss": 0.0935, + "step": 439820 + }, + { + "epoch": 0.98, + "learning_rate": 9.365562291671327e-07, + "loss": 0.0898, + "step": 439830 + }, + { + "epoch": 0.98, + "learning_rate": 9.354376859578085e-07, + "loss": 0.0938, + "step": 439840 + }, + { + "epoch": 0.98, + "learning_rate": 9.343191427484843e-07, + "loss": 0.0906, + "step": 439850 + }, + { + "epoch": 0.98, + "learning_rate": 9.332005995391602e-07, + "loss": 0.09, + "step": 439860 + }, + { + "epoch": 0.98, + "learning_rate": 9.320820563298361e-07, + "loss": 0.0919, + "step": 439870 + }, + { + "epoch": 0.98, + "learning_rate": 9.309635131205119e-07, + "loss": 0.0912, + "step": 439880 + }, + { + "epoch": 0.98, + "learning_rate": 9.298449699111877e-07, + "loss": 0.0927, + "step": 439890 + }, + { + "epoch": 0.98, + "learning_rate": 9.287264267018635e-07, + "loss": 0.0939, + "step": 439900 + }, + { + "epoch": 0.98, + "learning_rate": 9.276078834925393e-07, + "loss": 0.0954, + "step": 439910 + }, + { + "epoch": 0.98, + "learning_rate": 9.264893402832151e-07, + "loss": 0.0876, + "step": 439920 + }, + { + "epoch": 0.98, + "learning_rate": 9.253707970738909e-07, + "loss": 0.0934, + "step": 439930 + }, + { + "epoch": 0.98, + "learning_rate": 9.242522538645668e-07, + "loss": 0.0926, + "step": 439940 + }, + { + "epoch": 0.98, + "learning_rate": 9.231337106552427e-07, + "loss": 0.0904, + "step": 439950 + }, + { + "epoch": 0.98, + "learning_rate": 9.220151674459185e-07, + "loss": 0.0951, + "step": 439960 + }, + { + "epoch": 0.98, + "learning_rate": 9.208966242365943e-07, + "loss": 0.0924, + "step": 439970 + }, + { + "epoch": 0.98, + "learning_rate": 9.197780810272701e-07, + "loss": 0.0891, + "step": 439980 + }, + { + "epoch": 0.98, + "learning_rate": 9.186595378179459e-07, + "loss": 0.0947, + "step": 439990 + }, + { + "epoch": 0.98, + "learning_rate": 9.175409946086217e-07, + "loss": 0.0879, + "step": 440000 + }, + { + "epoch": 0.98, + "learning_rate": 9.164224513992975e-07, + "loss": 0.0926, + "step": 440010 + }, + { + "epoch": 0.98, + "learning_rate": 9.153039081899734e-07, + "loss": 0.0932, + "step": 440020 + }, + { + "epoch": 0.98, + "learning_rate": 9.141853649806492e-07, + "loss": 0.0898, + "step": 440030 + }, + { + "epoch": 0.98, + "learning_rate": 9.130668217713251e-07, + "loss": 0.0908, + "step": 440040 + }, + { + "epoch": 0.98, + "learning_rate": 9.119482785620009e-07, + "loss": 0.0898, + "step": 440050 + }, + { + "epoch": 0.98, + "learning_rate": 9.108297353526767e-07, + "loss": 0.0882, + "step": 440060 + }, + { + "epoch": 0.98, + "learning_rate": 9.097111921433525e-07, + "loss": 0.0881, + "step": 440070 + }, + { + "epoch": 0.98, + "learning_rate": 9.085926489340283e-07, + "loss": 0.0915, + "step": 440080 + }, + { + "epoch": 0.98, + "learning_rate": 9.074741057247042e-07, + "loss": 0.0902, + "step": 440090 + }, + { + "epoch": 0.98, + "learning_rate": 9.0635556251538e-07, + "loss": 0.087, + "step": 440100 + }, + { + "epoch": 0.98, + "learning_rate": 9.052370193060558e-07, + "loss": 0.0904, + "step": 440110 + }, + { + "epoch": 0.98, + "learning_rate": 9.041184760967316e-07, + "loss": 0.0934, + "step": 440120 + }, + { + "epoch": 0.98, + "learning_rate": 9.029999328874075e-07, + "loss": 0.0882, + "step": 440130 + }, + { + "epoch": 0.98, + "learning_rate": 9.018813896780833e-07, + "loss": 0.0886, + "step": 440140 + }, + { + "epoch": 0.98, + "learning_rate": 9.007628464687591e-07, + "loss": 0.0913, + "step": 440150 + }, + { + "epoch": 0.98, + "learning_rate": 8.996443032594349e-07, + "loss": 0.0886, + "step": 440160 + }, + { + "epoch": 0.98, + "learning_rate": 8.985257600501108e-07, + "loss": 0.0889, + "step": 440170 + }, + { + "epoch": 0.98, + "learning_rate": 8.974072168407866e-07, + "loss": 0.0875, + "step": 440180 + }, + { + "epoch": 0.98, + "learning_rate": 8.962886736314624e-07, + "loss": 0.092, + "step": 440190 + }, + { + "epoch": 0.98, + "learning_rate": 8.951701304221382e-07, + "loss": 0.091, + "step": 440200 + }, + { + "epoch": 0.98, + "learning_rate": 8.94051587212814e-07, + "loss": 0.0888, + "step": 440210 + }, + { + "epoch": 0.98, + "learning_rate": 8.929330440034898e-07, + "loss": 0.0873, + "step": 440220 + }, + { + "epoch": 0.98, + "learning_rate": 8.918145007941657e-07, + "loss": 0.0921, + "step": 440230 + }, + { + "epoch": 0.98, + "learning_rate": 8.906959575848416e-07, + "loss": 0.088, + "step": 440240 + }, + { + "epoch": 0.98, + "learning_rate": 8.895774143755174e-07, + "loss": 0.0928, + "step": 440250 + }, + { + "epoch": 0.98, + "learning_rate": 8.884588711661932e-07, + "loss": 0.0911, + "step": 440260 + }, + { + "epoch": 0.98, + "learning_rate": 8.87340327956869e-07, + "loss": 0.0921, + "step": 440270 + }, + { + "epoch": 0.98, + "learning_rate": 8.862217847475448e-07, + "loss": 0.0912, + "step": 440280 + }, + { + "epoch": 0.98, + "learning_rate": 8.851032415382206e-07, + "loss": 0.0891, + "step": 440290 + }, + { + "epoch": 0.98, + "learning_rate": 8.839846983288964e-07, + "loss": 0.0918, + "step": 440300 + }, + { + "epoch": 0.98, + "learning_rate": 8.828661551195722e-07, + "loss": 0.092, + "step": 440310 + }, + { + "epoch": 0.98, + "learning_rate": 8.817476119102482e-07, + "loss": 0.0894, + "step": 440320 + }, + { + "epoch": 0.98, + "learning_rate": 8.80629068700924e-07, + "loss": 0.0873, + "step": 440330 + }, + { + "epoch": 0.98, + "learning_rate": 8.796223798125322e-07, + "loss": 0.0915, + "step": 440340 + }, + { + "epoch": 0.98, + "learning_rate": 8.78503836603208e-07, + "loss": 0.0885, + "step": 440350 + }, + { + "epoch": 0.98, + "learning_rate": 8.773852933938838e-07, + "loss": 0.0944, + "step": 440360 + }, + { + "epoch": 0.98, + "learning_rate": 8.762667501845597e-07, + "loss": 0.0916, + "step": 440370 + }, + { + "epoch": 0.98, + "learning_rate": 8.751482069752355e-07, + "loss": 0.0909, + "step": 440380 + }, + { + "epoch": 0.98, + "learning_rate": 8.740296637659114e-07, + "loss": 0.0952, + "step": 440390 + }, + { + "epoch": 0.98, + "learning_rate": 8.729111205565872e-07, + "loss": 0.087, + "step": 440400 + }, + { + "epoch": 0.98, + "learning_rate": 8.71792577347263e-07, + "loss": 0.0873, + "step": 440410 + }, + { + "epoch": 0.98, + "learning_rate": 8.706740341379388e-07, + "loss": 0.0896, + "step": 440420 + }, + { + "epoch": 0.98, + "learning_rate": 8.695554909286146e-07, + "loss": 0.0919, + "step": 440430 + }, + { + "epoch": 0.98, + "learning_rate": 8.684369477192904e-07, + "loss": 0.0906, + "step": 440440 + }, + { + "epoch": 0.98, + "learning_rate": 8.673184045099662e-07, + "loss": 0.092, + "step": 440450 + }, + { + "epoch": 0.98, + "learning_rate": 8.66199861300642e-07, + "loss": 0.0876, + "step": 440460 + }, + { + "epoch": 0.98, + "learning_rate": 8.65081318091318e-07, + "loss": 0.0916, + "step": 440470 + }, + { + "epoch": 0.98, + "learning_rate": 8.639627748819938e-07, + "loss": 0.0885, + "step": 440480 + }, + { + "epoch": 0.98, + "learning_rate": 8.628442316726696e-07, + "loss": 0.0911, + "step": 440490 + }, + { + "epoch": 0.98, + "learning_rate": 8.617256884633454e-07, + "loss": 0.091, + "step": 440500 + }, + { + "epoch": 0.98, + "learning_rate": 8.606071452540212e-07, + "loss": 0.0917, + "step": 440510 + }, + { + "epoch": 0.98, + "learning_rate": 8.59488602044697e-07, + "loss": 0.0896, + "step": 440520 + }, + { + "epoch": 0.98, + "learning_rate": 8.583700588353728e-07, + "loss": 0.094, + "step": 440530 + }, + { + "epoch": 0.98, + "learning_rate": 8.572515156260487e-07, + "loss": 0.0924, + "step": 440540 + }, + { + "epoch": 0.98, + "learning_rate": 8.561329724167246e-07, + "loss": 0.0887, + "step": 440550 + }, + { + "epoch": 0.98, + "learning_rate": 8.550144292074004e-07, + "loss": 0.0906, + "step": 440560 + }, + { + "epoch": 0.98, + "learning_rate": 8.538958859980762e-07, + "loss": 0.0895, + "step": 440570 + }, + { + "epoch": 0.98, + "learning_rate": 8.52777342788752e-07, + "loss": 0.0906, + "step": 440580 + }, + { + "epoch": 0.98, + "learning_rate": 8.516587995794278e-07, + "loss": 0.0902, + "step": 440590 + }, + { + "epoch": 0.98, + "learning_rate": 8.505402563701036e-07, + "loss": 0.0935, + "step": 440600 + }, + { + "epoch": 0.98, + "learning_rate": 8.494217131607794e-07, + "loss": 0.0935, + "step": 440610 + }, + { + "epoch": 0.98, + "learning_rate": 8.483031699514553e-07, + "loss": 0.0917, + "step": 440620 + }, + { + "epoch": 0.98, + "learning_rate": 8.471846267421311e-07, + "loss": 0.0943, + "step": 440630 + }, + { + "epoch": 0.98, + "learning_rate": 8.46066083532807e-07, + "loss": 0.0907, + "step": 440640 + }, + { + "epoch": 0.98, + "learning_rate": 8.449475403234828e-07, + "loss": 0.0907, + "step": 440650 + }, + { + "epoch": 0.98, + "learning_rate": 8.438289971141586e-07, + "loss": 0.0896, + "step": 440660 + }, + { + "epoch": 0.98, + "learning_rate": 8.427104539048344e-07, + "loss": 0.0929, + "step": 440670 + }, + { + "epoch": 0.98, + "learning_rate": 8.415919106955102e-07, + "loss": 0.0894, + "step": 440680 + }, + { + "epoch": 0.98, + "learning_rate": 8.404733674861861e-07, + "loss": 0.0936, + "step": 440690 + }, + { + "epoch": 0.98, + "learning_rate": 8.393548242768619e-07, + "loss": 0.0951, + "step": 440700 + }, + { + "epoch": 0.98, + "learning_rate": 8.382362810675377e-07, + "loss": 0.0888, + "step": 440710 + }, + { + "epoch": 0.98, + "learning_rate": 8.371177378582135e-07, + "loss": 0.0908, + "step": 440720 + }, + { + "epoch": 0.98, + "learning_rate": 8.359991946488893e-07, + "loss": 0.0917, + "step": 440730 + }, + { + "epoch": 0.98, + "learning_rate": 8.348806514395652e-07, + "loss": 0.0881, + "step": 440740 + }, + { + "epoch": 0.98, + "learning_rate": 8.33762108230241e-07, + "loss": 0.0922, + "step": 440750 + }, + { + "epoch": 0.98, + "learning_rate": 8.326435650209168e-07, + "loss": 0.0908, + "step": 440760 + }, + { + "epoch": 0.98, + "learning_rate": 8.315250218115927e-07, + "loss": 0.0928, + "step": 440770 + }, + { + "epoch": 0.98, + "learning_rate": 8.304064786022685e-07, + "loss": 0.0863, + "step": 440780 + }, + { + "epoch": 0.98, + "learning_rate": 8.292879353929443e-07, + "loss": 0.0907, + "step": 440790 + }, + { + "epoch": 0.98, + "learning_rate": 8.281693921836201e-07, + "loss": 0.0938, + "step": 440800 + }, + { + "epoch": 0.98, + "learning_rate": 8.270508489742959e-07, + "loss": 0.0912, + "step": 440810 + }, + { + "epoch": 0.98, + "learning_rate": 8.259323057649717e-07, + "loss": 0.09, + "step": 440820 + }, + { + "epoch": 0.98, + "learning_rate": 8.248137625556476e-07, + "loss": 0.0939, + "step": 440830 + }, + { + "epoch": 0.98, + "learning_rate": 8.236952193463235e-07, + "loss": 0.0895, + "step": 440840 + }, + { + "epoch": 0.98, + "learning_rate": 8.225766761369993e-07, + "loss": 0.0907, + "step": 440850 + }, + { + "epoch": 0.98, + "learning_rate": 8.214581329276751e-07, + "loss": 0.0897, + "step": 440860 + }, + { + "epoch": 0.98, + "learning_rate": 8.203395897183509e-07, + "loss": 0.0918, + "step": 440870 + }, + { + "epoch": 0.98, + "learning_rate": 8.192210465090267e-07, + "loss": 0.0881, + "step": 440880 + }, + { + "epoch": 0.98, + "learning_rate": 8.181025032997025e-07, + "loss": 0.0907, + "step": 440890 + }, + { + "epoch": 0.98, + "learning_rate": 8.169839600903783e-07, + "loss": 0.0944, + "step": 440900 + }, + { + "epoch": 0.98, + "learning_rate": 8.158654168810541e-07, + "loss": 0.091, + "step": 440910 + }, + { + "epoch": 0.98, + "learning_rate": 8.147468736717301e-07, + "loss": 0.0916, + "step": 440920 + }, + { + "epoch": 0.98, + "learning_rate": 8.136283304624059e-07, + "loss": 0.0941, + "step": 440930 + }, + { + "epoch": 0.98, + "learning_rate": 8.125097872530817e-07, + "loss": 0.0926, + "step": 440940 + }, + { + "epoch": 0.98, + "learning_rate": 8.113912440437575e-07, + "loss": 0.0925, + "step": 440950 + }, + { + "epoch": 0.98, + "learning_rate": 8.102727008344333e-07, + "loss": 0.0889, + "step": 440960 + }, + { + "epoch": 0.98, + "learning_rate": 8.091541576251091e-07, + "loss": 0.0952, + "step": 440970 + }, + { + "epoch": 0.98, + "learning_rate": 8.080356144157849e-07, + "loss": 0.0864, + "step": 440980 + }, + { + "epoch": 0.98, + "learning_rate": 8.069170712064608e-07, + "loss": 0.0905, + "step": 440990 + }, + { + "epoch": 0.98, + "learning_rate": 8.057985279971366e-07, + "loss": 0.0913, + "step": 441000 + }, + { + "epoch": 0.98, + "learning_rate": 8.046799847878125e-07, + "loss": 0.0913, + "step": 441010 + }, + { + "epoch": 0.98, + "learning_rate": 8.035614415784883e-07, + "loss": 0.0923, + "step": 441020 + }, + { + "epoch": 0.98, + "learning_rate": 8.024428983691641e-07, + "loss": 0.0939, + "step": 441030 + }, + { + "epoch": 0.98, + "learning_rate": 8.013243551598399e-07, + "loss": 0.0895, + "step": 441040 + }, + { + "epoch": 0.98, + "learning_rate": 8.002058119505157e-07, + "loss": 0.0968, + "step": 441050 + }, + { + "epoch": 0.98, + "learning_rate": 7.990872687411915e-07, + "loss": 0.0892, + "step": 441060 + }, + { + "epoch": 0.98, + "learning_rate": 7.979687255318674e-07, + "loss": 0.09, + "step": 441070 + }, + { + "epoch": 0.98, + "learning_rate": 7.968501823225432e-07, + "loss": 0.0898, + "step": 441080 + }, + { + "epoch": 0.98, + "learning_rate": 7.95731639113219e-07, + "loss": 0.0917, + "step": 441090 + }, + { + "epoch": 0.98, + "learning_rate": 7.946130959038948e-07, + "loss": 0.0894, + "step": 441100 + }, + { + "epoch": 0.98, + "learning_rate": 7.934945526945707e-07, + "loss": 0.092, + "step": 441110 + }, + { + "epoch": 0.98, + "learning_rate": 7.923760094852465e-07, + "loss": 0.0913, + "step": 441120 + }, + { + "epoch": 0.98, + "learning_rate": 7.912574662759223e-07, + "loss": 0.0905, + "step": 441130 + }, + { + "epoch": 0.98, + "learning_rate": 7.901389230665982e-07, + "loss": 0.0908, + "step": 441140 + }, + { + "epoch": 0.98, + "learning_rate": 7.89020379857274e-07, + "loss": 0.0912, + "step": 441150 + }, + { + "epoch": 0.98, + "learning_rate": 7.879018366479498e-07, + "loss": 0.0883, + "step": 441160 + }, + { + "epoch": 0.98, + "learning_rate": 7.867832934386256e-07, + "loss": 0.0877, + "step": 441170 + }, + { + "epoch": 0.98, + "learning_rate": 7.856647502293014e-07, + "loss": 0.0901, + "step": 441180 + }, + { + "epoch": 0.98, + "learning_rate": 7.845462070199772e-07, + "loss": 0.0917, + "step": 441190 + }, + { + "epoch": 0.98, + "learning_rate": 7.834276638106531e-07, + "loss": 0.0886, + "step": 441200 + }, + { + "epoch": 0.98, + "learning_rate": 7.823091206013289e-07, + "loss": 0.0917, + "step": 441210 + }, + { + "epoch": 0.98, + "learning_rate": 7.811905773920047e-07, + "loss": 0.0898, + "step": 441220 + }, + { + "epoch": 0.98, + "learning_rate": 7.800720341826805e-07, + "loss": 0.09, + "step": 441230 + }, + { + "epoch": 0.98, + "learning_rate": 7.789534909733563e-07, + "loss": 0.0881, + "step": 441240 + }, + { + "epoch": 0.98, + "learning_rate": 7.778349477640321e-07, + "loss": 0.093, + "step": 441250 + }, + { + "epoch": 0.98, + "learning_rate": 7.767164045547079e-07, + "loss": 0.0938, + "step": 441260 + }, + { + "epoch": 0.98, + "learning_rate": 7.755978613453837e-07, + "loss": 0.092, + "step": 441270 + }, + { + "epoch": 0.98, + "learning_rate": 7.744793181360596e-07, + "loss": 0.0917, + "step": 441280 + }, + { + "epoch": 0.99, + "learning_rate": 7.733607749267355e-07, + "loss": 0.0905, + "step": 441290 + }, + { + "epoch": 0.99, + "learning_rate": 7.722422317174113e-07, + "loss": 0.0912, + "step": 441300 + }, + { + "epoch": 0.99, + "learning_rate": 7.711236885080871e-07, + "loss": 0.0925, + "step": 441310 + }, + { + "epoch": 0.99, + "learning_rate": 7.700051452987629e-07, + "loss": 0.0932, + "step": 441320 + }, + { + "epoch": 0.99, + "learning_rate": 7.688866020894387e-07, + "loss": 0.0931, + "step": 441330 + }, + { + "epoch": 0.99, + "learning_rate": 7.677680588801145e-07, + "loss": 0.0919, + "step": 441340 + }, + { + "epoch": 0.99, + "learning_rate": 7.666495156707904e-07, + "loss": 0.093, + "step": 441350 + }, + { + "epoch": 0.99, + "learning_rate": 7.655309724614662e-07, + "loss": 0.0874, + "step": 441360 + }, + { + "epoch": 0.99, + "learning_rate": 7.64412429252142e-07, + "loss": 0.0923, + "step": 441370 + }, + { + "epoch": 0.99, + "learning_rate": 7.632938860428178e-07, + "loss": 0.0999, + "step": 441380 + }, + { + "epoch": 0.99, + "learning_rate": 7.621753428334937e-07, + "loss": 0.0857, + "step": 441390 + }, + { + "epoch": 0.99, + "learning_rate": 7.610567996241695e-07, + "loss": 0.0858, + "step": 441400 + }, + { + "epoch": 0.99, + "learning_rate": 7.599382564148453e-07, + "loss": 0.0955, + "step": 441410 + }, + { + "epoch": 0.99, + "learning_rate": 7.588197132055211e-07, + "loss": 0.0937, + "step": 441420 + }, + { + "epoch": 0.99, + "learning_rate": 7.57701169996197e-07, + "loss": 0.0924, + "step": 441430 + }, + { + "epoch": 0.99, + "learning_rate": 7.565826267868728e-07, + "loss": 0.0922, + "step": 441440 + }, + { + "epoch": 0.99, + "learning_rate": 7.554640835775486e-07, + "loss": 0.0862, + "step": 441450 + }, + { + "epoch": 0.99, + "learning_rate": 7.543455403682244e-07, + "loss": 0.0912, + "step": 441460 + }, + { + "epoch": 0.99, + "learning_rate": 7.532269971589002e-07, + "loss": 0.0912, + "step": 441470 + }, + { + "epoch": 0.99, + "learning_rate": 7.521084539495761e-07, + "loss": 0.09, + "step": 441480 + }, + { + "epoch": 0.99, + "learning_rate": 7.509899107402519e-07, + "loss": 0.0917, + "step": 441490 + }, + { + "epoch": 0.99, + "learning_rate": 7.498713675309278e-07, + "loss": 0.09, + "step": 441500 + }, + { + "epoch": 0.99, + "learning_rate": 7.487528243216036e-07, + "loss": 0.0898, + "step": 441510 + }, + { + "epoch": 0.99, + "learning_rate": 7.476342811122794e-07, + "loss": 0.09, + "step": 441520 + }, + { + "epoch": 0.99, + "learning_rate": 7.465157379029552e-07, + "loss": 0.089, + "step": 441530 + }, + { + "epoch": 0.99, + "learning_rate": 7.45397194693631e-07, + "loss": 0.0898, + "step": 441540 + }, + { + "epoch": 0.99, + "learning_rate": 7.442786514843068e-07, + "loss": 0.0932, + "step": 441550 + }, + { + "epoch": 0.99, + "learning_rate": 7.431601082749826e-07, + "loss": 0.0938, + "step": 441560 + }, + { + "epoch": 0.99, + "learning_rate": 7.420415650656585e-07, + "loss": 0.0911, + "step": 441570 + }, + { + "epoch": 0.99, + "learning_rate": 7.409230218563344e-07, + "loss": 0.0917, + "step": 441580 + }, + { + "epoch": 0.99, + "learning_rate": 7.398044786470102e-07, + "loss": 0.0911, + "step": 441590 + }, + { + "epoch": 0.99, + "learning_rate": 7.38685935437686e-07, + "loss": 0.0922, + "step": 441600 + }, + { + "epoch": 0.99, + "learning_rate": 7.375673922283618e-07, + "loss": 0.0891, + "step": 441610 + }, + { + "epoch": 0.99, + "learning_rate": 7.364488490190376e-07, + "loss": 0.0887, + "step": 441620 + }, + { + "epoch": 0.99, + "learning_rate": 7.353303058097134e-07, + "loss": 0.0882, + "step": 441630 + }, + { + "epoch": 0.99, + "learning_rate": 7.342117626003892e-07, + "loss": 0.0907, + "step": 441640 + }, + { + "epoch": 0.99, + "learning_rate": 7.330932193910651e-07, + "loss": 0.0918, + "step": 441650 + }, + { + "epoch": 0.99, + "learning_rate": 7.31974676181741e-07, + "loss": 0.0878, + "step": 441660 + }, + { + "epoch": 0.99, + "learning_rate": 7.308561329724168e-07, + "loss": 0.093, + "step": 441670 + }, + { + "epoch": 0.99, + "learning_rate": 7.297375897630926e-07, + "loss": 0.09, + "step": 441680 + }, + { + "epoch": 0.99, + "learning_rate": 7.286190465537684e-07, + "loss": 0.0917, + "step": 441690 + }, + { + "epoch": 0.99, + "learning_rate": 7.275005033444442e-07, + "loss": 0.09, + "step": 441700 + }, + { + "epoch": 0.99, + "learning_rate": 7.2638196013512e-07, + "loss": 0.0895, + "step": 441710 + }, + { + "epoch": 0.99, + "learning_rate": 7.252634169257958e-07, + "loss": 0.0928, + "step": 441720 + }, + { + "epoch": 0.99, + "learning_rate": 7.241448737164717e-07, + "loss": 0.0926, + "step": 441730 + }, + { + "epoch": 0.99, + "learning_rate": 7.230263305071475e-07, + "loss": 0.0909, + "step": 441740 + }, + { + "epoch": 0.99, + "learning_rate": 7.219077872978234e-07, + "loss": 0.0937, + "step": 441750 + }, + { + "epoch": 0.99, + "learning_rate": 7.207892440884992e-07, + "loss": 0.0907, + "step": 441760 + }, + { + "epoch": 0.99, + "learning_rate": 7.19670700879175e-07, + "loss": 0.0932, + "step": 441770 + }, + { + "epoch": 0.99, + "learning_rate": 7.185521576698508e-07, + "loss": 0.0938, + "step": 441780 + }, + { + "epoch": 0.99, + "learning_rate": 7.174336144605266e-07, + "loss": 0.0904, + "step": 441790 + }, + { + "epoch": 0.99, + "learning_rate": 7.163150712512025e-07, + "loss": 0.0883, + "step": 441800 + }, + { + "epoch": 0.99, + "learning_rate": 7.151965280418783e-07, + "loss": 0.0894, + "step": 441810 + }, + { + "epoch": 0.99, + "learning_rate": 7.140779848325541e-07, + "loss": 0.0905, + "step": 441820 + }, + { + "epoch": 0.99, + "learning_rate": 7.129594416232299e-07, + "loss": 0.0878, + "step": 441830 + }, + { + "epoch": 0.99, + "learning_rate": 7.118408984139057e-07, + "loss": 0.0931, + "step": 441840 + }, + { + "epoch": 0.99, + "learning_rate": 7.107223552045816e-07, + "loss": 0.0907, + "step": 441850 + }, + { + "epoch": 0.99, + "learning_rate": 7.096038119952574e-07, + "loss": 0.0893, + "step": 441860 + }, + { + "epoch": 0.99, + "learning_rate": 7.084852687859333e-07, + "loss": 0.089, + "step": 441870 + }, + { + "epoch": 0.99, + "learning_rate": 7.073667255766091e-07, + "loss": 0.0861, + "step": 441880 + }, + { + "epoch": 0.99, + "learning_rate": 7.062481823672849e-07, + "loss": 0.0899, + "step": 441890 + }, + { + "epoch": 0.99, + "learning_rate": 7.051296391579607e-07, + "loss": 0.0929, + "step": 441900 + }, + { + "epoch": 0.99, + "learning_rate": 7.040110959486365e-07, + "loss": 0.0951, + "step": 441910 + }, + { + "epoch": 0.99, + "learning_rate": 7.028925527393123e-07, + "loss": 0.0866, + "step": 441920 + }, + { + "epoch": 0.99, + "learning_rate": 7.017740095299881e-07, + "loss": 0.087, + "step": 441930 + }, + { + "epoch": 0.99, + "learning_rate": 7.00655466320664e-07, + "loss": 0.0937, + "step": 441940 + }, + { + "epoch": 0.99, + "learning_rate": 6.995369231113399e-07, + "loss": 0.0874, + "step": 441950 + }, + { + "epoch": 0.99, + "learning_rate": 6.984183799020157e-07, + "loss": 0.0911, + "step": 441960 + }, + { + "epoch": 0.99, + "learning_rate": 6.972998366926915e-07, + "loss": 0.0917, + "step": 441970 + }, + { + "epoch": 0.99, + "learning_rate": 6.961812934833673e-07, + "loss": 0.0924, + "step": 441980 + }, + { + "epoch": 0.99, + "learning_rate": 6.950627502740431e-07, + "loss": 0.0916, + "step": 441990 + }, + { + "epoch": 0.99, + "learning_rate": 6.939442070647189e-07, + "loss": 0.0919, + "step": 442000 + }, + { + "epoch": 0.99, + "learning_rate": 6.928256638553947e-07, + "loss": 0.0896, + "step": 442010 + }, + { + "epoch": 0.99, + "learning_rate": 6.917071206460706e-07, + "loss": 0.0922, + "step": 442020 + }, + { + "epoch": 0.99, + "learning_rate": 6.905885774367465e-07, + "loss": 0.0878, + "step": 442030 + }, + { + "epoch": 0.99, + "learning_rate": 6.894700342274223e-07, + "loss": 0.0954, + "step": 442040 + }, + { + "epoch": 0.99, + "learning_rate": 6.883514910180981e-07, + "loss": 0.0876, + "step": 442050 + }, + { + "epoch": 0.99, + "learning_rate": 6.872329478087739e-07, + "loss": 0.0881, + "step": 442060 + }, + { + "epoch": 0.99, + "learning_rate": 6.861144045994497e-07, + "loss": 0.0921, + "step": 442070 + }, + { + "epoch": 0.99, + "learning_rate": 6.849958613901255e-07, + "loss": 0.0918, + "step": 442080 + }, + { + "epoch": 0.99, + "learning_rate": 6.838773181808013e-07, + "loss": 0.0876, + "step": 442090 + }, + { + "epoch": 0.99, + "learning_rate": 6.827587749714772e-07, + "loss": 0.0864, + "step": 442100 + }, + { + "epoch": 0.99, + "learning_rate": 6.81640231762153e-07, + "loss": 0.0907, + "step": 442110 + }, + { + "epoch": 0.99, + "learning_rate": 6.805216885528289e-07, + "loss": 0.0946, + "step": 442120 + }, + { + "epoch": 0.99, + "learning_rate": 6.794031453435047e-07, + "loss": 0.089, + "step": 442130 + }, + { + "epoch": 0.99, + "learning_rate": 6.782846021341805e-07, + "loss": 0.0951, + "step": 442140 + }, + { + "epoch": 0.99, + "learning_rate": 6.771660589248563e-07, + "loss": 0.0913, + "step": 442150 + }, + { + "epoch": 0.99, + "learning_rate": 6.760475157155321e-07, + "loss": 0.0905, + "step": 442160 + }, + { + "epoch": 0.99, + "learning_rate": 6.74928972506208e-07, + "loss": 0.0906, + "step": 442170 + }, + { + "epoch": 0.99, + "learning_rate": 6.738104292968838e-07, + "loss": 0.0875, + "step": 442180 + }, + { + "epoch": 0.99, + "learning_rate": 6.726918860875596e-07, + "loss": 0.0919, + "step": 442190 + }, + { + "epoch": 0.99, + "learning_rate": 6.715733428782354e-07, + "loss": 0.0916, + "step": 442200 + }, + { + "epoch": 0.99, + "learning_rate": 6.704547996689113e-07, + "loss": 0.0859, + "step": 442210 + }, + { + "epoch": 0.99, + "learning_rate": 6.693362564595871e-07, + "loss": 0.0914, + "step": 442220 + }, + { + "epoch": 0.99, + "learning_rate": 6.682177132502629e-07, + "loss": 0.0889, + "step": 442230 + }, + { + "epoch": 0.99, + "learning_rate": 6.670991700409387e-07, + "loss": 0.0945, + "step": 442240 + }, + { + "epoch": 0.99, + "learning_rate": 6.659806268316146e-07, + "loss": 0.0871, + "step": 442250 + }, + { + "epoch": 0.99, + "learning_rate": 6.648620836222904e-07, + "loss": 0.0961, + "step": 442260 + }, + { + "epoch": 0.99, + "learning_rate": 6.637435404129662e-07, + "loss": 0.0908, + "step": 442270 + }, + { + "epoch": 0.99, + "learning_rate": 6.62624997203642e-07, + "loss": 0.0873, + "step": 442280 + }, + { + "epoch": 0.99, + "learning_rate": 6.615064539943178e-07, + "loss": 0.0908, + "step": 442290 + }, + { + "epoch": 0.99, + "learning_rate": 6.603879107849936e-07, + "loss": 0.0871, + "step": 442300 + }, + { + "epoch": 0.99, + "learning_rate": 6.592693675756695e-07, + "loss": 0.0934, + "step": 442310 + }, + { + "epoch": 0.99, + "learning_rate": 6.581508243663454e-07, + "loss": 0.0911, + "step": 442320 + }, + { + "epoch": 0.99, + "learning_rate": 6.570322811570212e-07, + "loss": 0.0916, + "step": 442330 + }, + { + "epoch": 0.99, + "learning_rate": 6.55913737947697e-07, + "loss": 0.0908, + "step": 442340 + }, + { + "epoch": 0.99, + "learning_rate": 6.547951947383728e-07, + "loss": 0.095, + "step": 442350 + }, + { + "epoch": 0.99, + "learning_rate": 6.536766515290486e-07, + "loss": 0.0899, + "step": 442360 + }, + { + "epoch": 0.99, + "learning_rate": 6.525581083197244e-07, + "loss": 0.0888, + "step": 442370 + }, + { + "epoch": 0.99, + "learning_rate": 6.515514194313327e-07, + "loss": 0.0961, + "step": 442380 + }, + { + "epoch": 0.99, + "learning_rate": 6.504328762220085e-07, + "loss": 0.0918, + "step": 442390 + }, + { + "epoch": 0.99, + "learning_rate": 6.493143330126844e-07, + "loss": 0.0907, + "step": 442400 + }, + { + "epoch": 0.99, + "learning_rate": 6.481957898033602e-07, + "loss": 0.0899, + "step": 442410 + }, + { + "epoch": 0.99, + "learning_rate": 6.470772465940359e-07, + "loss": 0.0935, + "step": 442420 + }, + { + "epoch": 0.99, + "learning_rate": 6.459587033847117e-07, + "loss": 0.0866, + "step": 442430 + }, + { + "epoch": 0.99, + "learning_rate": 6.448401601753875e-07, + "loss": 0.0891, + "step": 442440 + }, + { + "epoch": 0.99, + "learning_rate": 6.437216169660633e-07, + "loss": 0.088, + "step": 442450 + }, + { + "epoch": 0.99, + "learning_rate": 6.426030737567393e-07, + "loss": 0.0935, + "step": 442460 + }, + { + "epoch": 0.99, + "learning_rate": 6.414845305474151e-07, + "loss": 0.0907, + "step": 442470 + }, + { + "epoch": 0.99, + "learning_rate": 6.403659873380909e-07, + "loss": 0.0893, + "step": 442480 + }, + { + "epoch": 0.99, + "learning_rate": 6.392474441287667e-07, + "loss": 0.0915, + "step": 442490 + }, + { + "epoch": 0.99, + "learning_rate": 6.381289009194425e-07, + "loss": 0.0845, + "step": 442500 + }, + { + "epoch": 0.99, + "learning_rate": 6.370103577101183e-07, + "loss": 0.0898, + "step": 442510 + }, + { + "epoch": 0.99, + "learning_rate": 6.358918145007941e-07, + "loss": 0.0903, + "step": 442520 + }, + { + "epoch": 0.99, + "learning_rate": 6.347732712914699e-07, + "loss": 0.0909, + "step": 442530 + }, + { + "epoch": 0.99, + "learning_rate": 6.336547280821458e-07, + "loss": 0.0878, + "step": 442540 + }, + { + "epoch": 0.99, + "learning_rate": 6.325361848728217e-07, + "loss": 0.0925, + "step": 442550 + }, + { + "epoch": 0.99, + "learning_rate": 6.314176416634975e-07, + "loss": 0.0893, + "step": 442560 + }, + { + "epoch": 0.99, + "learning_rate": 6.302990984541733e-07, + "loss": 0.0888, + "step": 442570 + }, + { + "epoch": 0.99, + "learning_rate": 6.291805552448491e-07, + "loss": 0.0939, + "step": 442580 + }, + { + "epoch": 0.99, + "learning_rate": 6.280620120355249e-07, + "loss": 0.0877, + "step": 442590 + }, + { + "epoch": 0.99, + "learning_rate": 6.269434688262007e-07, + "loss": 0.0894, + "step": 442600 + }, + { + "epoch": 0.99, + "learning_rate": 6.258249256168766e-07, + "loss": 0.0938, + "step": 442610 + }, + { + "epoch": 0.99, + "learning_rate": 6.247063824075524e-07, + "loss": 0.0908, + "step": 442620 + }, + { + "epoch": 0.99, + "learning_rate": 6.235878391982282e-07, + "loss": 0.0927, + "step": 442630 + }, + { + "epoch": 0.99, + "learning_rate": 6.224692959889041e-07, + "loss": 0.0946, + "step": 442640 + }, + { + "epoch": 0.99, + "learning_rate": 6.213507527795799e-07, + "loss": 0.0922, + "step": 442650 + }, + { + "epoch": 0.99, + "learning_rate": 6.202322095702557e-07, + "loss": 0.0897, + "step": 442660 + }, + { + "epoch": 0.99, + "learning_rate": 6.191136663609315e-07, + "loss": 0.0933, + "step": 442670 + }, + { + "epoch": 0.99, + "learning_rate": 6.179951231516073e-07, + "loss": 0.0931, + "step": 442680 + }, + { + "epoch": 0.99, + "learning_rate": 6.168765799422832e-07, + "loss": 0.09, + "step": 442690 + }, + { + "epoch": 0.99, + "learning_rate": 6.15758036732959e-07, + "loss": 0.0921, + "step": 442700 + }, + { + "epoch": 0.99, + "learning_rate": 6.146394935236348e-07, + "loss": 0.0863, + "step": 442710 + }, + { + "epoch": 0.99, + "learning_rate": 6.135209503143106e-07, + "loss": 0.0879, + "step": 442720 + }, + { + "epoch": 0.99, + "learning_rate": 6.124024071049865e-07, + "loss": 0.0916, + "step": 442730 + }, + { + "epoch": 0.99, + "learning_rate": 6.112838638956623e-07, + "loss": 0.092, + "step": 442740 + }, + { + "epoch": 0.99, + "learning_rate": 6.101653206863381e-07, + "loss": 0.0911, + "step": 442750 + }, + { + "epoch": 0.99, + "learning_rate": 6.09046777477014e-07, + "loss": 0.089, + "step": 442760 + }, + { + "epoch": 0.99, + "learning_rate": 6.079282342676898e-07, + "loss": 0.0876, + "step": 442770 + }, + { + "epoch": 0.99, + "learning_rate": 6.068096910583656e-07, + "loss": 0.0918, + "step": 442780 + }, + { + "epoch": 0.99, + "learning_rate": 6.056911478490414e-07, + "loss": 0.0903, + "step": 442790 + }, + { + "epoch": 0.99, + "learning_rate": 6.045726046397172e-07, + "loss": 0.0907, + "step": 442800 + }, + { + "epoch": 0.99, + "learning_rate": 6.03454061430393e-07, + "loss": 0.0881, + "step": 442810 + }, + { + "epoch": 0.99, + "learning_rate": 6.023355182210688e-07, + "loss": 0.0936, + "step": 442820 + }, + { + "epoch": 0.99, + "learning_rate": 6.012169750117447e-07, + "loss": 0.0897, + "step": 442830 + }, + { + "epoch": 0.99, + "learning_rate": 6.000984318024206e-07, + "loss": 0.0894, + "step": 442840 + }, + { + "epoch": 0.99, + "learning_rate": 5.989798885930964e-07, + "loss": 0.0907, + "step": 442850 + }, + { + "epoch": 0.99, + "learning_rate": 5.978613453837722e-07, + "loss": 0.0932, + "step": 442860 + }, + { + "epoch": 0.99, + "learning_rate": 5.96742802174448e-07, + "loss": 0.0987, + "step": 442870 + }, + { + "epoch": 0.99, + "learning_rate": 5.956242589651238e-07, + "loss": 0.093, + "step": 442880 + }, + { + "epoch": 0.99, + "learning_rate": 5.945057157557996e-07, + "loss": 0.089, + "step": 442890 + }, + { + "epoch": 0.99, + "learning_rate": 5.933871725464754e-07, + "loss": 0.0887, + "step": 442900 + }, + { + "epoch": 0.99, + "learning_rate": 5.922686293371514e-07, + "loss": 0.0908, + "step": 442910 + }, + { + "epoch": 0.99, + "learning_rate": 5.911500861278272e-07, + "loss": 0.0905, + "step": 442920 + }, + { + "epoch": 0.99, + "learning_rate": 5.90031542918503e-07, + "loss": 0.0915, + "step": 442930 + }, + { + "epoch": 0.99, + "learning_rate": 5.889129997091788e-07, + "loss": 0.0876, + "step": 442940 + }, + { + "epoch": 0.99, + "learning_rate": 5.877944564998546e-07, + "loss": 0.089, + "step": 442950 + }, + { + "epoch": 0.99, + "learning_rate": 5.866759132905304e-07, + "loss": 0.089, + "step": 442960 + }, + { + "epoch": 0.99, + "learning_rate": 5.855573700812062e-07, + "loss": 0.0903, + "step": 442970 + }, + { + "epoch": 0.99, + "learning_rate": 5.84438826871882e-07, + "loss": 0.0914, + "step": 442980 + }, + { + "epoch": 0.99, + "learning_rate": 5.833202836625579e-07, + "loss": 0.0919, + "step": 442990 + }, + { + "epoch": 0.99, + "learning_rate": 5.822017404532337e-07, + "loss": 0.0895, + "step": 443000 + }, + { + "epoch": 0.99, + "learning_rate": 5.810831972439096e-07, + "loss": 0.0917, + "step": 443010 + }, + { + "epoch": 0.99, + "learning_rate": 5.799646540345854e-07, + "loss": 0.09, + "step": 443020 + }, + { + "epoch": 0.99, + "learning_rate": 5.788461108252612e-07, + "loss": 0.0895, + "step": 443030 + }, + { + "epoch": 0.99, + "learning_rate": 5.77727567615937e-07, + "loss": 0.0925, + "step": 443040 + }, + { + "epoch": 0.99, + "learning_rate": 5.766090244066128e-07, + "loss": 0.092, + "step": 443050 + }, + { + "epoch": 0.99, + "learning_rate": 5.754904811972887e-07, + "loss": 0.0904, + "step": 443060 + }, + { + "epoch": 0.99, + "learning_rate": 5.743719379879645e-07, + "loss": 0.0863, + "step": 443070 + }, + { + "epoch": 0.99, + "learning_rate": 5.732533947786403e-07, + "loss": 0.0896, + "step": 443080 + }, + { + "epoch": 0.99, + "learning_rate": 5.721348515693161e-07, + "loss": 0.0883, + "step": 443090 + }, + { + "epoch": 0.99, + "learning_rate": 5.71016308359992e-07, + "loss": 0.0929, + "step": 443100 + }, + { + "epoch": 0.99, + "learning_rate": 5.698977651506678e-07, + "loss": 0.0916, + "step": 443110 + }, + { + "epoch": 0.99, + "learning_rate": 5.687792219413436e-07, + "loss": 0.0914, + "step": 443120 + }, + { + "epoch": 0.99, + "learning_rate": 5.676606787320195e-07, + "loss": 0.0911, + "step": 443130 + }, + { + "epoch": 0.99, + "learning_rate": 5.665421355226953e-07, + "loss": 0.0859, + "step": 443140 + }, + { + "epoch": 0.99, + "learning_rate": 5.654235923133711e-07, + "loss": 0.0885, + "step": 443150 + }, + { + "epoch": 0.99, + "learning_rate": 5.643050491040469e-07, + "loss": 0.092, + "step": 443160 + }, + { + "epoch": 0.99, + "learning_rate": 5.631865058947227e-07, + "loss": 0.0954, + "step": 443170 + }, + { + "epoch": 0.99, + "learning_rate": 5.620679626853985e-07, + "loss": 0.0901, + "step": 443180 + }, + { + "epoch": 0.99, + "learning_rate": 5.609494194760744e-07, + "loss": 0.0919, + "step": 443190 + }, + { + "epoch": 0.99, + "learning_rate": 5.598308762667502e-07, + "loss": 0.0918, + "step": 443200 + }, + { + "epoch": 0.99, + "learning_rate": 5.587123330574261e-07, + "loss": 0.0931, + "step": 443210 + }, + { + "epoch": 0.99, + "learning_rate": 5.575937898481019e-07, + "loss": 0.0892, + "step": 443220 + }, + { + "epoch": 0.99, + "learning_rate": 5.564752466387777e-07, + "loss": 0.0927, + "step": 443230 + }, + { + "epoch": 0.99, + "learning_rate": 5.553567034294535e-07, + "loss": 0.0925, + "step": 443240 + }, + { + "epoch": 0.99, + "learning_rate": 5.542381602201293e-07, + "loss": 0.0907, + "step": 443250 + }, + { + "epoch": 0.99, + "learning_rate": 5.531196170108051e-07, + "loss": 0.0921, + "step": 443260 + }, + { + "epoch": 0.99, + "learning_rate": 5.520010738014809e-07, + "loss": 0.0898, + "step": 443270 + }, + { + "epoch": 0.99, + "learning_rate": 5.508825305921569e-07, + "loss": 0.0909, + "step": 443280 + }, + { + "epoch": 0.99, + "learning_rate": 5.497639873828327e-07, + "loss": 0.093, + "step": 443290 + }, + { + "epoch": 0.99, + "learning_rate": 5.486454441735085e-07, + "loss": 0.0887, + "step": 443300 + }, + { + "epoch": 0.99, + "learning_rate": 5.475269009641843e-07, + "loss": 0.0905, + "step": 443310 + }, + { + "epoch": 0.99, + "learning_rate": 5.464083577548601e-07, + "loss": 0.0896, + "step": 443320 + }, + { + "epoch": 0.99, + "learning_rate": 5.452898145455359e-07, + "loss": 0.0915, + "step": 443330 + }, + { + "epoch": 0.99, + "learning_rate": 5.441712713362117e-07, + "loss": 0.0864, + "step": 443340 + }, + { + "epoch": 0.99, + "learning_rate": 5.430527281268875e-07, + "loss": 0.0911, + "step": 443350 + }, + { + "epoch": 0.99, + "learning_rate": 5.419341849175634e-07, + "loss": 0.091, + "step": 443360 + }, + { + "epoch": 0.99, + "learning_rate": 5.408156417082393e-07, + "loss": 0.0856, + "step": 443370 + }, + { + "epoch": 0.99, + "learning_rate": 5.396970984989151e-07, + "loss": 0.0906, + "step": 443380 + }, + { + "epoch": 0.99, + "learning_rate": 5.385785552895909e-07, + "loss": 0.0954, + "step": 443390 + }, + { + "epoch": 0.99, + "learning_rate": 5.374600120802667e-07, + "loss": 0.0919, + "step": 443400 + }, + { + "epoch": 0.99, + "learning_rate": 5.363414688709425e-07, + "loss": 0.0872, + "step": 443410 + }, + { + "epoch": 0.99, + "learning_rate": 5.352229256616183e-07, + "loss": 0.0911, + "step": 443420 + }, + { + "epoch": 0.99, + "learning_rate": 5.341043824522942e-07, + "loss": 0.0895, + "step": 443430 + }, + { + "epoch": 0.99, + "learning_rate": 5.3298583924297e-07, + "loss": 0.0936, + "step": 443440 + }, + { + "epoch": 0.99, + "learning_rate": 5.318672960336458e-07, + "loss": 0.0901, + "step": 443450 + }, + { + "epoch": 0.99, + "learning_rate": 5.307487528243216e-07, + "loss": 0.0904, + "step": 443460 + }, + { + "epoch": 0.99, + "learning_rate": 5.296302096149975e-07, + "loss": 0.092, + "step": 443470 + }, + { + "epoch": 0.99, + "learning_rate": 5.285116664056733e-07, + "loss": 0.0922, + "step": 443480 + }, + { + "epoch": 0.99, + "learning_rate": 5.273931231963491e-07, + "loss": 0.0895, + "step": 443490 + }, + { + "epoch": 0.99, + "learning_rate": 5.262745799870249e-07, + "loss": 0.0919, + "step": 443500 + }, + { + "epoch": 0.99, + "learning_rate": 5.251560367777008e-07, + "loss": 0.0886, + "step": 443510 + }, + { + "epoch": 0.99, + "learning_rate": 5.240374935683766e-07, + "loss": 0.0864, + "step": 443520 }, { "epoch": 0.99, - "learning_rate": 7.732837092507062e-07, - "loss": 0.1388, - "step": 220650 + "learning_rate": 5.229189503590524e-07, + "loss": 0.0882, + "step": 443530 }, { "epoch": 0.99, - "learning_rate": 7.710416573247837e-07, - "loss": 0.1357, - "step": 220660 + "learning_rate": 5.218004071497282e-07, + "loss": 0.0893, + "step": 443540 }, { "epoch": 0.99, - "learning_rate": 7.68799605398861e-07, - "loss": 0.1394, - "step": 220670 + "learning_rate": 5.20681863940404e-07, + "loss": 0.0933, + "step": 443550 }, { "epoch": 0.99, - "learning_rate": 7.665575534729385e-07, - "loss": 0.1381, - "step": 220680 + "learning_rate": 5.195633207310799e-07, + "loss": 0.0919, + "step": 443560 }, { "epoch": 0.99, - "learning_rate": 7.643155015470159e-07, - "loss": 0.1345, - "step": 220690 + "learning_rate": 5.184447775217557e-07, + "loss": 0.0914, + "step": 443570 }, { "epoch": 0.99, - "learning_rate": 7.620734496210933e-07, - "loss": 0.1337, - "step": 220700 + "learning_rate": 5.173262343124316e-07, + "loss": 0.0927, + "step": 443580 }, { "epoch": 0.99, - "learning_rate": 7.598313976951706e-07, - "loss": 0.1381, - "step": 220710 + "learning_rate": 5.162076911031074e-07, + "loss": 0.0872, + "step": 443590 }, { "epoch": 0.99, - "learning_rate": 7.575893457692481e-07, - "loss": 0.1321, - "step": 220720 + "learning_rate": 5.150891478937832e-07, + "loss": 0.0908, + "step": 443600 }, { "epoch": 0.99, - "learning_rate": 7.553472938433254e-07, - "loss": 0.132, - "step": 220730 + "learning_rate": 5.13970604684459e-07, + "loss": 0.0886, + "step": 443610 }, { "epoch": 0.99, - "learning_rate": 7.531052419174028e-07, - "loss": 0.1352, - "step": 220740 + "learning_rate": 5.128520614751348e-07, + "loss": 0.0925, + "step": 443620 }, { "epoch": 0.99, - "learning_rate": 7.508631899914803e-07, - "loss": 0.1337, - "step": 220750 + "learning_rate": 5.117335182658106e-07, + "loss": 0.0927, + "step": 443630 }, { "epoch": 0.99, - "learning_rate": 7.486211380655576e-07, - "loss": 0.1381, - "step": 220760 + "learning_rate": 5.106149750564864e-07, + "loss": 0.0927, + "step": 443640 }, { "epoch": 0.99, - "learning_rate": 7.46379086139635e-07, - "loss": 0.1388, - "step": 220770 + "learning_rate": 5.094964318471623e-07, + "loss": 0.0922, + "step": 443650 }, { "epoch": 0.99, - "learning_rate": 7.441370342137124e-07, - "loss": 0.1417, - "step": 220780 + "learning_rate": 5.083778886378382e-07, + "loss": 0.0946, + "step": 443660 }, { "epoch": 0.99, - "learning_rate": 7.418949822877899e-07, - "loss": 0.1404, - "step": 220790 + "learning_rate": 5.07259345428514e-07, + "loss": 0.092, + "step": 443670 }, { "epoch": 0.99, - "learning_rate": 7.396529303618672e-07, - "loss": 0.1325, - "step": 220800 + "learning_rate": 5.061408022191898e-07, + "loss": 0.0882, + "step": 443680 }, { "epoch": 0.99, - "learning_rate": 7.374108784359447e-07, - "loss": 0.1321, - "step": 220810 + "learning_rate": 5.050222590098656e-07, + "loss": 0.0922, + "step": 443690 }, { "epoch": 0.99, - "learning_rate": 7.35168826510022e-07, - "loss": 0.1371, - "step": 220820 + "learning_rate": 5.039037158005414e-07, + "loss": 0.0925, + "step": 443700 }, { "epoch": 0.99, - "learning_rate": 7.329267745840993e-07, - "loss": 0.1345, - "step": 220830 + "learning_rate": 5.027851725912172e-07, + "loss": 0.0904, + "step": 443710 }, { "epoch": 0.99, - "learning_rate": 7.306847226581768e-07, - "loss": 0.1355, - "step": 220840 + "learning_rate": 5.01666629381893e-07, + "loss": 0.0943, + "step": 443720 }, { "epoch": 0.99, - "learning_rate": 7.284426707322542e-07, - "loss": 0.1396, - "step": 220850 + "learning_rate": 5.005480861725689e-07, + "loss": 0.0926, + "step": 443730 }, { "epoch": 0.99, - "learning_rate": 7.262006188063316e-07, - "loss": 0.1353, - "step": 220860 + "learning_rate": 4.994295429632448e-07, + "loss": 0.0931, + "step": 443740 }, { "epoch": 0.99, - "learning_rate": 7.239585668804089e-07, - "loss": 0.1404, - "step": 220870 + "learning_rate": 4.983109997539206e-07, + "loss": 0.0931, + "step": 443750 }, { "epoch": 0.99, - "learning_rate": 7.217165149544864e-07, - "loss": 0.1351, - "step": 220880 + "learning_rate": 4.971924565445964e-07, + "loss": 0.0884, + "step": 443760 }, { "epoch": 0.99, - "learning_rate": 7.194744630285638e-07, - "loss": 0.138, - "step": 220890 + "learning_rate": 4.960739133352722e-07, + "loss": 0.0883, + "step": 443770 }, { "epoch": 0.99, - "learning_rate": 7.172324111026412e-07, - "loss": 0.1371, - "step": 220900 + "learning_rate": 4.94955370125948e-07, + "loss": 0.0893, + "step": 443780 }, { "epoch": 0.99, - "learning_rate": 7.149903591767186e-07, - "loss": 0.1379, - "step": 220910 + "learning_rate": 4.938368269166238e-07, + "loss": 0.0913, + "step": 443790 }, { "epoch": 0.99, - "learning_rate": 7.127483072507959e-07, - "loss": 0.137, - "step": 220920 + "learning_rate": 4.927182837072996e-07, + "loss": 0.0915, + "step": 443800 }, { "epoch": 0.99, - "learning_rate": 7.105062553248733e-07, - "loss": 0.1394, - "step": 220930 + "learning_rate": 4.915997404979755e-07, + "loss": 0.0868, + "step": 443810 }, { "epoch": 0.99, - "learning_rate": 7.082642033989507e-07, - "loss": 0.1374, - "step": 220940 + "learning_rate": 4.904811972886513e-07, + "loss": 0.0897, + "step": 443820 }, { "epoch": 0.99, - "learning_rate": 7.060221514730282e-07, - "loss": 0.1389, - "step": 220950 + "learning_rate": 4.893626540793272e-07, + "loss": 0.0914, + "step": 443830 }, { "epoch": 0.99, - "learning_rate": 7.037800995471055e-07, - "loss": 0.1357, - "step": 220960 + "learning_rate": 4.88244110870003e-07, + "loss": 0.0932, + "step": 443840 }, { "epoch": 0.99, - "learning_rate": 7.01538047621183e-07, - "loss": 0.1364, - "step": 220970 + "learning_rate": 4.871255676606788e-07, + "loss": 0.0873, + "step": 443850 }, { "epoch": 0.99, - "learning_rate": 6.992959956952603e-07, - "loss": 0.1396, - "step": 220980 + "learning_rate": 4.860070244513546e-07, + "loss": 0.089, + "step": 443860 }, { "epoch": 0.99, - "learning_rate": 6.970539437693378e-07, - "loss": 0.1397, - "step": 220990 + "learning_rate": 4.848884812420304e-07, + "loss": 0.0939, + "step": 443870 }, { "epoch": 0.99, - "learning_rate": 6.948118918434152e-07, - "loss": 0.1325, - "step": 221000 + "learning_rate": 4.837699380327063e-07, + "loss": 0.0878, + "step": 443880 }, { "epoch": 0.99, - "learning_rate": 6.925698399174925e-07, - "loss": 0.1338, - "step": 221010 + "learning_rate": 4.826513948233821e-07, + "loss": 0.0923, + "step": 443890 }, { "epoch": 0.99, - "learning_rate": 6.903277879915699e-07, - "loss": 0.131, - "step": 221020 + "learning_rate": 4.815328516140579e-07, + "loss": 0.0907, + "step": 443900 }, { "epoch": 0.99, - "learning_rate": 6.880857360656473e-07, - "loss": 0.1348, - "step": 221030 + "learning_rate": 4.804143084047337e-07, + "loss": 0.091, + "step": 443910 }, { "epoch": 0.99, - "learning_rate": 6.858436841397247e-07, - "loss": 0.1373, - "step": 221040 + "learning_rate": 4.792957651954095e-07, + "loss": 0.0865, + "step": 443920 }, { "epoch": 0.99, - "learning_rate": 6.836016322138021e-07, - "loss": 0.138, - "step": 221050 + "learning_rate": 4.781772219860854e-07, + "loss": 0.0867, + "step": 443930 }, { "epoch": 0.99, - "learning_rate": 6.813595802878795e-07, - "loss": 0.1393, - "step": 221060 + "learning_rate": 4.770586787767612e-07, + "loss": 0.0922, + "step": 443940 }, { "epoch": 0.99, - "learning_rate": 6.791175283619569e-07, - "loss": 0.136, - "step": 221070 + "learning_rate": 4.7594013556743703e-07, + "loss": 0.0959, + "step": 443950 }, { "epoch": 0.99, - "learning_rate": 6.768754764360343e-07, - "loss": 0.136, - "step": 221080 + "learning_rate": 4.7482159235811284e-07, + "loss": 0.0917, + "step": 443960 }, { "epoch": 0.99, - "learning_rate": 6.746334245101116e-07, - "loss": 0.1372, - "step": 221090 + "learning_rate": 4.737030491487887e-07, + "loss": 0.0924, + "step": 443970 }, { "epoch": 0.99, - "learning_rate": 6.723913725841891e-07, - "loss": 0.1417, - "step": 221100 + "learning_rate": 4.725845059394645e-07, + "loss": 0.089, + "step": 443980 }, { "epoch": 0.99, - "learning_rate": 6.701493206582665e-07, - "loss": 0.1348, - "step": 221110 + "learning_rate": 4.714659627301403e-07, + "loss": 0.091, + "step": 443990 }, { "epoch": 0.99, - "learning_rate": 6.679072687323438e-07, - "loss": 0.1334, - "step": 221120 + "learning_rate": 4.7034741952081614e-07, + "loss": 0.0894, + "step": 444000 }, { "epoch": 0.99, - "learning_rate": 6.656652168064213e-07, - "loss": 0.1239, - "step": 221130 + "learning_rate": 4.69228876311492e-07, + "loss": 0.0925, + "step": 444010 }, { "epoch": 0.99, - "learning_rate": 6.634231648804986e-07, - "loss": 0.1413, - "step": 221140 + "learning_rate": 4.681103331021678e-07, + "loss": 0.0869, + "step": 444020 }, { "epoch": 0.99, - "learning_rate": 6.611811129545761e-07, - "loss": 0.1367, - "step": 221150 + "learning_rate": 4.669917898928436e-07, + "loss": 0.0919, + "step": 444030 }, { "epoch": 0.99, - "learning_rate": 6.589390610286535e-07, - "loss": 0.1371, - "step": 221160 + "learning_rate": 4.6587324668351943e-07, + "loss": 0.0941, + "step": 444040 }, { "epoch": 0.99, - "learning_rate": 6.566970091027309e-07, - "loss": 0.1356, - "step": 221170 + "learning_rate": 4.647547034741953e-07, + "loss": 0.0939, + "step": 444050 }, { "epoch": 0.99, - "learning_rate": 6.544549571768082e-07, - "loss": 0.1389, - "step": 221180 + "learning_rate": 4.636361602648711e-07, + "loss": 0.09, + "step": 444060 }, { "epoch": 0.99, - "learning_rate": 6.522129052508856e-07, - "loss": 0.1389, - "step": 221190 + "learning_rate": 4.6251761705554686e-07, + "loss": 0.0889, + "step": 444070 }, { "epoch": 0.99, - "learning_rate": 6.499708533249631e-07, - "loss": 0.1394, - "step": 221200 + "learning_rate": 4.6139907384622267e-07, + "loss": 0.0873, + "step": 444080 }, { "epoch": 0.99, - "learning_rate": 6.477288013990404e-07, - "loss": 0.1352, - "step": 221210 + "learning_rate": 4.602805306368985e-07, + "loss": 0.0941, + "step": 444090 }, { "epoch": 0.99, - "learning_rate": 6.454867494731179e-07, - "loss": 0.1378, - "step": 221220 + "learning_rate": 4.591619874275743e-07, + "loss": 0.0899, + "step": 444100 }, { "epoch": 0.99, - "learning_rate": 6.432446975471952e-07, - "loss": 0.1336, - "step": 221230 + "learning_rate": 4.5804344421825015e-07, + "loss": 0.0913, + "step": 444110 }, { "epoch": 0.99, - "learning_rate": 6.410026456212726e-07, - "loss": 0.1349, - "step": 221240 + "learning_rate": 4.5692490100892596e-07, + "loss": 0.0928, + "step": 444120 }, { "epoch": 0.99, - "learning_rate": 6.3876059369535e-07, - "loss": 0.1423, - "step": 221250 + "learning_rate": 4.5580635779960177e-07, + "loss": 0.0939, + "step": 444130 }, { "epoch": 0.99, - "learning_rate": 6.365185417694275e-07, - "loss": 0.136, - "step": 221260 + "learning_rate": 4.546878145902776e-07, + "loss": 0.0963, + "step": 444140 }, { "epoch": 0.99, - "learning_rate": 6.342764898435048e-07, - "loss": 0.133, - "step": 221270 + "learning_rate": 4.5356927138095345e-07, + "loss": 0.092, + "step": 444150 }, { "epoch": 0.99, - "learning_rate": 6.320344379175822e-07, - "loss": 0.1324, - "step": 221280 + "learning_rate": 4.5245072817162926e-07, + "loss": 0.0894, + "step": 444160 }, { "epoch": 0.99, - "learning_rate": 6.297923859916596e-07, - "loss": 0.1403, - "step": 221290 + "learning_rate": 4.5133218496230507e-07, + "loss": 0.0866, + "step": 444170 }, { "epoch": 0.99, - "learning_rate": 6.275503340657369e-07, - "loss": 0.138, - "step": 221300 + "learning_rate": 4.502136417529809e-07, + "loss": 0.0917, + "step": 444180 }, { "epoch": 0.99, - "learning_rate": 6.253082821398144e-07, - "loss": 0.1356, - "step": 221310 + "learning_rate": 4.4909509854365674e-07, + "loss": 0.0923, + "step": 444190 }, { "epoch": 0.99, - "learning_rate": 6.230662302138918e-07, - "loss": 0.1331, - "step": 221320 + "learning_rate": 4.4797655533433255e-07, + "loss": 0.0893, + "step": 444200 }, { "epoch": 0.99, - "learning_rate": 6.208241782879692e-07, - "loss": 0.138, - "step": 221330 + "learning_rate": 4.4685801212500836e-07, + "loss": 0.0966, + "step": 444210 }, { "epoch": 0.99, - "learning_rate": 6.185821263620465e-07, - "loss": 0.139, - "step": 221340 + "learning_rate": 4.457394689156842e-07, + "loss": 0.0954, + "step": 444220 }, { "epoch": 0.99, - "learning_rate": 6.16340074436124e-07, - "loss": 0.136, - "step": 221350 + "learning_rate": 4.4462092570636003e-07, + "loss": 0.0928, + "step": 444230 }, { "epoch": 0.99, - "learning_rate": 6.140980225102014e-07, - "loss": 0.1371, - "step": 221360 + "learning_rate": 4.4350238249703584e-07, + "loss": 0.09, + "step": 444240 }, { "epoch": 0.99, - "learning_rate": 6.118559705842787e-07, - "loss": 0.1346, - "step": 221370 + "learning_rate": 4.4238383928771165e-07, + "loss": 0.0947, + "step": 444250 }, { "epoch": 0.99, - "learning_rate": 6.096139186583562e-07, - "loss": 0.1368, - "step": 221380 + "learning_rate": 4.412652960783875e-07, + "loss": 0.0885, + "step": 444260 }, { "epoch": 0.99, - "learning_rate": 6.073718667324335e-07, - "loss": 0.1397, - "step": 221390 + "learning_rate": 4.401467528690633e-07, + "loss": 0.0935, + "step": 444270 }, { "epoch": 0.99, - "learning_rate": 6.051298148065109e-07, - "loss": 0.1337, - "step": 221400 + "learning_rate": 4.3902820965973914e-07, + "loss": 0.0911, + "step": 444280 }, { "epoch": 0.99, - "learning_rate": 6.028877628805884e-07, - "loss": 0.1288, - "step": 221410 + "learning_rate": 4.3790966645041495e-07, + "loss": 0.092, + "step": 444290 }, { "epoch": 0.99, - "learning_rate": 6.006457109546658e-07, - "loss": 0.1357, - "step": 221420 + "learning_rate": 4.367911232410908e-07, + "loss": 0.0925, + "step": 444300 }, { "epoch": 0.99, - "learning_rate": 5.984036590287431e-07, - "loss": 0.1339, - "step": 221430 + "learning_rate": 4.356725800317666e-07, + "loss": 0.0947, + "step": 444310 }, { "epoch": 0.99, - "learning_rate": 5.961616071028206e-07, - "loss": 0.1386, - "step": 221440 + "learning_rate": 4.3455403682244243e-07, + "loss": 0.0877, + "step": 444320 }, { "epoch": 0.99, - "learning_rate": 5.939195551768979e-07, - "loss": 0.1337, - "step": 221450 + "learning_rate": 4.334354936131183e-07, + "loss": 0.0942, + "step": 444330 }, { "epoch": 0.99, - "learning_rate": 5.916775032509753e-07, - "loss": 0.1371, - "step": 221460 + "learning_rate": 4.323169504037941e-07, + "loss": 0.0899, + "step": 444340 }, { "epoch": 0.99, - "learning_rate": 5.894354513250528e-07, - "loss": 0.136, - "step": 221470 + "learning_rate": 4.311984071944699e-07, + "loss": 0.091, + "step": 444350 }, { "epoch": 0.99, - "learning_rate": 5.871933993991301e-07, - "loss": 0.1394, - "step": 221480 + "learning_rate": 4.300798639851457e-07, + "loss": 0.0918, + "step": 444360 }, { "epoch": 0.99, - "learning_rate": 5.849513474732075e-07, - "loss": 0.1424, - "step": 221490 + "learning_rate": 4.289613207758216e-07, + "loss": 0.0889, + "step": 444370 }, { "epoch": 0.99, - "learning_rate": 5.827092955472849e-07, - "loss": 0.1338, - "step": 221500 + "learning_rate": 4.278427775664974e-07, + "loss": 0.0915, + "step": 444380 }, { "epoch": 0.99, - "learning_rate": 5.804672436213623e-07, - "loss": 0.138, - "step": 221510 + "learning_rate": 4.267242343571732e-07, + "loss": 0.0868, + "step": 444390 }, { "epoch": 0.99, - "learning_rate": 5.782251916954397e-07, - "loss": 0.1413, - "step": 221520 + "learning_rate": 4.25605691147849e-07, + "loss": 0.0878, + "step": 444400 }, { "epoch": 0.99, - "learning_rate": 5.759831397695172e-07, - "loss": 0.137, - "step": 221530 + "learning_rate": 4.245990022594573e-07, + "loss": 0.0906, + "step": 444410 }, { "epoch": 0.99, - "learning_rate": 5.737410878435945e-07, - "loss": 0.1414, - "step": 221540 + "learning_rate": 4.2348045905013313e-07, + "loss": 0.0902, + "step": 444420 }, { "epoch": 0.99, - "learning_rate": 5.714990359176718e-07, - "loss": 0.1371, - "step": 221550 + "learning_rate": 4.2236191584080894e-07, + "loss": 0.0879, + "step": 444430 }, { "epoch": 0.99, - "learning_rate": 5.692569839917493e-07, - "loss": 0.1322, - "step": 221560 + "learning_rate": 4.2124337263148475e-07, + "loss": 0.0906, + "step": 444440 }, { "epoch": 0.99, - "learning_rate": 5.670149320658267e-07, - "loss": 0.1372, - "step": 221570 + "learning_rate": 4.201248294221606e-07, + "loss": 0.0893, + "step": 444450 }, { "epoch": 0.99, - "learning_rate": 5.647728801399041e-07, - "loss": 0.1382, - "step": 221580 + "learning_rate": 4.190062862128364e-07, + "loss": 0.0919, + "step": 444460 }, { "epoch": 0.99, - "learning_rate": 5.625308282139814e-07, - "loss": 0.1347, - "step": 221590 + "learning_rate": 4.1788774300351223e-07, + "loss": 0.0922, + "step": 444470 }, { "epoch": 0.99, - "learning_rate": 5.602887762880589e-07, - "loss": 0.1392, - "step": 221600 + "learning_rate": 4.1676919979418804e-07, + "loss": 0.0913, + "step": 444480 }, { "epoch": 0.99, - "learning_rate": 5.580467243621362e-07, - "loss": 0.1395, - "step": 221610 + "learning_rate": 4.156506565848639e-07, + "loss": 0.0923, + "step": 444490 }, { "epoch": 0.99, - "learning_rate": 5.558046724362137e-07, - "loss": 0.1342, - "step": 221620 + "learning_rate": 4.145321133755397e-07, + "loss": 0.0899, + "step": 444500 }, { "epoch": 0.99, - "learning_rate": 5.535626205102911e-07, - "loss": 0.1352, - "step": 221630 + "learning_rate": 4.134135701662155e-07, + "loss": 0.0918, + "step": 444510 }, { "epoch": 0.99, - "learning_rate": 5.513205685843684e-07, - "loss": 0.1401, - "step": 221640 + "learning_rate": 4.1229502695689134e-07, + "loss": 0.0942, + "step": 444520 }, { "epoch": 0.99, - "learning_rate": 5.493027218510381e-07, - "loss": 0.1417, - "step": 221650 + "learning_rate": 4.111764837475672e-07, + "loss": 0.0885, + "step": 444530 }, { "epoch": 0.99, - "learning_rate": 5.470606699251155e-07, - "loss": 0.1335, - "step": 221660 + "learning_rate": 4.10057940538243e-07, + "loss": 0.0928, + "step": 444540 }, { "epoch": 0.99, - "learning_rate": 5.448186179991928e-07, - "loss": 0.1368, - "step": 221670 + "learning_rate": 4.089393973289188e-07, + "loss": 0.0861, + "step": 444550 }, { "epoch": 0.99, - "learning_rate": 5.425765660732703e-07, - "loss": 0.1389, - "step": 221680 + "learning_rate": 4.078208541195947e-07, + "loss": 0.0925, + "step": 444560 }, { "epoch": 0.99, - "learning_rate": 5.403345141473477e-07, - "loss": 0.1326, - "step": 221690 + "learning_rate": 4.067023109102705e-07, + "loss": 0.0923, + "step": 444570 }, { "epoch": 0.99, - "learning_rate": 5.380924622214251e-07, - "loss": 0.1359, - "step": 221700 + "learning_rate": 4.055837677009463e-07, + "loss": 0.0906, + "step": 444580 }, { "epoch": 0.99, - "learning_rate": 5.358504102955025e-07, - "loss": 0.1314, - "step": 221710 + "learning_rate": 4.044652244916221e-07, + "loss": 0.0888, + "step": 444590 }, { "epoch": 0.99, - "learning_rate": 5.336083583695798e-07, - "loss": 0.1374, - "step": 221720 + "learning_rate": 4.03346681282298e-07, + "loss": 0.091, + "step": 444600 }, { "epoch": 0.99, - "learning_rate": 5.313663064436572e-07, - "loss": 0.136, - "step": 221730 + "learning_rate": 4.022281380729738e-07, + "loss": 0.0945, + "step": 444610 }, { "epoch": 0.99, - "learning_rate": 5.291242545177347e-07, - "loss": 0.1412, - "step": 221740 + "learning_rate": 4.011095948636496e-07, + "loss": 0.0915, + "step": 444620 }, { "epoch": 0.99, - "learning_rate": 5.268822025918121e-07, - "loss": 0.1376, - "step": 221750 + "learning_rate": 3.999910516543254e-07, + "loss": 0.0908, + "step": 444630 }, { "epoch": 0.99, - "learning_rate": 5.246401506658894e-07, - "loss": 0.1337, - "step": 221760 + "learning_rate": 3.9887250844500127e-07, + "loss": 0.0907, + "step": 444640 }, { "epoch": 0.99, - "learning_rate": 5.223980987399669e-07, - "loss": 0.1396, - "step": 221770 + "learning_rate": 3.977539652356771e-07, + "loss": 0.0891, + "step": 444650 }, { "epoch": 0.99, - "learning_rate": 5.201560468140442e-07, - "loss": 0.1383, - "step": 221780 + "learning_rate": 3.966354220263529e-07, + "loss": 0.092, + "step": 444660 }, { "epoch": 0.99, - "learning_rate": 5.179139948881217e-07, - "loss": 0.1367, - "step": 221790 + "learning_rate": 3.9551687881702875e-07, + "loss": 0.093, + "step": 444670 }, { "epoch": 0.99, - "learning_rate": 5.156719429621991e-07, - "loss": 0.1353, - "step": 221800 + "learning_rate": 3.9439833560770456e-07, + "loss": 0.089, + "step": 444680 }, { "epoch": 0.99, - "learning_rate": 5.134298910362764e-07, - "loss": 0.1396, - "step": 221810 + "learning_rate": 3.9327979239838037e-07, + "loss": 0.0878, + "step": 444690 }, { "epoch": 0.99, - "learning_rate": 5.111878391103538e-07, - "loss": 0.136, - "step": 221820 + "learning_rate": 3.921612491890562e-07, + "loss": 0.0909, + "step": 444700 }, { "epoch": 0.99, - "learning_rate": 5.089457871844311e-07, - "loss": 0.1339, - "step": 221830 + "learning_rate": 3.9104270597973205e-07, + "loss": 0.092, + "step": 444710 }, { "epoch": 0.99, - "learning_rate": 5.067037352585086e-07, - "loss": 0.1361, - "step": 221840 + "learning_rate": 3.8992416277040786e-07, + "loss": 0.0875, + "step": 444720 }, { "epoch": 0.99, - "learning_rate": 5.04461683332586e-07, - "loss": 0.1338, - "step": 221850 + "learning_rate": 3.8880561956108367e-07, + "loss": 0.0904, + "step": 444730 }, { "epoch": 0.99, - "learning_rate": 5.022196314066634e-07, - "loss": 0.1367, - "step": 221860 + "learning_rate": 3.876870763517595e-07, + "loss": 0.0911, + "step": 444740 }, { "epoch": 0.99, - "learning_rate": 4.999775794807408e-07, - "loss": 0.1418, - "step": 221870 + "learning_rate": 3.8656853314243534e-07, + "loss": 0.0908, + "step": 444750 }, { "epoch": 0.99, - "learning_rate": 4.977355275548182e-07, - "loss": 0.1415, - "step": 221880 + "learning_rate": 3.8544998993311115e-07, + "loss": 0.0924, + "step": 444760 }, { "epoch": 0.99, - "learning_rate": 4.954934756288956e-07, - "loss": 0.1385, - "step": 221890 + "learning_rate": 3.8433144672378696e-07, + "loss": 0.0888, + "step": 444770 }, { "epoch": 0.99, - "learning_rate": 4.93251423702973e-07, - "loss": 0.1405, - "step": 221900 + "learning_rate": 3.8321290351446277e-07, + "loss": 0.0903, + "step": 444780 }, { "epoch": 0.99, - "learning_rate": 4.910093717770504e-07, - "loss": 0.1378, - "step": 221910 + "learning_rate": 3.8209436030513863e-07, + "loss": 0.092, + "step": 444790 }, { "epoch": 0.99, - "learning_rate": 4.887673198511277e-07, - "loss": 0.1362, - "step": 221920 + "learning_rate": 3.8097581709581444e-07, + "loss": 0.0897, + "step": 444800 }, { "epoch": 0.99, - "learning_rate": 4.865252679252052e-07, - "loss": 0.1379, - "step": 221930 + "learning_rate": 3.7985727388649025e-07, + "loss": 0.0902, + "step": 444810 }, { "epoch": 0.99, - "learning_rate": 4.842832159992825e-07, - "loss": 0.1355, - "step": 221940 + "learning_rate": 3.787387306771661e-07, + "loss": 0.0921, + "step": 444820 }, { "epoch": 0.99, - "learning_rate": 4.8204116407336e-07, - "loss": 0.138, - "step": 221950 + "learning_rate": 3.776201874678419e-07, + "loss": 0.0944, + "step": 444830 }, { "epoch": 0.99, - "learning_rate": 4.797991121474374e-07, - "loss": 0.1344, - "step": 221960 + "learning_rate": 3.7650164425851774e-07, + "loss": 0.0909, + "step": 444840 }, { "epoch": 0.99, - "learning_rate": 4.775570602215148e-07, - "loss": 0.1359, - "step": 221970 + "learning_rate": 3.7538310104919355e-07, + "loss": 0.0894, + "step": 444850 }, { "epoch": 0.99, - "learning_rate": 4.7531500829559215e-07, - "loss": 0.1328, - "step": 221980 + "learning_rate": 3.742645578398694e-07, + "loss": 0.0885, + "step": 444860 }, { "epoch": 0.99, - "learning_rate": 4.730729563696696e-07, - "loss": 0.1375, - "step": 221990 + "learning_rate": 3.731460146305452e-07, + "loss": 0.0949, + "step": 444870 }, { "epoch": 0.99, - "learning_rate": 4.7083090444374694e-07, - "loss": 0.1401, - "step": 222000 + "learning_rate": 3.7202747142122103e-07, + "loss": 0.0888, + "step": 444880 }, { "epoch": 0.99, - "learning_rate": 4.6858885251782434e-07, - "loss": 0.1411, - "step": 222010 + "learning_rate": 3.7090892821189684e-07, + "loss": 0.0915, + "step": 444890 }, { "epoch": 0.99, - "learning_rate": 4.663468005919018e-07, - "loss": 0.1379, - "step": 222020 + "learning_rate": 3.697903850025727e-07, + "loss": 0.0931, + "step": 444900 }, { "epoch": 0.99, - "learning_rate": 4.641047486659791e-07, - "loss": 0.1397, - "step": 222030 + "learning_rate": 3.686718417932485e-07, + "loss": 0.0895, + "step": 444910 }, { "epoch": 0.99, - "learning_rate": 4.618626967400565e-07, - "loss": 0.1335, - "step": 222040 + "learning_rate": 3.675532985839243e-07, + "loss": 0.0875, + "step": 444920 }, { "epoch": 0.99, - "learning_rate": 4.5962064481413386e-07, - "loss": 0.134, - "step": 222050 + "learning_rate": 3.6643475537460013e-07, + "loss": 0.0949, + "step": 444930 }, { "epoch": 0.99, - "learning_rate": 4.573785928882113e-07, - "loss": 0.133, - "step": 222060 + "learning_rate": 3.65316212165276e-07, + "loss": 0.0925, + "step": 444940 }, { "epoch": 0.99, - "learning_rate": 4.551365409622887e-07, - "loss": 0.1366, - "step": 222070 + "learning_rate": 3.641976689559518e-07, + "loss": 0.0916, + "step": 444950 }, { "epoch": 0.99, - "learning_rate": 4.5289448903636604e-07, - "loss": 0.131, - "step": 222080 + "learning_rate": 3.630791257466276e-07, + "loss": 0.0888, + "step": 444960 }, { "epoch": 0.99, - "learning_rate": 4.5065243711044354e-07, - "loss": 0.1367, - "step": 222090 + "learning_rate": 3.619605825373035e-07, + "loss": 0.0934, + "step": 444970 }, { "epoch": 0.99, - "learning_rate": 4.484103851845209e-07, - "loss": 0.1286, - "step": 222100 + "learning_rate": 3.6084203932797924e-07, + "loss": 0.0945, + "step": 444980 }, { "epoch": 0.99, - "learning_rate": 4.461683332585983e-07, - "loss": 0.1289, - "step": 222110 + "learning_rate": 3.5972349611865505e-07, + "loss": 0.0955, + "step": 444990 }, { "epoch": 0.99, - "learning_rate": 4.439262813326757e-07, - "loss": 0.1343, - "step": 222120 + "learning_rate": 3.586049529093309e-07, + "loss": 0.0891, + "step": 445000 }, { "epoch": 0.99, - "learning_rate": 4.4168422940675307e-07, - "loss": 0.1301, - "step": 222130 + "learning_rate": 3.574864097000067e-07, + "loss": 0.0926, + "step": 445010 }, { "epoch": 0.99, - "learning_rate": 4.3944217748083046e-07, - "loss": 0.1382, - "step": 222140 + "learning_rate": 3.5636786649068253e-07, + "loss": 0.0901, + "step": 445020 }, { "epoch": 0.99, - "learning_rate": 4.372001255549079e-07, - "loss": 0.1355, - "step": 222150 + "learning_rate": 3.5524932328135834e-07, + "loss": 0.0857, + "step": 445030 }, { "epoch": 0.99, - "learning_rate": 4.3495807362898525e-07, - "loss": 0.1341, - "step": 222160 + "learning_rate": 3.541307800720342e-07, + "loss": 0.0888, + "step": 445040 }, { "epoch": 0.99, - "learning_rate": 4.3271602170306264e-07, - "loss": 0.1364, - "step": 222170 + "learning_rate": 3.5301223686271e-07, + "loss": 0.0857, + "step": 445050 }, { "epoch": 0.99, - "learning_rate": 4.304739697771401e-07, - "loss": 0.1362, - "step": 222180 + "learning_rate": 3.518936936533858e-07, + "loss": 0.0983, + "step": 445060 }, { "epoch": 0.99, - "learning_rate": 4.2823191785121743e-07, - "loss": 0.1424, - "step": 222190 + "learning_rate": 3.5077515044406163e-07, + "loss": 0.0887, + "step": 445070 }, { "epoch": 0.99, - "learning_rate": 4.259898659252948e-07, - "loss": 0.137, - "step": 222200 + "learning_rate": 3.496566072347375e-07, + "loss": 0.0887, + "step": 445080 }, { "epoch": 0.99, - "learning_rate": 4.2374781399937227e-07, - "loss": 0.1382, - "step": 222210 + "learning_rate": 3.485380640254133e-07, + "loss": 0.0934, + "step": 445090 }, { "epoch": 0.99, - "learning_rate": 4.2150576207344967e-07, - "loss": 0.1329, - "step": 222220 + "learning_rate": 3.474195208160891e-07, + "loss": 0.087, + "step": 445100 }, { "epoch": 0.99, - "learning_rate": 4.19263710147527e-07, - "loss": 0.1376, - "step": 222230 + "learning_rate": 3.463009776067649e-07, + "loss": 0.0872, + "step": 445110 }, { "epoch": 0.99, - "learning_rate": 4.1702165822160446e-07, - "loss": 0.1339, - "step": 222240 + "learning_rate": 3.451824343974408e-07, + "loss": 0.0941, + "step": 445120 }, { "epoch": 0.99, - "learning_rate": 4.1477960629568185e-07, - "loss": 0.1388, - "step": 222250 + "learning_rate": 3.440638911881166e-07, + "loss": 0.0908, + "step": 445130 }, { "epoch": 0.99, - "learning_rate": 4.125375543697592e-07, - "loss": 0.138, - "step": 222260 + "learning_rate": 3.429453479787924e-07, + "loss": 0.0945, + "step": 445140 }, { "epoch": 0.99, - "learning_rate": 4.1029550244383664e-07, - "loss": 0.133, - "step": 222270 + "learning_rate": 3.4182680476946827e-07, + "loss": 0.0919, + "step": 445150 }, { "epoch": 0.99, - "learning_rate": 4.0805345051791403e-07, - "loss": 0.1332, - "step": 222280 + "learning_rate": 3.407082615601441e-07, + "loss": 0.0876, + "step": 445160 }, { "epoch": 0.99, - "learning_rate": 4.058113985919914e-07, - "loss": 0.1382, - "step": 222290 + "learning_rate": 3.395897183508199e-07, + "loss": 0.0946, + "step": 445170 }, { "epoch": 0.99, - "learning_rate": 4.0356934666606877e-07, - "loss": 0.1357, - "step": 222300 + "learning_rate": 3.384711751414957e-07, + "loss": 0.089, + "step": 445180 }, { "epoch": 0.99, - "learning_rate": 4.013272947401462e-07, - "loss": 0.1331, - "step": 222310 + "learning_rate": 3.3735263193217157e-07, + "loss": 0.0906, + "step": 445190 }, { "epoch": 0.99, - "learning_rate": 3.990852428142236e-07, - "loss": 0.137, - "step": 222320 + "learning_rate": 3.362340887228474e-07, + "loss": 0.093, + "step": 445200 }, { "epoch": 0.99, - "learning_rate": 3.9684319088830095e-07, - "loss": 0.1326, - "step": 222330 + "learning_rate": 3.351155455135232e-07, + "loss": 0.0964, + "step": 445210 }, { "epoch": 0.99, - "learning_rate": 3.946011389623784e-07, - "loss": 0.1342, - "step": 222340 + "learning_rate": 3.33997002304199e-07, + "loss": 0.0892, + "step": 445220 }, { "epoch": 0.99, - "learning_rate": 3.923590870364558e-07, - "loss": 0.1373, - "step": 222350 + "learning_rate": 3.3287845909487486e-07, + "loss": 0.0861, + "step": 445230 }, { "epoch": 0.99, - "learning_rate": 3.901170351105332e-07, - "loss": 0.1375, - "step": 222360 + "learning_rate": 3.3175991588555067e-07, + "loss": 0.0891, + "step": 445240 }, { "epoch": 0.99, - "learning_rate": 3.878749831846106e-07, - "loss": 0.1396, - "step": 222370 + "learning_rate": 3.306413726762265e-07, + "loss": 0.0923, + "step": 445250 }, { "epoch": 0.99, - "learning_rate": 3.85632931258688e-07, - "loss": 0.1429, - "step": 222380 + "learning_rate": 3.295228294669023e-07, + "loss": 0.0959, + "step": 445260 }, { "epoch": 0.99, - "learning_rate": 3.8339087933276537e-07, - "loss": 0.1333, - "step": 222390 + "learning_rate": 3.2840428625757815e-07, + "loss": 0.089, + "step": 445270 }, { "epoch": 0.99, - "learning_rate": 3.8114882740684276e-07, - "loss": 0.1354, - "step": 222400 + "learning_rate": 3.2728574304825396e-07, + "loss": 0.0897, + "step": 445280 }, { "epoch": 0.99, - "learning_rate": 3.7890677548092016e-07, - "loss": 0.1362, - "step": 222410 + "learning_rate": 3.2616719983892977e-07, + "loss": 0.0922, + "step": 445290 }, { "epoch": 0.99, - "learning_rate": 3.7666472355499755e-07, - "loss": 0.1385, - "step": 222420 + "learning_rate": 3.2504865662960564e-07, + "loss": 0.0916, + "step": 445300 }, { "epoch": 0.99, - "learning_rate": 3.7442267162907495e-07, - "loss": 0.1357, - "step": 222430 + "learning_rate": 3.2393011342028145e-07, + "loss": 0.0936, + "step": 445310 }, { "epoch": 0.99, - "learning_rate": 3.7218061970315234e-07, - "loss": 0.1398, - "step": 222440 + "learning_rate": 3.2281157021095726e-07, + "loss": 0.0906, + "step": 445320 }, { "epoch": 0.99, - "learning_rate": 3.6993856777722974e-07, - "loss": 0.1345, - "step": 222450 + "learning_rate": 3.2169302700163307e-07, + "loss": 0.0894, + "step": 445330 }, { "epoch": 0.99, - "learning_rate": 3.6769651585130713e-07, - "loss": 0.142, - "step": 222460 + "learning_rate": 3.2057448379230893e-07, + "loss": 0.092, + "step": 445340 }, { "epoch": 0.99, - "learning_rate": 3.654544639253845e-07, - "loss": 0.1385, - "step": 222470 + "learning_rate": 3.1945594058298474e-07, + "loss": 0.092, + "step": 445350 }, { "epoch": 0.99, - "learning_rate": 3.632124119994619e-07, - "loss": 0.1349, - "step": 222480 + "learning_rate": 3.1833739737366055e-07, + "loss": 0.0937, + "step": 445360 }, { "epoch": 0.99, - "learning_rate": 3.609703600735393e-07, - "loss": 0.1407, - "step": 222490 + "learning_rate": 3.1721885416433636e-07, + "loss": 0.0919, + "step": 445370 }, { "epoch": 0.99, - "learning_rate": 3.587283081476167e-07, - "loss": 0.1313, - "step": 222500 + "learning_rate": 3.161003109550122e-07, + "loss": 0.09, + "step": 445380 }, { "epoch": 0.99, - "learning_rate": 3.564862562216941e-07, - "loss": 0.1397, - "step": 222510 + "learning_rate": 3.1498176774568803e-07, + "loss": 0.0918, + "step": 445390 }, { "epoch": 0.99, - "learning_rate": 3.542442042957715e-07, - "loss": 0.1348, - "step": 222520 + "learning_rate": 3.1386322453636384e-07, + "loss": 0.0895, + "step": 445400 }, { "epoch": 0.99, - "learning_rate": 3.5200215236984894e-07, - "loss": 0.1371, - "step": 222530 + "learning_rate": 3.127446813270397e-07, + "loss": 0.0925, + "step": 445410 }, { "epoch": 0.99, - "learning_rate": 3.497601004439263e-07, - "loss": 0.1336, - "step": 222540 + "learning_rate": 3.116261381177155e-07, + "loss": 0.0925, + "step": 445420 }, { "epoch": 0.99, - "learning_rate": 3.475180485180037e-07, - "loss": 0.1354, - "step": 222550 + "learning_rate": 3.105075949083913e-07, + "loss": 0.0907, + "step": 445430 }, { "epoch": 0.99, - "learning_rate": 3.452759965920811e-07, - "loss": 0.1325, - "step": 222560 + "learning_rate": 3.0938905169906714e-07, + "loss": 0.0899, + "step": 445440 }, { "epoch": 0.99, - "learning_rate": 3.4303394466615847e-07, - "loss": 0.1399, - "step": 222570 + "learning_rate": 3.08270508489743e-07, + "loss": 0.0885, + "step": 445450 }, { "epoch": 0.99, - "learning_rate": 3.4079189274023586e-07, - "loss": 0.1332, - "step": 222580 + "learning_rate": 3.071519652804188e-07, + "loss": 0.0908, + "step": 445460 }, { "epoch": 0.99, - "learning_rate": 3.3854984081431326e-07, - "loss": 0.1336, - "step": 222590 + "learning_rate": 3.060334220710946e-07, + "loss": 0.089, + "step": 445470 }, { "epoch": 0.99, - "learning_rate": 3.3630778888839065e-07, - "loss": 0.1371, - "step": 222600 + "learning_rate": 3.0491487886177043e-07, + "loss": 0.0851, + "step": 445480 }, { "epoch": 0.99, - "learning_rate": 3.340657369624681e-07, - "loss": 0.1365, - "step": 222610 + "learning_rate": 3.037963356524463e-07, + "loss": 0.0872, + "step": 445490 }, { "epoch": 0.99, - "learning_rate": 3.3182368503654544e-07, - "loss": 0.1367, - "step": 222620 + "learning_rate": 3.026777924431221e-07, + "loss": 0.0903, + "step": 445500 }, { "epoch": 0.99, - "learning_rate": 3.2958163311062283e-07, - "loss": 0.1329, - "step": 222630 + "learning_rate": 3.015592492337979e-07, + "loss": 0.0959, + "step": 445510 }, { "epoch": 0.99, - "learning_rate": 3.273395811847003e-07, - "loss": 0.1363, - "step": 222640 + "learning_rate": 3.004407060244737e-07, + "loss": 0.0914, + "step": 445520 }, { "epoch": 0.99, - "learning_rate": 3.250975292587776e-07, - "loss": 0.1342, - "step": 222650 + "learning_rate": 2.993221628151496e-07, + "loss": 0.0911, + "step": 445530 }, { "epoch": 0.99, - "learning_rate": 3.2285547733285507e-07, - "loss": 0.1369, - "step": 222660 + "learning_rate": 2.982036196058254e-07, + "loss": 0.0883, + "step": 445540 }, { "epoch": 0.99, - "learning_rate": 3.2061342540693246e-07, - "loss": 0.1364, - "step": 222670 + "learning_rate": 2.970850763965012e-07, + "loss": 0.0899, + "step": 445550 }, { "epoch": 0.99, - "learning_rate": 3.183713734810098e-07, - "loss": 0.1413, - "step": 222680 + "learning_rate": 2.9596653318717707e-07, + "loss": 0.0906, + "step": 445560 }, { "epoch": 0.99, - "learning_rate": 3.1612932155508725e-07, - "loss": 0.1441, - "step": 222690 + "learning_rate": 2.948479899778529e-07, + "loss": 0.0888, + "step": 445570 }, { "epoch": 0.99, - "learning_rate": 3.1388726962916464e-07, - "loss": 0.1364, - "step": 222700 + "learning_rate": 2.937294467685287e-07, + "loss": 0.0914, + "step": 445580 }, { "epoch": 0.99, - "learning_rate": 3.1164521770324204e-07, - "loss": 0.1419, - "step": 222710 + "learning_rate": 2.926109035592045e-07, + "loss": 0.0926, + "step": 445590 }, { "epoch": 0.99, - "learning_rate": 3.0940316577731943e-07, - "loss": 0.1378, - "step": 222720 + "learning_rate": 2.9149236034988036e-07, + "loss": 0.0903, + "step": 445600 }, { "epoch": 0.99, - "learning_rate": 3.071611138513968e-07, - "loss": 0.1389, - "step": 222730 + "learning_rate": 2.9037381714055617e-07, + "loss": 0.0894, + "step": 445610 }, { "epoch": 0.99, - "learning_rate": 3.049190619254742e-07, - "loss": 0.1331, - "step": 222740 + "learning_rate": 2.89255273931232e-07, + "loss": 0.089, + "step": 445620 }, { "epoch": 0.99, - "learning_rate": 3.026770099995516e-07, - "loss": 0.1372, - "step": 222750 + "learning_rate": 2.881367307219078e-07, + "loss": 0.0909, + "step": 445630 }, { "epoch": 0.99, - "learning_rate": 3.0043495807362896e-07, - "loss": 0.1371, - "step": 222760 + "learning_rate": 2.8701818751258366e-07, + "loss": 0.0884, + "step": 445640 }, { "epoch": 0.99, - "learning_rate": 2.981929061477064e-07, - "loss": 0.1363, - "step": 222770 + "learning_rate": 2.8589964430325947e-07, + "loss": 0.0912, + "step": 445650 }, { "epoch": 0.99, - "learning_rate": 2.959508542217838e-07, - "loss": 0.1345, - "step": 222780 + "learning_rate": 2.847811010939353e-07, + "loss": 0.0908, + "step": 445660 }, { "epoch": 0.99, - "learning_rate": 2.937088022958612e-07, - "loss": 0.1396, - "step": 222790 + "learning_rate": 2.836625578846111e-07, + "loss": 0.093, + "step": 445670 }, { "epoch": 0.99, - "learning_rate": 2.914667503699386e-07, - "loss": 0.1432, - "step": 222800 + "learning_rate": 2.8254401467528695e-07, + "loss": 0.0922, + "step": 445680 }, { "epoch": 0.99, - "learning_rate": 2.89224698444016e-07, - "loss": 0.1297, - "step": 222810 + "learning_rate": 2.8142547146596276e-07, + "loss": 0.0859, + "step": 445690 }, { "epoch": 0.99, - "learning_rate": 2.869826465180934e-07, - "loss": 0.1337, - "step": 222820 + "learning_rate": 2.8030692825663857e-07, + "loss": 0.0913, + "step": 445700 }, { "epoch": 0.99, - "learning_rate": 2.8474059459217077e-07, - "loss": 0.1365, - "step": 222830 + "learning_rate": 2.7918838504731443e-07, + "loss": 0.0902, + "step": 445710 }, { "epoch": 0.99, - "learning_rate": 2.8249854266624816e-07, - "loss": 0.134, - "step": 222840 + "learning_rate": 2.7806984183799024e-07, + "loss": 0.0916, + "step": 445720 }, { "epoch": 0.99, - "learning_rate": 2.8025649074032556e-07, - "loss": 0.1389, - "step": 222850 + "learning_rate": 2.7695129862866605e-07, + "loss": 0.0925, + "step": 445730 }, { "epoch": 0.99, - "learning_rate": 2.7801443881440295e-07, - "loss": 0.1394, - "step": 222860 + "learning_rate": 2.7583275541934186e-07, + "loss": 0.09, + "step": 445740 }, { "epoch": 0.99, - "learning_rate": 2.7577238688848035e-07, - "loss": 0.1327, - "step": 222870 + "learning_rate": 2.747142122100177e-07, + "loss": 0.0924, + "step": 445750 }, { "epoch": 0.99, - "learning_rate": 2.7353033496255774e-07, - "loss": 0.1369, - "step": 222880 + "learning_rate": 2.7359566900069354e-07, + "loss": 0.0884, + "step": 445760 }, { "epoch": 1.0, - "learning_rate": 2.7128828303663514e-07, - "loss": 0.1322, - "step": 222890 + "learning_rate": 2.7247712579136935e-07, + "loss": 0.092, + "step": 445770 }, { "epoch": 1.0, - "learning_rate": 2.6904623111071253e-07, - "loss": 0.1374, - "step": 222900 + "learning_rate": 2.7135858258204516e-07, + "loss": 0.0915, + "step": 445780 }, { "epoch": 1.0, - "learning_rate": 2.668041791847899e-07, - "loss": 0.1381, - "step": 222910 + "learning_rate": 2.70240039372721e-07, + "loss": 0.0963, + "step": 445790 }, { "epoch": 1.0, - "learning_rate": 2.6456212725886737e-07, - "loss": 0.1368, - "step": 222920 + "learning_rate": 2.6912149616339683e-07, + "loss": 0.0898, + "step": 445800 }, { "epoch": 1.0, - "learning_rate": 2.623200753329447e-07, - "loss": 0.1381, - "step": 222930 + "learning_rate": 2.680029529540726e-07, + "loss": 0.0942, + "step": 445810 }, { "epoch": 1.0, - "learning_rate": 2.600780234070221e-07, - "loss": 0.1359, - "step": 222940 + "learning_rate": 2.6688440974474845e-07, + "loss": 0.0915, + "step": 445820 }, { "epoch": 1.0, - "learning_rate": 2.5783597148109955e-07, - "loss": 0.1386, - "step": 222950 + "learning_rate": 2.6576586653542426e-07, + "loss": 0.0923, + "step": 445830 }, { "epoch": 1.0, - "learning_rate": 2.555939195551769e-07, - "loss": 0.1368, - "step": 222960 + "learning_rate": 2.6464732332610007e-07, + "loss": 0.0887, + "step": 445840 }, { "epoch": 1.0, - "learning_rate": 2.533518676292543e-07, - "loss": 0.1378, - "step": 222970 + "learning_rate": 2.635287801167759e-07, + "loss": 0.087, + "step": 445850 }, { "epoch": 1.0, - "learning_rate": 2.511098157033317e-07, - "loss": 0.1285, - "step": 222980 + "learning_rate": 2.6241023690745174e-07, + "loss": 0.0848, + "step": 445860 }, { "epoch": 1.0, - "learning_rate": 2.488677637774091e-07, - "loss": 0.1316, - "step": 222990 + "learning_rate": 2.6129169369812755e-07, + "loss": 0.0883, + "step": 445870 }, { "epoch": 1.0, - "learning_rate": 2.466257118514865e-07, - "loss": 0.1374, - "step": 223000 + "learning_rate": 2.6017315048880336e-07, + "loss": 0.091, + "step": 445880 }, { "epoch": 1.0, - "learning_rate": 2.4438365992556387e-07, - "loss": 0.1357, - "step": 223010 + "learning_rate": 2.590546072794792e-07, + "loss": 0.0896, + "step": 445890 }, { "epoch": 1.0, - "learning_rate": 2.4214160799964126e-07, - "loss": 0.1325, - "step": 223020 + "learning_rate": 2.5793606407015504e-07, + "loss": 0.0892, + "step": 445900 }, { "epoch": 1.0, - "learning_rate": 2.398995560737187e-07, - "loss": 0.1386, - "step": 223030 + "learning_rate": 2.5681752086083085e-07, + "loss": 0.0922, + "step": 445910 }, { "epoch": 1.0, - "learning_rate": 2.3765750414779608e-07, - "loss": 0.1413, - "step": 223040 + "learning_rate": 2.5569897765150666e-07, + "loss": 0.0935, + "step": 445920 }, { "epoch": 1.0, - "learning_rate": 2.3541545222187347e-07, - "loss": 0.1331, - "step": 223050 + "learning_rate": 2.545804344421825e-07, + "loss": 0.0911, + "step": 445930 }, { "epoch": 1.0, - "learning_rate": 2.331734002959509e-07, - "loss": 0.1335, - "step": 223060 + "learning_rate": 2.5346189123285833e-07, + "loss": 0.0912, + "step": 445940 }, { "epoch": 1.0, - "learning_rate": 2.3093134837002826e-07, - "loss": 0.1399, - "step": 223070 + "learning_rate": 2.5234334802353414e-07, + "loss": 0.0894, + "step": 445950 }, { "epoch": 1.0, - "learning_rate": 2.2868929644410565e-07, - "loss": 0.1432, - "step": 223080 + "learning_rate": 2.5122480481420995e-07, + "loss": 0.0893, + "step": 445960 }, { "epoch": 1.0, - "learning_rate": 2.2644724451818302e-07, - "loss": 0.1359, - "step": 223090 + "learning_rate": 2.501062616048858e-07, + "loss": 0.0897, + "step": 445970 }, { "epoch": 1.0, - "learning_rate": 2.2420519259226044e-07, - "loss": 0.132, - "step": 223100 + "learning_rate": 2.489877183955616e-07, + "loss": 0.0918, + "step": 445980 }, { "epoch": 1.0, - "learning_rate": 2.2196314066633786e-07, - "loss": 0.1388, - "step": 223110 + "learning_rate": 2.4786917518623743e-07, + "loss": 0.0937, + "step": 445990 }, { "epoch": 1.0, - "learning_rate": 2.1972108874041523e-07, - "loss": 0.1335, - "step": 223120 + "learning_rate": 2.4675063197691324e-07, + "loss": 0.0944, + "step": 446000 }, { "epoch": 1.0, - "learning_rate": 2.1747903681449262e-07, - "loss": 0.1365, - "step": 223130 + "learning_rate": 2.456320887675891e-07, + "loss": 0.0923, + "step": 446010 }, { "epoch": 1.0, - "learning_rate": 2.1523698488857005e-07, - "loss": 0.1298, - "step": 223140 + "learning_rate": 2.445135455582649e-07, + "loss": 0.0903, + "step": 446020 }, { "epoch": 1.0, - "learning_rate": 2.129949329626474e-07, - "loss": 0.1376, - "step": 223150 + "learning_rate": 2.433950023489407e-07, + "loss": 0.0934, + "step": 446030 }, { "epoch": 1.0, - "learning_rate": 2.1075288103672483e-07, - "loss": 0.1358, - "step": 223160 + "learning_rate": 2.422764591396166e-07, + "loss": 0.0939, + "step": 446040 }, { "epoch": 1.0, - "learning_rate": 2.0851082911080223e-07, - "loss": 0.1333, - "step": 223170 + "learning_rate": 2.411579159302924e-07, + "loss": 0.0893, + "step": 446050 }, { "epoch": 1.0, - "learning_rate": 2.062687771848796e-07, - "loss": 0.1378, - "step": 223180 + "learning_rate": 2.400393727209682e-07, + "loss": 0.0883, + "step": 446060 }, { "epoch": 1.0, - "learning_rate": 2.0402672525895702e-07, - "loss": 0.1398, - "step": 223190 + "learning_rate": 2.38920829511644e-07, + "loss": 0.0887, + "step": 446070 }, { "epoch": 1.0, - "learning_rate": 2.0178467333303438e-07, - "loss": 0.1362, - "step": 223200 + "learning_rate": 2.3780228630231986e-07, + "loss": 0.0881, + "step": 446080 }, { "epoch": 1.0, - "learning_rate": 1.995426214071118e-07, - "loss": 0.1384, - "step": 223210 + "learning_rate": 2.366837430929957e-07, + "loss": 0.0917, + "step": 446090 }, { "epoch": 1.0, - "learning_rate": 1.973005694811892e-07, - "loss": 0.1376, - "step": 223220 + "learning_rate": 2.355651998836715e-07, + "loss": 0.0911, + "step": 446100 }, { "epoch": 1.0, - "learning_rate": 1.950585175552666e-07, - "loss": 0.1454, - "step": 223230 + "learning_rate": 2.3444665667434734e-07, + "loss": 0.0869, + "step": 446110 }, { "epoch": 1.0, - "learning_rate": 1.92816465629344e-07, - "loss": 0.1316, - "step": 223240 + "learning_rate": 2.3332811346502315e-07, + "loss": 0.0922, + "step": 446120 }, { "epoch": 1.0, - "learning_rate": 1.9057441370342138e-07, - "loss": 0.1364, - "step": 223250 + "learning_rate": 2.3220957025569899e-07, + "loss": 0.0941, + "step": 446130 }, { "epoch": 1.0, - "learning_rate": 1.8833236177749878e-07, - "loss": 0.1382, - "step": 223260 + "learning_rate": 2.310910270463748e-07, + "loss": 0.0895, + "step": 446140 }, { "epoch": 1.0, - "learning_rate": 1.8609030985157617e-07, - "loss": 0.1298, - "step": 223270 + "learning_rate": 2.2997248383705063e-07, + "loss": 0.0916, + "step": 446150 }, { "epoch": 1.0, - "learning_rate": 1.8384825792565356e-07, - "loss": 0.1305, - "step": 223280 + "learning_rate": 2.2885394062772647e-07, + "loss": 0.0874, + "step": 446160 }, { "epoch": 1.0, - "learning_rate": 1.8160620599973096e-07, - "loss": 0.1433, - "step": 223290 + "learning_rate": 2.2773539741840228e-07, + "loss": 0.0934, + "step": 446170 }, { "epoch": 1.0, - "learning_rate": 1.7936415407380835e-07, - "loss": 0.1381, - "step": 223300 + "learning_rate": 2.2661685420907812e-07, + "loss": 0.0906, + "step": 446180 }, { "epoch": 1.0, - "learning_rate": 1.7712210214788575e-07, - "loss": 0.1372, - "step": 223310 + "learning_rate": 2.2549831099975393e-07, + "loss": 0.0866, + "step": 446190 }, { "epoch": 1.0, - "learning_rate": 1.7488005022196314e-07, - "loss": 0.1379, - "step": 223320 + "learning_rate": 2.2437976779042976e-07, + "loss": 0.0896, + "step": 446200 }, { "epoch": 1.0, - "learning_rate": 1.7263799829604056e-07, - "loss": 0.1394, - "step": 223330 + "learning_rate": 2.2326122458110557e-07, + "loss": 0.0876, + "step": 446210 }, { "epoch": 1.0, - "learning_rate": 1.7039594637011793e-07, - "loss": 0.1409, - "step": 223340 + "learning_rate": 2.221426813717814e-07, + "loss": 0.0882, + "step": 446220 }, { "epoch": 1.0, - "learning_rate": 1.6815389444419532e-07, - "loss": 0.1407, - "step": 223350 + "learning_rate": 2.2102413816245722e-07, + "loss": 0.091, + "step": 446230 }, { "epoch": 1.0, - "learning_rate": 1.6591184251827272e-07, - "loss": 0.1362, - "step": 223360 + "learning_rate": 2.1990559495313306e-07, + "loss": 0.0944, + "step": 446240 }, { "epoch": 1.0, - "learning_rate": 1.6366979059235014e-07, - "loss": 0.1316, - "step": 223370 + "learning_rate": 2.1878705174380887e-07, + "loss": 0.0881, + "step": 446250 }, { "epoch": 1.0, - "learning_rate": 1.6142773866642753e-07, - "loss": 0.1373, - "step": 223380 + "learning_rate": 2.176685085344847e-07, + "loss": 0.0891, + "step": 446260 }, { "epoch": 1.0, - "learning_rate": 1.591856867405049e-07, - "loss": 0.1378, - "step": 223390 + "learning_rate": 2.165499653251605e-07, + "loss": 0.0911, + "step": 446270 }, { "epoch": 1.0, - "learning_rate": 1.5694363481458232e-07, - "loss": 0.1321, - "step": 223400 + "learning_rate": 2.1543142211583635e-07, + "loss": 0.0942, + "step": 446280 }, { "epoch": 1.0, - "learning_rate": 1.5470158288865972e-07, - "loss": 0.1408, - "step": 223410 + "learning_rate": 2.1431287890651219e-07, + "loss": 0.0955, + "step": 446290 }, { "epoch": 1.0, - "learning_rate": 1.524595309627371e-07, - "loss": 0.1345, - "step": 223420 + "learning_rate": 2.13194335697188e-07, + "loss": 0.0884, + "step": 446300 }, { "epoch": 1.0, - "learning_rate": 1.5021747903681448e-07, - "loss": 0.1416, - "step": 223430 + "learning_rate": 2.1207579248786383e-07, + "loss": 0.0927, + "step": 446310 }, { "epoch": 1.0, - "learning_rate": 1.479754271108919e-07, - "loss": 0.1344, - "step": 223440 + "learning_rate": 2.1095724927853964e-07, + "loss": 0.0924, + "step": 446320 }, { "epoch": 1.0, - "learning_rate": 1.457333751849693e-07, - "loss": 0.1374, - "step": 223450 + "learning_rate": 2.0983870606921548e-07, + "loss": 0.0902, + "step": 446330 }, { "epoch": 1.0, - "learning_rate": 1.434913232590467e-07, - "loss": 0.138, - "step": 223460 + "learning_rate": 2.087201628598913e-07, + "loss": 0.0894, + "step": 446340 }, { "epoch": 1.0, - "learning_rate": 1.4124927133312408e-07, - "loss": 0.1327, - "step": 223470 + "learning_rate": 2.0760161965056713e-07, + "loss": 0.0936, + "step": 446350 }, { "epoch": 1.0, - "learning_rate": 1.3900721940720148e-07, - "loss": 0.1426, - "step": 223480 + "learning_rate": 2.0648307644124294e-07, + "loss": 0.0901, + "step": 446360 }, { "epoch": 1.0, - "learning_rate": 1.3676516748127887e-07, - "loss": 0.1332, - "step": 223490 + "learning_rate": 2.0536453323191877e-07, + "loss": 0.0892, + "step": 446370 }, { "epoch": 1.0, - "learning_rate": 1.3452311555535627e-07, - "loss": 0.1307, - "step": 223500 + "learning_rate": 2.0424599002259458e-07, + "loss": 0.0946, + "step": 446380 }, { "epoch": 1.0, - "learning_rate": 1.3228106362943369e-07, - "loss": 0.1424, - "step": 223510 + "learning_rate": 2.0312744681327042e-07, + "loss": 0.0898, + "step": 446390 }, { "epoch": 1.0, - "learning_rate": 1.3003901170351105e-07, - "loss": 0.1412, - "step": 223520 + "learning_rate": 2.0200890360394623e-07, + "loss": 0.0932, + "step": 446400 }, { "epoch": 1.0, - "learning_rate": 1.2779695977758845e-07, - "loss": 0.1376, - "step": 223530 + "learning_rate": 2.0089036039462207e-07, + "loss": 0.0896, + "step": 446410 }, { "epoch": 1.0, - "learning_rate": 1.2555490785166584e-07, - "loss": 0.1438, - "step": 223540 + "learning_rate": 1.998836715062303e-07, + "loss": 0.0945, + "step": 446420 }, { "epoch": 1.0, - "learning_rate": 1.2331285592574326e-07, - "loss": 0.1394, - "step": 223550 + "learning_rate": 1.987651282969061e-07, + "loss": 0.0919, + "step": 446430 }, { "epoch": 1.0, - "learning_rate": 1.2107080399982063e-07, - "loss": 0.1354, - "step": 223560 + "learning_rate": 1.9764658508758194e-07, + "loss": 0.0946, + "step": 446440 }, { "epoch": 1.0, - "learning_rate": 1.1882875207389804e-07, - "loss": 0.1355, - "step": 223570 + "learning_rate": 1.9652804187825775e-07, + "loss": 0.0887, + "step": 446450 }, { "epoch": 1.0, - "learning_rate": 1.1658670014797545e-07, - "loss": 0.1333, - "step": 223580 + "learning_rate": 1.9540949866893358e-07, + "loss": 0.0862, + "step": 446460 }, { "epoch": 1.0, - "learning_rate": 1.1434464822205283e-07, - "loss": 0.1331, - "step": 223590 + "learning_rate": 1.9429095545960942e-07, + "loss": 0.0908, + "step": 446470 }, { "epoch": 1.0, - "learning_rate": 1.1210259629613022e-07, - "loss": 0.14, - "step": 223600 + "learning_rate": 1.9317241225028526e-07, + "loss": 0.0957, + "step": 446480 }, { "epoch": 1.0, - "learning_rate": 1.0986054437020762e-07, - "loss": 0.1418, - "step": 223610 + "learning_rate": 1.9205386904096107e-07, + "loss": 0.0893, + "step": 446490 }, { "epoch": 1.0, - "learning_rate": 1.0761849244428502e-07, - "loss": 0.135, - "step": 223620 + "learning_rate": 1.909353258316369e-07, + "loss": 0.0932, + "step": 446500 }, { "epoch": 1.0, - "learning_rate": 1.0537644051836242e-07, - "loss": 0.1392, - "step": 223630 + "learning_rate": 1.898167826223127e-07, + "loss": 0.0995, + "step": 446510 }, { "epoch": 1.0, - "learning_rate": 1.031343885924398e-07, - "loss": 0.1416, - "step": 223640 + "learning_rate": 1.8869823941298852e-07, + "loss": 0.0948, + "step": 446520 }, { "epoch": 1.0, - "learning_rate": 1.0089233666651719e-07, - "loss": 0.1352, - "step": 223650 + "learning_rate": 1.8757969620366436e-07, + "loss": 0.0855, + "step": 446530 }, { "epoch": 1.0, - "learning_rate": 9.887448993318685e-08, - "loss": 0.1394, - "step": 223660 + "learning_rate": 1.8646115299434017e-07, + "loss": 0.0921, + "step": 446540 }, { "epoch": 1.0, - "learning_rate": 9.663243800726425e-08, - "loss": 0.1359, - "step": 223670 + "learning_rate": 1.85342609785016e-07, + "loss": 0.0882, + "step": 446550 }, { "epoch": 1.0, - "learning_rate": 9.439038608134166e-08, - "loss": 0.1388, - "step": 223680 + "learning_rate": 1.8422406657569182e-07, + "loss": 0.0914, + "step": 446560 }, { "epoch": 1.0, - "learning_rate": 9.214833415541904e-08, - "loss": 0.1367, - "step": 223690 + "learning_rate": 1.8310552336636765e-07, + "loss": 0.0892, + "step": 446570 }, { "epoch": 1.0, - "learning_rate": 8.990628222949645e-08, - "loss": 0.1406, - "step": 223700 + "learning_rate": 1.8198698015704346e-07, + "loss": 0.0919, + "step": 446580 }, { "epoch": 1.0, - "learning_rate": 8.766423030357383e-08, - "loss": 0.1442, - "step": 223710 + "learning_rate": 1.808684369477193e-07, + "loss": 0.0906, + "step": 446590 }, { "epoch": 1.0, - "learning_rate": 8.542217837765123e-08, - "loss": 0.1386, - "step": 223720 + "learning_rate": 1.797498937383951e-07, + "loss": 0.0897, + "step": 446600 }, { "epoch": 1.0, - "learning_rate": 8.318012645172863e-08, - "loss": 0.1391, - "step": 223730 + "learning_rate": 1.7863135052907095e-07, + "loss": 0.0919, + "step": 446610 }, { "epoch": 1.0, - "learning_rate": 8.093807452580602e-08, - "loss": 0.1375, - "step": 223740 + "learning_rate": 1.7751280731974676e-07, + "loss": 0.0915, + "step": 446620 }, { "epoch": 1.0, - "learning_rate": 7.869602259988342e-08, - "loss": 0.1374, - "step": 223750 + "learning_rate": 1.763942641104226e-07, + "loss": 0.0988, + "step": 446630 }, { "epoch": 1.0, - "learning_rate": 7.645397067396081e-08, - "loss": 0.1409, - "step": 223760 + "learning_rate": 1.752757209010984e-07, + "loss": 0.0924, + "step": 446640 }, { "epoch": 1.0, - "learning_rate": 7.421191874803822e-08, - "loss": 0.1325, - "step": 223770 + "learning_rate": 1.7415717769177424e-07, + "loss": 0.0888, + "step": 446650 }, { "epoch": 1.0, - "learning_rate": 7.19698668221156e-08, - "loss": 0.1333, - "step": 223780 + "learning_rate": 1.7303863448245005e-07, + "loss": 0.0918, + "step": 446660 }, { "epoch": 1.0, - "learning_rate": 6.972781489619301e-08, - "loss": 0.1353, - "step": 223790 + "learning_rate": 1.7192009127312589e-07, + "loss": 0.0892, + "step": 446670 }, { "epoch": 1.0, - "learning_rate": 6.748576297027039e-08, - "loss": 0.1394, - "step": 223800 + "learning_rate": 1.7080154806380172e-07, + "loss": 0.0899, + "step": 446680 }, { "epoch": 1.0, - "learning_rate": 6.52437110443478e-08, - "loss": 0.136, - "step": 223810 + "learning_rate": 1.6968300485447753e-07, + "loss": 0.0876, + "step": 446690 }, { "epoch": 1.0, - "learning_rate": 6.300165911842518e-08, - "loss": 0.1379, - "step": 223820 + "learning_rate": 1.6856446164515337e-07, + "loss": 0.0933, + "step": 446700 }, { "epoch": 1.0, - "learning_rate": 6.075960719250258e-08, - "loss": 0.1371, - "step": 223830 + "learning_rate": 1.6744591843582918e-07, + "loss": 0.0918, + "step": 446710 }, { "epoch": 1.0, - "learning_rate": 5.851755526657997e-08, - "loss": 0.1419, - "step": 223840 + "learning_rate": 1.6632737522650502e-07, + "loss": 0.0922, + "step": 446720 }, { "epoch": 1.0, - "learning_rate": 5.627550334065737e-08, - "loss": 0.1372, - "step": 223850 + "learning_rate": 1.6520883201718083e-07, + "loss": 0.0937, + "step": 446730 }, { "epoch": 1.0, - "learning_rate": 5.403345141473477e-08, - "loss": 0.136, - "step": 223860 + "learning_rate": 1.6409028880785666e-07, + "loss": 0.093, + "step": 446740 }, { "epoch": 1.0, - "learning_rate": 5.179139948881216e-08, - "loss": 0.1376, - "step": 223870 + "learning_rate": 1.6297174559853247e-07, + "loss": 0.0917, + "step": 446750 }, { "epoch": 1.0, - "learning_rate": 4.954934756288956e-08, - "loss": 0.1394, - "step": 223880 + "learning_rate": 1.618532023892083e-07, + "loss": 0.0968, + "step": 446760 }, { "epoch": 1.0, - "learning_rate": 4.7307295636966956e-08, - "loss": 0.1361, - "step": 223890 + "learning_rate": 1.6073465917988412e-07, + "loss": 0.0871, + "step": 446770 }, { "epoch": 1.0, - "learning_rate": 4.506524371104435e-08, - "loss": 0.1393, - "step": 223900 + "learning_rate": 1.5961611597055996e-07, + "loss": 0.0907, + "step": 446780 }, { "epoch": 1.0, - "learning_rate": 4.2823191785121744e-08, - "loss": 0.1369, - "step": 223910 + "learning_rate": 1.5849757276123577e-07, + "loss": 0.0905, + "step": 446790 }, { "epoch": 1.0, - "learning_rate": 4.058113985919914e-08, - "loss": 0.1375, - "step": 223920 + "learning_rate": 1.573790295519116e-07, + "loss": 0.0879, + "step": 446800 }, { "epoch": 1.0, - "learning_rate": 3.833908793327654e-08, - "loss": 0.137, - "step": 223930 + "learning_rate": 1.5626048634258744e-07, + "loss": 0.0898, + "step": 446810 }, { "epoch": 1.0, - "learning_rate": 3.6097036007353934e-08, - "loss": 0.1411, - "step": 223940 + "learning_rate": 1.5514194313326325e-07, + "loss": 0.0881, + "step": 446820 }, { "epoch": 1.0, - "learning_rate": 3.385498408143133e-08, - "loss": 0.138, - "step": 223950 + "learning_rate": 1.5402339992393909e-07, + "loss": 0.0916, + "step": 446830 }, { "epoch": 1.0, - "learning_rate": 3.161293215550872e-08, - "loss": 0.1336, - "step": 223960 + "learning_rate": 1.529048567146149e-07, + "loss": 0.088, + "step": 446840 }, { "epoch": 1.0, - "learning_rate": 2.9370880229586117e-08, - "loss": 0.1389, - "step": 223970 + "learning_rate": 1.5178631350529073e-07, + "loss": 0.0887, + "step": 446850 }, { "epoch": 1.0, - "learning_rate": 2.7128828303663518e-08, - "loss": 0.1345, - "step": 223980 + "learning_rate": 1.5066777029596654e-07, + "loss": 0.0888, + "step": 446860 }, { "epoch": 1.0, - "learning_rate": 2.4886776377740912e-08, - "loss": 0.1394, - "step": 223990 + "learning_rate": 1.4954922708664238e-07, + "loss": 0.093, + "step": 446870 }, { "epoch": 1.0, - "learning_rate": 2.2644724451818306e-08, - "loss": 0.1415, - "step": 224000 + "learning_rate": 1.484306838773182e-07, + "loss": 0.0902, + "step": 446880 }, { "epoch": 1.0, - "eval_NEIMS_canon_smiles": 0.94685, - "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.12601666666666667, - "eval_NEIMS_daylight_tanimoto_simil": 0.5248372483121932, - "eval_NEIMS_exact_mols": 0.12576666666666667, - "eval_NEIMS_exact_smiles": 0.12238333333333333, - "eval_NEIMS_loss": 0.17296098172664642, - "eval_NEIMS_matched_formulas": 0.65695, - "eval_NEIMS_morgan_tanimoto_simil": 0.4371484987482767, - "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.12631666666666666, - "eval_NEIMS_runtime": 713.0516, - "eval_NEIMS_samples_per_second": 84.145, - "eval_NEIMS_steps_per_second": 1.315, - "step": 224000 + "learning_rate": 1.4731214066799403e-07, + "loss": 0.0928, + "step": 446890 }, { "epoch": 1.0, - "eval_RASSP_canon_smiles": 0.9435669683106822, - "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.26875813937957055, - "eval_RASSP_daylight_tanimoto_simil": 0.6792164058093763, - "eval_RASSP_exact_mols": 0.2678064580759342, - "eval_RASSP_exact_smiles": 0.2604434500951681, - "eval_RASSP_loss": 0.11311110854148865, - "eval_RASSP_matched_formulas": 0.8309012588907069, - "eval_RASSP_morgan_tanimoto_simil": 0.567031216286806, - "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.2680402043610378, - "eval_RASSP_runtime": 816.712, - "eval_RASSP_samples_per_second": 73.336, - "eval_RASSP_steps_per_second": 1.146, - "step": 224000 + "learning_rate": 1.4619359745866984e-07, + "loss": 0.0928, + "step": 446900 }, { "epoch": 1.0, - "eval_NIST_canon_smiles": 0.8784114703481563, - "eval_NIST_daylight_tanimoto_hits_equals_1": 0.0188451573978777, - "eval_NIST_daylight_tanimoto_simil": 0.28303764326500064, - "eval_NIST_exact_mols": 0.018028888810022358, - "eval_NIST_exact_smiles": 0.016680271143130924, - "eval_NIST_loss": 1.8960157632827759, - "eval_NIST_matched_formulas": 0.10586648685097774, - "eval_NIST_morgan_tanimoto_simil": 0.235590992457229, - "eval_NIST_morgan_tanimoto_simil_equals_1": 0.018525747950456046, - "eval_NIST_runtime": 476.0566, - "eval_NIST_samples_per_second": 59.188, - "eval_NIST_steps_per_second": 0.926, - "step": 224000 + "learning_rate": 1.4507505424934567e-07, + "loss": 0.0928, + "step": 446910 + }, + { + "epoch": 1.0, + "learning_rate": 1.4395651104002148e-07, + "loss": 0.09, + "step": 446920 + }, + { + "epoch": 1.0, + "learning_rate": 1.428379678306973e-07, + "loss": 0.0882, + "step": 446930 + }, + { + "epoch": 1.0, + "learning_rate": 1.4171942462137313e-07, + "loss": 0.089, + "step": 446940 + }, + { + "epoch": 1.0, + "learning_rate": 1.4060088141204894e-07, + "loss": 0.0921, + "step": 446950 + }, + { + "epoch": 1.0, + "learning_rate": 1.3948233820272478e-07, + "loss": 0.0916, + "step": 446960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3836379499340059e-07, + "loss": 0.0926, + "step": 446970 + }, + { + "epoch": 1.0, + "learning_rate": 1.3724525178407642e-07, + "loss": 0.0926, + "step": 446980 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612670857475223e-07, + "loss": 0.0883, + "step": 446990 + }, + { + "epoch": 1.0, + "learning_rate": 1.3500816536542807e-07, + "loss": 0.0895, + "step": 447000 + }, + { + "epoch": 1.0, + "learning_rate": 1.3388962215610388e-07, + "loss": 0.0917, + "step": 447010 + }, + { + "epoch": 1.0, + "learning_rate": 1.3277107894677972e-07, + "loss": 0.0944, + "step": 447020 + }, + { + "epoch": 1.0, + "learning_rate": 1.3165253573745553e-07, + "loss": 0.092, + "step": 447030 + }, + { + "epoch": 1.0, + "learning_rate": 1.3053399252813136e-07, + "loss": 0.094, + "step": 447040 + }, + { + "epoch": 1.0, + "learning_rate": 1.294154493188072e-07, + "loss": 0.0918, + "step": 447050 + }, + { + "epoch": 1.0, + "learning_rate": 1.28296906109483e-07, + "loss": 0.0929, + "step": 447060 + }, + { + "epoch": 1.0, + "learning_rate": 1.2717836290015885e-07, + "loss": 0.0934, + "step": 447070 + }, + { + "epoch": 1.0, + "learning_rate": 1.2605981969083466e-07, + "loss": 0.0924, + "step": 447080 + }, + { + "epoch": 1.0, + "learning_rate": 1.249412764815105e-07, + "loss": 0.0878, + "step": 447090 + }, + { + "epoch": 1.0, + "learning_rate": 1.238227332721863e-07, + "loss": 0.0891, + "step": 447100 + }, + { + "epoch": 1.0, + "learning_rate": 1.2270419006286214e-07, + "loss": 0.0907, + "step": 447110 + }, + { + "epoch": 1.0, + "learning_rate": 1.2158564685353795e-07, + "loss": 0.0926, + "step": 447120 + }, + { + "epoch": 1.0, + "learning_rate": 1.2046710364421379e-07, + "loss": 0.0934, + "step": 447130 + }, + { + "epoch": 1.0, + "learning_rate": 1.193485604348896e-07, + "loss": 0.0903, + "step": 447140 + }, + { + "epoch": 1.0, + "learning_rate": 1.1823001722556543e-07, + "loss": 0.0891, + "step": 447150 + }, + { + "epoch": 1.0, + "learning_rate": 1.1711147401624126e-07, + "loss": 0.0913, + "step": 447160 + }, + { + "epoch": 1.0, + "learning_rate": 1.1599293080691708e-07, + "loss": 0.0882, + "step": 447170 + }, + { + "epoch": 1.0, + "learning_rate": 1.148743875975929e-07, + "loss": 0.0904, + "step": 447180 + }, + { + "epoch": 1.0, + "learning_rate": 1.1375584438826873e-07, + "loss": 0.0909, + "step": 447190 + }, + { + "epoch": 1.0, + "learning_rate": 1.1263730117894455e-07, + "loss": 0.0912, + "step": 447200 + }, + { + "epoch": 1.0, + "learning_rate": 1.1151875796962037e-07, + "loss": 0.0915, + "step": 447210 + }, + { + "epoch": 1.0, + "learning_rate": 1.104002147602962e-07, + "loss": 0.0909, + "step": 447220 + }, + { + "epoch": 1.0, + "learning_rate": 1.0928167155097202e-07, + "loss": 0.0935, + "step": 447230 + }, + { + "epoch": 1.0, + "learning_rate": 1.0816312834164784e-07, + "loss": 0.091, + "step": 447240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0704458513232368e-07, + "loss": 0.0902, + "step": 447250 + }, + { + "epoch": 1.0, + "learning_rate": 1.059260419229995e-07, + "loss": 0.0941, + "step": 447260 + }, + { + "epoch": 1.0, + "learning_rate": 1.0480749871367533e-07, + "loss": 0.0943, + "step": 447270 + }, + { + "epoch": 1.0, + "learning_rate": 1.0368895550435115e-07, + "loss": 0.0904, + "step": 447280 + }, + { + "epoch": 1.0, + "learning_rate": 1.0257041229502697e-07, + "loss": 0.0896, + "step": 447290 + }, + { + "epoch": 1.0, + "learning_rate": 1.014518690857028e-07, + "loss": 0.0902, + "step": 447300 + }, + { + "epoch": 1.0, + "learning_rate": 1.0033332587637862e-07, + "loss": 0.086, + "step": 447310 + }, + { + "epoch": 1.0, + "learning_rate": 9.921478266705444e-08, + "loss": 0.0937, + "step": 447320 + }, + { + "epoch": 1.0, + "learning_rate": 9.809623945773027e-08, + "loss": 0.0935, + "step": 447330 + }, + { + "epoch": 1.0, + "learning_rate": 9.697769624840608e-08, + "loss": 0.0951, + "step": 447340 + }, + { + "epoch": 1.0, + "learning_rate": 9.58591530390819e-08, + "loss": 0.088, + "step": 447350 + }, + { + "epoch": 1.0, + "learning_rate": 9.474060982975774e-08, + "loss": 0.0899, + "step": 447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.362206662043356e-08, + "loss": 0.0903, + "step": 447370 + }, + { + "epoch": 1.0, + "learning_rate": 9.250352341110938e-08, + "loss": 0.0915, + "step": 447380 + }, + { + "epoch": 1.0, + "learning_rate": 9.13849802017852e-08, + "loss": 0.0872, + "step": 447390 + }, + { + "epoch": 1.0, + "learning_rate": 9.026643699246103e-08, + "loss": 0.0938, + "step": 447400 + }, + { + "epoch": 1.0, + "learning_rate": 8.914789378313685e-08, + "loss": 0.0908, + "step": 447410 + }, + { + "epoch": 1.0, + "learning_rate": 8.802935057381268e-08, + "loss": 0.0969, + "step": 447420 + }, + { + "epoch": 1.0, + "learning_rate": 8.69108073644885e-08, + "loss": 0.0864, + "step": 447430 + }, + { + "epoch": 1.0, + "learning_rate": 8.579226415516432e-08, + "loss": 0.0899, + "step": 447440 + }, + { + "epoch": 1.0, + "learning_rate": 8.467372094584013e-08, + "loss": 0.0909, + "step": 447450 + }, + { + "epoch": 1.0, + "learning_rate": 8.355517773651596e-08, + "loss": 0.0903, + "step": 447460 + }, + { + "epoch": 1.0, + "learning_rate": 8.243663452719178e-08, + "loss": 0.0928, + "step": 447470 + }, + { + "epoch": 1.0, + "learning_rate": 8.131809131786762e-08, + "loss": 0.0933, + "step": 447480 + }, + { + "epoch": 1.0, + "learning_rate": 8.019954810854344e-08, + "loss": 0.0915, + "step": 447490 + }, + { + "epoch": 1.0, + "learning_rate": 7.908100489921926e-08, + "loss": 0.0938, + "step": 447500 + }, + { + "epoch": 1.0, + "learning_rate": 7.796246168989509e-08, + "loss": 0.0949, + "step": 447510 + }, + { + "epoch": 1.0, + "learning_rate": 7.684391848057091e-08, + "loss": 0.0876, + "step": 447520 + }, + { + "epoch": 1.0, + "learning_rate": 7.572537527124673e-08, + "loss": 0.0846, + "step": 447530 + }, + { + "epoch": 1.0, + "learning_rate": 7.460683206192256e-08, + "loss": 0.0943, + "step": 447540 + }, + { + "epoch": 1.0, + "learning_rate": 7.348828885259838e-08, + "loss": 0.0872, + "step": 447550 + }, + { + "epoch": 1.0, + "learning_rate": 7.23697456432742e-08, + "loss": 0.0923, + "step": 447560 + }, + { + "epoch": 1.0, + "learning_rate": 7.125120243395003e-08, + "loss": 0.0919, + "step": 447570 + }, + { + "epoch": 1.0, + "learning_rate": 7.013265922462585e-08, + "loss": 0.09, + "step": 447580 + }, + { + "epoch": 1.0, + "learning_rate": 6.901411601530167e-08, + "loss": 0.0898, + "step": 447590 + }, + { + "epoch": 1.0, + "learning_rate": 6.78955728059775e-08, + "loss": 0.0916, + "step": 447600 + }, + { + "epoch": 1.0, + "learning_rate": 6.677702959665332e-08, + "loss": 0.0894, + "step": 447610 + }, + { + "epoch": 1.0, + "learning_rate": 6.565848638732916e-08, + "loss": 0.0936, + "step": 447620 + }, + { + "epoch": 1.0, + "learning_rate": 6.453994317800498e-08, + "loss": 0.0879, + "step": 447630 + }, + { + "epoch": 1.0, + "learning_rate": 6.34213999686808e-08, + "loss": 0.0913, + "step": 447640 + }, + { + "epoch": 1.0, + "learning_rate": 6.230285675935661e-08, + "loss": 0.09, + "step": 447650 + }, + { + "epoch": 1.0, + "learning_rate": 6.118431355003244e-08, + "loss": 0.09, + "step": 447660 + }, + { + "epoch": 1.0, + "learning_rate": 6.006577034070826e-08, + "loss": 0.0889, + "step": 447670 + }, + { + "epoch": 1.0, + "learning_rate": 5.894722713138408e-08, + "loss": 0.0879, + "step": 447680 + }, + { + "epoch": 1.0, + "learning_rate": 5.7828683922059906e-08, + "loss": 0.0933, + "step": 447690 + }, + { + "epoch": 1.0, + "learning_rate": 5.6710140712735736e-08, + "loss": 0.0888, + "step": 447700 + }, + { + "epoch": 1.0, + "learning_rate": 5.559159750341156e-08, + "loss": 0.0883, + "step": 447710 + }, + { + "epoch": 1.0, + "learning_rate": 5.447305429408738e-08, + "loss": 0.0907, + "step": 447720 + }, + { + "epoch": 1.0, + "learning_rate": 5.3354511084763206e-08, + "loss": 0.0933, + "step": 447730 + }, + { + "epoch": 1.0, + "learning_rate": 5.223596787543903e-08, + "loss": 0.092, + "step": 447740 + }, + { + "epoch": 1.0, + "learning_rate": 5.111742466611485e-08, + "loss": 0.0949, + "step": 447750 + }, + { + "epoch": 1.0, + "learning_rate": 4.9998881456790676e-08, + "loss": 0.0895, + "step": 447760 + }, + { + "epoch": 1.0, + "learning_rate": 4.8880338247466506e-08, + "loss": 0.0904, + "step": 447770 + }, + { + "epoch": 1.0, + "learning_rate": 4.776179503814233e-08, + "loss": 0.0924, + "step": 447780 + }, + { + "epoch": 1.0, + "learning_rate": 4.664325182881815e-08, + "loss": 0.0921, + "step": 447790 + }, + { + "epoch": 1.0, + "learning_rate": 4.5524708619493976e-08, + "loss": 0.0907, + "step": 447800 + }, + { + "epoch": 1.0, + "learning_rate": 4.440616541016979e-08, + "loss": 0.0903, + "step": 447810 + }, + { + "epoch": 1.0, + "learning_rate": 4.3287622200845616e-08, + "loss": 0.089, + "step": 447820 + }, + { + "epoch": 1.0, + "learning_rate": 4.2169078991521446e-08, + "loss": 0.0862, + "step": 447830 + }, + { + "epoch": 1.0, + "learning_rate": 4.105053578219727e-08, + "loss": 0.0854, + "step": 447840 + }, + { + "epoch": 1.0, + "learning_rate": 3.993199257287309e-08, + "loss": 0.0874, + "step": 447850 + }, + { + "epoch": 1.0, + "learning_rate": 3.8813449363548916e-08, + "loss": 0.0907, + "step": 447860 + }, + { + "epoch": 1.0, + "learning_rate": 3.769490615422474e-08, + "loss": 0.0927, + "step": 447870 + }, + { + "epoch": 1.0, + "learning_rate": 3.657636294490056e-08, + "loss": 0.0911, + "step": 447880 + }, + { + "epoch": 1.0, + "learning_rate": 3.5457819735576386e-08, + "loss": 0.0891, + "step": 447890 + }, + { + "epoch": 1.0, + "learning_rate": 3.4339276526252216e-08, + "loss": 0.0928, + "step": 447900 + }, + { + "epoch": 1.0, + "learning_rate": 3.322073331692803e-08, + "loss": 0.0927, + "step": 447910 + }, + { + "epoch": 1.0, + "learning_rate": 3.2102190107603856e-08, + "loss": 0.091, + "step": 447920 + }, + { + "epoch": 1.0, + "learning_rate": 3.098364689827968e-08, + "loss": 0.0937, + "step": 447930 + }, + { + "epoch": 1.0, + "learning_rate": 2.98651036889555e-08, + "loss": 0.0919, + "step": 447940 + }, + { + "epoch": 1.0, + "learning_rate": 2.874656047963133e-08, + "loss": 0.0942, + "step": 447950 + }, + { + "epoch": 1.0, + "learning_rate": 2.7628017270307152e-08, + "loss": 0.0924, + "step": 447960 + }, + { + "epoch": 1.0, + "learning_rate": 2.650947406098298e-08, + "loss": 0.0905, + "step": 447970 + }, + { + "epoch": 1.0, + "learning_rate": 2.5390930851658802e-08, + "loss": 0.0953, + "step": 447980 + }, + { + "epoch": 1.0, + "learning_rate": 2.4272387642334622e-08, + "loss": 0.0898, + "step": 447990 + }, + { + "epoch": 1.0, + "learning_rate": 2.315384443301045e-08, + "loss": 0.0912, + "step": 448000 + }, + { + "epoch": 1.0, + "eval_NEIMS_canon_smiles": 0.9626333333333333, + "eval_NEIMS_daylight_tanimoto_hits_equals_1": 0.28681666666666666, + "eval_NEIMS_daylight_tanimoto_simil": 0.6443694869767471, + "eval_NEIMS_exact_mols": 0.28645, + "eval_NEIMS_exact_smiles": 0.28103333333333336, + "eval_NEIMS_loss": 0.11634597182273865, + "eval_NEIMS_matched_formulas": 0.7828666666666667, + "eval_NEIMS_morgan_tanimoto_simil": 0.5744133702663434, + "eval_NEIMS_morgan_tanimoto_simil_equals_1": 0.28726666666666667, + "eval_NEIMS_runtime": 718.7511, + "eval_NEIMS_samples_per_second": 83.478, + "eval_NEIMS_steps_per_second": 1.305, + "step": 448000 + }, + { + "epoch": 1.0, + "eval_RASSP_canon_smiles": 0.9617323938958827, + "eval_RASSP_daylight_tanimoto_hits_equals_1": 0.37040438107322937, + "eval_RASSP_daylight_tanimoto_simil": 0.7440783739407923, + "eval_RASSP_exact_mols": 0.36938591511670615, + "eval_RASSP_exact_smiles": 0.361488629912846, + "eval_RASSP_loss": 0.08890151977539062, + "eval_RASSP_matched_formulas": 0.9014759408287976, + "eval_RASSP_morgan_tanimoto_simil": 0.6441875598076626, + "eval_RASSP_morgan_tanimoto_simil_equals_1": 0.3695361805857014, + "eval_RASSP_runtime": 819.8788, + "eval_RASSP_samples_per_second": 73.052, + "eval_RASSP_steps_per_second": 1.142, + "step": 448000 + }, + { + "epoch": 1.0, + "eval_NEIMS_old_canon_smiles": 0.9610666666666666, + "eval_NEIMS_old_daylight_tanimoto_hits_equals_1": 0.2829, + "eval_NEIMS_old_daylight_tanimoto_simil": 0.6426089032002558, + "eval_NEIMS_old_exact_mols": 0.2825, + "eval_NEIMS_old_exact_smiles": 0.27666666666666667, + "eval_NEIMS_old_loss": 0.11637046933174133, + "eval_NEIMS_old_matched_formulas": 0.7817666666666667, + "eval_NEIMS_old_morgan_tanimoto_simil": 0.573222312739321, + "eval_NEIMS_old_morgan_tanimoto_simil_equals_1": 0.2833333333333333, + "eval_NEIMS_old_runtime": 360.8448, + "eval_NEIMS_old_samples_per_second": 83.138, + "eval_NEIMS_old_steps_per_second": 1.3, + "step": 448000 + }, + { + "epoch": 1.0, + "eval_RASSP_old_canon_smiles": 0.9617579337270998, + "eval_RASSP_old_daylight_tanimoto_hits_equals_1": 0.40437814929756066, + "eval_RASSP_old_daylight_tanimoto_simil": 0.7619834965980397, + "eval_RASSP_old_exact_mols": 0.4033103080054727, + "eval_RASSP_old_exact_smiles": 0.39460072746688024, + "eval_RASSP_old_loss": 0.08255165815353394, + "eval_RASSP_old_matched_formulas": 0.9124036440084092, + "eval_RASSP_old_morgan_tanimoto_simil": 0.6678758624661948, + "eval_RASSP_old_morgan_tanimoto_simil_equals_1": 0.4035105282477392, + "eval_RASSP_old_runtime": 408.034, + "eval_RASSP_old_samples_per_second": 73.442, + "eval_RASSP_old_steps_per_second": 1.149, + "step": 448000 + }, + { + "epoch": 1.0, + "eval_NIST_canon_smiles": 0.8645349043546154, + "eval_NIST_daylight_tanimoto_hits_equals_1": 0.03130212584732228, + "eval_NIST_daylight_tanimoto_simil": 0.3074504054866236, + "eval_NIST_exact_mols": 0.029882528303226037, + "eval_NIST_exact_smiles": 0.028462930759129788, + "eval_NIST_loss": 1.8025352954864502, + "eval_NIST_matched_formulas": 0.13802037122475777, + "eval_NIST_morgan_tanimoto_simil": 0.2583338527389404, + "eval_NIST_morgan_tanimoto_simil_equals_1": 0.03105369627710544, + "eval_NIST_runtime": 567.2377, + "eval_NIST_samples_per_second": 49.674, + "eval_NIST_steps_per_second": 0.777, + "step": 448000 } ], - "max_steps": 224010, + "max_steps": 448010, "num_train_epochs": 9223372036854775807, - "total_flos": 1.6768754049282736e+19, + "total_flos": 3.333153267795886e+19, "trial_name": null, "trial_params": null }